summaryrefslogtreecommitdiffstats
path: root/fs
diff options
context:
space:
mode:
Diffstat (limited to 'fs')
-rw-r--r--fs/9p/vfs_inode.c4
-rw-r--r--fs/9p/vfs_inode_dotl.c14
-rw-r--r--fs/Kconfig1
-rw-r--r--fs/Kconfig.binfmt3
-rw-r--r--fs/Makefile1
-rw-r--r--fs/afs/Kconfig1
-rw-r--r--fs/afs/dir.c233
-rw-r--r--fs/afs/dir_silly.c3
-rw-r--r--fs/afs/file.c484
-rw-r--r--fs/afs/fs_operation.c17
-rw-r--r--fs/afs/fsclient.c108
-rw-r--r--fs/afs/inode.c20
-rw-r--r--fs/afs/internal.h62
-rw-r--r--fs/afs/mntpt.c1
-rw-r--r--fs/afs/rxrpc.c150
-rw-r--r--fs/afs/write.c659
-rw-r--r--fs/afs/xattr.c31
-rw-r--r--fs/afs/yfsclient.c82
-rw-r--r--fs/aio.c5
-rw-r--r--fs/autofs/autofs_i.h1
-rw-r--r--fs/autofs/expire.c2
-rw-r--r--fs/autofs/waitq.c72
-rw-r--r--fs/befs/TODO14
-rw-r--r--fs/binfmt_elf.c4
-rw-r--r--fs/binfmt_elf_fdpic.c3
-rw-r--r--fs/binfmt_flat.c18
-rw-r--r--fs/block_dev.c27
-rw-r--r--fs/btrfs/Makefile12
-rw-r--r--fs/btrfs/backref.c33
-rw-r--r--fs/btrfs/block-group.c207
-rw-r--r--fs/btrfs/block-group.h3
-rw-r--r--fs/btrfs/btrfs_inode.h33
-rw-r--r--fs/btrfs/check-integrity.c14
-rw-r--r--fs/btrfs/compression.c15
-rw-r--r--fs/btrfs/ctree.c982
-rw-r--r--fs/btrfs/ctree.h83
-rw-r--r--fs/btrfs/delayed-inode.c35
-rw-r--r--fs/btrfs/delayed-ref.c31
-rw-r--r--fs/btrfs/dev-replace.c3
-rw-r--r--fs/btrfs/disk-io.c181
-rw-r--r--fs/btrfs/extent-tree.c34
-rw-r--r--fs/btrfs/extent_io.c472
-rw-r--r--fs/btrfs/extent_io.h4
-rw-r--r--fs/btrfs/file-item.c1
-rw-r--r--fs/btrfs/file.c118
-rw-r--r--fs/btrfs/free-space-cache.c9
-rw-r--r--fs/btrfs/inode.c184
-rw-r--r--fs/btrfs/ioctl.c269
-rw-r--r--fs/btrfs/lzo.c9
-rw-r--r--fs/btrfs/ordered-data.c19
-rw-r--r--fs/btrfs/ordered-data.h4
-rw-r--r--fs/btrfs/qgroup.c59
-rw-r--r--fs/btrfs/raid56.c73
-rw-r--r--fs/btrfs/reada.c35
-rw-r--r--fs/btrfs/reflink.c65
-rw-r--r--fs/btrfs/relocation.c448
-rw-r--r--fs/btrfs/scrub.c13
-rw-r--r--fs/btrfs/send.c43
-rw-r--r--fs/btrfs/space-info.c4
-rw-r--r--fs/btrfs/subpage.c140
-rw-r--r--fs/btrfs/subpage.h7
-rw-r--r--fs/btrfs/super.c26
-rw-r--r--fs/btrfs/sysfs.c50
-rw-r--r--fs/btrfs/transaction.c59
-rw-r--r--fs/btrfs/transaction.h9
-rw-r--r--fs/btrfs/tree-checker.c5
-rw-r--r--fs/btrfs/tree-log.c32
-rw-r--r--fs/btrfs/tree-mod-log.c929
-rw-r--r--fs/btrfs/tree-mod-log.h53
-rw-r--r--fs/btrfs/volumes.c129
-rw-r--r--fs/btrfs/volumes.h1
-rw-r--r--fs/btrfs/zoned.c60
-rw-r--r--fs/btrfs/zoned.h6
-rw-r--r--fs/buffer.c6
-rw-r--r--fs/cachefiles/Makefile1
-rw-r--r--fs/cachefiles/bind.c6
-rw-r--r--fs/cachefiles/interface.c5
-rw-r--r--fs/cachefiles/internal.h9
-rw-r--r--fs/cachefiles/io.c420
-rw-r--r--fs/cachefiles/rdwr.c7
-rw-r--r--fs/ceph/caps.c8
-rw-r--r--fs/ceph/dir.c2
-rw-r--r--fs/ceph/export.c9
-rw-r--r--fs/ceph/inode.c41
-rw-r--r--fs/cifs/Kconfig3
-rw-r--r--fs/cifs/Makefile5
-rw-r--r--fs/cifs/cifs_debug.c58
-rw-r--r--fs/cifs/cifs_dfs_ref.c14
-rw-r--r--fs/cifs/cifs_fs_sb.h4
-rw-r--r--fs/cifs/cifs_swn.c2
-rw-r--r--fs/cifs/cifs_swn.h27
-rw-r--r--fs/cifs/cifsacl.c12
-rw-r--r--fs/cifs/cifsfs.c50
-rw-r--r--fs/cifs/cifsfs.h2
-rw-r--r--fs/cifs/cifsglob.h38
-rw-r--r--fs/cifs/cifspdu.h7
-rw-r--r--fs/cifs/cifsproto.h32
-rw-r--r--fs/cifs/cifssmb.c52
-rw-r--r--fs/cifs/connect.c49
-rw-r--r--fs/cifs/dfs_cache.c41
-rw-r--r--fs/cifs/dir.c169
-rw-r--r--fs/cifs/file.c82
-rw-r--r--fs/cifs/fs_context.c149
-rw-r--r--fs/cifs/fs_context.h13
-rw-r--r--fs/cifs/inode.c207
-rw-r--r--fs/cifs/ioctl.c13
-rw-r--r--fs/cifs/link.c46
-rw-r--r--fs/cifs/misc.c2
-rw-r--r--fs/cifs/readdir.c19
-rw-r--r--fs/cifs/smb1ops.c6
-rw-r--r--fs/cifs/smb2glob.h1
-rw-r--r--fs/cifs/smb2inode.c10
-rw-r--r--fs/cifs/smb2misc.c5
-rw-r--r--fs/cifs/smb2ops.c222
-rw-r--r--fs/cifs/smb2pdu.c2
-rw-r--r--fs/cifs/smb2pdu.h49
-rw-r--r--fs/cifs/smb2proto.h16
-rw-r--r--fs/cifs/smb2transport.c37
-rw-r--r--fs/cifs/transport.c7
-rw-r--r--fs/cifs/unc.c4
-rw-r--r--fs/cifs/xattr.c40
-rw-r--r--fs/coda/file.c6
-rw-r--r--fs/coredump.c72
-rw-r--r--fs/crypto/Kconfig30
-rw-r--r--fs/d_path.c10
-rw-r--r--fs/dcache.c2
-rw-r--r--fs/debugfs/file.c94
-rw-r--r--fs/debugfs/inode.c2
-rw-r--r--fs/direct-io.c5
-rw-r--r--fs/dlm/config.c86
-rw-r--r--fs/dlm/config.h1
-rw-r--r--fs/dlm/debug_fs.c1
-rw-r--r--fs/dlm/lock.c2
-rw-r--r--fs/dlm/lockspace.c20
-rw-r--r--fs/dlm/lowcomms.c194
-rw-r--r--fs/dlm/lowcomms.h5
-rw-r--r--fs/dlm/midcomms.c33
-rw-r--r--fs/dlm/rcom.c2
-rw-r--r--fs/ecryptfs/ecryptfs_kernel.h17
-rw-r--r--fs/ecryptfs/inode.c185
-rw-r--r--fs/efivarfs/file.c77
-rw-r--r--fs/efivarfs/inode.c44
-rw-r--r--fs/erofs/Kconfig14
-rw-r--r--fs/erofs/Makefile2
-rw-r--r--fs/erofs/data.c19
-rw-r--r--fs/erofs/decompressor.c272
-rw-r--r--fs/erofs/erofs_fs.h54
-rw-r--r--fs/erofs/inode.c7
-rw-r--r--fs/erofs/internal.h86
-rw-r--r--fs/erofs/pcpubuf.c148
-rw-r--r--fs/erofs/super.c148
-rw-r--r--fs/erofs/utils.c12
-rw-r--r--fs/erofs/zdata.c254
-rw-r--r--fs/erofs/zdata.h14
-rw-r--r--fs/erofs/zmap.c164
-rw-r--r--fs/eventpoll.c52
-rw-r--r--fs/exfat/balloc.c95
-rw-r--r--fs/exfat/dir.c26
-rw-r--r--fs/exfat/exfat_fs.h11
-rw-r--r--fs/exfat/fatent.c41
-rw-r--r--fs/exfat/file.c53
-rw-r--r--fs/exfat/inode.c3
-rw-r--r--fs/exfat/namei.c11
-rw-r--r--fs/exfat/super.c1
-rw-r--r--fs/ext2/dir.c94
-rw-r--r--fs/ext2/ext2.h19
-rw-r--r--fs/ext2/file.c2
-rw-r--r--fs/ext2/ioctl.c88
-rw-r--r--fs/ext2/namei.c39
-rw-r--r--fs/ext2/super.c7
-rw-r--r--fs/ext4/balloc.c40
-rw-r--r--fs/ext4/dir.c41
-rw-r--r--fs/ext4/ext4.h122
-rw-r--r--fs/ext4/extents.c2
-rw-r--r--fs/ext4/fast_commit.c17
-rw-r--r--fs/ext4/file.c27
-rw-r--r--fs/ext4/fsmap.c4
-rw-r--r--fs/ext4/hash.c25
-rw-r--r--fs/ext4/ialloc.c53
-rw-r--r--fs/ext4/indirect.c2
-rw-r--r--fs/ext4/inline.c27
-rw-r--r--fs/ext4/inode.c26
-rw-r--r--fs/ext4/ioctl.c214
-rw-r--r--fs/ext4/mballoc.c603
-rw-r--r--fs/ext4/mballoc.h24
-rw-r--r--fs/ext4/migrate.c6
-rw-r--r--fs/ext4/mmp.c2
-rw-r--r--fs/ext4/namei.c300
-rw-r--r--fs/ext4/super.c128
-rw-r--r--fs/ext4/sysfs.c15
-rw-r--r--fs/ext4/verity.c101
-rw-r--r--fs/ext4/xattr.c8
-rw-r--r--fs/f2fs/dir.c4
-rw-r--r--fs/f2fs/f2fs.h3
-rw-r--r--fs/f2fs/file.c218
-rw-r--r--fs/f2fs/namei.c5
-rw-r--r--fs/f2fs/verity.c2
-rw-r--r--fs/file.c60
-rw-r--r--fs/fs_parser.c2
-rw-r--r--fs/fscache/Kconfig1
-rw-r--r--fs/fscache/Makefile1
-rw-r--r--fs/fscache/internal.h4
-rw-r--r--fs/fscache/io.c116
-rw-r--r--fs/fscache/page.c2
-rw-r--r--fs/fscache/stats.c1
-rw-r--r--fs/fuse/Makefile2
-rw-r--r--fs/fuse/acl.c7
-rw-r--r--fs/fuse/cuse.c12
-rw-r--r--fs/fuse/dev.c27
-rw-r--r--fs/fuse/dir.c12
-rw-r--r--fs/fuse/file.c506
-rw-r--r--fs/fuse/fuse_i.h54
-rw-r--r--fs/fuse/inode.c12
-rw-r--r--fs/fuse/ioctl.c490
-rw-r--r--fs/fuse/readdir.c2
-rw-r--r--fs/fuse/virtio_fs.c37
-rw-r--r--fs/fuse/xattr.c9
-rw-r--r--fs/gfs2/aops.c5
-rw-r--r--fs/gfs2/bmap.c153
-rw-r--r--fs/gfs2/bmap.h13
-rw-r--r--fs/gfs2/dir.c52
-rw-r--r--fs/gfs2/file.c75
-rw-r--r--fs/gfs2/glock.c15
-rw-r--r--fs/gfs2/glops.c38
-rw-r--r--fs/gfs2/incore.h3
-rw-r--r--fs/gfs2/inode.c36
-rw-r--r--fs/gfs2/inode.h4
-rw-r--r--fs/gfs2/lock_dlm.c37
-rw-r--r--fs/gfs2/log.c25
-rw-r--r--fs/gfs2/lops.c16
-rw-r--r--fs/gfs2/meta_io.c20
-rw-r--r--fs/gfs2/meta_io.h6
-rw-r--r--fs/gfs2/ops_fstype.c8
-rw-r--r--fs/gfs2/quota.c6
-rw-r--r--fs/gfs2/recovery.c8
-rw-r--r--fs/gfs2/rgrp.c8
-rw-r--r--fs/gfs2/super.c26
-rw-r--r--fs/gfs2/sys.c67
-rw-r--r--fs/gfs2/util.c19
-rw-r--r--fs/gfs2/xattr.c29
-rw-r--r--fs/hfsplus/dir.c2
-rw-r--r--fs/hfsplus/hfsplus_fs.h14
-rw-r--r--fs/hfsplus/inode.c54
-rw-r--r--fs/hfsplus/ioctl.c84
-rw-r--r--fs/hostfs/hostfs_kern.c10
-rw-r--r--fs/inode.c91
-rw-r--r--fs/io-wq.c368
-rw-r--r--fs/io-wq.h11
-rw-r--r--fs/io_uring.c2885
-rw-r--r--fs/ioctl.c325
-rw-r--r--fs/iomap/buffered-io.c3
-rw-r--r--fs/iomap/direct-io.c24
-rw-r--r--fs/iomap/swapfile.c48
-rw-r--r--fs/jbd2/recovery.c5
-rw-r--r--fs/jbd2/transaction.c15
-rw-r--r--fs/jffs2/TODO37
-rw-r--r--fs/jfs/file.c6
-rw-r--r--fs/jfs/ioctl.c111
-rw-r--r--fs/jfs/jfs_dinode.h7
-rw-r--r--fs/jfs/jfs_inode.h4
-rw-r--r--fs/jfs/namei.c6
-rw-r--r--fs/libfs.c1
-rw-r--r--fs/locks.c69
-rw-r--r--fs/namei.c39
-rw-r--r--fs/namespace.c14
-rw-r--r--fs/netfs/Kconfig23
-rw-r--r--fs/netfs/Makefile5
-rw-r--r--fs/netfs/internal.h97
-rw-r--r--fs/netfs/read_helper.c1185
-rw-r--r--fs/netfs/stats.c59
-rw-r--r--fs/nfs/fs_context.c3
-rw-r--r--fs/nfs/inode.c6
-rw-r--r--fs/nfs/internal.h1
-rw-r--r--fs/nfs/super.c6
-rw-r--r--fs/nfs_common/nfsacl.c71
-rw-r--r--fs/nfsd/Kconfig7
-rw-r--r--fs/nfsd/filecache.c2
-rw-r--r--fs/nfsd/netns.h6
-rw-r--r--fs/nfsd/nfs2acl.c87
-rw-r--r--fs/nfsd/nfs3acl.c39
-rw-r--r--fs/nfsd/nfs3proc.c97
-rw-r--r--fs/nfsd/nfs3xdr.c1043
-rw-r--r--fs/nfsd/nfs4callback.c1
-rw-r--r--fs/nfsd/nfs4proc.c42
-rw-r--r--fs/nfsd/nfs4recover.c8
-rw-r--r--fs/nfsd/nfs4state.c135
-rw-r--r--fs/nfsd/nfs4xdr.c110
-rw-r--r--fs/nfsd/nfsctl.c28
-rw-r--r--fs/nfsd/nfsd.h7
-rw-r--r--fs/nfsd/nfsfh.c2
-rw-r--r--fs/nfsd/nfsfh.h2
-rw-r--r--fs/nfsd/nfsproc.c55
-rw-r--r--fs/nfsd/nfssvc.c42
-rw-r--r--fs/nfsd/nfsxdr.c413
-rw-r--r--fs/nfsd/state.h4
-rw-r--r--fs/nfsd/trace.h24
-rw-r--r--fs/nfsd/vfs.c9
-rw-r--r--fs/nfsd/vfs.h2
-rw-r--r--fs/nfsd/xdr.h23
-rw-r--r--fs/nfsd/xdr3.h37
-rw-r--r--fs/nfsd/xdr4.h2
-rw-r--r--fs/nilfs2/file.c2
-rw-r--r--fs/nilfs2/ioctl.c61
-rw-r--r--fs/nilfs2/namei.c5
-rw-r--r--fs/nilfs2/nilfs.h3
-rw-r--r--fs/notify/fanotify/fanotify.c166
-rw-r--r--fs/notify/fanotify/fanotify.h46
-rw-r--r--fs/notify/fanotify/fanotify_user.c219
-rw-r--r--fs/notify/fdinfo.c3
-rw-r--r--fs/notify/group.c1
-rw-r--r--fs/notify/inotify/inotify_fsnotify.c9
-rw-r--r--fs/notify/inotify/inotify_user.c7
-rw-r--r--fs/notify/mark.c4
-rw-r--r--fs/notify/notification.c64
-rw-r--r--fs/ocfs2/aops.c11
-rw-r--r--fs/ocfs2/blockcheck.c2
-rw-r--r--fs/ocfs2/dlm/dlmrecovery.c7
-rw-r--r--fs/ocfs2/dlmglue.c12
-rw-r--r--fs/ocfs2/file.c10
-rw-r--r--fs/ocfs2/ioctl.c59
-rw-r--r--fs/ocfs2/ioctl.h3
-rw-r--r--fs/ocfs2/namei.c3
-rw-r--r--fs/ocfs2/ocfs2_ioctl.h8
-rw-r--r--fs/ocfs2/stack_o2cb.c36
-rw-r--r--fs/ocfs2/stackglue.c2
-rw-r--r--fs/openpromfs/inode.c67
-rw-r--r--fs/orangefs/file.c113
-rw-r--r--fs/orangefs/inode.c172
-rw-r--r--fs/orangefs/orangefs-mod.c2
-rw-r--r--fs/orangefs/orangefs-utils.c2
-rw-r--r--fs/overlayfs/copy_up.c3
-rw-r--r--fs/overlayfs/dir.c2
-rw-r--r--fs/overlayfs/file.c142
-rw-r--r--fs/overlayfs/inode.c95
-rw-r--r--fs/overlayfs/namei.c5
-rw-r--r--fs/overlayfs/overlayfs.h42
-rw-r--r--fs/overlayfs/readdir.c16
-rw-r--r--fs/overlayfs/super.c66
-rw-r--r--fs/overlayfs/util.c33
-rw-r--r--fs/proc/array.c2
-rw-r--r--fs/proc/proc_sysctl.c13
-rw-r--r--fs/pstore/platform.c5
-rw-r--r--fs/pstore/ram.c7
-rw-r--r--fs/pstore/ram_core.c18
-rw-r--r--fs/quota/quota.c50
-rw-r--r--fs/readdir.c6
-rw-r--r--fs/reiserfs/file.c2
-rw-r--r--fs/reiserfs/ioctl.c121
-rw-r--r--fs/reiserfs/journal.c6
-rw-r--r--fs/reiserfs/namei.c2
-rw-r--r--fs/reiserfs/reiserfs.h7
-rw-r--r--fs/reiserfs/super.c2
-rw-r--r--fs/reiserfs/xattr.h2
-rw-r--r--fs/select.c10
-rw-r--r--fs/seq_file.c18
-rw-r--r--fs/signalfd.c4
-rw-r--r--fs/squashfs/export.c8
-rw-r--r--fs/squashfs/id.c6
-rw-r--r--fs/squashfs/squashfs_fs.h1
-rw-r--r--fs/squashfs/xattr_id.c6
-rw-r--r--fs/stat.c8
-rw-r--r--fs/super.c1
-rw-r--r--fs/tracefs/inode.c2
-rw-r--r--fs/ubifs/dir.c2
-rw-r--r--fs/ubifs/file.c2
-rw-r--r--fs/ubifs/gc.c7
-rw-r--r--fs/ubifs/ioctl.c78
-rw-r--r--fs/ubifs/replay.c4
-rw-r--r--fs/ubifs/ubifs.h3
-rw-r--r--fs/udf/namei.c3
-rw-r--r--fs/ufs/super.c3
-rw-r--r--fs/vboxsf/dir.c4
-rw-r--r--fs/vboxsf/super.c4
-rw-r--r--fs/vboxsf/utils.c68
-rw-r--r--fs/vboxsf/vfsmod.h4
-rw-r--r--fs/verity/Kconfig8
-rw-r--r--fs/xattr.c14
-rw-r--r--fs/xfs/libxfs/xfs_ag.c115
-rw-r--r--fs/xfs/libxfs/xfs_ag.h2
-rw-r--r--fs/xfs/libxfs/xfs_ag_resv.c6
-rw-r--r--fs/xfs/libxfs/xfs_alloc.c8
-rw-r--r--fs/xfs/libxfs/xfs_attr.c54
-rw-r--r--fs/xfs/libxfs/xfs_attr.h1
-rw-r--r--fs/xfs/libxfs/xfs_attr_leaf.c35
-rw-r--r--fs/xfs/libxfs/xfs_bmap.c229
-rw-r--r--fs/xfs/libxfs/xfs_bmap.h2
-rw-r--r--fs/xfs/libxfs/xfs_bmap_btree.c6
-rw-r--r--fs/xfs/libxfs/xfs_btree_staging.c1
-rw-r--r--fs/xfs/libxfs/xfs_da_btree.c4
-rw-r--r--fs/xfs/libxfs/xfs_dir2.c14
-rw-r--r--fs/xfs/libxfs/xfs_dir2_block.c12
-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.c4
-rw-r--r--fs/xfs/libxfs/xfs_dir2_priv.h3
-rw-r--r--fs/xfs/libxfs/xfs_dir2_sf.c58
-rw-r--r--fs/xfs/libxfs/xfs_errortag.h4
-rw-r--r--fs/xfs/libxfs/xfs_format.h5
-rw-r--r--fs/xfs/libxfs/xfs_fs.h6
-rw-r--r--fs/xfs/libxfs/xfs_ialloc.c4
-rw-r--r--fs/xfs/libxfs/xfs_iext_tree.c2
-rw-r--r--fs/xfs/libxfs/xfs_inode_buf.c81
-rw-r--r--fs/xfs/libxfs/xfs_inode_buf.h33
-rw-r--r--fs/xfs/libxfs/xfs_inode_fork.c48
-rw-r--r--fs/xfs/libxfs/xfs_inode_fork.h20
-rw-r--r--fs/xfs/libxfs/xfs_rtbitmap.c4
-rw-r--r--fs/xfs/libxfs/xfs_shared.h4
-rw-r--r--fs/xfs/libxfs/xfs_trans_inode.c7
-rw-r--r--fs/xfs/libxfs/xfs_types.c18
-rw-r--r--fs/xfs/scrub/agheader.c33
-rw-r--r--fs/xfs/scrub/alloc.c5
-rw-r--r--fs/xfs/scrub/attr.c5
-rw-r--r--fs/xfs/scrub/bitmap.c4
-rw-r--r--fs/xfs/scrub/bmap.c20
-rw-r--r--fs/xfs/scrub/btree.c30
-rw-r--r--fs/xfs/scrub/common.c38
-rw-r--r--fs/xfs/scrub/common.h58
-rw-r--r--fs/xfs/scrub/dir.c20
-rw-r--r--fs/xfs/scrub/fscounters.c3
-rw-r--r--fs/xfs/scrub/health.c3
-rw-r--r--fs/xfs/scrub/ialloc.c8
-rw-r--r--fs/xfs/scrub/inode.c5
-rw-r--r--fs/xfs/scrub/parent.c7
-rw-r--r--fs/xfs/scrub/quota.c11
-rw-r--r--fs/xfs/scrub/refcount.c5
-rw-r--r--fs/xfs/scrub/repair.c11
-rw-r--r--fs/xfs/scrub/repair.h6
-rw-r--r--fs/xfs/scrub/rmap.c5
-rw-r--r--fs/xfs/scrub/rtbitmap.c7
-rw-r--r--fs/xfs/scrub/scrub.c42
-rw-r--r--fs/xfs/scrub/scrub.h14
-rw-r--r--fs/xfs/scrub/symlink.c9
-rw-r--r--fs/xfs/scrub/xfs_scrub.h4
-rw-r--r--fs/xfs/xfs_aops.c138
-rw-r--r--fs/xfs/xfs_attr_list.c2
-rw-r--r--fs/xfs/xfs_bmap_item.c4
-rw-r--r--fs/xfs/xfs_bmap_util.c209
-rw-r--r--fs/xfs/xfs_buf.c6
-rw-r--r--fs/xfs/xfs_buf_item.c141
-rw-r--r--fs/xfs/xfs_dir2_readdir.c12
-rw-r--r--fs/xfs/xfs_dquot.c10
-rw-r--r--fs/xfs/xfs_error.c5
-rw-r--r--fs/xfs/xfs_extent_busy.c4
-rw-r--r--fs/xfs/xfs_extent_busy.h3
-rw-r--r--fs/xfs/xfs_extfree_item.c4
-rw-r--r--fs/xfs/xfs_file.c12
-rw-r--r--fs/xfs/xfs_filestream.h2
-rw-r--r--fs/xfs/xfs_fsmap.c14
-rw-r--r--fs/xfs/xfs_fsops.c199
-rw-r--r--fs/xfs/xfs_icache.c35
-rw-r--r--fs/xfs/xfs_inode.c278
-rw-r--r--fs/xfs/xfs_inode.h42
-rw-r--r--fs/xfs/xfs_inode_item.c56
-rw-r--r--fs/xfs/xfs_ioctl.c329
-rw-r--r--fs/xfs/xfs_ioctl.h11
-rw-r--r--fs/xfs/xfs_ioctl32.c2
-rw-r--r--fs/xfs/xfs_ioctl32.h2
-rw-r--r--fs/xfs/xfs_iomap.c27
-rw-r--r--fs/xfs/xfs_iops.c72
-rw-r--r--fs/xfs/xfs_itable.c25
-rw-r--r--fs/xfs/xfs_linux.h2
-rw-r--r--fs/xfs/xfs_log_recover.c13
-rw-r--r--fs/xfs/xfs_mount.c104
-rw-r--r--fs/xfs/xfs_mount.h2
-rw-r--r--fs/xfs/xfs_pnfs.c2
-rw-r--r--fs/xfs/xfs_qm.c22
-rw-r--r--fs/xfs/xfs_qm_bhv.c2
-rw-r--r--fs/xfs/xfs_qm_syscalls.c2
-rw-r--r--fs/xfs/xfs_quotaops.c2
-rw-r--r--fs/xfs/xfs_refcount_item.c4
-rw-r--r--fs/xfs/xfs_reflink.c22
-rw-r--r--fs/xfs/xfs_rmap_item.c4
-rw-r--r--fs/xfs/xfs_rtalloc.c16
-rw-r--r--fs/xfs/xfs_super.c132
-rw-r--r--fs/xfs/xfs_super.h1
-rw-r--r--fs/xfs/xfs_symlink.c31
-rw-r--r--fs/xfs/xfs_trace.h16
-rw-r--r--fs/xfs/xfs_trans.c14
-rw-r--r--fs/xfs/xfs_xattr.c2
-rw-r--r--fs/zonefs/super.c106
480 files changed, 17619 insertions, 11310 deletions
diff --git a/fs/9p/vfs_inode.c b/fs/9p/vfs_inode.c
index 8d97f0b45e9c..795706520b5e 100644
--- a/fs/9p/vfs_inode.c
+++ b/fs/9p/vfs_inode.c
@@ -399,7 +399,7 @@ static int v9fs_test_inode(struct inode *inode, void *data)
umode = p9mode2unixmode(v9ses, st, &rdev);
/* don't match inode of different type */
- if ((inode->i_mode & S_IFMT) != (umode & S_IFMT))
+ if (inode_wrong_type(inode, umode))
return 0;
/* compare qid details */
@@ -1390,7 +1390,7 @@ int v9fs_refresh_inode(struct p9_fid *fid, struct inode *inode)
* Don't update inode if the file type is different
*/
umode = p9mode2unixmode(v9ses, st, &rdev);
- if ((inode->i_mode & S_IFMT) != (umode & S_IFMT))
+ if (inode_wrong_type(inode, umode))
goto out;
/*
diff --git a/fs/9p/vfs_inode_dotl.c b/fs/9p/vfs_inode_dotl.c
index 1dc7af046615..e1c0240b51c0 100644
--- a/fs/9p/vfs_inode_dotl.c
+++ b/fs/9p/vfs_inode_dotl.c
@@ -59,7 +59,7 @@ static int v9fs_test_inode_dotl(struct inode *inode, void *data)
struct p9_stat_dotl *st = (struct p9_stat_dotl *)data;
/* don't match inode of different type */
- if ((inode->i_mode & S_IFMT) != (st->st_mode & S_IFMT))
+ if (inode_wrong_type(inode, st->st_mode))
return 0;
if (inode->i_generation != st->st_gen)
@@ -663,14 +663,10 @@ v9fs_stat2inode_dotl(struct p9_stat_dotl *stat, struct inode *inode,
if (stat->st_result_mask & P9_STATS_NLINK)
set_nlink(inode, stat->st_nlink);
if (stat->st_result_mask & P9_STATS_MODE) {
- inode->i_mode = stat->st_mode;
- if ((S_ISBLK(inode->i_mode)) ||
- (S_ISCHR(inode->i_mode)))
- init_special_inode(inode, inode->i_mode,
- inode->i_rdev);
+ mode = stat->st_mode & S_IALLUGO;
+ mode |= inode->i_mode & ~S_IALLUGO;
+ inode->i_mode = mode;
}
- if (stat->st_result_mask & P9_STATS_RDEV)
- inode->i_rdev = new_decode_dev(stat->st_rdev);
if (!(flags & V9FS_STAT2INODE_KEEP_ISIZE) &&
stat->st_result_mask & P9_STATS_SIZE)
v9fs_i_size_write(inode, stat->st_size);
@@ -959,7 +955,7 @@ int v9fs_refresh_inode_dotl(struct p9_fid *fid, struct inode *inode)
/*
* Don't update inode if the file type is different
*/
- if ((inode->i_mode & S_IFMT) != (st->st_mode & S_IFMT))
+ if (inode_wrong_type(inode, st->st_mode))
goto out;
/*
diff --git a/fs/Kconfig b/fs/Kconfig
index a55bda4233bb..97e7b77c9309 100644
--- a/fs/Kconfig
+++ b/fs/Kconfig
@@ -125,6 +125,7 @@ source "fs/overlayfs/Kconfig"
menu "Caches"
+source "fs/netfs/Kconfig"
source "fs/fscache/Kconfig"
source "fs/cachefiles/Kconfig"
diff --git a/fs/Kconfig.binfmt b/fs/Kconfig.binfmt
index c6f1c8c1934e..06fb7a93a1bd 100644
--- a/fs/Kconfig.binfmt
+++ b/fs/Kconfig.binfmt
@@ -112,6 +112,9 @@ config BINFMT_FLAT_ARGVP_ENVP_ON_STACK
config BINFMT_FLAT_OLD_ALWAYS_RAM
bool
+config BINFMT_FLAT_NO_DATA_START_OFFSET
+ bool
+
config BINFMT_FLAT_OLD
bool "Enable support for very old legacy flat binaries"
depends on BINFMT_FLAT
diff --git a/fs/Makefile b/fs/Makefile
index 3215fe205256..9c708e1fbe8f 100644
--- a/fs/Makefile
+++ b/fs/Makefile
@@ -67,6 +67,7 @@ obj-y += devpts/
obj-$(CONFIG_DLM) += dlm/
# Do not add any filesystems before this line
+obj-$(CONFIG_NETFS_SUPPORT) += netfs/
obj-$(CONFIG_FSCACHE) += fscache/
obj-$(CONFIG_REISERFS_FS) += reiserfs/
obj-$(CONFIG_EXT4_FS) += ext4/
diff --git a/fs/afs/Kconfig b/fs/afs/Kconfig
index 1ad211d72b3b..fc8ba9142f2f 100644
--- a/fs/afs/Kconfig
+++ b/fs/afs/Kconfig
@@ -4,6 +4,7 @@ config AFS_FS
depends on INET
select AF_RXRPC
select DNS_RESOLVER
+ select NETFS_SUPPORT
help
If you say Y here, you will get an experimental Andrew File System
driver. It currently only supports unsecured read-only AFS access.
diff --git a/fs/afs/dir.c b/fs/afs/dir.c
index 714fcca9af99..9fbe5a5ec9bd 100644
--- a/fs/afs/dir.c
+++ b/fs/afs/dir.c
@@ -70,7 +70,6 @@ const struct inode_operations afs_dir_inode_operations = {
.permission = afs_permission,
.getattr = afs_getattr,
.setattr = afs_setattr,
- .listxattr = afs_listxattr,
};
const struct address_space_operations afs_dir_aops = {
@@ -104,6 +103,35 @@ struct afs_lookup_cookie {
};
/*
+ * Drop the refs that we're holding on the pages we were reading into. We've
+ * got refs on the first nr_pages pages.
+ */
+static void afs_dir_read_cleanup(struct afs_read *req)
+{
+ struct address_space *mapping = req->vnode->vfs_inode.i_mapping;
+ struct page *page;
+ pgoff_t last = req->nr_pages - 1;
+
+ XA_STATE(xas, &mapping->i_pages, 0);
+
+ if (unlikely(!req->nr_pages))
+ return;
+
+ rcu_read_lock();
+ xas_for_each(&xas, page, last) {
+ if (xas_retry(&xas, page))
+ continue;
+ BUG_ON(xa_is_value(page));
+ BUG_ON(PageCompound(page));
+ ASSERTCMP(page->mapping, ==, mapping);
+
+ put_page(page);
+ }
+
+ rcu_read_unlock();
+}
+
+/*
* check that a directory page is valid
*/
static bool afs_dir_check_page(struct afs_vnode *dvnode, struct page *page,
@@ -128,7 +156,7 @@ static bool afs_dir_check_page(struct afs_vnode *dvnode, struct page *page,
qty /= sizeof(union afs_xdr_dir_block);
/* check them */
- dbuf = kmap(page);
+ dbuf = kmap_atomic(page);
for (tmp = 0; tmp < qty; tmp++) {
if (dbuf->blocks[tmp].hdr.magic != AFS_DIR_MAGIC) {
printk("kAFS: %s(%lx): bad magic %d/%d is %04hx\n",
@@ -147,7 +175,7 @@ static bool afs_dir_check_page(struct afs_vnode *dvnode, struct page *page,
((u8 *)&dbuf->blocks[tmp])[AFS_DIR_BLOCK_SIZE - 1] = 0;
}
- kunmap(page);
+ kunmap_atomic(dbuf);
checked:
afs_stat_v(dvnode, n_read_dir);
@@ -158,35 +186,74 @@ error:
}
/*
- * Check the contents of a directory that we've just read.
+ * Dump the contents of a directory.
*/
-static bool afs_dir_check_pages(struct afs_vnode *dvnode, struct afs_read *req)
+static void afs_dir_dump(struct afs_vnode *dvnode, struct afs_read *req)
{
struct afs_xdr_dir_page *dbuf;
- unsigned int i, j, qty = PAGE_SIZE / sizeof(union afs_xdr_dir_block);
+ struct address_space *mapping = dvnode->vfs_inode.i_mapping;
+ struct page *page;
+ unsigned int i, qty = PAGE_SIZE / sizeof(union afs_xdr_dir_block);
+ pgoff_t last = req->nr_pages - 1;
- for (i = 0; i < req->nr_pages; i++)
- if (!afs_dir_check_page(dvnode, req->pages[i], req->actual_len))
- goto bad;
- return true;
+ XA_STATE(xas, &mapping->i_pages, 0);
-bad:
- pr_warn("DIR %llx:%llx f=%llx l=%llx al=%llx r=%llx\n",
+ pr_warn("DIR %llx:%llx f=%llx l=%llx al=%llx\n",
dvnode->fid.vid, dvnode->fid.vnode,
- req->file_size, req->len, req->actual_len, req->remain);
- pr_warn("DIR %llx %x %x %x\n",
- req->pos, req->index, req->nr_pages, req->offset);
+ req->file_size, req->len, req->actual_len);
+ pr_warn("DIR %llx %x %zx %zx\n",
+ req->pos, req->nr_pages,
+ req->iter->iov_offset, iov_iter_count(req->iter));
- for (i = 0; i < req->nr_pages; i++) {
- dbuf = kmap(req->pages[i]);
- for (j = 0; j < qty; j++) {
- union afs_xdr_dir_block *block = &dbuf->blocks[j];
+ xas_for_each(&xas, page, last) {
+ if (xas_retry(&xas, page))
+ continue;
+
+ BUG_ON(PageCompound(page));
+ BUG_ON(page->mapping != mapping);
+
+ dbuf = kmap_atomic(page);
+ for (i = 0; i < qty; i++) {
+ union afs_xdr_dir_block *block = &dbuf->blocks[i];
- pr_warn("[%02x] %32phN\n", i * qty + j, block);
+ pr_warn("[%02lx] %32phN\n", page->index * qty + i, block);
}
- kunmap(req->pages[i]);
+ kunmap_atomic(dbuf);
}
- return false;
+}
+
+/*
+ * Check all the pages in a directory. All the pages are held pinned.
+ */
+static int afs_dir_check(struct afs_vnode *dvnode, struct afs_read *req)
+{
+ struct address_space *mapping = dvnode->vfs_inode.i_mapping;
+ struct page *page;
+ pgoff_t last = req->nr_pages - 1;
+ int ret = 0;
+
+ XA_STATE(xas, &mapping->i_pages, 0);
+
+ if (unlikely(!req->nr_pages))
+ return 0;
+
+ rcu_read_lock();
+ xas_for_each(&xas, page, last) {
+ if (xas_retry(&xas, page))
+ continue;
+
+ BUG_ON(PageCompound(page));
+ BUG_ON(page->mapping != mapping);
+
+ if (!afs_dir_check_page(dvnode, page, req->file_size)) {
+ afs_dir_dump(dvnode, req);
+ ret = -EIO;
+ break;
+ }
+ }
+
+ rcu_read_unlock();
+ return ret;
}
/*
@@ -215,57 +282,57 @@ static struct afs_read *afs_read_dir(struct afs_vnode *dvnode, struct key *key)
{
struct afs_read *req;
loff_t i_size;
- int nr_pages, nr_inline, i, n;
- int ret = -ENOMEM;
+ int nr_pages, i, n;
+ int ret;
+
+ _enter("");
-retry:
+ req = kzalloc(sizeof(*req), GFP_KERNEL);
+ if (!req)
+ return ERR_PTR(-ENOMEM);
+
+ refcount_set(&req->usage, 1);
+ req->vnode = dvnode;
+ req->key = key_get(key);
+ req->cleanup = afs_dir_read_cleanup;
+
+expand:
i_size = i_size_read(&dvnode->vfs_inode);
- if (i_size < 2048)
- return ERR_PTR(afs_bad(dvnode, afs_file_error_dir_small));
+ if (i_size < 2048) {
+ ret = afs_bad(dvnode, afs_file_error_dir_small);
+ goto error;
+ }
if (i_size > 2048 * 1024) {
trace_afs_file_error(dvnode, -EFBIG, afs_file_error_dir_big);
- return ERR_PTR(-EFBIG);
+ ret = -EFBIG;
+ goto error;
}
_enter("%llu", i_size);
- /* Get a request record to hold the page list. We want to hold it
- * inline if we can, but we don't want to make an order 1 allocation.
- */
nr_pages = (i_size + PAGE_SIZE - 1) / PAGE_SIZE;
- nr_inline = nr_pages;
- if (nr_inline > (PAGE_SIZE - sizeof(*req)) / sizeof(struct page *))
- nr_inline = 0;
- req = kzalloc(struct_size(req, array, nr_inline), GFP_KERNEL);
- if (!req)
- return ERR_PTR(-ENOMEM);
-
- refcount_set(&req->usage, 1);
- req->nr_pages = nr_pages;
req->actual_len = i_size; /* May change */
req->len = nr_pages * PAGE_SIZE; /* We can ask for more than there is */
req->data_version = dvnode->status.data_version; /* May change */
- if (nr_inline > 0) {
- req->pages = req->array;
- } else {
- req->pages = kcalloc(nr_pages, sizeof(struct page *),
- GFP_KERNEL);
- if (!req->pages)
- goto error;
- }
+ iov_iter_xarray(&req->def_iter, READ, &dvnode->vfs_inode.i_mapping->i_pages,
+ 0, i_size);
+ req->iter = &req->def_iter;
- /* Get a list of all the pages that hold or will hold the directory
- * content. We need to fill in any gaps that we might find where the
- * memory reclaimer has been at work. If there are any gaps, we will
+ /* Fill in any gaps that we might find where the memory reclaimer has
+ * been at work and pin all the pages. If there are any gaps, we will
* need to reread the entire directory contents.
*/
- i = 0;
- do {
+ i = req->nr_pages;
+ while (i < nr_pages) {
+ struct page *pages[8], *page;
+
n = find_get_pages_contig(dvnode->vfs_inode.i_mapping, i,
- req->nr_pages - i,
- req->pages + i);
- _debug("find %u at %u/%u", n, i, req->nr_pages);
+ min_t(unsigned int, nr_pages - i,
+ ARRAY_SIZE(pages)),
+ pages);
+ _debug("find %u at %u/%u", n, i, nr_pages);
+
if (n == 0) {
gfp_t gfp = dvnode->vfs_inode.i_mapping->gfp_mask;
@@ -273,22 +340,24 @@ retry:
afs_stat_v(dvnode, n_inval);
ret = -ENOMEM;
- req->pages[i] = __page_cache_alloc(gfp);
- if (!req->pages[i])
+ page = __page_cache_alloc(gfp);
+ if (!page)
goto error;
- ret = add_to_page_cache_lru(req->pages[i],
+ ret = add_to_page_cache_lru(page,
dvnode->vfs_inode.i_mapping,
i, gfp);
if (ret < 0)
goto error;
- attach_page_private(req->pages[i], (void *)1);
- unlock_page(req->pages[i]);
+ attach_page_private(page, (void *)1);
+ unlock_page(page);
+ req->nr_pages++;
i++;
} else {
+ req->nr_pages += n;
i += n;
}
- } while (i < req->nr_pages);
+ }
/* If we're going to reload, we need to lock all the pages to prevent
* races.
@@ -306,18 +375,23 @@ retry:
if (!test_bit(AFS_VNODE_DIR_VALID, &dvnode->flags)) {
trace_afs_reload_dir(dvnode);
- ret = afs_fetch_data(dvnode, key, req);
+ ret = afs_fetch_data(dvnode, req);
if (ret < 0)
goto error_unlock;
task_io_account_read(PAGE_SIZE * req->nr_pages);
- if (req->len < req->file_size)
- goto content_has_grown;
+ if (req->len < req->file_size) {
+ /* The content has grown, so we need to expand the
+ * buffer.
+ */
+ up_write(&dvnode->validate_lock);
+ goto expand;
+ }
/* Validate the data we just read. */
- ret = -EIO;
- if (!afs_dir_check_pages(dvnode, req))
+ ret = afs_dir_check(dvnode, req);
+ if (ret < 0)
goto error_unlock;
// TODO: Trim excess pages
@@ -335,11 +409,6 @@ error:
afs_put_read(req);
_leave(" = %d", ret);
return ERR_PTR(ret);
-
-content_has_grown:
- up_write(&dvnode->validate_lock);
- afs_put_read(req);
- goto retry;
}
/*
@@ -449,6 +518,7 @@ static int afs_dir_iterate(struct inode *dir, struct dir_context *ctx,
struct afs_read *req;
struct page *page;
unsigned blkoff, limit;
+ void __rcu **slot;
int ret;
_enter("{%lu},%u,,", dir->i_ino, (unsigned)ctx->pos);
@@ -473,9 +543,15 @@ static int afs_dir_iterate(struct inode *dir, struct dir_context *ctx,
blkoff = ctx->pos & ~(sizeof(union afs_xdr_dir_block) - 1);
/* Fetch the appropriate page from the directory and re-add it
- * to the LRU.
+ * to the LRU. We have all the pages pinned with an extra ref.
*/
- page = req->pages[blkoff / PAGE_SIZE];
+ rcu_read_lock();
+ page = NULL;
+ slot = radix_tree_lookup_slot(&dvnode->vfs_inode.i_mapping->i_pages,
+ blkoff / PAGE_SIZE);
+ if (slot)
+ page = radix_tree_deref_slot(slot);
+ rcu_read_unlock();
if (!page) {
ret = afs_bad(dvnode, afs_file_error_dir_missing_page);
break;
@@ -1343,6 +1419,7 @@ static int afs_mkdir(struct user_namespace *mnt_userns, struct inode *dir,
afs_op_set_vnode(op, 0, dvnode);
op->file[0].dv_delta = 1;
+ op->file[0].modification = true;
op->file[0].update_ctime = true;
op->dentry = dentry;
op->create.mode = S_IFDIR | mode;
@@ -1424,6 +1501,7 @@ static int afs_rmdir(struct inode *dir, struct dentry *dentry)
afs_op_set_vnode(op, 0, dvnode);
op->file[0].dv_delta = 1;
+ op->file[0].modification = true;
op->file[0].update_ctime = true;
op->dentry = dentry;
@@ -1560,6 +1638,7 @@ static int afs_unlink(struct inode *dir, struct dentry *dentry)
afs_op_set_vnode(op, 0, dvnode);
op->file[0].dv_delta = 1;
+ op->file[0].modification = true;
op->file[0].update_ctime = true;
/* Try to make sure we have a callback promise on the victim. */
@@ -1642,6 +1721,7 @@ static int afs_create(struct user_namespace *mnt_userns, struct inode *dir,
afs_op_set_vnode(op, 0, dvnode);
op->file[0].dv_delta = 1;
+ op->file[0].modification = true;
op->file[0].update_ctime = true;
op->dentry = dentry;
@@ -1716,6 +1796,7 @@ static int afs_link(struct dentry *from, struct inode *dir,
afs_op_set_vnode(op, 0, dvnode);
afs_op_set_vnode(op, 1, vnode);
op->file[0].dv_delta = 1;
+ op->file[0].modification = true;
op->file[0].update_ctime = true;
op->file[1].update_ctime = true;
@@ -1911,6 +1992,8 @@ static int afs_rename(struct user_namespace *mnt_userns, struct inode *old_dir,
afs_op_set_vnode(op, 1, new_dvnode); /* May be same as orig_dvnode */
op->file[0].dv_delta = 1;
op->file[1].dv_delta = 1;
+ op->file[0].modification = true;
+ op->file[1].modification = true;
op->file[0].update_ctime = true;
op->file[1].update_ctime = true;
@@ -2007,6 +2090,6 @@ static void afs_dir_invalidatepage(struct page *page, unsigned int offset,
afs_stat_v(dvnode, n_inval);
/* we clean up only if the entire page is being invalidated */
- if (offset == 0 && length == PAGE_SIZE)
+ if (offset == 0 && length == thp_size(page))
detach_page_private(page);
}
diff --git a/fs/afs/dir_silly.c b/fs/afs/dir_silly.c
index 04f75a44f243..dae9a57d7ec0 100644
--- a/fs/afs/dir_silly.c
+++ b/fs/afs/dir_silly.c
@@ -73,6 +73,8 @@ static int afs_do_silly_rename(struct afs_vnode *dvnode, struct afs_vnode *vnode
afs_op_set_vnode(op, 1, dvnode);
op->file[0].dv_delta = 1;
op->file[1].dv_delta = 1;
+ op->file[0].modification = true;
+ op->file[1].modification = true;
op->file[0].update_ctime = true;
op->file[1].update_ctime = true;
@@ -201,6 +203,7 @@ static int afs_do_silly_unlink(struct afs_vnode *dvnode, struct afs_vnode *vnode
afs_op_set_vnode(op, 0, dvnode);
afs_op_set_vnode(op, 1, vnode);
op->file[0].dv_delta = 1;
+ op->file[0].modification = true;
op->file[0].update_ctime = true;
op->file[1].op_unlinked = true;
op->file[1].update_ctime = true;
diff --git a/fs/afs/file.c b/fs/afs/file.c
index 85f5adf21aa0..db035ae2a134 100644
--- a/fs/afs/file.c
+++ b/fs/afs/file.c
@@ -14,6 +14,7 @@
#include <linux/gfp.h>
#include <linux/task_io_accounting_ops.h>
#include <linux/mm.h>
+#include <linux/netfs.h>
#include "internal.h"
static int afs_file_mmap(struct file *file, struct vm_area_struct *vma);
@@ -22,8 +23,7 @@ static void afs_invalidatepage(struct page *page, unsigned int offset,
unsigned int length);
static int afs_releasepage(struct page *page, gfp_t gfp_flags);
-static int afs_readpages(struct file *filp, struct address_space *mapping,
- struct list_head *pages, unsigned nr_pages);
+static void afs_readahead(struct readahead_control *ractl);
const struct file_operations afs_file_operations = {
.open = afs_open,
@@ -43,12 +43,11 @@ const struct inode_operations afs_file_inode_operations = {
.getattr = afs_getattr,
.setattr = afs_setattr,
.permission = afs_permission,
- .listxattr = afs_listxattr,
};
const struct address_space_operations afs_fs_aops = {
.readpage = afs_readpage,
- .readpages = afs_readpages,
+ .readahead = afs_readahead,
.set_page_dirty = afs_set_page_dirty,
.launder_page = afs_launder_page,
.releasepage = afs_releasepage,
@@ -185,41 +184,50 @@ int afs_release(struct inode *inode, struct file *file)
}
/*
+ * Allocate a new read record.
+ */
+struct afs_read *afs_alloc_read(gfp_t gfp)
+{
+ struct afs_read *req;
+
+ req = kzalloc(sizeof(struct afs_read), gfp);
+ if (req)
+ refcount_set(&req->usage, 1);
+
+ return req;
+}
+
+/*
* Dispose of a ref to a read record.
*/
void afs_put_read(struct afs_read *req)
{
- int i;
-
if (refcount_dec_and_test(&req->usage)) {
- if (req->pages) {
- for (i = 0; i < req->nr_pages; i++)
- if (req->pages[i])
- put_page(req->pages[i]);
- if (req->pages != req->array)
- kfree(req->pages);
- }
+ if (req->cleanup)
+ req->cleanup(req);
+ key_put(req->key);
kfree(req);
}
}
-#ifdef CONFIG_AFS_FSCACHE
-/*
- * deal with notification that a page was read from the cache
- */
-static void afs_file_readpage_read_complete(struct page *page,
- void *data,
- int error)
+static void afs_fetch_data_notify(struct afs_operation *op)
{
- _enter("%p,%p,%d", page, data, error);
-
- /* if the read completes with an error, we just unlock the page and let
- * the VM reissue the readpage */
- if (!error)
- SetPageUptodate(page);
- unlock_page(page);
+ struct afs_read *req = op->fetch.req;
+ struct netfs_read_subrequest *subreq = req->subreq;
+ int error = op->error;
+
+ if (error == -ECONNABORTED)
+ error = afs_abort_to_error(op->ac.abort_code);
+ req->error = error;
+
+ if (subreq) {
+ __set_bit(NETFS_SREQ_CLEAR_TAIL, &subreq->flags);
+ netfs_subreq_terminated(subreq, error ?: req->actual_len, false);
+ req->subreq = NULL;
+ } else if (req->done) {
+ req->done(req);
+ }
}
-#endif
static void afs_fetch_data_success(struct afs_operation *op)
{
@@ -229,10 +237,12 @@ static void afs_fetch_data_success(struct afs_operation *op)
afs_vnode_commit_status(op, &op->file[0]);
afs_stat_v(vnode, n_fetches);
atomic_long_add(op->fetch.req->actual_len, &op->net->n_fetch_bytes);
+ afs_fetch_data_notify(op);
}
static void afs_fetch_data_put(struct afs_operation *op)
{
+ op->fetch.req->error = op->error;
afs_put_read(op->fetch.req);
}
@@ -241,13 +251,14 @@ static const struct afs_operation_ops afs_fetch_data_operation = {
.issue_yfs_rpc = yfs_fs_fetch_data,
.success = afs_fetch_data_success,
.aborted = afs_check_for_remote_deletion,
+ .failed = afs_fetch_data_notify,
.put = afs_fetch_data_put,
};
/*
* Fetch file data from the volume.
*/
-int afs_fetch_data(struct afs_vnode *vnode, struct key *key, struct afs_read *req)
+int afs_fetch_data(struct afs_vnode *vnode, struct afs_read *req)
{
struct afs_operation *op;
@@ -256,11 +267,14 @@ int afs_fetch_data(struct afs_vnode *vnode, struct key *key, struct afs_read *re
vnode->fid.vid,
vnode->fid.vnode,
vnode->fid.unique,
- key_serial(key));
+ key_serial(req->key));
- op = afs_alloc_operation(key, vnode->volume);
- if (IS_ERR(op))
+ op = afs_alloc_operation(req->key, vnode->volume);
+ if (IS_ERR(op)) {
+ if (req->subreq)
+ netfs_subreq_terminated(req->subreq, PTR_ERR(op), false);
return PTR_ERR(op);
+ }
afs_op_set_vnode(op, 0, vnode);
@@ -269,336 +283,103 @@ int afs_fetch_data(struct afs_vnode *vnode, struct key *key, struct afs_read *re
return afs_do_sync_operation(op);
}
-/*
- * read page from file, directory or symlink, given a key to use
- */
-int afs_page_filler(void *data, struct page *page)
+static void afs_req_issue_op(struct netfs_read_subrequest *subreq)
{
- struct inode *inode = page->mapping->host;
- struct afs_vnode *vnode = AFS_FS_I(inode);
- struct afs_read *req;
- struct key *key = data;
- int ret;
-
- _enter("{%x},{%lu},{%lu}", key_serial(key), inode->i_ino, page->index);
+ struct afs_vnode *vnode = AFS_FS_I(subreq->rreq->inode);
+ struct afs_read *fsreq;
- BUG_ON(!PageLocked(page));
+ fsreq = afs_alloc_read(GFP_NOFS);
+ if (!fsreq)
+ return netfs_subreq_terminated(subreq, -ENOMEM, false);
- ret = -ESTALE;
- if (test_bit(AFS_VNODE_DELETED, &vnode->flags))
- goto error;
+ fsreq->subreq = subreq;
+ fsreq->pos = subreq->start + subreq->transferred;
+ fsreq->len = subreq->len - subreq->transferred;
+ fsreq->key = subreq->rreq->netfs_priv;
+ fsreq->vnode = vnode;
+ fsreq->iter = &fsreq->def_iter;
- /* is it cached? */
-#ifdef CONFIG_AFS_FSCACHE
- ret = fscache_read_or_alloc_page(vnode->cache,
- page,
- afs_file_readpage_read_complete,
- NULL,
- GFP_KERNEL);
-#else
- ret = -ENOBUFS;
-#endif
- switch (ret) {
- /* read BIO submitted (page in cache) */
- case 0:
- break;
-
- /* page not yet cached */
- case -ENODATA:
- _debug("cache said ENODATA");
- goto go_on;
-
- /* page will not be cached */
- case -ENOBUFS:
- _debug("cache said ENOBUFS");
-
- fallthrough;
- default:
- go_on:
- req = kzalloc(struct_size(req, array, 1), GFP_KERNEL);
- if (!req)
- goto enomem;
-
- /* We request a full page. If the page is a partial one at the
- * end of the file, the server will return a short read and the
- * unmarshalling code will clear the unfilled space.
- */
- refcount_set(&req->usage, 1);
- req->pos = (loff_t)page->index << PAGE_SHIFT;
- req->len = PAGE_SIZE;
- req->nr_pages = 1;
- req->pages = req->array;
- req->pages[0] = page;
- get_page(page);
-
- /* read the contents of the file from the server into the
- * page */
- ret = afs_fetch_data(vnode, key, req);
- afs_put_read(req);
-
- if (ret < 0) {
- if (ret == -ENOENT) {
- _debug("got NOENT from server"
- " - marking file deleted and stale");
- set_bit(AFS_VNODE_DELETED, &vnode->flags);
- ret = -ESTALE;
- }
+ iov_iter_xarray(&fsreq->def_iter, READ,
+ &fsreq->vnode->vfs_inode.i_mapping->i_pages,
+ fsreq->pos, fsreq->len);
-#ifdef CONFIG_AFS_FSCACHE
- fscache_uncache_page(vnode->cache, page);
-#endif
- BUG_ON(PageFsCache(page));
-
- if (ret == -EINTR ||
- ret == -ENOMEM ||
- ret == -ERESTARTSYS ||
- ret == -EAGAIN)
- goto error;
- goto io_error;
- }
+ afs_fetch_data(fsreq->vnode, fsreq);
+}
- SetPageUptodate(page);
+static int afs_symlink_readpage(struct page *page)
+{
+ struct afs_vnode *vnode = AFS_FS_I(page->mapping->host);
+ struct afs_read *fsreq;
+ int ret;
- /* send the page to the cache */
-#ifdef CONFIG_AFS_FSCACHE
- if (PageFsCache(page) &&
- fscache_write_page(vnode->cache, page, vnode->status.size,
- GFP_KERNEL) != 0) {
- fscache_uncache_page(vnode->cache, page);
- BUG_ON(PageFsCache(page));
- }
-#endif
- unlock_page(page);
- }
+ fsreq = afs_alloc_read(GFP_NOFS);
+ if (!fsreq)
+ return -ENOMEM;
- _leave(" = 0");
- return 0;
+ fsreq->pos = page->index * PAGE_SIZE;
+ fsreq->len = PAGE_SIZE;
+ fsreq->vnode = vnode;
+ fsreq->iter = &fsreq->def_iter;
+ iov_iter_xarray(&fsreq->def_iter, READ, &page->mapping->i_pages,
+ fsreq->pos, fsreq->len);
-io_error:
- SetPageError(page);
- goto error;
-enomem:
- ret = -ENOMEM;
-error:
- unlock_page(page);
- _leave(" = %d", ret);
+ ret = afs_fetch_data(fsreq->vnode, fsreq);
+ page_endio(page, false, ret);
return ret;
}
-/*
- * read page from file, directory or symlink, given a file to nominate the key
- * to be used
- */
-static int afs_readpage(struct file *file, struct page *page)
+static void afs_init_rreq(struct netfs_read_request *rreq, struct file *file)
{
- struct key *key;
- int ret;
-
- if (file) {
- key = afs_file_key(file);
- ASSERT(key != NULL);
- ret = afs_page_filler(key, page);
- } else {
- struct inode *inode = page->mapping->host;
- key = afs_request_key(AFS_FS_S(inode->i_sb)->cell);
- if (IS_ERR(key)) {
- ret = PTR_ERR(key);
- } else {
- ret = afs_page_filler(key, page);
- key_put(key);
- }
- }
- return ret;
+ rreq->netfs_priv = key_get(afs_file_key(file));
}
-/*
- * Make pages available as they're filled.
- */
-static void afs_readpages_page_done(struct afs_read *req)
+static bool afs_is_cache_enabled(struct inode *inode)
{
-#ifdef CONFIG_AFS_FSCACHE
- struct afs_vnode *vnode = req->vnode;
-#endif
- struct page *page = req->pages[req->index];
+ struct fscache_cookie *cookie = afs_vnode_cache(AFS_FS_I(inode));
- req->pages[req->index] = NULL;
- SetPageUptodate(page);
-
- /* send the page to the cache */
-#ifdef CONFIG_AFS_FSCACHE
- if (PageFsCache(page) &&
- fscache_write_page(vnode->cache, page, vnode->status.size,
- GFP_KERNEL) != 0) {
- fscache_uncache_page(vnode->cache, page);
- BUG_ON(PageFsCache(page));
- }
-#endif
- unlock_page(page);
- put_page(page);
+ return fscache_cookie_enabled(cookie) && !hlist_empty(&cookie->backing_objects);
}
-/*
- * Read a contiguous set of pages.
- */
-static int afs_readpages_one(struct file *file, struct address_space *mapping,
- struct list_head *pages)
+static int afs_begin_cache_operation(struct netfs_read_request *rreq)
{
- struct afs_vnode *vnode = AFS_FS_I(mapping->host);
- struct afs_read *req;
- struct list_head *p;
- struct page *first, *page;
- struct key *key = afs_file_key(file);
- pgoff_t index;
- int ret, n, i;
-
- /* Count the number of contiguous pages at the front of the list. Note
- * that the list goes prev-wards rather than next-wards.
- */
- first = lru_to_page(pages);
- index = first->index + 1;
- n = 1;
- for (p = first->lru.prev; p != pages; p = p->prev) {
- page = list_entry(p, struct page, lru);
- if (page->index != index)
- break;
- index++;
- n++;
- }
-
- req = kzalloc(struct_size(req, array, n), GFP_NOFS);
- if (!req)
- return -ENOMEM;
-
- refcount_set(&req->usage, 1);
- req->vnode = vnode;
- req->page_done = afs_readpages_page_done;
- req->pos = first->index;
- req->pos <<= PAGE_SHIFT;
- req->pages = req->array;
-
- /* Transfer the pages to the request. We add them in until one fails
- * to add to the LRU and then we stop (as that'll make a hole in the
- * contiguous run.
- *
- * Note that it's possible for the file size to change whilst we're
- * doing this, but we rely on the server returning less than we asked
- * for if the file shrank. We also rely on this to deal with a partial
- * page at the end of the file.
- */
- do {
- page = lru_to_page(pages);
- list_del(&page->lru);
- index = page->index;
- if (add_to_page_cache_lru(page, mapping, index,
- readahead_gfp_mask(mapping))) {
-#ifdef CONFIG_AFS_FSCACHE
- fscache_uncache_page(vnode->cache, page);
-#endif
- put_page(page);
- break;
- }
-
- req->pages[req->nr_pages++] = page;
- req->len += PAGE_SIZE;
- } while (req->nr_pages < n);
+ struct afs_vnode *vnode = AFS_FS_I(rreq->inode);
- if (req->nr_pages == 0) {
- kfree(req);
- return 0;
- }
-
- ret = afs_fetch_data(vnode, key, req);
- if (ret < 0)
- goto error;
-
- task_io_account_read(PAGE_SIZE * req->nr_pages);
- afs_put_read(req);
- return 0;
-
-error:
- if (ret == -ENOENT) {
- _debug("got NOENT from server"
- " - marking file deleted and stale");
- set_bit(AFS_VNODE_DELETED, &vnode->flags);
- ret = -ESTALE;
- }
-
- for (i = 0; i < req->nr_pages; i++) {
- page = req->pages[i];
- if (page) {
-#ifdef CONFIG_AFS_FSCACHE
- fscache_uncache_page(vnode->cache, page);
-#endif
- SetPageError(page);
- unlock_page(page);
- }
- }
-
- afs_put_read(req);
- return ret;
+ return fscache_begin_read_operation(rreq, afs_vnode_cache(vnode));
}
-/*
- * read a set of pages
- */
-static int afs_readpages(struct file *file, struct address_space *mapping,
- struct list_head *pages, unsigned nr_pages)
+static int afs_check_write_begin(struct file *file, loff_t pos, unsigned len,
+ struct page *page, void **_fsdata)
{
- struct key *key = afs_file_key(file);
- struct afs_vnode *vnode;
- int ret = 0;
-
- _enter("{%d},{%lu},,%d",
- key_serial(key), mapping->host->i_ino, nr_pages);
+ struct afs_vnode *vnode = AFS_FS_I(file_inode(file));
- ASSERT(key != NULL);
+ return test_bit(AFS_VNODE_DELETED, &vnode->flags) ? -ESTALE : 0;
+}
- vnode = AFS_FS_I(mapping->host);
- if (test_bit(AFS_VNODE_DELETED, &vnode->flags)) {
- _leave(" = -ESTALE");
- return -ESTALE;
- }
+static void afs_priv_cleanup(struct address_space *mapping, void *netfs_priv)
+{
+ key_put(netfs_priv);
+}
- /* attempt to read as many of the pages as possible */
-#ifdef CONFIG_AFS_FSCACHE
- ret = fscache_read_or_alloc_pages(vnode->cache,
- mapping,
- pages,
- &nr_pages,
- afs_file_readpage_read_complete,
- NULL,
- mapping_gfp_mask(mapping));
-#else
- ret = -ENOBUFS;
-#endif
+const struct netfs_read_request_ops afs_req_ops = {
+ .init_rreq = afs_init_rreq,
+ .is_cache_enabled = afs_is_cache_enabled,
+ .begin_cache_operation = afs_begin_cache_operation,
+ .check_write_begin = afs_check_write_begin,
+ .issue_op = afs_req_issue_op,
+ .cleanup = afs_priv_cleanup,
+};
- switch (ret) {
- /* all pages are being read from the cache */
- case 0:
- BUG_ON(!list_empty(pages));
- BUG_ON(nr_pages != 0);
- _leave(" = 0 [reading all]");
- return 0;
-
- /* there were pages that couldn't be read from the cache */
- case -ENODATA:
- case -ENOBUFS:
- break;
-
- /* other error */
- default:
- _leave(" = %d", ret);
- return ret;
- }
+static int afs_readpage(struct file *file, struct page *page)
+{
+ if (!file)
+ return afs_symlink_readpage(page);
- while (!list_empty(pages)) {
- ret = afs_readpages_one(file, mapping, pages);
- if (ret < 0)
- break;
- }
+ return netfs_readpage(file, page, &afs_req_ops, NULL);
+}
- _leave(" = %d [netting]", ret);
- return ret;
+static void afs_readahead(struct readahead_control *ractl)
+{
+ netfs_readahead(ractl, &afs_req_ops, NULL);
}
/*
@@ -626,8 +407,8 @@ static void afs_invalidate_dirty(struct page *page, unsigned int offset,
return;
/* We may need to shorten the dirty region */
- f = afs_page_dirty_from(priv);
- t = afs_page_dirty_to(priv);
+ f = afs_page_dirty_from(page, priv);
+ t = afs_page_dirty_to(page, priv);
if (t <= offset || f >= end)
return; /* Doesn't overlap */
@@ -645,17 +426,17 @@ static void afs_invalidate_dirty(struct page *page, unsigned int offset,
if (f == t)
goto undirty;
- priv = afs_page_dirty(f, t);
+ priv = afs_page_dirty(page, f, t);
set_page_private(page, priv);
- trace_afs_page_dirty(vnode, tracepoint_string("trunc"), page->index, priv);
+ trace_afs_page_dirty(vnode, tracepoint_string("trunc"), page);
return;
undirty:
- trace_afs_page_dirty(vnode, tracepoint_string("undirty"), page->index, priv);
+ trace_afs_page_dirty(vnode, tracepoint_string("undirty"), page);
clear_page_dirty_for_io(page);
full_invalidate:
- priv = (unsigned long)detach_page_private(page);
- trace_afs_page_dirty(vnode, tracepoint_string("inval"), page->index, priv);
+ trace_afs_page_dirty(vnode, tracepoint_string("inval"), page);
+ detach_page_private(page);
}
/*
@@ -670,20 +451,10 @@ static void afs_invalidatepage(struct page *page, unsigned int offset,
BUG_ON(!PageLocked(page));
-#ifdef CONFIG_AFS_FSCACHE
- /* we clean up only if the entire page is being invalidated */
- if (offset == 0 && length == PAGE_SIZE) {
- if (PageFsCache(page)) {
- struct afs_vnode *vnode = AFS_FS_I(page->mapping->host);
- fscache_wait_on_page_write(vnode->cache, page);
- fscache_uncache_page(vnode->cache, page);
- }
- }
-#endif
-
if (PagePrivate(page))
afs_invalidate_dirty(page, offset, length);
+ wait_on_page_fscache(page);
_leave("");
}
@@ -694,7 +465,6 @@ static void afs_invalidatepage(struct page *page, unsigned int offset,
static int afs_releasepage(struct page *page, gfp_t gfp_flags)
{
struct afs_vnode *vnode = AFS_FS_I(page->mapping->host);
- unsigned long priv;
_enter("{{%llx:%llu}[%lu],%lx},%x",
vnode->fid.vid, vnode->fid.vnode, page->index, page->flags,
@@ -703,16 +473,16 @@ static int afs_releasepage(struct page *page, gfp_t gfp_flags)
/* deny if page is being written to the cache and the caller hasn't
* elected to wait */
#ifdef CONFIG_AFS_FSCACHE
- if (!fscache_maybe_release_page(vnode->cache, page, gfp_flags)) {
- _leave(" = F [cache busy]");
- return 0;
+ if (PageFsCache(page)) {
+ if (!(gfp_flags & __GFP_DIRECT_RECLAIM) || !(gfp_flags & __GFP_FS))
+ return false;
+ wait_on_page_fscache(page);
}
#endif
if (PagePrivate(page)) {
- priv = (unsigned long)detach_page_private(page);
- trace_afs_page_dirty(vnode, tracepoint_string("rel"),
- page->index, priv);
+ trace_afs_page_dirty(vnode, tracepoint_string("rel"), page);
+ detach_page_private(page);
}
/* indicate that the page can be released */
diff --git a/fs/afs/fs_operation.c b/fs/afs/fs_operation.c
index 97cab12b0a6c..d222dfbe976b 100644
--- a/fs/afs/fs_operation.c
+++ b/fs/afs/fs_operation.c
@@ -118,6 +118,8 @@ static void afs_prepare_vnode(struct afs_operation *op, struct afs_vnode_param *
vp->cb_break_before = afs_calc_vnode_cb_break(vnode);
if (vnode->lock_state != AFS_VNODE_LOCK_NONE)
op->flags |= AFS_OPERATION_CUR_ONLY;
+ if (vp->modification)
+ set_bit(AFS_VNODE_MODIFYING, &vnode->flags);
}
if (vp->fid.vnode)
@@ -181,10 +183,13 @@ void afs_wait_for_operation(struct afs_operation *op)
if (test_bit(AFS_SERVER_FL_IS_YFS, &op->server->flags) &&
op->ops->issue_yfs_rpc)
op->ops->issue_yfs_rpc(op);
- else
+ else if (op->ops->issue_afs_rpc)
op->ops->issue_afs_rpc(op);
+ else
+ op->ac.error = -ENOTSUPP;
- op->error = afs_wait_for_call_to_complete(op->call, &op->ac);
+ if (op->call)
+ op->error = afs_wait_for_call_to_complete(op->call, &op->ac);
}
switch (op->error) {
@@ -195,8 +200,10 @@ void afs_wait_for_operation(struct afs_operation *op)
case -ECONNABORTED:
if (op->ops->aborted)
op->ops->aborted(op);
- break;
+ fallthrough;
default:
+ if (op->ops->failed)
+ op->ops->failed(op);
break;
}
@@ -220,6 +227,10 @@ int afs_put_operation(struct afs_operation *op)
if (op->ops && op->ops->put)
op->ops->put(op);
+ if (op->file[0].modification)
+ clear_bit(AFS_VNODE_MODIFYING, &op->file[0].vnode->flags);
+ if (op->file[1].modification && op->file[1].vnode != op->file[0].vnode)
+ clear_bit(AFS_VNODE_MODIFYING, &op->file[1].vnode->flags);
if (op->file[0].put_vnode)
iput(&op->file[0].vnode->vfs_inode);
if (op->file[1].put_vnode)
diff --git a/fs/afs/fsclient.c b/fs/afs/fsclient.c
index 1d95ed9dd86e..2f695a260442 100644
--- a/fs/afs/fsclient.c
+++ b/fs/afs/fsclient.c
@@ -10,6 +10,7 @@
#include <linux/sched.h>
#include <linux/circ_buf.h>
#include <linux/iversion.h>
+#include <linux/netfs.h>
#include "internal.h"
#include "afs_fs.h"
#include "xdr_fs.h"
@@ -302,17 +303,15 @@ static int afs_deliver_fs_fetch_data(struct afs_call *call)
struct afs_vnode_param *vp = &op->file[0];
struct afs_read *req = op->fetch.req;
const __be32 *bp;
- unsigned int size;
int ret;
- _enter("{%u,%zu/%llu}",
- call->unmarshall, iov_iter_count(call->iter), req->actual_len);
+ _enter("{%u,%zu,%zu/%llu}",
+ call->unmarshall, call->iov_len, iov_iter_count(call->iter),
+ req->actual_len);
switch (call->unmarshall) {
case 0:
req->actual_len = 0;
- req->index = 0;
- req->offset = req->pos & (PAGE_SIZE - 1);
call->unmarshall++;
if (call->operation_ID == FSFETCHDATA64) {
afs_extract_to_tmp64(call);
@@ -322,7 +321,10 @@ static int afs_deliver_fs_fetch_data(struct afs_call *call)
}
fallthrough;
- /* extract the returned data length */
+ /* Extract the returned data length into
+ * ->actual_len. This may indicate more or less data than was
+ * requested will be returned.
+ */
case 1:
_debug("extract data length");
ret = afs_extract_data(call, true);
@@ -331,44 +333,25 @@ static int afs_deliver_fs_fetch_data(struct afs_call *call)
req->actual_len = be64_to_cpu(call->tmp64);
_debug("DATA length: %llu", req->actual_len);
- req->remain = min(req->len, req->actual_len);
- if (req->remain == 0)
+
+ if (req->actual_len == 0)
goto no_more_data;
+ call->iter = req->iter;
+ call->iov_len = min(req->actual_len, req->len);
call->unmarshall++;
-
- begin_page:
- ASSERTCMP(req->index, <, req->nr_pages);
- if (req->remain > PAGE_SIZE - req->offset)
- size = PAGE_SIZE - req->offset;
- else
- size = req->remain;
- call->bvec[0].bv_len = size;
- call->bvec[0].bv_offset = req->offset;
- call->bvec[0].bv_page = req->pages[req->index];
- iov_iter_bvec(&call->def_iter, READ, call->bvec, 1, size);
- ASSERTCMP(size, <=, PAGE_SIZE);
fallthrough;
/* extract the returned data */
case 2:
_debug("extract data %zu/%llu",
- iov_iter_count(call->iter), req->remain);
+ iov_iter_count(call->iter), req->actual_len);
ret = afs_extract_data(call, true);
if (ret < 0)
return ret;
- req->remain -= call->bvec[0].bv_len;
- req->offset += call->bvec[0].bv_len;
- ASSERTCMP(req->offset, <=, PAGE_SIZE);
- if (req->offset == PAGE_SIZE) {
- req->offset = 0;
- req->index++;
- if (req->remain > 0)
- goto begin_page;
- }
- ASSERTCMP(req->remain, ==, 0);
+ call->iter = &call->def_iter;
if (req->actual_len <= req->len)
goto no_more_data;
@@ -410,17 +393,6 @@ static int afs_deliver_fs_fetch_data(struct afs_call *call)
break;
}
- for (; req->index < req->nr_pages; req->index++) {
- if (req->offset < PAGE_SIZE)
- zero_user_segment(req->pages[req->index],
- req->offset, PAGE_SIZE);
- req->offset = 0;
- }
-
- if (req->page_done)
- for (req->index = 0; req->index < req->nr_pages; req->index++)
- req->page_done(req);
-
_leave(" = 0 [done]");
return 0;
}
@@ -494,6 +466,8 @@ void afs_fs_fetch_data(struct afs_operation *op)
if (!call)
return afs_op_nomem(op);
+ req->call_debug_id = call->debug_id;
+
/* marshall the parameters */
bp = call->request;
bp[0] = htonl(FSFETCHDATA);
@@ -1079,8 +1053,7 @@ static const struct afs_call_type afs_RXFSStoreData64 = {
/*
* store a set of pages to a very large file
*/
-static void afs_fs_store_data64(struct afs_operation *op,
- loff_t pos, loff_t size, loff_t i_size)
+static void afs_fs_store_data64(struct afs_operation *op)
{
struct afs_vnode_param *vp = &op->file[0];
struct afs_call *call;
@@ -1095,7 +1068,7 @@ static void afs_fs_store_data64(struct afs_operation *op,
if (!call)
return afs_op_nomem(op);
- call->send_pages = true;
+ call->write_iter = op->store.write_iter;
/* marshall the parameters */
bp = call->request;
@@ -1111,47 +1084,38 @@ static void afs_fs_store_data64(struct afs_operation *op,
*bp++ = 0; /* unix mode */
*bp++ = 0; /* segment size */
- *bp++ = htonl(upper_32_bits(pos));
- *bp++ = htonl(lower_32_bits(pos));
- *bp++ = htonl(upper_32_bits(size));
- *bp++ = htonl(lower_32_bits(size));
- *bp++ = htonl(upper_32_bits(i_size));
- *bp++ = htonl(lower_32_bits(i_size));
+ *bp++ = htonl(upper_32_bits(op->store.pos));
+ *bp++ = htonl(lower_32_bits(op->store.pos));
+ *bp++ = htonl(upper_32_bits(op->store.size));
+ *bp++ = htonl(lower_32_bits(op->store.size));
+ *bp++ = htonl(upper_32_bits(op->store.i_size));
+ *bp++ = htonl(lower_32_bits(op->store.i_size));
trace_afs_make_fs_call(call, &vp->fid);
afs_make_op_call(op, call, GFP_NOFS);
}
/*
- * store a set of pages
+ * Write data to a file on the server.
*/
void afs_fs_store_data(struct afs_operation *op)
{
struct afs_vnode_param *vp = &op->file[0];
struct afs_call *call;
- loff_t size, pos, i_size;
__be32 *bp;
_enter(",%x,{%llx:%llu},,",
key_serial(op->key), vp->fid.vid, vp->fid.vnode);
- size = (loff_t)op->store.last_to - (loff_t)op->store.first_offset;
- if (op->store.first != op->store.last)
- size += (loff_t)(op->store.last - op->store.first) << PAGE_SHIFT;
- pos = (loff_t)op->store.first << PAGE_SHIFT;
- pos += op->store.first_offset;
-
- i_size = i_size_read(&vp->vnode->vfs_inode);
- if (pos + size > i_size)
- i_size = size + pos;
-
_debug("size %llx, at %llx, i_size %llx",
- (unsigned long long) size, (unsigned long long) pos,
- (unsigned long long) i_size);
+ (unsigned long long)op->store.size,
+ (unsigned long long)op->store.pos,
+ (unsigned long long)op->store.i_size);
- if (upper_32_bits(pos) || upper_32_bits(i_size) || upper_32_bits(size) ||
- upper_32_bits(pos + size))
- return afs_fs_store_data64(op, pos, size, i_size);
+ if (upper_32_bits(op->store.pos) ||
+ upper_32_bits(op->store.size) ||
+ upper_32_bits(op->store.i_size))
+ return afs_fs_store_data64(op);
call = afs_alloc_flat_call(op->net, &afs_RXFSStoreData,
(4 + 6 + 3) * 4,
@@ -1159,7 +1123,7 @@ void afs_fs_store_data(struct afs_operation *op)
if (!call)
return afs_op_nomem(op);
- call->send_pages = true;
+ call->write_iter = op->store.write_iter;
/* marshall the parameters */
bp = call->request;
@@ -1175,9 +1139,9 @@ void afs_fs_store_data(struct afs_operation *op)
*bp++ = 0; /* unix mode */
*bp++ = 0; /* segment size */
- *bp++ = htonl(lower_32_bits(pos));
- *bp++ = htonl(lower_32_bits(size));
- *bp++ = htonl(lower_32_bits(i_size));
+ *bp++ = htonl(lower_32_bits(op->store.pos));
+ *bp++ = htonl(lower_32_bits(op->store.size));
+ *bp++ = htonl(lower_32_bits(op->store.i_size));
trace_afs_make_fs_call(call, &vp->fid);
afs_make_op_call(op, call, GFP_NOFS);
diff --git a/fs/afs/inode.c b/fs/afs/inode.c
index 1156b2df28d3..80b6c8d967d5 100644
--- a/fs/afs/inode.c
+++ b/fs/afs/inode.c
@@ -27,7 +27,6 @@
static const struct inode_operations afs_symlink_inode_operations = {
.get_link = page_get_link,
- .listxattr = afs_listxattr,
};
static noinline void dump_vnode(struct afs_vnode *vnode, struct afs_vnode *parent_vnode)
@@ -103,13 +102,13 @@ static int afs_inode_init_from_status(struct afs_operation *op,
switch (status->type) {
case AFS_FTYPE_FILE:
- inode->i_mode = S_IFREG | status->mode;
+ inode->i_mode = S_IFREG | (status->mode & S_IALLUGO);
inode->i_op = &afs_file_inode_operations;
inode->i_fop = &afs_file_operations;
inode->i_mapping->a_ops = &afs_fs_aops;
break;
case AFS_FTYPE_DIR:
- inode->i_mode = S_IFDIR | status->mode;
+ inode->i_mode = S_IFDIR | (status->mode & S_IALLUGO);
inode->i_op = &afs_dir_inode_operations;
inode->i_fop = &afs_dir_file_operations;
inode->i_mapping->a_ops = &afs_dir_aops;
@@ -199,7 +198,7 @@ static void afs_apply_status(struct afs_operation *op,
if (status->mode != vnode->status.mode) {
mode = inode->i_mode;
mode &= ~S_IALLUGO;
- mode |= status->mode;
+ mode |= status->mode & S_IALLUGO;
WRITE_ONCE(inode->i_mode, mode);
}
@@ -215,11 +214,12 @@ static void afs_apply_status(struct afs_operation *op,
if (vp->dv_before + vp->dv_delta != status->data_version) {
if (test_bit(AFS_VNODE_CB_PROMISED, &vnode->flags))
- pr_warn("kAFS: vnode modified {%llx:%llu} %llx->%llx %s\n",
+ pr_warn("kAFS: vnode modified {%llx:%llu} %llx->%llx %s (op=%x)\n",
vnode->fid.vid, vnode->fid.vnode,
(unsigned long long)vp->dv_before + vp->dv_delta,
(unsigned long long)status->data_version,
- op->type ? op->type->name : "???");
+ op->type ? op->type->name : "???",
+ op->debug_id);
vnode->invalid_before = status->data_version;
if (vnode->status.type == AFS_FTYPE_DIR) {
@@ -294,8 +294,9 @@ void afs_vnode_commit_status(struct afs_operation *op, struct afs_vnode_param *v
op->flags &= ~AFS_OPERATION_DIR_CONFLICT;
}
} else if (vp->scb.have_status) {
- if (vp->dv_before + vp->dv_delta != vp->scb.status.data_version &&
- vp->speculative)
+ if (vp->speculative &&
+ (test_bit(AFS_VNODE_MODIFYING, &vnode->flags) ||
+ vp->dv_before != vnode->status.data_version))
/* Ignore the result of a speculative bulk status fetch
* if it splits around a modification op, thereby
* appearing to regress the data version.
@@ -428,7 +429,7 @@ static void afs_get_inode_cache(struct afs_vnode *vnode)
} __packed key;
struct afs_vnode_cache_aux aux;
- if (vnode->status.type == AFS_FTYPE_DIR) {
+ if (vnode->status.type != AFS_FTYPE_FILE) {
vnode->cache = NULL;
return;
}
@@ -911,6 +912,7 @@ int afs_setattr(struct user_namespace *mnt_userns, struct dentry *dentry,
}
op->ctime = attr->ia_ctime;
op->file[0].update_ctime = 1;
+ op->file[0].modification = true;
op->ops = &afs_setattr_operation;
ret = afs_do_sync_operation(op);
diff --git a/fs/afs/internal.h b/fs/afs/internal.h
index b626e38e9ab5..5ed416f4ff33 100644
--- a/fs/afs/internal.h
+++ b/fs/afs/internal.h
@@ -14,6 +14,7 @@
#include <linux/key.h>
#include <linux/workqueue.h>
#include <linux/sched.h>
+#define FSCACHE_USE_NEW_IO_API
#include <linux/fscache.h>
#include <linux/backing-dev.h>
#include <linux/uuid.h>
@@ -31,6 +32,7 @@
struct pagevec;
struct afs_call;
+struct afs_vnode;
/*
* Partial file-locking emulation mode. (The problem being that AFS3 only
@@ -104,7 +106,9 @@ struct afs_call {
struct afs_server *server; /* The fileserver record if fs op (pins ref) */
struct afs_vlserver *vlserver; /* The vlserver record if vl op */
void *request; /* request data (first part) */
+ size_t iov_len; /* Size of *iter to be used */
struct iov_iter def_iter; /* Default buffer/data iterator */
+ struct iov_iter *write_iter; /* Iterator defining write to be made */
struct iov_iter *iter; /* Iterator currently in use */
union { /* Convenience for ->def_iter */
struct kvec kvec[1];
@@ -131,7 +135,6 @@ struct afs_call {
unsigned char unmarshall; /* unmarshalling phase */
unsigned char addr_ix; /* Address in ->alist */
bool drop_ref; /* T if need to drop ref for incoming call */
- bool send_pages; /* T if data from mapping should be sent */
bool need_attention; /* T if RxRPC poked us */
bool async; /* T if asynchronous */
bool upgrade; /* T to request service upgrade */
@@ -202,17 +205,19 @@ struct afs_read {
loff_t pos; /* Where to start reading */
loff_t len; /* How much we're asking for */
loff_t actual_len; /* How much we're actually getting */
- loff_t remain; /* Amount remaining */
loff_t file_size; /* File size returned by server */
+ struct key *key; /* The key to use to reissue the read */
+ struct afs_vnode *vnode; /* The file being read into. */
+ struct netfs_read_subrequest *subreq; /* Fscache helper read request this belongs to */
afs_dataversion_t data_version; /* Version number returned by server */
refcount_t usage;
- unsigned int index; /* Which page we're reading into */
+ unsigned int call_debug_id;
unsigned int nr_pages;
- unsigned int offset; /* offset into current page */
- struct afs_vnode *vnode;
- void (*page_done)(struct afs_read *);
- struct page **pages;
- struct page *array[];
+ int error;
+ void (*done)(struct afs_read *);
+ void (*cleanup)(struct afs_read *);
+ struct iov_iter *iter; /* Iterator representing the buffer */
+ struct iov_iter def_iter; /* Default iterator */
};
/*
@@ -640,6 +645,7 @@ struct afs_vnode {
#define AFS_VNODE_PSEUDODIR 7 /* set if Vnode is a pseudo directory */
#define AFS_VNODE_NEW_CONTENT 8 /* Set if file has new content (create/trunc-0) */
#define AFS_VNODE_SILLY_DELETED 9 /* Set if file has been silly-deleted */
+#define AFS_VNODE_MODIFYING 10 /* Set if we're performing a modification op */
struct list_head wb_keys; /* List of keys available for writeback */
struct list_head pending_locks; /* locks waiting to be granted */
@@ -739,6 +745,7 @@ struct afs_operation_ops {
void (*issue_yfs_rpc)(struct afs_operation *op);
void (*success)(struct afs_operation *op);
void (*aborted)(struct afs_operation *op);
+ void (*failed)(struct afs_operation *op);
void (*edit_dir)(struct afs_operation *op);
void (*put)(struct afs_operation *op);
};
@@ -756,6 +763,7 @@ struct afs_vnode_param {
bool set_size:1; /* Must update i_size */
bool op_unlinked:1; /* True if file was unlinked by op */
bool speculative:1; /* T if speculative status fetch (no vnode lock) */
+ bool modification:1; /* Set if the content gets modified */
};
/*
@@ -808,12 +816,11 @@ struct afs_operation {
afs_lock_type_t type;
} lock;
struct {
- struct address_space *mapping; /* Pages being written from */
- pgoff_t first; /* first page in mapping to deal with */
- pgoff_t last; /* last page in mapping to deal with */
- unsigned first_offset; /* offset into mapping[first] */
- unsigned last_to; /* amount of mapping[last] */
- bool laundering; /* Laundering page, PG_writeback not set */
+ struct iov_iter *write_iter;
+ loff_t pos;
+ loff_t size;
+ loff_t i_size;
+ bool laundering; /* Laundering page, PG_writeback not set */
} store;
struct {
struct iattr *attr;
@@ -875,31 +882,31 @@ struct afs_vnode_cache_aux {
#define __AFS_PAGE_PRIV_MMAPPED 0x8000UL
#endif
-static inline unsigned int afs_page_dirty_resolution(void)
+static inline unsigned int afs_page_dirty_resolution(struct page *page)
{
- int shift = PAGE_SHIFT - (__AFS_PAGE_PRIV_SHIFT - 1);
+ int shift = thp_order(page) + PAGE_SHIFT - (__AFS_PAGE_PRIV_SHIFT - 1);
return (shift > 0) ? shift : 0;
}
-static inline size_t afs_page_dirty_from(unsigned long priv)
+static inline size_t afs_page_dirty_from(struct page *page, unsigned long priv)
{
unsigned long x = priv & __AFS_PAGE_PRIV_MASK;
/* The lower bound is inclusive */
- return x << afs_page_dirty_resolution();
+ return x << afs_page_dirty_resolution(page);
}
-static inline size_t afs_page_dirty_to(unsigned long priv)
+static inline size_t afs_page_dirty_to(struct page *page, unsigned long priv)
{
unsigned long x = (priv >> __AFS_PAGE_PRIV_SHIFT) & __AFS_PAGE_PRIV_MASK;
/* The upper bound is immediately beyond the region */
- return (x + 1) << afs_page_dirty_resolution();
+ return (x + 1) << afs_page_dirty_resolution(page);
}
-static inline unsigned long afs_page_dirty(size_t from, size_t to)
+static inline unsigned long afs_page_dirty(struct page *page, size_t from, size_t to)
{
- unsigned int res = afs_page_dirty_resolution();
+ unsigned int res = afs_page_dirty_resolution(page);
from >>= res;
to = (to - 1) >> res;
return (to << __AFS_PAGE_PRIV_SHIFT) | from;
@@ -1040,13 +1047,14 @@ extern void afs_dynroot_depopulate(struct super_block *);
extern const struct address_space_operations afs_fs_aops;
extern const struct inode_operations afs_file_inode_operations;
extern const struct file_operations afs_file_operations;
+extern const struct netfs_read_request_ops afs_req_ops;
extern int afs_cache_wb_key(struct afs_vnode *, struct afs_file *);
extern void afs_put_wb_key(struct afs_wb_key *);
extern int afs_open(struct inode *, struct file *);
extern int afs_release(struct inode *, struct file *);
-extern int afs_fetch_data(struct afs_vnode *, struct key *, struct afs_read *);
-extern int afs_page_filler(void *, struct page *);
+extern int afs_fetch_data(struct afs_vnode *, struct afs_read *);
+extern struct afs_read *afs_alloc_read(gfp_t);
extern void afs_put_read(struct afs_read *);
static inline struct afs_read *afs_get_read(struct afs_read *req)
@@ -1270,6 +1278,7 @@ static inline void afs_make_op_call(struct afs_operation *op, struct afs_call *c
static inline void afs_extract_begin(struct afs_call *call, void *buf, size_t size)
{
+ call->iov_len = size;
call->kvec[0].iov_base = buf;
call->kvec[0].iov_len = size;
iov_iter_kvec(&call->def_iter, READ, call->kvec, 1, size);
@@ -1277,21 +1286,25 @@ static inline void afs_extract_begin(struct afs_call *call, void *buf, size_t si
static inline void afs_extract_to_tmp(struct afs_call *call)
{
+ call->iov_len = sizeof(call->tmp);
afs_extract_begin(call, &call->tmp, sizeof(call->tmp));
}
static inline void afs_extract_to_tmp64(struct afs_call *call)
{
+ call->iov_len = sizeof(call->tmp64);
afs_extract_begin(call, &call->tmp64, sizeof(call->tmp64));
}
static inline void afs_extract_discard(struct afs_call *call, size_t size)
{
+ call->iov_len = size;
iov_iter_discard(&call->def_iter, READ, size);
}
static inline void afs_extract_to_buf(struct afs_call *call, size_t size)
{
+ call->iov_len = size;
afs_extract_begin(call, call->buffer, size);
}
@@ -1509,7 +1522,6 @@ extern int afs_launder_page(struct page *);
* xattr.c
*/
extern const struct xattr_handler *afs_xattr_handlers[];
-extern ssize_t afs_listxattr(struct dentry *, char *, size_t);
/*
* yfsclient.c
diff --git a/fs/afs/mntpt.c b/fs/afs/mntpt.c
index 052dab2f5c03..bbb2c210d139 100644
--- a/fs/afs/mntpt.c
+++ b/fs/afs/mntpt.c
@@ -32,7 +32,6 @@ const struct inode_operations afs_mntpt_inode_operations = {
.lookup = afs_mntpt_lookup,
.readlink = page_readlink,
.getattr = afs_getattr,
- .listxattr = afs_listxattr,
};
const struct inode_operations afs_autocell_inode_operations = {
diff --git a/fs/afs/rxrpc.c b/fs/afs/rxrpc.c
index 8be709cb8542..23a1a92d64bb 100644
--- a/fs/afs/rxrpc.c
+++ b/fs/afs/rxrpc.c
@@ -271,40 +271,6 @@ void afs_flat_call_destructor(struct afs_call *call)
call->buffer = NULL;
}
-#define AFS_BVEC_MAX 8
-
-/*
- * Load the given bvec with the next few pages.
- */
-static void afs_load_bvec(struct afs_call *call, struct msghdr *msg,
- struct bio_vec *bv, pgoff_t first, pgoff_t last,
- unsigned offset)
-{
- struct afs_operation *op = call->op;
- struct page *pages[AFS_BVEC_MAX];
- unsigned int nr, n, i, to, bytes = 0;
-
- nr = min_t(pgoff_t, last - first + 1, AFS_BVEC_MAX);
- n = find_get_pages_contig(op->store.mapping, first, nr, pages);
- ASSERTCMP(n, ==, nr);
-
- msg->msg_flags |= MSG_MORE;
- for (i = 0; i < nr; i++) {
- to = PAGE_SIZE;
- if (first + i >= last) {
- to = op->store.last_to;
- msg->msg_flags &= ~MSG_MORE;
- }
- bv[i].bv_page = pages[i];
- bv[i].bv_len = to - offset;
- bv[i].bv_offset = offset;
- bytes += to - offset;
- offset = 0;
- }
-
- iov_iter_bvec(&msg->msg_iter, WRITE, bv, nr, bytes);
-}
-
/*
* Advance the AFS call state when the RxRPC call ends the transmit phase.
*/
@@ -318,42 +284,6 @@ static void afs_notify_end_request_tx(struct sock *sock,
}
/*
- * attach the data from a bunch of pages on an inode to a call
- */
-static int afs_send_pages(struct afs_call *call, struct msghdr *msg)
-{
- struct afs_operation *op = call->op;
- struct bio_vec bv[AFS_BVEC_MAX];
- unsigned int bytes, nr, loop, offset;
- pgoff_t first = op->store.first, last = op->store.last;
- int ret;
-
- offset = op->store.first_offset;
- op->store.first_offset = 0;
-
- do {
- afs_load_bvec(call, msg, bv, first, last, offset);
- trace_afs_send_pages(call, msg, first, last, offset);
-
- offset = 0;
- bytes = msg->msg_iter.count;
- nr = msg->msg_iter.nr_segs;
-
- ret = rxrpc_kernel_send_data(op->net->socket, call->rxcall, msg,
- bytes, afs_notify_end_request_tx);
- for (loop = 0; loop < nr; loop++)
- put_page(bv[loop].bv_page);
- if (ret < 0)
- break;
-
- first += nr;
- } while (first <= last);
-
- trace_afs_sent_pages(call, op->store.first, last, first, ret);
- return ret;
-}
-
-/*
* Initiate a call and synchronously queue up the parameters for dispatch. Any
* error is stored into the call struct, which the caller must check for.
*/
@@ -363,6 +293,7 @@ void afs_make_call(struct afs_addr_cursor *ac, struct afs_call *call, gfp_t gfp)
struct rxrpc_call *rxcall;
struct msghdr msg;
struct kvec iov[1];
+ size_t len;
s64 tx_total_len;
int ret;
@@ -383,21 +314,8 @@ void afs_make_call(struct afs_addr_cursor *ac, struct afs_call *call, gfp_t gfp)
* after the initial fixed part.
*/
tx_total_len = call->request_size;
- if (call->send_pages) {
- struct afs_operation *op = call->op;
-
- if (op->store.last == op->store.first) {
- tx_total_len += op->store.last_to - op->store.first_offset;
- } else {
- /* It looks mathematically like you should be able to
- * combine the following lines with the ones above, but
- * unsigned arithmetic is fun when it wraps...
- */
- tx_total_len += PAGE_SIZE - op->store.first_offset;
- tx_total_len += op->store.last_to;
- tx_total_len += (op->store.last - op->store.first - 1) * PAGE_SIZE;
- }
- }
+ if (call->write_iter)
+ tx_total_len += iov_iter_count(call->write_iter);
/* If the call is going to be asynchronous, we need an extra ref for
* the call to hold itself so the caller need not hang on to its ref.
@@ -439,7 +357,7 @@ void afs_make_call(struct afs_addr_cursor *ac, struct afs_call *call, gfp_t gfp)
iov_iter_kvec(&msg.msg_iter, WRITE, iov, 1, call->request_size);
msg.msg_control = NULL;
msg.msg_controllen = 0;
- msg.msg_flags = MSG_WAITALL | (call->send_pages ? MSG_MORE : 0);
+ msg.msg_flags = MSG_WAITALL | (call->write_iter ? MSG_MORE : 0);
ret = rxrpc_kernel_send_data(call->net->socket, rxcall,
&msg, call->request_size,
@@ -447,8 +365,18 @@ void afs_make_call(struct afs_addr_cursor *ac, struct afs_call *call, gfp_t gfp)
if (ret < 0)
goto error_do_abort;
- if (call->send_pages) {
- ret = afs_send_pages(call, &msg);
+ if (call->write_iter) {
+ msg.msg_iter = *call->write_iter;
+ msg.msg_flags &= ~MSG_MORE;
+ trace_afs_send_data(call, &msg);
+
+ ret = rxrpc_kernel_send_data(call->net->socket,
+ call->rxcall, &msg,
+ iov_iter_count(&msg.msg_iter),
+ afs_notify_end_request_tx);
+ *call->write_iter = msg.msg_iter;
+
+ trace_afs_sent_data(call, &msg, ret);
if (ret < 0)
goto error_do_abort;
}
@@ -466,9 +394,10 @@ error_do_abort:
rxrpc_kernel_abort_call(call->net->socket, rxcall,
RX_USER_ABORT, ret, "KSD");
} else {
+ len = 0;
iov_iter_kvec(&msg.msg_iter, READ, NULL, 0, 0);
rxrpc_kernel_recv_data(call->net->socket, rxcall,
- &msg.msg_iter, false,
+ &msg.msg_iter, &len, false,
&call->abort_code, &call->service_id);
ac->abort_code = call->abort_code;
ac->responded = true;
@@ -499,11 +428,45 @@ error_kill_call:
}
/*
+ * Log remote abort codes that indicate that we have a protocol disagreement
+ * with the server.
+ */
+static void afs_log_error(struct afs_call *call, s32 remote_abort)
+{
+ static int max = 0;
+ const char *msg;
+ int m;
+
+ switch (remote_abort) {
+ case RX_EOF: msg = "unexpected EOF"; break;
+ case RXGEN_CC_MARSHAL: msg = "client marshalling"; break;
+ case RXGEN_CC_UNMARSHAL: msg = "client unmarshalling"; break;
+ case RXGEN_SS_MARSHAL: msg = "server marshalling"; break;
+ case RXGEN_SS_UNMARSHAL: msg = "server unmarshalling"; break;
+ case RXGEN_DECODE: msg = "opcode decode"; break;
+ case RXGEN_SS_XDRFREE: msg = "server XDR cleanup"; break;
+ case RXGEN_CC_XDRFREE: msg = "client XDR cleanup"; break;
+ case -32: msg = "insufficient data"; break;
+ default:
+ return;
+ }
+
+ m = max;
+ if (m < 3) {
+ max = m + 1;
+ pr_notice("kAFS: Peer reported %s failure on %s [%pISp]\n",
+ msg, call->type->name,
+ &call->alist->addrs[call->addr_ix].transport);
+ }
+}
+
+/*
* deliver messages to a call
*/
static void afs_deliver_to_call(struct afs_call *call)
{
enum afs_call_state state;
+ size_t len;
u32 abort_code, remote_abort = 0;
int ret;
@@ -516,10 +479,11 @@ static void afs_deliver_to_call(struct afs_call *call)
state == AFS_CALL_SV_AWAIT_ACK
) {
if (state == AFS_CALL_SV_AWAIT_ACK) {
+ len = 0;
iov_iter_kvec(&call->def_iter, READ, NULL, 0, 0);
ret = rxrpc_kernel_recv_data(call->net->socket,
call->rxcall, &call->def_iter,
- false, &remote_abort,
+ &len, false, &remote_abort,
&call->service_id);
trace_afs_receive_data(call, &call->def_iter, false, ret);
@@ -559,6 +523,7 @@ static void afs_deliver_to_call(struct afs_call *call)
goto out;
case -ECONNABORTED:
ASSERTCMP(state, ==, AFS_CALL_COMPLETE);
+ afs_log_error(call, call->abort_code);
goto done;
case -ENOTSUPP:
abort_code = RXGEN_OPCODE;
@@ -929,10 +894,11 @@ int afs_extract_data(struct afs_call *call, bool want_more)
u32 remote_abort = 0;
int ret;
- _enter("{%s,%zu},%d", call->type->name, iov_iter_count(iter), want_more);
+ _enter("{%s,%zu,%zu},%d",
+ call->type->name, call->iov_len, iov_iter_count(iter), want_more);
ret = rxrpc_kernel_recv_data(net->socket, call->rxcall, iter,
- want_more, &remote_abort,
+ &call->iov_len, want_more, &remote_abort,
&call->service_id);
if (ret == 0 || ret == -EAGAIN)
return ret;
diff --git a/fs/afs/write.c b/fs/afs/write.c
index c9195fc67fd8..3edb6204b937 100644
--- a/fs/afs/write.c
+++ b/fs/afs/write.c
@@ -11,6 +11,8 @@
#include <linux/pagemap.h>
#include <linux/writeback.h>
#include <linux/pagevec.h>
+#include <linux/netfs.h>
+#include <linux/fscache.h>
#include "internal.h"
/*
@@ -23,55 +25,6 @@ int afs_set_page_dirty(struct page *page)
}
/*
- * partly or wholly fill a page that's under preparation for writing
- */
-static int afs_fill_page(struct afs_vnode *vnode, struct key *key,
- loff_t pos, unsigned int len, struct page *page)
-{
- struct afs_read *req;
- size_t p;
- void *data;
- int ret;
-
- _enter(",,%llu", (unsigned long long)pos);
-
- if (pos >= vnode->vfs_inode.i_size) {
- p = pos & ~PAGE_MASK;
- ASSERTCMP(p + len, <=, PAGE_SIZE);
- data = kmap(page);
- memset(data + p, 0, len);
- kunmap(page);
- return 0;
- }
-
- req = kzalloc(struct_size(req, array, 1), GFP_KERNEL);
- if (!req)
- return -ENOMEM;
-
- refcount_set(&req->usage, 1);
- req->pos = pos;
- req->len = len;
- req->nr_pages = 1;
- req->pages = req->array;
- req->pages[0] = page;
- get_page(page);
-
- ret = afs_fetch_data(vnode, key, req);
- afs_put_read(req);
- if (ret < 0) {
- if (ret == -ENOENT) {
- _debug("got NOENT from server"
- " - marking file deleted and stale");
- set_bit(AFS_VNODE_DELETED, &vnode->flags);
- ret = -ESTALE;
- }
- }
-
- _leave(" = %d", ret);
- return ret;
-}
-
-/*
* prepare to perform part of a write to a page
*/
int afs_write_begin(struct file *file, struct address_space *mapping,
@@ -80,47 +33,40 @@ int afs_write_begin(struct file *file, struct address_space *mapping,
{
struct afs_vnode *vnode = AFS_FS_I(file_inode(file));
struct page *page;
- struct key *key = afs_file_key(file);
unsigned long priv;
- unsigned f, from = pos & (PAGE_SIZE - 1);
- unsigned t, to = from + len;
- pgoff_t index = pos >> PAGE_SHIFT;
+ unsigned f, from;
+ unsigned t, to;
+ pgoff_t index;
int ret;
- _enter("{%llx:%llu},{%lx},%u,%u",
- vnode->fid.vid, vnode->fid.vnode, index, from, to);
+ _enter("{%llx:%llu},%llx,%x",
+ vnode->fid.vid, vnode->fid.vnode, pos, len);
- page = grab_cache_page_write_begin(mapping, index, flags);
- if (!page)
- return -ENOMEM;
+ /* Prefetch area to be written into the cache if we're caching this
+ * file. We need to do this before we get a lock on the page in case
+ * there's more than one writer competing for the same cache block.
+ */
+ ret = netfs_write_begin(file, mapping, pos, len, flags, &page, fsdata,
+ &afs_req_ops, NULL);
+ if (ret < 0)
+ return ret;
- if (!PageUptodate(page) && len != PAGE_SIZE) {
- ret = afs_fill_page(vnode, key, pos & PAGE_MASK, PAGE_SIZE, page);
- if (ret < 0) {
- unlock_page(page);
- put_page(page);
- _leave(" = %d [prep]", ret);
- return ret;
- }
- SetPageUptodate(page);
- }
+ index = page->index;
+ from = pos - index * PAGE_SIZE;
+ to = from + len;
try_again:
/* See if this page is already partially written in a way that we can
* merge the new write with.
*/
- t = f = 0;
if (PagePrivate(page)) {
priv = page_private(page);
- f = afs_page_dirty_from(priv);
- t = afs_page_dirty_to(priv);
+ f = afs_page_dirty_from(page, priv);
+ t = afs_page_dirty_to(page, priv);
ASSERTCMP(f, <=, t);
- }
- if (f != t) {
if (PageWriteback(page)) {
- trace_afs_page_dirty(vnode, tracepoint_string("alrdy"),
- page->index, priv);
+ trace_afs_page_dirty(vnode, tracepoint_string("alrdy"), page);
goto flush_conflicting_write;
}
/* If the file is being filled locally, allow inter-write
@@ -164,12 +110,10 @@ int afs_write_end(struct file *file, struct address_space *mapping,
struct page *page, void *fsdata)
{
struct afs_vnode *vnode = AFS_FS_I(file_inode(file));
- struct key *key = afs_file_key(file);
unsigned long priv;
- unsigned int f, from = pos & (PAGE_SIZE - 1);
+ unsigned int f, from = pos & (thp_size(page) - 1);
unsigned int t, to = from + copied;
loff_t i_size, maybe_i_size;
- int ret = 0;
_enter("{%llx:%llu},{%lx}",
vnode->fid.vid, vnode->fid.vnode, page->index);
@@ -188,88 +132,75 @@ int afs_write_end(struct file *file, struct address_space *mapping,
write_sequnlock(&vnode->cb_lock);
}
- if (!PageUptodate(page)) {
- if (copied < len) {
- /* Try and load any missing data from the server. The
- * unmarshalling routine will take care of clearing any
- * bits that are beyond the EOF.
- */
- ret = afs_fill_page(vnode, key, pos + copied,
- len - copied, page);
- if (ret < 0)
- goto out;
- }
- SetPageUptodate(page);
- }
+ ASSERT(PageUptodate(page));
if (PagePrivate(page)) {
priv = page_private(page);
- f = afs_page_dirty_from(priv);
- t = afs_page_dirty_to(priv);
+ f = afs_page_dirty_from(page, priv);
+ t = afs_page_dirty_to(page, priv);
if (from < f)
f = from;
if (to > t)
t = to;
- priv = afs_page_dirty(f, t);
+ priv = afs_page_dirty(page, f, t);
set_page_private(page, priv);
- trace_afs_page_dirty(vnode, tracepoint_string("dirty+"),
- page->index, priv);
+ trace_afs_page_dirty(vnode, tracepoint_string("dirty+"), page);
} else {
- priv = afs_page_dirty(from, to);
+ priv = afs_page_dirty(page, from, to);
attach_page_private(page, (void *)priv);
- trace_afs_page_dirty(vnode, tracepoint_string("dirty"),
- page->index, priv);
+ trace_afs_page_dirty(vnode, tracepoint_string("dirty"), page);
}
- set_page_dirty(page);
- if (PageDirty(page))
- _debug("dirtied");
- ret = copied;
+ if (set_page_dirty(page))
+ _debug("dirtied %lx", page->index);
out:
unlock_page(page);
put_page(page);
- return ret;
+ return copied;
}
/*
* kill all the pages in the given range
*/
static void afs_kill_pages(struct address_space *mapping,
- pgoff_t first, pgoff_t last)
+ loff_t start, loff_t len)
{
struct afs_vnode *vnode = AFS_FS_I(mapping->host);
struct pagevec pv;
- unsigned count, loop;
+ unsigned int loop, psize;
- _enter("{%llx:%llu},%lx-%lx",
- vnode->fid.vid, vnode->fid.vnode, first, last);
+ _enter("{%llx:%llu},%llx @%llx",
+ vnode->fid.vid, vnode->fid.vnode, len, start);
pagevec_init(&pv);
do {
- _debug("kill %lx-%lx", first, last);
+ _debug("kill %llx @%llx", len, start);
- count = last - first + 1;
- if (count > PAGEVEC_SIZE)
- count = PAGEVEC_SIZE;
- pv.nr = find_get_pages_contig(mapping, first, count, pv.pages);
- ASSERTCMP(pv.nr, ==, count);
+ pv.nr = find_get_pages_contig(mapping, start / PAGE_SIZE,
+ PAGEVEC_SIZE, pv.pages);
+ if (pv.nr == 0)
+ break;
- for (loop = 0; loop < count; loop++) {
+ for (loop = 0; loop < pv.nr; loop++) {
struct page *page = pv.pages[loop];
+
+ if (page->index * PAGE_SIZE >= start + len)
+ break;
+
+ psize = thp_size(page);
+ start += psize;
+ len -= psize;
ClearPageUptodate(page);
- SetPageError(page);
end_page_writeback(page);
- if (page->index >= first)
- first = page->index + 1;
lock_page(page);
generic_error_remove_page(mapping, page);
unlock_page(page);
}
__pagevec_release(&pv);
- } while (first <= last);
+ } while (len > 0);
_leave("");
}
@@ -279,37 +210,40 @@ static void afs_kill_pages(struct address_space *mapping,
*/
static void afs_redirty_pages(struct writeback_control *wbc,
struct address_space *mapping,
- pgoff_t first, pgoff_t last)
+ loff_t start, loff_t len)
{
struct afs_vnode *vnode = AFS_FS_I(mapping->host);
struct pagevec pv;
- unsigned count, loop;
+ unsigned int loop, psize;
- _enter("{%llx:%llu},%lx-%lx",
- vnode->fid.vid, vnode->fid.vnode, first, last);
+ _enter("{%llx:%llu},%llx @%llx",
+ vnode->fid.vid, vnode->fid.vnode, len, start);
pagevec_init(&pv);
do {
- _debug("redirty %lx-%lx", first, last);
+ _debug("redirty %llx @%llx", len, start);
- count = last - first + 1;
- if (count > PAGEVEC_SIZE)
- count = PAGEVEC_SIZE;
- pv.nr = find_get_pages_contig(mapping, first, count, pv.pages);
- ASSERTCMP(pv.nr, ==, count);
+ pv.nr = find_get_pages_contig(mapping, start / PAGE_SIZE,
+ PAGEVEC_SIZE, pv.pages);
+ if (pv.nr == 0)
+ break;
- for (loop = 0; loop < count; loop++) {
+ for (loop = 0; loop < pv.nr; loop++) {
struct page *page = pv.pages[loop];
+ if (page->index * PAGE_SIZE >= start + len)
+ break;
+
+ psize = thp_size(page);
+ start += psize;
+ len -= psize;
redirty_page_for_writepage(wbc, page);
end_page_writeback(page);
- if (page->index >= first)
- first = page->index + 1;
}
__pagevec_release(&pv);
- } while (first <= last);
+ } while (len > 0);
_leave("");
}
@@ -317,37 +251,32 @@ static void afs_redirty_pages(struct writeback_control *wbc,
/*
* completion of write to server
*/
-static void afs_pages_written_back(struct afs_vnode *vnode,
- pgoff_t first, pgoff_t last)
+static void afs_pages_written_back(struct afs_vnode *vnode, loff_t start, unsigned int len)
{
- struct pagevec pv;
- unsigned long priv;
- unsigned count, loop;
+ struct address_space *mapping = vnode->vfs_inode.i_mapping;
+ struct page *page;
+ pgoff_t end;
- _enter("{%llx:%llu},{%lx-%lx}",
- vnode->fid.vid, vnode->fid.vnode, first, last);
+ XA_STATE(xas, &mapping->i_pages, start / PAGE_SIZE);
- pagevec_init(&pv);
+ _enter("{%llx:%llu},{%x @%llx}",
+ vnode->fid.vid, vnode->fid.vnode, len, start);
- do {
- _debug("done %lx-%lx", first, last);
-
- count = last - first + 1;
- if (count > PAGEVEC_SIZE)
- count = PAGEVEC_SIZE;
- pv.nr = find_get_pages_contig(vnode->vfs_inode.i_mapping,
- first, count, pv.pages);
- ASSERTCMP(pv.nr, ==, count);
-
- for (loop = 0; loop < count; loop++) {
- priv = (unsigned long)detach_page_private(pv.pages[loop]);
- trace_afs_page_dirty(vnode, tracepoint_string("clear"),
- pv.pages[loop]->index, priv);
- end_page_writeback(pv.pages[loop]);
+ rcu_read_lock();
+
+ end = (start + len - 1) / PAGE_SIZE;
+ xas_for_each(&xas, page, end) {
+ if (!PageWriteback(page)) {
+ kdebug("bad %x @%llx page %lx %lx", len, start, page->index, end);
+ ASSERT(PageWriteback(page));
}
- first += count;
- __pagevec_release(&pv);
- } while (first <= last);
+
+ trace_afs_page_dirty(vnode, tracepoint_string("clear"), page);
+ detach_page_private(page);
+ page_endio(page, true, 0);
+ }
+
+ rcu_read_unlock();
afs_prune_wb_keys(vnode);
_leave("");
@@ -402,11 +331,9 @@ static void afs_store_data_success(struct afs_operation *op)
afs_vnode_commit_status(op, &op->file[0]);
if (op->error == 0) {
if (!op->store.laundering)
- afs_pages_written_back(vnode, op->store.first, op->store.last);
+ afs_pages_written_back(vnode, op->store.pos, op->store.size);
afs_stat_v(vnode, n_stores);
- atomic_long_add((op->store.last * PAGE_SIZE + op->store.last_to) -
- (op->store.first * PAGE_SIZE + op->store.first_offset),
- &afs_v2net(vnode)->n_store_bytes);
+ atomic_long_add(op->store.size, &afs_v2net(vnode)->n_store_bytes);
}
}
@@ -419,21 +346,20 @@ static const struct afs_operation_ops afs_store_data_operation = {
/*
* write to a file
*/
-static int afs_store_data(struct address_space *mapping,
- pgoff_t first, pgoff_t last,
- unsigned offset, unsigned to, bool laundering)
+static int afs_store_data(struct afs_vnode *vnode, struct iov_iter *iter, loff_t pos,
+ bool laundering)
{
- struct afs_vnode *vnode = AFS_FS_I(mapping->host);
struct afs_operation *op;
struct afs_wb_key *wbk = NULL;
- int ret;
+ loff_t size = iov_iter_count(iter), i_size;
+ int ret = -ENOKEY;
- _enter("%s{%llx:%llu.%u},%lx,%lx,%x,%x",
+ _enter("%s{%llx:%llu.%u},%llx,%llx",
vnode->volume->name,
vnode->fid.vid,
vnode->fid.vnode,
vnode->fid.unique,
- first, last, offset, to);
+ size, pos);
ret = afs_get_writeback_key(vnode, &wbk);
if (ret) {
@@ -447,13 +373,15 @@ static int afs_store_data(struct address_space *mapping,
return -ENOMEM;
}
+ i_size = i_size_read(&vnode->vfs_inode);
+
afs_op_set_vnode(op, 0, vnode);
op->file[0].dv_delta = 1;
- op->store.mapping = mapping;
- op->store.first = first;
- op->store.last = last;
- op->store.first_offset = offset;
- op->store.last_to = to;
+ op->file[0].modification = true;
+ op->store.write_iter = iter;
+ op->store.pos = pos;
+ op->store.size = size;
+ op->store.i_size = max(pos + size, i_size);
op->store.laundering = laundering;
op->mtime = vnode->vfs_inode.i_mtime;
op->flags |= AFS_OPERATION_UNINTR;
@@ -487,73 +415,58 @@ try_next_key:
}
/*
- * Synchronously write back the locked page and any subsequent non-locked dirty
- * pages.
+ * Extend the region to be written back to include subsequent contiguously
+ * dirty pages if possible, but don't sleep while doing so.
+ *
+ * If this page holds new content, then we can include filler zeros in the
+ * writeback.
*/
-static int afs_write_back_from_locked_page(struct address_space *mapping,
- struct writeback_control *wbc,
- struct page *primary_page,
- pgoff_t final_page)
+static void afs_extend_writeback(struct address_space *mapping,
+ struct afs_vnode *vnode,
+ long *_count,
+ loff_t start,
+ loff_t max_len,
+ bool new_content,
+ unsigned int *_len)
{
- struct afs_vnode *vnode = AFS_FS_I(mapping->host);
- struct page *pages[8], *page;
- unsigned long count, priv;
- unsigned n, offset, to, f, t;
- pgoff_t start, first, last;
- loff_t i_size, end;
- int loop, ret;
-
- _enter(",%lx", primary_page->index);
+ struct pagevec pvec;
+ struct page *page;
+ unsigned long priv;
+ unsigned int psize, filler = 0;
+ unsigned int f, t;
+ loff_t len = *_len;
+ pgoff_t index = (start + len) / PAGE_SIZE;
+ bool stop = true;
+ unsigned int i;
- count = 1;
- if (test_set_page_writeback(primary_page))
- BUG();
+ XA_STATE(xas, &mapping->i_pages, index);
+ pagevec_init(&pvec);
- /* Find all consecutive lockable dirty pages that have contiguous
- * written regions, stopping when we find a page that is not
- * immediately lockable, is not dirty or is missing, or we reach the
- * end of the range.
- */
- start = primary_page->index;
- priv = page_private(primary_page);
- offset = afs_page_dirty_from(priv);
- to = afs_page_dirty_to(priv);
- trace_afs_page_dirty(vnode, tracepoint_string("store"),
- primary_page->index, priv);
-
- WARN_ON(offset == to);
- if (offset == to)
- trace_afs_page_dirty(vnode, tracepoint_string("WARN"),
- primary_page->index, priv);
-
- if (start >= final_page ||
- (to < PAGE_SIZE && !test_bit(AFS_VNODE_NEW_CONTENT, &vnode->flags)))
- goto no_more;
-
- start++;
do {
- _debug("more %lx [%lx]", start, count);
- n = final_page - start + 1;
- if (n > ARRAY_SIZE(pages))
- n = ARRAY_SIZE(pages);
- n = find_get_pages_contig(mapping, start, ARRAY_SIZE(pages), pages);
- _debug("fgpc %u", n);
- if (n == 0)
- goto no_more;
- if (pages[0]->index != start) {
- do {
- put_page(pages[--n]);
- } while (n > 0);
- goto no_more;
- }
+ /* Firstly, we gather up a batch of contiguous dirty pages
+ * under the RCU read lock - but we can't clear the dirty flags
+ * there if any of those pages are mapped.
+ */
+ rcu_read_lock();
- for (loop = 0; loop < n; loop++) {
- page = pages[loop];
- if (to != PAGE_SIZE &&
- !test_bit(AFS_VNODE_NEW_CONTENT, &vnode->flags))
+ xas_for_each(&xas, page, ULONG_MAX) {
+ stop = true;
+ if (xas_retry(&xas, page))
+ continue;
+ if (xa_is_value(page))
break;
- if (page->index > final_page)
+ if (page->index != index)
break;
+
+ if (!page_cache_get_speculative(page)) {
+ xas_reset(&xas);
+ continue;
+ }
+
+ /* Has the page moved or been split? */
+ if (unlikely(page != xas_reload(&xas)))
+ break;
+
if (!trylock_page(page))
break;
if (!PageDirty(page) || PageWriteback(page)) {
@@ -561,57 +474,134 @@ static int afs_write_back_from_locked_page(struct address_space *mapping,
break;
}
+ psize = thp_size(page);
priv = page_private(page);
- f = afs_page_dirty_from(priv);
- t = afs_page_dirty_to(priv);
- if (f != 0 &&
- !test_bit(AFS_VNODE_NEW_CONTENT, &vnode->flags)) {
+ f = afs_page_dirty_from(page, priv);
+ t = afs_page_dirty_to(page, priv);
+ if (f != 0 && !new_content) {
unlock_page(page);
break;
}
- to = t;
- trace_afs_page_dirty(vnode, tracepoint_string("store+"),
- page->index, priv);
+ len += filler + t;
+ filler = psize - t;
+ if (len >= max_len || *_count <= 0)
+ stop = true;
+ else if (t == psize || new_content)
+ stop = false;
+
+ index += thp_nr_pages(page);
+ if (!pagevec_add(&pvec, page))
+ break;
+ if (stop)
+ break;
+ }
+
+ if (!stop)
+ xas_pause(&xas);
+ rcu_read_unlock();
+
+ /* Now, if we obtained any pages, we can shift them to being
+ * writable and mark them for caching.
+ */
+ if (!pagevec_count(&pvec))
+ break;
+
+ for (i = 0; i < pagevec_count(&pvec); i++) {
+ page = pvec.pages[i];
+ trace_afs_page_dirty(vnode, tracepoint_string("store+"), page);
if (!clear_page_dirty_for_io(page))
BUG();
if (test_set_page_writeback(page))
BUG();
+
+ *_count -= thp_nr_pages(page);
unlock_page(page);
- put_page(page);
- }
- count += loop;
- if (loop < n) {
- for (; loop < n; loop++)
- put_page(pages[loop]);
- goto no_more;
}
- start += loop;
- } while (start <= final_page && count < 65536);
+ pagevec_release(&pvec);
+ cond_resched();
+ } while (!stop);
+
+ *_len = len;
+}
+
+/*
+ * Synchronously write back the locked page and any subsequent non-locked dirty
+ * pages.
+ */
+static ssize_t afs_write_back_from_locked_page(struct address_space *mapping,
+ struct writeback_control *wbc,
+ struct page *page,
+ loff_t start, loff_t end)
+{
+ struct afs_vnode *vnode = AFS_FS_I(mapping->host);
+ struct iov_iter iter;
+ unsigned long priv;
+ unsigned int offset, to, len, max_len;
+ loff_t i_size = i_size_read(&vnode->vfs_inode);
+ bool new_content = test_bit(AFS_VNODE_NEW_CONTENT, &vnode->flags);
+ long count = wbc->nr_to_write;
+ int ret;
+
+ _enter(",%lx,%llx-%llx", page->index, start, end);
+
+ if (test_set_page_writeback(page))
+ BUG();
+
+ count -= thp_nr_pages(page);
+
+ /* Find all consecutive lockable dirty pages that have contiguous
+ * written regions, stopping when we find a page that is not
+ * immediately lockable, is not dirty or is missing, or we reach the
+ * end of the range.
+ */
+ priv = page_private(page);
+ offset = afs_page_dirty_from(page, priv);
+ to = afs_page_dirty_to(page, priv);
+ trace_afs_page_dirty(vnode, tracepoint_string("store"), page);
+
+ len = to - offset;
+ start += offset;
+ if (start < i_size) {
+ /* Trim the write to the EOF; the extra data is ignored. Also
+ * put an upper limit on the size of a single storedata op.
+ */
+ max_len = 65536 * 4096;
+ max_len = min_t(unsigned long long, max_len, end - start + 1);
+ max_len = min_t(unsigned long long, max_len, i_size - start);
+
+ if (len < max_len &&
+ (to == thp_size(page) || new_content))
+ afs_extend_writeback(mapping, vnode, &count,
+ start, max_len, new_content, &len);
+ len = min_t(loff_t, len, max_len);
+ }
-no_more:
/* We now have a contiguous set of dirty pages, each with writeback
* set; the first page is still locked at this point, but all the rest
* have been unlocked.
*/
- unlock_page(primary_page);
+ unlock_page(page);
- first = primary_page->index;
- last = first + count - 1;
+ if (start < i_size) {
+ _debug("write back %x @%llx [%llx]", len, start, i_size);
- end = (loff_t)last * PAGE_SIZE + to;
- i_size = i_size_read(&vnode->vfs_inode);
+ iov_iter_xarray(&iter, WRITE, &mapping->i_pages, start, len);
+ ret = afs_store_data(vnode, &iter, start, false);
+ } else {
+ _debug("write discard %x @%llx [%llx]", len, start, i_size);
- _debug("write back %lx[%u..] to %lx[..%u]", first, offset, last, to);
- if (end > i_size)
- to = i_size & ~PAGE_MASK;
+ /* The dirty region was entirely beyond the EOF. */
+ afs_pages_written_back(vnode, start, len);
+ ret = 0;
+ }
- ret = afs_store_data(mapping, first, last, offset, to, false);
switch (ret) {
case 0:
- ret = count;
+ wbc->nr_to_write = count;
+ ret = len;
break;
default:
@@ -623,13 +613,13 @@ no_more:
case -EKEYEXPIRED:
case -EKEYREJECTED:
case -EKEYREVOKED:
- afs_redirty_pages(wbc, mapping, first, last);
+ afs_redirty_pages(wbc, mapping, start, len);
mapping_set_error(mapping, ret);
break;
case -EDQUOT:
case -ENOSPC:
- afs_redirty_pages(wbc, mapping, first, last);
+ afs_redirty_pages(wbc, mapping, start, len);
mapping_set_error(mapping, -ENOSPC);
break;
@@ -641,7 +631,7 @@ no_more:
case -ENOMEDIUM:
case -ENXIO:
trace_afs_file_error(vnode, ret, afs_file_error_writeback_fail);
- afs_kill_pages(mapping, first, last);
+ afs_kill_pages(mapping, start, len);
mapping_set_error(mapping, ret);
break;
}
@@ -656,19 +646,19 @@ no_more:
*/
int afs_writepage(struct page *page, struct writeback_control *wbc)
{
- int ret;
+ ssize_t ret;
+ loff_t start;
_enter("{%lx},", page->index);
+ start = page->index * PAGE_SIZE;
ret = afs_write_back_from_locked_page(page->mapping, wbc, page,
- wbc->range_end >> PAGE_SHIFT);
+ start, LLONG_MAX - start);
if (ret < 0) {
- _leave(" = %d", ret);
- return 0;
+ _leave(" = %zd", ret);
+ return ret;
}
- wbc->nr_to_write -= ret;
-
_leave(" = 0");
return 0;
}
@@ -678,35 +668,46 @@ int afs_writepage(struct page *page, struct writeback_control *wbc)
*/
static int afs_writepages_region(struct address_space *mapping,
struct writeback_control *wbc,
- pgoff_t index, pgoff_t end, pgoff_t *_next)
+ loff_t start, loff_t end, loff_t *_next)
{
struct page *page;
- int ret, n;
+ ssize_t ret;
+ int n;
- _enter(",,%lx,%lx,", index, end);
+ _enter("%llx,%llx,", start, end);
do {
- n = find_get_pages_range_tag(mapping, &index, end,
- PAGECACHE_TAG_DIRTY, 1, &page);
+ pgoff_t index = start / PAGE_SIZE;
+
+ n = find_get_pages_range_tag(mapping, &index, end / PAGE_SIZE,
+ PAGECACHE_TAG_DIRTY, 1, &page);
if (!n)
break;
+ start = (loff_t)page->index * PAGE_SIZE; /* May regress with THPs */
+
_debug("wback %lx", page->index);
- /*
- * at this point we hold neither the i_pages lock nor the
+ /* At this point we hold neither the i_pages lock nor the
* page lock: the page may be truncated or invalidated
* (changing page->mapping to NULL), or even swizzled
* back from swapper_space to tmpfs file mapping
*/
- ret = lock_page_killable(page);
- if (ret < 0) {
- put_page(page);
- _leave(" = %d", ret);
- return ret;
+ if (wbc->sync_mode != WB_SYNC_NONE) {
+ ret = lock_page_killable(page);
+ if (ret < 0) {
+ put_page(page);
+ return ret;
+ }
+ } else {
+ if (!trylock_page(page)) {
+ put_page(page);
+ return 0;
+ }
}
if (page->mapping != mapping || !PageDirty(page)) {
+ start += thp_size(page);
unlock_page(page);
put_page(page);
continue;
@@ -722,20 +723,20 @@ static int afs_writepages_region(struct address_space *mapping,
if (!clear_page_dirty_for_io(page))
BUG();
- ret = afs_write_back_from_locked_page(mapping, wbc, page, end);
+ ret = afs_write_back_from_locked_page(mapping, wbc, page, start, end);
put_page(page);
if (ret < 0) {
- _leave(" = %d", ret);
+ _leave(" = %zd", ret);
return ret;
}
- wbc->nr_to_write -= ret;
+ start += ret * PAGE_SIZE;
cond_resched();
- } while (index < end && wbc->nr_to_write > 0);
+ } while (wbc->nr_to_write > 0);
- *_next = index;
- _leave(" = 0 [%lx]", *_next);
+ *_next = start;
+ _leave(" = 0 [%llx]", *_next);
return 0;
}
@@ -746,7 +747,7 @@ int afs_writepages(struct address_space *mapping,
struct writeback_control *wbc)
{
struct afs_vnode *vnode = AFS_FS_I(mapping->host);
- pgoff_t start, end, next;
+ loff_t start, next;
int ret;
_enter("");
@@ -761,22 +762,19 @@ int afs_writepages(struct address_space *mapping,
return 0;
if (wbc->range_cyclic) {
- start = mapping->writeback_index;
- end = -1;
- ret = afs_writepages_region(mapping, wbc, start, end, &next);
+ start = mapping->writeback_index * PAGE_SIZE;
+ ret = afs_writepages_region(mapping, wbc, start, LLONG_MAX, &next);
if (start > 0 && wbc->nr_to_write > 0 && ret == 0)
ret = afs_writepages_region(mapping, wbc, 0, start,
&next);
- mapping->writeback_index = next;
+ mapping->writeback_index = next / PAGE_SIZE;
} else if (wbc->range_start == 0 && wbc->range_end == LLONG_MAX) {
- end = (pgoff_t)(LLONG_MAX >> PAGE_SHIFT);
- ret = afs_writepages_region(mapping, wbc, 0, end, &next);
+ ret = afs_writepages_region(mapping, wbc, 0, LLONG_MAX, &next);
if (wbc->nr_to_write > 0)
mapping->writeback_index = next;
} else {
- start = wbc->range_start >> PAGE_SHIFT;
- end = wbc->range_end >> PAGE_SHIFT;
- ret = afs_writepages_region(mapping, wbc, start, end, &next);
+ ret = afs_writepages_region(mapping, wbc,
+ wbc->range_start, wbc->range_end, &next);
}
up_read(&vnode->validate_lock);
@@ -834,13 +832,13 @@ int afs_fsync(struct file *file, loff_t start, loff_t end, int datasync)
*/
vm_fault_t afs_page_mkwrite(struct vm_fault *vmf)
{
+ struct page *page = thp_head(vmf->page);
struct file *file = vmf->vma->vm_file;
struct inode *inode = file_inode(file);
struct afs_vnode *vnode = AFS_FS_I(inode);
unsigned long priv;
- _enter("{{%llx:%llu}},{%lx}",
- vnode->fid.vid, vnode->fid.vnode, vmf->page->index);
+ _enter("{{%llx:%llu}},{%lx}", vnode->fid.vid, vnode->fid.vnode, page->index);
sb_start_pagefault(inode->i_sb);
@@ -848,30 +846,35 @@ vm_fault_t afs_page_mkwrite(struct vm_fault *vmf)
* be modified. We then assume the entire page will need writing back.
*/
#ifdef CONFIG_AFS_FSCACHE
- fscache_wait_on_page_write(vnode->cache, vmf->page);
+ if (PageFsCache(page) &&
+ wait_on_page_fscache_killable(page) < 0)
+ return VM_FAULT_RETRY;
#endif
- if (PageWriteback(vmf->page) &&
- wait_on_page_bit_killable(vmf->page, PG_writeback) < 0)
+ if (wait_on_page_writeback_killable(page))
return VM_FAULT_RETRY;
- if (lock_page_killable(vmf->page) < 0)
+ if (lock_page_killable(page) < 0)
return VM_FAULT_RETRY;
/* We mustn't change page->private until writeback is complete as that
* details the portion of the page we need to write back and we might
* need to redirty the page if there's a problem.
*/
- wait_on_page_writeback(vmf->page);
+ if (wait_on_page_writeback_killable(page) < 0) {
+ unlock_page(page);
+ return VM_FAULT_RETRY;
+ }
- priv = afs_page_dirty(0, PAGE_SIZE);
+ priv = afs_page_dirty(page, 0, thp_size(page));
priv = afs_page_dirty_mmapped(priv);
- trace_afs_page_dirty(vnode, tracepoint_string("mkwrite"),
- vmf->page->index, priv);
- if (PagePrivate(vmf->page))
- set_page_private(vmf->page, priv);
- else
- attach_page_private(vmf->page, (void *)priv);
+ if (PagePrivate(page)) {
+ set_page_private(page, priv);
+ trace_afs_page_dirty(vnode, tracepoint_string("mkwrite+"), page);
+ } else {
+ attach_page_private(page, (void *)priv);
+ trace_afs_page_dirty(vnode, tracepoint_string("mkwrite"), page);
+ }
file_update_time(file);
sb_end_pagefault(inode->i_sb);
@@ -913,6 +916,8 @@ int afs_launder_page(struct page *page)
{
struct address_space *mapping = page->mapping;
struct afs_vnode *vnode = AFS_FS_I(mapping->host);
+ struct iov_iter iter;
+ struct bio_vec bv[1];
unsigned long priv;
unsigned int f, t;
int ret = 0;
@@ -922,26 +927,24 @@ int afs_launder_page(struct page *page)
priv = page_private(page);
if (clear_page_dirty_for_io(page)) {
f = 0;
- t = PAGE_SIZE;
+ t = thp_size(page);
if (PagePrivate(page)) {
- f = afs_page_dirty_from(priv);
- t = afs_page_dirty_to(priv);
+ f = afs_page_dirty_from(page, priv);
+ t = afs_page_dirty_to(page, priv);
}
- trace_afs_page_dirty(vnode, tracepoint_string("launder"),
- page->index, priv);
- ret = afs_store_data(mapping, page->index, page->index, t, f, true);
- }
-
- priv = (unsigned long)detach_page_private(page);
- trace_afs_page_dirty(vnode, tracepoint_string("laundered"),
- page->index, priv);
+ bv[0].bv_page = page;
+ bv[0].bv_offset = f;
+ bv[0].bv_len = t - f;
+ iov_iter_bvec(&iter, WRITE, bv, 1, bv[0].bv_len);
-#ifdef CONFIG_AFS_FSCACHE
- if (PageFsCache(page)) {
- fscache_wait_on_page_write(vnode->cache, page);
- fscache_uncache_page(vnode->cache, page);
+ trace_afs_page_dirty(vnode, tracepoint_string("launder"), page);
+ ret = afs_store_data(vnode, &iter, (loff_t)page->index * PAGE_SIZE,
+ true);
}
-#endif
+
+ trace_afs_page_dirty(vnode, tracepoint_string("laundered"), page);
+ detach_page_private(page);
+ wait_on_page_fscache(page);
return ret;
}
diff --git a/fs/afs/xattr.c b/fs/afs/xattr.c
index c629caae5002..7751b0b3f81d 100644
--- a/fs/afs/xattr.c
+++ b/fs/afs/xattr.c
@@ -11,29 +11,6 @@
#include <linux/xattr.h>
#include "internal.h"
-static const char afs_xattr_list[] =
- "afs.acl\0"
- "afs.cell\0"
- "afs.fid\0"
- "afs.volume\0"
- "afs.yfs.acl\0"
- "afs.yfs.acl_inherited\0"
- "afs.yfs.acl_num_cleaned\0"
- "afs.yfs.vol_acl";
-
-/*
- * Retrieve a list of the supported xattrs.
- */
-ssize_t afs_listxattr(struct dentry *dentry, char *buffer, size_t size)
-{
- if (size == 0)
- return sizeof(afs_xattr_list);
- if (size < sizeof(afs_xattr_list))
- return -ERANGE;
- memcpy(buffer, afs_xattr_list, sizeof(afs_xattr_list));
- return sizeof(afs_xattr_list);
-}
-
/*
* Deal with the result of a successful fetch ACL operation.
*/
@@ -231,6 +208,8 @@ static int afs_xattr_get_yfs(const struct xattr_handler *handler,
else
ret = -ERANGE;
}
+ } else if (ret == -ENOTSUPP) {
+ ret = -ENODATA;
}
error_yacl:
@@ -256,6 +235,7 @@ static int afs_xattr_set_yfs(const struct xattr_handler *handler,
{
struct afs_operation *op;
struct afs_vnode *vnode = AFS_FS_I(inode);
+ int ret;
if (flags == XATTR_CREATE ||
strcmp(name, "acl") != 0)
@@ -270,7 +250,10 @@ static int afs_xattr_set_yfs(const struct xattr_handler *handler,
return afs_put_operation(op);
op->ops = &yfs_store_opaque_acl2_operation;
- return afs_do_sync_operation(op);
+ ret = afs_do_sync_operation(op);
+ if (ret == -ENOTSUPP)
+ ret = -ENODATA;
+ return ret;
}
static const struct xattr_handler afs_xattr_yfs_handler = {
diff --git a/fs/afs/yfsclient.c b/fs/afs/yfsclient.c
index bd787e71a657..2b35cba8ad62 100644
--- a/fs/afs/yfsclient.c
+++ b/fs/afs/yfsclient.c
@@ -360,22 +360,23 @@ static int yfs_deliver_fs_fetch_data64(struct afs_call *call)
struct afs_vnode_param *vp = &op->file[0];
struct afs_read *req = op->fetch.req;
const __be32 *bp;
- unsigned int size;
int ret;
- _enter("{%u,%zu/%llu}",
- call->unmarshall, iov_iter_count(call->iter), req->actual_len);
+ _enter("{%u,%zu, %zu/%llu}",
+ call->unmarshall, call->iov_len, iov_iter_count(call->iter),
+ req->actual_len);
switch (call->unmarshall) {
case 0:
req->actual_len = 0;
- req->index = 0;
- req->offset = req->pos & (PAGE_SIZE - 1);
afs_extract_to_tmp64(call);
call->unmarshall++;
fallthrough;
- /* extract the returned data length */
+ /* Extract the returned data length into ->actual_len. This
+ * may indicate more or less data than was requested will be
+ * returned.
+ */
case 1:
_debug("extract data length");
ret = afs_extract_data(call, true);
@@ -384,44 +385,25 @@ static int yfs_deliver_fs_fetch_data64(struct afs_call *call)
req->actual_len = be64_to_cpu(call->tmp64);
_debug("DATA length: %llu", req->actual_len);
- req->remain = min(req->len, req->actual_len);
- if (req->remain == 0)
+
+ if (req->actual_len == 0)
goto no_more_data;
+ call->iter = req->iter;
+ call->iov_len = min(req->actual_len, req->len);
call->unmarshall++;
-
- begin_page:
- ASSERTCMP(req->index, <, req->nr_pages);
- if (req->remain > PAGE_SIZE - req->offset)
- size = PAGE_SIZE - req->offset;
- else
- size = req->remain;
- call->bvec[0].bv_len = size;
- call->bvec[0].bv_offset = req->offset;
- call->bvec[0].bv_page = req->pages[req->index];
- iov_iter_bvec(&call->def_iter, READ, call->bvec, 1, size);
- ASSERTCMP(size, <=, PAGE_SIZE);
fallthrough;
/* extract the returned data */
case 2:
_debug("extract data %zu/%llu",
- iov_iter_count(call->iter), req->remain);
+ iov_iter_count(call->iter), req->actual_len);
ret = afs_extract_data(call, true);
if (ret < 0)
return ret;
- req->remain -= call->bvec[0].bv_len;
- req->offset += call->bvec[0].bv_len;
- ASSERTCMP(req->offset, <=, PAGE_SIZE);
- if (req->offset == PAGE_SIZE) {
- req->offset = 0;
- req->index++;
- if (req->remain > 0)
- goto begin_page;
- }
- ASSERTCMP(req->remain, ==, 0);
+ call->iter = &call->def_iter;
if (req->actual_len <= req->len)
goto no_more_data;
@@ -467,17 +449,6 @@ static int yfs_deliver_fs_fetch_data64(struct afs_call *call)
break;
}
- for (; req->index < req->nr_pages; req->index++) {
- if (req->offset < PAGE_SIZE)
- zero_user_segment(req->pages[req->index],
- req->offset, PAGE_SIZE);
- req->offset = 0;
- }
-
- if (req->page_done)
- for (req->index = 0; req->index < req->nr_pages; req->index++)
- req->page_done(req);
-
_leave(" = 0 [done]");
return 0;
}
@@ -516,6 +487,8 @@ void yfs_fs_fetch_data(struct afs_operation *op)
if (!call)
return afs_op_nomem(op);
+ req->call_debug_id = call->debug_id;
+
/* marshall the parameters */
bp = call->request;
bp = xdr_encode_u32(bp, YFSFETCHDATA64);
@@ -1102,25 +1075,15 @@ void yfs_fs_store_data(struct afs_operation *op)
{
struct afs_vnode_param *vp = &op->file[0];
struct afs_call *call;
- loff_t size, pos, i_size;
__be32 *bp;
_enter(",%x,{%llx:%llu},,",
key_serial(op->key), vp->fid.vid, vp->fid.vnode);
- size = (loff_t)op->store.last_to - (loff_t)op->store.first_offset;
- if (op->store.first != op->store.last)
- size += (loff_t)(op->store.last - op->store.first) << PAGE_SHIFT;
- pos = (loff_t)op->store.first << PAGE_SHIFT;
- pos += op->store.first_offset;
-
- i_size = i_size_read(&vp->vnode->vfs_inode);
- if (pos + size > i_size)
- i_size = size + pos;
-
_debug("size %llx, at %llx, i_size %llx",
- (unsigned long long)size, (unsigned long long)pos,
- (unsigned long long)i_size);
+ (unsigned long long)op->store.size,
+ (unsigned long long)op->store.pos,
+ (unsigned long long)op->store.i_size);
call = afs_alloc_flat_call(op->net, &yfs_RXYFSStoreData64,
sizeof(__be32) +
@@ -1133,8 +1096,7 @@ void yfs_fs_store_data(struct afs_operation *op)
if (!call)
return afs_op_nomem(op);
- call->key = op->key;
- call->send_pages = true;
+ call->write_iter = op->store.write_iter;
/* marshall the parameters */
bp = call->request;
@@ -1142,9 +1104,9 @@ void yfs_fs_store_data(struct afs_operation *op)
bp = xdr_encode_u32(bp, 0); /* RPC flags */
bp = xdr_encode_YFSFid(bp, &vp->fid);
bp = xdr_encode_YFSStoreStatus_mtime(bp, &op->mtime);
- bp = xdr_encode_u64(bp, pos);
- bp = xdr_encode_u64(bp, size);
- bp = xdr_encode_u64(bp, i_size);
+ bp = xdr_encode_u64(bp, op->store.pos);
+ bp = xdr_encode_u64(bp, op->store.size);
+ bp = xdr_encode_u64(bp, op->store.i_size);
yfs_check_req(call, bp);
trace_afs_make_fs_call(call, &vp->fid);
diff --git a/fs/aio.c b/fs/aio.c
index 1f32da13d39e..76ce0cc3ee4e 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -323,16 +323,13 @@ static void aio_free_ring(struct kioctx *ctx)
}
}
-static int aio_ring_mremap(struct vm_area_struct *vma, unsigned long flags)
+static int aio_ring_mremap(struct vm_area_struct *vma)
{
struct file *file = vma->vm_file;
struct mm_struct *mm = vma->vm_mm;
struct kioctx_table *table;
int i, res = -EINVAL;
- if (flags & MREMAP_DONTUNMAP)
- return -EINVAL;
-
spin_lock(&mm->ioctx_lock);
rcu_read_lock();
table = rcu_dereference(mm->ioctx_table);
diff --git a/fs/autofs/autofs_i.h b/fs/autofs/autofs_i.h
index 054f97b07754..918826eaceea 100644
--- a/fs/autofs/autofs_i.h
+++ b/fs/autofs/autofs_i.h
@@ -87,6 +87,7 @@ struct autofs_wait_queue {
autofs_wqt_t wait_queue_token;
/* We use the following to see what we are waiting for */
struct qstr name;
+ u32 offset;
u32 dev;
u64 ino;
kuid_t uid;
diff --git a/fs/autofs/expire.c b/fs/autofs/expire.c
index a1c7701007e7..b3fefd6237c3 100644
--- a/fs/autofs/expire.c
+++ b/fs/autofs/expire.c
@@ -355,7 +355,7 @@ static struct dentry *should_expire(struct dentry *dentry,
return NULL;
}
- if (d_really_is_positive(dentry) && d_is_symlink(dentry)) {
+ if (d_is_symlink(dentry)) {
pr_debug("checking symlink %p %pd\n", dentry, dentry);
/* Forced expire, user space handles busy mounts */
diff --git a/fs/autofs/waitq.c b/fs/autofs/waitq.c
index 5ced859dac53..16b5fca0626e 100644
--- a/fs/autofs/waitq.c
+++ b/fs/autofs/waitq.c
@@ -30,7 +30,7 @@ void autofs_catatonic_mode(struct autofs_sb_info *sbi)
while (wq) {
nwq = wq->next;
wq->status = -ENOENT; /* Magic is gone - report failure */
- kfree(wq->name.name);
+ kfree(wq->name.name - wq->offset);
wq->name.name = NULL;
wq->wait_ctr--;
wake_up_interruptible(&wq->queue);
@@ -175,51 +175,6 @@ static void autofs_notify_daemon(struct autofs_sb_info *sbi,
fput(pipe);
}
-static int autofs_getpath(struct autofs_sb_info *sbi,
- struct dentry *dentry, char *name)
-{
- struct dentry *root = sbi->sb->s_root;
- struct dentry *tmp;
- char *buf;
- char *p;
- int len;
- unsigned seq;
-
-rename_retry:
- buf = name;
- len = 0;
-
- seq = read_seqbegin(&rename_lock);
- rcu_read_lock();
- spin_lock(&sbi->fs_lock);
- for (tmp = dentry ; tmp != root ; tmp = tmp->d_parent)
- len += tmp->d_name.len + 1;
-
- if (!len || --len > NAME_MAX) {
- spin_unlock(&sbi->fs_lock);
- rcu_read_unlock();
- if (read_seqretry(&rename_lock, seq))
- goto rename_retry;
- return 0;
- }
-
- *(buf + len) = '\0';
- p = buf + len - dentry->d_name.len;
- strncpy(p, dentry->d_name.name, dentry->d_name.len);
-
- for (tmp = dentry->d_parent; tmp != root ; tmp = tmp->d_parent) {
- *(--p) = '/';
- p -= tmp->d_name.len;
- strncpy(p, tmp->d_name.name, tmp->d_name.len);
- }
- spin_unlock(&sbi->fs_lock);
- rcu_read_unlock();
- if (read_seqretry(&rename_lock, seq))
- goto rename_retry;
-
- return len;
-}
-
static struct autofs_wait_queue *
autofs_find_wait(struct autofs_sb_info *sbi, const struct qstr *qstr)
{
@@ -352,6 +307,7 @@ int autofs_wait(struct autofs_sb_info *sbi,
struct qstr qstr;
char *name;
int status, ret, type;
+ unsigned int offset = 0;
pid_t pid;
pid_t tgid;
@@ -389,20 +345,23 @@ int autofs_wait(struct autofs_sb_info *sbi,
return -ENOMEM;
/* If this is a direct mount request create a dummy name */
- if (IS_ROOT(dentry) && autofs_type_trigger(sbi->type))
+ if (IS_ROOT(dentry) && autofs_type_trigger(sbi->type)) {
+ qstr.name = name;
qstr.len = sprintf(name, "%p", dentry);
- else {
- qstr.len = autofs_getpath(sbi, dentry, name);
- if (!qstr.len) {
+ } else {
+ char *p = dentry_path_raw(dentry, name, NAME_MAX);
+ if (IS_ERR(p)) {
kfree(name);
return -ENOENT;
}
+ qstr.name = ++p; // skip the leading slash
+ qstr.len = strlen(p);
+ offset = p - name;
}
- qstr.name = name;
qstr.hash = full_name_hash(dentry, name, qstr.len);
if (mutex_lock_interruptible(&sbi->wq_mutex)) {
- kfree(qstr.name);
+ kfree(name);
return -EINTR;
}
@@ -410,7 +369,7 @@ int autofs_wait(struct autofs_sb_info *sbi,
if (ret <= 0) {
if (ret != -EINTR)
mutex_unlock(&sbi->wq_mutex);
- kfree(qstr.name);
+ kfree(name);
return ret;
}
@@ -418,7 +377,7 @@ int autofs_wait(struct autofs_sb_info *sbi,
/* Create a new wait queue */
wq = kmalloc(sizeof(struct autofs_wait_queue), GFP_KERNEL);
if (!wq) {
- kfree(qstr.name);
+ kfree(name);
mutex_unlock(&sbi->wq_mutex);
return -ENOMEM;
}
@@ -430,6 +389,7 @@ int autofs_wait(struct autofs_sb_info *sbi,
sbi->queues = wq;
init_waitqueue_head(&wq->queue);
memcpy(&wq->name, &qstr, sizeof(struct qstr));
+ wq->offset = offset;
wq->dev = autofs_get_dev(sbi);
wq->ino = autofs_get_ino(sbi);
wq->uid = current_uid();
@@ -469,7 +429,7 @@ int autofs_wait(struct autofs_sb_info *sbi,
(unsigned long) wq->wait_queue_token, wq->name.len,
wq->name.name, notify);
mutex_unlock(&sbi->wq_mutex);
- kfree(qstr.name);
+ kfree(name);
}
/*
@@ -540,7 +500,7 @@ int autofs_wait_release(struct autofs_sb_info *sbi,
}
*wql = wq->next; /* Unlink from chain */
- kfree(wq->name.name);
+ kfree(wq->name.name - wq->offset);
wq->name.name = NULL; /* Do not wait on this queue */
wq->status = status;
wake_up(&wq->queue);
diff --git a/fs/befs/TODO b/fs/befs/TODO
deleted file mode 100644
index 3250921aa2e6..000000000000
--- a/fs/befs/TODO
+++ /dev/null
@@ -1,14 +0,0 @@
-TODO
-==========
-
-* Convert comments to the Kernel-Doc format.
-
-* Befs_fs.h has gotten big and messy. No reason not to break it up into
- smaller peices.
-
-* See if Alexander Viro's option parser made it into the kernel tree.
- Use that if we can. (include/linux/parser.h)
-
-* See if we really need separate types for on-disk and in-memory
- representations of the superblock and inode.
-
diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c
index b12ba98ae9f5..187b3f2b9202 100644
--- a/fs/binfmt_elf.c
+++ b/fs/binfmt_elf.c
@@ -2267,8 +2267,7 @@ static int elf_core_dump(struct coredump_params *cprm)
goto end_coredump;
/* Align to page */
- if (!dump_skip(cprm, dataoff - cprm->pos))
- goto end_coredump;
+ dump_skip_to(cprm, dataoff);
for (i = 0; i < vma_count; i++) {
struct core_vma_metadata *meta = vma_meta + i;
@@ -2276,7 +2275,6 @@ static int elf_core_dump(struct coredump_params *cprm)
if (!dump_user_range(cprm, meta->start, meta->dump_size))
goto end_coredump;
}
- dump_truncate(cprm);
if (!elf_core_write_extra_data(cprm))
goto end_coredump;
diff --git a/fs/binfmt_elf_fdpic.c b/fs/binfmt_elf_fdpic.c
index 3cfd6cd46f26..2c99b102c860 100644
--- a/fs/binfmt_elf_fdpic.c
+++ b/fs/binfmt_elf_fdpic.c
@@ -1631,8 +1631,7 @@ static int elf_fdpic_core_dump(struct coredump_params *cprm)
goto end_coredump;
}
- if (!dump_skip(cprm, dataoff - cprm->pos))
- goto end_coredump;
+ dump_skip_to(cprm, dataoff);
if (!elf_fdpic_dump_segments(cprm, vma_meta, vma_count))
goto end_coredump;
diff --git a/fs/binfmt_flat.c b/fs/binfmt_flat.c
index b9c658e0548e..a1072c6a2341 100644
--- a/fs/binfmt_flat.c
+++ b/fs/binfmt_flat.c
@@ -74,6 +74,12 @@
#define MAX_SHARED_LIBS (1)
#endif
+#ifdef CONFIG_BINFMT_FLAT_NO_DATA_START_OFFSET
+#define DATA_START_OFFSET_WORDS (0)
+#else
+#define DATA_START_OFFSET_WORDS (MAX_SHARED_LIBS)
+#endif
+
struct lib_info {
struct {
unsigned long start_code; /* Start of text segment */
@@ -576,7 +582,8 @@ static int load_flat_file(struct linux_binprm *bprm,
goto err;
}
- len = data_len + extra + MAX_SHARED_LIBS * sizeof(unsigned long);
+ len = data_len + extra +
+ DATA_START_OFFSET_WORDS * sizeof(unsigned long);
len = PAGE_ALIGN(len);
realdatastart = vm_mmap(NULL, 0, len,
PROT_READ|PROT_WRITE|PROT_EXEC, MAP_PRIVATE, 0);
@@ -591,7 +598,7 @@ static int load_flat_file(struct linux_binprm *bprm,
goto err;
}
datapos = ALIGN(realdatastart +
- MAX_SHARED_LIBS * sizeof(unsigned long),
+ DATA_START_OFFSET_WORDS * sizeof(unsigned long),
FLAT_DATA_ALIGN);
pr_debug("Allocated data+bss+stack (%u bytes): %lx\n",
@@ -622,7 +629,8 @@ static int load_flat_file(struct linux_binprm *bprm,
memp_size = len;
} else {
- len = text_len + data_len + extra + MAX_SHARED_LIBS * sizeof(u32);
+ len = text_len + data_len + extra +
+ DATA_START_OFFSET_WORDS * sizeof(u32);
len = PAGE_ALIGN(len);
textpos = vm_mmap(NULL, 0, len,
PROT_READ | PROT_EXEC | PROT_WRITE, MAP_PRIVATE, 0);
@@ -638,7 +646,7 @@ static int load_flat_file(struct linux_binprm *bprm,
realdatastart = textpos + ntohl(hdr->data_start);
datapos = ALIGN(realdatastart +
- MAX_SHARED_LIBS * sizeof(u32),
+ DATA_START_OFFSET_WORDS * sizeof(u32),
FLAT_DATA_ALIGN);
reloc = (__be32 __user *)
@@ -714,7 +722,7 @@ static int load_flat_file(struct linux_binprm *bprm,
ret = result;
pr_err("Unable to read code+data+bss, errno %d\n", ret);
vm_munmap(textpos, text_len + data_len + extra +
- MAX_SHARED_LIBS * sizeof(u32));
+ DATA_START_OFFSET_WORDS * sizeof(u32));
goto err;
}
}
diff --git a/fs/block_dev.c b/fs/block_dev.c
index 92ed7d5df677..a5244e08b6c8 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -275,6 +275,8 @@ __blkdev_direct_IO_simple(struct kiocb *iocb, struct iov_iter *iter,
bio.bi_opf = dio_bio_write_op(iocb);
task_io_account_write(ret);
}
+ if (iocb->ki_flags & IOCB_NOWAIT)
+ bio.bi_opf |= REQ_NOWAIT;
if (iocb->ki_flags & IOCB_HIPRI)
bio_set_polled(&bio, iocb);
@@ -428,6 +430,8 @@ static ssize_t __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
bio->bi_opf = dio_bio_write_op(iocb);
task_io_account_write(bio->bi_iter.bi_size);
}
+ if (iocb->ki_flags & IOCB_NOWAIT)
+ bio->bi_opf |= REQ_NOWAIT;
dio->size += bio->bi_iter.bi_size;
pos += bio->bi_iter.bi_size;
@@ -1236,16 +1240,18 @@ static void __blkdev_put(struct block_device *bdev, fmode_t mode, int for_part);
int bdev_disk_changed(struct block_device *bdev, bool invalidate)
{
struct gendisk *disk = bdev->bd_disk;
- int ret;
+ int ret = 0;
lockdep_assert_held(&bdev->bd_mutex);
- clear_bit(GD_NEED_PART_SCAN, &bdev->bd_disk->state);
-
rescan:
- ret = blk_drop_partitions(bdev);
- if (ret)
- return ret;
+ if (bdev->bd_part_count)
+ return -EBUSY;
+ sync_blockdev(bdev);
+ invalidate_bdev(bdev);
+ blk_drop_partitions(disk);
+
+ clear_bit(GD_NEED_PART_SCAN, &disk->state);
/*
* Historically we only set the capacity to zero for devices that
@@ -1259,9 +1265,6 @@ rescan:
if (disk_part_scan_enabled(disk) ||
!(disk->flags & GENHD_FL_REMOVABLE))
set_capacity(disk, 0);
- } else {
- if (disk->fops->revalidate_disk)
- disk->fops->revalidate_disk(disk);
}
if (get_capacity(disk)) {
@@ -1433,10 +1436,6 @@ struct block_device *blkdev_get_by_dev(dev_t dev, fmode_t mode, void *holder)
if (ret)
return ERR_PTR(ret);
- /*
- * If we lost a race with 'disk' being deleted, try again. See md.c.
- */
-retry:
bdev = blkdev_get_no_open(dev);
if (!bdev)
return ERR_PTR(-ENXIO);
@@ -1483,8 +1482,6 @@ abort_claiming:
disk_unblock_events(disk);
put_blkdev:
blkdev_put_no_open(bdev);
- if (ret == -ERESTARTSYS)
- goto retry;
return ERR_PTR(ret);
}
EXPORT_SYMBOL(blkdev_get_by_dev);
diff --git a/fs/btrfs/Makefile b/fs/btrfs/Makefile
index b634c42115ea..cec88a66bd6c 100644
--- a/fs/btrfs/Makefile
+++ b/fs/btrfs/Makefile
@@ -7,10 +7,12 @@ subdir-ccflags-y += -Wmissing-format-attribute
subdir-ccflags-y += -Wmissing-prototypes
subdir-ccflags-y += -Wold-style-definition
subdir-ccflags-y += -Wmissing-include-dirs
-subdir-ccflags-y += $(call cc-option, -Wunused-but-set-variable)
-subdir-ccflags-y += $(call cc-option, -Wunused-const-variable)
-subdir-ccflags-y += $(call cc-option, -Wpacked-not-aligned)
-subdir-ccflags-y += $(call cc-option, -Wstringop-truncation)
+condflags := \
+ $(call cc-option, -Wunused-but-set-variable) \
+ $(call cc-option, -Wunused-const-variable) \
+ $(call cc-option, -Wpacked-not-aligned) \
+ $(call cc-option, -Wstringop-truncation)
+subdir-ccflags-y += $(condflags)
# The following turn off the warnings enabled by -Wextra
subdir-ccflags-y += -Wno-missing-field-initializers
subdir-ccflags-y += -Wno-sign-compare
@@ -28,7 +30,7 @@ btrfs-y += super.o ctree.o extent-tree.o print-tree.o root-tree.o dir-item.o \
reada.o backref.o ulist.o qgroup.o send.o dev-replace.o raid56.o \
uuid-tree.o props.o free-space-tree.o tree-checker.o space-info.o \
block-rsv.o delalloc-space.o block-group.o discard.o reflink.o \
- subpage.o
+ subpage.o tree-mod-log.o
btrfs-$(CONFIG_BTRFS_FS_POSIX_ACL) += acl.o
btrfs-$(CONFIG_BTRFS_FS_CHECK_INTEGRITY) += check-integrity.o
diff --git a/fs/btrfs/backref.c b/fs/btrfs/backref.c
index f47c1528eb9a..117d423fdb93 100644
--- a/fs/btrfs/backref.c
+++ b/fs/btrfs/backref.c
@@ -14,6 +14,7 @@
#include "delayed-ref.h"
#include "locking.h"
#include "misc.h"
+#include "tree-mod-log.h"
/* Just an arbitrary number so we can be sure this happened */
#define BACKREF_FOUND_SHARED 6
@@ -452,7 +453,7 @@ static int add_all_parents(struct btrfs_root *root, struct btrfs_path *path,
if (path->slots[0] >= btrfs_header_nritems(eb) ||
is_shared_data_backref(preftrees, eb->start) ||
ref->root_id != btrfs_header_owner(eb)) {
- if (time_seq == SEQ_LAST)
+ if (time_seq == BTRFS_SEQ_LAST)
ret = btrfs_next_leaf(root, path);
else
ret = btrfs_next_old_leaf(root, path, time_seq);
@@ -476,7 +477,7 @@ static int add_all_parents(struct btrfs_root *root, struct btrfs_path *path,
if (slot == 0 &&
(is_shared_data_backref(preftrees, eb->start) ||
ref->root_id != btrfs_header_owner(eb))) {
- if (time_seq == SEQ_LAST)
+ if (time_seq == BTRFS_SEQ_LAST)
ret = btrfs_next_leaf(root, path);
else
ret = btrfs_next_old_leaf(root, path, time_seq);
@@ -514,7 +515,7 @@ static int add_all_parents(struct btrfs_root *root, struct btrfs_path *path,
eie = NULL;
}
next:
- if (time_seq == SEQ_LAST)
+ if (time_seq == BTRFS_SEQ_LAST)
ret = btrfs_next_item(root, path);
else
ret = btrfs_next_old_item(root, path, time_seq);
@@ -574,7 +575,7 @@ static int resolve_indirect_ref(struct btrfs_fs_info *fs_info,
if (path->search_commit_root)
root_level = btrfs_header_level(root->commit_root);
- else if (time_seq == SEQ_LAST)
+ else if (time_seq == BTRFS_SEQ_LAST)
root_level = btrfs_header_level(root->node);
else
root_level = btrfs_old_root_level(root, time_seq);
@@ -605,7 +606,7 @@ static int resolve_indirect_ref(struct btrfs_fs_info *fs_info,
search_key.offset >= LLONG_MAX)
search_key.offset = 0;
path->lowest_level = level;
- if (time_seq == SEQ_LAST)
+ if (time_seq == BTRFS_SEQ_LAST)
ret = btrfs_search_slot(NULL, root, &search_key, path, 0, 0);
else
ret = btrfs_search_old_slot(root, &search_key, path, time_seq);
@@ -1147,8 +1148,8 @@ static int add_keyed_refs(struct btrfs_fs_info *fs_info,
* indirect refs to their parent bytenr.
* When roots are found, they're added to the roots list
*
- * If time_seq is set to SEQ_LAST, it will not search delayed_refs, and behave
- * much like trans == NULL case, the difference only lies in it will not
+ * If time_seq is set to BTRFS_SEQ_LAST, it will not search delayed_refs, and
+ * behave much like trans == NULL case, the difference only lies in it will not
* commit root.
* The special case is for qgroup to search roots in commit_transaction().
*
@@ -1199,7 +1200,7 @@ static int find_parent_nodes(struct btrfs_trans_handle *trans,
path->skip_locking = 1;
}
- if (time_seq == SEQ_LAST)
+ if (time_seq == BTRFS_SEQ_LAST)
path->skip_locking = 1;
/*
@@ -1217,9 +1218,9 @@ again:
#ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS
if (trans && likely(trans->type != __TRANS_DUMMY) &&
- time_seq != SEQ_LAST) {
+ time_seq != BTRFS_SEQ_LAST) {
#else
- if (trans && time_seq != SEQ_LAST) {
+ if (trans && time_seq != BTRFS_SEQ_LAST) {
#endif
/*
* look if there are updates for this ref queued and lock the
@@ -1527,7 +1528,7 @@ int btrfs_check_shared(struct btrfs_root *root, u64 inum, u64 bytenr,
struct btrfs_trans_handle *trans;
struct ulist_iterator uiter;
struct ulist_node *node;
- struct seq_list elem = SEQ_LIST_INIT(elem);
+ struct btrfs_seq_list elem = BTRFS_SEQ_LIST_INIT(elem);
int ret = 0;
struct share_check shared = {
.root_objectid = root->root_key.objectid,
@@ -1953,7 +1954,7 @@ int iterate_extent_inodes(struct btrfs_fs_info *fs_info,
struct ulist *roots = NULL;
struct ulist_node *ref_node = NULL;
struct ulist_node *root_node = NULL;
- struct seq_list tree_mod_seq_elem = SEQ_LIST_INIT(tree_mod_seq_elem);
+ struct btrfs_seq_list seq_elem = BTRFS_SEQ_LIST_INIT(seq_elem);
struct ulist_iterator ref_uiter;
struct ulist_iterator root_uiter;
@@ -1971,12 +1972,12 @@ int iterate_extent_inodes(struct btrfs_fs_info *fs_info,
}
if (trans)
- btrfs_get_tree_mod_seq(fs_info, &tree_mod_seq_elem);
+ btrfs_get_tree_mod_seq(fs_info, &seq_elem);
else
down_read(&fs_info->commit_root_sem);
ret = btrfs_find_all_leafs(trans, fs_info, extent_item_objectid,
- tree_mod_seq_elem.seq, &refs,
+ seq_elem.seq, &refs,
&extent_item_pos, ignore_offset);
if (ret)
goto out;
@@ -1984,7 +1985,7 @@ int iterate_extent_inodes(struct btrfs_fs_info *fs_info,
ULIST_ITER_INIT(&ref_uiter);
while (!ret && (ref_node = ulist_next(refs, &ref_uiter))) {
ret = btrfs_find_all_roots_safe(trans, fs_info, ref_node->val,
- tree_mod_seq_elem.seq, &roots,
+ seq_elem.seq, &roots,
ignore_offset);
if (ret)
break;
@@ -2007,7 +2008,7 @@ int iterate_extent_inodes(struct btrfs_fs_info *fs_info,
free_leaf_list(refs);
out:
if (trans) {
- btrfs_put_tree_mod_seq(fs_info, &tree_mod_seq_elem);
+ btrfs_put_tree_mod_seq(fs_info, &seq_elem);
btrfs_end_transaction(trans);
} else {
up_read(&fs_info->commit_root_sem);
diff --git a/fs/btrfs/block-group.c b/fs/btrfs/block-group.c
index 744b99ddc28c..aa57bdc8fc89 100644
--- a/fs/btrfs/block-group.c
+++ b/fs/btrfs/block-group.c
@@ -1289,7 +1289,7 @@ void btrfs_delete_unused_bgs(struct btrfs_fs_info *fs_info)
* Long running balances can keep us blocked here for eternity, so
* simply skip deletion if we're unable to get the mutex.
*/
- if (!mutex_trylock(&fs_info->delete_unused_bgs_mutex))
+ if (!mutex_trylock(&fs_info->reclaim_bgs_lock))
return;
spin_lock(&fs_info->unused_bgs_lock);
@@ -1462,12 +1462,12 @@ next:
spin_lock(&fs_info->unused_bgs_lock);
}
spin_unlock(&fs_info->unused_bgs_lock);
- mutex_unlock(&fs_info->delete_unused_bgs_mutex);
+ mutex_unlock(&fs_info->reclaim_bgs_lock);
return;
flip_async:
btrfs_end_transaction(trans);
- mutex_unlock(&fs_info->delete_unused_bgs_mutex);
+ mutex_unlock(&fs_info->reclaim_bgs_lock);
btrfs_put_block_group(block_group);
btrfs_discard_punt_unused_bgs_list(fs_info);
}
@@ -1485,6 +1485,97 @@ void btrfs_mark_bg_unused(struct btrfs_block_group *bg)
spin_unlock(&fs_info->unused_bgs_lock);
}
+void btrfs_reclaim_bgs_work(struct work_struct *work)
+{
+ struct btrfs_fs_info *fs_info =
+ container_of(work, struct btrfs_fs_info, reclaim_bgs_work);
+ struct btrfs_block_group *bg;
+ struct btrfs_space_info *space_info;
+ int ret;
+
+ if (!test_bit(BTRFS_FS_OPEN, &fs_info->flags))
+ return;
+
+ if (!btrfs_exclop_start(fs_info, BTRFS_EXCLOP_BALANCE))
+ return;
+
+ mutex_lock(&fs_info->reclaim_bgs_lock);
+ spin_lock(&fs_info->unused_bgs_lock);
+ while (!list_empty(&fs_info->reclaim_bgs)) {
+ bg = list_first_entry(&fs_info->reclaim_bgs,
+ struct btrfs_block_group,
+ bg_list);
+ list_del_init(&bg->bg_list);
+
+ space_info = bg->space_info;
+ spin_unlock(&fs_info->unused_bgs_lock);
+
+ /* Don't race with allocators so take the groups_sem */
+ down_write(&space_info->groups_sem);
+
+ spin_lock(&bg->lock);
+ if (bg->reserved || bg->pinned || bg->ro) {
+ /*
+ * We want to bail if we made new allocations or have
+ * outstanding allocations in this block group. We do
+ * the ro check in case balance is currently acting on
+ * this block group.
+ */
+ spin_unlock(&bg->lock);
+ up_write(&space_info->groups_sem);
+ goto next;
+ }
+ spin_unlock(&bg->lock);
+
+ /* Get out fast, in case we're unmounting the filesystem */
+ if (btrfs_fs_closing(fs_info)) {
+ up_write(&space_info->groups_sem);
+ goto next;
+ }
+
+ ret = inc_block_group_ro(bg, 0);
+ up_write(&space_info->groups_sem);
+ if (ret < 0)
+ goto next;
+
+ btrfs_info(fs_info, "reclaiming chunk %llu with %llu%% used",
+ bg->start, div_u64(bg->used * 100, bg->length));
+ trace_btrfs_reclaim_block_group(bg);
+ ret = btrfs_relocate_chunk(fs_info, bg->start);
+ if (ret)
+ btrfs_err(fs_info, "error relocating chunk %llu",
+ bg->start);
+
+next:
+ btrfs_put_block_group(bg);
+ spin_lock(&fs_info->unused_bgs_lock);
+ }
+ spin_unlock(&fs_info->unused_bgs_lock);
+ mutex_unlock(&fs_info->reclaim_bgs_lock);
+ btrfs_exclop_finish(fs_info);
+}
+
+void btrfs_reclaim_bgs(struct btrfs_fs_info *fs_info)
+{
+ spin_lock(&fs_info->unused_bgs_lock);
+ if (!list_empty(&fs_info->reclaim_bgs))
+ queue_work(system_unbound_wq, &fs_info->reclaim_bgs_work);
+ spin_unlock(&fs_info->unused_bgs_lock);
+}
+
+void btrfs_mark_bg_to_reclaim(struct btrfs_block_group *bg)
+{
+ struct btrfs_fs_info *fs_info = bg->fs_info;
+
+ spin_lock(&fs_info->unused_bgs_lock);
+ if (list_empty(&bg->bg_list)) {
+ btrfs_get_block_group(bg);
+ trace_btrfs_add_reclaim_block_group(bg);
+ list_add_tail(&bg->bg_list, &fs_info->reclaim_bgs);
+ }
+ spin_unlock(&fs_info->unused_bgs_lock);
+}
+
static int read_bg_from_eb(struct btrfs_fs_info *fs_info, struct btrfs_key *key,
struct btrfs_path *path)
{
@@ -2267,29 +2358,33 @@ int btrfs_inc_block_group_ro(struct btrfs_block_group *cache,
struct btrfs_trans_handle *trans;
u64 alloc_flags;
int ret;
+ bool dirty_bg_running;
-again:
- trans = btrfs_join_transaction(fs_info->extent_root);
- if (IS_ERR(trans))
- return PTR_ERR(trans);
+ do {
+ trans = btrfs_join_transaction(fs_info->extent_root);
+ if (IS_ERR(trans))
+ return PTR_ERR(trans);
- /*
- * we're not allowed to set block groups readonly after the dirty
- * block groups cache has started writing. If it already started,
- * back off and let this transaction commit
- */
- mutex_lock(&fs_info->ro_block_group_mutex);
- if (test_bit(BTRFS_TRANS_DIRTY_BG_RUN, &trans->transaction->flags)) {
- u64 transid = trans->transid;
+ dirty_bg_running = false;
- mutex_unlock(&fs_info->ro_block_group_mutex);
- btrfs_end_transaction(trans);
+ /*
+ * We're not allowed to set block groups readonly after the dirty
+ * block group cache has started writing. If it already started,
+ * back off and let this transaction commit.
+ */
+ mutex_lock(&fs_info->ro_block_group_mutex);
+ if (test_bit(BTRFS_TRANS_DIRTY_BG_RUN, &trans->transaction->flags)) {
+ u64 transid = trans->transid;
- ret = btrfs_wait_for_commit(fs_info, transid);
- if (ret)
- return ret;
- goto again;
- }
+ mutex_unlock(&fs_info->ro_block_group_mutex);
+ btrfs_end_transaction(trans);
+
+ ret = btrfs_wait_for_commit(fs_info, transid);
+ if (ret)
+ return ret;
+ dirty_bg_running = true;
+ }
+ } while (dirty_bg_running);
if (do_chunk_alloc) {
/*
@@ -3269,6 +3364,7 @@ static u64 get_profile_num_devs(struct btrfs_fs_info *fs_info, u64 type)
*/
void check_system_chunk(struct btrfs_trans_handle *trans, u64 type)
{
+ struct btrfs_transaction *cur_trans = trans->transaction;
struct btrfs_fs_info *fs_info = trans->fs_info;
struct btrfs_space_info *info;
u64 left;
@@ -3283,6 +3379,7 @@ void check_system_chunk(struct btrfs_trans_handle *trans, u64 type)
lockdep_assert_held(&fs_info->chunk_mutex);
info = btrfs_find_space_info(fs_info, BTRFS_BLOCK_GROUP_SYSTEM);
+again:
spin_lock(&info->lock);
left = info->total_bytes - btrfs_space_info_used(info, true);
spin_unlock(&info->lock);
@@ -3301,6 +3398,58 @@ void check_system_chunk(struct btrfs_trans_handle *trans, u64 type)
if (left < thresh) {
u64 flags = btrfs_system_alloc_profile(fs_info);
+ u64 reserved = atomic64_read(&cur_trans->chunk_bytes_reserved);
+
+ /*
+ * If there's not available space for the chunk tree (system
+ * space) and there are other tasks that reserved space for
+ * creating a new system block group, wait for them to complete
+ * the creation of their system block group and release excess
+ * reserved space. We do this because:
+ *
+ * *) We can end up allocating more system chunks than necessary
+ * when there are multiple tasks that are concurrently
+ * allocating block groups, which can lead to exhaustion of
+ * the system array in the superblock;
+ *
+ * *) If we allocate extra and unnecessary system block groups,
+ * despite being empty for a long time, and possibly forever,
+ * they end not being added to the list of unused block groups
+ * because that typically happens only when deallocating the
+ * last extent from a block group - which never happens since
+ * we never allocate from them in the first place. The few
+ * exceptions are when mounting a filesystem or running scrub,
+ * which add unused block groups to the list of unused block
+ * groups, to be deleted by the cleaner kthread.
+ * And even when they are added to the list of unused block
+ * groups, it can take a long time until they get deleted,
+ * since the cleaner kthread might be sleeping or busy with
+ * other work (deleting subvolumes, running delayed iputs,
+ * defrag scheduling, etc);
+ *
+ * This is rare in practice, but can happen when too many tasks
+ * are allocating blocks groups in parallel (via fallocate())
+ * and before the one that reserved space for a new system block
+ * group finishes the block group creation and releases the space
+ * reserved in excess (at btrfs_create_pending_block_groups()),
+ * other tasks end up here and see free system space temporarily
+ * not enough for updating the chunk tree.
+ *
+ * We unlock the chunk mutex before waiting for such tasks and
+ * lock it again after the wait, otherwise we would deadlock.
+ * It is safe to do so because allocating a system chunk is the
+ * first thing done while allocating a new block group.
+ */
+ if (reserved > trans->chunk_bytes_reserved) {
+ const u64 min_needed = reserved - thresh;
+
+ mutex_unlock(&fs_info->chunk_mutex);
+ wait_event(cur_trans->chunk_reserve_wait,
+ atomic64_read(&cur_trans->chunk_bytes_reserved) <=
+ min_needed);
+ mutex_lock(&fs_info->chunk_mutex);
+ goto again;
+ }
/*
* Ignore failure to create system chunk. We might end up not
@@ -3315,8 +3464,10 @@ void check_system_chunk(struct btrfs_trans_handle *trans, u64 type)
ret = btrfs_block_rsv_add(fs_info->chunk_root,
&fs_info->chunk_block_rsv,
thresh, BTRFS_RESERVE_NO_FLUSH);
- if (!ret)
+ if (!ret) {
+ atomic64_add(thresh, &cur_trans->chunk_bytes_reserved);
trans->chunk_bytes_reserved += thresh;
+ }
}
}
@@ -3386,6 +3537,16 @@ int btrfs_free_block_groups(struct btrfs_fs_info *info)
}
spin_unlock(&info->unused_bgs_lock);
+ spin_lock(&info->unused_bgs_lock);
+ while (!list_empty(&info->reclaim_bgs)) {
+ block_group = list_first_entry(&info->reclaim_bgs,
+ struct btrfs_block_group,
+ bg_list);
+ list_del_init(&block_group->bg_list);
+ btrfs_put_block_group(block_group);
+ }
+ spin_unlock(&info->unused_bgs_lock);
+
spin_lock(&info->block_group_cache_lock);
while ((n = rb_last(&info->block_group_cache_tree)) != NULL) {
block_group = rb_entry(n, struct btrfs_block_group,
diff --git a/fs/btrfs/block-group.h b/fs/btrfs/block-group.h
index 3ecc3372a5ce..7b927425dc71 100644
--- a/fs/btrfs/block-group.h
+++ b/fs/btrfs/block-group.h
@@ -264,6 +264,9 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans,
u64 group_start, struct extent_map *em);
void btrfs_delete_unused_bgs(struct btrfs_fs_info *fs_info);
void btrfs_mark_bg_unused(struct btrfs_block_group *bg);
+void btrfs_reclaim_bgs_work(struct work_struct *work);
+void btrfs_reclaim_bgs(struct btrfs_fs_info *fs_info);
+void btrfs_mark_bg_to_reclaim(struct btrfs_block_group *bg);
int btrfs_read_block_groups(struct btrfs_fs_info *info);
int btrfs_make_block_group(struct btrfs_trans_handle *trans, u64 bytes_used,
u64 type, u64 chunk_offset, u64 size);
diff --git a/fs/btrfs/btrfs_inode.h b/fs/btrfs/btrfs_inode.h
index 28e202e89660..c652e19ad74e 100644
--- a/fs/btrfs/btrfs_inode.h
+++ b/fs/btrfs/btrfs_inode.h
@@ -220,6 +220,7 @@ struct btrfs_inode {
/* Hook into fs_info->delayed_iputs */
struct list_head delayed_iput;
+ struct rw_semaphore i_mmap_lock;
struct inode vfs_inode;
};
@@ -299,24 +300,30 @@ static inline void btrfs_mod_outstanding_extents(struct btrfs_inode *inode,
mod);
}
-static inline int btrfs_inode_in_log(struct btrfs_inode *inode, u64 generation)
+/*
+ * Called every time after doing a buffered, direct IO or memory mapped write.
+ *
+ * This is to ensure that if we write to a file that was previously fsynced in
+ * the current transaction, then try to fsync it again in the same transaction,
+ * we will know that there were changes in the file and that it needs to be
+ * logged.
+ */
+static inline void btrfs_set_inode_last_sub_trans(struct btrfs_inode *inode)
+{
+ spin_lock(&inode->lock);
+ inode->last_sub_trans = inode->root->log_transid;
+ spin_unlock(&inode->lock);
+}
+
+static inline bool btrfs_inode_in_log(struct btrfs_inode *inode, u64 generation)
{
- int ret = 0;
+ bool ret = false;
spin_lock(&inode->lock);
if (inode->logged_trans == generation &&
inode->last_sub_trans <= inode->last_log_commit &&
- inode->last_sub_trans <= inode->root->last_log_commit) {
- /*
- * After a ranged fsync we might have left some extent maps
- * (that fall outside the fsync's range). So return false
- * here if the list isn't empty, to make sure btrfs_log_inode()
- * will be called and process those extent maps.
- */
- smp_mb();
- if (list_empty(&inode->extent_tree.modified_extents))
- ret = 1;
- }
+ inode->last_sub_trans <= inode->root->last_log_commit)
+ ret = true;
spin_unlock(&inode->lock);
return ret;
}
diff --git a/fs/btrfs/check-integrity.c b/fs/btrfs/check-integrity.c
index 113cb85c1fd4..169508609324 100644
--- a/fs/btrfs/check-integrity.c
+++ b/fs/btrfs/check-integrity.c
@@ -1555,10 +1555,11 @@ static void btrfsic_release_block_ctx(struct btrfsic_block_data_ctx *block_ctx)
BUG_ON(!block_ctx->pagev);
num_pages = (block_ctx->len + (u64)PAGE_SIZE - 1) >>
PAGE_SHIFT;
+ /* Pages must be unmapped in reverse order */
while (num_pages > 0) {
num_pages--;
if (block_ctx->datav[num_pages]) {
- kunmap(block_ctx->pagev[num_pages]);
+ kunmap_local(block_ctx->datav[num_pages]);
block_ctx->datav[num_pages] = NULL;
}
if (block_ctx->pagev[num_pages]) {
@@ -1637,7 +1638,7 @@ static int btrfsic_read_block(struct btrfsic_state *state,
i = j;
}
for (i = 0; i < num_pages; i++)
- block_ctx->datav[i] = kmap(block_ctx->pagev[i]);
+ block_ctx->datav[i] = kmap_local_page(block_ctx->pagev[i]);
return block_ctx->len;
}
@@ -2677,7 +2678,7 @@ static void __btrfsic_submit_bio(struct bio *bio)
dev_state = btrfsic_dev_state_lookup(bio->bi_bdev->bd_dev);
if (NULL != dev_state &&
(bio_op(bio) == REQ_OP_WRITE) && bio_has_data(bio)) {
- unsigned int i = 0;
+ int i = 0;
u64 dev_bytenr;
u64 cur_bytenr;
struct bio_vec bvec;
@@ -2702,7 +2703,7 @@ static void __btrfsic_submit_bio(struct bio *bio)
bio_for_each_segment(bvec, bio, iter) {
BUG_ON(bvec.bv_len != PAGE_SIZE);
- mapped_datav[i] = kmap(bvec.bv_page);
+ mapped_datav[i] = kmap_local_page(bvec.bv_page);
i++;
if (dev_state->state->print_mask &
@@ -2715,8 +2716,9 @@ static void __btrfsic_submit_bio(struct bio *bio)
mapped_datav, segs,
bio, &bio_is_patched,
bio->bi_opf);
- bio_for_each_segment(bvec, bio, iter)
- kunmap(bvec.bv_page);
+ /* Unmap in reverse order */
+ for (--i; i >= 0; i--)
+ kunmap_local(mapped_datav[i]);
kfree(mapped_datav);
} else if (NULL != dev_state && (bio->bi_opf & REQ_PREFLUSH)) {
if (dev_state->state->print_mask &
diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c
index 3f4c832abfed..17f93fd28f7e 100644
--- a/fs/btrfs/compression.c
+++ b/fs/btrfs/compression.c
@@ -80,10 +80,15 @@ static int compression_compress_pages(int type, struct list_head *ws,
case BTRFS_COMPRESS_NONE:
default:
/*
- * This can't happen, the type is validated several times
- * before we get here. As a sane fallback, return what the
- * callers will understand as 'no compression happened'.
+ * This can happen when compression races with remount setting
+ * it to 'no compress', while caller doesn't call
+ * inode_need_compress() to check if we really need to
+ * compress.
+ *
+ * Not a big deal, just need to inform caller that we
+ * haven't allocated any pages yet.
*/
+ *out_pages = 0;
return -E2BIG;
}
}
@@ -1611,7 +1616,7 @@ static void heuristic_collect_sample(struct inode *inode, u64 start, u64 end,
curr_sample_pos = 0;
while (index < index_end) {
page = find_get_page(inode->i_mapping, index);
- in_data = kmap(page);
+ in_data = kmap_local_page(page);
/* Handle case where the start is not aligned to PAGE_SIZE */
i = start % PAGE_SIZE;
while (i < PAGE_SIZE - SAMPLING_READ_SIZE) {
@@ -1624,7 +1629,7 @@ static void heuristic_collect_sample(struct inode *inode, u64 start, u64 end,
start += SAMPLING_INTERVAL;
curr_sample_pos += SAMPLING_READ_SIZE;
}
- kunmap(page);
+ kunmap_local(in_data);
put_page(page);
index++;
diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c
index d56730a67885..a484fb72a01f 100644
--- a/fs/btrfs/ctree.c
+++ b/fs/btrfs/ctree.c
@@ -14,6 +14,7 @@
#include "locking.h"
#include "volumes.h"
#include "qgroup.h"
+#include "tree-mod-log.h"
static int split_node(struct btrfs_trans_handle *trans, struct btrfs_root
*root, struct btrfs_path *path, int level);
@@ -233,597 +234,6 @@ int btrfs_copy_root(struct btrfs_trans_handle *trans,
return 0;
}
-enum mod_log_op {
- MOD_LOG_KEY_REPLACE,
- MOD_LOG_KEY_ADD,
- MOD_LOG_KEY_REMOVE,
- MOD_LOG_KEY_REMOVE_WHILE_FREEING,
- MOD_LOG_KEY_REMOVE_WHILE_MOVING,
- MOD_LOG_MOVE_KEYS,
- MOD_LOG_ROOT_REPLACE,
-};
-
-struct tree_mod_root {
- u64 logical;
- u8 level;
-};
-
-struct tree_mod_elem {
- struct rb_node node;
- u64 logical;
- u64 seq;
- enum mod_log_op op;
-
- /* this is used for MOD_LOG_KEY_* and MOD_LOG_MOVE_KEYS operations */
- int slot;
-
- /* this is used for MOD_LOG_KEY* and MOD_LOG_ROOT_REPLACE */
- u64 generation;
-
- /* those are used for op == MOD_LOG_KEY_{REPLACE,REMOVE} */
- struct btrfs_disk_key key;
- u64 blockptr;
-
- /* this is used for op == MOD_LOG_MOVE_KEYS */
- struct {
- int dst_slot;
- int nr_items;
- } move;
-
- /* this is used for op == MOD_LOG_ROOT_REPLACE */
- struct tree_mod_root old_root;
-};
-
-/*
- * Pull a new tree mod seq number for our operation.
- */
-static inline u64 btrfs_inc_tree_mod_seq(struct btrfs_fs_info *fs_info)
-{
- return atomic64_inc_return(&fs_info->tree_mod_seq);
-}
-
-/*
- * This adds a new blocker to the tree mod log's blocker list if the @elem
- * passed does not already have a sequence number set. So when a caller expects
- * to record tree modifications, it should ensure to set elem->seq to zero
- * before calling btrfs_get_tree_mod_seq.
- * Returns a fresh, unused tree log modification sequence number, even if no new
- * blocker was added.
- */
-u64 btrfs_get_tree_mod_seq(struct btrfs_fs_info *fs_info,
- struct seq_list *elem)
-{
- write_lock(&fs_info->tree_mod_log_lock);
- if (!elem->seq) {
- elem->seq = btrfs_inc_tree_mod_seq(fs_info);
- list_add_tail(&elem->list, &fs_info->tree_mod_seq_list);
- }
- write_unlock(&fs_info->tree_mod_log_lock);
-
- return elem->seq;
-}
-
-void btrfs_put_tree_mod_seq(struct btrfs_fs_info *fs_info,
- struct seq_list *elem)
-{
- struct rb_root *tm_root;
- struct rb_node *node;
- struct rb_node *next;
- struct tree_mod_elem *tm;
- u64 min_seq = (u64)-1;
- u64 seq_putting = elem->seq;
-
- if (!seq_putting)
- return;
-
- write_lock(&fs_info->tree_mod_log_lock);
- list_del(&elem->list);
- elem->seq = 0;
-
- if (!list_empty(&fs_info->tree_mod_seq_list)) {
- struct seq_list *first;
-
- first = list_first_entry(&fs_info->tree_mod_seq_list,
- struct seq_list, list);
- if (seq_putting > first->seq) {
- /*
- * Blocker with lower sequence number exists, we
- * cannot remove anything from the log.
- */
- write_unlock(&fs_info->tree_mod_log_lock);
- return;
- }
- min_seq = first->seq;
- }
-
- /*
- * anything that's lower than the lowest existing (read: blocked)
- * sequence number can be removed from the tree.
- */
- tm_root = &fs_info->tree_mod_log;
- for (node = rb_first(tm_root); node; node = next) {
- next = rb_next(node);
- tm = rb_entry(node, struct tree_mod_elem, node);
- if (tm->seq >= min_seq)
- continue;
- rb_erase(node, tm_root);
- kfree(tm);
- }
- write_unlock(&fs_info->tree_mod_log_lock);
-}
-
-/*
- * key order of the log:
- * node/leaf start address -> sequence
- *
- * The 'start address' is the logical address of the *new* root node
- * for root replace operations, or the logical address of the affected
- * block for all other operations.
- */
-static noinline int
-__tree_mod_log_insert(struct btrfs_fs_info *fs_info, struct tree_mod_elem *tm)
-{
- struct rb_root *tm_root;
- struct rb_node **new;
- struct rb_node *parent = NULL;
- struct tree_mod_elem *cur;
-
- lockdep_assert_held_write(&fs_info->tree_mod_log_lock);
-
- tm->seq = btrfs_inc_tree_mod_seq(fs_info);
-
- tm_root = &fs_info->tree_mod_log;
- new = &tm_root->rb_node;
- while (*new) {
- cur = rb_entry(*new, struct tree_mod_elem, node);
- parent = *new;
- if (cur->logical < tm->logical)
- new = &((*new)->rb_left);
- else if (cur->logical > tm->logical)
- new = &((*new)->rb_right);
- else if (cur->seq < tm->seq)
- new = &((*new)->rb_left);
- else if (cur->seq > tm->seq)
- new = &((*new)->rb_right);
- else
- return -EEXIST;
- }
-
- rb_link_node(&tm->node, parent, new);
- rb_insert_color(&tm->node, tm_root);
- return 0;
-}
-
-/*
- * Determines if logging can be omitted. Returns 1 if it can. Otherwise, it
- * returns zero with the tree_mod_log_lock acquired. The caller must hold
- * this until all tree mod log insertions are recorded in the rb tree and then
- * write unlock fs_info::tree_mod_log_lock.
- */
-static inline int tree_mod_dont_log(struct btrfs_fs_info *fs_info,
- struct extent_buffer *eb) {
- smp_mb();
- if (list_empty(&(fs_info)->tree_mod_seq_list))
- return 1;
- if (eb && btrfs_header_level(eb) == 0)
- return 1;
-
- write_lock(&fs_info->tree_mod_log_lock);
- if (list_empty(&(fs_info)->tree_mod_seq_list)) {
- write_unlock(&fs_info->tree_mod_log_lock);
- return 1;
- }
-
- return 0;
-}
-
-/* Similar to tree_mod_dont_log, but doesn't acquire any locks. */
-static inline int tree_mod_need_log(const struct btrfs_fs_info *fs_info,
- struct extent_buffer *eb)
-{
- smp_mb();
- if (list_empty(&(fs_info)->tree_mod_seq_list))
- return 0;
- if (eb && btrfs_header_level(eb) == 0)
- return 0;
-
- return 1;
-}
-
-static struct tree_mod_elem *
-alloc_tree_mod_elem(struct extent_buffer *eb, int slot,
- enum mod_log_op op, gfp_t flags)
-{
- struct tree_mod_elem *tm;
-
- tm = kzalloc(sizeof(*tm), flags);
- if (!tm)
- return NULL;
-
- tm->logical = eb->start;
- if (op != MOD_LOG_KEY_ADD) {
- btrfs_node_key(eb, &tm->key, slot);
- tm->blockptr = btrfs_node_blockptr(eb, slot);
- }
- tm->op = op;
- tm->slot = slot;
- tm->generation = btrfs_node_ptr_generation(eb, slot);
- RB_CLEAR_NODE(&tm->node);
-
- return tm;
-}
-
-static noinline int tree_mod_log_insert_key(struct extent_buffer *eb, int slot,
- enum mod_log_op op, gfp_t flags)
-{
- struct tree_mod_elem *tm;
- int ret;
-
- if (!tree_mod_need_log(eb->fs_info, eb))
- return 0;
-
- tm = alloc_tree_mod_elem(eb, slot, op, flags);
- if (!tm)
- return -ENOMEM;
-
- if (tree_mod_dont_log(eb->fs_info, eb)) {
- kfree(tm);
- return 0;
- }
-
- ret = __tree_mod_log_insert(eb->fs_info, tm);
- write_unlock(&eb->fs_info->tree_mod_log_lock);
- if (ret)
- kfree(tm);
-
- return ret;
-}
-
-static noinline int tree_mod_log_insert_move(struct extent_buffer *eb,
- int dst_slot, int src_slot, int nr_items)
-{
- struct tree_mod_elem *tm = NULL;
- struct tree_mod_elem **tm_list = NULL;
- int ret = 0;
- int i;
- int locked = 0;
-
- if (!tree_mod_need_log(eb->fs_info, eb))
- return 0;
-
- tm_list = kcalloc(nr_items, sizeof(struct tree_mod_elem *), GFP_NOFS);
- if (!tm_list)
- return -ENOMEM;
-
- tm = kzalloc(sizeof(*tm), GFP_NOFS);
- if (!tm) {
- ret = -ENOMEM;
- goto free_tms;
- }
-
- tm->logical = eb->start;
- tm->slot = src_slot;
- tm->move.dst_slot = dst_slot;
- tm->move.nr_items = nr_items;
- tm->op = MOD_LOG_MOVE_KEYS;
-
- for (i = 0; i + dst_slot < src_slot && i < nr_items; i++) {
- tm_list[i] = alloc_tree_mod_elem(eb, i + dst_slot,
- MOD_LOG_KEY_REMOVE_WHILE_MOVING, GFP_NOFS);
- if (!tm_list[i]) {
- ret = -ENOMEM;
- goto free_tms;
- }
- }
-
- if (tree_mod_dont_log(eb->fs_info, eb))
- goto free_tms;
- locked = 1;
-
- /*
- * When we override something during the move, we log these removals.
- * This can only happen when we move towards the beginning of the
- * buffer, i.e. dst_slot < src_slot.
- */
- for (i = 0; i + dst_slot < src_slot && i < nr_items; i++) {
- ret = __tree_mod_log_insert(eb->fs_info, tm_list[i]);
- if (ret)
- goto free_tms;
- }
-
- ret = __tree_mod_log_insert(eb->fs_info, tm);
- if (ret)
- goto free_tms;
- write_unlock(&eb->fs_info->tree_mod_log_lock);
- kfree(tm_list);
-
- return 0;
-free_tms:
- for (i = 0; i < nr_items; i++) {
- if (tm_list[i] && !RB_EMPTY_NODE(&tm_list[i]->node))
- rb_erase(&tm_list[i]->node, &eb->fs_info->tree_mod_log);
- kfree(tm_list[i]);
- }
- if (locked)
- write_unlock(&eb->fs_info->tree_mod_log_lock);
- kfree(tm_list);
- kfree(tm);
-
- return ret;
-}
-
-static inline int
-__tree_mod_log_free_eb(struct btrfs_fs_info *fs_info,
- struct tree_mod_elem **tm_list,
- int nritems)
-{
- int i, j;
- int ret;
-
- for (i = nritems - 1; i >= 0; i--) {
- ret = __tree_mod_log_insert(fs_info, tm_list[i]);
- if (ret) {
- for (j = nritems - 1; j > i; j--)
- rb_erase(&tm_list[j]->node,
- &fs_info->tree_mod_log);
- return ret;
- }
- }
-
- return 0;
-}
-
-static noinline int tree_mod_log_insert_root(struct extent_buffer *old_root,
- struct extent_buffer *new_root, int log_removal)
-{
- struct btrfs_fs_info *fs_info = old_root->fs_info;
- struct tree_mod_elem *tm = NULL;
- struct tree_mod_elem **tm_list = NULL;
- int nritems = 0;
- int ret = 0;
- int i;
-
- if (!tree_mod_need_log(fs_info, NULL))
- return 0;
-
- if (log_removal && btrfs_header_level(old_root) > 0) {
- nritems = btrfs_header_nritems(old_root);
- tm_list = kcalloc(nritems, sizeof(struct tree_mod_elem *),
- GFP_NOFS);
- if (!tm_list) {
- ret = -ENOMEM;
- goto free_tms;
- }
- for (i = 0; i < nritems; i++) {
- tm_list[i] = alloc_tree_mod_elem(old_root, i,
- MOD_LOG_KEY_REMOVE_WHILE_FREEING, GFP_NOFS);
- if (!tm_list[i]) {
- ret = -ENOMEM;
- goto free_tms;
- }
- }
- }
-
- tm = kzalloc(sizeof(*tm), GFP_NOFS);
- if (!tm) {
- ret = -ENOMEM;
- goto free_tms;
- }
-
- tm->logical = new_root->start;
- tm->old_root.logical = old_root->start;
- tm->old_root.level = btrfs_header_level(old_root);
- tm->generation = btrfs_header_generation(old_root);
- tm->op = MOD_LOG_ROOT_REPLACE;
-
- if (tree_mod_dont_log(fs_info, NULL))
- goto free_tms;
-
- if (tm_list)
- ret = __tree_mod_log_free_eb(fs_info, tm_list, nritems);
- if (!ret)
- ret = __tree_mod_log_insert(fs_info, tm);
-
- write_unlock(&fs_info->tree_mod_log_lock);
- if (ret)
- goto free_tms;
- kfree(tm_list);
-
- return ret;
-
-free_tms:
- if (tm_list) {
- for (i = 0; i < nritems; i++)
- kfree(tm_list[i]);
- kfree(tm_list);
- }
- kfree(tm);
-
- return ret;
-}
-
-static struct tree_mod_elem *
-__tree_mod_log_search(struct btrfs_fs_info *fs_info, u64 start, u64 min_seq,
- int smallest)
-{
- struct rb_root *tm_root;
- struct rb_node *node;
- struct tree_mod_elem *cur = NULL;
- struct tree_mod_elem *found = NULL;
-
- read_lock(&fs_info->tree_mod_log_lock);
- tm_root = &fs_info->tree_mod_log;
- node = tm_root->rb_node;
- while (node) {
- cur = rb_entry(node, struct tree_mod_elem, node);
- if (cur->logical < start) {
- node = node->rb_left;
- } else if (cur->logical > start) {
- node = node->rb_right;
- } else if (cur->seq < min_seq) {
- node = node->rb_left;
- } else if (!smallest) {
- /* we want the node with the highest seq */
- if (found)
- BUG_ON(found->seq > cur->seq);
- found = cur;
- node = node->rb_left;
- } else if (cur->seq > min_seq) {
- /* we want the node with the smallest seq */
- if (found)
- BUG_ON(found->seq < cur->seq);
- found = cur;
- node = node->rb_right;
- } else {
- found = cur;
- break;
- }
- }
- read_unlock(&fs_info->tree_mod_log_lock);
-
- return found;
-}
-
-/*
- * this returns the element from the log with the smallest time sequence
- * value that's in the log (the oldest log item). any element with a time
- * sequence lower than min_seq will be ignored.
- */
-static struct tree_mod_elem *
-tree_mod_log_search_oldest(struct btrfs_fs_info *fs_info, u64 start,
- u64 min_seq)
-{
- return __tree_mod_log_search(fs_info, start, min_seq, 1);
-}
-
-/*
- * this returns the element from the log with the largest time sequence
- * value that's in the log (the most recent log item). any element with
- * a time sequence lower than min_seq will be ignored.
- */
-static struct tree_mod_elem *
-tree_mod_log_search(struct btrfs_fs_info *fs_info, u64 start, u64 min_seq)
-{
- return __tree_mod_log_search(fs_info, start, min_seq, 0);
-}
-
-static noinline int tree_mod_log_eb_copy(struct extent_buffer *dst,
- struct extent_buffer *src, unsigned long dst_offset,
- unsigned long src_offset, int nr_items)
-{
- struct btrfs_fs_info *fs_info = dst->fs_info;
- int ret = 0;
- struct tree_mod_elem **tm_list = NULL;
- struct tree_mod_elem **tm_list_add, **tm_list_rem;
- int i;
- int locked = 0;
-
- if (!tree_mod_need_log(fs_info, NULL))
- return 0;
-
- if (btrfs_header_level(dst) == 0 && btrfs_header_level(src) == 0)
- return 0;
-
- tm_list = kcalloc(nr_items * 2, sizeof(struct tree_mod_elem *),
- GFP_NOFS);
- if (!tm_list)
- return -ENOMEM;
-
- tm_list_add = tm_list;
- tm_list_rem = tm_list + nr_items;
- for (i = 0; i < nr_items; i++) {
- tm_list_rem[i] = alloc_tree_mod_elem(src, i + src_offset,
- MOD_LOG_KEY_REMOVE, GFP_NOFS);
- if (!tm_list_rem[i]) {
- ret = -ENOMEM;
- goto free_tms;
- }
-
- tm_list_add[i] = alloc_tree_mod_elem(dst, i + dst_offset,
- MOD_LOG_KEY_ADD, GFP_NOFS);
- if (!tm_list_add[i]) {
- ret = -ENOMEM;
- goto free_tms;
- }
- }
-
- if (tree_mod_dont_log(fs_info, NULL))
- goto free_tms;
- locked = 1;
-
- for (i = 0; i < nr_items; i++) {
- ret = __tree_mod_log_insert(fs_info, tm_list_rem[i]);
- if (ret)
- goto free_tms;
- ret = __tree_mod_log_insert(fs_info, tm_list_add[i]);
- if (ret)
- goto free_tms;
- }
-
- write_unlock(&fs_info->tree_mod_log_lock);
- kfree(tm_list);
-
- return 0;
-
-free_tms:
- for (i = 0; i < nr_items * 2; i++) {
- if (tm_list[i] && !RB_EMPTY_NODE(&tm_list[i]->node))
- rb_erase(&tm_list[i]->node, &fs_info->tree_mod_log);
- kfree(tm_list[i]);
- }
- if (locked)
- write_unlock(&fs_info->tree_mod_log_lock);
- kfree(tm_list);
-
- return ret;
-}
-
-static noinline int tree_mod_log_free_eb(struct extent_buffer *eb)
-{
- struct tree_mod_elem **tm_list = NULL;
- int nritems = 0;
- int i;
- int ret = 0;
-
- if (btrfs_header_level(eb) == 0)
- return 0;
-
- if (!tree_mod_need_log(eb->fs_info, NULL))
- return 0;
-
- nritems = btrfs_header_nritems(eb);
- tm_list = kcalloc(nritems, sizeof(struct tree_mod_elem *), GFP_NOFS);
- if (!tm_list)
- return -ENOMEM;
-
- for (i = 0; i < nritems; i++) {
- tm_list[i] = alloc_tree_mod_elem(eb, i,
- MOD_LOG_KEY_REMOVE_WHILE_FREEING, GFP_NOFS);
- if (!tm_list[i]) {
- ret = -ENOMEM;
- goto free_tms;
- }
- }
-
- if (tree_mod_dont_log(eb->fs_info, eb))
- goto free_tms;
-
- ret = __tree_mod_log_free_eb(eb->fs_info, tm_list, nritems);
- write_unlock(&eb->fs_info->tree_mod_log_lock);
- if (ret)
- goto free_tms;
- kfree(tm_list);
-
- return 0;
-
-free_tms:
- for (i = 0; i < nritems; i++)
- kfree(tm_list[i]);
- kfree(tm_list);
-
- return ret;
-}
-
/*
* check if the tree block can be shared by multiple trees
*/
@@ -1090,7 +500,7 @@ static noinline int __btrfs_cow_block(struct btrfs_trans_handle *trans,
parent_start = buf->start;
atomic_inc(&cow->refs);
- ret = tree_mod_log_insert_root(root->node, cow, 1);
+ ret = btrfs_tree_mod_log_insert_root(root->node, cow, true);
BUG_ON(ret < 0);
rcu_assign_pointer(root->node, cow);
@@ -1100,15 +510,15 @@ static noinline int __btrfs_cow_block(struct btrfs_trans_handle *trans,
add_root_to_dirty_list(root);
} else {
WARN_ON(trans->transid != btrfs_header_generation(parent));
- tree_mod_log_insert_key(parent, parent_slot,
- MOD_LOG_KEY_REPLACE, GFP_NOFS);
+ btrfs_tree_mod_log_insert_key(parent, parent_slot,
+ BTRFS_MOD_LOG_KEY_REPLACE, GFP_NOFS);
btrfs_set_node_blockptr(parent, parent_slot,
cow->start);
btrfs_set_node_ptr_generation(parent, parent_slot,
trans->transid);
btrfs_mark_buffer_dirty(parent);
if (last_ref) {
- ret = tree_mod_log_free_eb(buf);
+ ret = btrfs_tree_mod_log_free_eb(buf);
if (ret) {
btrfs_tree_unlock(cow);
free_extent_buffer(cow);
@@ -1127,296 +537,6 @@ static noinline int __btrfs_cow_block(struct btrfs_trans_handle *trans,
return 0;
}
-/*
- * returns the logical address of the oldest predecessor of the given root.
- * entries older than time_seq are ignored.
- */
-static struct tree_mod_elem *__tree_mod_log_oldest_root(
- struct extent_buffer *eb_root, u64 time_seq)
-{
- struct tree_mod_elem *tm;
- struct tree_mod_elem *found = NULL;
- u64 root_logical = eb_root->start;
- int looped = 0;
-
- if (!time_seq)
- return NULL;
-
- /*
- * the very last operation that's logged for a root is the
- * replacement operation (if it is replaced at all). this has
- * the logical address of the *new* root, making it the very
- * first operation that's logged for this root.
- */
- while (1) {
- tm = tree_mod_log_search_oldest(eb_root->fs_info, root_logical,
- time_seq);
- if (!looped && !tm)
- return NULL;
- /*
- * if there are no tree operation for the oldest root, we simply
- * return it. this should only happen if that (old) root is at
- * level 0.
- */
- if (!tm)
- break;
-
- /*
- * if there's an operation that's not a root replacement, we
- * found the oldest version of our root. normally, we'll find a
- * MOD_LOG_KEY_REMOVE_WHILE_FREEING operation here.
- */
- if (tm->op != MOD_LOG_ROOT_REPLACE)
- break;
-
- found = tm;
- root_logical = tm->old_root.logical;
- looped = 1;
- }
-
- /* if there's no old root to return, return what we found instead */
- if (!found)
- found = tm;
-
- return found;
-}
-
-/*
- * tm is a pointer to the first operation to rewind within eb. then, all
- * previous operations will be rewound (until we reach something older than
- * time_seq).
- */
-static void
-__tree_mod_log_rewind(struct btrfs_fs_info *fs_info, struct extent_buffer *eb,
- u64 time_seq, struct tree_mod_elem *first_tm)
-{
- u32 n;
- struct rb_node *next;
- struct tree_mod_elem *tm = first_tm;
- unsigned long o_dst;
- unsigned long o_src;
- unsigned long p_size = sizeof(struct btrfs_key_ptr);
-
- n = btrfs_header_nritems(eb);
- read_lock(&fs_info->tree_mod_log_lock);
- while (tm && tm->seq >= time_seq) {
- /*
- * all the operations are recorded with the operator used for
- * the modification. as we're going backwards, we do the
- * opposite of each operation here.
- */
- switch (tm->op) {
- case MOD_LOG_KEY_REMOVE_WHILE_FREEING:
- BUG_ON(tm->slot < n);
- fallthrough;
- case MOD_LOG_KEY_REMOVE_WHILE_MOVING:
- case MOD_LOG_KEY_REMOVE:
- btrfs_set_node_key(eb, &tm->key, tm->slot);
- btrfs_set_node_blockptr(eb, tm->slot, tm->blockptr);
- btrfs_set_node_ptr_generation(eb, tm->slot,
- tm->generation);
- n++;
- break;
- case MOD_LOG_KEY_REPLACE:
- BUG_ON(tm->slot >= n);
- btrfs_set_node_key(eb, &tm->key, tm->slot);
- btrfs_set_node_blockptr(eb, tm->slot, tm->blockptr);
- btrfs_set_node_ptr_generation(eb, tm->slot,
- tm->generation);
- break;
- case MOD_LOG_KEY_ADD:
- /* if a move operation is needed it's in the log */
- n--;
- break;
- case MOD_LOG_MOVE_KEYS:
- o_dst = btrfs_node_key_ptr_offset(tm->slot);
- o_src = btrfs_node_key_ptr_offset(tm->move.dst_slot);
- memmove_extent_buffer(eb, o_dst, o_src,
- tm->move.nr_items * p_size);
- break;
- case MOD_LOG_ROOT_REPLACE:
- /*
- * this operation is special. for roots, this must be
- * handled explicitly before rewinding.
- * for non-roots, this operation may exist if the node
- * was a root: root A -> child B; then A gets empty and
- * B is promoted to the new root. in the mod log, we'll
- * have a root-replace operation for B, a tree block
- * that is no root. we simply ignore that operation.
- */
- break;
- }
- next = rb_next(&tm->node);
- if (!next)
- break;
- tm = rb_entry(next, struct tree_mod_elem, node);
- if (tm->logical != first_tm->logical)
- break;
- }
- read_unlock(&fs_info->tree_mod_log_lock);
- btrfs_set_header_nritems(eb, n);
-}
-
-/*
- * Called with eb read locked. If the buffer cannot be rewound, the same buffer
- * is returned. If rewind operations happen, a fresh buffer is returned. The
- * returned buffer is always read-locked. If the returned buffer is not the
- * input buffer, the lock on the input buffer is released and the input buffer
- * is freed (its refcount is decremented).
- */
-static struct extent_buffer *
-tree_mod_log_rewind(struct btrfs_fs_info *fs_info, struct btrfs_path *path,
- struct extent_buffer *eb, u64 time_seq)
-{
- struct extent_buffer *eb_rewin;
- struct tree_mod_elem *tm;
-
- if (!time_seq)
- return eb;
-
- if (btrfs_header_level(eb) == 0)
- return eb;
-
- tm = tree_mod_log_search(fs_info, eb->start, time_seq);
- if (!tm)
- return eb;
-
- if (tm->op == MOD_LOG_KEY_REMOVE_WHILE_FREEING) {
- BUG_ON(tm->slot != 0);
- eb_rewin = alloc_dummy_extent_buffer(fs_info, eb->start);
- if (!eb_rewin) {
- btrfs_tree_read_unlock(eb);
- free_extent_buffer(eb);
- return NULL;
- }
- btrfs_set_header_bytenr(eb_rewin, eb->start);
- btrfs_set_header_backref_rev(eb_rewin,
- btrfs_header_backref_rev(eb));
- btrfs_set_header_owner(eb_rewin, btrfs_header_owner(eb));
- btrfs_set_header_level(eb_rewin, btrfs_header_level(eb));
- } else {
- eb_rewin = btrfs_clone_extent_buffer(eb);
- if (!eb_rewin) {
- btrfs_tree_read_unlock(eb);
- free_extent_buffer(eb);
- return NULL;
- }
- }
-
- btrfs_tree_read_unlock(eb);
- free_extent_buffer(eb);
-
- btrfs_set_buffer_lockdep_class(btrfs_header_owner(eb_rewin),
- eb_rewin, btrfs_header_level(eb_rewin));
- btrfs_tree_read_lock(eb_rewin);
- __tree_mod_log_rewind(fs_info, eb_rewin, time_seq, tm);
- WARN_ON(btrfs_header_nritems(eb_rewin) >
- BTRFS_NODEPTRS_PER_BLOCK(fs_info));
-
- return eb_rewin;
-}
-
-/*
- * get_old_root() rewinds the state of @root's root node to the given @time_seq
- * value. If there are no changes, the current root->root_node is returned. If
- * anything changed in between, there's a fresh buffer allocated on which the
- * rewind operations are done. In any case, the returned buffer is read locked.
- * Returns NULL on error (with no locks held).
- */
-static inline struct extent_buffer *
-get_old_root(struct btrfs_root *root, u64 time_seq)
-{
- struct btrfs_fs_info *fs_info = root->fs_info;
- struct tree_mod_elem *tm;
- struct extent_buffer *eb = NULL;
- struct extent_buffer *eb_root;
- u64 eb_root_owner = 0;
- struct extent_buffer *old;
- struct tree_mod_root *old_root = NULL;
- u64 old_generation = 0;
- u64 logical;
- int level;
-
- eb_root = btrfs_read_lock_root_node(root);
- tm = __tree_mod_log_oldest_root(eb_root, time_seq);
- if (!tm)
- return eb_root;
-
- if (tm->op == MOD_LOG_ROOT_REPLACE) {
- old_root = &tm->old_root;
- old_generation = tm->generation;
- logical = old_root->logical;
- level = old_root->level;
- } else {
- logical = eb_root->start;
- level = btrfs_header_level(eb_root);
- }
-
- tm = tree_mod_log_search(fs_info, logical, time_seq);
- if (old_root && tm && tm->op != MOD_LOG_KEY_REMOVE_WHILE_FREEING) {
- btrfs_tree_read_unlock(eb_root);
- free_extent_buffer(eb_root);
- old = read_tree_block(fs_info, logical, root->root_key.objectid,
- 0, level, NULL);
- if (WARN_ON(IS_ERR(old) || !extent_buffer_uptodate(old))) {
- if (!IS_ERR(old))
- free_extent_buffer(old);
- btrfs_warn(fs_info,
- "failed to read tree block %llu from get_old_root",
- logical);
- } else {
- eb = btrfs_clone_extent_buffer(old);
- free_extent_buffer(old);
- }
- } else if (old_root) {
- eb_root_owner = btrfs_header_owner(eb_root);
- btrfs_tree_read_unlock(eb_root);
- free_extent_buffer(eb_root);
- eb = alloc_dummy_extent_buffer(fs_info, logical);
- } else {
- eb = btrfs_clone_extent_buffer(eb_root);
- btrfs_tree_read_unlock(eb_root);
- free_extent_buffer(eb_root);
- }
-
- if (!eb)
- return NULL;
- if (old_root) {
- btrfs_set_header_bytenr(eb, eb->start);
- btrfs_set_header_backref_rev(eb, BTRFS_MIXED_BACKREF_REV);
- btrfs_set_header_owner(eb, eb_root_owner);
- btrfs_set_header_level(eb, old_root->level);
- btrfs_set_header_generation(eb, old_generation);
- }
- btrfs_set_buffer_lockdep_class(btrfs_header_owner(eb), eb,
- btrfs_header_level(eb));
- btrfs_tree_read_lock(eb);
- if (tm)
- __tree_mod_log_rewind(fs_info, eb, time_seq, tm);
- else
- WARN_ON(btrfs_header_level(eb) != 0);
- WARN_ON(btrfs_header_nritems(eb) > BTRFS_NODEPTRS_PER_BLOCK(fs_info));
-
- return eb;
-}
-
-int btrfs_old_root_level(struct btrfs_root *root, u64 time_seq)
-{
- struct tree_mod_elem *tm;
- int level;
- struct extent_buffer *eb_root = btrfs_root_node(root);
-
- tm = __tree_mod_log_oldest_root(eb_root, time_seq);
- if (tm && tm->op == MOD_LOG_ROOT_REPLACE) {
- level = tm->old_root.level;
- } else {
- level = btrfs_header_level(eb_root);
- }
- free_extent_buffer(eb_root);
-
- return level;
-}
-
static inline int should_cow_block(struct btrfs_trans_handle *trans,
struct btrfs_root *root,
struct extent_buffer *buf)
@@ -1838,7 +958,7 @@ static noinline int balance_level(struct btrfs_trans_handle *trans,
goto enospc;
}
- ret = tree_mod_log_insert_root(root->node, child, 1);
+ ret = btrfs_tree_mod_log_insert_root(root->node, child, true);
BUG_ON(ret < 0);
rcu_assign_pointer(root->node, child);
@@ -1918,8 +1038,8 @@ static noinline int balance_level(struct btrfs_trans_handle *trans,
} else {
struct btrfs_disk_key right_key;
btrfs_node_key(right, &right_key, 0);
- ret = tree_mod_log_insert_key(parent, pslot + 1,
- MOD_LOG_KEY_REPLACE, GFP_NOFS);
+ ret = btrfs_tree_mod_log_insert_key(parent, pslot + 1,
+ BTRFS_MOD_LOG_KEY_REPLACE, GFP_NOFS);
BUG_ON(ret < 0);
btrfs_set_node_key(parent, &right_key, pslot + 1);
btrfs_mark_buffer_dirty(parent);
@@ -1964,8 +1084,8 @@ static noinline int balance_level(struct btrfs_trans_handle *trans,
/* update the parent key to reflect our changes */
struct btrfs_disk_key mid_key;
btrfs_node_key(mid, &mid_key, 0);
- ret = tree_mod_log_insert_key(parent, pslot,
- MOD_LOG_KEY_REPLACE, GFP_NOFS);
+ ret = btrfs_tree_mod_log_insert_key(parent, pslot,
+ BTRFS_MOD_LOG_KEY_REPLACE, GFP_NOFS);
BUG_ON(ret < 0);
btrfs_set_node_key(parent, &mid_key, pslot);
btrfs_mark_buffer_dirty(parent);
@@ -2066,8 +1186,8 @@ static noinline int push_nodes_for_insert(struct btrfs_trans_handle *trans,
struct btrfs_disk_key disk_key;
orig_slot += left_nr;
btrfs_node_key(mid, &disk_key, 0);
- ret = tree_mod_log_insert_key(parent, pslot,
- MOD_LOG_KEY_REPLACE, GFP_NOFS);
+ ret = btrfs_tree_mod_log_insert_key(parent, pslot,
+ BTRFS_MOD_LOG_KEY_REPLACE, GFP_NOFS);
BUG_ON(ret < 0);
btrfs_set_node_key(parent, &disk_key, pslot);
btrfs_mark_buffer_dirty(parent);
@@ -2120,8 +1240,8 @@ static noinline int push_nodes_for_insert(struct btrfs_trans_handle *trans,
struct btrfs_disk_key disk_key;
btrfs_node_key(right, &disk_key, 0);
- ret = tree_mod_log_insert_key(parent, pslot + 1,
- MOD_LOG_KEY_REPLACE, GFP_NOFS);
+ ret = btrfs_tree_mod_log_insert_key(parent, pslot + 1,
+ BTRFS_MOD_LOG_KEY_REPLACE, GFP_NOFS);
BUG_ON(ret < 0);
btrfs_set_node_key(parent, &disk_key, pslot + 1);
btrfs_mark_buffer_dirty(parent);
@@ -2159,12 +1279,13 @@ static void reada_for_search(struct btrfs_fs_info *fs_info,
u64 search;
u64 target;
u64 nread = 0;
+ u64 nread_max;
struct extent_buffer *eb;
u32 nr;
u32 blocksize;
u32 nscan = 0;
- if (level != 1)
+ if (level != 1 && path->reada != READA_FORWARD_ALWAYS)
return;
if (!path->nodes[level])
@@ -2172,6 +1293,20 @@ static void reada_for_search(struct btrfs_fs_info *fs_info,
node = path->nodes[level];
+ /*
+ * Since the time between visiting leaves is much shorter than the time
+ * between visiting nodes, limit read ahead of nodes to 1, to avoid too
+ * much IO at once (possibly random).
+ */
+ if (path->reada == READA_FORWARD_ALWAYS) {
+ if (level > 1)
+ nread_max = node->fs_info->nodesize;
+ else
+ nread_max = SZ_128K;
+ } else {
+ nread_max = SZ_64K;
+ }
+
search = btrfs_node_blockptr(node, slot);
blocksize = fs_info->nodesize;
eb = find_extent_buffer(fs_info, search);
@@ -2190,7 +1325,8 @@ static void reada_for_search(struct btrfs_fs_info *fs_info,
if (nr == 0)
break;
nr--;
- } else if (path->reada == READA_FORWARD) {
+ } else if (path->reada == READA_FORWARD ||
+ path->reada == READA_FORWARD_ALWAYS) {
nr++;
if (nr >= nritems)
break;
@@ -2201,13 +1337,14 @@ static void reada_for_search(struct btrfs_fs_info *fs_info,
break;
}
search = btrfs_node_blockptr(node, nr);
- if ((search <= target && target - search <= 65536) ||
+ if (path->reada == READA_FORWARD_ALWAYS ||
+ (search <= target && target - search <= 65536) ||
(search > target && search - target <= 65536)) {
btrfs_readahead_node_child(node, nr);
nread += blocksize;
}
nscan++;
- if ((nread > 65536 || nscan > 32))
+ if (nread > nread_max || nscan > 32)
break;
}
}
@@ -2316,6 +1453,9 @@ read_block_for_search(struct btrfs_root *root, struct btrfs_path *p,
tmp = find_extent_buffer(fs_info, blocknr);
if (tmp) {
+ if (p->reada == READA_FORWARD_ALWAYS)
+ reada_for_search(fs_info, p, level, slot, key->objectid);
+
/* first we do an atomic uptodate check */
if (btrfs_buffer_uptodate(tmp, gen, 1) > 0) {
/*
@@ -2859,7 +1999,7 @@ int btrfs_search_old_slot(struct btrfs_root *root, const struct btrfs_key *key,
}
again:
- b = get_old_root(root, time_seq);
+ b = btrfs_get_old_root(root, time_seq);
if (!b) {
ret = -EIO;
goto done;
@@ -2914,7 +2054,7 @@ again:
level = btrfs_header_level(b);
btrfs_tree_read_lock(b);
- b = tree_mod_log_rewind(fs_info, p, b, time_seq);
+ b = btrfs_tree_mod_log_rewind(fs_info, p, b, time_seq);
if (!b) {
ret = -ENOMEM;
goto done;
@@ -3028,8 +2168,8 @@ static void fixup_low_keys(struct btrfs_path *path,
if (!path->nodes[i])
break;
t = path->nodes[i];
- ret = tree_mod_log_insert_key(t, tslot, MOD_LOG_KEY_REPLACE,
- GFP_ATOMIC);
+ ret = btrfs_tree_mod_log_insert_key(t, tslot,
+ BTRFS_MOD_LOG_KEY_REPLACE, GFP_ATOMIC);
BUG_ON(ret < 0);
btrfs_set_node_key(t, key, tslot);
btrfs_mark_buffer_dirty(path->nodes[i]);
@@ -3192,7 +2332,7 @@ static int push_node_left(struct btrfs_trans_handle *trans,
btrfs_abort_transaction(trans, ret);
return ret;
}
- ret = tree_mod_log_eb_copy(dst, src, dst_nritems, 0, push_items);
+ ret = btrfs_tree_mod_log_eb_copy(dst, src, dst_nritems, 0, push_items);
if (ret) {
btrfs_abort_transaction(trans, ret);
return ret;
@@ -3204,8 +2344,8 @@ static int push_node_left(struct btrfs_trans_handle *trans,
if (push_items < src_nritems) {
/*
- * Don't call tree_mod_log_insert_move here, key removal was
- * already fully logged by tree_mod_log_eb_copy above.
+ * Don't call btrfs_tree_mod_log_insert_move() here, key removal
+ * was already fully logged by btrfs_tree_mod_log_eb_copy() above.
*/
memmove_extent_buffer(src, btrfs_node_key_ptr_offset(0),
btrfs_node_key_ptr_offset(push_items),
@@ -3266,15 +2406,15 @@ static int balance_node_right(struct btrfs_trans_handle *trans,
btrfs_abort_transaction(trans, ret);
return ret;
}
- ret = tree_mod_log_insert_move(dst, push_items, 0, dst_nritems);
+ ret = btrfs_tree_mod_log_insert_move(dst, push_items, 0, dst_nritems);
BUG_ON(ret < 0);
memmove_extent_buffer(dst, btrfs_node_key_ptr_offset(push_items),
btrfs_node_key_ptr_offset(0),
(dst_nritems) *
sizeof(struct btrfs_key_ptr));
- ret = tree_mod_log_eb_copy(dst, src, 0, src_nritems - push_items,
- push_items);
+ ret = btrfs_tree_mod_log_eb_copy(dst, src, 0, src_nritems - push_items,
+ push_items);
if (ret) {
btrfs_abort_transaction(trans, ret);
return ret;
@@ -3340,7 +2480,7 @@ static noinline int insert_new_root(struct btrfs_trans_handle *trans,
btrfs_mark_buffer_dirty(c);
old = root->node;
- ret = tree_mod_log_insert_root(root->node, c, 0);
+ ret = btrfs_tree_mod_log_insert_root(root->node, c, false);
BUG_ON(ret < 0);
rcu_assign_pointer(root->node, c);
@@ -3379,8 +2519,8 @@ static void insert_ptr(struct btrfs_trans_handle *trans,
BUG_ON(nritems == BTRFS_NODEPTRS_PER_BLOCK(trans->fs_info));
if (slot != nritems) {
if (level) {
- ret = tree_mod_log_insert_move(lower, slot + 1, slot,
- nritems - slot);
+ ret = btrfs_tree_mod_log_insert_move(lower, slot + 1,
+ slot, nritems - slot);
BUG_ON(ret < 0);
}
memmove_extent_buffer(lower,
@@ -3389,8 +2529,8 @@ static void insert_ptr(struct btrfs_trans_handle *trans,
(nritems - slot) * sizeof(struct btrfs_key_ptr));
}
if (level) {
- ret = tree_mod_log_insert_key(lower, slot, MOD_LOG_KEY_ADD,
- GFP_NOFS);
+ ret = btrfs_tree_mod_log_insert_key(lower, slot,
+ BTRFS_MOD_LOG_KEY_ADD, GFP_NOFS);
BUG_ON(ret < 0);
}
btrfs_set_node_key(lower, key, slot);
@@ -3431,9 +2571,9 @@ static noinline int split_node(struct btrfs_trans_handle *trans,
* tree mod log: We don't log_removal old root in
* insert_new_root, because that root buffer will be kept as a
* normal node. We are going to log removal of half of the
- * elements below with tree_mod_log_eb_copy. We're holding a
- * tree lock on the buffer, which is why we cannot race with
- * other tree_mod_log users.
+ * elements below with btrfs_tree_mod_log_eb_copy(). We're
+ * holding a tree lock on the buffer, which is why we cannot
+ * race with other tree_mod_log users.
*/
ret = insert_new_root(trans, root, path, level + 1);
if (ret)
@@ -3460,7 +2600,7 @@ static noinline int split_node(struct btrfs_trans_handle *trans,
root_add_used(root, fs_info->nodesize);
ASSERT(btrfs_header_level(c) == level);
- ret = tree_mod_log_eb_copy(split, c, 0, mid, c_nritems - mid);
+ ret = btrfs_tree_mod_log_eb_copy(split, c, 0, mid, c_nritems - mid);
if (ret) {
btrfs_abort_transaction(trans, ret);
return ret;
@@ -4842,8 +3982,8 @@ static void del_ptr(struct btrfs_root *root, struct btrfs_path *path,
nritems = btrfs_header_nritems(parent);
if (slot != nritems - 1) {
if (level) {
- ret = tree_mod_log_insert_move(parent, slot, slot + 1,
- nritems - slot - 1);
+ ret = btrfs_tree_mod_log_insert_move(parent, slot,
+ slot + 1, nritems - slot - 1);
BUG_ON(ret < 0);
}
memmove_extent_buffer(parent,
@@ -4852,8 +3992,8 @@ static void del_ptr(struct btrfs_root *root, struct btrfs_path *path,
sizeof(struct btrfs_key_ptr) *
(nritems - slot - 1));
} else if (level) {
- ret = tree_mod_log_insert_key(parent, slot, MOD_LOG_KEY_REMOVE,
- GFP_NOFS);
+ ret = btrfs_tree_mod_log_insert_key(parent, slot,
+ BTRFS_MOD_LOG_KEY_REMOVE, GFP_NOFS);
BUG_ON(ret < 0);
}
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 9ae776ab3967..f83fd3cbf243 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -342,6 +342,27 @@ struct btrfs_node {
struct btrfs_key_ptr ptrs[];
} __attribute__ ((__packed__));
+/* Read ahead values for struct btrfs_path.reada */
+enum {
+ READA_NONE,
+ READA_BACK,
+ READA_FORWARD,
+ /*
+ * Similar to READA_FORWARD but unlike it:
+ *
+ * 1) It will trigger readahead even for leaves that are not close to
+ * each other on disk;
+ * 2) It also triggers readahead for nodes;
+ * 3) During a search, even when a node or leaf is already in memory, it
+ * will still trigger readahead for other nodes and leaves that follow
+ * it.
+ *
+ * This is meant to be used only when we know we are iterating over the
+ * entire tree or a very large part of it.
+ */
+ READA_FORWARD_ALWAYS,
+};
+
/*
* btrfs_paths remember the path taken from the root down to the leaf.
* level 0 is always the leaf, and nodes[1...BTRFS_MAX_LEVEL] will point
@@ -350,7 +371,6 @@ struct btrfs_node {
* The slots array records the index of the item or block pointer
* used while walking the tree.
*/
-enum { READA_NONE, READA_BACK, READA_FORWARD };
struct btrfs_path {
struct extent_buffer *nodes[BTRFS_MAX_LEVEL];
int slots[BTRFS_MAX_LEVEL];
@@ -482,16 +502,6 @@ struct btrfs_discard_ctl {
atomic64_t discard_bytes_saved;
};
-/* delayed seq elem */
-struct seq_list {
- struct list_head list;
- u64 seq;
-};
-
-#define SEQ_LIST_INIT(name) { .list = LIST_HEAD_INIT((name).list), .seq = 0 }
-
-#define SEQ_LAST ((u64)-1)
-
enum btrfs_orphan_cleanup_state {
ORPHAN_CLEANUP_STARTED = 1,
ORPHAN_CLEANUP_DONE = 2,
@@ -572,6 +582,15 @@ enum {
/* Indicate that we can't trust the free space tree for caching yet */
BTRFS_FS_FREE_SPACE_TREE_UNTRUSTED,
+
+ /* Indicate whether there are any tree modification log users */
+ BTRFS_FS_TREE_MOD_LOG_USERS,
+
+#if BITS_PER_LONG == 32
+ /* Indicate if we have error/warn message printed on 32bit systems */
+ BTRFS_FS_32BIT_ERROR,
+ BTRFS_FS_32BIT_WARN,
+#endif
};
/*
@@ -941,10 +960,16 @@ struct btrfs_fs_info {
struct work_struct async_data_reclaim_work;
struct work_struct preempt_reclaim_work;
+ /* Reclaim partially filled block groups in the background */
+ struct work_struct reclaim_bgs_work;
+ struct list_head reclaim_bgs;
+ int bg_reclaim_threshold;
+
spinlock_t unused_bgs_lock;
struct list_head unused_bgs;
struct mutex unused_bg_unpin_mutex;
- struct mutex delete_unused_bgs_mutex;
+ /* Protect block groups that are going to be deleted */
+ struct mutex reclaim_bgs_lock;
/* Cached block sizes */
u32 nodesize;
@@ -2691,7 +2716,6 @@ int btrfs_finish_extent_commit(struct btrfs_trans_handle *trans);
int btrfs_inc_extent_ref(struct btrfs_trans_handle *trans,
struct btrfs_ref *generic_ref);
-int btrfs_extent_readonly(struct btrfs_fs_info *fs_info, u64 bytenr);
void btrfs_clear_space_info_full(struct btrfs_fs_info *info);
/*
@@ -2929,13 +2953,6 @@ static inline void btrfs_clear_sb_rdonly(struct super_block *sb)
clear_bit(BTRFS_FS_STATE_RO, &btrfs_sb(sb)->fs_state);
}
-/* tree mod log functions from ctree.c */
-u64 btrfs_get_tree_mod_seq(struct btrfs_fs_info *fs_info,
- struct seq_list *elem);
-void btrfs_put_tree_mod_seq(struct btrfs_fs_info *fs_info,
- struct seq_list *elem);
-int btrfs_old_root_level(struct btrfs_root *root, u64 time_seq);
-
/* root-item.c */
int btrfs_add_root_ref(struct btrfs_trans_handle *trans, u64 root_id,
u64 ref_id, u64 dirid, u64 sequence, const char *name,
@@ -3084,7 +3101,7 @@ u64 btrfs_file_extent_end(const struct btrfs_path *path);
blk_status_t btrfs_submit_data_bio(struct inode *inode, struct bio *bio,
int mirror_num, unsigned long bio_flags);
int btrfs_verify_data_csum(struct btrfs_io_bio *io_bio, u32 bio_offset,
- struct page *page, u64 start, u64 end, int mirror);
+ struct page *page, u64 start, u64 end);
struct extent_map *btrfs_get_extent_fiemap(struct btrfs_inode *inode,
u64 start, u64 len);
noinline int can_nocow_extent(struct inode *inode, u64 offset, u64 *len,
@@ -3179,6 +3196,7 @@ extern const struct iomap_dio_ops btrfs_dio_ops;
/* Inode locking type flags, by default the exclusive lock is taken */
#define BTRFS_ILOCK_SHARED (1U << 0)
#define BTRFS_ILOCK_TRY (1U << 1)
+#define BTRFS_ILOCK_MMAP (1U << 2)
int btrfs_inode_lock(struct inode *inode, unsigned int ilock_flags);
void btrfs_inode_unlock(struct inode *inode, unsigned int ilock_flags);
@@ -3189,6 +3207,9 @@ void btrfs_update_inode_bytes(struct btrfs_inode *inode,
/* ioctl.c */
long btrfs_ioctl(struct file *file, unsigned int cmd, unsigned long arg);
long btrfs_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg);
+int btrfs_fileattr_get(struct dentry *dentry, struct fileattr *fa);
+int btrfs_fileattr_set(struct user_namespace *mnt_userns,
+ struct dentry *dentry, struct fileattr *fa);
int btrfs_ioctl_get_supported_features(void __user *arg);
void btrfs_sync_inode_flags_to_i_flags(struct inode *inode);
int __pure btrfs_is_empty_uuid(u8 *uuid);
@@ -3217,8 +3238,9 @@ extern const struct file_operations btrfs_file_operations;
int btrfs_drop_extents(struct btrfs_trans_handle *trans,
struct btrfs_root *root, struct btrfs_inode *inode,
struct btrfs_drop_extents_args *args);
-int btrfs_replace_file_extents(struct inode *inode, struct btrfs_path *path,
- const u64 start, const u64 end,
+int btrfs_replace_file_extents(struct btrfs_inode *inode,
+ struct btrfs_path *path, const u64 start,
+ const u64 end,
struct btrfs_replace_extent_info *extent_info,
struct btrfs_trans_handle **trans_out);
int btrfs_mark_extent_written(struct btrfs_trans_handle *trans,
@@ -3405,6 +3427,19 @@ static inline void assertfail(const char *expr, const char* file, int line) { }
#define ASSERT(expr) (void)(expr)
#endif
+#if BITS_PER_LONG == 32
+#define BTRFS_32BIT_MAX_FILE_SIZE (((u64)ULONG_MAX + 1) << PAGE_SHIFT)
+/*
+ * The warning threshold is 5/8th of the MAX_LFS_FILESIZE that limits the logical
+ * addresses of extents.
+ *
+ * For 4K page size it's about 10T, for 64K it's 160T.
+ */
+#define BTRFS_32BIT_EARLY_WARN_THRESHOLD (BTRFS_32BIT_MAX_FILE_SIZE * 5 / 8)
+void btrfs_warn_32bit_limit(struct btrfs_fs_info *fs_info);
+void btrfs_err_32bit_limit(struct btrfs_fs_info *fs_info);
+#endif
+
/*
* Get the correct offset inside the page of extent buffer.
*
@@ -3732,8 +3767,6 @@ static inline int btrfs_defrag_cancelled(struct btrfs_fs_info *fs_info)
return signal_pending(current);
}
-#define in_range(b, first, len) ((b) >= (first) && (b) < (first) + (len))
-
/* Sanity test specific functions */
#ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS
void btrfs_test_destroy_inode(struct inode *inode);
diff --git a/fs/btrfs/delayed-inode.c b/fs/btrfs/delayed-inode.c
index bf25401c9768..1a88f6214ebc 100644
--- a/fs/btrfs/delayed-inode.c
+++ b/fs/btrfs/delayed-inode.c
@@ -602,7 +602,6 @@ static void btrfs_delayed_item_release_metadata(struct btrfs_root *root,
static int btrfs_delayed_inode_reserve_metadata(
struct btrfs_trans_handle *trans,
struct btrfs_root *root,
- struct btrfs_inode *inode,
struct btrfs_delayed_node *node)
{
struct btrfs_fs_info *fs_info = root->fs_info;
@@ -633,32 +632,17 @@ static int btrfs_delayed_inode_reserve_metadata(
return ret;
ret = btrfs_block_rsv_add(root, dst_rsv, num_bytes,
BTRFS_RESERVE_NO_FLUSH);
- /*
- * Since we're under a transaction reserve_metadata_bytes could
- * try to commit the transaction which will make it return
- * EAGAIN to make us stop the transaction we have, so return
- * ENOSPC instead so that btrfs_dirty_inode knows what to do.
- */
- if (ret == -EAGAIN) {
- ret = -ENOSPC;
- btrfs_qgroup_free_meta_prealloc(root, num_bytes);
- }
- if (!ret) {
- node->bytes_reserved = num_bytes;
- trace_btrfs_space_reservation(fs_info,
- "delayed_inode",
- btrfs_ino(inode),
- num_bytes, 1);
- } else {
+ /* NO_FLUSH could only fail with -ENOSPC */
+ ASSERT(ret == 0 || ret == -ENOSPC);
+ if (ret)
btrfs_qgroup_free_meta_prealloc(root, num_bytes);
- }
- return ret;
+ } else {
+ ret = btrfs_block_rsv_migrate(src_rsv, dst_rsv, num_bytes, true);
}
- ret = btrfs_block_rsv_migrate(src_rsv, dst_rsv, num_bytes, true);
if (!ret) {
trace_btrfs_space_reservation(fs_info, "delayed_inode",
- btrfs_ino(inode), num_bytes, 1);
+ node->inode_id, num_bytes, 1);
node->bytes_reserved = num_bytes;
}
@@ -1589,8 +1573,8 @@ bool btrfs_readdir_get_delayed_items(struct inode *inode,
* We can only do one readdir with delayed items at a time because of
* item->readdir_list.
*/
- inode_unlock_shared(inode);
- inode_lock(inode);
+ btrfs_inode_unlock(inode, BTRFS_ILOCK_SHARED);
+ btrfs_inode_lock(inode, 0);
mutex_lock(&delayed_node->mutex);
item = __btrfs_first_delayed_insertion_item(delayed_node);
@@ -1833,8 +1817,7 @@ int btrfs_delayed_update_inode(struct btrfs_trans_handle *trans,
goto release_node;
}
- ret = btrfs_delayed_inode_reserve_metadata(trans, root, inode,
- delayed_node);
+ ret = btrfs_delayed_inode_reserve_metadata(trans, root, delayed_node);
if (ret)
goto release_node;
diff --git a/fs/btrfs/delayed-ref.c b/fs/btrfs/delayed-ref.c
index 63be7d01a9a3..c92d9d4f5f46 100644
--- a/fs/btrfs/delayed-ref.c
+++ b/fs/btrfs/delayed-ref.c
@@ -11,6 +11,7 @@
#include "transaction.h"
#include "qgroup.h"
#include "space-info.h"
+#include "tree-mod-log.h"
struct kmem_cache *btrfs_delayed_ref_head_cachep;
struct kmem_cache *btrfs_delayed_tree_ref_cachep;
@@ -494,16 +495,7 @@ void btrfs_merge_delayed_refs(struct btrfs_trans_handle *trans,
if (head->is_data)
return;
- read_lock(&fs_info->tree_mod_log_lock);
- if (!list_empty(&fs_info->tree_mod_seq_list)) {
- struct seq_list *elem;
-
- elem = list_first_entry(&fs_info->tree_mod_seq_list,
- struct seq_list, list);
- seq = elem->seq;
- }
- read_unlock(&fs_info->tree_mod_log_lock);
-
+ seq = btrfs_tree_mod_log_lowest_seq(fs_info);
again:
for (node = rb_first_cached(&head->ref_tree); node;
node = rb_next(node)) {
@@ -517,23 +509,16 @@ again:
int btrfs_check_delayed_seq(struct btrfs_fs_info *fs_info, u64 seq)
{
- struct seq_list *elem;
int ret = 0;
+ u64 min_seq = btrfs_tree_mod_log_lowest_seq(fs_info);
- read_lock(&fs_info->tree_mod_log_lock);
- if (!list_empty(&fs_info->tree_mod_seq_list)) {
- elem = list_first_entry(&fs_info->tree_mod_seq_list,
- struct seq_list, list);
- if (seq >= elem->seq) {
- btrfs_debug(fs_info,
- "holding back delayed_ref %#x.%x, lowest is %#x.%x",
- (u32)(seq >> 32), (u32)seq,
- (u32)(elem->seq >> 32), (u32)elem->seq);
- ret = 1;
- }
+ if (min_seq != 0 && seq >= min_seq) {
+ btrfs_debug(fs_info,
+ "holding back delayed_ref %llu, lowest is %llu",
+ seq, min_seq);
+ ret = 1;
}
- read_unlock(&fs_info->tree_mod_log_lock);
return ret;
}
diff --git a/fs/btrfs/dev-replace.c b/fs/btrfs/dev-replace.c
index 3a9c1e046ebe..d05f73530af7 100644
--- a/fs/btrfs/dev-replace.c
+++ b/fs/btrfs/dev-replace.c
@@ -81,6 +81,9 @@ int btrfs_init_dev_replace(struct btrfs_fs_info *fs_info)
struct btrfs_dev_replace_item *ptr;
u64 src_devid;
+ if (!dev_root)
+ return 0;
+
path = btrfs_alloc_path();
if (!path) {
ret = -ENOMEM;
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 41b718cfea40..c9a3036c23bf 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -42,6 +42,7 @@
#include "discard.h"
#include "space-info.h"
#include "zoned.h"
+#include "subpage.h"
#define BTRFS_SUPER_FLAG_SUPP (BTRFS_HEADER_FLAG_WRITTEN |\
BTRFS_HEADER_FLAG_RELOC |\
@@ -440,6 +441,74 @@ static int btree_read_extent_buffer_pages(struct extent_buffer *eb,
return ret;
}
+static int csum_one_extent_buffer(struct extent_buffer *eb)
+{
+ struct btrfs_fs_info *fs_info = eb->fs_info;
+ u8 result[BTRFS_CSUM_SIZE];
+ int ret;
+
+ ASSERT(memcmp_extent_buffer(eb, fs_info->fs_devices->metadata_uuid,
+ offsetof(struct btrfs_header, fsid),
+ BTRFS_FSID_SIZE) == 0);
+ csum_tree_block(eb, result);
+
+ if (btrfs_header_level(eb))
+ ret = btrfs_check_node(eb);
+ else
+ ret = btrfs_check_leaf_full(eb);
+
+ if (ret < 0) {
+ btrfs_print_tree(eb, 0);
+ btrfs_err(fs_info,
+ "block=%llu write time tree block corruption detected",
+ eb->start);
+ WARN_ON(IS_ENABLED(CONFIG_BTRFS_DEBUG));
+ return ret;
+ }
+ write_extent_buffer(eb, result, 0, fs_info->csum_size);
+
+ return 0;
+}
+
+/* Checksum all dirty extent buffers in one bio_vec */
+static int csum_dirty_subpage_buffers(struct btrfs_fs_info *fs_info,
+ struct bio_vec *bvec)
+{
+ struct page *page = bvec->bv_page;
+ u64 bvec_start = page_offset(page) + bvec->bv_offset;
+ u64 cur;
+ int ret = 0;
+
+ for (cur = bvec_start; cur < bvec_start + bvec->bv_len;
+ cur += fs_info->nodesize) {
+ struct extent_buffer *eb;
+ bool uptodate;
+
+ eb = find_extent_buffer(fs_info, cur);
+ uptodate = btrfs_subpage_test_uptodate(fs_info, page, cur,
+ fs_info->nodesize);
+
+ /* A dirty eb shouldn't disappear from buffer_radix */
+ if (WARN_ON(!eb))
+ return -EUCLEAN;
+
+ if (WARN_ON(cur != btrfs_header_bytenr(eb))) {
+ free_extent_buffer(eb);
+ return -EUCLEAN;
+ }
+ if (WARN_ON(!uptodate)) {
+ free_extent_buffer(eb);
+ return -EUCLEAN;
+ }
+
+ ret = csum_one_extent_buffer(eb);
+ free_extent_buffer(eb);
+ if (ret < 0)
+ return ret;
+ }
+ return ret;
+}
+
/*
* Checksum a dirty tree block before IO. This has extra checks to make sure
* we only fill in the checksum field in the first page of a multi-page block.
@@ -450,9 +519,10 @@ static int csum_dirty_buffer(struct btrfs_fs_info *fs_info, struct bio_vec *bvec
struct page *page = bvec->bv_page;
u64 start = page_offset(page);
u64 found_start;
- u8 result[BTRFS_CSUM_SIZE];
struct extent_buffer *eb;
- int ret;
+
+ if (fs_info->sectorsize < PAGE_SIZE)
+ return csum_dirty_subpage_buffers(fs_info, bvec);
eb = (struct extent_buffer *)page->private;
if (page != eb->pages[0])
@@ -474,28 +544,7 @@ static int csum_dirty_buffer(struct btrfs_fs_info *fs_info, struct bio_vec *bvec
if (WARN_ON(!PageUptodate(page)))
return -EUCLEAN;
- ASSERT(memcmp_extent_buffer(eb, fs_info->fs_devices->metadata_uuid,
- offsetof(struct btrfs_header, fsid),
- BTRFS_FSID_SIZE) == 0);
-
- csum_tree_block(eb, result);
-
- if (btrfs_header_level(eb))
- ret = btrfs_check_node(eb);
- else
- ret = btrfs_check_leaf_full(eb);
-
- if (ret < 0) {
- btrfs_print_tree(eb, 0);
- btrfs_err(fs_info,
- "block=%llu write time tree block corruption detected",
- eb->start);
- WARN_ON(IS_ENABLED(CONFIG_BTRFS_DEBUG));
- return ret;
- }
- write_extent_buffer(eb, result, 0, fs_info->csum_size);
-
- return 0;
+ return csum_one_extent_buffer(eb);
}
static int check_tree_block_fsid(struct extent_buffer *eb)
@@ -992,14 +1041,48 @@ static void btree_invalidatepage(struct page *page, unsigned int offset,
static int btree_set_page_dirty(struct page *page)
{
#ifdef DEBUG
+ struct btrfs_fs_info *fs_info = btrfs_sb(page->mapping->host->i_sb);
+ struct btrfs_subpage *subpage;
struct extent_buffer *eb;
+ int cur_bit = 0;
+ u64 page_start = page_offset(page);
+
+ if (fs_info->sectorsize == PAGE_SIZE) {
+ BUG_ON(!PagePrivate(page));
+ eb = (struct extent_buffer *)page->private;
+ BUG_ON(!eb);
+ BUG_ON(!test_bit(EXTENT_BUFFER_DIRTY, &eb->bflags));
+ BUG_ON(!atomic_read(&eb->refs));
+ btrfs_assert_tree_locked(eb);
+ return __set_page_dirty_nobuffers(page);
+ }
+ ASSERT(PagePrivate(page) && page->private);
+ subpage = (struct btrfs_subpage *)page->private;
+
+ ASSERT(subpage->dirty_bitmap);
+ while (cur_bit < BTRFS_SUBPAGE_BITMAP_SIZE) {
+ unsigned long flags;
+ u64 cur;
+ u16 tmp = (1 << cur_bit);
+
+ spin_lock_irqsave(&subpage->lock, flags);
+ if (!(tmp & subpage->dirty_bitmap)) {
+ spin_unlock_irqrestore(&subpage->lock, flags);
+ cur_bit++;
+ continue;
+ }
+ spin_unlock_irqrestore(&subpage->lock, flags);
+ cur = page_start + cur_bit * fs_info->sectorsize;
- BUG_ON(!PagePrivate(page));
- eb = (struct extent_buffer *)page->private;
- BUG_ON(!eb);
- BUG_ON(!test_bit(EXTENT_BUFFER_DIRTY, &eb->bflags));
- BUG_ON(!atomic_read(&eb->refs));
- btrfs_assert_tree_locked(eb);
+ eb = find_extent_buffer(fs_info, cur);
+ ASSERT(eb);
+ ASSERT(test_bit(EXTENT_BUFFER_DIRTY, &eb->bflags));
+ ASSERT(atomic_read(&eb->refs));
+ btrfs_assert_tree_locked(eb);
+ free_extent_buffer(eb);
+
+ cur_bit += (fs_info->nodesize >> fs_info->sectorsize_bits);
+ }
#endif
return __set_page_dirty_nobuffers(page);
}
@@ -1807,14 +1890,21 @@ static int cleaner_kthread(void *arg)
btrfs_run_defrag_inodes(fs_info);
/*
- * Acquires fs_info->delete_unused_bgs_mutex to avoid racing
+ * Acquires fs_info->reclaim_bgs_lock to avoid racing
* with relocation (btrfs_relocate_chunk) and relocation
* acquires fs_info->cleaner_mutex (btrfs_relocate_block_group)
- * after acquiring fs_info->delete_unused_bgs_mutex. So we
+ * after acquiring fs_info->reclaim_bgs_lock. So we
* can't hold, nor need to, fs_info->cleaner_mutex when deleting
* unused block groups.
*/
btrfs_delete_unused_bgs(fs_info);
+
+ /*
+ * Reclaim block groups in the reclaim_bgs list after we deleted
+ * all unused block_groups. This possibly gives us some more free
+ * space.
+ */
+ btrfs_reclaim_bgs(fs_info);
sleep:
clear_and_wake_up_bit(BTRFS_FS_CLEANER_RUNNING, &fs_info->flags);
if (kthread_should_park())
@@ -2387,8 +2477,9 @@ static int btrfs_read_roots(struct btrfs_fs_info *fs_info)
} else {
set_bit(BTRFS_ROOT_TRACK_DIRTY, &root->state);
fs_info->dev_root = root;
- btrfs_init_devices_late(fs_info);
}
+ /* Initialize fs_info for all devices in any case */
+ btrfs_init_devices_late(fs_info);
/* If IGNOREDATACSUMS is set don't bother reading the csum root. */
if (!btrfs_test_opt(fs_info, IGNOREDATACSUMS)) {
@@ -2792,7 +2883,7 @@ void btrfs_init_fs_info(struct btrfs_fs_info *fs_info)
spin_lock_init(&fs_info->treelog_bg_lock);
rwlock_init(&fs_info->tree_mod_log_lock);
mutex_init(&fs_info->unused_bg_unpin_mutex);
- mutex_init(&fs_info->delete_unused_bgs_mutex);
+ mutex_init(&fs_info->reclaim_bgs_lock);
mutex_init(&fs_info->reloc_mutex);
mutex_init(&fs_info->delalloc_root_mutex);
mutex_init(&fs_info->zoned_meta_io_lock);
@@ -2802,6 +2893,7 @@ void btrfs_init_fs_info(struct btrfs_fs_info *fs_info)
INIT_LIST_HEAD(&fs_info->space_info);
INIT_LIST_HEAD(&fs_info->tree_mod_seq_list);
INIT_LIST_HEAD(&fs_info->unused_bgs);
+ INIT_LIST_HEAD(&fs_info->reclaim_bgs);
#ifdef CONFIG_BTRFS_DEBUG
INIT_LIST_HEAD(&fs_info->allocated_roots);
INIT_LIST_HEAD(&fs_info->allocated_ebs);
@@ -2890,6 +2982,9 @@ void btrfs_init_fs_info(struct btrfs_fs_info *fs_info)
fs_info->swapfile_pins = RB_ROOT;
fs_info->send_in_progress = 0;
+
+ fs_info->bg_reclaim_threshold = BTRFS_DEFAULT_RECLAIM_THRESH;
+ INIT_WORK(&fs_info->reclaim_bgs_work, btrfs_reclaim_bgs_work);
}
static int init_mount_fs_info(struct btrfs_fs_info *fs_info, struct super_block *sb)
@@ -3009,6 +3104,21 @@ int btrfs_start_pre_rw_mount(struct btrfs_fs_info *fs_info)
}
}
+ /*
+ * btrfs_find_orphan_roots() is responsible for finding all the dead
+ * roots (with 0 refs), flag them with BTRFS_ROOT_DEAD_TREE and load
+ * them into the fs_info->fs_roots_radix tree. This must be done before
+ * calling btrfs_orphan_cleanup() on the tree root. If we don't do it
+ * first, then btrfs_orphan_cleanup() will delete a dead root's orphan
+ * item before the root's tree is deleted - this means that if we unmount
+ * or crash before the deletion completes, on the next mount we will not
+ * delete what remains of the tree because the orphan item does not
+ * exists anymore, which is what tells us we have a pending deletion.
+ */
+ ret = btrfs_find_orphan_roots(fs_info);
+ if (ret)
+ goto out;
+
ret = btrfs_cleanup_fs_roots(fs_info);
if (ret)
goto out;
@@ -3068,7 +3178,6 @@ int btrfs_start_pre_rw_mount(struct btrfs_fs_info *fs_info)
}
}
- ret = btrfs_find_orphan_roots(fs_info);
out:
return ret;
}
@@ -4234,6 +4343,8 @@ void __cold close_ctree(struct btrfs_fs_info *fs_info)
cancel_work_sync(&fs_info->async_data_reclaim_work);
cancel_work_sync(&fs_info->preempt_reclaim_work);
+ cancel_work_sync(&fs_info->reclaim_bgs_work);
+
/* Cancel or finish ongoing discard work */
btrfs_discard_cleanup(fs_info);
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 78ad31a59e59..7a28314189b4 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -2490,19 +2490,6 @@ int btrfs_dec_ref(struct btrfs_trans_handle *trans, struct btrfs_root *root,
return __btrfs_mod_ref(trans, root, buf, full_backref, 0);
}
-int btrfs_extent_readonly(struct btrfs_fs_info *fs_info, u64 bytenr)
-{
- struct btrfs_block_group *block_group;
- int readonly = 0;
-
- block_group = btrfs_lookup_block_group(fs_info, bytenr);
- if (!block_group || block_group->ro)
- readonly = 1;
- if (block_group)
- btrfs_put_block_group(block_group);
- return readonly;
-}
-
static u64 get_alloc_profile_by_root(struct btrfs_root *root, int data)
{
struct btrfs_fs_info *fs_info = root->fs_info;
@@ -3323,6 +3310,7 @@ void btrfs_free_tree_block(struct btrfs_trans_handle *trans,
if (last_ref && btrfs_header_generation(buf) == trans->transid) {
struct btrfs_block_group *cache;
+ bool must_pin = false;
if (root->root_key.objectid != BTRFS_TREE_LOG_OBJECTID) {
ret = check_ref_cleanup(trans, buf->start);
@@ -3340,7 +3328,25 @@ void btrfs_free_tree_block(struct btrfs_trans_handle *trans,
goto out;
}
- if (btrfs_is_zoned(fs_info)) {
+ /*
+ * If this is a leaf and there are tree mod log users, we may
+ * have recorded mod log operations that point to this leaf.
+ * So we must make sure no one reuses this leaf's extent before
+ * mod log operations are applied to a node, otherwise after
+ * rewinding a node using the mod log operations we get an
+ * inconsistent btree, as the leaf's extent may now be used as
+ * a node or leaf for another different btree.
+ * We are safe from races here because at this point no other
+ * node or root points to this extent buffer, so if after this
+ * check a new tree mod log user joins, it will not be able to
+ * find a node pointing to this leaf and record operations that
+ * point to this leaf.
+ */
+ if (btrfs_header_level(buf) == 0 &&
+ test_bit(BTRFS_FS_TREE_MOD_LOG_USERS, &fs_info->flags))
+ must_pin = true;
+
+ if (must_pin || btrfs_is_zoned(fs_info)) {
btrfs_redirty_list_add(trans->transaction, buf);
pin_down_extent(trans, cache, buf->start, buf->len, 1);
btrfs_put_block_group(cache);
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index 191e358f1322..f2d1bb234377 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -13,6 +13,7 @@
#include <linux/pagevec.h>
#include <linux/prefetch.h>
#include <linux/cleancache.h>
+#include "misc.h"
#include "extent_io.h"
#include "extent-io-tree.h"
#include "extent_map.h"
@@ -2886,6 +2887,35 @@ static void end_page_read(struct page *page, bool uptodate, u64 start, u32 len)
}
/*
+ * Find extent buffer for a givne bytenr.
+ *
+ * This is for end_bio_extent_readpage(), thus we can't do any unsafe locking
+ * in endio context.
+ */
+static struct extent_buffer *find_extent_buffer_readpage(
+ struct btrfs_fs_info *fs_info, struct page *page, u64 bytenr)
+{
+ struct extent_buffer *eb;
+
+ /*
+ * For regular sectorsize, we can use page->private to grab extent
+ * buffer
+ */
+ if (fs_info->sectorsize == PAGE_SIZE) {
+ ASSERT(PagePrivate(page) && page->private);
+ return (struct extent_buffer *)page->private;
+ }
+
+ /* For subpage case, we need to lookup buffer radix tree */
+ rcu_read_lock();
+ eb = radix_tree_lookup(&fs_info->buffer_radix,
+ bytenr >> fs_info->sectorsize_bits);
+ rcu_read_unlock();
+ ASSERT(eb);
+ return eb;
+}
+
+/*
* after a readpage IO is done, we need to:
* clear the uptodate bits on error
* set the uptodate bits if things worked
@@ -2954,8 +2984,7 @@ static void end_bio_extent_readpage(struct bio *bio)
if (likely(uptodate)) {
if (is_data_inode(inode))
ret = btrfs_verify_data_csum(io_bio,
- bio_offset, page, start, end,
- mirror);
+ bio_offset, page, start, end);
else
ret = btrfs_validate_metadata_buffer(io_bio,
page, start, end, mirror);
@@ -2996,7 +3025,7 @@ static void end_bio_extent_readpage(struct bio *bio)
} else {
struct extent_buffer *eb;
- eb = (struct extent_buffer *)page->private;
+ eb = find_extent_buffer_readpage(fs_info, page, start);
set_bit(EXTENT_BUFFER_READ_ERR, &eb->bflags);
eb->read_mirror = mirror;
atomic_dec(&eb->io_pages);
@@ -3020,7 +3049,7 @@ readpage_ok:
*/
if (page->index == end_index && i_size <= end) {
u32 zero_start = max(offset_in_page(i_size),
- offset_in_page(end));
+ offset_in_page(start));
zero_user_segment(page, zero_start,
offset_in_page(end) + 1);
@@ -3938,7 +3967,13 @@ static noinline_for_stack int lock_extent_buffer_for_io(struct extent_buffer *eb
btrfs_tree_unlock(eb);
- if (!ret)
+ /*
+ * Either we don't need to submit any tree block, or we're submitting
+ * subpage eb.
+ * Subpage metadata doesn't use page locking at all, so we can skip
+ * the page locking.
+ */
+ if (!ret || fs_info->sectorsize < PAGE_SIZE)
return ret;
num_pages = num_extent_pages(eb);
@@ -3983,12 +4018,11 @@ err_unlock:
return ret;
}
-static void set_btree_ioerr(struct page *page)
+static void set_btree_ioerr(struct page *page, struct extent_buffer *eb)
{
- struct extent_buffer *eb = (struct extent_buffer *)page->private;
- struct btrfs_fs_info *fs_info;
+ struct btrfs_fs_info *fs_info = eb->fs_info;
- SetPageError(page);
+ btrfs_page_set_error(fs_info, page, eb->start, eb->len);
if (test_and_set_bit(EXTENT_BUFFER_WRITE_ERR, &eb->bflags))
return;
@@ -3996,7 +4030,6 @@ static void set_btree_ioerr(struct page *page)
* If we error out, we should add back the dirty_metadata_bytes
* to make it consistent.
*/
- fs_info = eb->fs_info;
percpu_counter_add_batch(&fs_info->dirty_metadata_bytes,
eb->len, fs_info->dirty_metadata_batch);
@@ -4040,26 +4073,111 @@ static void set_btree_ioerr(struct page *page)
*/
switch (eb->log_index) {
case -1:
- set_bit(BTRFS_FS_BTREE_ERR, &eb->fs_info->flags);
+ set_bit(BTRFS_FS_BTREE_ERR, &fs_info->flags);
break;
case 0:
- set_bit(BTRFS_FS_LOG1_ERR, &eb->fs_info->flags);
+ set_bit(BTRFS_FS_LOG1_ERR, &fs_info->flags);
break;
case 1:
- set_bit(BTRFS_FS_LOG2_ERR, &eb->fs_info->flags);
+ set_bit(BTRFS_FS_LOG2_ERR, &fs_info->flags);
break;
default:
BUG(); /* unexpected, logic error */
}
}
+/*
+ * The endio specific version which won't touch any unsafe spinlock in endio
+ * context.
+ */
+static struct extent_buffer *find_extent_buffer_nolock(
+ struct btrfs_fs_info *fs_info, u64 start)
+{
+ struct extent_buffer *eb;
+
+ rcu_read_lock();
+ eb = radix_tree_lookup(&fs_info->buffer_radix,
+ start >> fs_info->sectorsize_bits);
+ if (eb && atomic_inc_not_zero(&eb->refs)) {
+ rcu_read_unlock();
+ return eb;
+ }
+ rcu_read_unlock();
+ return NULL;
+}
+
+/*
+ * The endio function for subpage extent buffer write.
+ *
+ * Unlike end_bio_extent_buffer_writepage(), we only call end_page_writeback()
+ * after all extent buffers in the page has finished their writeback.
+ */
+static void end_bio_subpage_eb_writepage(struct btrfs_fs_info *fs_info,
+ struct bio *bio)
+{
+ struct bio_vec *bvec;
+ struct bvec_iter_all iter_all;
+
+ ASSERT(!bio_flagged(bio, BIO_CLONED));
+ bio_for_each_segment_all(bvec, bio, iter_all) {
+ struct page *page = bvec->bv_page;
+ u64 bvec_start = page_offset(page) + bvec->bv_offset;
+ u64 bvec_end = bvec_start + bvec->bv_len - 1;
+ u64 cur_bytenr = bvec_start;
+
+ ASSERT(IS_ALIGNED(bvec->bv_len, fs_info->nodesize));
+
+ /* Iterate through all extent buffers in the range */
+ while (cur_bytenr <= bvec_end) {
+ struct extent_buffer *eb;
+ int done;
+
+ /*
+ * Here we can't use find_extent_buffer(), as it may
+ * try to lock eb->refs_lock, which is not safe in endio
+ * context.
+ */
+ eb = find_extent_buffer_nolock(fs_info, cur_bytenr);
+ ASSERT(eb);
+
+ cur_bytenr = eb->start + eb->len;
+
+ ASSERT(test_bit(EXTENT_BUFFER_WRITEBACK, &eb->bflags));
+ done = atomic_dec_and_test(&eb->io_pages);
+ ASSERT(done);
+
+ if (bio->bi_status ||
+ test_bit(EXTENT_BUFFER_WRITE_ERR, &eb->bflags)) {
+ ClearPageUptodate(page);
+ set_btree_ioerr(page, eb);
+ }
+
+ btrfs_subpage_clear_writeback(fs_info, page, eb->start,
+ eb->len);
+ end_extent_buffer_writeback(eb);
+ /*
+ * free_extent_buffer() will grab spinlock which is not
+ * safe in endio context. Thus here we manually dec
+ * the ref.
+ */
+ atomic_dec(&eb->refs);
+ }
+ }
+ bio_put(bio);
+}
+
static void end_bio_extent_buffer_writepage(struct bio *bio)
{
+ struct btrfs_fs_info *fs_info;
struct bio_vec *bvec;
struct extent_buffer *eb;
int done;
struct bvec_iter_all iter_all;
+ fs_info = btrfs_sb(bio_first_page_all(bio)->mapping->host->i_sb);
+ if (fs_info->sectorsize < PAGE_SIZE)
+ return end_bio_subpage_eb_writepage(fs_info, bio);
+
ASSERT(!bio_flagged(bio, BIO_CLONED));
bio_for_each_segment_all(bvec, bio, iter_all) {
struct page *page = bvec->bv_page;
@@ -4071,7 +4189,7 @@ static void end_bio_extent_buffer_writepage(struct bio *bio)
if (bio->bi_status ||
test_bit(EXTENT_BUFFER_WRITE_ERR, &eb->bflags)) {
ClearPageUptodate(page);
- set_btree_ioerr(page);
+ set_btree_ioerr(page, eb);
}
end_page_writeback(page);
@@ -4085,6 +4203,56 @@ static void end_bio_extent_buffer_writepage(struct bio *bio)
bio_put(bio);
}
+/*
+ * Unlike the work in write_one_eb(), we rely completely on extent locking.
+ * Page locking is only utilized at minimum to keep the VMM code happy.
+ *
+ * Caller should still call write_one_eb() other than this function directly.
+ * As write_one_eb() has extra preparation before submitting the extent buffer.
+ */
+static int write_one_subpage_eb(struct extent_buffer *eb,
+ struct writeback_control *wbc,
+ struct extent_page_data *epd)
+{
+ struct btrfs_fs_info *fs_info = eb->fs_info;
+ struct page *page = eb->pages[0];
+ unsigned int write_flags = wbc_to_write_flags(wbc) | REQ_META;
+ bool no_dirty_ebs = false;
+ int ret;
+
+ /* clear_page_dirty_for_io() in subpage helper needs page locked */
+ lock_page(page);
+ btrfs_subpage_set_writeback(fs_info, page, eb->start, eb->len);
+
+ /* Check if this is the last dirty bit to update nr_written */
+ no_dirty_ebs = btrfs_subpage_clear_and_test_dirty(fs_info, page,
+ eb->start, eb->len);
+ if (no_dirty_ebs)
+ clear_page_dirty_for_io(page);
+
+ ret = submit_extent_page(REQ_OP_WRITE | write_flags, wbc, page,
+ eb->start, eb->len, eb->start - page_offset(page),
+ &epd->bio, end_bio_extent_buffer_writepage, 0, 0, 0,
+ false);
+ if (ret) {
+ btrfs_subpage_clear_writeback(fs_info, page, eb->start, eb->len);
+ set_btree_ioerr(page, eb);
+ unlock_page(page);
+
+ if (atomic_dec_and_test(&eb->io_pages))
+ end_extent_buffer_writeback(eb);
+ return -EIO;
+ }
+ unlock_page(page);
+ /*
+ * Submission finished without problem, if no range of the page is
+ * dirty anymore, we have submitted a page. Update nr_written in wbc.
+ */
+ if (no_dirty_ebs)
+ update_nr_written(wbc, 1);
+ return ret;
+}
+
static noinline_for_stack int write_one_eb(struct extent_buffer *eb,
struct writeback_control *wbc,
struct extent_page_data *epd)
@@ -4116,6 +4284,9 @@ static noinline_for_stack int write_one_eb(struct extent_buffer *eb,
memzero_extent_buffer(eb, start, end - start);
}
+ if (eb->fs_info->sectorsize < PAGE_SIZE)
+ return write_one_subpage_eb(eb, wbc, epd);
+
for (i = 0; i < num_pages; i++) {
struct page *p = eb->pages[i];
@@ -4127,7 +4298,7 @@ static noinline_for_stack int write_one_eb(struct extent_buffer *eb,
end_bio_extent_buffer_writepage,
0, 0, 0, false);
if (ret) {
- set_btree_ioerr(p);
+ set_btree_ioerr(p, eb);
if (PageWriteback(p))
end_page_writeback(p);
if (atomic_sub_and_test(num_pages - i, &eb->io_pages))
@@ -4152,6 +4323,98 @@ static noinline_for_stack int write_one_eb(struct extent_buffer *eb,
}
/*
+ * Submit one subpage btree page.
+ *
+ * The main difference to submit_eb_page() is:
+ * - Page locking
+ * For subpage, we don't rely on page locking at all.
+ *
+ * - Flush write bio
+ * We only flush bio if we may be unable to fit current extent buffers into
+ * current bio.
+ *
+ * Return >=0 for the number of submitted extent buffers.
+ * Return <0 for fatal error.
+ */
+static int submit_eb_subpage(struct page *page,
+ struct writeback_control *wbc,
+ struct extent_page_data *epd)
+{
+ struct btrfs_fs_info *fs_info = btrfs_sb(page->mapping->host->i_sb);
+ int submitted = 0;
+ u64 page_start = page_offset(page);
+ int bit_start = 0;
+ const int nbits = BTRFS_SUBPAGE_BITMAP_SIZE;
+ int sectors_per_node = fs_info->nodesize >> fs_info->sectorsize_bits;
+ int ret;
+
+ /* Lock and write each dirty extent buffers in the range */
+ while (bit_start < nbits) {
+ struct btrfs_subpage *subpage = (struct btrfs_subpage *)page->private;
+ struct extent_buffer *eb;
+ unsigned long flags;
+ u64 start;
+
+ /*
+ * Take private lock to ensure the subpage won't be detached
+ * in the meantime.
+ */
+ spin_lock(&page->mapping->private_lock);
+ if (!PagePrivate(page)) {
+ spin_unlock(&page->mapping->private_lock);
+ break;
+ }
+ spin_lock_irqsave(&subpage->lock, flags);
+ if (!((1 << bit_start) & subpage->dirty_bitmap)) {
+ spin_unlock_irqrestore(&subpage->lock, flags);
+ spin_unlock(&page->mapping->private_lock);
+ bit_start++;
+ continue;
+ }
+
+ start = page_start + bit_start * fs_info->sectorsize;
+ bit_start += sectors_per_node;
+
+ /*
+ * Here we just want to grab the eb without touching extra
+ * spin locks, so call find_extent_buffer_nolock().
+ */
+ eb = find_extent_buffer_nolock(fs_info, start);
+ spin_unlock_irqrestore(&subpage->lock, flags);
+ spin_unlock(&page->mapping->private_lock);
+
+ /*
+ * The eb has already reached 0 refs thus find_extent_buffer()
+ * doesn't return it. We don't need to write back such eb
+ * anyway.
+ */
+ if (!eb)
+ continue;
+
+ ret = lock_extent_buffer_for_io(eb, epd);
+ if (ret == 0) {
+ free_extent_buffer(eb);
+ continue;
+ }
+ if (ret < 0) {
+ free_extent_buffer(eb);
+ goto cleanup;
+ }
+ ret = write_one_eb(eb, wbc, epd);
+ free_extent_buffer(eb);
+ if (ret < 0)
+ goto cleanup;
+ submitted++;
+ }
+ return submitted;
+
+cleanup:
+ /* We hit error, end bio for the submitted extent buffers */
+ end_write_bio(epd, ret);
+ return ret;
+}
+
+/*
* Submit all page(s) of one extent buffer.
*
* @page: the page of one extent buffer
@@ -4183,6 +4446,9 @@ static int submit_eb_page(struct page *page, struct writeback_control *wbc,
if (!PagePrivate(page))
return 0;
+ if (btrfs_sb(page->mapping->host->i_sb)->sectorsize < PAGE_SIZE)
+ return submit_eb_subpage(page, wbc, epd);
+
spin_lock(&mapping->private_lock);
if (!PagePrivate(page)) {
spin_unlock(&mapping->private_lock);
@@ -4623,10 +4889,8 @@ void extent_readahead(struct readahead_control *rac)
int nr;
while ((nr = readahead_page_batch(rac, pagepool))) {
- u64 contig_start = page_offset(pagepool[0]);
- u64 contig_end = page_offset(pagepool[nr - 1]) + PAGE_SIZE - 1;
-
- ASSERT(contig_start + nr * PAGE_SIZE - 1 == contig_end);
+ u64 contig_start = readahead_pos(rac);
+ u64 contig_end = contig_start + readahead_batch_length(rac) - 1;
contiguous_readpages(pagepool, nr, contig_start, contig_end,
&em_cached, &bio, &bio_flags, &prev_em_start);
@@ -5440,36 +5704,28 @@ struct extent_buffer *find_extent_buffer(struct btrfs_fs_info *fs_info,
{
struct extent_buffer *eb;
- rcu_read_lock();
- eb = radix_tree_lookup(&fs_info->buffer_radix,
- start >> fs_info->sectorsize_bits);
- if (eb && atomic_inc_not_zero(&eb->refs)) {
- rcu_read_unlock();
- /*
- * Lock our eb's refs_lock to avoid races with
- * free_extent_buffer. When we get our eb it might be flagged
- * with EXTENT_BUFFER_STALE and another task running
- * free_extent_buffer might have seen that flag set,
- * eb->refs == 2, that the buffer isn't under IO (dirty and
- * writeback flags not set) and it's still in the tree (flag
- * EXTENT_BUFFER_TREE_REF set), therefore being in the process
- * of decrementing the extent buffer's reference count twice.
- * So here we could race and increment the eb's reference count,
- * clear its stale flag, mark it as dirty and drop our reference
- * before the other task finishes executing free_extent_buffer,
- * which would later result in an attempt to free an extent
- * buffer that is dirty.
- */
- if (test_bit(EXTENT_BUFFER_STALE, &eb->bflags)) {
- spin_lock(&eb->refs_lock);
- spin_unlock(&eb->refs_lock);
- }
- mark_extent_buffer_accessed(eb, NULL);
- return eb;
+ eb = find_extent_buffer_nolock(fs_info, start);
+ if (!eb)
+ return NULL;
+ /*
+ * Lock our eb's refs_lock to avoid races with free_extent_buffer().
+ * When we get our eb it might be flagged with EXTENT_BUFFER_STALE and
+ * another task running free_extent_buffer() might have seen that flag
+ * set, eb->refs == 2, that the buffer isn't under IO (dirty and
+ * writeback flags not set) and it's still in the tree (flag
+ * EXTENT_BUFFER_TREE_REF set), therefore being in the process of
+ * decrementing the extent buffer's reference count twice. So here we
+ * could race and increment the eb's reference count, clear its stale
+ * flag, mark it as dirty and drop our reference before the other task
+ * finishes executing free_extent_buffer, which would later result in
+ * an attempt to free an extent buffer that is dirty.
+ */
+ if (test_bit(EXTENT_BUFFER_STALE, &eb->bflags)) {
+ spin_lock(&eb->refs_lock);
+ spin_unlock(&eb->refs_lock);
}
- rcu_read_unlock();
-
- return NULL;
+ mark_extent_buffer_accessed(eb, NULL);
+ return eb;
}
#ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS
@@ -5565,6 +5821,17 @@ struct extent_buffer *alloc_extent_buffer(struct btrfs_fs_info *fs_info,
return ERR_PTR(-EINVAL);
}
+#if BITS_PER_LONG == 32
+ if (start >= MAX_LFS_FILESIZE) {
+ btrfs_err_rl(fs_info,
+ "extent buffer %llu is beyond 32bit page cache limit", start);
+ btrfs_err_32bit_limit(fs_info);
+ return ERR_PTR(-EOVERFLOW);
+ }
+ if (start >= BTRFS_32BIT_EARLY_WARN_THRESHOLD)
+ btrfs_warn_32bit_limit(fs_info);
+#endif
+
if (fs_info->sectorsize < PAGE_SIZE &&
offset_in_page(start) + len > PAGE_SIZE) {
btrfs_err(fs_info,
@@ -5636,7 +5903,7 @@ struct extent_buffer *alloc_extent_buffer(struct btrfs_fs_info *fs_info,
btrfs_page_inc_eb_refs(fs_info, p);
spin_unlock(&mapping->private_lock);
- WARN_ON(PageDirty(p));
+ WARN_ON(btrfs_page_test_dirty(fs_info, p, eb->start, eb->len));
eb->pages[i] = p;
if (!PageUptodate(p))
uptodate = 0;
@@ -5785,28 +6052,51 @@ void free_extent_buffer_stale(struct extent_buffer *eb)
release_extent_buffer(eb);
}
+static void btree_clear_page_dirty(struct page *page)
+{
+ ASSERT(PageDirty(page));
+ ASSERT(PageLocked(page));
+ clear_page_dirty_for_io(page);
+ xa_lock_irq(&page->mapping->i_pages);
+ if (!PageDirty(page))
+ __xa_clear_mark(&page->mapping->i_pages,
+ page_index(page), PAGECACHE_TAG_DIRTY);
+ xa_unlock_irq(&page->mapping->i_pages);
+}
+
+static void clear_subpage_extent_buffer_dirty(const struct extent_buffer *eb)
+{
+ struct btrfs_fs_info *fs_info = eb->fs_info;
+ struct page *page = eb->pages[0];
+ bool last;
+
+ /* btree_clear_page_dirty() needs page locked */
+ lock_page(page);
+ last = btrfs_subpage_clear_and_test_dirty(fs_info, page, eb->start,
+ eb->len);
+ if (last)
+ btree_clear_page_dirty(page);
+ unlock_page(page);
+ WARN_ON(atomic_read(&eb->refs) == 0);
+}
+
void clear_extent_buffer_dirty(const struct extent_buffer *eb)
{
int i;
int num_pages;
struct page *page;
+ if (eb->fs_info->sectorsize < PAGE_SIZE)
+ return clear_subpage_extent_buffer_dirty(eb);
+
num_pages = num_extent_pages(eb);
for (i = 0; i < num_pages; i++) {
page = eb->pages[i];
if (!PageDirty(page))
continue;
-
lock_page(page);
- WARN_ON(!PagePrivate(page));
-
- clear_page_dirty_for_io(page);
- xa_lock_irq(&page->mapping->i_pages);
- if (!PageDirty(page))
- __xa_clear_mark(&page->mapping->i_pages,
- page_index(page), PAGECACHE_TAG_DIRTY);
- xa_unlock_irq(&page->mapping->i_pages);
+ btree_clear_page_dirty(page);
ClearPageError(page);
unlock_page(page);
}
@@ -5827,10 +6117,28 @@ bool set_extent_buffer_dirty(struct extent_buffer *eb)
WARN_ON(atomic_read(&eb->refs) == 0);
WARN_ON(!test_bit(EXTENT_BUFFER_TREE_REF, &eb->bflags));
- if (!was_dirty)
- for (i = 0; i < num_pages; i++)
- set_page_dirty(eb->pages[i]);
+ if (!was_dirty) {
+ bool subpage = eb->fs_info->sectorsize < PAGE_SIZE;
+ /*
+ * For subpage case, we can have other extent buffers in the
+ * same page, and in clear_subpage_extent_buffer_dirty() we
+ * have to clear page dirty without subpage lock held.
+ * This can cause race where our page gets dirty cleared after
+ * we just set it.
+ *
+ * Thankfully, clear_subpage_extent_buffer_dirty() has locked
+ * its page for other reasons, we can use page lock to prevent
+ * the above race.
+ */
+ if (subpage)
+ lock_page(eb->pages[0]);
+ for (i = 0; i < num_pages; i++)
+ btrfs_page_set_dirty(eb->fs_info, eb->pages[i],
+ eb->start, eb->len);
+ if (subpage)
+ unlock_page(eb->pages[0]);
+ }
#ifdef CONFIG_BTRFS_DEBUG
for (i = 0; i < num_pages; i++)
ASSERT(PageDirty(eb->pages[i]));
@@ -6188,12 +6496,34 @@ int memcmp_extent_buffer(const struct extent_buffer *eb, const void *ptrv,
return ret;
}
+/*
+ * Check that the extent buffer is uptodate.
+ *
+ * For regular sector size == PAGE_SIZE case, check if @page is uptodate.
+ * For subpage case, check if the range covered by the eb has EXTENT_UPTODATE.
+ */
+static void assert_eb_page_uptodate(const struct extent_buffer *eb,
+ struct page *page)
+{
+ struct btrfs_fs_info *fs_info = eb->fs_info;
+
+ if (fs_info->sectorsize < PAGE_SIZE) {
+ bool uptodate;
+
+ uptodate = btrfs_subpage_test_uptodate(fs_info, page,
+ eb->start, eb->len);
+ WARN_ON(!uptodate);
+ } else {
+ WARN_ON(!PageUptodate(page));
+ }
+}
+
void write_extent_buffer_chunk_tree_uuid(const struct extent_buffer *eb,
const void *srcv)
{
char *kaddr;
- WARN_ON(!PageUptodate(eb->pages[0]));
+ assert_eb_page_uptodate(eb, eb->pages[0]);
kaddr = page_address(eb->pages[0]) + get_eb_offset_in_page(eb, 0);
memcpy(kaddr + offsetof(struct btrfs_header, chunk_tree_uuid), srcv,
BTRFS_FSID_SIZE);
@@ -6203,7 +6533,7 @@ void write_extent_buffer_fsid(const struct extent_buffer *eb, const void *srcv)
{
char *kaddr;
- WARN_ON(!PageUptodate(eb->pages[0]));
+ assert_eb_page_uptodate(eb, eb->pages[0]);
kaddr = page_address(eb->pages[0]) + get_eb_offset_in_page(eb, 0);
memcpy(kaddr + offsetof(struct btrfs_header, fsid), srcv,
BTRFS_FSID_SIZE);
@@ -6228,7 +6558,7 @@ void write_extent_buffer(const struct extent_buffer *eb, const void *srcv,
while (len > 0) {
page = eb->pages[i];
- WARN_ON(!PageUptodate(page));
+ assert_eb_page_uptodate(eb, page);
cur = min(len, PAGE_SIZE - offset);
kaddr = page_address(page);
@@ -6257,7 +6587,7 @@ void memzero_extent_buffer(const struct extent_buffer *eb, unsigned long start,
while (len > 0) {
page = eb->pages[i];
- WARN_ON(!PageUptodate(page));
+ assert_eb_page_uptodate(eb, page);
cur = min(len, PAGE_SIZE - offset);
kaddr = page_address(page);
@@ -6315,7 +6645,7 @@ void copy_extent_buffer(const struct extent_buffer *dst,
while (len > 0) {
page = dst->pages[i];
- WARN_ON(!PageUptodate(page));
+ assert_eb_page_uptodate(dst, page);
cur = min(len, (unsigned long)(PAGE_SIZE - offset));
@@ -6377,7 +6707,7 @@ int extent_buffer_test_bit(const struct extent_buffer *eb, unsigned long start,
eb_bitmap_offset(eb, start, nr, &i, &offset);
page = eb->pages[i];
- WARN_ON(!PageUptodate(page));
+ assert_eb_page_uptodate(eb, page);
kaddr = page_address(page);
return 1U & (kaddr[offset] >> (nr & (BITS_PER_BYTE - 1)));
}
@@ -6402,7 +6732,7 @@ void extent_buffer_bitmap_set(const struct extent_buffer *eb, unsigned long star
eb_bitmap_offset(eb, start, pos, &i, &offset);
page = eb->pages[i];
- WARN_ON(!PageUptodate(page));
+ assert_eb_page_uptodate(eb, page);
kaddr = page_address(page);
while (len >= bits_to_set) {
@@ -6413,7 +6743,7 @@ void extent_buffer_bitmap_set(const struct extent_buffer *eb, unsigned long star
if (++offset >= PAGE_SIZE && len > 0) {
offset = 0;
page = eb->pages[++i];
- WARN_ON(!PageUptodate(page));
+ assert_eb_page_uptodate(eb, page);
kaddr = page_address(page);
}
}
@@ -6445,7 +6775,7 @@ void extent_buffer_bitmap_clear(const struct extent_buffer *eb,
eb_bitmap_offset(eb, start, pos, &i, &offset);
page = eb->pages[i];
- WARN_ON(!PageUptodate(page));
+ assert_eb_page_uptodate(eb, page);
kaddr = page_address(page);
while (len >= bits_to_clear) {
@@ -6456,7 +6786,7 @@ void extent_buffer_bitmap_clear(const struct extent_buffer *eb,
if (++offset >= PAGE_SIZE && len > 0) {
offset = 0;
page = eb->pages[++i];
- WARN_ON(!PageUptodate(page));
+ assert_eb_page_uptodate(eb, page);
kaddr = page_address(page);
}
}
diff --git a/fs/btrfs/extent_io.h b/fs/btrfs/extent_io.h
index 824640cb0ace..227215a5722c 100644
--- a/fs/btrfs/extent_io.h
+++ b/fs/btrfs/extent_io.h
@@ -66,6 +66,7 @@ enum {
struct btrfs_root;
struct btrfs_inode;
struct btrfs_io_bio;
+struct btrfs_fs_info;
struct io_failure_record;
struct extent_io_tree;
@@ -270,9 +271,6 @@ struct bio *btrfs_io_bio_alloc(unsigned int nr_iovecs);
struct bio *btrfs_bio_clone(struct bio *bio);
struct bio *btrfs_bio_clone_partial(struct bio *orig, int offset, int size);
-struct btrfs_fs_info;
-struct btrfs_inode;
-
int repair_io_failure(struct btrfs_fs_info *fs_info, u64 ino, u64 start,
u64 length, u64 logical, struct page *page,
unsigned int pg_offset, int mirror_num);
diff --git a/fs/btrfs/file-item.c b/fs/btrfs/file-item.c
index 47cd3a6dc635..294602f139ef 100644
--- a/fs/btrfs/file-item.c
+++ b/fs/btrfs/file-item.c
@@ -9,6 +9,7 @@
#include <linux/highmem.h>
#include <linux/sched/mm.h>
#include <crypto/hash.h>
+#include "misc.h"
#include "ctree.h"
#include "disk-io.h"
#include "transaction.h"
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index 0e155f013839..864c08d08a35 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -2014,14 +2014,8 @@ static ssize_t btrfs_file_write_iter(struct kiocb *iocb,
else
num_written = btrfs_buffered_write(iocb, from);
- /*
- * We also have to set last_sub_trans to the current log transid,
- * otherwise subsequent syncs to a file that's been synced in this
- * transaction will appear to have already occurred.
- */
- spin_lock(&inode->lock);
- inode->last_sub_trans = inode->root->log_transid;
- spin_unlock(&inode->lock);
+ btrfs_set_inode_last_sub_trans(inode);
+
if (num_written > 0)
num_written = generic_write_sync(iocb, num_written);
@@ -2122,7 +2116,7 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
if (ret)
goto out;
- inode_lock(inode);
+ btrfs_inode_lock(inode, BTRFS_ILOCK_MMAP);
atomic_inc(&root->log_batch);
@@ -2135,11 +2129,11 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
&BTRFS_I(inode)->runtime_flags);
/*
- * Before we acquired the inode's lock, someone may have dirtied more
- * pages in the target range. We need to make sure that writeback for
- * any such pages does not start while we are logging the inode, because
- * if it does, any of the following might happen when we are not doing a
- * full inode sync:
+ * Before we acquired the inode's lock and the mmap lock, someone may
+ * have dirtied more pages in the target range. We need to make sure
+ * that writeback for any such pages does not start while we are logging
+ * the inode, because if it does, any of the following might happen when
+ * we are not doing a full inode sync:
*
* 1) We log an extent after its writeback finishes but before its
* checksums are added to the csum tree, leading to -EIO errors
@@ -2154,7 +2148,7 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
*/
ret = start_ordered_ops(inode, start, end);
if (ret) {
- inode_unlock(inode);
+ btrfs_inode_unlock(inode, BTRFS_ILOCK_MMAP);
goto out;
}
@@ -2255,7 +2249,7 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
* file again, but that will end up using the synchronization
* inside btrfs_sync_log to keep things safe.
*/
- inode_unlock(inode);
+ btrfs_inode_unlock(inode, BTRFS_ILOCK_MMAP);
if (ret != BTRFS_NO_LOG_SYNC) {
if (!ret) {
@@ -2285,7 +2279,7 @@ out:
out_release_extents:
btrfs_release_log_ctx_extents(&ctx);
- inode_unlock(inode);
+ btrfs_inode_unlock(inode, BTRFS_ILOCK_MMAP);
goto out;
}
@@ -2605,16 +2599,17 @@ static int btrfs_insert_replace_extent(struct btrfs_trans_handle *trans,
* extents without inserting a new one, so we must abort the transaction to avoid
* a corruption.
*/
-int btrfs_replace_file_extents(struct inode *inode, struct btrfs_path *path,
- const u64 start, const u64 end,
- struct btrfs_replace_extent_info *extent_info,
- struct btrfs_trans_handle **trans_out)
+int btrfs_replace_file_extents(struct btrfs_inode *inode,
+ struct btrfs_path *path, const u64 start,
+ const u64 end,
+ struct btrfs_replace_extent_info *extent_info,
+ struct btrfs_trans_handle **trans_out)
{
struct btrfs_drop_extents_args drop_args = { 0 };
- struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
+ struct btrfs_root *root = inode->root;
+ struct btrfs_fs_info *fs_info = root->fs_info;
u64 min_size = btrfs_calc_insert_metadata_size(fs_info, 1);
- u64 ino_size = round_up(inode->i_size, fs_info->sectorsize);
- struct btrfs_root *root = BTRFS_I(inode)->root;
+ u64 ino_size = round_up(inode->vfs_inode.i_size, fs_info->sectorsize);
struct btrfs_trans_handle *trans = NULL;
struct btrfs_block_rsv *rsv;
unsigned int rsv_count;
@@ -2662,10 +2657,10 @@ int btrfs_replace_file_extents(struct inode *inode, struct btrfs_path *path,
drop_args.drop_cache = true;
while (cur_offset < end) {
drop_args.start = cur_offset;
- ret = btrfs_drop_extents(trans, root, BTRFS_I(inode), &drop_args);
+ ret = btrfs_drop_extents(trans, root, inode, &drop_args);
/* If we are punching a hole decrement the inode's byte count */
if (!extent_info)
- btrfs_update_inode_bytes(BTRFS_I(inode), 0,
+ btrfs_update_inode_bytes(inode, 0,
drop_args.bytes_found);
if (ret != -ENOSPC) {
/*
@@ -2685,8 +2680,8 @@ int btrfs_replace_file_extents(struct inode *inode, struct btrfs_path *path,
if (!extent_info && cur_offset < drop_args.drop_end &&
cur_offset < ino_size) {
- ret = fill_holes(trans, BTRFS_I(inode), path,
- cur_offset, drop_args.drop_end);
+ ret = fill_holes(trans, inode, path, cur_offset,
+ drop_args.drop_end);
if (ret) {
/*
* If we failed then we didn't insert our hole
@@ -2704,7 +2699,7 @@ int btrfs_replace_file_extents(struct inode *inode, struct btrfs_path *path,
* know to not set disk_i_size in this area until a new
* file extent is inserted here.
*/
- ret = btrfs_inode_clear_file_extent_range(BTRFS_I(inode),
+ ret = btrfs_inode_clear_file_extent_range(inode,
cur_offset,
drop_args.drop_end - cur_offset);
if (ret) {
@@ -2723,8 +2718,8 @@ int btrfs_replace_file_extents(struct inode *inode, struct btrfs_path *path,
u64 replace_len = drop_args.drop_end -
extent_info->file_offset;
- ret = btrfs_insert_replace_extent(trans, BTRFS_I(inode),
- path, extent_info, replace_len,
+ ret = btrfs_insert_replace_extent(trans, inode, path,
+ extent_info, replace_len,
drop_args.bytes_found);
if (ret) {
btrfs_abort_transaction(trans, ret);
@@ -2735,9 +2730,7 @@ int btrfs_replace_file_extents(struct inode *inode, struct btrfs_path *path,
extent_info->file_offset += replace_len;
}
- cur_offset = drop_args.drop_end;
-
- ret = btrfs_update_inode(trans, root, BTRFS_I(inode));
+ ret = btrfs_update_inode(trans, root, inode);
if (ret)
break;
@@ -2756,9 +2749,10 @@ int btrfs_replace_file_extents(struct inode *inode, struct btrfs_path *path,
BUG_ON(ret); /* shouldn't happen */
trans->block_rsv = rsv;
- if (!extent_info) {
- ret = find_first_non_hole(BTRFS_I(inode), &cur_offset,
- &len);
+ cur_offset = drop_args.drop_end;
+ len = end - cur_offset;
+ if (!extent_info && len) {
+ ret = find_first_non_hole(inode, &cur_offset, &len);
if (unlikely(ret < 0))
break;
if (ret && !len) {
@@ -2771,14 +2765,11 @@ int btrfs_replace_file_extents(struct inode *inode, struct btrfs_path *path,
/*
* If we were cloning, force the next fsync to be a full one since we
* we replaced (or just dropped in the case of cloning holes when
- * NO_HOLES is enabled) extents and extent maps.
- * This is for the sake of simplicity, and cloning into files larger
- * than 16Mb would force the full fsync any way (when
- * try_release_extent_mapping() is invoked during page cache truncation.
+ * NO_HOLES is enabled) file extent items and did not setup new extent
+ * maps for the replacement extents (or holes).
*/
if (extent_info && !extent_info->is_new_extent)
- set_bit(BTRFS_INODE_NEEDS_FULL_SYNC,
- &BTRFS_I(inode)->runtime_flags);
+ set_bit(BTRFS_INODE_NEEDS_FULL_SYNC, &inode->runtime_flags);
if (ret)
goto out_trans;
@@ -2804,8 +2795,8 @@ int btrfs_replace_file_extents(struct inode *inode, struct btrfs_path *path,
*/
if (!extent_info && cur_offset < ino_size &&
cur_offset < drop_args.drop_end) {
- ret = fill_holes(trans, BTRFS_I(inode), path,
- cur_offset, drop_args.drop_end);
+ ret = fill_holes(trans, inode, path, cur_offset,
+ drop_args.drop_end);
if (ret) {
/* Same comment as above. */
btrfs_abort_transaction(trans, ret);
@@ -2813,8 +2804,8 @@ int btrfs_replace_file_extents(struct inode *inode, struct btrfs_path *path,
}
} else if (!extent_info && cur_offset < drop_args.drop_end) {
/* See the comment in the loop above for the reasoning here. */
- ret = btrfs_inode_clear_file_extent_range(BTRFS_I(inode),
- cur_offset, drop_args.drop_end - cur_offset);
+ ret = btrfs_inode_clear_file_extent_range(inode, cur_offset,
+ drop_args.drop_end - cur_offset);
if (ret) {
btrfs_abort_transaction(trans, ret);
goto out_trans;
@@ -2822,7 +2813,7 @@ int btrfs_replace_file_extents(struct inode *inode, struct btrfs_path *path,
}
if (extent_info) {
- ret = btrfs_insert_replace_extent(trans, BTRFS_I(inode), path,
+ ret = btrfs_insert_replace_extent(trans, inode, path,
extent_info, extent_info->data_len,
drop_args.bytes_found);
if (ret) {
@@ -2868,7 +2859,7 @@ static int btrfs_punch_hole(struct inode *inode, loff_t offset, loff_t len)
if (ret)
return ret;
- inode_lock(inode);
+ btrfs_inode_lock(inode, BTRFS_ILOCK_MMAP);
ino_size = round_up(inode->i_size, fs_info->sectorsize);
ret = find_first_non_hole(BTRFS_I(inode), &offset, &len);
if (ret < 0)
@@ -2908,7 +2899,7 @@ static int btrfs_punch_hole(struct inode *inode, loff_t offset, loff_t len)
truncated_block = true;
ret = btrfs_truncate_block(BTRFS_I(inode), offset, 0, 0);
if (ret) {
- inode_unlock(inode);
+ btrfs_inode_unlock(inode, BTRFS_ILOCK_MMAP);
return ret;
}
}
@@ -2967,8 +2958,8 @@ static int btrfs_punch_hole(struct inode *inode, loff_t offset, loff_t len)
goto out;
}
- ret = btrfs_replace_file_extents(inode, path, lockstart, lockend, NULL,
- &trans);
+ ret = btrfs_replace_file_extents(BTRFS_I(inode), path, lockstart,
+ lockend, NULL, &trans);
btrfs_free_path(path);
if (ret)
goto out;
@@ -3009,7 +3000,7 @@ out_only_mutex:
ret = ret2;
}
}
- inode_unlock(inode);
+ btrfs_inode_unlock(inode, BTRFS_ILOCK_MMAP);
return ret;
}
@@ -3335,7 +3326,7 @@ static long btrfs_fallocate(struct file *file, int mode,
return ret;
}
- btrfs_inode_lock(inode, 0);
+ btrfs_inode_lock(inode, BTRFS_ILOCK_MMAP);
if (!(mode & FALLOC_FL_KEEP_SIZE) && offset + len > inode->i_size) {
ret = inode_newsize_ok(inode, offset + len);
@@ -3377,7 +3368,7 @@ static long btrfs_fallocate(struct file *file, int mode,
if (mode & FALLOC_FL_ZERO_RANGE) {
ret = btrfs_zero_range(inode, offset, len, mode);
- inode_unlock(inode);
+ btrfs_inode_unlock(inode, BTRFS_ILOCK_MMAP);
return ret;
}
@@ -3487,7 +3478,7 @@ out_unlock:
unlock_extent_cached(&BTRFS_I(inode)->io_tree, alloc_start, locked_end,
&cached_state);
out:
- inode_unlock(inode);
+ btrfs_inode_unlock(inode, BTRFS_ILOCK_MMAP);
/* Let go of our reservation. */
if (ret != 0 && !(mode & FALLOC_FL_ZERO_RANGE))
btrfs_free_reserved_data_space(BTRFS_I(inode), data_reserved,
@@ -3496,13 +3487,13 @@ out:
return ret;
}
-static loff_t find_desired_extent(struct inode *inode, loff_t offset,
+static loff_t find_desired_extent(struct btrfs_inode *inode, loff_t offset,
int whence)
{
- struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
+ struct btrfs_fs_info *fs_info = inode->root->fs_info;
struct extent_map *em = NULL;
struct extent_state *cached_state = NULL;
- loff_t i_size = inode->i_size;
+ loff_t i_size = inode->vfs_inode.i_size;
u64 lockstart;
u64 lockend;
u64 start;
@@ -3525,11 +3516,10 @@ static loff_t find_desired_extent(struct inode *inode, loff_t offset,
lockend--;
len = lockend - lockstart + 1;
- lock_extent_bits(&BTRFS_I(inode)->io_tree, lockstart, lockend,
- &cached_state);
+ lock_extent_bits(&inode->io_tree, lockstart, lockend, &cached_state);
while (start < i_size) {
- em = btrfs_get_extent_fiemap(BTRFS_I(inode), start, len);
+ em = btrfs_get_extent_fiemap(inode, start, len);
if (IS_ERR(em)) {
ret = PTR_ERR(em);
em = NULL;
@@ -3551,7 +3541,7 @@ static loff_t find_desired_extent(struct inode *inode, loff_t offset,
cond_resched();
}
free_extent_map(em);
- unlock_extent_cached(&BTRFS_I(inode)->io_tree, lockstart, lockend,
+ unlock_extent_cached(&inode->io_tree, lockstart, lockend,
&cached_state);
if (ret) {
offset = ret;
@@ -3575,7 +3565,7 @@ static loff_t btrfs_file_llseek(struct file *file, loff_t offset, int whence)
case SEEK_DATA:
case SEEK_HOLE:
btrfs_inode_lock(inode, BTRFS_ILOCK_SHARED);
- offset = find_desired_extent(inode, offset, whence);
+ offset = find_desired_extent(BTRFS_I(inode), offset, whence);
btrfs_inode_unlock(inode, BTRFS_ILOCK_SHARED);
break;
}
diff --git a/fs/btrfs/free-space-cache.c b/fs/btrfs/free-space-cache.c
index 9988decd5717..e54466fc101f 100644
--- a/fs/btrfs/free-space-cache.c
+++ b/fs/btrfs/free-space-cache.c
@@ -11,6 +11,7 @@
#include <linux/ratelimit.h>
#include <linux/error-injection.h>
#include <linux/sched/mm.h>
+#include "misc.h"
#include "ctree.h"
#include "free-space-cache.h"
#include "transaction.h"
@@ -2539,6 +2540,7 @@ out:
static int __btrfs_add_free_space_zoned(struct btrfs_block_group *block_group,
u64 bytenr, u64 size, bool used)
{
+ struct btrfs_fs_info *fs_info = block_group->fs_info;
struct btrfs_free_space_ctl *ctl = block_group->free_space_ctl;
u64 offset = bytenr - block_group->start;
u64 to_free, to_unusable;
@@ -2569,8 +2571,13 @@ static int __btrfs_add_free_space_zoned(struct btrfs_block_group *block_group,
}
/* All the region is now unusable. Mark it as unused and reclaim */
- if (block_group->zone_unusable == block_group->length)
+ if (block_group->zone_unusable == block_group->length) {
btrfs_mark_bg_unused(block_group);
+ } else if (block_group->zone_unusable >=
+ div_factor_fine(block_group->length,
+ fs_info->bg_reclaim_threshold)) {
+ btrfs_mark_bg_to_reclaim(block_group);
+ }
return 0;
}
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 35bfa0533f23..b21d491b3adc 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -102,6 +102,7 @@ static void __endio_write_update_ordered(struct btrfs_inode *inode,
* BTRFS_ILOCK_SHARED - acquire a shared lock on the inode
* BTRFS_ILOCK_TRY - try to acquire the lock, if fails on first attempt
* return -EAGAIN
+ * BTRFS_ILOCK_MMAP - acquire a write lock on the i_mmap_lock
*/
int btrfs_inode_lock(struct inode *inode, unsigned int ilock_flags)
{
@@ -122,6 +123,8 @@ int btrfs_inode_lock(struct inode *inode, unsigned int ilock_flags)
}
inode_lock(inode);
}
+ if (ilock_flags & BTRFS_ILOCK_MMAP)
+ down_write(&BTRFS_I(inode)->i_mmap_lock);
return 0;
}
@@ -133,6 +136,8 @@ int btrfs_inode_lock(struct inode *inode, unsigned int ilock_flags)
*/
void btrfs_inode_unlock(struct inode *inode, unsigned int ilock_flags)
{
+ if (ilock_flags & BTRFS_ILOCK_MMAP)
+ up_write(&BTRFS_I(inode)->i_mmap_lock);
if (ilock_flags & BTRFS_ILOCK_SHARED)
inode_unlock_shared(inode);
else
@@ -1516,7 +1521,7 @@ static int fallback_to_cow(struct btrfs_inode *inode, struct page *locked_page,
static noinline int run_delalloc_nocow(struct btrfs_inode *inode,
struct page *locked_page,
const u64 start, const u64 end,
- int *page_started, int force,
+ int *page_started,
unsigned long *nr_written)
{
struct btrfs_fs_info *fs_info = inode->root->fs_info;
@@ -1530,6 +1535,7 @@ static noinline int run_delalloc_nocow(struct btrfs_inode *inode,
u64 ino = btrfs_ino(inode);
bool nocow = false;
u64 disk_bytenr = 0;
+ const bool force = inode->flags & BTRFS_INODE_NODATACOW;
path = btrfs_alloc_path();
if (!path) {
@@ -1863,23 +1869,16 @@ error:
return ret;
}
-static inline int need_force_cow(struct btrfs_inode *inode, u64 start, u64 end)
+static bool should_nocow(struct btrfs_inode *inode, u64 start, u64 end)
{
-
- if (!(inode->flags & BTRFS_INODE_NODATACOW) &&
- !(inode->flags & BTRFS_INODE_PREALLOC))
- return 0;
-
- /*
- * @defrag_bytes is a hint value, no spinlock held here,
- * if is not zero, it means the file is defragging.
- * Force cow if given extent needs to be defragged.
- */
- if (inode->defrag_bytes &&
- test_range_bit(&inode->io_tree, start, end, EXTENT_DEFRAG, 0, NULL))
- return 1;
-
- return 0;
+ if (inode->flags & (BTRFS_INODE_NODATACOW | BTRFS_INODE_PREALLOC)) {
+ if (inode->defrag_bytes &&
+ test_range_bit(&inode->io_tree, start, end, EXTENT_DEFRAG,
+ 0, NULL))
+ return false;
+ return true;
+ }
+ return false;
}
/*
@@ -1891,17 +1890,12 @@ int btrfs_run_delalloc_range(struct btrfs_inode *inode, struct page *locked_page
struct writeback_control *wbc)
{
int ret;
- int force_cow = need_force_cow(inode, start, end);
const bool zoned = btrfs_is_zoned(inode->root->fs_info);
- if (inode->flags & BTRFS_INODE_NODATACOW && !force_cow) {
- ASSERT(!zoned);
- ret = run_delalloc_nocow(inode, locked_page, start, end,
- page_started, 1, nr_written);
- } else if (inode->flags & BTRFS_INODE_PREALLOC && !force_cow) {
+ if (should_nocow(inode, start, end)) {
ASSERT(!zoned);
ret = run_delalloc_nocow(inode, locked_page, start, end,
- page_started, 0, nr_written);
+ page_started, nr_written);
} else if (!inode_can_compress(inode) ||
!inode_need_compress(inode, start, end)) {
if (zoned)
@@ -3099,11 +3093,13 @@ void btrfs_writepage_endio_finish_ordered(struct page *page, u64 start,
* @bio_offset: offset to the beginning of the bio (in bytes)
* @page: page where is the data to be verified
* @pgoff: offset inside the page
+ * @start: logical offset in the file
*
* The length of such check is always one sector size.
*/
static int check_data_csum(struct inode *inode, struct btrfs_io_bio *io_bio,
- u32 bio_offset, struct page *page, u32 pgoff)
+ u32 bio_offset, struct page *page, u32 pgoff,
+ u64 start)
{
struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
SHASH_DESC_ON_STACK(shash, fs_info->csum_shash);
@@ -3130,8 +3126,8 @@ static int check_data_csum(struct inode *inode, struct btrfs_io_bio *io_bio,
kunmap_atomic(kaddr);
return 0;
zeroit:
- btrfs_print_data_csum_error(BTRFS_I(inode), page_offset(page) + pgoff,
- csum, csum_expected, io_bio->mirror_num);
+ btrfs_print_data_csum_error(BTRFS_I(inode), start, csum, csum_expected,
+ io_bio->mirror_num);
if (io_bio->device)
btrfs_dev_stat_inc_and_print(io_bio->device,
BTRFS_DEV_STAT_CORRUPTION_ERRS);
@@ -3149,10 +3145,9 @@ zeroit:
* @bio_offset: offset to the beginning of the bio (in bytes)
* @start: file offset of the range start
* @end: file offset of the range end (inclusive)
- * @mirror: mirror number
*/
int btrfs_verify_data_csum(struct btrfs_io_bio *io_bio, u32 bio_offset,
- struct page *page, u64 start, u64 end, int mirror)
+ struct page *page, u64 start, u64 end)
{
struct inode *inode = page->mapping->host;
struct extent_io_tree *io_tree = &BTRFS_I(inode)->io_tree;
@@ -3184,7 +3179,8 @@ int btrfs_verify_data_csum(struct btrfs_io_bio *io_bio, u32 bio_offset,
pg_off += sectorsize, bio_offset += sectorsize) {
int ret;
- ret = check_data_csum(inode, io_bio, bio_offset, page, pg_off);
+ ret = check_data_csum(inode, io_bio, bio_offset, page, pg_off,
+ page_offset(page) + pg_off);
if (ret < 0)
return -EIO;
}
@@ -3390,15 +3386,19 @@ int btrfs_orphan_cleanup(struct btrfs_root *root)
int is_dead_root = 0;
/*
- * this is an orphan in the tree root. Currently these
+ * This is an orphan in the tree root. Currently these
* could come from 2 sources:
- * a) a snapshot deletion in progress
+ * a) a root (snapshot/subvolume) deletion in progress
* b) a free space cache inode
- * We need to distinguish those two, as the snapshot
- * orphan must not get deleted.
- * find_dead_roots already ran before us, so if this
- * is a snapshot deletion, we should find the root
- * in the fs_roots radix tree.
+ * We need to distinguish those two, as the orphan item
+ * for a root must not get deleted before the deletion
+ * of the snapshot/subvolume's tree completes.
+ *
+ * btrfs_find_orphan_roots() ran before us, which has
+ * found all deleted roots and loaded them into
+ * fs_info->fs_roots_radix. So here we can find if an
+ * orphan item corresponds to a deleted root by looking
+ * up the root from that radix tree.
*/
spin_lock(&fs_info->fs_roots_radix_lock);
@@ -4329,7 +4329,11 @@ int btrfs_delete_subvolume(struct inode *dir, struct dentry *dentry)
goto out_end_trans;
}
- btrfs_record_root_in_trans(trans, dest);
+ ret = btrfs_record_root_in_trans(trans, dest);
+ if (ret) {
+ btrfs_abort_transaction(trans, ret);
+ goto out_end_trans;
+ }
memset(&dest->root_item.drop_progress, 0,
sizeof(dest->root_item.drop_progress));
@@ -7023,7 +7027,7 @@ next:
if (ret)
goto out;
} else {
- map = kmap(page);
+ map = kmap_local_page(page);
read_extent_buffer(leaf, map + pg_offset, ptr,
copy_size);
if (pg_offset + copy_size < PAGE_SIZE) {
@@ -7031,7 +7035,7 @@ next:
PAGE_SIZE - pg_offset -
copy_size);
}
- kunmap(page);
+ kunmap_local(map);
}
flush_dcache_page(page);
}
@@ -7259,6 +7263,19 @@ static struct extent_map *btrfs_new_extent_direct(struct btrfs_inode *inode,
return em;
}
+static bool btrfs_extent_readonly(struct btrfs_fs_info *fs_info, u64 bytenr)
+{
+ struct btrfs_block_group *block_group;
+ bool readonly = false;
+
+ block_group = btrfs_lookup_block_group(fs_info, bytenr);
+ if (!block_group || block_group->ro)
+ readonly = true;
+ if (block_group)
+ btrfs_put_block_group(block_group);
+ return readonly;
+}
+
/*
* Check if we can do nocow write into the range [@offset, @offset + @len)
*
@@ -7910,7 +7927,8 @@ static blk_status_t btrfs_check_read_dio_bio(struct inode *inode,
ASSERT(pgoff < PAGE_SIZE);
if (uptodate &&
(!csum || !check_data_csum(inode, io_bio,
- bio_offset, bvec.bv_page, pgoff))) {
+ bio_offset, bvec.bv_page,
+ pgoff, start))) {
clean_io_failure(fs_info, failure_tree, io_tree,
start, bvec.bv_page,
btrfs_ino(BTRFS_I(inode)),
@@ -8169,10 +8187,6 @@ static blk_qc_t btrfs_submit_direct(struct inode *inode, struct iomap *iomap,
bio->bi_end_io = btrfs_end_dio_bio;
btrfs_io_bio(bio)->logical = file_offset;
- WARN_ON_ONCE(write && btrfs_is_zoned(fs_info) &&
- fs_info->max_zone_append_size &&
- bio_op(bio) != REQ_OP_ZONE_APPEND);
-
if (bio_op(bio) == REQ_OP_ZONE_APPEND) {
status = extract_ordered_extent(BTRFS_I(inode), bio,
file_offset);
@@ -8403,17 +8417,11 @@ again:
* for the finish_ordered_io
*/
if (TestClearPagePrivate2(page)) {
- struct btrfs_ordered_inode_tree *tree;
- u64 new_len;
-
- tree = &inode->ordered_tree;
-
- spin_lock_irq(&tree->lock);
+ spin_lock_irq(&inode->ordered_tree.lock);
set_bit(BTRFS_ORDERED_TRUNCATED, &ordered->flags);
- new_len = start - ordered->file_offset;
- if (new_len < ordered->truncated_len)
- ordered->truncated_len = new_len;
- spin_unlock_irq(&tree->lock);
+ ordered->truncated_len = min(ordered->truncated_len,
+ start - ordered->file_offset);
+ spin_unlock_irq(&inode->ordered_tree.lock);
if (btrfs_dec_test_ordered_pending(inode, &ordered,
start,
@@ -8539,6 +8547,7 @@ vm_fault_t btrfs_page_mkwrite(struct vm_fault *vmf)
ret = VM_FAULT_NOPAGE; /* make the VM retry the fault */
again:
+ down_read(&BTRFS_I(inode)->i_mmap_lock);
lock_page(page);
size = i_size_read(inode);
@@ -8567,6 +8576,7 @@ again:
unlock_extent_cached(io_tree, page_start, page_end,
&cached_state);
unlock_page(page);
+ up_read(&BTRFS_I(inode)->i_mmap_lock);
btrfs_start_ordered_extent(ordered, 1);
btrfs_put_ordered_extent(ordered);
goto again;
@@ -8619,11 +8629,10 @@ again:
set_page_dirty(page);
SetPageUptodate(page);
- BTRFS_I(inode)->last_trans = fs_info->generation;
- BTRFS_I(inode)->last_sub_trans = BTRFS_I(inode)->root->log_transid;
- BTRFS_I(inode)->last_log_commit = BTRFS_I(inode)->root->last_log_commit;
+ btrfs_set_inode_last_sub_trans(BTRFS_I(inode));
unlock_extent_cached(io_tree, page_start, page_end, &cached_state);
+ up_read(&BTRFS_I(inode)->i_mmap_lock);
btrfs_delalloc_release_extents(BTRFS_I(inode), PAGE_SIZE);
sb_end_pagefault(inode->i_sb);
@@ -8632,6 +8641,7 @@ again:
out_unlock:
unlock_page(page);
+ up_read(&BTRFS_I(inode)->i_mmap_lock);
out:
btrfs_delalloc_release_extents(BTRFS_I(inode), PAGE_SIZE);
btrfs_delalloc_release_space(BTRFS_I(inode), data_reserved, page_start,
@@ -8883,6 +8893,7 @@ struct inode *btrfs_alloc_inode(struct super_block *sb)
INIT_LIST_HEAD(&ei->delalloc_inodes);
INIT_LIST_HEAD(&ei->delayed_iput);
RB_CLEAR_NODE(&ei->rb_node);
+ init_rwsem(&ei->i_mmap_lock);
return inode;
}
@@ -9008,7 +9019,7 @@ int __init btrfs_init_cachep(void)
btrfs_free_space_bitmap_cachep = kmem_cache_create("btrfs_free_space_bitmap",
PAGE_SIZE, PAGE_SIZE,
- SLAB_RED_ZONE, NULL);
+ SLAB_MEM_SPREAD, NULL);
if (!btrfs_free_space_bitmap_cachep)
goto fail;
@@ -9101,8 +9112,11 @@ static int btrfs_rename_exchange(struct inode *old_dir,
goto out_notrans;
}
- if (dest != root)
- btrfs_record_root_in_trans(trans, dest);
+ if (dest != root) {
+ ret = btrfs_record_root_in_trans(trans, dest);
+ if (ret)
+ goto out_fail;
+ }
/*
* We need to find a free sequence number both in the source and
@@ -9406,8 +9420,11 @@ static int btrfs_rename(struct inode *old_dir, struct dentry *old_dentry,
goto out_notrans;
}
- if (dest != root)
- btrfs_record_root_in_trans(trans, dest);
+ if (dest != root) {
+ ret = btrfs_record_root_in_trans(trans, dest);
+ if (ret)
+ goto out_fail;
+ }
ret = btrfs_set_inode_index(BTRFS_I(new_dir), &index);
if (ret)
@@ -9877,6 +9894,7 @@ static struct btrfs_trans_handle *insert_prealloc_file_extent(
struct btrfs_path *path;
u64 start = ins->objectid;
u64 len = ins->offset;
+ int qgroup_released;
int ret;
memset(&stack_fi, 0, sizeof(stack_fi));
@@ -9889,16 +9907,16 @@ static struct btrfs_trans_handle *insert_prealloc_file_extent(
btrfs_set_stack_file_extent_compression(&stack_fi, BTRFS_COMPRESS_NONE);
/* Encryption and other encoding is reserved and all 0 */
- ret = btrfs_qgroup_release_data(inode, file_offset, len);
- if (ret < 0)
- return ERR_PTR(ret);
+ qgroup_released = btrfs_qgroup_release_data(inode, file_offset, len);
+ if (qgroup_released < 0)
+ return ERR_PTR(qgroup_released);
if (trans) {
ret = insert_reserved_file_extent(trans, inode,
file_offset, &stack_fi,
- true, ret);
+ true, qgroup_released);
if (ret)
- return ERR_PTR(ret);
+ goto free_qgroup;
return trans;
}
@@ -9909,21 +9927,35 @@ static struct btrfs_trans_handle *insert_prealloc_file_extent(
extent_info.file_offset = file_offset;
extent_info.extent_buf = (char *)&stack_fi;
extent_info.is_new_extent = true;
- extent_info.qgroup_reserved = ret;
+ extent_info.qgroup_reserved = qgroup_released;
extent_info.insertions = 0;
path = btrfs_alloc_path();
- if (!path)
- return ERR_PTR(-ENOMEM);
+ if (!path) {
+ ret = -ENOMEM;
+ goto free_qgroup;
+ }
- ret = btrfs_replace_file_extents(&inode->vfs_inode, path, file_offset,
+ ret = btrfs_replace_file_extents(inode, path, file_offset,
file_offset + len - 1, &extent_info,
&trans);
btrfs_free_path(path);
if (ret)
- return ERR_PTR(ret);
-
+ goto free_qgroup;
return trans;
+
+free_qgroup:
+ /*
+ * We have released qgroup data range at the beginning of the function,
+ * and normally qgroup_released bytes will be freed when committing
+ * transaction.
+ * But if we error out early, we have to free what we have released
+ * or we leak qgroup data reservation.
+ */
+ btrfs_qgroup_free_refroot(inode->root->fs_info,
+ inode->root->root_key.objectid, qgroup_released,
+ BTRFS_QGROUP_RSV_DATA);
+ return ERR_PTR(ret);
}
static int __btrfs_prealloc_file_range(struct inode *inode, int mode,
@@ -10588,6 +10620,8 @@ static const struct inode_operations btrfs_dir_inode_operations = {
.set_acl = btrfs_set_acl,
.update_time = btrfs_update_time,
.tmpfile = btrfs_tmpfile,
+ .fileattr_get = btrfs_fileattr_get,
+ .fileattr_set = btrfs_fileattr_set,
};
static const struct file_operations btrfs_dir_file_operations = {
@@ -10641,6 +10675,8 @@ static const struct inode_operations btrfs_file_inode_operations = {
.get_acl = btrfs_get_acl,
.set_acl = btrfs_set_acl,
.update_time = btrfs_update_time,
+ .fileattr_get = btrfs_fileattr_get,
+ .fileattr_set = btrfs_fileattr_set,
};
static const struct inode_operations btrfs_special_inode_operations = {
.getattr = btrfs_getattr,
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index e8d53fea4c61..ee1dbabb5d3c 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -26,6 +26,7 @@
#include <linux/btrfs.h>
#include <linux/uaccess.h>
#include <linux/iversion.h>
+#include <linux/fileattr.h>
#include "ctree.h"
#include "disk-io.h"
#include "export.h"
@@ -153,16 +154,6 @@ void btrfs_sync_inode_flags_to_i_flags(struct inode *inode)
new_fl);
}
-static int btrfs_ioctl_getflags(struct file *file, void __user *arg)
-{
- struct btrfs_inode *binode = BTRFS_I(file_inode(file));
- unsigned int flags = btrfs_inode_flags_to_fsflags(binode->flags);
-
- if (copy_to_user(arg, &flags, sizeof(flags)))
- return -EFAULT;
- return 0;
-}
-
/*
* Check if @flags are a supported and valid set of FS_*_FL flags and that
* the old and new flags are not conflicting
@@ -201,9 +192,22 @@ static int check_fsflags_compatible(struct btrfs_fs_info *fs_info,
return 0;
}
-static int btrfs_ioctl_setflags(struct file *file, void __user *arg)
+/*
+ * Set flags/xflags from the internal inode flags. The remaining items of
+ * fsxattr are zeroed.
+ */
+int btrfs_fileattr_get(struct dentry *dentry, struct fileattr *fa)
+{
+ struct btrfs_inode *binode = BTRFS_I(d_inode(dentry));
+
+ fileattr_fill_flags(fa, btrfs_inode_flags_to_fsflags(binode->flags));
+ return 0;
+}
+
+int btrfs_fileattr_set(struct user_namespace *mnt_userns,
+ struct dentry *dentry, struct fileattr *fa)
{
- struct inode *inode = file_inode(file);
+ struct inode *inode = d_inode(dentry);
struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
struct btrfs_inode *binode = BTRFS_I(inode);
struct btrfs_root *root = binode->root;
@@ -213,34 +217,21 @@ static int btrfs_ioctl_setflags(struct file *file, void __user *arg)
const char *comp = NULL;
u32 binode_flags;
- if (!inode_owner_or_capable(&init_user_ns, inode))
- return -EPERM;
-
if (btrfs_root_readonly(root))
return -EROFS;
- if (copy_from_user(&fsflags, arg, sizeof(fsflags)))
- return -EFAULT;
-
- ret = mnt_want_write_file(file);
- if (ret)
- return ret;
+ if (fileattr_has_fsx(fa))
+ return -EOPNOTSUPP;
- inode_lock(inode);
- fsflags = btrfs_mask_fsflags_for_type(inode, fsflags);
+ fsflags = btrfs_mask_fsflags_for_type(inode, fa->flags);
old_fsflags = btrfs_inode_flags_to_fsflags(binode->flags);
-
- ret = vfs_ioc_setflags_prepare(inode, old_fsflags, fsflags);
- if (ret)
- goto out_unlock;
-
ret = check_fsflags(old_fsflags, fsflags);
if (ret)
- goto out_unlock;
+ return ret;
ret = check_fsflags_compatible(fs_info, fsflags);
if (ret)
- goto out_unlock;
+ return ret;
binode_flags = binode->flags;
if (fsflags & FS_SYNC_FL)
@@ -263,6 +254,14 @@ static int btrfs_ioctl_setflags(struct file *file, void __user *arg)
binode_flags |= BTRFS_INODE_NOATIME;
else
binode_flags &= ~BTRFS_INODE_NOATIME;
+
+ /* If coming from FS_IOC_FSSETXATTR then skip unconverted flags */
+ if (!fa->flags_valid) {
+ /* 1 item for the inode */
+ trans = btrfs_start_transaction(root, 1);
+ goto update_flags;
+ }
+
if (fsflags & FS_DIRSYNC_FL)
binode_flags |= BTRFS_INODE_DIRSYNC;
else
@@ -303,10 +302,8 @@ static int btrfs_ioctl_setflags(struct file *file, void __user *arg)
binode_flags |= BTRFS_INODE_NOCOMPRESS;
} else if (fsflags & FS_COMPR_FL) {
- if (IS_SWAPFILE(inode)) {
- ret = -ETXTBSY;
- goto out_unlock;
- }
+ if (IS_SWAPFILE(inode))
+ return -ETXTBSY;
binode_flags |= BTRFS_INODE_COMPRESS;
binode_flags &= ~BTRFS_INODE_NOCOMPRESS;
@@ -323,10 +320,8 @@ static int btrfs_ioctl_setflags(struct file *file, void __user *arg)
* 2 for properties
*/
trans = btrfs_start_transaction(root, 3);
- if (IS_ERR(trans)) {
- ret = PTR_ERR(trans);
- goto out_unlock;
- }
+ if (IS_ERR(trans))
+ return PTR_ERR(trans);
if (comp) {
ret = btrfs_set_prop(trans, inode, "btrfs.compression", comp,
@@ -344,6 +339,7 @@ static int btrfs_ioctl_setflags(struct file *file, void __user *arg)
}
}
+update_flags:
binode->flags = binode_flags;
btrfs_sync_inode_flags_to_i_flags(inode);
inode_inc_iversion(inode);
@@ -352,44 +348,9 @@ static int btrfs_ioctl_setflags(struct file *file, void __user *arg)
out_end_trans:
btrfs_end_transaction(trans);
- out_unlock:
- inode_unlock(inode);
- mnt_drop_write_file(file);
return ret;
}
-/*
- * Translate btrfs internal inode flags to xflags as expected by the
- * FS_IOC_FSGETXATT ioctl. Filter only the supported ones, unknown flags are
- * silently dropped.
- */
-static unsigned int btrfs_inode_flags_to_xflags(unsigned int flags)
-{
- unsigned int xflags = 0;
-
- if (flags & BTRFS_INODE_APPEND)
- xflags |= FS_XFLAG_APPEND;
- if (flags & BTRFS_INODE_IMMUTABLE)
- xflags |= FS_XFLAG_IMMUTABLE;
- if (flags & BTRFS_INODE_NOATIME)
- xflags |= FS_XFLAG_NOATIME;
- if (flags & BTRFS_INODE_NODUMP)
- xflags |= FS_XFLAG_NODUMP;
- if (flags & BTRFS_INODE_SYNC)
- xflags |= FS_XFLAG_SYNC;
-
- return xflags;
-}
-
-/* Check if @flags are a supported and valid set of FS_XFLAGS_* flags */
-static int check_xflags(unsigned int flags)
-{
- if (flags & ~(FS_XFLAG_APPEND | FS_XFLAG_IMMUTABLE | FS_XFLAG_NOATIME |
- FS_XFLAG_NODUMP | FS_XFLAG_SYNC))
- return -EOPNOTSUPP;
- return 0;
-}
-
bool btrfs_exclop_start(struct btrfs_fs_info *fs_info,
enum btrfs_exclusive_operation type)
{
@@ -402,111 +363,6 @@ void btrfs_exclop_finish(struct btrfs_fs_info *fs_info)
sysfs_notify(&fs_info->fs_devices->fsid_kobj, NULL, "exclusive_operation");
}
-/*
- * Set the xflags from the internal inode flags. The remaining items of fsxattr
- * are zeroed.
- */
-static int btrfs_ioctl_fsgetxattr(struct file *file, void __user *arg)
-{
- struct btrfs_inode *binode = BTRFS_I(file_inode(file));
- struct fsxattr fa;
-
- simple_fill_fsxattr(&fa, btrfs_inode_flags_to_xflags(binode->flags));
- if (copy_to_user(arg, &fa, sizeof(fa)))
- return -EFAULT;
-
- return 0;
-}
-
-static int btrfs_ioctl_fssetxattr(struct file *file, void __user *arg)
-{
- struct inode *inode = file_inode(file);
- struct btrfs_inode *binode = BTRFS_I(inode);
- struct btrfs_root *root = binode->root;
- struct btrfs_trans_handle *trans;
- struct fsxattr fa, old_fa;
- unsigned old_flags;
- unsigned old_i_flags;
- int ret = 0;
-
- if (!inode_owner_or_capable(&init_user_ns, inode))
- return -EPERM;
-
- if (btrfs_root_readonly(root))
- return -EROFS;
-
- if (copy_from_user(&fa, arg, sizeof(fa)))
- return -EFAULT;
-
- ret = check_xflags(fa.fsx_xflags);
- if (ret)
- return ret;
-
- if (fa.fsx_extsize != 0 || fa.fsx_projid != 0 || fa.fsx_cowextsize != 0)
- return -EOPNOTSUPP;
-
- ret = mnt_want_write_file(file);
- if (ret)
- return ret;
-
- inode_lock(inode);
-
- old_flags = binode->flags;
- old_i_flags = inode->i_flags;
-
- simple_fill_fsxattr(&old_fa,
- btrfs_inode_flags_to_xflags(binode->flags));
- ret = vfs_ioc_fssetxattr_check(inode, &old_fa, &fa);
- if (ret)
- goto out_unlock;
-
- if (fa.fsx_xflags & FS_XFLAG_SYNC)
- binode->flags |= BTRFS_INODE_SYNC;
- else
- binode->flags &= ~BTRFS_INODE_SYNC;
- if (fa.fsx_xflags & FS_XFLAG_IMMUTABLE)
- binode->flags |= BTRFS_INODE_IMMUTABLE;
- else
- binode->flags &= ~BTRFS_INODE_IMMUTABLE;
- if (fa.fsx_xflags & FS_XFLAG_APPEND)
- binode->flags |= BTRFS_INODE_APPEND;
- else
- binode->flags &= ~BTRFS_INODE_APPEND;
- if (fa.fsx_xflags & FS_XFLAG_NODUMP)
- binode->flags |= BTRFS_INODE_NODUMP;
- else
- binode->flags &= ~BTRFS_INODE_NODUMP;
- if (fa.fsx_xflags & FS_XFLAG_NOATIME)
- binode->flags |= BTRFS_INODE_NOATIME;
- else
- binode->flags &= ~BTRFS_INODE_NOATIME;
-
- /* 1 item for the inode */
- trans = btrfs_start_transaction(root, 1);
- if (IS_ERR(trans)) {
- ret = PTR_ERR(trans);
- goto out_unlock;
- }
-
- btrfs_sync_inode_flags_to_i_flags(inode);
- inode_inc_iversion(inode);
- inode->i_ctime = current_time(inode);
- ret = btrfs_update_inode(trans, root, BTRFS_I(inode));
-
- btrfs_end_transaction(trans);
-
-out_unlock:
- if (ret) {
- binode->flags = old_flags;
- inode->i_flags = old_i_flags;
- }
-
- inode_unlock(inode);
- mnt_drop_write_file(file);
-
- return ret;
-}
-
static int btrfs_ioctl_getversion(struct file *file, int __user *arg)
{
struct inode *inode = file_inode(file);
@@ -697,8 +553,6 @@ static noinline int create_subvol(struct inode *dir,
btrfs_set_root_otransid(root_item, trans->transid);
btrfs_tree_unlock(leaf);
- free_extent_buffer(leaf);
- leaf = NULL;
btrfs_set_root_dirid(root_item, BTRFS_FIRST_FREE_OBJECTID);
@@ -707,8 +561,22 @@ static noinline int create_subvol(struct inode *dir,
key.type = BTRFS_ROOT_ITEM_KEY;
ret = btrfs_insert_root(trans, fs_info->tree_root, &key,
root_item);
- if (ret)
+ if (ret) {
+ /*
+ * Since we don't abort the transaction in this case, free the
+ * tree block so that we don't leak space and leave the
+ * filesystem in an inconsistent state (an extent item in the
+ * extent tree without backreferences). Also no need to have
+ * the tree block locked since it is not in any tree at this
+ * point, so no other task can find it and use it.
+ */
+ btrfs_free_tree_block(trans, root, leaf, 0, 1);
+ free_extent_buffer(leaf);
goto fail;
+ }
+
+ free_extent_buffer(leaf);
+ leaf = NULL;
key.offset = (u64)-1;
new_root = btrfs_get_new_fs_root(fs_info, objectid, anon_dev);
@@ -721,7 +589,12 @@ static noinline int create_subvol(struct inode *dir,
/* Freeing will be done in btrfs_put_root() of new_root */
anon_dev = 0;
- btrfs_record_root_in_trans(trans, new_root);
+ ret = btrfs_record_root_in_trans(trans, new_root);
+ if (ret) {
+ btrfs_put_root(new_root);
+ btrfs_abort_transaction(trans, ret);
+ goto fail;
+ }
ret = btrfs_create_subvol_root(trans, new_root, root);
btrfs_put_root(new_root);
@@ -1014,7 +887,7 @@ out_up_read:
out_dput:
dput(dentry);
out_unlock:
- inode_unlock(dir);
+ btrfs_inode_unlock(dir, 0);
return error;
}
@@ -1612,7 +1485,7 @@ int btrfs_defrag_file(struct inode *inode, struct file *file,
ra_index += cluster;
}
- inode_lock(inode);
+ btrfs_inode_lock(inode, 0);
if (IS_SWAPFILE(inode)) {
ret = -ETXTBSY;
} else {
@@ -1621,13 +1494,13 @@ int btrfs_defrag_file(struct inode *inode, struct file *file,
ret = cluster_pages_for_defrag(inode, pages, i, cluster);
}
if (ret < 0) {
- inode_unlock(inode);
+ btrfs_inode_unlock(inode, 0);
goto out_ra;
}
defrag_count += ret;
balance_dirty_pages_ratelimited(inode->i_mapping);
- inode_unlock(inode);
+ btrfs_inode_unlock(inode, 0);
if (newer_than) {
if (newer_off == (u64)-1)
@@ -1675,9 +1548,9 @@ int btrfs_defrag_file(struct inode *inode, struct file *file,
out_ra:
if (do_compress) {
- inode_lock(inode);
+ btrfs_inode_lock(inode, 0);
BTRFS_I(inode)->defrag_compress = BTRFS_COMPRESS_NONE;
- inode_unlock(inode);
+ btrfs_inode_unlock(inode, 0);
}
if (!file)
kfree(ra);
@@ -3112,9 +2985,9 @@ static noinline int btrfs_ioctl_snap_destroy(struct file *file,
goto out_dput;
}
- inode_lock(inode);
+ btrfs_inode_lock(inode, 0);
err = btrfs_delete_subvolume(dir, dentry);
- inode_unlock(inode);
+ btrfs_inode_unlock(inode, 0);
if (!err) {
fsnotify_rmdir(dir, dentry);
d_delete(dentry);
@@ -3123,7 +2996,7 @@ static noinline int btrfs_ioctl_snap_destroy(struct file *file,
out_dput:
dput(dentry);
out_unlock_dir:
- inode_unlock(dir);
+ btrfs_inode_unlock(dir, 0);
free_subvol_name:
kfree(subvol_name_ptr);
free_parent:
@@ -4915,10 +4788,6 @@ long btrfs_ioctl(struct file *file, unsigned int
void __user *argp = (void __user *)arg;
switch (cmd) {
- case FS_IOC_GETFLAGS:
- return btrfs_ioctl_getflags(file, argp);
- case FS_IOC_SETFLAGS:
- return btrfs_ioctl_setflags(file, argp);
case FS_IOC_GETVERSION:
return btrfs_ioctl_getversion(file, argp);
case FS_IOC_GETFSLABEL:
@@ -5044,10 +4913,6 @@ long btrfs_ioctl(struct file *file, unsigned int
return btrfs_ioctl_get_features(fs_info, argp);
case BTRFS_IOC_SET_FEATURES:
return btrfs_ioctl_set_features(file, argp);
- case FS_IOC_FSGETXATTR:
- return btrfs_ioctl_fsgetxattr(file, argp);
- case FS_IOC_FSSETXATTR:
- return btrfs_ioctl_fssetxattr(file, argp);
case BTRFS_IOC_GET_SUBVOL_INFO:
return btrfs_ioctl_get_subvol_info(file, argp);
case BTRFS_IOC_GET_SUBVOL_ROOTREF:
@@ -5067,12 +4932,6 @@ long btrfs_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
* handling is necessary.
*/
switch (cmd) {
- case FS_IOC32_GETFLAGS:
- cmd = FS_IOC_GETFLAGS;
- break;
- case FS_IOC32_SETFLAGS:
- cmd = FS_IOC_SETFLAGS;
- break;
case FS_IOC32_GETVERSION:
cmd = FS_IOC_GETVERSION;
break;
diff --git a/fs/btrfs/lzo.c b/fs/btrfs/lzo.c
index 9084a950dc09..cd042c7567a4 100644
--- a/fs/btrfs/lzo.c
+++ b/fs/btrfs/lzo.c
@@ -118,7 +118,7 @@ int lzo_compress_pages(struct list_head *ws, struct address_space *mapping,
struct workspace *workspace = list_entry(ws, struct workspace, list);
int ret = 0;
char *data_in;
- char *cpage_out;
+ char *cpage_out, *sizes_ptr;
int nr_pages = 0;
struct page *in_page = NULL;
struct page *out_page = NULL;
@@ -258,10 +258,9 @@ int lzo_compress_pages(struct list_head *ws, struct address_space *mapping,
}
/* store the size of all chunks of compressed data */
- cpage_out = kmap(pages[0]);
- write_compress_length(cpage_out, tot_out);
-
- kunmap(pages[0]);
+ sizes_ptr = kmap_local_page(pages[0]);
+ write_compress_length(sizes_ptr, tot_out);
+ kunmap_local(sizes_ptr);
ret = 0;
*total_out = tot_out;
diff --git a/fs/btrfs/ordered-data.c b/fs/btrfs/ordered-data.c
index 985a21558437..07b0b4218791 100644
--- a/fs/btrfs/ordered-data.c
+++ b/fs/btrfs/ordered-data.c
@@ -107,17 +107,6 @@ static struct rb_node *__tree_search(struct rb_root *root, u64 file_offset,
return NULL;
}
-/*
- * helper to check if a given offset is inside a given entry
- */
-static int offset_in_entry(struct btrfs_ordered_extent *entry, u64 file_offset)
-{
- if (file_offset < entry->file_offset ||
- entry->file_offset + entry->num_bytes <= file_offset)
- return 0;
- return 1;
-}
-
static int range_overlaps(struct btrfs_ordered_extent *entry, u64 file_offset,
u64 len)
{
@@ -142,7 +131,7 @@ static inline struct rb_node *tree_search(struct btrfs_ordered_inode_tree *tree,
if (tree->last) {
entry = rb_entry(tree->last, struct btrfs_ordered_extent,
rb_node);
- if (offset_in_entry(entry, file_offset))
+ if (in_range(file_offset, entry->file_offset, entry->num_bytes))
return tree->last;
}
ret = __tree_search(root, file_offset, &prev);
@@ -349,7 +338,7 @@ bool btrfs_dec_test_first_ordered_pending(struct btrfs_inode *inode,
goto out;
entry = rb_entry(node, struct btrfs_ordered_extent, rb_node);
- if (!offset_in_entry(entry, *file_offset))
+ if (!in_range(*file_offset, entry->file_offset, entry->num_bytes))
goto out;
dec_start = max(*file_offset, entry->file_offset);
@@ -428,7 +417,7 @@ bool btrfs_dec_test_ordered_pending(struct btrfs_inode *inode,
entry = rb_entry(node, struct btrfs_ordered_extent, rb_node);
have_entry:
- if (!offset_in_entry(entry, file_offset))
+ if (!in_range(file_offset, entry->file_offset, entry->num_bytes))
goto out;
if (io_size > entry->bytes_left)
@@ -779,7 +768,7 @@ struct btrfs_ordered_extent *btrfs_lookup_ordered_extent(struct btrfs_inode *ino
goto out;
entry = rb_entry(node, struct btrfs_ordered_extent, rb_node);
- if (!offset_in_entry(entry, file_offset))
+ if (!in_range(file_offset, entry->file_offset, entry->num_bytes))
entry = NULL;
if (entry)
refcount_inc(&entry->refs);
diff --git a/fs/btrfs/ordered-data.h b/fs/btrfs/ordered-data.h
index 99e0853e4d3b..e60c07f36427 100644
--- a/fs/btrfs/ordered-data.h
+++ b/fs/btrfs/ordered-data.h
@@ -39,8 +39,8 @@ struct btrfs_ordered_sum {
*/
enum {
/*
- * Different types for direct io, one and only one of the 4 type can
- * be set when creating ordered extent.
+ * Different types for ordered extents, one and only one of the 4 types
+ * need to be set when creating ordered extent.
*
* REGULAR: For regular non-compressed COW write
* NOCOW: For NOCOW write into existing non-hole extent
diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c
index 14ff388fd3bd..2319c923c9e6 100644
--- a/fs/btrfs/qgroup.c
+++ b/fs/btrfs/qgroup.c
@@ -23,6 +23,7 @@
#include "qgroup.h"
#include "block-group.h"
#include "sysfs.h"
+#include "tree-mod-log.h"
/* TODO XXX FIXME
* - subvol delete -> delete when ref goes to 0? delete limits also?
@@ -226,7 +227,6 @@ static void __del_qgroup_rb(struct btrfs_fs_info *fs_info,
{
struct btrfs_qgroup_list *list;
- btrfs_sysfs_del_one_qgroup(fs_info, qgroup);
list_del(&qgroup->dirty);
while (!list_empty(&qgroup->groups)) {
list = list_first_entry(&qgroup->groups,
@@ -243,7 +243,6 @@ static void __del_qgroup_rb(struct btrfs_fs_info *fs_info,
list_del(&list->next_member);
kfree(list);
}
- kfree(qgroup);
}
/* must be called with qgroup_lock held */
@@ -569,6 +568,8 @@ void btrfs_free_qgroup_config(struct btrfs_fs_info *fs_info)
qgroup = rb_entry(n, struct btrfs_qgroup, node);
rb_erase(n, &fs_info->qgroup_tree);
__del_qgroup_rb(fs_info, qgroup);
+ btrfs_sysfs_del_one_qgroup(fs_info, qgroup);
+ kfree(qgroup);
}
/*
* We call btrfs_free_qgroup_config() when unmounting
@@ -1578,6 +1579,14 @@ int btrfs_remove_qgroup(struct btrfs_trans_handle *trans, u64 qgroupid)
spin_lock(&fs_info->qgroup_lock);
del_qgroup_rb(fs_info, qgroupid);
spin_unlock(&fs_info->qgroup_lock);
+
+ /*
+ * Remove the qgroup from sysfs now without holding the qgroup_lock
+ * spinlock, since the sysfs_remove_group() function needs to take
+ * the mutex kernfs_mutex through kernfs_remove_by_name_ns().
+ */
+ btrfs_sysfs_del_one_qgroup(fs_info, qgroup);
+ kfree(qgroup);
out:
mutex_unlock(&fs_info->qgroup_ioctl_lock);
return ret;
@@ -2631,12 +2640,12 @@ int btrfs_qgroup_account_extents(struct btrfs_trans_handle *trans)
record->data_rsv,
BTRFS_QGROUP_RSV_DATA);
/*
- * Use SEQ_LAST as time_seq to do special search, which
- * doesn't lock tree or delayed_refs and search current
- * root. It's safe inside commit_transaction().
+ * Use BTRFS_SEQ_LAST as time_seq to do special search,
+ * which doesn't lock tree or delayed_refs and search
+ * current root. It's safe inside commit_transaction().
*/
ret = btrfs_find_all_roots(trans, fs_info,
- record->bytenr, SEQ_LAST, &new_roots, false);
+ record->bytenr, BTRFS_SEQ_LAST, &new_roots, false);
if (ret < 0)
goto cleanup;
if (qgroup_to_skip) {
@@ -3535,37 +3544,19 @@ static int try_flush_qgroup(struct btrfs_root *root)
{
struct btrfs_trans_handle *trans;
int ret;
- bool can_commit = true;
- /*
- * If current process holds a transaction, we shouldn't flush, as we
- * assume all space reservation happens before a transaction handle is
- * held.
- *
- * But there are cases like btrfs_delayed_item_reserve_metadata() where
- * we try to reserve space with one transction handle already held.
- * In that case we can't commit transaction, but at least try to end it
- * and hope the started data writes can free some space.
- */
- if (current->journal_info &&
- current->journal_info != BTRFS_SEND_TRANS_STUB)
- can_commit = false;
+ /* Can't hold an open transaction or we run the risk of deadlocking */
+ ASSERT(current->journal_info == NULL ||
+ current->journal_info == BTRFS_SEND_TRANS_STUB);
+ if (WARN_ON(current->journal_info &&
+ current->journal_info != BTRFS_SEND_TRANS_STUB))
+ return 0;
/*
* We don't want to run flush again and again, so if there is a running
* one, we won't try to start a new flush, but exit directly.
*/
if (test_and_set_bit(BTRFS_ROOT_QGROUP_FLUSHING, &root->state)) {
- /*
- * We are already holding a transaction, thus we can block other
- * threads from flushing. So exit right now. This increases
- * the chance of EDQUOT for heavy load and near limit cases.
- * But we can argue that if we're already near limit, EDQUOT is
- * unavoidable anyway.
- */
- if (!can_commit)
- return 0;
-
wait_event(root->qgroup_flush_wait,
!test_bit(BTRFS_ROOT_QGROUP_FLUSHING, &root->state));
return 0;
@@ -3582,10 +3573,7 @@ static int try_flush_qgroup(struct btrfs_root *root)
goto out;
}
- if (can_commit)
- ret = btrfs_commit_transaction(trans);
- else
- ret = btrfs_end_transaction(trans);
+ ret = btrfs_commit_transaction(trans);
out:
clear_bit(BTRFS_ROOT_QGROUP_FLUSHING, &root->state);
wake_up(&root->qgroup_flush_wait);
@@ -3638,8 +3626,7 @@ cleanup:
qgroup_unreserve_range(inode, reserved, start, len);
out:
if (new_reserved) {
- extent_changeset_release(reserved);
- kfree(reserved);
+ extent_changeset_free(reserved);
*reserved_ret = NULL;
}
return ret;
diff --git a/fs/btrfs/raid56.c b/fs/btrfs/raid56.c
index 8c31357f08ed..244d499ebc72 100644
--- a/fs/btrfs/raid56.c
+++ b/fs/btrfs/raid56.c
@@ -13,6 +13,7 @@
#include <linux/list_sort.h>
#include <linux/raid/xor.h>
#include <linux/mm.h>
+#include "misc.h"
#include "ctree.h"
#include "disk-io.h"
#include "volumes.h"
@@ -1231,13 +1232,13 @@ static noinline void finish_rmw(struct btrfs_raid_bio *rbio)
/* 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);
+ pointers[stripe] = kmap_local_page(p);
}
/* then add the parity stripe */
p = rbio_pstripe_page(rbio, pagenr);
SetPageUptodate(p);
- pointers[stripe++] = kmap(p);
+ pointers[stripe++] = kmap_local_page(p);
if (has_qstripe) {
@@ -1247,7 +1248,7 @@ static noinline void finish_rmw(struct btrfs_raid_bio *rbio)
*/
p = rbio_qstripe_page(rbio, pagenr);
SetPageUptodate(p);
- pointers[stripe++] = kmap(p);
+ pointers[stripe++] = kmap_local_page(p);
raid6_call.gen_syndrome(rbio->real_stripes, PAGE_SIZE,
pointers);
@@ -1256,10 +1257,8 @@ static noinline void finish_rmw(struct btrfs_raid_bio *rbio)
copy_page(pointers[nr_data], pointers[0]);
run_xor(pointers + 1, nr_data - 1, PAGE_SIZE);
}
-
-
- for (stripe = 0; stripe < rbio->real_stripes; stripe++)
- kunmap(page_in_rbio(rbio, stripe, pagenr, 0));
+ for (stripe = stripe - 1; stripe >= 0; stripe--)
+ kunmap_local(pointers[stripe]);
}
/*
@@ -1634,7 +1633,8 @@ struct btrfs_plug_cb {
/*
* rbios on the plug list are sorted for easier merging.
*/
-static int plug_cmp(void *priv, struct list_head *a, struct list_head *b)
+static int plug_cmp(void *priv, const struct list_head *a,
+ const struct list_head *b)
{
struct btrfs_raid_bio *ra = container_of(a, struct btrfs_raid_bio,
plug_list);
@@ -1776,6 +1776,7 @@ static void __raid_recover_end_io(struct btrfs_raid_bio *rbio)
{
int pagenr, stripe;
void **pointers;
+ void **unmap_array;
int faila = -1, failb = -1;
struct page *page;
blk_status_t err;
@@ -1787,6 +1788,16 @@ static void __raid_recover_end_io(struct btrfs_raid_bio *rbio)
goto cleanup_io;
}
+ /*
+ * Store copy of pointers that does not get reordered during
+ * reconstruction so that kunmap_local works.
+ */
+ unmap_array = kcalloc(rbio->real_stripes, sizeof(void *), GFP_NOFS);
+ if (!unmap_array) {
+ err = BLK_STS_RESOURCE;
+ goto cleanup_pointers;
+ }
+
faila = rbio->faila;
failb = rbio->failb;
@@ -1808,8 +1819,11 @@ static void __raid_recover_end_io(struct btrfs_raid_bio *rbio)
!test_bit(pagenr, rbio->dbitmap))
continue;
- /* setup our array of pointers with pages
- * from each stripe
+ /*
+ * Setup our array of pointers with pages from each stripe
+ *
+ * NOTE: store a duplicate array of pointers to preserve the
+ * pointer order
*/
for (stripe = 0; stripe < rbio->real_stripes; stripe++) {
/*
@@ -1823,7 +1837,8 @@ static void __raid_recover_end_io(struct btrfs_raid_bio *rbio)
} else {
page = rbio_stripe_page(rbio, stripe, pagenr);
}
- pointers[stripe] = kmap(page);
+ pointers[stripe] = kmap_local_page(page);
+ unmap_array[stripe] = pointers[stripe];
}
/* all raid6 handling here */
@@ -1916,24 +1931,14 @@ pstripe:
}
}
}
- 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->operation == BTRFS_RBIO_READ_REBUILD ||
- rbio->operation == BTRFS_RBIO_REBUILD_MISSING) &&
- (stripe == faila || stripe == failb)) {
- page = page_in_rbio(rbio, stripe, pagenr, 0);
- } else {
- page = rbio_stripe_page(rbio, stripe, pagenr);
- }
- kunmap(page);
- }
+ for (stripe = rbio->real_stripes - 1; stripe >= 0; stripe--)
+ kunmap_local(unmap_array[stripe]);
}
err = BLK_STS_OK;
cleanup:
+ kfree(unmap_array);
+cleanup_pointers:
kfree(pointers);
cleanup_io:
@@ -2358,13 +2363,13 @@ static noinline void finish_parity_scrub(struct btrfs_raid_bio *rbio,
goto cleanup;
}
SetPageUptodate(q_page);
- pointers[rbio->real_stripes - 1] = kmap(q_page);
+ pointers[rbio->real_stripes - 1] = kmap_local_page(q_page);
}
atomic_set(&rbio->error, 0);
/* Map the parity stripe just once */
- pointers[nr_data] = kmap(p_page);
+ pointers[nr_data] = kmap_local_page(p_page);
for_each_set_bit(pagenr, rbio->dbitmap, rbio->stripe_npages) {
struct page *p;
@@ -2372,7 +2377,7 @@ static noinline void finish_parity_scrub(struct btrfs_raid_bio *rbio,
/* 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);
+ pointers[stripe] = kmap_local_page(p);
}
if (has_qstripe) {
@@ -2387,22 +2392,22 @@ static noinline void finish_parity_scrub(struct btrfs_raid_bio *rbio,
/* Check scrubbing parity and repair it */
p = rbio_stripe_page(rbio, rbio->scrubp, pagenr);
- parity = kmap(p);
+ parity = kmap_local_page(p);
if (memcmp(parity, pointers[rbio->scrubp], PAGE_SIZE))
copy_page(parity, pointers[rbio->scrubp]);
else
/* Parity is right, needn't writeback */
bitmap_clear(rbio->dbitmap, pagenr, 1);
- kunmap(p);
+ kunmap_local(parity);
- for (stripe = 0; stripe < nr_data; stripe++)
- kunmap(page_in_rbio(rbio, stripe, pagenr, 0));
+ for (stripe = nr_data - 1; stripe >= 0; stripe--)
+ kunmap_local(pointers[stripe]);
}
- kunmap(p_page);
+ kunmap_local(pointers[nr_data]);
__free_page(p_page);
if (q_page) {
- kunmap(q_page);
+ kunmap_local(pointers[rbio->real_stripes - 1]);
__free_page(q_page);
}
diff --git a/fs/btrfs/reada.c b/fs/btrfs/reada.c
index 20fd4aa48a8c..06713a8fe26b 100644
--- a/fs/btrfs/reada.c
+++ b/fs/btrfs/reada.c
@@ -209,7 +209,7 @@ int btree_readahead_hook(struct extent_buffer *eb, int err)
/* find extent */
spin_lock(&fs_info->reada_lock);
re = radix_tree_lookup(&fs_info->reada_tree,
- eb->start >> PAGE_SHIFT);
+ eb->start >> fs_info->sectorsize_bits);
if (re)
re->refcnt++;
spin_unlock(&fs_info->reada_lock);
@@ -240,7 +240,7 @@ static struct reada_zone *reada_find_zone(struct btrfs_device *dev, u64 logical,
zone = NULL;
spin_lock(&fs_info->reada_lock);
ret = radix_tree_gang_lookup(&dev->reada_zones, (void **)&zone,
- logical >> PAGE_SHIFT, 1);
+ logical >> fs_info->sectorsize_bits, 1);
if (ret == 1 && logical >= zone->start && logical <= zone->end) {
kref_get(&zone->refcnt);
spin_unlock(&fs_info->reada_lock);
@@ -283,13 +283,13 @@ static struct reada_zone *reada_find_zone(struct btrfs_device *dev, u64 logical,
spin_lock(&fs_info->reada_lock);
ret = radix_tree_insert(&dev->reada_zones,
- (unsigned long)(zone->end >> PAGE_SHIFT),
- zone);
+ (unsigned long)(zone->end >> fs_info->sectorsize_bits),
+ zone);
if (ret == -EEXIST) {
kfree(zone);
ret = radix_tree_gang_lookup(&dev->reada_zones, (void **)&zone,
- logical >> PAGE_SHIFT, 1);
+ logical >> fs_info->sectorsize_bits, 1);
if (ret == 1 && logical >= zone->start && logical <= zone->end)
kref_get(&zone->refcnt);
else
@@ -315,7 +315,7 @@ static struct reada_extent *reada_find_extent(struct btrfs_fs_info *fs_info,
u64 length;
int real_stripes;
int nzones = 0;
- unsigned long index = logical >> PAGE_SHIFT;
+ unsigned long index = logical >> fs_info->sectorsize_bits;
int dev_replace_is_ongoing;
int have_zone = 0;
@@ -497,7 +497,7 @@ static void reada_extent_put(struct btrfs_fs_info *fs_info,
struct reada_extent *re)
{
int i;
- unsigned long index = re->logical >> PAGE_SHIFT;
+ unsigned long index = re->logical >> fs_info->sectorsize_bits;
spin_lock(&fs_info->reada_lock);
if (--re->refcnt) {
@@ -538,11 +538,12 @@ static void reada_extent_put(struct btrfs_fs_info *fs_info,
static void reada_zone_release(struct kref *kref)
{
struct reada_zone *zone = container_of(kref, struct reada_zone, refcnt);
+ struct btrfs_fs_info *fs_info = zone->device->fs_info;
- lockdep_assert_held(&zone->device->fs_info->reada_lock);
+ lockdep_assert_held(&fs_info->reada_lock);
radix_tree_delete(&zone->device->reada_zones,
- zone->end >> PAGE_SHIFT);
+ zone->end >> fs_info->sectorsize_bits);
kfree(zone);
}
@@ -593,7 +594,7 @@ static int reada_add_block(struct reada_control *rc, u64 logical,
static void reada_peer_zones_set_lock(struct reada_zone *zone, int lock)
{
int i;
- unsigned long index = zone->end >> PAGE_SHIFT;
+ unsigned long index = zone->end >> zone->device->fs_info->sectorsize_bits;
for (i = 0; i < zone->ndevs; ++i) {
struct reada_zone *peer;
@@ -628,7 +629,7 @@ static int reada_pick_zone(struct btrfs_device *dev)
(void **)&zone, index, 1);
if (ret == 0)
break;
- index = (zone->end >> PAGE_SHIFT) + 1;
+ index = (zone->end >> dev->fs_info->sectorsize_bits) + 1;
if (zone->locked) {
if (zone->elems > top_locked_elems) {
top_locked_elems = zone->elems;
@@ -709,7 +710,7 @@ static int reada_start_machine_dev(struct btrfs_device *dev)
* plugging to speed things up
*/
ret = radix_tree_gang_lookup(&dev->reada_extents, (void **)&re,
- dev->reada_next >> PAGE_SHIFT, 1);
+ dev->reada_next >> fs_info->sectorsize_bits, 1);
if (ret == 0 || re->logical > dev->reada_curr_zone->end) {
ret = reada_pick_zone(dev);
if (!ret) {
@@ -718,7 +719,7 @@ static int reada_start_machine_dev(struct btrfs_device *dev)
}
re = NULL;
ret = radix_tree_gang_lookup(&dev->reada_extents, (void **)&re,
- dev->reada_next >> PAGE_SHIFT, 1);
+ dev->reada_next >> fs_info->sectorsize_bits, 1);
}
if (ret == 0) {
spin_unlock(&fs_info->reada_lock);
@@ -885,7 +886,7 @@ static void dump_devs(struct btrfs_fs_info *fs_info, int all)
pr_cont(" curr off %llu",
device->reada_next - zone->start);
pr_cont("\n");
- index = (zone->end >> PAGE_SHIFT) + 1;
+ index = (zone->end >> fs_info->sectorsize_bits) + 1;
}
cnt = 0;
index = 0;
@@ -910,7 +911,7 @@ static void dump_devs(struct btrfs_fs_info *fs_info, int all)
}
}
pr_cont("\n");
- index = (re->logical >> PAGE_SHIFT) + 1;
+ index = (re->logical >> fs_info->sectorsize_bits) + 1;
if (++cnt > 15)
break;
}
@@ -926,7 +927,7 @@ static void dump_devs(struct btrfs_fs_info *fs_info, int all)
if (ret == 0)
break;
if (!re->scheduled) {
- index = (re->logical >> PAGE_SHIFT) + 1;
+ index = (re->logical >> fs_info->sectorsize_bits) + 1;
continue;
}
pr_debug("re: logical %llu size %u list empty %d scheduled %d",
@@ -942,7 +943,7 @@ static void dump_devs(struct btrfs_fs_info *fs_info, int all)
}
}
pr_cont("\n");
- index = (re->logical >> PAGE_SHIFT) + 1;
+ index = (re->logical >> fs_info->sectorsize_bits) + 1;
}
spin_unlock(&fs_info->reada_lock);
}
diff --git a/fs/btrfs/reflink.c b/fs/btrfs/reflink.c
index 762881b777b3..f4ec06b53aa0 100644
--- a/fs/btrfs/reflink.c
+++ b/fs/btrfs/reflink.c
@@ -478,9 +478,9 @@ process_slot:
clone_info.file_offset = new_key.offset;
clone_info.extent_buf = buf;
clone_info.is_new_extent = false;
- ret = btrfs_replace_file_extents(inode, path, drop_start,
- new_key.offset + datal - 1, &clone_info,
- &trans);
+ ret = btrfs_replace_file_extents(BTRFS_I(inode), path,
+ drop_start, new_key.offset + datal - 1,
+ &clone_info, &trans);
if (ret)
goto out;
} else if (type == BTRFS_FILE_EXTENT_INLINE) {
@@ -567,8 +567,8 @@ process_slot:
set_bit(BTRFS_INODE_NEEDS_FULL_SYNC,
&BTRFS_I(inode)->runtime_flags);
- ret = btrfs_replace_file_extents(inode, path, last_dest_end,
- destoff + len - 1, NULL, &trans);
+ ret = btrfs_replace_file_extents(BTRFS_I(inode), path,
+ last_dest_end, destoff + len - 1, NULL, &trans);
if (ret)
goto out;
@@ -604,6 +604,20 @@ static void btrfs_double_extent_lock(struct inode *inode1, u64 loff1,
lock_extent(&BTRFS_I(inode2)->io_tree, loff2, loff2 + len - 1);
}
+static void btrfs_double_mmap_lock(struct inode *inode1, struct inode *inode2)
+{
+ if (inode1 < inode2)
+ swap(inode1, inode2);
+ down_write(&BTRFS_I(inode1)->i_mmap_lock);
+ down_write_nested(&BTRFS_I(inode2)->i_mmap_lock, SINGLE_DEPTH_NESTING);
+}
+
+static void btrfs_double_mmap_unlock(struct inode *inode1, struct inode *inode2)
+{
+ up_write(&BTRFS_I(inode1)->i_mmap_lock);
+ up_write(&BTRFS_I(inode2)->i_mmap_lock);
+}
+
static int btrfs_extent_same_range(struct inode *src, u64 loff, u64 len,
struct inode *dst, u64 dst_loff)
{
@@ -820,6 +834,16 @@ static int btrfs_remap_file_range_prep(struct file *file_in, loff_t pos_in,
len, remap_flags);
}
+static bool file_sync_write(const struct file *file)
+{
+ if (file->f_flags & (__O_SYNC | O_DSYNC))
+ return true;
+ if (IS_SYNC(file_inode(file)))
+ return true;
+
+ return false;
+}
+
loff_t btrfs_remap_file_range(struct file *src_file, loff_t off,
struct file *dst_file, loff_t destoff, loff_t len,
unsigned int remap_flags)
@@ -832,10 +856,12 @@ loff_t btrfs_remap_file_range(struct file *src_file, loff_t off,
if (remap_flags & ~(REMAP_FILE_DEDUP | REMAP_FILE_ADVISORY))
return -EINVAL;
- if (same_inode)
- inode_lock(src_inode);
- else
+ if (same_inode) {
+ btrfs_inode_lock(src_inode, BTRFS_ILOCK_MMAP);
+ } else {
lock_two_nondirectories(src_inode, dst_inode);
+ btrfs_double_mmap_lock(src_inode, dst_inode);
+ }
ret = btrfs_remap_file_range_prep(src_file, off, dst_file, destoff,
&len, remap_flags);
@@ -848,10 +874,27 @@ loff_t btrfs_remap_file_range(struct file *src_file, loff_t off,
ret = btrfs_clone_files(dst_file, src_file, off, len, destoff);
out_unlock:
- if (same_inode)
- inode_unlock(src_inode);
- else
+ if (same_inode) {
+ btrfs_inode_unlock(src_inode, BTRFS_ILOCK_MMAP);
+ } else {
+ btrfs_double_mmap_unlock(src_inode, dst_inode);
unlock_two_nondirectories(src_inode, dst_inode);
+ }
+
+ /*
+ * If either the source or the destination file was opened with O_SYNC,
+ * O_DSYNC or has the S_SYNC attribute, fsync both the destination and
+ * source files/ranges, so that after a successful return (0) followed
+ * by a power failure results in the reflinked data to be readable from
+ * both files/ranges.
+ */
+ if (ret == 0 && len > 0 &&
+ (file_sync_write(src_file) || file_sync_write(dst_file))) {
+ ret = btrfs_sync_file(src_file, off, off + len - 1, 0);
+ if (ret == 0)
+ ret = btrfs_sync_file(dst_file, destoff,
+ destoff + len - 1, 0);
+ }
return ret < 0 ? ret : len;
}
diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c
index 232d5da7b7be..b70be2ac2e9e 100644
--- a/fs/btrfs/relocation.c
+++ b/fs/btrfs/relocation.c
@@ -638,9 +638,10 @@ static int __must_check __add_reloc_root(struct btrfs_root *root)
node->bytenr, &node->rb_node);
spin_unlock(&rc->reloc_root_tree.lock);
if (rb_node) {
- btrfs_panic(fs_info, -EEXIST,
+ btrfs_err(fs_info,
"Duplicate root found for start=%llu while inserting into relocation tree",
node->bytenr);
+ return -EEXIST;
}
list_add_tail(&root->root_list, &rc->reloc_roots);
@@ -733,10 +734,12 @@ static struct btrfs_root *create_reloc_root(struct btrfs_trans_handle *trans,
struct extent_buffer *eb;
struct btrfs_root_item *root_item;
struct btrfs_key root_key;
- int ret;
+ int ret = 0;
+ bool must_abort = false;
root_item = kmalloc(sizeof(*root_item), GFP_NOFS);
- BUG_ON(!root_item);
+ if (!root_item)
+ return ERR_PTR(-ENOMEM);
root_key.objectid = BTRFS_TREE_RELOC_OBJECTID;
root_key.type = BTRFS_ROOT_ITEM_KEY;
@@ -748,7 +751,9 @@ static struct btrfs_root *create_reloc_root(struct btrfs_trans_handle *trans,
/* called by btrfs_init_reloc_root */
ret = btrfs_copy_root(trans, root, root->commit_root, &eb,
BTRFS_TREE_RELOC_OBJECTID);
- BUG_ON(ret);
+ if (ret)
+ goto fail;
+
/*
* Set the last_snapshot field to the generation of the commit
* root - like this ctree.c:btrfs_block_can_be_shared() behaves
@@ -769,9 +774,16 @@ static struct btrfs_root *create_reloc_root(struct btrfs_trans_handle *trans,
*/
ret = btrfs_copy_root(trans, root, root->node, &eb,
BTRFS_TREE_RELOC_OBJECTID);
- BUG_ON(ret);
+ if (ret)
+ goto fail;
}
+ /*
+ * We have changed references at this point, we must abort the
+ * transaction if anything fails.
+ */
+ must_abort = true;
+
memcpy(root_item, &root->root_item, sizeof(*root_item));
btrfs_set_root_bytenr(root_item, eb->start);
btrfs_set_root_level(root_item, btrfs_header_level(eb));
@@ -789,14 +801,25 @@ static struct btrfs_root *create_reloc_root(struct btrfs_trans_handle *trans,
ret = btrfs_insert_root(trans, fs_info->tree_root,
&root_key, root_item);
- BUG_ON(ret);
+ if (ret)
+ goto fail;
+
kfree(root_item);
reloc_root = btrfs_read_tree_root(fs_info->tree_root, &root_key);
- BUG_ON(IS_ERR(reloc_root));
+ if (IS_ERR(reloc_root)) {
+ ret = PTR_ERR(reloc_root);
+ goto abort;
+ }
set_bit(BTRFS_ROOT_SHAREABLE, &reloc_root->state);
reloc_root->last_trans = trans->transid;
return reloc_root;
+fail:
+ kfree(root_item);
+abort:
+ if (must_abort)
+ btrfs_abort_transaction(trans, ret);
+ return ERR_PTR(ret);
}
/*
@@ -856,9 +879,16 @@ int btrfs_init_reloc_root(struct btrfs_trans_handle *trans,
reloc_root = create_reloc_root(trans, root, root->root_key.objectid);
if (clear_rsv)
trans->block_rsv = rsv;
+ if (IS_ERR(reloc_root))
+ return PTR_ERR(reloc_root);
ret = __add_reloc_root(reloc_root);
- BUG_ON(ret < 0);
+ ASSERT(ret != -EEXIST);
+ if (ret) {
+ /* Pairs with create_reloc_root */
+ btrfs_put_root(reloc_root);
+ return ret;
+ }
root->reloc_root = btrfs_grab_root(reloc_root);
return 0;
}
@@ -875,7 +905,7 @@ int btrfs_update_reloc_root(struct btrfs_trans_handle *trans,
int ret;
if (!have_reloc_root(root))
- goto out;
+ return 0;
reloc_root = root->reloc_root;
root_item = &reloc_root->root_item;
@@ -908,10 +938,8 @@ int btrfs_update_reloc_root(struct btrfs_trans_handle *trans,
ret = btrfs_update_root(trans, fs_info->tree_root,
&reloc_root->root_key, root_item);
- BUG_ON(ret);
btrfs_put_root(reloc_root);
-out:
- return 0;
+ return ret;
}
/*
@@ -1185,8 +1213,8 @@ int replace_path(struct btrfs_trans_handle *trans, struct reloc_control *rc,
int ret;
int slot;
- BUG_ON(src->root_key.objectid != BTRFS_TREE_RELOC_OBJECTID);
- BUG_ON(dest->root_key.objectid == BTRFS_TREE_RELOC_OBJECTID);
+ ASSERT(src->root_key.objectid == BTRFS_TREE_RELOC_OBJECTID);
+ ASSERT(dest->root_key.objectid != BTRFS_TREE_RELOC_OBJECTID);
last_snapshot = btrfs_root_last_snapshot(&src->root_item);
again:
@@ -1205,7 +1233,11 @@ again:
if (cow) {
ret = btrfs_cow_block(trans, dest, eb, NULL, 0, &eb,
BTRFS_NESTING_COW);
- BUG_ON(ret);
+ if (ret) {
+ btrfs_tree_unlock(eb);
+ free_extent_buffer(eb);
+ return ret;
+ }
}
if (next_key) {
@@ -1217,7 +1249,7 @@ again:
parent = eb;
while (1) {
level = btrfs_header_level(parent);
- BUG_ON(level < lowest_level);
+ ASSERT(level >= lowest_level);
ret = btrfs_bin_search(parent, &key, &slot);
if (ret < 0)
@@ -1265,7 +1297,11 @@ again:
ret = btrfs_cow_block(trans, dest, eb, parent,
slot, &eb,
BTRFS_NESTING_COW);
- BUG_ON(ret);
+ if (ret) {
+ btrfs_tree_unlock(eb);
+ free_extent_buffer(eb);
+ break;
+ }
}
btrfs_tree_unlock(parent);
@@ -1289,7 +1325,11 @@ again:
path->lowest_level = level;
ret = btrfs_search_slot(trans, src, &key, path, 0, 1);
path->lowest_level = 0;
- BUG_ON(ret);
+ if (ret) {
+ if (ret > 0)
+ ret = -ENOENT;
+ break;
+ }
/*
* Info qgroup to trace both subtrees.
@@ -1329,27 +1369,39 @@ again:
ref.skip_qgroup = true;
btrfs_init_tree_ref(&ref, level - 1, src->root_key.objectid);
ret = btrfs_inc_extent_ref(trans, &ref);
- BUG_ON(ret);
+ if (ret) {
+ btrfs_abort_transaction(trans, ret);
+ break;
+ }
btrfs_init_generic_ref(&ref, BTRFS_ADD_DELAYED_REF, new_bytenr,
blocksize, 0);
ref.skip_qgroup = true;
btrfs_init_tree_ref(&ref, level - 1, dest->root_key.objectid);
ret = btrfs_inc_extent_ref(trans, &ref);
- BUG_ON(ret);
+ if (ret) {
+ btrfs_abort_transaction(trans, ret);
+ break;
+ }
btrfs_init_generic_ref(&ref, BTRFS_DROP_DELAYED_REF, new_bytenr,
blocksize, path->nodes[level]->start);
btrfs_init_tree_ref(&ref, level - 1, src->root_key.objectid);
ref.skip_qgroup = true;
ret = btrfs_free_extent(trans, &ref);
- BUG_ON(ret);
+ if (ret) {
+ btrfs_abort_transaction(trans, ret);
+ break;
+ }
btrfs_init_generic_ref(&ref, BTRFS_DROP_DELAYED_REF, old_bytenr,
blocksize, 0);
btrfs_init_tree_ref(&ref, level - 1, dest->root_key.objectid);
ref.skip_qgroup = true;
ret = btrfs_free_extent(trans, &ref);
- BUG_ON(ret);
+ if (ret) {
+ btrfs_abort_transaction(trans, ret);
+ break;
+ }
btrfs_unlock_up_safe(path, 0);
@@ -1537,12 +1589,13 @@ static int find_next_key(struct btrfs_path *path, int level,
/*
* Insert current subvolume into reloc_control::dirty_subvol_roots
*/
-static void insert_dirty_subvol(struct btrfs_trans_handle *trans,
- struct reloc_control *rc,
- struct btrfs_root *root)
+static int insert_dirty_subvol(struct btrfs_trans_handle *trans,
+ struct reloc_control *rc,
+ struct btrfs_root *root)
{
struct btrfs_root *reloc_root = root->reloc_root;
struct btrfs_root_item *reloc_root_item;
+ int ret;
/* @root must be a subvolume tree root with a valid reloc tree */
ASSERT(root->root_key.objectid != BTRFS_TREE_RELOC_OBJECTID);
@@ -1553,12 +1606,16 @@ static void insert_dirty_subvol(struct btrfs_trans_handle *trans,
sizeof(reloc_root_item->drop_progress));
btrfs_set_root_drop_level(reloc_root_item, 0);
btrfs_set_root_refs(reloc_root_item, 0);
- btrfs_update_reloc_root(trans, root);
+ ret = btrfs_update_reloc_root(trans, root);
+ if (ret)
+ return ret;
if (list_empty(&root->reloc_dirty_list)) {
btrfs_grab_root(root);
list_add_tail(&root->reloc_dirty_list, &rc->dirty_subvol_roots);
}
+
+ return 0;
}
static int clean_dirty_subvols(struct reloc_control *rc)
@@ -1760,8 +1817,11 @@ static noinline_for_stack int merge_reloc_root(struct reloc_control *rc,
out:
btrfs_free_path(path);
- if (ret == 0)
- insert_dirty_subvol(trans, rc, root);
+ if (ret == 0) {
+ ret = insert_dirty_subvol(trans, rc, root);
+ if (ret)
+ btrfs_abort_transaction(trans, ret);
+ }
if (trans)
btrfs_end_transaction_throttle(trans);
@@ -1825,8 +1885,18 @@ again:
root = btrfs_get_fs_root(fs_info, reloc_root->root_key.offset,
false);
- BUG_ON(IS_ERR(root));
- BUG_ON(root->reloc_root != reloc_root);
+ if (IS_ERR(root)) {
+ /*
+ * Even if we have an error we need this reloc root
+ * back on our list so we can clean up properly.
+ */
+ list_add(&reloc_root->root_list, &reloc_roots);
+ btrfs_abort_transaction(trans, (int)PTR_ERR(root));
+ if (!err)
+ err = PTR_ERR(root);
+ break;
+ }
+ ASSERT(root->reloc_root == reloc_root);
/*
* set reference count to 1, so btrfs_recover_relocation
@@ -1834,16 +1904,27 @@ again:
*/
if (!err)
btrfs_set_root_refs(&reloc_root->root_item, 1);
- btrfs_update_reloc_root(trans, root);
+ ret = btrfs_update_reloc_root(trans, root);
+ /*
+ * Even if we have an error we need this reloc root back on our
+ * list so we can clean up properly.
+ */
list_add(&reloc_root->root_list, &reloc_roots);
btrfs_put_root(root);
+
+ if (ret) {
+ btrfs_abort_transaction(trans, ret);
+ if (!err)
+ err = ret;
+ break;
+ }
}
list_splice(&reloc_roots, &rc->reloc_roots);
if (!err)
- btrfs_commit_transaction(trans);
+ err = btrfs_commit_transaction(trans);
else
btrfs_end_transaction(trans);
return err;
@@ -1888,8 +1969,29 @@ again:
root = btrfs_get_fs_root(fs_info, reloc_root->root_key.offset,
false);
if (btrfs_root_refs(&reloc_root->root_item) > 0) {
- BUG_ON(IS_ERR(root));
- BUG_ON(root->reloc_root != reloc_root);
+ if (IS_ERR(root)) {
+ /*
+ * For recovery we read the fs roots on mount,
+ * and if we didn't find the root then we marked
+ * the reloc root as a garbage root. For normal
+ * relocation obviously the root should exist in
+ * memory. However there's no reason we can't
+ * handle the error properly here just in case.
+ */
+ ASSERT(0);
+ ret = PTR_ERR(root);
+ goto out;
+ }
+ if (root->reloc_root != reloc_root) {
+ /*
+ * This is actually impossible without something
+ * going really wrong (like weird race condition
+ * or cosmic rays).
+ */
+ ASSERT(0);
+ ret = -EINVAL;
+ goto out;
+ }
ret = merge_reloc_root(rc, root);
btrfs_put_root(root);
if (ret) {
@@ -1971,8 +2073,27 @@ static int record_reloc_root_in_trans(struct btrfs_trans_handle *trans,
return 0;
root = btrfs_get_fs_root(fs_info, reloc_root->root_key.offset, false);
- BUG_ON(IS_ERR(root));
- BUG_ON(root->reloc_root != reloc_root);
+
+ /*
+ * This should succeed, since we can't have a reloc root without having
+ * already looked up the actual root and created the reloc root for this
+ * root.
+ *
+ * However if there's some sort of corruption where we have a ref to a
+ * reloc root without a corresponding root this could return ENOENT.
+ */
+ if (IS_ERR(root)) {
+ ASSERT(0);
+ return PTR_ERR(root);
+ }
+ if (root->reloc_root != reloc_root) {
+ ASSERT(0);
+ btrfs_err(fs_info,
+ "root %llu has two reloc roots associated with it",
+ reloc_root->root_key.offset);
+ btrfs_put_root(root);
+ return -EUCLEAN;
+ }
ret = btrfs_record_root_in_trans(trans, root);
btrfs_put_root(root);
@@ -1988,26 +2109,77 @@ struct btrfs_root *select_reloc_root(struct btrfs_trans_handle *trans,
struct btrfs_backref_node *next;
struct btrfs_root *root;
int index = 0;
+ int ret;
next = node;
while (1) {
cond_resched();
next = walk_up_backref(next, edges, &index);
root = next->root;
- BUG_ON(!root);
- BUG_ON(!test_bit(BTRFS_ROOT_SHAREABLE, &root->state));
+
+ /*
+ * If there is no root, then our references for this block are
+ * incomplete, as we should be able to walk all the way up to a
+ * block that is owned by a root.
+ *
+ * This path is only for SHAREABLE roots, so if we come upon a
+ * non-SHAREABLE root then we have backrefs that resolve
+ * improperly.
+ *
+ * Both of these cases indicate file system corruption, or a bug
+ * in the backref walking code.
+ */
+ if (!root) {
+ ASSERT(0);
+ btrfs_err(trans->fs_info,
+ "bytenr %llu doesn't have a backref path ending in a root",
+ node->bytenr);
+ return ERR_PTR(-EUCLEAN);
+ }
+ if (!test_bit(BTRFS_ROOT_SHAREABLE, &root->state)) {
+ ASSERT(0);
+ btrfs_err(trans->fs_info,
+ "bytenr %llu has multiple refs with one ending in a non-shareable root",
+ node->bytenr);
+ return ERR_PTR(-EUCLEAN);
+ }
if (root->root_key.objectid == BTRFS_TREE_RELOC_OBJECTID) {
- record_reloc_root_in_trans(trans, root);
+ ret = record_reloc_root_in_trans(trans, root);
+ if (ret)
+ return ERR_PTR(ret);
break;
}
- btrfs_record_root_in_trans(trans, root);
+ ret = btrfs_record_root_in_trans(trans, root);
+ if (ret)
+ return ERR_PTR(ret);
root = root->reloc_root;
+ /*
+ * We could have raced with another thread which failed, so
+ * root->reloc_root may not be set, return ENOENT in this case.
+ */
+ if (!root)
+ return ERR_PTR(-ENOENT);
+
if (next->new_bytenr != root->node->start) {
- BUG_ON(next->new_bytenr);
- BUG_ON(!list_empty(&next->list));
+ /*
+ * We just created the reloc root, so we shouldn't have
+ * ->new_bytenr set and this shouldn't be in the changed
+ * list. If it is then we have multiple roots pointing
+ * at the same bytenr which indicates corruption, or
+ * we've made a mistake in the backref walking code.
+ */
+ ASSERT(next->new_bytenr == 0);
+ ASSERT(list_empty(&next->list));
+ if (next->new_bytenr || !list_empty(&next->list)) {
+ btrfs_err(trans->fs_info,
+ "bytenr %llu possibly has multiple roots pointing at the same bytenr %llu",
+ node->bytenr, next->bytenr);
+ return ERR_PTR(-EUCLEAN);
+ }
+
next->new_bytenr = root->node->start;
btrfs_put_root(next->root);
next->root = btrfs_grab_root(root);
@@ -2024,8 +2196,14 @@ struct btrfs_root *select_reloc_root(struct btrfs_trans_handle *trans,
if (!next || next->level <= node->level)
break;
}
- if (!root)
- return NULL;
+ if (!root) {
+ /*
+ * This can happen if there's fs corruption or if there's a bug
+ * in the backref lookup code.
+ */
+ ASSERT(0);
+ return ERR_PTR(-ENOENT);
+ }
next = node;
/* setup backref node path for btrfs_reloc_cow_block */
@@ -2061,7 +2239,13 @@ struct btrfs_root *select_one_root(struct btrfs_backref_node *node)
cond_resched();
next = walk_up_backref(next, edges, &index);
root = next->root;
- BUG_ON(!root);
+
+ /*
+ * This can occur if we have incomplete extent refs leading all
+ * the way up a particular path, in this case return -EUCLEAN.
+ */
+ if (!root)
+ return ERR_PTR(-EUCLEAN);
/* No other choice for non-shareable tree */
if (!test_bit(BTRFS_ROOT_SHAREABLE, &root->state))
@@ -2181,7 +2365,11 @@ static int do_relocation(struct btrfs_trans_handle *trans,
int slot;
int ret = 0;
- BUG_ON(lowest && node->eb);
+ /*
+ * If we are lowest then this is the first time we're processing this
+ * block, and thus shouldn't have an eb associated with it yet.
+ */
+ ASSERT(!lowest || !node->eb);
path->lowest_level = node->level + 1;
rc->backref_cache.path[node->level] = node;
@@ -2192,7 +2380,10 @@ static int do_relocation(struct btrfs_trans_handle *trans,
upper = edge->node[UPPER];
root = select_reloc_root(trans, rc, upper, edges);
- BUG_ON(!root);
+ if (IS_ERR(root)) {
+ ret = PTR_ERR(root);
+ goto next;
+ }
if (upper->eb && !upper->locked) {
if (!lowest) {
@@ -2266,7 +2457,11 @@ static int do_relocation(struct btrfs_trans_handle *trans,
free_extent_buffer(eb);
if (ret < 0)
goto next;
- BUG_ON(node->eb != eb);
+ /*
+ * We've just COWed this block, it should have updated
+ * the correct backref node entry.
+ */
+ ASSERT(node->eb == eb);
} else {
btrfs_set_node_blockptr(upper->eb, slot,
node->eb->start);
@@ -2281,10 +2476,11 @@ static int do_relocation(struct btrfs_trans_handle *trans,
btrfs_init_tree_ref(&ref, node->level,
btrfs_header_owner(upper->eb));
ret = btrfs_inc_extent_ref(trans, &ref);
- BUG_ON(ret);
-
- ret = btrfs_drop_subtree(trans, root, eb, upper->eb);
- BUG_ON(ret);
+ if (!ret)
+ ret = btrfs_drop_subtree(trans, root, eb,
+ upper->eb);
+ if (ret)
+ btrfs_abort_transaction(trans, ret);
}
next:
if (!upper->pending)
@@ -2302,7 +2498,12 @@ next:
}
path->lowest_level = 0;
- BUG_ON(ret == -ENOSPC);
+
+ /*
+ * We should have allocated all of our space in the block rsv and thus
+ * shouldn't ENOSPC.
+ */
+ ASSERT(ret != -ENOSPC);
return ret;
}
@@ -2434,16 +2635,53 @@ static int relocate_tree_block(struct btrfs_trans_handle *trans,
BUG_ON(node->processed);
root = select_one_root(node);
- if (root == ERR_PTR(-ENOENT)) {
- update_processed_blocks(rc, node);
+ if (IS_ERR(root)) {
+ ret = PTR_ERR(root);
+
+ /* See explanation in select_one_root for the -EUCLEAN case. */
+ ASSERT(ret == -ENOENT);
+ if (ret == -ENOENT) {
+ ret = 0;
+ update_processed_blocks(rc, node);
+ }
goto out;
}
if (root) {
if (test_bit(BTRFS_ROOT_SHAREABLE, &root->state)) {
- BUG_ON(node->new_bytenr);
- BUG_ON(!list_empty(&node->list));
- btrfs_record_root_in_trans(trans, root);
+ /*
+ * This block was the root block of a root, and this is
+ * the first time we're processing the block and thus it
+ * should not have had the ->new_bytenr modified and
+ * should have not been included on the changed list.
+ *
+ * However in the case of corruption we could have
+ * multiple refs pointing to the same block improperly,
+ * and thus we would trip over these checks. ASSERT()
+ * for the developer case, because it could indicate a
+ * bug in the backref code, however error out for a
+ * normal user in the case of corruption.
+ */
+ ASSERT(node->new_bytenr == 0);
+ ASSERT(list_empty(&node->list));
+ if (node->new_bytenr || !list_empty(&node->list)) {
+ btrfs_err(root->fs_info,
+ "bytenr %llu has improper references to it",
+ node->bytenr);
+ ret = -EUCLEAN;
+ goto out;
+ }
+ ret = btrfs_record_root_in_trans(trans, root);
+ if (ret)
+ goto out;
+ /*
+ * Another thread could have failed, need to check if we
+ * have reloc_root actually set.
+ */
+ if (!root->reloc_root) {
+ ret = -ENOENT;
+ goto out;
+ }
root = root->reloc_root;
node->new_bytenr = root->node->start;
btrfs_put_root(node->root);
@@ -2578,7 +2816,7 @@ static noinline_for_stack int prealloc_file_extent_cluster(
return btrfs_end_transaction(trans);
}
- inode_lock(&inode->vfs_inode);
+ btrfs_inode_lock(&inode->vfs_inode, 0);
for (nr = 0; nr < cluster->nr; nr++) {
start = cluster->boundary[nr] - offset;
if (nr + 1 < cluster->nr)
@@ -2596,7 +2834,7 @@ static noinline_for_stack int prealloc_file_extent_cluster(
if (ret)
break;
}
- inode_unlock(&inode->vfs_inode);
+ btrfs_inode_unlock(&inode->vfs_inode, 0);
if (cur_offset < prealloc_end)
btrfs_free_reserved_data_space_noquota(inode->root->fs_info,
@@ -3220,20 +3458,6 @@ static void unset_reloc_control(struct reloc_control *rc)
mutex_unlock(&fs_info->reloc_mutex);
}
-static int check_extent_flags(u64 flags)
-{
- if ((flags & BTRFS_EXTENT_FLAG_DATA) &&
- (flags & BTRFS_EXTENT_FLAG_TREE_BLOCK))
- return 1;
- if (!(flags & BTRFS_EXTENT_FLAG_DATA) &&
- !(flags & BTRFS_EXTENT_FLAG_TREE_BLOCK))
- return 1;
- if ((flags & BTRFS_EXTENT_FLAG_DATA) &&
- (flags & BTRFS_BLOCK_FLAG_FULL_BACKREF))
- return 1;
- return 0;
-}
-
static noinline_for_stack
int prepare_to_relocate(struct reloc_control *rc)
{
@@ -3272,8 +3496,7 @@ int prepare_to_relocate(struct reloc_control *rc)
*/
return PTR_ERR(trans);
}
- btrfs_commit_transaction(trans);
- return 0;
+ return btrfs_commit_transaction(trans);
}
static noinline_for_stack int relocate_block_group(struct reloc_control *rc)
@@ -3285,7 +3508,6 @@ static noinline_for_stack int relocate_block_group(struct reloc_control *rc)
struct btrfs_path *path;
struct btrfs_extent_item *ei;
u64 flags;
- u32 item_size;
int ret;
int err = 0;
int progress = 0;
@@ -3334,19 +3556,7 @@ restart:
ei = btrfs_item_ptr(path->nodes[0], path->slots[0],
struct btrfs_extent_item);
- item_size = btrfs_item_size_nr(path->nodes[0], path->slots[0]);
- if (item_size >= sizeof(*ei)) {
- flags = btrfs_extent_flags(path->nodes[0], ei);
- ret = check_extent_flags(flags);
- BUG_ON(ret);
- } else if (unlikely(item_size == sizeof(struct btrfs_extent_item_v0))) {
- err = -EINVAL;
- btrfs_print_v0_err(trans->fs_info);
- btrfs_abort_transaction(trans, err);
- break;
- } else {
- BUG();
- }
+ flags = btrfs_extent_flags(path->nodes[0], ei);
if (flags & BTRFS_EXTENT_FLAG_TREE_BLOCK) {
ret = add_tree_block(rc, &key, path, &blocks);
@@ -3445,7 +3655,9 @@ restart:
err = PTR_ERR(trans);
goto out_free;
}
- btrfs_commit_transaction(trans);
+ ret = btrfs_commit_transaction(trans);
+ if (ret && !err)
+ err = ret;
out_free:
ret = clean_dirty_subvols(rc);
if (ret < 0 && !err)
@@ -3488,6 +3700,35 @@ out:
return ret;
}
+static void delete_orphan_inode(struct btrfs_trans_handle *trans,
+ struct btrfs_root *root, u64 objectid)
+{
+ struct btrfs_path *path;
+ struct btrfs_key key;
+ int ret = 0;
+
+ path = btrfs_alloc_path();
+ if (!path) {
+ ret = -ENOMEM;
+ goto out;
+ }
+
+ key.objectid = objectid;
+ key.type = BTRFS_INODE_ITEM_KEY;
+ key.offset = 0;
+ ret = btrfs_search_slot(trans, root, &key, path, -1, 1);
+ if (ret) {
+ if (ret > 0)
+ ret = -ENOENT;
+ goto out;
+ }
+ ret = btrfs_del_item(trans, root, path);
+out:
+ if (ret)
+ btrfs_abort_transaction(trans, ret);
+ btrfs_free_path(path);
+}
+
/*
* helper to create inode for data relocation.
* the inode is in data relocation tree and its link count is 0
@@ -3514,10 +3755,16 @@ struct inode *create_reloc_inode(struct btrfs_fs_info *fs_info,
goto out;
err = __insert_orphan_inode(trans, root, objectid);
- BUG_ON(err);
+ if (err)
+ goto out;
inode = btrfs_iget(fs_info->sb, objectid, root);
- BUG_ON(IS_ERR(inode));
+ if (IS_ERR(inode)) {
+ delete_orphan_inode(trans, root, objectid);
+ err = PTR_ERR(inode);
+ inode = NULL;
+ goto out;
+ }
BTRFS_I(inode)->index_cnt = group->start;
err = btrfs_orphan_add(trans, BTRFS_I(inode));
@@ -3859,7 +4106,13 @@ int btrfs_recover_relocation(struct btrfs_root *root)
}
err = __add_reloc_root(reloc_root);
- BUG_ON(err < 0); /* -ENOMEM or logic error */
+ ASSERT(err != -EEXIST);
+ if (err) {
+ list_add_tail(&reloc_root->root_list, &reloc_roots);
+ btrfs_put_root(fs_root);
+ btrfs_end_transaction(trans);
+ goto out_unset;
+ }
fs_root->reloc_root = btrfs_grab_root(reloc_root);
btrfs_put_root(fs_root);
}
@@ -4074,7 +4327,12 @@ int btrfs_reloc_post_snapshot(struct btrfs_trans_handle *trans,
return PTR_ERR(reloc_root);
ret = __add_reloc_root(reloc_root);
- BUG_ON(ret < 0);
+ ASSERT(ret != -EEXIST);
+ if (ret) {
+ /* Pairs with create_reloc_root */
+ btrfs_put_root(reloc_root);
+ return ret;
+ }
new_root->reloc_root = btrfs_grab_root(reloc_root);
if (rc->create_reloc_tree)
diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c
index 3d9088eab2fc..485cda3eb8d7 100644
--- a/fs/btrfs/scrub.c
+++ b/fs/btrfs/scrub.c
@@ -206,9 +206,6 @@ struct full_stripe_lock {
struct mutex mutex;
};
-static void scrub_pending_bio_inc(struct scrub_ctx *sctx);
-static void scrub_pending_bio_dec(struct scrub_ctx *sctx);
-static int scrub_handle_errored_block(struct scrub_block *sblock_to_check);
static int scrub_setup_recheck_block(struct scrub_block *original_sblock,
struct scrub_block *sblocks_for_recheck);
static void scrub_recheck_block(struct btrfs_fs_info *fs_info,
@@ -226,14 +223,11 @@ static int scrub_write_page_to_dev_replace(struct scrub_block *sblock,
static int scrub_checksum_data(struct scrub_block *sblock);
static int scrub_checksum_tree_block(struct scrub_block *sblock);
static int scrub_checksum_super(struct scrub_block *sblock);
-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, u32 len,
u64 physical, struct btrfs_device *dev, u64 flags,
u64 gen, int mirror_num, u8 *csum,
@@ -251,8 +245,6 @@ static int scrub_add_page_to_wr_bio(struct scrub_ctx *sctx,
static void scrub_wr_submit(struct scrub_ctx *sctx);
static void scrub_wr_bio_end_io(struct bio *bio);
static void scrub_wr_bio_end_io_worker(struct btrfs_work *work);
-static void __scrub_blocked_if_needed(struct btrfs_fs_info *fs_info);
-static void scrub_blocked_if_needed(struct btrfs_fs_info *fs_info);
static void scrub_put_ctx(struct scrub_ctx *sctx);
static inline int scrub_is_page_on_raid56(struct scrub_page *spage)
@@ -3682,8 +3674,8 @@ int scrub_enumerate_chunks(struct scrub_ctx *sctx,
spin_lock(&cache->lock);
if (!cache->to_copy) {
spin_unlock(&cache->lock);
- ro_set = 0;
- goto done;
+ btrfs_put_block_group(cache);
+ goto skip;
}
spin_unlock(&cache->lock);
}
@@ -3841,7 +3833,6 @@ int scrub_enumerate_chunks(struct scrub_ctx *sctx,
cache, found_key.offset))
ro_set = 0;
-done:
down_write(&dev_replace->rwsem);
dev_replace->cursor_left = dev_replace->cursor_right;
dev_replace->item_needs_writeback = 1;
diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c
index 8f323859156b..55741adf9071 100644
--- a/fs/btrfs/send.c
+++ b/fs/btrfs/send.c
@@ -6650,6 +6650,7 @@ static int full_send_tree(struct send_ctx *sctx)
path = alloc_path_for_send();
if (!path)
return -ENOMEM;
+ path->reada = READA_FORWARD_ALWAYS;
key.objectid = BTRFS_FIRST_FREE_OBJECTID;
key.type = BTRFS_INODE_ITEM_KEY;
@@ -6688,15 +6689,35 @@ out:
return ret;
}
-static int tree_move_down(struct btrfs_path *path, int *level)
+static int tree_move_down(struct btrfs_path *path, int *level, u64 reada_min_gen)
{
struct extent_buffer *eb;
+ struct extent_buffer *parent = path->nodes[*level];
+ int slot = path->slots[*level];
+ const int nritems = btrfs_header_nritems(parent);
+ u64 reada_max;
+ u64 reada_done = 0;
BUG_ON(*level == 0);
- eb = btrfs_read_node_slot(path->nodes[*level], path->slots[*level]);
+ eb = btrfs_read_node_slot(parent, slot);
if (IS_ERR(eb))
return PTR_ERR(eb);
+ /*
+ * Trigger readahead for the next leaves we will process, so that it is
+ * very likely that when we need them they are already in memory and we
+ * will not block on disk IO. For nodes we only do readahead for one,
+ * since the time window between processing nodes is typically larger.
+ */
+ reada_max = (*level == 1 ? SZ_128K : eb->fs_info->nodesize);
+
+ for (slot++; slot < nritems && reada_done < reada_max; slot++) {
+ if (btrfs_node_ptr_generation(parent, slot) > reada_min_gen) {
+ btrfs_readahead_node_child(parent, slot);
+ reada_done += eb->fs_info->nodesize;
+ }
+ }
+
path->nodes[*level - 1] = eb;
path->slots[*level - 1] = 0;
(*level)--;
@@ -6736,14 +6757,15 @@ static int tree_move_next_or_upnext(struct btrfs_path *path,
static int tree_advance(struct btrfs_path *path,
int *level, int root_level,
int allow_down,
- struct btrfs_key *key)
+ struct btrfs_key *key,
+ u64 reada_min_gen)
{
int ret;
if (*level == 0 || !allow_down) {
ret = tree_move_next_or_upnext(path, level, root_level);
} else {
- ret = tree_move_down(path, level);
+ ret = tree_move_down(path, level, reada_min_gen);
}
if (ret >= 0) {
if (*level == 0)
@@ -6817,6 +6839,7 @@ static int btrfs_compare_trees(struct btrfs_root *left_root,
u64 right_blockptr;
u64 left_gen;
u64 right_gen;
+ u64 reada_min_gen;
left_path = btrfs_alloc_path();
if (!left_path) {
@@ -6896,6 +6919,14 @@ static int btrfs_compare_trees(struct btrfs_root *left_root,
ret = -ENOMEM;
goto out;
}
+ /*
+ * Our right root is the parent root, while the left root is the "send"
+ * root. We know that all new nodes/leaves in the left root must have
+ * a generation greater than the right root's generation, so we trigger
+ * readahead for those nodes and leaves of the left root, as we know we
+ * will need to read them at some point.
+ */
+ reada_min_gen = btrfs_header_generation(right_root->commit_root);
up_read(&fs_info->commit_root_sem);
if (left_level == 0)
@@ -6920,7 +6951,7 @@ static int btrfs_compare_trees(struct btrfs_root *left_root,
ret = tree_advance(left_path, &left_level,
left_root_level,
advance_left != ADVANCE_ONLY_NEXT,
- &left_key);
+ &left_key, reada_min_gen);
if (ret == -1)
left_end_reached = ADVANCE;
else if (ret < 0)
@@ -6931,7 +6962,7 @@ static int btrfs_compare_trees(struct btrfs_root *left_root,
ret = tree_advance(right_path, &right_level,
right_root_level,
advance_right != ADVANCE_ONLY_NEXT,
- &right_key);
+ &right_key, reada_min_gen);
if (ret == -1)
right_end_reached = ADVANCE;
else if (ret < 0)
diff --git a/fs/btrfs/space-info.c b/fs/btrfs/space-info.c
index 2da6177f4b0b..2dc674b7c3b1 100644
--- a/fs/btrfs/space-info.c
+++ b/fs/btrfs/space-info.c
@@ -861,8 +861,8 @@ static bool need_preemptive_reclaim(struct btrfs_fs_info *fs_info,
* of heavy DIO or ordered reservations, preemptive flushing will just
* waste time and cause us to slow down.
*/
- ordered = percpu_counter_sum_positive(&fs_info->ordered_bytes);
- delalloc = percpu_counter_sum_positive(&fs_info->delalloc_bytes);
+ ordered = percpu_counter_read_positive(&fs_info->ordered_bytes);
+ delalloc = percpu_counter_read_positive(&fs_info->delalloc_bytes);
if (ordered >= delalloc)
used += fs_info->delayed_refs_rsv.reserved +
fs_info->delayed_block_rsv.reserved;
diff --git a/fs/btrfs/subpage.c b/fs/btrfs/subpage.c
index c69049e7daa9..2d19089ab625 100644
--- a/fs/btrfs/subpage.c
+++ b/fs/btrfs/subpage.c
@@ -4,6 +4,64 @@
#include "ctree.h"
#include "subpage.h"
+/*
+ * Subpage (sectorsize < PAGE_SIZE) support overview:
+ *
+ * Limitations:
+ *
+ * - Only support 64K page size for now
+ * This is to make metadata handling easier, as 64K page would ensure
+ * all nodesize would fit inside one page, thus we don't need to handle
+ * cases where a tree block crosses several pages.
+ *
+ * - Only metadata read-write for now
+ * The data read-write part is in development.
+ *
+ * - Metadata can't cross 64K page boundary
+ * btrfs-progs and kernel have done that for a while, thus only ancient
+ * filesystems could have such problem. For such case, do a graceful
+ * rejection.
+ *
+ * Special behavior:
+ *
+ * - Metadata
+ * Metadata read is fully supported.
+ * Meaning when reading one tree block will only trigger the read for the
+ * needed range, other unrelated range in the same page will not be touched.
+ *
+ * Metadata write support is partial.
+ * The writeback is still for the full page, but we will only submit
+ * the dirty extent buffers in the page.
+ *
+ * This means, if we have a metadata page like this:
+ *
+ * Page offset
+ * 0 16K 32K 48K 64K
+ * |/////////| |///////////|
+ * \- Tree block A \- Tree block B
+ *
+ * Even if we just want to writeback tree block A, we will also writeback
+ * tree block B if it's also dirty.
+ *
+ * This may cause extra metadata writeback which results more COW.
+ *
+ * Implementation:
+ *
+ * - Common
+ * Both metadata and data will use a new structure, btrfs_subpage, to
+ * record the status of each sector inside a page. This provides the extra
+ * granularity needed.
+ *
+ * - Metadata
+ * Since we have multiple tree blocks inside one page, we can't rely on page
+ * locking anymore, or we will have greatly reduced concurrency or even
+ * deadlocks (hold one tree lock while trying to lock another tree lock in
+ * the same page).
+ *
+ * Thus for metadata locking, subpage support relies on io_tree locking only.
+ * This means a slightly higher tree locking latency.
+ */
+
int btrfs_attach_subpage(const struct btrfs_fs_info *fs_info,
struct page *page, enum btrfs_subpage_type type)
{
@@ -220,6 +278,82 @@ void btrfs_subpage_clear_error(const struct btrfs_fs_info *fs_info,
spin_unlock_irqrestore(&subpage->lock, flags);
}
+void btrfs_subpage_set_dirty(const struct btrfs_fs_info *fs_info,
+ struct page *page, u64 start, u32 len)
+{
+ struct btrfs_subpage *subpage = (struct btrfs_subpage *)page->private;
+ u16 tmp = btrfs_subpage_calc_bitmap(fs_info, page, start, len);
+ unsigned long flags;
+
+ spin_lock_irqsave(&subpage->lock, flags);
+ subpage->dirty_bitmap |= tmp;
+ spin_unlock_irqrestore(&subpage->lock, flags);
+ set_page_dirty(page);
+}
+
+/*
+ * Extra clear_and_test function for subpage dirty bitmap.
+ *
+ * Return true if we're the last bits in the dirty_bitmap and clear the
+ * dirty_bitmap.
+ * Return false otherwise.
+ *
+ * NOTE: Callers should manually clear page dirty for true case, as we have
+ * extra handling for tree blocks.
+ */
+bool btrfs_subpage_clear_and_test_dirty(const struct btrfs_fs_info *fs_info,
+ struct page *page, u64 start, u32 len)
+{
+ struct btrfs_subpage *subpage = (struct btrfs_subpage *)page->private;
+ u16 tmp = btrfs_subpage_calc_bitmap(fs_info, page, start, len);
+ unsigned long flags;
+ bool last = false;
+
+ spin_lock_irqsave(&subpage->lock, flags);
+ subpage->dirty_bitmap &= ~tmp;
+ if (subpage->dirty_bitmap == 0)
+ last = true;
+ spin_unlock_irqrestore(&subpage->lock, flags);
+ return last;
+}
+
+void btrfs_subpage_clear_dirty(const struct btrfs_fs_info *fs_info,
+ struct page *page, u64 start, u32 len)
+{
+ bool last;
+
+ last = btrfs_subpage_clear_and_test_dirty(fs_info, page, start, len);
+ if (last)
+ clear_page_dirty_for_io(page);
+}
+
+void btrfs_subpage_set_writeback(const struct btrfs_fs_info *fs_info,
+ struct page *page, u64 start, u32 len)
+{
+ struct btrfs_subpage *subpage = (struct btrfs_subpage *)page->private;
+ u16 tmp = btrfs_subpage_calc_bitmap(fs_info, page, start, len);
+ unsigned long flags;
+
+ spin_lock_irqsave(&subpage->lock, flags);
+ subpage->writeback_bitmap |= tmp;
+ set_page_writeback(page);
+ spin_unlock_irqrestore(&subpage->lock, flags);
+}
+
+void btrfs_subpage_clear_writeback(const struct btrfs_fs_info *fs_info,
+ struct page *page, u64 start, u32 len)
+{
+ struct btrfs_subpage *subpage = (struct btrfs_subpage *)page->private;
+ u16 tmp = btrfs_subpage_calc_bitmap(fs_info, page, start, len);
+ unsigned long flags;
+
+ spin_lock_irqsave(&subpage->lock, flags);
+ subpage->writeback_bitmap &= ~tmp;
+ if (subpage->writeback_bitmap == 0)
+ end_page_writeback(page);
+ spin_unlock_irqrestore(&subpage->lock, flags);
+}
+
/*
* Unlike set/clear which is dependent on each page status, for test all bits
* are tested in the same way.
@@ -240,6 +374,8 @@ bool btrfs_subpage_test_##name(const struct btrfs_fs_info *fs_info, \
}
IMPLEMENT_BTRFS_SUBPAGE_TEST_OP(uptodate);
IMPLEMENT_BTRFS_SUBPAGE_TEST_OP(error);
+IMPLEMENT_BTRFS_SUBPAGE_TEST_OP(dirty);
+IMPLEMENT_BTRFS_SUBPAGE_TEST_OP(writeback);
/*
* Note that, in selftests (extent-io-tests), we can have empty fs_info passed
@@ -276,3 +412,7 @@ bool btrfs_page_test_##name(const struct btrfs_fs_info *fs_info, \
IMPLEMENT_BTRFS_PAGE_OPS(uptodate, SetPageUptodate, ClearPageUptodate,
PageUptodate);
IMPLEMENT_BTRFS_PAGE_OPS(error, SetPageError, ClearPageError, PageError);
+IMPLEMENT_BTRFS_PAGE_OPS(dirty, set_page_dirty, clear_page_dirty_for_io,
+ PageDirty);
+IMPLEMENT_BTRFS_PAGE_OPS(writeback, set_page_writeback, end_page_writeback,
+ PageWriteback);
diff --git a/fs/btrfs/subpage.h b/fs/btrfs/subpage.h
index b86a4881475d..bfd626e955be 100644
--- a/fs/btrfs/subpage.h
+++ b/fs/btrfs/subpage.h
@@ -20,6 +20,8 @@ struct btrfs_subpage {
spinlock_t lock;
u16 uptodate_bitmap;
u16 error_bitmap;
+ u16 dirty_bitmap;
+ u16 writeback_bitmap;
union {
/*
* Structures only used by metadata
@@ -87,5 +89,10 @@ bool btrfs_page_test_##name(const struct btrfs_fs_info *fs_info, \
DECLARE_BTRFS_SUBPAGE_OPS(uptodate);
DECLARE_BTRFS_SUBPAGE_OPS(error);
+DECLARE_BTRFS_SUBPAGE_OPS(dirty);
+DECLARE_BTRFS_SUBPAGE_OPS(writeback);
+
+bool btrfs_subpage_clear_and_test_dirty(const struct btrfs_fs_info *fs_info,
+ struct page *page, u64 start, u32 len);
#endif
diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index f7a4ad86adee..4a396c1147f1 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -252,6 +252,32 @@ void __cold btrfs_printk(const struct btrfs_fs_info *fs_info, const char *fmt, .
}
#endif
+#if BITS_PER_LONG == 32
+void __cold btrfs_warn_32bit_limit(struct btrfs_fs_info *fs_info)
+{
+ if (!test_and_set_bit(BTRFS_FS_32BIT_WARN, &fs_info->flags)) {
+ btrfs_warn(fs_info, "reaching 32bit limit for logical addresses");
+ btrfs_warn(fs_info,
+"due to page cache limit on 32bit systems, btrfs can't access metadata at or beyond %lluT",
+ BTRFS_32BIT_MAX_FILE_SIZE >> 40);
+ btrfs_warn(fs_info,
+ "please consider upgrading to 64bit kernel/hardware");
+ }
+}
+
+void __cold btrfs_err_32bit_limit(struct btrfs_fs_info *fs_info)
+{
+ if (!test_and_set_bit(BTRFS_FS_32BIT_ERROR, &fs_info->flags)) {
+ btrfs_err(fs_info, "reached 32bit limit for logical addresses");
+ btrfs_err(fs_info,
+"due to page cache limit on 32bit systems, metadata beyond %lluT can't be accessed",
+ BTRFS_32BIT_MAX_FILE_SIZE >> 40);
+ btrfs_err(fs_info,
+ "please consider upgrading to 64bit kernel/hardware");
+ }
+}
+#endif
+
/*
* We only mark the transaction aborted and then set the file system read-only.
* This will prevent new transactions from starting or trying to join this
diff --git a/fs/btrfs/sysfs.c b/fs/btrfs/sysfs.c
index 6eb1c50fa98c..436ac7b4b334 100644
--- a/fs/btrfs/sysfs.c
+++ b/fs/btrfs/sysfs.c
@@ -360,11 +360,26 @@ static ssize_t supported_rescue_options_show(struct kobject *kobj,
BTRFS_ATTR(static_feature, supported_rescue_options,
supported_rescue_options_show);
+static ssize_t supported_sectorsizes_show(struct kobject *kobj,
+ struct kobj_attribute *a,
+ char *buf)
+{
+ ssize_t ret = 0;
+
+ /* Only sectorsize == PAGE_SIZE is now supported */
+ ret += scnprintf(buf + ret, PAGE_SIZE - ret, "%lu\n", PAGE_SIZE);
+
+ return ret;
+}
+BTRFS_ATTR(static_feature, supported_sectorsizes,
+ supported_sectorsizes_show);
+
static struct attribute *btrfs_supported_static_feature_attrs[] = {
BTRFS_ATTR_PTR(static_feature, rmdir_subvol),
BTRFS_ATTR_PTR(static_feature, supported_checksums),
BTRFS_ATTR_PTR(static_feature, send_stream_version),
BTRFS_ATTR_PTR(static_feature, supported_rescue_options),
+ BTRFS_ATTR_PTR(static_feature, supported_sectorsizes),
NULL
};
@@ -965,6 +980,40 @@ static ssize_t btrfs_read_policy_store(struct kobject *kobj,
}
BTRFS_ATTR_RW(, read_policy, btrfs_read_policy_show, btrfs_read_policy_store);
+static ssize_t btrfs_bg_reclaim_threshold_show(struct kobject *kobj,
+ struct kobj_attribute *a,
+ char *buf)
+{
+ struct btrfs_fs_info *fs_info = to_fs_info(kobj);
+ ssize_t ret;
+
+ ret = scnprintf(buf, PAGE_SIZE, "%d\n", fs_info->bg_reclaim_threshold);
+
+ return ret;
+}
+
+static ssize_t btrfs_bg_reclaim_threshold_store(struct kobject *kobj,
+ struct kobj_attribute *a,
+ const char *buf, size_t len)
+{
+ struct btrfs_fs_info *fs_info = to_fs_info(kobj);
+ int thresh;
+ int ret;
+
+ ret = kstrtoint(buf, 10, &thresh);
+ if (ret)
+ return ret;
+
+ if (thresh <= 50 || thresh > 100)
+ return -EINVAL;
+
+ fs_info->bg_reclaim_threshold = thresh;
+
+ return len;
+}
+BTRFS_ATTR_RW(, bg_reclaim_threshold, btrfs_bg_reclaim_threshold_show,
+ btrfs_bg_reclaim_threshold_store);
+
static const struct attribute *btrfs_attrs[] = {
BTRFS_ATTR_PTR(, label),
BTRFS_ATTR_PTR(, nodesize),
@@ -976,6 +1025,7 @@ static const struct attribute *btrfs_attrs[] = {
BTRFS_ATTR_PTR(, exclusive_operation),
BTRFS_ATTR_PTR(, generation),
BTRFS_ATTR_PTR(, read_policy),
+ BTRFS_ATTR_PTR(, bg_reclaim_threshold),
NULL,
};
diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c
index acff6bb49a97..f75de9f6c0ad 100644
--- a/fs/btrfs/transaction.c
+++ b/fs/btrfs/transaction.c
@@ -260,6 +260,7 @@ static inline int extwriter_counter_read(struct btrfs_transaction *trans)
void btrfs_trans_release_chunk_metadata(struct btrfs_trans_handle *trans)
{
struct btrfs_fs_info *fs_info = trans->fs_info;
+ struct btrfs_transaction *cur_trans = trans->transaction;
if (!trans->chunk_bytes_reserved)
return;
@@ -268,6 +269,8 @@ void btrfs_trans_release_chunk_metadata(struct btrfs_trans_handle *trans)
btrfs_block_rsv_release(fs_info, &fs_info->chunk_block_rsv,
trans->chunk_bytes_reserved, NULL);
+ atomic64_sub(trans->chunk_bytes_reserved, &cur_trans->chunk_bytes_reserved);
+ cond_wake_up(&cur_trans->chunk_reserve_wait);
trans->chunk_bytes_reserved = 0;
}
@@ -383,6 +386,8 @@ loop:
spin_lock_init(&cur_trans->dropped_roots_lock);
INIT_LIST_HEAD(&cur_trans->releasing_ebs);
spin_lock_init(&cur_trans->releasing_ebs_lock);
+ atomic64_set(&cur_trans->chunk_bytes_reserved, 0);
+ init_waitqueue_head(&cur_trans->chunk_reserve_wait);
list_add_tail(&cur_trans->list, &fs_info->trans_list);
extent_io_tree_init(fs_info, &cur_trans->dirty_pages,
IO_TREE_TRANS_DIRTY_PAGES, fs_info->btree_inode);
@@ -408,6 +413,7 @@ static int record_root_in_trans(struct btrfs_trans_handle *trans,
int force)
{
struct btrfs_fs_info *fs_info = root->fs_info;
+ int ret = 0;
if ((test_bit(BTRFS_ROOT_SHAREABLE, &root->state) &&
root->last_trans < trans->transid) || force) {
@@ -456,11 +462,11 @@ static int record_root_in_trans(struct btrfs_trans_handle *trans,
* lock. smp_wmb() makes sure that all the writes above are
* done before we pop in the zero below
*/
- btrfs_init_reloc_root(trans, root);
+ ret = btrfs_init_reloc_root(trans, root);
smp_mb__before_atomic();
clear_bit(BTRFS_ROOT_IN_TRANS_SETUP, &root->state);
}
- return 0;
+ return ret;
}
@@ -487,6 +493,7 @@ int btrfs_record_root_in_trans(struct btrfs_trans_handle *trans,
struct btrfs_root *root)
{
struct btrfs_fs_info *fs_info = root->fs_info;
+ int ret;
if (!test_bit(BTRFS_ROOT_SHAREABLE, &root->state))
return 0;
@@ -501,10 +508,10 @@ int btrfs_record_root_in_trans(struct btrfs_trans_handle *trans,
return 0;
mutex_lock(&fs_info->reloc_mutex);
- record_root_in_trans(trans, root, 0);
+ ret = record_root_in_trans(trans, root, 0);
mutex_unlock(&fs_info->reloc_mutex);
- return 0;
+ return ret;
}
static inline int is_transaction_blocked(struct btrfs_transaction *trans)
@@ -741,7 +748,16 @@ got_it:
* Thus it need to be called after current->journal_info initialized,
* or we can deadlock.
*/
- btrfs_record_root_in_trans(h, root);
+ ret = btrfs_record_root_in_trans(h, root);
+ if (ret) {
+ /*
+ * The transaction handle is fully initialized and linked with
+ * other structures so it needs to be ended in case of errors,
+ * not just freed.
+ */
+ btrfs_end_transaction(h);
+ return ERR_PTR(ret);
+ }
return h;
@@ -1347,7 +1363,9 @@ static noinline int commit_fs_roots(struct btrfs_trans_handle *trans)
spin_unlock(&fs_info->fs_roots_radix_lock);
btrfs_free_log(trans, root);
- btrfs_update_reloc_root(trans, root);
+ ret2 = btrfs_update_reloc_root(trans, root);
+ if (ret2)
+ return ret2;
/* see comments in should_cow_block() */
clear_bit(BTRFS_ROOT_FORCE_COW, &root->state);
@@ -1440,7 +1458,9 @@ static int qgroup_account_snapshot(struct btrfs_trans_handle *trans,
* recorded root will never be updated again, causing an outdated root
* item.
*/
- record_root_in_trans(trans, src, 1);
+ ret = record_root_in_trans(trans, src, 1);
+ if (ret)
+ return ret;
/*
* btrfs_qgroup_inherit relies on a consistent view of the usage for the
@@ -1509,7 +1529,7 @@ out:
* insert_dir_item()
*/
if (!ret)
- record_root_in_trans(trans, parent, 1);
+ ret = record_root_in_trans(trans, parent, 1);
return ret;
}
@@ -1586,8 +1606,9 @@ static noinline int create_pending_snapshot(struct btrfs_trans_handle *trans,
dentry = pending->dentry;
parent_inode = pending->dir;
parent_root = BTRFS_I(parent_inode)->root;
- record_root_in_trans(trans, parent_root, 0);
-
+ ret = record_root_in_trans(trans, parent_root, 0);
+ if (ret)
+ goto fail;
cur_time = current_time(parent_inode);
/*
@@ -1623,7 +1644,11 @@ static noinline int create_pending_snapshot(struct btrfs_trans_handle *trans,
goto fail;
}
- record_root_in_trans(trans, root, 0);
+ ret = record_root_in_trans(trans, root, 0);
+ if (ret) {
+ btrfs_abort_transaction(trans, ret);
+ goto fail;
+ }
btrfs_set_root_last_snapshot(&root->root_item, trans->transid);
memcpy(new_root_item, &root->root_item, sizeof(*new_root_item));
btrfs_check_and_init_root_item(new_root_item);
@@ -1961,7 +1986,6 @@ static void cleanup_transaction(struct btrfs_trans_handle *trans, int err)
*/
BUG_ON(list_empty(&cur_trans->list));
- list_del_init(&cur_trans->list);
if (cur_trans == fs_info->running_transaction) {
cur_trans->state = TRANS_STATE_COMMIT_DOING;
spin_unlock(&fs_info->trans_lock);
@@ -1970,6 +1994,17 @@ static void cleanup_transaction(struct btrfs_trans_handle *trans, int err)
spin_lock(&fs_info->trans_lock);
}
+
+ /*
+ * Now that we know no one else is still using the transaction we can
+ * remove the transaction from the list of transactions. This avoids
+ * the transaction kthread from cleaning up the transaction while some
+ * other task is still using it, which could result in a use-after-free
+ * on things like log trees, as it forces the transaction kthread to
+ * wait for this transaction to be cleaned up by us.
+ */
+ list_del_init(&cur_trans->list);
+
spin_unlock(&fs_info->trans_lock);
btrfs_cleanup_one_transaction(trans->transaction, fs_info);
diff --git a/fs/btrfs/transaction.h b/fs/btrfs/transaction.h
index 6335716e513f..364cfbb4c5c5 100644
--- a/fs/btrfs/transaction.h
+++ b/fs/btrfs/transaction.h
@@ -96,6 +96,13 @@ struct btrfs_transaction {
spinlock_t releasing_ebs_lock;
struct list_head releasing_ebs;
+
+ /*
+ * The number of bytes currently reserved, by all transaction handles
+ * attached to this transaction, for metadata extents of the chunk tree.
+ */
+ atomic64_t chunk_bytes_reserved;
+ wait_queue_head_t chunk_reserve_wait;
};
#define __TRANS_FREEZABLE (1U << 0)
@@ -175,7 +182,7 @@ static inline void btrfs_set_inode_last_trans(struct btrfs_trans_handle *trans,
spin_lock(&inode->lock);
inode->last_trans = trans->transaction->transid;
inode->last_sub_trans = inode->root->log_transid;
- inode->last_log_commit = inode->root->last_log_commit;
+ inode->last_log_commit = inode->last_sub_trans - 1;
spin_unlock(&inode->lock);
}
diff --git a/fs/btrfs/tree-checker.c b/fs/btrfs/tree-checker.c
index f4ade821307d..a8b2e0d2c025 100644
--- a/fs/btrfs/tree-checker.c
+++ b/fs/btrfs/tree-checker.c
@@ -1290,6 +1290,11 @@ static int check_extent_item(struct extent_buffer *leaf,
key->offset, fs_info->sectorsize);
return -EUCLEAN;
}
+ if (unlikely(flags & BTRFS_BLOCK_FLAG_FULL_BACKREF)) {
+ extent_err(leaf, slot,
+ "invalid extent flag, data has full backref set");
+ return -EUCLEAN;
+ }
}
ptr = (unsigned long)(struct btrfs_extent_item *)(ei + 1);
diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index 2f1acc9aea9e..f67721d82e5d 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -3165,24 +3165,26 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans,
*/
mutex_unlock(&root->log_mutex);
- btrfs_init_log_ctx(&root_log_ctx, NULL);
-
- mutex_lock(&log_root_tree->log_mutex);
-
- index2 = log_root_tree->log_transid % 2;
- list_add_tail(&root_log_ctx.list, &log_root_tree->log_ctxs[index2]);
- root_log_ctx.log_transid = log_root_tree->log_transid;
-
if (btrfs_is_zoned(fs_info)) {
+ mutex_lock(&fs_info->tree_root->log_mutex);
if (!log_root_tree->node) {
ret = btrfs_alloc_log_tree_node(trans, log_root_tree);
if (ret) {
- mutex_unlock(&log_root_tree->log_mutex);
+ mutex_unlock(&fs_info->tree_log_mutex);
goto out;
}
}
+ mutex_unlock(&fs_info->tree_root->log_mutex);
}
+ btrfs_init_log_ctx(&root_log_ctx, NULL);
+
+ mutex_lock(&log_root_tree->log_mutex);
+
+ index2 = log_root_tree->log_transid % 2;
+ list_add_tail(&root_log_ctx.list, &log_root_tree->log_ctxs[index2]);
+ root_log_ctx.log_transid = log_root_tree->log_transid;
+
/*
* Now we are safe to update the log_root_tree because we're under the
* log_mutex, and we're a current writer so we're holding the commit
@@ -4136,7 +4138,8 @@ static noinline int copy_items(struct btrfs_trans_handle *trans,
return ret;
}
-static int extent_cmp(void *priv, struct list_head *a, struct list_head *b)
+static int extent_cmp(void *priv, const struct list_head *a,
+ const struct list_head *b)
{
struct extent_map *em1, *em2;
@@ -6278,8 +6281,13 @@ again:
}
wc.replay_dest->log_root = log;
- btrfs_record_root_in_trans(trans, wc.replay_dest);
- ret = walk_log_tree(trans, log, &wc);
+ ret = btrfs_record_root_in_trans(trans, wc.replay_dest);
+ if (ret)
+ /* The loop needs to continue due to the root refs */
+ btrfs_handle_fs_error(fs_info, ret,
+ "failed to record the log root in transaction");
+ else
+ ret = walk_log_tree(trans, log, &wc);
if (!ret && wc.stage == LOG_WALK_REPLAY_ALL) {
ret = fixup_inode_link_counts(trans, wc.replay_dest,
diff --git a/fs/btrfs/tree-mod-log.c b/fs/btrfs/tree-mod-log.c
new file mode 100644
index 000000000000..8a3a14686d3e
--- /dev/null
+++ b/fs/btrfs/tree-mod-log.c
@@ -0,0 +1,929 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include "tree-mod-log.h"
+#include "disk-io.h"
+
+struct tree_mod_root {
+ u64 logical;
+ u8 level;
+};
+
+struct tree_mod_elem {
+ struct rb_node node;
+ u64 logical;
+ u64 seq;
+ enum btrfs_mod_log_op op;
+
+ /*
+ * This is used for BTRFS_MOD_LOG_KEY_* and BTRFS_MOD_LOG_MOVE_KEYS
+ * operations.
+ */
+ int slot;
+
+ /* This is used for BTRFS_MOD_LOG_KEY* and BTRFS_MOD_LOG_ROOT_REPLACE. */
+ u64 generation;
+
+ /* Those are used for op == BTRFS_MOD_LOG_KEY_{REPLACE,REMOVE}. */
+ struct btrfs_disk_key key;
+ u64 blockptr;
+
+ /* This is used for op == BTRFS_MOD_LOG_MOVE_KEYS. */
+ struct {
+ int dst_slot;
+ int nr_items;
+ } move;
+
+ /* This is used for op == BTRFS_MOD_LOG_ROOT_REPLACE. */
+ struct tree_mod_root old_root;
+};
+
+/*
+ * Pull a new tree mod seq number for our operation.
+ */
+static inline u64 btrfs_inc_tree_mod_seq(struct btrfs_fs_info *fs_info)
+{
+ return atomic64_inc_return(&fs_info->tree_mod_seq);
+}
+
+/*
+ * This adds a new blocker to the tree mod log's blocker list if the @elem
+ * passed does not already have a sequence number set. So when a caller expects
+ * to record tree modifications, it should ensure to set elem->seq to zero
+ * before calling btrfs_get_tree_mod_seq.
+ * Returns a fresh, unused tree log modification sequence number, even if no new
+ * blocker was added.
+ */
+u64 btrfs_get_tree_mod_seq(struct btrfs_fs_info *fs_info,
+ struct btrfs_seq_list *elem)
+{
+ write_lock(&fs_info->tree_mod_log_lock);
+ if (!elem->seq) {
+ elem->seq = btrfs_inc_tree_mod_seq(fs_info);
+ list_add_tail(&elem->list, &fs_info->tree_mod_seq_list);
+ set_bit(BTRFS_FS_TREE_MOD_LOG_USERS, &fs_info->flags);
+ }
+ write_unlock(&fs_info->tree_mod_log_lock);
+
+ return elem->seq;
+}
+
+void btrfs_put_tree_mod_seq(struct btrfs_fs_info *fs_info,
+ struct btrfs_seq_list *elem)
+{
+ struct rb_root *tm_root;
+ struct rb_node *node;
+ struct rb_node *next;
+ struct tree_mod_elem *tm;
+ u64 min_seq = BTRFS_SEQ_LAST;
+ u64 seq_putting = elem->seq;
+
+ if (!seq_putting)
+ return;
+
+ write_lock(&fs_info->tree_mod_log_lock);
+ list_del(&elem->list);
+ elem->seq = 0;
+
+ if (list_empty(&fs_info->tree_mod_seq_list)) {
+ clear_bit(BTRFS_FS_TREE_MOD_LOG_USERS, &fs_info->flags);
+ } else {
+ struct btrfs_seq_list *first;
+
+ first = list_first_entry(&fs_info->tree_mod_seq_list,
+ struct btrfs_seq_list, list);
+ if (seq_putting > first->seq) {
+ /*
+ * Blocker with lower sequence number exists, we cannot
+ * remove anything from the log.
+ */
+ write_unlock(&fs_info->tree_mod_log_lock);
+ return;
+ }
+ min_seq = first->seq;
+ }
+
+ /*
+ * Anything that's lower than the lowest existing (read: blocked)
+ * sequence number can be removed from the tree.
+ */
+ tm_root = &fs_info->tree_mod_log;
+ for (node = rb_first(tm_root); node; node = next) {
+ next = rb_next(node);
+ tm = rb_entry(node, struct tree_mod_elem, node);
+ if (tm->seq >= min_seq)
+ continue;
+ rb_erase(node, tm_root);
+ kfree(tm);
+ }
+ write_unlock(&fs_info->tree_mod_log_lock);
+}
+
+/*
+ * Key order of the log:
+ * node/leaf start address -> sequence
+ *
+ * The 'start address' is the logical address of the *new* root node for root
+ * replace operations, or the logical address of the affected block for all
+ * other operations.
+ */
+static noinline int tree_mod_log_insert(struct btrfs_fs_info *fs_info,
+ struct tree_mod_elem *tm)
+{
+ struct rb_root *tm_root;
+ struct rb_node **new;
+ struct rb_node *parent = NULL;
+ struct tree_mod_elem *cur;
+
+ lockdep_assert_held_write(&fs_info->tree_mod_log_lock);
+
+ tm->seq = btrfs_inc_tree_mod_seq(fs_info);
+
+ tm_root = &fs_info->tree_mod_log;
+ new = &tm_root->rb_node;
+ while (*new) {
+ cur = rb_entry(*new, struct tree_mod_elem, node);
+ parent = *new;
+ if (cur->logical < tm->logical)
+ new = &((*new)->rb_left);
+ else if (cur->logical > tm->logical)
+ new = &((*new)->rb_right);
+ else if (cur->seq < tm->seq)
+ new = &((*new)->rb_left);
+ else if (cur->seq > tm->seq)
+ new = &((*new)->rb_right);
+ else
+ return -EEXIST;
+ }
+
+ rb_link_node(&tm->node, parent, new);
+ rb_insert_color(&tm->node, tm_root);
+ return 0;
+}
+
+/*
+ * Determines if logging can be omitted. Returns true if it can. Otherwise, it
+ * returns false with the tree_mod_log_lock acquired. The caller must hold
+ * this until all tree mod log insertions are recorded in the rb tree and then
+ * write unlock fs_info::tree_mod_log_lock.
+ */
+static inline bool tree_mod_dont_log(struct btrfs_fs_info *fs_info,
+ struct extent_buffer *eb)
+{
+ if (!test_bit(BTRFS_FS_TREE_MOD_LOG_USERS, &fs_info->flags))
+ return true;
+ if (eb && btrfs_header_level(eb) == 0)
+ return true;
+
+ write_lock(&fs_info->tree_mod_log_lock);
+ if (list_empty(&(fs_info)->tree_mod_seq_list)) {
+ write_unlock(&fs_info->tree_mod_log_lock);
+ return true;
+ }
+
+ return false;
+}
+
+/* Similar to tree_mod_dont_log, but doesn't acquire any locks. */
+static inline bool tree_mod_need_log(const struct btrfs_fs_info *fs_info,
+ struct extent_buffer *eb)
+{
+ if (!test_bit(BTRFS_FS_TREE_MOD_LOG_USERS, &fs_info->flags))
+ return false;
+ if (eb && btrfs_header_level(eb) == 0)
+ return false;
+
+ return true;
+}
+
+static struct tree_mod_elem *alloc_tree_mod_elem(struct extent_buffer *eb,
+ int slot,
+ enum btrfs_mod_log_op op,
+ gfp_t flags)
+{
+ struct tree_mod_elem *tm;
+
+ tm = kzalloc(sizeof(*tm), flags);
+ if (!tm)
+ return NULL;
+
+ tm->logical = eb->start;
+ if (op != BTRFS_MOD_LOG_KEY_ADD) {
+ btrfs_node_key(eb, &tm->key, slot);
+ tm->blockptr = btrfs_node_blockptr(eb, slot);
+ }
+ tm->op = op;
+ tm->slot = slot;
+ tm->generation = btrfs_node_ptr_generation(eb, slot);
+ RB_CLEAR_NODE(&tm->node);
+
+ return tm;
+}
+
+int btrfs_tree_mod_log_insert_key(struct extent_buffer *eb, int slot,
+ enum btrfs_mod_log_op op, gfp_t flags)
+{
+ struct tree_mod_elem *tm;
+ int ret;
+
+ if (!tree_mod_need_log(eb->fs_info, eb))
+ return 0;
+
+ tm = alloc_tree_mod_elem(eb, slot, op, flags);
+ if (!tm)
+ return -ENOMEM;
+
+ if (tree_mod_dont_log(eb->fs_info, eb)) {
+ kfree(tm);
+ return 0;
+ }
+
+ ret = tree_mod_log_insert(eb->fs_info, tm);
+ write_unlock(&eb->fs_info->tree_mod_log_lock);
+ if (ret)
+ kfree(tm);
+
+ return ret;
+}
+
+int btrfs_tree_mod_log_insert_move(struct extent_buffer *eb,
+ int dst_slot, int src_slot,
+ int nr_items)
+{
+ struct tree_mod_elem *tm = NULL;
+ struct tree_mod_elem **tm_list = NULL;
+ int ret = 0;
+ int i;
+ bool locked = false;
+
+ if (!tree_mod_need_log(eb->fs_info, eb))
+ return 0;
+
+ tm_list = kcalloc(nr_items, sizeof(struct tree_mod_elem *), GFP_NOFS);
+ if (!tm_list)
+ return -ENOMEM;
+
+ tm = kzalloc(sizeof(*tm), GFP_NOFS);
+ if (!tm) {
+ ret = -ENOMEM;
+ goto free_tms;
+ }
+
+ tm->logical = eb->start;
+ tm->slot = src_slot;
+ tm->move.dst_slot = dst_slot;
+ tm->move.nr_items = nr_items;
+ tm->op = BTRFS_MOD_LOG_MOVE_KEYS;
+
+ for (i = 0; i + dst_slot < src_slot && i < nr_items; i++) {
+ tm_list[i] = alloc_tree_mod_elem(eb, i + dst_slot,
+ BTRFS_MOD_LOG_KEY_REMOVE_WHILE_MOVING, GFP_NOFS);
+ if (!tm_list[i]) {
+ ret = -ENOMEM;
+ goto free_tms;
+ }
+ }
+
+ if (tree_mod_dont_log(eb->fs_info, eb))
+ goto free_tms;
+ locked = true;
+
+ /*
+ * When we override something during the move, we log these removals.
+ * This can only happen when we move towards the beginning of the
+ * buffer, i.e. dst_slot < src_slot.
+ */
+ for (i = 0; i + dst_slot < src_slot && i < nr_items; i++) {
+ ret = tree_mod_log_insert(eb->fs_info, tm_list[i]);
+ if (ret)
+ goto free_tms;
+ }
+
+ ret = tree_mod_log_insert(eb->fs_info, tm);
+ if (ret)
+ goto free_tms;
+ write_unlock(&eb->fs_info->tree_mod_log_lock);
+ kfree(tm_list);
+
+ return 0;
+
+free_tms:
+ for (i = 0; i < nr_items; i++) {
+ if (tm_list[i] && !RB_EMPTY_NODE(&tm_list[i]->node))
+ rb_erase(&tm_list[i]->node, &eb->fs_info->tree_mod_log);
+ kfree(tm_list[i]);
+ }
+ if (locked)
+ write_unlock(&eb->fs_info->tree_mod_log_lock);
+ kfree(tm_list);
+ kfree(tm);
+
+ return ret;
+}
+
+static inline int tree_mod_log_free_eb(struct btrfs_fs_info *fs_info,
+ struct tree_mod_elem **tm_list,
+ int nritems)
+{
+ int i, j;
+ int ret;
+
+ for (i = nritems - 1; i >= 0; i--) {
+ ret = tree_mod_log_insert(fs_info, tm_list[i]);
+ if (ret) {
+ for (j = nritems - 1; j > i; j--)
+ rb_erase(&tm_list[j]->node,
+ &fs_info->tree_mod_log);
+ return ret;
+ }
+ }
+
+ return 0;
+}
+
+int btrfs_tree_mod_log_insert_root(struct extent_buffer *old_root,
+ struct extent_buffer *new_root,
+ bool log_removal)
+{
+ struct btrfs_fs_info *fs_info = old_root->fs_info;
+ struct tree_mod_elem *tm = NULL;
+ struct tree_mod_elem **tm_list = NULL;
+ int nritems = 0;
+ int ret = 0;
+ int i;
+
+ if (!tree_mod_need_log(fs_info, NULL))
+ return 0;
+
+ if (log_removal && btrfs_header_level(old_root) > 0) {
+ nritems = btrfs_header_nritems(old_root);
+ tm_list = kcalloc(nritems, sizeof(struct tree_mod_elem *),
+ GFP_NOFS);
+ if (!tm_list) {
+ ret = -ENOMEM;
+ goto free_tms;
+ }
+ for (i = 0; i < nritems; i++) {
+ tm_list[i] = alloc_tree_mod_elem(old_root, i,
+ BTRFS_MOD_LOG_KEY_REMOVE_WHILE_FREEING, GFP_NOFS);
+ if (!tm_list[i]) {
+ ret = -ENOMEM;
+ goto free_tms;
+ }
+ }
+ }
+
+ tm = kzalloc(sizeof(*tm), GFP_NOFS);
+ if (!tm) {
+ ret = -ENOMEM;
+ goto free_tms;
+ }
+
+ tm->logical = new_root->start;
+ tm->old_root.logical = old_root->start;
+ tm->old_root.level = btrfs_header_level(old_root);
+ tm->generation = btrfs_header_generation(old_root);
+ tm->op = BTRFS_MOD_LOG_ROOT_REPLACE;
+
+ if (tree_mod_dont_log(fs_info, NULL))
+ goto free_tms;
+
+ if (tm_list)
+ ret = tree_mod_log_free_eb(fs_info, tm_list, nritems);
+ if (!ret)
+ ret = tree_mod_log_insert(fs_info, tm);
+
+ write_unlock(&fs_info->tree_mod_log_lock);
+ if (ret)
+ goto free_tms;
+ kfree(tm_list);
+
+ return ret;
+
+free_tms:
+ if (tm_list) {
+ for (i = 0; i < nritems; i++)
+ kfree(tm_list[i]);
+ kfree(tm_list);
+ }
+ kfree(tm);
+
+ return ret;
+}
+
+static struct tree_mod_elem *__tree_mod_log_search(struct btrfs_fs_info *fs_info,
+ u64 start, u64 min_seq,
+ bool smallest)
+{
+ struct rb_root *tm_root;
+ struct rb_node *node;
+ struct tree_mod_elem *cur = NULL;
+ struct tree_mod_elem *found = NULL;
+
+ read_lock(&fs_info->tree_mod_log_lock);
+ tm_root = &fs_info->tree_mod_log;
+ node = tm_root->rb_node;
+ while (node) {
+ cur = rb_entry(node, struct tree_mod_elem, node);
+ if (cur->logical < start) {
+ node = node->rb_left;
+ } else if (cur->logical > start) {
+ node = node->rb_right;
+ } else if (cur->seq < min_seq) {
+ node = node->rb_left;
+ } else if (!smallest) {
+ /* We want the node with the highest seq */
+ if (found)
+ BUG_ON(found->seq > cur->seq);
+ found = cur;
+ node = node->rb_left;
+ } else if (cur->seq > min_seq) {
+ /* We want the node with the smallest seq */
+ if (found)
+ BUG_ON(found->seq < cur->seq);
+ found = cur;
+ node = node->rb_right;
+ } else {
+ found = cur;
+ break;
+ }
+ }
+ read_unlock(&fs_info->tree_mod_log_lock);
+
+ return found;
+}
+
+/*
+ * This returns the element from the log with the smallest time sequence
+ * value that's in the log (the oldest log item). Any element with a time
+ * sequence lower than min_seq will be ignored.
+ */
+static struct tree_mod_elem *tree_mod_log_search_oldest(struct btrfs_fs_info *fs_info,
+ u64 start, u64 min_seq)
+{
+ return __tree_mod_log_search(fs_info, start, min_seq, true);
+}
+
+/*
+ * This returns the element from the log with the largest time sequence
+ * value that's in the log (the most recent log item). Any element with
+ * a time sequence lower than min_seq will be ignored.
+ */
+static struct tree_mod_elem *tree_mod_log_search(struct btrfs_fs_info *fs_info,
+ u64 start, u64 min_seq)
+{
+ return __tree_mod_log_search(fs_info, start, min_seq, false);
+}
+
+int btrfs_tree_mod_log_eb_copy(struct extent_buffer *dst,
+ struct extent_buffer *src,
+ unsigned long dst_offset,
+ unsigned long src_offset,
+ int nr_items)
+{
+ struct btrfs_fs_info *fs_info = dst->fs_info;
+ int ret = 0;
+ struct tree_mod_elem **tm_list = NULL;
+ struct tree_mod_elem **tm_list_add, **tm_list_rem;
+ int i;
+ bool locked = false;
+
+ if (!tree_mod_need_log(fs_info, NULL))
+ return 0;
+
+ if (btrfs_header_level(dst) == 0 && btrfs_header_level(src) == 0)
+ return 0;
+
+ tm_list = kcalloc(nr_items * 2, sizeof(struct tree_mod_elem *),
+ GFP_NOFS);
+ if (!tm_list)
+ return -ENOMEM;
+
+ tm_list_add = tm_list;
+ tm_list_rem = tm_list + nr_items;
+ for (i = 0; i < nr_items; i++) {
+ tm_list_rem[i] = alloc_tree_mod_elem(src, i + src_offset,
+ BTRFS_MOD_LOG_KEY_REMOVE, GFP_NOFS);
+ if (!tm_list_rem[i]) {
+ ret = -ENOMEM;
+ goto free_tms;
+ }
+
+ tm_list_add[i] = alloc_tree_mod_elem(dst, i + dst_offset,
+ BTRFS_MOD_LOG_KEY_ADD, GFP_NOFS);
+ if (!tm_list_add[i]) {
+ ret = -ENOMEM;
+ goto free_tms;
+ }
+ }
+
+ if (tree_mod_dont_log(fs_info, NULL))
+ goto free_tms;
+ locked = true;
+
+ for (i = 0; i < nr_items; i++) {
+ ret = tree_mod_log_insert(fs_info, tm_list_rem[i]);
+ if (ret)
+ goto free_tms;
+ ret = tree_mod_log_insert(fs_info, tm_list_add[i]);
+ if (ret)
+ goto free_tms;
+ }
+
+ write_unlock(&fs_info->tree_mod_log_lock);
+ kfree(tm_list);
+
+ return 0;
+
+free_tms:
+ for (i = 0; i < nr_items * 2; i++) {
+ if (tm_list[i] && !RB_EMPTY_NODE(&tm_list[i]->node))
+ rb_erase(&tm_list[i]->node, &fs_info->tree_mod_log);
+ kfree(tm_list[i]);
+ }
+ if (locked)
+ write_unlock(&fs_info->tree_mod_log_lock);
+ kfree(tm_list);
+
+ return ret;
+}
+
+int btrfs_tree_mod_log_free_eb(struct extent_buffer *eb)
+{
+ struct tree_mod_elem **tm_list = NULL;
+ int nritems = 0;
+ int i;
+ int ret = 0;
+
+ if (!tree_mod_need_log(eb->fs_info, eb))
+ return 0;
+
+ nritems = btrfs_header_nritems(eb);
+ tm_list = kcalloc(nritems, sizeof(struct tree_mod_elem *), GFP_NOFS);
+ if (!tm_list)
+ return -ENOMEM;
+
+ for (i = 0; i < nritems; i++) {
+ tm_list[i] = alloc_tree_mod_elem(eb, i,
+ BTRFS_MOD_LOG_KEY_REMOVE_WHILE_FREEING, GFP_NOFS);
+ if (!tm_list[i]) {
+ ret = -ENOMEM;
+ goto free_tms;
+ }
+ }
+
+ if (tree_mod_dont_log(eb->fs_info, eb))
+ goto free_tms;
+
+ ret = tree_mod_log_free_eb(eb->fs_info, tm_list, nritems);
+ write_unlock(&eb->fs_info->tree_mod_log_lock);
+ if (ret)
+ goto free_tms;
+ kfree(tm_list);
+
+ return 0;
+
+free_tms:
+ for (i = 0; i < nritems; i++)
+ kfree(tm_list[i]);
+ kfree(tm_list);
+
+ return ret;
+}
+
+/*
+ * Returns the logical address of the oldest predecessor of the given root.
+ * Entries older than time_seq are ignored.
+ */
+static struct tree_mod_elem *tree_mod_log_oldest_root(struct extent_buffer *eb_root,
+ u64 time_seq)
+{
+ struct tree_mod_elem *tm;
+ struct tree_mod_elem *found = NULL;
+ u64 root_logical = eb_root->start;
+ bool looped = false;
+
+ if (!time_seq)
+ return NULL;
+
+ /*
+ * The very last operation that's logged for a root is the replacement
+ * operation (if it is replaced at all). This has the logical address
+ * of the *new* root, making it the very first operation that's logged
+ * for this root.
+ */
+ while (1) {
+ tm = tree_mod_log_search_oldest(eb_root->fs_info, root_logical,
+ time_seq);
+ if (!looped && !tm)
+ return NULL;
+ /*
+ * If there are no tree operation for the oldest root, we simply
+ * return it. This should only happen if that (old) root is at
+ * level 0.
+ */
+ if (!tm)
+ break;
+
+ /*
+ * If there's an operation that's not a root replacement, we
+ * found the oldest version of our root. Normally, we'll find a
+ * BTRFS_MOD_LOG_KEY_REMOVE_WHILE_FREEING operation here.
+ */
+ if (tm->op != BTRFS_MOD_LOG_ROOT_REPLACE)
+ break;
+
+ found = tm;
+ root_logical = tm->old_root.logical;
+ looped = true;
+ }
+
+ /* If there's no old root to return, return what we found instead */
+ if (!found)
+ found = tm;
+
+ return found;
+}
+
+
+/*
+ * tm is a pointer to the first operation to rewind within eb. Then, all
+ * previous operations will be rewound (until we reach something older than
+ * time_seq).
+ */
+static void tree_mod_log_rewind(struct btrfs_fs_info *fs_info,
+ struct extent_buffer *eb,
+ u64 time_seq,
+ struct tree_mod_elem *first_tm)
+{
+ u32 n;
+ struct rb_node *next;
+ struct tree_mod_elem *tm = first_tm;
+ unsigned long o_dst;
+ unsigned long o_src;
+ unsigned long p_size = sizeof(struct btrfs_key_ptr);
+
+ n = btrfs_header_nritems(eb);
+ read_lock(&fs_info->tree_mod_log_lock);
+ while (tm && tm->seq >= time_seq) {
+ /*
+ * All the operations are recorded with the operator used for
+ * the modification. As we're going backwards, we do the
+ * opposite of each operation here.
+ */
+ switch (tm->op) {
+ case BTRFS_MOD_LOG_KEY_REMOVE_WHILE_FREEING:
+ BUG_ON(tm->slot < n);
+ fallthrough;
+ case BTRFS_MOD_LOG_KEY_REMOVE_WHILE_MOVING:
+ case BTRFS_MOD_LOG_KEY_REMOVE:
+ btrfs_set_node_key(eb, &tm->key, tm->slot);
+ btrfs_set_node_blockptr(eb, tm->slot, tm->blockptr);
+ btrfs_set_node_ptr_generation(eb, tm->slot,
+ tm->generation);
+ n++;
+ break;
+ case BTRFS_MOD_LOG_KEY_REPLACE:
+ BUG_ON(tm->slot >= n);
+ btrfs_set_node_key(eb, &tm->key, tm->slot);
+ btrfs_set_node_blockptr(eb, tm->slot, tm->blockptr);
+ btrfs_set_node_ptr_generation(eb, tm->slot,
+ tm->generation);
+ break;
+ case BTRFS_MOD_LOG_KEY_ADD:
+ /* if a move operation is needed it's in the log */
+ n--;
+ break;
+ case BTRFS_MOD_LOG_MOVE_KEYS:
+ o_dst = btrfs_node_key_ptr_offset(tm->slot);
+ o_src = btrfs_node_key_ptr_offset(tm->move.dst_slot);
+ memmove_extent_buffer(eb, o_dst, o_src,
+ tm->move.nr_items * p_size);
+ break;
+ case BTRFS_MOD_LOG_ROOT_REPLACE:
+ /*
+ * This operation is special. For roots, this must be
+ * handled explicitly before rewinding.
+ * For non-roots, this operation may exist if the node
+ * was a root: root A -> child B; then A gets empty and
+ * B is promoted to the new root. In the mod log, we'll
+ * have a root-replace operation for B, a tree block
+ * that is no root. We simply ignore that operation.
+ */
+ break;
+ }
+ next = rb_next(&tm->node);
+ if (!next)
+ break;
+ tm = rb_entry(next, struct tree_mod_elem, node);
+ if (tm->logical != first_tm->logical)
+ break;
+ }
+ read_unlock(&fs_info->tree_mod_log_lock);
+ btrfs_set_header_nritems(eb, n);
+}
+
+/*
+ * Called with eb read locked. If the buffer cannot be rewound, the same buffer
+ * is returned. If rewind operations happen, a fresh buffer is returned. The
+ * returned buffer is always read-locked. If the returned buffer is not the
+ * input buffer, the lock on the input buffer is released and the input buffer
+ * is freed (its refcount is decremented).
+ */
+struct extent_buffer *btrfs_tree_mod_log_rewind(struct btrfs_fs_info *fs_info,
+ struct btrfs_path *path,
+ struct extent_buffer *eb,
+ u64 time_seq)
+{
+ struct extent_buffer *eb_rewin;
+ struct tree_mod_elem *tm;
+
+ if (!time_seq)
+ return eb;
+
+ if (btrfs_header_level(eb) == 0)
+ return eb;
+
+ tm = tree_mod_log_search(fs_info, eb->start, time_seq);
+ if (!tm)
+ return eb;
+
+ if (tm->op == BTRFS_MOD_LOG_KEY_REMOVE_WHILE_FREEING) {
+ BUG_ON(tm->slot != 0);
+ eb_rewin = alloc_dummy_extent_buffer(fs_info, eb->start);
+ if (!eb_rewin) {
+ btrfs_tree_read_unlock(eb);
+ free_extent_buffer(eb);
+ return NULL;
+ }
+ btrfs_set_header_bytenr(eb_rewin, eb->start);
+ btrfs_set_header_backref_rev(eb_rewin,
+ btrfs_header_backref_rev(eb));
+ btrfs_set_header_owner(eb_rewin, btrfs_header_owner(eb));
+ btrfs_set_header_level(eb_rewin, btrfs_header_level(eb));
+ } else {
+ eb_rewin = btrfs_clone_extent_buffer(eb);
+ if (!eb_rewin) {
+ btrfs_tree_read_unlock(eb);
+ free_extent_buffer(eb);
+ return NULL;
+ }
+ }
+
+ btrfs_tree_read_unlock(eb);
+ free_extent_buffer(eb);
+
+ btrfs_set_buffer_lockdep_class(btrfs_header_owner(eb_rewin),
+ eb_rewin, btrfs_header_level(eb_rewin));
+ btrfs_tree_read_lock(eb_rewin);
+ tree_mod_log_rewind(fs_info, eb_rewin, time_seq, tm);
+ WARN_ON(btrfs_header_nritems(eb_rewin) >
+ BTRFS_NODEPTRS_PER_BLOCK(fs_info));
+
+ return eb_rewin;
+}
+
+/*
+ * Rewind the state of @root's root node to the given @time_seq value.
+ * If there are no changes, the current root->root_node is returned. If anything
+ * changed in between, there's a fresh buffer allocated on which the rewind
+ * operations are done. In any case, the returned buffer is read locked.
+ * Returns NULL on error (with no locks held).
+ */
+struct extent_buffer *btrfs_get_old_root(struct btrfs_root *root, u64 time_seq)
+{
+ struct btrfs_fs_info *fs_info = root->fs_info;
+ struct tree_mod_elem *tm;
+ struct extent_buffer *eb = NULL;
+ struct extent_buffer *eb_root;
+ u64 eb_root_owner = 0;
+ struct extent_buffer *old;
+ struct tree_mod_root *old_root = NULL;
+ u64 old_generation = 0;
+ u64 logical;
+ int level;
+
+ eb_root = btrfs_read_lock_root_node(root);
+ tm = tree_mod_log_oldest_root(eb_root, time_seq);
+ if (!tm)
+ return eb_root;
+
+ if (tm->op == BTRFS_MOD_LOG_ROOT_REPLACE) {
+ old_root = &tm->old_root;
+ old_generation = tm->generation;
+ logical = old_root->logical;
+ level = old_root->level;
+ } else {
+ logical = eb_root->start;
+ level = btrfs_header_level(eb_root);
+ }
+
+ tm = tree_mod_log_search(fs_info, logical, time_seq);
+ if (old_root && tm && tm->op != BTRFS_MOD_LOG_KEY_REMOVE_WHILE_FREEING) {
+ btrfs_tree_read_unlock(eb_root);
+ free_extent_buffer(eb_root);
+ old = read_tree_block(fs_info, logical, root->root_key.objectid,
+ 0, level, NULL);
+ if (WARN_ON(IS_ERR(old) || !extent_buffer_uptodate(old))) {
+ if (!IS_ERR(old))
+ free_extent_buffer(old);
+ btrfs_warn(fs_info,
+ "failed to read tree block %llu from get_old_root",
+ logical);
+ } else {
+ struct tree_mod_elem *tm2;
+
+ btrfs_tree_read_lock(old);
+ eb = btrfs_clone_extent_buffer(old);
+ /*
+ * After the lookup for the most recent tree mod operation
+ * above and before we locked and cloned the extent buffer
+ * 'old', a new tree mod log operation may have been added.
+ * So lookup for a more recent one to make sure the number
+ * of mod log operations we replay is consistent with the
+ * number of items we have in the cloned extent buffer,
+ * otherwise we can hit a BUG_ON when rewinding the extent
+ * buffer.
+ */
+ tm2 = tree_mod_log_search(fs_info, logical, time_seq);
+ btrfs_tree_read_unlock(old);
+ free_extent_buffer(old);
+ ASSERT(tm2);
+ ASSERT(tm2 == tm || tm2->seq > tm->seq);
+ if (!tm2 || tm2->seq < tm->seq) {
+ free_extent_buffer(eb);
+ return NULL;
+ }
+ tm = tm2;
+ }
+ } else if (old_root) {
+ eb_root_owner = btrfs_header_owner(eb_root);
+ btrfs_tree_read_unlock(eb_root);
+ free_extent_buffer(eb_root);
+ eb = alloc_dummy_extent_buffer(fs_info, logical);
+ } else {
+ eb = btrfs_clone_extent_buffer(eb_root);
+ btrfs_tree_read_unlock(eb_root);
+ free_extent_buffer(eb_root);
+ }
+
+ if (!eb)
+ return NULL;
+ if (old_root) {
+ btrfs_set_header_bytenr(eb, eb->start);
+ btrfs_set_header_backref_rev(eb, BTRFS_MIXED_BACKREF_REV);
+ btrfs_set_header_owner(eb, eb_root_owner);
+ btrfs_set_header_level(eb, old_root->level);
+ btrfs_set_header_generation(eb, old_generation);
+ }
+ btrfs_set_buffer_lockdep_class(btrfs_header_owner(eb), eb,
+ btrfs_header_level(eb));
+ btrfs_tree_read_lock(eb);
+ if (tm)
+ tree_mod_log_rewind(fs_info, eb, time_seq, tm);
+ else
+ WARN_ON(btrfs_header_level(eb) != 0);
+ WARN_ON(btrfs_header_nritems(eb) > BTRFS_NODEPTRS_PER_BLOCK(fs_info));
+
+ return eb;
+}
+
+int btrfs_old_root_level(struct btrfs_root *root, u64 time_seq)
+{
+ struct tree_mod_elem *tm;
+ int level;
+ struct extent_buffer *eb_root = btrfs_root_node(root);
+
+ tm = tree_mod_log_oldest_root(eb_root, time_seq);
+ if (tm && tm->op == BTRFS_MOD_LOG_ROOT_REPLACE)
+ level = tm->old_root.level;
+ else
+ level = btrfs_header_level(eb_root);
+
+ free_extent_buffer(eb_root);
+
+ return level;
+}
+
+/*
+ * Return the lowest sequence number in the tree modification log.
+ *
+ * Return the sequence number of the oldest tree modification log user, which
+ * corresponds to the lowest sequence number of all existing users. If there are
+ * no users it returns 0.
+ */
+u64 btrfs_tree_mod_log_lowest_seq(struct btrfs_fs_info *fs_info)
+{
+ u64 ret = 0;
+
+ read_lock(&fs_info->tree_mod_log_lock);
+ if (!list_empty(&fs_info->tree_mod_seq_list)) {
+ struct btrfs_seq_list *elem;
+
+ elem = list_first_entry(&fs_info->tree_mod_seq_list,
+ struct btrfs_seq_list, list);
+ ret = elem->seq;
+ }
+ read_unlock(&fs_info->tree_mod_log_lock);
+
+ return ret;
+}
diff --git a/fs/btrfs/tree-mod-log.h b/fs/btrfs/tree-mod-log.h
new file mode 100644
index 000000000000..12605d19621b
--- /dev/null
+++ b/fs/btrfs/tree-mod-log.h
@@ -0,0 +1,53 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#ifndef BTRFS_TREE_MOD_LOG_H
+#define BTRFS_TREE_MOD_LOG_H
+
+#include "ctree.h"
+
+/* Represents a tree mod log user. */
+struct btrfs_seq_list {
+ struct list_head list;
+ u64 seq;
+};
+
+#define BTRFS_SEQ_LIST_INIT(name) { .list = LIST_HEAD_INIT((name).list), .seq = 0 }
+#define BTRFS_SEQ_LAST ((u64)-1)
+
+enum btrfs_mod_log_op {
+ BTRFS_MOD_LOG_KEY_REPLACE,
+ BTRFS_MOD_LOG_KEY_ADD,
+ BTRFS_MOD_LOG_KEY_REMOVE,
+ BTRFS_MOD_LOG_KEY_REMOVE_WHILE_FREEING,
+ BTRFS_MOD_LOG_KEY_REMOVE_WHILE_MOVING,
+ BTRFS_MOD_LOG_MOVE_KEYS,
+ BTRFS_MOD_LOG_ROOT_REPLACE,
+};
+
+u64 btrfs_get_tree_mod_seq(struct btrfs_fs_info *fs_info,
+ struct btrfs_seq_list *elem);
+void btrfs_put_tree_mod_seq(struct btrfs_fs_info *fs_info,
+ struct btrfs_seq_list *elem);
+int btrfs_tree_mod_log_insert_root(struct extent_buffer *old_root,
+ struct extent_buffer *new_root,
+ bool log_removal);
+int btrfs_tree_mod_log_insert_key(struct extent_buffer *eb, int slot,
+ enum btrfs_mod_log_op op, gfp_t flags);
+int btrfs_tree_mod_log_free_eb(struct extent_buffer *eb);
+struct extent_buffer *btrfs_tree_mod_log_rewind(struct btrfs_fs_info *fs_info,
+ struct btrfs_path *path,
+ struct extent_buffer *eb,
+ u64 time_seq);
+struct extent_buffer *btrfs_get_old_root(struct btrfs_root *root, u64 time_seq);
+int btrfs_old_root_level(struct btrfs_root *root, u64 time_seq);
+int btrfs_tree_mod_log_eb_copy(struct extent_buffer *dst,
+ struct extent_buffer *src,
+ unsigned long dst_offset,
+ unsigned long src_offset,
+ int nr_items);
+int btrfs_tree_mod_log_insert_move(struct extent_buffer *eb,
+ int dst_slot, int src_slot,
+ int nr_items);
+u64 btrfs_tree_mod_log_lowest_seq(struct btrfs_fs_info *fs_info);
+
+#endif
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index bc3b33efddc5..9a1ead0c4a31 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -1224,7 +1224,8 @@ static int open_fs_devices(struct btrfs_fs_devices *fs_devices,
return 0;
}
-static int devid_cmp(void *priv, struct list_head *a, struct list_head *b)
+static int devid_cmp(void *priv, const struct list_head *a,
+ const struct list_head *b)
{
struct btrfs_device *dev1, *dev2;
@@ -1458,8 +1459,8 @@ static bool dev_extent_hole_check_zoned(struct btrfs_device *device,
/* Given hole range was invalid (outside of device) */
if (ret == -ERANGE) {
*hole_start += *hole_size;
- *hole_size = 0;
- return 1;
+ *hole_size = false;
+ return true;
}
*hole_start += zone_size;
@@ -3098,11 +3099,12 @@ out:
return ret;
}
-static int btrfs_relocate_chunk(struct btrfs_fs_info *fs_info, u64 chunk_offset)
+int btrfs_relocate_chunk(struct btrfs_fs_info *fs_info, u64 chunk_offset)
{
struct btrfs_root *root = fs_info->chunk_root;
struct btrfs_trans_handle *trans;
struct btrfs_block_group *block_group;
+ u64 length;
int ret;
/*
@@ -3117,7 +3119,7 @@ static int btrfs_relocate_chunk(struct btrfs_fs_info *fs_info, u64 chunk_offset)
* we release the path used to search the chunk/dev tree and before
* the current task acquires this mutex and calls us.
*/
- lockdep_assert_held(&fs_info->delete_unused_bgs_mutex);
+ lockdep_assert_held(&fs_info->reclaim_bgs_lock);
/* step one, relocate all the extents inside this chunk */
btrfs_scrub_pause(fs_info);
@@ -3130,8 +3132,23 @@ static int btrfs_relocate_chunk(struct btrfs_fs_info *fs_info, u64 chunk_offset)
if (!block_group)
return -ENOENT;
btrfs_discard_cancel_work(&fs_info->discard_ctl, block_group);
+ length = block_group->length;
btrfs_put_block_group(block_group);
+ /*
+ * On a zoned file system, discard the whole block group, this will
+ * trigger a REQ_OP_ZONE_RESET operation on the device zone. If
+ * resetting the zone fails, don't treat it as a fatal problem from the
+ * filesystem's point of view.
+ */
+ if (btrfs_is_zoned(fs_info)) {
+ ret = btrfs_discard_extent(fs_info, chunk_offset, length, NULL);
+ if (ret)
+ btrfs_info(fs_info,
+ "failed to reset zone %llu after relocation",
+ chunk_offset);
+ }
+
trans = btrfs_start_trans_remove_block_group(root->fs_info,
chunk_offset);
if (IS_ERR(trans)) {
@@ -3172,10 +3189,10 @@ again:
key.type = BTRFS_CHUNK_ITEM_KEY;
while (1) {
- mutex_lock(&fs_info->delete_unused_bgs_mutex);
+ mutex_lock(&fs_info->reclaim_bgs_lock);
ret = btrfs_search_slot(NULL, chunk_root, &key, path, 0, 0);
if (ret < 0) {
- mutex_unlock(&fs_info->delete_unused_bgs_mutex);
+ mutex_unlock(&fs_info->reclaim_bgs_lock);
goto error;
}
BUG_ON(ret == 0); /* Corruption */
@@ -3183,7 +3200,7 @@ again:
ret = btrfs_previous_item(chunk_root, path, key.objectid,
key.type);
if (ret)
- mutex_unlock(&fs_info->delete_unused_bgs_mutex);
+ mutex_unlock(&fs_info->reclaim_bgs_lock);
if (ret < 0)
goto error;
if (ret > 0)
@@ -3204,7 +3221,7 @@ again:
else
BUG_ON(ret);
}
- mutex_unlock(&fs_info->delete_unused_bgs_mutex);
+ mutex_unlock(&fs_info->reclaim_bgs_lock);
if (found_key.offset == 0)
break;
@@ -3744,10 +3761,10 @@ again:
goto error;
}
- mutex_lock(&fs_info->delete_unused_bgs_mutex);
+ mutex_lock(&fs_info->reclaim_bgs_lock);
ret = btrfs_search_slot(NULL, chunk_root, &key, path, 0, 0);
if (ret < 0) {
- mutex_unlock(&fs_info->delete_unused_bgs_mutex);
+ mutex_unlock(&fs_info->reclaim_bgs_lock);
goto error;
}
@@ -3761,7 +3778,7 @@ again:
ret = btrfs_previous_item(chunk_root, path, 0,
BTRFS_CHUNK_ITEM_KEY);
if (ret) {
- mutex_unlock(&fs_info->delete_unused_bgs_mutex);
+ mutex_unlock(&fs_info->reclaim_bgs_lock);
ret = 0;
break;
}
@@ -3771,7 +3788,7 @@ again:
btrfs_item_key_to_cpu(leaf, &found_key, slot);
if (found_key.objectid != key.objectid) {
- mutex_unlock(&fs_info->delete_unused_bgs_mutex);
+ mutex_unlock(&fs_info->reclaim_bgs_lock);
break;
}
@@ -3788,12 +3805,12 @@ again:
btrfs_release_path(path);
if (!ret) {
- mutex_unlock(&fs_info->delete_unused_bgs_mutex);
+ mutex_unlock(&fs_info->reclaim_bgs_lock);
goto loop;
}
if (counting) {
- mutex_unlock(&fs_info->delete_unused_bgs_mutex);
+ mutex_unlock(&fs_info->reclaim_bgs_lock);
spin_lock(&fs_info->balance_lock);
bctl->stat.expected++;
spin_unlock(&fs_info->balance_lock);
@@ -3818,7 +3835,7 @@ again:
count_meta < bctl->meta.limit_min)
|| ((chunk_type & BTRFS_BLOCK_GROUP_SYSTEM) &&
count_sys < bctl->sys.limit_min)) {
- mutex_unlock(&fs_info->delete_unused_bgs_mutex);
+ mutex_unlock(&fs_info->reclaim_bgs_lock);
goto loop;
}
@@ -3832,7 +3849,7 @@ again:
ret = btrfs_may_alloc_data_chunk(fs_info,
found_key.offset);
if (ret < 0) {
- mutex_unlock(&fs_info->delete_unused_bgs_mutex);
+ mutex_unlock(&fs_info->reclaim_bgs_lock);
goto error;
} else if (ret == 1) {
chunk_reserved = 1;
@@ -3840,7 +3857,7 @@ again:
}
ret = btrfs_relocate_chunk(fs_info, found_key.offset);
- mutex_unlock(&fs_info->delete_unused_bgs_mutex);
+ mutex_unlock(&fs_info->reclaim_bgs_lock);
if (ret == -ENOSPC) {
enospc_errors++;
} else if (ret == -ETXTBSY) {
@@ -4725,16 +4742,16 @@ again:
key.type = BTRFS_DEV_EXTENT_KEY;
do {
- mutex_lock(&fs_info->delete_unused_bgs_mutex);
+ mutex_lock(&fs_info->reclaim_bgs_lock);
ret = btrfs_search_slot(NULL, root, &key, path, 0, 0);
if (ret < 0) {
- mutex_unlock(&fs_info->delete_unused_bgs_mutex);
+ mutex_unlock(&fs_info->reclaim_bgs_lock);
goto done;
}
ret = btrfs_previous_item(root, path, 0, key.type);
if (ret) {
- mutex_unlock(&fs_info->delete_unused_bgs_mutex);
+ mutex_unlock(&fs_info->reclaim_bgs_lock);
if (ret < 0)
goto done;
ret = 0;
@@ -4747,7 +4764,7 @@ again:
btrfs_item_key_to_cpu(l, &key, path->slots[0]);
if (key.objectid != device->devid) {
- mutex_unlock(&fs_info->delete_unused_bgs_mutex);
+ mutex_unlock(&fs_info->reclaim_bgs_lock);
btrfs_release_path(path);
break;
}
@@ -4756,7 +4773,7 @@ again:
length = btrfs_dev_extent_length(l, dev_extent);
if (key.offset + length <= new_size) {
- mutex_unlock(&fs_info->delete_unused_bgs_mutex);
+ mutex_unlock(&fs_info->reclaim_bgs_lock);
btrfs_release_path(path);
break;
}
@@ -4772,12 +4789,12 @@ again:
*/
ret = btrfs_may_alloc_data_chunk(fs_info, chunk_offset);
if (ret < 0) {
- mutex_unlock(&fs_info->delete_unused_bgs_mutex);
+ mutex_unlock(&fs_info->reclaim_bgs_lock);
goto done;
}
ret = btrfs_relocate_chunk(fs_info, chunk_offset);
- mutex_unlock(&fs_info->delete_unused_bgs_mutex);
+ mutex_unlock(&fs_info->reclaim_bgs_lock);
if (ret == -ENOSPC) {
failed++;
} else if (ret) {
@@ -4989,6 +5006,8 @@ static void init_alloc_chunk_ctl_policy_zoned(
ctl->max_chunk_size = 2 * ctl->max_stripe_size;
ctl->devs_max = min_t(int, ctl->devs_max,
BTRFS_MAX_DEVS_SYS_CHUNK);
+ } else {
+ BUG();
}
/* We don't want a chunk larger than 10% of writable space */
@@ -6787,6 +6806,46 @@ static u64 calc_stripe_length(u64 type, u64 chunk_len, int num_stripes)
return div_u64(chunk_len, data_stripes);
}
+#if BITS_PER_LONG == 32
+/*
+ * Due to page cache limit, metadata beyond BTRFS_32BIT_MAX_FILE_SIZE
+ * can't be accessed on 32bit systems.
+ *
+ * This function do mount time check to reject the fs if it already has
+ * metadata chunk beyond that limit.
+ */
+static int check_32bit_meta_chunk(struct btrfs_fs_info *fs_info,
+ u64 logical, u64 length, u64 type)
+{
+ if (!(type & BTRFS_BLOCK_GROUP_METADATA))
+ return 0;
+
+ if (logical + length < MAX_LFS_FILESIZE)
+ return 0;
+
+ btrfs_err_32bit_limit(fs_info);
+ return -EOVERFLOW;
+}
+
+/*
+ * This is to give early warning for any metadata chunk reaching
+ * BTRFS_32BIT_EARLY_WARN_THRESHOLD.
+ * Although we can still access the metadata, it's not going to be possible
+ * once the limit is reached.
+ */
+static void warn_32bit_meta_chunk(struct btrfs_fs_info *fs_info,
+ u64 logical, u64 length, u64 type)
+{
+ if (!(type & BTRFS_BLOCK_GROUP_METADATA))
+ return;
+
+ if (logical + length < BTRFS_32BIT_EARLY_WARN_THRESHOLD)
+ return;
+
+ btrfs_warn_32bit_limit(fs_info);
+}
+#endif
+
static int read_one_chunk(struct btrfs_key *key, struct extent_buffer *leaf,
struct btrfs_chunk *chunk)
{
@@ -6797,6 +6856,7 @@ static int read_one_chunk(struct btrfs_key *key, struct extent_buffer *leaf,
u64 logical;
u64 length;
u64 devid;
+ u64 type;
u8 uuid[BTRFS_UUID_SIZE];
int num_stripes;
int ret;
@@ -6804,8 +6864,16 @@ static int read_one_chunk(struct btrfs_key *key, struct extent_buffer *leaf,
logical = key->offset;
length = btrfs_chunk_length(leaf, chunk);
+ type = btrfs_chunk_type(leaf, chunk);
num_stripes = btrfs_chunk_num_stripes(leaf, chunk);
+#if BITS_PER_LONG == 32
+ ret = check_32bit_meta_chunk(fs_info, logical, length, type);
+ if (ret < 0)
+ return ret;
+ warn_32bit_meta_chunk(fs_info, logical, length, type);
+#endif
+
/*
* Only need to verify chunk item if we're reading from sys chunk array,
* as chunk item in tree block is already verified by tree-checker.
@@ -6849,10 +6917,10 @@ static int read_one_chunk(struct btrfs_key *key, struct extent_buffer *leaf,
map->io_width = btrfs_chunk_io_width(leaf, chunk);
map->io_align = btrfs_chunk_io_align(leaf, chunk);
map->stripe_len = btrfs_chunk_stripe_len(leaf, chunk);
- map->type = btrfs_chunk_type(leaf, chunk);
+ map->type = type;
map->sub_stripes = btrfs_chunk_sub_stripes(leaf, chunk);
map->verified_stripes = 0;
- em->orig_block_len = calc_stripe_length(map->type, em->len,
+ em->orig_block_len = calc_stripe_length(type, em->len,
map->num_stripes);
for (i = 0; i < num_stripes; i++) {
map->stripes[i].physical =
@@ -7448,6 +7516,9 @@ static int btrfs_device_init_dev_stats(struct btrfs_device *device,
int item_size;
int i, ret, slot;
+ if (!device->fs_info->dev_root)
+ return 0;
+
key.objectid = BTRFS_DEV_STATS_OBJECTID;
key.type = BTRFS_PERSISTENT_ITEM_KEY;
key.offset = device->devid;
@@ -7998,7 +8069,7 @@ static int relocating_repair_kthread(void *data)
return -EBUSY;
}
- mutex_lock(&fs_info->delete_unused_bgs_mutex);
+ mutex_lock(&fs_info->reclaim_bgs_lock);
/* Ensure block group still exists */
cache = btrfs_lookup_block_group(fs_info, target);
@@ -8020,7 +8091,7 @@ static int relocating_repair_kthread(void *data)
out:
if (cache)
btrfs_put_block_group(cache);
- mutex_unlock(&fs_info->delete_unused_bgs_mutex);
+ mutex_unlock(&fs_info->reclaim_bgs_lock);
btrfs_exclop_finish(fs_info);
return ret;
diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h
index d4c3e0dd32b8..9c0d84e5ec06 100644
--- a/fs/btrfs/volumes.h
+++ b/fs/btrfs/volumes.h
@@ -484,6 +484,7 @@ void btrfs_describe_block_groups(u64 flags, char *buf, u32 size_buf);
int btrfs_resume_balance_async(struct btrfs_fs_info *fs_info);
int btrfs_recover_balance(struct btrfs_fs_info *fs_info);
int btrfs_pause_balance(struct btrfs_fs_info *fs_info);
+int btrfs_relocate_chunk(struct btrfs_fs_info *fs_info, u64 chunk_offset);
int btrfs_cancel_balance(struct btrfs_fs_info *fs_info);
int btrfs_create_uuid_tree(struct btrfs_fs_info *fs_info);
int btrfs_uuid_scan_kthread(void *data);
diff --git a/fs/btrfs/zoned.c b/fs/btrfs/zoned.c
index 1f972b75a9ab..70b23a0d03b1 100644
--- a/fs/btrfs/zoned.c
+++ b/fs/btrfs/zoned.c
@@ -21,9 +21,30 @@
/* Pseudo write pointer value for conventional zone */
#define WP_CONVENTIONAL ((u64)-2)
+/*
+ * Location of the first zone of superblock logging zone pairs.
+ *
+ * - primary superblock: 0B (zone 0)
+ * - first copy: 512G (zone starting at that offset)
+ * - second copy: 4T (zone starting at that offset)
+ */
+#define BTRFS_SB_LOG_PRIMARY_OFFSET (0ULL)
+#define BTRFS_SB_LOG_FIRST_OFFSET (512ULL * SZ_1G)
+#define BTRFS_SB_LOG_SECOND_OFFSET (4096ULL * SZ_1G)
+
+#define BTRFS_SB_LOG_FIRST_SHIFT const_ilog2(BTRFS_SB_LOG_FIRST_OFFSET)
+#define BTRFS_SB_LOG_SECOND_SHIFT const_ilog2(BTRFS_SB_LOG_SECOND_OFFSET)
+
/* Number of superblock log zones */
#define BTRFS_NR_SB_LOG_ZONES 2
+/*
+ * Maximum supported zone size. Currently, SMR disks have a zone size of
+ * 256MiB, and we are expecting ZNS drives to be in the 1-4GiB range. We do not
+ * expect the zone size to become larger than 8GiB in the near future.
+ */
+#define BTRFS_MAX_ZONE_SIZE SZ_8G
+
static int copy_zone_info_cb(struct blk_zone *zone, unsigned int idx, void *data)
{
struct blk_zone *zones = data;
@@ -111,23 +132,22 @@ static int sb_write_pointer(struct block_device *bdev, struct blk_zone *zones,
}
/*
- * The following zones are reserved as the circular buffer on ZONED btrfs.
- * - The primary superblock: zones 0 and 1
- * - The first copy: zones 16 and 17
- * - The second copy: zones 1024 or zone at 256GB which is minimum, and
- * the following one
+ * Get the first zone number of the superblock mirror
*/
static inline u32 sb_zone_number(int shift, int mirror)
{
- ASSERT(mirror < BTRFS_SUPER_MIRROR_MAX);
+ u64 zone;
+ ASSERT(mirror < BTRFS_SUPER_MIRROR_MAX);
switch (mirror) {
- case 0: return 0;
- case 1: return 16;
- case 2: return min_t(u64, btrfs_sb_offset(mirror) >> shift, 1024);
+ case 0: zone = 0; break;
+ case 1: zone = 1ULL << (BTRFS_SB_LOG_FIRST_SHIFT - shift); break;
+ case 2: zone = 1ULL << (BTRFS_SB_LOG_SECOND_SHIFT - shift); break;
}
- return 0;
+ ASSERT(zone <= U32_MAX);
+
+ return (u32)zone;
}
/*
@@ -300,10 +320,21 @@ int btrfs_get_dev_zone_info(struct btrfs_device *device)
zone_sectors = bdev_zone_sectors(bdev);
}
- nr_sectors = bdev_nr_sectors(bdev);
/* Check if it's power of 2 (see is_power_of_2) */
ASSERT(zone_sectors != 0 && (zone_sectors & (zone_sectors - 1)) == 0);
zone_info->zone_size = zone_sectors << SECTOR_SHIFT;
+
+ /* We reject devices with a zone size larger than 8GB */
+ if (zone_info->zone_size > BTRFS_MAX_ZONE_SIZE) {
+ btrfs_err_in_rcu(fs_info,
+ "zoned: %s: zone size %llu larger than supported maximum %llu",
+ rcu_str_deref(device->name),
+ zone_info->zone_size, BTRFS_MAX_ZONE_SIZE);
+ ret = -EINVAL;
+ goto out;
+ }
+
+ nr_sectors = bdev_nr_sectors(bdev);
zone_info->zone_size_shift = ilog2(zone_info->zone_size);
zone_info->max_zone_append_size =
(u64)queue_max_zone_append_sectors(queue) << SECTOR_SHIFT;
@@ -311,6 +342,13 @@ int btrfs_get_dev_zone_info(struct btrfs_device *device)
if (!IS_ALIGNED(nr_sectors, zone_sectors))
zone_info->nr_zones++;
+ if (bdev_is_zoned(bdev) && zone_info->max_zone_append_size == 0) {
+ btrfs_err(fs_info, "zoned: device %pg does not support zone append",
+ bdev);
+ ret = -EINVAL;
+ goto out;
+ }
+
zone_info->seq_zones = bitmap_zalloc(zone_info->nr_zones, GFP_KERNEL);
if (!zone_info->seq_zones) {
ret = -ENOMEM;
diff --git a/fs/btrfs/zoned.h b/fs/btrfs/zoned.h
index 61e969652fe1..5e41a74a9cb2 100644
--- a/fs/btrfs/zoned.h
+++ b/fs/btrfs/zoned.h
@@ -9,6 +9,12 @@
#include "disk-io.h"
#include "block-group.h"
+/*
+ * Block groups with more than this value (percents) of unusable space will be
+ * scheduled for background reclaim.
+ */
+#define BTRFS_DEFAULT_RECLAIM_THRESH 75
+
struct btrfs_zoned_device_info {
/*
* Number of zones, zone size and types of zones if bdev is a
diff --git a/fs/buffer.c b/fs/buffer.c
index 0cb7ffd4977c..c2e052c0fc5d 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -1020,11 +1020,7 @@ grow_buffers(struct block_device *bdev, sector_t block, int size, gfp_t gfp)
pgoff_t index;
int sizebits;
- sizebits = -1;
- do {
- sizebits++;
- } while ((size << sizebits) < PAGE_SIZE);
-
+ sizebits = PAGE_SHIFT - __ffs(size);
index = block >> sizebits;
/*
diff --git a/fs/cachefiles/Makefile b/fs/cachefiles/Makefile
index 891dedda5905..2227dc2d5498 100644
--- a/fs/cachefiles/Makefile
+++ b/fs/cachefiles/Makefile
@@ -7,6 +7,7 @@ cachefiles-y := \
bind.o \
daemon.o \
interface.o \
+ io.o \
key.o \
main.o \
namei.o \
diff --git a/fs/cachefiles/bind.c b/fs/cachefiles/bind.c
index dfb14dbddf51..38bb7764b454 100644
--- a/fs/cachefiles/bind.c
+++ b/fs/cachefiles/bind.c
@@ -118,6 +118,12 @@ static int cachefiles_daemon_add_cache(struct cachefiles_cache *cache)
cache->mnt = path.mnt;
root = path.dentry;
+ ret = -EINVAL;
+ if (mnt_user_ns(path.mnt) != &init_user_ns) {
+ pr_warn("File cache on idmapped mounts not supported");
+ goto error_unsupported;
+ }
+
/* check parameters */
ret = -EOPNOTSUPP;
if (d_is_negative(root) ||
diff --git a/fs/cachefiles/interface.c b/fs/cachefiles/interface.c
index 5efa6a3702c0..da3948fdb615 100644
--- a/fs/cachefiles/interface.c
+++ b/fs/cachefiles/interface.c
@@ -319,8 +319,8 @@ static void cachefiles_drop_object(struct fscache_object *_object)
/*
* dispose of a reference to an object
*/
-static void cachefiles_put_object(struct fscache_object *_object,
- enum fscache_obj_ref_trace why)
+void cachefiles_put_object(struct fscache_object *_object,
+ enum fscache_obj_ref_trace why)
{
struct cachefiles_object *object;
struct fscache_cache *cache;
@@ -568,4 +568,5 @@ const struct fscache_cache_ops cachefiles_cache_ops = {
.uncache_page = cachefiles_uncache_page,
.dissociate_pages = cachefiles_dissociate_pages,
.check_consistency = cachefiles_check_consistency,
+ .begin_read_operation = cachefiles_begin_read_operation,
};
diff --git a/fs/cachefiles/internal.h b/fs/cachefiles/internal.h
index cf9bd6401c2d..4ed83aa5253b 100644
--- a/fs/cachefiles/internal.h
+++ b/fs/cachefiles/internal.h
@@ -150,6 +150,9 @@ extern int cachefiles_has_space(struct cachefiles_cache *cache,
*/
extern const struct fscache_cache_ops cachefiles_cache_ops;
+void cachefiles_put_object(struct fscache_object *_object,
+ enum fscache_obj_ref_trace why);
+
/*
* key.c
*/
@@ -218,6 +221,12 @@ extern int cachefiles_write_page(struct fscache_storage *, struct page *);
extern void cachefiles_uncache_page(struct fscache_object *, struct page *);
/*
+ * rdwr2.c
+ */
+extern int cachefiles_begin_read_operation(struct netfs_read_request *,
+ struct fscache_retrieval *);
+
+/*
* security.c
*/
extern int cachefiles_get_security_ID(struct cachefiles_cache *cache);
diff --git a/fs/cachefiles/io.c b/fs/cachefiles/io.c
new file mode 100644
index 000000000000..b13fb45fc3f3
--- /dev/null
+++ b/fs/cachefiles/io.c
@@ -0,0 +1,420 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/* kiocb-using read/write
+ *
+ * Copyright (C) 2021 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ */
+
+#include <linux/mount.h>
+#include <linux/slab.h>
+#include <linux/file.h>
+#include <linux/uio.h>
+#include <linux/sched/mm.h>
+#include <linux/netfs.h>
+#include "internal.h"
+
+struct cachefiles_kiocb {
+ struct kiocb iocb;
+ refcount_t ki_refcnt;
+ loff_t start;
+ union {
+ size_t skipped;
+ size_t len;
+ };
+ netfs_io_terminated_t term_func;
+ void *term_func_priv;
+ bool was_async;
+};
+
+static inline void cachefiles_put_kiocb(struct cachefiles_kiocb *ki)
+{
+ if (refcount_dec_and_test(&ki->ki_refcnt)) {
+ fput(ki->iocb.ki_filp);
+ kfree(ki);
+ }
+}
+
+/*
+ * Handle completion of a read from the cache.
+ */
+static void cachefiles_read_complete(struct kiocb *iocb, long ret, long ret2)
+{
+ struct cachefiles_kiocb *ki = container_of(iocb, struct cachefiles_kiocb, iocb);
+
+ _enter("%ld,%ld", ret, ret2);
+
+ if (ki->term_func) {
+ if (ret >= 0)
+ ret += ki->skipped;
+ ki->term_func(ki->term_func_priv, ret, ki->was_async);
+ }
+
+ cachefiles_put_kiocb(ki);
+}
+
+/*
+ * Initiate a read from the cache.
+ */
+static int cachefiles_read(struct netfs_cache_resources *cres,
+ loff_t start_pos,
+ struct iov_iter *iter,
+ bool seek_data,
+ netfs_io_terminated_t term_func,
+ void *term_func_priv)
+{
+ struct cachefiles_kiocb *ki;
+ struct file *file = cres->cache_priv2;
+ unsigned int old_nofs;
+ ssize_t ret = -ENOBUFS;
+ size_t len = iov_iter_count(iter), skipped = 0;
+
+ _enter("%pD,%li,%llx,%zx/%llx",
+ file, file_inode(file)->i_ino, start_pos, len,
+ i_size_read(file->f_inode));
+
+ /* If the caller asked us to seek for data before doing the read, then
+ * we should do that now. If we find a gap, we fill it with zeros.
+ */
+ if (seek_data) {
+ loff_t off = start_pos, off2;
+
+ off2 = vfs_llseek(file, off, SEEK_DATA);
+ if (off2 < 0 && off2 >= (loff_t)-MAX_ERRNO && off2 != -ENXIO) {
+ skipped = 0;
+ ret = off2;
+ goto presubmission_error;
+ }
+
+ if (off2 == -ENXIO || off2 >= start_pos + len) {
+ /* The region is beyond the EOF or there's no more data
+ * in the region, so clear the rest of the buffer and
+ * return success.
+ */
+ iov_iter_zero(len, iter);
+ skipped = len;
+ ret = 0;
+ goto presubmission_error;
+ }
+
+ skipped = off2 - off;
+ iov_iter_zero(skipped, iter);
+ }
+
+ ret = -ENOBUFS;
+ ki = kzalloc(sizeof(struct cachefiles_kiocb), GFP_KERNEL);
+ if (!ki)
+ goto presubmission_error;
+
+ refcount_set(&ki->ki_refcnt, 2);
+ ki->iocb.ki_filp = file;
+ ki->iocb.ki_pos = start_pos + skipped;
+ ki->iocb.ki_flags = IOCB_DIRECT;
+ ki->iocb.ki_hint = ki_hint_validate(file_write_hint(file));
+ ki->iocb.ki_ioprio = get_current_ioprio();
+ ki->skipped = skipped;
+ ki->term_func = term_func;
+ ki->term_func_priv = term_func_priv;
+ ki->was_async = true;
+
+ if (ki->term_func)
+ ki->iocb.ki_complete = cachefiles_read_complete;
+
+ get_file(ki->iocb.ki_filp);
+
+ old_nofs = memalloc_nofs_save();
+ ret = vfs_iocb_iter_read(file, &ki->iocb, iter);
+ memalloc_nofs_restore(old_nofs);
+ switch (ret) {
+ case -EIOCBQUEUED:
+ goto in_progress;
+
+ case -ERESTARTSYS:
+ case -ERESTARTNOINTR:
+ case -ERESTARTNOHAND:
+ case -ERESTART_RESTARTBLOCK:
+ /* There's no easy way to restart the syscall since other AIO's
+ * may be already running. Just fail this IO with EINTR.
+ */
+ ret = -EINTR;
+ fallthrough;
+ default:
+ ki->was_async = false;
+ cachefiles_read_complete(&ki->iocb, ret, 0);
+ if (ret > 0)
+ ret = 0;
+ break;
+ }
+
+in_progress:
+ cachefiles_put_kiocb(ki);
+ _leave(" = %zd", ret);
+ return ret;
+
+presubmission_error:
+ if (term_func)
+ term_func(term_func_priv, ret < 0 ? ret : skipped, false);
+ return ret;
+}
+
+/*
+ * Handle completion of a write to the cache.
+ */
+static void cachefiles_write_complete(struct kiocb *iocb, long ret, long ret2)
+{
+ struct cachefiles_kiocb *ki = container_of(iocb, struct cachefiles_kiocb, iocb);
+ struct inode *inode = file_inode(ki->iocb.ki_filp);
+
+ _enter("%ld,%ld", ret, ret2);
+
+ /* Tell lockdep we inherited freeze protection from submission thread */
+ __sb_writers_acquired(inode->i_sb, SB_FREEZE_WRITE);
+ __sb_end_write(inode->i_sb, SB_FREEZE_WRITE);
+
+ if (ki->term_func)
+ ki->term_func(ki->term_func_priv, ret, ki->was_async);
+
+ cachefiles_put_kiocb(ki);
+}
+
+/*
+ * Initiate a write to the cache.
+ */
+static int cachefiles_write(struct netfs_cache_resources *cres,
+ loff_t start_pos,
+ struct iov_iter *iter,
+ netfs_io_terminated_t term_func,
+ void *term_func_priv)
+{
+ struct cachefiles_kiocb *ki;
+ struct inode *inode;
+ struct file *file = cres->cache_priv2;
+ unsigned int old_nofs;
+ ssize_t ret = -ENOBUFS;
+ size_t len = iov_iter_count(iter);
+
+ _enter("%pD,%li,%llx,%zx/%llx",
+ file, file_inode(file)->i_ino, start_pos, len,
+ i_size_read(file->f_inode));
+
+ ki = kzalloc(sizeof(struct cachefiles_kiocb), GFP_KERNEL);
+ if (!ki)
+ goto presubmission_error;
+
+ refcount_set(&ki->ki_refcnt, 2);
+ ki->iocb.ki_filp = file;
+ ki->iocb.ki_pos = start_pos;
+ ki->iocb.ki_flags = IOCB_DIRECT | IOCB_WRITE;
+ ki->iocb.ki_hint = ki_hint_validate(file_write_hint(file));
+ ki->iocb.ki_ioprio = get_current_ioprio();
+ ki->start = start_pos;
+ ki->len = len;
+ ki->term_func = term_func;
+ ki->term_func_priv = term_func_priv;
+ ki->was_async = true;
+
+ if (ki->term_func)
+ ki->iocb.ki_complete = cachefiles_write_complete;
+
+ /* Open-code file_start_write here to grab freeze protection, which
+ * will be released by another thread in aio_complete_rw(). Fool
+ * lockdep by telling it the lock got released so that it doesn't
+ * complain about the held lock when we return to userspace.
+ */
+ inode = file_inode(file);
+ __sb_start_write(inode->i_sb, SB_FREEZE_WRITE);
+ __sb_writers_release(inode->i_sb, SB_FREEZE_WRITE);
+
+ get_file(ki->iocb.ki_filp);
+
+ old_nofs = memalloc_nofs_save();
+ ret = vfs_iocb_iter_write(file, &ki->iocb, iter);
+ memalloc_nofs_restore(old_nofs);
+ switch (ret) {
+ case -EIOCBQUEUED:
+ goto in_progress;
+
+ case -ERESTARTSYS:
+ case -ERESTARTNOINTR:
+ case -ERESTARTNOHAND:
+ case -ERESTART_RESTARTBLOCK:
+ /* There's no easy way to restart the syscall since other AIO's
+ * may be already running. Just fail this IO with EINTR.
+ */
+ ret = -EINTR;
+ fallthrough;
+ default:
+ ki->was_async = false;
+ cachefiles_write_complete(&ki->iocb, ret, 0);
+ if (ret > 0)
+ ret = 0;
+ break;
+ }
+
+in_progress:
+ cachefiles_put_kiocb(ki);
+ _leave(" = %zd", ret);
+ return ret;
+
+presubmission_error:
+ if (term_func)
+ term_func(term_func_priv, -ENOMEM, false);
+ return -ENOMEM;
+}
+
+/*
+ * Prepare a read operation, shortening it to a cached/uncached
+ * boundary as appropriate.
+ */
+static enum netfs_read_source cachefiles_prepare_read(struct netfs_read_subrequest *subreq,
+ loff_t i_size)
+{
+ struct fscache_retrieval *op = subreq->rreq->cache_resources.cache_priv;
+ struct cachefiles_object *object;
+ struct cachefiles_cache *cache;
+ const struct cred *saved_cred;
+ struct file *file = subreq->rreq->cache_resources.cache_priv2;
+ loff_t off, to;
+
+ _enter("%zx @%llx/%llx", subreq->len, subreq->start, i_size);
+
+ object = container_of(op->op.object,
+ struct cachefiles_object, fscache);
+ cache = container_of(object->fscache.cache,
+ struct cachefiles_cache, cache);
+
+ if (!file)
+ goto cache_fail_nosec;
+
+ if (subreq->start >= i_size)
+ return NETFS_FILL_WITH_ZEROES;
+
+ cachefiles_begin_secure(cache, &saved_cred);
+
+ off = vfs_llseek(file, subreq->start, SEEK_DATA);
+ if (off < 0 && off >= (loff_t)-MAX_ERRNO) {
+ if (off == (loff_t)-ENXIO)
+ goto download_and_store;
+ goto cache_fail;
+ }
+
+ if (off >= subreq->start + subreq->len)
+ goto download_and_store;
+
+ if (off > subreq->start) {
+ off = round_up(off, cache->bsize);
+ subreq->len = off - subreq->start;
+ goto download_and_store;
+ }
+
+ to = vfs_llseek(file, subreq->start, SEEK_HOLE);
+ if (to < 0 && to >= (loff_t)-MAX_ERRNO)
+ goto cache_fail;
+
+ if (to < subreq->start + subreq->len) {
+ if (subreq->start + subreq->len >= i_size)
+ to = round_up(to, cache->bsize);
+ else
+ to = round_down(to, cache->bsize);
+ subreq->len = to - subreq->start;
+ }
+
+ cachefiles_end_secure(cache, saved_cred);
+ return NETFS_READ_FROM_CACHE;
+
+download_and_store:
+ if (cachefiles_has_space(cache, 0, (subreq->len + PAGE_SIZE - 1) / PAGE_SIZE) == 0)
+ __set_bit(NETFS_SREQ_WRITE_TO_CACHE, &subreq->flags);
+cache_fail:
+ cachefiles_end_secure(cache, saved_cred);
+cache_fail_nosec:
+ return NETFS_DOWNLOAD_FROM_SERVER;
+}
+
+/*
+ * Prepare for a write to occur.
+ */
+static int cachefiles_prepare_write(struct netfs_cache_resources *cres,
+ loff_t *_start, size_t *_len, loff_t i_size)
+{
+ loff_t start = *_start;
+ size_t len = *_len, down;
+
+ /* Round to DIO size */
+ down = start - round_down(start, PAGE_SIZE);
+ *_start = start - down;
+ *_len = round_up(down + len, PAGE_SIZE);
+ return 0;
+}
+
+/*
+ * Clean up an operation.
+ */
+static void cachefiles_end_operation(struct netfs_cache_resources *cres)
+{
+ struct fscache_retrieval *op = cres->cache_priv;
+ struct file *file = cres->cache_priv2;
+
+ _enter("");
+
+ if (file)
+ fput(file);
+ if (op) {
+ fscache_op_complete(&op->op, false);
+ fscache_put_retrieval(op);
+ }
+
+ _leave("");
+}
+
+static const struct netfs_cache_ops cachefiles_netfs_cache_ops = {
+ .end_operation = cachefiles_end_operation,
+ .read = cachefiles_read,
+ .write = cachefiles_write,
+ .prepare_read = cachefiles_prepare_read,
+ .prepare_write = cachefiles_prepare_write,
+};
+
+/*
+ * Open the cache file when beginning a cache operation.
+ */
+int cachefiles_begin_read_operation(struct netfs_read_request *rreq,
+ struct fscache_retrieval *op)
+{
+ struct cachefiles_object *object;
+ struct cachefiles_cache *cache;
+ struct path path;
+ struct file *file;
+
+ _enter("");
+
+ object = container_of(op->op.object,
+ struct cachefiles_object, fscache);
+ cache = container_of(object->fscache.cache,
+ struct cachefiles_cache, cache);
+
+ path.mnt = cache->mnt;
+ path.dentry = object->backer;
+ file = open_with_fake_path(&path, O_RDWR | O_LARGEFILE | O_DIRECT,
+ d_inode(object->backer), cache->cache_cred);
+ if (IS_ERR(file))
+ return PTR_ERR(file);
+ if (!S_ISREG(file_inode(file)->i_mode))
+ goto error_file;
+ if (unlikely(!file->f_op->read_iter) ||
+ unlikely(!file->f_op->write_iter)) {
+ pr_notice("Cache does not support read_iter and write_iter\n");
+ goto error_file;
+ }
+
+ fscache_get_retrieval(op);
+ rreq->cache_resources.cache_priv = op;
+ rreq->cache_resources.cache_priv2 = file;
+ rreq->cache_resources.ops = &cachefiles_netfs_cache_ops;
+ rreq->cookie_debug_id = object->fscache.debug_id;
+ _leave("");
+ return 0;
+
+error_file:
+ fput(file);
+ return -EIO;
+}
diff --git a/fs/cachefiles/rdwr.c b/fs/cachefiles/rdwr.c
index e027c718ca01..8ffc40e84a59 100644
--- a/fs/cachefiles/rdwr.c
+++ b/fs/cachefiles/rdwr.c
@@ -24,17 +24,16 @@ static int cachefiles_read_waiter(wait_queue_entry_t *wait, unsigned mode,
container_of(wait, struct cachefiles_one_read, monitor);
struct cachefiles_object *object;
struct fscache_retrieval *op = monitor->op;
- struct wait_bit_key *key = _key;
+ struct wait_page_key *key = _key;
struct page *page = wait->private;
ASSERT(key);
_enter("{%lu},%u,%d,{%p,%u}",
monitor->netfs_page->index, mode, sync,
- key->flags, key->bit_nr);
+ key->page, key->bit_nr);
- if (key->flags != &page->flags ||
- key->bit_nr != PG_locked)
+ if (key->page != page || key->bit_nr != PG_locked)
return 0;
_debug("--- monitor %p %lx ---", page, page->flags);
diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c
index 570731c4d019..3c03fa37cac4 100644
--- a/fs/ceph/caps.c
+++ b/fs/ceph/caps.c
@@ -3358,7 +3358,13 @@ static void handle_cap_grant(struct inode *inode,
if ((newcaps & CEPH_CAP_AUTH_SHARED) &&
(extra_info->issued & CEPH_CAP_AUTH_EXCL) == 0) {
- inode->i_mode = le32_to_cpu(grant->mode);
+ umode_t mode = le32_to_cpu(grant->mode);
+
+ if (inode_wrong_type(inode, mode))
+ pr_warn_once("inode type changed! (ino %llx.%llx is 0%o, mds says 0%o)\n",
+ ceph_vinop(inode), inode->i_mode, mode);
+ else
+ inode->i_mode = mode;
inode->i_uid = make_kuid(&init_user_ns, le32_to_cpu(grant->uid));
inode->i_gid = make_kgid(&init_user_ns, le32_to_cpu(grant->gid));
ci->i_btime = extra_info->btime;
diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c
index 83d9358854fb..f7a790ed62c4 100644
--- a/fs/ceph/dir.c
+++ b/fs/ceph/dir.c
@@ -677,6 +677,8 @@ 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);
+ if (IS_ERR(inode))
+ return PTR_ERR(inode);
dout("ENOENT on snapdir %p '%pd', linking to snapdir %p\n",
dentry, dentry, inode);
BUG_ON(!d_unhashed(dentry));
diff --git a/fs/ceph/export.c b/fs/ceph/export.c
index e088843a7734..f22156ee7306 100644
--- a/fs/ceph/export.c
+++ b/fs/ceph/export.c
@@ -248,9 +248,10 @@ static struct dentry *__snapfh_to_dentry(struct super_block *sb,
ihold(inode);
} else {
/* mds does not support lookup snapped inode */
- err = -EOPNOTSUPP;
- inode = NULL;
+ inode = ERR_PTR(-EOPNOTSUPP);
}
+ } else {
+ inode = ERR_PTR(-ESTALE);
}
ceph_mdsc_put_request(req);
@@ -261,8 +262,8 @@ static struct dentry *__snapfh_to_dentry(struct super_block *sb,
dout("snapfh_to_dentry %llx.%llx parent %llx hash %x err=%d",
vino.ino, vino.snap, sfh->parent_ino, sfh->hash, err);
}
- if (!inode)
- return ERR_PTR(-ESTALE);
+ if (IS_ERR(inode))
+ return ERR_CAST(inode);
/* see comments in ceph_get_parent() */
return unlinked ? d_obtain_root(inode) : d_obtain_alias(inode);
}
diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c
index 156f849f5385..689e3ffd29d7 100644
--- a/fs/ceph/inode.c
+++ b/fs/ceph/inode.c
@@ -78,9 +78,21 @@ struct inode *ceph_get_snapdir(struct inode *parent)
struct inode *inode = ceph_get_inode(parent->i_sb, vino);
struct ceph_inode_info *ci = ceph_inode(inode);
- BUG_ON(!S_ISDIR(parent->i_mode));
if (IS_ERR(inode))
return inode;
+
+ if (!S_ISDIR(parent->i_mode)) {
+ pr_warn_once("bad snapdir parent type (mode=0%o)\n",
+ parent->i_mode);
+ return ERR_PTR(-ENOTDIR);
+ }
+
+ if (!(inode->i_state & I_NEW) && !S_ISDIR(inode->i_mode)) {
+ pr_warn_once("bad snapdir inode type (mode=0%o)\n",
+ inode->i_mode);
+ return ERR_PTR(-ENOTDIR);
+ }
+
inode->i_mode = parent->i_mode;
inode->i_uid = parent->i_uid;
inode->i_gid = parent->i_gid;
@@ -757,11 +769,32 @@ int ceph_fill_inode(struct inode *inode, struct page *locked_page,
bool queue_trunc = false;
bool new_version = false;
bool fill_inline = false;
+ umode_t mode = le32_to_cpu(info->mode);
+ dev_t rdev = le32_to_cpu(info->rdev);
dout("%s %p ino %llx.%llx v %llu had %llu\n", __func__,
inode, ceph_vinop(inode), le64_to_cpu(info->version),
ci->i_version);
+ /* Once I_NEW is cleared, we can't change type or dev numbers */
+ if (inode->i_state & I_NEW) {
+ inode->i_mode = mode;
+ } else {
+ if (inode_wrong_type(inode, mode)) {
+ pr_warn_once("inode type changed! (ino %llx.%llx is 0%o, mds says 0%o)\n",
+ ceph_vinop(inode), inode->i_mode, mode);
+ return -ESTALE;
+ }
+
+ if ((S_ISCHR(mode) || S_ISBLK(mode)) && inode->i_rdev != rdev) {
+ pr_warn_once("dev inode rdev changed! (ino %llx.%llx is %u:%u, mds says %u:%u)\n",
+ ceph_vinop(inode), MAJOR(inode->i_rdev),
+ MINOR(inode->i_rdev), MAJOR(rdev),
+ MINOR(rdev));
+ return -ESTALE;
+ }
+ }
+
info_caps = le32_to_cpu(info->cap.caps);
/* prealloc new cap struct */
@@ -815,8 +848,6 @@ int ceph_fill_inode(struct inode *inode, struct page *locked_page,
issued |= __ceph_caps_dirty(ci);
new_issued = ~issued & info_caps;
- /* update inode */
- inode->i_rdev = le32_to_cpu(info->rdev);
/* directories have fl_stripe_unit set to zero */
if (le32_to_cpu(info->layout.fl_stripe_unit))
inode->i_blkbits =
@@ -828,7 +859,7 @@ int ceph_fill_inode(struct inode *inode, struct page *locked_page,
if ((new_version || (new_issued & CEPH_CAP_AUTH_SHARED)) &&
(issued & CEPH_CAP_AUTH_EXCL) == 0) {
- inode->i_mode = le32_to_cpu(info->mode);
+ inode->i_mode = mode;
inode->i_uid = make_kuid(&init_user_ns, le32_to_cpu(info->uid));
inode->i_gid = make_kgid(&init_user_ns, le32_to_cpu(info->gid));
dout("%p mode 0%o uid.gid %d.%d\n", inode, inode->i_mode,
@@ -926,7 +957,7 @@ int ceph_fill_inode(struct inode *inode, struct page *locked_page,
case S_IFCHR:
case S_IFSOCK:
inode->i_blkbits = PAGE_SHIFT;
- init_special_inode(inode, inode->i_mode, inode->i_rdev);
+ init_special_inode(inode, inode->i_mode, rdev);
inode->i_op = &ceph_file_iops;
break;
case S_IFREG:
diff --git a/fs/cifs/Kconfig b/fs/cifs/Kconfig
index fe03cbdae959..bf52e9326ebe 100644
--- a/fs/cifs/Kconfig
+++ b/fs/cifs/Kconfig
@@ -18,6 +18,7 @@ config CIFS
select CRYPTO_AES
select CRYPTO_LIB_DES
select KEYS
+ select DNS_RESOLVER
help
This is the client VFS module for the SMB3 family of NAS protocols,
(including support for the most recent, most secure dialect SMB3.1.1)
@@ -112,7 +113,6 @@ config CIFS_WEAK_PW_HASH
config CIFS_UPCALL
bool "Kerberos/SPNEGO advanced session setup"
depends on CIFS
- select DNS_RESOLVER
help
Enables an upcall mechanism for CIFS which accesses userspace helper
utilities to provide SPNEGO packaged (RFC 4178) Kerberos tickets
@@ -179,7 +179,6 @@ config CIFS_DEBUG_DUMP_KEYS
config CIFS_DFS_UPCALL
bool "DFS feature support"
depends on CIFS
- select DNS_RESOLVER
help
Distributed File System (DFS) support is used to access shares
transparently in an enterprise name space, even if the share
diff --git a/fs/cifs/Makefile b/fs/cifs/Makefile
index 5213b20843b5..3ee3b7de4ded 100644
--- a/fs/cifs/Makefile
+++ b/fs/cifs/Makefile
@@ -10,13 +10,14 @@ cifs-y := trace.o cifsfs.o cifssmb.o cifs_debug.o connect.o dir.o file.o \
cifs_unicode.o nterr.o cifsencrypt.o \
readdir.o ioctl.o sess.o export.o smb1ops.o unc.o winucase.o \
smb2ops.o smb2maperror.o smb2transport.o \
- smb2misc.o smb2pdu.o smb2inode.o smb2file.o cifsacl.o fs_context.o
+ smb2misc.o smb2pdu.o smb2inode.o smb2file.o cifsacl.o fs_context.o \
+ dns_resolve.o
cifs-$(CONFIG_CIFS_XATTR) += xattr.o
cifs-$(CONFIG_CIFS_UPCALL) += cifs_spnego.o
-cifs-$(CONFIG_CIFS_DFS_UPCALL) += dns_resolve.o cifs_dfs_ref.o dfs_cache.o
+cifs-$(CONFIG_CIFS_DFS_UPCALL) += cifs_dfs_ref.o dfs_cache.o
cifs-$(CONFIG_CIFS_SWN_UPCALL) += netlink.o cifs_swn.o
diff --git a/fs/cifs/cifs_debug.c b/fs/cifs/cifs_debug.c
index 88a7958170ee..68e8e5b27841 100644
--- a/fs/cifs/cifs_debug.c
+++ b/fs/cifs/cifs_debug.c
@@ -17,15 +17,14 @@
#include "cifsproto.h"
#include "cifs_debug.h"
#include "cifsfs.h"
+#include "fs_context.h"
#ifdef CONFIG_CIFS_DFS_UPCALL
#include "dfs_cache.h"
#endif
#ifdef CONFIG_CIFS_SMB_DIRECT
#include "smbdirect.h"
#endif
-#ifdef CONFIG_CIFS_SWN_UPCALL
#include "cifs_swn.h"
-#endif
void
cifs_dump_mem(char *label, void *data, int length)
@@ -118,10 +117,8 @@ static void cifs_debug_tcon(struct seq_file *m, struct cifs_tcon *tcon)
seq_printf(m, " POSIX Extensions");
if (tcon->ses->server->ops->dump_share_caps)
tcon->ses->server->ops->dump_share_caps(m, tcon);
-#ifdef CONFIG_CIFS_SWN_UPCALL
if (tcon->use_witness)
seq_puts(m, " Witness");
-#endif
if (tcon->need_reconnect)
seq_puts(m, "\tDISCONNECTED ");
@@ -490,10 +487,8 @@ skip_rdma:
spin_unlock(&cifs_tcp_ses_lock);
seq_putc(m, '\n');
-
-#ifdef CONFIG_CIFS_SWN_UPCALL
cifs_swn_dump(m);
-#endif
+
/* BB add code to dump additional info such as TCP session info now */
return 0;
}
@@ -702,6 +697,7 @@ static const struct proc_ops cifs_lookup_cache_proc_ops;
static const struct proc_ops traceSMB_proc_ops;
static const struct proc_ops cifs_security_flags_proc_ops;
static const struct proc_ops cifs_linux_ext_proc_ops;
+static const struct proc_ops cifs_mount_params_proc_ops;
void
cifs_proc_init(void)
@@ -726,6 +722,8 @@ cifs_proc_init(void)
proc_create("LookupCacheEnabled", 0644, proc_fs_cifs,
&cifs_lookup_cache_proc_ops);
+ proc_create("mount_params", 0444, proc_fs_cifs, &cifs_mount_params_proc_ops);
+
#ifdef CONFIG_CIFS_DFS_UPCALL
proc_create("dfscache", 0644, proc_fs_cifs, &dfscache_proc_ops);
#endif
@@ -764,6 +762,7 @@ cifs_proc_clean(void)
remove_proc_entry("SecurityFlags", proc_fs_cifs);
remove_proc_entry("LinuxExtensionsEnabled", proc_fs_cifs);
remove_proc_entry("LookupCacheEnabled", proc_fs_cifs);
+ remove_proc_entry("mount_params", proc_fs_cifs);
#ifdef CONFIG_CIFS_DFS_UPCALL
remove_proc_entry("dfscache", proc_fs_cifs);
@@ -1023,6 +1022,51 @@ static const struct proc_ops cifs_security_flags_proc_ops = {
.proc_release = single_release,
.proc_write = cifs_security_flags_proc_write,
};
+
+/* To make it easier to debug, can help to show mount params */
+static int cifs_mount_params_proc_show(struct seq_file *m, void *v)
+{
+ const struct fs_parameter_spec *p;
+ const char *type;
+
+ for (p = smb3_fs_parameters; p->name; p++) {
+ /* cannot use switch with pointers... */
+ if (!p->type) {
+ if (p->flags == fs_param_neg_with_no)
+ type = "noflag";
+ else
+ type = "flag";
+ } else if (p->type == fs_param_is_bool)
+ type = "bool";
+ else if (p->type == fs_param_is_u32)
+ type = "u32";
+ else if (p->type == fs_param_is_u64)
+ type = "u64";
+ else if (p->type == fs_param_is_string)
+ type = "string";
+ else
+ type = "unknown";
+
+ seq_printf(m, "%s:%s\n", p->name, type);
+ }
+
+ return 0;
+}
+
+static int cifs_mount_params_proc_open(struct inode *inode, struct file *file)
+{
+ return single_open(file, cifs_mount_params_proc_show, NULL);
+}
+
+static const struct proc_ops cifs_mount_params_proc_ops = {
+ .proc_open = cifs_mount_params_proc_open,
+ .proc_read = seq_read,
+ .proc_lseek = seq_lseek,
+ .proc_release = single_release,
+ /* No need for write for now */
+ /* .proc_write = cifs_mount_params_proc_write, */
+};
+
#else
inline void cifs_proc_init(void)
{
diff --git a/fs/cifs/cifs_dfs_ref.c b/fs/cifs/cifs_dfs_ref.c
index 6b1ce4efb591..c87c37cf2914 100644
--- a/fs/cifs/cifs_dfs_ref.c
+++ b/fs/cifs/cifs_dfs_ref.c
@@ -270,7 +270,7 @@ static struct vfsmount *cifs_dfs_do_mount(struct dentry *mntpt,
char *mountdata;
char *devname;
- devname = kstrndup(fullpath, strlen(fullpath), GFP_KERNEL);
+ devname = kstrdup(fullpath, GFP_KERNEL);
if (!devname)
return ERR_PTR(-ENOMEM);
@@ -302,6 +302,7 @@ static struct vfsmount *cifs_dfs_do_automount(struct dentry *mntpt)
struct cifs_sb_info *cifs_sb;
struct cifs_ses *ses;
struct cifs_tcon *tcon;
+ void *page;
char *full_path, *root_path;
unsigned int xid;
int rc;
@@ -324,10 +325,13 @@ static struct vfsmount *cifs_dfs_do_automount(struct dentry *mntpt)
goto cdda_exit;
}
+ page = alloc_dentry_path();
/* always use tree name prefix */
- full_path = build_path_from_dentry_optional_prefix(mntpt, true);
- if (full_path == NULL)
- goto cdda_exit;
+ full_path = build_path_from_dentry_optional_prefix(mntpt, page, true);
+ if (IS_ERR(full_path)) {
+ mnt = ERR_CAST(full_path);
+ goto free_full_path;
+ }
convert_delimiter(full_path, '\\');
@@ -385,7 +389,7 @@ static struct vfsmount *cifs_dfs_do_automount(struct dentry *mntpt)
free_root_path:
kfree(root_path);
free_full_path:
- kfree(full_path);
+ free_dentry_path(page);
cdda_exit:
cifs_dbg(FYI, "leaving %s\n" , __func__);
return mnt;
diff --git a/fs/cifs/cifs_fs_sb.h b/fs/cifs/cifs_fs_sb.h
index aa77edc12212..2a5325a7ae49 100644
--- a/fs/cifs/cifs_fs_sb.h
+++ b/fs/cifs/cifs_fs_sb.h
@@ -81,5 +81,9 @@ struct cifs_sb_info {
* (cifs_autodisable_serverino) in order to match new mounts.
*/
bool mnt_cifs_serverino_autodisabled;
+ /*
+ * Available once the mount has completed.
+ */
+ struct dentry *root;
};
#endif /* _CIFS_FS_SB_H */
diff --git a/fs/cifs/cifs_swn.c b/fs/cifs/cifs_swn.c
index f2d730fffccb..d829b8bf833e 100644
--- a/fs/cifs/cifs_swn.c
+++ b/fs/cifs/cifs_swn.c
@@ -248,7 +248,7 @@ nlmsg_fail:
/*
* Try to find a matching registration for the tcon's server name and share name.
- * Calls to this funciton must be protected by cifs_swnreg_idr_mutex.
+ * Calls to this function must be protected by cifs_swnreg_idr_mutex.
* TODO Try to avoid memory allocations
*/
static struct cifs_swn_reg *cifs_find_swn_reg(struct cifs_tcon *tcon)
diff --git a/fs/cifs/cifs_swn.h b/fs/cifs/cifs_swn.h
index 236ecd4959d5..8a9d2a5c9077 100644
--- a/fs/cifs/cifs_swn.h
+++ b/fs/cifs/cifs_swn.h
@@ -7,11 +7,13 @@
#ifndef _CIFS_SWN_H
#define _CIFS_SWN_H
+#include "cifsglob.h"
struct cifs_tcon;
struct sk_buff;
struct genl_info;
+#ifdef CONFIG_CIFS_SWN_UPCALL
extern int cifs_swn_register(struct cifs_tcon *tcon);
extern int cifs_swn_unregister(struct cifs_tcon *tcon);
@@ -22,4 +24,29 @@ extern void cifs_swn_dump(struct seq_file *m);
extern void cifs_swn_check(void);
+static inline bool cifs_swn_set_server_dstaddr(struct TCP_Server_Info *server)
+{
+ if (server->use_swn_dstaddr) {
+ server->dstaddr = server->swn_dstaddr;
+ return true;
+ }
+ return false;
+}
+
+static inline void cifs_swn_reset_server_dstaddr(struct TCP_Server_Info *server)
+{
+ server->use_swn_dstaddr = false;
+}
+
+#else
+
+static inline int cifs_swn_register(struct cifs_tcon *tcon) { return 0; }
+static inline int cifs_swn_unregister(struct cifs_tcon *tcon) { return 0; }
+static inline int cifs_swn_notify(struct sk_buff *s, struct genl_info *i) { return 0; }
+static inline void cifs_swn_dump(struct seq_file *m) {}
+static inline void cifs_swn_check(void) {}
+static inline bool cifs_swn_set_server_dstaddr(struct TCP_Server_Info *server) { return false; }
+static inline void cifs_swn_reset_server_dstaddr(struct TCP_Server_Info *server) {}
+
+#endif /* CONFIG_CIFS_SWN_UPCALL */
#endif /* _CIFS_SWN_H */
diff --git a/fs/cifs/cifsacl.c b/fs/cifs/cifsacl.c
index 9d29eb9660c2..784407f9280f 100644
--- a/fs/cifs/cifsacl.c
+++ b/fs/cifs/cifsacl.c
@@ -1094,11 +1094,9 @@ static int set_chmod_dacl(struct cifs_acl *pdacl, struct cifs_acl *pndacl,
struct cifs_ace *pnntace = NULL;
char *nacl_base = NULL;
u32 num_aces = 0;
- __u64 nmode;
bool new_aces_set = false;
/* Assuming that pndacl and pnmode are never NULL */
- nmode = *pnmode;
nacl_base = (char *)pndacl;
nsize = sizeof(struct cifs_acl);
@@ -1118,7 +1116,6 @@ static int set_chmod_dacl(struct cifs_acl *pdacl, struct cifs_acl *pndacl,
/* Retain old ACEs which we can retain */
for (i = 0; i < src_num_aces; ++i) {
pntace = (struct cifs_ace *) (acl_base + size);
- pnntace = (struct cifs_ace *) (nacl_base + nsize);
if (!new_aces_set && (pntace->flags & INHERITED_ACE)) {
/* Place the new ACEs in between existing explicit and inherited */
@@ -1131,14 +1128,17 @@ static int set_chmod_dacl(struct cifs_acl *pdacl, struct cifs_acl *pndacl,
}
/* If it's any one of the ACE we're replacing, skip! */
- if ((compare_sids(&pntace->sid, &sid_unix_NFS_mode) == 0) ||
+ if (((compare_sids(&pntace->sid, &sid_unix_NFS_mode) == 0) ||
(compare_sids(&pntace->sid, pownersid) == 0) ||
(compare_sids(&pntace->sid, pgrpsid) == 0) ||
(compare_sids(&pntace->sid, &sid_everyone) == 0) ||
- (compare_sids(&pntace->sid, &sid_authusers) == 0)) {
+ (compare_sids(&pntace->sid, &sid_authusers) == 0))) {
goto next_ace;
}
+ /* update the pointer to the next ACE to populate*/
+ pnntace = (struct cifs_ace *) (nacl_base + nsize);
+
nsize += cifs_copy_ace(pnntace, pntace, NULL);
num_aces++;
@@ -1649,7 +1649,7 @@ id_mode_to_cifs_acl(struct inode *inode, const char *path, __u64 *pnmode,
* Add three ACEs for owner, group, everyone getting rid of other ACEs
* as chmod disables ACEs and set the security descriptor. Allocate
* memory for the smb header, set security descriptor request security
- * descriptor parameters, and secuirty descriptor itself
+ * descriptor parameters, and security descriptor itself
*/
nsecdesclen = max_t(u32, nsecdesclen, DEFAULT_SEC_DESC_LEN);
pnntsd = kmalloc(nsecdesclen, GFP_KERNEL);
diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c
index 099ad9f3660b..5f2c139143a7 100644
--- a/fs/cifs/cifsfs.c
+++ b/fs/cifs/cifsfs.c
@@ -217,8 +217,11 @@ cifs_read_super(struct super_block *sb)
rc = super_setup_bdi(sb);
if (rc)
goto out_no_root;
- /* tune readahead according to rsize */
- sb->s_bdi->ra_pages = cifs_sb->ctx->rsize / PAGE_SIZE;
+ /* tune readahead according to rsize if readahead size not set on mount */
+ if (cifs_sb->ctx->rasize)
+ sb->s_bdi->ra_pages = cifs_sb->ctx->rasize / PAGE_SIZE;
+ else
+ sb->s_bdi->ra_pages = cifs_sb->ctx->rsize / PAGE_SIZE;
sb->s_blocksize = CIFS_MAX_MSGSIZE;
sb->s_blocksize_bits = 14; /* default 2**14 = CIFS_MAX_MSGSIZE */
@@ -257,6 +260,29 @@ out_no_root:
static void cifs_kill_sb(struct super_block *sb)
{
struct cifs_sb_info *cifs_sb = CIFS_SB(sb);
+ struct cifs_tcon *tcon;
+ struct cached_fid *cfid;
+
+ /*
+ * We ned to release all dentries for the cached directories
+ * before we kill the sb.
+ */
+ if (cifs_sb->root) {
+ dput(cifs_sb->root);
+ cifs_sb->root = NULL;
+ }
+ tcon = cifs_sb_master_tcon(cifs_sb);
+ if (tcon) {
+ cfid = &tcon->crfid;
+ mutex_lock(&cfid->fid_mutex);
+ if (cfid->dentry) {
+
+ dput(cfid->dentry);
+ cfid->dentry = NULL;
+ }
+ mutex_unlock(&cfid->fid_mutex);
+ }
+
kill_anon_super(sb);
cifs_umount(cifs_sb);
}
@@ -476,7 +502,8 @@ static int cifs_show_devname(struct seq_file *m, struct dentry *root)
seq_puts(m, "none");
else {
convert_delimiter(devname, '/');
- seq_puts(m, devname);
+ /* escape all spaces in share names */
+ seq_escape(m, devname, " \t");
kfree(devname);
}
return 0;
@@ -625,6 +652,8 @@ cifs_show_options(struct seq_file *s, struct dentry *root)
seq_printf(s, ",rsize=%u", cifs_sb->ctx->rsize);
seq_printf(s, ",wsize=%u", cifs_sb->ctx->wsize);
seq_printf(s, ",bsize=%u", cifs_sb->ctx->bsize);
+ if (cifs_sb->ctx->rasize)
+ seq_printf(s, ",rasize=%u", cifs_sb->ctx->rasize);
if (tcon->ses->server->min_offload)
seq_printf(s, ",esize=%u", tcon->ses->server->min_offload);
seq_printf(s, ",echo_interval=%lu",
@@ -655,10 +684,8 @@ cifs_show_options(struct seq_file *s, struct dentry *root)
seq_printf(s, ",multichannel,max_channels=%zu",
tcon->ses->chan_max);
-#ifdef CONFIG_CIFS_SWN_UPCALL
if (tcon->use_witness)
seq_puts(s, ",witness");
-#endif
return 0;
}
@@ -833,6 +860,12 @@ cifs_smb3_do_mount(struct file_system_type *fs_type,
goto out;
}
+ /* cifs_setup_volume_info->smb3_parse_devname() redups UNC & prepath */
+ kfree(cifs_sb->ctx->UNC);
+ cifs_sb->ctx->UNC = NULL;
+ kfree(cifs_sb->ctx->prepath);
+ cifs_sb->ctx->prepath = NULL;
+
rc = cifs_setup_volume_info(cifs_sb->ctx, NULL, old_ctx->UNC);
if (rc) {
root = ERR_PTR(rc);
@@ -887,6 +920,9 @@ cifs_smb3_do_mount(struct file_system_type *fs_type,
if (IS_ERR(root))
goto out_super;
+ if (cifs_sb)
+ cifs_sb->root = dget(root);
+
cifs_dbg(FYI, "dentry root is: %p\n", root);
return root;
@@ -1527,10 +1563,6 @@ init_cifs(void)
int rc = 0;
cifs_proc_init();
INIT_LIST_HEAD(&cifs_tcp_ses_list);
-#ifdef CONFIG_CIFS_DNOTIFY_EXPERIMENTAL /* unused temporarily */
- INIT_LIST_HEAD(&GlobalDnotifyReqList);
- INIT_LIST_HEAD(&GlobalDnotifyRsp_Q);
-#endif /* was needed for dnotify, and will be needed for inotify when VFS fix */
/*
* Initialize Global counters
*/
diff --git a/fs/cifs/cifsfs.h b/fs/cifs/cifsfs.h
index 0d7ef150dbb2..6beddb108ba0 100644
--- a/fs/cifs/cifsfs.h
+++ b/fs/cifs/cifsfs.h
@@ -165,5 +165,5 @@ extern struct dentry *cifs_smb3_do_mount(struct file_system_type *fs_type,
extern const struct export_operations cifs_export_ops;
#endif /* CONFIG_CIFS_NFSD_EXPORT */
-#define CIFS_VERSION "2.31"
+#define CIFS_VERSION "2.32"
#endif /* _CIFSFS_H */
diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h
index 31fc8695abd6..b23a0ee8c6f8 100644
--- a/fs/cifs/cifsglob.h
+++ b/fs/cifs/cifsglob.h
@@ -495,7 +495,7 @@ struct smb_version_operations {
struct inode *inode,
struct dentry *dentry,
struct cifs_tcon *tcon,
- char *full_path,
+ const char *full_path,
umode_t mode,
dev_t device_number);
/* version specific fiemap implementation */
@@ -919,8 +919,8 @@ struct cifs_ses {
bool binding:1; /* are we binding the session? */
__u16 session_flags;
__u8 smb3signingkey[SMB3_SIGN_KEY_SIZE];
- __u8 smb3encryptionkey[SMB3_SIGN_KEY_SIZE];
- __u8 smb3decryptionkey[SMB3_SIGN_KEY_SIZE];
+ __u8 smb3encryptionkey[SMB3_ENC_DEC_KEY_SIZE];
+ __u8 smb3decryptionkey[SMB3_ENC_DEC_KEY_SIZE];
__u8 preauth_sha_hash[SMB2_PREAUTH_HASH_SIZE];
__u8 binding_preauth_sha_hash[SMB2_PREAUTH_HASH_SIZE];
@@ -988,10 +988,12 @@ struct cached_fid {
bool is_valid:1; /* Do we have a useable root fid */
bool file_all_info_is_valid:1;
bool has_lease:1;
+ unsigned long time; /* jiffies of when lease was taken */
struct kref refcount;
struct cifs_fid *fid;
struct mutex fid_mutex;
struct cifs_tcon *tcon;
+ struct dentry *dentry;
struct work_struct lease_break;
struct smb2_file_all_info file_all_info;
};
@@ -1070,6 +1072,7 @@ struct cifs_tcon {
bool use_resilient:1; /* use resilient instead of durable handles */
bool use_persistent:1; /* use persistent instead of durable handles */
bool no_lease:1; /* Do not request leases on files or directories */
+ bool use_witness:1; /* use witness protocol */
__le32 capabilities;
__u32 share_flags;
__u32 maximal_access;
@@ -1094,9 +1097,6 @@ struct cifs_tcon {
int remap:2;
struct list_head ulist; /* cache update list */
#endif
-#ifdef CONFIG_CIFS_SWN_UPCALL
- bool use_witness:1; /* use witness protocol */
-#endif
};
/*
@@ -1283,8 +1283,6 @@ struct cifs_aio_ctx {
bool direct_io;
};
-struct cifs_readdata;
-
/* asynchronous read support */
struct cifs_readdata {
struct kref refcount;
@@ -1318,8 +1316,6 @@ struct cifs_readdata {
struct page **pages;
};
-struct cifs_writedata;
-
/* asynchronous write support */
struct cifs_writedata {
struct kref refcount;
@@ -1798,9 +1794,8 @@ require use of the stronger protocol */
*
* Semaphores
* ----------
- * sesSem operations on smb session
- * tconSem operations on tree connection
- * fh_sem file handle reconnection operations
+ * cifsInodeInfo->lock_sem protects:
+ * the list of locks held by the inode
*
****************************************************************************/
@@ -1831,13 +1826,6 @@ GLOBAL_EXTERN struct list_head cifs_tcp_ses_list;
*/
GLOBAL_EXTERN spinlock_t cifs_tcp_ses_lock;
-#ifdef CONFIG_CIFS_DNOTIFY_EXPERIMENTAL /* unused temporarily */
-/* Outstanding dir notify requests */
-GLOBAL_EXTERN struct list_head GlobalDnotifyReqList;
-/* DirNotify response queue */
-GLOBAL_EXTERN struct list_head GlobalDnotifyRsp_Q;
-#endif /* was needed for dnotify, and will be needed for inotify when VFS fix */
-
/*
* Global transaction id (XID) information
*/
@@ -1881,19 +1869,9 @@ extern unsigned int cifs_min_small; /* min size of small buf pool */
extern unsigned int cifs_max_pending; /* MAX requests at once to server*/
extern bool disable_legacy_dialects; /* forbid vers=1.0 and vers=2.0 mounts */
-GLOBAL_EXTERN struct rb_root uidtree;
-GLOBAL_EXTERN struct rb_root gidtree;
-GLOBAL_EXTERN spinlock_t siduidlock;
-GLOBAL_EXTERN spinlock_t sidgidlock;
-GLOBAL_EXTERN struct rb_root siduidtree;
-GLOBAL_EXTERN struct rb_root sidgidtree;
-GLOBAL_EXTERN spinlock_t uidsidlock;
-GLOBAL_EXTERN spinlock_t gidsidlock;
-
void cifs_oplock_break(struct work_struct *work);
void cifs_queue_oplock_break(struct cifsFileInfo *cfile);
-extern const struct slow_work_ops cifs_oplock_break_ops;
extern struct workqueue_struct *cifsiod_wq;
extern struct workqueue_struct *decrypt_wq;
extern struct workqueue_struct *fileinfo_put_wq;
diff --git a/fs/cifs/cifspdu.h b/fs/cifs/cifspdu.h
index 64fe5a47b5e8..b53a87db282f 100644
--- a/fs/cifs/cifspdu.h
+++ b/fs/cifs/cifspdu.h
@@ -147,6 +147,11 @@
*/
#define SMB3_SIGN_KEY_SIZE (16)
+/*
+ * Size of the smb3 encryption/decryption keys
+ */
+#define SMB3_ENC_DEC_KEY_SIZE (32)
+
#define CIFS_CLIENT_CHALLENGE_SIZE (8)
#define CIFS_SERVER_CHALLENGE_SIZE (8)
#define CIFS_HMAC_MD5_HASH_SIZE (16)
@@ -1898,7 +1903,7 @@ typedef struct smb_com_transaction2_fnext_req {
__le16 InformationLevel;
__u32 ResumeKey;
__le16 SearchFlags;
- char ResumeFileName[1];
+ char ResumeFileName[];
} __attribute__((packed)) TRANSACTION2_FNEXT_REQ;
typedef struct smb_com_transaction2_fnext_rsp {
diff --git a/fs/cifs/cifsproto.h b/fs/cifs/cifsproto.h
index 75ce6f742b8d..a79d50001fbf 100644
--- a/fs/cifs/cifsproto.h
+++ b/fs/cifs/cifsproto.h
@@ -69,9 +69,20 @@ extern int init_cifs_idmap(void);
extern void exit_cifs_idmap(void);
extern int init_cifs_spnego(void);
extern void exit_cifs_spnego(void);
-extern char *build_path_from_dentry(struct dentry *);
+extern const char *build_path_from_dentry(struct dentry *, void *);
extern char *build_path_from_dentry_optional_prefix(struct dentry *direntry,
- bool prefix);
+ void *page, bool prefix);
+static inline void *alloc_dentry_path(void)
+{
+ return __getname();
+}
+
+static inline void free_dentry_path(void *page)
+{
+ if (page)
+ __putname(page);
+}
+
extern char *cifs_build_path_to_root(struct smb3_fs_context *ctx,
struct cifs_sb_info *cifs_sb,
struct cifs_tcon *tcon,
@@ -184,7 +195,7 @@ extern struct cifsFileInfo *cifs_new_fileinfo(struct cifs_fid *fid,
struct file *file,
struct tcon_link *tlink,
__u32 oplock);
-extern int cifs_posix_open(char *full_path, struct inode **inode,
+extern int cifs_posix_open(const char *full_path, struct inode **inode,
struct super_block *sb, int mode,
unsigned int f_flags, __u32 *oplock, __u16 *netfid,
unsigned int xid);
@@ -194,7 +205,7 @@ extern void cifs_unix_basic_to_fattr(struct cifs_fattr *fattr,
struct cifs_sb_info *cifs_sb);
extern void cifs_dir_info_to_fattr(struct cifs_fattr *, FILE_DIRECTORY_INFO *,
struct cifs_sb_info *);
-extern void cifs_fattr_to_inode(struct inode *inode, struct cifs_fattr *fattr);
+extern int cifs_fattr_to_inode(struct inode *inode, struct cifs_fattr *fattr);
extern struct inode *cifs_iget(struct super_block *sb,
struct cifs_fattr *fattr);
@@ -207,7 +218,7 @@ extern int cifs_get_inode_info_unix(struct inode **pinode,
const unsigned char *search_path,
struct super_block *sb, unsigned int xid);
extern int cifs_set_file_info(struct inode *inode, struct iattr *attrs,
- unsigned int xid, char *full_path, __u32 dosattr);
+ unsigned int xid, const char *full_path, __u32 dosattr);
extern int cifs_rename_pending_delete(const char *full_path,
struct dentry *dentry,
const unsigned int xid);
@@ -358,11 +369,6 @@ extern int CIFSSMBSetFileDisposition(const unsigned int xid,
struct cifs_tcon *tcon,
bool delete_file, __u16 fid,
__u32 pid_of_opener);
-#if 0
-extern int CIFSSMBSetAttrLegacy(unsigned int xid, struct cifs_tcon *tcon,
- char *fileName, __u16 dos_attributes,
- const struct nls_table *nls_codepage);
-#endif /* possibly unneeded function */
extern int CIFSSMBSetEOF(const unsigned int xid, struct cifs_tcon *tcon,
const char *file_name, __u64 size,
struct cifs_sb_info *cifs_sb, bool set_allocation);
@@ -504,12 +510,6 @@ extern int generate_smb311signingkey(struct cifs_ses *);
extern int calc_lanman_hash(const char *password, const char *cryptkey,
bool encrypt, char *lnm_session_key);
#endif /* CIFS_WEAK_PW_HASH */
-#ifdef CONFIG_CIFS_DNOTIFY_EXPERIMENTAL /* unused temporarily */
-extern int CIFSSMBNotify(const unsigned int xid, struct cifs_tcon *tcon,
- const int notify_subdirs, const __u16 netfid,
- __u32 filter, struct file *file, int multishot,
- const struct nls_table *nls_codepage);
-#endif /* was needed for dnotify, and will be needed for inotify when VFS fix */
extern int CIFSSMBCopy(unsigned int xid,
struct cifs_tcon *source_tcon,
const char *fromName,
diff --git a/fs/cifs/cifssmb.c b/fs/cifs/cifssmb.c
index c279527aae92..41f74163cc1c 100644
--- a/fs/cifs/cifssmb.c
+++ b/fs/cifs/cifssmb.c
@@ -114,7 +114,7 @@ cifs_mark_open_files_invalid(struct cifs_tcon *tcon)
mutex_lock(&tcon->crfid.fid_mutex);
tcon->crfid.is_valid = false;
/* cached handle is not valid, so SMB2_CLOSE won't be sent below */
- close_shroot_lease_locked(&tcon->crfid);
+ close_cached_dir_lease_locked(&tcon->crfid);
memset(tcon->crfid.fid, 0, sizeof(struct cifs_fid));
mutex_unlock(&tcon->crfid.fid_mutex);
@@ -5917,56 +5917,6 @@ SetTimesRetry:
return rc;
}
-/* Can not be used to set time stamps yet (due to old DOS time format) */
-/* Can be used to set attributes */
-#if 0 /* Possibly not needed - since it turns out that strangely NT4 has a bug
- handling it anyway and NT4 was what we thought it would be needed for
- Do not delete it until we prove whether needed for Win9x though */
-int
-CIFSSMBSetAttrLegacy(unsigned int xid, struct cifs_tcon *tcon, char *fileName,
- __u16 dos_attrs, const struct nls_table *nls_codepage)
-{
- SETATTR_REQ *pSMB = NULL;
- SETATTR_RSP *pSMBr = NULL;
- int rc = 0;
- int bytes_returned;
- int name_len;
-
- cifs_dbg(FYI, "In SetAttrLegacy\n");
-
-SetAttrLgcyRetry:
- rc = smb_init(SMB_COM_SETATTR, 8, tcon, (void **) &pSMB,
- (void **) &pSMBr);
- if (rc)
- return rc;
-
- if (pSMB->hdr.Flags2 & SMBFLG2_UNICODE) {
- name_len =
- ConvertToUTF16((__le16 *) pSMB->fileName, fileName,
- PATH_MAX, nls_codepage);
- name_len++; /* trailing null */
- name_len *= 2;
- } else {
- name_len = copy_path_name(pSMB->fileName, fileName);
- }
- pSMB->attr = cpu_to_le16(dos_attrs);
- pSMB->BufferFormat = 0x04;
- inc_rfc1001_len(pSMB, name_len + 1);
- pSMB->ByteCount = cpu_to_le16(name_len + 1);
- rc = SendReceive(xid, tcon->ses, (struct smb_hdr *) pSMB,
- (struct smb_hdr *) pSMBr, &bytes_returned, 0);
- if (rc)
- cifs_dbg(FYI, "Error in LegacySetAttr = %d\n", rc);
-
- cifs_buf_release(pSMB);
-
- if (rc == -EAGAIN)
- goto SetAttrLgcyRetry;
-
- return rc;
-}
-#endif /* temporarily unneeded SetAttr legacy function */
-
static void
cifs_fill_unix_set_info(FILE_UNIX_BASIC_INFO *data_offset,
const struct cifs_unix_set_info_args *args)
diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c
index eec8a2052da2..121d8b4535b0 100644
--- a/fs/cifs/connect.c
+++ b/fs/cifs/connect.c
@@ -62,9 +62,7 @@
#include "dfs_cache.h"
#endif
#include "fs_context.h"
-#ifdef CONFIG_CIFS_SWN_UPCALL
#include "cifs_swn.h"
-#endif
extern mempool_t *cifs_req_poolp;
extern bool disable_legacy_dialects;
@@ -87,7 +85,6 @@ static void cifs_prune_tlinks(struct work_struct *work);
*
* This should be called with server->srv_mutex held.
*/
-#ifdef CONFIG_CIFS_DFS_UPCALL
static int reconn_set_ipaddr_from_hostname(struct TCP_Server_Info *server)
{
int rc;
@@ -124,6 +121,7 @@ static int reconn_set_ipaddr_from_hostname(struct TCP_Server_Info *server)
return !rc ? -1 : 0;
}
+#ifdef CONFIG_CIFS_DFS_UPCALL
/* These functions must be called with server->srv_mutex held */
static void reconn_set_next_dfs_target(struct TCP_Server_Info *server,
struct cifs_sb_info *cifs_sb,
@@ -314,25 +312,34 @@ cifs_reconnect(struct TCP_Server_Info *server)
mutex_lock(&server->srv_mutex);
-#ifdef CONFIG_CIFS_SWN_UPCALL
- if (server->use_swn_dstaddr) {
- server->dstaddr = server->swn_dstaddr;
- } else {
-#endif
+ if (!cifs_swn_set_server_dstaddr(server)) {
#ifdef CONFIG_CIFS_DFS_UPCALL
+ if (cifs_sb && cifs_sb->origin_fullpath)
/*
* Set up next DFS target server (if any) for reconnect. If DFS
* feature is disabled, then we will retry last server we
* connected to before.
*/
reconn_set_next_dfs_target(server, cifs_sb, &tgt_list, &tgt_it);
+ else {
#endif
+ /*
+ * Resolve the hostname again to make sure that IP address is up-to-date.
+ */
+ rc = reconn_set_ipaddr_from_hostname(server);
+ if (rc) {
+ cifs_dbg(FYI, "%s: failed to resolve hostname: %d\n",
+ __func__, rc);
+ }
-#ifdef CONFIG_CIFS_SWN_UPCALL
+#ifdef CONFIG_CIFS_DFS_UPCALL
}
#endif
+
+ }
+
if (cifs_rdma_enabled(server))
rc = smbd_reconnect(server);
else
@@ -348,9 +355,7 @@ cifs_reconnect(struct TCP_Server_Info *server)
if (server->tcpStatus != CifsExiting)
server->tcpStatus = CifsNeedNegotiate;
spin_unlock(&GlobalMid_Lock);
-#ifdef CONFIG_CIFS_SWN_UPCALL
- server->use_swn_dstaddr = false;
-#endif
+ cifs_swn_reset_server_dstaddr(server);
mutex_unlock(&server->srv_mutex);
}
} while (server->tcpStatus == CifsNeedReconnect);
@@ -415,10 +420,8 @@ cifs_echo_request(struct work_struct *work)
cifs_dbg(FYI, "Unable to send echo request to server: %s\n",
server->hostname);
-#ifdef CONFIG_CIFS_SWN_UPCALL
/* Check witness registrations */
cifs_swn_check();
-#endif
requeue_echo:
queue_delayed_work(cifsiod_wq, &server->echo, server->echo_interval);
@@ -1775,9 +1778,7 @@ cifs_set_cifscreds(struct smb3_fs_context *ctx, struct cifs_ses *ses)
* for the request.
*/
if (is_domain && ses->domainName) {
- ctx->domainname = kstrndup(ses->domainName,
- strlen(ses->domainName),
- GFP_KERNEL);
+ ctx->domainname = kstrdup(ses->domainName, GFP_KERNEL);
if (!ctx->domainname) {
cifs_dbg(FYI, "Unable to allocate %zd bytes for domain\n",
len);
@@ -1994,7 +1995,6 @@ cifs_put_tcon(struct cifs_tcon *tcon)
return;
}
-#ifdef CONFIG_CIFS_SWN_UPCALL
if (tcon->use_witness) {
int rc;
@@ -2004,7 +2004,6 @@ cifs_put_tcon(struct cifs_tcon *tcon)
__func__, rc);
}
}
-#endif
list_del_init(&tcon->tcon_list);
spin_unlock(&cifs_tcp_ses_lock);
@@ -2166,9 +2165,9 @@ cifs_get_tcon(struct cifs_ses *ses, struct smb3_fs_context *ctx)
}
tcon->use_resilient = true;
}
-#ifdef CONFIG_CIFS_SWN_UPCALL
+
tcon->use_witness = false;
- if (ctx->witness) {
+ if (IS_ENABLED(CONFIG_CIFS_SWN_UPCALL) && ctx->witness) {
if (ses->server->vals->protocol_id >= SMB30_PROT_ID) {
if (tcon->capabilities & SMB2_SHARE_CAP_CLUSTER) {
/*
@@ -2194,7 +2193,6 @@ cifs_get_tcon(struct cifs_ses *ses, struct smb3_fs_context *ctx)
goto out_fail;
}
}
-#endif
/* If the user really knows what they are doing they can override */
if (tcon->share_flags & SMB2_SHAREFLAG_NO_CACHING) {
@@ -3411,8 +3409,7 @@ int cifs_mount(struct cifs_sb_info *cifs_sb, struct smb3_fs_context *ctx)
goto error;
}
/* Save mount options */
- mntdata = kstrndup(cifs_sb->ctx->mount_options,
- strlen(cifs_sb->ctx->mount_options), GFP_KERNEL);
+ mntdata = kstrdup(cifs_sb->ctx->mount_options, GFP_KERNEL);
if (!mntdata) {
rc = -ENOMEM;
goto error;
@@ -3485,7 +3482,7 @@ int cifs_mount(struct cifs_sb_info *cifs_sb, struct smb3_fs_context *ctx)
* links, the prefix path is included in both and may be changed during reconnect. See
* cifs_tree_connect().
*/
- cifs_sb->origin_fullpath = kstrndup(full_path, strlen(full_path), GFP_KERNEL);
+ cifs_sb->origin_fullpath = kstrdup(full_path, GFP_KERNEL);
if (!cifs_sb->origin_fullpath) {
rc = -ENOMEM;
goto error;
@@ -3862,9 +3859,7 @@ cifs_construct_tcon(struct cifs_sb_info *cifs_sb, kuid_t fsuid)
ctx->sectype = master_tcon->ses->sectype;
ctx->sign = master_tcon->ses->sign;
ctx->seal = master_tcon->seal;
-#ifdef CONFIG_CIFS_SWN_UPCALL
ctx->witness = master_tcon->use_witness;
-#endif
rc = cifs_set_vol_auth(ctx, master_tcon->ses);
if (rc) {
diff --git a/fs/cifs/dfs_cache.c b/fs/cifs/dfs_cache.c
index 098b4bc8da59..b1fa30fefe1f 100644
--- a/fs/cifs/dfs_cache.c
+++ b/fs/cifs/dfs_cache.c
@@ -81,23 +81,24 @@ static void refresh_cache_worker(struct work_struct *work);
static DECLARE_DELAYED_WORK(refresh_task, refresh_cache_worker);
-static int get_normalized_path(const char *path, char **npath)
+static int get_normalized_path(const char *path, const char **npath)
{
if (!path || strlen(path) < 3 || (*path != '\\' && *path != '/'))
return -EINVAL;
if (*path == '\\') {
- *npath = (char *)path;
+ *npath = path;
} else {
- *npath = kstrndup(path, strlen(path), GFP_KERNEL);
- if (!*npath)
+ char *s = kstrdup(path, GFP_KERNEL);
+ if (!s)
return -ENOMEM;
- convert_delimiter(*npath, '\\');
+ convert_delimiter(s, '\\');
+ *npath = s;
}
return 0;
}
-static inline void free_normalized_path(const char *path, char *npath)
+static inline void free_normalized_path(const char *path, const char *npath)
{
if (path != npath)
kfree(npath);
@@ -358,7 +359,7 @@ static struct cache_dfs_tgt *alloc_target(const char *name, int path_consumed)
t = kmalloc(sizeof(*t), GFP_ATOMIC);
if (!t)
return ERR_PTR(-ENOMEM);
- t->name = kstrndup(name, strlen(name), GFP_ATOMIC);
+ t->name = kstrdup(name, GFP_ATOMIC);
if (!t->name) {
kfree(t);
return ERR_PTR(-ENOMEM);
@@ -419,7 +420,7 @@ static struct cache_entry *alloc_cache_entry(const char *path,
if (!ce)
return ERR_PTR(-ENOMEM);
- ce->path = kstrndup(path, strlen(path), GFP_KERNEL);
+ ce->path = kstrdup(path, GFP_KERNEL);
if (!ce->path) {
kmem_cache_free(cache_slab, ce);
return ERR_PTR(-ENOMEM);
@@ -531,7 +532,7 @@ static struct cache_entry *lookup_cache_entry(const char *path, unsigned int *ha
char *s, *e;
char sep;
- npath = kstrndup(path, strlen(path), GFP_KERNEL);
+ npath = kstrdup(path, GFP_KERNEL);
if (!npath)
return ERR_PTR(-ENOMEM);
@@ -641,7 +642,7 @@ static int __update_cache_entry(const char *path,
if (ce->tgthint) {
s = ce->tgthint->name;
- th = kstrndup(s, strlen(s), GFP_ATOMIC);
+ th = kstrdup(s, GFP_ATOMIC);
if (!th)
return -ENOMEM;
}
@@ -786,11 +787,11 @@ static int setup_referral(const char *path, struct cache_entry *ce,
memset(ref, 0, sizeof(*ref));
- ref->path_name = kstrndup(path, strlen(path), GFP_ATOMIC);
+ ref->path_name = kstrdup(path, GFP_ATOMIC);
if (!ref->path_name)
return -ENOMEM;
- ref->node_name = kstrndup(target, strlen(target), GFP_ATOMIC);
+ ref->node_name = kstrdup(target, GFP_ATOMIC);
if (!ref->node_name) {
rc = -ENOMEM;
goto err_free_path;
@@ -828,7 +829,7 @@ static int get_targets(struct cache_entry *ce, struct dfs_cache_tgt_list *tl)
goto err_free_it;
}
- it->it_name = kstrndup(t->name, strlen(t->name), GFP_ATOMIC);
+ it->it_name = kstrdup(t->name, GFP_ATOMIC);
if (!it->it_name) {
kfree(it);
rc = -ENOMEM;
@@ -882,7 +883,7 @@ int dfs_cache_find(const unsigned int xid, struct cifs_ses *ses,
struct dfs_cache_tgt_list *tgt_list)
{
int rc;
- char *npath;
+ const char *npath;
struct cache_entry *ce;
rc = get_normalized_path(path, &npath);
@@ -936,7 +937,7 @@ int dfs_cache_noreq_find(const char *path, struct dfs_info3_param *ref,
struct dfs_cache_tgt_list *tgt_list)
{
int rc;
- char *npath;
+ const char *npath;
struct cache_entry *ce;
rc = get_normalized_path(path, &npath);
@@ -991,7 +992,7 @@ int dfs_cache_update_tgthint(const unsigned int xid, struct cifs_ses *ses,
const struct dfs_cache_tgt_iterator *it)
{
int rc;
- char *npath;
+ const char *npath;
struct cache_entry *ce;
struct cache_dfs_tgt *t;
@@ -1053,7 +1054,7 @@ int dfs_cache_noreq_update_tgthint(const char *path,
const struct dfs_cache_tgt_iterator *it)
{
int rc;
- char *npath;
+ const char *npath;
struct cache_entry *ce;
struct cache_dfs_tgt *t;
@@ -1111,7 +1112,7 @@ int dfs_cache_get_tgt_referral(const char *path,
struct dfs_info3_param *ref)
{
int rc;
- char *npath;
+ const char *npath;
struct cache_entry *ce;
if (!it || !ref)
@@ -1166,7 +1167,7 @@ int dfs_cache_add_vol(char *mntdata, struct smb3_fs_context *ctx, const char *fu
if (!vi)
return -ENOMEM;
- vi->fullpath = kstrndup(fullpath, strlen(fullpath), GFP_KERNEL);
+ vi->fullpath = kstrdup(fullpath, GFP_KERNEL);
if (!vi->fullpath) {
rc = -ENOMEM;
goto err_free_vi;
@@ -1484,7 +1485,7 @@ static int refresh_tcon(struct vol_info *vi, struct cifs_tcon *tcon)
{
int rc = 0;
unsigned int xid;
- char *path, *npath;
+ const char *path, *npath;
struct cache_entry *ce;
struct cifs_ses *root_ses = NULL, *ses;
struct dfs_info3_param *refs = NULL;
diff --git a/fs/cifs/dir.c b/fs/cifs/dir.c
index a3fb81e0ba17..c85aff838305 100644
--- a/fs/cifs/dir.c
+++ b/fs/cifs/dir.c
@@ -78,31 +78,31 @@ cifs_build_path_to_root(struct smb3_fs_context *ctx, struct cifs_sb_info *cifs_s
}
/* Note: caller must free return buffer */
-char *
-build_path_from_dentry(struct dentry *direntry)
+const char *
+build_path_from_dentry(struct dentry *direntry, void *page)
{
struct cifs_sb_info *cifs_sb = CIFS_SB(direntry->d_sb);
struct cifs_tcon *tcon = cifs_sb_master_tcon(cifs_sb);
bool prefix = tcon->Flags & SMB_SHARE_IS_IN_DFS;
- return build_path_from_dentry_optional_prefix(direntry,
+ return build_path_from_dentry_optional_prefix(direntry, page,
prefix);
}
char *
-build_path_from_dentry_optional_prefix(struct dentry *direntry, bool prefix)
+build_path_from_dentry_optional_prefix(struct dentry *direntry, void *page,
+ bool prefix)
{
- struct dentry *temp;
- int namelen;
int dfsplen;
int pplen = 0;
- char *full_path;
- char dirsep;
struct cifs_sb_info *cifs_sb = CIFS_SB(direntry->d_sb);
struct cifs_tcon *tcon = cifs_sb_master_tcon(cifs_sb);
- unsigned seq;
+ char dirsep = CIFS_DIR_SEP(cifs_sb);
+ char *s;
+
+ if (unlikely(!page))
+ return ERR_PTR(-ENOMEM);
- dirsep = CIFS_DIR_SEP(cifs_sb);
if (prefix)
dfsplen = strnlen(tcon->treeName, MAX_TREE_SIZE + 1);
else
@@ -111,86 +111,39 @@ build_path_from_dentry_optional_prefix(struct dentry *direntry, bool prefix)
if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_USE_PREFIX_PATH)
pplen = cifs_sb->prepath ? strlen(cifs_sb->prepath) + 1 : 0;
-cifs_bp_rename_retry:
- namelen = dfsplen + pplen;
- seq = read_seqbegin(&rename_lock);
- rcu_read_lock();
- for (temp = direntry; !IS_ROOT(temp);) {
- namelen += (1 + temp->d_name.len);
- temp = temp->d_parent;
- if (temp == NULL) {
- cifs_dbg(VFS, "corrupt dentry\n");
- rcu_read_unlock();
- return NULL;
- }
- }
- rcu_read_unlock();
-
- full_path = kmalloc(namelen+1, GFP_ATOMIC);
- if (full_path == NULL)
- return full_path;
- full_path[namelen] = 0; /* trailing null */
- rcu_read_lock();
- for (temp = direntry; !IS_ROOT(temp);) {
- spin_lock(&temp->d_lock);
- namelen -= 1 + temp->d_name.len;
- if (namelen < 0) {
- spin_unlock(&temp->d_lock);
- break;
- } else {
- full_path[namelen] = dirsep;
- strncpy(full_path + namelen + 1, temp->d_name.name,
- temp->d_name.len);
- cifs_dbg(FYI, "name: %s\n", full_path + namelen);
- }
- spin_unlock(&temp->d_lock);
- temp = temp->d_parent;
- if (temp == NULL) {
- cifs_dbg(VFS, "corrupt dentry\n");
- rcu_read_unlock();
- kfree(full_path);
- return NULL;
- }
- }
- rcu_read_unlock();
- if (namelen != dfsplen + pplen || read_seqretry(&rename_lock, seq)) {
- cifs_dbg(FYI, "did not end path lookup where expected. namelen=%ddfsplen=%d\n",
- namelen, dfsplen);
- /* presumably this is only possible if racing with a rename
- of one of the parent directories (we can not lock the dentries
- above us to prevent this, but retrying should be harmless) */
- kfree(full_path);
- goto cifs_bp_rename_retry;
- }
- /* DIR_SEP already set for byte 0 / vs \ but not for
- subsequent slashes in prepath which currently must
- be entered the right way - not sure if there is an alternative
- since the '\' is a valid posix character so we can not switch
- those safely to '/' if any are found in the middle of the prepath */
- /* BB test paths to Windows with '/' in the midst of prepath */
-
+ s = dentry_path_raw(direntry, page, PAGE_SIZE);
+ if (IS_ERR(s))
+ return s;
+ if (!s[1]) // for root we want "", not "/"
+ s++;
+ if (s < (char *)page + pplen + dfsplen)
+ return ERR_PTR(-ENAMETOOLONG);
if (pplen) {
- int i;
-
cifs_dbg(FYI, "using cifs_sb prepath <%s>\n", cifs_sb->prepath);
- memcpy(full_path+dfsplen+1, cifs_sb->prepath, pplen-1);
- full_path[dfsplen] = dirsep;
- for (i = 0; i < pplen-1; i++)
- if (full_path[dfsplen+1+i] == '/')
- full_path[dfsplen+1+i] = CIFS_DIR_SEP(cifs_sb);
+ s -= pplen;
+ memcpy(s + 1, cifs_sb->prepath, pplen - 1);
+ *s = '/';
}
+ if (dirsep != '/') {
+ /* BB test paths to Windows with '/' in the midst of prepath */
+ char *p;
+ for (p = s; *p; p++)
+ if (*p == '/')
+ *p = dirsep;
+ }
if (dfsplen) {
- strncpy(full_path, tcon->treeName, dfsplen);
+ s -= dfsplen;
+ memcpy(s, tcon->treeName, dfsplen);
if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_POSIX_PATHS) {
int i;
for (i = 0; i < dfsplen; i++) {
- if (full_path[i] == '\\')
- full_path[i] = '/';
+ if (s[i] == '\\')
+ s[i] = '/';
}
}
}
- return full_path;
+ return s;
}
/*
@@ -233,7 +186,8 @@ cifs_do_create(struct inode *inode, struct dentry *direntry, unsigned int xid,
int desired_access;
struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb);
struct cifs_tcon *tcon = tlink_tcon(tlink);
- char *full_path = NULL;
+ const char *full_path;
+ void *page = alloc_dentry_path();
FILE_ALL_INFO *buf = NULL;
struct inode *newinode = NULL;
int disposition;
@@ -244,9 +198,11 @@ cifs_do_create(struct inode *inode, struct dentry *direntry, unsigned int xid,
if (tcon->ses->server->oplocks)
*oplock = REQ_OPLOCK;
- full_path = build_path_from_dentry(direntry);
- if (!full_path)
- return -ENOMEM;
+ full_path = build_path_from_dentry(direntry, page);
+ if (IS_ERR(full_path)) {
+ free_dentry_path(page);
+ return PTR_ERR(full_path);
+ }
if (tcon->unix_ext && cap_unix(tcon->ses) && !tcon->broken_posix_open &&
(CIFS_UNIX_POSIX_PATH_OPS_CAP &
@@ -418,15 +374,16 @@ cifs_create_get_file_info:
if (newinode) {
if (server->ops->set_lease_key)
server->ops->set_lease_key(newinode, fid);
- if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_DYNPERM)
- newinode->i_mode = mode;
- if ((*oplock & CIFS_CREATE_ACTION) &&
- (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SET_UID)) {
- newinode->i_uid = current_fsuid();
- if (inode->i_mode & S_ISGID)
- newinode->i_gid = inode->i_gid;
- else
- newinode->i_gid = current_fsgid();
+ if ((*oplock & CIFS_CREATE_ACTION) && S_ISREG(newinode->i_mode)) {
+ if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_DYNPERM)
+ newinode->i_mode = mode;
+ if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SET_UID) {
+ newinode->i_uid = current_fsuid();
+ if (inode->i_mode & S_ISGID)
+ newinode->i_gid = inode->i_gid;
+ else
+ newinode->i_gid = current_fsgid();
+ }
}
}
}
@@ -448,7 +405,7 @@ cifs_create_set_dentry:
out:
kfree(buf);
- kfree(full_path);
+ free_dentry_path(page);
return rc;
out_err:
@@ -619,7 +576,8 @@ int cifs_mknod(struct user_namespace *mnt_userns, struct inode *inode,
struct cifs_sb_info *cifs_sb;
struct tcon_link *tlink;
struct cifs_tcon *tcon;
- char *full_path = NULL;
+ const char *full_path;
+ void *page;
if (!old_valid_dev(device_number))
return -EINVAL;
@@ -629,13 +587,13 @@ int cifs_mknod(struct user_namespace *mnt_userns, struct inode *inode,
if (IS_ERR(tlink))
return PTR_ERR(tlink);
+ page = alloc_dentry_path();
tcon = tlink_tcon(tlink);
-
xid = get_xid();
- full_path = build_path_from_dentry(direntry);
- if (full_path == NULL) {
- rc = -ENOMEM;
+ full_path = build_path_from_dentry(direntry, page);
+ if (IS_ERR(full_path)) {
+ rc = PTR_ERR(full_path);
goto mknod_out;
}
@@ -644,7 +602,7 @@ int cifs_mknod(struct user_namespace *mnt_userns, struct inode *inode,
device_number);
mknod_out:
- kfree(full_path);
+ free_dentry_path(page);
free_xid(xid);
cifs_put_tlink(tlink);
return rc;
@@ -660,7 +618,8 @@ cifs_lookup(struct inode *parent_dir_inode, struct dentry *direntry,
struct tcon_link *tlink;
struct cifs_tcon *pTcon;
struct inode *newInode = NULL;
- char *full_path = NULL;
+ const char *full_path;
+ void *page;
xid = get_xid();
@@ -687,11 +646,13 @@ cifs_lookup(struct inode *parent_dir_inode, struct dentry *direntry,
/* can not grab the rename sem here since it would
deadlock in the cases (beginning of sys_rename itself)
in which we already have the sb rename sem */
- full_path = build_path_from_dentry(direntry);
- if (full_path == NULL) {
+ page = alloc_dentry_path();
+ full_path = build_path_from_dentry(direntry, page);
+ if (IS_ERR(full_path)) {
cifs_put_tlink(tlink);
free_xid(xid);
- return ERR_PTR(-ENOMEM);
+ free_dentry_path(page);
+ return ERR_CAST(full_path);
}
if (d_really_is_positive(direntry)) {
@@ -727,7 +688,7 @@ cifs_lookup(struct inode *parent_dir_inode, struct dentry *direntry,
}
newInode = ERR_PTR(rc);
}
- kfree(full_path);
+ free_dentry_path(page);
cifs_put_tlink(tlink);
free_xid(xid);
return d_splice_alias(newInode, direntry);
diff --git a/fs/cifs/file.c b/fs/cifs/file.c
index 26de4329d161..639c59596d4f 100644
--- a/fs/cifs/file.c
+++ b/fs/cifs/file.c
@@ -112,7 +112,7 @@ static inline int cifs_get_disposition(unsigned int flags)
return FILE_OPEN;
}
-int cifs_posix_open(char *full_path, struct inode **pinode,
+int cifs_posix_open(const char *full_path, struct inode **pinode,
struct super_block *sb, int mode, unsigned int f_flags,
__u32 *poplock, __u16 *pnetfid, unsigned int xid)
{
@@ -165,7 +165,8 @@ int cifs_posix_open(char *full_path, struct inode **pinode,
goto posix_open_ret;
}
} else {
- cifs_fattr_to_inode(*pinode, &fattr);
+ cifs_revalidate_mapping(*pinode);
+ rc = cifs_fattr_to_inode(*pinode, &fattr);
}
posix_open_ret:
@@ -174,7 +175,7 @@ posix_open_ret:
}
static int
-cifs_nt_open(char *full_path, struct inode *inode, struct cifs_sb_info *cifs_sb,
+cifs_nt_open(const char *full_path, struct inode *inode, struct cifs_sb_info *cifs_sb,
struct cifs_tcon *tcon, unsigned int f_flags, __u32 *oplock,
struct cifs_fid *fid, unsigned int xid)
{
@@ -529,7 +530,8 @@ int cifs_open(struct inode *inode, struct file *file)
struct cifs_tcon *tcon;
struct tcon_link *tlink;
struct cifsFileInfo *cfile = NULL;
- char *full_path = NULL;
+ void *page;
+ const char *full_path;
bool posix_open_ok = false;
struct cifs_fid fid;
struct cifs_pending_open open;
@@ -545,9 +547,10 @@ int cifs_open(struct inode *inode, struct file *file)
tcon = tlink_tcon(tlink);
server = tcon->ses->server;
- full_path = build_path_from_dentry(file_dentry(file));
- if (full_path == NULL) {
- rc = -ENOMEM;
+ page = alloc_dentry_path();
+ full_path = build_path_from_dentry(file_dentry(file), page);
+ if (IS_ERR(full_path)) {
+ rc = PTR_ERR(full_path);
goto out;
}
@@ -639,7 +642,7 @@ int cifs_open(struct inode *inode, struct file *file)
}
out:
- kfree(full_path);
+ free_dentry_path(page);
free_xid(xid);
cifs_put_tlink(tlink);
return rc;
@@ -688,7 +691,8 @@ cifs_reopen_file(struct cifsFileInfo *cfile, bool can_flush)
struct TCP_Server_Info *server;
struct cifsInodeInfo *cinode;
struct inode *inode;
- char *full_path = NULL;
+ void *page;
+ const char *full_path;
int desired_access;
int disposition = FILE_OPEN;
int create_options = CREATE_NOT_DIR;
@@ -698,9 +702,8 @@ cifs_reopen_file(struct cifsFileInfo *cfile, bool can_flush)
mutex_lock(&cfile->fh_mutex);
if (!cfile->invalidHandle) {
mutex_unlock(&cfile->fh_mutex);
- rc = 0;
free_xid(xid);
- return rc;
+ return 0;
}
inode = d_inode(cfile->dentry);
@@ -714,12 +717,13 @@ cifs_reopen_file(struct cifsFileInfo *cfile, bool can_flush)
* called and if the server was down that means we end up here, and we
* can never tell if the caller already has the rename_sem.
*/
- full_path = build_path_from_dentry(cfile->dentry);
- if (full_path == NULL) {
- rc = -ENOMEM;
+ page = alloc_dentry_path();
+ full_path = build_path_from_dentry(cfile->dentry, page);
+ if (IS_ERR(full_path)) {
mutex_unlock(&cfile->fh_mutex);
+ free_dentry_path(page);
free_xid(xid);
- return rc;
+ return PTR_ERR(full_path);
}
cifs_dbg(FYI, "inode = 0x%p file flags 0x%x for %s\n",
@@ -837,7 +841,7 @@ reopen_success:
cifs_relock_file(cfile);
reopen_error_exit:
- kfree(full_path);
+ free_dentry_path(page);
free_xid(xid);
return rc;
}
@@ -2068,34 +2072,31 @@ cifs_get_writable_path(struct cifs_tcon *tcon, const char *name,
int flags,
struct cifsFileInfo **ret_file)
{
- struct list_head *tmp;
struct cifsFileInfo *cfile;
- struct cifsInodeInfo *cinode;
- char *full_path;
+ void *page = alloc_dentry_path();
*ret_file = NULL;
spin_lock(&tcon->open_file_lock);
- list_for_each(tmp, &tcon->openFileList) {
- cfile = list_entry(tmp, struct cifsFileInfo,
- tlist);
- full_path = build_path_from_dentry(cfile->dentry);
- if (full_path == NULL) {
+ list_for_each_entry(cfile, &tcon->openFileList, tlist) {
+ struct cifsInodeInfo *cinode;
+ const char *full_path = build_path_from_dentry(cfile->dentry, page);
+ if (IS_ERR(full_path)) {
spin_unlock(&tcon->open_file_lock);
- return -ENOMEM;
+ free_dentry_path(page);
+ return PTR_ERR(full_path);
}
- if (strcmp(full_path, name)) {
- kfree(full_path);
+ if (strcmp(full_path, name))
continue;
- }
- kfree(full_path);
cinode = CIFS_I(d_inode(cfile->dentry));
spin_unlock(&tcon->open_file_lock);
+ free_dentry_path(page);
return cifs_get_writable_file(cinode, flags, ret_file);
}
spin_unlock(&tcon->open_file_lock);
+ free_dentry_path(page);
return -ENOENT;
}
@@ -2103,35 +2104,32 @@ int
cifs_get_readable_path(struct cifs_tcon *tcon, const char *name,
struct cifsFileInfo **ret_file)
{
- struct list_head *tmp;
struct cifsFileInfo *cfile;
- struct cifsInodeInfo *cinode;
- char *full_path;
+ void *page = alloc_dentry_path();
*ret_file = NULL;
spin_lock(&tcon->open_file_lock);
- list_for_each(tmp, &tcon->openFileList) {
- cfile = list_entry(tmp, struct cifsFileInfo,
- tlist);
- full_path = build_path_from_dentry(cfile->dentry);
- if (full_path == NULL) {
+ list_for_each_entry(cfile, &tcon->openFileList, tlist) {
+ struct cifsInodeInfo *cinode;
+ const char *full_path = build_path_from_dentry(cfile->dentry, page);
+ if (IS_ERR(full_path)) {
spin_unlock(&tcon->open_file_lock);
- return -ENOMEM;
+ free_dentry_path(page);
+ return PTR_ERR(full_path);
}
- if (strcmp(full_path, name)) {
- kfree(full_path);
+ if (strcmp(full_path, name))
continue;
- }
- kfree(full_path);
cinode = CIFS_I(d_inode(cfile->dentry));
spin_unlock(&tcon->open_file_lock);
+ free_dentry_path(page);
*ret_file = find_readable_file(cinode, 0);
return *ret_file ? 0 : -ENOENT;
}
spin_unlock(&tcon->open_file_lock);
+ free_dentry_path(page);
return -ENOENT;
}
diff --git a/fs/cifs/fs_context.c b/fs/cifs/fs_context.c
index 892f51a21278..3e0d016849e3 100644
--- a/fs/cifs/fs_context.c
+++ b/fs/cifs/fs_context.c
@@ -137,6 +137,7 @@ const struct fs_parameter_spec smb3_fs_parameters[] = {
fsparam_u32("min_enc_offload", Opt_min_enc_offload),
fsparam_u32("esize", Opt_min_enc_offload),
fsparam_u32("bsize", Opt_blocksize),
+ fsparam_u32("rasize", Opt_rasize),
fsparam_u32("rsize", Opt_rsize),
fsparam_u32("wsize", Opt_wsize),
fsparam_u32("actimeo", Opt_actimeo),
@@ -188,8 +189,8 @@ const struct fs_parameter_spec smb3_fs_parameters[] = {
{}
};
-int
-cifs_parse_security_flavors(char *value, struct smb3_fs_context *ctx)
+static int
+cifs_parse_security_flavors(struct fs_context *fc, char *value, struct smb3_fs_context *ctx)
{
substring_t args[MAX_OPT_ARGS];
@@ -203,7 +204,7 @@ cifs_parse_security_flavors(char *value, struct smb3_fs_context *ctx)
switch (match_token(value, cifs_secflavor_tokens, args)) {
case Opt_sec_krb5p:
- cifs_dbg(VFS, "sec=krb5p is not supported!\n");
+ cifs_errorf(fc, "sec=krb5p is not supported!\n");
return 1;
case Opt_sec_krb5i:
ctx->sign = true;
@@ -238,7 +239,7 @@ cifs_parse_security_flavors(char *value, struct smb3_fs_context *ctx)
ctx->nullauth = 1;
break;
default:
- cifs_dbg(VFS, "bad security option: %s\n", value);
+ cifs_errorf(fc, "bad security option: %s\n", value);
return 1;
}
@@ -254,8 +255,8 @@ static const match_table_t cifs_cacheflavor_tokens = {
{ Opt_cache_err, NULL }
};
-int
-cifs_parse_cache_flavor(char *value, struct smb3_fs_context *ctx)
+static int
+cifs_parse_cache_flavor(struct fs_context *fc, char *value, struct smb3_fs_context *ctx)
{
substring_t args[MAX_OPT_ARGS];
@@ -291,7 +292,7 @@ cifs_parse_cache_flavor(char *value, struct smb3_fs_context *ctx)
ctx->cache_rw = true;
break;
default:
- cifs_dbg(VFS, "bad cache= option: %s\n", value);
+ cifs_errorf(fc, "bad cache= option: %s\n", value);
return 1;
}
return 0;
@@ -339,7 +340,7 @@ smb3_fs_context_dup(struct smb3_fs_context *new_ctx, struct smb3_fs_context *ctx
}
static int
-cifs_parse_smb_version(char *value, struct smb3_fs_context *ctx, bool is_smb3)
+cifs_parse_smb_version(struct fs_context *fc, char *value, struct smb3_fs_context *ctx, bool is_smb3)
{
substring_t args[MAX_OPT_ARGS];
@@ -347,24 +348,24 @@ cifs_parse_smb_version(char *value, struct smb3_fs_context *ctx, bool is_smb3)
#ifdef CONFIG_CIFS_ALLOW_INSECURE_LEGACY
case Smb_1:
if (disable_legacy_dialects) {
- cifs_dbg(VFS, "mount with legacy dialect disabled\n");
+ cifs_errorf(fc, "mount with legacy dialect disabled\n");
return 1;
}
if (is_smb3) {
- cifs_dbg(VFS, "vers=1.0 (cifs) not permitted when mounting with smb3\n");
+ cifs_errorf(fc, "vers=1.0 (cifs) not permitted when mounting with smb3\n");
return 1;
}
- cifs_dbg(VFS, "Use of the less secure dialect vers=1.0 is not recommended unless required for access to very old servers\n");
+ cifs_errorf(fc, "Use of the less secure dialect vers=1.0 is not recommended unless required for access to very old servers\n");
ctx->ops = &smb1_operations;
ctx->vals = &smb1_values;
break;
case Smb_20:
if (disable_legacy_dialects) {
- cifs_dbg(VFS, "mount with legacy dialect disabled\n");
+ cifs_errorf(fc, "mount with legacy dialect disabled\n");
return 1;
}
if (is_smb3) {
- cifs_dbg(VFS, "vers=2.0 not permitted when mounting with smb3\n");
+ cifs_errorf(fc, "vers=2.0 not permitted when mounting with smb3\n");
return 1;
}
ctx->ops = &smb20_operations;
@@ -372,10 +373,10 @@ cifs_parse_smb_version(char *value, struct smb3_fs_context *ctx, bool is_smb3)
break;
#else
case Smb_1:
- cifs_dbg(VFS, "vers=1.0 (cifs) mount not permitted when legacy dialects disabled\n");
+ cifs_errorf(fc, "vers=1.0 (cifs) mount not permitted when legacy dialects disabled\n");
return 1;
case Smb_20:
- cifs_dbg(VFS, "vers=2.0 mount not permitted when legacy dialects disabled\n");
+ cifs_errorf(fc, "vers=2.0 mount not permitted when legacy dialects disabled\n");
return 1;
#endif /* CIFS_ALLOW_INSECURE_LEGACY */
case Smb_21:
@@ -403,7 +404,7 @@ cifs_parse_smb_version(char *value, struct smb3_fs_context *ctx, bool is_smb3)
ctx->vals = &smbdefault_values;
break;
default:
- cifs_dbg(VFS, "Unknown vers= option specified: %s\n", value);
+ cifs_errorf(fc, "Unknown vers= option specified: %s\n", value);
return 1;
}
return 0;
@@ -430,7 +431,7 @@ int smb3_parse_opt(const char *options, const char *key, char **val)
if (nval == p)
continue;
*nval++ = 0;
- *val = kstrndup(nval, strlen(nval), GFP_KERNEL);
+ *val = kstrdup(nval, GFP_KERNEL);
rc = !*val ? -ENOMEM : 0;
goto out;
}
@@ -588,14 +589,14 @@ static int smb3_fs_context_validate(struct fs_context *fc)
struct smb3_fs_context *ctx = smb3_fc2context(fc);
if (ctx->rdma && ctx->vals->protocol_id < SMB30_PROT_ID) {
- cifs_dbg(VFS, "SMB Direct requires Version >=3.0\n");
+ cifs_errorf(fc, "SMB Direct requires Version >=3.0\n");
return -EOPNOTSUPP;
}
#ifndef CONFIG_KEYS
/* Muliuser mounts require CONFIG_KEYS support */
if (ctx->multiuser) {
- cifs_dbg(VFS, "Multiuser mounts require kernels with CONFIG_KEYS enabled\n");
+ cifs_errorf(fc, "Multiuser mounts require kernels with CONFIG_KEYS enabled\n");
return -1;
}
#endif
@@ -605,13 +606,13 @@ static int smb3_fs_context_validate(struct fs_context *fc)
if (!ctx->UNC) {
- cifs_dbg(VFS, "CIFS mount error: No usable UNC path provided in device string!\n");
+ cifs_errorf(fc, "CIFS mount error: No usable UNC path provided in device string!\n");
return -1;
}
/* make sure UNC has a share name */
if (strlen(ctx->UNC) < 3 || !strchr(ctx->UNC + 3, '\\')) {
- cifs_dbg(VFS, "Malformed UNC. Unable to find share name.\n");
+ cifs_errorf(fc, "Malformed UNC. Unable to find share name.\n");
return -ENOENT;
}
@@ -684,49 +685,50 @@ static void smb3_fs_context_free(struct fs_context *fc)
* Compare the old and new proposed context during reconfigure
* and check if the changes are compatible.
*/
-static int smb3_verify_reconfigure_ctx(struct smb3_fs_context *new_ctx,
+static int smb3_verify_reconfigure_ctx(struct fs_context *fc,
+ struct smb3_fs_context *new_ctx,
struct smb3_fs_context *old_ctx)
{
if (new_ctx->posix_paths != old_ctx->posix_paths) {
- cifs_dbg(VFS, "can not change posixpaths during remount\n");
+ cifs_errorf(fc, "can not change posixpaths during remount\n");
return -EINVAL;
}
if (new_ctx->sectype != old_ctx->sectype) {
- cifs_dbg(VFS, "can not change sec during remount\n");
+ cifs_errorf(fc, "can not change sec during remount\n");
return -EINVAL;
}
if (new_ctx->multiuser != old_ctx->multiuser) {
- cifs_dbg(VFS, "can not change multiuser during remount\n");
+ cifs_errorf(fc, "can not change multiuser during remount\n");
return -EINVAL;
}
if (new_ctx->UNC &&
(!old_ctx->UNC || strcmp(new_ctx->UNC, old_ctx->UNC))) {
- cifs_dbg(VFS, "can not change UNC during remount\n");
+ cifs_errorf(fc, "can not change UNC during remount\n");
return -EINVAL;
}
if (new_ctx->username &&
(!old_ctx->username || strcmp(new_ctx->username, old_ctx->username))) {
- cifs_dbg(VFS, "can not change username during remount\n");
+ cifs_errorf(fc, "can not change username during remount\n");
return -EINVAL;
}
if (new_ctx->password &&
(!old_ctx->password || strcmp(new_ctx->password, old_ctx->password))) {
- cifs_dbg(VFS, "can not change password during remount\n");
+ cifs_errorf(fc, "can not change password during remount\n");
return -EINVAL;
}
if (new_ctx->domainname &&
(!old_ctx->domainname || strcmp(new_ctx->domainname, old_ctx->domainname))) {
- cifs_dbg(VFS, "can not change domainname during remount\n");
+ cifs_errorf(fc, "can not change domainname during remount\n");
return -EINVAL;
}
if (new_ctx->nodename &&
(!old_ctx->nodename || strcmp(new_ctx->nodename, old_ctx->nodename))) {
- cifs_dbg(VFS, "can not change nodename during remount\n");
+ cifs_errorf(fc, "can not change nodename during remount\n");
return -EINVAL;
}
if (new_ctx->iocharset &&
(!old_ctx->iocharset || strcmp(new_ctx->iocharset, old_ctx->iocharset))) {
- cifs_dbg(VFS, "can not change iocharset during remount\n");
+ cifs_errorf(fc, "can not change iocharset during remount\n");
return -EINVAL;
}
@@ -747,7 +749,7 @@ static int smb3_reconfigure(struct fs_context *fc)
struct cifs_sb_info *cifs_sb = CIFS_SB(root->d_sb);
int rc;
- rc = smb3_verify_reconfigure_ctx(ctx, cifs_sb->ctx);
+ rc = smb3_verify_reconfigure_ctx(fc, ctx, cifs_sb->ctx);
if (rc)
return rc;
@@ -933,13 +935,33 @@ static int smb3_fs_context_parse_param(struct fs_context *fc,
*/
if ((result.uint_32 < CIFS_MAX_MSGSIZE) ||
(result.uint_32 > (4 * SMB3_DEFAULT_IOSIZE))) {
- cifs_dbg(VFS, "%s: Invalid blocksize\n",
+ cifs_errorf(fc, "%s: Invalid blocksize\n",
__func__);
goto cifs_parse_mount_err;
}
ctx->bsize = result.uint_32;
ctx->got_bsize = true;
break;
+ case Opt_rasize:
+ /*
+ * readahead size realistically should never need to be
+ * less than 1M (CIFS_DEFAULT_IOSIZE) or greater than 32M
+ * (perhaps an exception should be considered in the
+ * for the case of a large number of channels
+ * when multichannel is negotiated) since that would lead
+ * to plenty of parallel I/O in flight to the server.
+ * Note that smaller read ahead sizes would
+ * hurt performance of common tools like cp and scp
+ * which often trigger sequential i/o with read ahead
+ */
+ if ((result.uint_32 > (8 * SMB3_DEFAULT_IOSIZE)) ||
+ (result.uint_32 < CIFS_DEFAULT_IOSIZE)) {
+ cifs_errorf(fc, "%s: Invalid rasize %d vs. %d\n",
+ __func__, result.uint_32, SMB3_DEFAULT_IOSIZE);
+ goto cifs_parse_mount_err;
+ }
+ ctx->rasize = result.uint_32;
+ break;
case Opt_rsize:
ctx->rsize = result.uint_32;
ctx->got_rsize = true;
@@ -951,25 +973,25 @@ static int smb3_fs_context_parse_param(struct fs_context *fc,
case Opt_acregmax:
ctx->acregmax = HZ * result.uint_32;
if (ctx->acregmax > CIFS_MAX_ACTIMEO) {
- cifs_dbg(VFS, "acregmax too large\n");
+ cifs_errorf(fc, "acregmax too large\n");
goto cifs_parse_mount_err;
}
break;
case Opt_acdirmax:
ctx->acdirmax = HZ * result.uint_32;
if (ctx->acdirmax > CIFS_MAX_ACTIMEO) {
- cifs_dbg(VFS, "acdirmax too large\n");
+ cifs_errorf(fc, "acdirmax too large\n");
goto cifs_parse_mount_err;
}
break;
case Opt_actimeo:
if (HZ * result.uint_32 > CIFS_MAX_ACTIMEO) {
- cifs_dbg(VFS, "timeout too large\n");
+ cifs_errorf(fc, "timeout too large\n");
goto cifs_parse_mount_err;
}
if ((ctx->acdirmax != CIFS_DEF_ACTIMEO) ||
(ctx->acregmax != CIFS_DEF_ACTIMEO)) {
- cifs_dbg(VFS, "actimeo ignored since acregmax or acdirmax specified\n");
+ cifs_errorf(fc, "actimeo ignored since acregmax or acdirmax specified\n");
break;
}
ctx->acdirmax = ctx->acregmax = HZ * result.uint_32;
@@ -982,7 +1004,7 @@ static int smb3_fs_context_parse_param(struct fs_context *fc,
break;
case Opt_max_credits:
if (result.uint_32 < 20 || result.uint_32 > 60000) {
- cifs_dbg(VFS, "%s: Invalid max_credits value\n",
+ cifs_errorf(fc, "%s: Invalid max_credits value\n",
__func__);
goto cifs_parse_mount_err;
}
@@ -990,7 +1012,7 @@ static int smb3_fs_context_parse_param(struct fs_context *fc,
break;
case Opt_max_channels:
if (result.uint_32 < 1 || result.uint_32 > CIFS_MAX_CHANNELS) {
- cifs_dbg(VFS, "%s: Invalid max_channels value, needs to be 1-%d\n",
+ cifs_errorf(fc, "%s: Invalid max_channels value, needs to be 1-%d\n",
__func__, CIFS_MAX_CHANNELS);
goto cifs_parse_mount_err;
}
@@ -999,7 +1021,7 @@ static int smb3_fs_context_parse_param(struct fs_context *fc,
case Opt_handletimeout:
ctx->handle_timeout = result.uint_32;
if (ctx->handle_timeout > SMB3_MAX_HANDLE_TIMEOUT) {
- cifs_dbg(VFS, "Invalid handle cache timeout, longer than 16 minutes\n");
+ cifs_errorf(fc, "Invalid handle cache timeout, longer than 16 minutes\n");
goto cifs_parse_mount_err;
}
break;
@@ -1010,23 +1032,23 @@ static int smb3_fs_context_parse_param(struct fs_context *fc,
case 0:
break;
case -ENOMEM:
- cifs_dbg(VFS, "Unable to allocate memory for devname\n");
+ cifs_errorf(fc, "Unable to allocate memory for devname\n");
goto cifs_parse_mount_err;
case -EINVAL:
- cifs_dbg(VFS, "Malformed UNC in devname\n");
+ cifs_errorf(fc, "Malformed UNC in devname\n");
goto cifs_parse_mount_err;
default:
- cifs_dbg(VFS, "Unknown error parsing devname\n");
+ cifs_errorf(fc, "Unknown error parsing devname\n");
goto cifs_parse_mount_err;
}
ctx->source = kstrdup(param->string, GFP_KERNEL);
if (ctx->source == NULL) {
- cifs_dbg(VFS, "OOM when copying UNC string\n");
+ cifs_errorf(fc, "OOM when copying UNC string\n");
goto cifs_parse_mount_err;
}
fc->source = kstrdup(param->string, GFP_KERNEL);
if (fc->source == NULL) {
- cifs_dbg(VFS, "OOM when copying UNC string\n");
+ cifs_errorf(fc, "OOM when copying UNC string\n");
goto cifs_parse_mount_err;
}
break;
@@ -1046,7 +1068,7 @@ static int smb3_fs_context_parse_param(struct fs_context *fc,
}
ctx->username = kstrdup(param->string, GFP_KERNEL);
if (ctx->username == NULL) {
- cifs_dbg(VFS, "OOM when copying username string\n");
+ cifs_errorf(fc, "OOM when copying username string\n");
goto cifs_parse_mount_err;
}
break;
@@ -1058,7 +1080,7 @@ static int smb3_fs_context_parse_param(struct fs_context *fc,
ctx->password = kstrdup(param->string, GFP_KERNEL);
if (ctx->password == NULL) {
- cifs_dbg(VFS, "OOM when copying password string\n");
+ cifs_errorf(fc, "OOM when copying password string\n");
goto cifs_parse_mount_err;
}
break;
@@ -1085,7 +1107,7 @@ static int smb3_fs_context_parse_param(struct fs_context *fc,
kfree(ctx->domainname);
ctx->domainname = kstrdup(param->string, GFP_KERNEL);
if (ctx->domainname == NULL) {
- cifs_dbg(VFS, "OOM when copying domainname string\n");
+ cifs_errorf(fc, "OOM when copying domainname string\n");
goto cifs_parse_mount_err;
}
cifs_dbg(FYI, "Domain name set\n");
@@ -1109,7 +1131,7 @@ static int smb3_fs_context_parse_param(struct fs_context *fc,
kfree(ctx->iocharset);
ctx->iocharset = kstrdup(param->string, GFP_KERNEL);
if (ctx->iocharset == NULL) {
- cifs_dbg(VFS, "OOM when copying iocharset string\n");
+ cifs_errorf(fc, "OOM when copying iocharset string\n");
goto cifs_parse_mount_err;
}
}
@@ -1175,30 +1197,32 @@ static int smb3_fs_context_parse_param(struct fs_context *fc,
goto cifs_parse_mount_err;
case Opt_vers:
/* protocol version (dialect) */
- if (cifs_parse_smb_version(param->string, ctx, is_smb3) != 0)
+ if (cifs_parse_smb_version(fc, param->string, ctx, is_smb3) != 0)
goto cifs_parse_mount_err;
ctx->got_version = true;
break;
case Opt_sec:
- if (cifs_parse_security_flavors(param->string, ctx) != 0)
+ if (cifs_parse_security_flavors(fc, param->string, ctx) != 0)
goto cifs_parse_mount_err;
break;
case Opt_cache:
- if (cifs_parse_cache_flavor(param->string, ctx) != 0)
+ if (cifs_parse_cache_flavor(fc, param->string, ctx) != 0)
goto cifs_parse_mount_err;
break;
case Opt_witness:
#ifndef CONFIG_CIFS_SWN_UPCALL
- cifs_dbg(VFS, "Witness support needs CONFIG_CIFS_SWN_UPCALL config option\n");
+ cifs_errorf(fc, "Witness support needs CONFIG_CIFS_SWN_UPCALL config option\n");
goto cifs_parse_mount_err;
#endif
ctx->witness = true;
pr_warn_once("Witness protocol support is experimental\n");
break;
case Opt_rootfs:
-#ifdef CONFIG_CIFS_ROOT
- ctx->rootfs = true;
+#ifndef CONFIG_CIFS_ROOT
+ cifs_dbg(VFS, "rootfs support requires CONFIG_CIFS_ROOT config option\n");
+ goto cifs_parse_mount_err;
#endif
+ ctx->rootfs = true;
break;
case Opt_posixpaths:
if (result.negated)
@@ -1288,7 +1312,7 @@ static int smb3_fs_context_parse_param(struct fs_context *fc,
break;
case Opt_fsc:
#ifndef CONFIG_CIFS_FSCACHE
- cifs_dbg(VFS, "FS-Cache support needs CONFIG_CIFS_FSCACHE kernel config option set\n");
+ cifs_errorf(fc, "FS-Cache support needs CONFIG_CIFS_FSCACHE kernel config option set\n");
goto cifs_parse_mount_err;
#endif
ctx->fsc = true;
@@ -1309,15 +1333,13 @@ static int smb3_fs_context_parse_param(struct fs_context *fc,
if (result.negated) {
ctx->nopersistent = true;
if (ctx->persistent) {
- cifs_dbg(VFS,
- "persistenthandles mount options conflict\n");
+ cifs_errorf(fc, "persistenthandles mount options conflict\n");
goto cifs_parse_mount_err;
}
} else {
ctx->persistent = true;
if ((ctx->nopersistent) || (ctx->resilient)) {
- cifs_dbg(VFS,
- "persistenthandles mount options conflict\n");
+ cifs_errorf(fc, "persistenthandles mount options conflict\n");
goto cifs_parse_mount_err;
}
}
@@ -1328,8 +1350,7 @@ static int smb3_fs_context_parse_param(struct fs_context *fc,
} else {
ctx->resilient = true;
if (ctx->persistent) {
- cifs_dbg(VFS,
- "persistenthandles mount options conflict\n");
+ cifs_errorf(fc, "persistenthandles mount options conflict\n");
goto cifs_parse_mount_err;
}
}
@@ -1377,7 +1398,9 @@ int smb3_init_fs_context(struct fs_context *fc)
ctx->cred_uid = current_uid();
ctx->linux_uid = current_uid();
ctx->linux_gid = current_gid();
- ctx->bsize = 1024 * 1024; /* can improve cp performance significantly */
+ /* By default 4MB read ahead size, 1MB block size */
+ ctx->bsize = CIFS_DEFAULT_IOSIZE; /* can improve cp performance significantly */
+ ctx->rasize = 0; /* 0 = use default (ie negotiated rsize) for read ahead pages */
/*
* default to SFM style remapping of seven reserved characters
diff --git a/fs/cifs/fs_context.h b/fs/cifs/fs_context.h
index 87dd1f7168f2..2a71c8e411ac 100644
--- a/fs/cifs/fs_context.h
+++ b/fs/cifs/fs_context.h
@@ -13,7 +13,12 @@
#include <linux/parser.h>
#include <linux/fs_parser.h>
-#define cifs_invalf(fc, fmt, ...) invalf(fc, fmt, ## __VA_ARGS__)
+/* Log errors in fs_context (new mount api) but also in dmesg (old style) */
+#define cifs_errorf(fc, fmt, ...) \
+ do { \
+ errorf(fc, fmt, ## __VA_ARGS__); \
+ cifs_dbg(VFS, fmt, ## __VA_ARGS__); \
+ } while (0)
enum smb_version {
Smb_1 = 1,
@@ -115,6 +120,7 @@ enum cifs_param {
Opt_dirmode,
Opt_min_enc_offload,
Opt_blocksize,
+ Opt_rasize,
Opt_rsize,
Opt_wsize,
Opt_actimeo,
@@ -230,6 +236,7 @@ struct smb3_fs_context {
/* reuse existing guid for multichannel */
u8 client_guid[SMB2_CLIENT_GUID_SIZE];
unsigned int bsize;
+ unsigned int rasize;
unsigned int rsize;
unsigned int wsize;
unsigned int min_offload;
@@ -257,10 +264,6 @@ struct smb3_fs_context {
extern const struct fs_parameter_spec smb3_fs_parameters[];
-extern int cifs_parse_cache_flavor(char *value,
- struct smb3_fs_context *ctx);
-extern int cifs_parse_security_flavors(char *value,
- struct smb3_fs_context *ctx);
extern int smb3_init_fs_context(struct fs_context *fc);
extern void smb3_cleanup_fs_context_contents(struct smb3_fs_context *ctx);
extern void smb3_cleanup_fs_context(struct smb3_fs_context *ctx);
diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c
index 7c61bc9573c0..002d864b8f7b 100644
--- a/fs/cifs/inode.c
+++ b/fs/cifs/inode.c
@@ -157,12 +157,18 @@ cifs_nlink_fattr_to_inode(struct inode *inode, struct cifs_fattr *fattr)
}
/* populate an inode with info from a cifs_fattr struct */
-void
+int
cifs_fattr_to_inode(struct inode *inode, struct cifs_fattr *fattr)
{
struct cifsInodeInfo *cifs_i = CIFS_I(inode);
struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb);
+ if (!(inode->i_state & I_NEW) &&
+ unlikely(inode_wrong_type(inode, fattr->cf_mode))) {
+ CIFS_I(inode)->time = 0; /* force reval */
+ return -ESTALE;
+ }
+
cifs_revalidate_cache(inode, fattr);
spin_lock(&inode->i_lock);
@@ -219,6 +225,7 @@ cifs_fattr_to_inode(struct inode *inode, struct cifs_fattr *fattr)
inode->i_flags |= S_AUTOMOUNT;
if (inode->i_state & I_NEW)
cifs_set_ops(inode);
+ return 0;
}
void
@@ -363,7 +370,7 @@ cifs_get_file_info_unix(struct file *filp)
rc = 0;
}
- cifs_fattr_to_inode(inode, &fattr);
+ rc = cifs_fattr_to_inode(inode, &fattr);
free_xid(xid);
return rc;
}
@@ -426,14 +433,7 @@ int cifs_get_inode_info_unix(struct inode **pinode,
}
/* if filetype is different, return error */
- if (unlikely(((*pinode)->i_mode & S_IFMT) !=
- (fattr.cf_mode & S_IFMT))) {
- CIFS_I(*pinode)->time = 0; /* force reval */
- rc = -ESTALE;
- goto cgiiu_exit;
- }
-
- cifs_fattr_to_inode(*pinode, &fattr);
+ rc = cifs_fattr_to_inode(*pinode, &fattr);
}
cgiiu_exit:
@@ -783,7 +783,8 @@ cifs_get_file_info(struct file *filp)
*/
fattr.cf_uniqueid = CIFS_I(inode)->uniqueid;
fattr.cf_flags |= CIFS_FATTR_NEED_REVAL;
- cifs_fattr_to_inode(inode, &fattr);
+ /* if filetype is different, return error */
+ rc = cifs_fattr_to_inode(inode, &fattr);
cgfi_exit:
free_xid(xid);
return rc;
@@ -1100,16 +1101,8 @@ handle_mnt_opt:
rc = -ESTALE;
goto out;
}
-
/* if filetype is different, return error */
- if (unlikely(((*inode)->i_mode & S_IFMT) !=
- (fattr.cf_mode & S_IFMT))) {
- CIFS_I(*inode)->time = 0; /* force reval */
- rc = -ESTALE;
- goto out;
- }
-
- cifs_fattr_to_inode(*inode, &fattr);
+ rc = cifs_fattr_to_inode(*inode, &fattr);
}
out:
cifs_buf_release(smb1_backup_rsp_buf);
@@ -1215,14 +1208,7 @@ smb311_posix_get_inode_info(struct inode **inode,
}
/* if filetype is different, return error */
- if (unlikely(((*inode)->i_mode & S_IFMT) !=
- (fattr.cf_mode & S_IFMT))) {
- CIFS_I(*inode)->time = 0; /* force reval */
- rc = -ESTALE;
- goto out;
- }
-
- cifs_fattr_to_inode(*inode, &fattr);
+ rc = cifs_fattr_to_inode(*inode, &fattr);
}
out:
cifs_put_tlink(tlink);
@@ -1249,7 +1235,7 @@ cifs_find_inode(struct inode *inode, void *opaque)
return 0;
/* don't match inode of different type */
- if ((inode->i_mode & S_IFMT) != (fattr->cf_mode & S_IFMT))
+ if (inode_wrong_type(inode, fattr->cf_mode))
return 0;
/* if it's not a directory or has no dentries, then flag it */
@@ -1317,6 +1303,7 @@ retry_iget5_locked:
}
}
+ /* can't fail - see cifs_find_inode() */
cifs_fattr_to_inode(inode, fattr);
if (sb->s_flags & SB_NOATIME)
inode->i_flags |= S_NOATIME | S_NOCMTIME;
@@ -1408,7 +1395,7 @@ out:
int
cifs_set_file_info(struct inode *inode, struct iattr *attrs, unsigned int xid,
- char *full_path, __u32 dosattr)
+ const char *full_path, __u32 dosattr)
{
bool set_time = false;
struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb);
@@ -1609,7 +1596,8 @@ int cifs_unlink(struct inode *dir, struct dentry *dentry)
{
int rc = 0;
unsigned int xid;
- char *full_path = NULL;
+ const char *full_path;
+ void *page;
struct inode *inode = d_inode(dentry);
struct cifsInodeInfo *cifs_inode;
struct super_block *sb = dir->i_sb;
@@ -1629,6 +1617,7 @@ int cifs_unlink(struct inode *dir, struct dentry *dentry)
server = tcon->ses->server;
xid = get_xid();
+ page = alloc_dentry_path();
if (tcon->nodelete) {
rc = -EACCES;
@@ -1637,9 +1626,9 @@ int cifs_unlink(struct inode *dir, struct dentry *dentry)
/* Unlink can be called from rename so we can not take the
* sb->s_vfs_rename_mutex here */
- full_path = build_path_from_dentry(dentry);
- if (full_path == NULL) {
- rc = -ENOMEM;
+ full_path = build_path_from_dentry(dentry, page);
+ if (IS_ERR(full_path)) {
+ rc = PTR_ERR(full_path);
goto unlink_out;
}
@@ -1713,7 +1702,7 @@ out_reval:
cifs_inode = CIFS_I(dir);
CIFS_I(dir)->time = 0; /* force revalidate of dir as well */
unlink_out:
- kfree(full_path);
+ free_dentry_path(page);
kfree(attrs);
free_xid(xid);
cifs_put_tlink(tlink);
@@ -1740,6 +1729,16 @@ cifs_mkdir_qinfo(struct inode *parent, struct dentry *dentry, umode_t mode,
if (rc)
return rc;
+ if (!S_ISDIR(inode->i_mode)) {
+ /*
+ * mkdir succeeded, but another client has managed to remove the
+ * sucker and replace it with non-directory. Return success,
+ * but don't leave the child in dcache.
+ */
+ iput(inode);
+ d_drop(dentry);
+ return 0;
+ }
/*
* setting nlink not necessary except in cases where we failed to get it
* from the server or was set bogus. Also, since this is a brand new
@@ -1791,7 +1790,7 @@ cifs_mkdir_qinfo(struct inode *parent, struct dentry *dentry, umode_t mode,
}
}
d_instantiate(dentry, inode);
- return rc;
+ return 0;
}
static int
@@ -1866,7 +1865,8 @@ int cifs_mkdir(struct user_namespace *mnt_userns, struct inode *inode,
struct tcon_link *tlink;
struct cifs_tcon *tcon;
struct TCP_Server_Info *server;
- char *full_path;
+ const char *full_path;
+ void *page;
cifs_dbg(FYI, "In cifs_mkdir, mode = %04ho inode = 0x%p\n",
mode, inode);
@@ -1879,9 +1879,10 @@ int cifs_mkdir(struct user_namespace *mnt_userns, struct inode *inode,
xid = get_xid();
- full_path = build_path_from_dentry(direntry);
- if (full_path == NULL) {
- rc = -ENOMEM;
+ page = alloc_dentry_path();
+ full_path = build_path_from_dentry(direntry, page);
+ if (IS_ERR(full_path)) {
+ rc = PTR_ERR(full_path);
goto mkdir_out;
}
@@ -1924,7 +1925,7 @@ mkdir_out:
* attributes are invalid now.
*/
CIFS_I(inode)->time = 0;
- kfree(full_path);
+ free_dentry_path(page);
free_xid(xid);
cifs_put_tlink(tlink);
return rc;
@@ -1938,16 +1939,17 @@ int cifs_rmdir(struct inode *inode, struct dentry *direntry)
struct tcon_link *tlink;
struct cifs_tcon *tcon;
struct TCP_Server_Info *server;
- char *full_path = NULL;
+ const char *full_path;
+ void *page = alloc_dentry_path();
struct cifsInodeInfo *cifsInode;
cifs_dbg(FYI, "cifs_rmdir, inode = 0x%p\n", inode);
xid = get_xid();
- full_path = build_path_from_dentry(direntry);
- if (full_path == NULL) {
- rc = -ENOMEM;
+ full_path = build_path_from_dentry(direntry, page);
+ if (IS_ERR(full_path)) {
+ rc = PTR_ERR(full_path);
goto rmdir_exit;
}
@@ -1997,7 +1999,7 @@ int cifs_rmdir(struct inode *inode, struct dentry *direntry)
current_time(inode);
rmdir_exit:
- kfree(full_path);
+ free_dentry_path(page);
free_xid(xid);
return rc;
}
@@ -2072,8 +2074,8 @@ cifs_rename2(struct user_namespace *mnt_userns, struct inode *source_dir,
struct dentry *source_dentry, struct inode *target_dir,
struct dentry *target_dentry, unsigned int flags)
{
- char *from_name = NULL;
- char *to_name = NULL;
+ const char *from_name, *to_name;
+ void *page1, *page2;
struct cifs_sb_info *cifs_sb;
struct tcon_link *tlink;
struct cifs_tcon *tcon;
@@ -2091,21 +2093,19 @@ cifs_rename2(struct user_namespace *mnt_userns, struct inode *source_dir,
return PTR_ERR(tlink);
tcon = tlink_tcon(tlink);
+ page1 = alloc_dentry_path();
+ page2 = alloc_dentry_path();
xid = get_xid();
- /*
- * we already have the rename sem so we do not need to
- * grab it again here to protect the path integrity
- */
- from_name = build_path_from_dentry(source_dentry);
- if (from_name == NULL) {
- rc = -ENOMEM;
+ from_name = build_path_from_dentry(source_dentry, page1);
+ if (IS_ERR(from_name)) {
+ rc = PTR_ERR(from_name);
goto cifs_rename_exit;
}
- to_name = build_path_from_dentry(target_dentry);
- if (to_name == NULL) {
- rc = -ENOMEM;
+ to_name = build_path_from_dentry(target_dentry, page2);
+ if (IS_ERR(to_name)) {
+ rc = PTR_ERR(to_name);
goto cifs_rename_exit;
}
@@ -2177,18 +2177,21 @@ unlink_target:
cifs_rename_exit:
kfree(info_buf_source);
- kfree(from_name);
- kfree(to_name);
+ free_dentry_path(page2);
+ free_dentry_path(page1);
free_xid(xid);
cifs_put_tlink(tlink);
return rc;
}
static bool
-cifs_inode_needs_reval(struct inode *inode)
+cifs_dentry_needs_reval(struct dentry *dentry)
{
+ struct inode *inode = d_inode(dentry);
struct cifsInodeInfo *cifs_i = CIFS_I(inode);
struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb);
+ struct cifs_tcon *tcon = cifs_sb_master_tcon(cifs_sb);
+ struct cached_fid *cfid = NULL;
if (cifs_i->time == 0)
return true;
@@ -2199,6 +2202,16 @@ cifs_inode_needs_reval(struct inode *inode)
if (!lookupCacheEnabled)
return true;
+ if (!open_cached_dir_by_dentry(tcon, dentry->d_parent, &cfid)) {
+ mutex_lock(&cfid->fid_mutex);
+ if (cfid->time && cifs_i->time > cfid->time) {
+ mutex_unlock(&cfid->fid_mutex);
+ close_cached_dir(cfid);
+ return false;
+ }
+ mutex_unlock(&cfid->fid_mutex);
+ close_cached_dir(cfid);
+ }
/*
* depending on inode type, check if attribute caching disabled for
* files or directories
@@ -2297,10 +2310,10 @@ cifs_zap_mapping(struct inode *inode)
int cifs_revalidate_file_attr(struct file *filp)
{
int rc = 0;
- struct inode *inode = file_inode(filp);
+ struct dentry *dentry = file_dentry(filp);
struct cifsFileInfo *cfile = (struct cifsFileInfo *) filp->private_data;
- if (!cifs_inode_needs_reval(inode))
+ if (!cifs_dentry_needs_reval(dentry))
return rc;
if (tlink_tcon(cfile->tlink)->unix_ext)
@@ -2317,22 +2330,22 @@ int cifs_revalidate_dentry_attr(struct dentry *dentry)
int rc = 0;
struct inode *inode = d_inode(dentry);
struct super_block *sb = dentry->d_sb;
- char *full_path = NULL;
+ const char *full_path;
+ void *page;
int count = 0;
if (inode == NULL)
return -ENOENT;
- if (!cifs_inode_needs_reval(inode))
+ if (!cifs_dentry_needs_reval(dentry))
return rc;
xid = get_xid();
- /* can not safely grab the rename sem here if rename calls revalidate
- since that would deadlock */
- full_path = build_path_from_dentry(dentry);
- if (full_path == NULL) {
- rc = -ENOMEM;
+ page = alloc_dentry_path();
+ full_path = build_path_from_dentry(dentry, page);
+ if (IS_ERR(full_path)) {
+ rc = PTR_ERR(full_path);
goto out;
}
@@ -2351,7 +2364,7 @@ again:
if (rc == -EAGAIN && count++ < 10)
goto again;
out:
- kfree(full_path);
+ free_dentry_path(page);
free_xid(xid);
return rc;
@@ -2395,7 +2408,7 @@ int cifs_getattr(struct user_namespace *mnt_userns, const struct path *path,
* We need to be sure that all dirty pages are written and the server
* has actual ctime, mtime and file length.
*/
- if ((request_mask & (STATX_CTIME | STATX_MTIME | STATX_SIZE)) &&
+ if ((request_mask & (STATX_CTIME | STATX_MTIME | STATX_SIZE | STATX_BLOCKS)) &&
!CIFS_CACHE_READ(CIFS_I(inode)) &&
inode->i_mapping && inode->i_mapping->nrpages != 0) {
rc = filemap_fdatawait(inode->i_mapping);
@@ -2522,7 +2535,7 @@ void cifs_setsize(struct inode *inode, loff_t offset)
static int
cifs_set_file_size(struct inode *inode, struct iattr *attrs,
- unsigned int xid, char *full_path)
+ unsigned int xid, const char *full_path)
{
int rc;
struct cifsFileInfo *open_file;
@@ -2585,6 +2598,14 @@ set_size_out:
if (rc == 0) {
cifsInode->server_eof = attrs->ia_size;
cifs_setsize(inode, attrs->ia_size);
+ /*
+ * i_blocks is not related to (i_size / i_blksize), but instead
+ * 512 byte (2**9) size is required for calculating num blocks.
+ * Until we can query the server for actual allocation size,
+ * this is best estimate we have for blocks allocated for a file
+ * Number of blocks must be rounded up so size 1 is not 0 blocks
+ */
+ inode->i_blocks = (512 - 1 + attrs->ia_size) >> 9;
/*
* The man page of truncate says if the size changed,
@@ -2605,7 +2626,8 @@ cifs_setattr_unix(struct dentry *direntry, struct iattr *attrs)
{
int rc;
unsigned int xid;
- char *full_path = NULL;
+ const char *full_path;
+ void *page = alloc_dentry_path();
struct inode *inode = d_inode(direntry);
struct cifsInodeInfo *cifsInode = CIFS_I(inode);
struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb);
@@ -2626,9 +2648,9 @@ cifs_setattr_unix(struct dentry *direntry, struct iattr *attrs)
if (rc < 0)
goto out;
- full_path = build_path_from_dentry(direntry);
- if (full_path == NULL) {
- rc = -ENOMEM;
+ full_path = build_path_from_dentry(direntry, page);
+ if (IS_ERR(full_path)) {
+ rc = PTR_ERR(full_path);
goto out;
}
@@ -2740,7 +2762,7 @@ cifs_setattr_unix(struct dentry *direntry, struct iattr *attrs)
cifsInode->time = 0;
out:
kfree(args);
- kfree(full_path);
+ free_dentry_path(page);
free_xid(xid);
return rc;
}
@@ -2756,7 +2778,8 @@ cifs_setattr_nounix(struct dentry *direntry, struct iattr *attrs)
struct cifsInodeInfo *cifsInode = CIFS_I(inode);
struct cifsFileInfo *wfile;
struct cifs_tcon *tcon;
- char *full_path = NULL;
+ const char *full_path;
+ void *page = alloc_dentry_path();
int rc = -EACCES;
__u32 dosattr = 0;
__u64 mode = NO_CHANGE_64;
@@ -2770,16 +2793,13 @@ cifs_setattr_nounix(struct dentry *direntry, struct iattr *attrs)
attrs->ia_valid |= ATTR_FORCE;
rc = setattr_prepare(&init_user_ns, direntry, attrs);
- if (rc < 0) {
- free_xid(xid);
- return rc;
- }
+ if (rc < 0)
+ goto cifs_setattr_exit;
- full_path = build_path_from_dentry(direntry);
- if (full_path == NULL) {
- rc = -ENOMEM;
- free_xid(xid);
- return rc;
+ full_path = build_path_from_dentry(direntry, page);
+ if (IS_ERR(full_path)) {
+ rc = PTR_ERR(full_path);
+ goto cifs_setattr_exit;
}
/*
@@ -2929,8 +2949,8 @@ cifs_setattr_nounix(struct dentry *direntry, struct iattr *attrs)
mark_inode_dirty(inode);
cifs_setattr_exit:
- kfree(full_path);
free_xid(xid);
+ free_dentry_path(page);
return rc;
}
@@ -2953,12 +2973,3 @@ cifs_setattr(struct user_namespace *mnt_userns, struct dentry *direntry,
/* BB: add cifs_setattr_legacy for really old servers */
return rc;
}
-
-#if 0
-void cifs_delete_inode(struct inode *inode)
-{
- cifs_dbg(FYI, "In cifs_delete_inode, inode = 0x%p\n", inode);
- /* may have to add back in if and when safe distributed caching of
- directories added e.g. via FindNotify */
-}
-#endif
diff --git a/fs/cifs/ioctl.c b/fs/cifs/ioctl.c
index dcde44ff6cf9..08d99fec593e 100644
--- a/fs/cifs/ioctl.c
+++ b/fs/cifs/ioctl.c
@@ -42,13 +42,16 @@ static long cifs_ioctl_query_info(unsigned int xid, struct file *filep,
struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb);
struct cifs_tcon *tcon = cifs_sb_master_tcon(cifs_sb);
struct dentry *dentry = filep->f_path.dentry;
- unsigned char *path;
+ const unsigned char *path;
+ void *page = alloc_dentry_path();
__le16 *utf16_path = NULL, root_path;
int rc = 0;
- path = build_path_from_dentry(dentry);
- if (path == NULL)
- return -ENOMEM;
+ path = build_path_from_dentry(dentry, page);
+ if (IS_ERR(path)) {
+ free_dentry_path(page);
+ return PTR_ERR(path);
+ }
cifs_dbg(FYI, "%s %s\n", __func__, path);
@@ -73,7 +76,7 @@ static long cifs_ioctl_query_info(unsigned int xid, struct file *filep,
ici_exit:
if (utf16_path != &root_path)
kfree(utf16_path);
- kfree(path);
+ free_dentry_path(page);
return rc;
}
diff --git a/fs/cifs/link.c b/fs/cifs/link.c
index 7c5878a645d9..616e1bc0cc0a 100644
--- a/fs/cifs/link.c
+++ b/fs/cifs/link.c
@@ -510,8 +510,8 @@ cifs_hardlink(struct dentry *old_file, struct inode *inode,
{
int rc = -EACCES;
unsigned int xid;
- char *from_name = NULL;
- char *to_name = NULL;
+ const char *from_name, *to_name;
+ void *page1, *page2;
struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb);
struct tcon_link *tlink;
struct cifs_tcon *tcon;
@@ -524,11 +524,17 @@ cifs_hardlink(struct dentry *old_file, struct inode *inode,
tcon = tlink_tcon(tlink);
xid = get_xid();
+ page1 = alloc_dentry_path();
+ page2 = alloc_dentry_path();
- from_name = build_path_from_dentry(old_file);
- to_name = build_path_from_dentry(direntry);
- if ((from_name == NULL) || (to_name == NULL)) {
- rc = -ENOMEM;
+ from_name = build_path_from_dentry(old_file, page1);
+ if (IS_ERR(from_name)) {
+ rc = PTR_ERR(from_name);
+ goto cifs_hl_exit;
+ }
+ to_name = build_path_from_dentry(direntry, page2);
+ if (IS_ERR(to_name)) {
+ rc = PTR_ERR(to_name);
goto cifs_hl_exit;
}
@@ -587,8 +593,8 @@ cifs_hardlink(struct dentry *old_file, struct inode *inode,
}
cifs_hl_exit:
- kfree(from_name);
- kfree(to_name);
+ free_dentry_path(page1);
+ free_dentry_path(page2);
free_xid(xid);
cifs_put_tlink(tlink);
return rc;
@@ -600,7 +606,8 @@ cifs_get_link(struct dentry *direntry, struct inode *inode,
{
int rc = -ENOMEM;
unsigned int xid;
- char *full_path = NULL;
+ const char *full_path;
+ void *page;
char *target_path = NULL;
struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb);
struct tcon_link *tlink = NULL;
@@ -620,11 +627,13 @@ cifs_get_link(struct dentry *direntry, struct inode *inode,
tcon = tlink_tcon(tlink);
server = tcon->ses->server;
- full_path = build_path_from_dentry(direntry);
- if (!full_path) {
+ page = alloc_dentry_path();
+ full_path = build_path_from_dentry(direntry, page);
+ if (IS_ERR(full_path)) {
free_xid(xid);
cifs_put_tlink(tlink);
- return ERR_PTR(-ENOMEM);
+ free_dentry_path(page);
+ return ERR_CAST(full_path);
}
cifs_dbg(FYI, "Full path: %s inode = 0x%p\n", full_path, inode);
@@ -649,7 +658,7 @@ cifs_get_link(struct dentry *direntry, struct inode *inode,
&target_path, reparse_point);
}
- kfree(full_path);
+ free_dentry_path(page);
free_xid(xid);
cifs_put_tlink(tlink);
if (rc != 0) {
@@ -669,7 +678,8 @@ cifs_symlink(struct user_namespace *mnt_userns, struct inode *inode,
struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb);
struct tcon_link *tlink;
struct cifs_tcon *pTcon;
- char *full_path = NULL;
+ const char *full_path;
+ void *page = alloc_dentry_path();
struct inode *newinode = NULL;
xid = get_xid();
@@ -681,9 +691,9 @@ cifs_symlink(struct user_namespace *mnt_userns, struct inode *inode,
}
pTcon = tlink_tcon(tlink);
- full_path = build_path_from_dentry(direntry);
- if (full_path == NULL) {
- rc = -ENOMEM;
+ full_path = build_path_from_dentry(direntry, page);
+ if (IS_ERR(full_path)) {
+ rc = PTR_ERR(full_path);
goto symlink_exit;
}
@@ -719,7 +729,7 @@ cifs_symlink(struct user_namespace *mnt_userns, struct inode *inode,
}
}
symlink_exit:
- kfree(full_path);
+ free_dentry_path(page);
cifs_put_tlink(tlink);
free_xid(xid);
return rc;
diff --git a/fs/cifs/misc.c b/fs/cifs/misc.c
index 82e176720ca6..c15a90e422be 100644
--- a/fs/cifs/misc.c
+++ b/fs/cifs/misc.c
@@ -1180,7 +1180,7 @@ int update_super_prepath(struct cifs_tcon *tcon, char *prefix)
kfree(cifs_sb->prepath);
if (prefix && *prefix) {
- cifs_sb->prepath = kstrndup(prefix, strlen(prefix), GFP_ATOMIC);
+ cifs_sb->prepath = kstrdup(prefix, GFP_ATOMIC);
if (!cifs_sb->prepath) {
rc = -ENOMEM;
goto out;
diff --git a/fs/cifs/readdir.c b/fs/cifs/readdir.c
index 80bf4c6f4c7b..63bfc533c9fb 100644
--- a/fs/cifs/readdir.c
+++ b/fs/cifs/readdir.c
@@ -119,9 +119,7 @@ retry:
/* 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);
+ cifs_fattr_to_inode(inode, fattr) == 0) {
dput(dentry);
return;
}
@@ -384,7 +382,7 @@ int get_symlink_reparse_path(char *full_path, struct cifs_sb_info *cifs_sb,
static int
initiate_cifs_search(const unsigned int xid, struct file *file,
- char *full_path)
+ const char *full_path)
{
__u16 search_flags;
int rc = 0;
@@ -704,7 +702,7 @@ static int cifs_save_resume_key(const char *current_entry,
*/
static int
find_cifs_entry(const unsigned int xid, struct cifs_tcon *tcon, loff_t pos,
- struct file *file, char *full_path,
+ struct file *file, const char *full_path,
char **current_entry, int *num_to_ret)
{
__u16 search_flags;
@@ -942,13 +940,14 @@ int cifs_readdir(struct file *file, struct dir_context *ctx)
char *tmp_buf = NULL;
char *end_of_smb;
unsigned int max_len;
- char *full_path = NULL;
+ const char *full_path;
+ void *page = alloc_dentry_path();
xid = get_xid();
- full_path = build_path_from_dentry(file_dentry(file));
- if (full_path == NULL) {
- rc = -ENOMEM;
+ full_path = build_path_from_dentry(file_dentry(file), page);
+ if (IS_ERR(full_path)) {
+ rc = PTR_ERR(full_path);
goto rddir2_exit;
}
@@ -1043,7 +1042,7 @@ int cifs_readdir(struct file *file, struct dir_context *ctx)
kfree(tmp_buf);
rddir2_exit:
- kfree(full_path);
+ free_dentry_path(page);
free_xid(xid);
return rc;
}
diff --git a/fs/cifs/smb1ops.c b/fs/cifs/smb1ops.c
index e31b939e628c..3b83839fc2c2 100644
--- a/fs/cifs/smb1ops.c
+++ b/fs/cifs/smb1ops.c
@@ -926,9 +926,7 @@ cifs_unix_dfs_readlink(const unsigned int xid, struct cifs_tcon *tcon,
0);
if (!rc) {
- *symlinkinfo = kstrndup(referral.node_name,
- strlen(referral.node_name),
- GFP_KERNEL);
+ *symlinkinfo = kstrdup(referral.node_name, GFP_KERNEL);
free_dfs_info_param(&referral);
if (!*symlinkinfo)
rc = -ENOMEM;
@@ -1027,7 +1025,7 @@ cifs_can_echo(struct TCP_Server_Info *server)
static int
cifs_make_node(unsigned int xid, struct inode *inode,
struct dentry *dentry, struct cifs_tcon *tcon,
- char *full_path, umode_t mode, dev_t dev)
+ const char *full_path, umode_t mode, dev_t dev)
{
struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb);
struct inode *newinode = NULL;
diff --git a/fs/cifs/smb2glob.h b/fs/cifs/smb2glob.h
index 99a1951a01ec..d9a990c99121 100644
--- a/fs/cifs/smb2glob.h
+++ b/fs/cifs/smb2glob.h
@@ -58,6 +58,7 @@
#define SMB2_HMACSHA256_SIZE (32)
#define SMB2_CMACAES_SIZE (16)
#define SMB3_SIGNKEY_SIZE (16)
+#define SMB3_GCM128_CRYPTKEY_SIZE (16)
#define SMB3_GCM256_CRYPTKEY_SIZE (32)
/* Maximum buffer size value we can send with 1 credit */
diff --git a/fs/cifs/smb2inode.c b/fs/cifs/smb2inode.c
index a718dc77e604..9a61209a283e 100644
--- a/fs/cifs/smb2inode.c
+++ b/fs/cifs/smb2inode.c
@@ -512,7 +512,6 @@ smb2_query_path_info(const unsigned int xid, struct cifs_tcon *tcon,
int rc;
struct smb2_file_all_info *smb2_data;
__u32 create_options = 0;
- bool no_cached_open = tcon->nohandlecache;
struct cifsFileInfo *cfile;
struct cached_fid *cfid = NULL;
@@ -525,11 +524,8 @@ smb2_query_path_info(const unsigned int xid, struct cifs_tcon *tcon,
return -ENOMEM;
/* If it is a root and its handle is cached then use it */
- if (!strlen(full_path) && !no_cached_open) {
- rc = open_shroot(xid, tcon, cifs_sb, &cfid);
- if (rc)
- goto out;
-
+ rc = open_cached_dir(xid, tcon, full_path, cifs_sb, &cfid);
+ if (!rc) {
if (tcon->crfid.file_all_info_is_valid) {
move_smb2_info_to_cifs(data,
&tcon->crfid.file_all_info);
@@ -540,7 +536,7 @@ smb2_query_path_info(const unsigned int xid, struct cifs_tcon *tcon,
if (!rc)
move_smb2_info_to_cifs(data, smb2_data);
}
- close_shroot(cfid);
+ close_cached_dir(cfid);
goto out;
}
diff --git a/fs/cifs/smb2misc.c b/fs/cifs/smb2misc.c
index b50164e2c88d..06d555d4da9a 100644
--- a/fs/cifs/smb2misc.c
+++ b/fs/cifs/smb2misc.c
@@ -667,6 +667,7 @@ smb2_is_valid_lease_break(char *buffer)
!memcmp(rsp->LeaseKey,
tcon->crfid.fid->lease_key,
SMB2_LEASE_KEY_SIZE)) {
+ tcon->crfid.time = 0;
INIT_WORK(&tcon->crfid.lease_break,
smb2_cached_lease_break);
queue_work(cifsiod_wq,
@@ -754,8 +755,8 @@ smb2_is_valid_oplock_break(char *buffer, struct TCP_Server_Info *server)
}
}
spin_unlock(&cifs_tcp_ses_lock);
- cifs_dbg(FYI, "Can not process oplock break for non-existent connection\n");
- return false;
+ cifs_dbg(FYI, "No file id matched, oplock break ignored\n");
+ return true;
}
void
diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c
index 9bae7e8deb09..dd0eb665b680 100644
--- a/fs/cifs/smb2ops.c
+++ b/fs/cifs/smb2ops.c
@@ -690,17 +690,21 @@ smb2_close_cached_fid(struct kref *ref)
cfid->is_valid = false;
cfid->file_all_info_is_valid = false;
cfid->has_lease = false;
+ if (cfid->dentry) {
+ dput(cfid->dentry);
+ cfid->dentry = NULL;
+ }
}
}
-void close_shroot(struct cached_fid *cfid)
+void close_cached_dir(struct cached_fid *cfid)
{
mutex_lock(&cfid->fid_mutex);
kref_put(&cfid->refcount, smb2_close_cached_fid);
mutex_unlock(&cfid->fid_mutex);
}
-void close_shroot_lease_locked(struct cached_fid *cfid)
+void close_cached_dir_lease_locked(struct cached_fid *cfid)
{
if (cfid->has_lease) {
cfid->has_lease = false;
@@ -708,10 +712,10 @@ void close_shroot_lease_locked(struct cached_fid *cfid)
}
}
-void close_shroot_lease(struct cached_fid *cfid)
+void close_cached_dir_lease(struct cached_fid *cfid)
{
mutex_lock(&cfid->fid_mutex);
- close_shroot_lease_locked(cfid);
+ close_cached_dir_lease_locked(cfid);
mutex_unlock(&cfid->fid_mutex);
}
@@ -721,13 +725,15 @@ smb2_cached_lease_break(struct work_struct *work)
struct cached_fid *cfid = container_of(work,
struct cached_fid, lease_break);
- close_shroot_lease(cfid);
+ close_cached_dir_lease(cfid);
}
/*
- * Open the directory at the root of a share
+ * Open the and cache a directory handle.
+ * Only supported for the root handle.
*/
-int open_shroot(unsigned int xid, struct cifs_tcon *tcon,
+int open_cached_dir(unsigned int xid, struct cifs_tcon *tcon,
+ const char *path,
struct cifs_sb_info *cifs_sb,
struct cached_fid **cfid)
{
@@ -745,6 +751,18 @@ int open_shroot(unsigned int xid, struct cifs_tcon *tcon,
__le16 utf16_path = 0; /* Null - since an open of top of share */
u8 oplock = SMB2_OPLOCK_LEVEL_II;
struct cifs_fid *pfid;
+ struct dentry *dentry;
+
+ if (tcon->nohandlecache)
+ return -ENOTSUPP;
+
+ if (cifs_sb->root == NULL)
+ return -ENOENT;
+
+ if (strlen(path))
+ return -ENOENT;
+
+ dentry = cifs_sb->root;
mutex_lock(&tcon->crfid.fid_mutex);
if (tcon->crfid.is_valid) {
@@ -830,11 +848,9 @@ int open_shroot(unsigned int xid, struct cifs_tcon *tcon,
};
/*
- * caller expects this func to set pfid to a valid
- * cached root, so we copy the existing one and get a
- * reference.
+ * caller expects this func to set the fid in crfid to valid
+ * cached root, so increment the refcount.
*/
- memcpy(pfid, tcon->crfid.fid, sizeof(*pfid));
kref_get(&tcon->crfid.refcount);
mutex_unlock(&tcon->crfid.fid_mutex);
@@ -867,13 +883,18 @@ int open_shroot(unsigned int xid, struct cifs_tcon *tcon,
oparms.fid->mid = le64_to_cpu(o_rsp->sync_hdr.MessageId);
#endif /* CIFS_DEBUG2 */
- memcpy(tcon->crfid.fid, pfid, sizeof(struct cifs_fid));
tcon->crfid.tcon = tcon;
tcon->crfid.is_valid = true;
+ tcon->crfid.dentry = dentry;
+ dget(dentry);
kref_init(&tcon->crfid.refcount);
/* BB TBD check to see if oplock level check can be removed below */
if (o_rsp->OplockLevel == SMB2_OPLOCK_LEVEL_LEASE) {
+ /*
+ * See commit 2f94a3125b87. Increment the refcount when we
+ * get a lease for root, release it if lease break occurs
+ */
kref_get(&tcon->crfid.refcount);
tcon->crfid.has_lease = true;
smb2_parse_contexts(server, o_rsp,
@@ -892,6 +913,8 @@ int open_shroot(unsigned int xid, struct cifs_tcon *tcon,
&rsp_iov[1], sizeof(struct smb2_file_all_info),
(char *)&tcon->crfid.file_all_info))
tcon->crfid.file_all_info_is_valid = true;
+ tcon->crfid.time = jiffies;
+
oshr_exit:
mutex_unlock(&tcon->crfid.fid_mutex);
@@ -905,6 +928,22 @@ oshr_free:
return rc;
}
+int open_cached_dir_by_dentry(struct cifs_tcon *tcon,
+ struct dentry *dentry,
+ struct cached_fid **cfid)
+{
+ mutex_lock(&tcon->crfid.fid_mutex);
+ if (tcon->crfid.dentry == dentry) {
+ cifs_dbg(FYI, "found a cached root file handle by dentry\n");
+ *cfid = &tcon->crfid;
+ kref_get(&tcon->crfid.refcount);
+ mutex_unlock(&tcon->crfid.fid_mutex);
+ return 0;
+ }
+ mutex_unlock(&tcon->crfid.fid_mutex);
+ return -ENOENT;
+}
+
static void
smb3_qfs_tcon(const unsigned int xid, struct cifs_tcon *tcon,
struct cifs_sb_info *cifs_sb)
@@ -914,7 +953,6 @@ smb3_qfs_tcon(const unsigned int xid, struct cifs_tcon *tcon,
u8 oplock = SMB2_OPLOCK_LEVEL_NONE;
struct cifs_open_parms oparms;
struct cifs_fid fid;
- bool no_cached_open = tcon->nohandlecache;
struct cached_fid *cfid = NULL;
oparms.tcon = tcon;
@@ -924,14 +962,12 @@ smb3_qfs_tcon(const unsigned int xid, struct cifs_tcon *tcon,
oparms.fid = &fid;
oparms.reconnect = false;
- if (no_cached_open) {
+ rc = open_cached_dir(xid, tcon, "", cifs_sb, &cfid);
+ if (rc == 0)
+ memcpy(&fid, cfid->fid, sizeof(struct cifs_fid));
+ else
rc = SMB2_open(xid, &oparms, &srch_path, &oplock, NULL, NULL,
NULL, NULL);
- } else {
- rc = open_shroot(xid, tcon, cifs_sb, &cfid);
- if (rc == 0)
- memcpy(&fid, cfid->fid, sizeof(struct cifs_fid));
- }
if (rc)
return;
@@ -945,10 +981,10 @@ smb3_qfs_tcon(const unsigned int xid, struct cifs_tcon *tcon,
FS_VOLUME_INFORMATION);
SMB2_QFS_attr(xid, tcon, fid.persistent_fid, fid.volatile_fid,
FS_SECTOR_SIZE_INFORMATION); /* SMB3 specific */
- if (no_cached_open)
+ if (cfid == NULL)
SMB2_close(xid, tcon, fid.persistent_fid, fid.volatile_fid);
else
- close_shroot(cfid);
+ close_cached_dir(cfid);
}
static void
@@ -1531,7 +1567,10 @@ SMB2_request_res_key(const unsigned int xid, struct cifs_tcon *tcon,
NULL, 0 /* no input */, CIFSMaxBufSize,
(char **)&res_key, &ret_data_len);
- if (rc) {
+ if (rc == -EOPNOTSUPP) {
+ pr_warn_once("Server share %s does not support copy range\n", tcon->treeName);
+ goto req_res_key_exit;
+ } else if (rc) {
cifs_tcon_dbg(VFS, "refcpy ioctl error %d getting resume key\n", rc);
goto req_res_key_exit;
}
@@ -1763,18 +1802,14 @@ smb2_ioctl_query_info(const unsigned int xid,
}
iqinf_exit:
- kfree(vars);
- kfree(buffer);
- SMB2_open_free(&rqst[0]);
- if (qi.flags & PASSTHRU_FSCTL)
- SMB2_ioctl_free(&rqst[1]);
- else
- SMB2_query_info_free(&rqst[1]);
-
- SMB2_close_free(&rqst[2]);
+ cifs_small_buf_release(rqst[0].rq_iov[0].iov_base);
+ cifs_small_buf_release(rqst[1].rq_iov[0].iov_base);
+ cifs_small_buf_release(rqst[2].rq_iov[0].iov_base);
free_rsp_buf(resp_buftype[0], rsp_iov[0].iov_base);
free_rsp_buf(resp_buftype[1], rsp_iov[1].iov_base);
free_rsp_buf(resp_buftype[2], rsp_iov[2].iov_base);
+ kfree(vars);
+ kfree(buffer);
return rc;
e_fault:
@@ -2038,6 +2073,7 @@ smb2_duplicate_extents(const unsigned int xid,
{
int rc;
unsigned int ret_data_len;
+ struct inode *inode;
struct duplicate_extents_to_file dup_ext_buf;
struct cifs_tcon *tcon = tlink_tcon(trgtfile->tlink);
@@ -2054,10 +2090,21 @@ smb2_duplicate_extents(const unsigned int xid,
cifs_dbg(FYI, "Duplicate extents: src off %lld dst off %lld len %lld\n",
src_off, dest_off, len);
- rc = smb2_set_file_size(xid, tcon, trgtfile, dest_off + len, false);
- if (rc)
- goto duplicate_extents_out;
+ inode = d_inode(trgtfile->dentry);
+ if (inode->i_size < dest_off + len) {
+ rc = smb2_set_file_size(xid, tcon, trgtfile, dest_off + len, false);
+ if (rc)
+ goto duplicate_extents_out;
+ /*
+ * Although also could set plausible allocation size (i_blocks)
+ * here in addition to setting the file size, in reflink
+ * it is likely that the target file is sparse. Its allocation
+ * size will be queried on next revalidate, but it is important
+ * to make sure that file's cached size is updated immediately
+ */
+ cifs_setsize(inode, dest_off + len);
+ }
rc = SMB2_ioctl(xid, tcon, trgtfile->fid.persistent_fid,
trgtfile->fid.volatile_fid,
FSCTL_DUPLICATE_EXTENTS_TO_FILE,
@@ -2205,22 +2252,23 @@ smb3_notify(const unsigned int xid, struct file *pfile,
struct smb3_notify notify;
struct dentry *dentry = pfile->f_path.dentry;
struct inode *inode = file_inode(pfile);
- struct cifs_sb_info *cifs_sb;
+ struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb);
struct cifs_open_parms oparms;
struct cifs_fid fid;
struct cifs_tcon *tcon;
- unsigned char *path = NULL;
+ const unsigned char *path;
+ void *page = alloc_dentry_path();
__le16 *utf16_path = NULL;
u8 oplock = SMB2_OPLOCK_LEVEL_NONE;
int rc = 0;
- path = build_path_from_dentry(dentry);
- if (path == NULL)
- return -ENOMEM;
-
- cifs_sb = CIFS_SB(inode->i_sb);
+ path = build_path_from_dentry(dentry, page);
+ if (IS_ERR(path)) {
+ rc = PTR_ERR(path);
+ goto notify_exit;
+ }
- utf16_path = cifs_convert_path_to_utf16(path + 1, cifs_sb);
+ utf16_path = cifs_convert_path_to_utf16(path, cifs_sb);
if (utf16_path == NULL) {
rc = -ENOMEM;
goto notify_exit;
@@ -2252,7 +2300,7 @@ smb3_notify(const unsigned int xid, struct file *pfile,
cifs_dbg(FYI, "change notify for path %s rc %d\n", path, rc);
notify_exit:
- kfree(path);
+ free_dentry_path(page);
kfree(utf16_path);
return rc;
}
@@ -3640,6 +3688,77 @@ out:
return rc;
}
+static long smb3_collapse_range(struct file *file, struct cifs_tcon *tcon,
+ loff_t off, loff_t len)
+{
+ int rc;
+ unsigned int xid;
+ struct cifsFileInfo *cfile = file->private_data;
+ __le64 eof;
+
+ xid = get_xid();
+
+ if (off >= i_size_read(file->f_inode) ||
+ off + len >= i_size_read(file->f_inode)) {
+ rc = -EINVAL;
+ goto out;
+ }
+
+ rc = smb2_copychunk_range(xid, cfile, cfile, off + len,
+ i_size_read(file->f_inode) - off - len, off);
+ if (rc < 0)
+ goto out;
+
+ eof = cpu_to_le64(i_size_read(file->f_inode) - len);
+ rc = SMB2_set_eof(xid, tcon, cfile->fid.persistent_fid,
+ cfile->fid.volatile_fid, cfile->pid, &eof);
+ if (rc < 0)
+ goto out;
+
+ rc = 0;
+ out:
+ free_xid(xid);
+ return rc;
+}
+
+static long smb3_insert_range(struct file *file, struct cifs_tcon *tcon,
+ loff_t off, loff_t len)
+{
+ int rc;
+ unsigned int xid;
+ struct cifsFileInfo *cfile = file->private_data;
+ __le64 eof;
+ __u64 count;
+
+ xid = get_xid();
+
+ if (off >= i_size_read(file->f_inode)) {
+ rc = -EINVAL;
+ goto out;
+ }
+
+ count = i_size_read(file->f_inode) - off;
+ eof = cpu_to_le64(i_size_read(file->f_inode) + len);
+
+ rc = SMB2_set_eof(xid, tcon, cfile->fid.persistent_fid,
+ cfile->fid.volatile_fid, cfile->pid, &eof);
+ if (rc < 0)
+ goto out;
+
+ rc = smb2_copychunk_range(xid, cfile, cfile, off, count, off + len);
+ if (rc < 0)
+ goto out;
+
+ rc = smb3_zero_range(file, tcon, off, len, 1);
+ if (rc < 0)
+ goto out;
+
+ rc = 0;
+ out:
+ free_xid(xid);
+ return rc;
+}
+
static loff_t smb3_llseek(struct file *file, struct cifs_tcon *tcon, loff_t offset, int whence)
{
struct cifsFileInfo *wrcfile, *cfile = file->private_data;
@@ -3811,6 +3930,10 @@ static long smb3_fallocate(struct file *file, struct cifs_tcon *tcon, int mode,
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 == FALLOC_FL_COLLAPSE_RANGE)
+ return smb3_collapse_range(file, tcon, off, len);
+ else if (mode == FALLOC_FL_INSERT_RANGE)
+ return smb3_insert_range(file, tcon, off, len);
else if (mode == 0)
return smb3_simple_falloc(file, tcon, off, len, false);
@@ -4158,7 +4281,7 @@ smb2_get_enc_key(struct TCP_Server_Info *server, __u64 ses_id, int enc, u8 *key)
if (ses->Suid == ses_id) {
ses_enc_key = enc ? ses->smb3encryptionkey :
ses->smb3decryptionkey;
- memcpy(key, ses_enc_key, SMB3_SIGN_KEY_SIZE);
+ memcpy(key, ses_enc_key, SMB3_ENC_DEC_KEY_SIZE);
spin_unlock(&cifs_tcp_ses_lock);
return 0;
}
@@ -4166,7 +4289,7 @@ smb2_get_enc_key(struct TCP_Server_Info *server, __u64 ses_id, int enc, u8 *key)
}
spin_unlock(&cifs_tcp_ses_lock);
- return 1;
+ return -EAGAIN;
}
/*
* Encrypt or decrypt @rqst message. @rqst[0] has the following format:
@@ -4185,7 +4308,7 @@ crypt_message(struct TCP_Server_Info *server, int num_rqst,
int rc = 0;
struct scatterlist *sg;
u8 sign[SMB2_SIGNATURE_SIZE] = {};
- u8 key[SMB3_SIGN_KEY_SIZE];
+ u8 key[SMB3_ENC_DEC_KEY_SIZE];
struct aead_request *req;
char *iv;
unsigned int iv_len;
@@ -4209,10 +4332,11 @@ crypt_message(struct TCP_Server_Info *server, int num_rqst,
tfm = enc ? server->secmech.ccmaesencrypt :
server->secmech.ccmaesdecrypt;
- if (server->cipher_type == SMB2_ENCRYPTION_AES256_GCM)
+ if ((server->cipher_type == SMB2_ENCRYPTION_AES256_CCM) ||
+ (server->cipher_type == SMB2_ENCRYPTION_AES256_GCM))
rc = crypto_aead_setkey(tfm, key, SMB3_GCM256_CRYPTKEY_SIZE);
else
- rc = crypto_aead_setkey(tfm, key, SMB3_SIGN_KEY_SIZE);
+ rc = crypto_aead_setkey(tfm, key, SMB3_GCM128_CRYPTKEY_SIZE);
if (rc) {
cifs_server_dbg(VFS, "%s: Failed to set aead key %d\n", __func__, rc);
@@ -4955,7 +5079,7 @@ smb2_next_header(char *buf)
static int
smb2_make_node(unsigned int xid, struct inode *inode,
struct dentry *dentry, struct cifs_tcon *tcon,
- char *full_path, umode_t mode, dev_t dev)
+ const char *full_path, umode_t mode, dev_t dev)
{
struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb);
int rc = -EPERM;
diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c
index 2199a9bfae8f..e36c2a867783 100644
--- a/fs/cifs/smb2pdu.c
+++ b/fs/cifs/smb2pdu.c
@@ -1857,7 +1857,7 @@ SMB2_tdis(const unsigned int xid, struct cifs_tcon *tcon)
if ((tcon->need_reconnect) || (tcon->ses->need_reconnect))
return 0;
- close_shroot_lease(&tcon->crfid);
+ close_cached_dir_lease(&tcon->crfid);
rc = smb2_plain_req_init(SMB2_TREE_DISCONNECT, tcon, ses->server,
(void **) &req,
diff --git a/fs/cifs/smb2pdu.h b/fs/cifs/smb2pdu.h
index a5a9e33c0d73..6442dc1c292b 100644
--- a/fs/cifs/smb2pdu.h
+++ b/fs/cifs/smb2pdu.h
@@ -144,7 +144,7 @@ struct smb2_transform_hdr {
} __packed;
/* See MS-SMB2 2.2.42 */
-struct smb2_compression_transform_hdr {
+struct smb2_compression_transform_hdr_unchained {
__le32 ProtocolId; /* 0xFC 'S' 'M' 'B' */
__le32 OriginalCompressedSegmentSize;
__le16 CompressionAlgorithm;
@@ -160,10 +160,17 @@ struct compression_payload_header {
__le16 CompressionAlgorithm;
__le16 Flags;
__le32 Length; /* length of compressed playload including field below if present */
- /* __le32 OriginalPayloadSize; */ /* optional */
+ /* __le32 OriginalPayloadSize; */ /* optional, present when LZNT1, LZ77, LZ77+Huffman */
} __packed;
/* See MS-SMB2 2.2.42.2 */
+struct smb2_compression_transform_hdr_chained {
+ __le32 ProtocolId; /* 0xFC 'S' 'M' 'B' */
+ __le32 OriginalCompressedSegmentSize;
+ /* struct compression_payload_header[] */
+} __packed;
+
+/* See MS-SMB2 2.2.42.2.2 */
struct compression_pattern_payload_v1 {
__le16 Pattern;
__le16 Reserved1;
@@ -181,7 +188,11 @@ struct smb2_rdma_transform {
__le32 Reserved2;
} __packed;
-struct smb2_rdma_encryption_transform {
+/* TransformType */
+#define SMB2_RDMA_TRANSFORM_TYPE_ENCRYPTION 0x0001
+#define SMB2_RDMA_TRANSFORM_TYPE_SIGNING 0x0002
+
+struct smb2_rdma_crypto_transform {
__le16 TransformType;
__le16 SignatureLength;
__le16 NonceLength;
@@ -409,13 +420,29 @@ struct smb2_netname_neg_context {
} __packed;
/*
- * For rdma transform capabilities context see MS-SMB2 2.2.3.1.6
+ * For smb2_transport_capabilities context see MS-SMB2 2.2.3.1.5
* and 2.2.4.1.5
*/
+/* Flags */
+#define SMB2_ACCEPT_TRANSFORM_LEVEL_SECURITY 0x00000001
+
+struct smb2_transport_capabilities_context {
+ __le16 ContextType; /* 6 */
+ __le16 DataLength;
+ __u32 Reserved;
+ __le32 Flags;
+} __packed;
+
+/*
+ * For rdma transform capabilities context see MS-SMB2 2.2.3.1.6
+ * and 2.2.4.1.6
+ */
+
/* RDMA Transform IDs */
#define SMB2_RDMA_TRANSFORM_NONE 0x0000
#define SMB2_RDMA_TRANSFORM_ENCRYPTION 0x0001
+#define SMB2_RDMA_TRANSFORM_SIGNING 0x0002
struct smb2_rdma_transform_capabilities_context {
__le16 ContextType; /* 7 */
@@ -427,6 +454,11 @@ struct smb2_rdma_transform_capabilities_context {
__le16 RDMATransformIds[];
} __packed;
+/*
+ * For signing capabilities context see MS-SMB2 2.2.3.1.7
+ * and 2.2.4.1.7
+ */
+
/* Signing algorithms */
#define SIGNING_ALG_HMAC_SHA256 0
#define SIGNING_ALG_AES_CMAC 1
@@ -634,7 +666,8 @@ struct smb2_tree_connect_rsp {
#define SHI1005_FLAGS_ENABLE_HASH_V2 0x00004000
#define SHI1005_FLAGS_ENCRYPT_DATA 0x00008000
#define SMB2_SHAREFLAG_IDENTITY_REMOTING 0x00040000 /* 3.1.1 */
-#define SHI1005_FLAGS_ALL 0x0004FF33
+#define SMB2_SHAREFLAG_COMPRESS_DATA 0x00100000 /* 3.1.1 */
+#define SHI1005_FLAGS_ALL 0x0014FF33
/* Possible share capabilities */
#define SMB2_SHARE_CAP_DFS cpu_to_le32(0x00000008) /* all dialects */
@@ -1390,7 +1423,11 @@ struct smb2_lock_req {
struct smb2_sync_hdr sync_hdr;
__le16 StructureSize; /* Must be 48 */
__le16 LockCount;
- __le32 Reserved;
+ /*
+ * The least significant four bits are the index, the other 28 bits are
+ * the lock sequence number (0 to 64). See MS-SMB2 2.2.26
+ */
+ __le32 LockSequenceNumber;
__u64 PersistentFileId; /* opaque endianness */
__u64 VolatileFileId; /* opaque endianness */
/* Followed by at least one */
diff --git a/fs/cifs/smb2proto.h b/fs/cifs/smb2proto.h
index a2eb34a8d9c9..a5f87b02cfaf 100644
--- a/fs/cifs/smb2proto.h
+++ b/fs/cifs/smb2proto.h
@@ -69,12 +69,16 @@ extern struct cifs_ses *smb2_find_smb_ses(struct TCP_Server_Info *server,
extern int smb3_handle_read_data(struct TCP_Server_Info *server,
struct mid_q_entry *mid);
-extern int open_shroot(unsigned int xid, struct cifs_tcon *tcon,
- struct cifs_sb_info *cifs_sb,
- struct cached_fid **cfid);
-extern void close_shroot(struct cached_fid *cfid);
-extern void close_shroot_lease(struct cached_fid *cfid);
-extern void close_shroot_lease_locked(struct cached_fid *cfid);
+extern int open_cached_dir(unsigned int xid, struct cifs_tcon *tcon,
+ const char *path,
+ struct cifs_sb_info *cifs_sb,
+ struct cached_fid **cfid);
+extern int open_cached_dir_by_dentry(struct cifs_tcon *tcon,
+ struct dentry *dentry,
+ struct cached_fid **cfid);
+extern void close_cached_dir(struct cached_fid *cfid);
+extern void close_cached_dir_lease(struct cached_fid *cfid);
+extern void close_cached_dir_lease_locked(struct cached_fid *cfid);
extern void move_smb2_info_to_cifs(FILE_ALL_INFO *dst,
struct smb2_file_all_info *src);
extern int smb2_query_reparse_tag(const unsigned int xid, struct cifs_tcon *tcon,
diff --git a/fs/cifs/smb2transport.c b/fs/cifs/smb2transport.c
index ebccd71cc60a..e6fa76ab70be 100644
--- a/fs/cifs/smb2transport.c
+++ b/fs/cifs/smb2transport.c
@@ -298,7 +298,8 @@ static int generate_key(struct cifs_ses *ses, struct kvec label,
{
unsigned char zero = 0x0;
__u8 i[4] = {0, 0, 0, 1};
- __u8 L[4] = {0, 0, 0, 128};
+ __u8 L128[4] = {0, 0, 0, 128};
+ __u8 L256[4] = {0, 0, 1, 0};
int rc = 0;
unsigned char prfhash[SMB2_HMACSHA256_SIZE];
unsigned char *hashptr = prfhash;
@@ -354,8 +355,14 @@ static int generate_key(struct cifs_ses *ses, struct kvec label,
goto smb3signkey_ret;
}
- rc = crypto_shash_update(&server->secmech.sdeschmacsha256->shash,
- L, 4);
+ if ((server->cipher_type == SMB2_ENCRYPTION_AES256_CCM) ||
+ (server->cipher_type == SMB2_ENCRYPTION_AES256_GCM)) {
+ rc = crypto_shash_update(&server->secmech.sdeschmacsha256->shash,
+ L256, 4);
+ } else {
+ rc = crypto_shash_update(&server->secmech.sdeschmacsha256->shash,
+ L128, 4);
+ }
if (rc) {
cifs_server_dbg(VFS, "%s: Could not update with L\n", __func__);
goto smb3signkey_ret;
@@ -390,6 +397,9 @@ generate_smb3signingkey(struct cifs_ses *ses,
const struct derivation_triplet *ptriplet)
{
int rc;
+#ifdef CONFIG_CIFS_DEBUG_DUMP_KEYS
+ struct TCP_Server_Info *server = ses->server;
+#endif
/*
* All channels use the same encryption/decryption keys but
@@ -422,11 +432,11 @@ generate_smb3signingkey(struct cifs_ses *ses,
rc = generate_key(ses, ptriplet->encryption.label,
ptriplet->encryption.context,
ses->smb3encryptionkey,
- SMB3_SIGN_KEY_SIZE);
+ SMB3_ENC_DEC_KEY_SIZE);
rc = generate_key(ses, ptriplet->decryption.label,
ptriplet->decryption.context,
ses->smb3decryptionkey,
- SMB3_SIGN_KEY_SIZE);
+ SMB3_ENC_DEC_KEY_SIZE);
if (rc)
return rc;
}
@@ -442,14 +452,23 @@ generate_smb3signingkey(struct cifs_ses *ses,
*/
cifs_dbg(VFS, "Session Id %*ph\n", (int)sizeof(ses->Suid),
&ses->Suid);
+ cifs_dbg(VFS, "Cipher type %d\n", server->cipher_type);
cifs_dbg(VFS, "Session Key %*ph\n",
SMB2_NTLMV2_SESSKEY_SIZE, ses->auth_key.response);
cifs_dbg(VFS, "Signing Key %*ph\n",
SMB3_SIGN_KEY_SIZE, ses->smb3signingkey);
- cifs_dbg(VFS, "ServerIn Key %*ph\n",
- SMB3_SIGN_KEY_SIZE, ses->smb3encryptionkey);
- cifs_dbg(VFS, "ServerOut Key %*ph\n",
- SMB3_SIGN_KEY_SIZE, ses->smb3decryptionkey);
+ if ((server->cipher_type == SMB2_ENCRYPTION_AES256_CCM) ||
+ (server->cipher_type == SMB2_ENCRYPTION_AES256_GCM)) {
+ cifs_dbg(VFS, "ServerIn Key %*ph\n",
+ SMB3_GCM256_CRYPTKEY_SIZE, ses->smb3encryptionkey);
+ cifs_dbg(VFS, "ServerOut Key %*ph\n",
+ SMB3_GCM256_CRYPTKEY_SIZE, ses->smb3decryptionkey);
+ } else {
+ cifs_dbg(VFS, "ServerIn Key %*ph\n",
+ SMB3_GCM128_CRYPTKEY_SIZE, ses->smb3encryptionkey);
+ cifs_dbg(VFS, "ServerOut Key %*ph\n",
+ SMB3_GCM128_CRYPTKEY_SIZE, ses->smb3decryptionkey);
+ }
#endif
return rc;
}
diff --git a/fs/cifs/transport.c b/fs/cifs/transport.c
index 007d99437c77..c1725b55f364 100644
--- a/fs/cifs/transport.c
+++ b/fs/cifs/transport.c
@@ -1196,9 +1196,12 @@ compound_send_recv(const unsigned int xid, struct cifs_ses *ses,
/*
* Compounding is never used during session establish.
*/
- if ((ses->status == CifsNew) || (optype & CIFS_NEG_OP) || (optype & CIFS_SESS_OP))
+ if ((ses->status == CifsNew) || (optype & CIFS_NEG_OP) || (optype & CIFS_SESS_OP)) {
+ mutex_lock(&server->srv_mutex);
smb311_update_preauth_hash(ses, rqst[0].rq_iov,
rqst[0].rq_nvec);
+ mutex_unlock(&server->srv_mutex);
+ }
for (i = 0; i < num_rqst; i++) {
rc = wait_for_response(server, midQ[i]);
@@ -1266,7 +1269,9 @@ compound_send_recv(const unsigned int xid, struct cifs_ses *ses,
.iov_base = resp_iov[0].iov_base,
.iov_len = resp_iov[0].iov_len
};
+ mutex_lock(&server->srv_mutex);
smb311_update_preauth_hash(ses, &iov, 1);
+ mutex_unlock(&server->srv_mutex);
}
out:
diff --git a/fs/cifs/unc.c b/fs/cifs/unc.c
index 394aa00cea40..f6fc5e343ea4 100644
--- a/fs/cifs/unc.c
+++ b/fs/cifs/unc.c
@@ -50,7 +50,6 @@ char *extract_sharename(const char *unc)
{
const char *src;
char *delim, *dst;
- int len;
/* skip double chars at the beginning */
src = unc + 2;
@@ -60,10 +59,9 @@ char *extract_sharename(const char *unc)
if (!delim)
return ERR_PTR(-EINVAL);
delim++;
- len = strlen(delim);
/* caller has to free the memory */
- dst = kstrndup(delim, len, GFP_KERNEL);
+ dst = kstrdup(delim, GFP_KERNEL);
if (!dst)
return ERR_PTR(-ENOMEM);
diff --git a/fs/cifs/xattr.c b/fs/cifs/xattr.c
index 41a611e76bb7..e351b945135b 100644
--- a/fs/cifs/xattr.c
+++ b/fs/cifs/xattr.c
@@ -53,7 +53,7 @@ enum { XATTR_USER, XATTR_CIFS_ACL, XATTR_ACL_ACCESS, XATTR_ACL_DEFAULT,
XATTR_CIFS_NTSD, XATTR_CIFS_NTSD_FULL };
static int cifs_attrib_set(unsigned int xid, struct cifs_tcon *pTcon,
- struct inode *inode, char *full_path,
+ struct inode *inode, const char *full_path,
const void *value, size_t size)
{
ssize_t rc = -EOPNOTSUPP;
@@ -77,7 +77,7 @@ static int cifs_attrib_set(unsigned int xid, struct cifs_tcon *pTcon,
}
static int cifs_creation_time_set(unsigned int xid, struct cifs_tcon *pTcon,
- struct inode *inode, char *full_path,
+ struct inode *inode, const char *full_path,
const void *value, size_t size)
{
ssize_t rc = -EOPNOTSUPP;
@@ -112,7 +112,8 @@ static int cifs_xattr_set(const struct xattr_handler *handler,
struct cifs_sb_info *cifs_sb = CIFS_SB(sb);
struct tcon_link *tlink;
struct cifs_tcon *pTcon;
- char *full_path;
+ const char *full_path;
+ void *page;
tlink = cifs_sb_tlink(cifs_sb);
if (IS_ERR(tlink))
@@ -120,10 +121,11 @@ static int cifs_xattr_set(const struct xattr_handler *handler,
pTcon = tlink_tcon(tlink);
xid = get_xid();
+ page = alloc_dentry_path();
- full_path = build_path_from_dentry(dentry);
- if (full_path == NULL) {
- rc = -ENOMEM;
+ full_path = build_path_from_dentry(dentry, page);
+ if (IS_ERR(full_path)) {
+ rc = PTR_ERR(full_path);
goto out;
}
/* return dos attributes as pseudo xattr */
@@ -235,7 +237,7 @@ static int cifs_xattr_set(const struct xattr_handler *handler,
}
out:
- kfree(full_path);
+ free_dentry_path(page);
free_xid(xid);
cifs_put_tlink(tlink);
return rc;
@@ -297,7 +299,8 @@ static int cifs_xattr_get(const struct xattr_handler *handler,
struct cifs_sb_info *cifs_sb = CIFS_SB(sb);
struct tcon_link *tlink;
struct cifs_tcon *pTcon;
- char *full_path;
+ const char *full_path;
+ void *page;
tlink = cifs_sb_tlink(cifs_sb);
if (IS_ERR(tlink))
@@ -305,10 +308,11 @@ static int cifs_xattr_get(const struct xattr_handler *handler,
pTcon = tlink_tcon(tlink);
xid = get_xid();
+ page = alloc_dentry_path();
- full_path = build_path_from_dentry(dentry);
- if (full_path == NULL) {
- rc = -ENOMEM;
+ full_path = build_path_from_dentry(dentry, page);
+ if (IS_ERR(full_path)) {
+ rc = PTR_ERR(full_path);
goto out;
}
@@ -401,7 +405,7 @@ static int cifs_xattr_get(const struct xattr_handler *handler,
rc = -EOPNOTSUPP;
out:
- kfree(full_path);
+ free_dentry_path(page);
free_xid(xid);
cifs_put_tlink(tlink);
return rc;
@@ -414,7 +418,8 @@ ssize_t cifs_listxattr(struct dentry *direntry, char *data, size_t buf_size)
struct cifs_sb_info *cifs_sb = CIFS_SB(direntry->d_sb);
struct tcon_link *tlink;
struct cifs_tcon *pTcon;
- char *full_path;
+ const char *full_path;
+ void *page;
if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NO_XATTR)
return -EOPNOTSUPP;
@@ -425,10 +430,11 @@ ssize_t cifs_listxattr(struct dentry *direntry, char *data, size_t buf_size)
pTcon = tlink_tcon(tlink);
xid = get_xid();
+ page = alloc_dentry_path();
- full_path = build_path_from_dentry(direntry);
- if (full_path == NULL) {
- rc = -ENOMEM;
+ full_path = build_path_from_dentry(direntry, page);
+ if (IS_ERR(full_path)) {
+ rc = PTR_ERR(full_path);
goto list_ea_exit;
}
/* return dos attributes as pseudo xattr */
@@ -442,7 +448,7 @@ ssize_t cifs_listxattr(struct dentry *direntry, char *data, size_t buf_size)
rc = pTcon->ses->server->ops->query_all_EAs(xid, pTcon,
full_path, NULL, data, buf_size, cifs_sb);
list_ea_exit:
- kfree(full_path);
+ free_dentry_path(page);
free_xid(xid);
cifs_put_tlink(tlink);
return rc;
diff --git a/fs/coda/file.c b/fs/coda/file.c
index 128d63df5bfb..ef5ca22bfb3e 100644
--- a/fs/coda/file.c
+++ b/fs/coda/file.c
@@ -175,10 +175,10 @@ coda_file_mmap(struct file *coda_file, struct vm_area_struct *vma)
ret = call_mmap(vma->vm_file, vma);
if (ret) {
- /* if call_mmap fails, our caller will put coda_file so we
- * should drop the reference to the host_file that we got.
+ /* if call_mmap fails, our caller will put host_file so we
+ * should drop the reference to the coda_file that we got.
*/
- fput(host_file);
+ fput(coda_file);
kfree(cvm_ops);
} else {
/* here we add redirects for the open/close vm_operations */
diff --git a/fs/coredump.c b/fs/coredump.c
index 1c0fdc1aa70b..2868e3e171ae 100644
--- a/fs/coredump.c
+++ b/fs/coredump.c
@@ -809,6 +809,16 @@ void do_coredump(const kernel_siginfo_t *siginfo)
}
file_start_write(cprm.file);
core_dumped = binfmt->core_dump(&cprm);
+ /*
+ * Ensures that file size is big enough to contain the current
+ * file postion. This prevents gdb from complaining about
+ * a truncated file if the last "write" to the file was
+ * dump_skip.
+ */
+ if (cprm.to_skip) {
+ cprm.to_skip--;
+ dump_emit(&cprm, "", 1);
+ }
file_end_write(cprm.file);
}
if (ispipe && core_pipe_limit)
@@ -835,7 +845,7 @@ fail:
* do on a core-file: use only these functions to write out all the
* necessary info.
*/
-int dump_emit(struct coredump_params *cprm, const void *addr, int nr)
+static int __dump_emit(struct coredump_params *cprm, const void *addr, int nr)
{
struct file *file = cprm->file;
loff_t pos = file->f_pos;
@@ -855,9 +865,8 @@ int dump_emit(struct coredump_params *cprm, const void *addr, int nr)
return 1;
}
-EXPORT_SYMBOL(dump_emit);
-int dump_skip(struct coredump_params *cprm, size_t nr)
+static int __dump_skip(struct coredump_params *cprm, size_t nr)
{
static char zeroes[PAGE_SIZE];
struct file *file = cprm->file;
@@ -869,13 +878,35 @@ int dump_skip(struct coredump_params *cprm, size_t nr)
return 1;
} else {
while (nr > PAGE_SIZE) {
- if (!dump_emit(cprm, zeroes, PAGE_SIZE))
+ if (!__dump_emit(cprm, zeroes, PAGE_SIZE))
return 0;
nr -= PAGE_SIZE;
}
- return dump_emit(cprm, zeroes, nr);
+ return __dump_emit(cprm, zeroes, nr);
}
}
+
+int dump_emit(struct coredump_params *cprm, const void *addr, int nr)
+{
+ if (cprm->to_skip) {
+ if (!__dump_skip(cprm, cprm->to_skip))
+ return 0;
+ cprm->to_skip = 0;
+ }
+ return __dump_emit(cprm, addr, nr);
+}
+EXPORT_SYMBOL(dump_emit);
+
+void dump_skip_to(struct coredump_params *cprm, unsigned long pos)
+{
+ cprm->to_skip = pos - cprm->pos;
+}
+EXPORT_SYMBOL(dump_skip_to);
+
+void dump_skip(struct coredump_params *cprm, size_t nr)
+{
+ cprm->to_skip += nr;
+}
EXPORT_SYMBOL(dump_skip);
#ifdef CONFIG_ELF_CORE
@@ -902,11 +933,11 @@ int dump_user_range(struct coredump_params *cprm, unsigned long start,
stop = !dump_emit(cprm, kaddr, PAGE_SIZE);
kunmap_local(kaddr);
put_page(page);
+ if (stop)
+ return 0;
} else {
- stop = !dump_skip(cprm, PAGE_SIZE);
+ dump_skip(cprm, PAGE_SIZE);
}
- if (stop)
- return 0;
}
return 1;
}
@@ -914,33 +945,16 @@ int dump_user_range(struct coredump_params *cprm, unsigned long start,
int dump_align(struct coredump_params *cprm, int align)
{
- unsigned mod = cprm->pos & (align - 1);
+ unsigned mod = (cprm->pos + cprm->to_skip) & (align - 1);
if (align & (align - 1))
return 0;
- return mod ? dump_skip(cprm, align - mod) : 1;
+ if (mod)
+ cprm->to_skip += align - mod;
+ return 1;
}
EXPORT_SYMBOL(dump_align);
/*
- * Ensures that file size is big enough to contain the current file
- * postion. This prevents gdb from complaining about a truncated file
- * if the last "write" to the file was dump_skip.
- */
-void dump_truncate(struct coredump_params *cprm)
-{
- struct file *file = cprm->file;
- loff_t offset;
-
- if (file->f_op->llseek && file->f_op->llseek != no_llseek) {
- offset = file->f_op->llseek(file, 0, SEEK_CUR);
- if (i_size_read(file->f_mapping->host) < offset)
- do_truncate(file_mnt_user_ns(file), file->f_path.dentry,
- offset, 0, file);
- }
-}
-EXPORT_SYMBOL(dump_truncate);
-
-/*
* The purpose of always_dump_vma() is to make sure that special kernel mappings
* that are useful for post-mortem analysis are included in every core dump.
* In that way we ensure that the core dump is fully interpretable later
diff --git a/fs/crypto/Kconfig b/fs/crypto/Kconfig
index a5f5c30368a2..2d0c8922f635 100644
--- a/fs/crypto/Kconfig
+++ b/fs/crypto/Kconfig
@@ -14,16 +14,30 @@ config FS_ENCRYPTION
F2FS and UBIFS make use of this feature.
# Filesystems supporting encryption must select this if FS_ENCRYPTION. This
-# allows the algorithms to be built as modules when all the filesystems are.
+# allows the algorithms to be built as modules when all the filesystems are,
+# whereas selecting them from FS_ENCRYPTION would force them to be built-in.
+#
+# Note: this option only pulls in the algorithms that filesystem encryption
+# needs "by default". If userspace will use "non-default" encryption modes such
+# as Adiantum encryption, then those other modes need to be explicitly enabled
+# in the crypto API; see Documentation/filesystems/fscrypt.rst for details.
+#
+# Also note that this option only pulls in the generic implementations of the
+# algorithms, not any per-architecture optimized implementations. It is
+# strongly recommended to enable optimized implementations too. It is safe to
+# disable these generic implementations if corresponding optimized
+# implementations will always be available too; for this reason, these are soft
+# dependencies ('imply' rather than 'select'). Only disable these generic
+# implementations if you're sure they will never be needed, though.
config FS_ENCRYPTION_ALGS
tristate
- select CRYPTO_AES
- select CRYPTO_CBC
- select CRYPTO_CTS
- select CRYPTO_ECB
- select CRYPTO_HMAC
- select CRYPTO_SHA512
- select CRYPTO_XTS
+ imply CRYPTO_AES
+ imply CRYPTO_CBC
+ imply CRYPTO_CTS
+ imply CRYPTO_ECB
+ imply CRYPTO_HMAC
+ imply CRYPTO_SHA512
+ imply CRYPTO_XTS
config FS_ENCRYPTION_INLINE_CRYPT
bool "Enable fscrypt to use inline crypto"
diff --git a/fs/d_path.c b/fs/d_path.c
index a69e2cd36e6e..270d62133996 100644
--- a/fs/d_path.c
+++ b/fs/d_path.c
@@ -326,9 +326,9 @@ char *simple_dname(struct dentry *dentry, char *buffer, int buflen)
/*
* Write full pathname from the root of the filesystem into the buffer.
*/
-static char *__dentry_path(struct dentry *d, char *buf, int buflen)
+static char *__dentry_path(const struct dentry *d, char *buf, int buflen)
{
- struct dentry *dentry;
+ const struct dentry *dentry;
char *end, *retval;
int len, seq = 0;
int error = 0;
@@ -347,7 +347,7 @@ restart:
*retval = '/';
read_seqbegin_or_lock(&rename_lock, &seq);
while (!IS_ROOT(dentry)) {
- struct dentry *parent = dentry->d_parent;
+ const struct dentry *parent = dentry->d_parent;
prefetch(parent);
error = prepend_name(&end, &len, &dentry->d_name);
@@ -371,13 +371,13 @@ Elong:
return ERR_PTR(-ENAMETOOLONG);
}
-char *dentry_path_raw(struct dentry *dentry, char *buf, int buflen)
+char *dentry_path_raw(const struct dentry *dentry, char *buf, int buflen)
{
return __dentry_path(dentry, buf, buflen);
}
EXPORT_SYMBOL(dentry_path_raw);
-char *dentry_path(struct dentry *dentry, char *buf, int buflen)
+char *dentry_path(const struct dentry *dentry, char *buf, int buflen)
{
char *p = NULL;
char *retval;
diff --git a/fs/dcache.c b/fs/dcache.c
index 7d24ff7eb206..cf871a81f4fd 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -84,6 +84,8 @@ const struct qstr empty_name = QSTR_INIT("", 0);
EXPORT_SYMBOL(empty_name);
const struct qstr slash_name = QSTR_INIT("/", 1);
EXPORT_SYMBOL(slash_name);
+const struct qstr dotdot_name = QSTR_INIT("..", 2);
+EXPORT_SYMBOL(dotdot_name);
/*
* This is the single most critical data structure when it comes
diff --git a/fs/debugfs/file.c b/fs/debugfs/file.c
index 686e0ad28788..e813acfaa6e8 100644
--- a/fs/debugfs/file.c
+++ b/fs/debugfs/file.c
@@ -773,7 +773,7 @@ EXPORT_SYMBOL_GPL(debugfs_create_atomic_t);
ssize_t debugfs_read_file_bool(struct file *file, char __user *user_buf,
size_t count, loff_t *ppos)
{
- char buf[3];
+ char buf[2];
bool val;
int r;
struct dentry *dentry = F_DENTRY(file);
@@ -789,7 +789,6 @@ ssize_t debugfs_read_file_bool(struct file *file, char __user *user_buf,
else
buf[0] = 'N';
buf[1] = '\n';
- buf[2] = 0x00;
return simple_read_from_buffer(user_buf, count, ppos, buf, 2);
}
EXPORT_SYMBOL_GPL(debugfs_read_file_bool);
@@ -865,6 +864,97 @@ struct dentry *debugfs_create_bool(const char *name, umode_t mode,
}
EXPORT_SYMBOL_GPL(debugfs_create_bool);
+ssize_t debugfs_read_file_str(struct file *file, char __user *user_buf,
+ size_t count, loff_t *ppos)
+{
+ struct dentry *dentry = F_DENTRY(file);
+ char *str, *copy = NULL;
+ int copy_len, len;
+ ssize_t ret;
+
+ ret = debugfs_file_get(dentry);
+ if (unlikely(ret))
+ return ret;
+
+ str = *(char **)file->private_data;
+ len = strlen(str) + 1;
+ copy = kmalloc(len, GFP_KERNEL);
+ if (!copy) {
+ debugfs_file_put(dentry);
+ return -ENOMEM;
+ }
+
+ copy_len = strscpy(copy, str, len);
+ debugfs_file_put(dentry);
+ if (copy_len < 0) {
+ kfree(copy);
+ return copy_len;
+ }
+
+ copy[copy_len] = '\n';
+
+ ret = simple_read_from_buffer(user_buf, count, ppos, copy, copy_len);
+ kfree(copy);
+
+ return ret;
+}
+
+static ssize_t debugfs_write_file_str(struct file *file, const char __user *user_buf,
+ size_t count, loff_t *ppos)
+{
+ /* This is really only for read-only strings */
+ return -EINVAL;
+}
+
+static const struct file_operations fops_str = {
+ .read = debugfs_read_file_str,
+ .write = debugfs_write_file_str,
+ .open = simple_open,
+ .llseek = default_llseek,
+};
+
+static const struct file_operations fops_str_ro = {
+ .read = debugfs_read_file_str,
+ .open = simple_open,
+ .llseek = default_llseek,
+};
+
+static const struct file_operations fops_str_wo = {
+ .write = debugfs_write_file_str,
+ .open = simple_open,
+ .llseek = default_llseek,
+};
+
+/**
+ * debugfs_create_str - create a debugfs file that is used to read and write a string value
+ * @name: a pointer to a string containing the name of the file to create.
+ * @mode: the permission that the file should have
+ * @parent: a pointer to the parent dentry for this file. This should be a
+ * directory dentry if set. If this parameter is %NULL, then the
+ * file will be created in the root of the debugfs filesystem.
+ * @value: a pointer to the variable that the file should read to and write
+ * from.
+ *
+ * This function creates a file in debugfs with the given name that
+ * contains the value of the variable @value. If the @mode variable is so
+ * set, it can be read from, and written to.
+ *
+ * This function will return a pointer to a dentry if it succeeds. This
+ * pointer must be passed to the debugfs_remove() function when the file is
+ * to be removed (no automatic cleanup happens if your module is unloaded,
+ * you are responsible here.) If an error occurs, ERR_PTR(-ERROR) will be
+ * returned.
+ *
+ * If debugfs is not enabled in the kernel, the value ERR_PTR(-ENODEV) will
+ * be returned.
+ */
+void debugfs_create_str(const char *name, umode_t mode,
+ struct dentry *parent, char **value)
+{
+ debugfs_create_mode_unsafe(name, mode, parent, value, &fops_str,
+ &fops_str_ro, &fops_str_wo);
+}
+
static ssize_t read_file_blob(struct file *file, char __user *user_buf,
size_t count, loff_t *ppos)
{
diff --git a/fs/debugfs/inode.c b/fs/debugfs/inode.c
index 22e86ae4dd5a..1d252164d97b 100644
--- a/fs/debugfs/inode.c
+++ b/fs/debugfs/inode.c
@@ -35,7 +35,7 @@
static struct vfsmount *debugfs_mount;
static int debugfs_mount_count;
static bool debugfs_registered;
-static unsigned int debugfs_allow = DEFAULT_DEBUGFS_ALLOW_BITS;
+static unsigned int debugfs_allow __ro_after_init = DEFAULT_DEBUGFS_ALLOW_BITS;
/*
* Don't allow access attributes to be changed whilst the kernel is locked down
diff --git a/fs/direct-io.c b/fs/direct-io.c
index b61491bf3166..b2e86e739d7a 100644
--- a/fs/direct-io.c
+++ b/fs/direct-io.c
@@ -812,6 +812,7 @@ submit_page_section(struct dio *dio, struct dio_submit *sdio, struct page *page,
struct buffer_head *map_bh)
{
int ret = 0;
+ int boundary = sdio->boundary; /* dio_send_cur_page may clear it */
if (dio->op == REQ_OP_WRITE) {
/*
@@ -850,10 +851,10 @@ submit_page_section(struct dio *dio, struct dio_submit *sdio, struct page *page,
sdio->cur_page_fs_offset = sdio->block_in_file << sdio->blkbits;
out:
/*
- * If sdio->boundary then we want to schedule the IO now to
+ * If boundary then we want to schedule the IO now to
* avoid metadata seeks.
*/
- if (sdio->boundary) {
+ if (boundary) {
ret = dio_send_cur_page(dio, sdio, map_bh);
if (sdio->bio)
dio_bio_submit(dio, sdio);
diff --git a/fs/dlm/config.c b/fs/dlm/config.c
index 49c5f9407098..88d95d96e36c 100644
--- a/fs/dlm/config.c
+++ b/fs/dlm/config.c
@@ -125,7 +125,7 @@ static ssize_t cluster_cluster_name_store(struct config_item *item,
CONFIGFS_ATTR(cluster_, cluster_name);
static ssize_t cluster_set(struct dlm_cluster *cl, unsigned int *cl_field,
- int *info_field, bool (*check_cb)(unsigned int x),
+ int *info_field, int (*check_cb)(unsigned int x),
const char *buf, size_t len)
{
unsigned int x;
@@ -137,8 +137,11 @@ static ssize_t cluster_set(struct dlm_cluster *cl, unsigned int *cl_field,
if (rc)
return rc;
- if (check_cb && check_cb(x))
- return -EINVAL;
+ if (check_cb) {
+ rc = check_cb(x);
+ if (rc)
+ return rc;
+ }
*cl_field = x;
*info_field = x;
@@ -161,17 +164,53 @@ static ssize_t cluster_##name##_show(struct config_item *item, char *buf) \
} \
CONFIGFS_ATTR(cluster_, name);
-static bool dlm_check_zero(unsigned int x)
+static int dlm_check_protocol_and_dlm_running(unsigned int x)
+{
+ switch (x) {
+ case 0:
+ /* TCP */
+ break;
+ case 1:
+ /* SCTP */
+ break;
+ default:
+ return -EINVAL;
+ }
+
+ if (dlm_allow_conn)
+ return -EBUSY;
+
+ return 0;
+}
+
+static int dlm_check_zero_and_dlm_running(unsigned int x)
+{
+ if (!x)
+ return -EINVAL;
+
+ if (dlm_allow_conn)
+ return -EBUSY;
+
+ return 0;
+}
+
+static int dlm_check_zero(unsigned int x)
{
- return !x;
+ if (!x)
+ return -EINVAL;
+
+ return 0;
}
-static bool dlm_check_buffer_size(unsigned int x)
+static int dlm_check_buffer_size(unsigned int x)
{
- return (x < DEFAULT_BUFFER_SIZE);
+ if (x < DEFAULT_BUFFER_SIZE)
+ return -EINVAL;
+
+ return 0;
}
-CLUSTER_ATTR(tcp_port, dlm_check_zero);
+CLUSTER_ATTR(tcp_port, dlm_check_zero_and_dlm_running);
CLUSTER_ATTR(buffer_size, dlm_check_buffer_size);
CLUSTER_ATTR(rsbtbl_size, dlm_check_zero);
CLUSTER_ATTR(recover_timer, dlm_check_zero);
@@ -179,7 +218,7 @@ CLUSTER_ATTR(toss_secs, dlm_check_zero);
CLUSTER_ATTR(scan_secs, dlm_check_zero);
CLUSTER_ATTR(log_debug, NULL);
CLUSTER_ATTR(log_info, NULL);
-CLUSTER_ATTR(protocol, NULL);
+CLUSTER_ATTR(protocol, dlm_check_protocol_and_dlm_running);
CLUSTER_ATTR(mark, NULL);
CLUSTER_ATTR(timewarn_cs, dlm_check_zero);
CLUSTER_ATTR(waitwarn_us, NULL);
@@ -688,6 +727,7 @@ static ssize_t comm_mark_show(struct config_item *item, char *buf)
static ssize_t comm_mark_store(struct config_item *item, const char *buf,
size_t len)
{
+ struct dlm_comm *comm;
unsigned int mark;
int rc;
@@ -695,7 +735,15 @@ static ssize_t comm_mark_store(struct config_item *item, const char *buf,
if (rc)
return rc;
- config_item_to_comm(item)->mark = mark;
+ if (mark == 0)
+ mark = dlm_config.ci_mark;
+
+ comm = config_item_to_comm(item);
+ rc = dlm_lowcomms_nodes_set_mark(comm->nodeid, mark);
+ if (rc)
+ return rc;
+
+ comm->mark = mark;
return len;
}
@@ -870,24 +918,6 @@ int dlm_comm_seq(int nodeid, uint32_t *seq)
return 0;
}
-void dlm_comm_mark(int nodeid, unsigned int *mark)
-{
- struct dlm_comm *cm;
-
- cm = get_comm(nodeid);
- if (!cm) {
- *mark = dlm_config.ci_mark;
- return;
- }
-
- if (cm->mark)
- *mark = cm->mark;
- else
- *mark = dlm_config.ci_mark;
-
- put_comm(cm);
-}
-
int dlm_our_nodeid(void)
{
return local_comm ? local_comm->nodeid : 0;
diff --git a/fs/dlm/config.h b/fs/dlm/config.h
index c210250a2581..d2cd4bd20313 100644
--- a/fs/dlm/config.h
+++ b/fs/dlm/config.h
@@ -48,7 +48,6 @@ void dlm_config_exit(void);
int dlm_config_nodes(char *lsname, struct dlm_config_node **nodes_out,
int *count_out);
int dlm_comm_seq(int nodeid, uint32_t *seq);
-void dlm_comm_mark(int nodeid, unsigned int *mark);
int dlm_our_nodeid(void);
int dlm_our_addr(struct sockaddr_storage *addr, int num);
diff --git a/fs/dlm/debug_fs.c b/fs/dlm/debug_fs.c
index d6bbccb0ed15..d5bd990bcab8 100644
--- a/fs/dlm/debug_fs.c
+++ b/fs/dlm/debug_fs.c
@@ -542,6 +542,7 @@ static void *table_seq_next(struct seq_file *seq, void *iter_ptr, loff_t *pos)
if (bucket >= ls->ls_rsbtbl_size) {
kfree(ri);
+ ++*pos;
return NULL;
}
tree = toss ? &ls->ls_rsbtbl[bucket].toss : &ls->ls_rsbtbl[bucket].keep;
diff --git a/fs/dlm/lock.c b/fs/dlm/lock.c
index 002123efc6b0..b93df39d0915 100644
--- a/fs/dlm/lock.c
+++ b/fs/dlm/lock.c
@@ -3541,8 +3541,6 @@ static int _create_message(struct dlm_ls *ls, int mb_len,
if (!mh)
return -ENOBUFS;
- memset(mb, 0, mb_len);
-
ms = (struct dlm_message *) mb;
ms->m_header.h_version = (DLM_HEADER_MAJOR | DLM_HEADER_MINOR);
diff --git a/fs/dlm/lockspace.c b/fs/dlm/lockspace.c
index 561dcad08ad6..c14cf2b7faab 100644
--- a/fs/dlm/lockspace.c
+++ b/fs/dlm/lockspace.c
@@ -404,12 +404,6 @@ static int threads_start(void)
return error;
}
-static void threads_stop(void)
-{
- dlm_scand_stop();
- dlm_lowcomms_stop();
-}
-
static int new_lockspace(const char *name, const char *cluster,
uint32_t flags, int lvblen,
const struct dlm_lockspace_ops *ops, void *ops_arg,
@@ -702,8 +696,11 @@ int dlm_new_lockspace(const char *name, const char *cluster,
ls_count++;
if (error > 0)
error = 0;
- if (!ls_count)
- threads_stop();
+ if (!ls_count) {
+ dlm_scand_stop();
+ dlm_lowcomms_shutdown();
+ dlm_lowcomms_stop();
+ }
out:
mutex_unlock(&ls_lock);
return error;
@@ -788,6 +785,11 @@ static int release_lockspace(struct dlm_ls *ls, int force)
dlm_recoverd_stop(ls);
+ if (ls_count == 1) {
+ dlm_scand_stop();
+ dlm_lowcomms_shutdown();
+ }
+
dlm_callback_stop(ls);
remove_lockspace(ls);
@@ -880,7 +882,7 @@ int dlm_release_lockspace(void *lockspace, int force)
if (!error)
ls_count--;
if (!ls_count)
- threads_stop();
+ dlm_lowcomms_stop();
mutex_unlock(&ls_lock);
return error;
diff --git a/fs/dlm/lowcomms.c b/fs/dlm/lowcomms.c
index 372c34ff8594..166e36fcf3e4 100644
--- a/fs/dlm/lowcomms.c
+++ b/fs/dlm/lowcomms.c
@@ -102,6 +102,9 @@ struct listen_connection {
struct work_struct rwork;
};
+#define DLM_WQ_REMAIN_BYTES(e) (PAGE_SIZE - e->end)
+#define DLM_WQ_LENGTH_BYTES(e) (e->end - e->offset)
+
/* An entry waiting to be sent */
struct writequeue_entry {
struct list_head list;
@@ -116,6 +119,7 @@ struct writequeue_entry {
struct dlm_node_addr {
struct list_head list;
int nodeid;
+ int mark;
int addr_count;
int curr_addr_index;
struct sockaddr_storage *addr[DLM_MAX_ADDR_COUNT];
@@ -134,7 +138,7 @@ static DEFINE_SPINLOCK(dlm_node_addrs_spin);
static struct listen_connection listen_con;
static struct sockaddr_storage *dlm_local_addr[DLM_MAX_ADDR_COUNT];
static int dlm_local_count;
-static int dlm_allow_conn;
+int dlm_allow_conn;
/* Work queues */
static struct workqueue_struct *recv_workqueue;
@@ -303,7 +307,8 @@ static int addr_compare(const struct sockaddr_storage *x,
}
static int nodeid_to_addr(int nodeid, struct sockaddr_storage *sas_out,
- struct sockaddr *sa_out, bool try_new_addr)
+ struct sockaddr *sa_out, bool try_new_addr,
+ unsigned int *mark)
{
struct sockaddr_storage sas;
struct dlm_node_addr *na;
@@ -331,6 +336,8 @@ static int nodeid_to_addr(int nodeid, struct sockaddr_storage *sas_out,
if (!na->addr_count)
return -ENOENT;
+ *mark = na->mark;
+
if (sas_out)
memcpy(sas_out, &sas, sizeof(struct sockaddr_storage));
@@ -350,7 +357,8 @@ static int nodeid_to_addr(int nodeid, struct sockaddr_storage *sas_out,
return 0;
}
-static int addr_to_nodeid(struct sockaddr_storage *addr, int *nodeid)
+static int addr_to_nodeid(struct sockaddr_storage *addr, int *nodeid,
+ unsigned int *mark)
{
struct dlm_node_addr *na;
int rv = -EEXIST;
@@ -364,6 +372,7 @@ static int addr_to_nodeid(struct sockaddr_storage *addr, int *nodeid)
for (addr_i = 0; addr_i < na->addr_count; addr_i++) {
if (addr_compare(na->addr[addr_i], addr)) {
*nodeid = na->nodeid;
+ *mark = na->mark;
rv = 0;
goto unlock;
}
@@ -412,6 +421,7 @@ int dlm_lowcomms_addr(int nodeid, struct sockaddr_storage *addr, int len)
new_node->nodeid = nodeid;
new_node->addr[0] = new_addr;
new_node->addr_count = 1;
+ new_node->mark = dlm_config.ci_mark;
list_add(&new_node->list, &dlm_node_addrs);
spin_unlock(&dlm_node_addrs_spin);
return 0;
@@ -519,6 +529,23 @@ int dlm_lowcomms_connect_node(int nodeid)
return 0;
}
+int dlm_lowcomms_nodes_set_mark(int nodeid, unsigned int mark)
+{
+ struct dlm_node_addr *na;
+
+ spin_lock(&dlm_node_addrs_spin);
+ na = find_node_addr(nodeid);
+ if (!na) {
+ spin_unlock(&dlm_node_addrs_spin);
+ return -ENOENT;
+ }
+
+ na->mark = mark;
+ spin_unlock(&dlm_node_addrs_spin);
+
+ return 0;
+}
+
static void lowcomms_error_report(struct sock *sk)
{
struct connection *con;
@@ -685,10 +712,7 @@ static void shutdown_connection(struct connection *con)
{
int ret;
- if (cancel_work_sync(&con->swork)) {
- log_print("canceled swork for node %d", con->nodeid);
- clear_bit(CF_WRITE_PENDING, &con->flags);
- }
+ flush_work(&con->swork);
mutex_lock(&con->sock_mutex);
/* nothing to shutdown */
@@ -867,7 +891,7 @@ static int accept_from_sock(struct listen_connection *con)
/* Get the new node's NODEID */
make_sockaddr(&peeraddr, 0, &len);
- if (addr_to_nodeid(&peeraddr, &nodeid)) {
+ if (addr_to_nodeid(&peeraddr, &nodeid, &mark)) {
unsigned char *b=(unsigned char *)&peeraddr;
log_print("connect from non cluster node");
print_hex_dump_bytes("ss: ", DUMP_PREFIX_NONE,
@@ -876,9 +900,6 @@ static int accept_from_sock(struct listen_connection *con)
return -1;
}
- dlm_comm_mark(nodeid, &mark);
- sock_set_mark(newsock->sk, mark);
-
log_print("got connection from %d", nodeid);
/* Check to see if we already have a connection to this node. This
@@ -892,6 +913,8 @@ static int accept_from_sock(struct listen_connection *con)
goto accept_err;
}
+ sock_set_mark(newsock->sk, mark);
+
mutex_lock(&newcon->sock_mutex);
if (newcon->sock) {
struct connection *othercon = newcon->othercon;
@@ -908,16 +931,18 @@ static int accept_from_sock(struct listen_connection *con)
result = dlm_con_init(othercon, nodeid);
if (result < 0) {
kfree(othercon);
+ mutex_unlock(&newcon->sock_mutex);
goto accept_err;
}
+ lockdep_set_subclass(&othercon->sock_mutex, 1);
newcon->othercon = othercon;
} else {
/* close other sock con if we have something new */
close_connection(othercon, false, true, false);
}
- mutex_lock_nested(&othercon->sock_mutex, 1);
+ mutex_lock(&othercon->sock_mutex);
add_sock(newsock, othercon);
addcon = othercon;
mutex_unlock(&othercon->sock_mutex);
@@ -930,6 +955,7 @@ static int accept_from_sock(struct listen_connection *con)
addcon = newcon;
}
+ set_bit(CF_CONNECTED, &addcon->flags);
mutex_unlock(&newcon->sock_mutex);
/*
@@ -1015,8 +1041,6 @@ static void sctp_connect_to_sock(struct connection *con)
struct socket *sock;
unsigned int mark;
- dlm_comm_mark(con->nodeid, &mark);
-
mutex_lock(&con->sock_mutex);
/* Some odd races can cause double-connects, ignore them */
@@ -1029,7 +1053,7 @@ static void sctp_connect_to_sock(struct connection *con)
}
memset(&daddr, 0, sizeof(daddr));
- result = nodeid_to_addr(con->nodeid, &daddr, NULL, true);
+ result = nodeid_to_addr(con->nodeid, &daddr, NULL, true, &mark);
if (result < 0) {
log_print("no address for nodeid %d", con->nodeid);
goto out;
@@ -1104,13 +1128,11 @@ out:
static void tcp_connect_to_sock(struct connection *con)
{
struct sockaddr_storage saddr, src_addr;
+ unsigned int mark;
int addr_len;
struct socket *sock = NULL;
- unsigned int mark;
int result;
- dlm_comm_mark(con->nodeid, &mark);
-
mutex_lock(&con->sock_mutex);
if (con->retries++ > MAX_CONNECT_RETRIES)
goto out;
@@ -1125,15 +1147,15 @@ static void tcp_connect_to_sock(struct connection *con)
if (result < 0)
goto out_err;
- sock_set_mark(sock->sk, mark);
-
memset(&saddr, 0, sizeof(saddr));
- result = nodeid_to_addr(con->nodeid, &saddr, NULL, false);
+ result = nodeid_to_addr(con->nodeid, &saddr, NULL, false, &mark);
if (result < 0) {
log_print("no address for nodeid %d", con->nodeid);
goto out_err;
}
+ sock_set_mark(sock->sk, mark);
+
add_sock(sock, con);
/* Bind to our cluster-known address connecting to avoid
@@ -1330,70 +1352,72 @@ static struct writequeue_entry *new_writequeue_entry(struct connection *con,
{
struct writequeue_entry *entry;
- entry = kmalloc(sizeof(struct writequeue_entry), allocation);
+ entry = kzalloc(sizeof(*entry), allocation);
if (!entry)
return NULL;
- entry->page = alloc_page(allocation);
+ entry->page = alloc_page(allocation | __GFP_ZERO);
if (!entry->page) {
kfree(entry);
return NULL;
}
- entry->offset = 0;
- entry->len = 0;
- entry->end = 0;
- entry->users = 0;
entry->con = con;
+ entry->users = 1;
return entry;
}
-void *dlm_lowcomms_get_buffer(int nodeid, int len, gfp_t allocation, char **ppc)
+static struct writequeue_entry *new_wq_entry(struct connection *con, int len,
+ gfp_t allocation, char **ppc)
{
- struct connection *con;
struct writequeue_entry *e;
- int offset = 0;
- if (len > LOWCOMMS_MAX_TX_BUFFER_LEN) {
- BUILD_BUG_ON(PAGE_SIZE < LOWCOMMS_MAX_TX_BUFFER_LEN);
- log_print("failed to allocate a buffer of size %d", len);
- return NULL;
+ spin_lock(&con->writequeue_lock);
+ if (!list_empty(&con->writequeue)) {
+ e = list_last_entry(&con->writequeue, struct writequeue_entry, list);
+ if (DLM_WQ_REMAIN_BYTES(e) >= len) {
+ *ppc = page_address(e->page) + e->end;
+ e->end += len;
+ e->users++;
+ spin_unlock(&con->writequeue_lock);
+
+ return e;
+ }
}
+ spin_unlock(&con->writequeue_lock);
- con = nodeid2con(nodeid, allocation);
- if (!con)
+ e = new_writequeue_entry(con, allocation);
+ if (!e)
return NULL;
+ *ppc = page_address(e->page);
+ e->end += len;
+
spin_lock(&con->writequeue_lock);
- e = list_entry(con->writequeue.prev, struct writequeue_entry, list);
- if ((&e->list == &con->writequeue) ||
- (PAGE_SIZE - e->end < len)) {
- e = NULL;
- } else {
- offset = e->end;
- e->end += len;
- e->users++;
- }
+ list_add_tail(&e->list, &con->writequeue);
spin_unlock(&con->writequeue_lock);
- if (e) {
- got_one:
- *ppc = page_address(e->page) + offset;
- return e;
- }
+ return e;
+};
- e = new_writequeue_entry(con, allocation);
- if (e) {
- spin_lock(&con->writequeue_lock);
- offset = e->end;
- e->end += len;
- e->users++;
- list_add_tail(&e->list, &con->writequeue);
- spin_unlock(&con->writequeue_lock);
- goto got_one;
+void *dlm_lowcomms_get_buffer(int nodeid, int len, gfp_t allocation, char **ppc)
+{
+ struct connection *con;
+
+ if (len > DEFAULT_BUFFER_SIZE ||
+ len < sizeof(struct dlm_header)) {
+ BUILD_BUG_ON(PAGE_SIZE < DEFAULT_BUFFER_SIZE);
+ log_print("failed to allocate a buffer of size %d", len);
+ WARN_ON(1);
+ return NULL;
}
- return NULL;
+
+ con = nodeid2con(nodeid, allocation);
+ if (!con)
+ return NULL;
+
+ return new_wq_entry(con, len, allocation, ppc);
}
void dlm_lowcomms_commit_buffer(void *mh)
@@ -1406,7 +1430,8 @@ void dlm_lowcomms_commit_buffer(void *mh)
users = --e->users;
if (users)
goto out;
- e->len = e->end - e->offset;
+
+ e->len = DLM_WQ_LENGTH_BYTES(e);
spin_unlock(&con->writequeue_lock);
queue_work(send_workqueue, &con->swork);
@@ -1432,11 +1457,10 @@ static void send_to_sock(struct connection *con)
spin_lock(&con->writequeue_lock);
for (;;) {
- e = list_entry(con->writequeue.next, struct writequeue_entry,
- list);
- if ((struct list_head *) e == &con->writequeue)
+ if (list_empty(&con->writequeue))
break;
+ e = list_first_entry(&con->writequeue, struct writequeue_entry, list);
len = e->len;
offset = e->offset;
BUG_ON(len == 0 && e->users == 0);
@@ -1589,6 +1613,29 @@ static int work_start(void)
return 0;
}
+static void shutdown_conn(struct connection *con)
+{
+ if (con->shutdown_action)
+ con->shutdown_action(con);
+}
+
+void dlm_lowcomms_shutdown(void)
+{
+ /* Set all the flags to prevent any
+ * socket activity.
+ */
+ dlm_allow_conn = 0;
+
+ if (recv_workqueue)
+ flush_workqueue(recv_workqueue);
+ if (send_workqueue)
+ flush_workqueue(send_workqueue);
+
+ dlm_close_sock(&listen_con.sock);
+
+ foreach_conn(shutdown_conn);
+}
+
static void _stop_conn(struct connection *con, bool and_other)
{
mutex_lock(&con->sock_mutex);
@@ -1610,12 +1657,6 @@ static void stop_conn(struct connection *con)
_stop_conn(con, true);
}
-static void shutdown_conn(struct connection *con)
-{
- if (con->shutdown_action)
- con->shutdown_action(con);
-}
-
static void connection_release(struct rcu_head *rcu)
{
struct connection *con = container_of(rcu, struct connection, rcu);
@@ -1672,19 +1713,6 @@ static void work_flush(void)
void dlm_lowcomms_stop(void)
{
- /* Set all the flags to prevent any
- socket activity.
- */
- dlm_allow_conn = 0;
-
- if (recv_workqueue)
- flush_workqueue(recv_workqueue);
- if (send_workqueue)
- flush_workqueue(send_workqueue);
-
- dlm_close_sock(&listen_con.sock);
-
- foreach_conn(shutdown_conn);
work_flush();
foreach_conn(free_conn);
work_stop();
diff --git a/fs/dlm/lowcomms.h b/fs/dlm/lowcomms.h
index 0918f9376489..48bbc4e18761 100644
--- a/fs/dlm/lowcomms.h
+++ b/fs/dlm/lowcomms.h
@@ -14,13 +14,18 @@
#define LOWCOMMS_MAX_TX_BUFFER_LEN 4096
+/* switch to check if dlm is running */
+extern int dlm_allow_conn;
+
int dlm_lowcomms_start(void);
+void dlm_lowcomms_shutdown(void);
void dlm_lowcomms_stop(void);
void dlm_lowcomms_exit(void);
int dlm_lowcomms_close(int nodeid);
void *dlm_lowcomms_get_buffer(int nodeid, int len, gfp_t allocation, char **ppc);
void dlm_lowcomms_commit_buffer(void *mh);
int dlm_lowcomms_connect_node(int nodeid);
+int dlm_lowcomms_nodes_set_mark(int nodeid, unsigned int mark);
int dlm_lowcomms_addr(int nodeid, struct sockaddr_storage *addr, int len);
#endif /* __LOWCOMMS_DOT_H__ */
diff --git a/fs/dlm/midcomms.c b/fs/dlm/midcomms.c
index fde3a6afe4be..1c6654a21ec4 100644
--- a/fs/dlm/midcomms.c
+++ b/fs/dlm/midcomms.c
@@ -22,8 +22,6 @@
* into packets and sends them to the comms layer.
*/
-#include <asm/unaligned.h>
-
#include "dlm_internal.h"
#include "lowcomms.h"
#include "config.h"
@@ -45,13 +43,22 @@ int dlm_process_incoming_buffer(int nodeid, unsigned char *buf, int len)
while (len >= sizeof(struct dlm_header)) {
hd = (struct dlm_header *)ptr;
- /* no message should be more than this otherwise we
- * cannot deliver this message to upper layers
+ /* no message should be more than DEFAULT_BUFFER_SIZE or
+ * less than dlm_header size.
+ *
+ * Some messages does not have a 8 byte length boundary yet
+ * which can occur in a unaligned memory access of some dlm
+ * messages. However this problem need to be fixed at the
+ * sending side, for now it seems nobody run into architecture
+ * related issues yet but it slows down some processing.
+ * Fixing this issue should be scheduled in future by doing
+ * the next major version bump.
*/
- msglen = get_unaligned_le16(&hd->h_length);
- if (msglen > DEFAULT_BUFFER_SIZE) {
- log_print("received invalid length header: %u, will abort message parsing",
- msglen);
+ msglen = le16_to_cpu(hd->h_length);
+ if (msglen > DEFAULT_BUFFER_SIZE ||
+ msglen < sizeof(struct dlm_header)) {
+ log_print("received invalid length header: %u from node %d, will abort message parsing",
+ msglen, nodeid);
return -EBADMSG;
}
@@ -84,15 +91,7 @@ int dlm_process_incoming_buffer(int nodeid, unsigned char *buf, int len)
goto skip;
}
- /* for aligned memory access, we just copy current message
- * to begin of the buffer which contains already parsed buffer
- * data and should provide align access for upper layers
- * because the start address of the buffer has a aligned
- * address. This memmove can be removed when the upperlayer
- * is capable of unaligned memory access.
- */
- memmove(buf, ptr, msglen);
- dlm_receive_buffer((union dlm_packet *)buf, nodeid);
+ dlm_receive_buffer((union dlm_packet *)ptr, nodeid);
skip:
ret += msglen;
diff --git a/fs/dlm/rcom.c b/fs/dlm/rcom.c
index 73ddee5159d7..f5b1bd65728d 100644
--- a/fs/dlm/rcom.c
+++ b/fs/dlm/rcom.c
@@ -41,7 +41,6 @@ static int create_rcom(struct dlm_ls *ls, int to_nodeid, int type, int len,
to_nodeid, type, len);
return -ENOBUFS;
}
- memset(mb, 0, mb_len);
rc = (struct dlm_rcom *) mb;
@@ -462,7 +461,6 @@ int dlm_send_ls_not_ready(int nodeid, struct dlm_rcom *rc_in)
mh = dlm_lowcomms_get_buffer(nodeid, mb_len, GFP_NOFS, &mb);
if (!mh)
return -ENOBUFS;
- memset(mb, 0, mb_len);
rc = (struct dlm_rcom *) mb;
diff --git a/fs/ecryptfs/ecryptfs_kernel.h b/fs/ecryptfs/ecryptfs_kernel.h
index e6ac78c62ca4..495fb4514d09 100644
--- a/fs/ecryptfs/ecryptfs_kernel.h
+++ b/fs/ecryptfs/ecryptfs_kernel.h
@@ -262,10 +262,7 @@ struct ecryptfs_inode_info {
* vfsmount too. */
struct ecryptfs_dentry_info {
struct path lower_path;
- union {
- struct ecryptfs_crypt_stat *crypt_stat;
- struct rcu_head rcu;
- };
+ struct rcu_head rcu;
};
/**
@@ -496,12 +493,6 @@ ecryptfs_set_superblock_lower(struct super_block *sb,
((struct ecryptfs_sb_info *)sb->s_fs_info)->wsi_sb = lower_sb;
}
-static inline struct ecryptfs_dentry_info *
-ecryptfs_dentry_to_private(struct dentry *dentry)
-{
- return (struct ecryptfs_dentry_info *)dentry->d_fsdata;
-}
-
static inline void
ecryptfs_set_dentry_private(struct dentry *dentry,
struct ecryptfs_dentry_info *dentry_info)
@@ -515,12 +506,6 @@ ecryptfs_dentry_to_lower(struct dentry *dentry)
return ((struct ecryptfs_dentry_info *)dentry->d_fsdata)->lower_path.dentry;
}
-static inline struct vfsmount *
-ecryptfs_dentry_to_lower_mnt(struct dentry *dentry)
-{
- return ((struct ecryptfs_dentry_info *)dentry->d_fsdata)->lower_path.mnt;
-}
-
static inline struct path *
ecryptfs_dentry_to_lower_path(struct dentry *dentry)
{
diff --git a/fs/ecryptfs/inode.c b/fs/ecryptfs/inode.c
index 18e9285fbb4c..0a1ab1db1450 100644
--- a/fs/ecryptfs/inode.c
+++ b/fs/ecryptfs/inode.c
@@ -18,22 +18,22 @@
#include <linux/fs_stack.h>
#include <linux/slab.h>
#include <linux/xattr.h>
+#include <linux/fileattr.h>
#include <asm/unaligned.h>
#include "ecryptfs_kernel.h"
-static struct dentry *lock_parent(struct dentry *dentry)
+static int lock_parent(struct dentry *dentry,
+ struct dentry **lower_dentry,
+ struct inode **lower_dir)
{
- struct dentry *dir;
+ struct dentry *lower_dir_dentry;
- dir = dget_parent(dentry);
- inode_lock_nested(d_inode(dir), I_MUTEX_PARENT);
- return dir;
-}
+ lower_dir_dentry = ecryptfs_dentry_to_lower(dentry->d_parent);
+ *lower_dir = d_inode(lower_dir_dentry);
+ *lower_dentry = ecryptfs_dentry_to_lower(dentry);
-static void unlock_dir(struct dentry *dir)
-{
- inode_unlock(d_inode(dir));
- dput(dir);
+ inode_lock_nested(*lower_dir, I_MUTEX_PARENT);
+ return (*lower_dentry)->d_parent == lower_dir_dentry ? 0 : -EINVAL;
}
static int ecryptfs_inode_test(struct inode *inode, void *lower_inode)
@@ -127,32 +127,29 @@ static int ecryptfs_interpose(struct dentry *lower_dentry,
static int ecryptfs_do_unlink(struct inode *dir, struct dentry *dentry,
struct inode *inode)
{
- struct dentry *lower_dentry = ecryptfs_dentry_to_lower(dentry);
- struct dentry *lower_dir_dentry;
- struct inode *lower_dir_inode;
+ struct dentry *lower_dentry;
+ struct inode *lower_dir;
int rc;
- lower_dir_dentry = ecryptfs_dentry_to_lower(dentry->d_parent);
- lower_dir_inode = d_inode(lower_dir_dentry);
- inode_lock_nested(lower_dir_inode, I_MUTEX_PARENT);
+ rc = lock_parent(dentry, &lower_dentry, &lower_dir);
dget(lower_dentry); // don't even try to make the lower negative
- if (lower_dentry->d_parent != lower_dir_dentry)
- rc = -EINVAL;
- else if (d_unhashed(lower_dentry))
- rc = -EINVAL;
- else
- rc = vfs_unlink(&init_user_ns, lower_dir_inode, lower_dentry,
- NULL);
+ if (!rc) {
+ if (d_unhashed(lower_dentry))
+ rc = -EINVAL;
+ else
+ rc = vfs_unlink(&init_user_ns, lower_dir, lower_dentry,
+ NULL);
+ }
if (rc) {
printk(KERN_ERR "Error in vfs_unlink; rc = [%d]\n", rc);
goto out_unlock;
}
- fsstack_copy_attr_times(dir, lower_dir_inode);
+ fsstack_copy_attr_times(dir, lower_dir);
set_nlink(inode, ecryptfs_inode_to_lower(inode)->i_nlink);
inode->i_ctime = dir->i_ctime;
out_unlock:
dput(lower_dentry);
- inode_unlock(lower_dir_inode);
+ inode_unlock(lower_dir);
if (!rc)
d_drop(dentry);
return rc;
@@ -176,13 +173,13 @@ ecryptfs_do_create(struct inode *directory_inode,
{
int rc;
struct dentry *lower_dentry;
- struct dentry *lower_dir_dentry;
+ struct inode *lower_dir;
struct inode *inode;
- lower_dentry = ecryptfs_dentry_to_lower(ecryptfs_dentry);
- lower_dir_dentry = lock_parent(lower_dentry);
- rc = vfs_create(&init_user_ns, d_inode(lower_dir_dentry), lower_dentry,
- mode, true);
+ rc = lock_parent(ecryptfs_dentry, &lower_dentry, &lower_dir);
+ if (!rc)
+ rc = vfs_create(&init_user_ns, lower_dir,
+ lower_dentry, mode, true);
if (rc) {
printk(KERN_ERR "%s: Failure to create dentry in lower fs; "
"rc = [%d]\n", __func__, rc);
@@ -192,14 +189,13 @@ ecryptfs_do_create(struct inode *directory_inode,
inode = __ecryptfs_get_inode(d_inode(lower_dentry),
directory_inode->i_sb);
if (IS_ERR(inode)) {
- vfs_unlink(&init_user_ns, d_inode(lower_dir_dentry),
- lower_dentry, NULL);
+ vfs_unlink(&init_user_ns, lower_dir, lower_dentry, NULL);
goto out_lock;
}
- fsstack_copy_attr_times(directory_inode, d_inode(lower_dir_dentry));
- fsstack_copy_inode_size(directory_inode, d_inode(lower_dir_dentry));
+ fsstack_copy_attr_times(directory_inode, lower_dir);
+ fsstack_copy_inode_size(directory_inode, lower_dir);
out_lock:
- unlock_dir(lower_dir_dentry);
+ inode_unlock(lower_dir);
return inode;
}
@@ -430,32 +426,28 @@ static int ecryptfs_link(struct dentry *old_dentry, struct inode *dir,
{
struct dentry *lower_old_dentry;
struct dentry *lower_new_dentry;
- struct dentry *lower_dir_dentry;
+ struct inode *lower_dir;
u64 file_size_save;
int rc;
file_size_save = i_size_read(d_inode(old_dentry));
lower_old_dentry = ecryptfs_dentry_to_lower(old_dentry);
- lower_new_dentry = ecryptfs_dentry_to_lower(new_dentry);
- dget(lower_old_dentry);
- dget(lower_new_dentry);
- lower_dir_dentry = lock_parent(lower_new_dentry);
- rc = vfs_link(lower_old_dentry, &init_user_ns,
- d_inode(lower_dir_dentry), lower_new_dentry, NULL);
+ rc = lock_parent(new_dentry, &lower_new_dentry, &lower_dir);
+ if (!rc)
+ rc = vfs_link(lower_old_dentry, &init_user_ns, lower_dir,
+ lower_new_dentry, NULL);
if (rc || d_really_is_negative(lower_new_dentry))
goto out_lock;
rc = ecryptfs_interpose(lower_new_dentry, new_dentry, dir->i_sb);
if (rc)
goto out_lock;
- fsstack_copy_attr_times(dir, d_inode(lower_dir_dentry));
- fsstack_copy_inode_size(dir, d_inode(lower_dir_dentry));
+ fsstack_copy_attr_times(dir, lower_dir);
+ fsstack_copy_inode_size(dir, lower_dir);
set_nlink(d_inode(old_dentry),
ecryptfs_inode_to_lower(d_inode(old_dentry))->i_nlink);
i_size_write(d_inode(new_dentry), file_size_save);
out_lock:
- unlock_dir(lower_dir_dentry);
- dput(lower_new_dentry);
- dput(lower_old_dentry);
+ inode_unlock(lower_dir);
return rc;
}
@@ -470,14 +462,14 @@ static int ecryptfs_symlink(struct user_namespace *mnt_userns,
{
int rc;
struct dentry *lower_dentry;
- struct dentry *lower_dir_dentry;
+ struct inode *lower_dir;
char *encoded_symname;
size_t encoded_symlen;
struct ecryptfs_mount_crypt_stat *mount_crypt_stat = NULL;
- lower_dentry = ecryptfs_dentry_to_lower(dentry);
- dget(lower_dentry);
- lower_dir_dentry = lock_parent(lower_dentry);
+ rc = lock_parent(dentry, &lower_dentry, &lower_dir);
+ if (rc)
+ goto out_lock;
mount_crypt_stat = &ecryptfs_superblock_to_private(
dir->i_sb)->mount_crypt_stat;
rc = ecryptfs_encrypt_and_encode_filename(&encoded_symname,
@@ -486,7 +478,7 @@ static int ecryptfs_symlink(struct user_namespace *mnt_userns,
strlen(symname));
if (rc)
goto out_lock;
- rc = vfs_symlink(&init_user_ns, d_inode(lower_dir_dentry), lower_dentry,
+ rc = vfs_symlink(&init_user_ns, lower_dir, lower_dentry,
encoded_symname);
kfree(encoded_symname);
if (rc || d_really_is_negative(lower_dentry))
@@ -494,11 +486,10 @@ static int ecryptfs_symlink(struct user_namespace *mnt_userns,
rc = ecryptfs_interpose(lower_dentry, dentry, dir->i_sb);
if (rc)
goto out_lock;
- fsstack_copy_attr_times(dir, d_inode(lower_dir_dentry));
- fsstack_copy_inode_size(dir, d_inode(lower_dir_dentry));
+ fsstack_copy_attr_times(dir, lower_dir);
+ fsstack_copy_inode_size(dir, lower_dir);
out_lock:
- unlock_dir(lower_dir_dentry);
- dput(lower_dentry);
+ inode_unlock(lower_dir);
if (d_really_is_negative(dentry))
d_drop(dentry);
return rc;
@@ -509,22 +500,22 @@ static int ecryptfs_mkdir(struct user_namespace *mnt_userns, struct inode *dir,
{
int rc;
struct dentry *lower_dentry;
- struct dentry *lower_dir_dentry;
+ struct inode *lower_dir;
- lower_dentry = ecryptfs_dentry_to_lower(dentry);
- lower_dir_dentry = lock_parent(lower_dentry);
- rc = vfs_mkdir(&init_user_ns, d_inode(lower_dir_dentry), lower_dentry,
- mode);
+ rc = lock_parent(dentry, &lower_dentry, &lower_dir);
+ if (!rc)
+ rc = vfs_mkdir(&init_user_ns, lower_dir,
+ lower_dentry, mode);
if (rc || d_really_is_negative(lower_dentry))
goto out;
rc = ecryptfs_interpose(lower_dentry, dentry, dir->i_sb);
if (rc)
goto out;
- fsstack_copy_attr_times(dir, d_inode(lower_dir_dentry));
- fsstack_copy_inode_size(dir, d_inode(lower_dir_dentry));
- set_nlink(dir, d_inode(lower_dir_dentry)->i_nlink);
+ fsstack_copy_attr_times(dir, lower_dir);
+ fsstack_copy_inode_size(dir, lower_dir);
+ set_nlink(dir, lower_dir->i_nlink);
out:
- unlock_dir(lower_dir_dentry);
+ inode_unlock(lower_dir);
if (d_really_is_negative(dentry))
d_drop(dentry);
return rc;
@@ -533,29 +524,24 @@ out:
static int ecryptfs_rmdir(struct inode *dir, struct dentry *dentry)
{
struct dentry *lower_dentry;
- struct dentry *lower_dir_dentry;
- struct inode *lower_dir_inode;
+ struct inode *lower_dir;
int rc;
- lower_dentry = ecryptfs_dentry_to_lower(dentry);
- lower_dir_dentry = ecryptfs_dentry_to_lower(dentry->d_parent);
- lower_dir_inode = d_inode(lower_dir_dentry);
-
- inode_lock_nested(lower_dir_inode, I_MUTEX_PARENT);
+ rc = lock_parent(dentry, &lower_dentry, &lower_dir);
dget(lower_dentry); // don't even try to make the lower negative
- if (lower_dentry->d_parent != lower_dir_dentry)
- rc = -EINVAL;
- else if (d_unhashed(lower_dentry))
- rc = -EINVAL;
- else
- rc = vfs_rmdir(&init_user_ns, lower_dir_inode, lower_dentry);
+ if (!rc) {
+ if (d_unhashed(lower_dentry))
+ rc = -EINVAL;
+ else
+ rc = vfs_rmdir(&init_user_ns, lower_dir, lower_dentry);
+ }
if (!rc) {
clear_nlink(d_inode(dentry));
- fsstack_copy_attr_times(dir, lower_dir_inode);
- set_nlink(dir, lower_dir_inode->i_nlink);
+ fsstack_copy_attr_times(dir, lower_dir);
+ set_nlink(dir, lower_dir->i_nlink);
}
dput(lower_dentry);
- inode_unlock(lower_dir_inode);
+ inode_unlock(lower_dir);
if (!rc)
d_drop(dentry);
return rc;
@@ -567,21 +553,21 @@ ecryptfs_mknod(struct user_namespace *mnt_userns, struct inode *dir,
{
int rc;
struct dentry *lower_dentry;
- struct dentry *lower_dir_dentry;
+ struct inode *lower_dir;
- lower_dentry = ecryptfs_dentry_to_lower(dentry);
- lower_dir_dentry = lock_parent(lower_dentry);
- rc = vfs_mknod(&init_user_ns, d_inode(lower_dir_dentry), lower_dentry,
- mode, dev);
+ rc = lock_parent(dentry, &lower_dentry, &lower_dir);
+ if (!rc)
+ rc = vfs_mknod(&init_user_ns, lower_dir,
+ lower_dentry, mode, dev);
if (rc || d_really_is_negative(lower_dentry))
goto out;
rc = ecryptfs_interpose(lower_dentry, dentry, dir->i_sb);
if (rc)
goto out;
- fsstack_copy_attr_times(dir, d_inode(lower_dir_dentry));
- fsstack_copy_inode_size(dir, d_inode(lower_dir_dentry));
+ fsstack_copy_attr_times(dir, lower_dir);
+ fsstack_copy_inode_size(dir, lower_dir);
out:
- unlock_dir(lower_dir_dentry);
+ inode_unlock(lower_dir);
if (d_really_is_negative(dentry))
d_drop(dentry);
return rc;
@@ -1118,6 +1104,23 @@ out:
return rc;
}
+static int ecryptfs_fileattr_get(struct dentry *dentry, struct fileattr *fa)
+{
+ return vfs_fileattr_get(ecryptfs_dentry_to_lower(dentry), fa);
+}
+
+static int ecryptfs_fileattr_set(struct user_namespace *mnt_userns,
+ struct dentry *dentry, struct fileattr *fa)
+{
+ struct dentry *lower_dentry = ecryptfs_dentry_to_lower(dentry);
+ int rc;
+
+ rc = vfs_fileattr_set(&init_user_ns, lower_dentry, fa);
+ fsstack_copy_attr_all(d_inode(dentry), d_inode(lower_dentry));
+
+ return rc;
+}
+
const struct inode_operations ecryptfs_symlink_iops = {
.get_link = ecryptfs_get_link,
.permission = ecryptfs_permission,
@@ -1139,6 +1142,8 @@ const struct inode_operations ecryptfs_dir_iops = {
.permission = ecryptfs_permission,
.setattr = ecryptfs_setattr,
.listxattr = ecryptfs_listxattr,
+ .fileattr_get = ecryptfs_fileattr_get,
+ .fileattr_set = ecryptfs_fileattr_set,
};
const struct inode_operations ecryptfs_main_iops = {
@@ -1146,6 +1151,8 @@ const struct inode_operations ecryptfs_main_iops = {
.setattr = ecryptfs_setattr,
.getattr = ecryptfs_getattr,
.listxattr = ecryptfs_listxattr,
+ .fileattr_get = ecryptfs_fileattr_get,
+ .fileattr_set = ecryptfs_fileattr_set,
};
static int ecryptfs_xattr_get(const struct xattr_handler *handler,
diff --git a/fs/efivarfs/file.c b/fs/efivarfs/file.c
index e6bc0302643b..d57ee15874f9 100644
--- a/fs/efivarfs/file.c
+++ b/fs/efivarfs/file.c
@@ -106,86 +106,9 @@ out_free:
return size;
}
-static inline unsigned int efivarfs_getflags(struct inode *inode)
-{
- unsigned int i_flags;
- unsigned int flags = 0;
-
- i_flags = inode->i_flags;
- if (i_flags & S_IMMUTABLE)
- flags |= FS_IMMUTABLE_FL;
- return flags;
-}
-
-static int
-efivarfs_ioc_getxflags(struct file *file, void __user *arg)
-{
- struct inode *inode = file->f_mapping->host;
- unsigned int flags = efivarfs_getflags(inode);
-
- if (copy_to_user(arg, &flags, sizeof(flags)))
- return -EFAULT;
- return 0;
-}
-
-static int
-efivarfs_ioc_setxflags(struct file *file, void __user *arg)
-{
- struct inode *inode = file->f_mapping->host;
- unsigned int flags;
- unsigned int i_flags = 0;
- unsigned int oldflags = efivarfs_getflags(inode);
- int error;
-
- if (!inode_owner_or_capable(&init_user_ns, inode))
- return -EACCES;
-
- if (copy_from_user(&flags, arg, sizeof(flags)))
- return -EFAULT;
-
- if (flags & ~FS_IMMUTABLE_FL)
- return -EOPNOTSUPP;
-
- if (flags & FS_IMMUTABLE_FL)
- i_flags |= S_IMMUTABLE;
-
-
- error = mnt_want_write_file(file);
- if (error)
- return error;
-
- inode_lock(inode);
-
- error = vfs_ioc_setflags_prepare(inode, oldflags, flags);
- if (error)
- goto out;
-
- inode_set_flags(inode, i_flags, S_IMMUTABLE);
-out:
- inode_unlock(inode);
- mnt_drop_write_file(file);
- return error;
-}
-
-static long
-efivarfs_file_ioctl(struct file *file, unsigned int cmd, unsigned long p)
-{
- void __user *arg = (void __user *)p;
-
- switch (cmd) {
- case FS_IOC_GETFLAGS:
- return efivarfs_ioc_getxflags(file, arg);
- case FS_IOC_SETFLAGS:
- return efivarfs_ioc_setxflags(file, arg);
- }
-
- return -ENOTTY;
-}
-
const struct file_operations efivarfs_file_operations = {
.open = simple_open,
.read = efivarfs_file_read,
.write = efivarfs_file_write,
.llseek = no_llseek,
- .unlocked_ioctl = efivarfs_file_ioctl,
};
diff --git a/fs/efivarfs/inode.c b/fs/efivarfs/inode.c
index 14e2947975fd..939e5e242b98 100644
--- a/fs/efivarfs/inode.c
+++ b/fs/efivarfs/inode.c
@@ -10,9 +10,12 @@
#include <linux/kmemleak.h>
#include <linux/slab.h>
#include <linux/uuid.h>
+#include <linux/fileattr.h>
#include "internal.h"
+static const struct inode_operations efivarfs_file_inode_operations;
+
struct inode *efivarfs_get_inode(struct super_block *sb,
const struct inode *dir, int mode,
dev_t dev, bool is_removable)
@@ -26,6 +29,7 @@ struct inode *efivarfs_get_inode(struct super_block *sb,
inode->i_flags = is_removable ? 0 : S_IMMUTABLE;
switch (mode & S_IFMT) {
case S_IFREG:
+ inode->i_op = &efivarfs_file_inode_operations;
inode->i_fop = &efivarfs_file_operations;
break;
case S_IFDIR:
@@ -138,3 +142,43 @@ const struct inode_operations efivarfs_dir_inode_operations = {
.unlink = efivarfs_unlink,
.create = efivarfs_create,
};
+
+static int
+efivarfs_fileattr_get(struct dentry *dentry, struct fileattr *fa)
+{
+ unsigned int i_flags;
+ unsigned int flags = 0;
+
+ i_flags = d_inode(dentry)->i_flags;
+ if (i_flags & S_IMMUTABLE)
+ flags |= FS_IMMUTABLE_FL;
+
+ fileattr_fill_flags(fa, flags);
+
+ return 0;
+}
+
+static int
+efivarfs_fileattr_set(struct user_namespace *mnt_userns,
+ struct dentry *dentry, struct fileattr *fa)
+{
+ unsigned int i_flags = 0;
+
+ if (fileattr_has_fsx(fa))
+ return -EOPNOTSUPP;
+
+ if (fa->flags & ~FS_IMMUTABLE_FL)
+ return -EOPNOTSUPP;
+
+ if (fa->flags & FS_IMMUTABLE_FL)
+ i_flags |= S_IMMUTABLE;
+
+ inode_set_flags(d_inode(dentry), i_flags, S_IMMUTABLE);
+
+ return 0;
+}
+
+static const struct inode_operations efivarfs_file_inode_operations = {
+ .fileattr_get = efivarfs_fileattr_get,
+ .fileattr_set = efivarfs_fileattr_set,
+};
diff --git a/fs/erofs/Kconfig b/fs/erofs/Kconfig
index 74b0aaa7114c..858b3339f381 100644
--- a/fs/erofs/Kconfig
+++ b/fs/erofs/Kconfig
@@ -76,17 +76,3 @@ config EROFS_FS_ZIP
If you don't want to enable compression feature, say N.
-config EROFS_FS_CLUSTER_PAGE_LIMIT
- int "EROFS Cluster Pages Hard Limit"
- depends on EROFS_FS_ZIP
- range 1 256
- default "1"
- help
- Indicates maximum # of pages of a compressed
- physical cluster.
-
- For example, if files in a image were compressed
- into 8k-unit, hard limit should not be configured
- less than 2. Otherwise, the image will be refused
- to mount on this kernel.
-
diff --git a/fs/erofs/Makefile b/fs/erofs/Makefile
index af159539fc1b..1f9aced49070 100644
--- a/fs/erofs/Makefile
+++ b/fs/erofs/Makefile
@@ -1,6 +1,6 @@
# SPDX-License-Identifier: GPL-2.0-only
obj-$(CONFIG_EROFS_FS) += erofs.o
-erofs-objs := super.o inode.o data.o namei.o dir.o utils.o
+erofs-objs := super.o inode.o data.o namei.o dir.o utils.o pcpubuf.o
erofs-$(CONFIG_EROFS_FS_XATTR) += xattr.o
erofs-$(CONFIG_EROFS_FS_ZIP) += decompressor.o zmap.o zdata.o
diff --git a/fs/erofs/data.c b/fs/erofs/data.c
index 1249e74b3bf0..ebac756cb2a3 100644
--- a/fs/erofs/data.c
+++ b/fs/erofs/data.c
@@ -109,21 +109,6 @@ err_out:
return err;
}
-int erofs_map_blocks(struct inode *inode,
- struct erofs_map_blocks *map, int flags)
-{
- if (erofs_inode_is_data_compressed(EROFS_I(inode)->datalayout)) {
- int err = z_erofs_map_blocks_iter(inode, map, flags);
-
- if (map->mpage) {
- put_page(map->mpage);
- map->mpage = NULL;
- }
- return err;
- }
- return erofs_map_blocks_flatmode(inode, map, flags);
-}
-
static inline struct bio *erofs_read_raw_page(struct bio *bio,
struct address_space *mapping,
struct page *page,
@@ -159,7 +144,7 @@ submit_bio_retry:
erofs_blk_t blknr;
unsigned int blkoff;
- err = erofs_map_blocks(inode, &map, EROFS_GET_BLOCKS_RAW);
+ err = erofs_map_blocks_flatmode(inode, &map, EROFS_GET_BLOCKS_RAW);
if (err)
goto err_out;
@@ -318,7 +303,7 @@ static sector_t erofs_bmap(struct address_space *mapping, sector_t block)
return 0;
}
- if (!erofs_map_blocks(inode, &map, EROFS_GET_BLOCKS_RAW))
+ if (!erofs_map_blocks_flatmode(inode, &map, EROFS_GET_BLOCKS_RAW))
return erofs_blknr(map.m_pa);
return 0;
diff --git a/fs/erofs/decompressor.c b/fs/erofs/decompressor.c
index 1cb1ffd10569..88e33addf229 100644
--- a/fs/erofs/decompressor.c
+++ b/fs/erofs/decompressor.c
@@ -28,6 +28,42 @@ struct z_erofs_decompressor {
char *name;
};
+int z_erofs_load_lz4_config(struct super_block *sb,
+ struct erofs_super_block *dsb,
+ struct z_erofs_lz4_cfgs *lz4, int size)
+{
+ struct erofs_sb_info *sbi = EROFS_SB(sb);
+ u16 distance;
+
+ if (lz4) {
+ if (size < sizeof(struct z_erofs_lz4_cfgs)) {
+ erofs_err(sb, "invalid lz4 cfgs, size=%u", size);
+ return -EINVAL;
+ }
+ distance = le16_to_cpu(lz4->max_distance);
+
+ sbi->lz4.max_pclusterblks = le16_to_cpu(lz4->max_pclusterblks);
+ if (!sbi->lz4.max_pclusterblks) {
+ sbi->lz4.max_pclusterblks = 1; /* reserved case */
+ } else if (sbi->lz4.max_pclusterblks >
+ Z_EROFS_PCLUSTER_MAX_SIZE / EROFS_BLKSIZ) {
+ erofs_err(sb, "too large lz4 pclusterblks %u",
+ sbi->lz4.max_pclusterblks);
+ return -EINVAL;
+ } else if (sbi->lz4.max_pclusterblks >= 2) {
+ erofs_info(sb, "EXPERIMENTAL big pcluster feature in use. Use at your own risk!");
+ }
+ } else {
+ distance = le16_to_cpu(dsb->u1.lz4_max_distance);
+ sbi->lz4.max_pclusterblks = 1;
+ }
+
+ sbi->lz4.max_distance_pages = distance ?
+ DIV_ROUND_UP(distance, PAGE_SIZE) + 1 :
+ LZ4_MAX_DISTANCE_PAGES;
+ return erofs_pcpubuf_growsize(sbi->lz4.max_pclusterblks);
+}
+
static int z_erofs_lz4_prepare_destpages(struct z_erofs_decompress_req *rq,
struct list_head *pagepool)
{
@@ -36,6 +72,8 @@ static int z_erofs_lz4_prepare_destpages(struct z_erofs_decompress_req *rq,
struct page *availables[LZ4_MAX_DISTANCE_PAGES] = { NULL };
unsigned long bounced[DIV_ROUND_UP(LZ4_MAX_DISTANCE_PAGES,
BITS_PER_LONG)] = { 0 };
+ unsigned int lz4_max_distance_pages =
+ EROFS_SB(rq->sb)->lz4.max_distance_pages;
void *kaddr = NULL;
unsigned int i, j, top;
@@ -44,14 +82,14 @@ static int z_erofs_lz4_prepare_destpages(struct z_erofs_decompress_req *rq,
struct page *const page = rq->out[i];
struct page *victim;
- if (j >= LZ4_MAX_DISTANCE_PAGES)
+ if (j >= lz4_max_distance_pages)
j = 0;
/* 'valid' bounced can only be tested after a complete round */
if (test_bit(j, bounced)) {
- DBG_BUGON(i < LZ4_MAX_DISTANCE_PAGES);
- DBG_BUGON(top >= LZ4_MAX_DISTANCE_PAGES);
- availables[top++] = rq->out[i - LZ4_MAX_DISTANCE_PAGES];
+ DBG_BUGON(i < lz4_max_distance_pages);
+ DBG_BUGON(top >= lz4_max_distance_pages);
+ availables[top++] = rq->out[i - lz4_max_distance_pages];
}
if (page) {
@@ -73,9 +111,8 @@ static int z_erofs_lz4_prepare_destpages(struct z_erofs_decompress_req *rq,
victim = availables[--top];
get_page(victim);
} else {
- victim = erofs_allocpage(pagepool, GFP_KERNEL);
- if (!victim)
- return -ENOMEM;
+ victim = erofs_allocpage(pagepool,
+ GFP_KERNEL | __GFP_NOFAIL);
set_page_private(victim, Z_EROFS_SHORTLIVED_PAGE);
}
rq->out[i] = victim;
@@ -83,96 +120,123 @@ static int z_erofs_lz4_prepare_destpages(struct z_erofs_decompress_req *rq,
return kaddr ? 1 : 0;
}
-static void *generic_copy_inplace_data(struct z_erofs_decompress_req *rq,
- u8 *src, unsigned int pageofs_in)
+static void *z_erofs_handle_inplace_io(struct z_erofs_decompress_req *rq,
+ void *inpage, unsigned int *inputmargin, int *maptype,
+ bool support_0padding)
{
- /*
- * if in-place decompression is ongoing, those decompressed
- * pages should be copied in order to avoid being overlapped.
- */
- struct page **in = rq->in;
- u8 *const tmp = erofs_get_pcpubuf(0);
- u8 *tmpp = tmp;
- unsigned int inlen = rq->inputsize - pageofs_in;
- unsigned int count = min_t(uint, inlen, PAGE_SIZE - pageofs_in);
-
- while (tmpp < tmp + inlen) {
- if (!src)
- src = kmap_atomic(*in);
- memcpy(tmpp, src + pageofs_in, count);
- kunmap_atomic(src);
- src = NULL;
- tmpp += count;
- pageofs_in = 0;
- count = PAGE_SIZE;
+ unsigned int nrpages_in, nrpages_out;
+ unsigned int ofull, oend, inputsize, total, i, j;
+ struct page **in;
+ void *src, *tmp;
+
+ inputsize = rq->inputsize;
+ nrpages_in = PAGE_ALIGN(inputsize) >> PAGE_SHIFT;
+ oend = rq->pageofs_out + rq->outputsize;
+ ofull = PAGE_ALIGN(oend);
+ nrpages_out = ofull >> PAGE_SHIFT;
+
+ if (rq->inplace_io) {
+ if (rq->partial_decoding || !support_0padding ||
+ ofull - oend < LZ4_DECOMPRESS_INPLACE_MARGIN(inputsize))
+ goto docopy;
+
+ for (i = 0; i < nrpages_in; ++i) {
+ DBG_BUGON(rq->in[i] == NULL);
+ for (j = 0; j < nrpages_out - nrpages_in + i; ++j)
+ if (rq->out[j] == rq->in[i])
+ goto docopy;
+ }
+ }
+
+ if (nrpages_in <= 1) {
+ *maptype = 0;
+ return inpage;
+ }
+ kunmap_atomic(inpage);
+ might_sleep();
+ src = erofs_vm_map_ram(rq->in, nrpages_in);
+ if (!src)
+ return ERR_PTR(-ENOMEM);
+ *maptype = 1;
+ return src;
+
+docopy:
+ /* Or copy compressed data which can be overlapped to per-CPU buffer */
+ in = rq->in;
+ src = erofs_get_pcpubuf(nrpages_in);
+ if (!src) {
+ DBG_BUGON(1);
+ kunmap_atomic(inpage);
+ return ERR_PTR(-EFAULT);
+ }
+
+ tmp = src;
+ total = rq->inputsize;
+ while (total) {
+ unsigned int page_copycnt =
+ min_t(unsigned int, total, PAGE_SIZE - *inputmargin);
+
+ if (!inpage)
+ inpage = kmap_atomic(*in);
+ memcpy(tmp, inpage + *inputmargin, page_copycnt);
+ kunmap_atomic(inpage);
+ inpage = NULL;
+ tmp += page_copycnt;
+ total -= page_copycnt;
++in;
+ *inputmargin = 0;
}
- return tmp;
+ *maptype = 2;
+ return src;
}
static int z_erofs_lz4_decompress(struct z_erofs_decompress_req *rq, u8 *out)
{
- unsigned int inputmargin, inlen;
- u8 *src;
- bool copied, support_0padding;
- int ret;
-
- if (rq->inputsize > PAGE_SIZE)
- return -EOPNOTSUPP;
+ unsigned int inputmargin;
+ u8 *headpage, *src;
+ bool support_0padding;
+ int ret, maptype;
- src = kmap_atomic(*rq->in);
+ DBG_BUGON(*rq->in == NULL);
+ headpage = kmap_atomic(*rq->in);
inputmargin = 0;
support_0padding = false;
/* decompression inplace is only safe when 0padding is enabled */
- if (EROFS_SB(rq->sb)->feature_incompat &
- EROFS_FEATURE_INCOMPAT_LZ4_0PADDING) {
+ if (erofs_sb_has_lz4_0padding(EROFS_SB(rq->sb))) {
support_0padding = true;
- while (!src[inputmargin & ~PAGE_MASK])
+ while (!headpage[inputmargin & ~PAGE_MASK])
if (!(++inputmargin & ~PAGE_MASK))
break;
if (inputmargin >= rq->inputsize) {
- kunmap_atomic(src);
+ kunmap_atomic(headpage);
return -EIO;
}
}
- copied = false;
- inlen = rq->inputsize - inputmargin;
- if (rq->inplace_io) {
- const uint oend = (rq->pageofs_out +
- rq->outputsize) & ~PAGE_MASK;
- const uint nr = PAGE_ALIGN(rq->pageofs_out +
- rq->outputsize) >> PAGE_SHIFT;
-
- if (rq->partial_decoding || !support_0padding ||
- rq->out[nr - 1] != rq->in[0] ||
- rq->inputsize - oend <
- LZ4_DECOMPRESS_INPLACE_MARGIN(inlen)) {
- src = generic_copy_inplace_data(rq, src, inputmargin);
- inputmargin = 0;
- copied = true;
- }
- }
+ rq->inputsize -= inputmargin;
+ src = z_erofs_handle_inplace_io(rq, headpage, &inputmargin, &maptype,
+ support_0padding);
+ if (IS_ERR(src))
+ return PTR_ERR(src);
/* legacy format could compress extra data in a pcluster. */
if (rq->partial_decoding || !support_0padding)
ret = LZ4_decompress_safe_partial(src + inputmargin, out,
- inlen, rq->outputsize,
- rq->outputsize);
+ rq->inputsize, rq->outputsize, rq->outputsize);
else
ret = LZ4_decompress_safe(src + inputmargin, out,
- inlen, rq->outputsize);
+ rq->inputsize, rq->outputsize);
if (ret != rq->outputsize) {
erofs_err(rq->sb, "failed to decompress %d in[%u, %u] out[%u]",
- ret, inlen, inputmargin, rq->outputsize);
+ ret, rq->inputsize, inputmargin, rq->outputsize);
WARN_ON(1);
print_hex_dump(KERN_DEBUG, "[ in]: ", DUMP_PREFIX_OFFSET,
- 16, 1, src + inputmargin, inlen, true);
+ 16, 1, src + inputmargin, rq->inputsize, true);
print_hex_dump(KERN_DEBUG, "[out]: ", DUMP_PREFIX_OFFSET,
16, 1, out, rq->outputsize, true);
@@ -181,10 +245,16 @@ static int z_erofs_lz4_decompress(struct z_erofs_decompress_req *rq, u8 *out)
ret = -EIO;
}
- if (copied)
- erofs_put_pcpubuf(src);
- else
+ if (maptype == 0) {
kunmap_atomic(src);
+ } else if (maptype == 1) {
+ vm_unmap_ram(src, PAGE_ALIGN(rq->inputsize) >> PAGE_SHIFT);
+ } else if (maptype == 2) {
+ erofs_put_pcpubuf(src);
+ } else {
+ DBG_BUGON(1);
+ return -EFAULT;
+ }
return ret;
}
@@ -234,57 +304,51 @@ static int z_erofs_decompress_generic(struct z_erofs_decompress_req *rq,
const struct z_erofs_decompressor *alg = decompressors + rq->alg;
unsigned int dst_maptype;
void *dst;
- int ret, i;
+ int ret;
- if (nrpages_out == 1 && !rq->inplace_io) {
- DBG_BUGON(!*rq->out);
- dst = kmap_atomic(*rq->out);
- dst_maptype = 0;
- goto dstmap_out;
- }
+ /* two optimized fast paths only for non bigpcluster cases yet */
+ if (rq->inputsize <= PAGE_SIZE) {
+ if (nrpages_out == 1 && !rq->inplace_io) {
+ DBG_BUGON(!*rq->out);
+ dst = kmap_atomic(*rq->out);
+ dst_maptype = 0;
+ goto dstmap_out;
+ }
- /*
- * For the case of small output size (especially much less
- * than PAGE_SIZE), memcpy the decompressed data rather than
- * compressed data is preferred.
- */
- if (rq->outputsize <= PAGE_SIZE * 7 / 8) {
- dst = erofs_get_pcpubuf(0);
- if (IS_ERR(dst))
- return PTR_ERR(dst);
-
- rq->inplace_io = false;
- ret = alg->decompress(rq, dst);
- if (!ret)
- copy_from_pcpubuf(rq->out, dst, rq->pageofs_out,
- rq->outputsize);
-
- erofs_put_pcpubuf(dst);
- return ret;
+ /*
+ * For the case of small output size (especially much less
+ * than PAGE_SIZE), memcpy the decompressed data rather than
+ * compressed data is preferred.
+ */
+ if (rq->outputsize <= PAGE_SIZE * 7 / 8) {
+ dst = erofs_get_pcpubuf(1);
+ if (IS_ERR(dst))
+ return PTR_ERR(dst);
+
+ rq->inplace_io = false;
+ ret = alg->decompress(rq, dst);
+ if (!ret)
+ copy_from_pcpubuf(rq->out, dst, rq->pageofs_out,
+ rq->outputsize);
+
+ erofs_put_pcpubuf(dst);
+ return ret;
+ }
}
+ /* general decoding path which can be used for all cases */
ret = alg->prepare_destpages(rq, pagepool);
- if (ret < 0) {
+ if (ret < 0)
return ret;
- } else if (ret) {
+ if (ret) {
dst = page_address(*rq->out);
dst_maptype = 1;
goto dstmap_out;
}
- i = 0;
- while (1) {
- dst = vm_map_ram(rq->out, nrpages_out, -1);
-
- /* retry two more times (totally 3 times) */
- if (dst || ++i >= 3)
- break;
- vm_unmap_aliases();
- }
-
+ dst = erofs_vm_map_ram(rq->out, nrpages_out);
if (!dst)
return -ENOMEM;
-
dst_maptype = 2;
dstmap_out:
diff --git a/fs/erofs/erofs_fs.h b/fs/erofs/erofs_fs.h
index 9ad1615f4474..8739d3adf51f 100644
--- a/fs/erofs/erofs_fs.h
+++ b/fs/erofs/erofs_fs.h
@@ -18,15 +18,22 @@
* be incompatible with this kernel version.
*/
#define EROFS_FEATURE_INCOMPAT_LZ4_0PADDING 0x00000001
-#define EROFS_ALL_FEATURE_INCOMPAT EROFS_FEATURE_INCOMPAT_LZ4_0PADDING
+#define EROFS_FEATURE_INCOMPAT_COMPR_CFGS 0x00000002
+#define EROFS_FEATURE_INCOMPAT_BIG_PCLUSTER 0x00000002
+#define EROFS_ALL_FEATURE_INCOMPAT \
+ (EROFS_FEATURE_INCOMPAT_LZ4_0PADDING | \
+ EROFS_FEATURE_INCOMPAT_COMPR_CFGS | \
+ EROFS_FEATURE_INCOMPAT_BIG_PCLUSTER)
-/* 128-byte erofs on-disk super block */
+#define EROFS_SB_EXTSLOT_SIZE 16
+
+/* erofs on-disk super block (currently 128 bytes) */
struct erofs_super_block {
__le32 magic; /* file system magic number */
__le32 checksum; /* crc32c(super_block) */
__le32 feature_compat;
__u8 blkszbits; /* support block_size == PAGE_SIZE only */
- __u8 reserved;
+ __u8 sb_extslots; /* superblock size = 128 + sb_extslots * 16 */
__le16 root_nid; /* nid of root directory */
__le64 inos; /* total valid ino # (== f_files - f_favail) */
@@ -39,7 +46,13 @@ struct erofs_super_block {
__u8 uuid[16]; /* 128-bit uuid for volume */
__u8 volume_name[16]; /* volume name */
__le32 feature_incompat;
- __u8 reserved2[44];
+ union {
+ /* bitmap for available compression algorithms */
+ __le16 available_compr_algs;
+ /* customized sliding window size instead of 64k by default */
+ __le16 lz4_max_distance;
+ } __packed u1;
+ __u8 reserved2[42];
};
/*
@@ -75,6 +88,9 @@ static inline bool erofs_inode_is_data_compressed(unsigned int datamode)
#define EROFS_I_VERSION_BIT 0
#define EROFS_I_DATALAYOUT_BIT 1
+#define EROFS_I_ALL \
+ ((1 << (EROFS_I_DATALAYOUT_BIT + EROFS_I_DATALAYOUT_BITS)) - 1)
+
/* 32-byte reduced form of an ondisk inode */
struct erofs_inode_compact {
__le16 i_format; /* inode format hints */
@@ -189,20 +205,33 @@ static inline unsigned int erofs_xattr_entry_size(struct erofs_xattr_entry *e)
e->e_name_len + le16_to_cpu(e->e_value_size));
}
+/* maximum supported size of a physical compression cluster */
+#define Z_EROFS_PCLUSTER_MAX_SIZE (1024 * 1024)
+
/* available compression algorithm types (for h_algorithmtype) */
enum {
Z_EROFS_COMPRESSION_LZ4 = 0,
Z_EROFS_COMPRESSION_MAX
};
+#define Z_EROFS_ALL_COMPR_ALGS (1 << (Z_EROFS_COMPRESSION_MAX - 1))
+
+/* 14 bytes (+ length field = 16 bytes) */
+struct z_erofs_lz4_cfgs {
+ __le16 max_distance;
+ __le16 max_pclusterblks;
+ u8 reserved[10];
+} __packed;
/*
* bit 0 : COMPACTED_2B indexes (0 - off; 1 - on)
* e.g. for 4k logical cluster size, 4B if compacted 2B is off;
* (4B) + 2B + (4B) if compacted 2B is on.
+ * bit 1 : HEAD1 big pcluster (0 - off; 1 - on)
+ * bit 2 : HEAD2 big pcluster (0 - off; 1 - on)
*/
-#define Z_EROFS_ADVISE_COMPACTED_2B_BIT 0
-
-#define Z_EROFS_ADVISE_COMPACTED_2B (1 << Z_EROFS_ADVISE_COMPACTED_2B_BIT)
+#define Z_EROFS_ADVISE_COMPACTED_2B 0x0001
+#define Z_EROFS_ADVISE_BIG_PCLUSTER_1 0x0002
+#define Z_EROFS_ADVISE_BIG_PCLUSTER_2 0x0004
struct z_erofs_map_header {
__le32 h_reserved1;
@@ -214,9 +243,7 @@ struct z_erofs_map_header {
__u8 h_algorithmtype;
/*
* bit 0-2 : logical cluster bits - 12, e.g. 0 for 4096;
- * bit 3-4 : (physical - logical) cluster bits of head 1:
- * For example, if logical clustersize = 4096, 1 for 8192.
- * bit 5-7 : (physical - logical) cluster bits of head 2.
+ * bit 3-7 : reserved.
*/
__u8 h_clusterbits;
};
@@ -259,6 +286,13 @@ enum {
#define Z_EROFS_VLE_DI_CLUSTER_TYPE_BITS 2
#define Z_EROFS_VLE_DI_CLUSTER_TYPE_BIT 0
+/*
+ * D0_CBLKCNT will be marked _only_ at the 1st non-head lcluster to store the
+ * compressed block count of a compressed extent (in logical clusters, aka.
+ * block count of a pcluster).
+ */
+#define Z_EROFS_VLE_DI_D0_CBLKCNT (1 << 11)
+
struct z_erofs_vle_decompressed_index {
__le16 di_advise;
/* where to decompress in the head cluster */
diff --git a/fs/erofs/inode.c b/fs/erofs/inode.c
index 119fdce1b520..7ed2d7391692 100644
--- a/fs/erofs/inode.c
+++ b/fs/erofs/inode.c
@@ -44,6 +44,13 @@ static struct page *erofs_read_inode(struct inode *inode,
dic = page_address(page) + *ofs;
ifmt = le16_to_cpu(dic->i_format);
+ if (ifmt & ~EROFS_I_ALL) {
+ erofs_err(inode->i_sb, "unsupported i_format %u of nid %llu",
+ ifmt, vi->nid);
+ err = -EOPNOTSUPP;
+ goto err_out;
+ }
+
vi->datalayout = erofs_inode_datalayout(ifmt);
if (vi->datalayout >= EROFS_INODE_DATALAYOUT_MAX) {
erofs_err(inode->i_sb, "unsupported datalayout %u of nid %llu",
diff --git a/fs/erofs/internal.h b/fs/erofs/internal.h
index 351dae524a0c..f92e3e32b9f4 100644
--- a/fs/erofs/internal.h
+++ b/fs/erofs/internal.h
@@ -50,6 +50,8 @@ struct erofs_fs_context {
#ifdef CONFIG_EROFS_FS_ZIP
/* current strategy of how to use managed cache */
unsigned char cache_strategy;
+ /* strategy of sync decompression (false - auto, true - force on) */
+ bool readahead_sync_decompress;
/* threshold for decompression synchronously */
unsigned int max_sync_decompress_pages;
@@ -57,6 +59,14 @@ struct erofs_fs_context {
unsigned int mount_opt;
};
+/* all filesystem-wide lz4 configurations */
+struct erofs_sb_lz4_info {
+ /* # of pages needed for EROFS lz4 rolling decompression */
+ u16 max_distance_pages;
+ /* maximum possible blocks for pclusters in the filesystem */
+ u16 max_pclusterblks;
+};
+
struct erofs_sb_info {
#ifdef CONFIG_EROFS_FS_ZIP
/* list for all registered superblocks, mainly for shrinker */
@@ -67,9 +77,12 @@ struct erofs_sb_info {
struct xarray managed_pslots;
unsigned int shrinker_run_no;
+ u16 available_compr_algs;
/* pseudo inode to manage cached pages */
struct inode *managed_cache;
+
+ struct erofs_sb_lz4_info lz4;
#endif /* CONFIG_EROFS_FS_ZIP */
u32 blocks;
u32 meta_blkaddr;
@@ -80,6 +93,7 @@ struct erofs_sb_info {
/* inode slot unit size in bit shift */
unsigned char islotbits;
+ u32 sb_size; /* total superblock size */
u32 build_time_nsec;
u64 build_time;
@@ -182,12 +196,6 @@ static inline int erofs_wait_on_workgroup_freezed(struct erofs_workgroup *grp)
return v;
}
#endif /* !CONFIG_SMP */
-
-/* hard limit of pages per compressed cluster */
-#define Z_EROFS_CLUSTER_MAX_PAGES (CONFIG_EROFS_FS_CLUSTER_PAGE_LIMIT)
-#define EROFS_PCPUBUF_NR_PAGES Z_EROFS_CLUSTER_MAX_PAGES
-#else
-#define EROFS_PCPUBUF_NR_PAGES 0
#endif /* !CONFIG_EROFS_FS_ZIP */
/* we strictly follow PAGE_SIZE and no buffer head yet */
@@ -216,6 +224,17 @@ static inline erofs_off_t iloc(struct erofs_sb_info *sbi, erofs_nid_t nid)
return blknr_to_addr(sbi->meta_blkaddr) + (nid << sbi->islotbits);
}
+#define EROFS_FEATURE_FUNCS(name, compat, feature) \
+static inline bool erofs_sb_has_##name(struct erofs_sb_info *sbi) \
+{ \
+ return sbi->feature_##compat & EROFS_FEATURE_##feature; \
+}
+
+EROFS_FEATURE_FUNCS(lz4_0padding, incompat, INCOMPAT_LZ4_0PADDING)
+EROFS_FEATURE_FUNCS(compr_cfgs, incompat, INCOMPAT_COMPR_CFGS)
+EROFS_FEATURE_FUNCS(big_pcluster, incompat, INCOMPAT_BIG_PCLUSTER)
+EROFS_FEATURE_FUNCS(sb_chksum, compat, COMPAT_SB_CHKSUM)
+
/* atomic flag definitions */
#define EROFS_I_EA_INITED_BIT 0
#define EROFS_I_Z_INITED_BIT 1
@@ -244,7 +263,6 @@ struct erofs_inode {
unsigned short z_advise;
unsigned char z_algorithmtype[2];
unsigned char z_logical_clusterbits;
- unsigned char z_physical_clusterbits[2];
};
#endif /* CONFIG_EROFS_FS_ZIP */
};
@@ -287,7 +305,7 @@ extern const struct address_space_operations erofs_raw_access_aops;
extern const struct address_space_operations z_erofs_aops;
/*
- * Logical to physical block mapping, used by erofs_map_blocks()
+ * Logical to physical block mapping
*
* Different with other file systems, it is used for 2 access modes:
*
@@ -334,7 +352,7 @@ struct erofs_map_blocks {
struct page *mpage;
};
-/* Flags used by erofs_map_blocks() */
+/* Flags used by erofs_map_blocks_flatmode() */
#define EROFS_GET_BLOCKS_RAW 0x0001
/* zmap.c */
@@ -356,8 +374,6 @@ static inline int z_erofs_map_blocks_iter(struct inode *inode,
/* data.c */
struct page *erofs_get_meta_page(struct super_block *sb, erofs_blk_t blkaddr);
-int erofs_map_blocks(struct inode *, struct erofs_map_blocks *, int);
-
/* inode.c */
static inline unsigned long erofs_inode_hash(erofs_nid_t nid)
{
@@ -386,23 +402,30 @@ int erofs_namei(struct inode *dir, struct qstr *name,
/* dir.c */
extern const struct file_operations erofs_dir_fops;
-/* utils.c / zdata.c */
-struct page *erofs_allocpage(struct list_head *pool, gfp_t gfp);
-
-#if (EROFS_PCPUBUF_NR_PAGES > 0)
-void *erofs_get_pcpubuf(unsigned int pagenr);
-#define erofs_put_pcpubuf(buf) do { \
- (void)&(buf); \
- preempt_enable(); \
-} while (0)
-#else
-static inline void *erofs_get_pcpubuf(unsigned int pagenr)
+static inline void *erofs_vm_map_ram(struct page **pages, unsigned int count)
{
- return ERR_PTR(-EOPNOTSUPP);
+ int retried = 0;
+
+ while (1) {
+ void *p = vm_map_ram(pages, count, -1);
+
+ /* retry two more times (totally 3 times) */
+ if (p || ++retried >= 3)
+ return p;
+ vm_unmap_aliases();
+ }
+ return NULL;
}
-#define erofs_put_pcpubuf(buf) do {} while (0)
-#endif
+/* pcpubuf.c */
+void *erofs_get_pcpubuf(unsigned int requiredpages);
+void erofs_put_pcpubuf(void *ptr);
+int erofs_pcpubuf_growsize(unsigned int nrpages);
+void erofs_pcpubuf_init(void);
+void erofs_pcpubuf_exit(void);
+
+/* utils.c / zdata.c */
+struct page *erofs_allocpage(struct list_head *pool, gfp_t gfp);
#ifdef CONFIG_EROFS_FS_ZIP
int erofs_workgroup_put(struct erofs_workgroup *grp);
@@ -421,6 +444,9 @@ int erofs_try_to_free_all_cached_pages(struct erofs_sb_info *sbi,
struct erofs_workgroup *egrp);
int erofs_try_to_free_cached_page(struct address_space *mapping,
struct page *page);
+int z_erofs_load_lz4_config(struct super_block *sb,
+ struct erofs_super_block *dsb,
+ struct z_erofs_lz4_cfgs *lz4, int len);
#else
static inline void erofs_shrinker_register(struct super_block *sb) {}
static inline void erofs_shrinker_unregister(struct super_block *sb) {}
@@ -428,6 +454,16 @@ static inline int erofs_init_shrinker(void) { return 0; }
static inline void erofs_exit_shrinker(void) {}
static inline int z_erofs_init_zip_subsystem(void) { return 0; }
static inline void z_erofs_exit_zip_subsystem(void) {}
+static inline int z_erofs_load_lz4_config(struct super_block *sb,
+ struct erofs_super_block *dsb,
+ struct z_erofs_lz4_cfgs *lz4, int len)
+{
+ if (lz4 || dsb->u1.lz4_max_distance) {
+ erofs_err(sb, "lz4 algorithm isn't enabled");
+ return -EINVAL;
+ }
+ return 0;
+}
#endif /* !CONFIG_EROFS_FS_ZIP */
#define EFSCORRUPTED EUCLEAN /* Filesystem is corrupted */
diff --git a/fs/erofs/pcpubuf.c b/fs/erofs/pcpubuf.c
new file mode 100644
index 000000000000..6c885575128a
--- /dev/null
+++ b/fs/erofs/pcpubuf.c
@@ -0,0 +1,148 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) Gao Xiang <xiang@kernel.org>
+ *
+ * For low-latency decompression algorithms (e.g. lz4), reserve consecutive
+ * per-CPU virtual memory (in pages) in advance to store such inplace I/O
+ * data if inplace decompression is failed (due to unmet inplace margin for
+ * example).
+ */
+#include "internal.h"
+
+struct erofs_pcpubuf {
+ raw_spinlock_t lock;
+ void *ptr;
+ struct page **pages;
+ unsigned int nrpages;
+};
+
+static DEFINE_PER_CPU(struct erofs_pcpubuf, erofs_pcb);
+
+void *erofs_get_pcpubuf(unsigned int requiredpages)
+ __acquires(pcb->lock)
+{
+ struct erofs_pcpubuf *pcb = &get_cpu_var(erofs_pcb);
+
+ raw_spin_lock(&pcb->lock);
+ /* check if the per-CPU buffer is too small */
+ if (requiredpages > pcb->nrpages) {
+ raw_spin_unlock(&pcb->lock);
+ put_cpu_var(erofs_pcb);
+ /* (for sparse checker) pretend pcb->lock is still taken */
+ __acquire(pcb->lock);
+ return NULL;
+ }
+ return pcb->ptr;
+}
+
+void erofs_put_pcpubuf(void *ptr) __releases(pcb->lock)
+{
+ struct erofs_pcpubuf *pcb = &per_cpu(erofs_pcb, smp_processor_id());
+
+ DBG_BUGON(pcb->ptr != ptr);
+ raw_spin_unlock(&pcb->lock);
+ put_cpu_var(erofs_pcb);
+}
+
+/* the next step: support per-CPU page buffers hotplug */
+int erofs_pcpubuf_growsize(unsigned int nrpages)
+{
+ static DEFINE_MUTEX(pcb_resize_mutex);
+ static unsigned int pcb_nrpages;
+ LIST_HEAD(pagepool);
+ int delta, cpu, ret, i;
+
+ mutex_lock(&pcb_resize_mutex);
+ delta = nrpages - pcb_nrpages;
+ ret = 0;
+ /* avoid shrinking pcpubuf, since no idea how many fses rely on */
+ if (delta <= 0)
+ goto out;
+
+ for_each_possible_cpu(cpu) {
+ struct erofs_pcpubuf *pcb = &per_cpu(erofs_pcb, cpu);
+ struct page **pages, **oldpages;
+ void *ptr, *old_ptr;
+
+ pages = kmalloc_array(nrpages, sizeof(*pages), GFP_KERNEL);
+ if (!pages) {
+ ret = -ENOMEM;
+ break;
+ }
+
+ for (i = 0; i < nrpages; ++i) {
+ pages[i] = erofs_allocpage(&pagepool, GFP_KERNEL);
+ if (!pages[i]) {
+ ret = -ENOMEM;
+ oldpages = pages;
+ goto free_pagearray;
+ }
+ }
+ ptr = vmap(pages, nrpages, VM_MAP, PAGE_KERNEL);
+ if (!ptr) {
+ ret = -ENOMEM;
+ oldpages = pages;
+ goto free_pagearray;
+ }
+ raw_spin_lock(&pcb->lock);
+ old_ptr = pcb->ptr;
+ pcb->ptr = ptr;
+ oldpages = pcb->pages;
+ pcb->pages = pages;
+ i = pcb->nrpages;
+ pcb->nrpages = nrpages;
+ raw_spin_unlock(&pcb->lock);
+
+ if (!oldpages) {
+ DBG_BUGON(old_ptr);
+ continue;
+ }
+
+ if (old_ptr)
+ vunmap(old_ptr);
+free_pagearray:
+ while (i)
+ list_add(&oldpages[--i]->lru, &pagepool);
+ kfree(oldpages);
+ if (ret)
+ break;
+ }
+ pcb_nrpages = nrpages;
+ put_pages_list(&pagepool);
+out:
+ mutex_unlock(&pcb_resize_mutex);
+ return ret;
+}
+
+void erofs_pcpubuf_init(void)
+{
+ int cpu;
+
+ for_each_possible_cpu(cpu) {
+ struct erofs_pcpubuf *pcb = &per_cpu(erofs_pcb, cpu);
+
+ raw_spin_lock_init(&pcb->lock);
+ }
+}
+
+void erofs_pcpubuf_exit(void)
+{
+ int cpu, i;
+
+ for_each_possible_cpu(cpu) {
+ struct erofs_pcpubuf *pcb = &per_cpu(erofs_pcb, cpu);
+
+ if (pcb->ptr) {
+ vunmap(pcb->ptr);
+ pcb->ptr = NULL;
+ }
+ if (!pcb->pages)
+ continue;
+
+ for (i = 0; i < pcb->nrpages; ++i)
+ if (pcb->pages[i])
+ put_page(pcb->pages[i]);
+ kfree(pcb->pages);
+ pcb->pages = NULL;
+ }
+}
diff --git a/fs/erofs/super.c b/fs/erofs/super.c
index d5a6b9b888a5..bbf3bbd908e0 100644
--- a/fs/erofs/super.c
+++ b/fs/erofs/super.c
@@ -122,6 +122,136 @@ static bool check_layout_compatibility(struct super_block *sb,
return true;
}
+#ifdef CONFIG_EROFS_FS_ZIP
+/* read variable-sized metadata, offset will be aligned by 4-byte */
+static void *erofs_read_metadata(struct super_block *sb, struct page **pagep,
+ erofs_off_t *offset, int *lengthp)
+{
+ struct page *page = *pagep;
+ u8 *buffer, *ptr;
+ int len, i, cnt;
+ erofs_blk_t blk;
+
+ *offset = round_up(*offset, 4);
+ blk = erofs_blknr(*offset);
+
+ if (!page || page->index != blk) {
+ if (page) {
+ unlock_page(page);
+ put_page(page);
+ }
+ page = erofs_get_meta_page(sb, blk);
+ if (IS_ERR(page))
+ goto err_nullpage;
+ }
+
+ ptr = kmap(page);
+ len = le16_to_cpu(*(__le16 *)&ptr[erofs_blkoff(*offset)]);
+ if (!len)
+ len = U16_MAX + 1;
+ buffer = kmalloc(len, GFP_KERNEL);
+ if (!buffer) {
+ buffer = ERR_PTR(-ENOMEM);
+ goto out;
+ }
+ *offset += sizeof(__le16);
+ *lengthp = len;
+
+ for (i = 0; i < len; i += cnt) {
+ cnt = min(EROFS_BLKSIZ - (int)erofs_blkoff(*offset), len - i);
+ blk = erofs_blknr(*offset);
+
+ if (!page || page->index != blk) {
+ if (page) {
+ kunmap(page);
+ unlock_page(page);
+ put_page(page);
+ }
+ page = erofs_get_meta_page(sb, blk);
+ if (IS_ERR(page)) {
+ kfree(buffer);
+ goto err_nullpage;
+ }
+ ptr = kmap(page);
+ }
+ memcpy(buffer + i, ptr + erofs_blkoff(*offset), cnt);
+ *offset += cnt;
+ }
+out:
+ kunmap(page);
+ *pagep = page;
+ return buffer;
+err_nullpage:
+ *pagep = NULL;
+ return page;
+}
+
+static int erofs_load_compr_cfgs(struct super_block *sb,
+ struct erofs_super_block *dsb)
+{
+ struct erofs_sb_info *sbi;
+ struct page *page;
+ unsigned int algs, alg;
+ erofs_off_t offset;
+ int size, ret;
+
+ sbi = EROFS_SB(sb);
+ sbi->available_compr_algs = le16_to_cpu(dsb->u1.available_compr_algs);
+
+ if (sbi->available_compr_algs & ~Z_EROFS_ALL_COMPR_ALGS) {
+ erofs_err(sb, "try to load compressed fs with unsupported algorithms %x",
+ sbi->available_compr_algs & ~Z_EROFS_ALL_COMPR_ALGS);
+ return -EINVAL;
+ }
+
+ offset = EROFS_SUPER_OFFSET + sbi->sb_size;
+ page = NULL;
+ alg = 0;
+ ret = 0;
+
+ for (algs = sbi->available_compr_algs; algs; algs >>= 1, ++alg) {
+ void *data;
+
+ if (!(algs & 1))
+ continue;
+
+ data = erofs_read_metadata(sb, &page, &offset, &size);
+ if (IS_ERR(data)) {
+ ret = PTR_ERR(data);
+ goto err;
+ }
+
+ switch (alg) {
+ case Z_EROFS_COMPRESSION_LZ4:
+ ret = z_erofs_load_lz4_config(sb, dsb, data, size);
+ break;
+ default:
+ DBG_BUGON(1);
+ ret = -EFAULT;
+ }
+ kfree(data);
+ if (ret)
+ goto err;
+ }
+err:
+ if (page) {
+ unlock_page(page);
+ put_page(page);
+ }
+ return ret;
+}
+#else
+static int erofs_load_compr_cfgs(struct super_block *sb,
+ struct erofs_super_block *dsb)
+{
+ if (dsb->u1.available_compr_algs) {
+ erofs_err(sb, "try to load compressed fs when compression is disabled");
+ return -EINVAL;
+ }
+ return 0;
+}
+#endif
+
static int erofs_read_superblock(struct super_block *sb)
{
struct erofs_sb_info *sbi;
@@ -149,7 +279,7 @@ static int erofs_read_superblock(struct super_block *sb)
}
sbi->feature_compat = le32_to_cpu(dsb->feature_compat);
- if (sbi->feature_compat & EROFS_FEATURE_COMPAT_SB_CHKSUM) {
+ if (erofs_sb_has_sb_chksum(sbi)) {
ret = erofs_superblock_csum_verify(sb, data);
if (ret)
goto out;
@@ -166,6 +296,12 @@ static int erofs_read_superblock(struct super_block *sb)
if (!check_layout_compatibility(sb, dsb))
goto out;
+ sbi->sb_size = 128 + dsb->sb_extslots * EROFS_SB_EXTSLOT_SIZE;
+ if (sbi->sb_size > EROFS_BLKSIZ) {
+ erofs_err(sb, "invalid sb_extslots %u (more than a fs block)",
+ sbi->sb_size);
+ goto out;
+ }
sbi->blocks = le32_to_cpu(dsb->blocks);
sbi->meta_blkaddr = le32_to_cpu(dsb->meta_blkaddr);
#ifdef CONFIG_EROFS_FS_XATTR
@@ -187,7 +323,12 @@ static int erofs_read_superblock(struct super_block *sb)
ret = -EFSCORRUPTED;
goto out;
}
- ret = 0;
+
+ /* parse on-disk compression configurations */
+ if (erofs_sb_has_compr_cfgs(sbi))
+ ret = erofs_load_compr_cfgs(sb, dsb);
+ else
+ ret = z_erofs_load_lz4_config(sb, dsb, NULL, 0);
out:
kunmap(page);
put_page(page);
@@ -200,6 +341,7 @@ static void erofs_default_options(struct erofs_fs_context *ctx)
#ifdef CONFIG_EROFS_FS_ZIP
ctx->cache_strategy = EROFS_ZIP_CACHE_READAROUND;
ctx->max_sync_decompress_pages = 3;
+ ctx->readahead_sync_decompress = false;
#endif
#ifdef CONFIG_EROFS_FS_XATTR
set_opt(ctx, XATTR_USER);
@@ -513,6 +655,7 @@ static int __init erofs_module_init(void)
if (err)
goto shrinker_err;
+ erofs_pcpubuf_init();
err = z_erofs_init_zip_subsystem();
if (err)
goto zip_err;
@@ -542,6 +685,7 @@ static void __exit erofs_module_exit(void)
/* Ensure all RCU free inodes are safe before cache is destroyed. */
rcu_barrier();
kmem_cache_destroy(erofs_inode_cachep);
+ erofs_pcpubuf_exit();
}
/* get filesystem statistics */
diff --git a/fs/erofs/utils.c b/fs/erofs/utils.c
index de9986d2f82f..6758c5b19f7c 100644
--- a/fs/erofs/utils.c
+++ b/fs/erofs/utils.c
@@ -21,18 +21,6 @@ struct page *erofs_allocpage(struct list_head *pool, gfp_t gfp)
return page;
}
-#if (EROFS_PCPUBUF_NR_PAGES > 0)
-static struct {
- u8 data[PAGE_SIZE * EROFS_PCPUBUF_NR_PAGES];
-} ____cacheline_aligned_in_smp erofs_pcpubuf[NR_CPUS];
-
-void *erofs_get_pcpubuf(unsigned int pagenr)
-{
- preempt_disable();
- return &erofs_pcpubuf[smp_processor_id()].data[pagenr * PAGE_SIZE];
-}
-#endif
-
#ifdef CONFIG_EROFS_FS_ZIP
/* global shrink count (for all mounted EROFS instances) */
static atomic_long_t erofs_global_shrink_cnt;
diff --git a/fs/erofs/zdata.c b/fs/erofs/zdata.c
index 3851e1a64f73..78e4b598ecca 100644
--- a/fs/erofs/zdata.c
+++ b/fs/erofs/zdata.c
@@ -11,6 +11,93 @@
#include <trace/events/erofs.h>
/*
+ * since pclustersize is variable for big pcluster feature, introduce slab
+ * pools implementation for different pcluster sizes.
+ */
+struct z_erofs_pcluster_slab {
+ struct kmem_cache *slab;
+ unsigned int maxpages;
+ char name[48];
+};
+
+#define _PCLP(n) { .maxpages = n }
+
+static struct z_erofs_pcluster_slab pcluster_pool[] __read_mostly = {
+ _PCLP(1), _PCLP(4), _PCLP(16), _PCLP(64), _PCLP(128),
+ _PCLP(Z_EROFS_PCLUSTER_MAX_PAGES)
+};
+
+static void z_erofs_destroy_pcluster_pool(void)
+{
+ int i;
+
+ for (i = 0; i < ARRAY_SIZE(pcluster_pool); ++i) {
+ if (!pcluster_pool[i].slab)
+ continue;
+ kmem_cache_destroy(pcluster_pool[i].slab);
+ pcluster_pool[i].slab = NULL;
+ }
+}
+
+static int z_erofs_create_pcluster_pool(void)
+{
+ struct z_erofs_pcluster_slab *pcs;
+ struct z_erofs_pcluster *a;
+ unsigned int size;
+
+ for (pcs = pcluster_pool;
+ pcs < pcluster_pool + ARRAY_SIZE(pcluster_pool); ++pcs) {
+ size = struct_size(a, compressed_pages, pcs->maxpages);
+
+ sprintf(pcs->name, "erofs_pcluster-%u", pcs->maxpages);
+ pcs->slab = kmem_cache_create(pcs->name, size, 0,
+ SLAB_RECLAIM_ACCOUNT, NULL);
+ if (pcs->slab)
+ continue;
+
+ z_erofs_destroy_pcluster_pool();
+ return -ENOMEM;
+ }
+ return 0;
+}
+
+static struct z_erofs_pcluster *z_erofs_alloc_pcluster(unsigned int nrpages)
+{
+ int i;
+
+ for (i = 0; i < ARRAY_SIZE(pcluster_pool); ++i) {
+ struct z_erofs_pcluster_slab *pcs = pcluster_pool + i;
+ struct z_erofs_pcluster *pcl;
+
+ if (nrpages > pcs->maxpages)
+ continue;
+
+ pcl = kmem_cache_zalloc(pcs->slab, GFP_NOFS);
+ if (!pcl)
+ return ERR_PTR(-ENOMEM);
+ pcl->pclusterpages = nrpages;
+ return pcl;
+ }
+ return ERR_PTR(-EINVAL);
+}
+
+static void z_erofs_free_pcluster(struct z_erofs_pcluster *pcl)
+{
+ int i;
+
+ for (i = 0; i < ARRAY_SIZE(pcluster_pool); ++i) {
+ struct z_erofs_pcluster_slab *pcs = pcluster_pool + i;
+
+ if (pcl->pclusterpages > pcs->maxpages)
+ continue;
+
+ kmem_cache_free(pcs->slab, pcl);
+ return;
+ }
+ DBG_BUGON(1);
+}
+
+/*
* a compressed_pages[] placeholder in order to avoid
* being filled with file pages for in-place decompression.
*/
@@ -37,12 +124,11 @@ typedef tagptr1_t compressed_page_t;
tagptr_fold(compressed_page_t, page, 1)
static struct workqueue_struct *z_erofs_workqueue __read_mostly;
-static struct kmem_cache *pcluster_cachep __read_mostly;
void z_erofs_exit_zip_subsystem(void)
{
destroy_workqueue(z_erofs_workqueue);
- kmem_cache_destroy(pcluster_cachep);
+ z_erofs_destroy_pcluster_pool();
}
static inline int z_erofs_init_workqueue(void)
@@ -59,32 +145,16 @@ static inline int z_erofs_init_workqueue(void)
return z_erofs_workqueue ? 0 : -ENOMEM;
}
-static void z_erofs_pcluster_init_once(void *ptr)
-{
- struct z_erofs_pcluster *pcl = ptr;
- struct z_erofs_collection *cl = z_erofs_primarycollection(pcl);
- unsigned int i;
-
- mutex_init(&cl->lock);
- cl->nr_pages = 0;
- cl->vcnt = 0;
- for (i = 0; i < Z_EROFS_CLUSTER_MAX_PAGES; ++i)
- pcl->compressed_pages[i] = NULL;
-}
-
int __init z_erofs_init_zip_subsystem(void)
{
- pcluster_cachep = kmem_cache_create("erofs_compress",
- Z_EROFS_WORKGROUP_SIZE, 0,
- SLAB_RECLAIM_ACCOUNT,
- z_erofs_pcluster_init_once);
- if (pcluster_cachep) {
- if (!z_erofs_init_workqueue())
- return 0;
-
- kmem_cache_destroy(pcluster_cachep);
- }
- return -ENOMEM;
+ int err = z_erofs_create_pcluster_pool();
+
+ if (err)
+ return err;
+ err = z_erofs_init_workqueue();
+ if (err)
+ z_erofs_destroy_pcluster_pool();
+ return err;
}
enum z_erofs_collectmode {
@@ -104,6 +174,12 @@ enum z_erofs_collectmode {
* |_______PRIMARY_FOLLOWED_______|________PRIMARY_HOOKED___________|
*/
COLLECT_PRIMARY_HOOKED,
+ /*
+ * a weak form of COLLECT_PRIMARY_FOLLOWED, the difference is that it
+ * could be dispatched into bypass queue later due to uptodated managed
+ * pages. All related online pages cannot be reused for inplace I/O (or
+ * pagevec) since it can be directly decoded without I/O submission.
+ */
COLLECT_PRIMARY_FOLLOWED_NOINPLACE,
/*
* The current collection has been linked with the owned chain, and
@@ -128,7 +204,8 @@ struct z_erofs_collector {
struct z_erofs_pcluster *pcl, *tailpcl;
struct z_erofs_collection *cl;
- struct page **compressedpages;
+ /* a pointer used to pick up inplace I/O pages */
+ struct page **icpage_ptr;
z_erofs_next_pcluster_t owned_head;
enum z_erofs_collectmode mode;
@@ -162,18 +239,19 @@ static void preload_compressed_pages(struct z_erofs_collector *clt,
enum z_erofs_cache_alloctype type,
struct list_head *pagepool)
{
- const struct z_erofs_pcluster *pcl = clt->pcl;
- const unsigned int clusterpages = BIT(pcl->clusterbits);
- struct page **pages = clt->compressedpages;
- pgoff_t index = pcl->obj.index + (pages - pcl->compressed_pages);
+ struct z_erofs_pcluster *pcl = clt->pcl;
bool standalone = true;
gfp_t gfp = (mapping_gfp_mask(mc) & ~__GFP_DIRECT_RECLAIM) |
__GFP_NOMEMALLOC | __GFP_NORETRY | __GFP_NOWARN;
+ struct page **pages;
+ pgoff_t index;
if (clt->mode < COLLECT_PRIMARY_FOLLOWED)
return;
- for (; pages < pcl->compressed_pages + clusterpages; ++pages) {
+ pages = pcl->compressed_pages;
+ index = pcl->obj.index;
+ for (; index < pcl->obj.index + pcl->pclusterpages; ++index, ++pages) {
struct page *page;
compressed_page_t t;
struct page *newpage = NULL;
@@ -186,21 +264,25 @@ static void preload_compressed_pages(struct z_erofs_collector *clt,
if (page) {
t = tag_compressed_page_justfound(page);
- } else if (type == DELAYEDALLOC) {
- t = tagptr_init(compressed_page_t, PAGE_UNALLOCATED);
- } else if (type == TRYALLOC) {
- newpage = erofs_allocpage(pagepool, gfp);
- if (!newpage)
- goto dontalloc;
-
- set_page_private(newpage, Z_EROFS_PREALLOCATED_PAGE);
- t = tag_compressed_page_justfound(newpage);
- } else { /* DONTALLOC */
-dontalloc:
- if (standalone)
- clt->compressedpages = pages;
+ } else {
+ /* I/O is needed, no possible to decompress directly */
standalone = false;
- continue;
+ switch (type) {
+ case DELAYEDALLOC:
+ t = tagptr_init(compressed_page_t,
+ PAGE_UNALLOCATED);
+ break;
+ case TRYALLOC:
+ newpage = erofs_allocpage(pagepool, gfp);
+ if (!newpage)
+ continue;
+ set_page_private(newpage,
+ Z_EROFS_PREALLOCATED_PAGE);
+ t = tag_compressed_page_justfound(newpage);
+ break;
+ default: /* DONTALLOC */
+ continue;
+ }
}
if (!cmpxchg_relaxed(pages, NULL, tagptr_cast_ptr(t)))
@@ -214,7 +296,11 @@ dontalloc:
}
}
- if (standalone) /* downgrade to PRIMARY_FOLLOWED_NOINPLACE */
+ /*
+ * don't do inplace I/O if all compressed pages are available in
+ * managed cache since it can be moved to the bypass queue instead.
+ */
+ if (standalone)
clt->mode = COLLECT_PRIMARY_FOLLOWED_NOINPLACE;
}
@@ -225,14 +311,13 @@ int erofs_try_to_free_all_cached_pages(struct erofs_sb_info *sbi,
struct z_erofs_pcluster *const pcl =
container_of(grp, struct z_erofs_pcluster, obj);
struct address_space *const mapping = MNGD_MAPPING(sbi);
- const unsigned int clusterpages = BIT(pcl->clusterbits);
int i;
/*
* refcount of workgroup is now freezed as 1,
* therefore no need to worry about available decompression users.
*/
- for (i = 0; i < clusterpages; ++i) {
+ for (i = 0; i < pcl->pclusterpages; ++i) {
struct page *page = pcl->compressed_pages[i];
if (!page)
@@ -257,13 +342,12 @@ int erofs_try_to_free_cached_page(struct address_space *mapping,
struct page *page)
{
struct z_erofs_pcluster *const pcl = (void *)page_private(page);
- const unsigned int clusterpages = BIT(pcl->clusterbits);
int ret = 0; /* 0 - busy */
if (erofs_workgroup_try_to_freeze(&pcl->obj, 1)) {
unsigned int i;
- for (i = 0; i < clusterpages; ++i) {
+ for (i = 0; i < pcl->pclusterpages; ++i) {
if (pcl->compressed_pages[i] == page) {
WRITE_ONCE(pcl->compressed_pages[i], NULL);
ret = 1;
@@ -279,16 +363,14 @@ int erofs_try_to_free_cached_page(struct address_space *mapping,
}
/* page_type must be Z_EROFS_PAGE_TYPE_EXCLUSIVE */
-static inline bool z_erofs_try_inplace_io(struct z_erofs_collector *clt,
- struct page *page)
+static bool z_erofs_try_inplace_io(struct z_erofs_collector *clt,
+ struct page *page)
{
struct z_erofs_pcluster *const pcl = clt->pcl;
- const unsigned int clusterpages = BIT(pcl->clusterbits);
- while (clt->compressedpages < pcl->compressed_pages + clusterpages) {
- if (!cmpxchg(clt->compressedpages++, NULL, page))
+ while (clt->icpage_ptr > pcl->compressed_pages)
+ if (!cmpxchg(--clt->icpage_ptr, NULL, page))
return true;
- }
return false;
}
@@ -399,10 +481,10 @@ static int z_erofs_register_collection(struct z_erofs_collector *clt,
struct erofs_workgroup *grp;
int err;
- /* no available workgroup, let's allocate one */
- pcl = kmem_cache_alloc(pcluster_cachep, GFP_NOFS);
- if (!pcl)
- return -ENOMEM;
+ /* no available pcluster, let's allocate one */
+ pcl = z_erofs_alloc_pcluster(map->m_plen >> PAGE_SHIFT);
+ if (IS_ERR(pcl))
+ return PTR_ERR(pcl);
atomic_set(&pcl->obj.refcount, 1);
pcl->obj.index = map->m_pa >> PAGE_SHIFT;
@@ -416,25 +498,18 @@ static int z_erofs_register_collection(struct z_erofs_collector *clt,
else
pcl->algorithmformat = Z_EROFS_COMPRESSION_SHIFTED;
- pcl->clusterbits = EROFS_I(inode)->z_physical_clusterbits[0];
- pcl->clusterbits -= PAGE_SHIFT;
-
/* new pclusters should be claimed as type 1, primary and followed */
pcl->next = clt->owned_head;
clt->mode = COLLECT_PRIMARY_FOLLOWED;
cl = z_erofs_primarycollection(pcl);
-
- /* must be cleaned before freeing to slab */
- DBG_BUGON(cl->nr_pages);
- DBG_BUGON(cl->vcnt);
-
cl->pageofs = map->m_la & ~PAGE_MASK;
/*
* lock all primary followed works before visible to others
* and mutex_trylock *never* fails for a new pcluster.
*/
+ mutex_init(&cl->lock);
DBG_BUGON(!mutex_trylock(&cl->lock));
grp = erofs_insert_workgroup(inode->i_sb, &pcl->obj);
@@ -458,7 +533,7 @@ static int z_erofs_register_collection(struct z_erofs_collector *clt,
err_out:
mutex_unlock(&cl->lock);
- kmem_cache_free(pcluster_cachep, pcl);
+ z_erofs_free_pcluster(pcl);
return err;
}
@@ -502,9 +577,8 @@ out:
z_erofs_pagevec_ctor_init(&clt->vector, Z_EROFS_NR_INLINE_PAGEVECS,
clt->cl->pagevec, clt->cl->vcnt);
- clt->compressedpages = clt->pcl->compressed_pages;
- if (clt->mode <= COLLECT_PRIMARY) /* cannot do in-place I/O */
- clt->compressedpages += Z_EROFS_CLUSTER_MAX_PAGES;
+ /* since file-backed online pages are traversed in reverse order */
+ clt->icpage_ptr = clt->pcl->compressed_pages + clt->pcl->pclusterpages;
return 0;
}
@@ -517,9 +591,8 @@ static void z_erofs_rcu_callback(struct rcu_head *head)
struct z_erofs_collection *const cl =
container_of(head, struct z_erofs_collection, rcu);
- kmem_cache_free(pcluster_cachep,
- container_of(cl, struct z_erofs_pcluster,
- primary_collection));
+ z_erofs_free_pcluster(container_of(cl, struct z_erofs_pcluster,
+ primary_collection));
}
void erofs_workgroup_free_rcu(struct erofs_workgroup *grp)
@@ -706,9 +779,12 @@ err_out:
goto out;
}
+static void z_erofs_decompressqueue_work(struct work_struct *work);
static void z_erofs_decompress_kickoff(struct z_erofs_decompressqueue *io,
bool sync, int bios)
{
+ struct erofs_sb_info *const sbi = EROFS_SB(io->sb);
+
/* wake up the caller thread for sync decompression */
if (sync) {
unsigned long flags;
@@ -720,8 +796,15 @@ static void z_erofs_decompress_kickoff(struct z_erofs_decompressqueue *io,
return;
}
- if (!atomic_add_return(bios, &io->pending_bios))
+ if (atomic_add_return(bios, &io->pending_bios))
+ return;
+ /* Use workqueue and sync decompression for atomic contexts only */
+ if (in_atomic() || irqs_disabled()) {
queue_work(z_erofs_workqueue, &io->u.work);
+ sbi->ctx.readahead_sync_decompress = true;
+ return;
+ }
+ z_erofs_decompressqueue_work(&io->u.work);
}
static bool z_erofs_page_is_invalidated(struct page *page)
@@ -761,9 +844,8 @@ static int z_erofs_decompress_pcluster(struct super_block *sb,
struct list_head *pagepool)
{
struct erofs_sb_info *const sbi = EROFS_SB(sb);
- const unsigned int clusterpages = BIT(pcl->clusterbits);
struct z_erofs_pagevec_ctor ctor;
- unsigned int i, outputsize, llen, nr_pages;
+ unsigned int i, inputsize, outputsize, llen, nr_pages;
struct page *pages_onstack[Z_EROFS_VMAP_ONSTACK_PAGES];
struct page **pages, **compressed_pages, *page;
@@ -843,7 +925,7 @@ static int z_erofs_decompress_pcluster(struct super_block *sb,
overlapped = false;
compressed_pages = pcl->compressed_pages;
- for (i = 0; i < clusterpages; ++i) {
+ for (i = 0; i < pcl->pclusterpages; ++i) {
unsigned int pagenr;
page = compressed_pages[i];
@@ -896,12 +978,13 @@ static int z_erofs_decompress_pcluster(struct super_block *sb,
partial = true;
}
+ inputsize = pcl->pclusterpages * PAGE_SIZE;
err = z_erofs_decompress(&(struct z_erofs_decompress_req) {
.sb = sb,
.in = compressed_pages,
.out = pages,
.pageofs_out = cl->pageofs,
- .inputsize = PAGE_SIZE,
+ .inputsize = inputsize,
.outputsize = outputsize,
.alg = pcl->algorithmformat,
.inplace_io = overlapped,
@@ -909,8 +992,8 @@ static int z_erofs_decompress_pcluster(struct super_block *sb,
}, pagepool);
out:
- /* must handle all compressed pages before endding pages */
- for (i = 0; i < clusterpages; ++i) {
+ /* must handle all compressed pages before ending pages */
+ for (i = 0; i < pcl->pclusterpages; ++i) {
page = compressed_pages[i];
if (erofs_page_is_managed(sbi, page))
@@ -1213,7 +1296,7 @@ static void z_erofs_submit_queue(struct super_block *sb,
pcl = container_of(owned_head, struct z_erofs_pcluster, next);
cur = pcl->obj.index;
- end = cur + BIT(pcl->clusterbits);
+ end = cur + pcl->pclusterpages;
/* close the main owned chain at first */
owned_head = cmpxchg(&pcl->next, Z_EROFS_PCLUSTER_TAIL,
@@ -1333,7 +1416,8 @@ static void z_erofs_readahead(struct readahead_control *rac)
struct erofs_sb_info *const sbi = EROFS_I_SB(inode);
unsigned int nr_pages = readahead_count(rac);
- bool sync = (nr_pages <= sbi->ctx.max_sync_decompress_pages);
+ bool sync = (sbi->ctx.readahead_sync_decompress &&
+ nr_pages <= sbi->ctx.max_sync_decompress_pages);
struct z_erofs_decompress_frontend f = DECOMPRESS_FRONTEND_INIT(inode);
struct page *page, *head = NULL;
LIST_HEAD(pagepool);
diff --git a/fs/erofs/zdata.h b/fs/erofs/zdata.h
index b503b353d4ab..942ee69dff6a 100644
--- a/fs/erofs/zdata.h
+++ b/fs/erofs/zdata.h
@@ -10,6 +10,7 @@
#include "internal.h"
#include "zpvec.h"
+#define Z_EROFS_PCLUSTER_MAX_PAGES (Z_EROFS_PCLUSTER_MAX_SIZE / PAGE_SIZE)
#define Z_EROFS_NR_INLINE_PAGEVECS 3
/*
@@ -59,16 +60,17 @@ struct z_erofs_pcluster {
/* A: point to next chained pcluster or TAILs */
z_erofs_next_pcluster_t next;
- /* A: compressed pages (including multi-usage pages) */
- struct page *compressed_pages[Z_EROFS_CLUSTER_MAX_PAGES];
-
/* A: lower limit of decompressed length and if full length or not */
unsigned int length;
+ /* I: physical cluster size in pages */
+ unsigned short pclusterpages;
+
/* I: compression algorithm format */
unsigned char algorithmformat;
- /* I: bit shift of physical cluster size */
- unsigned char clusterbits;
+
+ /* A: compressed pages (can be cached or inplaced pages) */
+ struct page *compressed_pages[];
};
#define z_erofs_primarycollection(pcluster) (&(pcluster)->primary_collection)
@@ -82,8 +84,6 @@ struct z_erofs_pcluster {
#define Z_EROFS_PCLUSTER_NIL (NULL)
-#define Z_EROFS_WORKGROUP_SIZE sizeof(struct z_erofs_pcluster)
-
struct z_erofs_decompressqueue {
struct super_block *sb;
atomic_t pending_bios;
diff --git a/fs/erofs/zmap.c b/fs/erofs/zmap.c
index 14d2de35110c..e62d813756f2 100644
--- a/fs/erofs/zmap.c
+++ b/fs/erofs/zmap.c
@@ -11,17 +11,16 @@
int z_erofs_fill_inode(struct inode *inode)
{
struct erofs_inode *const vi = EROFS_I(inode);
+ struct erofs_sb_info *sbi = EROFS_SB(inode->i_sb);
- if (vi->datalayout == EROFS_INODE_FLAT_COMPRESSION_LEGACY) {
+ if (!erofs_sb_has_big_pcluster(sbi) &&
+ vi->datalayout == EROFS_INODE_FLAT_COMPRESSION_LEGACY) {
vi->z_advise = 0;
vi->z_algorithmtype[0] = 0;
vi->z_algorithmtype[1] = 0;
vi->z_logical_clusterbits = LOG_BLOCK_SIZE;
- vi->z_physical_clusterbits[0] = vi->z_logical_clusterbits;
- vi->z_physical_clusterbits[1] = vi->z_logical_clusterbits;
set_bit(EROFS_I_Z_INITED_BIT, &vi->flags);
}
-
inode->i_mapping->a_ops = &z_erofs_aops;
return 0;
}
@@ -52,7 +51,8 @@ static int z_erofs_fill_inode_lazy(struct inode *inode)
if (test_bit(EROFS_I_Z_INITED_BIT, &vi->flags))
goto out_unlock;
- DBG_BUGON(vi->datalayout == EROFS_INODE_FLAT_COMPRESSION_LEGACY);
+ DBG_BUGON(!erofs_sb_has_big_pcluster(EROFS_SB(sb)) &&
+ vi->datalayout == EROFS_INODE_FLAT_COMPRESSION_LEGACY);
pos = ALIGN(iloc(EROFS_SB(sb), vi->nid) + vi->inode_isize +
vi->xattr_isize, 8);
@@ -77,18 +77,22 @@ static int z_erofs_fill_inode_lazy(struct inode *inode)
}
vi->z_logical_clusterbits = LOG_BLOCK_SIZE + (h->h_clusterbits & 7);
- vi->z_physical_clusterbits[0] = vi->z_logical_clusterbits +
- ((h->h_clusterbits >> 3) & 3);
-
- if (vi->z_physical_clusterbits[0] != LOG_BLOCK_SIZE) {
- erofs_err(sb, "unsupported physical clusterbits %u for nid %llu, please upgrade kernel",
- vi->z_physical_clusterbits[0], vi->nid);
- err = -EOPNOTSUPP;
+ if (!erofs_sb_has_big_pcluster(EROFS_SB(sb)) &&
+ vi->z_advise & (Z_EROFS_ADVISE_BIG_PCLUSTER_1 |
+ Z_EROFS_ADVISE_BIG_PCLUSTER_2)) {
+ erofs_err(sb, "per-inode big pcluster without sb feature for nid %llu",
+ vi->nid);
+ err = -EFSCORRUPTED;
+ goto unmap_done;
+ }
+ if (vi->datalayout == EROFS_INODE_FLAT_COMPRESSION &&
+ !(vi->z_advise & Z_EROFS_ADVISE_BIG_PCLUSTER_1) ^
+ !(vi->z_advise & Z_EROFS_ADVISE_BIG_PCLUSTER_2)) {
+ erofs_err(sb, "big pcluster head1/2 of compact indexes should be consistent for nid %llu",
+ vi->nid);
+ err = -EFSCORRUPTED;
goto unmap_done;
}
-
- vi->z_physical_clusterbits[1] = vi->z_logical_clusterbits +
- ((h->h_clusterbits >> 5) & 7);
/* paired with smp_mb() at the beginning of the function */
smp_mb();
set_bit(EROFS_I_Z_INITED_BIT, &vi->flags);
@@ -111,7 +115,7 @@ struct z_erofs_maprecorder {
u8 type;
u16 clusterofs;
u16 delta[2];
- erofs_blk_t pblk;
+ erofs_blk_t pblk, compressedlcs;
};
static int z_erofs_reload_indexes(struct z_erofs_maprecorder *m,
@@ -174,6 +178,15 @@ static int legacy_load_cluster_from_disk(struct z_erofs_maprecorder *m,
case Z_EROFS_VLE_CLUSTER_TYPE_NONHEAD:
m->clusterofs = 1 << vi->z_logical_clusterbits;
m->delta[0] = le16_to_cpu(di->di_u.delta[0]);
+ if (m->delta[0] & Z_EROFS_VLE_DI_D0_CBLKCNT) {
+ if (!(vi->z_advise & Z_EROFS_ADVISE_BIG_PCLUSTER_1)) {
+ DBG_BUGON(1);
+ return -EFSCORRUPTED;
+ }
+ m->compressedlcs = m->delta[0] &
+ ~Z_EROFS_VLE_DI_D0_CBLKCNT;
+ m->delta[0] = 1;
+ }
m->delta[1] = le16_to_cpu(di->di_u.delta[1]);
break;
case Z_EROFS_VLE_CLUSTER_TYPE_PLAIN:
@@ -210,6 +223,7 @@ static int unpack_compacted_index(struct z_erofs_maprecorder *m,
unsigned int vcnt, base, lo, encodebits, nblk;
int i;
u8 *in, type;
+ bool big_pcluster;
if (1 << amortizedshift == 4)
vcnt = 2;
@@ -218,6 +232,7 @@ static int unpack_compacted_index(struct z_erofs_maprecorder *m,
else
return -EOPNOTSUPP;
+ big_pcluster = vi->z_advise & Z_EROFS_ADVISE_BIG_PCLUSTER_1;
encodebits = ((vcnt << amortizedshift) - sizeof(__le32)) * 8 / vcnt;
base = round_down(eofs, vcnt << amortizedshift);
in = m->kaddr + base;
@@ -229,7 +244,15 @@ static int unpack_compacted_index(struct z_erofs_maprecorder *m,
m->type = type;
if (type == Z_EROFS_VLE_CLUSTER_TYPE_NONHEAD) {
m->clusterofs = 1 << lclusterbits;
- if (i + 1 != vcnt) {
+ if (lo & Z_EROFS_VLE_DI_D0_CBLKCNT) {
+ if (!big_pcluster) {
+ DBG_BUGON(1);
+ return -EFSCORRUPTED;
+ }
+ m->compressedlcs = lo & ~Z_EROFS_VLE_DI_D0_CBLKCNT;
+ m->delta[0] = 1;
+ return 0;
+ } else if (i + 1 != (int)vcnt) {
m->delta[0] = lo;
return 0;
}
@@ -242,22 +265,48 @@ static int unpack_compacted_index(struct z_erofs_maprecorder *m,
in, encodebits * (i - 1), &type);
if (type != Z_EROFS_VLE_CLUSTER_TYPE_NONHEAD)
lo = 0;
+ else if (lo & Z_EROFS_VLE_DI_D0_CBLKCNT)
+ lo = 1;
m->delta[0] = lo + 1;
return 0;
}
m->clusterofs = lo;
m->delta[0] = 0;
/* figout out blkaddr (pblk) for HEAD lclusters */
- nblk = 1;
- while (i > 0) {
- --i;
- lo = decode_compactedbits(lclusterbits, lomask,
- in, encodebits * i, &type);
- if (type == Z_EROFS_VLE_CLUSTER_TYPE_NONHEAD)
- i -= lo;
-
- if (i >= 0)
+ if (!big_pcluster) {
+ nblk = 1;
+ while (i > 0) {
+ --i;
+ lo = decode_compactedbits(lclusterbits, lomask,
+ in, encodebits * i, &type);
+ if (type == Z_EROFS_VLE_CLUSTER_TYPE_NONHEAD)
+ i -= lo;
+
+ if (i >= 0)
+ ++nblk;
+ }
+ } else {
+ nblk = 0;
+ while (i > 0) {
+ --i;
+ lo = decode_compactedbits(lclusterbits, lomask,
+ in, encodebits * i, &type);
+ if (type == Z_EROFS_VLE_CLUSTER_TYPE_NONHEAD) {
+ if (lo & Z_EROFS_VLE_DI_D0_CBLKCNT) {
+ --i;
+ nblk += lo & ~Z_EROFS_VLE_DI_D0_CBLKCNT;
+ continue;
+ }
+ /* bigpcluster shouldn't have plain d0 == 1 */
+ if (lo <= 1) {
+ DBG_BUGON(1);
+ return -EFSCORRUPTED;
+ }
+ i -= lo - 2;
+ continue;
+ }
++nblk;
+ }
}
in += (vcnt << amortizedshift) - sizeof(__le32);
m->pblk = le32_to_cpu(*(__le32 *)in) + nblk;
@@ -381,6 +430,58 @@ static int z_erofs_extent_lookback(struct z_erofs_maprecorder *m,
return 0;
}
+static int z_erofs_get_extent_compressedlen(struct z_erofs_maprecorder *m,
+ unsigned int initial_lcn)
+{
+ struct erofs_inode *const vi = EROFS_I(m->inode);
+ struct erofs_map_blocks *const map = m->map;
+ const unsigned int lclusterbits = vi->z_logical_clusterbits;
+ unsigned long lcn;
+ int err;
+
+ DBG_BUGON(m->type != Z_EROFS_VLE_CLUSTER_TYPE_PLAIN &&
+ m->type != Z_EROFS_VLE_CLUSTER_TYPE_HEAD);
+ if (!(map->m_flags & EROFS_MAP_ZIPPED) ||
+ !(vi->z_advise & Z_EROFS_ADVISE_BIG_PCLUSTER_1)) {
+ map->m_plen = 1 << lclusterbits;
+ return 0;
+ }
+
+ lcn = m->lcn + 1;
+ if (m->compressedlcs)
+ goto out;
+ if (lcn == initial_lcn)
+ goto err_bonus_cblkcnt;
+
+ err = z_erofs_load_cluster_from_disk(m, lcn);
+ if (err)
+ return err;
+
+ switch (m->type) {
+ case Z_EROFS_VLE_CLUSTER_TYPE_NONHEAD:
+ if (m->delta[0] != 1)
+ goto err_bonus_cblkcnt;
+ if (m->compressedlcs)
+ break;
+ fallthrough;
+ default:
+ erofs_err(m->inode->i_sb,
+ "cannot found CBLKCNT @ lcn %lu of nid %llu",
+ lcn, vi->nid);
+ DBG_BUGON(1);
+ return -EFSCORRUPTED;
+ }
+out:
+ map->m_plen = m->compressedlcs << lclusterbits;
+ return 0;
+err_bonus_cblkcnt:
+ erofs_err(m->inode->i_sb,
+ "bogus CBLKCNT @ lcn %lu of nid %llu",
+ lcn, vi->nid);
+ DBG_BUGON(1);
+ return -EFSCORRUPTED;
+}
+
int z_erofs_map_blocks_iter(struct inode *inode,
struct erofs_map_blocks *map,
int flags)
@@ -392,6 +493,7 @@ int z_erofs_map_blocks_iter(struct inode *inode,
};
int err = 0;
unsigned int lclusterbits, endoff;
+ unsigned long initial_lcn;
unsigned long long ofs, end;
trace_z_erofs_map_blocks_iter_enter(inode, map, flags);
@@ -410,10 +512,10 @@ int z_erofs_map_blocks_iter(struct inode *inode,
lclusterbits = vi->z_logical_clusterbits;
ofs = map->m_la;
- m.lcn = ofs >> lclusterbits;
+ initial_lcn = ofs >> lclusterbits;
endoff = ofs & ((1 << lclusterbits) - 1);
- err = z_erofs_load_cluster_from_disk(&m, m.lcn);
+ err = z_erofs_load_cluster_from_disk(&m, initial_lcn);
if (err)
goto unmap_out;
@@ -443,7 +545,7 @@ int z_erofs_map_blocks_iter(struct inode *inode,
m.delta[0] = 1;
fallthrough;
case Z_EROFS_VLE_CLUSTER_TYPE_NONHEAD:
- /* get the correspoinding first chunk */
+ /* get the corresponding first chunk */
err = z_erofs_extent_lookback(&m, m.delta[0]);
if (err)
goto unmap_out;
@@ -457,10 +559,12 @@ int z_erofs_map_blocks_iter(struct inode *inode,
}
map->m_llen = end - map->m_la;
- map->m_plen = 1 << lclusterbits;
map->m_pa = blknr_to_addr(m.pblk);
map->m_flags |= EROFS_MAP_MAPPED;
+ err = z_erofs_get_extent_compressedlen(&m, initial_lcn);
+ if (err)
+ goto out;
unmap_out:
if (m.kaddr)
kunmap_atomic(m.kaddr);
diff --git a/fs/eventpoll.c b/fs/eventpoll.c
index 3196474cbe24..73138ea68342 100644
--- a/fs/eventpoll.c
+++ b/fs/eventpoll.c
@@ -366,8 +366,8 @@ static inline struct epitem *ep_item_from_wait(wait_queue_entry_t *p)
*
* @ep: Pointer to the eventpoll context.
*
- * Returns: Returns a value different than zero if ready events are available,
- * or zero otherwise.
+ * Return: a value different than %zero if ready events are available,
+ * or %zero otherwise.
*/
static inline int ep_events_available(struct eventpoll *ep)
{
@@ -1023,7 +1023,7 @@ struct file *get_epoll_tfile_raw_ptr(struct file *file, int tfd,
}
#endif /* CONFIG_KCMP */
-/**
+/*
* Adds a new entry to the tail of the list in a lockless way, i.e.
* multiple CPUs are allowed to call this function concurrently.
*
@@ -1035,10 +1035,10 @@ struct file *get_epoll_tfile_raw_ptr(struct file *file, int tfd,
* completed.
*
* Also an element can be locklessly added to the list only in one
- * direction i.e. either to the tail either to the head, otherwise
+ * direction i.e. either to the tail or to the head, otherwise
* concurrent access will corrupt the list.
*
- * Returns %false if element has been already added to the list, %true
+ * Return: %false if element has been already added to the list, %true
* otherwise.
*/
static inline bool list_add_tail_lockless(struct list_head *new,
@@ -1076,11 +1076,11 @@ static inline bool list_add_tail_lockless(struct list_head *new,
return true;
}
-/**
+/*
* Chains a new epi entry to the tail of the ep->ovflist in a lockless way,
* i.e. multiple CPUs are allowed to call this function concurrently.
*
- * Returns %false if epi element has been already chained, %true otherwise.
+ * Return: %false if epi element has been already chained, %true otherwise.
*/
static inline bool chain_epi_lockless(struct epitem *epi)
{
@@ -1105,8 +1105,8 @@ static inline bool chain_epi_lockless(struct epitem *epi)
* mechanism. It is called by the stored file descriptors when they
* have events to report.
*
- * This callback takes a read lock in order not to content with concurrent
- * events from another file descriptors, thus all modifications to ->rdllist
+ * This callback takes a read lock in order not to contend with concurrent
+ * events from another file descriptor, thus all modifications to ->rdllist
* or ->ovflist are lockless. Read lock is paired with the write lock from
* ep_scan_ready_list(), which stops all list modifications and guarantees
* that lists state is seen correctly.
@@ -1335,8 +1335,8 @@ static int reverse_path_check_proc(struct hlist_head *refs, int depth)
* paths such that we will spend all our time waking up
* eventpoll objects.
*
- * Returns: Returns zero if the proposed links don't create too many paths,
- * -1 otherwise.
+ * Return: %zero if the proposed links don't create too many paths,
+ * %-1 otherwise.
*/
static int reverse_path_check(void)
{
@@ -1734,7 +1734,7 @@ static struct timespec64 *ep_timeout_to_timespec(struct timespec64 *to, long ms)
}
/**
- * ep_poll - Retrieves ready events, and delivers them to the caller supplied
+ * ep_poll - Retrieves ready events, and delivers them to the caller-supplied
* event buffer.
*
* @ep: Pointer to the eventpoll context.
@@ -1747,7 +1747,7 @@ static struct timespec64 *ep_timeout_to_timespec(struct timespec64 *to, long ms)
* until at least one event has been retrieved (or an error
* occurred).
*
- * Returns: Returns the number of ready events which have been fetched, or an
+ * Return: the number of ready events which have been fetched, or an
* error code, in case of error.
*/
static int ep_poll(struct eventpoll *ep, struct epoll_event __user *events,
@@ -1774,9 +1774,9 @@ static int ep_poll(struct eventpoll *ep, struct epoll_event __user *events,
/*
* This call is racy: We may or may not see events that are being added
- * to the ready list under the lock (e.g., in IRQ callbacks). For, cases
+ * to the ready list under the lock (e.g., in IRQ callbacks). For cases
* with a non-zero timeout, this thread will check the ready list under
- * lock and will added to the wait queue. For, cases with a zero
+ * lock and will add to the wait queue. For cases with a zero
* timeout, the user by definition should not care and will have to
* recheck again.
*/
@@ -1869,15 +1869,15 @@ static int ep_poll(struct eventpoll *ep, struct epoll_event __user *events,
/**
* ep_loop_check_proc - verify that adding an epoll file inside another
- * epoll structure, does not violate the constraints, in
+ * epoll structure does not violate the constraints, in
* terms of closed loops, or too deep chains (which can
* result in excessive stack usage).
*
- * @priv: Pointer to the epoll file to be currently checked.
+ * @ep: the &struct eventpoll to be currently checked.
* @depth: Current depth of the path being checked.
*
- * Returns: Returns zero if adding the epoll @file inside current epoll
- * structure @ep does not violate the constraints, or -1 otherwise.
+ * Return: %zero if adding the epoll @file inside current epoll
+ * structure @ep does not violate the constraints, or %-1 otherwise.
*/
static int ep_loop_check_proc(struct eventpoll *ep, int depth)
{
@@ -1919,14 +1919,14 @@ static int ep_loop_check_proc(struct eventpoll *ep, int depth)
/**
* ep_loop_check - Performs a check to verify that adding an epoll file (@to)
- * into another epoll file (represented by @from) does not create
+ * into another epoll file (represented by @ep) does not create
* closed loops or too deep chains.
*
- * @from: Pointer to the epoll we are inserting into.
+ * @ep: Pointer to the epoll we are inserting into.
* @to: Pointer to the epoll to be inserted.
*
- * Returns: Returns zero if adding the epoll @to inside the epoll @from
- * does not violate the constraints, or -1 otherwise.
+ * Return: %zero if adding the epoll @to inside the epoll @from
+ * does not violate the constraints, or %-1 otherwise.
*/
static int ep_loop_check(struct eventpoll *ep, struct eventpoll *to)
{
@@ -2074,8 +2074,8 @@ int do_epoll_ctl(int epfd, int op, int fd, struct epoll_event *epds,
ep = f.file->private_data;
/*
- * When we insert an epoll file descriptor, inside another epoll file
- * descriptor, there is the change of creating closed loops, which are
+ * When we insert an epoll file descriptor inside another epoll file
+ * descriptor, there is the chance of creating closed loops, which are
* better be handled here, than in more critical paths. While we are
* checking for loops we also determine the list of files reachable
* and hang them on the tfile_check_list, so we can check that we
@@ -2113,7 +2113,7 @@ int do_epoll_ctl(int epfd, int op, int fd, struct epoll_event *epds,
}
/*
- * Try to lookup the file inside our RB tree, Since we grabbed "mtx"
+ * Try to lookup the file inside our RB tree. Since we grabbed "mtx"
* above, we can be sure to be able to use the item looked up by
* ep_find() till we release the mutex.
*/
diff --git a/fs/exfat/balloc.c b/fs/exfat/balloc.c
index 761c79c3a4ba..cc5cffc4a769 100644
--- a/fs/exfat/balloc.c
+++ b/fs/exfat/balloc.c
@@ -141,11 +141,7 @@ void exfat_free_bitmap(struct exfat_sb_info *sbi)
kfree(sbi->vol_amap);
}
-/*
- * If the value of "clu" is 0, it means cluster 2 which is the first cluster of
- * the cluster heap.
- */
-int exfat_set_bitmap(struct inode *inode, unsigned int clu)
+int exfat_set_bitmap(struct inode *inode, unsigned int clu, bool sync)
{
int i, b;
unsigned int ent_idx;
@@ -158,14 +154,10 @@ int exfat_set_bitmap(struct inode *inode, unsigned int clu)
b = BITMAP_OFFSET_BIT_IN_SECTOR(sb, ent_idx);
set_bit_le(b, sbi->vol_amap[i]->b_data);
- exfat_update_bh(sbi->vol_amap[i], IS_DIRSYNC(inode));
+ exfat_update_bh(sbi->vol_amap[i], sync);
return 0;
}
-/*
- * If the value of "clu" is 0, it means cluster 2 which is the first cluster of
- * the cluster heap.
- */
void exfat_clear_bitmap(struct inode *inode, unsigned int clu, bool sync)
{
int i, b;
@@ -186,8 +178,7 @@ void exfat_clear_bitmap(struct inode *inode, unsigned int clu, bool sync)
int ret_discard;
ret_discard = sb_issue_discard(sb,
- exfat_cluster_to_sector(sbi, clu +
- EXFAT_RESERVED_CLUSTERS),
+ exfat_cluster_to_sector(sbi, clu),
(1 << sbi->sect_per_clus_bits), GFP_NOFS, 0);
if (ret_discard == -EOPNOTSUPP) {
@@ -273,3 +264,83 @@ int exfat_count_used_clusters(struct super_block *sb, unsigned int *ret_count)
*ret_count = count;
return 0;
}
+
+int exfat_trim_fs(struct inode *inode, struct fstrim_range *range)
+{
+ unsigned int trim_begin, trim_end, count, next_free_clu;
+ u64 clu_start, clu_end, trim_minlen, trimmed_total = 0;
+ struct super_block *sb = inode->i_sb;
+ struct exfat_sb_info *sbi = EXFAT_SB(sb);
+ int err = 0;
+
+ clu_start = max_t(u64, range->start >> sbi->cluster_size_bits,
+ EXFAT_FIRST_CLUSTER);
+ clu_end = clu_start + (range->len >> sbi->cluster_size_bits) - 1;
+ trim_minlen = range->minlen >> sbi->cluster_size_bits;
+
+ if (clu_start >= sbi->num_clusters || range->len < sbi->cluster_size)
+ return -EINVAL;
+
+ if (clu_end >= sbi->num_clusters)
+ clu_end = sbi->num_clusters - 1;
+
+ mutex_lock(&sbi->bitmap_lock);
+
+ trim_begin = trim_end = exfat_find_free_bitmap(sb, clu_start);
+ if (trim_begin == EXFAT_EOF_CLUSTER)
+ goto unlock;
+
+ next_free_clu = exfat_find_free_bitmap(sb, trim_end + 1);
+ if (next_free_clu == EXFAT_EOF_CLUSTER)
+ goto unlock;
+
+ do {
+ if (next_free_clu == trim_end + 1) {
+ /* extend trim range for continuous free cluster */
+ trim_end++;
+ } else {
+ /* trim current range if it's larger than trim_minlen */
+ count = trim_end - trim_begin + 1;
+ if (count >= trim_minlen) {
+ err = sb_issue_discard(sb,
+ exfat_cluster_to_sector(sbi, trim_begin),
+ count * sbi->sect_per_clus, GFP_NOFS, 0);
+ if (err)
+ goto unlock;
+
+ trimmed_total += count;
+ }
+
+ /* set next start point of the free hole */
+ trim_begin = trim_end = next_free_clu;
+ }
+
+ if (next_free_clu >= clu_end)
+ break;
+
+ if (fatal_signal_pending(current)) {
+ err = -ERESTARTSYS;
+ goto unlock;
+ }
+
+ next_free_clu = exfat_find_free_bitmap(sb, next_free_clu + 1);
+ } while (next_free_clu != EXFAT_EOF_CLUSTER &&
+ next_free_clu > trim_end);
+
+ /* try to trim remainder */
+ count = trim_end - trim_begin + 1;
+ if (count >= trim_minlen) {
+ err = sb_issue_discard(sb, exfat_cluster_to_sector(sbi, trim_begin),
+ count * sbi->sect_per_clus, GFP_NOFS, 0);
+ if (err)
+ goto unlock;
+
+ trimmed_total += count;
+ }
+
+unlock:
+ mutex_unlock(&sbi->bitmap_lock);
+ range->len = trimmed_total << sbi->cluster_size_bits;
+
+ return err;
+}
diff --git a/fs/exfat/dir.c b/fs/exfat/dir.c
index 916797077aad..c4523648472a 100644
--- a/fs/exfat/dir.c
+++ b/fs/exfat/dir.c
@@ -4,6 +4,7 @@
*/
#include <linux/slab.h>
+#include <linux/compat.h>
#include <linux/bio.h>
#include <linux/buffer_head.h>
@@ -146,7 +147,7 @@ static int exfat_readdir(struct inode *inode, loff_t *cpos, struct exfat_dir_ent
0);
*uni_name.name = 0x0;
- exfat_get_uniname_from_ext_entry(sb, &dir, dentry,
+ exfat_get_uniname_from_ext_entry(sb, &clu, i,
uni_name.name);
exfat_utf16_to_nls(sb, &uni_name,
dir_entry->namebuf.lfn,
@@ -306,6 +307,10 @@ const struct file_operations exfat_dir_operations = {
.llseek = generic_file_llseek,
.read = generic_read_dir,
.iterate = exfat_iterate,
+ .unlocked_ioctl = exfat_ioctl,
+#ifdef CONFIG_COMPAT
+ .compat_ioctl = exfat_compat_ioctl,
+#endif
.fsync = exfat_file_fsync,
};
@@ -315,7 +320,7 @@ int exfat_alloc_new_dir(struct inode *inode, struct exfat_chain *clu)
exfat_chain_set(clu, EXFAT_EOF_CLUSTER, 0, ALLOC_NO_FAT_CHAIN);
- ret = exfat_alloc_cluster(inode, 1, clu);
+ ret = exfat_alloc_cluster(inode, 1, clu, IS_DIRSYNC(inode));
if (ret)
return ret;
@@ -906,14 +911,19 @@ enum {
};
/*
- * return values:
- * >= 0 : return dir entiry position with the name in dir
- * -ENOENT : entry with the name does not exist
- * -EIO : I/O error
+ * @ei: inode info of parent directory
+ * @p_dir: directory structure of parent directory
+ * @num_entries:entry size of p_uniname
+ * @hint_opt: If p_uniname is found, filled with optimized dir/entry
+ * for traversing cluster chain.
+ * @return:
+ * >= 0: file directory entry position where the name exists
+ * -ENOENT: entry with the name does not exist
+ * -EIO: I/O error
*/
int exfat_find_dir_entry(struct super_block *sb, struct exfat_inode_info *ei,
struct exfat_chain *p_dir, struct exfat_uni_name *p_uniname,
- int num_entries, unsigned int type)
+ int num_entries, unsigned int type, struct exfat_hint *hint_opt)
{
int i, rewind = 0, dentry = 0, end_eidx = 0, num_ext = 0, len;
int order, step, name_len = 0;
@@ -990,6 +1000,8 @@ rewind:
if (entry_type == TYPE_FILE || entry_type == TYPE_DIR) {
step = DIRENT_STEP_FILE;
+ hint_opt->clu = clu.dir;
+ hint_opt->eidx = i;
if (type == TYPE_ALL || type == entry_type) {
num_ext = ep->dentry.file.num_ext;
step = DIRENT_STEP_STRM;
diff --git a/fs/exfat/exfat_fs.h b/fs/exfat/exfat_fs.h
index fa21421a14d9..1d6da61157c9 100644
--- a/fs/exfat/exfat_fs.h
+++ b/fs/exfat/exfat_fs.h
@@ -238,6 +238,7 @@ struct exfat_sb_info {
unsigned int used_clusters; /* number of used clusters */
struct mutex s_lock; /* superblock lock */
+ struct mutex bitmap_lock; /* bitmap lock */
struct exfat_mount_options options;
struct nls_table *nls_io; /* Charset used for input and display */
struct ratelimit_state ratelimit;
@@ -388,7 +389,7 @@ int exfat_clear_volume_dirty(struct super_block *sb);
#define exfat_get_next_cluster(sb, pclu) exfat_ent_get(sb, *(pclu), pclu)
int exfat_alloc_cluster(struct inode *inode, unsigned int num_alloc,
- struct exfat_chain *p_chain);
+ struct exfat_chain *p_chain, bool sync_bmap);
int exfat_free_cluster(struct inode *inode, struct exfat_chain *p_chain);
int exfat_ent_get(struct super_block *sb, unsigned int loc,
unsigned int *content);
@@ -407,10 +408,11 @@ int exfat_count_num_clusters(struct super_block *sb,
/* balloc.c */
int exfat_load_bitmap(struct super_block *sb);
void exfat_free_bitmap(struct exfat_sb_info *sbi);
-int exfat_set_bitmap(struct inode *inode, unsigned int clu);
+int exfat_set_bitmap(struct inode *inode, unsigned int clu, bool sync);
void exfat_clear_bitmap(struct inode *inode, unsigned int clu, bool sync);
unsigned int exfat_find_free_bitmap(struct super_block *sb, unsigned int clu);
int exfat_count_used_clusters(struct super_block *sb, unsigned int *ret_count);
+int exfat_trim_fs(struct inode *inode, struct fstrim_range *range);
/* file.c */
extern const struct file_operations exfat_file_operations;
@@ -422,6 +424,9 @@ int exfat_getattr(struct user_namespace *mnt_userns, const struct path *path,
struct kstat *stat, unsigned int request_mask,
unsigned int query_flags);
int exfat_file_fsync(struct file *file, loff_t start, loff_t end, int datasync);
+long exfat_ioctl(struct file *filp, unsigned int cmd, unsigned long arg);
+long exfat_compat_ioctl(struct file *filp, unsigned int cmd,
+ unsigned long arg);
/* namei.c */
extern const struct dentry_operations exfat_dentry_ops;
@@ -452,7 +457,7 @@ void exfat_update_dir_chksum_with_entry_set(struct exfat_entry_set_cache *es);
int exfat_calc_num_entries(struct exfat_uni_name *p_uniname);
int exfat_find_dir_entry(struct super_block *sb, struct exfat_inode_info *ei,
struct exfat_chain *p_dir, struct exfat_uni_name *p_uniname,
- int num_entries, unsigned int type);
+ int num_entries, unsigned int type, struct exfat_hint *hint_opt);
int exfat_alloc_new_dir(struct inode *inode, struct exfat_chain *clu);
int exfat_find_location(struct super_block *sb, struct exfat_chain *p_dir,
int entry, sector_t *sector, int *offset);
diff --git a/fs/exfat/fatent.c b/fs/exfat/fatent.c
index 7b2e8af17193..e949e563443c 100644
--- a/fs/exfat/fatent.c
+++ b/fs/exfat/fatent.c
@@ -151,13 +151,14 @@ int exfat_chain_cont_cluster(struct super_block *sb, unsigned int chain,
return 0;
}
-int exfat_free_cluster(struct inode *inode, struct exfat_chain *p_chain)
+/* This function must be called with bitmap_lock held */
+static int __exfat_free_cluster(struct inode *inode, struct exfat_chain *p_chain)
{
- unsigned int num_clusters = 0;
- unsigned int clu;
struct super_block *sb = inode->i_sb;
struct exfat_sb_info *sbi = EXFAT_SB(sb);
int cur_cmap_i, next_cmap_i;
+ unsigned int num_clusters = 0;
+ unsigned int clu;
/* invalid cluster number */
if (p_chain->dir == EXFAT_FREE_CLUSTER ||
@@ -230,6 +231,17 @@ dec_used_clus:
return 0;
}
+int exfat_free_cluster(struct inode *inode, struct exfat_chain *p_chain)
+{
+ int ret = 0;
+
+ mutex_lock(&EXFAT_SB(inode->i_sb)->bitmap_lock);
+ ret = __exfat_free_cluster(inode, p_chain);
+ mutex_unlock(&EXFAT_SB(inode->i_sb)->bitmap_lock);
+
+ return ret;
+}
+
int exfat_find_last_cluster(struct super_block *sb, struct exfat_chain *p_chain,
unsigned int *ret_clu)
{
@@ -308,7 +320,7 @@ release_bhs:
}
int exfat_alloc_cluster(struct inode *inode, unsigned int num_alloc,
- struct exfat_chain *p_chain)
+ struct exfat_chain *p_chain, bool sync_bmap)
{
int ret = -ENOSPC;
unsigned int num_clusters = 0, total_cnt;
@@ -328,6 +340,8 @@ int exfat_alloc_cluster(struct inode *inode, unsigned int num_alloc,
if (num_alloc > total_cnt - sbi->used_clusters)
return -ENOSPC;
+ mutex_lock(&sbi->bitmap_lock);
+
hint_clu = p_chain->dir;
/* find new cluster */
if (hint_clu == EXFAT_EOF_CLUSTER) {
@@ -338,8 +352,10 @@ int exfat_alloc_cluster(struct inode *inode, unsigned int num_alloc,
}
hint_clu = exfat_find_free_bitmap(sb, sbi->clu_srch_ptr);
- if (hint_clu == EXFAT_EOF_CLUSTER)
- return -ENOSPC;
+ if (hint_clu == EXFAT_EOF_CLUSTER) {
+ ret = -ENOSPC;
+ goto unlock;
+ }
}
/* check cluster validation */
@@ -349,8 +365,10 @@ int exfat_alloc_cluster(struct inode *inode, unsigned int num_alloc,
hint_clu = EXFAT_FIRST_CLUSTER;
if (p_chain->flags == ALLOC_NO_FAT_CHAIN) {
if (exfat_chain_cont_cluster(sb, p_chain->dir,
- num_clusters))
- return -EIO;
+ num_clusters)) {
+ ret = -EIO;
+ goto unlock;
+ }
p_chain->flags = ALLOC_FAT_CHAIN;
}
}
@@ -370,7 +388,7 @@ int exfat_alloc_cluster(struct inode *inode, unsigned int num_alloc,
}
/* update allocation bitmap */
- if (exfat_set_bitmap(inode, new_clu)) {
+ if (exfat_set_bitmap(inode, new_clu, sync_bmap)) {
ret = -EIO;
goto free_cluster;
}
@@ -400,6 +418,7 @@ int exfat_alloc_cluster(struct inode *inode, unsigned int num_alloc,
sbi->used_clusters += num_clusters;
p_chain->size += num_clusters;
+ mutex_unlock(&sbi->bitmap_lock);
return 0;
}
@@ -419,7 +438,9 @@ int exfat_alloc_cluster(struct inode *inode, unsigned int num_alloc,
}
free_cluster:
if (num_clusters)
- exfat_free_cluster(inode, p_chain);
+ __exfat_free_cluster(inode, p_chain);
+unlock:
+ mutex_unlock(&sbi->bitmap_lock);
return ret;
}
diff --git a/fs/exfat/file.c b/fs/exfat/file.c
index f783cf38dd8e..6af0191b648f 100644
--- a/fs/exfat/file.c
+++ b/fs/exfat/file.c
@@ -4,6 +4,7 @@
*/
#include <linux/slab.h>
+#include <linux/compat.h>
#include <linux/cred.h>
#include <linux/buffer_head.h>
#include <linux/blkdev.h>
@@ -350,6 +351,54 @@ out:
return error;
}
+static int exfat_ioctl_fitrim(struct inode *inode, unsigned long arg)
+{
+ struct request_queue *q = bdev_get_queue(inode->i_sb->s_bdev);
+ struct fstrim_range range;
+ int ret = 0;
+
+ if (!capable(CAP_SYS_ADMIN))
+ return -EPERM;
+
+ if (!blk_queue_discard(q))
+ return -EOPNOTSUPP;
+
+ if (copy_from_user(&range, (struct fstrim_range __user *)arg, sizeof(range)))
+ return -EFAULT;
+
+ range.minlen = max_t(unsigned int, range.minlen,
+ q->limits.discard_granularity);
+
+ ret = exfat_trim_fs(inode, &range);
+ if (ret < 0)
+ return ret;
+
+ if (copy_to_user((struct fstrim_range __user *)arg, &range, sizeof(range)))
+ return -EFAULT;
+
+ return 0;
+}
+
+long exfat_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
+{
+ struct inode *inode = file_inode(filp);
+
+ switch (cmd) {
+ case FITRIM:
+ return exfat_ioctl_fitrim(inode, arg);
+ default:
+ return -ENOTTY;
+ }
+}
+
+#ifdef CONFIG_COMPAT
+long exfat_compat_ioctl(struct file *filp, unsigned int cmd,
+ unsigned long arg)
+{
+ return exfat_ioctl(filp, cmd, (unsigned long)compat_ptr(arg));
+}
+#endif
+
int exfat_file_fsync(struct file *filp, loff_t start, loff_t end, int datasync)
{
struct inode *inode = filp->f_mapping->host;
@@ -370,6 +419,10 @@ const struct file_operations exfat_file_operations = {
.llseek = generic_file_llseek,
.read_iter = generic_file_read_iter,
.write_iter = generic_file_write_iter,
+ .unlocked_ioctl = exfat_ioctl,
+#ifdef CONFIG_COMPAT
+ .compat_ioctl = exfat_compat_ioctl,
+#endif
.mmap = generic_file_mmap,
.fsync = exfat_file_fsync,
.splice_read = generic_file_splice_read,
diff --git a/fs/exfat/inode.c b/fs/exfat/inode.c
index 730373e0965a..1803ef3220fd 100644
--- a/fs/exfat/inode.c
+++ b/fs/exfat/inode.c
@@ -179,7 +179,8 @@ static int exfat_map_cluster(struct inode *inode, unsigned int clu_offset,
return -EIO;
}
- ret = exfat_alloc_cluster(inode, num_to_be_allocated, &new_clu);
+ ret = exfat_alloc_cluster(inode, num_to_be_allocated, &new_clu,
+ inode_needs_sync(inode));
if (ret)
return ret;
diff --git a/fs/exfat/namei.c b/fs/exfat/namei.c
index d9e8ec689c55..24b41103d1cc 100644
--- a/fs/exfat/namei.c
+++ b/fs/exfat/namei.c
@@ -340,7 +340,7 @@ static int exfat_find_empty_entry(struct inode *inode,
exfat_chain_set(&clu, last_clu + 1, 0, p_dir->flags);
/* allocate a cluster */
- ret = exfat_alloc_cluster(inode, 1, &clu);
+ ret = exfat_alloc_cluster(inode, 1, &clu, IS_DIRSYNC(inode));
if (ret)
return ret;
@@ -596,6 +596,8 @@ static int exfat_find(struct inode *dir, struct qstr *qname,
struct exfat_inode_info *ei = EXFAT_I(dir);
struct exfat_dentry *ep, *ep2;
struct exfat_entry_set_cache *es;
+ /* for optimized dir & entry to prevent long traverse of cluster chain */
+ struct exfat_hint hint_opt;
if (qname->len == 0)
return -ENOENT;
@@ -619,7 +621,7 @@ static int exfat_find(struct inode *dir, struct qstr *qname,
/* search the file name for directories */
dentry = exfat_find_dir_entry(sb, ei, &cdir, &uni_name,
- num_entries, TYPE_ALL);
+ num_entries, TYPE_ALL, &hint_opt);
if (dentry < 0)
return dentry; /* -error value */
@@ -628,6 +630,11 @@ static int exfat_find(struct inode *dir, struct qstr *qname,
info->entry = dentry;
info->num_subdirs = 0;
+ /* adjust cdir to the optimized value */
+ cdir.dir = hint_opt.clu;
+ if (cdir.flags & ALLOC_NO_FAT_CHAIN)
+ cdir.size -= dentry / sbi->dentries_per_clu;
+ dentry = hint_opt.eidx;
es = exfat_get_dentry_set(sb, &cdir, dentry, ES_2_ENTRIES);
if (!es)
return -EIO;
diff --git a/fs/exfat/super.c b/fs/exfat/super.c
index c6d8d2e53486..d38d17a77e76 100644
--- a/fs/exfat/super.c
+++ b/fs/exfat/super.c
@@ -752,6 +752,7 @@ static int exfat_init_fs_context(struct fs_context *fc)
return -ENOMEM;
mutex_init(&sbi->s_lock);
+ mutex_init(&sbi->bitmap_lock);
ratelimit_state_init(&sbi->ratelimit, DEFAULT_RATELIMIT_INTERVAL,
DEFAULT_RATELIMIT_BURST);
diff --git a/fs/ext2/dir.c b/fs/ext2/dir.c
index 14aa45316ad2..14292dba3a12 100644
--- a/fs/ext2/dir.c
+++ b/fs/ext2/dir.c
@@ -190,13 +190,20 @@ fail:
return false;
}
+/*
+ * Calls to ext2_get_page()/ext2_put_page() must be nested according to the
+ * rules documented in kmap_local_page()/kunmap_local().
+ *
+ * NOTE: ext2_find_entry() and ext2_dotdot() act as a call to ext2_get_page()
+ * and should be treated as a call to ext2_get_page() for nesting purposes.
+ */
static struct page * ext2_get_page(struct inode *dir, unsigned long n,
- int quiet)
+ int quiet, void **page_addr)
{
struct address_space *mapping = dir->i_mapping;
struct page *page = read_mapping_page(mapping, n, NULL);
if (!IS_ERR(page)) {
- kmap(page);
+ *page_addr = kmap_local_page(page);
if (unlikely(!PageChecked(page))) {
if (PageError(page) || !ext2_check_page(page, quiet))
goto fail;
@@ -205,7 +212,7 @@ static struct page * ext2_get_page(struct inode *dir, unsigned long n,
return page;
fail:
- ext2_put_page(page);
+ ext2_put_page(page, *page_addr);
return ERR_PTR(-EIO);
}
@@ -276,7 +283,7 @@ ext2_readdir(struct file *file, struct dir_context *ctx)
for ( ; n < npages; n++, offset = 0) {
char *kaddr, *limit;
ext2_dirent *de;
- struct page *page = ext2_get_page(inode, n, 0);
+ struct page *page = ext2_get_page(inode, n, 0, (void **)&kaddr);
if (IS_ERR(page)) {
ext2_error(sb, __func__,
@@ -285,7 +292,6 @@ ext2_readdir(struct file *file, struct dir_context *ctx)
ctx->pos += PAGE_SIZE - offset;
return PTR_ERR(page);
}
- kaddr = page_address(page);
if (unlikely(need_revalidate)) {
if (offset) {
offset = ext2_validate_entry(kaddr, offset, chunk_mask);
@@ -300,7 +306,7 @@ ext2_readdir(struct file *file, struct dir_context *ctx)
if (de->rec_len == 0) {
ext2_error(sb, __func__,
"zero-length directory entry");
- ext2_put_page(page);
+ ext2_put_page(page, kaddr);
return -EIO;
}
if (de->inode) {
@@ -312,13 +318,13 @@ ext2_readdir(struct file *file, struct dir_context *ctx)
if (!dir_emit(ctx, de->name, de->name_len,
le32_to_cpu(de->inode),
d_type)) {
- ext2_put_page(page);
+ ext2_put_page(page, kaddr);
return 0;
}
}
ctx->pos += ext2_rec_len_from_disk(de->rec_len);
}
- ext2_put_page(page);
+ ext2_put_page(page, kaddr);
}
return 0;
}
@@ -332,9 +338,16 @@ ext2_readdir(struct file *file, struct dir_context *ctx)
* Entry is guaranteed to be valid.
*
* On Success ext2_put_page() should be called on *res_page.
+ *
+ * NOTE: Calls to ext2_get_page()/ext2_put_page() must be nested according to
+ * the rules documented in kmap_local_page()/kunmap_local().
+ *
+ * ext2_find_entry() and ext2_dotdot() act as a call to ext2_get_page() and
+ * should be treated as a call to ext2_get_page() for nesting purposes.
*/
struct ext2_dir_entry_2 *ext2_find_entry (struct inode *dir,
- const struct qstr *child, struct page **res_page)
+ const struct qstr *child, struct page **res_page,
+ void **res_page_addr)
{
const char *name = child->name;
int namelen = child->len;
@@ -344,12 +357,14 @@ struct ext2_dir_entry_2 *ext2_find_entry (struct inode *dir,
struct page *page = NULL;
struct ext2_inode_info *ei = EXT2_I(dir);
ext2_dirent * de;
+ void *page_addr;
if (npages == 0)
goto out;
/* OFFSET_CACHE */
*res_page = NULL;
+ *res_page_addr = NULL;
start = ei->i_dir_start_lookup;
if (start >= npages)
@@ -357,25 +372,25 @@ struct ext2_dir_entry_2 *ext2_find_entry (struct inode *dir,
n = start;
do {
char *kaddr;
- page = ext2_get_page(dir, n, 0);
+ page = ext2_get_page(dir, n, 0, &page_addr);
if (IS_ERR(page))
return ERR_CAST(page);
- kaddr = page_address(page);
+ kaddr = page_addr;
de = (ext2_dirent *) kaddr;
kaddr += ext2_last_byte(dir, n) - reclen;
while ((char *) de <= kaddr) {
if (de->rec_len == 0) {
ext2_error(dir->i_sb, __func__,
"zero-length directory entry");
- ext2_put_page(page);
+ ext2_put_page(page, page_addr);
goto out;
}
if (ext2_match(namelen, name, de))
goto found;
de = ext2_next_entry(de);
}
- ext2_put_page(page);
+ ext2_put_page(page, page_addr);
if (++n >= npages)
n = 0;
@@ -393,6 +408,7 @@ out:
found:
*res_page = page;
+ *res_page_addr = page_addr;
ei->i_dir_start_lookup = n;
return de;
}
@@ -402,15 +418,24 @@ found:
* (as a parameter - p).
*
* On Success ext2_put_page() should be called on *p.
+ *
+ * NOTE: Calls to ext2_get_page()/ext2_put_page() must be nested according to
+ * the rules documented in kmap_local_page()/kunmap_local().
+ *
+ * ext2_find_entry() and ext2_dotdot() act as a call to ext2_get_page() and
+ * should be treated as a call to ext2_get_page() for nesting purposes.
*/
-struct ext2_dir_entry_2 * ext2_dotdot (struct inode *dir, struct page **p)
+struct ext2_dir_entry_2 *ext2_dotdot(struct inode *dir, struct page **p,
+ void **pa)
{
- struct page *page = ext2_get_page(dir, 0, 0);
+ void *page_addr;
+ struct page *page = ext2_get_page(dir, 0, 0, &page_addr);
ext2_dirent *de = NULL;
if (!IS_ERR(page)) {
- de = ext2_next_entry((ext2_dirent *) page_address(page));
+ de = ext2_next_entry((ext2_dirent *) page_addr);
*p = page;
+ *pa = page_addr;
}
return de;
}
@@ -419,13 +444,14 @@ int ext2_inode_by_name(struct inode *dir, const struct qstr *child, ino_t *ino)
{
struct ext2_dir_entry_2 *de;
struct page *page;
+ void *page_addr;
- de = ext2_find_entry(dir, child, &page);
+ de = ext2_find_entry(dir, child, &page, &page_addr);
if (IS_ERR(de))
return PTR_ERR(de);
*ino = le32_to_cpu(de->inode);
- ext2_put_page(page);
+ ext2_put_page(page, page_addr);
return 0;
}
@@ -434,12 +460,12 @@ static int ext2_prepare_chunk(struct page *page, loff_t pos, unsigned len)
return __block_write_begin(page, pos, len, ext2_get_block);
}
-/* Releases the page */
void ext2_set_link(struct inode *dir, struct ext2_dir_entry_2 *de,
- struct page *page, struct inode *inode, int update_times)
+ struct page *page, void *page_addr, struct inode *inode,
+ int update_times)
{
loff_t pos = page_offset(page) +
- (char *) de - (char *) page_address(page);
+ (char *) de - (char *) page_addr;
unsigned len = ext2_rec_len_from_disk(de->rec_len);
int err;
@@ -449,7 +475,6 @@ void ext2_set_link(struct inode *dir, struct ext2_dir_entry_2 *de,
de->inode = cpu_to_le32(inode->i_ino);
ext2_set_de_type(de, inode);
err = ext2_commit_chunk(page, pos, len);
- ext2_put_page(page);
if (update_times)
dir->i_mtime = dir->i_ctime = current_time(dir);
EXT2_I(dir)->i_flags &= ~EXT2_BTREE_FL;
@@ -468,10 +493,10 @@ int ext2_add_link (struct dentry *dentry, struct inode *inode)
unsigned reclen = EXT2_DIR_REC_LEN(namelen);
unsigned short rec_len, name_len;
struct page *page = NULL;
+ void *page_addr = NULL;
ext2_dirent * de;
unsigned long npages = dir_pages(dir);
unsigned long n;
- char *kaddr;
loff_t pos;
int err;
@@ -481,14 +506,15 @@ int ext2_add_link (struct dentry *dentry, struct inode *inode)
* to protect that region.
*/
for (n = 0; n <= npages; n++) {
+ char *kaddr;
char *dir_end;
- page = ext2_get_page(dir, n, 0);
+ page = ext2_get_page(dir, n, 0, &page_addr);
err = PTR_ERR(page);
if (IS_ERR(page))
goto out;
lock_page(page);
- kaddr = page_address(page);
+ kaddr = page_addr;
dir_end = kaddr + ext2_last_byte(dir, n);
de = (ext2_dirent *)kaddr;
kaddr += PAGE_SIZE - reclen;
@@ -519,14 +545,14 @@ int ext2_add_link (struct dentry *dentry, struct inode *inode)
de = (ext2_dirent *) ((char *) de + rec_len);
}
unlock_page(page);
- ext2_put_page(page);
+ ext2_put_page(page, page_addr);
}
BUG();
return -EINVAL;
got_it:
pos = page_offset(page) +
- (char*)de - (char*)page_address(page);
+ (char *)de - (char *)page_addr;
err = ext2_prepare_chunk(page, pos, rec_len);
if (err)
goto out_unlock;
@@ -546,7 +572,7 @@ got_it:
mark_inode_dirty(dir);
/* OFFSET_CACHE */
out_put:
- ext2_put_page(page);
+ ext2_put_page(page, page_addr);
out:
return err;
out_unlock:
@@ -556,7 +582,7 @@ out_unlock:
/*
* ext2_delete_entry deletes a directory entry by merging it with the
- * previous entry. Page is up-to-date. Releases the page.
+ * previous entry. Page is up-to-date.
*/
int ext2_delete_entry (struct ext2_dir_entry_2 * dir, struct page * page )
{
@@ -594,7 +620,6 @@ int ext2_delete_entry (struct ext2_dir_entry_2 * dir, struct page * page )
EXT2_I(inode)->i_flags &= ~EXT2_BTREE_FL;
mark_inode_dirty(inode);
out:
- ext2_put_page(page);
return err;
}
@@ -644,6 +669,7 @@ fail:
*/
int ext2_empty_dir (struct inode * inode)
{
+ void *page_addr = NULL;
struct page *page = NULL;
unsigned long i, npages = dir_pages(inode);
int dir_has_error = 0;
@@ -651,14 +677,14 @@ int ext2_empty_dir (struct inode * inode)
for (i = 0; i < npages; i++) {
char *kaddr;
ext2_dirent * de;
- page = ext2_get_page(inode, i, dir_has_error);
+ page = ext2_get_page(inode, i, dir_has_error, &page_addr);
if (IS_ERR(page)) {
dir_has_error = 1;
continue;
}
- kaddr = page_address(page);
+ kaddr = page_addr;
de = (ext2_dirent *)kaddr;
kaddr += ext2_last_byte(inode, i) - EXT2_DIR_REC_LEN(1);
@@ -684,12 +710,12 @@ int ext2_empty_dir (struct inode * inode)
}
de = ext2_next_entry(de);
}
- ext2_put_page(page);
+ ext2_put_page(page, page_addr);
}
return 1;
not_empty:
- ext2_put_page(page);
+ ext2_put_page(page, page_addr);
return 0;
}
diff --git a/fs/ext2/ext2.h b/fs/ext2/ext2.h
index 3309fb2d327a..b0a694820cb7 100644
--- a/fs/ext2/ext2.h
+++ b/fs/ext2/ext2.h
@@ -283,8 +283,6 @@ static inline __u32 ext2_mask_flags(umode_t mode, __u32 flags)
/*
* ioctl commands
*/
-#define EXT2_IOC_GETFLAGS FS_IOC_GETFLAGS
-#define EXT2_IOC_SETFLAGS FS_IOC_SETFLAGS
#define EXT2_IOC_GETVERSION FS_IOC_GETVERSION
#define EXT2_IOC_SETVERSION FS_IOC_SETVERSION
#define EXT2_IOC_GETRSVSZ _IOR('f', 5, long)
@@ -293,8 +291,6 @@ static inline __u32 ext2_mask_flags(umode_t mode, __u32 flags)
/*
* ioctl commands in 32 bit emulation
*/
-#define EXT2_IOC32_GETFLAGS FS_IOC32_GETFLAGS
-#define EXT2_IOC32_SETFLAGS FS_IOC32_SETFLAGS
#define EXT2_IOC32_GETVERSION FS_IOC32_GETVERSION
#define EXT2_IOC32_SETVERSION FS_IOC32_SETVERSION
@@ -742,14 +738,16 @@ extern int ext2_add_link (struct dentry *, struct inode *);
extern int ext2_inode_by_name(struct inode *dir,
const struct qstr *child, ino_t *ino);
extern int ext2_make_empty(struct inode *, struct inode *);
-extern struct ext2_dir_entry_2 * ext2_find_entry (struct inode *,const struct qstr *, struct page **);
+extern struct ext2_dir_entry_2 *ext2_find_entry(struct inode *, const struct qstr *,
+ struct page **, void **res_page_addr);
extern int ext2_delete_entry (struct ext2_dir_entry_2 *, struct page *);
extern int ext2_empty_dir (struct inode *);
-extern struct ext2_dir_entry_2 * ext2_dotdot (struct inode *, struct page **);
-extern void ext2_set_link(struct inode *, struct ext2_dir_entry_2 *, struct page *, struct inode *, int);
-static inline void ext2_put_page(struct page *page)
+extern struct ext2_dir_entry_2 *ext2_dotdot(struct inode *dir, struct page **p, void **pa);
+extern void ext2_set_link(struct inode *, struct ext2_dir_entry_2 *, struct page *, void *,
+ struct inode *, int);
+static inline void ext2_put_page(struct page *page, void *page_addr)
{
- kunmap(page);
+ kunmap_local(page_addr);
put_page(page);
}
@@ -772,6 +770,9 @@ extern int ext2_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
u64 start, u64 len);
/* ioctl.c */
+extern int ext2_fileattr_get(struct dentry *dentry, struct fileattr *fa);
+extern int ext2_fileattr_set(struct user_namespace *mnt_userns,
+ struct dentry *dentry, struct fileattr *fa);
extern long ext2_ioctl(struct file *, unsigned int, unsigned long);
extern long ext2_compat_ioctl(struct file *, unsigned int, unsigned long);
diff --git a/fs/ext2/file.c b/fs/ext2/file.c
index 96044f5dbc0e..f98466acc672 100644
--- a/fs/ext2/file.c
+++ b/fs/ext2/file.c
@@ -204,4 +204,6 @@ const struct inode_operations ext2_file_inode_operations = {
.get_acl = ext2_get_acl,
.set_acl = ext2_set_acl,
.fiemap = ext2_fiemap,
+ .fileattr_get = ext2_fileattr_get,
+ .fileattr_set = ext2_fileattr_set,
};
diff --git a/fs/ext2/ioctl.c b/fs/ext2/ioctl.c
index b399cbb7022d..e8340bf09b10 100644
--- a/fs/ext2/ioctl.c
+++ b/fs/ext2/ioctl.c
@@ -16,69 +16,51 @@
#include <linux/mount.h>
#include <asm/current.h>
#include <linux/uaccess.h>
+#include <linux/fileattr.h>
-
-long ext2_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
+int ext2_fileattr_get(struct dentry *dentry, struct fileattr *fa)
{
- struct inode *inode = file_inode(filp);
- struct ext2_inode_info *ei = EXT2_I(inode);
- unsigned int flags;
- unsigned short rsv_window_size;
- int ret;
+ struct ext2_inode_info *ei = EXT2_I(d_inode(dentry));
- ext2_debug ("cmd = %u, arg = %lu\n", cmd, arg);
+ fileattr_fill_flags(fa, ei->i_flags & EXT2_FL_USER_VISIBLE);
- switch (cmd) {
- case EXT2_IOC_GETFLAGS:
- flags = ei->i_flags & EXT2_FL_USER_VISIBLE;
- return put_user(flags, (int __user *) arg);
- case EXT2_IOC_SETFLAGS: {
- unsigned int oldflags;
+ return 0;
+}
- ret = mnt_want_write_file(filp);
- if (ret)
- return ret;
+int ext2_fileattr_set(struct user_namespace *mnt_userns,
+ struct dentry *dentry, struct fileattr *fa)
+{
+ struct inode *inode = d_inode(dentry);
+ struct ext2_inode_info *ei = EXT2_I(inode);
- if (!inode_owner_or_capable(&init_user_ns, inode)) {
- ret = -EACCES;
- goto setflags_out;
- }
+ if (fileattr_has_fsx(fa))
+ return -EOPNOTSUPP;
- if (get_user(flags, (int __user *) arg)) {
- ret = -EFAULT;
- goto setflags_out;
- }
+ /* Is it quota file? Do not allow user to mess with it */
+ if (IS_NOQUOTA(inode))
+ return -EPERM;
- flags = ext2_mask_flags(inode->i_mode, flags);
+ ei->i_flags = (ei->i_flags & ~EXT2_FL_USER_MODIFIABLE) |
+ (fa->flags & EXT2_FL_USER_MODIFIABLE);
- inode_lock(inode);
- /* Is it quota file? Do not allow user to mess with it */
- if (IS_NOQUOTA(inode)) {
- inode_unlock(inode);
- ret = -EPERM;
- goto setflags_out;
- }
- oldflags = ei->i_flags;
+ ext2_set_inode_flags(inode);
+ inode->i_ctime = current_time(inode);
+ mark_inode_dirty(inode);
- ret = vfs_ioc_setflags_prepare(inode, oldflags, flags);
- if (ret) {
- inode_unlock(inode);
- goto setflags_out;
- }
+ return 0;
+}
- flags = flags & EXT2_FL_USER_MODIFIABLE;
- flags |= oldflags & ~EXT2_FL_USER_MODIFIABLE;
- ei->i_flags = flags;
- ext2_set_inode_flags(inode);
- inode->i_ctime = current_time(inode);
- inode_unlock(inode);
+long ext2_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
+{
+ struct inode *inode = file_inode(filp);
+ struct ext2_inode_info *ei = EXT2_I(inode);
+ unsigned short rsv_window_size;
+ int ret;
- mark_inode_dirty(inode);
-setflags_out:
- mnt_drop_write_file(filp);
- return ret;
- }
+ ext2_debug ("cmd = %u, arg = %lu\n", cmd, arg);
+
+ switch (cmd) {
case EXT2_IOC_GETVERSION:
return put_user(inode->i_generation, (int __user *) arg);
case EXT2_IOC_SETVERSION: {
@@ -163,12 +145,6 @@ long ext2_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
{
/* These are just misnamed, they actually get/put from/to user an int */
switch (cmd) {
- case EXT2_IOC32_GETFLAGS:
- cmd = EXT2_IOC_GETFLAGS;
- break;
- case EXT2_IOC32_SETFLAGS:
- cmd = EXT2_IOC_SETFLAGS;
- break;
case EXT2_IOC32_GETVERSION:
cmd = EXT2_IOC_GETVERSION;
break;
diff --git a/fs/ext2/namei.c b/fs/ext2/namei.c
index 3367384d344d..1f69b81655b6 100644
--- a/fs/ext2/namei.c
+++ b/fs/ext2/namei.c
@@ -81,11 +81,10 @@ static struct dentry *ext2_lookup(struct inode * dir, struct dentry *dentry, uns
struct dentry *ext2_get_parent(struct dentry *child)
{
- struct qstr dotdot = QSTR_INIT("..", 2);
ino_t ino;
int res;
- res = ext2_inode_by_name(d_inode(child), &dotdot, &ino);
+ res = ext2_inode_by_name(d_inode(child), &dotdot_name, &ino);
if (res)
return ERR_PTR(res);
@@ -281,19 +280,21 @@ static int ext2_unlink(struct inode * dir, struct dentry *dentry)
struct inode * inode = d_inode(dentry);
struct ext2_dir_entry_2 * de;
struct page * page;
+ void *page_addr;
int err;
err = dquot_initialize(dir);
if (err)
goto out;
- de = ext2_find_entry(dir, &dentry->d_name, &page);
+ de = ext2_find_entry(dir, &dentry->d_name, &page, &page_addr);
if (IS_ERR(de)) {
err = PTR_ERR(de);
goto out;
}
err = ext2_delete_entry (de, page);
+ ext2_put_page(page, page_addr);
if (err)
goto out;
@@ -328,8 +329,10 @@ static int ext2_rename (struct user_namespace * mnt_userns,
struct inode * old_inode = d_inode(old_dentry);
struct inode * new_inode = d_inode(new_dentry);
struct page * dir_page = NULL;
+ void *dir_page_addr;
struct ext2_dir_entry_2 * dir_de = NULL;
struct page * old_page;
+ void *old_page_addr;
struct ext2_dir_entry_2 * old_de;
int err;
@@ -344,7 +347,8 @@ static int ext2_rename (struct user_namespace * mnt_userns,
if (err)
goto out;
- old_de = ext2_find_entry(old_dir, &old_dentry->d_name, &old_page);
+ old_de = ext2_find_entry(old_dir, &old_dentry->d_name, &old_page,
+ &old_page_addr);
if (IS_ERR(old_de)) {
err = PTR_ERR(old_de);
goto out;
@@ -352,12 +356,13 @@ static int ext2_rename (struct user_namespace * mnt_userns,
if (S_ISDIR(old_inode->i_mode)) {
err = -EIO;
- dir_de = ext2_dotdot(old_inode, &dir_page);
+ dir_de = ext2_dotdot(old_inode, &dir_page, &dir_page_addr);
if (!dir_de)
goto out_old;
}
if (new_inode) {
+ void *page_addr;
struct page *new_page;
struct ext2_dir_entry_2 *new_de;
@@ -365,12 +370,14 @@ static int ext2_rename (struct user_namespace * mnt_userns,
if (dir_de && !ext2_empty_dir (new_inode))
goto out_dir;
- new_de = ext2_find_entry(new_dir, &new_dentry->d_name, &new_page);
+ new_de = ext2_find_entry(new_dir, &new_dentry->d_name,
+ &new_page, &page_addr);
if (IS_ERR(new_de)) {
err = PTR_ERR(new_de);
goto out_dir;
}
- ext2_set_link(new_dir, new_de, new_page, old_inode, 1);
+ ext2_set_link(new_dir, new_de, new_page, page_addr, old_inode, 1);
+ ext2_put_page(new_page, page_addr);
new_inode->i_ctime = current_time(new_inode);
if (dir_de)
drop_nlink(new_inode);
@@ -390,23 +397,25 @@ static int ext2_rename (struct user_namespace * mnt_userns,
old_inode->i_ctime = current_time(old_inode);
mark_inode_dirty(old_inode);
- ext2_delete_entry (old_de, old_page);
+ ext2_delete_entry(old_de, old_page);
if (dir_de) {
if (old_dir != new_dir)
- ext2_set_link(old_inode, dir_de, dir_page, new_dir, 0);
- else
- ext2_put_page(dir_page);
+ ext2_set_link(old_inode, dir_de, dir_page,
+ dir_page_addr, new_dir, 0);
+
+ ext2_put_page(dir_page, dir_page_addr);
inode_dec_link_count(old_dir);
}
- return 0;
+ ext2_put_page(old_page, old_page_addr);
+ return 0;
out_dir:
if (dir_de)
- ext2_put_page(dir_page);
+ ext2_put_page(dir_page, dir_page_addr);
out_old:
- ext2_put_page(old_page);
+ ext2_put_page(old_page, old_page_addr);
out:
return err;
}
@@ -427,6 +436,8 @@ const struct inode_operations ext2_dir_inode_operations = {
.get_acl = ext2_get_acl,
.set_acl = ext2_set_acl,
.tmpfile = ext2_tmpfile,
+ .fileattr_get = ext2_fileattr_get,
+ .fileattr_set = ext2_fileattr_set,
};
const struct inode_operations ext2_special_inode_operations = {
diff --git a/fs/ext2/super.c b/fs/ext2/super.c
index 6c4753277916..21e09fbaa46f 100644
--- a/fs/ext2/super.c
+++ b/fs/ext2/super.c
@@ -1104,7 +1104,7 @@ static int ext2_fill_super(struct super_block *sb, void *data, int silent)
get_random_bytes(&sbi->s_next_generation, sizeof(u32));
spin_lock_init(&sbi->s_next_gen_lock);
- /* per fileystem reservation list head & lock */
+ /* per filesystem reservation list head & lock */
spin_lock_init(&sbi->s_rsv_window_lock);
sbi->s_rsv_window_root = RB_ROOT;
/*
@@ -1399,7 +1399,6 @@ static int ext2_statfs (struct dentry * dentry, struct kstatfs * buf)
struct super_block *sb = dentry->d_sb;
struct ext2_sb_info *sbi = EXT2_SB(sb);
struct ext2_super_block *es = sbi->s_es;
- u64 fsid;
spin_lock(&sbi->s_lock);
@@ -1453,9 +1452,7 @@ static int ext2_statfs (struct dentry * dentry, struct kstatfs * buf)
buf->f_ffree = ext2_count_free_inodes(sb);
es->s_free_inodes_count = cpu_to_le32(buf->f_ffree);
buf->f_namelen = EXT2_NAME_LEN;
- fsid = le64_to_cpup((void *)es->s_uuid) ^
- le64_to_cpup((void *)es->s_uuid + sizeof(u64));
- buf->f_fsid = u64_to_fsid(fsid);
+ buf->f_fsid = uuid_to_fsid(es->s_uuid);
spin_unlock(&sbi->s_lock);
return 0;
}
diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c
index f45f9feebe59..9dc6e74b265c 100644
--- a/fs/ext4/balloc.c
+++ b/fs/ext4/balloc.c
@@ -239,7 +239,7 @@ unsigned ext4_free_clusters_after_init(struct super_block *sb,
ext4_group_t block_group,
struct ext4_group_desc *gdp)
{
- return num_clusters_in_group(sb, block_group) -
+ return num_clusters_in_group(sb, block_group) -
ext4_num_overhead_clusters(sb, block_group, gdp);
}
@@ -626,27 +626,41 @@ int ext4_claim_free_clusters(struct ext4_sb_info *sbi,
/**
* ext4_should_retry_alloc() - check if a block allocation should be retried
- * @sb: super block
- * @retries: number of attemps has been made
+ * @sb: superblock
+ * @retries: number of retry attempts made so far
*
- * ext4_should_retry_alloc() is called when ENOSPC is returned, and if
- * it is profitable to retry the operation, this function will wait
- * for the current or committing transaction to complete, and then
- * return TRUE. We will only retry once.
+ * ext4_should_retry_alloc() is called when ENOSPC is returned while
+ * attempting to allocate blocks. If there's an indication that a pending
+ * journal transaction might free some space and allow another attempt to
+ * succeed, this function will wait for the current or committing transaction
+ * to complete and then return TRUE.
*/
int ext4_should_retry_alloc(struct super_block *sb, int *retries)
{
- if (!ext4_has_free_clusters(EXT4_SB(sb), 1, 0) ||
- (*retries)++ > 1 ||
- !EXT4_SB(sb)->s_journal)
+ struct ext4_sb_info *sbi = EXT4_SB(sb);
+
+ if (!sbi->s_journal)
return 0;
- smp_mb();
- if (EXT4_SB(sb)->s_mb_free_pending == 0)
+ if (++(*retries) > 3) {
+ percpu_counter_inc(&sbi->s_sra_exceeded_retry_limit);
return 0;
+ }
+ /*
+ * if there's no indication that blocks are about to be freed it's
+ * possible we just missed a transaction commit that did so
+ */
+ smp_mb();
+ if (sbi->s_mb_free_pending == 0)
+ return ext4_has_free_clusters(sbi, 1, 0);
+
+ /*
+ * it's possible we've just missed a transaction commit here,
+ * so ignore the returned status
+ */
jbd_debug(1, "%s: retrying operation after ENOSPC\n", sb->s_id);
- jbd2_journal_force_commit_nested(EXT4_SB(sb)->s_journal);
+ (void) jbd2_journal_force_commit_nested(sbi->s_journal);
return 1;
}
diff --git a/fs/ext4/dir.c b/fs/ext4/dir.c
index 5ed870614c8d..ffb295aa891c 100644
--- a/fs/ext4/dir.c
+++ b/fs/ext4/dir.c
@@ -55,6 +55,18 @@ static int is_dx_dir(struct inode *inode)
return 0;
}
+static bool is_fake_dir_entry(struct ext4_dir_entry_2 *de)
+{
+ /* Check if . or .. , or skip if namelen is 0 */
+ if ((de->name_len > 0) && (de->name_len <= 2) && (de->name[0] == '.') &&
+ (de->name[1] == '.' || de->name[1] == '\0'))
+ return true;
+ /* Check if this is a csum entry */
+ if (de->file_type == EXT4_FT_DIR_CSUM)
+ return true;
+ return false;
+}
+
/*
* Return 0 if the directory entry is OK, and 1 if there is a problem
*
@@ -73,16 +85,20 @@ int __ext4_check_dir_entry(const char *function, unsigned int line,
const int rlen = ext4_rec_len_from_disk(de->rec_len,
dir->i_sb->s_blocksize);
const int next_offset = ((char *) de - buf) + rlen;
+ bool fake = is_fake_dir_entry(de);
+ bool has_csum = ext4_has_metadata_csum(dir->i_sb);
- if (unlikely(rlen < EXT4_DIR_REC_LEN(1)))
+ if (unlikely(rlen < ext4_dir_rec_len(1, fake ? NULL : dir)))
error_msg = "rec_len is smaller than minimal";
else if (unlikely(rlen % 4 != 0))
error_msg = "rec_len % 4 != 0";
- else if (unlikely(rlen < EXT4_DIR_REC_LEN(de->name_len)))
+ else if (unlikely(rlen < ext4_dir_rec_len(de->name_len,
+ fake ? NULL : dir)))
error_msg = "rec_len is too small for name_len";
else if (unlikely(next_offset > size))
error_msg = "directory entry overrun";
- else if (unlikely(next_offset > size - EXT4_DIR_REC_LEN(1) &&
+ else if (unlikely(next_offset > size - ext4_dir_rec_len(1,
+ has_csum ? NULL : dir) &&
next_offset != size))
error_msg = "directory entry too close to block end";
else if (unlikely(le32_to_cpu(de->inode) >
@@ -94,15 +110,15 @@ int __ext4_check_dir_entry(const char *function, unsigned int line,
if (filp)
ext4_error_file(filp, function, line, bh->b_blocknr,
"bad entry in directory: %s - offset=%u, "
- "inode=%u, rec_len=%d, name_len=%d, size=%d",
+ "inode=%u, rec_len=%d, size=%d fake=%d",
error_msg, offset, le32_to_cpu(de->inode),
- rlen, de->name_len, size);
+ rlen, size, fake);
else
ext4_error_inode(dir, function, line, bh->b_blocknr,
"bad entry in directory: %s - offset=%u, "
- "inode=%u, rec_len=%d, name_len=%d, size=%d",
+ "inode=%u, rec_len=%d, size=%d fake=%d",
error_msg, offset, le32_to_cpu(de->inode),
- rlen, de->name_len, size);
+ rlen, size, fake);
return 1;
}
@@ -124,9 +140,9 @@ static int ext4_readdir(struct file *file, struct dir_context *ctx)
if (is_dx_dir(inode)) {
err = ext4_dx_readdir(file, ctx);
- if (err != ERR_BAD_DX_DIR) {
+ if (err != ERR_BAD_DX_DIR)
return err;
- }
+
/* Can we just clear INDEX flag to ignore htree information? */
if (!ext4_has_metadata_csum(sb)) {
/*
@@ -224,7 +240,8 @@ static int ext4_readdir(struct file *file, struct dir_context *ctx)
* failure will be detected in the
* dirent test below. */
if (ext4_rec_len_from_disk(de->rec_len,
- sb->s_blocksize) < EXT4_DIR_REC_LEN(1))
+ sb->s_blocksize) < ext4_dir_rec_len(1,
+ inode))
break;
i += ext4_rec_len_from_disk(de->rec_len,
sb->s_blocksize);
@@ -265,7 +282,9 @@ static int ext4_readdir(struct file *file, struct dir_context *ctx)
/* Directory is encrypted */
err = fscrypt_fname_disk_to_usr(inode,
- 0, 0, &de_name, &fstr);
+ EXT4_DIRENT_HASH(de),
+ EXT4_DIRENT_MINOR_HASH(de),
+ &de_name, &fstr);
de_name = fstr;
fstr.len = save_len;
if (err)
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 644fd69185d3..37002663d521 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -162,7 +162,12 @@ enum SHIFT_DIRECTION {
#define EXT4_MB_USE_RESERVED 0x2000
/* Do strict check for free blocks while retrying block allocation */
#define EXT4_MB_STRICT_CHECK 0x4000
-
+/* Large fragment size list lookup succeeded at least once for cr = 0 */
+#define EXT4_MB_CR0_OPTIMIZED 0x8000
+/* Avg fragment size rb tree lookup succeeded at least once for cr = 1 */
+#define EXT4_MB_CR1_OPTIMIZED 0x00010000
+/* Perform linear traversal for one group */
+#define EXT4_MB_SEARCH_NEXT_LINEAR 0x00020000
struct ext4_allocation_request {
/* target inode for block we're allocating */
struct inode *inode;
@@ -472,15 +477,6 @@ struct flex_groups {
EXT4_VERITY_FL | \
EXT4_INLINE_DATA_FL)
-/* Flags we can manipulate with through FS_IOC_FSSETXATTR */
-#define EXT4_FL_XFLAG_VISIBLE (EXT4_SYNC_FL | \
- EXT4_IMMUTABLE_FL | \
- EXT4_APPEND_FL | \
- EXT4_NODUMP_FL | \
- EXT4_NOATIME_FL | \
- EXT4_PROJINHERIT_FL | \
- EXT4_DAX_FL)
-
/* Flags that should be inherited by new inodes from their parent. */
#define EXT4_FL_INHERITED (EXT4_SECRM_FL | EXT4_UNRM_FL | EXT4_COMPR_FL |\
EXT4_SYNC_FL | EXT4_NODUMP_FL | EXT4_NOATIME_FL |\
@@ -1222,7 +1218,7 @@ struct ext4_inode_info {
#define EXT4_MOUNT_JOURNAL_CHECKSUM 0x800000 /* Journal checksums */
#define EXT4_MOUNT_JOURNAL_ASYNC_COMMIT 0x1000000 /* Journal Async Commit */
#define EXT4_MOUNT_WARN_ON_ERROR 0x2000000 /* Trigger WARN_ON on error */
-#define EXT4_MOUNT_PREFETCH_BLOCK_BITMAPS 0x4000000
+#define EXT4_MOUNT_NO_PREFETCH_BLOCK_BITMAPS 0x4000000
#define EXT4_MOUNT_DELALLOC 0x8000000 /* Delalloc support */
#define EXT4_MOUNT_DATA_ERR_ABORT 0x10000000 /* Abort on file data write */
#define EXT4_MOUNT_BLOCK_VALIDITY 0x20000000 /* Block validity checking */
@@ -1247,7 +1243,9 @@ struct ext4_inode_info {
#define EXT4_MOUNT2_JOURNAL_FAST_COMMIT 0x00000010 /* Journal fast commit */
#define EXT4_MOUNT2_DAX_NEVER 0x00000020 /* Do not allow Direct Access */
#define EXT4_MOUNT2_DAX_INODE 0x00000040 /* For printing options only */
-
+#define EXT4_MOUNT2_MB_OPTIMIZE_SCAN 0x00000080 /* Optimize group
+ * scanning in mballoc
+ */
#define clear_opt(sb, opt) EXT4_SB(sb)->s_mount_opt &= \
~EXT4_MOUNT_##opt
@@ -1484,6 +1482,7 @@ struct ext4_sb_info {
struct percpu_counter s_freeinodes_counter;
struct percpu_counter s_dirs_counter;
struct percpu_counter s_dirtyclusters_counter;
+ struct percpu_counter s_sra_exceeded_retry_limit;
struct blockgroup_lock *s_blockgroup_lock;
struct proc_dir_entry *s_proc;
struct kobject s_kobj;
@@ -1527,9 +1526,14 @@ struct ext4_sb_info {
unsigned int s_mb_free_pending;
struct list_head s_freed_data_list; /* List of blocks to be freed
after commit completed */
+ struct rb_root s_mb_avg_fragment_size_root;
+ rwlock_t s_mb_rb_lock;
+ struct list_head *s_mb_largest_free_orders;
+ rwlock_t *s_mb_largest_free_orders_locks;
/* tunables */
unsigned long s_stripe;
+ unsigned int s_mb_max_linear_groups;
unsigned int s_mb_stream_request;
unsigned int s_mb_max_to_scan;
unsigned int s_mb_min_to_scan;
@@ -1549,12 +1553,17 @@ struct ext4_sb_info {
atomic_t s_bal_success; /* we found long enough chunks */
atomic_t s_bal_allocated; /* in blocks */
atomic_t s_bal_ex_scanned; /* total extents scanned */
+ atomic_t s_bal_groups_scanned; /* number of groups scanned */
atomic_t s_bal_goals; /* goal hits */
atomic_t s_bal_breaks; /* too long searches */
atomic_t s_bal_2orders; /* 2^order hits */
- spinlock_t s_bal_lock;
- unsigned long s_mb_buddies_generated;
- unsigned long long s_mb_generation_time;
+ atomic_t s_bal_cr0_bad_suggestions;
+ atomic_t s_bal_cr1_bad_suggestions;
+ atomic64_t s_bal_cX_groups_considered[4];
+ atomic64_t s_bal_cX_hits[4];
+ atomic64_t s_bal_cX_failed[4]; /* cX loop didn't find blocks */
+ atomic_t s_mb_buddies_generated; /* number of buddies generated */
+ atomic64_t s_mb_generation_time;
atomic_t s_mb_lost_chunks;
atomic_t s_mb_preallocated;
atomic_t s_mb_discarded;
@@ -2195,6 +2204,17 @@ struct ext4_dir_entry {
char name[EXT4_NAME_LEN]; /* File name */
};
+
+/*
+ * Encrypted Casefolded entries require saving the hash on disk. This structure
+ * followed ext4_dir_entry_2's name[name_len] at the next 4 byte aligned
+ * boundary.
+ */
+struct ext4_dir_entry_hash {
+ __le32 hash;
+ __le32 minor_hash;
+};
+
/*
* The new version of the directory entry. Since EXT4 structures are
* stored in intel byte order, and the name_len field could never be
@@ -2210,6 +2230,22 @@ struct ext4_dir_entry_2 {
};
/*
+ * Access the hashes at the end of ext4_dir_entry_2
+ */
+#define EXT4_DIRENT_HASHES(entry) \
+ ((struct ext4_dir_entry_hash *) \
+ (((void *)(entry)) + \
+ ((8 + (entry)->name_len + EXT4_DIR_ROUND) & ~EXT4_DIR_ROUND)))
+#define EXT4_DIRENT_HASH(entry) le32_to_cpu(EXT4_DIRENT_HASHES(de)->hash)
+#define EXT4_DIRENT_MINOR_HASH(entry) \
+ le32_to_cpu(EXT4_DIRENT_HASHES(de)->minor_hash)
+
+static inline bool ext4_hash_in_dirent(const struct inode *inode)
+{
+ return IS_CASEFOLDED(inode) && IS_ENCRYPTED(inode);
+}
+
+/*
* This is a bogus directory entry at the end of each leaf block that
* records checksums.
*/
@@ -2250,11 +2286,25 @@ struct ext4_dir_entry_tail {
*/
#define EXT4_DIR_PAD 4
#define EXT4_DIR_ROUND (EXT4_DIR_PAD - 1)
-#define EXT4_DIR_REC_LEN(name_len) (((name_len) + 8 + EXT4_DIR_ROUND) & \
- ~EXT4_DIR_ROUND)
#define EXT4_MAX_REC_LEN ((1<<16)-1)
/*
+ * The rec_len is dependent on the type of directory. Directories that are
+ * casefolded and encrypted need to store the hash as well, so we add room for
+ * ext4_extended_dir_entry_2. For all entries related to '.' or '..' you should
+ * pass NULL for dir, as those entries do not use the extra fields.
+ */
+static inline unsigned int ext4_dir_rec_len(__u8 name_len,
+ const struct inode *dir)
+{
+ int rec_len = (name_len + 8 + EXT4_DIR_ROUND);
+
+ if (dir && ext4_hash_in_dirent(dir))
+ rec_len += sizeof(struct ext4_dir_entry_hash);
+ return (rec_len & ~EXT4_DIR_ROUND);
+}
+
+/*
* If we ever get support for fs block sizes > page_size, we'll need
* to remove the #if statements in the next two functions...
*/
@@ -2310,6 +2360,7 @@ static inline __le16 ext4_rec_len_to_disk(unsigned len, unsigned blocksize)
#define DX_HASH_LEGACY_UNSIGNED 3
#define DX_HASH_HALF_MD4_UNSIGNED 4
#define DX_HASH_TEA_UNSIGNED 5
+#define DX_HASH_SIPHASH 6
static inline u32 ext4_chksum(struct ext4_sb_info *sbi, u32 crc,
const void *address, unsigned int length)
@@ -2364,6 +2415,7 @@ struct ext4_filename {
};
#define fname_name(p) ((p)->disk_name.name)
+#define fname_usr_name(p) ((p)->usr_fname->name)
#define fname_len(p) ((p)->disk_name.len)
/*
@@ -2594,9 +2646,9 @@ extern unsigned ext4_free_clusters_after_init(struct super_block *sb,
ext4_fsblk_t ext4_inode_to_goal_block(struct inode *);
#ifdef CONFIG_UNICODE
-extern void ext4_fname_setup_ci_filename(struct inode *dir,
+extern int ext4_fname_setup_ci_filename(struct inode *dir,
const struct qstr *iname,
- struct fscrypt_str *fname);
+ struct ext4_filename *fname);
#endif
#ifdef CONFIG_FS_ENCRYPTION
@@ -2627,9 +2679,9 @@ static inline int ext4_fname_setup_filename(struct inode *dir,
ext4_fname_from_fscrypt_name(fname, &name);
#ifdef CONFIG_UNICODE
- ext4_fname_setup_ci_filename(dir, iname, &fname->cf_name);
+ err = ext4_fname_setup_ci_filename(dir, iname, fname);
#endif
- return 0;
+ return err;
}
static inline int ext4_fname_prepare_lookup(struct inode *dir,
@@ -2646,9 +2698,9 @@ static inline int ext4_fname_prepare_lookup(struct inode *dir,
ext4_fname_from_fscrypt_name(fname, &name);
#ifdef CONFIG_UNICODE
- ext4_fname_setup_ci_filename(dir, &dentry->d_name, &fname->cf_name);
+ err = ext4_fname_setup_ci_filename(dir, &dentry->d_name, fname);
#endif
- return 0;
+ return err;
}
static inline void ext4_fname_free_filename(struct ext4_filename *fname)
@@ -2673,15 +2725,16 @@ static inline int ext4_fname_setup_filename(struct inode *dir,
int lookup,
struct ext4_filename *fname)
{
+ int err = 0;
fname->usr_fname = iname;
fname->disk_name.name = (unsigned char *) iname->name;
fname->disk_name.len = iname->len;
#ifdef CONFIG_UNICODE
- ext4_fname_setup_ci_filename(dir, iname, &fname->cf_name);
+ err = ext4_fname_setup_ci_filename(dir, iname, fname);
#endif
- return 0;
+ return err;
}
static inline int ext4_fname_prepare_lookup(struct inode *dir,
@@ -2706,9 +2759,9 @@ extern int __ext4_check_dir_entry(const char *, unsigned int, struct inode *,
struct ext4_dir_entry_2 *,
struct buffer_head *, char *, int,
unsigned int);
-#define ext4_check_dir_entry(dir, filp, de, bh, buf, size, offset) \
+#define ext4_check_dir_entry(dir, filp, de, bh, buf, size, offset) \
unlikely(__ext4_check_dir_entry(__func__, __LINE__, (dir), (filp), \
- (de), (bh), (buf), (size), (offset)))
+ (de), (bh), (buf), (size), (offset)))
extern int ext4_htree_store_dirent(struct file *dir_file, __u32 hash,
__u32 minor_hash,
struct ext4_dir_entry_2 *dirent,
@@ -2719,7 +2772,7 @@ extern int ext4_find_dest_de(struct inode *dir, struct inode *inode,
void *buf, int buf_size,
struct ext4_filename *fname,
struct ext4_dir_entry_2 **dest_de);
-void ext4_insert_dentry(struct inode *inode,
+void ext4_insert_dentry(struct inode *dir, struct inode *inode,
struct ext4_dir_entry_2 *de,
int buf_size,
struct ext4_filename *fname);
@@ -2793,6 +2846,8 @@ void __ext4_fc_track_link(handle_t *handle, struct inode *inode,
struct dentry *dentry);
void ext4_fc_track_unlink(handle_t *handle, struct dentry *dentry);
void ext4_fc_track_link(handle_t *handle, struct dentry *dentry);
+void __ext4_fc_track_create(handle_t *handle, struct inode *inode,
+ struct dentry *dentry);
void ext4_fc_track_create(handle_t *handle, struct dentry *dentry);
void ext4_fc_track_inode(handle_t *handle, struct inode *inode);
void ext4_fc_mark_ineligible(struct super_block *sb, int reason);
@@ -2808,8 +2863,10 @@ int __init ext4_fc_init_dentry_cache(void);
/* mballoc.c */
extern const struct seq_operations ext4_mb_seq_groups_ops;
+extern const struct seq_operations ext4_mb_seq_structs_summary_ops;
extern long ext4_mb_stats;
extern long ext4_mb_max_to_scan;
+extern int ext4_seq_mb_stats_show(struct seq_file *seq, void *offset);
extern int ext4_mb_init(struct super_block *);
extern int ext4_mb_release(struct super_block *);
extern ext4_fsblk_t ext4_mb_new_blocks(handle_t *,
@@ -2925,6 +2982,9 @@ extern int ext4_ind_remove_space(handle_t *handle, struct inode *inode,
/* ioctl.c */
extern long ext4_ioctl(struct file *, unsigned int, unsigned long);
extern long ext4_compat_ioctl(struct file *, unsigned int, unsigned long);
+int ext4_fileattr_set(struct user_namespace *mnt_userns,
+ struct dentry *dentry, struct fileattr *fa);
+int ext4_fileattr_get(struct dentry *dentry, struct fileattr *fa);
extern void ext4_reset_inode_seed(struct inode *inode);
/* migrate.c */
@@ -3309,11 +3369,14 @@ struct ext4_group_info {
ext4_grpblk_t bb_free; /* total free blocks */
ext4_grpblk_t bb_fragments; /* nr of freespace fragments */
ext4_grpblk_t bb_largest_free_order;/* order of largest frag in BG */
+ ext4_group_t bb_group; /* Group number */
struct list_head bb_prealloc_list;
#ifdef DOUBLE_CHECK
void *bb_bitmap;
#endif
struct rw_semaphore alloc_sem;
+ struct rb_node bb_avg_fragment_size_rb;
+ struct list_head bb_largest_free_order_node;
ext4_grpblk_t bb_counters[]; /* Nr of free power-of-two-block
* regions, index is order.
* bb_counters[3] = 5 means
@@ -3516,9 +3579,6 @@ extern void ext4_initialize_dirent_tail(struct buffer_head *bh,
unsigned int blocksize);
extern int ext4_handle_dirty_dirblock(handle_t *handle, struct inode *inode,
struct buffer_head *bh);
-extern int ext4_ci_compare(const struct inode *parent,
- const struct qstr *fname,
- const struct qstr *entry, bool quick);
extern int __ext4_unlink(handle_t *handle, struct inode *dir, const struct qstr *d_name,
struct inode *inode);
extern int __ext4_link(struct inode *dir, struct inode *inode,
diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index 77c7c8a54da7..77c84d6f1af6 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -4382,7 +4382,7 @@ static int ext4_alloc_file_blocks(struct file *file, ext4_lblk_t offset,
{
struct inode *inode = file_inode(file);
handle_t *handle;
- int ret, ret2 = 0, ret3 = 0;
+ int ret = 0, ret2 = 0, ret3 = 0;
int retries = 0;
int depth = 0;
struct ext4_map_blocks map;
diff --git a/fs/ext4/fast_commit.c b/fs/ext4/fast_commit.c
index 6c4f19b0a556..f98ca4f37ef6 100644
--- a/fs/ext4/fast_commit.c
+++ b/fs/ext4/fast_commit.c
@@ -66,7 +66,7 @@
* Fast Commit Ineligibility
* -------------------------
* Not all operations are supported by fast commits today (e.g extended
- * attributes). Fast commit ineligiblity is marked by calling one of the
+ * attributes). Fast commit ineligibility is marked by calling one of the
* two following functions:
*
* - ext4_fc_mark_ineligible(): This makes next fast commit operation to fall
@@ -513,10 +513,10 @@ void ext4_fc_track_link(handle_t *handle, struct dentry *dentry)
__ext4_fc_track_link(handle, d_inode(dentry), dentry);
}
-void ext4_fc_track_create(handle_t *handle, struct dentry *dentry)
+void __ext4_fc_track_create(handle_t *handle, struct inode *inode,
+ struct dentry *dentry)
{
struct __track_dentry_update_args args;
- struct inode *inode = d_inode(dentry);
int ret;
args.dentry = dentry;
@@ -527,6 +527,11 @@ void ext4_fc_track_create(handle_t *handle, struct dentry *dentry)
trace_ext4_fc_track_create(inode, dentry, ret);
}
+void ext4_fc_track_create(handle_t *handle, struct dentry *dentry)
+{
+ __ext4_fc_track_create(handle, d_inode(dentry), dentry);
+}
+
/* __track_fn for inode tracking */
static int __track_inode(struct inode *inode, void *arg, bool update)
{
@@ -1083,8 +1088,10 @@ static int ext4_fc_perform_commit(journal_t *journal)
head.fc_tid = cpu_to_le32(
sbi->s_journal->j_running_transaction->t_tid);
if (!ext4_fc_add_tlv(sb, EXT4_FC_TAG_HEAD, sizeof(head),
- (u8 *)&head, &crc))
+ (u8 *)&head, &crc)) {
+ ret = -ENOSPC;
goto out;
+ }
}
spin_lock(&sbi->s_fc_lock);
@@ -1729,7 +1736,7 @@ static int ext4_fc_replay_add_range(struct super_block *sb,
}
/* Range is mapped and needs a state change */
- jbd_debug(1, "Converting from %d to %d %lld",
+ jbd_debug(1, "Converting from %ld to %d %lld",
map.m_flags & EXT4_MAP_UNWRITTEN,
ext4_ext_is_unwritten(ex), map.m_pblk);
ret = ext4_ext_replay_update_ex(inode, cur, map.m_len,
diff --git a/fs/ext4/file.c b/fs/ext4/file.c
index 194f5d00fa32..816dedcbd541 100644
--- a/fs/ext4/file.c
+++ b/fs/ext4/file.c
@@ -371,15 +371,32 @@ truncate:
static int ext4_dio_write_end_io(struct kiocb *iocb, ssize_t size,
int error, unsigned int flags)
{
- loff_t offset = iocb->ki_pos;
+ loff_t pos = iocb->ki_pos;
struct inode *inode = file_inode(iocb->ki_filp);
if (error)
return error;
- if (size && flags & IOMAP_DIO_UNWRITTEN)
- return ext4_convert_unwritten_extents(NULL, inode,
- offset, size);
+ if (size && flags & IOMAP_DIO_UNWRITTEN) {
+ error = ext4_convert_unwritten_extents(NULL, inode, pos, size);
+ if (error < 0)
+ return error;
+ }
+ /*
+ * If we are extending the file, we have to update i_size here before
+ * page cache gets invalidated in iomap_dio_rw(). Otherwise racing
+ * buffered reads could zero out too much from page cache pages. Update
+ * of on-disk size will happen later in ext4_dio_write_iter() where
+ * we have enough information to also perform orphan list handling etc.
+ * Note that we perform all extending writes synchronously under
+ * i_rwsem held exclusively so i_size update is safe here in that case.
+ * If the write was not extending, we cannot see pos > i_size here
+ * because operations reducing i_size like truncate wait for all
+ * outstanding DIO before updating i_size.
+ */
+ pos += size;
+ if (pos > i_size_read(inode))
+ i_size_write(inode, pos);
return 0;
}
@@ -919,5 +936,7 @@ const struct inode_operations ext4_file_inode_operations = {
.get_acl = ext4_get_acl,
.set_acl = ext4_set_acl,
.fiemap = ext4_fiemap,
+ .fileattr_get = ext4_fileattr_get,
+ .fileattr_set = ext4_fileattr_set,
};
diff --git a/fs/ext4/fsmap.c b/fs/ext4/fsmap.c
index 4c2a9fe30067..4493ef0c715e 100644
--- a/fs/ext4/fsmap.c
+++ b/fs/ext4/fsmap.c
@@ -354,8 +354,8 @@ static unsigned int ext4_getfsmap_find_sb(struct super_block *sb,
/* Compare two fsmap items. */
static int ext4_getfsmap_compare(void *priv,
- struct list_head *a,
- struct list_head *b)
+ const struct list_head *a,
+ const struct list_head *b)
{
struct ext4_fsmap *fa;
struct ext4_fsmap *fb;
diff --git a/fs/ext4/hash.c b/fs/ext4/hash.c
index a92eb79de0cc..f34f4176c1e7 100644
--- a/fs/ext4/hash.c
+++ b/fs/ext4/hash.c
@@ -197,7 +197,7 @@ static void str2hashbuf_unsigned(const char *msg, int len, __u32 *buf, int num)
* represented, and whether or not the returned hash is 32 bits or 64
* bits. 32 bit hashes will return 0 for the minor hash.
*/
-static int __ext4fs_dirhash(const char *name, int len,
+static int __ext4fs_dirhash(const struct inode *dir, const char *name, int len,
struct dx_hash_info *hinfo)
{
__u32 hash;
@@ -259,6 +259,22 @@ static int __ext4fs_dirhash(const char *name, int len,
hash = buf[0];
minor_hash = buf[1];
break;
+ case DX_HASH_SIPHASH:
+ {
+ struct qstr qname = QSTR_INIT(name, len);
+ __u64 combined_hash;
+
+ if (fscrypt_has_encryption_key(dir)) {
+ combined_hash = fscrypt_fname_siphash(dir, &qname);
+ } else {
+ ext4_warning_inode(dir, "Siphash requires key");
+ return -1;
+ }
+
+ hash = (__u32)(combined_hash >> 32);
+ minor_hash = (__u32)combined_hash;
+ break;
+ }
default:
hinfo->hash = 0;
return -1;
@@ -280,7 +296,8 @@ int ext4fs_dirhash(const struct inode *dir, const char *name, int len,
unsigned char *buff;
struct qstr qstr = {.name = name, .len = len };
- if (len && IS_CASEFOLDED(dir) && um) {
+ if (len && IS_CASEFOLDED(dir) && um &&
+ (!IS_ENCRYPTED(dir) || fscrypt_has_encryption_key(dir))) {
buff = kzalloc(sizeof(char) * PATH_MAX, GFP_KERNEL);
if (!buff)
return -ENOMEM;
@@ -291,12 +308,12 @@ int ext4fs_dirhash(const struct inode *dir, const char *name, int len,
goto opaque_seq;
}
- r = __ext4fs_dirhash(buff, dlen, hinfo);
+ r = __ext4fs_dirhash(dir, buff, dlen, hinfo);
kfree(buff);
return r;
}
opaque_seq:
#endif
- return __ext4fs_dirhash(name, len, hinfo);
+ return __ext4fs_dirhash(dir, name, len, hinfo);
}
diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c
index 633ae7becd61..81a17a3cd80e 100644
--- a/fs/ext4/ialloc.c
+++ b/fs/ext4/ialloc.c
@@ -970,7 +970,7 @@ struct inode *__ext4_new_inode(struct user_namespace *mnt_userns,
i_gid_write(inode, owner[1]);
} else if (test_opt(sb, GRPID)) {
inode->i_mode = mode;
- inode->i_uid = fsuid_into_mnt(mnt_userns);
+ inode_fsuid_set(inode, mnt_userns);
inode->i_gid = dir->i_gid;
} else
inode_init_owner(mnt_userns, inode, dir, mode);
@@ -1292,7 +1292,8 @@ got:
ei->i_extra_isize = sbi->s_want_extra_isize;
ei->i_inline_off = 0;
- if (ext4_has_feature_inline_data(sb))
+ if (ext4_has_feature_inline_data(sb) &&
+ (!(ei->i_flags & EXT4_DAX_FL) || S_ISDIR(mode)))
ext4_set_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA);
ret = inode;
err = dquot_alloc_inode(inode);
@@ -1513,6 +1514,7 @@ int ext4_init_inode_table(struct super_block *sb, ext4_group_t group,
handle_t *handle;
ext4_fsblk_t blk;
int num, ret = 0, used_blks = 0;
+ unsigned long used_inos = 0;
/* This should not happen, but just to be sure check this */
if (sb_rdonly(sb)) {
@@ -1543,22 +1545,37 @@ int ext4_init_inode_table(struct super_block *sb, ext4_group_t group,
* used inodes so we need to skip blocks with used inodes in
* inode table.
*/
- if (!(gdp->bg_flags & cpu_to_le16(EXT4_BG_INODE_UNINIT)))
- used_blks = DIV_ROUND_UP((EXT4_INODES_PER_GROUP(sb) -
- ext4_itable_unused_count(sb, gdp)),
- sbi->s_inodes_per_block);
-
- if ((used_blks < 0) || (used_blks > sbi->s_itb_per_group) ||
- ((group == 0) && ((EXT4_INODES_PER_GROUP(sb) -
- ext4_itable_unused_count(sb, gdp)) <
- EXT4_FIRST_INO(sb)))) {
- ext4_error(sb, "Something is wrong with group %u: "
- "used itable blocks: %d; "
- "itable unused count: %u",
- group, used_blks,
- ext4_itable_unused_count(sb, gdp));
- ret = 1;
- goto err_out;
+ if (!(gdp->bg_flags & cpu_to_le16(EXT4_BG_INODE_UNINIT))) {
+ used_inos = EXT4_INODES_PER_GROUP(sb) -
+ ext4_itable_unused_count(sb, gdp);
+ used_blks = DIV_ROUND_UP(used_inos, sbi->s_inodes_per_block);
+
+ /* Bogus inode unused count? */
+ if (used_blks < 0 || used_blks > sbi->s_itb_per_group) {
+ ext4_error(sb, "Something is wrong with group %u: "
+ "used itable blocks: %d; "
+ "itable unused count: %u",
+ group, used_blks,
+ ext4_itable_unused_count(sb, gdp));
+ ret = 1;
+ goto err_out;
+ }
+
+ used_inos += group * EXT4_INODES_PER_GROUP(sb);
+ /*
+ * Are there some uninitialized inodes in the inode table
+ * before the first normal inode?
+ */
+ if ((used_blks != sbi->s_itb_per_group) &&
+ (used_inos < EXT4_FIRST_INO(sb))) {
+ ext4_error(sb, "Something is wrong with group %u: "
+ "itable unused count: %u; "
+ "itables initialized count: %ld",
+ group, ext4_itable_unused_count(sb, gdp),
+ used_inos);
+ ret = 1;
+ goto err_out;
+ }
}
blk = ext4_inode_table(sb, gdp) + used_blks;
diff --git a/fs/ext4/indirect.c b/fs/ext4/indirect.c
index 1223a18c3ff9..a7bc6ad656a9 100644
--- a/fs/ext4/indirect.c
+++ b/fs/ext4/indirect.c
@@ -705,7 +705,7 @@ static int ext4_ind_trunc_restart_fn(handle_t *handle, struct inode *inode,
/*
* Truncate transactions can be complex and absolutely huge. So we need to
- * be able to restart the transaction at a conventient checkpoint to make
+ * be able to restart the transaction at a convenient checkpoint to make
* sure we don't overflow the journal.
*
* Try to extend this transaction for the purposes of truncation. If
diff --git a/fs/ext4/inline.c b/fs/ext4/inline.c
index b41512d1badc..3cf01629010d 100644
--- a/fs/ext4/inline.c
+++ b/fs/ext4/inline.c
@@ -795,7 +795,7 @@ ext4_journalled_write_inline_data(struct inode *inode,
* clear the inode state safely.
* 2. The inode has inline data, then we need to read the data, make it
* update and dirty so that ext4_da_writepages can handle it. We don't
- * need to start the journal since the file's metatdata isn't changed now.
+ * need to start the journal since the file's metadata isn't changed now.
*/
static int ext4_da_convert_inline_data_to_extent(struct address_space *mapping,
struct inode *inode,
@@ -1031,7 +1031,7 @@ static int ext4_add_dirent_to_inline(handle_t *handle,
err = ext4_journal_get_write_access(handle, iloc->bh);
if (err)
return err;
- ext4_insert_dentry(inode, de, inline_size, fname);
+ ext4_insert_dentry(dir, inode, de, inline_size, fname);
ext4_show_inline_dir(dir, iloc->bh, inline_start, inline_size);
@@ -1100,7 +1100,7 @@ static int ext4_update_inline_dir(handle_t *handle, struct inode *dir,
int old_size = EXT4_I(dir)->i_inline_size - EXT4_MIN_INLINE_DATA_SIZE;
int new_size = get_max_inline_xattr_value_size(dir, iloc);
- if (new_size - old_size <= EXT4_DIR_REC_LEN(1))
+ if (new_size - old_size <= ext4_dir_rec_len(1, NULL))
return -ENOSPC;
ret = ext4_update_inline_data(handle, dir,
@@ -1380,8 +1380,8 @@ int ext4_inlinedir_to_tree(struct file *dir_file,
fake.name_len = 1;
strcpy(fake.name, ".");
fake.rec_len = ext4_rec_len_to_disk(
- EXT4_DIR_REC_LEN(fake.name_len),
- inline_size);
+ ext4_dir_rec_len(fake.name_len, NULL),
+ inline_size);
ext4_set_de_type(inode->i_sb, &fake, S_IFDIR);
de = &fake;
pos = EXT4_INLINE_DOTDOT_OFFSET;
@@ -1390,8 +1390,8 @@ int ext4_inlinedir_to_tree(struct file *dir_file,
fake.name_len = 2;
strcpy(fake.name, "..");
fake.rec_len = ext4_rec_len_to_disk(
- EXT4_DIR_REC_LEN(fake.name_len),
- inline_size);
+ ext4_dir_rec_len(fake.name_len, NULL),
+ inline_size);
ext4_set_de_type(inode->i_sb, &fake, S_IFDIR);
de = &fake;
pos = EXT4_INLINE_DOTDOT_SIZE;
@@ -1406,7 +1406,12 @@ int ext4_inlinedir_to_tree(struct file *dir_file,
}
}
- ext4fs_dirhash(dir, de->name, de->name_len, hinfo);
+ if (ext4_hash_in_dirent(dir)) {
+ hinfo->hash = EXT4_DIRENT_HASH(de);
+ hinfo->minor_hash = EXT4_DIRENT_MINOR_HASH(de);
+ } else {
+ ext4fs_dirhash(dir, de->name, de->name_len, hinfo);
+ }
if ((hinfo->hash < start_hash) ||
((hinfo->hash == start_hash) &&
(hinfo->minor_hash < start_minor_hash)))
@@ -1488,8 +1493,8 @@ int ext4_read_inline_dir(struct file *file,
* So we will use extra_offset and extra_size to indicate them
* during the inline dir iteration.
*/
- dotdot_offset = EXT4_DIR_REC_LEN(1);
- dotdot_size = dotdot_offset + EXT4_DIR_REC_LEN(2);
+ dotdot_offset = ext4_dir_rec_len(1, NULL);
+ dotdot_size = dotdot_offset + ext4_dir_rec_len(2, NULL);
extra_offset = dotdot_size - EXT4_INLINE_DOTDOT_SIZE;
extra_size = extra_offset + inline_size;
@@ -1524,7 +1529,7 @@ int ext4_read_inline_dir(struct file *file,
* failure will be detected in the
* dirent test below. */
if (ext4_rec_len_from_disk(de->rec_len, extra_size)
- < EXT4_DIR_REC_LEN(1))
+ < ext4_dir_rec_len(1, NULL))
break;
i += ext4_rec_len_from_disk(de->rec_len,
extra_size);
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 650c5acd2f2d..fe6045a46599 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -1066,8 +1066,7 @@ static int ext4_block_write_begin(struct page *page, loff_t pos, unsigned len,
block_end = block_start + blocksize;
if (block_end <= from || block_start >= to) {
if (PageUptodate(page)) {
- if (!buffer_uptodate(bh))
- set_buffer_uptodate(bh);
+ set_buffer_uptodate(bh);
}
continue;
}
@@ -1092,8 +1091,7 @@ static int ext4_block_write_begin(struct page *page, loff_t pos, unsigned len,
}
}
if (PageUptodate(page)) {
- if (!buffer_uptodate(bh))
- set_buffer_uptodate(bh);
+ set_buffer_uptodate(bh);
continue;
}
if (!buffer_uptodate(bh) && !buffer_delay(bh) &&
@@ -1938,13 +1936,13 @@ static int __ext4_journalled_writepage(struct page *page,
if (!ret)
ret = err;
- if (!ext4_has_inline_data(inode))
- ext4_walk_page_buffers(NULL, page_bufs, 0, len,
- NULL, bput_one);
ext4_set_inode_state(inode, EXT4_STATE_JDATA);
out:
unlock_page(page);
out_no_pagelock:
+ if (!inline_data && page_bufs)
+ ext4_walk_page_buffers(NULL, page_bufs, 0, len,
+ NULL, bput_one);
brelse(inode_bh);
return ret;
}
@@ -3824,7 +3822,7 @@ unlock:
* starting from file offset 'from'. The range to be zero'd must
* be contained with in one block. If the specified range exceeds
* the end of the block it will be shortened to end of the block
- * that cooresponds to 'from'
+ * that corresponds to 'from'
*/
static int ext4_block_zero_page_range(handle_t *handle,
struct address_space *mapping, loff_t from, loff_t length)
@@ -5026,7 +5024,7 @@ static int ext4_do_update_inode(handle_t *handle,
struct ext4_inode_info *ei = EXT4_I(inode);
struct buffer_head *bh = iloc->bh;
struct super_block *sb = inode->i_sb;
- int err = 0, rc, block;
+ int err = 0, block;
int need_datasync = 0, set_large_file = 0;
uid_t i_uid;
gid_t i_gid;
@@ -5138,9 +5136,9 @@ static int ext4_do_update_inode(handle_t *handle,
bh->b_data);
BUFFER_TRACE(bh, "call ext4_handle_dirty_metadata");
- rc = ext4_handle_dirty_metadata(handle, NULL, bh);
- if (!err)
- err = rc;
+ err = ext4_handle_dirty_metadata(handle, NULL, bh);
+ if (err)
+ goto out_brelse;
ext4_clear_inode_state(inode, EXT4_STATE_NEW);
if (set_large_file) {
BUFFER_TRACE(EXT4_SB(sb)->s_sbh, "get write access");
@@ -5387,8 +5385,10 @@ int ext4_setattr(struct user_namespace *mnt_userns, struct dentry *dentry,
inode->i_gid = attr->ia_gid;
error = ext4_mark_inode_dirty(handle, inode);
ext4_journal_stop(handle);
- if (unlikely(error))
+ if (unlikely(error)) {
+ ext4_fc_stop_update(inode);
return error;
+ }
}
if (attr->ia_valid & ATTR_SIZE) {
diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c
index a2cf35066f46..31627f7dc5cd 100644
--- a/fs/ext4/ioctl.c
+++ b/fs/ext4/ioctl.c
@@ -20,6 +20,7 @@
#include <linux/uaccess.h>
#include <linux/delay.h>
#include <linux/iversion.h>
+#include <linux/fileattr.h>
#include "ext4_jbd2.h"
#include "ext4.h"
#include <linux/fsmap.h>
@@ -315,6 +316,12 @@ static void ext4_dax_dontcache(struct inode *inode, unsigned int flags)
static bool dax_compatible(struct inode *inode, unsigned int oldflags,
unsigned int flags)
{
+ /* Allow the DAX flag to be changed on inline directories */
+ if (S_ISDIR(inode->i_mode)) {
+ flags &= ~EXT4_INLINE_DATA_FL;
+ oldflags &= ~EXT4_INLINE_DATA_FL;
+ }
+
if (flags & EXT4_DAX_FL) {
if ((oldflags & EXT4_DAX_MUT_EXCL) ||
ext4_test_inode_state(inode,
@@ -344,11 +351,6 @@ static int ext4_ioctl_setflags(struct inode *inode,
goto flags_out;
oldflags = ei->i_flags;
-
- err = vfs_ioc_setflags_prepare(inode, oldflags, flags);
- if (err)
- goto flags_out;
-
/*
* The JOURNAL_DATA flag can only be changed by
* the relevant capability.
@@ -459,9 +461,8 @@ flags_out:
}
#ifdef CONFIG_QUOTA
-static int ext4_ioctl_setproject(struct file *filp, __u32 projid)
+static int ext4_ioctl_setproject(struct inode *inode, __u32 projid)
{
- struct inode *inode = file_inode(filp);
struct super_block *sb = inode->i_sb;
struct ext4_inode_info *ei = EXT4_I(inode);
int err, rc;
@@ -545,7 +546,7 @@ out_stop:
return err;
}
#else
-static int ext4_ioctl_setproject(struct file *filp, __u32 projid)
+static int ext4_ioctl_setproject(struct inode *inode, __u32 projid)
{
if (projid != EXT4_DEF_PROJID)
return -EOPNOTSUPP;
@@ -553,56 +554,6 @@ static int ext4_ioctl_setproject(struct file *filp, __u32 projid)
}
#endif
-/* Transfer internal flags to xflags */
-static inline __u32 ext4_iflags_to_xflags(unsigned long iflags)
-{
- __u32 xflags = 0;
-
- if (iflags & EXT4_SYNC_FL)
- xflags |= FS_XFLAG_SYNC;
- if (iflags & EXT4_IMMUTABLE_FL)
- xflags |= FS_XFLAG_IMMUTABLE;
- if (iflags & EXT4_APPEND_FL)
- xflags |= FS_XFLAG_APPEND;
- if (iflags & EXT4_NODUMP_FL)
- xflags |= FS_XFLAG_NODUMP;
- if (iflags & EXT4_NOATIME_FL)
- xflags |= FS_XFLAG_NOATIME;
- if (iflags & EXT4_PROJINHERIT_FL)
- xflags |= FS_XFLAG_PROJINHERIT;
- if (iflags & EXT4_DAX_FL)
- xflags |= FS_XFLAG_DAX;
- return xflags;
-}
-
-#define EXT4_SUPPORTED_FS_XFLAGS (FS_XFLAG_SYNC | FS_XFLAG_IMMUTABLE | \
- FS_XFLAG_APPEND | FS_XFLAG_NODUMP | \
- FS_XFLAG_NOATIME | FS_XFLAG_PROJINHERIT | \
- FS_XFLAG_DAX)
-
-/* Transfer xflags flags to internal */
-static inline unsigned long ext4_xflags_to_iflags(__u32 xflags)
-{
- unsigned long iflags = 0;
-
- if (xflags & FS_XFLAG_SYNC)
- iflags |= EXT4_SYNC_FL;
- if (xflags & FS_XFLAG_IMMUTABLE)
- iflags |= EXT4_IMMUTABLE_FL;
- if (xflags & FS_XFLAG_APPEND)
- iflags |= EXT4_APPEND_FL;
- if (xflags & FS_XFLAG_NODUMP)
- iflags |= EXT4_NODUMP_FL;
- if (xflags & FS_XFLAG_NOATIME)
- iflags |= EXT4_NOATIME_FL;
- if (xflags & FS_XFLAG_PROJINHERIT)
- iflags |= EXT4_PROJINHERIT_FL;
- if (xflags & FS_XFLAG_DAX)
- iflags |= EXT4_DAX_FL;
-
- return iflags;
-}
-
static int ext4_shutdown(struct super_block *sb, unsigned long arg)
{
struct ext4_sb_info *sbi = EXT4_SB(sb);
@@ -770,15 +721,52 @@ group_add_out:
return err;
}
-static void ext4_fill_fsxattr(struct inode *inode, struct fsxattr *fa)
+int ext4_fileattr_get(struct dentry *dentry, struct fileattr *fa)
{
+ struct inode *inode = d_inode(dentry);
struct ext4_inode_info *ei = EXT4_I(inode);
+ u32 flags = ei->i_flags & EXT4_FL_USER_VISIBLE;
- simple_fill_fsxattr(fa, ext4_iflags_to_xflags(ei->i_flags &
- EXT4_FL_USER_VISIBLE));
+ if (S_ISREG(inode->i_mode))
+ flags &= ~FS_PROJINHERIT_FL;
+ fileattr_fill_flags(fa, flags);
if (ext4_has_feature_project(inode->i_sb))
fa->fsx_projid = from_kprojid(&init_user_ns, ei->i_projid);
+
+ return 0;
+}
+
+int ext4_fileattr_set(struct user_namespace *mnt_userns,
+ struct dentry *dentry, struct fileattr *fa)
+{
+ struct inode *inode = d_inode(dentry);
+ u32 flags = fa->flags;
+ int err = -EOPNOTSUPP;
+
+ ext4_fc_start_update(inode);
+ if (flags & ~EXT4_FL_USER_VISIBLE)
+ goto out;
+
+ /*
+ * chattr(1) grabs flags via GETFLAGS, modifies the result and
+ * passes that to SETFLAGS. So we cannot easily make SETFLAGS
+ * more restrictive than just silently masking off visible but
+ * not settable flags as we always did.
+ */
+ flags &= EXT4_FL_USER_MODIFIABLE;
+ if (ext4_mask_flags(inode->i_mode, flags) != flags)
+ goto out;
+ err = ext4_ioctl_check_immutable(inode, fa->fsx_projid, flags);
+ if (err)
+ goto out;
+ err = ext4_ioctl_setflags(inode, flags);
+ if (err)
+ goto out;
+ err = ext4_ioctl_setproject(inode, fa->fsx_projid);
+out:
+ ext4_fc_stop_update(inode);
+ return err;
}
/* So that the fiemap access checks can't overflow on 32 bit machines. */
@@ -816,55 +804,13 @@ static long __ext4_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
{
struct inode *inode = file_inode(filp);
struct super_block *sb = inode->i_sb;
- struct ext4_inode_info *ei = EXT4_I(inode);
struct user_namespace *mnt_userns = file_mnt_user_ns(filp);
- unsigned int flags;
ext4_debug("cmd = %u, arg = %lu\n", cmd, arg);
switch (cmd) {
case FS_IOC_GETFSMAP:
return ext4_ioc_getfsmap(sb, (void __user *)arg);
- case FS_IOC_GETFLAGS:
- flags = ei->i_flags & EXT4_FL_USER_VISIBLE;
- if (S_ISREG(inode->i_mode))
- flags &= ~EXT4_PROJINHERIT_FL;
- return put_user(flags, (int __user *) arg);
- case FS_IOC_SETFLAGS: {
- int err;
-
- if (!inode_owner_or_capable(mnt_userns, inode))
- return -EACCES;
-
- if (get_user(flags, (int __user *) arg))
- return -EFAULT;
-
- if (flags & ~EXT4_FL_USER_VISIBLE)
- return -EOPNOTSUPP;
- /*
- * chattr(1) grabs flags via GETFLAGS, modifies the result and
- * passes that to SETFLAGS. So we cannot easily make SETFLAGS
- * more restrictive than just silently masking off visible but
- * not settable flags as we always did.
- */
- flags &= EXT4_FL_USER_MODIFIABLE;
- if (ext4_mask_flags(inode->i_mode, flags) != flags)
- return -EOPNOTSUPP;
-
- err = mnt_want_write_file(filp);
- if (err)
- return err;
-
- inode_lock(inode);
- err = ext4_ioctl_check_immutable(inode,
- from_kprojid(&init_user_ns, ei->i_projid),
- flags);
- if (!err)
- err = ext4_ioctl_setflags(inode, flags);
- inode_unlock(inode);
- mnt_drop_write_file(filp);
- return err;
- }
case EXT4_IOC_GETVERSION:
case EXT4_IOC_GETVERSION_OLD:
return put_user(inode->i_generation, (int __user *) arg);
@@ -1246,60 +1192,6 @@ resizefs_out:
case EXT4_IOC_GET_ES_CACHE:
return ext4_ioctl_get_es_cache(filp, arg);
- case FS_IOC_FSGETXATTR:
- {
- struct fsxattr fa;
-
- ext4_fill_fsxattr(inode, &fa);
-
- if (copy_to_user((struct fsxattr __user *)arg,
- &fa, sizeof(fa)))
- return -EFAULT;
- return 0;
- }
- case FS_IOC_FSSETXATTR:
- {
- struct fsxattr fa, old_fa;
- int err;
-
- if (copy_from_user(&fa, (struct fsxattr __user *)arg,
- sizeof(fa)))
- return -EFAULT;
-
- /* Make sure caller has proper permission */
- if (!inode_owner_or_capable(mnt_userns, inode))
- return -EACCES;
-
- if (fa.fsx_xflags & ~EXT4_SUPPORTED_FS_XFLAGS)
- return -EOPNOTSUPP;
-
- flags = ext4_xflags_to_iflags(fa.fsx_xflags);
- if (ext4_mask_flags(inode->i_mode, flags) != flags)
- return -EOPNOTSUPP;
-
- err = mnt_want_write_file(filp);
- if (err)
- return err;
-
- inode_lock(inode);
- ext4_fill_fsxattr(inode, &old_fa);
- err = vfs_ioc_fssetxattr_check(inode, &old_fa, &fa);
- if (err)
- goto out;
- flags = (ei->i_flags & ~EXT4_FL_XFLAG_VISIBLE) |
- (flags & EXT4_FL_XFLAG_VISIBLE);
- err = ext4_ioctl_check_immutable(inode, fa.fsx_projid, flags);
- if (err)
- goto out;
- err = ext4_ioctl_setflags(inode, flags);
- if (err)
- goto out;
- err = ext4_ioctl_setproject(filp, fa.fsx_projid);
-out:
- inode_unlock(inode);
- mnt_drop_write_file(filp);
- return err;
- }
case EXT4_IOC_SHUTDOWN:
return ext4_shutdown(sb, arg);
@@ -1340,12 +1232,6 @@ long ext4_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
{
/* These are just misnamed, they actually get/put from/to user an int */
switch (cmd) {
- case FS_IOC32_GETFLAGS:
- cmd = FS_IOC_GETFLAGS;
- break;
- case FS_IOC32_SETFLAGS:
- cmd = FS_IOC_SETFLAGS;
- break;
case EXT4_IOC32_GETVERSION:
cmd = EXT4_IOC_GETVERSION;
break;
@@ -1405,8 +1291,6 @@ long ext4_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
case EXT4_IOC_CLEAR_ES_CACHE:
case EXT4_IOC_GETSTATE:
case EXT4_IOC_GET_ES_CACHE:
- case FS_IOC_FSGETXATTR:
- case FS_IOC_FSSETXATTR:
break;
default:
return -ENOIOCTLCMD;
diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index 99bf091fee10..3239e6669e84 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -127,11 +127,50 @@
* smallest multiple of the stripe value (sbi->s_stripe) which is
* greater than the default mb_group_prealloc.
*
+ * If "mb_optimize_scan" mount option is set, we maintain in memory group info
+ * structures in two data structures:
+ *
+ * 1) Array of largest free order lists (sbi->s_mb_largest_free_orders)
+ *
+ * Locking: sbi->s_mb_largest_free_orders_locks(array of rw locks)
+ *
+ * This is an array of lists where the index in the array represents the
+ * largest free order in the buddy bitmap of the participating group infos of
+ * that list. So, there are exactly MB_NUM_ORDERS(sb) (which means total
+ * number of buddy bitmap orders possible) number of lists. Group-infos are
+ * placed in appropriate lists.
+ *
+ * 2) Average fragment size rb tree (sbi->s_mb_avg_fragment_size_root)
+ *
+ * Locking: sbi->s_mb_rb_lock (rwlock)
+ *
+ * This is a red black tree consisting of group infos and the tree is sorted
+ * by average fragment sizes (which is calculated as ext4_group_info->bb_free
+ * / ext4_group_info->bb_fragments).
+ *
+ * When "mb_optimize_scan" mount option is set, mballoc consults the above data
+ * structures to decide the order in which groups are to be traversed for
+ * fulfilling an allocation request.
+ *
+ * At CR = 0, we look for groups which have the largest_free_order >= the order
+ * of the request. We directly look at the largest free order list in the data
+ * structure (1) above where largest_free_order = order of the request. If that
+ * list is empty, we look at remaining list in the increasing order of
+ * largest_free_order. This allows us to perform CR = 0 lookup in O(1) time.
+ *
+ * At CR = 1, we only consider groups where average fragment size > request
+ * size. So, we lookup a group which has average fragment size just above or
+ * equal to request size using our rb tree (data structure 2) in O(log N) time.
+ *
+ * If "mb_optimize_scan" mount option is not set, mballoc traverses groups in
+ * linear order which requires O(N) search time for each CR 0 and CR 1 phase.
+ *
* The regular allocator (using the buddy cache) supports a few tunables.
*
* /sys/fs/ext4/<partition>/mb_min_to_scan
* /sys/fs/ext4/<partition>/mb_max_to_scan
* /sys/fs/ext4/<partition>/mb_order2_req
+ * /sys/fs/ext4/<partition>/mb_linear_limit
*
* The regular allocator uses buddy scan only if the request len is power of
* 2 blocks and the order of allocation is >= sbi->s_mb_order2_reqs. The
@@ -149,6 +188,16 @@
* can be used for allocation. ext4_mb_good_group explains how the groups are
* checked.
*
+ * When "mb_optimize_scan" is turned on, as mentioned above, the groups may not
+ * get traversed linearly. That may result in subsequent allocations being not
+ * close to each other. And so, the underlying device may get filled up in a
+ * non-linear fashion. While that may not matter on non-rotational devices, for
+ * rotational devices that may result in higher seek times. "mb_linear_limit"
+ * tells mballoc how many groups mballoc should search linearly before
+ * performing consulting above data structures for more efficient lookups. For
+ * non rotational devices, this value defaults to 0 and for rotational devices
+ * this is set to MB_DEFAULT_LINEAR_LIMIT.
+ *
* Both the prealloc space are getting populated as above. So for the first
* request we will hit the buddy cache which will result in this prealloc
* space getting filled. The prealloc space is then later used for the
@@ -299,6 +348,8 @@
* - bitlock on a group (group)
* - object (inode/locality) (object)
* - per-pa lock (pa)
+ * - cr0 lists lock (cr0)
+ * - cr1 tree lock (cr1)
*
* Paths:
* - new pa
@@ -328,6 +379,9 @@
* group
* object
*
+ * - allocation path (ext4_mb_regular_allocator)
+ * group
+ * cr0/cr1
*/
static struct kmem_cache *ext4_pspace_cachep;
static struct kmem_cache *ext4_ac_cachep;
@@ -351,6 +405,9 @@ static void ext4_mb_generate_from_freelist(struct super_block *sb, void *bitmap,
ext4_group_t group);
static void ext4_mb_new_preallocation(struct ext4_allocation_context *ac);
+static bool ext4_mb_good_group(struct ext4_allocation_context *ac,
+ ext4_group_t group, int cr);
+
/*
* The algorithm using this percpu seq counter goes below:
* 1. We sample the percpu discard_pa_seq counter before trying for block
@@ -744,6 +801,269 @@ static void ext4_mb_mark_free_simple(struct super_block *sb,
}
}
+static void ext4_mb_rb_insert(struct rb_root *root, struct rb_node *new,
+ int (*cmp)(struct rb_node *, struct rb_node *))
+{
+ struct rb_node **iter = &root->rb_node, *parent = NULL;
+
+ while (*iter) {
+ parent = *iter;
+ if (cmp(new, *iter) > 0)
+ iter = &((*iter)->rb_left);
+ else
+ iter = &((*iter)->rb_right);
+ }
+
+ rb_link_node(new, parent, iter);
+ rb_insert_color(new, root);
+}
+
+static int
+ext4_mb_avg_fragment_size_cmp(struct rb_node *rb1, struct rb_node *rb2)
+{
+ struct ext4_group_info *grp1 = rb_entry(rb1,
+ struct ext4_group_info,
+ bb_avg_fragment_size_rb);
+ struct ext4_group_info *grp2 = rb_entry(rb2,
+ struct ext4_group_info,
+ bb_avg_fragment_size_rb);
+ int num_frags_1, num_frags_2;
+
+ num_frags_1 = grp1->bb_fragments ?
+ grp1->bb_free / grp1->bb_fragments : 0;
+ num_frags_2 = grp2->bb_fragments ?
+ grp2->bb_free / grp2->bb_fragments : 0;
+
+ return (num_frags_2 - num_frags_1);
+}
+
+/*
+ * Reinsert grpinfo into the avg_fragment_size tree with new average
+ * fragment size.
+ */
+static void
+mb_update_avg_fragment_size(struct super_block *sb, struct ext4_group_info *grp)
+{
+ struct ext4_sb_info *sbi = EXT4_SB(sb);
+
+ if (!test_opt2(sb, MB_OPTIMIZE_SCAN) || grp->bb_free == 0)
+ return;
+
+ write_lock(&sbi->s_mb_rb_lock);
+ if (!RB_EMPTY_NODE(&grp->bb_avg_fragment_size_rb)) {
+ rb_erase(&grp->bb_avg_fragment_size_rb,
+ &sbi->s_mb_avg_fragment_size_root);
+ RB_CLEAR_NODE(&grp->bb_avg_fragment_size_rb);
+ }
+
+ ext4_mb_rb_insert(&sbi->s_mb_avg_fragment_size_root,
+ &grp->bb_avg_fragment_size_rb,
+ ext4_mb_avg_fragment_size_cmp);
+ write_unlock(&sbi->s_mb_rb_lock);
+}
+
+/*
+ * Choose next group by traversing largest_free_order lists. Updates *new_cr if
+ * cr level needs an update.
+ */
+static void ext4_mb_choose_next_group_cr0(struct ext4_allocation_context *ac,
+ int *new_cr, ext4_group_t *group, ext4_group_t ngroups)
+{
+ struct ext4_sb_info *sbi = EXT4_SB(ac->ac_sb);
+ struct ext4_group_info *iter, *grp;
+ int i;
+
+ if (ac->ac_status == AC_STATUS_FOUND)
+ return;
+
+ if (unlikely(sbi->s_mb_stats && ac->ac_flags & EXT4_MB_CR0_OPTIMIZED))
+ atomic_inc(&sbi->s_bal_cr0_bad_suggestions);
+
+ grp = NULL;
+ for (i = ac->ac_2order; i < MB_NUM_ORDERS(ac->ac_sb); i++) {
+ if (list_empty(&sbi->s_mb_largest_free_orders[i]))
+ continue;
+ read_lock(&sbi->s_mb_largest_free_orders_locks[i]);
+ if (list_empty(&sbi->s_mb_largest_free_orders[i])) {
+ read_unlock(&sbi->s_mb_largest_free_orders_locks[i]);
+ continue;
+ }
+ grp = NULL;
+ list_for_each_entry(iter, &sbi->s_mb_largest_free_orders[i],
+ bb_largest_free_order_node) {
+ if (sbi->s_mb_stats)
+ atomic64_inc(&sbi->s_bal_cX_groups_considered[0]);
+ if (likely(ext4_mb_good_group(ac, iter->bb_group, 0))) {
+ grp = iter;
+ break;
+ }
+ }
+ read_unlock(&sbi->s_mb_largest_free_orders_locks[i]);
+ if (grp)
+ break;
+ }
+
+ if (!grp) {
+ /* Increment cr and search again */
+ *new_cr = 1;
+ } else {
+ *group = grp->bb_group;
+ ac->ac_last_optimal_group = *group;
+ ac->ac_flags |= EXT4_MB_CR0_OPTIMIZED;
+ }
+}
+
+/*
+ * Choose next group by traversing average fragment size tree. Updates *new_cr
+ * if cr lvel needs an update. Sets EXT4_MB_SEARCH_NEXT_LINEAR to indicate that
+ * the linear search should continue for one iteration since there's lock
+ * contention on the rb tree lock.
+ */
+static void ext4_mb_choose_next_group_cr1(struct ext4_allocation_context *ac,
+ int *new_cr, ext4_group_t *group, ext4_group_t ngroups)
+{
+ struct ext4_sb_info *sbi = EXT4_SB(ac->ac_sb);
+ int avg_fragment_size, best_so_far;
+ struct rb_node *node, *found;
+ struct ext4_group_info *grp;
+
+ /*
+ * If there is contention on the lock, instead of waiting for the lock
+ * to become available, just continue searching lineraly. We'll resume
+ * our rb tree search later starting at ac->ac_last_optimal_group.
+ */
+ if (!read_trylock(&sbi->s_mb_rb_lock)) {
+ ac->ac_flags |= EXT4_MB_SEARCH_NEXT_LINEAR;
+ return;
+ }
+
+ if (unlikely(ac->ac_flags & EXT4_MB_CR1_OPTIMIZED)) {
+ if (sbi->s_mb_stats)
+ atomic_inc(&sbi->s_bal_cr1_bad_suggestions);
+ /* We have found something at CR 1 in the past */
+ grp = ext4_get_group_info(ac->ac_sb, ac->ac_last_optimal_group);
+ for (found = rb_next(&grp->bb_avg_fragment_size_rb); found != NULL;
+ found = rb_next(found)) {
+ grp = rb_entry(found, struct ext4_group_info,
+ bb_avg_fragment_size_rb);
+ if (sbi->s_mb_stats)
+ atomic64_inc(&sbi->s_bal_cX_groups_considered[1]);
+ if (likely(ext4_mb_good_group(ac, grp->bb_group, 1)))
+ break;
+ }
+ goto done;
+ }
+
+ node = sbi->s_mb_avg_fragment_size_root.rb_node;
+ best_so_far = 0;
+ found = NULL;
+
+ while (node) {
+ grp = rb_entry(node, struct ext4_group_info,
+ bb_avg_fragment_size_rb);
+ avg_fragment_size = 0;
+ if (ext4_mb_good_group(ac, grp->bb_group, 1)) {
+ avg_fragment_size = grp->bb_fragments ?
+ grp->bb_free / grp->bb_fragments : 0;
+ if (!best_so_far || avg_fragment_size < best_so_far) {
+ best_so_far = avg_fragment_size;
+ found = node;
+ }
+ }
+ if (avg_fragment_size > ac->ac_g_ex.fe_len)
+ node = node->rb_right;
+ else
+ node = node->rb_left;
+ }
+
+done:
+ if (found) {
+ grp = rb_entry(found, struct ext4_group_info,
+ bb_avg_fragment_size_rb);
+ *group = grp->bb_group;
+ ac->ac_flags |= EXT4_MB_CR1_OPTIMIZED;
+ } else {
+ *new_cr = 2;
+ }
+
+ read_unlock(&sbi->s_mb_rb_lock);
+ ac->ac_last_optimal_group = *group;
+}
+
+static inline int should_optimize_scan(struct ext4_allocation_context *ac)
+{
+ if (unlikely(!test_opt2(ac->ac_sb, MB_OPTIMIZE_SCAN)))
+ return 0;
+ if (ac->ac_criteria >= 2)
+ return 0;
+ if (ext4_test_inode_flag(ac->ac_inode, EXT4_INODE_EXTENTS))
+ return 0;
+ return 1;
+}
+
+/*
+ * Return next linear group for allocation. If linear traversal should not be
+ * performed, this function just returns the same group
+ */
+static int
+next_linear_group(struct ext4_allocation_context *ac, int group, int ngroups)
+{
+ if (!should_optimize_scan(ac))
+ goto inc_and_return;
+
+ if (ac->ac_groups_linear_remaining) {
+ ac->ac_groups_linear_remaining--;
+ goto inc_and_return;
+ }
+
+ if (ac->ac_flags & EXT4_MB_SEARCH_NEXT_LINEAR) {
+ ac->ac_flags &= ~EXT4_MB_SEARCH_NEXT_LINEAR;
+ goto inc_and_return;
+ }
+
+ return group;
+inc_and_return:
+ /*
+ * Artificially restricted ngroups for non-extent
+ * files makes group > ngroups possible on first loop.
+ */
+ return group + 1 >= ngroups ? 0 : group + 1;
+}
+
+/*
+ * ext4_mb_choose_next_group: choose next group for allocation.
+ *
+ * @ac Allocation Context
+ * @new_cr This is an output parameter. If the there is no good group
+ * available at current CR level, this field is updated to indicate
+ * the new cr level that should be used.
+ * @group This is an input / output parameter. As an input it indicates the
+ * next group that the allocator intends to use for allocation. As
+ * output, this field indicates the next group that should be used as
+ * determined by the optimization functions.
+ * @ngroups Total number of groups
+ */
+static void ext4_mb_choose_next_group(struct ext4_allocation_context *ac,
+ int *new_cr, ext4_group_t *group, ext4_group_t ngroups)
+{
+ *new_cr = ac->ac_criteria;
+
+ if (!should_optimize_scan(ac) || ac->ac_groups_linear_remaining)
+ return;
+
+ if (*new_cr == 0) {
+ ext4_mb_choose_next_group_cr0(ac, new_cr, group, ngroups);
+ } else if (*new_cr == 1) {
+ ext4_mb_choose_next_group_cr1(ac, new_cr, group, ngroups);
+ } else {
+ /*
+ * TODO: For CR=2, we can arrange groups in an rb tree sorted by
+ * bb_free. But until that happens, we should never come here.
+ */
+ WARN_ON(1);
+ }
+}
+
/*
* Cache the order of the largest free extent we have available in this block
* group.
@@ -751,18 +1071,33 @@ static void ext4_mb_mark_free_simple(struct super_block *sb,
static void
mb_set_largest_free_order(struct super_block *sb, struct ext4_group_info *grp)
{
+ struct ext4_sb_info *sbi = EXT4_SB(sb);
int i;
- int bits;
+ if (test_opt2(sb, MB_OPTIMIZE_SCAN) && grp->bb_largest_free_order >= 0) {
+ write_lock(&sbi->s_mb_largest_free_orders_locks[
+ grp->bb_largest_free_order]);
+ list_del_init(&grp->bb_largest_free_order_node);
+ write_unlock(&sbi->s_mb_largest_free_orders_locks[
+ grp->bb_largest_free_order]);
+ }
grp->bb_largest_free_order = -1; /* uninit */
- bits = sb->s_blocksize_bits + 1;
- for (i = bits; i >= 0; i--) {
+ for (i = MB_NUM_ORDERS(sb) - 1; i >= 0; i--) {
if (grp->bb_counters[i] > 0) {
grp->bb_largest_free_order = i;
break;
}
}
+ if (test_opt2(sb, MB_OPTIMIZE_SCAN) &&
+ grp->bb_largest_free_order >= 0 && grp->bb_free) {
+ write_lock(&sbi->s_mb_largest_free_orders_locks[
+ grp->bb_largest_free_order]);
+ list_add_tail(&grp->bb_largest_free_order_node,
+ &sbi->s_mb_largest_free_orders[grp->bb_largest_free_order]);
+ write_unlock(&sbi->s_mb_largest_free_orders_locks[
+ grp->bb_largest_free_order]);
+ }
}
static noinline_for_stack
@@ -816,10 +1151,9 @@ void ext4_mb_generate_buddy(struct super_block *sb,
clear_bit(EXT4_GROUP_INFO_NEED_INIT_BIT, &(grp->bb_state));
period = get_cycles() - period;
- spin_lock(&sbi->s_bal_lock);
- sbi->s_mb_buddies_generated++;
- sbi->s_mb_generation_time += period;
- spin_unlock(&sbi->s_bal_lock);
+ atomic_inc(&sbi->s_mb_buddies_generated);
+ atomic64_add(period, &sbi->s_mb_generation_time);
+ mb_update_avg_fragment_size(sb, grp);
}
/* The buddy information is attached the buddy cache inode
@@ -959,7 +1293,7 @@ static int ext4_mb_init_cache(struct page *page, char *incore, gfp_t gfp)
grinfo->bb_fragments = 0;
memset(grinfo->bb_counters, 0,
sizeof(*grinfo->bb_counters) *
- (sb->s_blocksize_bits+2));
+ (MB_NUM_ORDERS(sb)));
/*
* incore got set to the group block bitmap below
*/
@@ -1519,6 +1853,7 @@ static void mb_free_blocks(struct inode *inode, struct ext4_buddy *e4b,
done:
mb_set_largest_free_order(sb, e4b->bd_info);
+ mb_update_avg_fragment_size(sb, e4b->bd_info);
mb_check_buddy(e4b);
}
@@ -1655,6 +1990,7 @@ static int mb_mark_used(struct ext4_buddy *e4b, struct ext4_free_extent *ex)
}
mb_set_largest_free_order(e4b->bd_sb, e4b->bd_info);
+ mb_update_avg_fragment_size(e4b->bd_sb, e4b->bd_info);
ext4_set_bits(e4b->bd_bitmap, ex->fe_start, len0);
mb_check_buddy(e4b);
@@ -1930,7 +2266,7 @@ void ext4_mb_simple_scan_group(struct ext4_allocation_context *ac,
int max;
BUG_ON(ac->ac_2order <= 0);
- for (i = ac->ac_2order; i <= sb->s_blocksize_bits + 1; i++) {
+ for (i = ac->ac_2order; i < MB_NUM_ORDERS(sb); i++) {
if (grp->bb_counters[i] == 0)
continue;
@@ -2109,7 +2445,7 @@ static bool ext4_mb_good_group(struct ext4_allocation_context *ac,
if (free < ac->ac_g_ex.fe_len)
return false;
- if (ac->ac_2order > ac->ac_sb->s_blocksize_bits+1)
+ if (ac->ac_2order >= MB_NUM_ORDERS(ac->ac_sb))
return true;
if (grp->bb_largest_free_order < ac->ac_2order)
@@ -2148,6 +2484,8 @@ static int ext4_mb_good_group_nolock(struct ext4_allocation_context *ac,
ext4_grpblk_t free;
int ret = 0;
+ if (sbi->s_mb_stats)
+ atomic64_inc(&sbi->s_bal_cX_groups_considered[ac->ac_criteria]);
if (should_lock)
ext4_lock_group(sb, group);
free = grp->bb_free;
@@ -2315,13 +2653,13 @@ ext4_mb_regular_allocator(struct ext4_allocation_context *ac)
* We also support searching for power-of-two requests only for
* requests upto maximum buddy size we have constructed.
*/
- if (i >= sbi->s_mb_order2_reqs && i <= sb->s_blocksize_bits + 2) {
+ if (i >= sbi->s_mb_order2_reqs && i <= MB_NUM_ORDERS(sb)) {
/*
* This should tell if fe_len is exactly power of 2
*/
if ((ac->ac_g_ex.fe_len & (~(1 << (i - 1)))) == 0)
ac->ac_2order = array_index_nospec(i - 1,
- sb->s_blocksize_bits + 2);
+ MB_NUM_ORDERS(sb));
}
/* if stream allocation is enabled, use global goal */
@@ -2347,17 +2685,21 @@ repeat:
* from the goal value specified
*/
group = ac->ac_g_ex.fe_group;
+ ac->ac_last_optimal_group = group;
+ ac->ac_groups_linear_remaining = sbi->s_mb_max_linear_groups;
prefetch_grp = group;
- for (i = 0; i < ngroups; group++, i++) {
- int ret = 0;
+ for (i = 0; i < ngroups; group = next_linear_group(ac, group, ngroups),
+ i++) {
+ int ret = 0, new_cr;
+
cond_resched();
- /*
- * Artificially restricted ngroups for non-extent
- * files makes group > ngroups possible on first loop.
- */
- if (group >= ngroups)
- group = 0;
+
+ ext4_mb_choose_next_group(ac, &new_cr, &group, ngroups);
+ if (new_cr != cr) {
+ cr = new_cr;
+ goto repeat;
+ }
/*
* Batch reads of the block allocation bitmaps
@@ -2422,6 +2764,9 @@ repeat:
if (ac->ac_status != AC_STATUS_CONTINUE)
break;
}
+ /* Processed all groups and haven't found blocks */
+ if (sbi->s_mb_stats && i == ngroups)
+ atomic64_inc(&sbi->s_bal_cX_failed[cr]);
}
if (ac->ac_b_ex.fe_len > 0 && ac->ac_status != AC_STATUS_FOUND &&
@@ -2451,6 +2796,9 @@ repeat:
goto repeat;
}
}
+
+ if (sbi->s_mb_stats && ac->ac_status == AC_STATUS_FOUND)
+ atomic64_inc(&sbi->s_bal_cX_hits[ac->ac_criteria]);
out:
if (!err && ac->ac_status != AC_STATUS_FOUND && first_err)
err = first_err;
@@ -2550,6 +2898,157 @@ const struct seq_operations ext4_mb_seq_groups_ops = {
.show = ext4_mb_seq_groups_show,
};
+int ext4_seq_mb_stats_show(struct seq_file *seq, void *offset)
+{
+ struct super_block *sb = (struct super_block *)seq->private;
+ struct ext4_sb_info *sbi = EXT4_SB(sb);
+
+ seq_puts(seq, "mballoc:\n");
+ if (!sbi->s_mb_stats) {
+ seq_puts(seq, "\tmb stats collection turned off.\n");
+ seq_puts(seq, "\tTo enable, please write \"1\" to sysfs file mb_stats.\n");
+ return 0;
+ }
+ seq_printf(seq, "\treqs: %u\n", atomic_read(&sbi->s_bal_reqs));
+ seq_printf(seq, "\tsuccess: %u\n", atomic_read(&sbi->s_bal_success));
+
+ seq_printf(seq, "\tgroups_scanned: %u\n", atomic_read(&sbi->s_bal_groups_scanned));
+
+ seq_puts(seq, "\tcr0_stats:\n");
+ seq_printf(seq, "\t\thits: %llu\n", atomic64_read(&sbi->s_bal_cX_hits[0]));
+ seq_printf(seq, "\t\tgroups_considered: %llu\n",
+ atomic64_read(&sbi->s_bal_cX_groups_considered[0]));
+ seq_printf(seq, "\t\tuseless_loops: %llu\n",
+ atomic64_read(&sbi->s_bal_cX_failed[0]));
+ seq_printf(seq, "\t\tbad_suggestions: %u\n",
+ atomic_read(&sbi->s_bal_cr0_bad_suggestions));
+
+ seq_puts(seq, "\tcr1_stats:\n");
+ seq_printf(seq, "\t\thits: %llu\n", atomic64_read(&sbi->s_bal_cX_hits[1]));
+ seq_printf(seq, "\t\tgroups_considered: %llu\n",
+ atomic64_read(&sbi->s_bal_cX_groups_considered[1]));
+ seq_printf(seq, "\t\tuseless_loops: %llu\n",
+ atomic64_read(&sbi->s_bal_cX_failed[1]));
+ seq_printf(seq, "\t\tbad_suggestions: %u\n",
+ atomic_read(&sbi->s_bal_cr1_bad_suggestions));
+
+ seq_puts(seq, "\tcr2_stats:\n");
+ seq_printf(seq, "\t\thits: %llu\n", atomic64_read(&sbi->s_bal_cX_hits[2]));
+ seq_printf(seq, "\t\tgroups_considered: %llu\n",
+ atomic64_read(&sbi->s_bal_cX_groups_considered[2]));
+ seq_printf(seq, "\t\tuseless_loops: %llu\n",
+ atomic64_read(&sbi->s_bal_cX_failed[2]));
+
+ seq_puts(seq, "\tcr3_stats:\n");
+ seq_printf(seq, "\t\thits: %llu\n", atomic64_read(&sbi->s_bal_cX_hits[3]));
+ seq_printf(seq, "\t\tgroups_considered: %llu\n",
+ atomic64_read(&sbi->s_bal_cX_groups_considered[3]));
+ seq_printf(seq, "\t\tuseless_loops: %llu\n",
+ atomic64_read(&sbi->s_bal_cX_failed[3]));
+ seq_printf(seq, "\textents_scanned: %u\n", atomic_read(&sbi->s_bal_ex_scanned));
+ seq_printf(seq, "\t\tgoal_hits: %u\n", atomic_read(&sbi->s_bal_goals));
+ seq_printf(seq, "\t\t2^n_hits: %u\n", atomic_read(&sbi->s_bal_2orders));
+ seq_printf(seq, "\t\tbreaks: %u\n", atomic_read(&sbi->s_bal_breaks));
+ seq_printf(seq, "\t\tlost: %u\n", atomic_read(&sbi->s_mb_lost_chunks));
+
+ seq_printf(seq, "\tbuddies_generated: %u/%u\n",
+ atomic_read(&sbi->s_mb_buddies_generated),
+ ext4_get_groups_count(sb));
+ seq_printf(seq, "\tbuddies_time_used: %llu\n",
+ atomic64_read(&sbi->s_mb_generation_time));
+ seq_printf(seq, "\tpreallocated: %u\n",
+ atomic_read(&sbi->s_mb_preallocated));
+ seq_printf(seq, "\tdiscarded: %u\n",
+ atomic_read(&sbi->s_mb_discarded));
+ return 0;
+}
+
+static void *ext4_mb_seq_structs_summary_start(struct seq_file *seq, loff_t *pos)
+{
+ struct super_block *sb = PDE_DATA(file_inode(seq->file));
+ unsigned long position;
+
+ read_lock(&EXT4_SB(sb)->s_mb_rb_lock);
+
+ if (*pos < 0 || *pos >= MB_NUM_ORDERS(sb) + 1)
+ return NULL;
+ position = *pos + 1;
+ return (void *) ((unsigned long) position);
+}
+
+static void *ext4_mb_seq_structs_summary_next(struct seq_file *seq, void *v, loff_t *pos)
+{
+ struct super_block *sb = PDE_DATA(file_inode(seq->file));
+ unsigned long position;
+
+ ++*pos;
+ if (*pos < 0 || *pos >= MB_NUM_ORDERS(sb) + 1)
+ return NULL;
+ position = *pos + 1;
+ return (void *) ((unsigned long) position);
+}
+
+static int ext4_mb_seq_structs_summary_show(struct seq_file *seq, void *v)
+{
+ struct super_block *sb = PDE_DATA(file_inode(seq->file));
+ struct ext4_sb_info *sbi = EXT4_SB(sb);
+ unsigned long position = ((unsigned long) v);
+ struct ext4_group_info *grp;
+ struct rb_node *n;
+ unsigned int count, min, max;
+
+ position--;
+ if (position >= MB_NUM_ORDERS(sb)) {
+ seq_puts(seq, "fragment_size_tree:\n");
+ n = rb_first(&sbi->s_mb_avg_fragment_size_root);
+ if (!n) {
+ seq_puts(seq, "\ttree_min: 0\n\ttree_max: 0\n\ttree_nodes: 0\n");
+ return 0;
+ }
+ grp = rb_entry(n, struct ext4_group_info, bb_avg_fragment_size_rb);
+ min = grp->bb_fragments ? grp->bb_free / grp->bb_fragments : 0;
+ count = 1;
+ while (rb_next(n)) {
+ count++;
+ n = rb_next(n);
+ }
+ grp = rb_entry(n, struct ext4_group_info, bb_avg_fragment_size_rb);
+ max = grp->bb_fragments ? grp->bb_free / grp->bb_fragments : 0;
+
+ seq_printf(seq, "\ttree_min: %u\n\ttree_max: %u\n\ttree_nodes: %u\n",
+ min, max, count);
+ return 0;
+ }
+
+ if (position == 0) {
+ seq_printf(seq, "optimize_scan: %d\n",
+ test_opt2(sb, MB_OPTIMIZE_SCAN) ? 1 : 0);
+ seq_puts(seq, "max_free_order_lists:\n");
+ }
+ count = 0;
+ list_for_each_entry(grp, &sbi->s_mb_largest_free_orders[position],
+ bb_largest_free_order_node)
+ count++;
+ seq_printf(seq, "\tlist_order_%u_groups: %u\n",
+ (unsigned int)position, count);
+
+ return 0;
+}
+
+static void ext4_mb_seq_structs_summary_stop(struct seq_file *seq, void *v)
+{
+ struct super_block *sb = PDE_DATA(file_inode(seq->file));
+
+ read_unlock(&EXT4_SB(sb)->s_mb_rb_lock);
+}
+
+const struct seq_operations ext4_mb_seq_structs_summary_ops = {
+ .start = ext4_mb_seq_structs_summary_start,
+ .next = ext4_mb_seq_structs_summary_next,
+ .stop = ext4_mb_seq_structs_summary_stop,
+ .show = ext4_mb_seq_structs_summary_show,
+};
+
static struct kmem_cache *get_groupinfo_cache(int blocksize_bits)
{
int cache_index = blocksize_bits - EXT4_MIN_BLOCK_LOG_SIZE;
@@ -2590,7 +3089,7 @@ int ext4_mb_alloc_groupinfo(struct super_block *sb, ext4_group_t ngroups)
sbi->s_group_info_size = size / sizeof(*sbi->s_group_info);
if (old_groupinfo)
ext4_kvfree_array_rcu(old_groupinfo);
- ext4_debug("allocated s_groupinfo array for %d meta_bg's\n",
+ ext4_debug("allocated s_groupinfo array for %d meta_bg's\n",
sbi->s_group_info_size);
return 0;
}
@@ -2652,7 +3151,10 @@ int ext4_mb_add_groupinfo(struct super_block *sb, ext4_group_t group,
INIT_LIST_HEAD(&meta_group_info[i]->bb_prealloc_list);
init_rwsem(&meta_group_info[i]->alloc_sem);
meta_group_info[i]->bb_free_root = RB_ROOT;
+ INIT_LIST_HEAD(&meta_group_info[i]->bb_largest_free_order_node);
+ RB_CLEAR_NODE(&meta_group_info[i]->bb_avg_fragment_size_rb);
meta_group_info[i]->bb_largest_free_order = -1; /* uninit */
+ meta_group_info[i]->bb_group = group;
mb_group_bb_bitmap_alloc(sb, meta_group_info[i], group);
return 0;
@@ -2709,8 +3211,15 @@ static int ext4_mb_init_backend(struct super_block *sb)
}
if (ext4_has_feature_flex_bg(sb)) {
- /* a single flex group is supposed to be read by a single IO */
- sbi->s_mb_prefetch = min(1 << sbi->s_es->s_log_groups_per_flex,
+ /* a single flex group is supposed to be read by a single IO.
+ * 2 ^ s_log_groups_per_flex != UINT_MAX as s_mb_prefetch is
+ * unsigned integer, so the maximum shift is 32.
+ */
+ if (sbi->s_es->s_log_groups_per_flex >= 32) {
+ ext4_msg(sb, KERN_ERR, "too many log groups per flexible block group");
+ goto err_freesgi;
+ }
+ sbi->s_mb_prefetch = min_t(uint, 1 << sbi->s_es->s_log_groups_per_flex,
BLK_MAX_SEGMENT_SIZE >> (sb->s_blocksize_bits - 9));
sbi->s_mb_prefetch *= 8; /* 8 prefetch IOs in flight at most */
} else {
@@ -2806,7 +3315,7 @@ int ext4_mb_init(struct super_block *sb)
unsigned max;
int ret;
- i = (sb->s_blocksize_bits + 2) * sizeof(*sbi->s_mb_offsets);
+ i = MB_NUM_ORDERS(sb) * sizeof(*sbi->s_mb_offsets);
sbi->s_mb_offsets = kmalloc(i, GFP_KERNEL);
if (sbi->s_mb_offsets == NULL) {
@@ -2814,7 +3323,7 @@ int ext4_mb_init(struct super_block *sb)
goto out;
}
- i = (sb->s_blocksize_bits + 2) * sizeof(*sbi->s_mb_maxs);
+ i = MB_NUM_ORDERS(sb) * sizeof(*sbi->s_mb_maxs);
sbi->s_mb_maxs = kmalloc(i, GFP_KERNEL);
if (sbi->s_mb_maxs == NULL) {
ret = -ENOMEM;
@@ -2840,10 +3349,30 @@ int ext4_mb_init(struct super_block *sb)
offset_incr = offset_incr >> 1;
max = max >> 1;
i++;
- } while (i <= sb->s_blocksize_bits + 1);
+ } while (i < MB_NUM_ORDERS(sb));
+
+ sbi->s_mb_avg_fragment_size_root = RB_ROOT;
+ sbi->s_mb_largest_free_orders =
+ kmalloc_array(MB_NUM_ORDERS(sb), sizeof(struct list_head),
+ GFP_KERNEL);
+ if (!sbi->s_mb_largest_free_orders) {
+ ret = -ENOMEM;
+ goto out;
+ }
+ sbi->s_mb_largest_free_orders_locks =
+ kmalloc_array(MB_NUM_ORDERS(sb), sizeof(rwlock_t),
+ GFP_KERNEL);
+ if (!sbi->s_mb_largest_free_orders_locks) {
+ ret = -ENOMEM;
+ goto out;
+ }
+ for (i = 0; i < MB_NUM_ORDERS(sb); i++) {
+ INIT_LIST_HEAD(&sbi->s_mb_largest_free_orders[i]);
+ rwlock_init(&sbi->s_mb_largest_free_orders_locks[i]);
+ }
+ rwlock_init(&sbi->s_mb_rb_lock);
spin_lock_init(&sbi->s_md_lock);
- spin_lock_init(&sbi->s_bal_lock);
sbi->s_mb_free_pending = 0;
INIT_LIST_HEAD(&sbi->s_freed_data_list);
@@ -2894,6 +3423,10 @@ int ext4_mb_init(struct super_block *sb)
spin_lock_init(&lg->lg_prealloc_lock);
}
+ if (blk_queue_nonrot(bdev_get_queue(sb->s_bdev)))
+ sbi->s_mb_max_linear_groups = 0;
+ else
+ sbi->s_mb_max_linear_groups = MB_DEFAULT_LINEAR_LIMIT;
/* init file for buddy data */
ret = ext4_mb_init_backend(sb);
if (ret != 0)
@@ -2905,6 +3438,8 @@ out_free_locality_groups:
free_percpu(sbi->s_locality_groups);
sbi->s_locality_groups = NULL;
out:
+ kfree(sbi->s_mb_largest_free_orders);
+ kfree(sbi->s_mb_largest_free_orders_locks);
kfree(sbi->s_mb_offsets);
sbi->s_mb_offsets = NULL;
kfree(sbi->s_mb_maxs);
@@ -2961,6 +3496,8 @@ int ext4_mb_release(struct super_block *sb)
kvfree(group_info);
rcu_read_unlock();
}
+ kfree(sbi->s_mb_largest_free_orders);
+ kfree(sbi->s_mb_largest_free_orders_locks);
kfree(sbi->s_mb_offsets);
kfree(sbi->s_mb_maxs);
iput(sbi->s_buddy_cache);
@@ -2971,17 +3508,18 @@ int ext4_mb_release(struct super_block *sb)
atomic_read(&sbi->s_bal_reqs),
atomic_read(&sbi->s_bal_success));
ext4_msg(sb, KERN_INFO,
- "mballoc: %u extents scanned, %u goal hits, "
+ "mballoc: %u extents scanned, %u groups scanned, %u goal hits, "
"%u 2^N hits, %u breaks, %u lost",
atomic_read(&sbi->s_bal_ex_scanned),
+ atomic_read(&sbi->s_bal_groups_scanned),
atomic_read(&sbi->s_bal_goals),
atomic_read(&sbi->s_bal_2orders),
atomic_read(&sbi->s_bal_breaks),
atomic_read(&sbi->s_mb_lost_chunks));
ext4_msg(sb, KERN_INFO,
- "mballoc: %lu generated and it took %Lu",
- sbi->s_mb_buddies_generated,
- sbi->s_mb_generation_time);
+ "mballoc: %u generated and it took %llu",
+ atomic_read(&sbi->s_mb_buddies_generated),
+ atomic64_read(&sbi->s_mb_generation_time));
ext4_msg(sb, KERN_INFO,
"mballoc: %u preallocated, %u discarded",
atomic_read(&sbi->s_mb_preallocated),
@@ -3576,12 +4114,13 @@ static void ext4_mb_collect_stats(struct ext4_allocation_context *ac)
{
struct ext4_sb_info *sbi = EXT4_SB(ac->ac_sb);
- if (sbi->s_mb_stats && ac->ac_g_ex.fe_len > 1) {
+ if (sbi->s_mb_stats && ac->ac_g_ex.fe_len >= 1) {
atomic_inc(&sbi->s_bal_reqs);
atomic_add(ac->ac_b_ex.fe_len, &sbi->s_bal_allocated);
if (ac->ac_b_ex.fe_len >= ac->ac_o_ex.fe_len)
atomic_inc(&sbi->s_bal_success);
atomic_add(ac->ac_found, &sbi->s_bal_ex_scanned);
+ atomic_add(ac->ac_groups_scanned, &sbi->s_bal_groups_scanned);
if (ac->ac_g_ex.fe_start == ac->ac_b_ex.fe_start &&
ac->ac_g_ex.fe_group == ac->ac_b_ex.fe_group)
atomic_inc(&sbi->s_bal_goals);
diff --git a/fs/ext4/mballoc.h b/fs/ext4/mballoc.h
index e75b4749aa1c..39da92ceabf8 100644
--- a/fs/ext4/mballoc.h
+++ b/fs/ext4/mballoc.h
@@ -59,7 +59,7 @@
* by the stream allocator, which purpose is to pack requests
* as close each to other as possible to produce smooth I/O traffic
* We use locality group prealloc space for stream request.
- * We can tune the same via /proc/fs/ext4/<parition>/stream_req
+ * We can tune the same via /proc/fs/ext4/<partition>/stream_req
*/
#define MB_DEFAULT_STREAM_THRESHOLD 16 /* 64K */
@@ -78,6 +78,23 @@
*/
#define MB_DEFAULT_MAX_INODE_PREALLOC 512
+/*
+ * Number of groups to search linearly before performing group scanning
+ * optimization.
+ */
+#define MB_DEFAULT_LINEAR_LIMIT 4
+
+/*
+ * Minimum number of groups that should be present in the file system to perform
+ * group scanning optimizations.
+ */
+#define MB_DEFAULT_LINEAR_SCAN_THRESHOLD 16
+
+/*
+ * Number of valid buddy orders
+ */
+#define MB_NUM_ORDERS(sb) ((sb)->s_blocksize_bits + 2)
+
struct ext4_free_data {
/* this links the free block information from sb_info */
struct list_head efd_list;
@@ -161,11 +178,14 @@ struct ext4_allocation_context {
/* copy of the best found extent taken before preallocation efforts */
struct ext4_free_extent ac_f_ex;
+ ext4_group_t ac_last_optimal_group;
+ __u32 ac_groups_considered;
+ __u32 ac_flags; /* allocation hints */
__u16 ac_groups_scanned;
+ __u16 ac_groups_linear_remaining;
__u16 ac_found;
__u16 ac_tail;
__u16 ac_buddy;
- __u16 ac_flags; /* allocation hints */
__u8 ac_status;
__u8 ac_criteria;
__u8 ac_2order; /* if request is to allocate 2^N blocks and
diff --git a/fs/ext4/migrate.c b/fs/ext4/migrate.c
index c5e3fc998211..7e0b4f81c6c0 100644
--- a/fs/ext4/migrate.c
+++ b/fs/ext4/migrate.c
@@ -32,7 +32,7 @@ static int finish_range(handle_t *handle, struct inode *inode,
newext.ee_block = cpu_to_le32(lb->first_block);
newext.ee_len = cpu_to_le16(lb->last_block - lb->first_block + 1);
ext4_ext_store_pblock(&newext, lb->first_pblock);
- /* Locking only for convinience since we are operating on temp inode */
+ /* Locking only for convenience since we are operating on temp inode */
down_write(&EXT4_I(inode)->i_data_sem);
path = ext4_find_extent(inode, lb->first_block, NULL, 0);
if (IS_ERR(path)) {
@@ -43,8 +43,8 @@ static int finish_range(handle_t *handle, struct inode *inode,
/*
* Calculate the credit needed to inserting this extent
- * Since we are doing this in loop we may accumalate extra
- * credit. But below we try to not accumalate too much
+ * Since we are doing this in loop we may accumulate extra
+ * credit. But below we try to not accumulate too much
* of them by restarting the journal.
*/
needed = ext4_ext_calc_credits_for_single_extent(inode,
diff --git a/fs/ext4/mmp.c b/fs/ext4/mmp.c
index 795c3ff2907c..68fbeedd627b 100644
--- a/fs/ext4/mmp.c
+++ b/fs/ext4/mmp.c
@@ -56,7 +56,7 @@ static int write_mmp_block(struct super_block *sb, struct buffer_head *bh)
wait_on_buffer(bh);
sb_end_write(sb);
if (unlikely(!buffer_uptodate(bh)))
- return 1;
+ return -EIO;
return 0;
}
diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c
index 686bf982c84e..afb9d05a99ba 100644
--- a/fs/ext4/namei.c
+++ b/fs/ext4/namei.c
@@ -280,9 +280,11 @@ static int dx_make_map(struct inode *dir, struct ext4_dir_entry_2 *de,
unsigned blocksize, struct dx_hash_info *hinfo,
struct dx_map_entry map[]);
static void dx_sort_map(struct dx_map_entry *map, unsigned count);
-static struct ext4_dir_entry_2 *dx_move_dirents(char *from, char *to,
- struct dx_map_entry *offsets, int count, unsigned blocksize);
-static struct ext4_dir_entry_2* dx_pack_dirents(char *base, unsigned blocksize);
+static struct ext4_dir_entry_2 *dx_move_dirents(struct inode *dir, char *from,
+ char *to, struct dx_map_entry *offsets,
+ int count, unsigned int blocksize);
+static struct ext4_dir_entry_2 *dx_pack_dirents(struct inode *dir, char *base,
+ unsigned int blocksize);
static void dx_insert_block(struct dx_frame *frame,
u32 hash, ext4_lblk_t block);
static int ext4_htree_next_block(struct inode *dir, __u32 hash,
@@ -574,8 +576,9 @@ static inline void dx_set_limit(struct dx_entry *entries, unsigned value)
static inline unsigned dx_root_limit(struct inode *dir, unsigned infosize)
{
- unsigned entry_space = dir->i_sb->s_blocksize - EXT4_DIR_REC_LEN(1) -
- EXT4_DIR_REC_LEN(2) - infosize;
+ unsigned int entry_space = dir->i_sb->s_blocksize -
+ ext4_dir_rec_len(1, NULL) -
+ ext4_dir_rec_len(2, NULL) - infosize;
if (ext4_has_metadata_csum(dir->i_sb))
entry_space -= sizeof(struct dx_tail);
@@ -584,7 +587,8 @@ static inline unsigned dx_root_limit(struct inode *dir, unsigned infosize)
static inline unsigned dx_node_limit(struct inode *dir)
{
- unsigned entry_space = dir->i_sb->s_blocksize - EXT4_DIR_REC_LEN(0);
+ unsigned int entry_space = dir->i_sb->s_blocksize -
+ ext4_dir_rec_len(0, dir);
if (ext4_has_metadata_csum(dir->i_sb))
entry_space -= sizeof(struct dx_tail);
@@ -673,7 +677,10 @@ static struct stats dx_show_leaf(struct inode *dir,
name = fname_crypto_str.name;
len = fname_crypto_str.len;
}
- ext4fs_dirhash(dir, de->name,
+ if (IS_CASEFOLDED(dir))
+ h.hash = EXT4_DIRENT_HASH(de);
+ else
+ ext4fs_dirhash(dir, de->name,
de->name_len, &h);
printk("%*.s:(E)%x.%u ", len, name,
h.hash, (unsigned) ((char *) de
@@ -689,7 +696,7 @@ static struct stats dx_show_leaf(struct inode *dir,
(unsigned) ((char *) de - base));
#endif
}
- space += EXT4_DIR_REC_LEN(de->name_len);
+ space += ext4_dir_rec_len(de->name_len, dir);
names++;
}
de = ext4_next_entry(de, size);
@@ -784,18 +791,34 @@ dx_probe(struct ext4_filename *fname, struct inode *dir,
root = (struct dx_root *) frame->bh->b_data;
if (root->info.hash_version != DX_HASH_TEA &&
root->info.hash_version != DX_HASH_HALF_MD4 &&
- root->info.hash_version != DX_HASH_LEGACY) {
+ root->info.hash_version != DX_HASH_LEGACY &&
+ root->info.hash_version != DX_HASH_SIPHASH) {
ext4_warning_inode(dir, "Unrecognised inode hash code %u",
root->info.hash_version);
goto fail;
}
+ if (ext4_hash_in_dirent(dir)) {
+ if (root->info.hash_version != DX_HASH_SIPHASH) {
+ ext4_warning_inode(dir,
+ "Hash in dirent, but hash is not SIPHASH");
+ goto fail;
+ }
+ } else {
+ if (root->info.hash_version == DX_HASH_SIPHASH) {
+ ext4_warning_inode(dir,
+ "Hash code is SIPHASH, but hash not in dirent");
+ goto fail;
+ }
+ }
if (fname)
hinfo = &fname->hinfo;
hinfo->hash_version = root->info.hash_version;
if (hinfo->hash_version <= DX_HASH_TEA)
hinfo->hash_version += EXT4_SB(dir->i_sb)->s_hash_unsigned;
hinfo->seed = EXT4_SB(dir->i_sb)->s_hash_seed;
- if (fname && fname_name(fname))
+ /* hash is already computed for encrypted casefolded directory */
+ if (fname && fname_name(fname) &&
+ !(IS_ENCRYPTED(dir) && IS_CASEFOLDED(dir)))
ext4fs_dirhash(dir, fname_name(fname), fname_len(fname), hinfo);
hash = hinfo->hash;
@@ -956,7 +979,7 @@ static int ext4_htree_next_block(struct inode *dir, __u32 hash,
* If the hash is 1, then continue only if the next page has a
* continuation hash of any value. This is used for readdir
* handling. Otherwise, check to see if the hash matches the
- * desired contiuation hash. If it doesn't, return since
+ * desired continuation hash. If it doesn't, return since
* there's no point to read in the successive index pages.
*/
bhash = dx_get_hash(p->at);
@@ -997,6 +1020,7 @@ static int htree_dirblock_to_tree(struct file *dir_file,
struct ext4_dir_entry_2 *de, *top;
int err = 0, count = 0;
struct fscrypt_str fname_crypto_str = FSTR_INIT(NULL, 0), tmp_str;
+ int csum = ext4_has_metadata_csum(dir->i_sb);
dxtrace(printk(KERN_INFO "In htree dirblock_to_tree: block %lu\n",
(unsigned long)block));
@@ -1005,9 +1029,11 @@ static int htree_dirblock_to_tree(struct file *dir_file,
return PTR_ERR(bh);
de = (struct ext4_dir_entry_2 *) bh->b_data;
+ /* csum entries are not larger in the casefolded encrypted case */
top = (struct ext4_dir_entry_2 *) ((char *) de +
dir->i_sb->s_blocksize -
- EXT4_DIR_REC_LEN(0));
+ ext4_dir_rec_len(0,
+ csum ? NULL : dir));
/* Check if the directory is encrypted */
if (IS_ENCRYPTED(dir)) {
err = fscrypt_prepare_readdir(dir);
@@ -1031,7 +1057,17 @@ static int htree_dirblock_to_tree(struct file *dir_file,
/* silently ignore the rest of the block */
break;
}
- ext4fs_dirhash(dir, de->name, de->name_len, hinfo);
+ if (ext4_hash_in_dirent(dir)) {
+ if (de->name_len && de->inode) {
+ hinfo->hash = EXT4_DIRENT_HASH(de);
+ hinfo->minor_hash = EXT4_DIRENT_MINOR_HASH(de);
+ } else {
+ hinfo->hash = 0;
+ hinfo->minor_hash = 0;
+ }
+ } else {
+ ext4fs_dirhash(dir, de->name, de->name_len, hinfo);
+ }
if ((hinfo->hash < start_hash) ||
((hinfo->hash == start_hash) &&
(hinfo->minor_hash < start_minor_hash)))
@@ -1100,7 +1136,11 @@ int ext4_htree_fill_tree(struct file *dir_file, __u32 start_hash,
start_hash, start_minor_hash));
dir = file_inode(dir_file);
if (!(ext4_test_inode_flag(dir, EXT4_INODE_INDEX))) {
- hinfo.hash_version = EXT4_SB(dir->i_sb)->s_def_hash_version;
+ if (ext4_hash_in_dirent(dir))
+ hinfo.hash_version = DX_HASH_SIPHASH;
+ else
+ hinfo.hash_version =
+ EXT4_SB(dir->i_sb)->s_def_hash_version;
if (hinfo.hash_version <= DX_HASH_TEA)
hinfo.hash_version +=
EXT4_SB(dir->i_sb)->s_hash_unsigned;
@@ -1218,7 +1258,10 @@ static int dx_make_map(struct inode *dir, struct ext4_dir_entry_2 *de,
while ((char *) de < base + blocksize) {
if (de->name_len && de->inode) {
- ext4fs_dirhash(dir, de->name, de->name_len, &h);
+ if (ext4_hash_in_dirent(dir))
+ h.hash = EXT4_DIRENT_HASH(de);
+ else
+ ext4fs_dirhash(dir, de->name, de->name_len, &h);
map_tail--;
map_tail->hash = h.hash;
map_tail->offs = ((char *) de - base)>>2;
@@ -1282,47 +1325,65 @@ static void dx_insert_block(struct dx_frame *frame, u32 hash, ext4_lblk_t block)
* Returns: 0 if the directory entry matches, more than 0 if it
* doesn't match or less than zero on error.
*/
-int ext4_ci_compare(const struct inode *parent, const struct qstr *name,
- const struct qstr *entry, bool quick)
+static int ext4_ci_compare(const struct inode *parent, const struct qstr *name,
+ u8 *de_name, size_t de_name_len, bool quick)
{
const struct super_block *sb = parent->i_sb;
const struct unicode_map *um = sb->s_encoding;
+ struct fscrypt_str decrypted_name = FSTR_INIT(NULL, de_name_len);
+ struct qstr entry = QSTR_INIT(de_name, de_name_len);
int ret;
+ if (IS_ENCRYPTED(parent)) {
+ const struct fscrypt_str encrypted_name =
+ FSTR_INIT(de_name, de_name_len);
+
+ decrypted_name.name = kmalloc(de_name_len, GFP_KERNEL);
+ if (!decrypted_name.name)
+ return -ENOMEM;
+ ret = fscrypt_fname_disk_to_usr(parent, 0, 0, &encrypted_name,
+ &decrypted_name);
+ if (ret < 0)
+ goto out;
+ entry.name = decrypted_name.name;
+ entry.len = decrypted_name.len;
+ }
+
if (quick)
- ret = utf8_strncasecmp_folded(um, name, entry);
+ ret = utf8_strncasecmp_folded(um, name, &entry);
else
- ret = utf8_strncasecmp(um, name, entry);
-
+ ret = utf8_strncasecmp(um, name, &entry);
if (ret < 0) {
/* Handle invalid character sequence as either an error
* or as an opaque byte sequence.
*/
if (sb_has_strict_encoding(sb))
- return -EINVAL;
-
- if (name->len != entry->len)
- return 1;
-
- return !!memcmp(name->name, entry->name, name->len);
+ ret = -EINVAL;
+ else if (name->len != entry.len)
+ ret = 1;
+ else
+ ret = !!memcmp(name->name, entry.name, entry.len);
}
-
+out:
+ kfree(decrypted_name.name);
return ret;
}
-void ext4_fname_setup_ci_filename(struct inode *dir, const struct qstr *iname,
- struct fscrypt_str *cf_name)
+int ext4_fname_setup_ci_filename(struct inode *dir, const struct qstr *iname,
+ struct ext4_filename *name)
{
+ struct fscrypt_str *cf_name = &name->cf_name;
+ struct dx_hash_info *hinfo = &name->hinfo;
int len;
if (!IS_CASEFOLDED(dir) || !dir->i_sb->s_encoding) {
cf_name->name = NULL;
- return;
+ return 0;
}
cf_name->name = kmalloc(EXT4_NAME_LEN, GFP_NOFS);
if (!cf_name->name)
- return;
+ return -ENOMEM;
len = utf8_casefold(dir->i_sb->s_encoding,
iname, cf_name->name,
@@ -1330,10 +1391,18 @@ void ext4_fname_setup_ci_filename(struct inode *dir, const struct qstr *iname,
if (len <= 0) {
kfree(cf_name->name);
cf_name->name = NULL;
- return;
}
cf_name->len = (unsigned) len;
+ if (!IS_ENCRYPTED(dir))
+ return 0;
+ hinfo->hash_version = DX_HASH_SIPHASH;
+ hinfo->seed = NULL;
+ if (cf_name->name)
+ ext4fs_dirhash(dir, cf_name->name, cf_name->len, hinfo);
+ else
+ ext4fs_dirhash(dir, iname->name, iname->len, hinfo);
+ return 0;
}
#endif
@@ -1342,14 +1411,11 @@ void ext4_fname_setup_ci_filename(struct inode *dir, const struct qstr *iname,
*
* Return: %true if the directory entry matches, otherwise %false.
*/
-static inline bool ext4_match(const struct inode *parent,
+static bool ext4_match(struct inode *parent,
const struct ext4_filename *fname,
- const struct ext4_dir_entry_2 *de)
+ struct ext4_dir_entry_2 *de)
{
struct fscrypt_name f;
-#ifdef CONFIG_UNICODE
- const struct qstr entry = {.name = de->name, .len = de->name_len};
-#endif
if (!de->inode)
return false;
@@ -1365,10 +1431,19 @@ static inline bool ext4_match(const struct inode *parent,
if (fname->cf_name.name) {
struct qstr cf = {.name = fname->cf_name.name,
.len = fname->cf_name.len};
- return !ext4_ci_compare(parent, &cf, &entry, true);
+ if (IS_ENCRYPTED(parent)) {
+ if (fname->hinfo.hash != EXT4_DIRENT_HASH(de) ||
+ fname->hinfo.minor_hash !=
+ EXT4_DIRENT_MINOR_HASH(de)) {
+
+ return 0;
+ }
+ }
+ return !ext4_ci_compare(parent, &cf, de->name,
+ de->name_len, true);
}
- return !ext4_ci_compare(parent, fname->usr_fname, &entry,
- false);
+ return !ext4_ci_compare(parent, fname->usr_fname, de->name,
+ de->name_len, false);
}
#endif
@@ -1739,11 +1814,10 @@ static struct dentry *ext4_lookup(struct inode *dir, struct dentry *dentry, unsi
struct dentry *ext4_get_parent(struct dentry *child)
{
__u32 ino;
- static const struct qstr dotdot = QSTR_INIT("..", 2);
struct ext4_dir_entry_2 * de;
struct buffer_head *bh;
- bh = ext4_find_entry(d_inode(child), &dotdot, &de, NULL);
+ bh = ext4_find_entry(d_inode(child), &dotdot_name, &de, NULL);
if (IS_ERR(bh))
return ERR_CAST(bh);
if (!bh)
@@ -1765,7 +1839,8 @@ struct dentry *ext4_get_parent(struct dentry *child)
* Returns pointer to last entry moved.
*/
static struct ext4_dir_entry_2 *
-dx_move_dirents(char *from, char *to, struct dx_map_entry *map, int count,
+dx_move_dirents(struct inode *dir, char *from, char *to,
+ struct dx_map_entry *map, int count,
unsigned blocksize)
{
unsigned rec_len = 0;
@@ -1773,11 +1848,19 @@ dx_move_dirents(char *from, char *to, struct dx_map_entry *map, int count,
while (count--) {
struct ext4_dir_entry_2 *de = (struct ext4_dir_entry_2 *)
(from + (map->offs<<2));
- rec_len = EXT4_DIR_REC_LEN(de->name_len);
+ rec_len = ext4_dir_rec_len(de->name_len, dir);
+
memcpy (to, de, rec_len);
((struct ext4_dir_entry_2 *) to)->rec_len =
ext4_rec_len_to_disk(rec_len, blocksize);
+
+ /* wipe dir_entry excluding the rec_len field */
de->inode = 0;
+ memset(&de->name_len, 0, ext4_rec_len_from_disk(de->rec_len,
+ blocksize) -
+ offsetof(struct ext4_dir_entry_2,
+ name_len));
+
map++;
to += rec_len;
}
@@ -1788,7 +1871,8 @@ dx_move_dirents(char *from, char *to, struct dx_map_entry *map, int count,
* Compact each dir entry in the range to the minimal rec_len.
* Returns pointer to last entry in range.
*/
-static struct ext4_dir_entry_2* dx_pack_dirents(char *base, unsigned blocksize)
+static struct ext4_dir_entry_2 *dx_pack_dirents(struct inode *dir, char *base,
+ unsigned int blocksize)
{
struct ext4_dir_entry_2 *next, *to, *prev, *de = (struct ext4_dir_entry_2 *) base;
unsigned rec_len = 0;
@@ -1797,7 +1881,7 @@ static struct ext4_dir_entry_2* dx_pack_dirents(char *base, unsigned blocksize)
while ((char*)de < base + blocksize) {
next = ext4_next_entry(de, blocksize);
if (de->inode && de->name_len) {
- rec_len = EXT4_DIR_REC_LEN(de->name_len);
+ rec_len = ext4_dir_rec_len(de->name_len, dir);
if (de > to)
memmove(to, de, rec_len);
to->rec_len = ext4_rec_len_to_disk(rec_len, blocksize);
@@ -1887,9 +1971,9 @@ static struct ext4_dir_entry_2 *do_split(handle_t *handle, struct inode *dir,
hash2, split, count-split));
/* Fancy dance to stay within two buffers */
- de2 = dx_move_dirents(data1, data2, map + split, count - split,
+ de2 = dx_move_dirents(dir, data1, data2, map + split, count - split,
blocksize);
- de = dx_pack_dirents(data1, blocksize);
+ de = dx_pack_dirents(dir, data1, blocksize);
de->rec_len = ext4_rec_len_to_disk(data1 + (blocksize - csum_size) -
(char *) de,
blocksize);
@@ -1937,7 +2021,7 @@ int ext4_find_dest_de(struct inode *dir, struct inode *inode,
struct ext4_dir_entry_2 **dest_de)
{
struct ext4_dir_entry_2 *de;
- unsigned short reclen = EXT4_DIR_REC_LEN(fname_len(fname));
+ unsigned short reclen = ext4_dir_rec_len(fname_len(fname), dir);
int nlen, rlen;
unsigned int offset = 0;
char *top;
@@ -1950,7 +2034,7 @@ int ext4_find_dest_de(struct inode *dir, struct inode *inode,
return -EFSCORRUPTED;
if (ext4_match(dir, fname, de))
return -EEXIST;
- nlen = EXT4_DIR_REC_LEN(de->name_len);
+ nlen = ext4_dir_rec_len(de->name_len, dir);
rlen = ext4_rec_len_from_disk(de->rec_len, buf_size);
if ((de->inode ? rlen - nlen : rlen) >= reclen)
break;
@@ -1964,7 +2048,8 @@ int ext4_find_dest_de(struct inode *dir, struct inode *inode,
return 0;
}
-void ext4_insert_dentry(struct inode *inode,
+void ext4_insert_dentry(struct inode *dir,
+ struct inode *inode,
struct ext4_dir_entry_2 *de,
int buf_size,
struct ext4_filename *fname)
@@ -1972,7 +2057,7 @@ void ext4_insert_dentry(struct inode *inode,
int nlen, rlen;
- nlen = EXT4_DIR_REC_LEN(de->name_len);
+ nlen = ext4_dir_rec_len(de->name_len, dir);
rlen = ext4_rec_len_from_disk(de->rec_len, buf_size);
if (de->inode) {
struct ext4_dir_entry_2 *de1 =
@@ -1986,6 +2071,13 @@ void ext4_insert_dentry(struct inode *inode,
ext4_set_de_type(inode->i_sb, de, inode->i_mode);
de->name_len = fname_len(fname);
memcpy(de->name, fname_name(fname), fname_len(fname));
+ if (ext4_hash_in_dirent(dir)) {
+ struct dx_hash_info *hinfo = &fname->hinfo;
+
+ EXT4_DIRENT_HASHES(de)->hash = cpu_to_le32(hinfo->hash);
+ EXT4_DIRENT_HASHES(de)->minor_hash =
+ cpu_to_le32(hinfo->minor_hash);
+ }
}
/*
@@ -2022,7 +2114,7 @@ static int add_dirent_to_buf(handle_t *handle, struct ext4_filename *fname,
}
/* By now the buffer is marked for journaling */
- ext4_insert_dentry(inode, de, blocksize, fname);
+ ext4_insert_dentry(dir, inode, de, blocksize, fname);
/*
* XXX shouldn't update any times until successful
@@ -2102,6 +2194,7 @@ static int make_indexed_dir(handle_t *handle, struct ext4_filename *fname,
data2 = bh2->b_data;
memcpy(data2, de, len);
+ memset(de, 0, len); /* wipe old data */
de = (struct ext4_dir_entry_2 *) data2;
top = data2 + len;
while ((char *)(de2 = ext4_next_entry(de, blocksize)) < top)
@@ -2114,11 +2207,16 @@ static int make_indexed_dir(handle_t *handle, struct ext4_filename *fname,
/* Initialize the root; the dot dirents already exist */
de = (struct ext4_dir_entry_2 *) (&root->dotdot);
- de->rec_len = ext4_rec_len_to_disk(blocksize - EXT4_DIR_REC_LEN(2),
- blocksize);
+ de->rec_len = ext4_rec_len_to_disk(
+ blocksize - ext4_dir_rec_len(2, NULL), blocksize);
memset (&root->info, 0, sizeof(root->info));
root->info.info_length = sizeof(root->info);
- root->info.hash_version = EXT4_SB(dir->i_sb)->s_def_hash_version;
+ if (ext4_hash_in_dirent(dir))
+ root->info.hash_version = DX_HASH_SIPHASH;
+ else
+ root->info.hash_version =
+ EXT4_SB(dir->i_sb)->s_def_hash_version;
+
entries = root->entries;
dx_set_block(entries, 1);
dx_set_count(entries, 1);
@@ -2129,7 +2227,11 @@ static int make_indexed_dir(handle_t *handle, struct ext4_filename *fname,
if (fname->hinfo.hash_version <= DX_HASH_TEA)
fname->hinfo.hash_version += EXT4_SB(dir->i_sb)->s_hash_unsigned;
fname->hinfo.seed = EXT4_SB(dir->i_sb)->s_hash_seed;
- ext4fs_dirhash(dir, fname_name(fname), fname_len(fname), &fname->hinfo);
+
+ /* casefolded encrypted hashes are computed on fname setup */
+ if (!ext4_hash_in_dirent(dir))
+ ext4fs_dirhash(dir, fname_name(fname),
+ fname_len(fname), &fname->hinfo);
memset(frames, 0, sizeof(frames));
frame = frames;
@@ -2139,10 +2241,10 @@ static int make_indexed_dir(handle_t *handle, struct ext4_filename *fname,
retval = ext4_handle_dirty_dx_node(handle, dir, frame->bh);
if (retval)
- goto out_frames;
+ goto out_frames;
retval = ext4_handle_dirty_dirblock(handle, dir, bh2);
if (retval)
- goto out_frames;
+ goto out_frames;
de = do_split(handle,dir, &bh2, frame, &fname->hinfo);
if (IS_ERR(de)) {
@@ -2482,15 +2584,27 @@ int ext4_generic_delete_entry(struct inode *dir,
entry_buf, buf_size, i))
return -EFSCORRUPTED;
if (de == de_del) {
- if (pde)
+ if (pde) {
pde->rec_len = ext4_rec_len_to_disk(
ext4_rec_len_from_disk(pde->rec_len,
blocksize) +
ext4_rec_len_from_disk(de->rec_len,
blocksize),
blocksize);
- else
+
+ /* wipe entire dir_entry */
+ memset(de, 0, ext4_rec_len_from_disk(de->rec_len,
+ blocksize));
+ } else {
+ /* wipe dir_entry excluding the rec_len field */
de->inode = 0;
+ memset(&de->name_len, 0,
+ ext4_rec_len_from_disk(de->rec_len,
+ blocksize) -
+ offsetof(struct ext4_dir_entry_2,
+ name_len));
+ }
+
inode_inc_iversion(dir);
return 0;
}
@@ -2722,7 +2836,7 @@ struct ext4_dir_entry_2 *ext4_init_dot_dotdot(struct inode *inode,
{
de->inode = cpu_to_le32(inode->i_ino);
de->name_len = 1;
- de->rec_len = ext4_rec_len_to_disk(EXT4_DIR_REC_LEN(de->name_len),
+ de->rec_len = ext4_rec_len_to_disk(ext4_dir_rec_len(de->name_len, NULL),
blocksize);
strcpy(de->name, ".");
ext4_set_de_type(inode->i_sb, de, S_IFDIR);
@@ -2732,11 +2846,12 @@ struct ext4_dir_entry_2 *ext4_init_dot_dotdot(struct inode *inode,
de->name_len = 2;
if (!dotdot_real_len)
de->rec_len = ext4_rec_len_to_disk(blocksize -
- (csum_size + EXT4_DIR_REC_LEN(1)),
+ (csum_size + ext4_dir_rec_len(1, NULL)),
blocksize);
else
de->rec_len = ext4_rec_len_to_disk(
- EXT4_DIR_REC_LEN(de->name_len), blocksize);
+ ext4_dir_rec_len(de->name_len, NULL),
+ blocksize);
strcpy(de->name, "..");
ext4_set_de_type(inode->i_sb, de, S_IFDIR);
@@ -2869,7 +2984,8 @@ bool ext4_empty_dir(struct inode *inode)
}
sb = inode->i_sb;
- if (inode->i_size < EXT4_DIR_REC_LEN(1) + EXT4_DIR_REC_LEN(2)) {
+ if (inode->i_size < ext4_dir_rec_len(1, NULL) +
+ ext4_dir_rec_len(2, NULL)) {
EXT4_ERROR_INODE(inode, "invalid size");
return true;
}
@@ -3372,7 +3488,7 @@ static int ext4_symlink(struct user_namespace *mnt_userns, struct inode *dir,
* for transaction commit if we are running out of space
* and thus we deadlock. So we have to stop transaction now
* and restart it when symlink contents is written.
- *
+ *
* To keep fs consistent in case of crash, we have to put inode
* to orphan list in the mean time.
*/
@@ -3613,6 +3729,31 @@ static int ext4_setent(handle_t *handle, struct ext4_renament *ent,
return retval;
}
+static void ext4_resetent(handle_t *handle, struct ext4_renament *ent,
+ unsigned ino, unsigned file_type)
+{
+ struct ext4_renament old = *ent;
+ int retval = 0;
+
+ /*
+ * old->de could have moved from under us during make indexed dir,
+ * so the old->de may no longer valid and need to find it again
+ * before reset old inode info.
+ */
+ old.bh = ext4_find_entry(old.dir, &old.dentry->d_name, &old.de, NULL);
+ if (IS_ERR(old.bh))
+ retval = PTR_ERR(old.bh);
+ if (!old.bh)
+ retval = -ENOENT;
+ if (retval) {
+ ext4_std_error(old.dir->i_sb, retval);
+ return;
+ }
+
+ ext4_setent(handle, &old, ino, file_type);
+ brelse(old.bh);
+}
+
static int ext4_find_delete_entry(handle_t *handle, struct inode *dir,
const struct qstr *d_name)
{
@@ -3774,14 +3915,14 @@ static int ext4_rename(struct user_namespace *mnt_userns, struct inode *old_dir,
*/
retval = -ENOENT;
if (!old.bh || le32_to_cpu(old.de->inode) != old.inode->i_ino)
- goto end_rename;
+ goto release_bh;
new.bh = ext4_find_entry(new.dir, &new.dentry->d_name,
&new.de, &new.inlined);
if (IS_ERR(new.bh)) {
retval = PTR_ERR(new.bh);
new.bh = NULL;
- goto end_rename;
+ goto release_bh;
}
if (new.bh) {
if (!new.inode) {
@@ -3798,15 +3939,13 @@ static int ext4_rename(struct user_namespace *mnt_userns, struct inode *old_dir,
handle = ext4_journal_start(old.dir, EXT4_HT_DIR, credits);
if (IS_ERR(handle)) {
retval = PTR_ERR(handle);
- handle = NULL;
- goto end_rename;
+ goto release_bh;
}
} else {
whiteout = ext4_whiteout_for_rename(mnt_userns, &old, credits, &handle);
if (IS_ERR(whiteout)) {
retval = PTR_ERR(whiteout);
- whiteout = NULL;
- goto end_rename;
+ goto release_bh;
}
}
@@ -3850,6 +3989,7 @@ static int ext4_rename(struct user_namespace *mnt_userns, struct inode *old_dir,
retval = ext4_mark_inode_dirty(handle, whiteout);
if (unlikely(retval))
goto end_rename;
+
}
if (!new.bh) {
retval = ext4_add_entry(handle, new.dentry, old.inode);
@@ -3923,6 +4063,8 @@ static int ext4_rename(struct user_namespace *mnt_userns, struct inode *old_dir,
ext4_fc_track_unlink(handle, new.dentry);
__ext4_fc_track_link(handle, old.inode, new.dentry);
__ext4_fc_track_unlink(handle, old.inode, old.dentry);
+ if (whiteout)
+ __ext4_fc_track_create(handle, whiteout, old.dentry);
}
if (new.inode) {
@@ -3937,19 +4079,21 @@ static int ext4_rename(struct user_namespace *mnt_userns, struct inode *old_dir,
end_rename:
if (whiteout) {
if (retval) {
- ext4_setent(handle, &old,
- old.inode->i_ino, old_file_type);
+ ext4_resetent(handle, &old,
+ old.inode->i_ino, old_file_type);
drop_nlink(whiteout);
+ ext4_orphan_add(handle, whiteout);
}
unlock_new_inode(whiteout);
+ ext4_journal_stop(handle);
iput(whiteout);
-
+ } else {
+ ext4_journal_stop(handle);
}
+release_bh:
brelse(old.dir_bh);
brelse(old.bh);
brelse(new.bh);
- if (handle)
- ext4_journal_stop(handle);
return retval;
}
@@ -4144,6 +4288,8 @@ const struct inode_operations ext4_dir_inode_operations = {
.get_acl = ext4_get_acl,
.set_acl = ext4_set_acl,
.fiemap = ext4_fiemap,
+ .fileattr_get = ext4_fileattr_get,
+ .fileattr_set = ext4_fileattr_set,
};
const struct inode_operations ext4_special_inode_operations = {
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index ad34a37278cd..7dc94f3e18e6 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -667,9 +667,6 @@ static void ext4_handle_error(struct super_block *sb, bool force_ro, int error,
ext4_commit_super(sb);
}
- if (sb_rdonly(sb) || continue_fs)
- return;
-
/*
* We force ERRORS_RO behavior when system is rebooting. Otherwise we
* could panic during 'reboot -f' as the underlying device got already
@@ -679,6 +676,10 @@ static void ext4_handle_error(struct super_block *sb, bool force_ro, int error,
panic("EXT4-fs (device %s): panic forced after error\n",
sb->s_id);
}
+
+ if (sb_rdonly(sb) || continue_fs)
+ return;
+
ext4_msg(sb, KERN_CRIT, "Remounting filesystem read-only");
/*
* Make sure updated value of ->s_mount_flags will be visible before
@@ -1210,6 +1211,7 @@ static void ext4_put_super(struct super_block *sb)
percpu_counter_destroy(&sbi->s_freeinodes_counter);
percpu_counter_destroy(&sbi->s_dirs_counter);
percpu_counter_destroy(&sbi->s_dirtyclusters_counter);
+ percpu_counter_destroy(&sbi->s_sra_exceeded_retry_limit);
percpu_free_rwsem(&sbi->s_writepages_rwsem);
#ifdef CONFIG_QUOTA
for (i = 0; i < EXT4_MAXQUOTAS; i++)
@@ -1687,7 +1689,7 @@ enum {
Opt_dioread_nolock, Opt_dioread_lock,
Opt_discard, Opt_nodiscard, Opt_init_itable, Opt_noinit_itable,
Opt_max_dir_size_kb, Opt_nojournal_checksum, Opt_nombcache,
- Opt_prefetch_block_bitmaps,
+ Opt_no_prefetch_block_bitmaps, Opt_mb_optimize_scan,
#ifdef CONFIG_EXT4_DEBUG
Opt_fc_debug_max_replay, Opt_fc_debug_force
#endif
@@ -1787,7 +1789,9 @@ static const match_table_t tokens = {
{Opt_inlinecrypt, "inlinecrypt"},
{Opt_nombcache, "nombcache"},
{Opt_nombcache, "no_mbcache"}, /* for backward compatibility */
- {Opt_prefetch_block_bitmaps, "prefetch_block_bitmaps"},
+ {Opt_removed, "prefetch_block_bitmaps"},
+ {Opt_no_prefetch_block_bitmaps, "no_prefetch_block_bitmaps"},
+ {Opt_mb_optimize_scan, "mb_optimize_scan=%d"},
{Opt_removed, "check=none"}, /* mount option from ext2/3 */
{Opt_removed, "nocheck"}, /* mount option from ext2/3 */
{Opt_removed, "reservation"}, /* mount option from ext2/3 */
@@ -1820,6 +1824,8 @@ static ext4_fsblk_t get_sb_block(void **data)
}
#define DEFAULT_JOURNAL_IOPRIO (IOPRIO_PRIO_VALUE(IOPRIO_CLASS_BE, 3))
+#define DEFAULT_MB_OPTIMIZE_SCAN (-1)
+
static const char deprecated_msg[] =
"Mount option \"%s\" will be removed by %s\n"
"Contact linux-ext4@vger.kernel.org if you think we should keep it.\n";
@@ -2006,8 +2012,9 @@ static const struct mount_opts {
{Opt_max_dir_size_kb, 0, MOPT_GTE0},
{Opt_test_dummy_encryption, 0, MOPT_STRING},
{Opt_nombcache, EXT4_MOUNT_NO_MBCACHE, MOPT_SET},
- {Opt_prefetch_block_bitmaps, EXT4_MOUNT_PREFETCH_BLOCK_BITMAPS,
+ {Opt_no_prefetch_block_bitmaps, EXT4_MOUNT_NO_PREFETCH_BLOCK_BITMAPS,
MOPT_SET},
+ {Opt_mb_optimize_scan, EXT4_MOUNT2_MB_OPTIMIZE_SCAN, MOPT_GTE0},
#ifdef CONFIG_EXT4_DEBUG
{Opt_fc_debug_force, EXT4_MOUNT2_JOURNAL_FAST_COMMIT,
MOPT_SET | MOPT_2 | MOPT_EXT4_ONLY},
@@ -2089,9 +2096,15 @@ static int ext4_set_test_dummy_encryption(struct super_block *sb,
return 1;
}
+struct ext4_parsed_options {
+ unsigned long journal_devnum;
+ unsigned int journal_ioprio;
+ int mb_optimize_scan;
+};
+
static int handle_mount_opt(struct super_block *sb, char *opt, int token,
- substring_t *args, unsigned long *journal_devnum,
- unsigned int *journal_ioprio, int is_remount)
+ substring_t *args, struct ext4_parsed_options *parsed_opts,
+ int is_remount)
{
struct ext4_sb_info *sbi = EXT4_SB(sb);
const struct mount_opts *m;
@@ -2248,7 +2261,7 @@ static int handle_mount_opt(struct super_block *sb, char *opt, int token,
"Cannot specify journal on remount");
return -1;
}
- *journal_devnum = arg;
+ parsed_opts->journal_devnum = arg;
} else if (token == Opt_journal_path) {
char *journal_path;
struct inode *journal_inode;
@@ -2284,7 +2297,7 @@ static int handle_mount_opt(struct super_block *sb, char *opt, int token,
return -1;
}
- *journal_devnum = new_encode_dev(journal_inode->i_rdev);
+ parsed_opts->journal_devnum = new_encode_dev(journal_inode->i_rdev);
path_put(&path);
kfree(journal_path);
} else if (token == Opt_journal_ioprio) {
@@ -2293,7 +2306,7 @@ static int handle_mount_opt(struct super_block *sb, char *opt, int token,
" (must be 0-7)");
return -1;
}
- *journal_ioprio =
+ parsed_opts->journal_ioprio =
IOPRIO_PRIO_VALUE(IOPRIO_CLASS_BE, arg);
} else if (token == Opt_test_dummy_encryption) {
return ext4_set_test_dummy_encryption(sb, opt, &args[0],
@@ -2383,6 +2396,13 @@ static int handle_mount_opt(struct super_block *sb, char *opt, int token,
sbi->s_mount_opt |= m->mount_opt;
} else if (token == Opt_data_err_ignore) {
sbi->s_mount_opt &= ~m->mount_opt;
+ } else if (token == Opt_mb_optimize_scan) {
+ if (arg != 0 && arg != 1) {
+ ext4_msg(sb, KERN_WARNING,
+ "mb_optimize_scan should be set to 0 or 1.");
+ return -1;
+ }
+ parsed_opts->mb_optimize_scan = arg;
} else {
if (!args->from)
arg = 1;
@@ -2410,8 +2430,7 @@ static int handle_mount_opt(struct super_block *sb, char *opt, int token,
}
static int parse_options(char *options, struct super_block *sb,
- unsigned long *journal_devnum,
- unsigned int *journal_ioprio,
+ struct ext4_parsed_options *ret_opts,
int is_remount)
{
struct ext4_sb_info __maybe_unused *sbi = EXT4_SB(sb);
@@ -2431,8 +2450,8 @@ static int parse_options(char *options, struct super_block *sb,
*/
args[0].to = args[0].from = NULL;
token = match_token(p, tokens, args);
- if (handle_mount_opt(sb, p, token, args, journal_devnum,
- journal_ioprio, is_remount) < 0)
+ if (handle_mount_opt(sb, p, token, args, ret_opts,
+ is_remount) < 0)
return 0;
}
#ifdef CONFIG_QUOTA
@@ -3022,9 +3041,6 @@ static void ext4_orphan_cleanup(struct super_block *sb,
sb->s_flags &= ~SB_RDONLY;
}
#ifdef CONFIG_QUOTA
- /* Needed for iput() to work correctly and not trash data */
- sb->s_flags |= SB_ACTIVE;
-
/*
* Turn on quotas which were not enabled for read-only mounts if
* filesystem has quota feature, so that they are updated correctly.
@@ -3690,11 +3706,11 @@ static struct ext4_li_request *ext4_li_request_new(struct super_block *sb,
elr->lr_super = sb;
elr->lr_first_not_zeroed = start;
- if (test_opt(sb, PREFETCH_BLOCK_BITMAPS))
- elr->lr_mode = EXT4_LI_MODE_PREFETCH_BBITMAP;
- else {
+ if (test_opt(sb, NO_PREFETCH_BLOCK_BITMAPS)) {
elr->lr_mode = EXT4_LI_MODE_ITABLE;
elr->lr_next_group = start;
+ } else {
+ elr->lr_mode = EXT4_LI_MODE_PREFETCH_BBITMAP;
}
/*
@@ -3725,7 +3741,7 @@ int ext4_register_li_request(struct super_block *sb,
goto out;
}
- if (!test_opt(sb, PREFETCH_BLOCK_BITMAPS) &&
+ if (test_opt(sb, NO_PREFETCH_BLOCK_BITMAPS) &&
(first_not_zeroed == ngroups || sb_rdonly(sb) ||
!test_opt(sb, INIT_INODE_TABLE)))
goto out;
@@ -4014,7 +4030,6 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
ext4_fsblk_t sb_block = get_sb_block(&data);
ext4_fsblk_t logical_sb_block;
unsigned long offset = 0;
- unsigned long journal_devnum = 0;
unsigned long def_mount_opts;
struct inode *root;
const char *descr;
@@ -4025,8 +4040,13 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
int needs_recovery, has_huge_files;
__u64 blocks_count;
int err = 0;
- unsigned int journal_ioprio = DEFAULT_JOURNAL_IOPRIO;
ext4_group_t first_not_zeroed;
+ struct ext4_parsed_options parsed_opts;
+
+ /* Set defaults for the variables that will be set during parsing */
+ parsed_opts.journal_ioprio = DEFAULT_JOURNAL_IOPRIO;
+ parsed_opts.journal_devnum = 0;
+ parsed_opts.mb_optimize_scan = DEFAULT_MB_OPTIMIZE_SCAN;
if ((data && !orig_data) || !sbi)
goto out_free_base;
@@ -4272,8 +4292,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
GFP_KERNEL);
if (!s_mount_opts)
goto failed_mount;
- if (!parse_options(s_mount_opts, sb, &journal_devnum,
- &journal_ioprio, 0)) {
+ if (!parse_options(s_mount_opts, sb, &parsed_opts, 0)) {
ext4_msg(sb, KERN_WARNING,
"failed to parse options in superblock: %s",
s_mount_opts);
@@ -4281,8 +4300,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
kfree(s_mount_opts);
}
sbi->s_def_mount_opt = sbi->s_mount_opt;
- if (!parse_options((char *) data, sb, &journal_devnum,
- &journal_ioprio, 0))
+ if (!parse_options((char *) data, sb, &parsed_opts, 0))
goto failed_mount;
#ifdef CONFIG_UNICODE
@@ -4291,12 +4309,6 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
struct unicode_map *encoding;
__u16 encoding_flags;
- if (ext4_has_feature_encrypt(sb)) {
- ext4_msg(sb, KERN_ERR,
- "Can't mount with encoding and encryption");
- goto failed_mount;
- }
-
if (ext4_sb_read_encoding(es, &encoding_info,
&encoding_flags)) {
ext4_msg(sb, KERN_ERR,
@@ -4773,7 +4785,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
* root first: it may be modified in the journal!
*/
if (!test_opt(sb, NOLOAD) && ext4_has_feature_journal(sb)) {
- err = ext4_load_journal(sb, es, journal_devnum);
+ err = ext4_load_journal(sb, es, parsed_opts.journal_devnum);
if (err)
goto failed_mount3a;
} else if (test_opt(sb, NOLOAD) && !sb_rdonly(sb) &&
@@ -4873,7 +4885,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
goto failed_mount_wq;
}
- set_task_ioprio(sbi->s_journal->j_task, journal_ioprio);
+ set_task_ioprio(sbi->s_journal->j_task, parsed_opts.journal_ioprio);
sbi->s_journal->j_submit_inode_data_buffers =
ext4_journal_submit_inode_data_buffers;
@@ -4979,6 +4991,19 @@ no_journal:
ext4_fc_replay_cleanup(sb);
ext4_ext_init(sb);
+
+ /*
+ * Enable optimize_scan if number of groups is > threshold. This can be
+ * turned off by passing "mb_optimize_scan=0". This can also be
+ * turned on forcefully by passing "mb_optimize_scan=1".
+ */
+ if (parsed_opts.mb_optimize_scan == 1)
+ set_opt2(sb, MB_OPTIMIZE_SCAN);
+ else if (parsed_opts.mb_optimize_scan == 0)
+ clear_opt2(sb, MB_OPTIMIZE_SCAN);
+ else if (sbi->s_groups_count >= MB_DEFAULT_LINEAR_SCAN_THRESHOLD)
+ set_opt2(sb, MB_OPTIMIZE_SCAN);
+
err = ext4_mb_init(sb);
if (err) {
ext4_msg(sb, KERN_ERR, "failed to initialize mballoc (%d)",
@@ -4995,7 +5020,7 @@ no_journal:
ext4_journal_commit_callback;
block = ext4_count_free_clusters(sb);
- ext4_free_blocks_count_set(sbi->s_es,
+ ext4_free_blocks_count_set(sbi->s_es,
EXT4_C2B(sbi, block));
err = percpu_counter_init(&sbi->s_freeclusters_counter, block,
GFP_KERNEL);
@@ -5012,6 +5037,9 @@ no_journal:
err = percpu_counter_init(&sbi->s_dirtyclusters_counter, 0,
GFP_KERNEL);
if (!err)
+ err = percpu_counter_init(&sbi->s_sra_exceeded_retry_limit, 0,
+ GFP_KERNEL);
+ if (!err)
err = percpu_init_rwsem(&sbi->s_writepages_rwsem);
if (err) {
@@ -5124,6 +5152,7 @@ failed_mount6:
percpu_counter_destroy(&sbi->s_freeinodes_counter);
percpu_counter_destroy(&sbi->s_dirs_counter);
percpu_counter_destroy(&sbi->s_dirtyclusters_counter);
+ percpu_counter_destroy(&sbi->s_sra_exceeded_retry_limit);
percpu_free_rwsem(&sbi->s_writepages_rwsem);
failed_mount5:
ext4_ext_release(sb);
@@ -5149,8 +5178,8 @@ failed_mount_wq:
failed_mount3a:
ext4_es_unregister_shrinker(sbi);
failed_mount3:
- del_timer_sync(&sbi->s_err_report);
flush_work(&sbi->s_error_work);
+ del_timer_sync(&sbi->s_err_report);
if (sbi->s_mmp_tsk)
kthread_stop(sbi->s_mmp_tsk);
failed_mount2:
@@ -5556,8 +5585,10 @@ static int ext4_commit_super(struct super_block *sb)
struct buffer_head *sbh = EXT4_SB(sb)->s_sbh;
int error = 0;
- if (!sbh || block_device_ejected(sb))
- return error;
+ if (!sbh)
+ return -EINVAL;
+ if (block_device_ejected(sb))
+ return -ENODEV;
ext4_update_super(sb);
@@ -5808,13 +5839,16 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data)
struct ext4_mount_options old_opts;
int enable_quota = 0;
ext4_group_t g;
- unsigned int journal_ioprio = DEFAULT_JOURNAL_IOPRIO;
int err = 0;
#ifdef CONFIG_QUOTA
int i, j;
char *to_free[EXT4_MAXQUOTAS];
#endif
char *orig_data = kstrdup(data, GFP_KERNEL);
+ struct ext4_parsed_options parsed_opts;
+
+ parsed_opts.journal_ioprio = DEFAULT_JOURNAL_IOPRIO;
+ parsed_opts.journal_devnum = 0;
if (data && !orig_data)
return -ENOMEM;
@@ -5845,7 +5879,8 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data)
old_opts.s_qf_names[i] = NULL;
#endif
if (sbi->s_journal && sbi->s_journal->j_task->io_context)
- journal_ioprio = sbi->s_journal->j_task->io_context->ioprio;
+ parsed_opts.journal_ioprio =
+ sbi->s_journal->j_task->io_context->ioprio;
/*
* Some options can be enabled by ext4 and/or by VFS mount flag
@@ -5855,7 +5890,7 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data)
vfs_flags = SB_LAZYTIME | SB_I_VERSION;
sb->s_flags = (sb->s_flags & ~vfs_flags) | (*flags & vfs_flags);
- if (!parse_options(data, sb, NULL, &journal_ioprio, 1)) {
+ if (!parse_options(data, sb, &parsed_opts, 1)) {
err = -EINVAL;
goto restore_opts;
}
@@ -5905,7 +5940,7 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data)
if (sbi->s_journal) {
ext4_init_journal_params(sb, sbi->s_journal);
- set_task_ioprio(sbi->s_journal->j_task, journal_ioprio);
+ set_task_ioprio(sbi->s_journal->j_task, parsed_opts.journal_ioprio);
}
/* Flush outstanding errors before changing fs state */
@@ -6148,7 +6183,6 @@ static int ext4_statfs(struct dentry *dentry, struct kstatfs *buf)
struct ext4_sb_info *sbi = EXT4_SB(sb);
struct ext4_super_block *es = sbi->s_es;
ext4_fsblk_t overhead = 0, resv_blocks;
- u64 fsid;
s64 bfree;
resv_blocks = EXT4_C2B(sbi, atomic64_read(&sbi->s_resv_clusters));
@@ -6169,9 +6203,7 @@ static int ext4_statfs(struct dentry *dentry, struct kstatfs *buf)
buf->f_files = le32_to_cpu(es->s_inodes_count);
buf->f_ffree = percpu_counter_sum_positive(&sbi->s_freeinodes_counter);
buf->f_namelen = EXT4_NAME_LEN;
- fsid = le64_to_cpup((void *)es->s_uuid) ^
- le64_to_cpup((void *)es->s_uuid + sizeof(u64));
- buf->f_fsid = u64_to_fsid(fsid);
+ buf->f_fsid = uuid_to_fsid(es->s_uuid);
#ifdef CONFIG_QUOTA
if (ext4_test_inode_flag(dentry->d_inode, EXT4_INODE_PROJINHERIT) &&
diff --git a/fs/ext4/sysfs.c b/fs/ext4/sysfs.c
index 075aa3a19ff5..6f825dedc3d4 100644
--- a/fs/ext4/sysfs.c
+++ b/fs/ext4/sysfs.c
@@ -24,6 +24,7 @@ typedef enum {
attr_session_write_kbytes,
attr_lifetime_write_kbytes,
attr_reserved_clusters,
+ attr_sra_exceeded_retry_limit,
attr_inode_readahead,
attr_trigger_test_error,
attr_first_error_time,
@@ -202,6 +203,7 @@ EXT4_ATTR_FUNC(delayed_allocation_blocks, 0444);
EXT4_ATTR_FUNC(session_write_kbytes, 0444);
EXT4_ATTR_FUNC(lifetime_write_kbytes, 0444);
EXT4_ATTR_FUNC(reserved_clusters, 0644);
+EXT4_ATTR_FUNC(sra_exceeded_retry_limit, 0444);
EXT4_ATTR_OFFSET(inode_readahead_blks, 0644, inode_readahead,
ext4_sb_info, s_inode_readahead_blks);
@@ -213,6 +215,7 @@ EXT4_RW_ATTR_SBI_UI(mb_order2_req, s_mb_order2_reqs);
EXT4_RW_ATTR_SBI_UI(mb_stream_req, s_mb_stream_request);
EXT4_RW_ATTR_SBI_UI(mb_group_prealloc, s_mb_group_prealloc);
EXT4_RW_ATTR_SBI_UI(mb_max_inode_prealloc, s_mb_max_inode_prealloc);
+EXT4_RW_ATTR_SBI_UI(mb_max_linear_groups, s_mb_max_linear_groups);
EXT4_RW_ATTR_SBI_UI(extent_max_zeroout_kb, s_extent_max_zeroout_kb);
EXT4_ATTR(trigger_fs_error, 0200, trigger_test_error);
EXT4_RW_ATTR_SBI_UI(err_ratelimit_interval_ms, s_err_ratelimit_state.interval);
@@ -251,6 +254,7 @@ static struct attribute *ext4_attrs[] = {
ATTR_LIST(session_write_kbytes),
ATTR_LIST(lifetime_write_kbytes),
ATTR_LIST(reserved_clusters),
+ ATTR_LIST(sra_exceeded_retry_limit),
ATTR_LIST(inode_readahead_blks),
ATTR_LIST(inode_goal),
ATTR_LIST(mb_stats),
@@ -260,6 +264,7 @@ static struct attribute *ext4_attrs[] = {
ATTR_LIST(mb_stream_req),
ATTR_LIST(mb_group_prealloc),
ATTR_LIST(mb_max_inode_prealloc),
+ ATTR_LIST(mb_max_linear_groups),
ATTR_LIST(max_writeback_mb_bump),
ATTR_LIST(extent_max_zeroout_kb),
ATTR_LIST(trigger_fs_error),
@@ -310,6 +315,7 @@ EXT4_ATTR_FEATURE(verity);
#endif
EXT4_ATTR_FEATURE(metadata_csum_seed);
EXT4_ATTR_FEATURE(fast_commit);
+EXT4_ATTR_FEATURE(encrypted_casefold);
static struct attribute *ext4_feat_attrs[] = {
ATTR_LIST(lazy_itable_init),
@@ -327,6 +333,7 @@ static struct attribute *ext4_feat_attrs[] = {
#endif
ATTR_LIST(metadata_csum_seed),
ATTR_LIST(fast_commit),
+ ATTR_LIST(encrypted_casefold),
NULL,
};
ATTRIBUTE_GROUPS(ext4_feat);
@@ -374,6 +381,10 @@ static ssize_t ext4_attr_show(struct kobject *kobj,
return snprintf(buf, PAGE_SIZE, "%llu\n",
(unsigned long long)
atomic64_read(&sbi->s_resv_clusters));
+ case attr_sra_exceeded_retry_limit:
+ return snprintf(buf, PAGE_SIZE, "%llu\n",
+ (unsigned long long)
+ percpu_counter_sum(&sbi->s_sra_exceeded_retry_limit));
case attr_inode_readahead:
case attr_pointer_ui:
if (!ptr)
@@ -521,6 +532,10 @@ int ext4_register_sysfs(struct super_block *sb)
ext4_fc_info_show, sb);
proc_create_seq_data("mb_groups", S_IRUGO, sbi->s_proc,
&ext4_mb_seq_groups_ops, sb);
+ proc_create_single_data("mb_stats", 0444, sbi->s_proc,
+ ext4_seq_mb_stats_show, sb);
+ proc_create_seq_data("mb_structs_summary", 0444, sbi->s_proc,
+ &ext4_mb_seq_structs_summary_ops, sb);
}
return 0;
}
diff --git a/fs/ext4/verity.c b/fs/ext4/verity.c
index 5b7ba8f71153..eacbd489e3bf 100644
--- a/fs/ext4/verity.c
+++ b/fs/ext4/verity.c
@@ -45,16 +45,13 @@ static int pagecache_read(struct inode *inode, void *buf, size_t count,
size_t n = min_t(size_t, count,
PAGE_SIZE - offset_in_page(pos));
struct page *page;
- void *addr;
page = read_mapping_page(inode->i_mapping, pos >> PAGE_SHIFT,
NULL);
if (IS_ERR(page))
return PTR_ERR(page);
- addr = kmap_atomic(page);
- memcpy(buf, addr + offset_in_page(pos), n);
- kunmap_atomic(addr);
+ memcpy_from_page(buf, page, offset_in_page(pos), n);
put_page(page);
@@ -80,7 +77,6 @@ static int pagecache_write(struct inode *inode, const void *buf, size_t count,
PAGE_SIZE - offset_in_page(pos));
struct page *page;
void *fsdata;
- void *addr;
int res;
res = pagecache_write_begin(NULL, inode->i_mapping, pos, n, 0,
@@ -88,9 +84,7 @@ static int pagecache_write(struct inode *inode, const void *buf, size_t count,
if (res)
return res;
- addr = kmap_atomic(page);
- memcpy(addr + offset_in_page(pos), buf, n);
- kunmap_atomic(addr);
+ memcpy_to_page(page, offset_in_page(pos), buf, n);
res = pagecache_write_end(NULL, inode->i_mapping, pos, n, n,
page, fsdata);
@@ -201,55 +195,76 @@ static int ext4_end_enable_verity(struct file *filp, const void *desc,
struct inode *inode = file_inode(filp);
const int credits = 2; /* superblock and inode for ext4_orphan_del() */
handle_t *handle;
+ struct ext4_iloc iloc;
int err = 0;
- int err2;
- if (desc != NULL) {
- /* Succeeded; write the verity descriptor. */
- err = ext4_write_verity_descriptor(inode, desc, desc_size,
- merkle_tree_size);
-
- /* Write all pages before clearing VERITY_IN_PROGRESS. */
- if (!err)
- err = filemap_write_and_wait(inode->i_mapping);
- }
+ /*
+ * If an error already occurred (which fs/verity/ signals by passing
+ * desc == NULL), then only clean-up is needed.
+ */
+ if (desc == NULL)
+ goto cleanup;
- /* If we failed, truncate anything we wrote past i_size. */
- if (desc == NULL || err)
- ext4_truncate(inode);
+ /* Append the verity descriptor. */
+ err = ext4_write_verity_descriptor(inode, desc, desc_size,
+ merkle_tree_size);
+ if (err)
+ goto cleanup;
/*
- * We must always clean up by clearing EXT4_STATE_VERITY_IN_PROGRESS and
- * deleting the inode from the orphan list, even if something failed.
- * If everything succeeded, we'll also set the verity bit in the same
- * transaction.
+ * Write all pages (both data and verity metadata). Note that this must
+ * happen before clearing EXT4_STATE_VERITY_IN_PROGRESS; otherwise pages
+ * beyond i_size won't be written properly. For crash consistency, this
+ * also must happen before the verity inode flag gets persisted.
*/
+ err = filemap_write_and_wait(inode->i_mapping);
+ if (err)
+ goto cleanup;
- ext4_clear_inode_state(inode, EXT4_STATE_VERITY_IN_PROGRESS);
+ /*
+ * Finally, set the verity inode flag and remove the inode from the
+ * orphan list (in a single transaction).
+ */
handle = ext4_journal_start(inode, EXT4_HT_INODE, credits);
if (IS_ERR(handle)) {
- ext4_orphan_del(NULL, inode);
- return PTR_ERR(handle);
+ err = PTR_ERR(handle);
+ goto cleanup;
}
- err2 = ext4_orphan_del(handle, inode);
- if (err2)
- goto out_stop;
+ err = ext4_orphan_del(handle, inode);
+ if (err)
+ goto stop_and_cleanup;
- if (desc != NULL && !err) {
- struct ext4_iloc iloc;
+ err = ext4_reserve_inode_write(handle, inode, &iloc);
+ if (err)
+ goto stop_and_cleanup;
- err = ext4_reserve_inode_write(handle, inode, &iloc);
- if (err)
- goto out_stop;
- ext4_set_inode_flag(inode, EXT4_INODE_VERITY);
- ext4_set_inode_flags(inode, false);
- err = ext4_mark_iloc_dirty(handle, inode, &iloc);
- }
-out_stop:
+ ext4_set_inode_flag(inode, EXT4_INODE_VERITY);
+ ext4_set_inode_flags(inode, false);
+ err = ext4_mark_iloc_dirty(handle, inode, &iloc);
+ if (err)
+ goto stop_and_cleanup;
+
+ ext4_journal_stop(handle);
+
+ ext4_clear_inode_state(inode, EXT4_STATE_VERITY_IN_PROGRESS);
+ return 0;
+
+stop_and_cleanup:
ext4_journal_stop(handle);
- return err ?: err2;
+cleanup:
+ /*
+ * Verity failed to be enabled, so clean up by truncating any verity
+ * metadata that was written beyond i_size (both from cache and from
+ * disk), removing the inode from the orphan list (if it wasn't done
+ * already), and clearing EXT4_STATE_VERITY_IN_PROGRESS.
+ */
+ truncate_inode_pages(inode->i_mapping, inode->i_size);
+ ext4_truncate(inode);
+ ext4_orphan_del(NULL, inode);
+ ext4_clear_inode_state(inode, EXT4_STATE_VERITY_IN_PROGRESS);
+ return err;
}
static int ext4_get_verity_descriptor_location(struct inode *inode,
@@ -349,7 +364,7 @@ static struct page *ext4_read_merkle_tree_page(struct inode *inode,
pgoff_t index,
unsigned long num_ra_pages)
{
- DEFINE_READAHEAD(ractl, NULL, inode->i_mapping, index);
+ DEFINE_READAHEAD(ractl, NULL, NULL, inode->i_mapping, index);
struct page *page;
index += ext4_verity_metadata_pos(inode) >> PAGE_SHIFT;
diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c
index 372208500f4e..10ba4b24a0aa 100644
--- a/fs/ext4/xattr.c
+++ b/fs/ext4/xattr.c
@@ -1462,6 +1462,9 @@ ext4_xattr_inode_cache_find(struct inode *inode, const void *value,
if (!ce)
return NULL;
+ WARN_ON_ONCE(ext4_handle_valid(journal_current_handle()) &&
+ !(current->flags & PF_MEMALLOC_NOFS));
+
ea_data = kvmalloc(value_len, GFP_KERNEL);
if (!ea_data) {
mb_cache_entry_put(ea_inode_cache, ce);
@@ -1614,7 +1617,7 @@ static int ext4_xattr_set_entry(struct ext4_xattr_info *i,
* If storing the value in an external inode is an option,
* reserve space for xattr entries/names in the external
* attribute block so that a long value does not occupy the
- * whole space and prevent futher entries being added.
+ * whole space and prevent further entries being added.
*/
if (ext4_has_feature_ea_inode(inode->i_sb) &&
new_size && is_block &&
@@ -2327,6 +2330,7 @@ ext4_xattr_set_handle(handle_t *handle, struct inode *inode, int name_index,
error = -ENOSPC;
goto cleanup;
}
+ WARN_ON_ONCE(!(current->flags & PF_MEMALLOC_NOFS));
}
error = ext4_reserve_inode_write(handle, inode, &is.iloc);
@@ -2400,7 +2404,7 @@ retry_inode:
* external inode if possible.
*/
if (ext4_has_feature_ea_inode(inode->i_sb) &&
- !i.in_inode) {
+ i.value_len && !i.in_inode) {
i.in_inode = 1;
goto retry_inode;
}
diff --git a/fs/f2fs/dir.c b/fs/f2fs/dir.c
index e6270a867be1..e211a1b6b013 100644
--- a/fs/f2fs/dir.c
+++ b/fs/f2fs/dir.c
@@ -449,9 +449,7 @@ struct f2fs_dir_entry *f2fs_find_entry(struct inode *dir,
struct f2fs_dir_entry *f2fs_parent_dir(struct inode *dir, struct page **p)
{
- struct qstr dotdot = QSTR_INIT("..", 2);
-
- return f2fs_find_entry(dir, &dotdot, p);
+ return f2fs_find_entry(dir, &dotdot_name, p);
}
ino_t f2fs_inode_by_name(struct inode *dir, const struct qstr *qstr,
diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index e2d302ae3a46..11a20dc505aa 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -3194,6 +3194,9 @@ int f2fs_setattr(struct user_namespace *mnt_userns, struct dentry *dentry,
int f2fs_truncate_hole(struct inode *inode, pgoff_t pg_start, pgoff_t pg_end);
void f2fs_truncate_data_blocks_range(struct dnode_of_data *dn, int count);
int f2fs_precache_extents(struct inode *inode);
+int f2fs_fileattr_get(struct dentry *dentry, struct fileattr *fa);
+int f2fs_fileattr_set(struct user_namespace *mnt_userns,
+ struct dentry *dentry, struct fileattr *fa);
long f2fs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg);
long f2fs_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg);
int f2fs_transfer_project_quota(struct inode *inode, kprojid_t kprojid);
diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c
index d26ff2ae3f5e..8a56acbcee4c 100644
--- a/fs/f2fs/file.c
+++ b/fs/f2fs/file.c
@@ -22,6 +22,7 @@
#include <linux/file.h>
#include <linux/nls.h>
#include <linux/sched/signal.h>
+#include <linux/fileattr.h>
#include "f2fs.h"
#include "node.h"
@@ -990,6 +991,8 @@ const struct inode_operations f2fs_file_inode_operations = {
.set_acl = f2fs_set_acl,
.listxattr = f2fs_listxattr,
.fiemap = f2fs_fiemap,
+ .fileattr_get = f2fs_fileattr_get,
+ .fileattr_set = f2fs_fileattr_set,
};
static int fill_zero(struct inode *inode, pgoff_t index,
@@ -1871,13 +1874,16 @@ static int f2fs_setflags_common(struct inode *inode, u32 iflags, u32 mask)
return 0;
}
-/* FS_IOC_GETFLAGS and FS_IOC_SETFLAGS support */
+/* FS_IOC_[GS]ETFLAGS and FS_IOC_FS[GS]ETXATTR support */
/*
* To make a new on-disk f2fs i_flag gettable via FS_IOC_GETFLAGS, add an entry
* for it to f2fs_fsflags_map[], and add its FS_*_FL equivalent to
* F2FS_GETTABLE_FS_FL. To also make it settable via FS_IOC_SETFLAGS, also add
* its FS_*_FL equivalent to F2FS_SETTABLE_FS_FL.
+ *
+ * Translating flags to fsx_flags value used by FS_IOC_FSGETXATTR and
+ * FS_IOC_FSSETXATTR is done by the VFS.
*/
static const struct {
@@ -1952,67 +1958,6 @@ static inline u32 f2fs_fsflags_to_iflags(u32 fsflags)
return iflags;
}
-static int f2fs_ioc_getflags(struct file *filp, unsigned long arg)
-{
- struct inode *inode = file_inode(filp);
- struct f2fs_inode_info *fi = F2FS_I(inode);
- u32 fsflags = f2fs_iflags_to_fsflags(fi->i_flags);
-
- if (IS_ENCRYPTED(inode))
- fsflags |= FS_ENCRYPT_FL;
- if (IS_VERITY(inode))
- fsflags |= FS_VERITY_FL;
- if (f2fs_has_inline_data(inode) || f2fs_has_inline_dentry(inode))
- fsflags |= FS_INLINE_DATA_FL;
- if (is_inode_flag_set(inode, FI_PIN_FILE))
- fsflags |= FS_NOCOW_FL;
-
- fsflags &= F2FS_GETTABLE_FS_FL;
-
- return put_user(fsflags, (int __user *)arg);
-}
-
-static int f2fs_ioc_setflags(struct file *filp, unsigned long arg)
-{
- struct inode *inode = file_inode(filp);
- struct f2fs_inode_info *fi = F2FS_I(inode);
- u32 fsflags, old_fsflags;
- u32 iflags;
- int ret;
-
- if (!inode_owner_or_capable(&init_user_ns, inode))
- return -EACCES;
-
- if (get_user(fsflags, (int __user *)arg))
- return -EFAULT;
-
- if (fsflags & ~F2FS_GETTABLE_FS_FL)
- return -EOPNOTSUPP;
- fsflags &= F2FS_SETTABLE_FS_FL;
-
- iflags = f2fs_fsflags_to_iflags(fsflags);
- if (f2fs_mask_flags(inode->i_mode, iflags) != iflags)
- return -EOPNOTSUPP;
-
- ret = mnt_want_write_file(filp);
- if (ret)
- return ret;
-
- inode_lock(inode);
-
- old_fsflags = f2fs_iflags_to_fsflags(fi->i_flags);
- ret = vfs_ioc_setflags_prepare(inode, old_fsflags, fsflags);
- if (ret)
- goto out;
-
- ret = f2fs_setflags_common(inode, iflags,
- f2fs_fsflags_to_iflags(F2FS_SETTABLE_FS_FL));
-out:
- inode_unlock(inode);
- mnt_drop_write_file(filp);
- return ret;
-}
-
static int f2fs_ioc_getversion(struct file *filp, unsigned long arg)
{
struct inode *inode = file_inode(filp);
@@ -3019,9 +2964,8 @@ int f2fs_transfer_project_quota(struct inode *inode, kprojid_t kprojid)
return err;
}
-static int f2fs_ioc_setproject(struct file *filp, __u32 projid)
+static int f2fs_ioc_setproject(struct inode *inode, __u32 projid)
{
- struct inode *inode = file_inode(filp);
struct f2fs_inode_info *fi = F2FS_I(inode);
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
struct page *ipage;
@@ -3082,7 +3026,7 @@ int f2fs_transfer_project_quota(struct inode *inode, kprojid_t kprojid)
return 0;
}
-static int f2fs_ioc_setproject(struct file *filp, __u32 projid)
+static int f2fs_ioc_setproject(struct inode *inode, __u32 projid)
{
if (projid != F2FS_DEF_PROJID)
return -EOPNOTSUPP;
@@ -3090,123 +3034,55 @@ static int f2fs_ioc_setproject(struct file *filp, __u32 projid)
}
#endif
-/* FS_IOC_FSGETXATTR and FS_IOC_FSSETXATTR support */
-
-/*
- * To make a new on-disk f2fs i_flag gettable via FS_IOC_FSGETXATTR and settable
- * via FS_IOC_FSSETXATTR, add an entry for it to f2fs_xflags_map[], and add its
- * FS_XFLAG_* equivalent to F2FS_SUPPORTED_XFLAGS.
- */
-
-static const struct {
- u32 iflag;
- u32 xflag;
-} f2fs_xflags_map[] = {
- { F2FS_SYNC_FL, FS_XFLAG_SYNC },
- { F2FS_IMMUTABLE_FL, FS_XFLAG_IMMUTABLE },
- { F2FS_APPEND_FL, FS_XFLAG_APPEND },
- { F2FS_NODUMP_FL, FS_XFLAG_NODUMP },
- { F2FS_NOATIME_FL, FS_XFLAG_NOATIME },
- { F2FS_PROJINHERIT_FL, FS_XFLAG_PROJINHERIT },
-};
-
-#define F2FS_SUPPORTED_XFLAGS ( \
- FS_XFLAG_SYNC | \
- FS_XFLAG_IMMUTABLE | \
- FS_XFLAG_APPEND | \
- FS_XFLAG_NODUMP | \
- FS_XFLAG_NOATIME | \
- FS_XFLAG_PROJINHERIT)
-
-/* Convert f2fs on-disk i_flags to FS_IOC_FS{GET,SET}XATTR flags */
-static inline u32 f2fs_iflags_to_xflags(u32 iflags)
-{
- u32 xflags = 0;
- int i;
-
- for (i = 0; i < ARRAY_SIZE(f2fs_xflags_map); i++)
- if (iflags & f2fs_xflags_map[i].iflag)
- xflags |= f2fs_xflags_map[i].xflag;
-
- return xflags;
-}
-
-/* Convert FS_IOC_FS{GET,SET}XATTR flags to f2fs on-disk i_flags */
-static inline u32 f2fs_xflags_to_iflags(u32 xflags)
-{
- u32 iflags = 0;
- int i;
-
- for (i = 0; i < ARRAY_SIZE(f2fs_xflags_map); i++)
- if (xflags & f2fs_xflags_map[i].xflag)
- iflags |= f2fs_xflags_map[i].iflag;
-
- return iflags;
-}
-
-static void f2fs_fill_fsxattr(struct inode *inode, struct fsxattr *fa)
+int f2fs_fileattr_get(struct dentry *dentry, struct fileattr *fa)
{
+ struct inode *inode = d_inode(dentry);
struct f2fs_inode_info *fi = F2FS_I(inode);
+ u32 fsflags = f2fs_iflags_to_fsflags(fi->i_flags);
- simple_fill_fsxattr(fa, f2fs_iflags_to_xflags(fi->i_flags));
+ if (IS_ENCRYPTED(inode))
+ fsflags |= FS_ENCRYPT_FL;
+ if (IS_VERITY(inode))
+ fsflags |= FS_VERITY_FL;
+ if (f2fs_has_inline_data(inode) || f2fs_has_inline_dentry(inode))
+ fsflags |= FS_INLINE_DATA_FL;
+ if (is_inode_flag_set(inode, FI_PIN_FILE))
+ fsflags |= FS_NOCOW_FL;
+
+ fileattr_fill_flags(fa, fsflags & F2FS_GETTABLE_FS_FL);
if (f2fs_sb_has_project_quota(F2FS_I_SB(inode)))
fa->fsx_projid = from_kprojid(&init_user_ns, fi->i_projid);
-}
-static int f2fs_ioc_fsgetxattr(struct file *filp, unsigned long arg)
-{
- struct inode *inode = file_inode(filp);
- struct fsxattr fa;
-
- f2fs_fill_fsxattr(inode, &fa);
-
- if (copy_to_user((struct fsxattr __user *)arg, &fa, sizeof(fa)))
- return -EFAULT;
return 0;
}
-static int f2fs_ioc_fssetxattr(struct file *filp, unsigned long arg)
+int f2fs_fileattr_set(struct user_namespace *mnt_userns,
+ struct dentry *dentry, struct fileattr *fa)
{
- struct inode *inode = file_inode(filp);
- struct fsxattr fa, old_fa;
+ struct inode *inode = d_inode(dentry);
+ u32 fsflags = fa->flags, mask = F2FS_SETTABLE_FS_FL;
u32 iflags;
int err;
- if (copy_from_user(&fa, (struct fsxattr __user *)arg, sizeof(fa)))
- return -EFAULT;
-
- /* Make sure caller has proper permission */
- if (!inode_owner_or_capable(&init_user_ns, inode))
- return -EACCES;
-
- if (fa.fsx_xflags & ~F2FS_SUPPORTED_XFLAGS)
+ if (unlikely(f2fs_cp_error(F2FS_I_SB(inode))))
+ return -EIO;
+ if (!f2fs_is_checkpoint_ready(F2FS_I_SB(inode)))
+ return -ENOSPC;
+ if (fsflags & ~F2FS_GETTABLE_FS_FL)
return -EOPNOTSUPP;
+ fsflags &= F2FS_SETTABLE_FS_FL;
+ if (!fa->flags_valid)
+ mask &= FS_COMMON_FL;
- iflags = f2fs_xflags_to_iflags(fa.fsx_xflags);
+ iflags = f2fs_fsflags_to_iflags(fsflags);
if (f2fs_mask_flags(inode->i_mode, iflags) != iflags)
return -EOPNOTSUPP;
- err = mnt_want_write_file(filp);
- if (err)
- return err;
-
- inode_lock(inode);
-
- f2fs_fill_fsxattr(inode, &old_fa);
- err = vfs_ioc_fssetxattr_check(inode, &old_fa, &fa);
- if (err)
- goto out;
-
- err = f2fs_setflags_common(inode, iflags,
- f2fs_xflags_to_iflags(F2FS_SUPPORTED_XFLAGS));
- if (err)
- goto out;
+ err = f2fs_setflags_common(inode, iflags, f2fs_fsflags_to_iflags(mask));
+ if (!err)
+ err = f2fs_ioc_setproject(inode, fa->fsx_projid);
- err = f2fs_ioc_setproject(filp, fa.fsx_projid);
-out:
- inode_unlock(inode);
- mnt_drop_write_file(filp);
return err;
}
@@ -4051,7 +3927,7 @@ out:
static int redirty_blocks(struct inode *inode, pgoff_t page_idx, int len)
{
- DEFINE_READAHEAD(ractl, NULL, inode->i_mapping, page_idx);
+ DEFINE_READAHEAD(ractl, NULL, NULL, inode->i_mapping, page_idx);
struct address_space *mapping = inode->i_mapping;
struct page *page;
pgoff_t redirty_idx = page_idx;
@@ -4233,10 +4109,6 @@ out:
static long __f2fs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
{
switch (cmd) {
- case FS_IOC_GETFLAGS:
- return f2fs_ioc_getflags(filp, arg);
- case FS_IOC_SETFLAGS:
- return f2fs_ioc_setflags(filp, arg);
case FS_IOC_GETVERSION:
return f2fs_ioc_getversion(filp, arg);
case F2FS_IOC_START_ATOMIC_WRITE:
@@ -4285,10 +4157,6 @@ static long __f2fs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
return f2fs_ioc_flush_device(filp, arg);
case F2FS_IOC_GET_FEATURES:
return f2fs_ioc_get_features(filp, arg);
- case FS_IOC_FSGETXATTR:
- return f2fs_ioc_fsgetxattr(filp, arg);
- case FS_IOC_FSSETXATTR:
- return f2fs_ioc_fssetxattr(filp, arg);
case F2FS_IOC_GET_PIN_FILE:
return f2fs_ioc_get_pin_file(filp, arg);
case F2FS_IOC_SET_PIN_FILE:
@@ -4518,12 +4386,6 @@ long f2fs_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
return -ENOSPC;
switch (cmd) {
- case FS_IOC32_GETFLAGS:
- cmd = FS_IOC_GETFLAGS;
- break;
- case FS_IOC32_SETFLAGS:
- cmd = FS_IOC_SETFLAGS;
- break;
case FS_IOC32_GETVERSION:
cmd = FS_IOC_GETVERSION;
break;
@@ -4552,8 +4414,6 @@ long f2fs_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
case F2FS_IOC_DEFRAGMENT:
case F2FS_IOC_FLUSH_DEVICE:
case F2FS_IOC_GET_FEATURES:
- case FS_IOC_FSGETXATTR:
- case FS_IOC_FSSETXATTR:
case F2FS_IOC_GET_PIN_FILE:
case F2FS_IOC_SET_PIN_FILE:
case F2FS_IOC_PRECACHE_EXTENTS:
diff --git a/fs/f2fs/namei.c b/fs/f2fs/namei.c
index 17bd072a5d39..377c6b161b23 100644
--- a/fs/f2fs/namei.c
+++ b/fs/f2fs/namei.c
@@ -416,9 +416,8 @@ out:
struct dentry *f2fs_get_parent(struct dentry *child)
{
- struct qstr dotdot = QSTR_INIT("..", 2);
struct page *page;
- unsigned long ino = f2fs_inode_by_name(d_inode(child), &dotdot, &page);
+ unsigned long ino = f2fs_inode_by_name(d_inode(child), &dotdot_name, &page);
if (!ino) {
if (IS_ERR(page))
return ERR_CAST(page);
@@ -1327,6 +1326,8 @@ const struct inode_operations f2fs_dir_inode_operations = {
.set_acl = f2fs_set_acl,
.listxattr = f2fs_listxattr,
.fiemap = f2fs_fiemap,
+ .fileattr_get = f2fs_fileattr_get,
+ .fileattr_set = f2fs_fileattr_set,
};
const struct inode_operations f2fs_symlink_inode_operations = {
diff --git a/fs/f2fs/verity.c b/fs/f2fs/verity.c
index 054ec852b5ea..a7beff28a3c5 100644
--- a/fs/f2fs/verity.c
+++ b/fs/f2fs/verity.c
@@ -228,7 +228,7 @@ static struct page *f2fs_read_merkle_tree_page(struct inode *inode,
pgoff_t index,
unsigned long num_ra_pages)
{
- DEFINE_READAHEAD(ractl, NULL, inode->i_mapping, index);
+ DEFINE_READAHEAD(ractl, NULL, NULL, inode->i_mapping, index);
struct page *page;
index += f2fs_verity_metadata_pos(inode) >> PAGE_SHIFT;
diff --git a/fs/file.c b/fs/file.c
index f3a4bac2cbe9..86dc9956af32 100644
--- a/fs/file.c
+++ b/fs/file.c
@@ -629,17 +629,30 @@ int close_fd(unsigned fd)
}
EXPORT_SYMBOL(close_fd); /* for ksys_close() */
+/**
+ * last_fd - return last valid index into fd table
+ * @cur_fds: files struct
+ *
+ * Context: Either rcu read lock or files_lock must be held.
+ *
+ * Returns: Last valid index into fdtable.
+ */
+static inline unsigned last_fd(struct fdtable *fdt)
+{
+ return fdt->max_fds - 1;
+}
+
static inline void __range_cloexec(struct files_struct *cur_fds,
unsigned int fd, unsigned int max_fd)
{
struct fdtable *fdt;
- if (fd > max_fd)
- return;
-
+ /* make sure we're using the correct maximum value */
spin_lock(&cur_fds->file_lock);
fdt = files_fdtable(cur_fds);
- bitmap_set(fdt->close_on_exec, fd, max_fd - fd + 1);
+ max_fd = min(last_fd(fdt), max_fd);
+ if (fd <= max_fd)
+ bitmap_set(fdt->close_on_exec, fd, max_fd - fd + 1);
spin_unlock(&cur_fds->file_lock);
}
@@ -1068,8 +1081,6 @@ out_unlock:
/**
* __receive_fd() - Install received file into file descriptor table
- *
- * @fd: fd to install into (if negative, a new fd will be allocated)
* @file: struct file that was received from another process
* @ufd: __user pointer to write new fd number to
* @o_flags: the O_* flags to apply to the new fd entry
@@ -1083,7 +1094,7 @@ out_unlock:
*
* Returns newly install fd or -ve on error.
*/
-int __receive_fd(int fd, struct file *file, int __user *ufd, unsigned int o_flags)
+int __receive_fd(struct file *file, int __user *ufd, unsigned int o_flags)
{
int new_fd;
int error;
@@ -1092,32 +1103,33 @@ int __receive_fd(int fd, struct file *file, int __user *ufd, unsigned int o_flag
if (error)
return error;
- if (fd < 0) {
- new_fd = get_unused_fd_flags(o_flags);
- if (new_fd < 0)
- return new_fd;
- } else {
- new_fd = fd;
- }
+ new_fd = get_unused_fd_flags(o_flags);
+ if (new_fd < 0)
+ return new_fd;
if (ufd) {
error = put_user(new_fd, ufd);
if (error) {
- if (fd < 0)
- put_unused_fd(new_fd);
+ put_unused_fd(new_fd);
return error;
}
}
- if (fd < 0) {
- fd_install(new_fd, get_file(file));
- } else {
- error = replace_fd(new_fd, file, o_flags);
- if (error)
- return error;
- }
+ fd_install(new_fd, get_file(file));
+ __receive_sock(file);
+ return new_fd;
+}
- /* Bump the sock usage counts, if any. */
+int receive_fd_replace(int new_fd, struct file *file, unsigned int o_flags)
+{
+ int error;
+
+ error = security_file_receive(file);
+ if (error)
+ return error;
+ error = replace_fd(new_fd, file, o_flags);
+ if (error)
+ return error;
__receive_sock(file);
return new_fd;
}
diff --git a/fs/fs_parser.c b/fs/fs_parser.c
index 68b0148f4bb8..980d44fd3a36 100644
--- a/fs/fs_parser.c
+++ b/fs/fs_parser.c
@@ -310,7 +310,6 @@ EXPORT_SYMBOL(fs_param_is_path);
#ifdef CONFIG_VALIDATE_FS_PARSER
/**
* validate_constant_table - Validate a constant table
- * @name: Name to use in reporting
* @tbl: The constant table to validate.
* @tbl_size: The size of the table.
* @low: The lowest permissible value.
@@ -360,6 +359,7 @@ bool validate_constant_table(const struct constant_table *tbl, size_t tbl_size,
/**
* fs_validate_description - Validate a parameter description
+ * @name: The parameter name to search for.
* @desc: The parameter description to validate.
*/
bool fs_validate_description(const char *name,
diff --git a/fs/fscache/Kconfig b/fs/fscache/Kconfig
index 5e796e6c38e5..427efa73b9bd 100644
--- a/fs/fscache/Kconfig
+++ b/fs/fscache/Kconfig
@@ -2,6 +2,7 @@
config FSCACHE
tristate "General filesystem local caching manager"
+ select NETFS_SUPPORT
help
This option enables a generic filesystem caching manager that can be
used by various network and other filesystems to cache data locally.
diff --git a/fs/fscache/Makefile b/fs/fscache/Makefile
index 79e08e05ef84..3b2ffa93ac18 100644
--- a/fs/fscache/Makefile
+++ b/fs/fscache/Makefile
@@ -7,6 +7,7 @@ fscache-y := \
cache.o \
cookie.o \
fsdef.o \
+ io.o \
main.o \
netfs.o \
object.o \
diff --git a/fs/fscache/internal.h b/fs/fscache/internal.h
index 08e91efbce53..c483863b740a 100644
--- a/fs/fscache/internal.h
+++ b/fs/fscache/internal.h
@@ -142,6 +142,10 @@ extern int fscache_wait_for_operation_activation(struct fscache_object *,
atomic_t *,
atomic_t *);
extern void fscache_invalidate_writes(struct fscache_cookie *);
+struct fscache_retrieval *fscache_alloc_retrieval(struct fscache_cookie *cookie,
+ struct address_space *mapping,
+ fscache_rw_complete_t end_io_func,
+ void *context);
/*
* proc.c
diff --git a/fs/fscache/io.c b/fs/fscache/io.c
new file mode 100644
index 000000000000..8ecc1141802f
--- /dev/null
+++ b/fs/fscache/io.c
@@ -0,0 +1,116 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/* Cache data I/O routines
+ *
+ * Copyright (C) 2021 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ */
+
+#define FSCACHE_DEBUG_LEVEL PAGE
+#include <linux/module.h>
+#define FSCACHE_USE_NEW_IO_API
+#include <linux/fscache-cache.h>
+#include <linux/slab.h>
+#include <linux/netfs.h>
+#include "internal.h"
+
+/*
+ * Start a cache read operation.
+ * - we return:
+ * -ENOMEM - out of memory, some pages may be being read
+ * -ERESTARTSYS - interrupted, some pages may be being read
+ * -ENOBUFS - no backing object or space available in which to cache any
+ * pages not being read
+ * -ENODATA - no data available in the backing object for some or all of
+ * the pages
+ * 0 - dispatched a read on all pages
+ */
+int __fscache_begin_read_operation(struct netfs_read_request *rreq,
+ struct fscache_cookie *cookie)
+{
+ struct fscache_retrieval *op;
+ struct fscache_object *object;
+ bool wake_cookie = false;
+ int ret;
+
+ _enter("rr=%08x", rreq->debug_id);
+
+ fscache_stat(&fscache_n_retrievals);
+
+ if (hlist_empty(&cookie->backing_objects))
+ goto nobufs;
+
+ if (test_bit(FSCACHE_COOKIE_INVALIDATING, &cookie->flags)) {
+ _leave(" = -ENOBUFS [invalidating]");
+ return -ENOBUFS;
+ }
+
+ ASSERTCMP(cookie->def->type, !=, FSCACHE_COOKIE_TYPE_INDEX);
+
+ if (fscache_wait_for_deferred_lookup(cookie) < 0)
+ return -ERESTARTSYS;
+
+ op = fscache_alloc_retrieval(cookie, NULL, NULL, NULL);
+ if (!op)
+ return -ENOMEM;
+ trace_fscache_page_op(cookie, NULL, &op->op, fscache_page_op_retr_multi);
+
+ spin_lock(&cookie->lock);
+
+ if (!fscache_cookie_enabled(cookie) ||
+ hlist_empty(&cookie->backing_objects))
+ goto nobufs_unlock;
+ object = hlist_entry(cookie->backing_objects.first,
+ struct fscache_object, cookie_link);
+
+ __fscache_use_cookie(cookie);
+ atomic_inc(&object->n_reads);
+ __set_bit(FSCACHE_OP_DEC_READ_CNT, &op->op.flags);
+
+ if (fscache_submit_op(object, &op->op) < 0)
+ goto nobufs_unlock_dec;
+ spin_unlock(&cookie->lock);
+
+ fscache_stat(&fscache_n_retrieval_ops);
+
+ /* we wait for the operation to become active, and then process it
+ * *here*, in this thread, and not in the thread pool */
+ ret = fscache_wait_for_operation_activation(
+ object, &op->op,
+ __fscache_stat(&fscache_n_retrieval_op_waits),
+ __fscache_stat(&fscache_n_retrievals_object_dead));
+ if (ret < 0)
+ goto error;
+
+ /* ask the cache to honour the operation */
+ ret = object->cache->ops->begin_read_operation(rreq, op);
+
+error:
+ if (ret == -ENOMEM)
+ fscache_stat(&fscache_n_retrievals_nomem);
+ else if (ret == -ERESTARTSYS)
+ fscache_stat(&fscache_n_retrievals_intr);
+ else if (ret == -ENODATA)
+ fscache_stat(&fscache_n_retrievals_nodata);
+ else if (ret < 0)
+ fscache_stat(&fscache_n_retrievals_nobufs);
+ else
+ fscache_stat(&fscache_n_retrievals_ok);
+
+ fscache_put_retrieval(op);
+ _leave(" = %d", ret);
+ return ret;
+
+nobufs_unlock_dec:
+ atomic_dec(&object->n_reads);
+ wake_cookie = __fscache_unuse_cookie(cookie);
+nobufs_unlock:
+ spin_unlock(&cookie->lock);
+ fscache_put_retrieval(op);
+ if (wake_cookie)
+ __fscache_wake_unused_cookie(cookie);
+nobufs:
+ fscache_stat(&fscache_n_retrievals_nobufs);
+ _leave(" = -ENOBUFS");
+ return -ENOBUFS;
+}
+EXPORT_SYMBOL(__fscache_begin_read_operation);
diff --git a/fs/fscache/page.c b/fs/fscache/page.c
index 26af6fdf1538..991b0a871744 100644
--- a/fs/fscache/page.c
+++ b/fs/fscache/page.c
@@ -299,7 +299,7 @@ static void fscache_release_retrieval_op(struct fscache_operation *_op)
/*
* allocate a retrieval op
*/
-static struct fscache_retrieval *fscache_alloc_retrieval(
+struct fscache_retrieval *fscache_alloc_retrieval(
struct fscache_cookie *cookie,
struct address_space *mapping,
fscache_rw_complete_t end_io_func,
diff --git a/fs/fscache/stats.c b/fs/fscache/stats.c
index a5aa93ece8c5..a7c3ed89a3e0 100644
--- a/fs/fscache/stats.c
+++ b/fs/fscache/stats.c
@@ -278,5 +278,6 @@ int fscache_stats_show(struct seq_file *m, void *v)
atomic_read(&fscache_n_cache_stale_objects),
atomic_read(&fscache_n_cache_retired_objects),
atomic_read(&fscache_n_cache_culled_objects));
+ netfs_stats_show(m);
return 0;
}
diff --git a/fs/fuse/Makefile b/fs/fuse/Makefile
index 8c7021fb2cd4..0c48b35c058d 100644
--- a/fs/fuse/Makefile
+++ b/fs/fuse/Makefile
@@ -7,7 +7,7 @@ obj-$(CONFIG_FUSE_FS) += fuse.o
obj-$(CONFIG_CUSE) += cuse.o
obj-$(CONFIG_VIRTIO_FS) += virtiofs.o
-fuse-y := dev.o dir.o file.o inode.o control.o xattr.o acl.o readdir.o
+fuse-y := dev.o dir.o file.o inode.o control.o xattr.o acl.o readdir.o ioctl.o
fuse-$(CONFIG_FUSE_DAX) += dax.o
virtiofs-y := virtio_fs.o
diff --git a/fs/fuse/acl.c b/fs/fuse/acl.c
index e9c0f916349d..52b165319be1 100644
--- a/fs/fuse/acl.c
+++ b/fs/fuse/acl.c
@@ -71,6 +71,7 @@ int fuse_set_acl(struct user_namespace *mnt_userns, struct inode *inode,
return -EINVAL;
if (acl) {
+ unsigned int extra_flags = 0;
/*
* Fuse userspace is responsible for updating access
* permissions in the inode, if needed. fuse_setxattr
@@ -94,7 +95,11 @@ int fuse_set_acl(struct user_namespace *mnt_userns, struct inode *inode,
return ret;
}
- ret = fuse_setxattr(inode, name, value, size, 0);
+ if (!in_group_p(i_gid_into_mnt(&init_user_ns, inode)) &&
+ !capable_wrt_inode_uidgid(&init_user_ns, inode, CAP_FSETID))
+ extra_flags |= FUSE_SETXATTR_ACL_KILL_SGID;
+
+ ret = fuse_setxattr(inode, name, value, size, 0, extra_flags);
kfree(value);
} else {
ret = fuse_removexattr(inode, name);
diff --git a/fs/fuse/cuse.c b/fs/fuse/cuse.c
index 45082269e698..c7d882a9fe33 100644
--- a/fs/fuse/cuse.c
+++ b/fs/fuse/cuse.c
@@ -511,20 +511,18 @@ static int cuse_channel_open(struct inode *inode, struct file *file)
fuse_conn_init(&cc->fc, &cc->fm, file->f_cred->user_ns,
&fuse_dev_fiq_ops, NULL);
+ cc->fc.release = cuse_fc_release;
fud = fuse_dev_alloc_install(&cc->fc);
- if (!fud) {
- kfree(cc);
+ fuse_conn_put(&cc->fc);
+ if (!fud)
return -ENOMEM;
- }
INIT_LIST_HEAD(&cc->list);
- cc->fc.release = cuse_fc_release;
cc->fc.initialized = 1;
rc = cuse_send_init(cc);
if (rc) {
fuse_dev_free(fud);
- fuse_conn_put(&cc->fc);
return rc;
}
file->private_data = fud;
@@ -561,8 +559,6 @@ static int cuse_channel_release(struct inode *inode, struct file *file)
unregister_chrdev_region(cc->cdev->dev, 1);
cdev_del(cc->cdev);
}
- /* Base reference is now owned by "fud" */
- fuse_conn_put(&cc->fc);
rc = fuse_dev_release(inode, file); /* puts the base reference */
@@ -627,6 +623,8 @@ static int __init cuse_init(void)
cuse_channel_fops.owner = THIS_MODULE;
cuse_channel_fops.open = cuse_channel_open;
cuse_channel_fops.release = cuse_channel_release;
+ /* CUSE is not prepared for FUSE_DEV_IOC_CLONE */
+ cuse_channel_fops.unlocked_ioctl = NULL;
cuse_class = class_create(THIS_MODULE, "cuse");
if (IS_ERR(cuse_class))
diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c
index c6636b4c4ccf..a5ceccc5ef00 100644
--- a/fs/fuse/dev.c
+++ b/fs/fuse/dev.c
@@ -2229,19 +2229,18 @@ static int fuse_device_clone(struct fuse_conn *fc, struct file *new)
static long fuse_dev_ioctl(struct file *file, unsigned int cmd,
unsigned long arg)
{
- int err = -ENOTTY;
-
- if (cmd == FUSE_DEV_IOC_CLONE) {
- int oldfd;
-
- err = -EFAULT;
- if (!get_user(oldfd, (__u32 __user *) arg)) {
+ int res;
+ int oldfd;
+ struct fuse_dev *fud = NULL;
+
+ switch (cmd) {
+ case FUSE_DEV_IOC_CLONE:
+ res = -EFAULT;
+ if (!get_user(oldfd, (__u32 __user *)arg)) {
struct file *old = fget(oldfd);
- err = -EINVAL;
+ res = -EINVAL;
if (old) {
- struct fuse_dev *fud = NULL;
-
/*
* Check against file->f_op because CUSE
* uses the same ioctl handler.
@@ -2252,14 +2251,18 @@ static long fuse_dev_ioctl(struct file *file, unsigned int cmd,
if (fud) {
mutex_lock(&fuse_mutex);
- err = fuse_device_clone(fud->fc, file);
+ res = fuse_device_clone(fud->fc, file);
mutex_unlock(&fuse_mutex);
}
fput(old);
}
}
+ break;
+ default:
+ res = -ENOTTY;
+ break;
}
- return err;
+ return res;
}
const struct file_operations fuse_dev_operations = {
diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c
index 06a18700a845..1b6c001a7dd1 100644
--- a/fs/fuse/dir.c
+++ b/fs/fuse/dir.c
@@ -252,7 +252,7 @@ static int fuse_dentry_revalidate(struct dentry *entry, unsigned int flags)
if (ret == -ENOMEM)
goto out;
if (ret || fuse_invalid_attr(&outarg.attr) ||
- (outarg.attr.mode ^ inode->i_mode) & S_IFMT)
+ inode_wrong_type(inode, outarg.attr.mode))
goto invalid;
forget_all_cached_acls(inode);
@@ -508,7 +508,7 @@ static struct dentry *fuse_lookup(struct inode *dir, struct dentry *entry,
* 'mknod' + 'open' requests.
*/
static int fuse_create_open(struct inode *dir, struct dentry *entry,
- struct file *file, unsigned flags,
+ struct file *file, unsigned int flags,
umode_t mode)
{
int err;
@@ -1054,7 +1054,7 @@ static int fuse_do_getattr(struct inode *inode, struct kstat *stat,
err = fuse_simple_request(fm, &args);
if (!err) {
if (fuse_invalid_attr(&outarg.attr) ||
- (inode->i_mode ^ outarg.attr.mode) & S_IFMT) {
+ inode_wrong_type(inode, outarg.attr.mode)) {
fuse_make_bad(inode);
err = -EIO;
} else {
@@ -1703,7 +1703,7 @@ int fuse_do_setattr(struct dentry *dentry, struct iattr *attr,
}
if (fuse_invalid_attr(&outarg.attr) ||
- (inode->i_mode ^ outarg.attr.mode) & S_IFMT) {
+ inode_wrong_type(inode, outarg.attr.mode)) {
fuse_make_bad(inode);
err = -EIO;
goto error;
@@ -1866,6 +1866,8 @@ static const struct inode_operations fuse_dir_inode_operations = {
.listxattr = fuse_listxattr,
.get_acl = fuse_get_acl,
.set_acl = fuse_set_acl,
+ .fileattr_get = fuse_fileattr_get,
+ .fileattr_set = fuse_fileattr_set,
};
static const struct file_operations fuse_dir_operations = {
@@ -1886,6 +1888,8 @@ static const struct inode_operations fuse_common_inode_operations = {
.listxattr = fuse_listxattr,
.get_acl = fuse_get_acl,
.set_acl = fuse_set_acl,
+ .fileattr_get = fuse_fileattr_get,
+ .fileattr_set = fuse_fileattr_set,
};
static const struct inode_operations fuse_symlink_inode_operations = {
diff --git a/fs/fuse/file.c b/fs/fuse/file.c
index 8cccecb55fb8..09ef2a4d25ed 100644
--- a/fs/fuse/file.c
+++ b/fs/fuse/file.c
@@ -14,32 +14,20 @@
#include <linux/sched.h>
#include <linux/sched/signal.h>
#include <linux/module.h>
-#include <linux/compat.h>
#include <linux/swap.h>
#include <linux/falloc.h>
#include <linux/uio.h>
#include <linux/fs.h>
-static struct page **fuse_pages_alloc(unsigned int npages, gfp_t flags,
- struct fuse_page_desc **desc)
-{
- struct page **pages;
-
- pages = kzalloc(npages * (sizeof(struct page *) +
- sizeof(struct fuse_page_desc)), flags);
- *desc = (void *) (pages + npages);
-
- return pages;
-}
-
-static int fuse_send_open(struct fuse_mount *fm, u64 nodeid, struct file *file,
- int opcode, struct fuse_open_out *outargp)
+static int fuse_send_open(struct fuse_mount *fm, u64 nodeid,
+ unsigned int open_flags, int opcode,
+ struct fuse_open_out *outargp)
{
struct fuse_open_in inarg;
FUSE_ARGS(args);
memset(&inarg, 0, sizeof(inarg));
- inarg.flags = file->f_flags & ~(O_CREAT | O_EXCL | O_NOCTTY);
+ inarg.flags = open_flags & ~(O_CREAT | O_EXCL | O_NOCTTY);
if (!fm->fc->atomic_o_trunc)
inarg.flags &= ~O_TRUNC;
@@ -136,8 +124,8 @@ static void fuse_file_put(struct fuse_file *ff, bool sync, bool isdir)
}
}
-int fuse_do_open(struct fuse_mount *fm, u64 nodeid, struct file *file,
- bool isdir)
+struct fuse_file *fuse_file_open(struct fuse_mount *fm, u64 nodeid,
+ unsigned int open_flags, bool isdir)
{
struct fuse_conn *fc = fm->fc;
struct fuse_file *ff;
@@ -145,7 +133,7 @@ int fuse_do_open(struct fuse_mount *fm, u64 nodeid, struct file *file,
ff = fuse_file_alloc(fm);
if (!ff)
- return -ENOMEM;
+ return ERR_PTR(-ENOMEM);
ff->fh = 0;
/* Default for no-open */
@@ -154,14 +142,14 @@ int fuse_do_open(struct fuse_mount *fm, u64 nodeid, struct file *file,
struct fuse_open_out outarg;
int err;
- err = fuse_send_open(fm, nodeid, file, opcode, &outarg);
+ err = fuse_send_open(fm, nodeid, open_flags, opcode, &outarg);
if (!err) {
ff->fh = outarg.fh;
ff->open_flags = outarg.open_flags;
} else if (err != -ENOSYS) {
fuse_file_free(ff);
- return err;
+ return ERR_PTR(err);
} else {
if (isdir)
fc->no_opendir = 1;
@@ -174,9 +162,19 @@ int fuse_do_open(struct fuse_mount *fm, u64 nodeid, struct file *file,
ff->open_flags &= ~FOPEN_DIRECT_IO;
ff->nodeid = nodeid;
- file->private_data = ff;
- return 0;
+ return ff;
+}
+
+int fuse_do_open(struct fuse_mount *fm, u64 nodeid, struct file *file,
+ bool isdir)
+{
+ struct fuse_file *ff = fuse_file_open(fm, nodeid, file->f_flags, isdir);
+
+ if (!IS_ERR(ff))
+ file->private_data = ff;
+
+ return PTR_ERR_OR_ZERO(ff);
}
EXPORT_SYMBOL_GPL(fuse_do_open);
@@ -268,7 +266,7 @@ out:
}
static void fuse_prepare_release(struct fuse_inode *fi, struct fuse_file *ff,
- int flags, int opcode)
+ unsigned int flags, int opcode)
{
struct fuse_conn *fc = ff->fm->fc;
struct fuse_release_args *ra = ff->release_args;
@@ -297,22 +295,21 @@ static void fuse_prepare_release(struct fuse_inode *fi, struct fuse_file *ff,
ra->args.nocreds = true;
}
-void fuse_release_common(struct file *file, bool isdir)
+void fuse_file_release(struct inode *inode, struct fuse_file *ff,
+ unsigned int open_flags, fl_owner_t id, bool isdir)
{
- struct fuse_inode *fi = get_fuse_inode(file_inode(file));
- struct fuse_file *ff = file->private_data;
+ struct fuse_inode *fi = get_fuse_inode(inode);
struct fuse_release_args *ra = ff->release_args;
int opcode = isdir ? FUSE_RELEASEDIR : FUSE_RELEASE;
- fuse_prepare_release(fi, ff, file->f_flags, opcode);
+ fuse_prepare_release(fi, ff, open_flags, opcode);
if (ff->flock) {
ra->inarg.release_flags |= FUSE_RELEASE_FLOCK_UNLOCK;
- ra->inarg.lock_owner = fuse_lock_owner_id(ff->fm->fc,
- (fl_owner_t) file);
+ ra->inarg.lock_owner = fuse_lock_owner_id(ff->fm->fc, id);
}
/* Hold inode until release is finished */
- ra->inode = igrab(file_inode(file));
+ ra->inode = igrab(inode);
/*
* Normally this will send the RELEASE request, however if
@@ -326,6 +323,12 @@ void fuse_release_common(struct file *file, bool isdir)
fuse_file_put(ff, ff->fm->fc->destroy, isdir);
}
+void fuse_release_common(struct file *file, bool isdir)
+{
+ fuse_file_release(file_inode(file), file->private_data, file->f_flags,
+ (fl_owner_t) file, isdir);
+}
+
static int fuse_open(struct inode *inode, struct file *file)
{
return fuse_open_common(inode, file, false);
@@ -345,7 +348,8 @@ static int fuse_release(struct inode *inode, struct file *file)
return 0;
}
-void fuse_sync_release(struct fuse_inode *fi, struct fuse_file *ff, int flags)
+void fuse_sync_release(struct fuse_inode *fi, struct fuse_file *ff,
+ unsigned int flags)
{
WARN_ON(refcount_read(&ff->count) > 1);
fuse_prepare_release(fi, ff, flags, FUSE_RELEASE);
@@ -798,21 +802,12 @@ static void fuse_short_read(struct inode *inode, u64 attr_ver, size_t num_read,
{
struct fuse_conn *fc = get_fuse_conn(inode);
- if (fc->writeback_cache) {
- /*
- * A hole in a file. Some data after the hole are in page cache,
- * but have not reached the client fs yet. So, the hole is not
- * present there.
- */
- int i;
- int start_idx = num_read >> PAGE_SHIFT;
- size_t off = num_read & (PAGE_SIZE - 1);
-
- for (i = start_idx; i < ap->num_pages; i++) {
- zero_user_segment(ap->pages[i], off, PAGE_SIZE);
- off = 0;
- }
- } else {
+ /*
+ * If writeback_cache is enabled, a short read means there's a hole in
+ * the file. Some data after the hole is in page cache, but has not
+ * reached the client fs yet. So the hole is not present there.
+ */
+ if (!fc->writeback_cache) {
loff_t pos = page_offset(ap->pages[0]) + num_read;
fuse_read_update_size(inode, pos, attr_ver);
}
@@ -1099,6 +1094,7 @@ static ssize_t fuse_send_write_pages(struct fuse_io_args *ia,
struct fuse_file *ff = file->private_data;
struct fuse_mount *fm = ff->fm;
unsigned int offset, i;
+ bool short_write;
int err;
for (i = 0; i < ap->num_pages; i++)
@@ -1113,32 +1109,38 @@ static ssize_t fuse_send_write_pages(struct fuse_io_args *ia,
if (!err && ia->write.out.size > count)
err = -EIO;
+ short_write = ia->write.out.size < count;
offset = ap->descs[0].offset;
count = ia->write.out.size;
for (i = 0; i < ap->num_pages; i++) {
struct page *page = ap->pages[i];
- if (!err && !offset && count >= PAGE_SIZE)
- SetPageUptodate(page);
-
- if (count > PAGE_SIZE - offset)
- count -= PAGE_SIZE - offset;
- else
- count = 0;
- offset = 0;
-
- unlock_page(page);
+ if (err) {
+ ClearPageUptodate(page);
+ } else {
+ if (count >= PAGE_SIZE - offset)
+ count -= PAGE_SIZE - offset;
+ else {
+ if (short_write)
+ ClearPageUptodate(page);
+ count = 0;
+ }
+ offset = 0;
+ }
+ if (ia->write.page_locked && (i == ap->num_pages - 1))
+ unlock_page(page);
put_page(page);
}
return err;
}
-static ssize_t fuse_fill_write_pages(struct fuse_args_pages *ap,
+static ssize_t fuse_fill_write_pages(struct fuse_io_args *ia,
struct address_space *mapping,
struct iov_iter *ii, loff_t pos,
unsigned int max_pages)
{
+ struct fuse_args_pages *ap = &ia->ap;
struct fuse_conn *fc = get_fuse_conn(mapping->host);
unsigned offset = pos & (PAGE_SIZE - 1);
size_t count = 0;
@@ -1191,6 +1193,16 @@ static ssize_t fuse_fill_write_pages(struct fuse_args_pages *ap,
if (offset == PAGE_SIZE)
offset = 0;
+ /* If we copied full page, mark it uptodate */
+ if (tmp == PAGE_SIZE)
+ SetPageUptodate(page);
+
+ if (PageUptodate(page)) {
+ unlock_page(page);
+ } else {
+ ia->write.page_locked = true;
+ break;
+ }
if (!fc->big_writes)
break;
} while (iov_iter_count(ii) && count < fc->max_write &&
@@ -1234,7 +1246,7 @@ static ssize_t fuse_perform_write(struct kiocb *iocb,
break;
}
- count = fuse_fill_write_pages(ap, mapping, ii, pos, nr_pages);
+ count = fuse_fill_write_pages(&ia, mapping, ii, pos, nr_pages);
if (count <= 0) {
err = count;
} else {
@@ -1346,16 +1358,6 @@ out:
return written ? written : err;
}
-static inline void fuse_page_descs_length_init(struct fuse_page_desc *descs,
- unsigned int index,
- unsigned int nr_pages)
-{
- int i;
-
- for (i = index; i < index + nr_pages; i++)
- descs[i].length = PAGE_SIZE - descs[i].offset;
-}
-
static inline unsigned long fuse_get_user_addr(const struct iov_iter *ii)
{
return (unsigned long)ii->iov->iov_base + ii->iov_offset;
@@ -1759,8 +1761,17 @@ static void fuse_writepage_end(struct fuse_mount *fm, struct fuse_args *args,
container_of(args, typeof(*wpa), ia.ap.args);
struct inode *inode = wpa->inode;
struct fuse_inode *fi = get_fuse_inode(inode);
+ struct fuse_conn *fc = get_fuse_conn(inode);
mapping_set_error(inode->i_mapping, error);
+ /*
+ * A writeback finished and this might have updated mtime/ctime on
+ * server making local mtime/ctime stale. Hence invalidate attrs.
+ * Do this only if writeback_cache is not enabled. If writeback_cache
+ * is enabled, we trust local ctime/mtime.
+ */
+ if (!fc->writeback_cache)
+ fuse_invalidate_attr(inode);
spin_lock(&fi->lock);
rb_erase(&wpa->writepages_entry, &fi->writepages);
while (wpa->next) {
@@ -2637,363 +2648,6 @@ static loff_t fuse_file_llseek(struct file *file, loff_t offset, int whence)
}
/*
- * CUSE servers compiled on 32bit broke on 64bit kernels because the
- * ABI was defined to be 'struct iovec' which is different on 32bit
- * and 64bit. Fortunately we can determine which structure the server
- * used from the size of the reply.
- */
-static int fuse_copy_ioctl_iovec_old(struct iovec *dst, void *src,
- size_t transferred, unsigned count,
- bool is_compat)
-{
-#ifdef CONFIG_COMPAT
- if (count * sizeof(struct compat_iovec) == transferred) {
- struct compat_iovec *ciov = src;
- unsigned i;
-
- /*
- * With this interface a 32bit server cannot support
- * non-compat (i.e. ones coming from 64bit apps) ioctl
- * requests
- */
- if (!is_compat)
- return -EINVAL;
-
- for (i = 0; i < count; i++) {
- dst[i].iov_base = compat_ptr(ciov[i].iov_base);
- dst[i].iov_len = ciov[i].iov_len;
- }
- return 0;
- }
-#endif
-
- if (count * sizeof(struct iovec) != transferred)
- return -EIO;
-
- memcpy(dst, src, transferred);
- return 0;
-}
-
-/* Make sure iov_length() won't overflow */
-static int fuse_verify_ioctl_iov(struct fuse_conn *fc, struct iovec *iov,
- size_t count)
-{
- size_t n;
- u32 max = fc->max_pages << PAGE_SHIFT;
-
- for (n = 0; n < count; n++, iov++) {
- if (iov->iov_len > (size_t) max)
- return -ENOMEM;
- max -= iov->iov_len;
- }
- return 0;
-}
-
-static int fuse_copy_ioctl_iovec(struct fuse_conn *fc, struct iovec *dst,
- void *src, size_t transferred, unsigned count,
- bool is_compat)
-{
- unsigned i;
- struct fuse_ioctl_iovec *fiov = src;
-
- if (fc->minor < 16) {
- return fuse_copy_ioctl_iovec_old(dst, src, transferred,
- count, is_compat);
- }
-
- if (count * sizeof(struct fuse_ioctl_iovec) != transferred)
- return -EIO;
-
- for (i = 0; i < count; i++) {
- /* Did the server supply an inappropriate value? */
- if (fiov[i].base != (unsigned long) fiov[i].base ||
- fiov[i].len != (unsigned long) fiov[i].len)
- return -EIO;
-
- dst[i].iov_base = (void __user *) (unsigned long) fiov[i].base;
- dst[i].iov_len = (size_t) fiov[i].len;
-
-#ifdef CONFIG_COMPAT
- if (is_compat &&
- (ptr_to_compat(dst[i].iov_base) != fiov[i].base ||
- (compat_size_t) dst[i].iov_len != fiov[i].len))
- return -EIO;
-#endif
- }
-
- return 0;
-}
-
-
-/*
- * For ioctls, there is no generic way to determine how much memory
- * needs to be read and/or written. Furthermore, ioctls are allowed
- * to dereference the passed pointer, so the parameter requires deep
- * copying but FUSE has no idea whatsoever about what to copy in or
- * out.
- *
- * This is solved by allowing FUSE server to retry ioctl with
- * necessary in/out iovecs. Let's assume the ioctl implementation
- * needs to read in the following structure.
- *
- * struct a {
- * char *buf;
- * size_t buflen;
- * }
- *
- * On the first callout to FUSE server, inarg->in_size and
- * inarg->out_size will be NULL; then, the server completes the ioctl
- * with FUSE_IOCTL_RETRY set in out->flags, out->in_iovs set to 1 and
- * the actual iov array to
- *
- * { { .iov_base = inarg.arg, .iov_len = sizeof(struct a) } }
- *
- * which tells FUSE to copy in the requested area and retry the ioctl.
- * On the second round, the server has access to the structure and
- * from that it can tell what to look for next, so on the invocation,
- * it sets FUSE_IOCTL_RETRY, out->in_iovs to 2 and iov array to
- *
- * { { .iov_base = inarg.arg, .iov_len = sizeof(struct a) },
- * { .iov_base = a.buf, .iov_len = a.buflen } }
- *
- * FUSE will copy both struct a and the pointed buffer from the
- * process doing the ioctl and retry ioctl with both struct a and the
- * buffer.
- *
- * This time, FUSE server has everything it needs and completes ioctl
- * without FUSE_IOCTL_RETRY which finishes the ioctl call.
- *
- * Copying data out works the same way.
- *
- * Note that if FUSE_IOCTL_UNRESTRICTED is clear, the kernel
- * automatically initializes in and out iovs by decoding @cmd with
- * _IOC_* macros and the server is not allowed to request RETRY. This
- * limits ioctl data transfers to well-formed ioctls and is the forced
- * behavior for all FUSE servers.
- */
-long fuse_do_ioctl(struct file *file, unsigned int cmd, unsigned long arg,
- unsigned int flags)
-{
- struct fuse_file *ff = file->private_data;
- struct fuse_mount *fm = ff->fm;
- struct fuse_ioctl_in inarg = {
- .fh = ff->fh,
- .cmd = cmd,
- .arg = arg,
- .flags = flags
- };
- struct fuse_ioctl_out outarg;
- struct iovec *iov_page = NULL;
- struct iovec *in_iov = NULL, *out_iov = NULL;
- unsigned int in_iovs = 0, out_iovs = 0, max_pages;
- size_t in_size, out_size, c;
- ssize_t transferred;
- int err, i;
- struct iov_iter ii;
- struct fuse_args_pages ap = {};
-
-#if BITS_PER_LONG == 32
- inarg.flags |= FUSE_IOCTL_32BIT;
-#else
- if (flags & FUSE_IOCTL_COMPAT) {
- inarg.flags |= FUSE_IOCTL_32BIT;
-#ifdef CONFIG_X86_X32
- if (in_x32_syscall())
- inarg.flags |= FUSE_IOCTL_COMPAT_X32;
-#endif
- }
-#endif
-
- /* assume all the iovs returned by client always fits in a page */
- BUILD_BUG_ON(sizeof(struct fuse_ioctl_iovec) * FUSE_IOCTL_MAX_IOV > PAGE_SIZE);
-
- err = -ENOMEM;
- ap.pages = fuse_pages_alloc(fm->fc->max_pages, GFP_KERNEL, &ap.descs);
- iov_page = (struct iovec *) __get_free_page(GFP_KERNEL);
- if (!ap.pages || !iov_page)
- goto out;
-
- fuse_page_descs_length_init(ap.descs, 0, fm->fc->max_pages);
-
- /*
- * If restricted, initialize IO parameters as encoded in @cmd.
- * RETRY from server is not allowed.
- */
- if (!(flags & FUSE_IOCTL_UNRESTRICTED)) {
- struct iovec *iov = iov_page;
-
- iov->iov_base = (void __user *)arg;
-
- switch (cmd) {
- case FS_IOC_GETFLAGS:
- case FS_IOC_SETFLAGS:
- iov->iov_len = sizeof(int);
- break;
- default:
- iov->iov_len = _IOC_SIZE(cmd);
- break;
- }
-
- if (_IOC_DIR(cmd) & _IOC_WRITE) {
- in_iov = iov;
- in_iovs = 1;
- }
-
- if (_IOC_DIR(cmd) & _IOC_READ) {
- out_iov = iov;
- out_iovs = 1;
- }
- }
-
- retry:
- inarg.in_size = in_size = iov_length(in_iov, in_iovs);
- inarg.out_size = out_size = iov_length(out_iov, out_iovs);
-
- /*
- * Out data can be used either for actual out data or iovs,
- * make sure there always is at least one page.
- */
- out_size = max_t(size_t, out_size, PAGE_SIZE);
- max_pages = DIV_ROUND_UP(max(in_size, out_size), PAGE_SIZE);
-
- /* make sure there are enough buffer pages and init request with them */
- err = -ENOMEM;
- if (max_pages > fm->fc->max_pages)
- goto out;
- while (ap.num_pages < max_pages) {
- ap.pages[ap.num_pages] = alloc_page(GFP_KERNEL | __GFP_HIGHMEM);
- if (!ap.pages[ap.num_pages])
- goto out;
- ap.num_pages++;
- }
-
-
- /* okay, let's send it to the client */
- ap.args.opcode = FUSE_IOCTL;
- ap.args.nodeid = ff->nodeid;
- ap.args.in_numargs = 1;
- ap.args.in_args[0].size = sizeof(inarg);
- ap.args.in_args[0].value = &inarg;
- if (in_size) {
- ap.args.in_numargs++;
- ap.args.in_args[1].size = in_size;
- ap.args.in_pages = true;
-
- err = -EFAULT;
- iov_iter_init(&ii, WRITE, in_iov, in_iovs, in_size);
- for (i = 0; iov_iter_count(&ii) && !WARN_ON(i >= ap.num_pages); i++) {
- c = copy_page_from_iter(ap.pages[i], 0, PAGE_SIZE, &ii);
- if (c != PAGE_SIZE && iov_iter_count(&ii))
- goto out;
- }
- }
-
- ap.args.out_numargs = 2;
- ap.args.out_args[0].size = sizeof(outarg);
- ap.args.out_args[0].value = &outarg;
- ap.args.out_args[1].size = out_size;
- ap.args.out_pages = true;
- ap.args.out_argvar = true;
-
- transferred = fuse_simple_request(fm, &ap.args);
- err = transferred;
- if (transferred < 0)
- goto out;
-
- /* did it ask for retry? */
- if (outarg.flags & FUSE_IOCTL_RETRY) {
- void *vaddr;
-
- /* no retry if in restricted mode */
- err = -EIO;
- if (!(flags & FUSE_IOCTL_UNRESTRICTED))
- goto out;
-
- in_iovs = outarg.in_iovs;
- out_iovs = outarg.out_iovs;
-
- /*
- * Make sure things are in boundary, separate checks
- * are to protect against overflow.
- */
- err = -ENOMEM;
- if (in_iovs > FUSE_IOCTL_MAX_IOV ||
- out_iovs > FUSE_IOCTL_MAX_IOV ||
- in_iovs + out_iovs > FUSE_IOCTL_MAX_IOV)
- goto out;
-
- vaddr = kmap_atomic(ap.pages[0]);
- err = fuse_copy_ioctl_iovec(fm->fc, iov_page, vaddr,
- transferred, in_iovs + out_iovs,
- (flags & FUSE_IOCTL_COMPAT) != 0);
- kunmap_atomic(vaddr);
- if (err)
- goto out;
-
- in_iov = iov_page;
- out_iov = in_iov + in_iovs;
-
- err = fuse_verify_ioctl_iov(fm->fc, in_iov, in_iovs);
- if (err)
- goto out;
-
- err = fuse_verify_ioctl_iov(fm->fc, out_iov, out_iovs);
- if (err)
- goto out;
-
- goto retry;
- }
-
- err = -EIO;
- if (transferred > inarg.out_size)
- goto out;
-
- err = -EFAULT;
- iov_iter_init(&ii, READ, out_iov, out_iovs, transferred);
- for (i = 0; iov_iter_count(&ii) && !WARN_ON(i >= ap.num_pages); i++) {
- c = copy_page_to_iter(ap.pages[i], 0, PAGE_SIZE, &ii);
- if (c != PAGE_SIZE && iov_iter_count(&ii))
- goto out;
- }
- err = 0;
- out:
- free_page((unsigned long) iov_page);
- while (ap.num_pages)
- __free_page(ap.pages[--ap.num_pages]);
- kfree(ap.pages);
-
- return err ? err : outarg.result;
-}
-EXPORT_SYMBOL_GPL(fuse_do_ioctl);
-
-long fuse_ioctl_common(struct file *file, unsigned int cmd,
- unsigned long arg, unsigned int flags)
-{
- struct inode *inode = file_inode(file);
- struct fuse_conn *fc = get_fuse_conn(inode);
-
- if (!fuse_allow_current_process(fc))
- return -EACCES;
-
- if (fuse_is_bad(inode))
- return -EIO;
-
- return fuse_do_ioctl(file, cmd, arg, flags);
-}
-
-static long fuse_file_ioctl(struct file *file, unsigned int cmd,
- unsigned long arg)
-{
- return fuse_ioctl_common(file, cmd, arg, 0);
-}
-
-static long fuse_file_compat_ioctl(struct file *file, unsigned int cmd,
- unsigned long arg)
-{
- return fuse_ioctl_common(file, cmd, arg, FUSE_IOCTL_COMPAT);
-}
-
-/*
* All files which have been polled are linked to RB tree
* fuse_conn->polled_files which is indexed by kh. Walk the tree and
* find the matching one.
diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h
index 68cca8d4db6e..7e463e220053 100644
--- a/fs/fuse/fuse_i.h
+++ b/fs/fuse/fuse_i.h
@@ -552,9 +552,12 @@ struct fuse_conn {
/** Maximum write size */
unsigned max_write;
- /** Maxmum number of pages that can be used in a single request */
+ /** Maximum number of pages that can be used in a single request */
unsigned int max_pages;
+ /** Constrain ->max_pages to this value during feature negotiation */
+ unsigned int max_pages_limit;
+
/** Input queue */
struct fuse_iqueue iq;
@@ -668,6 +671,9 @@ struct fuse_conn {
/** Is setxattr not implemented by fs? */
unsigned no_setxattr:1;
+ /** Does file server support extended setxattr */
+ unsigned setxattr_ext:1;
+
/** Is getxattr not implemented by fs? */
unsigned no_getxattr:1;
@@ -713,7 +719,7 @@ struct fuse_conn {
/** Use enhanced/automatic page cache invalidation. */
unsigned auto_inval_data:1;
- /** Filesystem is fully reponsible for page cache invalidation. */
+ /** Filesystem is fully responsible for page cache invalidation. */
unsigned explicit_inval_data:1;
/** Does the filesystem support readdirplus? */
@@ -863,6 +869,7 @@ static inline u64 fuse_get_attr_version(struct fuse_conn *fc)
static inline void fuse_make_bad(struct inode *inode)
{
+ remove_inode_hash(inode);
set_bit(FUSE_I_BAD, &get_fuse_inode(inode)->state);
}
@@ -871,6 +878,28 @@ static inline bool fuse_is_bad(struct inode *inode)
return unlikely(test_bit(FUSE_I_BAD, &get_fuse_inode(inode)->state));
}
+static inline struct page **fuse_pages_alloc(unsigned int npages, gfp_t flags,
+ struct fuse_page_desc **desc)
+{
+ struct page **pages;
+
+ pages = kzalloc(npages * (sizeof(struct page *) +
+ sizeof(struct fuse_page_desc)), flags);
+ *desc = (void *) (pages + npages);
+
+ return pages;
+}
+
+static inline void fuse_page_descs_length_init(struct fuse_page_desc *descs,
+ unsigned int index,
+ unsigned int nr_pages)
+{
+ int i;
+
+ for (i = index; i < index + nr_pages; i++)
+ descs[i].length = PAGE_SIZE - descs[i].offset;
+}
+
/** Device operations */
extern const struct file_operations fuse_dev_operations;
@@ -911,6 +940,7 @@ struct fuse_io_args {
struct {
struct fuse_write_in in;
struct fuse_write_out out;
+ bool page_locked;
} write;
};
struct fuse_args_pages ap;
@@ -931,7 +961,8 @@ struct fuse_file *fuse_file_alloc(struct fuse_mount *fm);
void fuse_file_free(struct fuse_file *ff);
void fuse_finish_open(struct inode *inode, struct file *file);
-void fuse_sync_release(struct fuse_inode *fi, struct fuse_file *ff, int flags);
+void fuse_sync_release(struct fuse_inode *fi, struct fuse_file *ff,
+ unsigned int flags);
/**
* Send RELEASE or RELEASEDIR request
@@ -1169,7 +1200,7 @@ void fuse_unlock_inode(struct inode *inode, bool locked);
bool fuse_lock_inode(struct inode *inode);
int fuse_setxattr(struct inode *inode, const char *name, const void *value,
- size_t size, int flags);
+ size_t size, int flags, unsigned int extra_flags);
ssize_t fuse_getxattr(struct inode *inode, const char *name, void *value,
size_t size);
ssize_t fuse_listxattr(struct dentry *entry, char *list, size_t size);
@@ -1213,4 +1244,19 @@ void fuse_dax_inode_cleanup(struct inode *inode);
bool fuse_dax_check_alignment(struct fuse_conn *fc, unsigned int map_alignment);
void fuse_dax_cancel_work(struct fuse_conn *fc);
+/* ioctl.c */
+long fuse_file_ioctl(struct file *file, unsigned int cmd, unsigned long arg);
+long fuse_file_compat_ioctl(struct file *file, unsigned int cmd,
+ unsigned long arg);
+int fuse_fileattr_get(struct dentry *dentry, struct fileattr *fa);
+int fuse_fileattr_set(struct user_namespace *mnt_userns,
+ struct dentry *dentry, struct fileattr *fa);
+
+/* file.c */
+
+struct fuse_file *fuse_file_open(struct fuse_mount *fm, u64 nodeid,
+ unsigned int open_flags, bool isdir);
+void fuse_file_release(struct inode *inode, struct fuse_file *ff,
+ unsigned int open_flags, fl_owner_t id, bool isdir);
+
#endif /* _FS_FUSE_I_H */
diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c
index b0e18b470e91..393e36b74dc4 100644
--- a/fs/fuse/inode.c
+++ b/fs/fuse/inode.c
@@ -350,7 +350,7 @@ retry:
inode->i_generation = generation;
fuse_init_inode(inode, attr);
unlock_new_inode(inode);
- } else if ((inode->i_mode ^ attr->mode) & S_IFMT) {
+ } else if (inode_wrong_type(inode, attr->mode)) {
/* Inode has changed type, any I/O on the old should fail */
fuse_make_bad(inode);
iput(inode);
@@ -712,6 +712,7 @@ void fuse_conn_init(struct fuse_conn *fc, struct fuse_mount *fm,
fc->pid_ns = get_pid_ns(task_active_pid_ns(current));
fc->user_ns = get_user_ns(user_ns);
fc->max_pages = FUSE_DEFAULT_MAX_PAGES_PER_REQ;
+ fc->max_pages_limit = FUSE_MAX_MAX_PAGES;
INIT_LIST_HEAD(&fc->mounts);
list_add(&fm->fc_entry, &fc->mounts);
@@ -872,14 +873,13 @@ static struct dentry *fuse_get_parent(struct dentry *child)
struct inode *inode;
struct dentry *parent;
struct fuse_entry_out outarg;
- const struct qstr name = QSTR_INIT("..", 2);
int err;
if (!fc->export_support)
return ERR_PTR(-ESTALE);
err = fuse_lookup_name(child_inode->i_sb, get_node_id(child_inode),
- &name, &outarg, &inode);
+ &dotdot_name, &outarg, &inode);
if (err) {
if (err == -ENOENT)
return ERR_PTR(-ESTALE);
@@ -1040,7 +1040,7 @@ static void process_init_reply(struct fuse_mount *fm, struct fuse_args *args,
fc->abort_err = 1;
if (arg->flags & FUSE_MAX_PAGES) {
fc->max_pages =
- min_t(unsigned int, FUSE_MAX_MAX_PAGES,
+ min_t(unsigned int, fc->max_pages_limit,
max_t(unsigned int, arg->max_pages, 1));
}
if (IS_ENABLED(CONFIG_FUSE_DAX) &&
@@ -1052,6 +1052,8 @@ static void process_init_reply(struct fuse_mount *fm, struct fuse_args *args,
fc->handle_killpriv_v2 = 1;
fm->sb->s_flags |= SB_NOSEC;
}
+ if (arg->flags & FUSE_SETXATTR_EXT)
+ fc->setxattr_ext = 1;
} else {
ra_pages = fc->max_read / PAGE_SIZE;
fc->no_lock = 1;
@@ -1095,7 +1097,7 @@ void fuse_send_init(struct fuse_mount *fm)
FUSE_PARALLEL_DIROPS | FUSE_HANDLE_KILLPRIV | FUSE_POSIX_ACL |
FUSE_ABORT_ERROR | FUSE_MAX_PAGES | FUSE_CACHE_SYMLINKS |
FUSE_NO_OPENDIR_SUPPORT | FUSE_EXPLICIT_INVAL_DATA |
- FUSE_HANDLE_KILLPRIV_V2;
+ FUSE_HANDLE_KILLPRIV_V2 | FUSE_SETXATTR_EXT;
#ifdef CONFIG_FUSE_DAX
if (fm->fc->dax)
ia->in.flags |= FUSE_MAP_ALIGNMENT;
diff --git a/fs/fuse/ioctl.c b/fs/fuse/ioctl.c
new file mode 100644
index 000000000000..546ea3d58fb4
--- /dev/null
+++ b/fs/fuse/ioctl.c
@@ -0,0 +1,490 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2017 Red Hat, Inc.
+ */
+
+#include "fuse_i.h"
+
+#include <linux/uio.h>
+#include <linux/compat.h>
+#include <linux/fileattr.h>
+
+/*
+ * CUSE servers compiled on 32bit broke on 64bit kernels because the
+ * ABI was defined to be 'struct iovec' which is different on 32bit
+ * and 64bit. Fortunately we can determine which structure the server
+ * used from the size of the reply.
+ */
+static int fuse_copy_ioctl_iovec_old(struct iovec *dst, void *src,
+ size_t transferred, unsigned count,
+ bool is_compat)
+{
+#ifdef CONFIG_COMPAT
+ if (count * sizeof(struct compat_iovec) == transferred) {
+ struct compat_iovec *ciov = src;
+ unsigned i;
+
+ /*
+ * With this interface a 32bit server cannot support
+ * non-compat (i.e. ones coming from 64bit apps) ioctl
+ * requests
+ */
+ if (!is_compat)
+ return -EINVAL;
+
+ for (i = 0; i < count; i++) {
+ dst[i].iov_base = compat_ptr(ciov[i].iov_base);
+ dst[i].iov_len = ciov[i].iov_len;
+ }
+ return 0;
+ }
+#endif
+
+ if (count * sizeof(struct iovec) != transferred)
+ return -EIO;
+
+ memcpy(dst, src, transferred);
+ return 0;
+}
+
+/* Make sure iov_length() won't overflow */
+static int fuse_verify_ioctl_iov(struct fuse_conn *fc, struct iovec *iov,
+ size_t count)
+{
+ size_t n;
+ u32 max = fc->max_pages << PAGE_SHIFT;
+
+ for (n = 0; n < count; n++, iov++) {
+ if (iov->iov_len > (size_t) max)
+ return -ENOMEM;
+ max -= iov->iov_len;
+ }
+ return 0;
+}
+
+static int fuse_copy_ioctl_iovec(struct fuse_conn *fc, struct iovec *dst,
+ void *src, size_t transferred, unsigned count,
+ bool is_compat)
+{
+ unsigned i;
+ struct fuse_ioctl_iovec *fiov = src;
+
+ if (fc->minor < 16) {
+ return fuse_copy_ioctl_iovec_old(dst, src, transferred,
+ count, is_compat);
+ }
+
+ if (count * sizeof(struct fuse_ioctl_iovec) != transferred)
+ return -EIO;
+
+ for (i = 0; i < count; i++) {
+ /* Did the server supply an inappropriate value? */
+ if (fiov[i].base != (unsigned long) fiov[i].base ||
+ fiov[i].len != (unsigned long) fiov[i].len)
+ return -EIO;
+
+ dst[i].iov_base = (void __user *) (unsigned long) fiov[i].base;
+ dst[i].iov_len = (size_t) fiov[i].len;
+
+#ifdef CONFIG_COMPAT
+ if (is_compat &&
+ (ptr_to_compat(dst[i].iov_base) != fiov[i].base ||
+ (compat_size_t) dst[i].iov_len != fiov[i].len))
+ return -EIO;
+#endif
+ }
+
+ return 0;
+}
+
+
+/*
+ * For ioctls, there is no generic way to determine how much memory
+ * needs to be read and/or written. Furthermore, ioctls are allowed
+ * to dereference the passed pointer, so the parameter requires deep
+ * copying but FUSE has no idea whatsoever about what to copy in or
+ * out.
+ *
+ * This is solved by allowing FUSE server to retry ioctl with
+ * necessary in/out iovecs. Let's assume the ioctl implementation
+ * needs to read in the following structure.
+ *
+ * struct a {
+ * char *buf;
+ * size_t buflen;
+ * }
+ *
+ * On the first callout to FUSE server, inarg->in_size and
+ * inarg->out_size will be NULL; then, the server completes the ioctl
+ * with FUSE_IOCTL_RETRY set in out->flags, out->in_iovs set to 1 and
+ * the actual iov array to
+ *
+ * { { .iov_base = inarg.arg, .iov_len = sizeof(struct a) } }
+ *
+ * which tells FUSE to copy in the requested area and retry the ioctl.
+ * On the second round, the server has access to the structure and
+ * from that it can tell what to look for next, so on the invocation,
+ * it sets FUSE_IOCTL_RETRY, out->in_iovs to 2 and iov array to
+ *
+ * { { .iov_base = inarg.arg, .iov_len = sizeof(struct a) },
+ * { .iov_base = a.buf, .iov_len = a.buflen } }
+ *
+ * FUSE will copy both struct a and the pointed buffer from the
+ * process doing the ioctl and retry ioctl with both struct a and the
+ * buffer.
+ *
+ * This time, FUSE server has everything it needs and completes ioctl
+ * without FUSE_IOCTL_RETRY which finishes the ioctl call.
+ *
+ * Copying data out works the same way.
+ *
+ * Note that if FUSE_IOCTL_UNRESTRICTED is clear, the kernel
+ * automatically initializes in and out iovs by decoding @cmd with
+ * _IOC_* macros and the server is not allowed to request RETRY. This
+ * limits ioctl data transfers to well-formed ioctls and is the forced
+ * behavior for all FUSE servers.
+ */
+long fuse_do_ioctl(struct file *file, unsigned int cmd, unsigned long arg,
+ unsigned int flags)
+{
+ struct fuse_file *ff = file->private_data;
+ struct fuse_mount *fm = ff->fm;
+ struct fuse_ioctl_in inarg = {
+ .fh = ff->fh,
+ .cmd = cmd,
+ .arg = arg,
+ .flags = flags
+ };
+ struct fuse_ioctl_out outarg;
+ struct iovec *iov_page = NULL;
+ struct iovec *in_iov = NULL, *out_iov = NULL;
+ unsigned int in_iovs = 0, out_iovs = 0, max_pages;
+ size_t in_size, out_size, c;
+ ssize_t transferred;
+ int err, i;
+ struct iov_iter ii;
+ struct fuse_args_pages ap = {};
+
+#if BITS_PER_LONG == 32
+ inarg.flags |= FUSE_IOCTL_32BIT;
+#else
+ if (flags & FUSE_IOCTL_COMPAT) {
+ inarg.flags |= FUSE_IOCTL_32BIT;
+#ifdef CONFIG_X86_X32
+ if (in_x32_syscall())
+ inarg.flags |= FUSE_IOCTL_COMPAT_X32;
+#endif
+ }
+#endif
+
+ /* assume all the iovs returned by client always fits in a page */
+ BUILD_BUG_ON(sizeof(struct fuse_ioctl_iovec) * FUSE_IOCTL_MAX_IOV > PAGE_SIZE);
+
+ err = -ENOMEM;
+ ap.pages = fuse_pages_alloc(fm->fc->max_pages, GFP_KERNEL, &ap.descs);
+ iov_page = (struct iovec *) __get_free_page(GFP_KERNEL);
+ if (!ap.pages || !iov_page)
+ goto out;
+
+ fuse_page_descs_length_init(ap.descs, 0, fm->fc->max_pages);
+
+ /*
+ * If restricted, initialize IO parameters as encoded in @cmd.
+ * RETRY from server is not allowed.
+ */
+ if (!(flags & FUSE_IOCTL_UNRESTRICTED)) {
+ struct iovec *iov = iov_page;
+
+ iov->iov_base = (void __user *)arg;
+ iov->iov_len = _IOC_SIZE(cmd);
+
+ if (_IOC_DIR(cmd) & _IOC_WRITE) {
+ in_iov = iov;
+ in_iovs = 1;
+ }
+
+ if (_IOC_DIR(cmd) & _IOC_READ) {
+ out_iov = iov;
+ out_iovs = 1;
+ }
+ }
+
+ retry:
+ inarg.in_size = in_size = iov_length(in_iov, in_iovs);
+ inarg.out_size = out_size = iov_length(out_iov, out_iovs);
+
+ /*
+ * Out data can be used either for actual out data or iovs,
+ * make sure there always is at least one page.
+ */
+ out_size = max_t(size_t, out_size, PAGE_SIZE);
+ max_pages = DIV_ROUND_UP(max(in_size, out_size), PAGE_SIZE);
+
+ /* make sure there are enough buffer pages and init request with them */
+ err = -ENOMEM;
+ if (max_pages > fm->fc->max_pages)
+ goto out;
+ while (ap.num_pages < max_pages) {
+ ap.pages[ap.num_pages] = alloc_page(GFP_KERNEL | __GFP_HIGHMEM);
+ if (!ap.pages[ap.num_pages])
+ goto out;
+ ap.num_pages++;
+ }
+
+
+ /* okay, let's send it to the client */
+ ap.args.opcode = FUSE_IOCTL;
+ ap.args.nodeid = ff->nodeid;
+ ap.args.in_numargs = 1;
+ ap.args.in_args[0].size = sizeof(inarg);
+ ap.args.in_args[0].value = &inarg;
+ if (in_size) {
+ ap.args.in_numargs++;
+ ap.args.in_args[1].size = in_size;
+ ap.args.in_pages = true;
+
+ err = -EFAULT;
+ iov_iter_init(&ii, WRITE, in_iov, in_iovs, in_size);
+ for (i = 0; iov_iter_count(&ii) && !WARN_ON(i >= ap.num_pages); i++) {
+ c = copy_page_from_iter(ap.pages[i], 0, PAGE_SIZE, &ii);
+ if (c != PAGE_SIZE && iov_iter_count(&ii))
+ goto out;
+ }
+ }
+
+ ap.args.out_numargs = 2;
+ ap.args.out_args[0].size = sizeof(outarg);
+ ap.args.out_args[0].value = &outarg;
+ ap.args.out_args[1].size = out_size;
+ ap.args.out_pages = true;
+ ap.args.out_argvar = true;
+
+ transferred = fuse_simple_request(fm, &ap.args);
+ err = transferred;
+ if (transferred < 0)
+ goto out;
+
+ /* did it ask for retry? */
+ if (outarg.flags & FUSE_IOCTL_RETRY) {
+ void *vaddr;
+
+ /* no retry if in restricted mode */
+ err = -EIO;
+ if (!(flags & FUSE_IOCTL_UNRESTRICTED))
+ goto out;
+
+ in_iovs = outarg.in_iovs;
+ out_iovs = outarg.out_iovs;
+
+ /*
+ * Make sure things are in boundary, separate checks
+ * are to protect against overflow.
+ */
+ err = -ENOMEM;
+ if (in_iovs > FUSE_IOCTL_MAX_IOV ||
+ out_iovs > FUSE_IOCTL_MAX_IOV ||
+ in_iovs + out_iovs > FUSE_IOCTL_MAX_IOV)
+ goto out;
+
+ vaddr = kmap_atomic(ap.pages[0]);
+ err = fuse_copy_ioctl_iovec(fm->fc, iov_page, vaddr,
+ transferred, in_iovs + out_iovs,
+ (flags & FUSE_IOCTL_COMPAT) != 0);
+ kunmap_atomic(vaddr);
+ if (err)
+ goto out;
+
+ in_iov = iov_page;
+ out_iov = in_iov + in_iovs;
+
+ err = fuse_verify_ioctl_iov(fm->fc, in_iov, in_iovs);
+ if (err)
+ goto out;
+
+ err = fuse_verify_ioctl_iov(fm->fc, out_iov, out_iovs);
+ if (err)
+ goto out;
+
+ goto retry;
+ }
+
+ err = -EIO;
+ if (transferred > inarg.out_size)
+ goto out;
+
+ err = -EFAULT;
+ iov_iter_init(&ii, READ, out_iov, out_iovs, transferred);
+ for (i = 0; iov_iter_count(&ii) && !WARN_ON(i >= ap.num_pages); i++) {
+ c = copy_page_to_iter(ap.pages[i], 0, PAGE_SIZE, &ii);
+ if (c != PAGE_SIZE && iov_iter_count(&ii))
+ goto out;
+ }
+ err = 0;
+ out:
+ free_page((unsigned long) iov_page);
+ while (ap.num_pages)
+ __free_page(ap.pages[--ap.num_pages]);
+ kfree(ap.pages);
+
+ return err ? err : outarg.result;
+}
+EXPORT_SYMBOL_GPL(fuse_do_ioctl);
+
+long fuse_ioctl_common(struct file *file, unsigned int cmd,
+ unsigned long arg, unsigned int flags)
+{
+ struct inode *inode = file_inode(file);
+ struct fuse_conn *fc = get_fuse_conn(inode);
+
+ if (!fuse_allow_current_process(fc))
+ return -EACCES;
+
+ if (fuse_is_bad(inode))
+ return -EIO;
+
+ return fuse_do_ioctl(file, cmd, arg, flags);
+}
+
+long fuse_file_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
+{
+ return fuse_ioctl_common(file, cmd, arg, 0);
+}
+
+long fuse_file_compat_ioctl(struct file *file, unsigned int cmd,
+ unsigned long arg)
+{
+ return fuse_ioctl_common(file, cmd, arg, FUSE_IOCTL_COMPAT);
+}
+
+static int fuse_priv_ioctl(struct inode *inode, struct fuse_file *ff,
+ unsigned int cmd, void *ptr, size_t size)
+{
+ struct fuse_mount *fm = ff->fm;
+ struct fuse_ioctl_in inarg;
+ struct fuse_ioctl_out outarg;
+ FUSE_ARGS(args);
+ int err;
+
+ memset(&inarg, 0, sizeof(inarg));
+ inarg.fh = ff->fh;
+ inarg.cmd = cmd;
+
+#if BITS_PER_LONG == 32
+ inarg.flags |= FUSE_IOCTL_32BIT;
+#endif
+ if (S_ISDIR(inode->i_mode))
+ inarg.flags |= FUSE_IOCTL_DIR;
+
+ if (_IOC_DIR(cmd) & _IOC_READ)
+ inarg.out_size = size;
+ if (_IOC_DIR(cmd) & _IOC_WRITE)
+ inarg.in_size = size;
+
+ args.opcode = FUSE_IOCTL;
+ args.nodeid = ff->nodeid;
+ args.in_numargs = 2;
+ args.in_args[0].size = sizeof(inarg);
+ args.in_args[0].value = &inarg;
+ args.in_args[1].size = inarg.in_size;
+ args.in_args[1].value = ptr;
+ args.out_numargs = 2;
+ args.out_args[0].size = sizeof(outarg);
+ args.out_args[0].value = &outarg;
+ args.out_args[1].size = inarg.out_size;
+ args.out_args[1].value = ptr;
+
+ err = fuse_simple_request(fm, &args);
+ if (!err && outarg.flags & FUSE_IOCTL_RETRY)
+ err = -EIO;
+
+ return err;
+}
+
+static struct fuse_file *fuse_priv_ioctl_prepare(struct inode *inode)
+{
+ struct fuse_mount *fm = get_fuse_mount(inode);
+ bool isdir = S_ISDIR(inode->i_mode);
+
+ if (!S_ISREG(inode->i_mode) && !isdir)
+ return ERR_PTR(-ENOTTY);
+
+ return fuse_file_open(fm, get_node_id(inode), O_RDONLY, isdir);
+}
+
+static void fuse_priv_ioctl_cleanup(struct inode *inode, struct fuse_file *ff)
+{
+ fuse_file_release(inode, ff, O_RDONLY, NULL, S_ISDIR(inode->i_mode));
+}
+
+int fuse_fileattr_get(struct dentry *dentry, struct fileattr *fa)
+{
+ struct inode *inode = d_inode(dentry);
+ struct fuse_file *ff;
+ unsigned int flags;
+ struct fsxattr xfa;
+ int err;
+
+ ff = fuse_priv_ioctl_prepare(inode);
+ if (IS_ERR(ff))
+ return PTR_ERR(ff);
+
+ if (fa->flags_valid) {
+ err = fuse_priv_ioctl(inode, ff, FS_IOC_GETFLAGS,
+ &flags, sizeof(flags));
+ if (err)
+ goto cleanup;
+
+ fileattr_fill_flags(fa, flags);
+ } else {
+ err = fuse_priv_ioctl(inode, ff, FS_IOC_FSGETXATTR,
+ &xfa, sizeof(xfa));
+ if (err)
+ goto cleanup;
+
+ fileattr_fill_xflags(fa, xfa.fsx_xflags);
+ fa->fsx_extsize = xfa.fsx_extsize;
+ fa->fsx_nextents = xfa.fsx_nextents;
+ fa->fsx_projid = xfa.fsx_projid;
+ fa->fsx_cowextsize = xfa.fsx_cowextsize;
+ }
+cleanup:
+ fuse_priv_ioctl_cleanup(inode, ff);
+
+ return err;
+}
+
+int fuse_fileattr_set(struct user_namespace *mnt_userns,
+ struct dentry *dentry, struct fileattr *fa)
+{
+ struct inode *inode = d_inode(dentry);
+ struct fuse_file *ff;
+ unsigned int flags = fa->flags;
+ struct fsxattr xfa;
+ int err;
+
+ ff = fuse_priv_ioctl_prepare(inode);
+ if (IS_ERR(ff))
+ return PTR_ERR(ff);
+
+ if (fa->flags_valid) {
+ err = fuse_priv_ioctl(inode, ff, FS_IOC_SETFLAGS,
+ &flags, sizeof(flags));
+ if (err)
+ goto cleanup;
+ } else {
+ memset(&xfa, 0, sizeof(xfa));
+ xfa.fsx_xflags = fa->fsx_xflags;
+ xfa.fsx_extsize = fa->fsx_extsize;
+ xfa.fsx_nextents = fa->fsx_nextents;
+ xfa.fsx_projid = fa->fsx_projid;
+ xfa.fsx_cowextsize = fa->fsx_cowextsize;
+
+ err = fuse_priv_ioctl(inode, ff, FS_IOC_FSSETXATTR,
+ &xfa, sizeof(xfa));
+ }
+
+cleanup:
+ fuse_priv_ioctl_cleanup(inode, ff);
+
+ return err;
+}
diff --git a/fs/fuse/readdir.c b/fs/fuse/readdir.c
index 3441ffa740f3..277f7041d55a 100644
--- a/fs/fuse/readdir.c
+++ b/fs/fuse/readdir.c
@@ -202,7 +202,7 @@ retry:
inode = d_inode(dentry);
if (!inode ||
get_node_id(inode) != o->nodeid ||
- ((o->attr.mode ^ inode->i_mode) & S_IFMT)) {
+ inode_wrong_type(inode, o->attr.mode)) {
d_invalidate(dentry);
dput(dentry);
goto retry;
diff --git a/fs/fuse/virtio_fs.c b/fs/fuse/virtio_fs.c
index 8868ac31a3c0..bcb8a02e2d8b 100644
--- a/fs/fuse/virtio_fs.c
+++ b/fs/fuse/virtio_fs.c
@@ -18,6 +18,12 @@
#include <linux/uio.h>
#include "fuse_i.h"
+/* Used to help calculate the FUSE connection's max_pages limit for a request's
+ * size. Parts of the struct fuse_req are sliced into scattergather lists in
+ * addition to the pages used, so this can help account for that overhead.
+ */
+#define FUSE_HEADER_OVERHEAD 4
+
/* List of virtio-fs device instances and a lock for the list. Also provides
* mutual exclusion in device removal and mounting path
*/
@@ -127,11 +133,6 @@ static inline struct virtio_fs_vq *vq_to_fsvq(struct virtqueue *vq)
return &fs->vqs[vq->index];
}
-static inline struct fuse_pqueue *vq_to_fpq(struct virtqueue *vq)
-{
- return &vq_to_fsvq(vq)->fud->pq;
-}
-
/* Should be called with fsvq->lock held. */
static inline void inc_in_flight_req(struct virtio_fs_vq *fsvq)
{
@@ -896,6 +897,7 @@ static int virtio_fs_probe(struct virtio_device *vdev)
out_vqs:
vdev->config->reset(vdev);
virtio_fs_cleanup_vqs(vdev, fs);
+ kfree(fs->vqs);
out:
vdev->priv = NULL;
@@ -1324,8 +1326,15 @@ static int virtio_fs_fill_super(struct super_block *sb, struct fs_context *fsc)
/* virtiofs allocates and installs its own fuse devices */
ctx->fudptr = NULL;
- if (ctx->dax)
+ if (ctx->dax) {
+ if (!fs->dax_dev) {
+ err = -EINVAL;
+ pr_err("virtio-fs: dax can't be enabled as filesystem"
+ " device does not support it.\n");
+ goto err_free_fuse_devs;
+ }
ctx->dax_dev = fs->dax_dev;
+ }
err = fuse_fill_super_common(sb, ctx);
if (err < 0)
goto err_free_fuse_devs;
@@ -1406,9 +1415,10 @@ static int virtio_fs_get_tree(struct fs_context *fsc)
{
struct virtio_fs *fs;
struct super_block *sb;
- struct fuse_conn *fc;
+ struct fuse_conn *fc = NULL;
struct fuse_mount *fm;
- int err;
+ unsigned int virtqueue_size;
+ int err = -EIO;
/* This gets a reference on virtio_fs object. This ptr gets installed
* in fc->iq->priv. Once fuse_conn is going away, it calls ->put()
@@ -1420,6 +1430,10 @@ static int virtio_fs_get_tree(struct fs_context *fsc)
return -EINVAL;
}
+ virtqueue_size = virtqueue_get_vring_size(fs->vqs[VQ_REQUEST].vq);
+ if (WARN_ON(virtqueue_size <= FUSE_HEADER_OVERHEAD))
+ goto out_err;
+
err = -ENOMEM;
fc = kzalloc(sizeof(struct fuse_conn), GFP_KERNEL);
if (!fc)
@@ -1429,12 +1443,15 @@ static int virtio_fs_get_tree(struct fs_context *fsc)
if (!fm)
goto out_err;
- fuse_conn_init(fc, fm, get_user_ns(current_user_ns()),
- &virtio_fs_fiq_ops, fs);
+ fuse_conn_init(fc, fm, fsc->user_ns, &virtio_fs_fiq_ops, fs);
fc->release = fuse_free_conn;
fc->delete_stale = true;
fc->auto_submounts = true;
+ /* Tell FUSE to split requests that exceed the virtqueue's size */
+ fc->max_pages_limit = min_t(unsigned int, fc->max_pages_limit,
+ virtqueue_size - FUSE_HEADER_OVERHEAD);
+
fsc->s_fs_info = fm;
sb = sget_fc(fsc, virtio_fs_test_super, set_anon_super_fc);
if (fsc->s_fs_info) {
diff --git a/fs/fuse/xattr.c b/fs/fuse/xattr.c
index 1a7d7ace54e1..61dfaf7b7d20 100644
--- a/fs/fuse/xattr.c
+++ b/fs/fuse/xattr.c
@@ -12,7 +12,7 @@
#include <linux/posix_acl_xattr.h>
int fuse_setxattr(struct inode *inode, const char *name, const void *value,
- size_t size, int flags)
+ size_t size, int flags, unsigned int extra_flags)
{
struct fuse_mount *fm = get_fuse_mount(inode);
FUSE_ARGS(args);
@@ -25,10 +25,13 @@ int fuse_setxattr(struct inode *inode, const char *name, const void *value,
memset(&inarg, 0, sizeof(inarg));
inarg.size = size;
inarg.flags = flags;
+ inarg.setxattr_flags = extra_flags;
+
args.opcode = FUSE_SETXATTR;
args.nodeid = get_node_id(inode);
args.in_numargs = 3;
- args.in_args[0].size = sizeof(inarg);
+ args.in_args[0].size = fm->fc->setxattr_ext ?
+ sizeof(inarg) : FUSE_COMPAT_SETXATTR_IN_SIZE;
args.in_args[0].value = &inarg;
args.in_args[1].size = strlen(name) + 1;
args.in_args[1].value = name;
@@ -199,7 +202,7 @@ static int fuse_xattr_set(const struct xattr_handler *handler,
if (!value)
return fuse_removexattr(inode, name);
- return fuse_setxattr(inode, name, value, size, flags);
+ return fuse_setxattr(inode, name, value, size, flags, 0);
}
static bool no_xattr_list(struct dentry *dentry)
diff --git a/fs/gfs2/aops.c b/fs/gfs2/aops.c
index cc4f987687f3..23b5be3db044 100644
--- a/fs/gfs2/aops.c
+++ b/fs/gfs2/aops.c
@@ -540,10 +540,7 @@ int gfs2_internal_read(struct gfs2_inode *ip, char *buf, loff_t *pos,
/**
* gfs2_readahead - Read a bunch of pages at once
- * @file: The file to read from
- * @mapping: Address space info
- * @pages: List of pages to read
- * @nr_pages: Number of pages to read
+ * @rac: Read-ahead control structure
*
* Some notes:
* 1. This is only for readahead, so we can simply ignore any things
diff --git a/fs/gfs2/bmap.c b/fs/gfs2/bmap.c
index 7a358ae05185..0bcf11a9987b 100644
--- a/fs/gfs2/bmap.c
+++ b/fs/gfs2/bmap.c
@@ -331,7 +331,7 @@ static int __fillup_metapath(struct gfs2_inode *ip, struct metapath *mp,
if (!dblock)
break;
- ret = gfs2_meta_indirect_buffer(ip, x + 1, dblock, &mp->mp_bh[x + 1]);
+ ret = gfs2_meta_buffer(ip, GFS2_METATYPE_IN, dblock, &mp->mp_bh[x + 1]);
if (ret)
return ret;
}
@@ -632,7 +632,7 @@ enum alloc_state {
};
/**
- * gfs2_iomap_alloc - Build a metadata tree of the requested height
+ * __gfs2_iomap_alloc - Build a metadata tree of the requested height
* @inode: The GFS2 inode
* @iomap: The iomap structure
* @mp: The metapath, with proper height information calculated
@@ -642,7 +642,7 @@ enum alloc_state {
* ii) Indirect blocks to fill in lower part of the metadata tree
* iii) Data blocks
*
- * This function is called after gfs2_iomap_get, which works out the
+ * This function is called after __gfs2_iomap_get, which works out the
* total number of blocks which we need via gfs2_alloc_size.
*
* We then do the actual allocation asking for an extent at a time (if
@@ -660,8 +660,8 @@ enum alloc_state {
* Returns: errno on error
*/
-static int gfs2_iomap_alloc(struct inode *inode, struct iomap *iomap,
- struct metapath *mp)
+static int __gfs2_iomap_alloc(struct inode *inode, struct iomap *iomap,
+ struct metapath *mp)
{
struct gfs2_inode *ip = GFS2_I(inode);
struct gfs2_sbd *sdp = GFS2_SB(inode);
@@ -802,10 +802,10 @@ static u64 gfs2_alloc_size(struct inode *inode, struct metapath *mp, u64 size)
/*
* For writes to stuffed files, this function is called twice via
- * gfs2_iomap_get, before and after unstuffing. The size we return the
+ * __gfs2_iomap_get, before and after unstuffing. The size we return the
* first time needs to be large enough to get the reservation and
* allocation sizes right. The size we return the second time must
- * be exact or else gfs2_iomap_alloc won't do the right thing.
+ * be exact or else __gfs2_iomap_alloc won't do the right thing.
*/
if (gfs2_is_stuffed(ip) || mp->mp_fheight != mp->mp_aheight) {
@@ -829,7 +829,7 @@ static u64 gfs2_alloc_size(struct inode *inode, struct metapath *mp, u64 size)
}
/**
- * gfs2_iomap_get - Map blocks from an inode to disk blocks
+ * __gfs2_iomap_get - Map blocks from an inode to disk blocks
* @inode: The inode
* @pos: Starting position in bytes
* @length: Length to map, in bytes
@@ -839,9 +839,9 @@ static u64 gfs2_alloc_size(struct inode *inode, struct metapath *mp, u64 size)
*
* Returns: errno
*/
-static int gfs2_iomap_get(struct inode *inode, loff_t pos, loff_t length,
- unsigned flags, struct iomap *iomap,
- struct metapath *mp)
+static int __gfs2_iomap_get(struct inode *inode, loff_t pos, loff_t length,
+ unsigned flags, struct iomap *iomap,
+ struct metapath *mp)
{
struct gfs2_inode *ip = GFS2_I(inode);
struct gfs2_sbd *sdp = GFS2_SB(inode);
@@ -961,32 +961,6 @@ hole_found:
goto out;
}
-/**
- * gfs2_lblk_to_dblk - convert logical block to disk block
- * @inode: the inode of the file we're mapping
- * @lblock: the block relative to the start of the file
- * @dblock: the returned dblock, if no error
- *
- * This function maps a single block from a file logical block (relative to
- * the start of the file) to a file system absolute block using iomap.
- *
- * Returns: the absolute file system block, or an error
- */
-int gfs2_lblk_to_dblk(struct inode *inode, u32 lblock, u64 *dblock)
-{
- struct iomap iomap = { };
- struct metapath mp = { .mp_aheight = 1, };
- loff_t pos = (loff_t)lblock << inode->i_blkbits;
- int ret;
-
- ret = gfs2_iomap_get(inode, pos, i_blocksize(inode), 0, &iomap, &mp);
- release_metapath(&mp);
- if (ret == 0)
- *dblock = iomap.addr >> inode->i_blkbits;
-
- return ret;
-}
-
static int gfs2_write_lock(struct inode *inode)
{
struct gfs2_inode *ip = GFS2_I(inode);
@@ -1109,14 +1083,14 @@ static int gfs2_iomap_begin_write(struct inode *inode, loff_t pos,
if (ret)
goto out_trans_end;
release_metapath(mp);
- ret = gfs2_iomap_get(inode, iomap->offset,
- iomap->length, flags, iomap, mp);
+ ret = __gfs2_iomap_get(inode, iomap->offset,
+ iomap->length, flags, iomap, mp);
if (ret)
goto out_trans_end;
}
if (iomap->type == IOMAP_HOLE) {
- ret = gfs2_iomap_alloc(inode, iomap, mp);
+ ret = __gfs2_iomap_alloc(inode, iomap, mp);
if (ret) {
gfs2_trans_end(sdp);
gfs2_inplace_release(ip);
@@ -1168,7 +1142,7 @@ static int gfs2_iomap_begin(struct inode *inode, loff_t pos, loff_t length,
goto out;
}
- ret = gfs2_iomap_get(inode, pos, length, flags, iomap, &mp);
+ ret = __gfs2_iomap_get(inode, pos, length, flags, iomap, &mp);
if (ret)
goto out_unlock;
@@ -1290,9 +1264,7 @@ int gfs2_block_map(struct inode *inode, sector_t lblock,
struct gfs2_inode *ip = GFS2_I(inode);
loff_t pos = (loff_t)lblock << inode->i_blkbits;
loff_t length = bh_map->b_size;
- struct metapath mp = { .mp_aheight = 1, };
struct iomap iomap = { };
- int flags = create ? IOMAP_WRITE : 0;
int ret;
clear_buffer_mapped(bh_map);
@@ -1300,10 +1272,10 @@ int gfs2_block_map(struct inode *inode, sector_t lblock,
clear_buffer_boundary(bh_map);
trace_gfs2_bmap(ip, bh_map, lblock, create, 1);
- ret = gfs2_iomap_get(inode, pos, length, flags, &iomap, &mp);
- if (create && !ret && iomap.type == IOMAP_HOLE)
- ret = gfs2_iomap_alloc(inode, &iomap, &mp);
- release_metapath(&mp);
+ if (!create)
+ ret = gfs2_iomap_get(inode, pos, length, &iomap);
+ else
+ ret = gfs2_iomap_alloc(inode, pos, length, &iomap);
if (ret)
goto out;
@@ -1324,28 +1296,47 @@ out:
return ret;
}
-/*
- * Deprecated: do not use in new code
- */
-int gfs2_extent_map(struct inode *inode, u64 lblock, int *new, u64 *dblock, unsigned *extlen)
+int gfs2_get_extent(struct inode *inode, u64 lblock, u64 *dblock,
+ unsigned int *extlen)
{
- struct buffer_head bh = { .b_state = 0, .b_blocknr = 0 };
+ unsigned int blkbits = inode->i_blkbits;
+ struct iomap iomap = { };
+ unsigned int len;
int ret;
- int create = *new;
-
- BUG_ON(!extlen);
- BUG_ON(!dblock);
- BUG_ON(!new);
-
- bh.b_size = BIT(inode->i_blkbits + (create ? 0 : 5));
- ret = gfs2_block_map(inode, lblock, &bh, create);
- *extlen = bh.b_size >> inode->i_blkbits;
- *dblock = bh.b_blocknr;
- if (buffer_new(&bh))
- *new = 1;
- else
- *new = 0;
- return ret;
+
+ ret = gfs2_iomap_get(inode, lblock << blkbits, *extlen << blkbits,
+ &iomap);
+ if (ret)
+ return ret;
+ if (iomap.type != IOMAP_MAPPED)
+ return -EIO;
+ *dblock = iomap.addr >> blkbits;
+ len = iomap.length >> blkbits;
+ if (len < *extlen)
+ *extlen = len;
+ return 0;
+}
+
+int gfs2_alloc_extent(struct inode *inode, u64 lblock, u64 *dblock,
+ unsigned int *extlen, bool *new)
+{
+ unsigned int blkbits = inode->i_blkbits;
+ struct iomap iomap = { };
+ unsigned int len;
+ int ret;
+
+ ret = gfs2_iomap_alloc(inode, lblock << blkbits, *extlen << blkbits,
+ &iomap);
+ if (ret)
+ return ret;
+ if (iomap.type != IOMAP_MAPPED)
+ return -EIO;
+ *dblock = iomap.addr >> blkbits;
+ len = iomap.length >> blkbits;
+ if (len < *extlen)
+ *extlen = len;
+ *new = iomap.flags & IOMAP_F_NEW;
+ return 0;
}
/*
@@ -1461,15 +1452,26 @@ out:
return error;
}
-int gfs2_iomap_get_alloc(struct inode *inode, loff_t pos, loff_t length,
- struct iomap *iomap)
+int gfs2_iomap_get(struct inode *inode, loff_t pos, loff_t length,
+ struct iomap *iomap)
{
struct metapath mp = { .mp_aheight = 1, };
int ret;
- ret = gfs2_iomap_get(inode, pos, length, IOMAP_WRITE, iomap, &mp);
+ ret = __gfs2_iomap_get(inode, pos, length, 0, iomap, &mp);
+ release_metapath(&mp);
+ return ret;
+}
+
+int gfs2_iomap_alloc(struct inode *inode, loff_t pos, loff_t length,
+ struct iomap *iomap)
+{
+ struct metapath mp = { .mp_aheight = 1, };
+ int ret;
+
+ ret = __gfs2_iomap_get(inode, pos, length, IOMAP_WRITE, iomap, &mp);
if (!ret && iomap->type == IOMAP_HOLE)
- ret = gfs2_iomap_alloc(inode, iomap, &mp);
+ ret = __gfs2_iomap_alloc(inode, iomap, &mp);
release_metapath(&mp);
return ret;
}
@@ -1477,7 +1479,7 @@ int gfs2_iomap_get_alloc(struct inode *inode, loff_t pos, loff_t length,
/**
* sweep_bh_for_rgrps - find an rgrp in a meta buffer and free blocks therein
* @ip: inode
- * @rg_gh: holder of resource group glock
+ * @rd_gh: holder of resource group glock
* @bh: buffer head to sweep
* @start: starting point in bh
* @end: end point in bh
@@ -1658,8 +1660,11 @@ static bool mp_eq_to_hgt(struct metapath *mp, __u16 *list, unsigned int h)
/**
* find_nonnull_ptr - find a non-null pointer given a metapath and height
+ * @sdp: The superblock
* @mp: starting metapath
* @h: desired height to search
+ * @end_list: See punch_hole().
+ * @end_aligned: See punch_hole().
*
* Assumes the metapath is valid (with buffers) out to height h.
* Returns: true if a non-null pointer was found in the metapath buffer
@@ -2519,7 +2524,6 @@ out:
static int gfs2_map_blocks(struct iomap_writepage_ctx *wpc, struct inode *inode,
loff_t offset)
{
- struct metapath mp = { .mp_aheight = 1, };
int ret;
if (WARN_ON_ONCE(gfs2_is_stuffed(GFS2_I(inode))))
@@ -2530,8 +2534,7 @@ static int gfs2_map_blocks(struct iomap_writepage_ctx *wpc, struct inode *inode,
return 0;
memset(&wpc->iomap, 0, sizeof(wpc->iomap));
- ret = gfs2_iomap_get(inode, offset, INT_MAX, 0, &wpc->iomap, &mp);
- release_metapath(&mp);
+ ret = gfs2_iomap_get(inode, offset, INT_MAX, &wpc->iomap);
return ret;
}
diff --git a/fs/gfs2/bmap.h b/fs/gfs2/bmap.h
index aed4632d47d3..6676d863faef 100644
--- a/fs/gfs2/bmap.h
+++ b/fs/gfs2/bmap.h
@@ -49,10 +49,14 @@ extern const struct iomap_writeback_ops gfs2_writeback_ops;
extern int gfs2_unstuff_dinode(struct gfs2_inode *ip, struct page *page);
extern int gfs2_block_map(struct inode *inode, sector_t lblock,
struct buffer_head *bh, int create);
-extern int gfs2_iomap_get_alloc(struct inode *inode, loff_t pos, loff_t length,
- struct iomap *iomap);
-extern int gfs2_extent_map(struct inode *inode, u64 lblock, int *new,
- u64 *dblock, unsigned *extlen);
+extern int gfs2_iomap_get(struct inode *inode, loff_t pos, loff_t length,
+ struct iomap *iomap);
+extern int gfs2_iomap_alloc(struct inode *inode, loff_t pos, loff_t length,
+ struct iomap *iomap);
+extern int gfs2_get_extent(struct inode *inode, u64 lblock, u64 *dblock,
+ unsigned int *extlen);
+extern int gfs2_alloc_extent(struct inode *inode, u64 lblock, u64 *dblock,
+ unsigned *extlen, bool *new);
extern int gfs2_setattr_size(struct inode *inode, u64 size);
extern void gfs2_trim_blocks(struct inode *inode);
extern int gfs2_truncatei_resume(struct gfs2_inode *ip);
@@ -62,6 +66,5 @@ extern int gfs2_write_alloc_required(struct gfs2_inode *ip, u64 offset,
extern int gfs2_map_journal_extents(struct gfs2_sbd *sdp, struct gfs2_jdesc *jd);
extern void gfs2_free_journal_extents(struct gfs2_jdesc *jd);
extern int __gfs2_punch_hole(struct file *file, loff_t offset, loff_t length);
-extern int gfs2_lblk_to_dblk(struct inode *inode, u32 lblock, u64 *dblock);
#endif /* __BMAP_DOT_H__ */
diff --git a/fs/gfs2/dir.c b/fs/gfs2/dir.c
index c0f2875c946c..18f67b37d6f8 100644
--- a/fs/gfs2/dir.c
+++ b/fs/gfs2/dir.c
@@ -159,7 +159,7 @@ static int gfs2_dir_write_data(struct gfs2_inode *ip, const char *buf,
unsigned int o;
int copied = 0;
int error = 0;
- int new = 0;
+ bool new = false;
if (!size)
return 0;
@@ -189,9 +189,9 @@ static int gfs2_dir_write_data(struct gfs2_inode *ip, const char *buf,
amount = sdp->sd_sb.sb_bsize - o;
if (!extlen) {
- new = 1;
- error = gfs2_extent_map(&ip->i_inode, lblock, &new,
- &dblock, &extlen);
+ extlen = 1;
+ error = gfs2_alloc_extent(&ip->i_inode, lblock, &dblock,
+ &extlen, &new);
if (error)
goto fail;
error = -EIO;
@@ -286,15 +286,14 @@ static int gfs2_dir_read_data(struct gfs2_inode *ip, __be64 *buf,
while (copied < size) {
unsigned int amount;
struct buffer_head *bh;
- int new;
amount = size - copied;
if (amount > sdp->sd_sb.sb_bsize - o)
amount = sdp->sd_sb.sb_bsize - o;
if (!extlen) {
- new = 0;
- error = gfs2_extent_map(&ip->i_inode, lblock, &new,
+ extlen = 32;
+ error = gfs2_get_extent(&ip->i_inode, lblock,
&dblock, &extlen);
if (error || !dblock)
goto fail;
@@ -770,14 +769,13 @@ static int get_leaf(struct gfs2_inode *dip, u64 leaf_no,
/**
* get_leaf_nr - Get a leaf number associated with the index
* @dip: The GFS2 inode
- * @index:
- * @leaf_out:
+ * @index: hash table index of the targeted leaf
+ * @leaf_out: Resulting leaf block number
*
* Returns: 0 on success, error code otherwise
*/
-static int get_leaf_nr(struct gfs2_inode *dip, u32 index,
- u64 *leaf_out)
+static int get_leaf_nr(struct gfs2_inode *dip, u32 index, u64 *leaf_out)
{
__be64 *hash;
int error;
@@ -898,7 +896,7 @@ static struct gfs2_leaf *new_leaf(struct inode *inode, struct buffer_head **pbh,
/**
* dir_make_exhash - Convert a stuffed directory into an ExHash directory
- * @dip: The GFS2 inode
+ * @inode: The directory inode to be converted to exhash
*
* Returns: 0 on success, error code otherwise
*/
@@ -991,9 +989,8 @@ static int dir_make_exhash(struct inode *inode)
/**
* dir_split_leaf - Split a leaf block into two
- * @dip: The GFS2 inode
- * @index:
- * @leaf_no:
+ * @inode: The directory inode to be split
+ * @name: name of the dirent we're trying to insert
*
* Returns: 0 on success, error code on failure
*/
@@ -1252,6 +1249,7 @@ static int compare_dents(const void *a, const void *b)
* @ctx: what to feed the entries to
* @darr: an array of struct gfs2_dirent pointers to read
* @entries: the number of entries in darr
+ * @sort_start: index of the directory array to start our sort
* @copied: pointer to int that's non-zero if a entry has been copied out
*
* Jump through some hoops to make sure that if there are hash collsions,
@@ -1468,6 +1466,10 @@ out:
/**
* gfs2_dir_readahead - Issue read-ahead requests for leaf blocks.
+ * @inode: the directory inode
+ * @hsize: hash table size
+ * @index: index into the hash table
+ * @f_ra: read-ahead parameters
*
* Note: we can't calculate each index like dir_e_read can because we don't
* have the leaf, and therefore we don't have the depth, and therefore we
@@ -1517,8 +1519,9 @@ static void gfs2_dir_readahead(struct inode *inode, unsigned hsize, u32 index,
/**
* dir_e_read - Reads the entries from a directory into a filldir buffer
- * @dip: dinode pointer
+ * @inode: the directory inode
* @ctx: actor to feed the entries to
+ * @f_ra: read-ahead parameters
*
* Returns: errno
*/
@@ -1627,7 +1630,7 @@ out:
/**
* gfs2_dir_search - Search a directory
- * @dip: The GFS2 dir inode
+ * @dir: The GFS2 directory inode
* @name: The name we are looking up
* @fail_on_exist: Fail if the name exists rather than looking it up
*
@@ -1864,7 +1867,7 @@ int gfs2_dir_add(struct inode *inode, const struct qstr *name,
/**
* gfs2_dir_del - Delete a directory entry
* @dip: The GFS2 inode
- * @filename: The filename
+ * @dentry: The directory entry we want to delete
*
* Returns: 0 on success, error code on failure
*/
@@ -1918,9 +1921,10 @@ int gfs2_dir_del(struct gfs2_inode *dip, const struct dentry *dentry)
/**
* gfs2_dir_mvino - Change inode number of directory entry
- * @dip: The GFS2 inode
- * @filename:
- * @new_inode:
+ * @dip: The GFS2 directory inode
+ * @filename: the filename to be moved
+ * @nip: the new GFS2 inode
+ * @new_type: the de_type of the new dirent
*
* This routine changes the inode number of a directory entry. It's used
* by rename to change ".." when a directory is moved.
@@ -1960,7 +1964,7 @@ int gfs2_dir_mvino(struct gfs2_inode *dip, const struct qstr *filename,
* @len: the number of pointers to this leaf
* @leaf_no: the leaf number
* @leaf_bh: buffer_head for the starting leaf
- * last_dealloc: 1 if this is the final dealloc for the leaf, else 0
+ * @last_dealloc: 1 if this is the final dealloc for the leaf, else 0
*
* Returns: errno
*/
@@ -2142,8 +2146,8 @@ out:
/**
* gfs2_diradd_alloc_required - find if adding entry will require an allocation
- * @ip: the file being written to
- * @filname: the filename that's going to be added
+ * @inode: the directory inode being written to
+ * @name: the filename that's going to be added
* @da: The structure to return dir alloc info
*
* Returns: 0 if ok, -ve on error
diff --git a/fs/gfs2/file.c b/fs/gfs2/file.c
index 2d500f90cdac..a0b542d84cd9 100644
--- a/fs/gfs2/file.c
+++ b/fs/gfs2/file.c
@@ -25,6 +25,7 @@
#include <linux/dlm_plock.h>
#include <linux/delay.h>
#include <linux/backing-dev.h>
+#include <linux/fileattr.h>
#include "gfs2.h"
#include "incore.h"
@@ -118,8 +119,8 @@ static int gfs2_readdir(struct file *file, struct dir_context *ctx)
return error;
}
-/**
- * fsflag_gfs2flag
+/*
+ * struct fsflag_gfs2flag
*
* The FS_JOURNAL_DATA_FL flag maps to GFS2_DIF_INHERIT_JDATA for directories,
* and to GFS2_DIF_JDATA for non-directories.
@@ -153,14 +154,17 @@ static inline u32 gfs2_gfsflags_to_fsflags(struct inode *inode, u32 gfsflags)
return fsflags;
}
-static int gfs2_get_flags(struct file *filp, u32 __user *ptr)
+int gfs2_fileattr_get(struct dentry *dentry, struct fileattr *fa)
{
- struct inode *inode = file_inode(filp);
+ struct inode *inode = d_inode(dentry);
struct gfs2_inode *ip = GFS2_I(inode);
struct gfs2_holder gh;
int error;
u32 fsflags;
+ if (d_is_special(dentry))
+ return -ENOTTY;
+
gfs2_holder_init(ip->i_gl, LM_ST_SHARED, 0, &gh);
error = gfs2_glock_nq(&gh);
if (error)
@@ -168,8 +172,7 @@ static int gfs2_get_flags(struct file *filp, u32 __user *ptr)
fsflags = gfs2_gfsflags_to_fsflags(inode, ip->i_diskflags);
- if (put_user(fsflags, ptr))
- error = -EFAULT;
+ fileattr_fill_flags(fa, fsflags);
gfs2_glock_dq(&gh);
out_uninit:
@@ -213,33 +216,19 @@ void gfs2_set_inode_flags(struct inode *inode)
* @fsflags: The FS_* inode flags passed in
*
*/
-static int do_gfs2_set_flags(struct file *filp, u32 reqflags, u32 mask,
+static int do_gfs2_set_flags(struct inode *inode, u32 reqflags, u32 mask,
const u32 fsflags)
{
- struct inode *inode = file_inode(filp);
struct gfs2_inode *ip = GFS2_I(inode);
struct gfs2_sbd *sdp = GFS2_SB(inode);
struct buffer_head *bh;
struct gfs2_holder gh;
int error;
- u32 new_flags, flags, oldflags;
-
- error = mnt_want_write_file(filp);
- if (error)
- return error;
+ u32 new_flags, flags;
error = gfs2_glock_nq_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, &gh);
if (error)
- goto out_drop_write;
-
- oldflags = gfs2_gfsflags_to_fsflags(inode, ip->i_diskflags);
- error = vfs_ioc_setflags_prepare(inode, oldflags, fsflags);
- if (error)
- goto out;
-
- error = -EACCES;
- if (!inode_owner_or_capable(&init_user_ns, inode))
- goto out;
+ return error;
error = 0;
flags = ip->i_diskflags;
@@ -252,9 +241,6 @@ static int do_gfs2_set_flags(struct file *filp, u32 reqflags, u32 mask,
goto out;
if (IS_APPEND(inode) && (new_flags & GFS2_DIF_APPENDONLY))
goto out;
- if (((new_flags ^ flags) & GFS2_DIF_IMMUTABLE) &&
- !capable(CAP_LINUX_IMMUTABLE))
- goto out;
if (!IS_IMMUTABLE(inode)) {
error = gfs2_permission(&init_user_ns, inode, MAY_WRITE);
if (error)
@@ -291,20 +277,22 @@ out_trans_end:
gfs2_trans_end(sdp);
out:
gfs2_glock_dq_uninit(&gh);
-out_drop_write:
- mnt_drop_write_file(filp);
return error;
}
-static int gfs2_set_flags(struct file *filp, u32 __user *ptr)
+int gfs2_fileattr_set(struct user_namespace *mnt_userns,
+ struct dentry *dentry, struct fileattr *fa)
{
- struct inode *inode = file_inode(filp);
- u32 fsflags, gfsflags = 0;
+ struct inode *inode = d_inode(dentry);
+ u32 fsflags = fa->flags, gfsflags = 0;
u32 mask;
int i;
- if (get_user(fsflags, ptr))
- return -EFAULT;
+ if (d_is_special(dentry))
+ return -ENOTTY;
+
+ if (fileattr_has_fsx(fa))
+ return -EOPNOTSUPP;
for (i = 0; i < ARRAY_SIZE(fsflag_gfs2flag); i++) {
if (fsflags & fsflag_gfs2flag[i].fsflag) {
@@ -325,7 +313,7 @@ static int gfs2_set_flags(struct file *filp, u32 __user *ptr)
mask &= ~(GFS2_DIF_TOPDIR | GFS2_DIF_INHERIT_JDATA);
}
- return do_gfs2_set_flags(filp, gfsflags, mask, fsflags);
+ return do_gfs2_set_flags(inode, gfsflags, mask, fsflags);
}
static int gfs2_getlabel(struct file *filp, char __user *label)
@@ -342,10 +330,6 @@ static int gfs2_getlabel(struct file *filp, char __user *label)
static long gfs2_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
{
switch(cmd) {
- case FS_IOC_GETFLAGS:
- return gfs2_get_flags(filp, (u32 __user *)arg);
- case FS_IOC_SETFLAGS:
- return gfs2_set_flags(filp, (u32 __user *)arg);
case FITRIM:
return gfs2_fitrim(filp, (void __user *)arg);
case FS_IOC_GETFSLABEL:
@@ -359,13 +343,6 @@ static long gfs2_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
static long gfs2_compat_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
{
switch(cmd) {
- /* These are just misnamed, they actually get/put from/to user an int */
- case FS_IOC32_GETFLAGS:
- cmd = FS_IOC_GETFLAGS;
- break;
- case FS_IOC32_SETFLAGS:
- cmd = FS_IOC_SETFLAGS;
- break;
/* Keep this list in sync with gfs2_ioctl */
case FITRIM:
case FS_IOC_GETFSLABEL:
@@ -421,7 +398,7 @@ static int gfs2_allocate_page_backing(struct page *page, unsigned int length)
do {
struct iomap iomap = { };
- if (gfs2_iomap_get_alloc(page->mapping->host, pos, length, &iomap))
+ if (gfs2_iomap_alloc(page->mapping->host, pos, length, &iomap))
return -EIO;
if (length < iomap.length)
@@ -435,7 +412,6 @@ static int gfs2_allocate_page_backing(struct page *page, unsigned int length)
/**
* gfs2_page_mkwrite - Make a shared, mmap()ed, page writable
- * @vma: The virtual memory area
* @vmf: The virtual memory fault containing the page to become writable
*
* When the page becomes writable, we need to ensure that we have
@@ -586,7 +562,7 @@ static const struct vm_operations_struct gfs2_vm_ops = {
};
/**
- * gfs2_mmap -
+ * gfs2_mmap
* @file: The file to map
* @vma: The VMA which described the mapping
*
@@ -991,8 +967,7 @@ static int fallocate_chunk(struct inode *inode, loff_t offset, loff_t len,
while (offset < end) {
struct iomap iomap = { };
- error = gfs2_iomap_get_alloc(inode, offset, end - offset,
- &iomap);
+ error = gfs2_iomap_alloc(inode, offset, end - offset, &iomap);
if (error)
goto out;
offset = iomap.offset + iomap.length;
diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c
index 9567520d79f7..84c38103aa06 100644
--- a/fs/gfs2/glock.c
+++ b/fs/gfs2/glock.c
@@ -359,7 +359,8 @@ static void gfs2_holder_wake(struct gfs2_holder *gh)
/**
* do_error - Something unexpected has happened during a lock request
- *
+ * @gl: The glock
+ * @ret: The status from the DLM
*/
static void do_error(struct gfs2_glock *gl, const int ret)
@@ -454,8 +455,7 @@ static inline struct gfs2_holder *find_first_waiter(const struct gfs2_glock *gl)
/**
* state_change - record that the glock is now in a different state
* @gl: the glock
- * @new_state the new state
- *
+ * @new_state: the new state
*/
static void state_change(struct gfs2_glock *gl, unsigned int new_state)
@@ -566,7 +566,7 @@ retry:
if (state != LM_ST_UNLOCKED) {
if (glops->go_xmote_bh) {
spin_unlock(&gl->gl_lockref.lock);
- rv = glops->go_xmote_bh(gl, gh);
+ rv = glops->go_xmote_bh(gl);
spin_lock(&gl->gl_lockref.lock);
if (rv) {
do_error(gl, rv);
@@ -1268,6 +1268,8 @@ wait_for_dlm:
* handle_callback - process a demote request
* @gl: the glock
* @state: the state the caller wants us to change to
+ * @delay: zero to demote immediately; otherwise pending demote
+ * @remote: true if this came from a different cluster node
*
* There are only two requests that we are going to see in actual
* practise: LM_ST_SHARED and LM_ST_UNLOCKED
@@ -1569,6 +1571,7 @@ static int glock_compare(const void *arg_a, const void *arg_b)
* nq_m_sync - synchonously acquire more than one glock in deadlock free order
* @num_gh: the number of structures
* @ghs: an array of struct gfs2_holder structures
+ * @p: placeholder for the holder structure to pass back
*
* Returns: 0 on success (all glocks acquired),
* errno on failure (no glocks acquired)
@@ -1732,7 +1735,8 @@ void gfs2_glock_complete(struct gfs2_glock *gl, int ret)
spin_unlock(&gl->gl_lockref.lock);
}
-static int glock_cmp(void *priv, struct list_head *a, struct list_head *b)
+static int glock_cmp(void *priv, const struct list_head *a,
+ const struct list_head *b)
{
struct gfs2_glock *gla, *glb;
@@ -1985,7 +1989,6 @@ static void dump_glock_func(struct gfs2_glock *gl)
/**
* gfs2_gl_hash_clear - Empty out the glock hash table
* @sdp: the filesystem
- * @wait: wait until it's all gone
*
* Called when unmounting the filesystem.
*/
diff --git a/fs/gfs2/glops.c b/fs/gfs2/glops.c
index 8e32d569c8bf..454095e9fedf 100644
--- a/fs/gfs2/glops.c
+++ b/fs/gfs2/glops.c
@@ -49,6 +49,7 @@ static void gfs2_ail_error(struct gfs2_glock *gl, const struct buffer_head *bh)
* __gfs2_ail_flush - remove all buffers for a given lock from the AIL
* @gl: the glock
* @fsync: set when called from fsync (not all buffers will be clean)
+ * @nr_revokes: Number of buffers to revoke
*
* None of the buffers should be dirty, locked, or pinned.
*/
@@ -394,18 +395,24 @@ static int gfs2_dinode_in(struct gfs2_inode *ip, const void *buf)
const struct gfs2_dinode *str = buf;
struct timespec64 atime;
u16 height, depth;
+ umode_t mode = be32_to_cpu(str->di_mode);
+ bool is_new = ip->i_inode.i_flags & I_NEW;
if (unlikely(ip->i_no_addr != be64_to_cpu(str->di_num.no_addr)))
goto corrupt;
+ if (unlikely(!is_new && inode_wrong_type(&ip->i_inode, mode)))
+ goto corrupt;
ip->i_no_formal_ino = be64_to_cpu(str->di_num.no_formal_ino);
- ip->i_inode.i_mode = be32_to_cpu(str->di_mode);
- ip->i_inode.i_rdev = 0;
- switch (ip->i_inode.i_mode & S_IFMT) {
- case S_IFBLK:
- case S_IFCHR:
- ip->i_inode.i_rdev = MKDEV(be32_to_cpu(str->di_major),
- be32_to_cpu(str->di_minor));
- break;
+ ip->i_inode.i_mode = mode;
+ if (is_new) {
+ ip->i_inode.i_rdev = 0;
+ switch (mode & S_IFMT) {
+ case S_IFBLK:
+ case S_IFCHR:
+ ip->i_inode.i_rdev = MKDEV(be32_to_cpu(str->di_major),
+ be32_to_cpu(str->di_minor));
+ break;
+ }
}
i_uid_write(&ip->i_inode, be32_to_cpu(str->di_uid));
@@ -474,8 +481,7 @@ int gfs2_inode_refresh(struct gfs2_inode *ip)
/**
* inode_go_lock - operation done after an inode lock is locked by a process
- * @gl: the glock
- * @flags:
+ * @gh: The glock holder
*
* Returns: errno
*/
@@ -516,7 +522,7 @@ static int inode_go_lock(struct gfs2_holder *gh)
/**
* inode_go_dump - print information about an inode
* @seq: The iterator
- * @ip: the inode
+ * @gl: The glock
* @fs_id_buf: file system id (may be empty)
*
*/
@@ -547,9 +553,6 @@ static void inode_go_dump(struct seq_file *seq, struct gfs2_glock *gl,
/**
* freeze_go_sync - promote/demote the freeze glock
* @gl: the glock
- * @state: the requested state
- * @flags:
- *
*/
static int freeze_go_sync(struct gfs2_glock *gl)
@@ -594,10 +597,8 @@ static int freeze_go_sync(struct gfs2_glock *gl)
/**
* freeze_go_xmote_bh - After promoting/demoting the freeze glock
* @gl: the glock
- *
*/
-
-static int freeze_go_xmote_bh(struct gfs2_glock *gl, struct gfs2_holder *gh)
+static int freeze_go_xmote_bh(struct gfs2_glock *gl)
{
struct gfs2_sbd *sdp = gl->gl_name.ln_sbd;
struct gfs2_inode *ip = GFS2_I(sdp->sd_jdesc->jd_inode);
@@ -624,7 +625,7 @@ static int freeze_go_xmote_bh(struct gfs2_glock *gl, struct gfs2_holder *gh)
}
/**
- * trans_go_demote_ok
+ * freeze_go_demote_ok
* @gl: the glock
*
* Always returns 0
@@ -638,6 +639,7 @@ static int freeze_go_demote_ok(const struct gfs2_glock *gl)
/**
* iopen_go_callback - schedule the dcache entry for the inode to be deleted
* @gl: the glock
+ * @remote: true if this came from a different cluster node
*
* gl_lockref.lock lock is held while calling this
*/
diff --git a/fs/gfs2/incore.h b/fs/gfs2/incore.h
index 0957119f7744..e6f820f146cb 100644
--- a/fs/gfs2/incore.h
+++ b/fs/gfs2/incore.h
@@ -217,7 +217,7 @@ struct lm_lockname {
struct gfs2_glock_operations {
int (*go_sync) (struct gfs2_glock *gl);
- int (*go_xmote_bh) (struct gfs2_glock *gl, struct gfs2_holder *gh);
+ int (*go_xmote_bh)(struct gfs2_glock *gl);
void (*go_inval) (struct gfs2_glock *gl, int flags);
int (*go_demote_ok) (const struct gfs2_glock *gl);
int (*go_lock) (struct gfs2_holder *gh);
@@ -625,7 +625,6 @@ struct gfs2_inum_host {
struct gfs2_sb_host {
u32 sb_magic;
u32 sb_type;
- u32 sb_format;
u32 sb_fs_format;
u32 sb_multihost_format;
diff --git a/fs/gfs2/inode.c b/fs/gfs2/inode.c
index c9775d5c6594..6e15434b23ac 100644
--- a/fs/gfs2/inode.c
+++ b/fs/gfs2/inode.c
@@ -285,10 +285,9 @@ struct inode *gfs2_lookup_simple(struct inode *dip, const char *name)
/**
* gfs2_lookupi - Look up a filename in a directory and return its inode
- * @d_gh: An initialized holder for the directory glock
+ * @dir: The inode of the directory containing the inode to look-up
* @name: The name of the inode to look for
* @is_root: If 1, ignore the caller's permissions
- * @i_gh: An uninitialized holder for the new inode glock
*
* This can be called via the VFS filldir function when NFS is doing
* a readdirplus and the inode which its intending to stat isn't
@@ -476,7 +475,6 @@ static void gfs2_init_xattr(struct gfs2_inode *ip)
* @dip: The directory this inode is being created in
* @ip: The inode
* @symname: The symlink destination (if a symlink)
- * @bhp: The buffer head (returned to caller)
*
*/
@@ -514,7 +512,7 @@ static void init_dinode(struct gfs2_inode *dip, struct gfs2_inode *ip,
}
/**
- * gfs2_trans_da_blocks - Calculate number of blocks to link inode
+ * gfs2_trans_da_blks - Calculate number of blocks to link inode
* @dip: The directory we are linking into
* @da: The dir add information
* @nr_inodes: The number of inodes involved
@@ -595,6 +593,7 @@ static int gfs2_initxattrs(struct inode *inode, const struct xattr *xattr_array,
* @dev: For device nodes, this is the device number
* @symname: For symlinks, this is the link destination
* @size: The initial size of the inode (ignored for directories)
+ * @excl: Force fail if inode exists
*
* Returns: 0 on success, or error code
*/
@@ -837,9 +836,11 @@ fail:
/**
* gfs2_create - Create a file
+ * @mnt_userns: User namespace of the mount the inode was found from
* @dir: The directory in which to create the file
* @dentry: The dentry of the new file
* @mode: The mode of the new file
+ * @excl: Force fail if inode exists
*
* Returns: errno
*/
@@ -962,6 +963,7 @@ static int gfs2_link(struct dentry *old_dentry, struct inode *dir,
break;
case 0:
error = -EEXIST;
+ goto out_gunlock;
default:
goto out_gunlock;
}
@@ -1080,8 +1082,7 @@ static int gfs2_unlink_ok(struct gfs2_inode *dip, const struct qstr *name,
/**
* gfs2_unlink_inode - Removes an inode from its parent dir and unlinks it
* @dip: The parent directory
- * @name: The name of the entry in the parent directory
- * @inode: The inode to be removed
+ * @dentry: The dentry to unlink
*
* Called with all the locks and in a transaction. This will only be
* called for a directory after it has been checked to ensure it is empty.
@@ -1199,6 +1200,7 @@ out_inodes:
/**
* gfs2_symlink - Create a symlink
+ * @mnt_userns: User namespace of the mount the inode was found from
* @dir: The directory to create the symlink in
* @dentry: The dentry to put the symlink in
* @symname: The thing which the link points to
@@ -1220,6 +1222,7 @@ static int gfs2_symlink(struct user_namespace *mnt_userns, struct inode *dir,
/**
* gfs2_mkdir - Make a directory
+ * @mnt_userns: User namespace of the mount the inode was found from
* @dir: The parent directory of the new one
* @dentry: The dentry of the new directory
* @mode: The mode of the new directory
@@ -1236,6 +1239,7 @@ static int gfs2_mkdir(struct user_namespace *mnt_userns, struct inode *dir,
/**
* gfs2_mknod - Make a special file
+ * @mnt_userns: User namespace of the mount the inode was found from
* @dir: The directory in which the special file will reside
* @dentry: The dentry of the special file
* @mode: The mode of the special file
@@ -1505,6 +1509,7 @@ static int gfs2_rename(struct inode *odir, struct dentry *odentry,
break;
case 0:
error = -EEXIST;
+ goto out_gunlock;
default:
goto out_gunlock;
}
@@ -1828,10 +1833,10 @@ out:
}
/**
- * gfs2_permission -
+ * gfs2_permission
+ * @mnt_userns: User namespace of the mount the inode was found from
* @inode: The inode
* @mask: The mask to be tested
- * @flags: Indicates whether this is an RCU path walk or not
*
* This may be called from the VFS directly, or from within GFS2 with the
* inode locked, so we look to see if the glock is already locked and only
@@ -1874,15 +1879,7 @@ static int __gfs2_setattr_simple(struct inode *inode, struct iattr *attr)
return 0;
}
-/**
- * gfs2_setattr_simple -
- * @ip:
- * @attr:
- *
- * Returns: errno
- */
-
-int gfs2_setattr_simple(struct inode *inode, struct iattr *attr)
+static int gfs2_setattr_simple(struct inode *inode, struct iattr *attr)
{
int error;
@@ -1962,6 +1959,7 @@ out:
/**
* gfs2_setattr - Change attributes on an inode
+ * @mnt_userns: User namespace of the mount the inode was found from
* @dentry: The dentry which is changing
* @attr: The structure describing the change
*
@@ -2157,6 +2155,8 @@ static const struct inode_operations gfs2_file_iops = {
.get_acl = gfs2_get_acl,
.set_acl = gfs2_set_acl,
.update_time = gfs2_update_time,
+ .fileattr_get = gfs2_fileattr_get,
+ .fileattr_set = gfs2_fileattr_set,
};
static const struct inode_operations gfs2_dir_iops = {
@@ -2178,6 +2178,8 @@ static const struct inode_operations gfs2_dir_iops = {
.set_acl = gfs2_set_acl,
.update_time = gfs2_update_time,
.atomic_open = gfs2_atomic_open,
+ .fileattr_get = gfs2_fileattr_get,
+ .fileattr_set = gfs2_fileattr_set,
};
static const struct inode_operations gfs2_symlink_iops = {
diff --git a/fs/gfs2/inode.h b/fs/gfs2/inode.h
index c447bd5b3017..7b2c1f390db7 100644
--- a/fs/gfs2/inode.h
+++ b/fs/gfs2/inode.h
@@ -101,7 +101,6 @@ extern struct inode *gfs2_lookupi(struct inode *dir, const struct qstr *name,
int is_root);
extern int gfs2_permission(struct user_namespace *mnt_userns,
struct inode *inode, int mask);
-extern int gfs2_setattr_simple(struct inode *inode, struct iattr *attr);
extern struct inode *gfs2_lookup_simple(struct inode *dip, const char *name);
extern void gfs2_dinode_out(const struct gfs2_inode *ip, void *buf);
extern int gfs2_open_common(struct inode *inode, struct file *file);
@@ -111,6 +110,9 @@ extern loff_t gfs2_seek_hole(struct file *file, loff_t offset);
extern const struct file_operations gfs2_file_fops_nolock;
extern const struct file_operations gfs2_dir_fops_nolock;
+extern int gfs2_fileattr_get(struct dentry *dentry, struct fileattr *fa);
+extern int gfs2_fileattr_set(struct user_namespace *mnt_userns,
+ struct dentry *dentry, struct fileattr *fa);
extern void gfs2_set_inode_flags(struct inode *inode);
#ifdef CONFIG_GFS2_FS_LOCKING_DLM
diff --git a/fs/gfs2/lock_dlm.c b/fs/gfs2/lock_dlm.c
index 153272f82984..dac040162ecc 100644
--- a/fs/gfs2/lock_dlm.c
+++ b/fs/gfs2/lock_dlm.c
@@ -24,28 +24,31 @@
/**
* gfs2_update_stats - Update time based stats
- * @mv: Pointer to mean/variance structure to update
+ * @s: The stats to update (local or global)
+ * @index: The index inside @s
* @sample: New data to include
- *
- * @delta is the difference between the current rtt sample and the
- * running average srtt. We add 1/8 of that to the srtt in order to
- * update the current srtt estimate. The variance estimate is a bit
- * more complicated. We subtract the current variance estimate from
- * the abs value of the @delta and add 1/4 of that to the running
- * total. That's equivalent to 3/4 of the current variance
- * estimate plus 1/4 of the abs of @delta.
- *
- * Note that the index points at the array entry containing the smoothed
- * mean value, and the variance is always in the following entry
- *
- * Reference: TCP/IP Illustrated, vol 2, p. 831,832
- * All times are in units of integer nanoseconds. Unlike the TCP/IP case,
- * they are not scaled fixed point.
*/
-
static inline void gfs2_update_stats(struct gfs2_lkstats *s, unsigned index,
s64 sample)
{
+ /*
+ * @delta is the difference between the current rtt sample and the
+ * running average srtt. We add 1/8 of that to the srtt in order to
+ * update the current srtt estimate. The variance estimate is a bit
+ * more complicated. We subtract the current variance estimate from
+ * the abs value of the @delta and add 1/4 of that to the running
+ * total. That's equivalent to 3/4 of the current variance
+ * estimate plus 1/4 of the abs of @delta.
+ *
+ * Note that the index points at the array entry containing the
+ * smoothed mean value, and the variance is always in the following
+ * entry
+ *
+ * Reference: TCP/IP Illustrated, vol 2, p. 831,832
+ * All times are in units of integer nanoseconds. Unlike the TCP/IP
+ * case, they are not scaled fixed point.
+ */
+
s64 delta = sample - s->stats[index];
s->stats[index] += (delta >> 3);
index++;
diff --git a/fs/gfs2/log.c b/fs/gfs2/log.c
index 6410281546f9..97d54e581a7b 100644
--- a/fs/gfs2/log.c
+++ b/fs/gfs2/log.c
@@ -65,7 +65,6 @@ unsigned int gfs2_struct2blk(struct gfs2_sbd *sdp, unsigned int nstruct)
/**
* gfs2_remove_from_ail - Remove an entry from the ail lists, updating counters
- * @mapping: The associated mapping (maybe NULL)
* @bd: The gfs2_bufdata to remove
*
* The ail lock _must_ be held when calling this function
@@ -82,11 +81,11 @@ void gfs2_remove_from_ail(struct gfs2_bufdata *bd)
}
/**
- * gfs2_ail1_start_one - Start I/O on a part of the AIL
- * @sdp: the filesystem
+ * gfs2_ail1_start_one - Start I/O on a transaction
+ * @sdp: The superblock
* @wbc: The writeback control structure
- * @ai: The ail structure
- *
+ * @tr: The transaction to start I/O on
+ * @plug: The block plug currently active
*/
static int gfs2_ail1_start_one(struct gfs2_sbd *sdp,
@@ -269,7 +268,7 @@ static void gfs2_log_update_head(struct gfs2_sbd *sdp)
sdp->sd_log_head = new_head;
}
-/**
+/*
* gfs2_ail_empty_tr - empty one of the ail lists of a transaction
*/
@@ -695,7 +694,7 @@ void log_flush_wait(struct gfs2_sbd *sdp)
}
}
-static int ip_cmp(void *priv, struct list_head *a, struct list_head *b)
+static int ip_cmp(void *priv, const struct list_head *a, const struct list_head *b)
{
struct gfs2_inode *ipa, *ipb;
@@ -859,7 +858,11 @@ void gfs2_write_log_header(struct gfs2_sbd *sdp, struct gfs2_jdesc *jd,
if (!list_empty(&jd->extent_list))
dblock = gfs2_log_bmap(jd, lblock);
else {
- int ret = gfs2_lblk_to_dblk(jd->jd_inode, lblock, &dblock);
+ unsigned int extlen;
+ int ret;
+
+ extlen = 1;
+ ret = gfs2_get_extent(jd->jd_inode, lblock, &dblock, &extlen);
if (gfs2_assert_withdraw(sdp, ret == 0))
return;
}
@@ -1014,7 +1017,7 @@ static void trans_drain(struct gfs2_trans *tr)
/**
* gfs2_log_flush - flush incore transaction(s)
- * @sdp: the filesystem
+ * @sdp: The filesystem
* @gl: The glock structure to flush. If NULL, flush the whole incore log
* @flags: The log header flags: GFS2_LOG_HEAD_FLUSH_* and debug flags
*
@@ -1166,7 +1169,7 @@ out_withdraw:
/**
* gfs2_merge_trans - Merge a new transaction into a cached transaction
- * @old: Original transaction to be expanded
+ * @sdp: the filesystem
* @new: New transaction to be merged
*/
@@ -1283,7 +1286,7 @@ static inline int gfs2_ail_flush_reqd(struct gfs2_sbd *sdp)
/**
* gfs2_logd - Update log tail as Active Items get flushed to in-place blocks
- * @sdp: Pointer to GFS2 superblock
+ * @data: Pointer to GFS2 superblock
*
* Also, periodically check to make sure that we're using the most recent
* journal index.
diff --git a/fs/gfs2/lops.c b/fs/gfs2/lops.c
index a82f4747aa8d..221e7118cc3b 100644
--- a/fs/gfs2/lops.c
+++ b/fs/gfs2/lops.c
@@ -96,9 +96,7 @@ out:
* gfs2_unpin - Unpin a buffer
* @sdp: the filesystem the buffer belongs to
* @bh: The buffer to unpin
- * @ai:
- * @flags: The inode dirty flags
- *
+ * @tr: The system transaction being flushed
*/
static void gfs2_unpin(struct gfs2_sbd *sdp, struct buffer_head *bh,
@@ -281,7 +279,7 @@ static struct bio *gfs2_log_alloc_bio(struct gfs2_sbd *sdp, u64 blkno,
* gfs2_log_get_bio - Get cached log bio, or allocate a new one
* @sdp: The super block
* @blkno: The device block number we want to write to
- * @bio: The bio to get or allocate
+ * @biop: The bio to get or allocate
* @op: REQ_OP
* @end_io: The bi_end_io callback
* @flush: Always flush the current bio and allocate a new one?
@@ -317,6 +315,7 @@ static struct bio *gfs2_log_get_bio(struct gfs2_sbd *sdp, u64 blkno,
/**
* gfs2_log_write - write to log
* @sdp: the filesystem
+ * @jd: The journal descriptor
* @page: the page to write
* @size: the size of the data to write
* @offset: the offset within the page
@@ -417,6 +416,7 @@ static void gfs2_end_log_read(struct bio *bio)
/**
* gfs2_jhead_pg_srch - Look for the journal head in a given page.
* @jd: The journal descriptor
+ * @head: The journal head to start from
* @page: The page to look in
*
* Returns: 1 if found, 0 otherwise.
@@ -450,6 +450,7 @@ static bool gfs2_jhead_pg_srch(struct gfs2_jdesc *jd,
* gfs2_jhead_process_page - Search/cleanup a page
* @jd: The journal descriptor
* @index: Index of the page to look into
+ * @head: The journal head to start from
* @done: If set, perform only cleanup, else search and set if found.
*
* Find the page with 'index' in the journal's mapping. Search the page for
@@ -502,6 +503,7 @@ static struct bio *gfs2_chain_bio(struct bio *prev, unsigned int nr_iovecs)
* gfs2_find_jhead - find the head of a log
* @jd: The journal descriptor
* @head: The log descriptor for the head of the log is returned here
+ * @keep_cache: If set inode pages will not be truncated
*
* Do a search of a journal by reading it in large chunks using bios and find
* the valid log entry with the highest sequence number. (i.e. the log head)
@@ -634,7 +636,8 @@ static void gfs2_check_magic(struct buffer_head *bh)
kunmap_atomic(kaddr);
}
-static int blocknr_cmp(void *priv, struct list_head *a, struct list_head *b)
+static int blocknr_cmp(void *priv, const struct list_head *a,
+ const struct list_head *b)
{
struct gfs2_bufdata *bda, *bdb;
@@ -976,7 +979,8 @@ static void revoke_lo_after_scan(struct gfs2_jdesc *jd, int error, int pass)
/**
* databuf_lo_before_commit - Scan the data buffers, writing as we go
- *
+ * @sdp: The filesystem
+ * @tr: The system transaction being flushed
*/
static void databuf_lo_before_commit(struct gfs2_sbd *sdp, struct gfs2_trans *tr)
diff --git a/fs/gfs2/meta_io.c b/fs/gfs2/meta_io.c
index 2db573e31f78..d68184ebbfdd 100644
--- a/fs/gfs2/meta_io.c
+++ b/fs/gfs2/meta_io.c
@@ -131,16 +131,19 @@ struct buffer_head *gfs2_getbuf(struct gfs2_glock *gl, u64 blkno, int create)
break;
yield();
}
+ if (!page_has_buffers(page))
+ create_empty_buffers(page, sdp->sd_sb.sb_bsize, 0);
} else {
page = find_get_page_flags(mapping, index,
FGP_LOCK|FGP_ACCESSED);
if (!page)
return NULL;
+ if (!page_has_buffers(page)) {
+ bh = NULL;
+ goto out_unlock;
+ }
}
- if (!page_has_buffers(page))
- create_empty_buffers(page, sdp->sd_sb.sb_bsize, 0);
-
/* Locate header for our buffer within our page */
for (bh = page_buffers(page); bufnum--; bh = bh->b_this_page)
/* Do nothing */;
@@ -149,6 +152,7 @@ struct buffer_head *gfs2_getbuf(struct gfs2_glock *gl, u64 blkno, int create)
if (!buffer_mapped(bh))
map_bh(bh, sdp->sd_vfs, blkno);
+out_unlock:
unlock_page(page);
put_page(page);
@@ -239,6 +243,7 @@ static void gfs2_submit_bhs(int op, int op_flags, struct buffer_head *bhs[],
* @gl: The glock covering the block
* @blkno: The block number
* @flags: flags
+ * @rahead: Do read-ahead
* @bhp: the place where the buffer is returned (NULL on failure)
*
* Returns: errno
@@ -462,23 +467,22 @@ void gfs2_journal_wipe(struct gfs2_inode *ip, u64 bstart, u32 blen)
}
/**
- * gfs2_meta_indirect_buffer - Get a metadata buffer
+ * gfs2_meta_buffer - Get a metadata buffer
* @ip: The GFS2 inode
- * @height: The level of this buf in the metadata (indir addr) tree (if any)
+ * @mtype: The block type (GFS2_METATYPE_*)
* @num: The block number (device relative) of the buffer
* @bhp: the buffer is returned here
*
* Returns: errno
*/
-int gfs2_meta_indirect_buffer(struct gfs2_inode *ip, int height, u64 num,
- struct buffer_head **bhp)
+int gfs2_meta_buffer(struct gfs2_inode *ip, u32 mtype, u64 num,
+ struct buffer_head **bhp)
{
struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
struct gfs2_glock *gl = ip->i_gl;
struct buffer_head *bh;
int ret = 0;
- u32 mtype = height ? GFS2_METATYPE_IN : GFS2_METATYPE_DI;
int rahead = 0;
if (num == ip->i_no_addr)
diff --git a/fs/gfs2/meta_io.h b/fs/gfs2/meta_io.h
index 4a8c01929b79..21880d72081a 100644
--- a/fs/gfs2/meta_io.h
+++ b/fs/gfs2/meta_io.h
@@ -61,13 +61,13 @@ enum {
extern void gfs2_remove_from_journal(struct buffer_head *bh, int meta);
extern void gfs2_journal_wipe(struct gfs2_inode *ip, u64 bstart, u32 blen);
-extern int gfs2_meta_indirect_buffer(struct gfs2_inode *ip, int height, u64 num,
- struct buffer_head **bhp);
+extern int gfs2_meta_buffer(struct gfs2_inode *ip, u32 mtype, u64 num,
+ struct buffer_head **bhp);
static inline int gfs2_meta_inode_buffer(struct gfs2_inode *ip,
struct buffer_head **bhp)
{
- return gfs2_meta_indirect_buffer(ip, 0, ip->i_no_addr, bhp);
+ return gfs2_meta_buffer(ip, GFS2_METATYPE_DI, ip->i_no_addr, bhp);
}
struct buffer_head *gfs2_meta_ra(struct gfs2_glock *gl, u64 dblock, u32 extlen);
diff --git a/fs/gfs2/ops_fstype.c b/fs/gfs2/ops_fstype.c
index aa4136055a83..826f77d9cff5 100644
--- a/fs/gfs2/ops_fstype.c
+++ b/fs/gfs2/ops_fstype.c
@@ -150,7 +150,6 @@ fail:
/**
* gfs2_check_sb - Check superblock
* @sdp: the filesystem
- * @sb: The superblock
* @silent: Don't print a message if the check fails
*
* Checks the version code of the FS is one that we understand how to
@@ -204,7 +203,6 @@ static void gfs2_sb_in(struct gfs2_sbd *sdp, const void *buf)
sb->sb_magic = be32_to_cpu(str->sb_header.mh_magic);
sb->sb_type = be32_to_cpu(str->sb_header.mh_type);
- sb->sb_format = be32_to_cpu(str->sb_header.mh_format);
sb->sb_fs_format = be32_to_cpu(str->sb_fs_format);
sb->sb_multihost_format = be32_to_cpu(str->sb_multihost_format);
sb->sb_bsize = be32_to_cpu(str->sb_bsize);
@@ -223,7 +221,7 @@ static void gfs2_sb_in(struct gfs2_sbd *sdp, const void *buf)
* gfs2_read_super - Read the gfs2 super block from disk
* @sdp: The GFS2 super block
* @sector: The location of the super block
- * @error: The error code to return
+ * @silent: Don't print a message if the check fails
*
* This uses the bio functions to read the super block from disk
* because we want to be 100% sure that we never read cached data.
@@ -983,7 +981,6 @@ static const struct lm_lockops nolock_ops = {
/**
* gfs2_lm_mount - mount a locking protocol
* @sdp: the filesystem
- * @args: mount arguments
* @silent: if 1, don't complain if the FS isn't a GFS2 fs
*
* Returns: errno
@@ -1093,8 +1090,7 @@ void gfs2_online_uevent(struct gfs2_sbd *sdp)
/**
* gfs2_fill_super - Read in superblock
* @sb: The VFS superblock
- * @args: Mount options
- * @silent: Don't complain if it's not a GFS2 filesystem
+ * @fc: Mount options and flags
*
* Returns: -errno
*/
diff --git a/fs/gfs2/quota.c b/fs/gfs2/quota.c
index 6e173ae378c4..94637c307cc8 100644
--- a/fs/gfs2/quota.c
+++ b/fs/gfs2/quota.c
@@ -1375,8 +1375,8 @@ int gfs2_quota_init(struct gfs2_sbd *sdp)
unsigned int y;
if (!extlen) {
- int new = 0;
- error = gfs2_extent_map(&ip->i_inode, x, &new, &dblock, &extlen);
+ extlen = 32;
+ error = gfs2_get_extent(&ip->i_inode, x, &dblock, &extlen);
if (error)
goto fail;
}
@@ -1534,7 +1534,7 @@ void gfs2_wake_up_statfs(struct gfs2_sbd *sdp) {
/**
* gfs2_quotad - Write cached quota changes into the quota file
- * @sdp: Pointer to GFS2 superblock
+ * @data: Pointer to GFS2 superblock
*
*/
diff --git a/fs/gfs2/recovery.c b/fs/gfs2/recovery.c
index 282173774005..016ed1b2ca1d 100644
--- a/fs/gfs2/recovery.c
+++ b/fs/gfs2/recovery.c
@@ -34,12 +34,12 @@ int gfs2_replay_read_block(struct gfs2_jdesc *jd, unsigned int blk,
{
struct gfs2_inode *ip = GFS2_I(jd->jd_inode);
struct gfs2_glock *gl = ip->i_gl;
- int new = 0;
u64 dblock;
u32 extlen;
int error;
- error = gfs2_extent_map(&ip->i_inode, blk, &new, &dblock, &extlen);
+ extlen = 32;
+ error = gfs2_get_extent(&ip->i_inode, blk, &dblock, &extlen);
if (error)
return error;
if (!dblock) {
@@ -154,7 +154,7 @@ int __get_log_header(struct gfs2_sbd *sdp, const struct gfs2_log_header *lh,
* get_log_header - read the log header for a given segment
* @jd: the journal
* @blk: the block to look at
- * @lh: the log header to return
+ * @head: the log header to return
*
* Read the log header for a given segement in a given journal. Do a few
* sanity checks on it.
@@ -187,6 +187,7 @@ static int get_log_header(struct gfs2_jdesc *jd, unsigned int blk,
* @jd: the journal
* @start: the first log header in the active region
* @end: the last log header (don't process the contents of this entry))
+ * @pass: iteration number (foreach_descriptor() is called in a for() loop)
*
* Call a given function once for every log descriptor in the active
* portion of the log.
@@ -437,6 +438,7 @@ void gfs2_recover_func(struct work_struct *work)
case GLR_TRYFAILED:
fs_info(sdp, "jid=%u: Busy\n", jd->jd_jid);
error = 0;
+ goto fail;
default:
goto fail;
diff --git a/fs/gfs2/rgrp.c b/fs/gfs2/rgrp.c
index 89c37a845e64..c3b00ba92ed2 100644
--- a/fs/gfs2/rgrp.c
+++ b/fs/gfs2/rgrp.c
@@ -743,7 +743,7 @@ void gfs2_clear_rgrpd(struct gfs2_sbd *sdp)
}
/**
- * gfs2_compute_bitstructs - Compute the bitmap sizes
+ * compute_bitstructs - Compute the bitmap sizes
* @rgd: The resource group descriptor
*
* Calculates bitmap descriptors, one for each block that contains bitmap data
@@ -1534,8 +1534,9 @@ static void rs_insert(struct gfs2_inode *ip)
}
/**
- * rgd_free - return the number of free blocks we can allocate.
+ * rgd_free - return the number of free blocks we can allocate
* @rgd: the resource group
+ * @rs: The reservation to free
*
* This function returns the number of free blocks for an rgrp.
* That's the clone-free blocks (blocks that are free, not including those
@@ -1783,7 +1784,7 @@ static int gfs2_rbm_find(struct gfs2_rbm *rbm, u8 state, u32 *minext,
goto next_bitmap;
}
rbm->offset = offset;
- if (!rs)
+ if (!rs || !minext)
return 0;
ret = gfs2_reservation_check_and_update(rbm, rs, *minext,
@@ -2019,6 +2020,7 @@ static bool gfs2_select_rgrp(struct gfs2_rgrpd **pos, const struct gfs2_rgrpd *b
/**
* fast_to_acquire - determine if a resource group will be fast to acquire
+ * @rgd: The rgrp
*
* If this is one of our preferred rgrps, it should be quicker to acquire,
* because we tried to set ourselves up as dlm lock master.
diff --git a/fs/gfs2/super.c b/fs/gfs2/super.c
index 97076d3f562f..4d4ceb0b6903 100644
--- a/fs/gfs2/super.c
+++ b/fs/gfs2/super.c
@@ -162,8 +162,10 @@ int gfs2_make_fs_rw(struct gfs2_sbd *sdp)
int error;
error = init_threads(sdp);
- if (error)
+ if (error) {
+ gfs2_withdraw_delayed(sdp);
return error;
+ }
j_gl->gl_ops->go_inval(j_gl, DIO_METADATA);
if (gfs2_withdrawn(sdp)) {
@@ -385,8 +387,6 @@ struct lfcc {
* gfs2_lock_fs_check_clean - Stop all writes to the FS and check that all
* journals are clean
* @sdp: the file system
- * @state: the state to put the transaction lock into
- * @t_gh: the hold on the transaction lock
*
* Returns: errno
*/
@@ -699,6 +699,7 @@ restart:
/**
* gfs2_sync_fs - sync the filesystem
* @sb: the superblock
+ * @wait: true to wait for completion
*
* Flushes the log to disk.
*/
@@ -750,11 +751,13 @@ void gfs2_freeze_func(struct work_struct *work)
static int gfs2_freeze(struct super_block *sb)
{
struct gfs2_sbd *sdp = sb->s_fs_info;
- int error = 0;
+ int error;
mutex_lock(&sdp->sd_freeze_mutex);
- if (atomic_read(&sdp->sd_freeze_state) != SFS_UNFROZEN)
+ if (atomic_read(&sdp->sd_freeze_state) != SFS_UNFROZEN) {
+ error = -EBUSY;
goto out;
+ }
for (;;) {
if (gfs2_withdrawn(sdp)) {
@@ -795,10 +798,10 @@ static int gfs2_unfreeze(struct super_block *sb)
struct gfs2_sbd *sdp = sb->s_fs_info;
mutex_lock(&sdp->sd_freeze_mutex);
- if (atomic_read(&sdp->sd_freeze_state) != SFS_FROZEN ||
+ if (atomic_read(&sdp->sd_freeze_state) != SFS_FROZEN ||
!gfs2_holder_initialized(&sdp->sd_freeze_gh)) {
mutex_unlock(&sdp->sd_freeze_mutex);
- return 0;
+ return -EINVAL;
}
gfs2_freeze_unlock(&sdp->sd_freeze_gh);
@@ -807,7 +810,7 @@ static int gfs2_unfreeze(struct super_block *sb)
}
/**
- * statfs_fill - fill in the sg for a given RG
+ * statfs_slow_fill - fill in the sg for a given RG
* @rgd: the RG
* @sc: the sc structure
*
@@ -905,7 +908,7 @@ static int gfs2_statfs_slow(struct gfs2_sbd *sdp, struct gfs2_statfs_change_host
/**
* gfs2_statfs_i - Do a statfs
* @sdp: the filesystem
- * @sg: the sg structure
+ * @sc: the sc structure
*
* Returns: errno
*/
@@ -936,8 +939,8 @@ static int gfs2_statfs_i(struct gfs2_sbd *sdp, struct gfs2_statfs_change_host *s
/**
* gfs2_statfs - Gather and return stats about the filesystem
- * @sb: The superblock
- * @statfsbuf: The buffer
+ * @dentry: The name of the link
+ * @buf: The buffer
*
* Returns: 0 on success or error code
*/
@@ -1268,6 +1271,7 @@ static bool gfs2_upgrade_iopen_glock(struct inode *inode)
/**
* evict_should_delete - determine whether the inode is eligible for deletion
* @inode: The inode to evict
+ * @gh: The glock holder structure
*
* This function determines whether the evicted inode is eligible to be deleted
* and locks the inode glock.
diff --git a/fs/gfs2/sys.c b/fs/gfs2/sys.c
index c3e72dba7418..c0a34d9ddee4 100644
--- a/fs/gfs2/sys.c
+++ b/fs/gfs2/sys.c
@@ -63,6 +63,71 @@ static ssize_t id_show(struct gfs2_sbd *sdp, char *buf)
MAJOR(sdp->sd_vfs->s_dev), MINOR(sdp->sd_vfs->s_dev));
}
+static ssize_t status_show(struct gfs2_sbd *sdp, char *buf)
+{
+ unsigned long f = sdp->sd_flags;
+ ssize_t s;
+
+ s = snprintf(buf, PAGE_SIZE,
+ "Journal Checked: %d\n"
+ "Journal Live: %d\n"
+ "Journal ID: %d\n"
+ "Spectator: %d\n"
+ "Withdrawn: %d\n"
+ "No barriers: %d\n"
+ "No recovery: %d\n"
+ "Demote: %d\n"
+ "No Journal ID: %d\n"
+ "Mounted RO: %d\n"
+ "RO Recovery: %d\n"
+ "Skip DLM Unlock: %d\n"
+ "Force AIL Flush: %d\n"
+ "FS Frozen: %d\n"
+ "Withdrawing: %d\n"
+ "Withdraw In Prog: %d\n"
+ "Remote Withdraw: %d\n"
+ "Withdraw Recovery: %d\n"
+ "sd_log_error: %d\n"
+ "sd_log_flush_lock: %d\n"
+ "sd_log_num_revoke: %u\n"
+ "sd_log_in_flight: %d\n"
+ "sd_log_blks_needed: %d\n"
+ "sd_log_blks_free: %d\n"
+ "sd_log_flush_head: %d\n"
+ "sd_log_flush_tail: %d\n"
+ "sd_log_blks_reserved: %d\n"
+ "sd_log_revokes_available: %d\n",
+ test_bit(SDF_JOURNAL_CHECKED, &f),
+ test_bit(SDF_JOURNAL_LIVE, &f),
+ (sdp->sd_jdesc ? sdp->sd_jdesc->jd_jid : 0),
+ (sdp->sd_args.ar_spectator ? 1 : 0),
+ test_bit(SDF_WITHDRAWN, &f),
+ test_bit(SDF_NOBARRIERS, &f),
+ test_bit(SDF_NORECOVERY, &f),
+ test_bit(SDF_DEMOTE, &f),
+ test_bit(SDF_NOJOURNALID, &f),
+ (sb_rdonly(sdp->sd_vfs) ? 1 : 0),
+ test_bit(SDF_RORECOVERY, &f),
+ test_bit(SDF_SKIP_DLM_UNLOCK, &f),
+ test_bit(SDF_FORCE_AIL_FLUSH, &f),
+ test_bit(SDF_FS_FROZEN, &f),
+ test_bit(SDF_WITHDRAWING, &f),
+ test_bit(SDF_WITHDRAW_IN_PROG, &f),
+ test_bit(SDF_REMOTE_WITHDRAW, &f),
+ test_bit(SDF_WITHDRAW_RECOVERY, &f),
+ sdp->sd_log_error,
+ rwsem_is_locked(&sdp->sd_log_flush_lock),
+ sdp->sd_log_num_revoke,
+ atomic_read(&sdp->sd_log_in_flight),
+ atomic_read(&sdp->sd_log_blks_needed),
+ atomic_read(&sdp->sd_log_blks_free),
+ sdp->sd_log_flush_head,
+ sdp->sd_log_flush_tail,
+ sdp->sd_log_blks_reserved,
+ atomic_read(&sdp->sd_log_revokes_available));
+ return s;
+}
+
static ssize_t fsname_show(struct gfs2_sbd *sdp, char *buf)
{
return snprintf(buf, PAGE_SIZE, "%s\n", sdp->sd_fsname);
@@ -283,6 +348,7 @@ GFS2_ATTR(quota_sync, 0200, NULL, quota_sync_store);
GFS2_ATTR(quota_refresh_user, 0200, NULL, quota_refresh_user_store);
GFS2_ATTR(quota_refresh_group, 0200, NULL, quota_refresh_group_store);
GFS2_ATTR(demote_rq, 0200, NULL, demote_rq_store);
+GFS2_ATTR(status, 0400, status_show, NULL);
static struct attribute *gfs2_attrs[] = {
&gfs2_attr_id.attr,
@@ -295,6 +361,7 @@ static struct attribute *gfs2_attrs[] = {
&gfs2_attr_quota_refresh_user.attr,
&gfs2_attr_quota_refresh_group.attr,
&gfs2_attr_demote_rq.attr,
+ &gfs2_attr_status.attr,
NULL,
};
ATTRIBUTE_GROUPS(gfs2);
diff --git a/fs/gfs2/util.c b/fs/gfs2/util.c
index 4f034b87b427..3e08027a6c81 100644
--- a/fs/gfs2/util.c
+++ b/fs/gfs2/util.c
@@ -44,6 +44,7 @@ void gfs2_assert_i(struct gfs2_sbd *sdp)
* check_journal_clean - Make sure a journal is clean for a spectator mount
* @sdp: The GFS2 superblock
* @jd: The journal descriptor
+ * @verbose: Show more prints in the log
*
* Returns: 0 if the journal is clean or locked, else an error
*/
@@ -362,7 +363,7 @@ int gfs2_withdraw(struct gfs2_sbd *sdp)
return -1;
}
-/**
+/*
* gfs2_assert_withdraw_i - Cause the machine to withdraw if @assertion is false
*/
@@ -392,7 +393,7 @@ void gfs2_assert_withdraw_i(struct gfs2_sbd *sdp, char *assertion,
dump_stack();
}
-/**
+/*
* gfs2_assert_warn_i - Print a message to the console if @assertion is false
*/
@@ -422,7 +423,7 @@ void gfs2_assert_warn_i(struct gfs2_sbd *sdp, char *assertion,
sdp->sd_last_warning = jiffies;
}
-/**
+/*
* gfs2_consist_i - Flag a filesystem consistency error and withdraw
*/
@@ -435,7 +436,7 @@ void gfs2_consist_i(struct gfs2_sbd *sdp, const char *function,
gfs2_withdraw(sdp);
}
-/**
+/*
* gfs2_consist_inode_i - Flag an inode consistency error and withdraw
*/
@@ -454,7 +455,7 @@ void gfs2_consist_inode_i(struct gfs2_inode *ip,
gfs2_withdraw(sdp);
}
-/**
+/*
* gfs2_consist_rgrpd_i - Flag a RG consistency error and withdraw
*/
@@ -475,7 +476,7 @@ void gfs2_consist_rgrpd_i(struct gfs2_rgrpd *rgd,
gfs2_withdraw(sdp);
}
-/**
+/*
* gfs2_meta_check_ii - Flag a magic number consistency error and withdraw
* Returns: -1 if this call withdrew the machine,
* -2 if it was already withdrawn
@@ -497,7 +498,7 @@ int gfs2_meta_check_ii(struct gfs2_sbd *sdp, struct buffer_head *bh,
return (me) ? -1 : -2;
}
-/**
+/*
* gfs2_metatype_check_ii - Flag a metadata type consistency error and withdraw
* Returns: -1 if this call withdrew the machine,
* -2 if it was already withdrawn
@@ -519,7 +520,7 @@ int gfs2_metatype_check_ii(struct gfs2_sbd *sdp, struct buffer_head *bh,
return (me) ? -1 : -2;
}
-/**
+/*
* gfs2_io_error_i - Flag an I/O error and withdraw
* Returns: -1 if this call withdrew the machine,
* 0 if it was already withdrawn
@@ -535,7 +536,7 @@ int gfs2_io_error_i(struct gfs2_sbd *sdp, const char *function, char *file,
return gfs2_withdraw(sdp);
}
-/**
+/*
* gfs2_io_error_bh_i - Flag a buffer I/O error
* @withdraw: withdraw the filesystem
*/
diff --git a/fs/gfs2/xattr.c b/fs/gfs2/xattr.c
index 124b3d5a7266..0c5650fe1fd1 100644
--- a/fs/gfs2/xattr.c
+++ b/fs/gfs2/xattr.c
@@ -26,12 +26,9 @@
#include "trans.h"
#include "util.h"
-/**
- * ea_calc_size - returns the acutal number of bytes the request will take up
+/*
+ * ea_calc_size - returns the actual number of bytes the request will take up
* (not counting any unstuffed data blocks)
- * @sdp:
- * @er:
- * @size:
*
* Returns: 1 if the EA should be stuffed
*/
@@ -219,13 +216,8 @@ static int gfs2_ea_find(struct gfs2_inode *ip, int type, const char *name,
return error;
}
-/**
- * ea_dealloc_unstuffed -
- * @ip:
- * @bh:
- * @ea:
- * @prev:
- * @private:
+/*
+ * ea_dealloc_unstuffed
*
* Take advantage of the fact that all unstuffed blocks are
* allocated from the same RG. But watch, this may not always
@@ -448,8 +440,8 @@ ssize_t gfs2_listxattr(struct dentry *dentry, char *buffer, size_t size)
}
/**
- * ea_iter_unstuffed - copies the unstuffed xattr data to/from the
- * request buffer
+ * gfs2_iter_unstuffed - copies the unstuffed xattr data to/from the
+ * request buffer
* @ip: The GFS2 inode
* @ea: The extended attribute header structure
* @din: The data to be copied in
@@ -573,7 +565,7 @@ out:
}
/**
- * gfs2_xattr_get - Get a GFS2 extended attribute
+ * __gfs2_xattr_get - Get a GFS2 extended attribute
* @inode: The inode
* @name: The name of the extended attribute
* @buffer: The buffer to write the result into
@@ -801,14 +793,11 @@ static int ea_init_i(struct gfs2_inode *ip, struct gfs2_ea_request *er,
return error;
}
-/**
+/*
* ea_init - initializes a new eattr block
- * @ip:
- * @er:
*
* Returns: errno
*/
-
static int ea_init(struct gfs2_inode *ip, int type, const char *name,
const void *data, size_t size)
{
@@ -1164,7 +1153,7 @@ static int gfs2_xattr_remove(struct gfs2_inode *ip, int type, const char *name)
/**
* __gfs2_xattr_set - Set (or remove) a GFS2 extended attribute
- * @ip: The inode
+ * @inode: The inode
* @name: The name of the extended attribute
* @value: The value of the extended attribute (NULL for remove)
* @size: The size of the @value argument
diff --git a/fs/hfsplus/dir.c b/fs/hfsplus/dir.c
index 03e6c046faf4..84714bbccc12 100644
--- a/fs/hfsplus/dir.c
+++ b/fs/hfsplus/dir.c
@@ -569,6 +569,8 @@ const struct inode_operations hfsplus_dir_inode_operations = {
.rename = hfsplus_rename,
.getattr = hfsplus_getattr,
.listxattr = hfsplus_listxattr,
+ .fileattr_get = hfsplus_fileattr_get,
+ .fileattr_set = hfsplus_fileattr_set,
};
const struct file_operations hfsplus_dir_operations = {
diff --git a/fs/hfsplus/hfsplus_fs.h b/fs/hfsplus/hfsplus_fs.h
index 12b20479ed2b..1798949f269b 100644
--- a/fs/hfsplus/hfsplus_fs.h
+++ b/fs/hfsplus/hfsplus_fs.h
@@ -345,17 +345,6 @@ static inline unsigned short hfsplus_min_io_size(struct super_block *sb)
#define hfs_part_find hfsplus_part_find
/*
- * definitions for ext2 flag ioctls (linux really needs a generic
- * interface for this).
- */
-
-/* ext2 ioctls (EXT2_IOC_GETFLAGS and EXT2_IOC_SETFLAGS) to support
- * chattr/lsattr */
-#define HFSPLUS_IOC_EXT2_GETFLAGS FS_IOC_GETFLAGS
-#define HFSPLUS_IOC_EXT2_SETFLAGS FS_IOC_SETFLAGS
-
-
-/*
* hfs+-specific ioctl for making the filesystem bootable
*/
#define HFSPLUS_IOC_BLESS _IO('h', 0x80)
@@ -493,6 +482,9 @@ int hfsplus_getattr(struct user_namespace *mnt_userns, const struct path *path,
unsigned int query_flags);
int hfsplus_file_fsync(struct file *file, loff_t start, loff_t end,
int datasync);
+int hfsplus_fileattr_get(struct dentry *dentry, struct fileattr *fa);
+int hfsplus_fileattr_set(struct user_namespace *mnt_userns,
+ struct dentry *dentry, struct fileattr *fa);
/* ioctl.c */
long hfsplus_ioctl(struct file *filp, unsigned int cmd, unsigned long arg);
diff --git a/fs/hfsplus/inode.c b/fs/hfsplus/inode.c
index 078c5c8a5156..8ea447e5c470 100644
--- a/fs/hfsplus/inode.c
+++ b/fs/hfsplus/inode.c
@@ -17,6 +17,7 @@
#include <linux/sched.h>
#include <linux/cred.h>
#include <linux/uio.h>
+#include <linux/fileattr.h>
#include "hfsplus_fs.h"
#include "hfsplus_raw.h"
@@ -353,6 +354,8 @@ static const struct inode_operations hfsplus_file_inode_operations = {
.setattr = hfsplus_setattr,
.getattr = hfsplus_getattr,
.listxattr = hfsplus_listxattr,
+ .fileattr_get = hfsplus_fileattr_get,
+ .fileattr_set = hfsplus_fileattr_set,
};
static const struct file_operations hfsplus_file_operations = {
@@ -628,3 +631,54 @@ out:
hfs_find_exit(&fd);
return 0;
}
+
+int hfsplus_fileattr_get(struct dentry *dentry, struct fileattr *fa)
+{
+ struct inode *inode = d_inode(dentry);
+ struct hfsplus_inode_info *hip = HFSPLUS_I(inode);
+ unsigned int flags = 0;
+
+ if (inode->i_flags & S_IMMUTABLE)
+ flags |= FS_IMMUTABLE_FL;
+ if (inode->i_flags & S_APPEND)
+ flags |= FS_APPEND_FL;
+ if (hip->userflags & HFSPLUS_FLG_NODUMP)
+ flags |= FS_NODUMP_FL;
+
+ fileattr_fill_flags(fa, flags);
+
+ return 0;
+}
+
+int hfsplus_fileattr_set(struct user_namespace *mnt_userns,
+ struct dentry *dentry, struct fileattr *fa)
+{
+ struct inode *inode = d_inode(dentry);
+ struct hfsplus_inode_info *hip = HFSPLUS_I(inode);
+ unsigned int new_fl = 0;
+
+ if (fileattr_has_fsx(fa))
+ return -EOPNOTSUPP;
+
+ /* don't silently ignore unsupported ext2 flags */
+ if (fa->flags & ~(FS_IMMUTABLE_FL|FS_APPEND_FL|FS_NODUMP_FL))
+ return -EOPNOTSUPP;
+
+ if (fa->flags & FS_IMMUTABLE_FL)
+ new_fl |= S_IMMUTABLE;
+
+ if (fa->flags & FS_APPEND_FL)
+ new_fl |= S_APPEND;
+
+ inode_set_flags(inode, new_fl, S_IMMUTABLE | S_APPEND);
+
+ if (fa->flags & FS_NODUMP_FL)
+ hip->userflags |= HFSPLUS_FLG_NODUMP;
+ else
+ hip->userflags &= ~HFSPLUS_FLG_NODUMP;
+
+ inode->i_ctime = current_time(inode);
+ mark_inode_dirty(inode);
+
+ return 0;
+}
diff --git a/fs/hfsplus/ioctl.c b/fs/hfsplus/ioctl.c
index 3edb1926d127..5661a2e24d03 100644
--- a/fs/hfsplus/ioctl.c
+++ b/fs/hfsplus/ioctl.c
@@ -57,95 +57,11 @@ static int hfsplus_ioctl_bless(struct file *file, int __user *user_flags)
return 0;
}
-static inline unsigned int hfsplus_getflags(struct inode *inode)
-{
- struct hfsplus_inode_info *hip = HFSPLUS_I(inode);
- unsigned int flags = 0;
-
- if (inode->i_flags & S_IMMUTABLE)
- flags |= FS_IMMUTABLE_FL;
- if (inode->i_flags & S_APPEND)
- flags |= FS_APPEND_FL;
- if (hip->userflags & HFSPLUS_FLG_NODUMP)
- flags |= FS_NODUMP_FL;
- return flags;
-}
-
-static int hfsplus_ioctl_getflags(struct file *file, int __user *user_flags)
-{
- struct inode *inode = file_inode(file);
- unsigned int flags = hfsplus_getflags(inode);
-
- return put_user(flags, user_flags);
-}
-
-static int hfsplus_ioctl_setflags(struct file *file, int __user *user_flags)
-{
- struct inode *inode = file_inode(file);
- struct hfsplus_inode_info *hip = HFSPLUS_I(inode);
- unsigned int flags, new_fl = 0;
- unsigned int oldflags = hfsplus_getflags(inode);
- int err = 0;
-
- err = mnt_want_write_file(file);
- if (err)
- goto out;
-
- if (!inode_owner_or_capable(&init_user_ns, inode)) {
- err = -EACCES;
- goto out_drop_write;
- }
-
- if (get_user(flags, user_flags)) {
- err = -EFAULT;
- goto out_drop_write;
- }
-
- inode_lock(inode);
-
- err = vfs_ioc_setflags_prepare(inode, oldflags, flags);
- if (err)
- goto out_unlock_inode;
-
- /* don't silently ignore unsupported ext2 flags */
- if (flags & ~(FS_IMMUTABLE_FL|FS_APPEND_FL|FS_NODUMP_FL)) {
- err = -EOPNOTSUPP;
- goto out_unlock_inode;
- }
-
- if (flags & FS_IMMUTABLE_FL)
- new_fl |= S_IMMUTABLE;
-
- if (flags & FS_APPEND_FL)
- new_fl |= S_APPEND;
-
- inode_set_flags(inode, new_fl, S_IMMUTABLE | S_APPEND);
-
- if (flags & FS_NODUMP_FL)
- hip->userflags |= HFSPLUS_FLG_NODUMP;
- else
- hip->userflags &= ~HFSPLUS_FLG_NODUMP;
-
- inode->i_ctime = current_time(inode);
- mark_inode_dirty(inode);
-
-out_unlock_inode:
- inode_unlock(inode);
-out_drop_write:
- mnt_drop_write_file(file);
-out:
- return err;
-}
-
long hfsplus_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
{
void __user *argp = (void __user *)arg;
switch (cmd) {
- case HFSPLUS_IOC_EXT2_GETFLAGS:
- return hfsplus_ioctl_getflags(file, argp);
- case HFSPLUS_IOC_EXT2_SETFLAGS:
- return hfsplus_ioctl_setflags(file, argp);
case HFSPLUS_IOC_BLESS:
return hfsplus_ioctl_bless(file, argp);
default:
diff --git a/fs/hostfs/hostfs_kern.c b/fs/hostfs/hostfs_kern.c
index 29e407762626..7d0c3dbb2898 100644
--- a/fs/hostfs/hostfs_kern.c
+++ b/fs/hostfs/hostfs_kern.c
@@ -144,7 +144,7 @@ static char *follow_link(char *link)
char *name, *resolved, *end;
int n;
- name = __getname();
+ name = kmalloc(PATH_MAX, GFP_KERNEL);
if (!name) {
n = -ENOMEM;
goto out_free;
@@ -173,12 +173,11 @@ static char *follow_link(char *link)
goto out_free;
}
- __putname(name);
- kfree(link);
+ kfree(name);
return resolved;
out_free:
- __putname(name);
+ kfree(name);
return ERR_PTR(n);
}
@@ -317,7 +316,7 @@ retry:
if (mode & FMODE_WRITE)
r = w = 1;
- name = dentry_name(d_real(file->f_path.dentry, file->f_inode));
+ name = dentry_name(file_dentry(file));
if (name == NULL)
return -ENOMEM;
@@ -712,7 +711,6 @@ static int hostfs_mknod(struct user_namespace *mnt_userns, struct inode *dir,
if (name == NULL)
goto out_put;
- init_special_inode(inode, mode, dev);
err = do_mknod(name, mode, MAJOR(dev), MINOR(dev));
if (err)
goto out_free;
diff --git a/fs/inode.c b/fs/inode.c
index a047ab306f9a..9e192bea0630 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -12,7 +12,6 @@
#include <linux/security.h>
#include <linux/cdev.h>
#include <linux/memblock.h>
-#include <linux/fscrypt.h>
#include <linux/fsnotify.h>
#include <linux/mount.h>
#include <linux/posix_acl.h>
@@ -2148,7 +2147,7 @@ EXPORT_SYMBOL(init_special_inode);
void inode_init_owner(struct user_namespace *mnt_userns, struct inode *inode,
const struct inode *dir, umode_t mode)
{
- inode->i_uid = fsuid_into_mnt(mnt_userns);
+ inode_fsuid_set(inode, mnt_userns);
if (dir && dir->i_mode & S_ISGID) {
inode->i_gid = dir->i_gid;
@@ -2160,7 +2159,7 @@ void inode_init_owner(struct user_namespace *mnt_userns, struct inode *inode,
!capable_wrt_inode_uidgid(mnt_userns, dir, CAP_FSETID))
mode &= ~S_ISGID;
} else
- inode->i_gid = fsgid_into_mnt(mnt_userns);
+ inode_fsgid_set(inode, mnt_userns);
inode->i_mode = mode;
}
EXPORT_SYMBOL(inode_init_owner);
@@ -2314,89 +2313,3 @@ struct timespec64 current_time(struct inode *inode)
return timestamp_truncate(now, inode);
}
EXPORT_SYMBOL(current_time);
-
-/*
- * Generic function to check FS_IOC_SETFLAGS values and reject any invalid
- * configurations.
- *
- * Note: the caller should be holding i_mutex, or else be sure that they have
- * exclusive access to the inode structure.
- */
-int vfs_ioc_setflags_prepare(struct inode *inode, unsigned int oldflags,
- unsigned int flags)
-{
- /*
- * The IMMUTABLE and APPEND_ONLY flags can only be changed by
- * the relevant capability.
- *
- * This test looks nicer. Thanks to Pauline Middelink
- */
- if ((flags ^ oldflags) & (FS_APPEND_FL | FS_IMMUTABLE_FL) &&
- !capable(CAP_LINUX_IMMUTABLE))
- return -EPERM;
-
- return fscrypt_prepare_setflags(inode, oldflags, flags);
-}
-EXPORT_SYMBOL(vfs_ioc_setflags_prepare);
-
-/*
- * Generic function to check FS_IOC_FSSETXATTR values and reject any invalid
- * configurations.
- *
- * Note: the caller should be holding i_mutex, or else be sure that they have
- * exclusive access to the inode structure.
- */
-int vfs_ioc_fssetxattr_check(struct inode *inode, const struct fsxattr *old_fa,
- struct fsxattr *fa)
-{
- /*
- * Can't modify an immutable/append-only file unless we have
- * appropriate permission.
- */
- if ((old_fa->fsx_xflags ^ fa->fsx_xflags) &
- (FS_XFLAG_IMMUTABLE | FS_XFLAG_APPEND) &&
- !capable(CAP_LINUX_IMMUTABLE))
- return -EPERM;
-
- /*
- * Project Quota ID state is only allowed to change from within the init
- * namespace. Enforce that restriction only if we are trying to change
- * the quota ID state. Everything else is allowed in user namespaces.
- */
- if (current_user_ns() != &init_user_ns) {
- if (old_fa->fsx_projid != fa->fsx_projid)
- return -EINVAL;
- if ((old_fa->fsx_xflags ^ fa->fsx_xflags) &
- FS_XFLAG_PROJINHERIT)
- return -EINVAL;
- }
-
- /* Check extent size hints. */
- if ((fa->fsx_xflags & FS_XFLAG_EXTSIZE) && !S_ISREG(inode->i_mode))
- return -EINVAL;
-
- if ((fa->fsx_xflags & FS_XFLAG_EXTSZINHERIT) &&
- !S_ISDIR(inode->i_mode))
- return -EINVAL;
-
- if ((fa->fsx_xflags & FS_XFLAG_COWEXTSIZE) &&
- !S_ISREG(inode->i_mode) && !S_ISDIR(inode->i_mode))
- return -EINVAL;
-
- /*
- * It is only valid to set the DAX flag on regular files and
- * directories on filesystems.
- */
- if ((fa->fsx_xflags & FS_XFLAG_DAX) &&
- !(S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode)))
- return -EINVAL;
-
- /* Extent size hints of zero turn off the flags. */
- if (fa->fsx_extsize == 0)
- fa->fsx_xflags &= ~(FS_XFLAG_EXTSIZE | FS_XFLAG_EXTSZINHERIT);
- if (fa->fsx_cowextsize == 0)
- fa->fsx_xflags &= ~FS_XFLAG_COWEXTSIZE;
-
- return 0;
-}
-EXPORT_SYMBOL(vfs_ioc_fssetxattr_check);
diff --git a/fs/io-wq.c b/fs/io-wq.c
index 0ae9ecadf295..5361a9b4b47b 100644
--- a/fs/io-wq.c
+++ b/fs/io-wq.c
@@ -16,9 +16,7 @@
#include <linux/rculist_nulls.h>
#include <linux/cpu.h>
#include <linux/tracehook.h>
-#include <linux/freezer.h>
-#include "../kernel/sched/sched.h"
#include "io-wq.h"
#define WORKER_IDLE_TIMEOUT (5 * HZ)
@@ -69,6 +67,7 @@ struct io_worker {
struct io_wqe_acct {
unsigned nr_workers;
unsigned max_workers;
+ int index;
atomic_t nr_running;
};
@@ -109,19 +108,16 @@ struct io_wq {
free_work_fn *free_work;
io_wq_work_fn *do_work;
- struct task_struct *manager;
-
struct io_wq_hash *hash;
refcount_t refs;
- struct completion exited;
atomic_t worker_refs;
struct completion worker_done;
struct hlist_node cpuhp_node;
- pid_t task_pid;
+ struct task_struct *task;
};
static enum cpuhp_state io_wq_online;
@@ -134,8 +130,7 @@ struct io_cb_cancel_data {
bool cancel_all;
};
-static void io_wqe_cancel_pending_work(struct io_wqe *wqe,
- struct io_cb_cancel_data *match);
+static void create_io_worker(struct io_wq *wq, struct io_wqe *wqe, int index);
static bool io_worker_get(struct io_worker *worker)
{
@@ -148,23 +143,26 @@ static void io_worker_release(struct io_worker *worker)
complete(&worker->ref_done);
}
+static inline struct io_wqe_acct *io_get_acct(struct io_wqe *wqe, bool bound)
+{
+ return &wqe->acct[bound ? IO_WQ_ACCT_BOUND : IO_WQ_ACCT_UNBOUND];
+}
+
static inline struct io_wqe_acct *io_work_get_acct(struct io_wqe *wqe,
struct io_wq_work *work)
{
- if (work->flags & IO_WQ_WORK_UNBOUND)
- return &wqe->acct[IO_WQ_ACCT_UNBOUND];
-
- return &wqe->acct[IO_WQ_ACCT_BOUND];
+ return io_get_acct(wqe, !(work->flags & IO_WQ_WORK_UNBOUND));
}
static inline struct io_wqe_acct *io_wqe_get_acct(struct io_worker *worker)
{
- struct io_wqe *wqe = worker->wqe;
-
- if (worker->flags & IO_WORKER_F_BOUND)
- return &wqe->acct[IO_WQ_ACCT_BOUND];
+ return io_get_acct(worker->wqe, worker->flags & IO_WORKER_F_BOUND);
+}
- return &wqe->acct[IO_WQ_ACCT_UNBOUND];
+static void io_worker_ref_put(struct io_wq *wq)
+{
+ if (atomic_dec_and_test(&wq->worker_refs))
+ complete(&wq->worker_done);
}
static void io_worker_exit(struct io_worker *worker)
@@ -194,8 +192,7 @@ static void io_worker_exit(struct io_worker *worker)
raw_spin_unlock_irq(&wqe->lock);
kfree_rcu(worker, rcu);
- if (atomic_dec_and_test(&wqe->wq->worker_refs))
- complete(&wqe->wq->worker_done);
+ io_worker_ref_put(wqe->wq);
do_exit(0);
}
@@ -210,7 +207,7 @@ static inline bool io_wqe_run_queue(struct io_wqe *wqe)
/*
* Check head of free list for an available worker. If one isn't available,
- * caller must wake up the wq manager to create one.
+ * caller must create one.
*/
static bool io_wqe_activate_free_worker(struct io_wqe *wqe)
__must_hold(RCU)
@@ -234,7 +231,7 @@ static bool io_wqe_activate_free_worker(struct io_wqe *wqe)
/*
* We need a worker. If we find a free one, we're good. If not, and we're
- * below the max number of workers, wake up the manager to create one.
+ * below the max number of workers, create one.
*/
static void io_wqe_wake_worker(struct io_wqe *wqe, struct io_wqe_acct *acct)
{
@@ -250,8 +247,11 @@ static void io_wqe_wake_worker(struct io_wqe *wqe, struct io_wqe_acct *acct)
ret = io_wqe_activate_free_worker(wqe);
rcu_read_unlock();
- if (!ret && acct->nr_workers < acct->max_workers)
- wake_up_process(wqe->wq->manager);
+ if (!ret && acct->nr_workers < acct->max_workers) {
+ atomic_inc(&acct->nr_running);
+ atomic_inc(&wqe->wq->worker_refs);
+ create_io_worker(wqe->wq, wqe, acct->index);
+ }
}
static void io_wqe_inc_running(struct io_worker *worker)
@@ -261,14 +261,61 @@ static void io_wqe_inc_running(struct io_worker *worker)
atomic_inc(&acct->nr_running);
}
+struct create_worker_data {
+ struct callback_head work;
+ struct io_wqe *wqe;
+ int index;
+};
+
+static void create_worker_cb(struct callback_head *cb)
+{
+ struct create_worker_data *cwd;
+ struct io_wq *wq;
+
+ cwd = container_of(cb, struct create_worker_data, work);
+ wq = cwd->wqe->wq;
+ create_io_worker(wq, cwd->wqe, cwd->index);
+ kfree(cwd);
+}
+
+static void io_queue_worker_create(struct io_wqe *wqe, struct io_wqe_acct *acct)
+{
+ struct create_worker_data *cwd;
+ struct io_wq *wq = wqe->wq;
+
+ /* raced with exit, just ignore create call */
+ if (test_bit(IO_WQ_BIT_EXIT, &wq->state))
+ goto fail;
+
+ cwd = kmalloc(sizeof(*cwd), GFP_ATOMIC);
+ if (cwd) {
+ init_task_work(&cwd->work, create_worker_cb);
+ cwd->wqe = wqe;
+ cwd->index = acct->index;
+ if (!task_work_add(wq->task, &cwd->work, TWA_SIGNAL))
+ return;
+
+ kfree(cwd);
+ }
+fail:
+ atomic_dec(&acct->nr_running);
+ io_worker_ref_put(wq);
+}
+
static void io_wqe_dec_running(struct io_worker *worker)
__must_hold(wqe->lock)
{
struct io_wqe_acct *acct = io_wqe_get_acct(worker);
struct io_wqe *wqe = worker->wqe;
- if (atomic_dec_and_test(&acct->nr_running) && io_wqe_run_queue(wqe))
- io_wqe_wake_worker(wqe, acct);
+ if (!(worker->flags & IO_WORKER_F_UP))
+ return;
+
+ if (atomic_dec_and_test(&acct->nr_running) && io_wqe_run_queue(wqe)) {
+ atomic_inc(&acct->nr_running);
+ atomic_inc(&wqe->wq->worker_refs);
+ io_queue_worker_create(wqe, acct);
+ }
}
/*
@@ -281,6 +328,8 @@ static void __io_worker_busy(struct io_wqe *wqe, struct io_worker *worker,
{
bool worker_bound, work_bound;
+ BUILD_BUG_ON((IO_WQ_ACCT_UNBOUND ^ IO_WQ_ACCT_BOUND) != 1);
+
if (worker->flags & IO_WORKER_F_FREE) {
worker->flags &= ~IO_WORKER_F_FREE;
hlist_nulls_del_init_rcu(&worker->nulls_node);
@@ -293,16 +342,11 @@ static void __io_worker_busy(struct io_wqe *wqe, struct io_worker *worker,
worker_bound = (worker->flags & IO_WORKER_F_BOUND) != 0;
work_bound = (work->flags & IO_WQ_WORK_UNBOUND) == 0;
if (worker_bound != work_bound) {
+ int index = work_bound ? IO_WQ_ACCT_UNBOUND : IO_WQ_ACCT_BOUND;
io_wqe_dec_running(worker);
- if (work_bound) {
- worker->flags |= IO_WORKER_F_BOUND;
- wqe->acct[IO_WQ_ACCT_UNBOUND].nr_workers--;
- wqe->acct[IO_WQ_ACCT_BOUND].nr_workers++;
- } else {
- worker->flags &= ~IO_WORKER_F_BOUND;
- wqe->acct[IO_WQ_ACCT_UNBOUND].nr_workers++;
- wqe->acct[IO_WQ_ACCT_BOUND].nr_workers--;
- }
+ worker->flags ^= IO_WORKER_F_BOUND;
+ wqe->acct[index].nr_workers--;
+ wqe->acct[index ^ 1].nr_workers++;
io_wqe_inc_running(worker);
}
}
@@ -386,13 +430,14 @@ static struct io_wq_work *io_get_next_work(struct io_wqe *wqe)
return NULL;
}
-static void io_flush_signals(void)
+static bool io_flush_signals(void)
{
- if (unlikely(test_tsk_thread_flag(current, TIF_NOTIFY_SIGNAL))) {
- if (current->task_works)
- task_work_run();
- clear_tsk_thread_flag(current, TIF_NOTIFY_SIGNAL);
+ if (unlikely(test_thread_flag(TIF_NOTIFY_SIGNAL))) {
+ __set_current_state(TASK_RUNNING);
+ tracehook_notify_signal();
+ return true;
}
+ return false;
}
static void io_assign_current_work(struct io_worker *worker,
@@ -415,6 +460,7 @@ static void io_worker_handle_work(struct io_worker *worker)
{
struct io_wqe *wqe = worker->wqe;
struct io_wq *wq = wqe->wq;
+ bool do_kill = test_bit(IO_WQ_BIT_EXIT, &wq->state);
do {
struct io_wq_work *work;
@@ -444,6 +490,9 @@ get_next:
unsigned int hash = io_get_work_hash(work);
next_hashed = wq_next_work(work);
+
+ if (unlikely(do_kill) && (work->flags & IO_WQ_WORK_UNBOUND))
+ work->flags |= IO_WQ_WORK_CANCEL;
wq->do_work(work);
io_assign_current_work(worker, NULL);
@@ -482,12 +531,13 @@ static int io_wqe_worker(void *data)
char buf[TASK_COMM_LEN];
worker->flags |= (IO_WORKER_F_UP | IO_WORKER_F_RUNNING);
- io_wqe_inc_running(worker);
- sprintf(buf, "iou-wrk-%d", wq->task_pid);
+ snprintf(buf, sizeof(buf), "iou-wrk-%d", wq->task->pid);
set_task_comm(current, buf);
while (!test_bit(IO_WQ_BIT_EXIT, &wq->state)) {
+ long ret;
+
set_current_state(TASK_INTERRUPTIBLE);
loop:
raw_spin_lock_irq(&wqe->lock);
@@ -497,11 +547,18 @@ loop:
}
__io_worker_idle(wqe, worker);
raw_spin_unlock_irq(&wqe->lock);
- io_flush_signals();
- if (schedule_timeout(WORKER_IDLE_TIMEOUT))
+ if (io_flush_signals())
continue;
- if (fatal_signal_pending(current))
+ ret = schedule_timeout(WORKER_IDLE_TIMEOUT);
+ if (signal_pending(current)) {
+ struct ksignal ksig;
+
+ if (!get_signal(&ksig))
+ continue;
break;
+ }
+ if (ret)
+ continue;
/* timed out, exit unless we're the fixed worker */
if (test_bit(IO_WQ_BIT_EXIT, &wq->state) ||
!(worker->flags & IO_WORKER_F_FIXED))
@@ -539,8 +596,7 @@ void io_wq_worker_running(struct task_struct *tsk)
/*
* Called when worker is going to sleep. If there are no workers currently
- * running and we have work pending, wake up a free one or have the manager
- * set one up.
+ * running and we have work pending, wake up a free one or create a new one.
*/
void io_wq_worker_sleeping(struct task_struct *tsk)
{
@@ -560,7 +616,7 @@ void io_wq_worker_sleeping(struct task_struct *tsk)
raw_spin_unlock_irq(&worker->wqe->lock);
}
-static bool create_io_worker(struct io_wq *wq, struct io_wqe *wqe, int index)
+static void create_io_worker(struct io_wq *wq, struct io_wqe *wqe, int index)
{
struct io_wqe_acct *acct = &wqe->acct[index];
struct io_worker *worker;
@@ -570,7 +626,7 @@ static bool create_io_worker(struct io_wq *wq, struct io_wqe *wqe, int index)
worker = kzalloc_node(sizeof(*worker), GFP_KERNEL, wqe->node);
if (!worker)
- return false;
+ goto fail;
refcount_set(&worker->ref, 1);
worker->nulls_node.pprev = NULL;
@@ -578,14 +634,13 @@ static bool create_io_worker(struct io_wq *wq, struct io_wqe *wqe, int index)
spin_lock_init(&worker->lock);
init_completion(&worker->ref_done);
- atomic_inc(&wq->worker_refs);
-
tsk = create_io_thread(io_wqe_worker, worker, wqe->node);
if (IS_ERR(tsk)) {
- if (atomic_dec_and_test(&wq->worker_refs))
- complete(&wq->worker_done);
kfree(worker);
- return false;
+fail:
+ atomic_dec(&acct->nr_running);
+ io_worker_ref_put(wq);
+ return;
}
tsk->pf_io_worker = worker;
@@ -604,20 +659,6 @@ static bool create_io_worker(struct io_wq *wq, struct io_wqe *wqe, int index)
acct->nr_workers++;
raw_spin_unlock_irq(&wqe->lock);
wake_up_new_task(tsk);
- return true;
-}
-
-static inline bool io_wqe_need_worker(struct io_wqe *wqe, int index)
- __must_hold(wqe->lock)
-{
- struct io_wqe_acct *acct = &wqe->acct[index];
-
- if (acct->nr_workers && test_bit(IO_WQ_BIT_EXIT, &wqe->wq->state))
- return false;
- /* if we have available workers or no work, no need */
- if (!hlist_nulls_empty(&wqe->free_list) || !io_wqe_run_queue(wqe))
- return false;
- return acct->nr_workers < acct->max_workers;
}
/*
@@ -652,88 +693,11 @@ static bool io_wq_worker_wake(struct io_worker *worker, void *data)
return false;
}
-static void io_wq_check_workers(struct io_wq *wq)
-{
- int node;
-
- for_each_node(node) {
- struct io_wqe *wqe = wq->wqes[node];
- bool fork_worker[2] = { false, false };
-
- if (!node_online(node))
- continue;
-
- raw_spin_lock_irq(&wqe->lock);
- if (io_wqe_need_worker(wqe, IO_WQ_ACCT_BOUND))
- fork_worker[IO_WQ_ACCT_BOUND] = true;
- if (io_wqe_need_worker(wqe, IO_WQ_ACCT_UNBOUND))
- fork_worker[IO_WQ_ACCT_UNBOUND] = true;
- raw_spin_unlock_irq(&wqe->lock);
- if (fork_worker[IO_WQ_ACCT_BOUND])
- create_io_worker(wq, wqe, IO_WQ_ACCT_BOUND);
- if (fork_worker[IO_WQ_ACCT_UNBOUND])
- create_io_worker(wq, wqe, IO_WQ_ACCT_UNBOUND);
- }
-}
-
static bool io_wq_work_match_all(struct io_wq_work *work, void *data)
{
return true;
}
-static void io_wq_cancel_pending(struct io_wq *wq)
-{
- struct io_cb_cancel_data match = {
- .fn = io_wq_work_match_all,
- .cancel_all = true,
- };
- int node;
-
- for_each_node(node)
- io_wqe_cancel_pending_work(wq->wqes[node], &match);
-}
-
-/*
- * Manager thread. Tasked with creating new workers, if we need them.
- */
-static int io_wq_manager(void *data)
-{
- struct io_wq *wq = data;
- char buf[TASK_COMM_LEN];
- int node;
-
- sprintf(buf, "iou-mgr-%d", wq->task_pid);
- set_task_comm(current, buf);
-
- do {
- set_current_state(TASK_INTERRUPTIBLE);
- io_wq_check_workers(wq);
- schedule_timeout(HZ);
- if (fatal_signal_pending(current))
- set_bit(IO_WQ_BIT_EXIT, &wq->state);
- } while (!test_bit(IO_WQ_BIT_EXIT, &wq->state));
-
- io_wq_check_workers(wq);
-
- rcu_read_lock();
- for_each_node(node)
- io_wq_for_each_worker(wq->wqes[node], io_wq_worker_wake, NULL);
- rcu_read_unlock();
-
- if (atomic_dec_and_test(&wq->worker_refs))
- complete(&wq->worker_done);
- wait_for_completion(&wq->worker_done);
-
- spin_lock_irq(&wq->hash->wait.lock);
- for_each_node(node)
- list_del_init(&wq->wqes[node]->wait.entry);
- spin_unlock_irq(&wq->hash->wait.lock);
-
- io_wq_cancel_pending(wq);
- complete(&wq->exited);
- do_exit(0);
-}
-
static void io_run_cancel(struct io_wq_work *work, struct io_wqe *wqe)
{
struct io_wq *wq = wqe->wq;
@@ -765,39 +729,13 @@ append:
wq_list_add_after(&work->list, &tail->list, &wqe->work_list);
}
-static int io_wq_fork_manager(struct io_wq *wq)
-{
- struct task_struct *tsk;
-
- if (wq->manager)
- return 0;
-
- WARN_ON_ONCE(test_bit(IO_WQ_BIT_EXIT, &wq->state));
-
- init_completion(&wq->worker_done);
- atomic_set(&wq->worker_refs, 1);
- tsk = create_io_thread(io_wq_manager, wq, NUMA_NO_NODE);
- if (!IS_ERR(tsk)) {
- wq->manager = get_task_struct(tsk);
- wake_up_new_task(tsk);
- return 0;
- }
-
- if (atomic_dec_and_test(&wq->worker_refs))
- complete(&wq->worker_done);
-
- return PTR_ERR(tsk);
-}
-
static void io_wqe_enqueue(struct io_wqe *wqe, struct io_wq_work *work)
{
struct io_wqe_acct *acct = io_work_get_acct(wqe, work);
int work_flags;
unsigned long flags;
- /* Can only happen if manager creation fails after exec */
- if (io_wq_fork_manager(wqe->wq) ||
- test_bit(IO_WQ_BIT_EXIT, &wqe->wq->state)) {
+ if (test_bit(IO_WQ_BIT_EXIT, &wqe->wq->state)) {
io_run_cancel(work, wqe);
return;
}
@@ -952,17 +890,12 @@ static int io_wqe_hash_wake(struct wait_queue_entry *wait, unsigned mode,
int sync, void *key)
{
struct io_wqe *wqe = container_of(wait, struct io_wqe, wait);
- int ret;
list_del_init(&wait->entry);
rcu_read_lock();
- ret = io_wqe_activate_free_worker(wqe);
+ io_wqe_activate_free_worker(wqe);
rcu_read_unlock();
-
- if (!ret)
- wake_up_process(wqe->wq->manager);
-
return 1;
}
@@ -1003,6 +936,8 @@ struct io_wq *io_wq_create(unsigned bounded, struct io_wq_data *data)
goto err;
wq->wqes[node] = wqe;
wqe->node = alloc_node;
+ wqe->acct[IO_WQ_ACCT_BOUND].index = IO_WQ_ACCT_BOUND;
+ wqe->acct[IO_WQ_ACCT_UNBOUND].index = IO_WQ_ACCT_UNBOUND;
wqe->acct[IO_WQ_ACCT_BOUND].max_workers = bounded;
atomic_set(&wqe->acct[IO_WQ_ACCT_BOUND].nr_running, 0);
wqe->acct[IO_WQ_ACCT_UNBOUND].max_workers =
@@ -1017,13 +952,11 @@ struct io_wq *io_wq_create(unsigned bounded, struct io_wq_data *data)
INIT_LIST_HEAD(&wqe->all_list);
}
- wq->task_pid = current->pid;
- init_completion(&wq->exited);
+ wq->task = get_task_struct(data->task);
refcount_set(&wq->refs, 1);
-
- ret = io_wq_fork_manager(wq);
- if (!ret)
- return wq;
+ atomic_set(&wq->worker_refs, 1);
+ init_completion(&wq->worker_done);
+ return wq;
err:
io_wq_put_hash(data->hash);
cpuhp_state_remove_instance_nocalls(io_wq_online, &wq->cpuhp_node);
@@ -1036,14 +969,49 @@ err_wq:
return ERR_PTR(ret);
}
-static void io_wq_destroy_manager(struct io_wq *wq)
+static bool io_task_work_match(struct callback_head *cb, void *data)
{
- if (wq->manager) {
- wake_up_process(wq->manager);
- wait_for_completion(&wq->exited);
- put_task_struct(wq->manager);
- wq->manager = NULL;
+ struct create_worker_data *cwd;
+
+ if (cb->func != create_worker_cb)
+ return false;
+ cwd = container_of(cb, struct create_worker_data, work);
+ return cwd->wqe->wq == data;
+}
+
+static void io_wq_exit_workers(struct io_wq *wq)
+{
+ struct callback_head *cb;
+ int node;
+
+ set_bit(IO_WQ_BIT_EXIT, &wq->state);
+
+ if (!wq->task)
+ return;
+
+ while ((cb = task_work_cancel_match(wq->task, io_task_work_match, wq)) != NULL) {
+ struct create_worker_data *cwd;
+
+ cwd = container_of(cb, struct create_worker_data, work);
+ atomic_dec(&cwd->wqe->acct[cwd->index].nr_running);
+ io_worker_ref_put(wq);
+ kfree(cwd);
}
+
+ rcu_read_lock();
+ for_each_node(node) {
+ struct io_wqe *wqe = wq->wqes[node];
+
+ io_wq_for_each_worker(wqe, io_wq_worker_wake, NULL);
+ spin_lock_irq(&wq->hash->wait.lock);
+ list_del_init(&wq->wqes[node]->wait.entry);
+ spin_unlock_irq(&wq->hash->wait.lock);
+ }
+ rcu_read_unlock();
+ io_worker_ref_put(wq);
+ wait_for_completion(&wq->worker_done);
+ put_task_struct(wq->task);
+ wq->task = NULL;
}
static void io_wq_destroy(struct io_wq *wq)
@@ -1052,12 +1020,15 @@ static void io_wq_destroy(struct io_wq *wq)
cpuhp_state_remove_instance_nocalls(io_wq_online, &wq->cpuhp_node);
- set_bit(IO_WQ_BIT_EXIT, &wq->state);
- io_wq_destroy_manager(wq);
+ io_wq_exit_workers(wq);
for_each_node(node) {
struct io_wqe *wqe = wq->wqes[node];
- WARN_ON_ONCE(!wq_list_empty(&wqe->work_list));
+ struct io_cb_cancel_data match = {
+ .fn = io_wq_work_match_all,
+ .cancel_all = true,
+ };
+ io_wqe_cancel_pending_work(wqe, &match);
kfree(wqe);
}
io_wq_put_hash(wq->hash);
@@ -1073,21 +1044,14 @@ void io_wq_put(struct io_wq *wq)
void io_wq_put_and_exit(struct io_wq *wq)
{
- set_bit(IO_WQ_BIT_EXIT, &wq->state);
- io_wq_destroy_manager(wq);
+ io_wq_exit_workers(wq);
io_wq_put(wq);
}
static bool io_wq_worker_affinity(struct io_worker *worker, void *data)
{
- struct task_struct *task = worker->task;
- struct rq_flags rf;
- struct rq *rq;
-
- rq = task_rq_lock(task, &rf);
- do_set_cpus_allowed(task, cpumask_of_node(worker->wqe->node));
- task->flags |= PF_NO_SETAFFINITY;
- task_rq_unlock(rq, task, &rf);
+ set_cpus_allowed_ptr(worker->task, cpumask_of_node(worker->wqe->node));
+
return false;
}
diff --git a/fs/io-wq.h b/fs/io-wq.h
index 1ac2f3248088..0e6d310999e8 100644
--- a/fs/io-wq.h
+++ b/fs/io-wq.h
@@ -2,7 +2,6 @@
#define INTERNAL_IO_WQ_H
#include <linux/refcount.h>
-#include <linux/io_uring.h>
struct io_wq;
@@ -21,6 +20,15 @@ enum io_wq_cancel {
IO_WQ_CANCEL_NOTFOUND, /* work not found */
};
+struct io_wq_work_node {
+ struct io_wq_work_node *next;
+};
+
+struct io_wq_work_list {
+ struct io_wq_work_node *first;
+ struct io_wq_work_node *last;
+};
+
static inline void wq_list_add_after(struct io_wq_work_node *node,
struct io_wq_work_node *pos,
struct io_wq_work_list *list)
@@ -108,6 +116,7 @@ static inline void io_wq_put_hash(struct io_wq_hash *hash)
struct io_wq_data {
struct io_wq_hash *hash;
+ struct task_struct *task;
io_wq_work_fn *do_work;
free_work_fn *free_work;
};
diff --git a/fs/io_uring.c b/fs/io_uring.c
index a4bce17af506..360f81395d81 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -78,7 +78,6 @@
#include <linux/task_work.h>
#include <linux/pagemap.h>
#include <linux/io_uring.h>
-#include <linux/freezer.h>
#define CREATE_TRACE_POINTS
#include <trace/events/io_uring.h>
@@ -195,43 +194,56 @@ enum io_uring_cmd_flags {
struct io_mapped_ubuf {
u64 ubuf;
- size_t len;
- struct bio_vec *bvec;
+ u64 ubuf_end;
unsigned int nr_bvecs;
unsigned long acct_pages;
+ struct bio_vec bvec[];
};
struct io_ring_ctx;
+struct io_overflow_cqe {
+ struct io_uring_cqe cqe;
+ struct list_head list;
+};
+
+struct io_fixed_file {
+ /* file * with additional FFS_* flags */
+ unsigned long file_ptr;
+};
+
struct io_rsrc_put {
struct list_head list;
+ u64 tag;
union {
void *rsrc;
struct file *file;
+ struct io_mapped_ubuf *buf;
};
};
-struct fixed_rsrc_table {
- struct file **files;
+struct io_file_table {
+ /* two level table */
+ struct io_fixed_file **files;
};
-struct fixed_rsrc_ref_node {
+struct io_rsrc_node {
struct percpu_ref refs;
struct list_head node;
struct list_head rsrc_list;
- struct fixed_rsrc_data *rsrc_data;
- void (*rsrc_put)(struct io_ring_ctx *ctx,
- struct io_rsrc_put *prsrc);
+ struct io_rsrc_data *rsrc_data;
struct llist_node llist;
bool done;
};
-struct fixed_rsrc_data {
- struct fixed_rsrc_table *table;
+typedef void (rsrc_put_fn)(struct io_ring_ctx *ctx, struct io_rsrc_put *prsrc);
+
+struct io_rsrc_data {
struct io_ring_ctx *ctx;
- struct fixed_rsrc_ref_node *node;
- struct percpu_ref refs;
+ u64 *tags;
+ rsrc_put_fn *do_put;
+ atomic_t refs;
struct completion done;
bool quiesce;
};
@@ -258,7 +270,8 @@ enum {
struct io_sq_data {
refcount_t refs;
- struct rw_semaphore rw_lock;
+ atomic_t park_pending;
+ struct mutex lock;
/* ctx's that are using this sqd */
struct list_head ctx_list;
@@ -273,6 +286,7 @@ struct io_sq_data {
unsigned long state;
struct completion exited;
+ struct callback_head *park_task_work;
};
#define IO_IOPOLL_BATCH 8
@@ -329,7 +343,6 @@ struct io_ring_ctx {
struct {
unsigned int flags;
unsigned int compat: 1;
- unsigned int cq_overflow_flushed: 1;
unsigned int drain_next: 1;
unsigned int eventfd_async: 1;
unsigned int restricted: 1;
@@ -387,12 +400,14 @@ struct io_ring_ctx {
* readers must ensure that ->refs is alive as long as the file* is
* used. Only updated through io_uring_register(2).
*/
- struct fixed_rsrc_data *file_data;
+ struct io_rsrc_data *file_data;
+ struct io_file_table file_table;
unsigned nr_user_files;
/* if used, fixed mapped user buffers */
+ struct io_rsrc_data *buf_data;
unsigned nr_user_bufs;
- struct io_mapped_ubuf *user_bufs;
+ struct io_mapped_ubuf **user_bufs;
struct user_struct *user;
@@ -402,7 +417,7 @@ struct io_ring_ctx {
struct socket *ring_sock;
#endif
- struct idr io_buffer_idr;
+ struct xarray io_buffers;
struct xarray personalities;
u32 pers_next;
@@ -413,6 +428,7 @@ struct io_ring_ctx {
unsigned cq_mask;
atomic_t cq_timeouts;
unsigned cq_last_tm_flush;
+ unsigned cq_extra;
unsigned long cq_check_overflow;
struct wait_queue_head cq_wait;
struct fasync_struct *cq_fasync;
@@ -432,28 +448,41 @@ struct io_ring_ctx {
struct hlist_head *cancel_hash;
unsigned cancel_hash_bits;
bool poll_multi_file;
-
- spinlock_t inflight_lock;
- struct list_head inflight_list;
} ____cacheline_aligned_in_smp;
struct delayed_work rsrc_put_work;
struct llist_head rsrc_put_llist;
struct list_head rsrc_ref_list;
spinlock_t rsrc_ref_lock;
+ struct io_rsrc_node *rsrc_node;
+ struct io_rsrc_node *rsrc_backup_node;
struct io_restriction restrictions;
/* exit task_work */
struct callback_head *exit_task_work;
- struct wait_queue_head hash_wait;
-
/* Keep this last, we don't need it for the fast path */
struct work_struct exit_work;
struct list_head tctx_list;
};
+struct io_uring_task {
+ /* submission side */
+ struct xarray xa;
+ struct wait_queue_head wait;
+ const struct io_ring_ctx *last;
+ struct io_wq *io_wq;
+ struct percpu_counter inflight;
+ atomic_t inflight_tracked;
+ atomic_t in_idle;
+
+ spinlock_t task_lock;
+ struct io_wq_work_list task_list;
+ unsigned long task_state;
+ struct callback_head task_work;
+};
+
/*
* First field must be the file pointer in all the
* iocb unions! See also 'struct kiocb' in <linux/fs.h>
@@ -467,9 +496,13 @@ struct io_poll_iocb {
struct wait_queue_entry wait;
};
-struct io_poll_remove {
+struct io_poll_update {
struct file *file;
- u64 addr;
+ u64 old_user_data;
+ u64 new_user_data;
+ __poll_t events;
+ bool update_events;
+ bool update_user_data;
};
struct io_close {
@@ -539,8 +572,9 @@ struct io_connect {
struct io_sr_msg {
struct file *file;
union {
- struct user_msghdr __user *umsg;
- void __user *buf;
+ struct compat_msghdr __user *umsg_compat;
+ struct user_msghdr __user *umsg;
+ void __user *buf;
};
int msg_flags;
int bgid;
@@ -597,7 +631,7 @@ struct io_splice {
struct io_provide_buf {
struct file *file;
__u64 addr;
- __s32 len;
+ __u32 len;
__u32 bgid;
__u16 nbufs;
__u16 bid;
@@ -636,7 +670,7 @@ struct io_unlink {
struct io_completion {
struct file *file;
struct list_head list;
- int cflags;
+ u32 cflags;
};
struct io_async_connect {
@@ -673,13 +707,17 @@ enum {
REQ_F_CUR_POS_BIT,
REQ_F_NOWAIT_BIT,
REQ_F_LINK_TIMEOUT_BIT,
- REQ_F_ISREG_BIT,
REQ_F_NEED_CLEANUP_BIT,
REQ_F_POLLED_BIT,
REQ_F_BUFFER_SELECTED_BIT,
- REQ_F_NO_FILE_TABLE_BIT,
REQ_F_LTIMEOUT_ACTIVE_BIT,
REQ_F_COMPLETE_INLINE_BIT,
+ REQ_F_REISSUE_BIT,
+ REQ_F_DONT_REISSUE_BIT,
+ /* keep async read/write and isreg together and in order */
+ REQ_F_ASYNC_READ_BIT,
+ REQ_F_ASYNC_WRITE_BIT,
+ REQ_F_ISREG_BIT,
/* not a real bit, just to check we're not overflowing the space */
__REQ_F_LAST_BIT,
@@ -709,20 +747,26 @@ enum {
REQ_F_NOWAIT = BIT(REQ_F_NOWAIT_BIT),
/* has or had linked timeout */
REQ_F_LINK_TIMEOUT = BIT(REQ_F_LINK_TIMEOUT_BIT),
- /* regular file */
- REQ_F_ISREG = BIT(REQ_F_ISREG_BIT),
/* needs cleanup */
REQ_F_NEED_CLEANUP = BIT(REQ_F_NEED_CLEANUP_BIT),
/* already went through poll handler */
REQ_F_POLLED = BIT(REQ_F_POLLED_BIT),
/* buffer already selected */
REQ_F_BUFFER_SELECTED = BIT(REQ_F_BUFFER_SELECTED_BIT),
- /* doesn't need file table for this request */
- REQ_F_NO_FILE_TABLE = BIT(REQ_F_NO_FILE_TABLE_BIT),
/* linked timeout is active, i.e. prepared by link's head */
REQ_F_LTIMEOUT_ACTIVE = BIT(REQ_F_LTIMEOUT_ACTIVE_BIT),
/* completion is deferred through io_comp_state */
REQ_F_COMPLETE_INLINE = BIT(REQ_F_COMPLETE_INLINE_BIT),
+ /* caller should reissue async */
+ REQ_F_REISSUE = BIT(REQ_F_REISSUE_BIT),
+ /* don't attempt request reissue, see io_rw_reissue() */
+ REQ_F_DONT_REISSUE = BIT(REQ_F_DONT_REISSUE_BIT),
+ /* supports async reads */
+ REQ_F_ASYNC_READ = BIT(REQ_F_ASYNC_READ_BIT),
+ /* supports async writes */
+ REQ_F_ASYNC_WRITE = BIT(REQ_F_ASYNC_WRITE_BIT),
+ /* regular file */
+ REQ_F_ISREG = BIT(REQ_F_ISREG_BIT),
};
struct async_poll {
@@ -746,7 +790,7 @@ struct io_kiocb {
struct file *file;
struct io_rw rw;
struct io_poll_iocb poll;
- struct io_poll_remove poll_remove;
+ struct io_poll_update poll_update;
struct io_accept accept;
struct io_sync sync;
struct io_cancel cancel;
@@ -781,17 +825,14 @@ struct io_kiocb {
struct io_ring_ctx *ctx;
unsigned int flags;
- refcount_t refs;
+ atomic_t refs;
struct task_struct *task;
u64 user_data;
struct io_kiocb *link;
struct percpu_ref *fixed_rsrc_refs;
- /*
- * 1. used with ctx->iopoll_list with reads/writes
- * 2. to track reqs with ->files (see io_op_def::file_table)
- */
+ /* used with ctx->iopoll_list with reads/writes */
struct list_head inflight_entry;
union {
struct io_task_work io_task_work;
@@ -801,6 +842,8 @@ struct io_kiocb {
struct hlist_node hash_node;
struct async_poll *apoll;
struct io_wq_work work;
+ /* store used ubuf, so we can prevent reloading */
+ struct io_mapped_ubuf *imu;
};
struct io_tctx_node {
@@ -829,8 +872,8 @@ struct io_op_def {
unsigned pollout : 1;
/* op supports buffer selection */
unsigned buffer_select : 1;
- /* must always have async data allocated */
- unsigned needs_async_data : 1;
+ /* do prep async if is going to be punted */
+ unsigned needs_async_setup : 1;
/* should block plug */
unsigned plug : 1;
/* size of async data needed, if any */
@@ -844,7 +887,7 @@ static const struct io_op_def io_op_defs[] = {
.unbound_nonreg_file = 1,
.pollin = 1,
.buffer_select = 1,
- .needs_async_data = 1,
+ .needs_async_setup = 1,
.plug = 1,
.async_size = sizeof(struct io_async_rw),
},
@@ -853,7 +896,7 @@ static const struct io_op_def io_op_defs[] = {
.hash_reg_file = 1,
.unbound_nonreg_file = 1,
.pollout = 1,
- .needs_async_data = 1,
+ .needs_async_setup = 1,
.plug = 1,
.async_size = sizeof(struct io_async_rw),
},
@@ -887,7 +930,7 @@ static const struct io_op_def io_op_defs[] = {
.needs_file = 1,
.unbound_nonreg_file = 1,
.pollout = 1,
- .needs_async_data = 1,
+ .needs_async_setup = 1,
.async_size = sizeof(struct io_async_msghdr),
},
[IORING_OP_RECVMSG] = {
@@ -895,11 +938,10 @@ static const struct io_op_def io_op_defs[] = {
.unbound_nonreg_file = 1,
.pollin = 1,
.buffer_select = 1,
- .needs_async_data = 1,
+ .needs_async_setup = 1,
.async_size = sizeof(struct io_async_msghdr),
},
[IORING_OP_TIMEOUT] = {
- .needs_async_data = 1,
.async_size = sizeof(struct io_timeout_data),
},
[IORING_OP_TIMEOUT_REMOVE] = {
@@ -912,14 +954,13 @@ static const struct io_op_def io_op_defs[] = {
},
[IORING_OP_ASYNC_CANCEL] = {},
[IORING_OP_LINK_TIMEOUT] = {
- .needs_async_data = 1,
.async_size = sizeof(struct io_timeout_data),
},
[IORING_OP_CONNECT] = {
.needs_file = 1,
.unbound_nonreg_file = 1,
.pollout = 1,
- .needs_async_data = 1,
+ .needs_async_setup = 1,
.async_size = sizeof(struct io_async_connect),
},
[IORING_OP_FALLOCATE] = {
@@ -988,40 +1029,31 @@ static void io_uring_del_task_file(unsigned long index);
static void io_uring_try_cancel_requests(struct io_ring_ctx *ctx,
struct task_struct *task,
struct files_struct *files);
-static void io_uring_cancel_sqpoll(struct io_ring_ctx *ctx);
-static void destroy_fixed_rsrc_ref_node(struct fixed_rsrc_ref_node *ref_node);
-static struct fixed_rsrc_ref_node *alloc_fixed_rsrc_ref_node(
- struct io_ring_ctx *ctx);
-static void io_ring_file_put(struct io_ring_ctx *ctx, struct io_rsrc_put *prsrc);
-
-static bool io_rw_reissue(struct io_kiocb *req);
-static void io_cqring_fill_event(struct io_kiocb *req, long res);
+static void io_uring_cancel_sqpoll(struct io_sq_data *sqd);
+static struct io_rsrc_node *io_rsrc_node_alloc(struct io_ring_ctx *ctx);
+
+static bool io_cqring_fill_event(struct io_ring_ctx *ctx, u64 user_data,
+ long res, unsigned int cflags);
static void io_put_req(struct io_kiocb *req);
static void io_put_req_deferred(struct io_kiocb *req, int nr);
-static void io_double_put_req(struct io_kiocb *req);
static void io_dismantle_req(struct io_kiocb *req);
static void io_put_task(struct task_struct *task, int nr);
-static void io_queue_next(struct io_kiocb *req);
static struct io_kiocb *io_prep_linked_timeout(struct io_kiocb *req);
-static void __io_queue_linked_timeout(struct io_kiocb *req);
static void io_queue_linked_timeout(struct io_kiocb *req);
-static int __io_sqe_files_update(struct io_ring_ctx *ctx,
- struct io_uring_rsrc_update *ip,
- unsigned nr_args);
-static void __io_clean_op(struct io_kiocb *req);
+static int __io_register_rsrc_update(struct io_ring_ctx *ctx, unsigned type,
+ struct io_uring_rsrc_update2 *up,
+ unsigned nr_args);
+static void io_clean_op(struct io_kiocb *req);
static struct file *io_file_get(struct io_submit_state *state,
struct io_kiocb *req, int fd, bool fixed);
static void __io_queue_sqe(struct io_kiocb *req);
static void io_rsrc_put_work(struct work_struct *work);
-static int io_import_iovec(int rw, struct io_kiocb *req, struct iovec **iovec,
- struct iov_iter *iter, bool needs_lock);
-static int io_setup_async_rw(struct io_kiocb *req, const struct iovec *iovec,
- const struct iovec *fast_iov,
- struct iov_iter *iter, bool force);
static void io_req_task_queue(struct io_kiocb *req);
static void io_submit_flush_completions(struct io_comp_state *cs,
struct io_ring_ctx *ctx);
+static bool io_poll_remove_waitqs(struct io_kiocb *req);
+static int io_req_prep_async(struct io_kiocb *req);
static struct kmem_cache *req_cachep;
@@ -1043,49 +1075,49 @@ EXPORT_SYMBOL(io_uring_get_socket);
#define io_for_each_link(pos, head) \
for (pos = (head); pos; pos = pos->link)
-static inline void io_clean_op(struct io_kiocb *req)
-{
- if (req->flags & (REQ_F_NEED_CLEANUP | REQ_F_BUFFER_SELECTED))
- __io_clean_op(req);
-}
-
-static inline void io_set_resource_node(struct io_kiocb *req)
+static inline void io_req_set_rsrc_node(struct io_kiocb *req)
{
struct io_ring_ctx *ctx = req->ctx;
if (!req->fixed_rsrc_refs) {
- req->fixed_rsrc_refs = &ctx->file_data->node->refs;
+ req->fixed_rsrc_refs = &ctx->rsrc_node->refs;
percpu_ref_get(req->fixed_rsrc_refs);
}
}
+static void io_refs_resurrect(struct percpu_ref *ref, struct completion *compl)
+{
+ bool got = percpu_ref_tryget(ref);
+
+ /* already at zero, wait for ->release() */
+ if (!got)
+ wait_for_completion(compl);
+ percpu_ref_resurrect(ref);
+ if (got)
+ percpu_ref_put(ref);
+}
+
static bool io_match_task(struct io_kiocb *head,
struct task_struct *task,
struct files_struct *files)
{
struct io_kiocb *req;
- if (task && head->task != task) {
- /* in terms of cancelation, always match if req task is dead */
- if (head->task->flags & PF_EXITING)
- return true;
+ if (task && head->task != task)
return false;
- }
if (!files)
return true;
io_for_each_link(req, head) {
if (req->flags & REQ_F_INFLIGHT)
return true;
- if (req->task->files == files)
- return true;
}
return false;
}
static inline void req_set_fail_links(struct io_kiocb *req)
{
- if ((req->flags & (REQ_F_LINK | REQ_F_HARDLINK)) == REQ_F_LINK)
+ if (req->flags & REQ_F_LINK)
req->flags |= REQ_F_FAIL_LINK;
}
@@ -1135,7 +1167,7 @@ static struct io_ring_ctx *io_ring_ctx_alloc(struct io_uring_params *p)
init_waitqueue_head(&ctx->cq_wait);
INIT_LIST_HEAD(&ctx->cq_overflow_list);
init_completion(&ctx->ref_comp);
- idr_init(&ctx->io_buffer_idr);
+ xa_init_flags(&ctx->io_buffers, XA_FLAGS_ALLOC1);
xa_init_flags(&ctx->personalities, XA_FLAGS_ALLOC1);
mutex_init(&ctx->uring_lock);
init_waitqueue_head(&ctx->wait);
@@ -1143,8 +1175,6 @@ static struct io_ring_ctx *io_ring_ctx_alloc(struct io_uring_params *p)
INIT_LIST_HEAD(&ctx->iopoll_list);
INIT_LIST_HEAD(&ctx->defer_list);
INIT_LIST_HEAD(&ctx->timeout_list);
- spin_lock_init(&ctx->inflight_lock);
- INIT_LIST_HEAD(&ctx->inflight_list);
spin_lock_init(&ctx->rsrc_ref_lock);
INIT_LIST_HEAD(&ctx->rsrc_ref_list);
INIT_DELAYED_WORK(&ctx->rsrc_put_work, io_rsrc_put_work);
@@ -1164,7 +1194,7 @@ static bool req_need_defer(struct io_kiocb *req, u32 seq)
if (unlikely(req->flags & REQ_F_IO_DRAIN)) {
struct io_ring_ctx *ctx = req->ctx;
- return seq != ctx->cached_cq_tail
+ return seq + ctx->cq_extra != ctx->cached_cq_tail
+ READ_ONCE(ctx->cached_cq_overflow);
}
@@ -1173,14 +1203,9 @@ static bool req_need_defer(struct io_kiocb *req, u32 seq)
static void io_req_track_inflight(struct io_kiocb *req)
{
- struct io_ring_ctx *ctx = req->ctx;
-
if (!(req->flags & REQ_F_INFLIGHT)) {
req->flags |= REQ_F_INFLIGHT;
-
- spin_lock_irq(&ctx->inflight_lock);
- list_add(&req->inflight_entry, &ctx->inflight_list);
- spin_unlock_irq(&ctx->inflight_lock);
+ atomic_inc(&current->io_uring->inflight_tracked);
}
}
@@ -1192,16 +1217,26 @@ static void io_prep_async_work(struct io_kiocb *req)
if (!req->work.creds)
req->work.creds = get_current_cred();
+ req->work.list.next = NULL;
+ req->work.flags = 0;
if (req->flags & REQ_F_FORCE_ASYNC)
req->work.flags |= IO_WQ_WORK_CONCURRENT;
if (req->flags & REQ_F_ISREG) {
if (def->hash_reg_file || (ctx->flags & IORING_SETUP_IOPOLL))
io_wq_hash_work(&req->work, file_inode(req->file));
- } else {
+ } else if (!req->file || !S_ISBLK(file_inode(req->file)->i_mode)) {
if (def->unbound_nonreg_file)
req->work.flags |= IO_WQ_WORK_UNBOUND;
}
+
+ switch (req->opcode) {
+ case IORING_OP_SPLICE:
+ case IORING_OP_TEE:
+ if (!S_ISREG(file_inode(req->splice.file_in)->i_mode))
+ req->work.flags |= IO_WQ_WORK_UNBOUND;
+ break;
+ }
}
static void io_prep_async_link(struct io_kiocb *req)
@@ -1221,50 +1256,29 @@ static void io_queue_async_work(struct io_kiocb *req)
BUG_ON(!tctx);
BUG_ON(!tctx->io_wq);
- trace_io_uring_queue_async_work(ctx, io_wq_is_hashed(&req->work), req,
- &req->work, req->flags);
/* init ->work of the whole link before punting */
io_prep_async_link(req);
+ trace_io_uring_queue_async_work(ctx, io_wq_is_hashed(&req->work), req,
+ &req->work, req->flags);
io_wq_enqueue(tctx->io_wq, &req->work);
if (link)
io_queue_linked_timeout(link);
}
-static void io_kill_timeout(struct io_kiocb *req)
+static void io_kill_timeout(struct io_kiocb *req, int status)
+ __must_hold(&req->ctx->completion_lock)
{
struct io_timeout_data *io = req->async_data;
- int ret;
- ret = hrtimer_try_to_cancel(&io->timer);
- if (ret != -1) {
+ if (hrtimer_try_to_cancel(&io->timer) != -1) {
atomic_set(&req->ctx->cq_timeouts,
atomic_read(&req->ctx->cq_timeouts) + 1);
list_del_init(&req->timeout.list);
- io_cqring_fill_event(req, 0);
+ io_cqring_fill_event(req->ctx, req->user_data, status, 0);
io_put_req_deferred(req, 1);
}
}
-/*
- * Returns true if we found and killed one or more timeouts
- */
-static bool io_kill_timeouts(struct io_ring_ctx *ctx, struct task_struct *tsk,
- struct files_struct *files)
-{
- struct io_kiocb *req, *tmp;
- int canceled = 0;
-
- spin_lock_irq(&ctx->completion_lock);
- list_for_each_entry_safe(req, tmp, &ctx->timeout_list, timeout.list) {
- if (io_match_task(req, tsk, files)) {
- io_kill_timeout(req);
- canceled++;
- }
- }
- spin_unlock_irq(&ctx->completion_lock);
- return canceled != 0;
-}
-
static void __io_queue_deferred(struct io_ring_ctx *ctx)
{
do {
@@ -1309,7 +1323,7 @@ static void io_flush_timeouts(struct io_ring_ctx *ctx)
break;
list_del_init(&req->timeout.list);
- io_kill_timeout(req);
+ io_kill_timeout(req, 0);
} while (!list_empty(&ctx->timeout_list));
ctx->cq_last_tm_flush = seq;
@@ -1338,7 +1352,7 @@ static inline unsigned int __io_cqring_events(struct io_ring_ctx *ctx)
return ctx->cached_cq_tail - READ_ONCE(ctx->rings->cq.head);
}
-static struct io_uring_cqe *io_get_cqring(struct io_ring_ctx *ctx)
+static inline struct io_uring_cqe *io_get_cqring(struct io_ring_ctx *ctx)
{
struct io_rings *rings = ctx->rings;
unsigned tail;
@@ -1357,13 +1371,11 @@ static struct io_uring_cqe *io_get_cqring(struct io_ring_ctx *ctx)
static inline bool io_should_trigger_evfd(struct io_ring_ctx *ctx)
{
- if (!ctx->cq_ev_fd)
+ if (likely(!ctx->cq_ev_fd))
return false;
if (READ_ONCE(ctx->rings->cq_flags) & IORING_CQ_EVENTFD_DISABLED)
return false;
- if (!ctx->eventfd_async)
- return true;
- return io_wq_current_is_worker();
+ return !ctx->eventfd_async || io_wq_current_is_worker();
}
static void io_cqring_ev_posted(struct io_ring_ctx *ctx)
@@ -1401,41 +1413,33 @@ static void io_cqring_ev_posted_iopoll(struct io_ring_ctx *ctx)
}
/* Returns true if there are no backlogged entries after the flush */
-static bool __io_cqring_overflow_flush(struct io_ring_ctx *ctx, bool force,
- struct task_struct *tsk,
- struct files_struct *files)
+static bool __io_cqring_overflow_flush(struct io_ring_ctx *ctx, bool force)
{
struct io_rings *rings = ctx->rings;
- struct io_kiocb *req, *tmp;
- struct io_uring_cqe *cqe;
unsigned long flags;
bool all_flushed, posted;
- LIST_HEAD(list);
if (!force && __io_cqring_events(ctx) == rings->cq_ring_entries)
return false;
posted = false;
spin_lock_irqsave(&ctx->completion_lock, flags);
- list_for_each_entry_safe(req, tmp, &ctx->cq_overflow_list, compl.list) {
- if (!io_match_task(req, tsk, files))
- continue;
+ while (!list_empty(&ctx->cq_overflow_list)) {
+ struct io_uring_cqe *cqe = io_get_cqring(ctx);
+ struct io_overflow_cqe *ocqe;
- cqe = io_get_cqring(ctx);
if (!cqe && !force)
break;
-
- list_move(&req->compl.list, &list);
- if (cqe) {
- WRITE_ONCE(cqe->user_data, req->user_data);
- WRITE_ONCE(cqe->res, req->result);
- WRITE_ONCE(cqe->flags, req->compl.cflags);
- } else {
- ctx->cached_cq_overflow++;
+ ocqe = list_first_entry(&ctx->cq_overflow_list,
+ struct io_overflow_cqe, list);
+ if (cqe)
+ memcpy(cqe, &ocqe->cqe, sizeof(*cqe));
+ else
WRITE_ONCE(ctx->rings->cq_overflow,
- ctx->cached_cq_overflow);
- }
+ ++ctx->cached_cq_overflow);
posted = true;
+ list_del(&ocqe->list);
+ kfree(ocqe);
}
all_flushed = list_empty(&ctx->cq_overflow_list);
@@ -1450,19 +1454,10 @@ static bool __io_cqring_overflow_flush(struct io_ring_ctx *ctx, bool force,
spin_unlock_irqrestore(&ctx->completion_lock, flags);
if (posted)
io_cqring_ev_posted(ctx);
-
- while (!list_empty(&list)) {
- req = list_first_entry(&list, struct io_kiocb, compl.list);
- list_del(&req->compl.list);
- io_put_req(req);
- }
-
return all_flushed;
}
-static bool io_cqring_overflow_flush(struct io_ring_ctx *ctx, bool force,
- struct task_struct *tsk,
- struct files_struct *files)
+static bool io_cqring_overflow_flush(struct io_ring_ctx *ctx, bool force)
{
bool ret = true;
@@ -1470,7 +1465,7 @@ static bool io_cqring_overflow_flush(struct io_ring_ctx *ctx, bool force,
/* iopoll syncs against uring_lock, not completion_lock */
if (ctx->flags & IORING_SETUP_IOPOLL)
mutex_lock(&ctx->uring_lock);
- ret = __io_cqring_overflow_flush(ctx, force, tsk, files);
+ ret = __io_cqring_overflow_flush(ctx, force);
if (ctx->flags & IORING_SETUP_IOPOLL)
mutex_unlock(&ctx->uring_lock);
}
@@ -1478,12 +1473,74 @@ static bool io_cqring_overflow_flush(struct io_ring_ctx *ctx, bool force,
return ret;
}
-static void __io_cqring_fill_event(struct io_kiocb *req, long res, long cflags)
+/*
+ * Shamelessly stolen from the mm implementation of page reference checking,
+ * see commit f958d7b528b1 for details.
+ */
+#define req_ref_zero_or_close_to_overflow(req) \
+ ((unsigned int) atomic_read(&(req->refs)) + 127u <= 127u)
+
+static inline bool req_ref_inc_not_zero(struct io_kiocb *req)
+{
+ return atomic_inc_not_zero(&req->refs);
+}
+
+static inline bool req_ref_sub_and_test(struct io_kiocb *req, int refs)
+{
+ WARN_ON_ONCE(req_ref_zero_or_close_to_overflow(req));
+ return atomic_sub_and_test(refs, &req->refs);
+}
+
+static inline bool req_ref_put_and_test(struct io_kiocb *req)
+{
+ WARN_ON_ONCE(req_ref_zero_or_close_to_overflow(req));
+ return atomic_dec_and_test(&req->refs);
+}
+
+static inline void req_ref_put(struct io_kiocb *req)
+{
+ WARN_ON_ONCE(req_ref_put_and_test(req));
+}
+
+static inline void req_ref_get(struct io_kiocb *req)
+{
+ WARN_ON_ONCE(req_ref_zero_or_close_to_overflow(req));
+ atomic_inc(&req->refs);
+}
+
+static bool io_cqring_event_overflow(struct io_ring_ctx *ctx, u64 user_data,
+ long res, unsigned int cflags)
+{
+ struct io_overflow_cqe *ocqe;
+
+ ocqe = kmalloc(sizeof(*ocqe), GFP_ATOMIC | __GFP_ACCOUNT);
+ if (!ocqe) {
+ /*
+ * If we're in ring overflow flush mode, or in task cancel mode,
+ * or cannot allocate an overflow entry, then we need to drop it
+ * on the floor.
+ */
+ WRITE_ONCE(ctx->rings->cq_overflow, ++ctx->cached_cq_overflow);
+ return false;
+ }
+ if (list_empty(&ctx->cq_overflow_list)) {
+ set_bit(0, &ctx->sq_check_overflow);
+ set_bit(0, &ctx->cq_check_overflow);
+ ctx->rings->sq_flags |= IORING_SQ_CQ_OVERFLOW;
+ }
+ ocqe->cqe.user_data = user_data;
+ ocqe->cqe.res = res;
+ ocqe->cqe.flags = cflags;
+ list_add_tail(&ocqe->list, &ctx->cq_overflow_list);
+ return true;
+}
+
+static inline bool __io_cqring_fill_event(struct io_ring_ctx *ctx, u64 user_data,
+ long res, unsigned int cflags)
{
- struct io_ring_ctx *ctx = req->ctx;
struct io_uring_cqe *cqe;
- trace_io_uring_complete(ctx, req->user_data, res);
+ trace_io_uring_complete(ctx, user_data, res, cflags);
/*
* If we can't get a cq entry, userspace overflowed the
@@ -1492,35 +1549,19 @@ static void __io_cqring_fill_event(struct io_kiocb *req, long res, long cflags)
*/
cqe = io_get_cqring(ctx);
if (likely(cqe)) {
- WRITE_ONCE(cqe->user_data, req->user_data);
+ WRITE_ONCE(cqe->user_data, user_data);
WRITE_ONCE(cqe->res, res);
WRITE_ONCE(cqe->flags, cflags);
- } else if (ctx->cq_overflow_flushed ||
- atomic_read(&req->task->io_uring->in_idle)) {
- /*
- * If we're in ring overflow flush mode, or in task cancel mode,
- * then we cannot store the request for later flushing, we need
- * to drop it on the floor.
- */
- ctx->cached_cq_overflow++;
- WRITE_ONCE(ctx->rings->cq_overflow, ctx->cached_cq_overflow);
- } else {
- if (list_empty(&ctx->cq_overflow_list)) {
- set_bit(0, &ctx->sq_check_overflow);
- set_bit(0, &ctx->cq_check_overflow);
- ctx->rings->sq_flags |= IORING_SQ_CQ_OVERFLOW;
- }
- io_clean_op(req);
- req->result = res;
- req->compl.cflags = cflags;
- refcount_inc(&req->refs);
- list_add_tail(&req->compl.list, &ctx->cq_overflow_list);
+ return true;
}
+ return io_cqring_event_overflow(ctx, user_data, res, cflags);
}
-static void io_cqring_fill_event(struct io_kiocb *req, long res)
+/* not as hot to bloat with inlining */
+static noinline bool io_cqring_fill_event(struct io_ring_ctx *ctx, u64 user_data,
+ long res, unsigned int cflags)
{
- __io_cqring_fill_event(req, res, 0);
+ return __io_cqring_fill_event(ctx, user_data, res, cflags);
}
static void io_req_complete_post(struct io_kiocb *req, long res,
@@ -1530,12 +1571,12 @@ static void io_req_complete_post(struct io_kiocb *req, long res,
unsigned long flags;
spin_lock_irqsave(&ctx->completion_lock, flags);
- __io_cqring_fill_event(req, res, cflags);
+ __io_cqring_fill_event(ctx, req->user_data, res, cflags);
/*
* If we're the last reference to this request, add to our locked
* free_list cache.
*/
- if (refcount_dec_and_test(&req->refs)) {
+ if (req_ref_put_and_test(req)) {
struct io_comp_state *cs = &ctx->submit_state.comp;
if (req->flags & (REQ_F_LINK | REQ_F_HARDLINK)) {
@@ -1550,20 +1591,30 @@ static void io_req_complete_post(struct io_kiocb *req, long res,
io_put_task(req->task, 1);
list_add(&req->compl.list, &cs->locked_free_list);
cs->locked_free_nr++;
- } else
- req = NULL;
+ } else {
+ if (!percpu_ref_tryget(&ctx->refs))
+ req = NULL;
+ }
io_commit_cqring(ctx);
spin_unlock_irqrestore(&ctx->completion_lock, flags);
- io_cqring_ev_posted(ctx);
- if (req)
+ if (req) {
+ io_cqring_ev_posted(ctx);
percpu_ref_put(&ctx->refs);
+ }
+}
+
+static inline bool io_req_needs_clean(struct io_kiocb *req)
+{
+ return req->flags & (REQ_F_BUFFER_SELECTED | REQ_F_NEED_CLEANUP |
+ REQ_F_POLLED | REQ_F_INFLIGHT);
}
static void io_req_complete_state(struct io_kiocb *req, long res,
unsigned int cflags)
{
- io_clean_op(req);
+ if (io_req_needs_clean(req))
+ io_clean_op(req);
req->result = res;
req->compl.cflags = cflags;
req->flags |= REQ_F_COMPLETE_INLINE;
@@ -1583,34 +1634,50 @@ static inline void io_req_complete(struct io_kiocb *req, long res)
__io_req_complete(req, 0, res, 0);
}
+static void io_req_complete_failed(struct io_kiocb *req, long res)
+{
+ req_set_fail_links(req);
+ io_put_req(req);
+ io_req_complete_post(req, res, 0);
+}
+
+static void io_flush_cached_locked_reqs(struct io_ring_ctx *ctx,
+ struct io_comp_state *cs)
+{
+ spin_lock_irq(&ctx->completion_lock);
+ list_splice_init(&cs->locked_free_list, &cs->free_list);
+ cs->locked_free_nr = 0;
+ spin_unlock_irq(&ctx->completion_lock);
+}
+
+/* Returns true IFF there are requests in the cache */
static bool io_flush_cached_reqs(struct io_ring_ctx *ctx)
{
struct io_submit_state *state = &ctx->submit_state;
struct io_comp_state *cs = &state->comp;
- struct io_kiocb *req = NULL;
+ int nr;
/*
* If we have more than a batch's worth of requests in our IRQ side
* locked cache, grab the lock and move them over to our submission
* side cache.
*/
- if (READ_ONCE(cs->locked_free_nr) > IO_COMPL_BATCH) {
- spin_lock_irq(&ctx->completion_lock);
- list_splice_init(&cs->locked_free_list, &cs->free_list);
- cs->locked_free_nr = 0;
- spin_unlock_irq(&ctx->completion_lock);
- }
+ if (READ_ONCE(cs->locked_free_nr) > IO_COMPL_BATCH)
+ io_flush_cached_locked_reqs(ctx, cs);
+ nr = state->free_reqs;
while (!list_empty(&cs->free_list)) {
- req = list_first_entry(&cs->free_list, struct io_kiocb,
- compl.list);
+ struct io_kiocb *req = list_first_entry(&cs->free_list,
+ struct io_kiocb, compl.list);
+
list_del(&req->compl.list);
- state->reqs[state->free_reqs++] = req;
- if (state->free_reqs == ARRAY_SIZE(state->reqs))
+ state->reqs[nr++] = req;
+ if (nr == ARRAY_SIZE(state->reqs))
break;
}
- return req != NULL;
+ state->free_reqs = nr;
+ return nr != 0;
}
static struct io_kiocb *io_alloc_req(struct io_ring_ctx *ctx)
@@ -1646,37 +1713,28 @@ got_req:
return state->reqs[state->free_reqs];
}
-static inline void io_put_file(struct io_kiocb *req, struct file *file,
- bool fixed)
+static inline void io_put_file(struct file *file)
{
- if (!fixed)
+ if (file)
fput(file);
}
static void io_dismantle_req(struct io_kiocb *req)
{
- io_clean_op(req);
+ unsigned int flags = req->flags;
- if (req->async_data)
- kfree(req->async_data);
- if (req->file)
- io_put_file(req, req->file, (req->flags & REQ_F_FIXED_FILE));
+ if (io_req_needs_clean(req))
+ io_clean_op(req);
+ if (!(flags & REQ_F_FIXED_FILE))
+ io_put_file(req->file);
if (req->fixed_rsrc_refs)
percpu_ref_put(req->fixed_rsrc_refs);
+ if (req->async_data)
+ kfree(req->async_data);
if (req->work.creds) {
put_cred(req->work.creds);
req->work.creds = NULL;
}
-
- if (req->flags & REQ_F_INFLIGHT) {
- struct io_ring_ctx *ctx = req->ctx;
- unsigned long flags;
-
- spin_lock_irqsave(&ctx->inflight_lock, flags);
- list_del(&req->inflight_entry);
- spin_unlock_irqrestore(&ctx->inflight_lock, flags);
- req->flags &= ~REQ_F_INFLIGHT;
- }
}
/* must to be called somewhat shortly after putting a request */
@@ -1713,7 +1771,6 @@ static bool io_kill_linked_timeout(struct io_kiocb *req)
__must_hold(&req->ctx->completion_lock)
{
struct io_kiocb *link = req->link;
- bool cancelled = false;
/*
* Can happen if a linked timeout fired and link had been like
@@ -1721,19 +1778,17 @@ static bool io_kill_linked_timeout(struct io_kiocb *req)
*/
if (link && (link->flags & REQ_F_LTIMEOUT_ACTIVE)) {
struct io_timeout_data *io = link->async_data;
- int ret;
io_remove_next_linked(req);
link->timeout.head = NULL;
- ret = hrtimer_try_to_cancel(&io->timer);
- if (ret != -1) {
- io_cqring_fill_event(link, -ECANCELED);
+ if (hrtimer_try_to_cancel(&io->timer) != -1) {
+ io_cqring_fill_event(link->ctx, link->user_data,
+ -ECANCELED, 0);
io_put_req_deferred(link, 1);
- cancelled = true;
+ return true;
}
}
- req->flags &= ~REQ_F_LINK_TIMEOUT;
- return cancelled;
+ return false;
}
static void io_fail_links(struct io_kiocb *req)
@@ -1747,7 +1802,7 @@ static void io_fail_links(struct io_kiocb *req)
link->link = NULL;
trace_io_uring_fail_link(req, link);
- io_cqring_fill_event(link, -ECANCELED);
+ io_cqring_fill_event(link->ctx, link->user_data, -ECANCELED, 0);
io_put_req_deferred(link, 2);
link = nxt;
}
@@ -1760,7 +1815,8 @@ static bool io_disarm_next(struct io_kiocb *req)
if (likely(req->flags & REQ_F_LINK_TIMEOUT))
posted = io_kill_linked_timeout(req);
- if (unlikely(req->flags & REQ_F_FAIL_LINK)) {
+ if (unlikely((req->flags & REQ_F_FAIL_LINK) &&
+ !(req->flags & REQ_F_HARDLINK))) {
posted |= (req->link != NULL);
io_fail_links(req);
}
@@ -1858,13 +1914,17 @@ static void tctx_task_work(struct callback_head *cb)
cond_resched();
}
-static int io_task_work_add(struct task_struct *tsk, struct io_kiocb *req,
- enum task_work_notify_mode notify)
+static int io_req_task_work_add(struct io_kiocb *req)
{
+ struct task_struct *tsk = req->task;
struct io_uring_task *tctx = tsk->io_uring;
+ enum task_work_notify_mode notify;
struct io_wq_work_node *node, *prev;
unsigned long flags;
- int ret;
+ int ret = 0;
+
+ if (unlikely(tsk->flags & PF_EXITING))
+ return -ESRCH;
WARN_ON_ONCE(!tctx);
@@ -1877,14 +1937,23 @@ static int io_task_work_add(struct task_struct *tsk, struct io_kiocb *req,
test_and_set_bit(0, &tctx->task_state))
return 0;
- if (!task_work_add(tsk, &tctx->task_work, notify))
+ /*
+ * SQPOLL kernel thread doesn't need notification, just a wakeup. For
+ * all other cases, use TWA_SIGNAL unconditionally to ensure we're
+ * processing task_work. There's no reliable way to tell if TWA_RESUME
+ * will do the job.
+ */
+ notify = (req->ctx->flags & IORING_SETUP_SQPOLL) ? TWA_NONE : TWA_SIGNAL;
+
+ if (!task_work_add(tsk, &tctx->task_work, notify)) {
+ wake_up_process(tsk);
return 0;
+ }
/*
* Slow path - we failed, find and delete work. if the work is not
* in the list, it got run and we're fine.
*/
- ret = 0;
spin_lock_irqsave(&tctx->task_lock, flags);
wq_list_for_each(node, prev, &tctx->task_list) {
if (&req->io_task_work.node == node) {
@@ -1898,58 +1967,44 @@ static int io_task_work_add(struct task_struct *tsk, struct io_kiocb *req,
return ret;
}
-static int io_req_task_work_add(struct io_kiocb *req)
+static bool io_run_task_work_head(struct callback_head **work_head)
{
- struct task_struct *tsk = req->task;
- struct io_ring_ctx *ctx = req->ctx;
- enum task_work_notify_mode notify;
- int ret;
-
- if (tsk->flags & PF_EXITING)
- return -ESRCH;
+ struct callback_head *work, *next;
+ bool executed = false;
- /*
- * SQPOLL kernel thread doesn't need notification, just a wakeup. For
- * all other cases, use TWA_SIGNAL unconditionally to ensure we're
- * processing task_work. There's no reliable way to tell if TWA_RESUME
- * will do the job.
- */
- notify = TWA_NONE;
- if (!(ctx->flags & IORING_SETUP_SQPOLL))
- notify = TWA_SIGNAL;
+ do {
+ work = xchg(work_head, NULL);
+ if (!work)
+ break;
- ret = io_task_work_add(tsk, req, notify);
- if (!ret)
- wake_up_process(tsk);
+ do {
+ next = work->next;
+ work->func(work);
+ work = next;
+ cond_resched();
+ } while (work);
+ executed = true;
+ } while (1);
- return ret;
+ return executed;
}
-static void io_req_task_work_add_fallback(struct io_kiocb *req,
- task_work_func_t cb)
+static void io_task_work_add_head(struct callback_head **work_head,
+ struct callback_head *task_work)
{
- struct io_ring_ctx *ctx = req->ctx;
struct callback_head *head;
- init_task_work(&req->task_work, cb);
do {
- head = READ_ONCE(ctx->exit_task_work);
- req->task_work.next = head;
- } while (cmpxchg(&ctx->exit_task_work, head, &req->task_work) != head);
+ head = READ_ONCE(*work_head);
+ task_work->next = head;
+ } while (cmpxchg(work_head, head, task_work) != head);
}
-static void __io_req_task_cancel(struct io_kiocb *req, int error)
+static void io_req_task_work_add_fallback(struct io_kiocb *req,
+ task_work_func_t cb)
{
- struct io_ring_ctx *ctx = req->ctx;
-
- spin_lock_irq(&ctx->completion_lock);
- io_cqring_fill_event(req, error);
- io_commit_cqring(ctx);
- spin_unlock_irq(&ctx->completion_lock);
-
- io_cqring_ev_posted(ctx);
- req_set_fail_links(req);
- io_double_put_req(req);
+ init_task_work(&req->task_work, cb);
+ io_task_work_add_head(&req->ctx->exit_task_work, &req->task_work);
}
static void io_req_task_cancel(struct callback_head *cb)
@@ -1957,10 +2012,10 @@ static void io_req_task_cancel(struct callback_head *cb)
struct io_kiocb *req = container_of(cb, struct io_kiocb, task_work);
struct io_ring_ctx *ctx = req->ctx;
+ /* ctx is guaranteed to stay alive while we hold uring_lock */
mutex_lock(&ctx->uring_lock);
- __io_req_task_cancel(req, req->result);
+ io_req_complete_failed(req, req->result);
mutex_unlock(&ctx->uring_lock);
- percpu_ref_put(&ctx->refs);
}
static void __io_req_task_submit(struct io_kiocb *req)
@@ -1972,7 +2027,7 @@ static void __io_req_task_submit(struct io_kiocb *req)
if (!(current->flags & PF_EXITING) && !current->in_execve)
__io_queue_sqe(req);
else
- __io_req_task_cancel(req, -EFAULT);
+ io_req_complete_failed(req, -EFAULT);
mutex_unlock(&ctx->uring_lock);
}
@@ -1983,27 +2038,21 @@ static void io_req_task_submit(struct callback_head *cb)
__io_req_task_submit(req);
}
-static void io_req_task_queue(struct io_kiocb *req)
+static void io_req_task_queue_fail(struct io_kiocb *req, int ret)
{
- int ret;
+ req->result = ret;
+ req->task_work.func = io_req_task_cancel;
- req->task_work.func = io_req_task_submit;
- ret = io_req_task_work_add(req);
- if (unlikely(ret)) {
- req->result = -ECANCELED;
- percpu_ref_get(&req->ctx->refs);
+ if (unlikely(io_req_task_work_add(req)))
io_req_task_work_add_fallback(req, io_req_task_cancel);
- }
}
-static void io_req_task_queue_fail(struct io_kiocb *req, int ret)
+static void io_req_task_queue(struct io_kiocb *req)
{
- percpu_ref_get(&req->ctx->refs);
- req->result = ret;
- req->task_work.func = io_req_task_cancel;
+ req->task_work.func = io_req_task_submit;
if (unlikely(io_req_task_work_add(req)))
- io_req_task_work_add_fallback(req, io_req_task_cancel);
+ io_req_task_queue_fail(req, -ECANCELED);
}
static inline void io_queue_next(struct io_kiocb *req)
@@ -2046,6 +2095,7 @@ static void io_req_free_batch(struct req_batch *rb, struct io_kiocb *req,
struct io_submit_state *state)
{
io_queue_next(req);
+ io_dismantle_req(req);
if (req->task != rb->task) {
if (rb->task)
@@ -2056,7 +2106,6 @@ static void io_req_free_batch(struct req_batch *rb, struct io_kiocb *req,
rb->task_refs++;
rb->ctx_refs++;
- io_dismantle_req(req);
if (state->free_reqs != ARRAY_SIZE(state->reqs))
state->reqs[state->free_reqs++] = req;
else
@@ -2074,7 +2123,8 @@ static void io_submit_flush_completions(struct io_comp_state *cs,
spin_lock_irq(&ctx->completion_lock);
for (i = 0; i < nr; i++) {
req = cs->reqs[i];
- __io_cqring_fill_event(req, req->result, req->compl.cflags);
+ __io_cqring_fill_event(ctx, req->user_data, req->result,
+ req->compl.cflags);
}
io_commit_cqring(ctx);
spin_unlock_irq(&ctx->completion_lock);
@@ -2084,7 +2134,7 @@ static void io_submit_flush_completions(struct io_comp_state *cs,
req = cs->reqs[i];
/* submission and completion refs */
- if (refcount_sub_and_test(2, &req->refs))
+ if (req_ref_sub_and_test(req, 2))
io_req_free_batch(&rb, req, &ctx->submit_state);
}
@@ -2096,20 +2146,20 @@ static void io_submit_flush_completions(struct io_comp_state *cs,
* Drop reference to request, return next in chain (if there is one) if this
* was the last reference to this request.
*/
-static struct io_kiocb *io_put_req_find_next(struct io_kiocb *req)
+static inline struct io_kiocb *io_put_req_find_next(struct io_kiocb *req)
{
struct io_kiocb *nxt = NULL;
- if (refcount_dec_and_test(&req->refs)) {
+ if (req_ref_put_and_test(req)) {
nxt = io_req_find_next(req);
__io_free_req(req);
}
return nxt;
}
-static void io_put_req(struct io_kiocb *req)
+static inline void io_put_req(struct io_kiocb *req)
{
- if (refcount_dec_and_test(&req->refs))
+ if (req_ref_put_and_test(req))
io_free_req(req);
}
@@ -2122,27 +2172,17 @@ static void io_put_req_deferred_cb(struct callback_head *cb)
static void io_free_req_deferred(struct io_kiocb *req)
{
- int ret;
-
req->task_work.func = io_put_req_deferred_cb;
- ret = io_req_task_work_add(req);
- if (unlikely(ret))
+ if (unlikely(io_req_task_work_add(req)))
io_req_task_work_add_fallback(req, io_put_req_deferred_cb);
}
static inline void io_put_req_deferred(struct io_kiocb *req, int refs)
{
- if (refcount_sub_and_test(refs, &req->refs))
+ if (req_ref_sub_and_test(req, refs))
io_free_req_deferred(req);
}
-static void io_double_put_req(struct io_kiocb *req)
-{
- /* drop both submit and complete references */
- if (refcount_sub_and_test(2, &req->refs))
- io_free_req(req);
-}
-
static unsigned io_cqring_events(struct io_ring_ctx *ctx)
{
/* See comment at the top of this file */
@@ -2213,19 +2253,21 @@ static void io_iopoll_complete(struct io_ring_ctx *ctx, unsigned int *nr_events,
req = list_first_entry(done, struct io_kiocb, inflight_entry);
list_del(&req->inflight_entry);
- if (READ_ONCE(req->result) == -EAGAIN) {
+ if (READ_ONCE(req->result) == -EAGAIN &&
+ !(req->flags & REQ_F_DONT_REISSUE)) {
req->iopoll_completed = 0;
- if (io_rw_reissue(req))
- continue;
+ req_ref_get(req);
+ io_queue_async_work(req);
+ continue;
}
if (req->flags & REQ_F_BUFFER_SELECTED)
cflags = io_put_rw_kbuf(req);
- __io_cqring_fill_event(req, req->result, cflags);
+ __io_cqring_fill_event(ctx, req->user_data, req->result, cflags);
(*nr_events)++;
- if (refcount_dec_and_test(&req->refs))
+ if (req_ref_put_and_test(req))
io_req_free_batch(&rb, req, &ctx->submit_state);
}
@@ -2284,27 +2326,6 @@ static int io_do_iopoll(struct io_ring_ctx *ctx, unsigned int *nr_events,
}
/*
- * Poll for a minimum of 'min' events. Note that if min == 0 we consider that a
- * non-spinning poll check - we'll still enter the driver poll loop, but only
- * as a non-spinning completion check.
- */
-static int io_iopoll_getevents(struct io_ring_ctx *ctx, unsigned int *nr_events,
- long min)
-{
- while (!list_empty(&ctx->iopoll_list) && !need_resched()) {
- int ret;
-
- ret = io_do_iopoll(ctx, nr_events, min);
- if (ret < 0)
- return ret;
- if (*nr_events >= min)
- return 0;
- }
-
- return 1;
-}
-
-/*
* We can't just wait for polled events to come to us, we have to actively
* find and complete them.
*/
@@ -2339,7 +2360,7 @@ static void io_iopoll_try_reap_events(struct io_ring_ctx *ctx)
static int io_iopoll_check(struct io_ring_ctx *ctx, long min)
{
unsigned int nr_events = 0;
- int iters = 0, ret = 0;
+ int ret = 0;
/*
* We disallow the app entering submit/complete with polling, but we
@@ -2347,18 +2368,17 @@ static int io_iopoll_check(struct io_ring_ctx *ctx, long min)
* that got punted to a workqueue.
*/
mutex_lock(&ctx->uring_lock);
+ /*
+ * Don't enter poll loop if we already have events pending.
+ * If we do, we can potentially be spinning for commands that
+ * already triggered a CQE (eg in error).
+ */
+ if (test_bit(0, &ctx->cq_check_overflow))
+ __io_cqring_overflow_flush(ctx, false);
+ if (io_cqring_events(ctx))
+ goto out;
do {
/*
- * Don't enter poll loop if we already have events pending.
- * If we do, we can potentially be spinning for commands that
- * already triggered a CQE (eg in error).
- */
- if (test_bit(0, &ctx->cq_check_overflow))
- __io_cqring_overflow_flush(ctx, false, NULL, NULL);
- if (io_cqring_events(ctx))
- break;
-
- /*
* If a submit got punted to a workqueue, we can have the
* application entering polling for a command before it gets
* issued. That app will hold the uring_lock for the duration
@@ -2368,18 +2388,17 @@ static int io_iopoll_check(struct io_ring_ctx *ctx, long min)
* forever, while the workqueue is stuck trying to acquire the
* very same mutex.
*/
- if (!(++iters & 7)) {
+ if (list_empty(&ctx->iopoll_list)) {
mutex_unlock(&ctx->uring_lock);
io_run_task_work();
mutex_lock(&ctx->uring_lock);
- }
-
- ret = io_iopoll_getevents(ctx, &nr_events, min);
- if (ret <= 0)
- break;
- ret = 0;
- } while (min && !nr_events && !need_resched());
+ if (list_empty(&ctx->iopoll_list))
+ break;
+ }
+ ret = io_do_iopoll(ctx, &nr_events, min);
+ } while (!ret && nr_events < min && !need_resched());
+out:
mutex_unlock(&ctx->uring_lock);
return ret;
}
@@ -2391,45 +2410,23 @@ static void kiocb_end_write(struct io_kiocb *req)
* thread.
*/
if (req->flags & REQ_F_ISREG) {
- struct inode *inode = file_inode(req->file);
+ struct super_block *sb = file_inode(req->file)->i_sb;
- __sb_writers_acquired(inode->i_sb, SB_FREEZE_WRITE);
+ __sb_writers_acquired(sb, SB_FREEZE_WRITE);
+ sb_end_write(sb);
}
- file_end_write(req->file);
}
#ifdef CONFIG_BLOCK
static bool io_resubmit_prep(struct io_kiocb *req)
{
- struct iovec inline_vecs[UIO_FASTIOV], *iovec = inline_vecs;
- int rw, ret;
- struct iov_iter iter;
-
- /* already prepared */
- if (req->async_data)
- return true;
-
- switch (req->opcode) {
- case IORING_OP_READV:
- case IORING_OP_READ_FIXED:
- case IORING_OP_READ:
- rw = READ;
- break;
- case IORING_OP_WRITEV:
- case IORING_OP_WRITE_FIXED:
- case IORING_OP_WRITE:
- rw = WRITE;
- break;
- default:
- printk_once(KERN_WARNING "io_uring: bad opcode in resubmit %d\n",
- req->opcode);
- return false;
- }
+ struct io_async_rw *rw = req->async_data;
- ret = io_import_iovec(rw, req, &iovec, &iter, false);
- if (ret < 0)
- return false;
- return !io_setup_async_rw(req, iovec, inline_vecs, &iter, false);
+ if (!rw)
+ return !io_req_prep_async(req);
+ /* may have left rw->iter inconsistent on -EIOCBQUEUED */
+ iov_iter_revert(&rw->iter, req->result - iov_iter_count(&rw->iter));
+ return true;
}
static bool io_rw_should_reissue(struct io_kiocb *req)
@@ -2451,38 +2448,32 @@ static bool io_rw_should_reissue(struct io_kiocb *req)
return false;
return true;
}
-#endif
-
-static bool io_rw_reissue(struct io_kiocb *req)
+#else
+static bool io_resubmit_prep(struct io_kiocb *req)
{
-#ifdef CONFIG_BLOCK
- if (!io_rw_should_reissue(req))
- return false;
-
- lockdep_assert_held(&req->ctx->uring_lock);
-
- if (io_resubmit_prep(req)) {
- refcount_inc(&req->refs);
- io_queue_async_work(req);
- return true;
- }
- req_set_fail_links(req);
-#endif
return false;
}
+static bool io_rw_should_reissue(struct io_kiocb *req)
+{
+ return false;
+}
+#endif
static void __io_complete_rw(struct io_kiocb *req, long res, long res2,
unsigned int issue_flags)
{
int cflags = 0;
- if ((res == -EAGAIN || res == -EOPNOTSUPP) && io_rw_reissue(req))
- return;
- if (res != req->result)
- req_set_fail_links(req);
-
if (req->rw.kiocb.ki_flags & IOCB_WRITE)
kiocb_end_write(req);
+ if (res != req->result) {
+ if ((res == -EAGAIN || res == -EOPNOTSUPP) &&
+ io_rw_should_reissue(req)) {
+ req->flags |= REQ_F_REISSUE;
+ return;
+ }
+ req_set_fail_links(req);
+ }
if (req->flags & REQ_F_BUFFER_SELECTED)
cflags = io_put_rw_kbuf(req);
__io_req_complete(req, issue_flags, res, cflags);
@@ -2499,27 +2490,18 @@ static void io_complete_rw_iopoll(struct kiocb *kiocb, long res, long res2)
{
struct io_kiocb *req = container_of(kiocb, struct io_kiocb, rw.kiocb);
-#ifdef CONFIG_BLOCK
- /* Rewind iter, if we have one. iopoll path resubmits as usual */
- if (res == -EAGAIN && io_rw_should_reissue(req)) {
- struct io_async_rw *rw = req->async_data;
-
- if (rw)
- iov_iter_revert(&rw->iter,
- req->result - iov_iter_count(&rw->iter));
- else if (!io_resubmit_prep(req))
- res = -EIO;
- }
-#endif
-
if (kiocb->ki_flags & IOCB_WRITE)
kiocb_end_write(req);
-
- if (res != -EAGAIN && res != req->result)
- req_set_fail_links(req);
+ if (unlikely(res != req->result)) {
+ if (!(res == -EAGAIN && io_rw_should_reissue(req) &&
+ io_resubmit_prep(req))) {
+ req_set_fail_links(req);
+ req->flags |= REQ_F_DONT_REISSUE;
+ }
+ }
WRITE_ONCE(req->result, res);
- /* order with io_poll_complete() checking ->result */
+ /* order with io_iopoll_complete() checking ->result */
smp_wmb();
WRITE_ONCE(req->iopoll_completed, 1);
}
@@ -2527,7 +2509,7 @@ static void io_complete_rw_iopoll(struct kiocb *kiocb, long res, long res2)
/*
* After the iocb has been issued, it's safe to be found on the poll list.
* Adding the kiocb to the list AFTER submission ensures that we don't
- * find it from a io_iopoll_getevents() thread before the issuer is done
+ * find it from a io_do_iopoll() thread before the issuer is done
* accessing the kiocb cookie.
*/
static void io_iopoll_req_issued(struct io_kiocb *req, bool in_async)
@@ -2613,7 +2595,7 @@ static bool io_bdev_nowait(struct block_device *bdev)
* any file. For now, just ensure that anything potentially problematic is done
* inline.
*/
-static bool io_file_supports_async(struct file *file, int rw)
+static bool __io_file_supports_async(struct file *file, int rw)
{
umode_t mode = file_inode(file)->i_mode;
@@ -2646,6 +2628,16 @@ static bool io_file_supports_async(struct file *file, int rw)
return file->f_op->write_iter != NULL;
}
+static bool io_file_supports_async(struct io_kiocb *req, int rw)
+{
+ if (rw == READ && (req->flags & REQ_F_ASYNC_READ))
+ return true;
+ else if (rw == WRITE && (req->flags & REQ_F_ASYNC_WRITE))
+ return true;
+
+ return __io_file_supports_async(req->file, rw);
+}
+
static int io_prep_rw(struct io_kiocb *req, const struct io_uring_sqe *sqe)
{
struct io_ring_ctx *ctx = req->ctx;
@@ -2654,7 +2646,7 @@ static int io_prep_rw(struct io_kiocb *req, const struct io_uring_sqe *sqe)
unsigned ioprio;
int ret;
- if (S_ISREG(file_inode(file)->i_mode))
+ if (!(req->flags & REQ_F_ISREG) && S_ISREG(file_inode(file)->i_mode))
req->flags |= REQ_F_ISREG;
kiocb->ki_pos = READ_ONCE(sqe->off);
@@ -2696,6 +2688,12 @@ static int io_prep_rw(struct io_kiocb *req, const struct io_uring_sqe *sqe)
kiocb->ki_complete = io_complete_rw;
}
+ if (req->opcode == IORING_OP_READ_FIXED ||
+ req->opcode == IORING_OP_WRITE_FIXED) {
+ req->imu = NULL;
+ io_req_set_rsrc_node(req);
+ }
+
req->rw.addr = READ_ONCE(sqe->addr);
req->rw.len = READ_ONCE(sqe->len);
req->buf_index = READ_ONCE(sqe->buf_index);
@@ -2728,6 +2726,7 @@ static void kiocb_done(struct kiocb *kiocb, ssize_t ret,
{
struct io_kiocb *req = container_of(kiocb, struct io_kiocb, rw.kiocb);
struct io_async_rw *io = req->async_data;
+ bool check_reissue = kiocb->ki_complete == io_complete_rw;
/* add previously done IO, if any */
if (io && io->bytes_done > 0) {
@@ -2743,28 +2742,34 @@ static void kiocb_done(struct kiocb *kiocb, ssize_t ret,
__io_complete_rw(req, ret, 0, issue_flags);
else
io_rw_done(kiocb, ret);
+
+ if (check_reissue && req->flags & REQ_F_REISSUE) {
+ req->flags &= ~REQ_F_REISSUE;
+ if (io_resubmit_prep(req)) {
+ req_ref_get(req);
+ io_queue_async_work(req);
+ } else {
+ int cflags = 0;
+
+ req_set_fail_links(req);
+ if (req->flags & REQ_F_BUFFER_SELECTED)
+ cflags = io_put_rw_kbuf(req);
+ __io_req_complete(req, issue_flags, ret, cflags);
+ }
+ }
}
-static int io_import_fixed(struct io_kiocb *req, int rw, struct iov_iter *iter)
+static int __io_import_fixed(struct io_kiocb *req, int rw, struct iov_iter *iter,
+ struct io_mapped_ubuf *imu)
{
- struct io_ring_ctx *ctx = req->ctx;
size_t len = req->rw.len;
- struct io_mapped_ubuf *imu;
- u16 index, buf_index = req->buf_index;
+ u64 buf_end, buf_addr = req->rw.addr;
size_t offset;
- u64 buf_addr;
-
- if (unlikely(buf_index >= ctx->nr_user_bufs))
- return -EFAULT;
- index = array_index_nospec(buf_index, ctx->nr_user_bufs);
- imu = &ctx->user_bufs[index];
- buf_addr = req->rw.addr;
- /* overflow */
- if (buf_addr + len < buf_addr)
+ if (unlikely(check_add_overflow(buf_addr, (u64)len, &buf_end)))
return -EFAULT;
/* not inside the mapped region */
- if (buf_addr < imu->ubuf || buf_addr + len > imu->ubuf + imu->len)
+ if (unlikely(buf_addr < imu->ubuf || buf_end > imu->ubuf_end))
return -EFAULT;
/*
@@ -2812,6 +2817,22 @@ static int io_import_fixed(struct io_kiocb *req, int rw, struct iov_iter *iter)
return 0;
}
+static int io_import_fixed(struct io_kiocb *req, int rw, struct iov_iter *iter)
+{
+ struct io_ring_ctx *ctx = req->ctx;
+ struct io_mapped_ubuf *imu = req->imu;
+ u16 index, buf_index = req->buf_index;
+
+ if (likely(!imu)) {
+ if (unlikely(buf_index >= ctx->nr_user_bufs))
+ return -EFAULT;
+ index = array_index_nospec(buf_index, ctx->nr_user_bufs);
+ imu = READ_ONCE(ctx->user_bufs[index]);
+ req->imu = imu;
+ }
+ return __io_import_fixed(req, rw, iter, imu);
+}
+
static void io_ring_submit_unlock(struct io_ring_ctx *ctx, bool needs_lock)
{
if (needs_lock)
@@ -2843,7 +2864,7 @@ static struct io_buffer *io_buffer_select(struct io_kiocb *req, size_t *len,
lockdep_assert_held(&req->ctx->uring_lock);
- head = idr_find(&req->ctx->io_buffer_idr, bgid);
+ head = xa_load(&req->ctx->io_buffers, bgid);
if (head) {
if (!list_empty(&head->list)) {
kbuf = list_last_entry(&head->list, struct io_buffer,
@@ -2851,7 +2872,7 @@ static struct io_buffer *io_buffer_select(struct io_kiocb *req, size_t *len,
list_del(&kbuf->list);
} else {
kbuf = head;
- idr_remove(&req->ctx->io_buffer_idr, bgid);
+ xa_erase(&req->ctx->io_buffers, bgid);
}
if (*len > kbuf->len)
*len = kbuf->len;
@@ -3079,29 +3100,21 @@ static void io_req_map_rw(struct io_kiocb *req, const struct iovec *iovec,
}
}
-static inline int __io_alloc_async_data(struct io_kiocb *req)
+static inline int io_alloc_async_data(struct io_kiocb *req)
{
WARN_ON_ONCE(!io_op_defs[req->opcode].async_size);
req->async_data = kmalloc(io_op_defs[req->opcode].async_size, GFP_KERNEL);
return req->async_data == NULL;
}
-static int io_alloc_async_data(struct io_kiocb *req)
-{
- if (!io_op_defs[req->opcode].needs_async_data)
- return 0;
-
- return __io_alloc_async_data(req);
-}
-
static int io_setup_async_rw(struct io_kiocb *req, const struct iovec *iovec,
const struct iovec *fast_iov,
struct iov_iter *iter, bool force)
{
- if (!force && !io_op_defs[req->opcode].needs_async_data)
+ if (!force && !io_op_defs[req->opcode].needs_async_setup)
return 0;
if (!req->async_data) {
- if (__io_alloc_async_data(req)) {
+ if (io_alloc_async_data(req)) {
kfree(iovec);
return -ENOMEM;
}
@@ -3161,7 +3174,7 @@ static int io_async_buf_func(struct wait_queue_entry *wait, unsigned mode,
list_del_init(&wait->entry);
/* submit ref gets dropped, acquire a new one */
- refcount_inc(&req->refs);
+ req_ref_get(req);
io_req_task_queue(req);
return 1;
}
@@ -3246,7 +3259,7 @@ static int io_read(struct io_kiocb *req, unsigned int issue_flags)
kiocb->ki_flags |= IOCB_NOWAIT;
/* If the file doesn't support async, just async punt */
- if (force_nonblock && !io_file_supports_async(req->file, READ)) {
+ if (force_nonblock && !io_file_supports_async(req, READ)) {
ret = io_setup_async_rw(req, iovec, inline_vecs, iter, true);
return ret ?: -EAGAIN;
}
@@ -3259,11 +3272,8 @@ static int io_read(struct io_kiocb *req, unsigned int issue_flags)
ret = io_iter_do_read(req, iter);
- if (ret == -EIOCBQUEUED) {
- if (req->async_data)
- iov_iter_revert(iter, io_size - iov_iter_count(iter));
- goto out_free;
- } else if (ret == -EAGAIN) {
+ if (ret == -EAGAIN || (req->flags & REQ_F_REISSUE)) {
+ req->flags &= ~REQ_F_REISSUE;
/* IOPOLL retry should happen for io-wq threads */
if (!force_nonblock && !(req->ctx->flags & IORING_SETUP_IOPOLL))
goto done;
@@ -3273,6 +3283,8 @@ static int io_read(struct io_kiocb *req, unsigned int issue_flags)
/* some cases will consume bytes even on error returns */
iov_iter_revert(iter, io_size - iov_iter_count(iter));
ret = 0;
+ } else if (ret == -EIOCBQUEUED) {
+ goto out_free;
} else if (ret <= 0 || ret == io_size || !force_nonblock ||
(req->flags & REQ_F_NOWAIT) || !(req->flags & REQ_F_ISREG)) {
/* read all, failed, already did sync or don't want to retry */
@@ -3352,7 +3364,7 @@ static int io_write(struct io_kiocb *req, unsigned int issue_flags)
kiocb->ki_flags |= IOCB_NOWAIT;
/* If the file doesn't support async, just async punt */
- if (force_nonblock && !io_file_supports_async(req->file, WRITE))
+ if (force_nonblock && !io_file_supports_async(req, WRITE))
goto copy_iov;
/* file path doesn't support NOWAIT for non-direct_IO */
@@ -3385,6 +3397,11 @@ static int io_write(struct io_kiocb *req, unsigned int issue_flags)
else
ret2 = -EINVAL;
+ if (req->flags & REQ_F_REISSUE) {
+ req->flags &= ~REQ_F_REISSUE;
+ ret2 = -EAGAIN;
+ }
+
/*
* Raw bdev writes will return -EOPNOTSUPP for IOCB_NOWAIT. Just
* retry them without IOCB_NOWAIT.
@@ -3394,8 +3411,6 @@ static int io_write(struct io_kiocb *req, unsigned int issue_flags)
/* no retry on NONBLOCK nor RWF_NOWAIT */
if (ret2 == -EAGAIN && (req->flags & REQ_F_NOWAIT))
goto done;
- if (ret2 == -EIOCBQUEUED && req->async_data)
- iov_iter_revert(iter, io_size - iov_iter_count(iter));
if (!force_nonblock || ret2 != -EAGAIN) {
/* IOPOLL retry should happen for io-wq threads */
if ((req->ctx->flags & IORING_SETUP_IOPOLL) && ret2 == -EAGAIN)
@@ -3568,15 +3583,6 @@ static int __io_splice_prep(struct io_kiocb *req,
if (!sp->file_in)
return -EBADF;
req->flags |= REQ_F_NEED_CLEANUP;
-
- if (!S_ISREG(file_inode(sp->file_in)->i_mode)) {
- /*
- * Splice operation will be punted aync, and here need to
- * modify io_wq_work.flags, so initialize io_wq_work firstly.
- */
- req->work.flags |= IO_WQ_WORK_UNBOUND;
- }
-
return 0;
}
@@ -3601,7 +3607,8 @@ static int io_tee(struct io_kiocb *req, unsigned int issue_flags)
if (sp->len)
ret = do_tee(in, out, sp->len, flags);
- io_put_file(req, in, (sp->flags & SPLICE_F_FD_IN_FIXED));
+ if (!(sp->flags & SPLICE_F_FD_IN_FIXED))
+ io_put_file(in);
req->flags &= ~REQ_F_NEED_CLEANUP;
if (ret != sp->len)
@@ -3637,7 +3644,8 @@ static int io_splice(struct io_kiocb *req, unsigned int issue_flags)
if (sp->len)
ret = do_splice(in, poff_in, out, poff_out, sp->len, flags);
- io_put_file(req, in, (sp->flags & SPLICE_F_FD_IN_FIXED));
+ if (!(sp->flags & SPLICE_F_FD_IN_FIXED))
+ io_put_file(in);
req->flags &= ~REQ_F_NEED_CLEANUP;
if (ret != sp->len)
@@ -3843,7 +3851,7 @@ err:
req->flags &= ~REQ_F_NEED_CLEANUP;
if (ret < 0)
req_set_fail_links(req);
- io_req_complete(req, ret);
+ __io_req_complete(req, issue_flags, ret, 0);
return 0;
}
@@ -3892,7 +3900,7 @@ static int __io_remove_buffers(struct io_ring_ctx *ctx, struct io_buffer *buf,
}
i++;
kfree(buf);
- idr_remove(&ctx->io_buffer_idr, bgid);
+ xa_erase(&ctx->io_buffers, bgid);
return i;
}
@@ -3910,26 +3918,22 @@ static int io_remove_buffers(struct io_kiocb *req, unsigned int issue_flags)
lockdep_assert_held(&ctx->uring_lock);
ret = -ENOENT;
- head = idr_find(&ctx->io_buffer_idr, p->bgid);
+ head = xa_load(&ctx->io_buffers, p->bgid);
if (head)
ret = __io_remove_buffers(ctx, head, p->bgid, p->nbufs);
if (ret < 0)
req_set_fail_links(req);
- /* need to hold the lock to complete IOPOLL requests */
- if (ctx->flags & IORING_SETUP_IOPOLL) {
- __io_req_complete(req, issue_flags, ret, 0);
- io_ring_submit_unlock(ctx, !force_nonblock);
- } else {
- io_ring_submit_unlock(ctx, !force_nonblock);
- __io_req_complete(req, issue_flags, ret, 0);
- }
+ /* complete before unlock, IOPOLL may need the lock */
+ __io_req_complete(req, issue_flags, ret, 0);
+ io_ring_submit_unlock(ctx, !force_nonblock);
return 0;
}
static int io_provide_buffers_prep(struct io_kiocb *req,
const struct io_uring_sqe *sqe)
{
+ unsigned long size, tmp_check;
struct io_provide_buf *p = &req->pbuf;
u64 tmp;
@@ -3943,7 +3947,14 @@ static int io_provide_buffers_prep(struct io_kiocb *req,
p->addr = READ_ONCE(sqe->addr);
p->len = READ_ONCE(sqe->len);
- if (!access_ok(u64_to_user_ptr(p->addr), (p->len * p->nbufs)))
+ if (check_mul_overflow((unsigned long)p->len, (unsigned long)p->nbufs,
+ &size))
+ return -EOVERFLOW;
+ if (check_add_overflow((unsigned long)p->addr, size, &tmp_check))
+ return -EOVERFLOW;
+
+ size = (unsigned long)p->len * p->nbufs;
+ if (!access_ok(u64_to_user_ptr(p->addr), size))
return -EFAULT;
p->bgid = READ_ONCE(sqe->buf_group);
@@ -3993,32 +4004,19 @@ static int io_provide_buffers(struct io_kiocb *req, unsigned int issue_flags)
lockdep_assert_held(&ctx->uring_lock);
- list = head = idr_find(&ctx->io_buffer_idr, p->bgid);
+ list = head = xa_load(&ctx->io_buffers, p->bgid);
ret = io_add_buffers(p, &head);
- if (ret < 0)
- goto out;
-
- if (!list) {
- ret = idr_alloc(&ctx->io_buffer_idr, head, p->bgid, p->bgid + 1,
- GFP_KERNEL);
- if (ret < 0) {
+ if (ret >= 0 && !list) {
+ ret = xa_insert(&ctx->io_buffers, p->bgid, head, GFP_KERNEL);
+ if (ret < 0)
__io_remove_buffers(ctx, head, p->bgid, -1U);
- goto out;
- }
}
-out:
if (ret < 0)
req_set_fail_links(req);
-
- /* need to hold the lock to complete IOPOLL requests */
- if (ctx->flags & IORING_SETUP_IOPOLL) {
- __io_req_complete(req, issue_flags, ret, 0);
- io_ring_submit_unlock(ctx, !force_nonblock);
- } else {
- io_ring_submit_unlock(ctx, !force_nonblock);
- __io_req_complete(req, issue_flags, ret, 0);
- }
+ /* complete before unlock, IOPOLL may need the lock */
+ __io_req_complete(req, issue_flags, ret, 0);
+ io_ring_submit_unlock(ctx, !force_nonblock);
return 0;
}
@@ -4137,7 +4135,7 @@ static int io_fadvise(struct io_kiocb *req, unsigned int issue_flags)
ret = vfs_fadvise(req->file, fa->offset, fa->len, fa->advice);
if (ret < 0)
req_set_fail_links(req);
- io_req_complete(req, ret);
+ __io_req_complete(req, issue_flags, ret, 0);
return 0;
}
@@ -4164,12 +4162,8 @@ static int io_statx(struct io_kiocb *req, unsigned int issue_flags)
struct io_statx *ctx = &req->statx;
int ret;
- if (issue_flags & IO_URING_F_NONBLOCK) {
- /* only need file table for an actual valid fd */
- if (ctx->dfd == -1 || ctx->dfd == AT_FDCWD)
- req->flags |= REQ_F_NO_FILE_TABLE;
+ if (issue_flags & IO_URING_F_NONBLOCK)
return -EAGAIN;
- }
ret = do_statx(ctx->dfd, ctx->filename, ctx->flags, ctx->mask,
ctx->buffer);
@@ -4199,11 +4193,9 @@ static int io_close(struct io_kiocb *req, unsigned int issue_flags)
struct files_struct *files = current->files;
struct io_close *close = &req->close;
struct fdtable *fdt;
- struct file *file;
- int ret;
+ struct file *file = NULL;
+ int ret = -EBADF;
- file = NULL;
- ret = -EBADF;
spin_lock(&files->file_lock);
fdt = files_fdtable(files);
if (close->fd >= fdt->max_fds) {
@@ -4211,12 +4203,7 @@ static int io_close(struct io_kiocb *req, unsigned int issue_flags)
goto err;
}
file = fdt->fd[close->fd];
- if (!file) {
- spin_unlock(&files->file_lock);
- goto err;
- }
-
- if (file->f_op == &io_uring_fops) {
+ if (!file || file->f_op == &io_uring_fops) {
spin_unlock(&files->file_lock);
file = NULL;
goto err;
@@ -4314,8 +4301,6 @@ static int io_sendmsg_prep_async(struct io_kiocb *req)
{
int ret;
- if (!io_op_defs[req->opcode].needs_async_data)
- return 0;
ret = io_sendmsg_copy_hdr(req, req->async_data);
if (!ret)
req->flags |= REQ_F_NEED_CLEANUP;
@@ -4329,9 +4314,11 @@ static int io_sendmsg_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL))
return -EINVAL;
- sr->msg_flags = READ_ONCE(sqe->msg_flags);
sr->umsg = u64_to_user_ptr(READ_ONCE(sqe->addr));
sr->len = READ_ONCE(sqe->len);
+ sr->msg_flags = READ_ONCE(sqe->msg_flags) | MSG_NOSIGNAL;
+ if (sr->msg_flags & MSG_DONTWAIT)
+ req->flags |= REQ_F_NOWAIT;
#ifdef CONFIG_COMPAT
if (req->ctx->compat)
@@ -4345,6 +4332,7 @@ static int io_sendmsg(struct io_kiocb *req, unsigned int issue_flags)
struct io_async_msghdr iomsg, *kmsg;
struct socket *sock;
unsigned flags;
+ int min_ret = 0;
int ret;
sock = sock_from_file(req->file);
@@ -4360,10 +4348,10 @@ static int io_sendmsg(struct io_kiocb *req, unsigned int issue_flags)
}
flags = req->sr_msg.msg_flags;
- if (flags & MSG_DONTWAIT)
- req->flags |= REQ_F_NOWAIT;
- else if (issue_flags & IO_URING_F_NONBLOCK)
+ if (issue_flags & IO_URING_F_NONBLOCK)
flags |= MSG_DONTWAIT;
+ if (flags & MSG_WAITALL)
+ min_ret = iov_iter_count(&kmsg->msg.msg_iter);
ret = __sys_sendmsg_sock(sock, &kmsg->msg, flags);
if ((issue_flags & IO_URING_F_NONBLOCK) && ret == -EAGAIN)
@@ -4375,7 +4363,7 @@ static int io_sendmsg(struct io_kiocb *req, unsigned int issue_flags)
if (kmsg->free_iov)
kfree(kmsg->free_iov);
req->flags &= ~REQ_F_NEED_CLEANUP;
- if (ret < 0)
+ if (ret < min_ret)
req_set_fail_links(req);
__io_req_complete(req, issue_flags, ret, 0);
return 0;
@@ -4388,6 +4376,7 @@ static int io_send(struct io_kiocb *req, unsigned int issue_flags)
struct iovec iov;
struct socket *sock;
unsigned flags;
+ int min_ret = 0;
int ret;
sock = sock_from_file(req->file);
@@ -4404,10 +4393,10 @@ static int io_send(struct io_kiocb *req, unsigned int issue_flags)
msg.msg_namelen = 0;
flags = req->sr_msg.msg_flags;
- if (flags & MSG_DONTWAIT)
- req->flags |= REQ_F_NOWAIT;
- else if (issue_flags & IO_URING_F_NONBLOCK)
+ if (issue_flags & IO_URING_F_NONBLOCK)
flags |= MSG_DONTWAIT;
+ if (flags & MSG_WAITALL)
+ min_ret = iov_iter_count(&msg.msg_iter);
msg.msg_flags = flags;
ret = sock_sendmsg(sock, &msg);
@@ -4416,7 +4405,7 @@ static int io_send(struct io_kiocb *req, unsigned int issue_flags)
if (ret == -ERESTARTSYS)
ret = -EINTR;
- if (ret < 0)
+ if (ret < min_ret)
req_set_fail_links(req);
__io_req_complete(req, issue_flags, ret, 0);
return 0;
@@ -4458,16 +4447,14 @@ static int __io_recvmsg_copy_hdr(struct io_kiocb *req,
static int __io_compat_recvmsg_copy_hdr(struct io_kiocb *req,
struct io_async_msghdr *iomsg)
{
- struct compat_msghdr __user *msg_compat;
struct io_sr_msg *sr = &req->sr_msg;
struct compat_iovec __user *uiov;
compat_uptr_t ptr;
compat_size_t len;
int ret;
- msg_compat = (struct compat_msghdr __user *) sr->umsg;
- ret = __get_compat_msghdr(&iomsg->msg, msg_compat, &iomsg->uaddr,
- &ptr, &len);
+ ret = __get_compat_msghdr(&iomsg->msg, sr->umsg_compat, &iomsg->uaddr,
+ &ptr, &len);
if (ret)
return ret;
@@ -4535,8 +4522,6 @@ static int io_recvmsg_prep_async(struct io_kiocb *req)
{
int ret;
- if (!io_op_defs[req->opcode].needs_async_data)
- return 0;
ret = io_recvmsg_copy_hdr(req, req->async_data);
if (!ret)
req->flags |= REQ_F_NEED_CLEANUP;
@@ -4550,10 +4535,12 @@ static int io_recvmsg_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL))
return -EINVAL;
- sr->msg_flags = READ_ONCE(sqe->msg_flags);
sr->umsg = u64_to_user_ptr(READ_ONCE(sqe->addr));
sr->len = READ_ONCE(sqe->len);
sr->bgid = READ_ONCE(sqe->buf_group);
+ sr->msg_flags = READ_ONCE(sqe->msg_flags) | MSG_NOSIGNAL;
+ if (sr->msg_flags & MSG_DONTWAIT)
+ req->flags |= REQ_F_NOWAIT;
#ifdef CONFIG_COMPAT
if (req->ctx->compat)
@@ -4568,6 +4555,7 @@ static int io_recvmsg(struct io_kiocb *req, unsigned int issue_flags)
struct socket *sock;
struct io_buffer *kbuf;
unsigned flags;
+ int min_ret = 0;
int ret, cflags = 0;
bool force_nonblock = issue_flags & IO_URING_F_NONBLOCK;
@@ -4594,10 +4582,10 @@ static int io_recvmsg(struct io_kiocb *req, unsigned int issue_flags)
}
flags = req->sr_msg.msg_flags;
- if (flags & MSG_DONTWAIT)
- req->flags |= REQ_F_NOWAIT;
- else if (force_nonblock)
+ if (force_nonblock)
flags |= MSG_DONTWAIT;
+ if (flags & MSG_WAITALL)
+ min_ret = iov_iter_count(&kmsg->msg.msg_iter);
ret = __sys_recvmsg_sock(sock, &kmsg->msg, req->sr_msg.umsg,
kmsg->uaddr, flags);
@@ -4612,7 +4600,7 @@ static int io_recvmsg(struct io_kiocb *req, unsigned int issue_flags)
if (kmsg->free_iov)
kfree(kmsg->free_iov);
req->flags &= ~REQ_F_NEED_CLEANUP;
- if (ret < 0)
+ if (ret < min_ret || ((flags & MSG_WAITALL) && (kmsg->msg.msg_flags & (MSG_TRUNC | MSG_CTRUNC))))
req_set_fail_links(req);
__io_req_complete(req, issue_flags, ret, cflags);
return 0;
@@ -4627,6 +4615,7 @@ static int io_recv(struct io_kiocb *req, unsigned int issue_flags)
struct socket *sock;
struct iovec iov;
unsigned flags;
+ int min_ret = 0;
int ret, cflags = 0;
bool force_nonblock = issue_flags & IO_URING_F_NONBLOCK;
@@ -4653,10 +4642,10 @@ static int io_recv(struct io_kiocb *req, unsigned int issue_flags)
msg.msg_flags = 0;
flags = req->sr_msg.msg_flags;
- if (flags & MSG_DONTWAIT)
- req->flags |= REQ_F_NOWAIT;
- else if (force_nonblock)
+ if (force_nonblock)
flags |= MSG_DONTWAIT;
+ if (flags & MSG_WAITALL)
+ min_ret = iov_iter_count(&msg.msg_iter);
ret = sock_recvmsg(sock, &msg, flags);
if (force_nonblock && ret == -EAGAIN)
@@ -4666,7 +4655,7 @@ static int io_recv(struct io_kiocb *req, unsigned int issue_flags)
out_free:
if (req->flags & REQ_F_BUFFER_SELECTED)
cflags = io_put_recv_kbuf(req);
- if (ret < 0)
+ if (ret < min_ret || ((flags & MSG_WAITALL) && (msg.msg_flags & (MSG_TRUNC | MSG_CTRUNC))))
req_set_fail_links(req);
__io_req_complete(req, issue_flags, ret, cflags);
return 0;
@@ -4763,7 +4752,6 @@ static int io_connect(struct io_kiocb *req, unsigned int issue_flags)
ret = -ENOMEM;
goto out;
}
- io = req->async_data;
memcpy(req->async_data, &__io, sizeof(__io));
return -EAGAIN;
}
@@ -4825,7 +4813,6 @@ static int __io_async_wake(struct io_kiocb *req, struct io_poll_iocb *poll,
req->result = mask;
req->task_work.func = func;
- percpu_ref_get(&req->ctx->refs);
/*
* If this fails, then the task is exiting. When a task exits, the
@@ -4877,6 +4864,7 @@ static struct io_poll_iocb *io_poll_get_single(struct io_kiocb *req)
}
static void io_poll_remove_double(struct io_kiocb *req)
+ __must_hold(&req->ctx->completion_lock)
{
struct io_poll_iocb *poll = io_poll_get_double(req);
@@ -4888,20 +4876,37 @@ static void io_poll_remove_double(struct io_kiocb *req)
spin_lock(&head->lock);
list_del_init(&poll->wait.entry);
if (poll->wait.private)
- refcount_dec(&req->refs);
+ req_ref_put(req);
poll->head = NULL;
spin_unlock(&head->lock);
}
}
-static void io_poll_complete(struct io_kiocb *req, __poll_t mask, int error)
+static bool io_poll_complete(struct io_kiocb *req, __poll_t mask)
+ __must_hold(&req->ctx->completion_lock)
{
struct io_ring_ctx *ctx = req->ctx;
+ unsigned flags = IORING_CQE_F_MORE;
+ int error;
+
+ if (READ_ONCE(req->poll.canceled)) {
+ error = -ECANCELED;
+ req->poll.events |= EPOLLONESHOT;
+ } else {
+ error = mangle_poll(mask);
+ }
+ if (req->poll.events & EPOLLONESHOT)
+ flags = 0;
+ if (!io_cqring_fill_event(ctx, req->user_data, error, flags)) {
+ io_poll_remove_waitqs(req);
+ req->poll.done = true;
+ flags = 0;
+ }
+ if (flags & IORING_CQE_F_MORE)
+ ctx->cq_extra++;
- io_poll_remove_double(req);
- req->poll.done = true;
- io_cqring_fill_event(req, error ? error : mangle_poll(mask));
io_commit_cqring(ctx);
+ return !(flags & IORING_CQE_F_MORE);
}
static void io_poll_task_func(struct callback_head *cb)
@@ -4913,17 +4918,24 @@ static void io_poll_task_func(struct callback_head *cb)
if (io_poll_rewait(req, &req->poll)) {
spin_unlock_irq(&ctx->completion_lock);
} else {
- hash_del(&req->hash_node);
- io_poll_complete(req, req->result, 0);
- spin_unlock_irq(&ctx->completion_lock);
+ bool done;
- nxt = io_put_req_find_next(req);
+ done = io_poll_complete(req, req->result);
+ if (done) {
+ hash_del(&req->hash_node);
+ } else {
+ req->result = 0;
+ add_wait_queue(req->poll.head, &req->poll.wait);
+ }
+ spin_unlock_irq(&ctx->completion_lock);
io_cqring_ev_posted(ctx);
- if (nxt)
- __io_req_task_submit(nxt);
- }
- percpu_ref_put(&ctx->refs);
+ if (done) {
+ nxt = io_put_req_find_next(req);
+ if (nxt)
+ __io_req_task_submit(nxt);
+ }
+ }
}
static int io_poll_double_wake(struct wait_queue_entry *wait, unsigned mode,
@@ -4936,6 +4948,8 @@ static int io_poll_double_wake(struct wait_queue_entry *wait, unsigned mode,
/* for instances that support it check for an event match first: */
if (mask && !(mask & poll->events))
return 0;
+ if (!(poll->events & EPOLLONESHOT))
+ return poll->wait.func(&poll->wait, mode, sync, key);
list_del_init(&wait->entry);
@@ -4954,7 +4968,7 @@ static int io_poll_double_wake(struct wait_queue_entry *wait, unsigned mode,
poll->wait.func(&poll->wait, mode, sync, key);
}
}
- refcount_dec(&req->refs);
+ req_ref_put(req);
return 1;
}
@@ -4964,7 +4978,9 @@ static void io_init_poll_iocb(struct io_poll_iocb *poll, __poll_t events,
poll->head = NULL;
poll->done = false;
poll->canceled = false;
- poll->events = events;
+#define IO_POLL_UNMASK (EPOLLERR|EPOLLHUP|EPOLLNVAL|EPOLLRDHUP)
+ /* mask in events that we always want/need */
+ poll->events = events | IO_POLL_UNMASK;
INIT_LIST_HEAD(&poll->wait.entry);
init_waitqueue_func_entry(&poll->wait, wake_func);
}
@@ -4988,6 +5004,12 @@ static void __io_queue_proc(struct io_poll_iocb *poll, struct io_poll_table *pt,
pt->error = -EINVAL;
return;
}
+ /*
+ * Can't handle multishot for double wait for now, turn it
+ * into one-shot mode.
+ */
+ if (!(req->poll.events & EPOLLONESHOT))
+ req->poll.events |= EPOLLONESHOT;
/* double add on the same waitqueue head, ignore */
if (poll->head == head)
return;
@@ -4997,7 +5019,7 @@ static void __io_queue_proc(struct io_poll_iocb *poll, struct io_poll_table *pt,
return;
}
io_init_poll_iocb(poll, poll_one->events, io_poll_double_wake);
- refcount_inc(&req->refs);
+ req_ref_get(req);
poll->wait.private = req;
*poll_ptr = poll;
}
@@ -5030,25 +5052,17 @@ static void io_async_task_func(struct callback_head *cb)
if (io_poll_rewait(req, &apoll->poll)) {
spin_unlock_irq(&ctx->completion_lock);
- percpu_ref_put(&ctx->refs);
return;
}
- /* If req is still hashed, it cannot have been canceled. Don't check. */
- if (hash_hashed(&req->hash_node))
- hash_del(&req->hash_node);
-
+ hash_del(&req->hash_node);
io_poll_remove_double(req);
spin_unlock_irq(&ctx->completion_lock);
if (!READ_ONCE(apoll->poll.canceled))
__io_req_task_submit(req);
else
- __io_req_task_cancel(req, -ECANCELED);
-
- percpu_ref_put(&ctx->refs);
- kfree(apoll->double_poll);
- kfree(apoll);
+ io_req_complete_failed(req, -ECANCELED);
}
static int io_async_wake(struct wait_queue_entry *wait, unsigned mode, int sync,
@@ -5101,7 +5115,7 @@ static __poll_t __io_arm_poll_handler(struct io_kiocb *req,
ipt->error = 0;
mask = 0;
}
- if (mask || ipt->error)
+ if ((mask && (poll->events & EPOLLONESHOT)) || ipt->error)
list_del_init(&poll->wait.entry);
else if (cancel)
WRITE_ONCE(poll->canceled, true);
@@ -5133,7 +5147,7 @@ static bool io_arm_poll_handler(struct io_kiocb *req)
else
return false;
/* if we can't nonblock try, then no point in arming a poll handler */
- if (!io_file_supports_async(req->file, rw))
+ if (!io_file_supports_async(req, rw))
return false;
apoll = kmalloc(sizeof(*apoll), GFP_ATOMIC);
@@ -5144,7 +5158,7 @@ static bool io_arm_poll_handler(struct io_kiocb *req)
req->flags |= REQ_F_POLLED;
req->apoll = apoll;
- mask = 0;
+ mask = EPOLLONESHOT;
if (def->pollin)
mask |= POLLIN | POLLRDNORM;
if (def->pollout)
@@ -5164,8 +5178,6 @@ static bool io_arm_poll_handler(struct io_kiocb *req)
if (ret || ipt.error) {
io_poll_remove_double(req);
spin_unlock_irq(&ctx->completion_lock);
- kfree(apoll->double_poll);
- kfree(apoll);
return false;
}
spin_unlock_irq(&ctx->completion_lock);
@@ -5175,12 +5187,16 @@ static bool io_arm_poll_handler(struct io_kiocb *req)
}
static bool __io_poll_remove_one(struct io_kiocb *req,
- struct io_poll_iocb *poll)
+ struct io_poll_iocb *poll, bool do_cancel)
+ __must_hold(&req->ctx->completion_lock)
{
bool do_complete = false;
+ if (!poll->head)
+ return false;
spin_lock(&poll->head->lock);
- WRITE_ONCE(poll->canceled, true);
+ if (do_cancel)
+ WRITE_ONCE(poll->canceled, true);
if (!list_empty(&poll->wait.entry)) {
list_del_init(&poll->wait.entry);
do_complete = true;
@@ -5190,28 +5206,29 @@ static bool __io_poll_remove_one(struct io_kiocb *req,
return do_complete;
}
-static bool io_poll_remove_one(struct io_kiocb *req)
+static bool io_poll_remove_waitqs(struct io_kiocb *req)
+ __must_hold(&req->ctx->completion_lock)
{
bool do_complete;
io_poll_remove_double(req);
+ do_complete = __io_poll_remove_one(req, io_poll_get_single(req), true);
- if (req->opcode == IORING_OP_POLL_ADD) {
- do_complete = __io_poll_remove_one(req, &req->poll);
- } else {
- struct async_poll *apoll = req->apoll;
-
+ if (req->opcode != IORING_OP_POLL_ADD && do_complete) {
/* non-poll requests have submit ref still */
- do_complete = __io_poll_remove_one(req, &apoll->poll);
- if (do_complete) {
- io_put_req(req);
- kfree(apoll->double_poll);
- kfree(apoll);
- }
+ req_ref_put(req);
}
+ return do_complete;
+}
+
+static bool io_poll_remove_one(struct io_kiocb *req)
+ __must_hold(&req->ctx->completion_lock)
+{
+ bool do_complete;
+ do_complete = io_poll_remove_waitqs(req);
if (do_complete) {
- io_cqring_fill_event(req, -ECANCELED);
+ io_cqring_fill_event(req->ctx, req->user_data, -ECANCELED, 0);
io_commit_cqring(req->ctx);
req_set_fail_links(req);
io_put_req_deferred(req, 1);
@@ -5248,7 +5265,9 @@ static bool io_poll_remove_all(struct io_ring_ctx *ctx, struct task_struct *tsk,
return posted != 0;
}
-static int io_poll_cancel(struct io_ring_ctx *ctx, __u64 sqe_addr)
+static struct io_kiocb *io_poll_find(struct io_ring_ctx *ctx, __u64 sqe_addr,
+ bool poll_only)
+ __must_hold(&ctx->completion_lock)
{
struct hlist_head *list;
struct io_kiocb *req;
@@ -5257,43 +5276,72 @@ static int io_poll_cancel(struct io_ring_ctx *ctx, __u64 sqe_addr)
hlist_for_each_entry(req, list, hash_node) {
if (sqe_addr != req->user_data)
continue;
- if (io_poll_remove_one(req))
- return 0;
- return -EALREADY;
+ if (poll_only && req->opcode != IORING_OP_POLL_ADD)
+ continue;
+ return req;
}
+ return NULL;
+}
+
+static int io_poll_cancel(struct io_ring_ctx *ctx, __u64 sqe_addr,
+ bool poll_only)
+ __must_hold(&ctx->completion_lock)
+{
+ struct io_kiocb *req;
+
+ req = io_poll_find(ctx, sqe_addr, poll_only);
+ if (!req)
+ return -ENOENT;
+ if (io_poll_remove_one(req))
+ return 0;
+
+ return -EALREADY;
+}
+
+static __poll_t io_poll_parse_events(const struct io_uring_sqe *sqe,
+ unsigned int flags)
+{
+ u32 events;
- return -ENOENT;
+ events = READ_ONCE(sqe->poll32_events);
+#ifdef __BIG_ENDIAN
+ events = swahw32(events);
+#endif
+ if (!(flags & IORING_POLL_ADD_MULTI))
+ events |= EPOLLONESHOT;
+ return demangle_poll(events) | (events & (EPOLLEXCLUSIVE|EPOLLONESHOT));
}
-static int io_poll_remove_prep(struct io_kiocb *req,
+static int io_poll_update_prep(struct io_kiocb *req,
const struct io_uring_sqe *sqe)
{
+ struct io_poll_update *upd = &req->poll_update;
+ u32 flags;
+
if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL))
return -EINVAL;
- if (sqe->ioprio || sqe->off || sqe->len || sqe->buf_index ||
- sqe->poll_events)
+ if (sqe->ioprio || sqe->buf_index)
+ return -EINVAL;
+ flags = READ_ONCE(sqe->len);
+ if (flags & ~(IORING_POLL_UPDATE_EVENTS | IORING_POLL_UPDATE_USER_DATA |
+ IORING_POLL_ADD_MULTI))
+ return -EINVAL;
+ /* meaningless without update */
+ if (flags == IORING_POLL_ADD_MULTI)
return -EINVAL;
- req->poll_remove.addr = READ_ONCE(sqe->addr);
- return 0;
-}
-
-/*
- * Find a running poll command that matches one specified in sqe->addr,
- * and remove it if found.
- */
-static int io_poll_remove(struct io_kiocb *req, unsigned int issue_flags)
-{
- struct io_ring_ctx *ctx = req->ctx;
- int ret;
+ upd->old_user_data = READ_ONCE(sqe->addr);
+ upd->update_events = flags & IORING_POLL_UPDATE_EVENTS;
+ upd->update_user_data = flags & IORING_POLL_UPDATE_USER_DATA;
- spin_lock_irq(&ctx->completion_lock);
- ret = io_poll_cancel(ctx, req->poll_remove.addr);
- spin_unlock_irq(&ctx->completion_lock);
+ upd->new_user_data = READ_ONCE(sqe->off);
+ if (!upd->update_user_data && upd->new_user_data)
+ return -EINVAL;
+ if (upd->update_events)
+ upd->events = io_poll_parse_events(sqe, flags);
+ else if (sqe->poll32_events)
+ return -EINVAL;
- if (ret < 0)
- req_set_fail_links(req);
- io_req_complete(req, ret);
return 0;
}
@@ -5317,19 +5365,17 @@ static void io_poll_queue_proc(struct file *file, struct wait_queue_head *head,
static int io_poll_add_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
{
struct io_poll_iocb *poll = &req->poll;
- u32 events;
+ u32 flags;
if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL))
return -EINVAL;
- if (sqe->addr || sqe->ioprio || sqe->off || sqe->len || sqe->buf_index)
+ if (sqe->ioprio || sqe->buf_index || sqe->off || sqe->addr)
+ return -EINVAL;
+ flags = READ_ONCE(sqe->len);
+ if (flags & ~IORING_POLL_ADD_MULTI)
return -EINVAL;
- events = READ_ONCE(sqe->poll32_events);
-#ifdef __BIG_ENDIAN
- events = swahw32(events);
-#endif
- poll->events = demangle_poll(events) | EPOLLERR | EPOLLHUP |
- (events & EPOLLEXCLUSIVE);
+ poll->events = io_poll_parse_events(sqe, flags);
return 0;
}
@@ -5347,17 +5393,80 @@ static int io_poll_add(struct io_kiocb *req, unsigned int issue_flags)
if (mask) { /* no async, we'd stolen it */
ipt.error = 0;
- io_poll_complete(req, mask, 0);
+ io_poll_complete(req, mask);
}
spin_unlock_irq(&ctx->completion_lock);
if (mask) {
io_cqring_ev_posted(ctx);
- io_put_req(req);
+ if (poll->events & EPOLLONESHOT)
+ io_put_req(req);
}
return ipt.error;
}
+static int io_poll_update(struct io_kiocb *req, unsigned int issue_flags)
+{
+ struct io_ring_ctx *ctx = req->ctx;
+ struct io_kiocb *preq;
+ bool completing;
+ int ret;
+
+ spin_lock_irq(&ctx->completion_lock);
+ preq = io_poll_find(ctx, req->poll_update.old_user_data, true);
+ if (!preq) {
+ ret = -ENOENT;
+ goto err;
+ }
+
+ if (!req->poll_update.update_events && !req->poll_update.update_user_data) {
+ completing = true;
+ ret = io_poll_remove_one(preq) ? 0 : -EALREADY;
+ goto err;
+ }
+
+ /*
+ * Don't allow racy completion with singleshot, as we cannot safely
+ * update those. For multishot, if we're racing with completion, just
+ * let completion re-add it.
+ */
+ completing = !__io_poll_remove_one(preq, &preq->poll, false);
+ if (completing && (preq->poll.events & EPOLLONESHOT)) {
+ ret = -EALREADY;
+ goto err;
+ }
+ /* we now have a detached poll request. reissue. */
+ ret = 0;
+err:
+ if (ret < 0) {
+ spin_unlock_irq(&ctx->completion_lock);
+ req_set_fail_links(req);
+ io_req_complete(req, ret);
+ return 0;
+ }
+ /* only mask one event flags, keep behavior flags */
+ if (req->poll_update.update_events) {
+ preq->poll.events &= ~0xffff;
+ preq->poll.events |= req->poll_update.events & 0xffff;
+ preq->poll.events |= IO_POLL_UNMASK;
+ }
+ if (req->poll_update.update_user_data)
+ preq->user_data = req->poll_update.new_user_data;
+ spin_unlock_irq(&ctx->completion_lock);
+
+ /* complete update request, we're done with it */
+ io_req_complete(req, ret);
+
+ if (!completing) {
+ ret = io_poll_add(preq, issue_flags);
+ if (ret < 0) {
+ req_set_fail_links(preq);
+ io_req_complete(preq, ret);
+ }
+ }
+ return 0;
+}
+
static enum hrtimer_restart io_timeout_fn(struct hrtimer *timer)
{
struct io_timeout_data *data = container_of(timer,
@@ -5371,7 +5480,7 @@ static enum hrtimer_restart io_timeout_fn(struct hrtimer *timer)
atomic_set(&req->ctx->cq_timeouts,
atomic_read(&req->ctx->cq_timeouts) + 1);
- io_cqring_fill_event(req, -ETIME);
+ io_cqring_fill_event(ctx, req->user_data, -ETIME, 0);
io_commit_cqring(ctx);
spin_unlock_irqrestore(&ctx->completion_lock, flags);
@@ -5383,30 +5492,29 @@ static enum hrtimer_restart io_timeout_fn(struct hrtimer *timer)
static struct io_kiocb *io_timeout_extract(struct io_ring_ctx *ctx,
__u64 user_data)
+ __must_hold(&ctx->completion_lock)
{
struct io_timeout_data *io;
struct io_kiocb *req;
- int ret = -ENOENT;
+ bool found = false;
list_for_each_entry(req, &ctx->timeout_list, timeout.list) {
- if (user_data == req->user_data) {
- ret = 0;
+ found = user_data == req->user_data;
+ if (found)
break;
- }
}
-
- if (ret == -ENOENT)
- return ERR_PTR(ret);
+ if (!found)
+ return ERR_PTR(-ENOENT);
io = req->async_data;
- ret = hrtimer_try_to_cancel(&io->timer);
- if (ret == -1)
+ if (hrtimer_try_to_cancel(&io->timer) == -1)
return ERR_PTR(-EALREADY);
list_del_init(&req->timeout.list);
return req;
}
static int io_timeout_cancel(struct io_ring_ctx *ctx, __u64 user_data)
+ __must_hold(&ctx->completion_lock)
{
struct io_kiocb *req = io_timeout_extract(ctx, user_data);
@@ -5414,13 +5522,14 @@ static int io_timeout_cancel(struct io_ring_ctx *ctx, __u64 user_data)
return PTR_ERR(req);
req_set_fail_links(req);
- io_cqring_fill_event(req, -ECANCELED);
+ io_cqring_fill_event(ctx, req->user_data, -ECANCELED, 0);
io_put_req_deferred(req, 1);
return 0;
}
static int io_timeout_update(struct io_ring_ctx *ctx, __u64 user_data,
struct timespec64 *ts, enum hrtimer_mode mode)
+ __must_hold(&ctx->completion_lock)
{
struct io_kiocb *req = io_timeout_extract(ctx, user_data);
struct io_timeout_data *data;
@@ -5486,7 +5595,7 @@ static int io_timeout_remove(struct io_kiocb *req, unsigned int issue_flags)
ret = io_timeout_update(ctx, tr->addr, &tr->ts,
io_translate_timeout_mode(tr->flags));
- io_cqring_fill_event(req, ret);
+ io_cqring_fill_event(ctx, req->user_data, ret, 0);
io_commit_cqring(ctx);
spin_unlock_irq(&ctx->completion_lock);
io_cqring_ev_posted(ctx);
@@ -5526,7 +5635,8 @@ static int io_timeout_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe,
data->mode = io_translate_timeout_mode(flags);
hrtimer_init(&data->timer, CLOCK_MONOTONIC, data->mode);
- io_req_track_inflight(req);
+ if (is_timeout_link)
+ io_req_track_inflight(req);
return 0;
}
@@ -5627,27 +5737,23 @@ static void io_async_find_and_cancel(struct io_ring_ctx *ctx,
int ret;
ret = io_async_cancel_one(req->task->io_uring, sqe_addr, ctx);
- if (ret != -ENOENT) {
- spin_lock_irqsave(&ctx->completion_lock, flags);
- goto done;
- }
-
spin_lock_irqsave(&ctx->completion_lock, flags);
+ if (ret != -ENOENT)
+ goto done;
ret = io_timeout_cancel(ctx, sqe_addr);
if (ret != -ENOENT)
goto done;
- ret = io_poll_cancel(ctx, sqe_addr);
+ ret = io_poll_cancel(ctx, sqe_addr, false);
done:
if (!ret)
ret = success_ret;
- io_cqring_fill_event(req, ret);
+ io_cqring_fill_event(ctx, req->user_data, ret, 0);
io_commit_cqring(ctx);
spin_unlock_irqrestore(&ctx->completion_lock, flags);
io_cqring_ev_posted(ctx);
if (ret < 0)
req_set_fail_links(req);
- io_put_req(req);
}
static int io_async_cancel_prep(struct io_kiocb *req,
@@ -5679,7 +5785,7 @@ static int io_async_cancel(struct io_kiocb *req, unsigned int issue_flags)
ret = io_timeout_cancel(ctx, sqe_addr);
if (ret != -ENOENT)
goto done;
- ret = io_poll_cancel(ctx, sqe_addr);
+ ret = io_poll_cancel(ctx, sqe_addr, false);
if (ret != -ENOENT)
goto done;
spin_unlock_irq(&ctx->completion_lock);
@@ -5690,8 +5796,6 @@ static int io_async_cancel(struct io_kiocb *req, unsigned int issue_flags)
list_for_each_entry(node, &ctx->tctx_list, ctx_node) {
struct io_uring_task *tctx = node->task->io_uring;
- if (!tctx || !tctx->io_wq)
- continue;
ret = io_async_cancel_one(tctx, req->cancel.addr, ctx);
if (ret != -ENOENT)
break;
@@ -5700,7 +5804,7 @@ static int io_async_cancel(struct io_kiocb *req, unsigned int issue_flags)
spin_lock_irq(&ctx->completion_lock);
done:
- io_cqring_fill_event(req, ret);
+ io_cqring_fill_event(ctx, req->user_data, ret, 0);
io_commit_cqring(ctx);
spin_unlock_irq(&ctx->completion_lock);
io_cqring_ev_posted(ctx);
@@ -5732,7 +5836,7 @@ static int io_rsrc_update_prep(struct io_kiocb *req,
static int io_files_update(struct io_kiocb *req, unsigned int issue_flags)
{
struct io_ring_ctx *ctx = req->ctx;
- struct io_uring_rsrc_update up;
+ struct io_uring_rsrc_update2 up;
int ret;
if (issue_flags & IO_URING_F_NONBLOCK)
@@ -5740,9 +5844,13 @@ static int io_files_update(struct io_kiocb *req, unsigned int issue_flags)
up.offset = req->rsrc_update.offset;
up.data = req->rsrc_update.arg;
+ up.nr = 0;
+ up.tags = 0;
+ up.resv = 0;
mutex_lock(&ctx->uring_lock);
- ret = __io_sqe_files_update(ctx, &up, req->rsrc_update.nr_args);
+ ret = __io_register_rsrc_update(ctx, IORING_RSRC_FILE,
+ &up, req->rsrc_update.nr_args);
mutex_unlock(&ctx->uring_lock);
if (ret < 0)
@@ -5767,7 +5875,7 @@ static int io_req_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
case IORING_OP_POLL_ADD:
return io_poll_add_prep(req, sqe);
case IORING_OP_POLL_REMOVE:
- return io_poll_remove_prep(req, sqe);
+ return io_poll_update_prep(req, sqe);
case IORING_OP_FSYNC:
return io_fsync_prep(req, sqe);
case IORING_OP_SYNC_FILE_RANGE:
@@ -5826,42 +5934,33 @@ static int io_req_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
printk_once(KERN_WARNING "io_uring: unhandled opcode %d\n",
req->opcode);
- return-EINVAL;
+ return -EINVAL;
}
static int io_req_prep_async(struct io_kiocb *req)
{
+ if (!io_op_defs[req->opcode].needs_async_setup)
+ return 0;
+ if (WARN_ON_ONCE(req->async_data))
+ return -EFAULT;
+ if (io_alloc_async_data(req))
+ return -EAGAIN;
+
switch (req->opcode) {
case IORING_OP_READV:
- case IORING_OP_READ_FIXED:
- case IORING_OP_READ:
return io_rw_prep_async(req, READ);
case IORING_OP_WRITEV:
- case IORING_OP_WRITE_FIXED:
- case IORING_OP_WRITE:
return io_rw_prep_async(req, WRITE);
case IORING_OP_SENDMSG:
- case IORING_OP_SEND:
return io_sendmsg_prep_async(req);
case IORING_OP_RECVMSG:
- case IORING_OP_RECV:
return io_recvmsg_prep_async(req);
case IORING_OP_CONNECT:
return io_connect_prep_async(req);
}
- return 0;
-}
-
-static int io_req_defer_prep(struct io_kiocb *req)
-{
- if (!io_op_defs[req->opcode].needs_async_data)
- return 0;
- /* some opcodes init it during the inital prep */
- if (req->async_data)
- return 0;
- if (__io_alloc_async_data(req))
- return -EAGAIN;
- return io_req_prep_async(req);
+ printk_once(KERN_WARNING "io_uring: prep_async() bad opcode %d\n",
+ req->opcode);
+ return -EFAULT;
}
static u32 io_get_sequence(struct io_kiocb *req)
@@ -5894,7 +5993,7 @@ static int io_req_defer(struct io_kiocb *req)
if (!req_need_defer(req, seq) && list_empty_careful(&ctx->defer_list))
return 0;
- ret = io_req_defer_prep(req);
+ ret = io_req_prep_async(req);
if (ret)
return ret;
io_prep_async_link(req);
@@ -5918,7 +6017,7 @@ static int io_req_defer(struct io_kiocb *req)
return -EIOCBQUEUED;
}
-static void __io_clean_op(struct io_kiocb *req)
+static void io_clean_op(struct io_kiocb *req)
{
if (req->flags & REQ_F_BUFFER_SELECTED) {
switch (req->opcode) {
@@ -5957,8 +6056,8 @@ static void __io_clean_op(struct io_kiocb *req)
}
case IORING_OP_SPLICE:
case IORING_OP_TEE:
- io_put_file(req, req->splice.file_in,
- (req->splice.flags & SPLICE_F_FD_IN_FIXED));
+ if (!(req->splice.flags & SPLICE_F_FD_IN_FIXED))
+ io_put_file(req->splice.file_in);
break;
case IORING_OP_OPENAT:
case IORING_OP_OPENAT2:
@@ -5975,6 +6074,17 @@ static void __io_clean_op(struct io_kiocb *req)
}
req->flags &= ~REQ_F_NEED_CLEANUP;
}
+ if ((req->flags & REQ_F_POLLED) && req->apoll) {
+ kfree(req->apoll->double_poll);
+ kfree(req->apoll);
+ req->apoll = NULL;
+ }
+ if (req->flags & REQ_F_INFLIGHT) {
+ struct io_uring_task *tctx = req->task->io_uring;
+
+ atomic_dec(&tctx->inflight_tracked);
+ req->flags &= ~REQ_F_INFLIGHT;
+ }
}
static int io_issue_sqe(struct io_kiocb *req, unsigned int issue_flags)
@@ -6007,7 +6117,7 @@ static int io_issue_sqe(struct io_kiocb *req, unsigned int issue_flags)
ret = io_poll_add(req, issue_flags);
break;
case IORING_OP_POLL_REMOVE:
- ret = io_poll_remove(req, issue_flags);
+ ret = io_poll_update(req, issue_flags);
break;
case IORING_OP_SYNC_FILE_RANGE:
ret = io_sync_file_range(req, issue_flags);
@@ -6145,18 +6255,48 @@ static void io_wq_submit_work(struct io_wq_work *work)
/* avoid locking problems by failing it from a clean context */
if (ret) {
/* io-wq is going to take one down */
- refcount_inc(&req->refs);
+ req_ref_get(req);
io_req_task_queue_fail(req, ret);
}
}
+#define FFS_ASYNC_READ 0x1UL
+#define FFS_ASYNC_WRITE 0x2UL
+#ifdef CONFIG_64BIT
+#define FFS_ISREG 0x4UL
+#else
+#define FFS_ISREG 0x0UL
+#endif
+#define FFS_MASK ~(FFS_ASYNC_READ|FFS_ASYNC_WRITE|FFS_ISREG)
+
+static inline struct io_fixed_file *io_fixed_file_slot(struct io_file_table *table,
+ unsigned i)
+{
+ struct io_fixed_file *table_l2;
+
+ table_l2 = table->files[i >> IORING_FILE_TABLE_SHIFT];
+ return &table_l2[i & IORING_FILE_TABLE_MASK];
+}
+
static inline struct file *io_file_from_index(struct io_ring_ctx *ctx,
int index)
{
- struct fixed_rsrc_table *table;
+ struct io_fixed_file *slot = io_fixed_file_slot(&ctx->file_table, index);
- table = &ctx->file_data->table[index >> IORING_FILE_TABLE_SHIFT];
- return table->files[index & IORING_FILE_TABLE_MASK];
+ return (struct file *) (slot->file_ptr & FFS_MASK);
+}
+
+static void io_fixed_file_set(struct io_fixed_file *file_slot, struct file *file)
+{
+ unsigned long file_ptr = (unsigned long) file;
+
+ if (__io_file_supports_async(file, READ))
+ file_ptr |= FFS_ASYNC_READ;
+ if (__io_file_supports_async(file, WRITE))
+ file_ptr |= FFS_ASYNC_WRITE;
+ if (S_ISREG(file_inode(file)->i_mode))
+ file_ptr |= FFS_ISREG;
+ file_slot->file_ptr = file_ptr;
}
static struct file *io_file_get(struct io_submit_state *state,
@@ -6166,18 +6306,26 @@ static struct file *io_file_get(struct io_submit_state *state,
struct file *file;
if (fixed) {
+ unsigned long file_ptr;
+
if (unlikely((unsigned int)fd >= ctx->nr_user_files))
return NULL;
fd = array_index_nospec(fd, ctx->nr_user_files);
- file = io_file_from_index(ctx, fd);
- io_set_resource_node(req);
+ file_ptr = io_fixed_file_slot(&ctx->file_table, fd)->file_ptr;
+ file = (struct file *) (file_ptr & FFS_MASK);
+ file_ptr &= ~FFS_MASK;
+ /* mask in overlapping REQ_F and FFS bits */
+ req->flags |= (file_ptr << REQ_F_ASYNC_READ_BIT);
+ io_req_set_rsrc_node(req);
} else {
trace_io_uring_file_get(ctx, fd);
file = __io_file_get(state, fd);
+
+ /* we don't allow fixed io_uring files */
+ if (file && unlikely(file->f_op == &io_uring_fops))
+ io_req_track_inflight(req);
}
- if (file && unlikely(file->f_op == &io_uring_fops))
- io_req_track_inflight(req);
return file;
}
@@ -6197,25 +6345,27 @@ static enum hrtimer_restart io_link_timeout_fn(struct hrtimer *timer)
* We don't expect the list to be empty, that will only happen if we
* race with the completion of the linked work.
*/
- if (prev && refcount_inc_not_zero(&prev->refs))
+ if (prev && req_ref_inc_not_zero(prev))
io_remove_next_linked(prev);
else
prev = NULL;
spin_unlock_irqrestore(&ctx->completion_lock, flags);
if (prev) {
- req_set_fail_links(prev);
io_async_find_and_cancel(ctx, req, prev->user_data, -ETIME);
io_put_req_deferred(prev, 1);
} else {
io_req_complete_post(req, -ETIME, 0);
- io_put_req_deferred(req, 1);
}
+ io_put_req_deferred(req, 1);
return HRTIMER_NORESTART;
}
-static void __io_queue_linked_timeout(struct io_kiocb *req)
+static void io_queue_linked_timeout(struct io_kiocb *req)
{
+ struct io_ring_ctx *ctx = req->ctx;
+
+ spin_lock_irq(&ctx->completion_lock);
/*
* If the back reference is NULL, then our linked request finished
* before we got a chance to setup the timer
@@ -6227,16 +6377,7 @@ static void __io_queue_linked_timeout(struct io_kiocb *req)
hrtimer_start(&data->timer, timespec64_to_ktime(data->ts),
data->mode);
}
-}
-
-static void io_queue_linked_timeout(struct io_kiocb *req)
-{
- struct io_ring_ctx *ctx = req->ctx;
-
- spin_lock_irq(&ctx->completion_lock);
- __io_queue_linked_timeout(req);
spin_unlock_irq(&ctx->completion_lock);
-
/* drop submission reference */
io_put_req(req);
}
@@ -6266,15 +6407,7 @@ static void __io_queue_sqe(struct io_kiocb *req)
* We async punt it if the file wasn't marked NOWAIT, or if the file
* doesn't support non-blocking read/write attempts
*/
- if (ret == -EAGAIN && !(req->flags & REQ_F_NOWAIT)) {
- if (!io_arm_poll_handler(req)) {
- /*
- * Queued up for async execution, worker will release
- * submit reference when the iocb is actually submitted.
- */
- io_queue_async_work(req);
- }
- } else if (likely(!ret)) {
+ if (likely(!ret)) {
/* drop submission reference */
if (req->flags & REQ_F_COMPLETE_INLINE) {
struct io_ring_ctx *ctx = req->ctx;
@@ -6286,10 +6419,16 @@ static void __io_queue_sqe(struct io_kiocb *req)
} else {
io_put_req(req);
}
+ } else if (ret == -EAGAIN && !(req->flags & REQ_F_NOWAIT)) {
+ if (!io_arm_poll_handler(req)) {
+ /*
+ * Queued up for async execution, worker will release
+ * submit reference when the iocb is actually submitted.
+ */
+ io_queue_async_work(req);
+ }
} else {
- req_set_fail_links(req);
- io_put_req(req);
- io_req_complete(req, ret);
+ io_req_complete_failed(req, ret);
}
if (linked_timeout)
io_queue_linked_timeout(linked_timeout);
@@ -6303,12 +6442,10 @@ static void io_queue_sqe(struct io_kiocb *req)
if (ret) {
if (ret != -EIOCBQUEUED) {
fail_req:
- req_set_fail_links(req);
- io_put_req(req);
- io_req_complete(req, ret);
+ io_req_complete_failed(req, ret);
}
} else if (req->flags & REQ_F_FORCE_ASYNC) {
- ret = io_req_defer_prep(req);
+ ret = io_req_prep_async(req);
if (unlikely(ret))
goto fail_req;
io_queue_async_work(req);
@@ -6360,12 +6497,10 @@ static int io_init_req(struct io_ring_ctx *ctx, struct io_kiocb *req,
req->link = NULL;
req->fixed_rsrc_refs = NULL;
/* one is dropped after submission, the other at completion */
- refcount_set(&req->refs, 2);
+ atomic_set(&req->refs, 2);
req->task = current;
req->result = 0;
- req->work.list.next = NULL;
req->work.creds = NULL;
- req->work.flags = 0;
/* enforce forwards compatibility on users */
if (unlikely(sqe_flags & ~SQE_VALID_FLAGS)) {
@@ -6423,15 +6558,13 @@ static int io_submit_sqe(struct io_ring_ctx *ctx, struct io_kiocb *req,
ret = io_init_req(ctx, req, sqe);
if (unlikely(ret)) {
fail_req:
- io_put_req(req);
- io_req_complete(req, ret);
if (link->head) {
/* fail even hard links since we don't submit */
link->head->flags |= REQ_F_FAIL_LINK;
- io_put_req(link->head);
- io_req_complete(link->head, -ECANCELED);
+ io_req_complete_failed(link->head, -ECANCELED);
link->head = NULL;
}
+ io_req_complete_failed(req, ret);
return ret;
}
ret = io_req_prep(req, sqe);
@@ -6463,7 +6596,7 @@ fail_req:
head->flags |= REQ_F_IO_DRAIN;
ctx->drain_next = 1;
}
- ret = io_req_defer_prep(req);
+ ret = io_req_prep_async(req);
if (unlikely(ret))
goto fail_req;
trace_io_uring_link(ctx, req, head);
@@ -6565,12 +6698,6 @@ static int io_submit_sqes(struct io_ring_ctx *ctx, unsigned int nr)
{
int submitted = 0;
- /* if we have a backlog and couldn't flush it all, return BUSY */
- if (test_bit(0, &ctx->sq_check_overflow)) {
- if (!__io_cqring_overflow_flush(ctx, false, NULL, NULL))
- return -EBUSY;
- }
-
/* make sure SQ entry isn't read before tail */
nr = min3(nr, ctx->sq_entries, io_sqring_entries(ctx));
@@ -6651,6 +6778,10 @@ static int __io_sq_thread(struct io_ring_ctx *ctx, bool cap_entries)
if (!list_empty(&ctx->iopoll_list))
io_do_iopoll(ctx, &nr_events, 0);
+ /*
+ * Don't submit if refs are dying, good for io_uring_register(),
+ * but also it is relied upon by io_ring_exit_work()
+ */
if (to_submit && likely(!percpu_ref_is_dying(&ctx->refs)) &&
!(ctx->flags & IORING_SETUP_R_DISABLED))
ret = io_submit_sqes(ctx, to_submit);
@@ -6668,11 +6799,8 @@ static void io_sqd_update_thread_idle(struct io_sq_data *sqd)
struct io_ring_ctx *ctx;
unsigned sq_thread_idle = 0;
- list_for_each_entry(ctx, &sqd->ctx_list, sqd_list) {
- if (sq_thread_idle < ctx->sq_thread_idle)
- sq_thread_idle = ctx->sq_thread_idle;
- }
-
+ list_for_each_entry(ctx, &sqd->ctx_list, sqd_list)
+ sq_thread_idle = max(sq_thread_idle, ctx->sq_thread_idle);
sqd->sq_thread_idle = sq_thread_idle;
}
@@ -6684,9 +6812,8 @@ static int io_sq_thread(void *data)
char buf[TASK_COMM_LEN];
DEFINE_WAIT(wait);
- sprintf(buf, "iou-sqp-%d", sqd->task_pid);
+ snprintf(buf, sizeof(buf), "iou-sqp-%d", sqd->task_pid);
set_task_comm(current, buf);
- current->pf_io_worker = NULL;
if (sqd->sq_cpu != -1)
set_cpus_allowed_ptr(current, cpumask_of(sqd->sq_cpu));
@@ -6694,22 +6821,33 @@ static int io_sq_thread(void *data)
set_cpus_allowed_ptr(current, cpu_online_mask);
current->flags |= PF_NO_SETAFFINITY;
- down_read(&sqd->rw_lock);
+ mutex_lock(&sqd->lock);
+ /* a user may had exited before the thread started */
+ io_run_task_work_head(&sqd->park_task_work);
while (!test_bit(IO_SQ_THREAD_SHOULD_STOP, &sqd->state)) {
int ret;
bool cap_entries, sqt_spin, needs_sched;
- if (test_bit(IO_SQ_THREAD_SHOULD_PARK, &sqd->state)) {
- up_read(&sqd->rw_lock);
+ if (test_bit(IO_SQ_THREAD_SHOULD_PARK, &sqd->state) ||
+ signal_pending(current)) {
+ bool did_sig = false;
+
+ mutex_unlock(&sqd->lock);
+ if (signal_pending(current)) {
+ struct ksignal ksig;
+
+ did_sig = get_signal(&ksig);
+ }
cond_resched();
- down_read(&sqd->rw_lock);
+ mutex_lock(&sqd->lock);
io_run_task_work();
+ io_run_task_work_head(&sqd->park_task_work);
+ if (did_sig)
+ break;
timeout = jiffies + sqd->sq_thread_idle;
continue;
}
- if (fatal_signal_pending(current))
- break;
sqt_spin = false;
cap_entries = !list_is_singular(&sqd->ctx_list);
list_for_each_entry(ctx, &sqd->ctx_list, sqd_list) {
@@ -6732,50 +6870,46 @@ static int io_sq_thread(void *data)
continue;
}
- needs_sched = true;
prepare_to_wait(&sqd->wait, &wait, TASK_INTERRUPTIBLE);
- list_for_each_entry(ctx, &sqd->ctx_list, sqd_list) {
- if ((ctx->flags & IORING_SETUP_IOPOLL) &&
- !list_empty_careful(&ctx->iopoll_list)) {
- needs_sched = false;
- break;
- }
- if (io_sqring_entries(ctx)) {
- needs_sched = false;
- break;
- }
- }
-
- if (needs_sched && !test_bit(IO_SQ_THREAD_SHOULD_PARK, &sqd->state)) {
+ if (!test_bit(IO_SQ_THREAD_SHOULD_PARK, &sqd->state)) {
list_for_each_entry(ctx, &sqd->ctx_list, sqd_list)
io_ring_set_wakeup_flag(ctx);
- up_read(&sqd->rw_lock);
- schedule();
- down_read(&sqd->rw_lock);
+ needs_sched = true;
+ list_for_each_entry(ctx, &sqd->ctx_list, sqd_list) {
+ if ((ctx->flags & IORING_SETUP_IOPOLL) &&
+ !list_empty_careful(&ctx->iopoll_list)) {
+ needs_sched = false;
+ break;
+ }
+ if (io_sqring_entries(ctx)) {
+ needs_sched = false;
+ break;
+ }
+ }
+
+ if (needs_sched) {
+ mutex_unlock(&sqd->lock);
+ schedule();
+ mutex_lock(&sqd->lock);
+ }
list_for_each_entry(ctx, &sqd->ctx_list, sqd_list)
io_ring_clear_wakeup_flag(ctx);
}
finish_wait(&sqd->wait, &wait);
+ io_run_task_work_head(&sqd->park_task_work);
timeout = jiffies + sqd->sq_thread_idle;
}
- up_read(&sqd->rw_lock);
- down_write(&sqd->rw_lock);
- /*
- * someone may have parked and added a cancellation task_work, run
- * it first because we don't want it in io_uring_cancel_sqpoll()
- */
- io_run_task_work();
- list_for_each_entry(ctx, &sqd->ctx_list, sqd_list)
- io_uring_cancel_sqpoll(ctx);
+ io_uring_cancel_sqpoll(sqd);
sqd->thread = NULL;
list_for_each_entry(ctx, &sqd->ctx_list, sqd_list)
io_ring_set_wakeup_flag(ctx);
- up_write(&sqd->rw_lock);
-
io_run_task_work();
+ io_run_task_work_head(&sqd->park_task_work);
+ mutex_unlock(&sqd->lock);
+
complete(&sqd->exited);
do_exit(0);
}
@@ -6821,7 +6955,7 @@ static int io_run_task_work_sig(void)
return 1;
if (!signal_pending(current))
return 0;
- if (test_tsk_thread_flag(current, TIF_NOTIFY_SIGNAL))
+ if (test_thread_flag(TIF_NOTIFY_SIGNAL))
return -ERESTARTSYS;
return -EINTR;
}
@@ -6867,7 +7001,7 @@ static int io_cqring_wait(struct io_ring_ctx *ctx, int min_events,
int ret;
do {
- io_cqring_overflow_flush(ctx, false, NULL, NULL);
+ io_cqring_overflow_flush(ctx, false);
if (io_cqring_events(ctx) >= min_events)
return 0;
if (!io_run_task_work())
@@ -6899,7 +7033,7 @@ static int io_cqring_wait(struct io_ring_ctx *ctx, int min_events,
trace_io_uring_cqring_wait(ctx, min_events);
do {
/* if we can't even flush overflow, don't wait for more */
- if (!io_cqring_overflow_flush(ctx, false, NULL, NULL)) {
+ if (!io_cqring_overflow_flush(ctx, false)) {
ret = -EBUSY;
break;
}
@@ -6915,35 +7049,14 @@ static int io_cqring_wait(struct io_ring_ctx *ctx, int min_events,
return READ_ONCE(rings->cq.head) == READ_ONCE(rings->cq.tail) ? ret : 0;
}
-static void __io_sqe_files_unregister(struct io_ring_ctx *ctx)
+static void io_free_file_tables(struct io_file_table *table, unsigned nr_files)
{
-#if defined(CONFIG_UNIX)
- if (ctx->ring_sock) {
- struct sock *sock = ctx->ring_sock->sk;
- struct sk_buff *skb;
+ unsigned i, nr_tables = DIV_ROUND_UP(nr_files, IORING_MAX_FILES_TABLE);
- while ((skb = skb_dequeue(&sock->sk_receive_queue)) != NULL)
- kfree_skb(skb);
- }
-#else
- int i;
-
- for (i = 0; i < ctx->nr_user_files; i++) {
- struct file *file;
-
- file = io_file_from_index(ctx, i);
- if (file)
- fput(file);
- }
-#endif
-}
-
-static void io_rsrc_data_ref_zero(struct percpu_ref *ref)
-{
- struct fixed_rsrc_data *data;
-
- data = container_of(ref, struct fixed_rsrc_data, refs);
- complete(&data->done);
+ for (i = 0; i < nr_tables; i++)
+ kfree(table->files[i]);
+ kfree(table->files);
+ table->files = NULL;
}
static inline void io_rsrc_ref_lock(struct io_ring_ctx *ctx)
@@ -6956,142 +7069,173 @@ static inline void io_rsrc_ref_unlock(struct io_ring_ctx *ctx)
spin_unlock_bh(&ctx->rsrc_ref_lock);
}
-static void io_sqe_rsrc_set_node(struct io_ring_ctx *ctx,
- struct fixed_rsrc_data *rsrc_data,
- struct fixed_rsrc_ref_node *ref_node)
+static void io_rsrc_node_destroy(struct io_rsrc_node *ref_node)
{
- io_rsrc_ref_lock(ctx);
- rsrc_data->node = ref_node;
- list_add_tail(&ref_node->node, &ctx->rsrc_ref_list);
- io_rsrc_ref_unlock(ctx);
- percpu_ref_get(&rsrc_data->refs);
+ percpu_ref_exit(&ref_node->refs);
+ kfree(ref_node);
}
-static void io_sqe_rsrc_kill_node(struct io_ring_ctx *ctx, struct fixed_rsrc_data *data)
+static void io_rsrc_node_switch(struct io_ring_ctx *ctx,
+ struct io_rsrc_data *data_to_kill)
{
- struct fixed_rsrc_ref_node *ref_node = NULL;
+ WARN_ON_ONCE(!ctx->rsrc_backup_node);
+ WARN_ON_ONCE(data_to_kill && !ctx->rsrc_node);
- io_rsrc_ref_lock(ctx);
- ref_node = data->node;
- data->node = NULL;
- io_rsrc_ref_unlock(ctx);
- if (ref_node)
- percpu_ref_kill(&ref_node->refs);
+ if (data_to_kill) {
+ struct io_rsrc_node *rsrc_node = ctx->rsrc_node;
+
+ rsrc_node->rsrc_data = data_to_kill;
+ io_rsrc_ref_lock(ctx);
+ list_add_tail(&rsrc_node->node, &ctx->rsrc_ref_list);
+ io_rsrc_ref_unlock(ctx);
+
+ atomic_inc(&data_to_kill->refs);
+ percpu_ref_kill(&rsrc_node->refs);
+ ctx->rsrc_node = NULL;
+ }
+
+ if (!ctx->rsrc_node) {
+ ctx->rsrc_node = ctx->rsrc_backup_node;
+ ctx->rsrc_backup_node = NULL;
+ }
+}
+
+static int io_rsrc_node_switch_start(struct io_ring_ctx *ctx)
+{
+ if (ctx->rsrc_backup_node)
+ return 0;
+ ctx->rsrc_backup_node = io_rsrc_node_alloc(ctx);
+ return ctx->rsrc_backup_node ? 0 : -ENOMEM;
}
-static int io_rsrc_ref_quiesce(struct fixed_rsrc_data *data,
- struct io_ring_ctx *ctx,
- void (*rsrc_put)(struct io_ring_ctx *ctx,
- struct io_rsrc_put *prsrc))
+static int io_rsrc_ref_quiesce(struct io_rsrc_data *data, struct io_ring_ctx *ctx)
{
- struct fixed_rsrc_ref_node *backup_node;
int ret;
+ /* As we may drop ->uring_lock, other task may have started quiesce */
if (data->quiesce)
return -ENXIO;
data->quiesce = true;
do {
- ret = -ENOMEM;
- backup_node = alloc_fixed_rsrc_ref_node(ctx);
- if (!backup_node)
+ ret = io_rsrc_node_switch_start(ctx);
+ if (ret)
break;
- backup_node->rsrc_data = data;
- backup_node->rsrc_put = rsrc_put;
+ io_rsrc_node_switch(ctx, data);
- io_sqe_rsrc_kill_node(ctx, data);
- percpu_ref_kill(&data->refs);
+ /* kill initial ref, already quiesced if zero */
+ if (atomic_dec_and_test(&data->refs))
+ break;
flush_delayed_work(&ctx->rsrc_put_work);
-
ret = wait_for_completion_interruptible(&data->done);
if (!ret)
break;
- percpu_ref_resurrect(&data->refs);
- io_sqe_rsrc_set_node(ctx, data, backup_node);
- backup_node = NULL;
+ atomic_inc(&data->refs);
+ /* wait for all works potentially completing data->done */
+ flush_delayed_work(&ctx->rsrc_put_work);
reinit_completion(&data->done);
+
mutex_unlock(&ctx->uring_lock);
ret = io_run_task_work_sig();
mutex_lock(&ctx->uring_lock);
} while (ret >= 0);
data->quiesce = false;
- if (backup_node)
- destroy_fixed_rsrc_ref_node(backup_node);
return ret;
}
-static struct fixed_rsrc_data *alloc_fixed_rsrc_data(struct io_ring_ctx *ctx)
+static void io_rsrc_data_free(struct io_rsrc_data *data)
+{
+ kvfree(data->tags);
+ kfree(data);
+}
+
+static struct io_rsrc_data *io_rsrc_data_alloc(struct io_ring_ctx *ctx,
+ rsrc_put_fn *do_put,
+ unsigned nr)
{
- struct fixed_rsrc_data *data;
+ struct io_rsrc_data *data;
data = kzalloc(sizeof(*data), GFP_KERNEL);
if (!data)
return NULL;
- if (percpu_ref_init(&data->refs, io_rsrc_data_ref_zero,
- PERCPU_REF_ALLOW_REINIT, GFP_KERNEL)) {
+ data->tags = kvcalloc(nr, sizeof(*data->tags), GFP_KERNEL);
+ if (!data->tags) {
kfree(data);
return NULL;
}
+
+ atomic_set(&data->refs, 1);
data->ctx = ctx;
+ data->do_put = do_put;
init_completion(&data->done);
return data;
}
-static void free_fixed_rsrc_data(struct fixed_rsrc_data *data)
+static void __io_sqe_files_unregister(struct io_ring_ctx *ctx)
{
- percpu_ref_exit(&data->refs);
- kfree(data->table);
- kfree(data);
+#if defined(CONFIG_UNIX)
+ if (ctx->ring_sock) {
+ struct sock *sock = ctx->ring_sock->sk;
+ struct sk_buff *skb;
+
+ while ((skb = skb_dequeue(&sock->sk_receive_queue)) != NULL)
+ kfree_skb(skb);
+ }
+#else
+ int i;
+
+ for (i = 0; i < ctx->nr_user_files; i++) {
+ struct file *file;
+
+ file = io_file_from_index(ctx, i);
+ if (file)
+ fput(file);
+ }
+#endif
+ io_free_file_tables(&ctx->file_table, ctx->nr_user_files);
+ io_rsrc_data_free(ctx->file_data);
+ ctx->file_data = NULL;
+ ctx->nr_user_files = 0;
}
static int io_sqe_files_unregister(struct io_ring_ctx *ctx)
{
- struct fixed_rsrc_data *data = ctx->file_data;
- unsigned nr_tables, i;
int ret;
- /*
- * percpu_ref_is_dying() is to stop parallel files unregister
- * Since we possibly drop uring lock later in this function to
- * run task work.
- */
- if (!data || percpu_ref_is_dying(&data->refs))
+ if (!ctx->file_data)
return -ENXIO;
- ret = io_rsrc_ref_quiesce(data, ctx, io_ring_file_put);
- if (ret)
- return ret;
-
- __io_sqe_files_unregister(ctx);
- nr_tables = DIV_ROUND_UP(ctx->nr_user_files, IORING_MAX_FILES_TABLE);
- for (i = 0; i < nr_tables; i++)
- kfree(data->table[i].files);
- free_fixed_rsrc_data(data);
- ctx->file_data = NULL;
- ctx->nr_user_files = 0;
- return 0;
+ ret = io_rsrc_ref_quiesce(ctx->file_data, ctx);
+ if (!ret)
+ __io_sqe_files_unregister(ctx);
+ return ret;
}
static void io_sq_thread_unpark(struct io_sq_data *sqd)
- __releases(&sqd->rw_lock)
+ __releases(&sqd->lock)
{
WARN_ON_ONCE(sqd->thread == current);
+ /*
+ * Do the dance but not conditional clear_bit() because it'd race with
+ * other threads incrementing park_pending and setting the bit.
+ */
clear_bit(IO_SQ_THREAD_SHOULD_PARK, &sqd->state);
- up_write(&sqd->rw_lock);
+ if (atomic_dec_return(&sqd->park_pending))
+ set_bit(IO_SQ_THREAD_SHOULD_PARK, &sqd->state);
+ mutex_unlock(&sqd->lock);
}
static void io_sq_thread_park(struct io_sq_data *sqd)
- __acquires(&sqd->rw_lock)
+ __acquires(&sqd->lock)
{
WARN_ON_ONCE(sqd->thread == current);
+ atomic_inc(&sqd->park_pending);
set_bit(IO_SQ_THREAD_SHOULD_PARK, &sqd->state);
- down_write(&sqd->rw_lock);
- /* set again for consistency, in case concurrent parks are happening */
- set_bit(IO_SQ_THREAD_SHOULD_PARK, &sqd->state);
+ mutex_lock(&sqd->lock);
if (sqd->thread)
wake_up_process(sqd->thread);
}
@@ -7099,18 +7243,21 @@ static void io_sq_thread_park(struct io_sq_data *sqd)
static void io_sq_thread_stop(struct io_sq_data *sqd)
{
WARN_ON_ONCE(sqd->thread == current);
+ WARN_ON_ONCE(test_bit(IO_SQ_THREAD_SHOULD_STOP, &sqd->state));
- down_write(&sqd->rw_lock);
set_bit(IO_SQ_THREAD_SHOULD_STOP, &sqd->state);
+ mutex_lock(&sqd->lock);
if (sqd->thread)
wake_up_process(sqd->thread);
- up_write(&sqd->rw_lock);
+ mutex_unlock(&sqd->lock);
wait_for_completion(&sqd->exited);
}
static void io_put_sq_data(struct io_sq_data *sqd)
{
if (refcount_dec_and_test(&sqd->refs)) {
+ WARN_ON_ONCE(atomic_read(&sqd->park_pending));
+
io_sq_thread_stop(sqd);
kfree(sqd);
}
@@ -7128,8 +7275,6 @@ static void io_sq_thread_finish(struct io_ring_ctx *ctx)
io_put_sq_data(sqd);
ctx->sq_data = NULL;
- if (ctx->sq_creds)
- put_cred(ctx->sq_creds);
}
}
@@ -7184,9 +7329,10 @@ static struct io_sq_data *io_get_sq_data(struct io_uring_params *p,
if (!sqd)
return ERR_PTR(-ENOMEM);
+ atomic_set(&sqd->park_pending, 0);
refcount_set(&sqd->refs, 1);
INIT_LIST_HEAD(&sqd->ctx_list);
- init_rwsem(&sqd->rw_lock);
+ mutex_init(&sqd->lock);
init_waitqueue_head(&sqd->wait);
init_completion(&sqd->exited);
return sqd;
@@ -7289,34 +7435,32 @@ static int io_sqe_files_scm(struct io_ring_ctx *ctx)
}
#endif
-static int io_sqe_alloc_file_tables(struct fixed_rsrc_data *file_data,
- unsigned nr_tables, unsigned nr_files)
+static bool io_alloc_file_tables(struct io_file_table *table, unsigned nr_files)
{
- int i;
+ unsigned i, nr_tables = DIV_ROUND_UP(nr_files, IORING_MAX_FILES_TABLE);
+
+ table->files = kcalloc(nr_tables, sizeof(*table->files), GFP_KERNEL);
+ if (!table->files)
+ return false;
for (i = 0; i < nr_tables; i++) {
- struct fixed_rsrc_table *table = &file_data->table[i];
- unsigned this_files;
+ unsigned int this_files = min(nr_files, IORING_MAX_FILES_TABLE);
- this_files = min(nr_files, IORING_MAX_FILES_TABLE);
- table->files = kcalloc(this_files, sizeof(struct file *),
+ table->files[i] = kcalloc(this_files, sizeof(*table->files[i]),
GFP_KERNEL);
- if (!table->files)
+ if (!table->files[i])
break;
nr_files -= this_files;
}
if (i == nr_tables)
- return 0;
+ return true;
- for (i = 0; i < nr_tables; i++) {
- struct fixed_rsrc_table *table = &file_data->table[i];
- kfree(table->files);
- }
- return 1;
+ io_free_file_tables(table, nr_tables * IORING_MAX_FILES_TABLE);
+ return false;
}
-static void io_ring_file_put(struct io_ring_ctx *ctx, struct io_rsrc_put *prsrc)
+static void io_rsrc_file_put(struct io_ring_ctx *ctx, struct io_rsrc_put *prsrc)
{
struct file *file = prsrc->file;
#if defined(CONFIG_UNIX)
@@ -7379,21 +7523,35 @@ static void io_ring_file_put(struct io_ring_ctx *ctx, struct io_rsrc_put *prsrc)
#endif
}
-static void __io_rsrc_put_work(struct fixed_rsrc_ref_node *ref_node)
+static void __io_rsrc_put_work(struct io_rsrc_node *ref_node)
{
- struct fixed_rsrc_data *rsrc_data = ref_node->rsrc_data;
+ struct io_rsrc_data *rsrc_data = ref_node->rsrc_data;
struct io_ring_ctx *ctx = rsrc_data->ctx;
struct io_rsrc_put *prsrc, *tmp;
list_for_each_entry_safe(prsrc, tmp, &ref_node->rsrc_list, list) {
list_del(&prsrc->list);
- ref_node->rsrc_put(ctx, prsrc);
+
+ if (prsrc->tag) {
+ bool lock_ring = ctx->flags & IORING_SETUP_IOPOLL;
+ unsigned long flags;
+
+ io_ring_submit_lock(ctx, lock_ring);
+ spin_lock_irqsave(&ctx->completion_lock, flags);
+ io_cqring_fill_event(ctx, prsrc->tag, 0, 0);
+ io_commit_cqring(ctx);
+ spin_unlock_irqrestore(&ctx->completion_lock, flags);
+ io_cqring_ev_posted(ctx);
+ io_ring_submit_unlock(ctx, lock_ring);
+ }
+
+ rsrc_data->do_put(ctx, prsrc);
kfree(prsrc);
}
- percpu_ref_exit(&ref_node->refs);
- kfree(ref_node);
- percpu_ref_put(&rsrc_data->refs);
+ io_rsrc_node_destroy(ref_node);
+ if (atomic_dec_and_test(&rsrc_data->refs))
+ complete(&rsrc_data->done);
}
static void io_rsrc_put_work(struct work_struct *work)
@@ -7405,63 +7563,42 @@ static void io_rsrc_put_work(struct work_struct *work)
node = llist_del_all(&ctx->rsrc_put_llist);
while (node) {
- struct fixed_rsrc_ref_node *ref_node;
+ struct io_rsrc_node *ref_node;
struct llist_node *next = node->next;
- ref_node = llist_entry(node, struct fixed_rsrc_ref_node, llist);
+ ref_node = llist_entry(node, struct io_rsrc_node, llist);
__io_rsrc_put_work(ref_node);
node = next;
}
}
-static struct file **io_fixed_file_slot(struct fixed_rsrc_data *file_data,
- unsigned i)
-{
- struct fixed_rsrc_table *table;
-
- table = &file_data->table[i >> IORING_FILE_TABLE_SHIFT];
- return &table->files[i & IORING_FILE_TABLE_MASK];
-}
-
static void io_rsrc_node_ref_zero(struct percpu_ref *ref)
{
- struct fixed_rsrc_ref_node *ref_node;
- struct fixed_rsrc_data *data;
- struct io_ring_ctx *ctx;
+ struct io_rsrc_node *node = container_of(ref, struct io_rsrc_node, refs);
+ struct io_ring_ctx *ctx = node->rsrc_data->ctx;
bool first_add = false;
- int delay = HZ;
-
- ref_node = container_of(ref, struct fixed_rsrc_ref_node, refs);
- data = ref_node->rsrc_data;
- ctx = data->ctx;
io_rsrc_ref_lock(ctx);
- ref_node->done = true;
+ node->done = true;
while (!list_empty(&ctx->rsrc_ref_list)) {
- ref_node = list_first_entry(&ctx->rsrc_ref_list,
- struct fixed_rsrc_ref_node, node);
+ node = list_first_entry(&ctx->rsrc_ref_list,
+ struct io_rsrc_node, node);
/* recycle ref nodes in order */
- if (!ref_node->done)
+ if (!node->done)
break;
- list_del(&ref_node->node);
- first_add |= llist_add(&ref_node->llist, &ctx->rsrc_put_llist);
+ list_del(&node->node);
+ first_add |= llist_add(&node->llist, &ctx->rsrc_put_llist);
}
io_rsrc_ref_unlock(ctx);
- if (percpu_ref_is_dying(&data->refs))
- delay = 0;
-
- if (!delay)
- mod_delayed_work(system_wq, &ctx->rsrc_put_work, 0);
- else if (first_add)
- queue_delayed_work(system_wq, &ctx->rsrc_put_work, delay);
+ if (first_add)
+ mod_delayed_work(system_wq, &ctx->rsrc_put_work, HZ);
}
-static struct fixed_rsrc_ref_node *alloc_fixed_rsrc_ref_node(
- struct io_ring_ctx *ctx)
+static struct io_rsrc_node *io_rsrc_node_alloc(struct io_ring_ctx *ctx)
{
- struct fixed_rsrc_ref_node *ref_node;
+ struct io_rsrc_node *ref_node;
ref_node = kzalloc(sizeof(*ref_node), GFP_KERNEL);
if (!ref_node)
@@ -7478,29 +7615,14 @@ static struct fixed_rsrc_ref_node *alloc_fixed_rsrc_ref_node(
return ref_node;
}
-static void init_fixed_file_ref_node(struct io_ring_ctx *ctx,
- struct fixed_rsrc_ref_node *ref_node)
-{
- ref_node->rsrc_data = ctx->file_data;
- ref_node->rsrc_put = io_ring_file_put;
-}
-
-static void destroy_fixed_rsrc_ref_node(struct fixed_rsrc_ref_node *ref_node)
-{
- percpu_ref_exit(&ref_node->refs);
- kfree(ref_node);
-}
-
-
static int io_sqe_files_register(struct io_ring_ctx *ctx, void __user *arg,
- unsigned nr_args)
+ unsigned nr_args, u64 __user *tags)
{
__s32 __user *fds = (__s32 __user *) arg;
- unsigned nr_tables, i;
struct file *file;
- int fd, ret = -ENOMEM;
- struct fixed_rsrc_ref_node *ref_node;
- struct fixed_rsrc_data *file_data;
+ int fd, ret;
+ unsigned i;
+ struct io_rsrc_data *file_data;
if (ctx->file_data)
return -EBUSY;
@@ -7508,33 +7630,37 @@ static int io_sqe_files_register(struct io_ring_ctx *ctx, void __user *arg,
return -EINVAL;
if (nr_args > IORING_MAX_FIXED_FILES)
return -EMFILE;
+ ret = io_rsrc_node_switch_start(ctx);
+ if (ret)
+ return ret;
- file_data = alloc_fixed_rsrc_data(ctx);
+ file_data = io_rsrc_data_alloc(ctx, io_rsrc_file_put, nr_args);
if (!file_data)
return -ENOMEM;
ctx->file_data = file_data;
-
- nr_tables = DIV_ROUND_UP(nr_args, IORING_MAX_FILES_TABLE);
- file_data->table = kcalloc(nr_tables, sizeof(*file_data->table),
- GFP_KERNEL);
- if (!file_data->table)
- goto out_free;
-
- if (io_sqe_alloc_file_tables(file_data, nr_tables, nr_args))
+ ret = -ENOMEM;
+ if (!io_alloc_file_tables(&ctx->file_table, nr_args))
goto out_free;
for (i = 0; i < nr_args; i++, ctx->nr_user_files++) {
- if (copy_from_user(&fd, &fds[i], sizeof(fd))) {
+ u64 tag = 0;
+
+ if ((tags && copy_from_user(&tag, &tags[i], sizeof(tag))) ||
+ copy_from_user(&fd, &fds[i], sizeof(fd))) {
ret = -EFAULT;
goto out_fput;
}
/* allow sparse sets */
- if (fd == -1)
+ if (fd == -1) {
+ ret = -EINVAL;
+ if (unlikely(tag))
+ goto out_fput;
continue;
+ }
file = fget(fd);
ret = -EBADF;
- if (!file)
+ if (unlikely(!file))
goto out_fput;
/*
@@ -7548,23 +7674,17 @@ static int io_sqe_files_register(struct io_ring_ctx *ctx, void __user *arg,
fput(file);
goto out_fput;
}
- *io_fixed_file_slot(file_data, i) = file;
+ ctx->file_data->tags[i] = tag;
+ io_fixed_file_set(io_fixed_file_slot(&ctx->file_table, i), file);
}
ret = io_sqe_files_scm(ctx);
if (ret) {
- io_sqe_files_unregister(ctx);
+ __io_sqe_files_unregister(ctx);
return ret;
}
- ref_node = alloc_fixed_rsrc_ref_node(ctx);
- if (!ref_node) {
- io_sqe_files_unregister(ctx);
- return -ENOMEM;
- }
- init_fixed_file_ref_node(ctx, ref_node);
-
- io_sqe_rsrc_set_node(ctx, file_data, ref_node);
+ io_rsrc_node_switch(ctx, NULL);
return ret;
out_fput:
for (i = 0; i < ctx->nr_user_files; i++) {
@@ -7572,11 +7692,10 @@ out_fput:
if (file)
fput(file);
}
- for (i = 0; i < nr_tables; i++)
- kfree(file_data->table[i].files);
+ io_free_file_tables(&ctx->file_table, nr_args);
ctx->nr_user_files = 0;
out_free:
- free_fixed_rsrc_data(ctx->file_data);
+ io_rsrc_data_free(ctx->file_data);
ctx->file_data = NULL;
return ret;
}
@@ -7624,67 +7743,64 @@ static int io_sqe_file_register(struct io_ring_ctx *ctx, struct file *file,
#endif
}
-static int io_queue_rsrc_removal(struct fixed_rsrc_data *data, void *rsrc)
+static int io_queue_rsrc_removal(struct io_rsrc_data *data, unsigned idx,
+ struct io_rsrc_node *node, void *rsrc)
{
struct io_rsrc_put *prsrc;
- struct fixed_rsrc_ref_node *ref_node = data->node;
prsrc = kzalloc(sizeof(*prsrc), GFP_KERNEL);
if (!prsrc)
return -ENOMEM;
+ prsrc->tag = data->tags[idx];
prsrc->rsrc = rsrc;
- list_add(&prsrc->list, &ref_node->rsrc_list);
-
+ list_add(&prsrc->list, &node->rsrc_list);
return 0;
}
-static inline int io_queue_file_removal(struct fixed_rsrc_data *data,
- struct file *file)
-{
- return io_queue_rsrc_removal(data, (void *)file);
-}
-
static int __io_sqe_files_update(struct io_ring_ctx *ctx,
- struct io_uring_rsrc_update *up,
+ struct io_uring_rsrc_update2 *up,
unsigned nr_args)
{
- struct fixed_rsrc_data *data = ctx->file_data;
- struct fixed_rsrc_ref_node *ref_node;
- struct file *file, **file_slot;
- __s32 __user *fds;
- int fd, i, err;
- __u32 done;
+ u64 __user *tags = u64_to_user_ptr(up->tags);
+ __s32 __user *fds = u64_to_user_ptr(up->data);
+ struct io_rsrc_data *data = ctx->file_data;
+ struct io_fixed_file *file_slot;
+ struct file *file;
+ int fd, i, err = 0;
+ unsigned int done;
bool needs_switch = false;
- if (check_add_overflow(up->offset, nr_args, &done))
- return -EOVERFLOW;
- if (done > ctx->nr_user_files)
+ if (!ctx->file_data)
+ return -ENXIO;
+ if (up->offset + nr_args > ctx->nr_user_files)
return -EINVAL;
- ref_node = alloc_fixed_rsrc_ref_node(ctx);
- if (!ref_node)
- return -ENOMEM;
- init_fixed_file_ref_node(ctx, ref_node);
-
- fds = u64_to_user_ptr(up->data);
for (done = 0; done < nr_args; done++) {
- err = 0;
- if (copy_from_user(&fd, &fds[done], sizeof(fd))) {
+ u64 tag = 0;
+
+ if ((tags && copy_from_user(&tag, &tags[done], sizeof(tag))) ||
+ copy_from_user(&fd, &fds[done], sizeof(fd))) {
err = -EFAULT;
break;
}
+ if ((fd == IORING_REGISTER_FILES_SKIP || fd == -1) && tag) {
+ err = -EINVAL;
+ break;
+ }
if (fd == IORING_REGISTER_FILES_SKIP)
continue;
i = array_index_nospec(up->offset + done, ctx->nr_user_files);
- file_slot = io_fixed_file_slot(ctx->file_data, i);
+ file_slot = io_fixed_file_slot(&ctx->file_table, i);
- if (*file_slot) {
- err = io_queue_file_removal(data, *file_slot);
+ if (file_slot->file_ptr) {
+ file = (struct file *)(file_slot->file_ptr & FFS_MASK);
+ err = io_queue_rsrc_removal(data, up->offset + done,
+ ctx->rsrc_node, file);
if (err)
break;
- *file_slot = NULL;
+ file_slot->file_ptr = 0;
needs_switch = true;
}
if (fd != -1) {
@@ -7706,42 +7822,22 @@ static int __io_sqe_files_update(struct io_ring_ctx *ctx,
err = -EBADF;
break;
}
- *file_slot = file;
+ data->tags[up->offset + done] = tag;
+ io_fixed_file_set(file_slot, file);
err = io_sqe_file_register(ctx, file, i);
if (err) {
- *file_slot = NULL;
+ file_slot->file_ptr = 0;
fput(file);
break;
}
}
}
- if (needs_switch) {
- percpu_ref_kill(&data->node->refs);
- io_sqe_rsrc_set_node(ctx, data, ref_node);
- } else
- destroy_fixed_rsrc_ref_node(ref_node);
-
+ if (needs_switch)
+ io_rsrc_node_switch(ctx, data);
return done ? done : err;
}
-static int io_sqe_files_update(struct io_ring_ctx *ctx, void __user *arg,
- unsigned nr_args)
-{
- struct io_uring_rsrc_update up;
-
- if (!ctx->file_data)
- return -ENXIO;
- if (!nr_args)
- return -EINVAL;
- if (copy_from_user(&up, arg, sizeof(up)))
- return -EFAULT;
- if (up.resv)
- return -EINVAL;
-
- return __io_sqe_files_update(ctx, &up, nr_args);
-}
-
static struct io_wq_work *io_free_work(struct io_wq_work *work)
{
struct io_kiocb *req = container_of(work, struct io_kiocb, work);
@@ -7750,7 +7846,8 @@ static struct io_wq_work *io_free_work(struct io_wq_work *work)
return req ? &req->work : NULL;
}
-static struct io_wq *io_init_wq_offload(struct io_ring_ctx *ctx)
+static struct io_wq *io_init_wq_offload(struct io_ring_ctx *ctx,
+ struct task_struct *task)
{
struct io_wq_hash *hash;
struct io_wq_data data;
@@ -7767,6 +7864,7 @@ static struct io_wq *io_init_wq_offload(struct io_ring_ctx *ctx)
}
data.hash = hash;
+ data.task = task;
data.free_work = io_free_work;
data.do_work = io_wq_submit_work;
@@ -7792,7 +7890,7 @@ static int io_uring_alloc_task_context(struct task_struct *task,
return ret;
}
- tctx->io_wq = io_init_wq_offload(ctx);
+ tctx->io_wq = io_init_wq_offload(ctx, task);
if (IS_ERR(tctx->io_wq)) {
ret = PTR_ERR(tctx->io_wq);
percpu_counter_destroy(&tctx->inflight);
@@ -7804,6 +7902,7 @@ static int io_uring_alloc_task_context(struct task_struct *task,
init_waitqueue_head(&tctx->wait);
tctx->last = NULL;
atomic_set(&tctx->in_idle, 0);
+ atomic_set(&tctx->inflight_tracked, 0);
task->io_uring = tctx;
spin_lock_init(&tctx->task_lock);
INIT_WQ_LIST(&tctx->task_list);
@@ -7837,21 +7936,15 @@ static int io_sq_offload_create(struct io_ring_ctx *ctx,
f = fdget(p->wq_fd);
if (!f.file)
return -ENXIO;
- if (f.file->f_op != &io_uring_fops) {
- fdput(f);
- return -EINVAL;
- }
fdput(f);
+ if (f.file->f_op != &io_uring_fops)
+ return -EINVAL;
}
if (ctx->flags & IORING_SETUP_SQPOLL) {
struct task_struct *tsk;
struct io_sq_data *sqd;
bool attached;
- ret = -EPERM;
- if (!capable(CAP_SYS_ADMIN) && !capable(CAP_SYS_NICE))
- goto err;
-
sqd = io_get_sq_data(p, &attached);
if (IS_ERR(sqd)) {
ret = PTR_ERR(sqd);
@@ -7864,34 +7957,24 @@ static int io_sq_offload_create(struct io_ring_ctx *ctx,
if (!ctx->sq_thread_idle)
ctx->sq_thread_idle = HZ;
- ret = 0;
io_sq_thread_park(sqd);
+ list_add(&ctx->sqd_list, &sqd->ctx_list);
+ io_sqd_update_thread_idle(sqd);
/* don't attach to a dying SQPOLL thread, would be racy */
- if (attached && !sqd->thread) {
- ret = -ENXIO;
- } else {
- list_add(&ctx->sqd_list, &sqd->ctx_list);
- io_sqd_update_thread_idle(sqd);
- }
+ ret = (attached && !sqd->thread) ? -ENXIO : 0;
io_sq_thread_unpark(sqd);
- if (ret < 0) {
- io_put_sq_data(sqd);
- ctx->sq_data = NULL;
- return ret;
- } else if (attached) {
+ if (ret < 0)
+ goto err;
+ if (attached)
return 0;
- }
if (p->flags & IORING_SETUP_SQ_AFF) {
int cpu = p->sq_thread_cpu;
ret = -EINVAL;
- if (cpu >= nr_cpu_ids)
+ if (cpu >= nr_cpu_ids || !cpu_online(cpu))
goto err_sqpoll;
- if (!cpu_online(cpu))
- goto err_sqpoll;
-
sqd->sq_cpu = cpu;
} else {
sqd->sq_cpu = -1;
@@ -7917,12 +8000,11 @@ static int io_sq_offload_create(struct io_ring_ctx *ctx,
}
return 0;
+err_sqpoll:
+ complete(&ctx->sq_data->exited);
err:
io_sq_thread_finish(ctx);
return ret;
-err_sqpoll:
- complete(&ctx->sq_data->exited);
- goto err;
}
static inline void __io_unaccount_mem(struct user_struct *user,
@@ -8024,29 +8106,49 @@ static unsigned long rings_size(unsigned sq_entries, unsigned cq_entries,
return off;
}
-static int io_sqe_buffers_unregister(struct io_ring_ctx *ctx)
+static void io_buffer_unmap(struct io_ring_ctx *ctx, struct io_mapped_ubuf **slot)
{
- int i, j;
+ struct io_mapped_ubuf *imu = *slot;
+ unsigned int i;
- if (!ctx->user_bufs)
- return -ENXIO;
-
- for (i = 0; i < ctx->nr_user_bufs; i++) {
- struct io_mapped_ubuf *imu = &ctx->user_bufs[i];
+ for (i = 0; i < imu->nr_bvecs; i++)
+ unpin_user_page(imu->bvec[i].bv_page);
+ if (imu->acct_pages)
+ io_unaccount_mem(ctx, imu->acct_pages);
+ kvfree(imu);
+ *slot = NULL;
+}
- for (j = 0; j < imu->nr_bvecs; j++)
- unpin_user_page(imu->bvec[j].bv_page);
+static void io_rsrc_buf_put(struct io_ring_ctx *ctx, struct io_rsrc_put *prsrc)
+{
+ io_buffer_unmap(ctx, &prsrc->buf);
+ prsrc->buf = NULL;
+}
- if (imu->acct_pages)
- io_unaccount_mem(ctx, imu->acct_pages);
- kvfree(imu->bvec);
- imu->nr_bvecs = 0;
- }
+static void __io_sqe_buffers_unregister(struct io_ring_ctx *ctx)
+{
+ unsigned int i;
+ for (i = 0; i < ctx->nr_user_bufs; i++)
+ io_buffer_unmap(ctx, &ctx->user_bufs[i]);
kfree(ctx->user_bufs);
+ kfree(ctx->buf_data);
ctx->user_bufs = NULL;
+ ctx->buf_data = NULL;
ctx->nr_user_bufs = 0;
- return 0;
+}
+
+static int io_sqe_buffers_unregister(struct io_ring_ctx *ctx)
+{
+ int ret;
+
+ if (!ctx->buf_data)
+ return -ENXIO;
+
+ ret = io_rsrc_ref_quiesce(ctx->buf_data, ctx);
+ if (!ret)
+ __io_sqe_buffers_unregister(ctx);
+ return ret;
}
static int io_copy_iov(struct io_ring_ctx *ctx, struct iovec *dst,
@@ -8098,7 +8200,7 @@ static bool headpage_already_acct(struct io_ring_ctx *ctx, struct page **pages,
/* check previously registered pages */
for (i = 0; i < ctx->nr_user_bufs; i++) {
- struct io_mapped_ubuf *imu = &ctx->user_bufs[i];
+ struct io_mapped_ubuf *imu = ctx->user_bufs[i];
for (j = 0; j < imu->nr_bvecs; j++) {
if (!PageCompound(imu->bvec[j].bv_page))
@@ -8143,9 +8245,10 @@ static int io_buffer_account_pin(struct io_ring_ctx *ctx, struct page **pages,
}
static int io_sqe_buffer_register(struct io_ring_ctx *ctx, struct iovec *iov,
- struct io_mapped_ubuf *imu,
+ struct io_mapped_ubuf **pimu,
struct page **last_hpage)
{
+ struct io_mapped_ubuf *imu = NULL;
struct vm_area_struct **vmas = NULL;
struct page **pages = NULL;
unsigned long off, start, end, ubuf;
@@ -8157,6 +8260,7 @@ static int io_sqe_buffer_register(struct io_ring_ctx *ctx, struct iovec *iov,
start = ubuf >> PAGE_SHIFT;
nr_pages = end - start;
+ *pimu = NULL;
ret = -ENOMEM;
pages = kvmalloc_array(nr_pages, sizeof(struct page *), GFP_KERNEL);
@@ -8168,9 +8272,8 @@ static int io_sqe_buffer_register(struct io_ring_ctx *ctx, struct iovec *iov,
if (!vmas)
goto done;
- imu->bvec = kvmalloc_array(nr_pages, sizeof(struct bio_vec),
- GFP_KERNEL);
- if (!imu->bvec)
+ imu = kvmalloc(struct_size(imu, bvec, nr_pages), GFP_KERNEL);
+ if (!imu)
goto done;
ret = 0;
@@ -8199,14 +8302,12 @@ static int io_sqe_buffer_register(struct io_ring_ctx *ctx, struct iovec *iov,
*/
if (pret > 0)
unpin_user_pages(pages, pret);
- kvfree(imu->bvec);
goto done;
}
ret = io_buffer_account_pin(ctx, pages, pret, imu, last_hpage);
if (ret) {
unpin_user_pages(pages, pret);
- kvfree(imu->bvec);
goto done;
}
@@ -8224,10 +8325,13 @@ static int io_sqe_buffer_register(struct io_ring_ctx *ctx, struct iovec *iov,
}
/* store original address for later verification */
imu->ubuf = ubuf;
- imu->len = iov->iov_len;
+ imu->ubuf_end = ubuf + iov->iov_len;
imu->nr_bvecs = nr_pages;
+ *pimu = imu;
ret = 0;
done:
+ if (ret)
+ kvfree(imu);
kvfree(pages);
kvfree(vmas);
return ret;
@@ -8235,21 +8339,14 @@ done:
static int io_buffers_map_alloc(struct io_ring_ctx *ctx, unsigned int nr_args)
{
- if (ctx->user_bufs)
- return -EBUSY;
- if (!nr_args || nr_args > UIO_MAXIOV)
- return -EINVAL;
-
- ctx->user_bufs = kcalloc(nr_args, sizeof(struct io_mapped_ubuf),
- GFP_KERNEL);
- if (!ctx->user_bufs)
- return -ENOMEM;
-
- return 0;
+ ctx->user_bufs = kcalloc(nr_args, sizeof(*ctx->user_bufs), GFP_KERNEL);
+ return ctx->user_bufs ? 0 : -ENOMEM;
}
static int io_buffer_validate(struct iovec *iov)
{
+ unsigned long tmp, acct_len = iov->iov_len + (PAGE_SIZE - 1);
+
/*
* Don't impose further limits on the size and buffer
* constraints here, we'll -EINVAL later when IO is
@@ -8262,44 +8359,123 @@ static int io_buffer_validate(struct iovec *iov)
if (iov->iov_len > SZ_1G)
return -EFAULT;
+ if (check_add_overflow((unsigned long)iov->iov_base, acct_len, &tmp))
+ return -EOVERFLOW;
+
return 0;
}
static int io_sqe_buffers_register(struct io_ring_ctx *ctx, void __user *arg,
- unsigned int nr_args)
+ unsigned int nr_args, u64 __user *tags)
{
+ struct page *last_hpage = NULL;
+ struct io_rsrc_data *data;
int i, ret;
struct iovec iov;
- struct page *last_hpage = NULL;
- ret = io_buffers_map_alloc(ctx, nr_args);
+ if (ctx->user_bufs)
+ return -EBUSY;
+ if (!nr_args || nr_args > UIO_MAXIOV)
+ return -EINVAL;
+ ret = io_rsrc_node_switch_start(ctx);
if (ret)
return ret;
+ data = io_rsrc_data_alloc(ctx, io_rsrc_buf_put, nr_args);
+ if (!data)
+ return -ENOMEM;
+ ret = io_buffers_map_alloc(ctx, nr_args);
+ if (ret) {
+ kfree(data);
+ return ret;
+ }
- for (i = 0; i < nr_args; i++) {
- struct io_mapped_ubuf *imu = &ctx->user_bufs[i];
+ for (i = 0; i < nr_args; i++, ctx->nr_user_bufs++) {
+ u64 tag = 0;
+ if (tags && copy_from_user(&tag, &tags[i], sizeof(tag))) {
+ ret = -EFAULT;
+ break;
+ }
ret = io_copy_iov(ctx, &iov, arg, i);
if (ret)
break;
-
ret = io_buffer_validate(&iov);
if (ret)
break;
- ret = io_sqe_buffer_register(ctx, &iov, imu, &last_hpage);
+ ret = io_sqe_buffer_register(ctx, &iov, &ctx->user_bufs[i],
+ &last_hpage);
if (ret)
break;
-
- ctx->nr_user_bufs++;
+ data->tags[i] = tag;
}
- if (ret)
- io_sqe_buffers_unregister(ctx);
+ WARN_ON_ONCE(ctx->buf_data);
+ ctx->buf_data = data;
+ if (ret)
+ __io_sqe_buffers_unregister(ctx);
+ else
+ io_rsrc_node_switch(ctx, NULL);
return ret;
}
+static int __io_sqe_buffers_update(struct io_ring_ctx *ctx,
+ struct io_uring_rsrc_update2 *up,
+ unsigned int nr_args)
+{
+ u64 __user *tags = u64_to_user_ptr(up->tags);
+ struct iovec iov, __user *iovs = u64_to_user_ptr(up->data);
+ struct page *last_hpage = NULL;
+ bool needs_switch = false;
+ __u32 done;
+ int i, err;
+
+ if (!ctx->buf_data)
+ return -ENXIO;
+ if (up->offset + nr_args > ctx->nr_user_bufs)
+ return -EINVAL;
+
+ for (done = 0; done < nr_args; done++) {
+ struct io_mapped_ubuf *imu;
+ int offset = up->offset + done;
+ u64 tag = 0;
+
+ err = io_copy_iov(ctx, &iov, iovs, done);
+ if (err)
+ break;
+ if (tags && copy_from_user(&tag, &tags[done], sizeof(tag))) {
+ err = -EFAULT;
+ break;
+ }
+ err = io_buffer_validate(&iov);
+ if (err)
+ break;
+ err = io_sqe_buffer_register(ctx, &iov, &imu, &last_hpage);
+ if (err)
+ break;
+
+ i = array_index_nospec(offset, ctx->nr_user_bufs);
+ if (ctx->user_bufs[i]) {
+ err = io_queue_rsrc_removal(ctx->buf_data, offset,
+ ctx->rsrc_node, ctx->user_bufs[i]);
+ if (unlikely(err)) {
+ io_buffer_unmap(ctx, &imu);
+ break;
+ }
+ ctx->user_bufs[i] = NULL;
+ needs_switch = true;
+ }
+
+ ctx->user_bufs[i] = imu;
+ ctx->buf_data->tags[offset] = tag;
+ }
+
+ if (needs_switch)
+ io_rsrc_node_switch(ctx, ctx->buf_data);
+ return done ? done : err;
+}
+
static int io_eventfd_register(struct io_ring_ctx *ctx, void __user *arg)
{
__s32 __user *fds = arg;
@@ -8332,19 +8508,13 @@ static int io_eventfd_unregister(struct io_ring_ctx *ctx)
return -ENXIO;
}
-static int __io_destroy_buffers(int id, void *p, void *data)
-{
- struct io_ring_ctx *ctx = data;
- struct io_buffer *buf = p;
-
- __io_remove_buffers(ctx, buf, id, -1U);
- return 0;
-}
-
static void io_destroy_buffers(struct io_ring_ctx *ctx)
{
- idr_for_each(&ctx->io_buffer_idr, __io_destroy_buffers, ctx);
- idr_destroy(&ctx->io_buffer_idr);
+ struct io_buffer *buf;
+ unsigned long index;
+
+ xa_for_each(&ctx->io_buffers, index, buf)
+ __io_remove_buffers(ctx, buf, index, -1U);
}
static void io_req_cache_free(struct list_head *list, struct task_struct *tsk)
@@ -8372,28 +8542,23 @@ static void io_req_caches_free(struct io_ring_ctx *ctx)
submit_state->free_reqs = 0;
}
- spin_lock_irq(&ctx->completion_lock);
- list_splice_init(&cs->locked_free_list, &cs->free_list);
- cs->locked_free_nr = 0;
- spin_unlock_irq(&ctx->completion_lock);
-
+ io_flush_cached_locked_reqs(ctx, cs);
io_req_cache_free(&cs->free_list, NULL);
-
mutex_unlock(&ctx->uring_lock);
}
-static void io_ring_ctx_free(struct io_ring_ctx *ctx)
+static bool io_wait_rsrc_data(struct io_rsrc_data *data)
{
- /*
- * Some may use context even when all refs and requests have been put,
- * and they are free to do so while still holding uring_lock, see
- * __io_req_task_submit(). Wait for them to finish.
- */
- mutex_lock(&ctx->uring_lock);
- mutex_unlock(&ctx->uring_lock);
+ if (!data)
+ return false;
+ if (!atomic_dec_and_test(&data->refs))
+ wait_for_completion(&data->done);
+ return true;
+}
+static void io_ring_ctx_free(struct io_ring_ctx *ctx)
+{
io_sq_thread_finish(ctx);
- io_sqe_buffers_unregister(ctx);
if (ctx->mm_account) {
mmdrop(ctx->mm_account);
@@ -8401,10 +8566,27 @@ static void io_ring_ctx_free(struct io_ring_ctx *ctx)
}
mutex_lock(&ctx->uring_lock);
- io_sqe_files_unregister(ctx);
+ if (io_wait_rsrc_data(ctx->buf_data))
+ __io_sqe_buffers_unregister(ctx);
+ if (io_wait_rsrc_data(ctx->file_data))
+ __io_sqe_files_unregister(ctx);
+ if (ctx->rings)
+ __io_cqring_overflow_flush(ctx, true);
mutex_unlock(&ctx->uring_lock);
io_eventfd_unregister(ctx);
io_destroy_buffers(ctx);
+ if (ctx->sq_creds)
+ put_cred(ctx->sq_creds);
+
+ /* there are no registered resources left, nobody uses it */
+ if (ctx->rsrc_node)
+ io_rsrc_node_destroy(ctx->rsrc_node);
+ if (ctx->rsrc_backup_node)
+ io_rsrc_node_destroy(ctx->rsrc_backup_node);
+ flush_delayed_work(&ctx->rsrc_put_work);
+
+ WARN_ON_ONCE(!list_empty(&ctx->rsrc_ref_list));
+ WARN_ON_ONCE(!llist_empty(&ctx->rsrc_put_llist));
#if defined(CONFIG_UNIX)
if (ctx->ring_sock) {
@@ -8478,26 +8660,9 @@ static int io_unregister_personality(struct io_ring_ctx *ctx, unsigned id)
return -EINVAL;
}
-static bool io_run_ctx_fallback(struct io_ring_ctx *ctx)
+static inline bool io_run_ctx_fallback(struct io_ring_ctx *ctx)
{
- struct callback_head *work, *next;
- bool executed = false;
-
- do {
- work = xchg(&ctx->exit_task_work, NULL);
- if (!work)
- break;
-
- do {
- next = work->next;
- work->func(work);
- work = next;
- cond_resched();
- } while (work);
- executed = true;
- } while (1);
-
- return executed;
+ return io_run_task_work_head(&ctx->exit_task_work);
}
struct io_tctx_exit {
@@ -8521,6 +8686,13 @@ static void io_tctx_exit_cb(struct callback_head *cb)
complete(&work->completion);
}
+static bool io_cancel_ctx_cb(struct io_wq_work *work, void *data)
+{
+ struct io_kiocb *req = container_of(work, struct io_kiocb, work);
+
+ return req->ctx == data;
+}
+
static void io_ring_exit_work(struct work_struct *work)
{
struct io_ring_ctx *ctx = container_of(work, struct io_ring_ctx, exit_work);
@@ -8537,19 +8709,38 @@ static void io_ring_exit_work(struct work_struct *work)
*/
do {
io_uring_try_cancel_requests(ctx, NULL, NULL);
+ if (ctx->sq_data) {
+ struct io_sq_data *sqd = ctx->sq_data;
+ struct task_struct *tsk;
+
+ io_sq_thread_park(sqd);
+ tsk = sqd->thread;
+ if (tsk && tsk->io_uring && tsk->io_uring->io_wq)
+ io_wq_cancel_cb(tsk->io_uring->io_wq,
+ io_cancel_ctx_cb, ctx, true);
+ io_sq_thread_unpark(sqd);
+ }
WARN_ON_ONCE(time_after(jiffies, timeout));
} while (!wait_for_completion_timeout(&ctx->ref_comp, HZ/20));
+ init_completion(&exit.completion);
+ init_task_work(&exit.task_work, io_tctx_exit_cb);
+ exit.ctx = ctx;
+ /*
+ * Some may use context even when all refs and requests have been put,
+ * and they are free to do so while still holding uring_lock or
+ * completion_lock, see __io_req_task_submit(). Apart from other work,
+ * this lock/unlock section also waits them to finish.
+ */
mutex_lock(&ctx->uring_lock);
while (!list_empty(&ctx->tctx_list)) {
WARN_ON_ONCE(time_after(jiffies, timeout));
node = list_first_entry(&ctx->tctx_list, struct io_tctx_node,
ctx_node);
- exit.ctx = ctx;
- init_completion(&exit.completion);
- init_task_work(&exit.task_work, io_tctx_exit_cb);
+ /* don't spin on a single task if cancellation failed */
+ list_rotate_left(&ctx->tctx_list);
ret = task_work_add(node->task, &exit.task_work, TWA_SIGNAL);
if (WARN_ON_ONCE(ret))
continue;
@@ -8557,14 +8748,37 @@ static void io_ring_exit_work(struct work_struct *work)
mutex_unlock(&ctx->uring_lock);
wait_for_completion(&exit.completion);
- cond_resched();
mutex_lock(&ctx->uring_lock);
}
mutex_unlock(&ctx->uring_lock);
+ spin_lock_irq(&ctx->completion_lock);
+ spin_unlock_irq(&ctx->completion_lock);
io_ring_ctx_free(ctx);
}
+/* Returns true if we found and killed one or more timeouts */
+static bool io_kill_timeouts(struct io_ring_ctx *ctx, struct task_struct *tsk,
+ struct files_struct *files)
+{
+ struct io_kiocb *req, *tmp;
+ int canceled = 0;
+
+ spin_lock_irq(&ctx->completion_lock);
+ list_for_each_entry_safe(req, tmp, &ctx->timeout_list, timeout.list) {
+ if (io_match_task(req, tsk, files)) {
+ io_kill_timeout(req, -ECANCELED);
+ canceled++;
+ }
+ }
+ if (canceled != 0)
+ io_commit_cqring(ctx);
+ spin_unlock_irq(&ctx->completion_lock);
+ if (canceled != 0)
+ io_cqring_ev_posted(ctx);
+ return canceled != 0;
+}
+
static void io_ring_ctx_wait_and_kill(struct io_ring_ctx *ctx)
{
unsigned long index;
@@ -8572,10 +8786,8 @@ static void io_ring_ctx_wait_and_kill(struct io_ring_ctx *ctx)
mutex_lock(&ctx->uring_lock);
percpu_ref_kill(&ctx->refs);
- /* if force is set, the ring is going away. always drop after that */
- ctx->cq_overflow_flushed = 1;
if (ctx->rings)
- __io_cqring_overflow_flush(ctx, true, NULL, NULL);
+ __io_cqring_overflow_flush(ctx, true);
xa_for_each(&ctx->personalities, index, creds)
io_unregister_personality(ctx, index);
mutex_unlock(&ctx->uring_lock);
@@ -8651,21 +8863,12 @@ static bool io_cancel_defer_files(struct io_ring_ctx *ctx,
while (!list_empty(&list)) {
de = list_first_entry(&list, struct io_defer_entry, list);
list_del_init(&de->list);
- req_set_fail_links(de->req);
- io_put_req(de->req);
- io_req_complete(de->req, -ECANCELED);
+ io_req_complete_failed(de->req, -ECANCELED);
kfree(de);
}
return true;
}
-static bool io_cancel_ctx_cb(struct io_wq_work *work, void *data)
-{
- struct io_kiocb *req = container_of(work, struct io_kiocb, work);
-
- return req->ctx == data;
-}
-
static bool io_uring_try_cancel_iowq(struct io_ring_ctx *ctx)
{
struct io_tctx_node *node;
@@ -8727,53 +8930,13 @@ static void io_uring_try_cancel_requests(struct io_ring_ctx *ctx,
ret |= io_kill_timeouts(ctx, task, files);
ret |= io_run_task_work();
ret |= io_run_ctx_fallback(ctx);
- io_cqring_overflow_flush(ctx, true, task, files);
if (!ret)
break;
cond_resched();
}
}
-static int io_uring_count_inflight(struct io_ring_ctx *ctx,
- struct task_struct *task,
- struct files_struct *files)
-{
- struct io_kiocb *req;
- int cnt = 0;
-
- spin_lock_irq(&ctx->inflight_lock);
- list_for_each_entry(req, &ctx->inflight_list, inflight_entry)
- cnt += io_match_task(req, task, files);
- spin_unlock_irq(&ctx->inflight_lock);
- return cnt;
-}
-
-static void io_uring_cancel_files(struct io_ring_ctx *ctx,
- struct task_struct *task,
- struct files_struct *files)
-{
- while (!list_empty_careful(&ctx->inflight_list)) {
- DEFINE_WAIT(wait);
- int inflight;
-
- inflight = io_uring_count_inflight(ctx, task, files);
- if (!inflight)
- break;
-
- io_uring_try_cancel_requests(ctx, task, files);
-
- prepare_to_wait(&task->io_uring->wait, &wait,
- TASK_UNINTERRUPTIBLE);
- if (inflight == io_uring_count_inflight(ctx, task, files))
- schedule();
- finish_wait(&task->io_uring->wait, &wait);
- }
-}
-
-/*
- * Note that this task has used io_uring. We use it for cancelation purposes.
- */
-static int io_uring_add_task_file(struct io_ring_ctx *ctx)
+static int __io_uring_add_task_file(struct io_ring_ctx *ctx)
{
struct io_uring_task *tctx = current->io_uring;
struct io_tctx_node *node;
@@ -8785,33 +8948,41 @@ static int io_uring_add_task_file(struct io_ring_ctx *ctx)
return ret;
tctx = current->io_uring;
}
- if (tctx->last != ctx) {
- void *old = xa_load(&tctx->xa, (unsigned long)ctx);
-
- if (!old) {
- node = kmalloc(sizeof(*node), GFP_KERNEL);
- if (!node)
- return -ENOMEM;
- node->ctx = ctx;
- node->task = current;
-
- ret = xa_err(xa_store(&tctx->xa, (unsigned long)ctx,
- node, GFP_KERNEL));
- if (ret) {
- kfree(node);
- return ret;
- }
+ if (!xa_load(&tctx->xa, (unsigned long)ctx)) {
+ node = kmalloc(sizeof(*node), GFP_KERNEL);
+ if (!node)
+ return -ENOMEM;
+ node->ctx = ctx;
+ node->task = current;
- mutex_lock(&ctx->uring_lock);
- list_add(&node->ctx_node, &ctx->tctx_list);
- mutex_unlock(&ctx->uring_lock);
+ ret = xa_err(xa_store(&tctx->xa, (unsigned long)ctx,
+ node, GFP_KERNEL));
+ if (ret) {
+ kfree(node);
+ return ret;
}
- tctx->last = ctx;
+
+ mutex_lock(&ctx->uring_lock);
+ list_add(&node->ctx_node, &ctx->tctx_list);
+ mutex_unlock(&ctx->uring_lock);
}
+ tctx->last = ctx;
return 0;
}
/*
+ * Note that this task has used io_uring. We use it for cancelation purposes.
+ */
+static inline int io_uring_add_task_file(struct io_ring_ctx *ctx)
+{
+ struct io_uring_task *tctx = current->io_uring;
+
+ if (likely(tctx && tctx->last == ctx))
+ return 0;
+ return __io_uring_add_task_file(ctx);
+}
+
+/*
* Remove this io_uring_file -> task mapping.
*/
static void io_uring_del_task_file(unsigned long index)
@@ -8850,86 +9021,48 @@ static void io_uring_clean_tctx(struct io_uring_task *tctx)
}
}
-static s64 tctx_inflight(struct io_uring_task *tctx)
+static s64 tctx_inflight(struct io_uring_task *tctx, bool tracked)
{
+ if (tracked)
+ return atomic_read(&tctx->inflight_tracked);
return percpu_counter_sum(&tctx->inflight);
}
-static void io_sqpoll_cancel_cb(struct callback_head *cb)
-{
- struct io_tctx_exit *work = container_of(cb, struct io_tctx_exit, task_work);
- struct io_ring_ctx *ctx = work->ctx;
- struct io_sq_data *sqd = ctx->sq_data;
-
- if (sqd->thread)
- io_uring_cancel_sqpoll(ctx);
- complete(&work->completion);
-}
-
-static void io_sqpoll_cancel_sync(struct io_ring_ctx *ctx)
-{
- struct io_sq_data *sqd = ctx->sq_data;
- struct io_tctx_exit work = { .ctx = ctx, };
- struct task_struct *task;
-
- io_sq_thread_park(sqd);
- list_del_init(&ctx->sqd_list);
- io_sqd_update_thread_idle(sqd);
- task = sqd->thread;
- if (task) {
- init_completion(&work.completion);
- init_task_work(&work.task_work, io_sqpoll_cancel_cb);
- WARN_ON_ONCE(task_work_add(task, &work.task_work, TWA_SIGNAL));
- wake_up_process(task);
- }
- io_sq_thread_unpark(sqd);
-
- if (task)
- wait_for_completion(&work.completion);
-}
-
-void __io_uring_files_cancel(struct files_struct *files)
+static void io_uring_try_cancel(struct files_struct *files)
{
struct io_uring_task *tctx = current->io_uring;
struct io_tctx_node *node;
unsigned long index;
- /* make sure overflow events are dropped */
- atomic_inc(&tctx->in_idle);
xa_for_each(&tctx->xa, index, node) {
struct io_ring_ctx *ctx = node->ctx;
- if (ctx->sq_data) {
- io_sqpoll_cancel_sync(ctx);
- continue;
- }
- io_uring_cancel_files(ctx, current, files);
- if (!files)
- io_uring_try_cancel_requests(ctx, current, NULL);
+ /* sqpoll task will cancel all its requests */
+ if (!ctx->sq_data)
+ io_uring_try_cancel_requests(ctx, current, files);
}
- atomic_dec(&tctx->in_idle);
-
- if (files)
- io_uring_clean_tctx(tctx);
}
/* should only be called by SQPOLL task */
-static void io_uring_cancel_sqpoll(struct io_ring_ctx *ctx)
+static void io_uring_cancel_sqpoll(struct io_sq_data *sqd)
{
- struct io_sq_data *sqd = ctx->sq_data;
struct io_uring_task *tctx = current->io_uring;
+ struct io_ring_ctx *ctx;
s64 inflight;
DEFINE_WAIT(wait);
- WARN_ON_ONCE(!sqd || ctx->sq_data->thread != current);
+ if (!current->io_uring)
+ return;
+ WARN_ON_ONCE(!sqd || sqd->thread != current);
atomic_inc(&tctx->in_idle);
do {
/* read completions before cancelations */
- inflight = tctx_inflight(tctx);
+ inflight = tctx_inflight(tctx, false);
if (!inflight)
break;
- io_uring_try_cancel_requests(ctx, current, NULL);
+ list_for_each_entry(ctx, &sqd->ctx_list, sqd_list)
+ io_uring_try_cancel_requests(ctx, current, NULL);
prepare_to_wait(&tctx->wait, &wait, TASK_UNINTERRUPTIBLE);
/*
@@ -8937,7 +9070,7 @@ static void io_uring_cancel_sqpoll(struct io_ring_ctx *ctx)
* avoids a race where a completion comes in before we did
* prepare_to_wait().
*/
- if (inflight == tctx_inflight(tctx))
+ if (inflight == tctx_inflight(tctx, false))
schedule();
finish_wait(&tctx->wait, &wait);
} while (1);
@@ -8948,7 +9081,7 @@ static void io_uring_cancel_sqpoll(struct io_ring_ctx *ctx)
* Find any io_uring fd that this task has registered or done IO on, and cancel
* requests.
*/
-void __io_uring_task_cancel(void)
+void __io_uring_cancel(struct files_struct *files)
{
struct io_uring_task *tctx = current->io_uring;
DEFINE_WAIT(wait);
@@ -8958,11 +9091,10 @@ void __io_uring_task_cancel(void)
atomic_inc(&tctx->in_idle);
do {
/* read completions before cancelations */
- inflight = tctx_inflight(tctx);
+ inflight = tctx_inflight(tctx, !!files);
if (!inflight)
break;
- __io_uring_files_cancel(NULL);
-
+ io_uring_try_cancel(files);
prepare_to_wait(&tctx->wait, &wait, TASK_UNINTERRUPTIBLE);
/*
@@ -8970,16 +9102,17 @@ void __io_uring_task_cancel(void)
* avoids a race where a completion comes in before we did
* prepare_to_wait().
*/
- if (inflight == tctx_inflight(tctx))
+ if (inflight == tctx_inflight(tctx, !!files))
schedule();
finish_wait(&tctx->wait, &wait);
} while (1);
-
atomic_dec(&tctx->in_idle);
io_uring_clean_tctx(tctx);
- /* all current's requests should be gone, we can kill tctx */
- __io_uring_free(current);
+ if (!files) {
+ /* for exec all current's requests should be gone, kill tctx */
+ __io_uring_free(current);
+ }
}
static void *io_uring_validate_mmap_request(struct file *file,
@@ -9105,31 +9238,31 @@ SYSCALL_DEFINE6(io_uring_enter, unsigned int, fd, u32, to_submit,
size_t, argsz)
{
struct io_ring_ctx *ctx;
- long ret = -EBADF;
int submitted = 0;
struct fd f;
+ long ret;
io_run_task_work();
- if (flags & ~(IORING_ENTER_GETEVENTS | IORING_ENTER_SQ_WAKEUP |
- IORING_ENTER_SQ_WAIT | IORING_ENTER_EXT_ARG))
+ if (unlikely(flags & ~(IORING_ENTER_GETEVENTS | IORING_ENTER_SQ_WAKEUP |
+ IORING_ENTER_SQ_WAIT | IORING_ENTER_EXT_ARG)))
return -EINVAL;
f = fdget(fd);
- if (!f.file)
+ if (unlikely(!f.file))
return -EBADF;
ret = -EOPNOTSUPP;
- if (f.file->f_op != &io_uring_fops)
+ if (unlikely(f.file->f_op != &io_uring_fops))
goto out_fput;
ret = -ENXIO;
ctx = f.file->private_data;
- if (!percpu_ref_tryget(&ctx->refs))
+ if (unlikely(!percpu_ref_tryget(&ctx->refs)))
goto out_fput;
ret = -EBADFD;
- if (ctx->flags & IORING_SETUP_R_DISABLED)
+ if (unlikely(ctx->flags & IORING_SETUP_R_DISABLED))
goto out;
/*
@@ -9139,7 +9272,7 @@ SYSCALL_DEFINE6(io_uring_enter, unsigned int, fd, u32, to_submit,
*/
ret = 0;
if (ctx->flags & IORING_SETUP_SQPOLL) {
- io_cqring_overflow_flush(ctx, false, NULL, NULL);
+ io_cqring_overflow_flush(ctx, false);
ret = -EOWNERDEAD;
if (unlikely(ctx->sq_data->thread == NULL)) {
@@ -9252,7 +9385,7 @@ static void __io_uring_show_fdinfo(struct io_ring_ctx *ctx, struct seq_file *m)
seq_printf(m, "SqThreadCpu:\t%d\n", sq ? task_cpu(sq->thread) : -1);
seq_printf(m, "UserFiles:\t%u\n", ctx->nr_user_files);
for (i = 0; has_lock && i < ctx->nr_user_files; i++) {
- struct file *f = *io_fixed_file_slot(ctx->file_data, i);
+ struct file *f = io_file_from_index(ctx, i);
if (f)
seq_printf(m, "%5u: %s\n", i, file_dentry(f)->d_iname);
@@ -9261,10 +9394,10 @@ static void __io_uring_show_fdinfo(struct io_ring_ctx *ctx, struct seq_file *m)
}
seq_printf(m, "UserBufs:\t%u\n", ctx->nr_user_bufs);
for (i = 0; has_lock && i < ctx->nr_user_bufs; i++) {
- struct io_mapped_ubuf *buf = &ctx->user_bufs[i];
+ struct io_mapped_ubuf *buf = ctx->user_bufs[i];
+ unsigned int len = buf->ubuf_end - buf->ubuf;
- seq_printf(m, "%5u: 0x%llx/%u\n", i, buf->ubuf,
- (unsigned int) buf->len);
+ seq_printf(m, "%5u: 0x%llx/%u\n", i, buf->ubuf, len);
}
if (has_lock && !xa_empty(&ctx->personalities)) {
unsigned long index;
@@ -9473,6 +9606,9 @@ static int io_uring_create(unsigned entries, struct io_uring_params *p,
ret = io_sq_offload_create(ctx, p);
if (ret)
goto err;
+ /* always set a rsrc node */
+ io_rsrc_node_switch_start(ctx);
+ io_rsrc_node_switch(ctx, NULL);
memset(&p->sq_off, 0, sizeof(p->sq_off));
p->sq_off.head = offsetof(struct io_rings, sq.head);
@@ -9698,14 +9834,96 @@ static int io_register_enable_rings(struct io_ring_ctx *ctx)
return 0;
}
+static int __io_register_rsrc_update(struct io_ring_ctx *ctx, unsigned type,
+ struct io_uring_rsrc_update2 *up,
+ unsigned nr_args)
+{
+ __u32 tmp;
+ int err;
+
+ if (up->resv)
+ return -EINVAL;
+ if (check_add_overflow(up->offset, nr_args, &tmp))
+ return -EOVERFLOW;
+ err = io_rsrc_node_switch_start(ctx);
+ if (err)
+ return err;
+
+ switch (type) {
+ case IORING_RSRC_FILE:
+ return __io_sqe_files_update(ctx, up, nr_args);
+ case IORING_RSRC_BUFFER:
+ return __io_sqe_buffers_update(ctx, up, nr_args);
+ }
+ return -EINVAL;
+}
+
+static int io_register_files_update(struct io_ring_ctx *ctx, void __user *arg,
+ unsigned nr_args)
+{
+ struct io_uring_rsrc_update2 up;
+
+ if (!nr_args)
+ return -EINVAL;
+ memset(&up, 0, sizeof(up));
+ if (copy_from_user(&up, arg, sizeof(struct io_uring_rsrc_update)))
+ return -EFAULT;
+ return __io_register_rsrc_update(ctx, IORING_RSRC_FILE, &up, nr_args);
+}
+
+static int io_register_rsrc_update(struct io_ring_ctx *ctx, void __user *arg,
+ unsigned size)
+{
+ struct io_uring_rsrc_update2 up;
+
+ if (size != sizeof(up))
+ return -EINVAL;
+ if (copy_from_user(&up, arg, sizeof(up)))
+ return -EFAULT;
+ if (!up.nr)
+ return -EINVAL;
+ return __io_register_rsrc_update(ctx, up.type, &up, up.nr);
+}
+
+static int io_register_rsrc(struct io_ring_ctx *ctx, void __user *arg,
+ unsigned int size)
+{
+ struct io_uring_rsrc_register rr;
+
+ /* keep it extendible */
+ if (size != sizeof(rr))
+ return -EINVAL;
+
+ memset(&rr, 0, sizeof(rr));
+ if (copy_from_user(&rr, arg, size))
+ return -EFAULT;
+ if (!rr.nr)
+ return -EINVAL;
+
+ switch (rr.type) {
+ case IORING_RSRC_FILE:
+ return io_sqe_files_register(ctx, u64_to_user_ptr(rr.data),
+ rr.nr, u64_to_user_ptr(rr.tags));
+ case IORING_RSRC_BUFFER:
+ return io_sqe_buffers_register(ctx, u64_to_user_ptr(rr.data),
+ rr.nr, u64_to_user_ptr(rr.tags));
+ }
+ return -EINVAL;
+}
+
static bool io_register_op_must_quiesce(int op)
{
switch (op) {
+ case IORING_REGISTER_BUFFERS:
+ case IORING_UNREGISTER_BUFFERS:
+ case IORING_REGISTER_FILES:
case IORING_UNREGISTER_FILES:
case IORING_REGISTER_FILES_UPDATE:
case IORING_REGISTER_PROBE:
case IORING_REGISTER_PERSONALITY:
case IORING_UNREGISTER_PERSONALITY:
+ case IORING_REGISTER_RSRC:
+ case IORING_REGISTER_RSRC_UPDATE:
return false;
default:
return true;
@@ -9727,6 +9945,14 @@ static int __io_uring_register(struct io_ring_ctx *ctx, unsigned opcode,
if (percpu_ref_is_dying(&ctx->refs))
return -ENXIO;
+ if (ctx->restricted) {
+ if (opcode >= IORING_REGISTER_LAST)
+ return -EINVAL;
+ opcode = array_index_nospec(opcode, IORING_REGISTER_LAST);
+ if (!test_bit(opcode, ctx->restrictions.register_op))
+ return -EACCES;
+ }
+
if (io_register_op_must_quiesce(opcode)) {
percpu_ref_kill(&ctx->refs);
@@ -9747,30 +9973,17 @@ static int __io_uring_register(struct io_ring_ctx *ctx, unsigned opcode,
if (ret < 0)
break;
} while (1);
-
mutex_lock(&ctx->uring_lock);
if (ret) {
- percpu_ref_resurrect(&ctx->refs);
- goto out_quiesce;
- }
- }
-
- if (ctx->restricted) {
- if (opcode >= IORING_REGISTER_LAST) {
- ret = -EINVAL;
- goto out;
- }
-
- if (!test_bit(opcode, ctx->restrictions.register_op)) {
- ret = -EACCES;
- goto out;
+ io_refs_resurrect(&ctx->refs, &ctx->ref_comp);
+ return ret;
}
}
switch (opcode) {
case IORING_REGISTER_BUFFERS:
- ret = io_sqe_buffers_register(ctx, arg, nr_args);
+ ret = io_sqe_buffers_register(ctx, arg, nr_args, NULL);
break;
case IORING_UNREGISTER_BUFFERS:
ret = -EINVAL;
@@ -9779,7 +9992,7 @@ static int __io_uring_register(struct io_ring_ctx *ctx, unsigned opcode,
ret = io_sqe_buffers_unregister(ctx);
break;
case IORING_REGISTER_FILES:
- ret = io_sqe_files_register(ctx, arg, nr_args);
+ ret = io_sqe_files_register(ctx, arg, nr_args, NULL);
break;
case IORING_UNREGISTER_FILES:
ret = -EINVAL;
@@ -9788,7 +10001,7 @@ static int __io_uring_register(struct io_ring_ctx *ctx, unsigned opcode,
ret = io_sqe_files_unregister(ctx);
break;
case IORING_REGISTER_FILES_UPDATE:
- ret = io_sqe_files_update(ctx, arg, nr_args);
+ ret = io_register_files_update(ctx, arg, nr_args);
break;
case IORING_REGISTER_EVENTFD:
case IORING_REGISTER_EVENTFD_ASYNC:
@@ -9836,16 +10049,20 @@ static int __io_uring_register(struct io_ring_ctx *ctx, unsigned opcode,
case IORING_REGISTER_RESTRICTIONS:
ret = io_register_restrictions(ctx, arg, nr_args);
break;
+ case IORING_REGISTER_RSRC:
+ ret = io_register_rsrc(ctx, arg, nr_args);
+ break;
+ case IORING_REGISTER_RSRC_UPDATE:
+ ret = io_register_rsrc_update(ctx, arg, nr_args);
+ break;
default:
ret = -EINVAL;
break;
}
-out:
if (io_register_op_must_quiesce(opcode)) {
/* bring the ctx back to life */
percpu_ref_reinit(&ctx->refs);
-out_quiesce:
reinit_completion(&ctx->ref_comp);
}
return ret;
diff --git a/fs/ioctl.c b/fs/ioctl.c
index 4e6cc0a7d69c..1e2204fa9963 100644
--- a/fs/ioctl.c
+++ b/fs/ioctl.c
@@ -19,6 +19,9 @@
#include <linux/falloc.h>
#include <linux/sched/signal.h>
#include <linux/fiemap.h>
+#include <linux/mount.h>
+#include <linux/fscrypt.h>
+#include <linux/fileattr.h>
#include "internal.h"
@@ -657,6 +660,307 @@ out:
return ret;
}
+/**
+ * fileattr_fill_xflags - initialize fileattr with xflags
+ * @fa: fileattr pointer
+ * @xflags: FS_XFLAG_* flags
+ *
+ * Set ->fsx_xflags, ->fsx_valid and ->flags (translated xflags). All
+ * other fields are zeroed.
+ */
+void fileattr_fill_xflags(struct fileattr *fa, u32 xflags)
+{
+ memset(fa, 0, sizeof(*fa));
+ fa->fsx_valid = true;
+ fa->fsx_xflags = xflags;
+ if (fa->fsx_xflags & FS_XFLAG_IMMUTABLE)
+ fa->flags |= FS_IMMUTABLE_FL;
+ if (fa->fsx_xflags & FS_XFLAG_APPEND)
+ fa->flags |= FS_APPEND_FL;
+ if (fa->fsx_xflags & FS_XFLAG_SYNC)
+ fa->flags |= FS_SYNC_FL;
+ if (fa->fsx_xflags & FS_XFLAG_NOATIME)
+ fa->flags |= FS_NOATIME_FL;
+ if (fa->fsx_xflags & FS_XFLAG_NODUMP)
+ fa->flags |= FS_NODUMP_FL;
+ if (fa->fsx_xflags & FS_XFLAG_DAX)
+ fa->flags |= FS_DAX_FL;
+ if (fa->fsx_xflags & FS_XFLAG_PROJINHERIT)
+ fa->flags |= FS_PROJINHERIT_FL;
+}
+EXPORT_SYMBOL(fileattr_fill_xflags);
+
+/**
+ * fileattr_fill_flags - initialize fileattr with flags
+ * @fa: fileattr pointer
+ * @flags: FS_*_FL flags
+ *
+ * Set ->flags, ->flags_valid and ->fsx_xflags (translated flags).
+ * All other fields are zeroed.
+ */
+void fileattr_fill_flags(struct fileattr *fa, u32 flags)
+{
+ memset(fa, 0, sizeof(*fa));
+ fa->flags_valid = true;
+ fa->flags = flags;
+ if (fa->flags & FS_SYNC_FL)
+ fa->fsx_xflags |= FS_XFLAG_SYNC;
+ if (fa->flags & FS_IMMUTABLE_FL)
+ fa->fsx_xflags |= FS_XFLAG_IMMUTABLE;
+ if (fa->flags & FS_APPEND_FL)
+ fa->fsx_xflags |= FS_XFLAG_APPEND;
+ if (fa->flags & FS_NODUMP_FL)
+ fa->fsx_xflags |= FS_XFLAG_NODUMP;
+ if (fa->flags & FS_NOATIME_FL)
+ fa->fsx_xflags |= FS_XFLAG_NOATIME;
+ if (fa->flags & FS_DAX_FL)
+ fa->fsx_xflags |= FS_XFLAG_DAX;
+ if (fa->flags & FS_PROJINHERIT_FL)
+ fa->fsx_xflags |= FS_XFLAG_PROJINHERIT;
+}
+EXPORT_SYMBOL(fileattr_fill_flags);
+
+/**
+ * vfs_fileattr_get - retrieve miscellaneous file attributes
+ * @dentry: the object to retrieve from
+ * @fa: fileattr pointer
+ *
+ * Call i_op->fileattr_get() callback, if exists.
+ *
+ * Return: 0 on success, or a negative error on failure.
+ */
+int vfs_fileattr_get(struct dentry *dentry, struct fileattr *fa)
+{
+ struct inode *inode = d_inode(dentry);
+
+ if (!inode->i_op->fileattr_get)
+ return -ENOIOCTLCMD;
+
+ return inode->i_op->fileattr_get(dentry, fa);
+}
+EXPORT_SYMBOL(vfs_fileattr_get);
+
+/**
+ * copy_fsxattr_to_user - copy fsxattr to userspace.
+ * @fa: fileattr pointer
+ * @ufa: fsxattr user pointer
+ *
+ * Return: 0 on success, or -EFAULT on failure.
+ */
+int copy_fsxattr_to_user(const struct fileattr *fa, struct fsxattr __user *ufa)
+{
+ struct fsxattr xfa;
+
+ memset(&xfa, 0, sizeof(xfa));
+ xfa.fsx_xflags = fa->fsx_xflags;
+ xfa.fsx_extsize = fa->fsx_extsize;
+ xfa.fsx_nextents = fa->fsx_nextents;
+ xfa.fsx_projid = fa->fsx_projid;
+ xfa.fsx_cowextsize = fa->fsx_cowextsize;
+
+ if (copy_to_user(ufa, &xfa, sizeof(xfa)))
+ return -EFAULT;
+
+ return 0;
+}
+EXPORT_SYMBOL(copy_fsxattr_to_user);
+
+static int copy_fsxattr_from_user(struct fileattr *fa,
+ struct fsxattr __user *ufa)
+{
+ struct fsxattr xfa;
+
+ if (copy_from_user(&xfa, ufa, sizeof(xfa)))
+ return -EFAULT;
+
+ fileattr_fill_xflags(fa, xfa.fsx_xflags);
+ fa->fsx_extsize = xfa.fsx_extsize;
+ fa->fsx_nextents = xfa.fsx_nextents;
+ fa->fsx_projid = xfa.fsx_projid;
+ fa->fsx_cowextsize = xfa.fsx_cowextsize;
+
+ return 0;
+}
+
+/*
+ * Generic function to check FS_IOC_FSSETXATTR/FS_IOC_SETFLAGS values and reject
+ * any invalid configurations.
+ *
+ * Note: must be called with inode lock held.
+ */
+static int fileattr_set_prepare(struct inode *inode,
+ const struct fileattr *old_ma,
+ struct fileattr *fa)
+{
+ int err;
+
+ /*
+ * The IMMUTABLE and APPEND_ONLY flags can only be changed by
+ * the relevant capability.
+ */
+ if ((fa->flags ^ old_ma->flags) & (FS_APPEND_FL | FS_IMMUTABLE_FL) &&
+ !capable(CAP_LINUX_IMMUTABLE))
+ return -EPERM;
+
+ err = fscrypt_prepare_setflags(inode, old_ma->flags, fa->flags);
+ if (err)
+ return err;
+
+ /*
+ * Project Quota ID state is only allowed to change from within the init
+ * namespace. Enforce that restriction only if we are trying to change
+ * the quota ID state. Everything else is allowed in user namespaces.
+ */
+ if (current_user_ns() != &init_user_ns) {
+ if (old_ma->fsx_projid != fa->fsx_projid)
+ return -EINVAL;
+ if ((old_ma->fsx_xflags ^ fa->fsx_xflags) &
+ FS_XFLAG_PROJINHERIT)
+ return -EINVAL;
+ }
+
+ /* Check extent size hints. */
+ if ((fa->fsx_xflags & FS_XFLAG_EXTSIZE) && !S_ISREG(inode->i_mode))
+ return -EINVAL;
+
+ if ((fa->fsx_xflags & FS_XFLAG_EXTSZINHERIT) &&
+ !S_ISDIR(inode->i_mode))
+ return -EINVAL;
+
+ if ((fa->fsx_xflags & FS_XFLAG_COWEXTSIZE) &&
+ !S_ISREG(inode->i_mode) && !S_ISDIR(inode->i_mode))
+ return -EINVAL;
+
+ /*
+ * It is only valid to set the DAX flag on regular files and
+ * directories on filesystems.
+ */
+ if ((fa->fsx_xflags & FS_XFLAG_DAX) &&
+ !(S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode)))
+ return -EINVAL;
+
+ /* Extent size hints of zero turn off the flags. */
+ if (fa->fsx_extsize == 0)
+ fa->fsx_xflags &= ~(FS_XFLAG_EXTSIZE | FS_XFLAG_EXTSZINHERIT);
+ if (fa->fsx_cowextsize == 0)
+ fa->fsx_xflags &= ~FS_XFLAG_COWEXTSIZE;
+
+ return 0;
+}
+
+/**
+ * vfs_fileattr_set - change miscellaneous file attributes
+ * @mnt_userns: user namespace of the mount
+ * @dentry: the object to change
+ * @fa: fileattr pointer
+ *
+ * After verifying permissions, call i_op->fileattr_set() callback, if
+ * exists.
+ *
+ * Verifying attributes involves retrieving current attributes with
+ * i_op->fileattr_get(), this also allows initializing attributes that have
+ * not been set by the caller to current values. Inode lock is held
+ * thoughout to prevent racing with another instance.
+ *
+ * Return: 0 on success, or a negative error on failure.
+ */
+int vfs_fileattr_set(struct user_namespace *mnt_userns, struct dentry *dentry,
+ struct fileattr *fa)
+{
+ struct inode *inode = d_inode(dentry);
+ struct fileattr old_ma = {};
+ int err;
+
+ if (!inode->i_op->fileattr_set)
+ return -ENOIOCTLCMD;
+
+ if (!inode_owner_or_capable(mnt_userns, inode))
+ return -EPERM;
+
+ inode_lock(inode);
+ err = vfs_fileattr_get(dentry, &old_ma);
+ if (!err) {
+ /* initialize missing bits from old_ma */
+ if (fa->flags_valid) {
+ fa->fsx_xflags |= old_ma.fsx_xflags & ~FS_XFLAG_COMMON;
+ fa->fsx_extsize = old_ma.fsx_extsize;
+ fa->fsx_nextents = old_ma.fsx_nextents;
+ fa->fsx_projid = old_ma.fsx_projid;
+ fa->fsx_cowextsize = old_ma.fsx_cowextsize;
+ } else {
+ fa->flags |= old_ma.flags & ~FS_COMMON_FL;
+ }
+ err = fileattr_set_prepare(inode, &old_ma, fa);
+ if (!err)
+ err = inode->i_op->fileattr_set(mnt_userns, dentry, fa);
+ }
+ inode_unlock(inode);
+
+ return err;
+}
+EXPORT_SYMBOL(vfs_fileattr_set);
+
+static int ioctl_getflags(struct file *file, unsigned int __user *argp)
+{
+ struct fileattr fa = { .flags_valid = true }; /* hint only */
+ int err;
+
+ err = vfs_fileattr_get(file->f_path.dentry, &fa);
+ if (!err)
+ err = put_user(fa.flags, argp);
+ return err;
+}
+
+static int ioctl_setflags(struct file *file, unsigned int __user *argp)
+{
+ struct user_namespace *mnt_userns = file_mnt_user_ns(file);
+ struct dentry *dentry = file->f_path.dentry;
+ struct fileattr fa;
+ unsigned int flags;
+ int err;
+
+ err = get_user(flags, argp);
+ if (!err) {
+ err = mnt_want_write_file(file);
+ if (!err) {
+ fileattr_fill_flags(&fa, flags);
+ err = vfs_fileattr_set(mnt_userns, dentry, &fa);
+ mnt_drop_write_file(file);
+ }
+ }
+ return err;
+}
+
+static int ioctl_fsgetxattr(struct file *file, void __user *argp)
+{
+ struct fileattr fa = { .fsx_valid = true }; /* hint only */
+ int err;
+
+ err = vfs_fileattr_get(file->f_path.dentry, &fa);
+ if (!err)
+ err = copy_fsxattr_to_user(&fa, argp);
+
+ return err;
+}
+
+static int ioctl_fssetxattr(struct file *file, void __user *argp)
+{
+ struct user_namespace *mnt_userns = file_mnt_user_ns(file);
+ struct dentry *dentry = file->f_path.dentry;
+ struct fileattr fa;
+ int err;
+
+ err = copy_fsxattr_from_user(&fa, argp);
+ if (!err) {
+ err = mnt_want_write_file(file);
+ if (!err) {
+ err = vfs_fileattr_set(mnt_userns, dentry, &fa);
+ mnt_drop_write_file(file);
+ }
+ }
+ return err;
+}
+
/*
* do_vfs_ioctl() is not for drivers and not intended to be EXPORT_SYMBOL()'d.
* It's just a simple helper for sys_ioctl and compat_sys_ioctl.
@@ -727,6 +1031,18 @@ static int do_vfs_ioctl(struct file *filp, unsigned int fd,
return put_user(i_size_read(inode) - filp->f_pos,
(int __user *)argp);
+ case FS_IOC_GETFLAGS:
+ return ioctl_getflags(filp, argp);
+
+ case FS_IOC_SETFLAGS:
+ return ioctl_setflags(filp, argp);
+
+ case FS_IOC_FSGETXATTR:
+ return ioctl_fsgetxattr(filp, argp);
+
+ case FS_IOC_FSSETXATTR:
+ return ioctl_fssetxattr(filp, argp);
+
default:
if (S_ISREG(inode->i_mode))
return file_ioctl(filp, cmd, argp);
@@ -828,6 +1144,15 @@ COMPAT_SYSCALL_DEFINE3(ioctl, unsigned int, fd, unsigned int, cmd,
#endif
/*
+ * These access 32-bit values anyway so no further handling is
+ * necessary.
+ */
+ case FS_IOC32_GETFLAGS:
+ case FS_IOC32_SETFLAGS:
+ cmd = (cmd == FS_IOC32_GETFLAGS) ?
+ FS_IOC_GETFLAGS : FS_IOC_SETFLAGS;
+ fallthrough;
+ /*
* everything else in do_vfs_ioctl() takes either a compatible
* pointer argument or no argument -- call it with a modified
* argument.
diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c
index 414769a6ad11..0129e6bab985 100644
--- a/fs/iomap/buffered-io.c
+++ b/fs/iomap/buffered-io.c
@@ -1155,7 +1155,8 @@ iomap_ioend_try_merge(struct iomap_ioend *ioend, struct list_head *more_ioends,
EXPORT_SYMBOL_GPL(iomap_ioend_try_merge);
static int
-iomap_ioend_compare(void *priv, struct list_head *a, struct list_head *b)
+iomap_ioend_compare(void *priv, const struct list_head *a,
+ const struct list_head *b)
{
struct iomap_ioend *ia = container_of(a, struct iomap_ioend, io_list);
struct iomap_ioend *ib = container_of(b, struct iomap_ioend, io_list);
diff --git a/fs/iomap/direct-io.c b/fs/iomap/direct-io.c
index bdd0d89bbf0a..9398b8c31323 100644
--- a/fs/iomap/direct-io.c
+++ b/fs/iomap/direct-io.c
@@ -487,12 +487,28 @@ __iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
if (pos >= dio->i_size)
goto out_free_dio;
+ if (iocb->ki_flags & IOCB_NOWAIT) {
+ if (filemap_range_needs_writeback(mapping, pos, end)) {
+ ret = -EAGAIN;
+ goto out_free_dio;
+ }
+ iomap_flags |= IOMAP_NOWAIT;
+ }
+
if (iter_is_iovec(iter))
dio->flags |= IOMAP_DIO_DIRTY;
} else {
iomap_flags |= IOMAP_WRITE;
dio->flags |= IOMAP_DIO_WRITE;
+ if (iocb->ki_flags & IOCB_NOWAIT) {
+ if (filemap_range_has_page(mapping, pos, end)) {
+ ret = -EAGAIN;
+ goto out_free_dio;
+ }
+ iomap_flags |= IOMAP_NOWAIT;
+ }
+
/* for data sync or sync, we need sync completion processing */
if (iocb->ki_flags & IOCB_DSYNC)
dio->flags |= IOMAP_DIO_NEED_SYNC;
@@ -507,14 +523,6 @@ __iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
dio->flags |= IOMAP_DIO_WRITE_FUA;
}
- if (iocb->ki_flags & IOCB_NOWAIT) {
- if (filemap_range_has_page(mapping, pos, end)) {
- ret = -EAGAIN;
- goto out_free_dio;
- }
- iomap_flags |= IOMAP_NOWAIT;
- }
-
if (dio_flags & IOMAP_DIO_OVERWRITE_ONLY) {
ret = -EAGAIN;
if (pos >= dio->i_size || pos + count > dio->i_size)
diff --git a/fs/iomap/swapfile.c b/fs/iomap/swapfile.c
index a648dbf6991e..6250ca6a1f85 100644
--- a/fs/iomap/swapfile.c
+++ b/fs/iomap/swapfile.c
@@ -18,6 +18,7 @@ struct iomap_swapfile_info {
uint64_t highest_ppage; /* highest physical addr seen (pages) */
unsigned long nr_pages; /* number of pages collected */
int nr_extents; /* extent count */
+ struct file *file;
};
/*
@@ -70,6 +71,18 @@ static int iomap_swapfile_add_extent(struct iomap_swapfile_info *isi)
return 0;
}
+static int iomap_swapfile_fail(struct iomap_swapfile_info *isi, const char *str)
+{
+ char *buf, *p = ERR_PTR(-ENOMEM);
+
+ buf = kmalloc(PATH_MAX, GFP_KERNEL);
+ if (buf)
+ p = file_path(isi->file, buf, PATH_MAX);
+ pr_err("swapon: file %s %s\n", IS_ERR(p) ? "<unknown>" : p, str);
+ kfree(buf);
+ return -EINVAL;
+}
+
/*
* Accumulate iomaps for this swap file. We have to accumulate iomaps because
* swap only cares about contiguous page-aligned physical extents and makes no
@@ -89,28 +102,20 @@ static loff_t iomap_swapfile_activate_actor(struct inode *inode, loff_t pos,
break;
case IOMAP_INLINE:
/* No inline data. */
- pr_err("swapon: file is inline\n");
- return -EINVAL;
+ return iomap_swapfile_fail(isi, "is inline");
default:
- pr_err("swapon: file has unallocated extents\n");
- return -EINVAL;
+ return iomap_swapfile_fail(isi, "has unallocated extents");
}
/* No uncommitted metadata or shared blocks. */
- if (iomap->flags & IOMAP_F_DIRTY) {
- pr_err("swapon: file is not committed\n");
- return -EINVAL;
- }
- if (iomap->flags & IOMAP_F_SHARED) {
- pr_err("swapon: file has shared extents\n");
- return -EINVAL;
- }
+ if (iomap->flags & IOMAP_F_DIRTY)
+ return iomap_swapfile_fail(isi, "is not committed");
+ if (iomap->flags & IOMAP_F_SHARED)
+ return iomap_swapfile_fail(isi, "has shared extents");
/* Only one bdev per swap file. */
- if (iomap->bdev != isi->sis->bdev) {
- pr_err("swapon: file is on multiple devices\n");
- return -EINVAL;
- }
+ if (iomap->bdev != isi->sis->bdev)
+ return iomap_swapfile_fail(isi, "outside the main device");
if (isi->iomap.length == 0) {
/* No accumulated extent, so just store it. */
@@ -139,6 +144,7 @@ int iomap_swapfile_activate(struct swap_info_struct *sis,
struct iomap_swapfile_info isi = {
.sis = sis,
.lowest_ppage = (sector_t)-1ULL,
+ .file = swap_file,
};
struct address_space *mapping = swap_file->f_mapping;
struct inode *inode = mapping->host;
@@ -170,6 +176,16 @@ int iomap_swapfile_activate(struct swap_info_struct *sis,
return ret;
}
+ /*
+ * If this swapfile doesn't contain even a single page-aligned
+ * contiguous range of blocks, reject this useless swapfile to
+ * prevent confusion later on.
+ */
+ if (isi.nr_pages == 0) {
+ pr_warn("swapon: Cannot find a single usable page in file.\n");
+ return -EINVAL;
+ }
+
*pagespan = 1 + isi.highest_ppage - isi.lowest_ppage;
sis->max = isi.nr_pages;
sis->pages = isi.nr_pages - 1;
diff --git a/fs/jbd2/recovery.c b/fs/jbd2/recovery.c
index 69f18fe20923..d47a0d96bf30 100644
--- a/fs/jbd2/recovery.c
+++ b/fs/jbd2/recovery.c
@@ -245,15 +245,14 @@ static int fc_do_one_pass(journal_t *journal,
return 0;
while (next_fc_block <= journal->j_fc_last) {
- jbd_debug(3, "Fast commit replay: next block %ld",
+ jbd_debug(3, "Fast commit replay: next block %ld\n",
next_fc_block);
err = jread(&bh, journal, next_fc_block);
if (err) {
- jbd_debug(3, "Fast commit replay: read error");
+ jbd_debug(3, "Fast commit replay: read error\n");
break;
}
- jbd_debug(3, "Processing fast commit blk with seq %d");
err = journal->j_fc_replay_callback(journal, bh, pass,
next_fc_block - journal->j_fc_first,
expected_commit_id);
diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c
index 9396666b7314..e8fc45fd751f 100644
--- a/fs/jbd2/transaction.c
+++ b/fs/jbd2/transaction.c
@@ -349,7 +349,12 @@ static int start_this_handle(journal_t *journal, handle_t *handle,
}
alloc_transaction:
- if (!journal->j_running_transaction) {
+ /*
+ * This check is racy but it is just an optimization of allocating new
+ * transaction early if there are high chances we'll need it. If we
+ * guess wrong, we'll retry or free unused transaction.
+ */
+ if (!data_race(journal->j_running_transaction)) {
/*
* If __GFP_FS is not present, then we may be being called from
* inside the fs writeback layer, so we MUST NOT fail.
@@ -1474,8 +1479,8 @@ int jbd2_journal_dirty_metadata(handle_t *handle, struct buffer_head *bh)
* crucial to catch bugs so let's do a reliable check until the
* lockless handling is fully proven.
*/
- if (jh->b_transaction != transaction &&
- jh->b_next_transaction != transaction) {
+ if (data_race(jh->b_transaction != transaction &&
+ jh->b_next_transaction != transaction)) {
spin_lock(&jh->b_state_lock);
J_ASSERT_JH(jh, jh->b_transaction == transaction ||
jh->b_next_transaction == transaction);
@@ -1483,8 +1488,8 @@ int jbd2_journal_dirty_metadata(handle_t *handle, struct buffer_head *bh)
}
if (jh->b_modified == 1) {
/* If it's in our transaction it must be in BJ_Metadata list. */
- if (jh->b_transaction == transaction &&
- jh->b_jlist != BJ_Metadata) {
+ if (data_race(jh->b_transaction == transaction &&
+ jh->b_jlist != BJ_Metadata)) {
spin_lock(&jh->b_state_lock);
if (jh->b_transaction == transaction &&
jh->b_jlist != BJ_Metadata)
diff --git a/fs/jffs2/TODO b/fs/jffs2/TODO
deleted file mode 100644
index ca28964abd4b..000000000000
--- a/fs/jffs2/TODO
+++ /dev/null
@@ -1,37 +0,0 @@
-
- - support asynchronous operation -- add a per-fs 'reserved_space' count,
- let each outstanding write reserve the _maximum_ amount of physical
- space it could take. Let GC flush the outstanding writes because the
- reservations will necessarily be pessimistic. With this we could even
- do shared writable mmap, if we can have a fs hook for do_wp_page() to
- make the reservation.
- - disable compression in commit_write()?
- - fine-tune the allocation / GC thresholds
- - chattr support - turning on/off and tuning compression per-inode
- - checkpointing (do we need this? scan is quite fast)
- - make the scan code populate real inodes so read_inode just after
- mount doesn't have to read the flash twice for large files.
- Make this a per-inode option, changeable with chattr, so you can
- decide which inodes should be in-core immediately after mount.
- - test, test, test
-
- - NAND flash support:
- - almost done :)
- - use bad block check instead of the hardwired byte check
-
- - Optimisations:
- - Split writes so they go to two separate blocks rather than just c->nextblock.
- By writing _new_ nodes to one block, and garbage-collected REF_PRISTINE
- nodes to a different one, we can separate clean nodes from those which
- are likely to become dirty, and end up with blocks which are each far
- closer to 100% or 0% clean, hence speeding up later GC progress dramatically.
- - Stop keeping name in-core with struct jffs2_full_dirent. If we keep the hash in
- the full dirent, we only need to go to the flash in lookup() when we think we've
- got a match, and in readdir().
- - Doubly-linked next_in_ino list to allow us to free obsoleted raw_node_refs immediately?
- - Remove size from jffs2_raw_node_frag.
-
-dedekind:
-1. __jffs2_flush_wbuf() has a strange 'pad' parameter. Eliminate.
-2. get_sb()->build_fs()->scan() path... Why get_sb() removes scan()'s crap in
- case of failure? scan() does not clean everything. Fix.
diff --git a/fs/jfs/file.c b/fs/jfs/file.c
index 28b70e7c7dd4..1d732fd223d4 100644
--- a/fs/jfs/file.c
+++ b/fs/jfs/file.c
@@ -130,6 +130,8 @@ int jfs_setattr(struct user_namespace *mnt_userns, struct dentry *dentry,
const struct inode_operations jfs_file_inode_operations = {
.listxattr = jfs_listxattr,
.setattr = jfs_setattr,
+ .fileattr_get = jfs_fileattr_get,
+ .fileattr_set = jfs_fileattr_set,
#ifdef CONFIG_JFS_POSIX_ACL
.get_acl = jfs_get_acl,
.set_acl = jfs_set_acl,
@@ -147,7 +149,5 @@ const struct file_operations jfs_file_operations = {
.fsync = jfs_fsync,
.release = jfs_release,
.unlocked_ioctl = jfs_ioctl,
-#ifdef CONFIG_COMPAT
- .compat_ioctl = jfs_compat_ioctl,
-#endif
+ .compat_ioctl = compat_ptr_ioctl,
};
diff --git a/fs/jfs/ioctl.c b/fs/jfs/ioctl.c
index 2581d4db58ff..03a845ab4f00 100644
--- a/fs/jfs/ioctl.c
+++ b/fs/jfs/ioctl.c
@@ -15,6 +15,7 @@
#include <linux/blkdev.h>
#include <asm/current.h>
#include <linux/uaccess.h>
+#include <linux/fileattr.h>
#include "jfs_filsys.h"
#include "jfs_debug.h"
@@ -56,69 +57,56 @@ static long jfs_map_ext2(unsigned long flags, int from)
return mapped;
}
+int jfs_fileattr_get(struct dentry *dentry, struct fileattr *fa)
+{
+ struct jfs_inode_info *jfs_inode = JFS_IP(d_inode(dentry));
+ unsigned int flags = jfs_inode->mode2 & JFS_FL_USER_VISIBLE;
-long jfs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
+ if (d_is_special(dentry))
+ return -ENOTTY;
+
+ fileattr_fill_flags(fa, jfs_map_ext2(flags, 0));
+
+ return 0;
+}
+
+int jfs_fileattr_set(struct user_namespace *mnt_userns,
+ struct dentry *dentry, struct fileattr *fa)
{
- struct inode *inode = file_inode(filp);
+ struct inode *inode = d_inode(dentry);
struct jfs_inode_info *jfs_inode = JFS_IP(inode);
unsigned int flags;
- switch (cmd) {
- case JFS_IOC_GETFLAGS:
- flags = jfs_inode->mode2 & JFS_FL_USER_VISIBLE;
- flags = jfs_map_ext2(flags, 0);
- return put_user(flags, (int __user *) arg);
- case JFS_IOC_SETFLAGS: {
- unsigned int oldflags;
- int err;
-
- err = mnt_want_write_file(filp);
- if (err)
- return err;
-
- if (!inode_owner_or_capable(&init_user_ns, inode)) {
- err = -EACCES;
- goto setflags_out;
- }
- if (get_user(flags, (int __user *) arg)) {
- err = -EFAULT;
- goto setflags_out;
- }
+ if (d_is_special(dentry))
+ return -ENOTTY;
- flags = jfs_map_ext2(flags, 1);
- if (!S_ISDIR(inode->i_mode))
- flags &= ~JFS_DIRSYNC_FL;
+ if (fileattr_has_fsx(fa))
+ return -EOPNOTSUPP;
- /* Is it quota file? Do not allow user to mess with it */
- if (IS_NOQUOTA(inode)) {
- err = -EPERM;
- goto setflags_out;
- }
+ flags = jfs_map_ext2(fa->flags, 1);
+ if (!S_ISDIR(inode->i_mode))
+ flags &= ~JFS_DIRSYNC_FL;
- /* Lock against other parallel changes of flags */
- inode_lock(inode);
+ /* Is it quota file? Do not allow user to mess with it */
+ if (IS_NOQUOTA(inode))
+ return -EPERM;
- oldflags = jfs_map_ext2(jfs_inode->mode2 & JFS_FL_USER_VISIBLE,
- 0);
- err = vfs_ioc_setflags_prepare(inode, oldflags, flags);
- if (err) {
- inode_unlock(inode);
- goto setflags_out;
- }
+ flags = flags & JFS_FL_USER_MODIFIABLE;
+ flags |= jfs_inode->mode2 & ~JFS_FL_USER_MODIFIABLE;
+ jfs_inode->mode2 = flags;
- flags = flags & JFS_FL_USER_MODIFIABLE;
- flags |= jfs_inode->mode2 & ~JFS_FL_USER_MODIFIABLE;
- jfs_inode->mode2 = flags;
-
- jfs_set_inode_flags(inode);
- inode_unlock(inode);
- inode->i_ctime = current_time(inode);
- mark_inode_dirty(inode);
-setflags_out:
- mnt_drop_write_file(filp);
- return err;
- }
+ jfs_set_inode_flags(inode);
+ inode->i_ctime = current_time(inode);
+ mark_inode_dirty(inode);
+
+ return 0;
+}
+
+long jfs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
+{
+ struct inode *inode = file_inode(filp);
+ switch (cmd) {
case FITRIM:
{
struct super_block *sb = inode->i_sb;
@@ -156,22 +144,3 @@ setflags_out:
return -ENOTTY;
}
}
-
-#ifdef CONFIG_COMPAT
-long jfs_compat_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
-{
- /* While these ioctl numbers defined with 'long' and have different
- * numbers than the 64bit ABI,
- * the actual implementation only deals with ints and is compatible.
- */
- switch (cmd) {
- case JFS_IOC_GETFLAGS32:
- cmd = JFS_IOC_GETFLAGS;
- break;
- case JFS_IOC_SETFLAGS32:
- cmd = JFS_IOC_SETFLAGS;
- break;
- }
- return jfs_ioctl(filp, cmd, arg);
-}
-#endif
diff --git a/fs/jfs/jfs_dinode.h b/fs/jfs/jfs_dinode.h
index 5fa9fd594115..d6af79e94263 100644
--- a/fs/jfs/jfs_dinode.h
+++ b/fs/jfs/jfs_dinode.h
@@ -160,11 +160,4 @@ struct dinode {
#define JFS_FL_USER_MODIFIABLE 0x03F80000
#define JFS_FL_INHERIT 0x03C80000
-/* These are identical to EXT[23]_IOC_GETFLAGS/SETFLAGS */
-#define JFS_IOC_GETFLAGS _IOR('f', 1, long)
-#define JFS_IOC_SETFLAGS _IOW('f', 2, long)
-
-#define JFS_IOC_GETFLAGS32 _IOR('f', 1, int)
-#define JFS_IOC_SETFLAGS32 _IOW('f', 2, int)
-
#endif /*_H_JFS_DINODE */
diff --git a/fs/jfs/jfs_inode.h b/fs/jfs/jfs_inode.h
index 01daa0cb0ae5..7de961a81862 100644
--- a/fs/jfs/jfs_inode.h
+++ b/fs/jfs/jfs_inode.h
@@ -9,8 +9,10 @@ struct fid;
extern struct inode *ialloc(struct inode *, umode_t);
extern int jfs_fsync(struct file *, loff_t, loff_t, int);
+extern int jfs_fileattr_get(struct dentry *dentry, struct fileattr *fa);
+extern int jfs_fileattr_set(struct user_namespace *mnt_userns,
+ struct dentry *dentry, struct fileattr *fa);
extern long jfs_ioctl(struct file *, unsigned int, unsigned long);
-extern long jfs_compat_ioctl(struct file *, unsigned int, unsigned long);
extern struct inode *jfs_iget(struct super_block *, unsigned long);
extern int jfs_commit_inode(struct inode *, int);
extern int jfs_write_inode(struct inode *, struct writeback_control *);
diff --git a/fs/jfs/namei.c b/fs/jfs/namei.c
index 9abed0d750e5..9db4f5789c0e 100644
--- a/fs/jfs/namei.c
+++ b/fs/jfs/namei.c
@@ -1522,6 +1522,8 @@ const struct inode_operations jfs_dir_inode_operations = {
.rename = jfs_rename,
.listxattr = jfs_listxattr,
.setattr = jfs_setattr,
+ .fileattr_get = jfs_fileattr_get,
+ .fileattr_set = jfs_fileattr_set,
#ifdef CONFIG_JFS_POSIX_ACL
.get_acl = jfs_get_acl,
.set_acl = jfs_set_acl,
@@ -1533,9 +1535,7 @@ const struct file_operations jfs_dir_operations = {
.iterate = jfs_readdir,
.fsync = jfs_fsync,
.unlocked_ioctl = jfs_ioctl,
-#ifdef CONFIG_COMPAT
- .compat_ioctl = jfs_compat_ioctl,
-#endif
+ .compat_ioctl = compat_ptr_ioctl,
.llseek = generic_file_llseek,
};
diff --git a/fs/libfs.c b/fs/libfs.c
index e2de5401abca..e9b29c6ffccb 100644
--- a/fs/libfs.c
+++ b/fs/libfs.c
@@ -481,6 +481,7 @@ EXPORT_SYMBOL(simple_rename);
/**
* simple_setattr - setattr for simple filesystem
+ * @mnt_userns: user namespace of the target mount
* @dentry: dentry
* @iattr: iattr structure
*
diff --git a/fs/locks.c b/fs/locks.c
index 99ca97e81b7a..5c42363aa811 100644
--- a/fs/locks.c
+++ b/fs/locks.c
@@ -1808,9 +1808,6 @@ check_conflicting_open(struct file *filp, const long arg, int flags)
if (flags & FL_LAYOUT)
return 0;
- if (flags & FL_DELEG)
- /* We leave these checks to the caller. */
- return 0;
if (arg == F_RDLCK)
return inode_is_open_for_write(inode) ? -EAGAIN : 0;
@@ -2372,7 +2369,6 @@ int fcntl_getlk(struct file *filp, unsigned int cmd, struct flock *flock)
if (flock->l_pid != 0)
goto out;
- cmd = F_GETLK;
fl->fl_flags |= FL_OFDLCK;
fl->fl_owner = filp;
}
@@ -2828,7 +2824,7 @@ struct locks_iterator {
};
static void lock_get_status(struct seq_file *f, struct file_lock *fl,
- loff_t id, char *pfx)
+ loff_t id, char *pfx, int repeat)
{
struct inode *inode = NULL;
unsigned int fl_pid;
@@ -2844,7 +2840,11 @@ static void lock_get_status(struct seq_file *f, struct file_lock *fl,
if (fl->fl_file != NULL)
inode = locks_inode(fl->fl_file);
- seq_printf(f, "%lld:%s ", id, pfx);
+ seq_printf(f, "%lld: ", id);
+
+ if (repeat)
+ seq_printf(f, "%*s", repeat - 1 + (int)strlen(pfx), pfx);
+
if (IS_POSIX(fl)) {
if (fl->fl_flags & FL_ACCESS)
seq_puts(f, "ACCESS");
@@ -2906,21 +2906,64 @@ static void lock_get_status(struct seq_file *f, struct file_lock *fl,
}
}
+static struct file_lock *get_next_blocked_member(struct file_lock *node)
+{
+ struct file_lock *tmp;
+
+ /* NULL node or root node */
+ if (node == NULL || node->fl_blocker == NULL)
+ return NULL;
+
+ /* Next member in the linked list could be itself */
+ tmp = list_next_entry(node, fl_blocked_member);
+ if (list_entry_is_head(tmp, &node->fl_blocker->fl_blocked_requests, fl_blocked_member)
+ || tmp == node) {
+ return NULL;
+ }
+
+ return tmp;
+}
+
static int locks_show(struct seq_file *f, void *v)
{
struct locks_iterator *iter = f->private;
- struct file_lock *fl, *bfl;
+ struct file_lock *cur, *tmp;
struct pid_namespace *proc_pidns = proc_pid_ns(file_inode(f->file)->i_sb);
+ int level = 0;
- fl = hlist_entry(v, struct file_lock, fl_link);
+ cur = hlist_entry(v, struct file_lock, fl_link);
- if (locks_translate_pid(fl, proc_pidns) == 0)
+ if (locks_translate_pid(cur, proc_pidns) == 0)
return 0;
- lock_get_status(f, fl, iter->li_pos, "");
+ /* View this crossed linked list as a binary tree, the first member of fl_blocked_requests
+ * is the left child of current node, the next silibing in fl_blocked_member is the
+ * right child, we can alse get the parent of current node from fl_blocker, so this
+ * question becomes traversal of a binary tree
+ */
+ while (cur != NULL) {
+ if (level)
+ lock_get_status(f, cur, iter->li_pos, "-> ", level);
+ else
+ lock_get_status(f, cur, iter->li_pos, "", level);
- list_for_each_entry(bfl, &fl->fl_blocked_requests, fl_blocked_member)
- lock_get_status(f, bfl, iter->li_pos, " ->");
+ if (!list_empty(&cur->fl_blocked_requests)) {
+ /* Turn left */
+ cur = list_first_entry_or_null(&cur->fl_blocked_requests,
+ struct file_lock, fl_blocked_member);
+ level++;
+ } else {
+ /* Turn right */
+ tmp = get_next_blocked_member(cur);
+ /* Fall back to parent node */
+ while (tmp == NULL && cur->fl_blocker != NULL) {
+ cur = cur->fl_blocker;
+ level--;
+ tmp = get_next_blocked_member(cur);
+ }
+ cur = tmp;
+ }
+ }
return 0;
}
@@ -2941,7 +2984,7 @@ static void __show_fd_locks(struct seq_file *f,
(*id)++;
seq_puts(f, "lock:\t");
- lock_get_status(f, fl, *id, "");
+ lock_get_status(f, fl, *id, "", 0);
}
}
diff --git a/fs/namei.c b/fs/namei.c
index 216f16e74351..79b0ff9b151e 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -579,6 +579,8 @@ static void set_nameidata(struct nameidata *p, int dfd, struct filename *name)
p->stack = p->internal;
p->dfd = dfd;
p->name = name;
+ p->path.mnt = NULL;
+ p->path.dentry = NULL;
p->total_link_count = old ? old->total_link_count : 0;
p->saved = old;
current->nameidata = p;
@@ -652,6 +654,8 @@ static void terminate_walk(struct nameidata *nd)
rcu_read_unlock();
}
nd->depth = 0;
+ nd->path.mnt = NULL;
+ nd->path.dentry = NULL;
}
/* path_put is needed afterwards regardless of success or failure */
@@ -1122,8 +1126,7 @@ int may_linkat(struct user_namespace *mnt_userns, struct path *link)
* should be allowed, or not, on files that already
* exist.
* @mnt_userns: user namespace of the mount the inode was found from
- * @dir_mode: mode bits of directory
- * @dir_uid: owner of directory
+ * @nd: nameidata pathwalk data
* @inode: the inode of the file to open
*
* Block an O_CREAT open of a FIFO (or a regular file) when:
@@ -2322,8 +2325,6 @@ static const char *path_init(struct nameidata *nd, unsigned flags)
}
nd->root.mnt = NULL;
- nd->path.mnt = NULL;
- nd->path.dentry = NULL;
/* Absolute pathname -- fetch the root (LOOKUP_IN_ROOT uses nd->dfd). */
if (*s == '/' && !(flags & LOOKUP_IN_ROOT)) {
@@ -2419,16 +2420,16 @@ static int path_lookupat(struct nameidata *nd, unsigned flags, struct path *path
while (!(err = link_path_walk(s, nd)) &&
(s = lookup_last(nd)) != NULL)
;
+ if (!err && unlikely(nd->flags & LOOKUP_MOUNTPOINT)) {
+ err = handle_lookup_down(nd);
+ nd->flags &= ~LOOKUP_JUMPED; // no d_weak_revalidate(), please...
+ }
if (!err)
err = complete_walk(nd);
if (!err && nd->flags & LOOKUP_DIRECTORY)
if (!d_can_lookup(nd->path.dentry))
err = -ENOTDIR;
- if (!err && unlikely(nd->flags & LOOKUP_MOUNTPOINT)) {
- err = handle_lookup_down(nd);
- nd->flags &= ~LOOKUP_JUMPED; // no d_weak_revalidate(), please...
- }
if (!err) {
*path = nd->path;
nd->path.mnt = NULL;
@@ -2823,16 +2824,14 @@ static int may_delete(struct user_namespace *mnt_userns, struct inode *dir,
static inline int may_create(struct user_namespace *mnt_userns,
struct inode *dir, struct dentry *child)
{
- struct user_namespace *s_user_ns;
audit_inode_child(dir, child, AUDIT_TYPE_CHILD_CREATE);
if (child->d_inode)
return -EEXIST;
if (IS_DEADDIR(dir))
return -ENOENT;
- s_user_ns = dir->i_sb->s_user_ns;
- if (!kuid_has_mapping(s_user_ns, fsuid_into_mnt(mnt_userns)) ||
- !kgid_has_mapping(s_user_ns, fsgid_into_mnt(mnt_userns)))
+ if (!fsuidgid_has_mapping(dir->i_sb, mnt_userns))
return -EOVERFLOW;
+
return inode_permission(mnt_userns, dir, MAY_WRITE | MAY_EXEC);
}
@@ -3034,14 +3033,11 @@ static int may_o_create(struct user_namespace *mnt_userns,
const struct path *dir, struct dentry *dentry,
umode_t mode)
{
- struct user_namespace *s_user_ns;
int error = security_path_mknod(dir, dentry, mode, 0);
if (error)
return error;
- s_user_ns = dir->dentry->d_sb->s_user_ns;
- if (!kuid_has_mapping(s_user_ns, fsuid_into_mnt(mnt_userns)) ||
- !kgid_has_mapping(s_user_ns, fsgid_into_mnt(mnt_userns)))
+ if (!fsuidgid_has_mapping(dir->dentry->d_sb, mnt_userns))
return -EOVERFLOW;
error = inode_permission(mnt_userns, dir->dentry->d_inode,
@@ -3381,7 +3377,7 @@ static int do_open(struct nameidata *nd,
* @mnt_userns: user namespace of the mount the inode was found from
* @dentry: pointer to dentry of the base directory
* @mode: mode of the new tmpfile
- * @open_flags: flags
+ * @open_flag: flags
*
* Create a temporary file.
*
@@ -4406,14 +4402,7 @@ SYSCALL_DEFINE2(link, const char __user *, oldname, const char __user *, newname
/**
* vfs_rename - rename a filesystem object
- * @old_mnt_userns: old user namespace of the mount the inode was found from
- * @old_dir: parent of source
- * @old_dentry: source
- * @new_mnt_userns: new user namespace of the mount the inode was found from
- * @new_dir: parent of destination
- * @new_dentry: destination
- * @delegated_inode: returns an inode needing a delegation break
- * @flags: rename flags
+ * @rd: pointer to &struct renamedata info
*
* The caller must hold multiple mutexes--see lock_rename()).
*
diff --git a/fs/namespace.c b/fs/namespace.c
index 56bb5a5fdc0d..f63337828e1c 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -1242,8 +1242,9 @@ struct vfsmount *mntget(struct vfsmount *mnt)
}
EXPORT_SYMBOL(mntget);
-/* path_is_mountpoint() - Check if path is a mount in the current
- * namespace.
+/**
+ * path_is_mountpoint() - Check if path is a mount in the current namespace.
+ * @path: path to check
*
* d_mountpoint() can only be used reliably to establish if a dentry is
* not mounted in any namespace and that common case is handled inline.
@@ -1369,7 +1370,7 @@ void mnt_cursor_del(struct mnt_namespace *ns, struct mount *cursor)
/**
* may_umount_tree - check if a mount tree is busy
- * @mnt: root of mount tree
+ * @m: root of mount tree
*
* This is called to check if a tree of mounts has any
* open files, pwds, chroots or sub mounts that are
@@ -1939,10 +1940,11 @@ void drop_collected_mounts(struct vfsmount *mnt)
/**
* clone_private_mount - create a private clone of a path
+ * @path: path to clone
*
- * This creates a new vfsmount, which will be the clone of @path. The new will
- * not be attached anywhere in the namespace and will be private (i.e. changes
- * to the originating mount won't be propagated into this).
+ * This creates a new vfsmount, which will be the clone of @path. The new mount
+ * will not be attached anywhere in the namespace and will be private (i.e.
+ * changes to the originating mount won't be propagated into this).
*
* Release with mntput().
*/
diff --git a/fs/netfs/Kconfig b/fs/netfs/Kconfig
new file mode 100644
index 000000000000..578112713703
--- /dev/null
+++ b/fs/netfs/Kconfig
@@ -0,0 +1,23 @@
+# SPDX-License-Identifier: GPL-2.0-only
+
+config NETFS_SUPPORT
+ tristate "Support for network filesystem high-level I/O"
+ help
+ This option enables support for network filesystems, including
+ helpers for high-level buffered I/O, abstracting out read
+ segmentation, local caching and transparent huge page support.
+
+config NETFS_STATS
+ bool "Gather statistical information on local caching"
+ depends on NETFS_SUPPORT && PROC_FS
+ help
+ This option causes statistical information to be gathered on local
+ caching and exported through file:
+
+ /proc/fs/fscache/stats
+
+ The gathering of statistics adds a certain amount of overhead to
+ execution as there are a quite a few stats gathered, and on a
+ multi-CPU system these may be on cachelines that keep bouncing
+ between CPUs. On the other hand, the stats are very useful for
+ debugging purposes. Saying 'Y' here is recommended.
diff --git a/fs/netfs/Makefile b/fs/netfs/Makefile
new file mode 100644
index 000000000000..c15bfc966d96
--- /dev/null
+++ b/fs/netfs/Makefile
@@ -0,0 +1,5 @@
+# SPDX-License-Identifier: GPL-2.0
+
+netfs-y := read_helper.o stats.o
+
+obj-$(CONFIG_NETFS_SUPPORT) := netfs.o
diff --git a/fs/netfs/internal.h b/fs/netfs/internal.h
new file mode 100644
index 000000000000..b7f2c4459f33
--- /dev/null
+++ b/fs/netfs/internal.h
@@ -0,0 +1,97 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/* Internal definitions for network filesystem support
+ *
+ * Copyright (C) 2021 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ */
+
+#ifdef pr_fmt
+#undef pr_fmt
+#endif
+
+#define pr_fmt(fmt) "netfs: " fmt
+
+/*
+ * read_helper.c
+ */
+extern unsigned int netfs_debug;
+
+/*
+ * stats.c
+ */
+#ifdef CONFIG_NETFS_STATS
+extern atomic_t netfs_n_rh_readahead;
+extern atomic_t netfs_n_rh_readpage;
+extern atomic_t netfs_n_rh_rreq;
+extern atomic_t netfs_n_rh_sreq;
+extern atomic_t netfs_n_rh_download;
+extern atomic_t netfs_n_rh_download_done;
+extern atomic_t netfs_n_rh_download_failed;
+extern atomic_t netfs_n_rh_download_instead;
+extern atomic_t netfs_n_rh_read;
+extern atomic_t netfs_n_rh_read_done;
+extern atomic_t netfs_n_rh_read_failed;
+extern atomic_t netfs_n_rh_zero;
+extern atomic_t netfs_n_rh_short_read;
+extern atomic_t netfs_n_rh_write;
+extern atomic_t netfs_n_rh_write_begin;
+extern atomic_t netfs_n_rh_write_done;
+extern atomic_t netfs_n_rh_write_failed;
+extern atomic_t netfs_n_rh_write_zskip;
+
+
+static inline void netfs_stat(atomic_t *stat)
+{
+ atomic_inc(stat);
+}
+
+static inline void netfs_stat_d(atomic_t *stat)
+{
+ atomic_dec(stat);
+}
+
+#else
+#define netfs_stat(x) do {} while(0)
+#define netfs_stat_d(x) do {} while(0)
+#endif
+
+/*****************************************************************************/
+/*
+ * debug tracing
+ */
+#define dbgprintk(FMT, ...) \
+ printk("[%-6.6s] "FMT"\n", current->comm, ##__VA_ARGS__)
+
+#define kenter(FMT, ...) dbgprintk("==> %s("FMT")", __func__, ##__VA_ARGS__)
+#define kleave(FMT, ...) dbgprintk("<== %s()"FMT"", __func__, ##__VA_ARGS__)
+#define kdebug(FMT, ...) dbgprintk(FMT, ##__VA_ARGS__)
+
+#ifdef __KDEBUG
+#define _enter(FMT, ...) kenter(FMT, ##__VA_ARGS__)
+#define _leave(FMT, ...) kleave(FMT, ##__VA_ARGS__)
+#define _debug(FMT, ...) kdebug(FMT, ##__VA_ARGS__)
+
+#elif defined(CONFIG_NETFS_DEBUG)
+#define _enter(FMT, ...) \
+do { \
+ if (netfs_debug) \
+ kenter(FMT, ##__VA_ARGS__); \
+} while (0)
+
+#define _leave(FMT, ...) \
+do { \
+ if (netfs_debug) \
+ kleave(FMT, ##__VA_ARGS__); \
+} while (0)
+
+#define _debug(FMT, ...) \
+do { \
+ if (netfs_debug) \
+ kdebug(FMT, ##__VA_ARGS__); \
+} while (0)
+
+#else
+#define _enter(FMT, ...) no_printk("==> %s("FMT")", __func__, ##__VA_ARGS__)
+#define _leave(FMT, ...) no_printk("<== %s()"FMT"", __func__, ##__VA_ARGS__)
+#define _debug(FMT, ...) no_printk(FMT, ##__VA_ARGS__)
+#endif
diff --git a/fs/netfs/read_helper.c b/fs/netfs/read_helper.c
new file mode 100644
index 000000000000..193841d03de0
--- /dev/null
+++ b/fs/netfs/read_helper.c
@@ -0,0 +1,1185 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/* Network filesystem high-level read support.
+ *
+ * Copyright (C) 2021 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ */
+
+#include <linux/module.h>
+#include <linux/export.h>
+#include <linux/fs.h>
+#include <linux/mm.h>
+#include <linux/pagemap.h>
+#include <linux/slab.h>
+#include <linux/uio.h>
+#include <linux/sched/mm.h>
+#include <linux/task_io_accounting_ops.h>
+#include <linux/netfs.h>
+#include "internal.h"
+#define CREATE_TRACE_POINTS
+#include <trace/events/netfs.h>
+
+MODULE_DESCRIPTION("Network fs support");
+MODULE_AUTHOR("Red Hat, Inc.");
+MODULE_LICENSE("GPL");
+
+unsigned netfs_debug;
+module_param_named(debug, netfs_debug, uint, S_IWUSR | S_IRUGO);
+MODULE_PARM_DESC(netfs_debug, "Netfs support debugging mask");
+
+static void netfs_rreq_work(struct work_struct *);
+static void __netfs_put_subrequest(struct netfs_read_subrequest *, bool);
+
+static void netfs_put_subrequest(struct netfs_read_subrequest *subreq,
+ bool was_async)
+{
+ if (refcount_dec_and_test(&subreq->usage))
+ __netfs_put_subrequest(subreq, was_async);
+}
+
+static struct netfs_read_request *netfs_alloc_read_request(
+ const struct netfs_read_request_ops *ops, void *netfs_priv,
+ struct file *file)
+{
+ static atomic_t debug_ids;
+ struct netfs_read_request *rreq;
+
+ rreq = kzalloc(sizeof(struct netfs_read_request), GFP_KERNEL);
+ if (rreq) {
+ rreq->netfs_ops = ops;
+ rreq->netfs_priv = netfs_priv;
+ rreq->inode = file_inode(file);
+ rreq->i_size = i_size_read(rreq->inode);
+ rreq->debug_id = atomic_inc_return(&debug_ids);
+ INIT_LIST_HEAD(&rreq->subrequests);
+ INIT_WORK(&rreq->work, netfs_rreq_work);
+ refcount_set(&rreq->usage, 1);
+ __set_bit(NETFS_RREQ_IN_PROGRESS, &rreq->flags);
+ ops->init_rreq(rreq, file);
+ netfs_stat(&netfs_n_rh_rreq);
+ }
+
+ return rreq;
+}
+
+static void netfs_get_read_request(struct netfs_read_request *rreq)
+{
+ refcount_inc(&rreq->usage);
+}
+
+static void netfs_rreq_clear_subreqs(struct netfs_read_request *rreq,
+ bool was_async)
+{
+ struct netfs_read_subrequest *subreq;
+
+ while (!list_empty(&rreq->subrequests)) {
+ subreq = list_first_entry(&rreq->subrequests,
+ struct netfs_read_subrequest, rreq_link);
+ list_del(&subreq->rreq_link);
+ netfs_put_subrequest(subreq, was_async);
+ }
+}
+
+static void netfs_free_read_request(struct work_struct *work)
+{
+ struct netfs_read_request *rreq =
+ container_of(work, struct netfs_read_request, work);
+ netfs_rreq_clear_subreqs(rreq, false);
+ if (rreq->netfs_priv)
+ rreq->netfs_ops->cleanup(rreq->mapping, rreq->netfs_priv);
+ trace_netfs_rreq(rreq, netfs_rreq_trace_free);
+ if (rreq->cache_resources.ops)
+ rreq->cache_resources.ops->end_operation(&rreq->cache_resources);
+ kfree(rreq);
+ netfs_stat_d(&netfs_n_rh_rreq);
+}
+
+static void netfs_put_read_request(struct netfs_read_request *rreq, bool was_async)
+{
+ if (refcount_dec_and_test(&rreq->usage)) {
+ if (was_async) {
+ rreq->work.func = netfs_free_read_request;
+ if (!queue_work(system_unbound_wq, &rreq->work))
+ BUG();
+ } else {
+ netfs_free_read_request(&rreq->work);
+ }
+ }
+}
+
+/*
+ * Allocate and partially initialise an I/O request structure.
+ */
+static struct netfs_read_subrequest *netfs_alloc_subrequest(
+ struct netfs_read_request *rreq)
+{
+ struct netfs_read_subrequest *subreq;
+
+ subreq = kzalloc(sizeof(struct netfs_read_subrequest), GFP_KERNEL);
+ if (subreq) {
+ INIT_LIST_HEAD(&subreq->rreq_link);
+ refcount_set(&subreq->usage, 2);
+ subreq->rreq = rreq;
+ netfs_get_read_request(rreq);
+ netfs_stat(&netfs_n_rh_sreq);
+ }
+
+ return subreq;
+}
+
+static void netfs_get_read_subrequest(struct netfs_read_subrequest *subreq)
+{
+ refcount_inc(&subreq->usage);
+}
+
+static void __netfs_put_subrequest(struct netfs_read_subrequest *subreq,
+ bool was_async)
+{
+ struct netfs_read_request *rreq = subreq->rreq;
+
+ trace_netfs_sreq(subreq, netfs_sreq_trace_free);
+ kfree(subreq);
+ netfs_stat_d(&netfs_n_rh_sreq);
+ netfs_put_read_request(rreq, was_async);
+}
+
+/*
+ * Clear the unread part of an I/O request.
+ */
+static void netfs_clear_unread(struct netfs_read_subrequest *subreq)
+{
+ struct iov_iter iter;
+
+ iov_iter_xarray(&iter, WRITE, &subreq->rreq->mapping->i_pages,
+ subreq->start + subreq->transferred,
+ subreq->len - subreq->transferred);
+ iov_iter_zero(iov_iter_count(&iter), &iter);
+}
+
+static void netfs_cache_read_terminated(void *priv, ssize_t transferred_or_error,
+ bool was_async)
+{
+ struct netfs_read_subrequest *subreq = priv;
+
+ netfs_subreq_terminated(subreq, transferred_or_error, was_async);
+}
+
+/*
+ * Issue a read against the cache.
+ * - Eats the caller's ref on subreq.
+ */
+static void netfs_read_from_cache(struct netfs_read_request *rreq,
+ struct netfs_read_subrequest *subreq,
+ bool seek_data)
+{
+ struct netfs_cache_resources *cres = &rreq->cache_resources;
+ struct iov_iter iter;
+
+ netfs_stat(&netfs_n_rh_read);
+ iov_iter_xarray(&iter, READ, &rreq->mapping->i_pages,
+ subreq->start + subreq->transferred,
+ subreq->len - subreq->transferred);
+
+ cres->ops->read(cres, subreq->start, &iter, seek_data,
+ netfs_cache_read_terminated, subreq);
+}
+
+/*
+ * Fill a subrequest region with zeroes.
+ */
+static void netfs_fill_with_zeroes(struct netfs_read_request *rreq,
+ struct netfs_read_subrequest *subreq)
+{
+ netfs_stat(&netfs_n_rh_zero);
+ __set_bit(NETFS_SREQ_CLEAR_TAIL, &subreq->flags);
+ netfs_subreq_terminated(subreq, 0, false);
+}
+
+/*
+ * Ask the netfs to issue a read request to the server for us.
+ *
+ * The netfs is expected to read from subreq->pos + subreq->transferred to
+ * subreq->pos + subreq->len - 1. It may not backtrack and write data into the
+ * buffer prior to the transferred point as it might clobber dirty data
+ * obtained from the cache.
+ *
+ * Alternatively, the netfs is allowed to indicate one of two things:
+ *
+ * - NETFS_SREQ_SHORT_READ: A short read - it will get called again to try and
+ * make progress.
+ *
+ * - NETFS_SREQ_CLEAR_TAIL: A short read - the rest of the buffer will be
+ * cleared.
+ */
+static void netfs_read_from_server(struct netfs_read_request *rreq,
+ struct netfs_read_subrequest *subreq)
+{
+ netfs_stat(&netfs_n_rh_download);
+ rreq->netfs_ops->issue_op(subreq);
+}
+
+/*
+ * Release those waiting.
+ */
+static void netfs_rreq_completed(struct netfs_read_request *rreq, bool was_async)
+{
+ trace_netfs_rreq(rreq, netfs_rreq_trace_done);
+ netfs_rreq_clear_subreqs(rreq, was_async);
+ netfs_put_read_request(rreq, was_async);
+}
+
+/*
+ * Deal with the completion of writing the data to the cache. We have to clear
+ * the PG_fscache bits on the pages involved and release the caller's ref.
+ *
+ * May be called in softirq mode and we inherit a ref from the caller.
+ */
+static void netfs_rreq_unmark_after_write(struct netfs_read_request *rreq,
+ bool was_async)
+{
+ struct netfs_read_subrequest *subreq;
+ struct page *page;
+ pgoff_t unlocked = 0;
+ bool have_unlocked = false;
+
+ rcu_read_lock();
+
+ list_for_each_entry(subreq, &rreq->subrequests, rreq_link) {
+ XA_STATE(xas, &rreq->mapping->i_pages, subreq->start / PAGE_SIZE);
+
+ xas_for_each(&xas, page, (subreq->start + subreq->len - 1) / PAGE_SIZE) {
+ /* We might have multiple writes from the same huge
+ * page, but we mustn't unlock a page more than once.
+ */
+ if (have_unlocked && page->index <= unlocked)
+ continue;
+ unlocked = page->index;
+ end_page_fscache(page);
+ have_unlocked = true;
+ }
+ }
+
+ rcu_read_unlock();
+ netfs_rreq_completed(rreq, was_async);
+}
+
+static void netfs_rreq_copy_terminated(void *priv, ssize_t transferred_or_error,
+ bool was_async)
+{
+ struct netfs_read_subrequest *subreq = priv;
+ struct netfs_read_request *rreq = subreq->rreq;
+
+ if (IS_ERR_VALUE(transferred_or_error)) {
+ netfs_stat(&netfs_n_rh_write_failed);
+ trace_netfs_failure(rreq, subreq, transferred_or_error,
+ netfs_fail_copy_to_cache);
+ } else {
+ netfs_stat(&netfs_n_rh_write_done);
+ }
+
+ trace_netfs_sreq(subreq, netfs_sreq_trace_write_term);
+
+ /* If we decrement nr_wr_ops to 0, the ref belongs to us. */
+ if (atomic_dec_and_test(&rreq->nr_wr_ops))
+ netfs_rreq_unmark_after_write(rreq, was_async);
+
+ netfs_put_subrequest(subreq, was_async);
+}
+
+/*
+ * Perform any outstanding writes to the cache. We inherit a ref from the
+ * caller.
+ */
+static void netfs_rreq_do_write_to_cache(struct netfs_read_request *rreq)
+{
+ struct netfs_cache_resources *cres = &rreq->cache_resources;
+ struct netfs_read_subrequest *subreq, *next, *p;
+ struct iov_iter iter;
+ int ret;
+
+ trace_netfs_rreq(rreq, netfs_rreq_trace_write);
+
+ /* We don't want terminating writes trying to wake us up whilst we're
+ * still going through the list.
+ */
+ atomic_inc(&rreq->nr_wr_ops);
+
+ list_for_each_entry_safe(subreq, p, &rreq->subrequests, rreq_link) {
+ if (!test_bit(NETFS_SREQ_WRITE_TO_CACHE, &subreq->flags)) {
+ list_del_init(&subreq->rreq_link);
+ netfs_put_subrequest(subreq, false);
+ }
+ }
+
+ list_for_each_entry(subreq, &rreq->subrequests, rreq_link) {
+ /* Amalgamate adjacent writes */
+ while (!list_is_last(&subreq->rreq_link, &rreq->subrequests)) {
+ next = list_next_entry(subreq, rreq_link);
+ if (next->start != subreq->start + subreq->len)
+ break;
+ subreq->len += next->len;
+ list_del_init(&next->rreq_link);
+ netfs_put_subrequest(next, false);
+ }
+
+ ret = cres->ops->prepare_write(cres, &subreq->start, &subreq->len,
+ rreq->i_size);
+ if (ret < 0) {
+ trace_netfs_failure(rreq, subreq, ret, netfs_fail_prepare_write);
+ trace_netfs_sreq(subreq, netfs_sreq_trace_write_skip);
+ continue;
+ }
+
+ iov_iter_xarray(&iter, WRITE, &rreq->mapping->i_pages,
+ subreq->start, subreq->len);
+
+ atomic_inc(&rreq->nr_wr_ops);
+ netfs_stat(&netfs_n_rh_write);
+ netfs_get_read_subrequest(subreq);
+ trace_netfs_sreq(subreq, netfs_sreq_trace_write);
+ cres->ops->write(cres, subreq->start, &iter,
+ netfs_rreq_copy_terminated, subreq);
+ }
+
+ /* If we decrement nr_wr_ops to 0, the usage ref belongs to us. */
+ if (atomic_dec_and_test(&rreq->nr_wr_ops))
+ netfs_rreq_unmark_after_write(rreq, false);
+}
+
+static void netfs_rreq_write_to_cache_work(struct work_struct *work)
+{
+ struct netfs_read_request *rreq =
+ container_of(work, struct netfs_read_request, work);
+
+ netfs_rreq_do_write_to_cache(rreq);
+}
+
+static void netfs_rreq_write_to_cache(struct netfs_read_request *rreq,
+ bool was_async)
+{
+ if (was_async) {
+ rreq->work.func = netfs_rreq_write_to_cache_work;
+ if (!queue_work(system_unbound_wq, &rreq->work))
+ BUG();
+ } else {
+ netfs_rreq_do_write_to_cache(rreq);
+ }
+}
+
+/*
+ * Unlock the pages in a read operation. We need to set PG_fscache on any
+ * pages we're going to write back before we unlock them.
+ */
+static void netfs_rreq_unlock(struct netfs_read_request *rreq)
+{
+ struct netfs_read_subrequest *subreq;
+ struct page *page;
+ unsigned int iopos, account = 0;
+ pgoff_t start_page = rreq->start / PAGE_SIZE;
+ pgoff_t last_page = ((rreq->start + rreq->len) / PAGE_SIZE) - 1;
+ bool subreq_failed = false;
+ int i;
+
+ XA_STATE(xas, &rreq->mapping->i_pages, start_page);
+
+ if (test_bit(NETFS_RREQ_FAILED, &rreq->flags)) {
+ __clear_bit(NETFS_RREQ_WRITE_TO_CACHE, &rreq->flags);
+ list_for_each_entry(subreq, &rreq->subrequests, rreq_link) {
+ __clear_bit(NETFS_SREQ_WRITE_TO_CACHE, &subreq->flags);
+ }
+ }
+
+ /* Walk through the pagecache and the I/O request lists simultaneously.
+ * We may have a mixture of cached and uncached sections and we only
+ * really want to write out the uncached sections. This is slightly
+ * complicated by the possibility that we might have huge pages with a
+ * mixture inside.
+ */
+ subreq = list_first_entry(&rreq->subrequests,
+ struct netfs_read_subrequest, rreq_link);
+ iopos = 0;
+ subreq_failed = (subreq->error < 0);
+
+ trace_netfs_rreq(rreq, netfs_rreq_trace_unlock);
+
+ rcu_read_lock();
+ xas_for_each(&xas, page, last_page) {
+ unsigned int pgpos = (page->index - start_page) * PAGE_SIZE;
+ unsigned int pgend = pgpos + thp_size(page);
+ bool pg_failed = false;
+
+ for (;;) {
+ if (!subreq) {
+ pg_failed = true;
+ break;
+ }
+ if (test_bit(NETFS_SREQ_WRITE_TO_CACHE, &subreq->flags))
+ set_page_fscache(page);
+ pg_failed |= subreq_failed;
+ if (pgend < iopos + subreq->len)
+ break;
+
+ account += subreq->transferred;
+ iopos += subreq->len;
+ if (!list_is_last(&subreq->rreq_link, &rreq->subrequests)) {
+ subreq = list_next_entry(subreq, rreq_link);
+ subreq_failed = (subreq->error < 0);
+ } else {
+ subreq = NULL;
+ subreq_failed = false;
+ }
+ if (pgend == iopos)
+ break;
+ }
+
+ if (!pg_failed) {
+ for (i = 0; i < thp_nr_pages(page); i++)
+ flush_dcache_page(page);
+ SetPageUptodate(page);
+ }
+
+ if (!test_bit(NETFS_RREQ_DONT_UNLOCK_PAGES, &rreq->flags)) {
+ if (page->index == rreq->no_unlock_page &&
+ test_bit(NETFS_RREQ_NO_UNLOCK_PAGE, &rreq->flags))
+ _debug("no unlock");
+ else
+ unlock_page(page);
+ }
+ }
+ rcu_read_unlock();
+
+ task_io_account_read(account);
+ if (rreq->netfs_ops->done)
+ rreq->netfs_ops->done(rreq);
+}
+
+/*
+ * Handle a short read.
+ */
+static void netfs_rreq_short_read(struct netfs_read_request *rreq,
+ struct netfs_read_subrequest *subreq)
+{
+ __clear_bit(NETFS_SREQ_SHORT_READ, &subreq->flags);
+ __set_bit(NETFS_SREQ_SEEK_DATA_READ, &subreq->flags);
+
+ netfs_stat(&netfs_n_rh_short_read);
+ trace_netfs_sreq(subreq, netfs_sreq_trace_resubmit_short);
+
+ netfs_get_read_subrequest(subreq);
+ atomic_inc(&rreq->nr_rd_ops);
+ if (subreq->source == NETFS_READ_FROM_CACHE)
+ netfs_read_from_cache(rreq, subreq, true);
+ else
+ netfs_read_from_server(rreq, subreq);
+}
+
+/*
+ * Resubmit any short or failed operations. Returns true if we got the rreq
+ * ref back.
+ */
+static bool netfs_rreq_perform_resubmissions(struct netfs_read_request *rreq)
+{
+ struct netfs_read_subrequest *subreq;
+
+ WARN_ON(in_interrupt());
+
+ trace_netfs_rreq(rreq, netfs_rreq_trace_resubmit);
+
+ /* We don't want terminating submissions trying to wake us up whilst
+ * we're still going through the list.
+ */
+ atomic_inc(&rreq->nr_rd_ops);
+
+ __clear_bit(NETFS_RREQ_INCOMPLETE_IO, &rreq->flags);
+ list_for_each_entry(subreq, &rreq->subrequests, rreq_link) {
+ if (subreq->error) {
+ if (subreq->source != NETFS_READ_FROM_CACHE)
+ break;
+ subreq->source = NETFS_DOWNLOAD_FROM_SERVER;
+ subreq->error = 0;
+ netfs_stat(&netfs_n_rh_download_instead);
+ trace_netfs_sreq(subreq, netfs_sreq_trace_download_instead);
+ netfs_get_read_subrequest(subreq);
+ atomic_inc(&rreq->nr_rd_ops);
+ netfs_read_from_server(rreq, subreq);
+ } else if (test_bit(NETFS_SREQ_SHORT_READ, &subreq->flags)) {
+ netfs_rreq_short_read(rreq, subreq);
+ }
+ }
+
+ /* If we decrement nr_rd_ops to 0, the usage ref belongs to us. */
+ if (atomic_dec_and_test(&rreq->nr_rd_ops))
+ return true;
+
+ wake_up_var(&rreq->nr_rd_ops);
+ return false;
+}
+
+/*
+ * Check to see if the data read is still valid.
+ */
+static void netfs_rreq_is_still_valid(struct netfs_read_request *rreq)
+{
+ struct netfs_read_subrequest *subreq;
+
+ if (!rreq->netfs_ops->is_still_valid ||
+ rreq->netfs_ops->is_still_valid(rreq))
+ return;
+
+ list_for_each_entry(subreq, &rreq->subrequests, rreq_link) {
+ if (subreq->source == NETFS_READ_FROM_CACHE) {
+ subreq->error = -ESTALE;
+ __set_bit(NETFS_RREQ_INCOMPLETE_IO, &rreq->flags);
+ }
+ }
+}
+
+/*
+ * Assess the state of a read request and decide what to do next.
+ *
+ * Note that we could be in an ordinary kernel thread, on a workqueue or in
+ * softirq context at this point. We inherit a ref from the caller.
+ */
+static void netfs_rreq_assess(struct netfs_read_request *rreq, bool was_async)
+{
+ trace_netfs_rreq(rreq, netfs_rreq_trace_assess);
+
+again:
+ netfs_rreq_is_still_valid(rreq);
+
+ if (!test_bit(NETFS_RREQ_FAILED, &rreq->flags) &&
+ test_bit(NETFS_RREQ_INCOMPLETE_IO, &rreq->flags)) {
+ if (netfs_rreq_perform_resubmissions(rreq))
+ goto again;
+ return;
+ }
+
+ netfs_rreq_unlock(rreq);
+
+ clear_bit_unlock(NETFS_RREQ_IN_PROGRESS, &rreq->flags);
+ wake_up_bit(&rreq->flags, NETFS_RREQ_IN_PROGRESS);
+
+ if (test_bit(NETFS_RREQ_WRITE_TO_CACHE, &rreq->flags))
+ return netfs_rreq_write_to_cache(rreq, was_async);
+
+ netfs_rreq_completed(rreq, was_async);
+}
+
+static void netfs_rreq_work(struct work_struct *work)
+{
+ struct netfs_read_request *rreq =
+ container_of(work, struct netfs_read_request, work);
+ netfs_rreq_assess(rreq, false);
+}
+
+/*
+ * Handle the completion of all outstanding I/O operations on a read request.
+ * We inherit a ref from the caller.
+ */
+static void netfs_rreq_terminated(struct netfs_read_request *rreq,
+ bool was_async)
+{
+ if (test_bit(NETFS_RREQ_INCOMPLETE_IO, &rreq->flags) &&
+ was_async) {
+ if (!queue_work(system_unbound_wq, &rreq->work))
+ BUG();
+ } else {
+ netfs_rreq_assess(rreq, was_async);
+ }
+}
+
+/**
+ * netfs_subreq_terminated - Note the termination of an I/O operation.
+ * @subreq: The I/O request that has terminated.
+ * @transferred_or_error: The amount of data transferred or an error code.
+ * @was_async: The termination was asynchronous
+ *
+ * This tells the read helper that a contributory I/O operation has terminated,
+ * one way or another, and that it should integrate the results.
+ *
+ * The caller indicates in @transferred_or_error the outcome of the operation,
+ * supplying a positive value to indicate the number of bytes transferred, 0 to
+ * indicate a failure to transfer anything that should be retried or a negative
+ * error code. The helper will look after reissuing I/O operations as
+ * appropriate and writing downloaded data to the cache.
+ *
+ * If @was_async is true, the caller might be running in softirq or interrupt
+ * context and we can't sleep.
+ */
+void netfs_subreq_terminated(struct netfs_read_subrequest *subreq,
+ ssize_t transferred_or_error,
+ bool was_async)
+{
+ struct netfs_read_request *rreq = subreq->rreq;
+ int u;
+
+ _enter("[%u]{%llx,%lx},%zd",
+ subreq->debug_index, subreq->start, subreq->flags,
+ transferred_or_error);
+
+ switch (subreq->source) {
+ case NETFS_READ_FROM_CACHE:
+ netfs_stat(&netfs_n_rh_read_done);
+ break;
+ case NETFS_DOWNLOAD_FROM_SERVER:
+ netfs_stat(&netfs_n_rh_download_done);
+ break;
+ default:
+ break;
+ }
+
+ if (IS_ERR_VALUE(transferred_or_error)) {
+ subreq->error = transferred_or_error;
+ trace_netfs_failure(rreq, subreq, transferred_or_error,
+ netfs_fail_read);
+ goto failed;
+ }
+
+ if (WARN(transferred_or_error > subreq->len - subreq->transferred,
+ "Subreq overread: R%x[%x] %zd > %zu - %zu",
+ rreq->debug_id, subreq->debug_index,
+ transferred_or_error, subreq->len, subreq->transferred))
+ transferred_or_error = subreq->len - subreq->transferred;
+
+ subreq->error = 0;
+ subreq->transferred += transferred_or_error;
+ if (subreq->transferred < subreq->len)
+ goto incomplete;
+
+complete:
+ __clear_bit(NETFS_SREQ_NO_PROGRESS, &subreq->flags);
+ if (test_bit(NETFS_SREQ_WRITE_TO_CACHE, &subreq->flags))
+ set_bit(NETFS_RREQ_WRITE_TO_CACHE, &rreq->flags);
+
+out:
+ trace_netfs_sreq(subreq, netfs_sreq_trace_terminated);
+
+ /* If we decrement nr_rd_ops to 0, the ref belongs to us. */
+ u = atomic_dec_return(&rreq->nr_rd_ops);
+ if (u == 0)
+ netfs_rreq_terminated(rreq, was_async);
+ else if (u == 1)
+ wake_up_var(&rreq->nr_rd_ops);
+
+ netfs_put_subrequest(subreq, was_async);
+ return;
+
+incomplete:
+ if (test_bit(NETFS_SREQ_CLEAR_TAIL, &subreq->flags)) {
+ netfs_clear_unread(subreq);
+ subreq->transferred = subreq->len;
+ goto complete;
+ }
+
+ if (transferred_or_error == 0) {
+ if (__test_and_set_bit(NETFS_SREQ_NO_PROGRESS, &subreq->flags)) {
+ subreq->error = -ENODATA;
+ goto failed;
+ }
+ } else {
+ __clear_bit(NETFS_SREQ_NO_PROGRESS, &subreq->flags);
+ }
+
+ __set_bit(NETFS_SREQ_SHORT_READ, &subreq->flags);
+ set_bit(NETFS_RREQ_INCOMPLETE_IO, &rreq->flags);
+ goto out;
+
+failed:
+ if (subreq->source == NETFS_READ_FROM_CACHE) {
+ netfs_stat(&netfs_n_rh_read_failed);
+ set_bit(NETFS_RREQ_INCOMPLETE_IO, &rreq->flags);
+ } else {
+ netfs_stat(&netfs_n_rh_download_failed);
+ set_bit(NETFS_RREQ_FAILED, &rreq->flags);
+ rreq->error = subreq->error;
+ }
+ goto out;
+}
+EXPORT_SYMBOL(netfs_subreq_terminated);
+
+static enum netfs_read_source netfs_cache_prepare_read(struct netfs_read_subrequest *subreq,
+ loff_t i_size)
+{
+ struct netfs_read_request *rreq = subreq->rreq;
+ struct netfs_cache_resources *cres = &rreq->cache_resources;
+
+ if (cres->ops)
+ return cres->ops->prepare_read(subreq, i_size);
+ if (subreq->start >= rreq->i_size)
+ return NETFS_FILL_WITH_ZEROES;
+ return NETFS_DOWNLOAD_FROM_SERVER;
+}
+
+/*
+ * Work out what sort of subrequest the next one will be.
+ */
+static enum netfs_read_source
+netfs_rreq_prepare_read(struct netfs_read_request *rreq,
+ struct netfs_read_subrequest *subreq)
+{
+ enum netfs_read_source source;
+
+ _enter("%llx-%llx,%llx", subreq->start, subreq->start + subreq->len, rreq->i_size);
+
+ source = netfs_cache_prepare_read(subreq, rreq->i_size);
+ if (source == NETFS_INVALID_READ)
+ goto out;
+
+ if (source == NETFS_DOWNLOAD_FROM_SERVER) {
+ /* Call out to the netfs to let it shrink the request to fit
+ * its own I/O sizes and boundaries. If it shinks it here, it
+ * will be called again to make simultaneous calls; if it wants
+ * to make serial calls, it can indicate a short read and then
+ * we will call it again.
+ */
+ if (subreq->len > rreq->i_size - subreq->start)
+ subreq->len = rreq->i_size - subreq->start;
+
+ if (rreq->netfs_ops->clamp_length &&
+ !rreq->netfs_ops->clamp_length(subreq)) {
+ source = NETFS_INVALID_READ;
+ goto out;
+ }
+ }
+
+ if (WARN_ON(subreq->len == 0))
+ source = NETFS_INVALID_READ;
+
+out:
+ subreq->source = source;
+ trace_netfs_sreq(subreq, netfs_sreq_trace_prepare);
+ return source;
+}
+
+/*
+ * Slice off a piece of a read request and submit an I/O request for it.
+ */
+static bool netfs_rreq_submit_slice(struct netfs_read_request *rreq,
+ unsigned int *_debug_index)
+{
+ struct netfs_read_subrequest *subreq;
+ enum netfs_read_source source;
+
+ subreq = netfs_alloc_subrequest(rreq);
+ if (!subreq)
+ return false;
+
+ subreq->debug_index = (*_debug_index)++;
+ subreq->start = rreq->start + rreq->submitted;
+ subreq->len = rreq->len - rreq->submitted;
+
+ _debug("slice %llx,%zx,%zx", subreq->start, subreq->len, rreq->submitted);
+ list_add_tail(&subreq->rreq_link, &rreq->subrequests);
+
+ /* Call out to the cache to find out what it can do with the remaining
+ * subset. It tells us in subreq->flags what it decided should be done
+ * and adjusts subreq->len down if the subset crosses a cache boundary.
+ *
+ * Then when we hand the subset, it can choose to take a subset of that
+ * (the starts must coincide), in which case, we go around the loop
+ * again and ask it to download the next piece.
+ */
+ source = netfs_rreq_prepare_read(rreq, subreq);
+ if (source == NETFS_INVALID_READ)
+ goto subreq_failed;
+
+ atomic_inc(&rreq->nr_rd_ops);
+
+ rreq->submitted += subreq->len;
+
+ trace_netfs_sreq(subreq, netfs_sreq_trace_submit);
+ switch (source) {
+ case NETFS_FILL_WITH_ZEROES:
+ netfs_fill_with_zeroes(rreq, subreq);
+ break;
+ case NETFS_DOWNLOAD_FROM_SERVER:
+ netfs_read_from_server(rreq, subreq);
+ break;
+ case NETFS_READ_FROM_CACHE:
+ netfs_read_from_cache(rreq, subreq, false);
+ break;
+ default:
+ BUG();
+ }
+
+ return true;
+
+subreq_failed:
+ rreq->error = subreq->error;
+ netfs_put_subrequest(subreq, false);
+ return false;
+}
+
+static void netfs_cache_expand_readahead(struct netfs_read_request *rreq,
+ loff_t *_start, size_t *_len, loff_t i_size)
+{
+ struct netfs_cache_resources *cres = &rreq->cache_resources;
+
+ if (cres->ops && cres->ops->expand_readahead)
+ cres->ops->expand_readahead(cres, _start, _len, i_size);
+}
+
+static void netfs_rreq_expand(struct netfs_read_request *rreq,
+ struct readahead_control *ractl)
+{
+ /* Give the cache a chance to change the request parameters. The
+ * resultant request must contain the original region.
+ */
+ netfs_cache_expand_readahead(rreq, &rreq->start, &rreq->len, rreq->i_size);
+
+ /* Give the netfs a chance to change the request parameters. The
+ * resultant request must contain the original region.
+ */
+ if (rreq->netfs_ops->expand_readahead)
+ rreq->netfs_ops->expand_readahead(rreq);
+
+ /* Expand the request if the cache wants it to start earlier. Note
+ * that the expansion may get further extended if the VM wishes to
+ * insert THPs and the preferred start and/or end wind up in the middle
+ * of THPs.
+ *
+ * If this is the case, however, the THP size should be an integer
+ * multiple of the cache granule size, so we get a whole number of
+ * granules to deal with.
+ */
+ if (rreq->start != readahead_pos(ractl) ||
+ rreq->len != readahead_length(ractl)) {
+ readahead_expand(ractl, rreq->start, rreq->len);
+ rreq->start = readahead_pos(ractl);
+ rreq->len = readahead_length(ractl);
+
+ trace_netfs_read(rreq, readahead_pos(ractl), readahead_length(ractl),
+ netfs_read_trace_expanded);
+ }
+}
+
+/**
+ * netfs_readahead - Helper to manage a read request
+ * @ractl: The description of the readahead request
+ * @ops: The network filesystem's operations for the helper to use
+ * @netfs_priv: Private netfs data to be retained in the request
+ *
+ * Fulfil a readahead request by drawing data from the cache if possible, or
+ * the netfs if not. Space beyond the EOF is zero-filled. Multiple I/O
+ * requests from different sources will get munged together. If necessary, the
+ * readahead window can be expanded in either direction to a more convenient
+ * alighment for RPC efficiency or to make storage in the cache feasible.
+ *
+ * The calling netfs must provide a table of operations, only one of which,
+ * issue_op, is mandatory. It may also be passed a private token, which will
+ * be retained in rreq->netfs_priv and will be cleaned up by ops->cleanup().
+ *
+ * This is usable whether or not caching is enabled.
+ */
+void netfs_readahead(struct readahead_control *ractl,
+ const struct netfs_read_request_ops *ops,
+ void *netfs_priv)
+{
+ struct netfs_read_request *rreq;
+ struct page *page;
+ unsigned int debug_index = 0;
+ int ret;
+
+ _enter("%lx,%x", readahead_index(ractl), readahead_count(ractl));
+
+ if (readahead_count(ractl) == 0)
+ goto cleanup;
+
+ rreq = netfs_alloc_read_request(ops, netfs_priv, ractl->file);
+ if (!rreq)
+ goto cleanup;
+ rreq->mapping = ractl->mapping;
+ rreq->start = readahead_pos(ractl);
+ rreq->len = readahead_length(ractl);
+
+ if (ops->begin_cache_operation) {
+ ret = ops->begin_cache_operation(rreq);
+ if (ret == -ENOMEM || ret == -EINTR || ret == -ERESTARTSYS)
+ goto cleanup_free;
+ }
+
+ netfs_stat(&netfs_n_rh_readahead);
+ trace_netfs_read(rreq, readahead_pos(ractl), readahead_length(ractl),
+ netfs_read_trace_readahead);
+
+ netfs_rreq_expand(rreq, ractl);
+
+ atomic_set(&rreq->nr_rd_ops, 1);
+ do {
+ if (!netfs_rreq_submit_slice(rreq, &debug_index))
+ break;
+
+ } while (rreq->submitted < rreq->len);
+
+ /* Drop the refs on the pages here rather than in the cache or
+ * filesystem. The locks will be dropped in netfs_rreq_unlock().
+ */
+ while ((page = readahead_page(ractl)))
+ put_page(page);
+
+ /* If we decrement nr_rd_ops to 0, the ref belongs to us. */
+ if (atomic_dec_and_test(&rreq->nr_rd_ops))
+ netfs_rreq_assess(rreq, false);
+ return;
+
+cleanup_free:
+ netfs_put_read_request(rreq, false);
+ return;
+cleanup:
+ if (netfs_priv)
+ ops->cleanup(ractl->mapping, netfs_priv);
+ return;
+}
+EXPORT_SYMBOL(netfs_readahead);
+
+/**
+ * netfs_readpage - Helper to manage a readpage request
+ * @file: The file to read from
+ * @page: The page to read
+ * @ops: The network filesystem's operations for the helper to use
+ * @netfs_priv: Private netfs data to be retained in the request
+ *
+ * Fulfil a readpage request by drawing data from the cache if possible, or the
+ * netfs if not. Space beyond the EOF is zero-filled. Multiple I/O requests
+ * from different sources will get munged together.
+ *
+ * The calling netfs must provide a table of operations, only one of which,
+ * issue_op, is mandatory. It may also be passed a private token, which will
+ * be retained in rreq->netfs_priv and will be cleaned up by ops->cleanup().
+ *
+ * This is usable whether or not caching is enabled.
+ */
+int netfs_readpage(struct file *file,
+ struct page *page,
+ const struct netfs_read_request_ops *ops,
+ void *netfs_priv)
+{
+ struct netfs_read_request *rreq;
+ unsigned int debug_index = 0;
+ int ret;
+
+ _enter("%lx", page_index(page));
+
+ rreq = netfs_alloc_read_request(ops, netfs_priv, file);
+ if (!rreq) {
+ if (netfs_priv)
+ ops->cleanup(netfs_priv, page_file_mapping(page));
+ unlock_page(page);
+ return -ENOMEM;
+ }
+ rreq->mapping = page_file_mapping(page);
+ rreq->start = page_file_offset(page);
+ rreq->len = thp_size(page);
+
+ if (ops->begin_cache_operation) {
+ ret = ops->begin_cache_operation(rreq);
+ if (ret == -ENOMEM || ret == -EINTR || ret == -ERESTARTSYS) {
+ unlock_page(page);
+ goto out;
+ }
+ }
+
+ netfs_stat(&netfs_n_rh_readpage);
+ trace_netfs_read(rreq, rreq->start, rreq->len, netfs_read_trace_readpage);
+
+ netfs_get_read_request(rreq);
+
+ atomic_set(&rreq->nr_rd_ops, 1);
+ do {
+ if (!netfs_rreq_submit_slice(rreq, &debug_index))
+ break;
+
+ } while (rreq->submitted < rreq->len);
+
+ /* Keep nr_rd_ops incremented so that the ref always belongs to us, and
+ * the service code isn't punted off to a random thread pool to
+ * process.
+ */
+ do {
+ wait_var_event(&rreq->nr_rd_ops, atomic_read(&rreq->nr_rd_ops) == 1);
+ netfs_rreq_assess(rreq, false);
+ } while (test_bit(NETFS_RREQ_IN_PROGRESS, &rreq->flags));
+
+ ret = rreq->error;
+ if (ret == 0 && rreq->submitted < rreq->len) {
+ trace_netfs_failure(rreq, NULL, ret, netfs_fail_short_readpage);
+ ret = -EIO;
+ }
+out:
+ netfs_put_read_request(rreq, false);
+ return ret;
+}
+EXPORT_SYMBOL(netfs_readpage);
+
+static void netfs_clear_thp(struct page *page)
+{
+ unsigned int i;
+
+ for (i = 0; i < thp_nr_pages(page); i++)
+ clear_highpage(page + i);
+}
+
+/**
+ * netfs_write_begin - Helper to prepare for writing
+ * @file: The file to read from
+ * @mapping: The mapping to read from
+ * @pos: File position at which the write will begin
+ * @len: The length of the write in this page
+ * @flags: AOP_* flags
+ * @_page: Where to put the resultant page
+ * @_fsdata: Place for the netfs to store a cookie
+ * @ops: The network filesystem's operations for the helper to use
+ * @netfs_priv: Private netfs data to be retained in the request
+ *
+ * Pre-read data for a write-begin request by drawing data from the cache if
+ * possible, or the netfs if not. Space beyond the EOF is zero-filled.
+ * Multiple I/O requests from different sources will get munged together. If
+ * necessary, the readahead window can be expanded in either direction to a
+ * more convenient alighment for RPC efficiency or to make storage in the cache
+ * feasible.
+ *
+ * The calling netfs must provide a table of operations, only one of which,
+ * issue_op, is mandatory.
+ *
+ * The check_write_begin() operation can be provided to check for and flush
+ * conflicting writes once the page is grabbed and locked. It is passed a
+ * pointer to the fsdata cookie that gets returned to the VM to be passed to
+ * write_end. It is permitted to sleep. It should return 0 if the request
+ * should go ahead; unlock the page and return -EAGAIN to cause the page to be
+ * regot; or return an error.
+ *
+ * This is usable whether or not caching is enabled.
+ */
+int netfs_write_begin(struct file *file, struct address_space *mapping,
+ loff_t pos, unsigned int len, unsigned int flags,
+ struct page **_page, void **_fsdata,
+ const struct netfs_read_request_ops *ops,
+ void *netfs_priv)
+{
+ struct netfs_read_request *rreq;
+ struct page *page, *xpage;
+ struct inode *inode = file_inode(file);
+ unsigned int debug_index = 0;
+ pgoff_t index = pos >> PAGE_SHIFT;
+ int pos_in_page = pos & ~PAGE_MASK;
+ loff_t size;
+ int ret;
+
+ DEFINE_READAHEAD(ractl, file, NULL, mapping, index);
+
+retry:
+ page = grab_cache_page_write_begin(mapping, index, 0);
+ if (!page)
+ return -ENOMEM;
+
+ if (ops->check_write_begin) {
+ /* Allow the netfs (eg. ceph) to flush conflicts. */
+ ret = ops->check_write_begin(file, pos, len, page, _fsdata);
+ if (ret < 0) {
+ trace_netfs_failure(NULL, NULL, ret, netfs_fail_check_write_begin);
+ if (ret == -EAGAIN)
+ goto retry;
+ goto error;
+ }
+ }
+
+ if (PageUptodate(page))
+ goto have_page;
+
+ /* If the page is beyond the EOF, we want to clear it - unless it's
+ * within the cache granule containing the EOF, in which case we need
+ * to preload the granule.
+ */
+ size = i_size_read(inode);
+ if (!ops->is_cache_enabled(inode) &&
+ ((pos_in_page == 0 && len == thp_size(page)) ||
+ (pos >= size) ||
+ (pos_in_page == 0 && (pos + len) >= size))) {
+ netfs_clear_thp(page);
+ SetPageUptodate(page);
+ netfs_stat(&netfs_n_rh_write_zskip);
+ goto have_page_no_wait;
+ }
+
+ ret = -ENOMEM;
+ rreq = netfs_alloc_read_request(ops, netfs_priv, file);
+ if (!rreq)
+ goto error;
+ rreq->mapping = page->mapping;
+ rreq->start = page_offset(page);
+ rreq->len = thp_size(page);
+ rreq->no_unlock_page = page->index;
+ __set_bit(NETFS_RREQ_NO_UNLOCK_PAGE, &rreq->flags);
+ netfs_priv = NULL;
+
+ if (ops->begin_cache_operation) {
+ ret = ops->begin_cache_operation(rreq);
+ if (ret == -ENOMEM || ret == -EINTR || ret == -ERESTARTSYS)
+ goto error_put;
+ }
+
+ netfs_stat(&netfs_n_rh_write_begin);
+ trace_netfs_read(rreq, pos, len, netfs_read_trace_write_begin);
+
+ /* Expand the request to meet caching requirements and download
+ * preferences.
+ */
+ ractl._nr_pages = thp_nr_pages(page);
+ netfs_rreq_expand(rreq, &ractl);
+ netfs_get_read_request(rreq);
+
+ /* We hold the page locks, so we can drop the references */
+ while ((xpage = readahead_page(&ractl)))
+ if (xpage != page)
+ put_page(xpage);
+
+ atomic_set(&rreq->nr_rd_ops, 1);
+ do {
+ if (!netfs_rreq_submit_slice(rreq, &debug_index))
+ break;
+
+ } while (rreq->submitted < rreq->len);
+
+ /* Keep nr_rd_ops incremented so that the ref always belongs to us, and
+ * the service code isn't punted off to a random thread pool to
+ * process.
+ */
+ for (;;) {
+ wait_var_event(&rreq->nr_rd_ops, atomic_read(&rreq->nr_rd_ops) == 1);
+ netfs_rreq_assess(rreq, false);
+ if (!test_bit(NETFS_RREQ_IN_PROGRESS, &rreq->flags))
+ break;
+ cond_resched();
+ }
+
+ ret = rreq->error;
+ if (ret == 0 && rreq->submitted < rreq->len) {
+ trace_netfs_failure(rreq, NULL, ret, netfs_fail_short_write_begin);
+ ret = -EIO;
+ }
+ netfs_put_read_request(rreq, false);
+ if (ret < 0)
+ goto error;
+
+have_page:
+ ret = wait_on_page_fscache_killable(page);
+ if (ret < 0)
+ goto error;
+have_page_no_wait:
+ if (netfs_priv)
+ ops->cleanup(netfs_priv, mapping);
+ *_page = page;
+ _leave(" = 0");
+ return 0;
+
+error_put:
+ netfs_put_read_request(rreq, false);
+error:
+ unlock_page(page);
+ put_page(page);
+ if (netfs_priv)
+ ops->cleanup(netfs_priv, mapping);
+ _leave(" = %d", ret);
+ return ret;
+}
+EXPORT_SYMBOL(netfs_write_begin);
diff --git a/fs/netfs/stats.c b/fs/netfs/stats.c
new file mode 100644
index 000000000000..9ae538c85378
--- /dev/null
+++ b/fs/netfs/stats.c
@@ -0,0 +1,59 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/* Netfs support statistics
+ *
+ * Copyright (C) 2021 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ */
+
+#include <linux/export.h>
+#include <linux/seq_file.h>
+#include <linux/netfs.h>
+#include "internal.h"
+
+atomic_t netfs_n_rh_readahead;
+atomic_t netfs_n_rh_readpage;
+atomic_t netfs_n_rh_rreq;
+atomic_t netfs_n_rh_sreq;
+atomic_t netfs_n_rh_download;
+atomic_t netfs_n_rh_download_done;
+atomic_t netfs_n_rh_download_failed;
+atomic_t netfs_n_rh_download_instead;
+atomic_t netfs_n_rh_read;
+atomic_t netfs_n_rh_read_done;
+atomic_t netfs_n_rh_read_failed;
+atomic_t netfs_n_rh_zero;
+atomic_t netfs_n_rh_short_read;
+atomic_t netfs_n_rh_write;
+atomic_t netfs_n_rh_write_begin;
+atomic_t netfs_n_rh_write_done;
+atomic_t netfs_n_rh_write_failed;
+atomic_t netfs_n_rh_write_zskip;
+
+void netfs_stats_show(struct seq_file *m)
+{
+ seq_printf(m, "RdHelp : RA=%u RP=%u WB=%u WBZ=%u rr=%u sr=%u\n",
+ atomic_read(&netfs_n_rh_readahead),
+ atomic_read(&netfs_n_rh_readpage),
+ atomic_read(&netfs_n_rh_write_begin),
+ atomic_read(&netfs_n_rh_write_zskip),
+ atomic_read(&netfs_n_rh_rreq),
+ atomic_read(&netfs_n_rh_sreq));
+ seq_printf(m, "RdHelp : ZR=%u sh=%u sk=%u\n",
+ atomic_read(&netfs_n_rh_zero),
+ atomic_read(&netfs_n_rh_short_read),
+ atomic_read(&netfs_n_rh_write_zskip));
+ seq_printf(m, "RdHelp : DL=%u ds=%u df=%u di=%u\n",
+ atomic_read(&netfs_n_rh_download),
+ atomic_read(&netfs_n_rh_download_done),
+ atomic_read(&netfs_n_rh_download_failed),
+ atomic_read(&netfs_n_rh_download_instead));
+ seq_printf(m, "RdHelp : RD=%u rs=%u rf=%u\n",
+ atomic_read(&netfs_n_rh_read),
+ atomic_read(&netfs_n_rh_read_done),
+ atomic_read(&netfs_n_rh_read_failed));
+ seq_printf(m, "RdHelp : WR=%u ws=%u wf=%u\n",
+ atomic_read(&netfs_n_rh_write),
+ atomic_read(&netfs_n_rh_write_done),
+ atomic_read(&netfs_n_rh_write_failed));
+}
+EXPORT_SYMBOL(netfs_stats_show);
diff --git a/fs/nfs/fs_context.c b/fs/nfs/fs_context.c
index 971a9251c1d9..a06d213d7689 100644
--- a/fs/nfs/fs_context.c
+++ b/fs/nfs/fs_context.c
@@ -463,6 +463,9 @@ static int nfs_fs_context_parse_param(struct fs_context *fc,
if (opt < 0)
return ctx->sloppy ? 1 : opt;
+ if (fc->security)
+ ctx->has_sec_mnt_opts = 1;
+
switch (opt) {
case Opt_source:
if (fc->source)
diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c
index a7fb076a5f44..5a8854de0c19 100644
--- a/fs/nfs/inode.c
+++ b/fs/nfs/inode.c
@@ -335,7 +335,7 @@ nfs_find_actor(struct inode *inode, void *opaque)
if (NFS_FILEID(inode) != fattr->fileid)
return 0;
- if ((S_IFMT & inode->i_mode) != (S_IFMT & fattr->mode))
+ if (inode_wrong_type(inode, fattr->mode))
return 0;
if (nfs_compare_fh(NFS_FH(inode), fh))
return 0;
@@ -1461,7 +1461,7 @@ static int nfs_check_inode_attributes(struct inode *inode, struct nfs_fattr *fat
return 0;
return -ESTALE;
}
- if ((fattr->valid & NFS_ATTR_FATTR_TYPE) && (inode->i_mode & S_IFMT) != (fattr->mode & S_IFMT))
+ if ((fattr->valid & NFS_ATTR_FATTR_TYPE) && inode_wrong_type(inode, fattr->mode))
return -ESTALE;
@@ -1876,7 +1876,7 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
/*
* Make sure the inode's type hasn't changed.
*/
- if ((fattr->valid & NFS_ATTR_FATTR_TYPE) && (inode->i_mode & S_IFMT) != (fattr->mode & S_IFMT)) {
+ if ((fattr->valid & NFS_ATTR_FATTR_TYPE) && inode_wrong_type(inode, fattr->mode)) {
/*
* Big trouble! The inode has become a different object.
*/
diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h
index 7b644d6c09e4..7395d0977b7d 100644
--- a/fs/nfs/internal.h
+++ b/fs/nfs/internal.h
@@ -96,6 +96,7 @@ struct nfs_fs_context {
char *fscache_uniq;
unsigned short protofamily;
unsigned short mountfamily;
+ bool has_sec_mnt_opts;
struct {
union {
diff --git a/fs/nfs/super.c b/fs/nfs/super.c
index 94885c6f8f54..4aaa1f5dd381 100644
--- a/fs/nfs/super.c
+++ b/fs/nfs/super.c
@@ -1045,7 +1045,7 @@ static void nfs_fill_super(struct super_block *sb, struct nfs_fs_context *ctx)
sb->s_blocksize = 0;
sb->s_xattr = server->nfs_client->cl_nfs_mod->xattr;
sb->s_op = server->nfs_client->cl_nfs_mod->sops;
- if (ctx && ctx->bsize)
+ if (ctx->bsize)
sb->s_blocksize = nfs_block_size(ctx->bsize, &sb->s_blocksize_bits);
if (server->nfs_client->rpc_ops->version != 2) {
@@ -1077,6 +1077,7 @@ static void nfs_fill_super(struct super_block *sb, struct nfs_fs_context *ctx)
&sb->s_blocksize_bits);
nfs_super_set_maxbytes(sb, server->maxfilesize);
+ server->has_sec_mnt_opts = ctx->has_sec_mnt_opts;
}
static int nfs_compare_mount_options(const struct super_block *s, const struct nfs_server *b,
@@ -1193,6 +1194,9 @@ static int nfs_compare_super(struct super_block *sb, struct fs_context *fc)
return 0;
if (!nfs_compare_userns(old, server))
return 0;
+ if ((old->has_sec_mnt_opts || fc->security) &&
+ security_sb_mnt_opts_compat(sb, fc->security))
+ return 0;
return nfs_compare_mount_options(sb, server, fc);
}
diff --git a/fs/nfs_common/nfsacl.c b/fs/nfs_common/nfsacl.c
index 79c563c1a5e8..5a5bd85d08f8 100644
--- a/fs/nfs_common/nfsacl.c
+++ b/fs/nfs_common/nfsacl.c
@@ -136,6 +136,77 @@ int nfsacl_encode(struct xdr_buf *buf, unsigned int base, struct inode *inode,
}
EXPORT_SYMBOL_GPL(nfsacl_encode);
+/**
+ * nfs_stream_encode_acl - Encode an NFSv3 ACL
+ *
+ * @xdr: an xdr_stream positioned to receive an encoded ACL
+ * @inode: inode of file whose ACL this is
+ * @acl: posix_acl to encode
+ * @encode_entries: whether to encode ACEs as well
+ * @typeflag: ACL type: NFS_ACL_DEFAULT or zero
+ *
+ * Return values:
+ * %false: The ACL could not be encoded
+ * %true: @xdr is advanced to the next available position
+ */
+bool nfs_stream_encode_acl(struct xdr_stream *xdr, struct inode *inode,
+ struct posix_acl *acl, int encode_entries,
+ int typeflag)
+{
+ const size_t elem_size = XDR_UNIT * 3;
+ u32 entries = (acl && acl->a_count) ? max_t(int, acl->a_count, 4) : 0;
+ struct nfsacl_encode_desc nfsacl_desc = {
+ .desc = {
+ .elem_size = elem_size,
+ .array_len = encode_entries ? entries : 0,
+ .xcode = xdr_nfsace_encode,
+ },
+ .acl = acl,
+ .typeflag = typeflag,
+ .uid = inode->i_uid,
+ .gid = inode->i_gid,
+ };
+ struct nfsacl_simple_acl aclbuf;
+ unsigned int base;
+ int err;
+
+ if (entries > NFS_ACL_MAX_ENTRIES)
+ return false;
+ if (xdr_stream_encode_u32(xdr, entries) < 0)
+ return false;
+
+ if (encode_entries && acl && acl->a_count == 3) {
+ struct posix_acl *acl2 = &aclbuf.acl;
+
+ /* Avoid the use of posix_acl_alloc(). nfsacl_encode() is
+ * invoked in contexts where a memory allocation failure is
+ * fatal. Fortunately this fake ACL is small enough to
+ * construct on the stack. */
+ posix_acl_init(acl2, 4);
+
+ /* Insert entries in canonical order: other orders seem
+ to confuse Solaris VxFS. */
+ acl2->a_entries[0] = acl->a_entries[0]; /* ACL_USER_OBJ */
+ acl2->a_entries[1] = acl->a_entries[1]; /* ACL_GROUP_OBJ */
+ acl2->a_entries[2] = acl->a_entries[1]; /* ACL_MASK */
+ acl2->a_entries[2].e_tag = ACL_MASK;
+ acl2->a_entries[3] = acl->a_entries[2]; /* ACL_OTHER */
+ nfsacl_desc.acl = acl2;
+ }
+
+ base = xdr_stream_pos(xdr);
+ if (!xdr_reserve_space(xdr, XDR_UNIT +
+ elem_size * nfsacl_desc.desc.array_len))
+ return false;
+ err = xdr_encode_array2(xdr->buf, base, &nfsacl_desc.desc);
+ if (err)
+ return false;
+
+ return true;
+}
+EXPORT_SYMBOL_GPL(nfs_stream_encode_acl);
+
+
struct nfsacl_decode_desc {
struct xdr_array2_desc desc;
unsigned int count;
diff --git a/fs/nfsd/Kconfig b/fs/nfsd/Kconfig
index 821e5913faee..5fa38ad9e7e3 100644
--- a/fs/nfsd/Kconfig
+++ b/fs/nfsd/Kconfig
@@ -73,6 +73,7 @@ config NFSD_V4
select NFSD_V3
select FS_POSIX_ACL
select SUNRPC_GSS
+ select CRYPTO
select CRYPTO_MD5
select CRYPTO_SHA256
select GRACE_PERIOD
@@ -98,7 +99,7 @@ config NFSD_BLOCKLAYOUT
help
This option enables support for the exporting pNFS block layouts
in the kernel's NFS server. The pNFS block layout enables NFS
- clients to directly perform I/O to block devices accesible to both
+ clients to directly perform I/O to block devices accessible to both
the server and the clients. See RFC 5663 for more details.
If unsure, say N.
@@ -112,7 +113,7 @@ config NFSD_SCSILAYOUT
help
This option enables support for the exporting pNFS SCSI layouts
in the kernel's NFS server. The pNFS SCSI layout enables NFS
- clients to directly perform I/O to SCSI devices accesible to both
+ clients to directly perform I/O to SCSI devices accessible to both
the server and the clients. See draft-ietf-nfsv4-scsi-layout for
more details.
@@ -126,7 +127,7 @@ config NFSD_FLEXFILELAYOUT
This option enables support for the exporting pNFS Flex File
layouts in the kernel's NFS server. The pNFS Flex File layout
enables NFS clients to directly perform I/O to NFSv3 devices
- accesible to both the server and the clients. See
+ accessible to both the server and the clients. See
draft-ietf-nfsv4-flex-files for more details.
Warning, this server implements the bare minimum functionality
diff --git a/fs/nfsd/filecache.c b/fs/nfsd/filecache.c
index 53fcbf79bdca..7629248fdd53 100644
--- a/fs/nfsd/filecache.c
+++ b/fs/nfsd/filecache.c
@@ -898,6 +898,8 @@ nfsd_file_find_locked(struct inode *inode, unsigned int may_flags,
continue;
if (!nfsd_match_cred(nf->nf_cred, current_cred()))
continue;
+ if (!test_bit(NFSD_FILE_HASHED, &nf->nf_flags))
+ continue;
if (nfsd_file_get(nf) != NULL)
return nf;
}
diff --git a/fs/nfsd/netns.h b/fs/nfsd/netns.h
index c330f5bd0cf3..a75abeb1e698 100644
--- a/fs/nfsd/netns.h
+++ b/fs/nfsd/netns.h
@@ -51,9 +51,6 @@ struct nfsd_net {
bool grace_ended;
time64_t boot_time;
- /* internal mount of the "nfsd" pseudofilesystem: */
- struct vfsmount *nfsd_mnt;
-
struct dentry *nfsd_client_dir;
/*
@@ -130,6 +127,9 @@ struct nfsd_net {
wait_queue_head_t ntf_wq;
atomic_t ntf_refcnt;
+ /* Allow umount to wait for nfsd state cleanup */
+ struct completion nfsd_shutdown_complete;
+
/*
* clientid and stateid data for construction of net unique COPY
* stateids.
diff --git a/fs/nfsd/nfs2acl.c b/fs/nfsd/nfs2acl.c
index 855e17772eba..4b43929c1f25 100644
--- a/fs/nfsd/nfs2acl.c
+++ b/fs/nfsd/nfs2acl.c
@@ -242,79 +242,61 @@ static int nfsaclsvc_decode_accessargs(struct svc_rqst *rqstp, __be32 *p)
/* GETACL */
static int nfsaclsvc_encode_getaclres(struct svc_rqst *rqstp, __be32 *p)
{
+ struct xdr_stream *xdr = &rqstp->rq_res_stream;
struct nfsd3_getaclres *resp = rqstp->rq_resp;
struct dentry *dentry = resp->fh.fh_dentry;
struct inode *inode;
- struct kvec *head = rqstp->rq_res.head;
- unsigned int base;
- int n;
int w;
- *p++ = resp->status;
- if (resp->status != nfs_ok)
- return xdr_ressize_check(rqstp, p);
+ if (!svcxdr_encode_stat(xdr, resp->status))
+ return 0;
- /*
- * Since this is version 2, the check for nfserr in
- * nfsd_dispatch actually ensures the following cannot happen.
- * However, it seems fragile to depend on that.
- */
if (dentry == NULL || d_really_is_negative(dentry))
- return 0;
+ return 1;
inode = d_inode(dentry);
- p = nfs2svc_encode_fattr(rqstp, p, &resp->fh, &resp->stat);
- *p++ = htonl(resp->mask);
- if (!xdr_ressize_check(rqstp, p))
+ if (!svcxdr_encode_fattr(rqstp, xdr, &resp->fh, &resp->stat))
+ return 0;
+ if (xdr_stream_encode_u32(xdr, resp->mask) < 0)
return 0;
- base = (char *)p - (char *)head->iov_base;
rqstp->rq_res.page_len = w = nfsacl_size(
(resp->mask & NFS_ACL) ? resp->acl_access : NULL,
(resp->mask & NFS_DFACL) ? resp->acl_default : NULL);
while (w > 0) {
if (!*(rqstp->rq_next_page++))
- return 0;
+ return 1;
w -= PAGE_SIZE;
}
- n = nfsacl_encode(&rqstp->rq_res, base, inode,
- resp->acl_access,
- resp->mask & NFS_ACL, 0);
- if (n > 0)
- n = nfsacl_encode(&rqstp->rq_res, base + n, inode,
- resp->acl_default,
- resp->mask & NFS_DFACL,
- NFS_ACL_DEFAULT);
- return (n > 0);
-}
-
-static int nfsaclsvc_encode_attrstatres(struct svc_rqst *rqstp, __be32 *p)
-{
- struct nfsd_attrstat *resp = rqstp->rq_resp;
-
- *p++ = resp->status;
- if (resp->status != nfs_ok)
- goto out;
+ if (!nfs_stream_encode_acl(xdr, inode, resp->acl_access,
+ resp->mask & NFS_ACL, 0))
+ return 0;
+ if (!nfs_stream_encode_acl(xdr, inode, resp->acl_default,
+ resp->mask & NFS_DFACL, NFS_ACL_DEFAULT))
+ return 0;
- p = nfs2svc_encode_fattr(rqstp, p, &resp->fh, &resp->stat);
-out:
- return xdr_ressize_check(rqstp, p);
+ return 1;
}
/* ACCESS */
static int nfsaclsvc_encode_accessres(struct svc_rqst *rqstp, __be32 *p)
{
+ struct xdr_stream *xdr = &rqstp->rq_res_stream;
struct nfsd3_accessres *resp = rqstp->rq_resp;
- *p++ = resp->status;
- if (resp->status != nfs_ok)
- goto out;
+ if (!svcxdr_encode_stat(xdr, resp->status))
+ return 0;
+ switch (resp->status) {
+ case nfs_ok:
+ if (!svcxdr_encode_fattr(rqstp, xdr, &resp->fh, &resp->stat))
+ return 0;
+ if (xdr_stream_encode_u32(xdr, resp->access) < 0)
+ return 0;
+ break;
+ }
- p = nfs2svc_encode_fattr(rqstp, p, &resp->fh, &resp->stat);
- *p++ = htonl(resp->access);
-out:
- return xdr_ressize_check(rqstp, p);
+ return 1;
}
/*
@@ -329,13 +311,6 @@ static void nfsaclsvc_release_getacl(struct svc_rqst *rqstp)
posix_acl_release(resp->acl_default);
}
-static void nfsaclsvc_release_attrstat(struct svc_rqst *rqstp)
-{
- struct nfsd_attrstat *resp = rqstp->rq_resp;
-
- fh_put(&resp->fh);
-}
-
static void nfsaclsvc_release_access(struct svc_rqst *rqstp)
{
struct nfsd3_accessres *resp = rqstp->rq_resp;
@@ -375,8 +350,8 @@ static const struct svc_procedure nfsd_acl_procedures2[5] = {
[ACLPROC2_SETACL] = {
.pc_func = nfsacld_proc_setacl,
.pc_decode = nfsaclsvc_decode_setaclargs,
- .pc_encode = nfsaclsvc_encode_attrstatres,
- .pc_release = nfsaclsvc_release_attrstat,
+ .pc_encode = nfssvc_encode_attrstatres,
+ .pc_release = nfssvc_release_attrstat,
.pc_argsize = sizeof(struct nfsd3_setaclargs),
.pc_ressize = sizeof(struct nfsd_attrstat),
.pc_cachetype = RC_NOCACHE,
@@ -386,8 +361,8 @@ static const struct svc_procedure nfsd_acl_procedures2[5] = {
[ACLPROC2_GETATTR] = {
.pc_func = nfsacld_proc_getattr,
.pc_decode = nfssvc_decode_fhandleargs,
- .pc_encode = nfsaclsvc_encode_attrstatres,
- .pc_release = nfsaclsvc_release_attrstat,
+ .pc_encode = nfssvc_encode_attrstatres,
+ .pc_release = nfssvc_release_attrstat,
.pc_argsize = sizeof(struct nfsd_fhandle),
.pc_ressize = sizeof(struct nfsd_attrstat),
.pc_cachetype = RC_NOCACHE,
diff --git a/fs/nfsd/nfs3acl.c b/fs/nfsd/nfs3acl.c
index 9a6f18d74d14..a1591feeea22 100644
--- a/fs/nfsd/nfs3acl.c
+++ b/fs/nfsd/nfs3acl.c
@@ -168,22 +168,25 @@ static int nfs3svc_decode_setaclargs(struct svc_rqst *rqstp, __be32 *p)
/* GETACL */
static int nfs3svc_encode_getaclres(struct svc_rqst *rqstp, __be32 *p)
{
+ struct xdr_stream *xdr = &rqstp->rq_res_stream;
struct nfsd3_getaclres *resp = rqstp->rq_resp;
struct dentry *dentry = resp->fh.fh_dentry;
+ struct kvec *head = rqstp->rq_res.head;
+ struct inode *inode = d_inode(dentry);
+ unsigned int base;
+ int n;
+ int w;
- *p++ = resp->status;
- p = nfs3svc_encode_post_op_attr(rqstp, p, &resp->fh);
- if (resp->status == 0 && dentry && d_really_is_positive(dentry)) {
- struct inode *inode = d_inode(dentry);
- struct kvec *head = rqstp->rq_res.head;
- unsigned int base;
- int n;
- int w;
-
- *p++ = htonl(resp->mask);
- if (!xdr_ressize_check(rqstp, p))
+ if (!svcxdr_encode_nfsstat3(xdr, resp->status))
+ return 0;
+ switch (resp->status) {
+ case nfs_ok:
+ if (!svcxdr_encode_post_op_attr(rqstp, xdr, &resp->fh))
+ return 0;
+ if (xdr_stream_encode_u32(xdr, resp->mask) < 0)
return 0;
- base = (char *)p - (char *)head->iov_base;
+
+ base = (char *)xdr->p - (char *)head->iov_base;
rqstp->rq_res.page_len = w = nfsacl_size(
(resp->mask & NFS_ACL) ? resp->acl_access : NULL,
@@ -204,9 +207,11 @@ static int nfs3svc_encode_getaclres(struct svc_rqst *rqstp, __be32 *p)
NFS_ACL_DEFAULT);
if (n <= 0)
return 0;
- } else
- if (!xdr_ressize_check(rqstp, p))
+ break;
+ default:
+ if (!svcxdr_encode_post_op_attr(rqstp, xdr, &resp->fh))
return 0;
+ }
return 1;
}
@@ -214,11 +219,11 @@ static int nfs3svc_encode_getaclres(struct svc_rqst *rqstp, __be32 *p)
/* SETACL */
static int nfs3svc_encode_setaclres(struct svc_rqst *rqstp, __be32 *p)
{
+ struct xdr_stream *xdr = &rqstp->rq_res_stream;
struct nfsd3_attrstat *resp = rqstp->rq_resp;
- *p++ = resp->status;
- p = nfs3svc_encode_post_op_attr(rqstp, p, &resp->fh);
- return xdr_ressize_check(rqstp, p);
+ return svcxdr_encode_nfsstat3(xdr, resp->status) &&
+ svcxdr_encode_post_op_attr(rqstp, xdr, &resp->fh);
}
/*
diff --git a/fs/nfsd/nfs3proc.c b/fs/nfsd/nfs3proc.c
index 8675851199f8..17715a6c7a40 100644
--- a/fs/nfsd/nfs3proc.c
+++ b/fs/nfsd/nfs3proc.c
@@ -126,14 +126,15 @@ nfsd3_proc_readlink(struct svc_rqst *rqstp)
{
struct nfsd_fhandle *argp = rqstp->rq_argp;
struct nfsd3_readlinkres *resp = rqstp->rq_resp;
- char *buffer = page_address(*(rqstp->rq_next_page++));
dprintk("nfsd: READLINK(3) %s\n", SVCFH_fmt(&argp->fh));
/* Read the symlink. */
fh_copy(&resp->fh, &argp->fh);
resp->len = NFS3_MAXPATHLEN;
- resp->status = nfsd_readlink(rqstp, &resp->fh, buffer, &resp->len);
+ resp->pages = rqstp->rq_next_page++;
+ resp->status = nfsd_readlink(rqstp, &resp->fh,
+ page_address(*resp->pages), &resp->len);
return rpc_success;
}
@@ -158,6 +159,7 @@ nfsd3_proc_read(struct svc_rqst *rqstp)
v = 0;
len = argp->count;
+ resp->pages = rqstp->rq_next_page;
while (len > 0) {
struct page *page = *(rqstp->rq_next_page++);
@@ -439,17 +441,30 @@ static void nfsd3_init_dirlist_pages(struct svc_rqst *rqstp,
struct nfsd3_readdirres *resp,
int count)
{
+ struct xdr_buf *buf = &resp->dirlist;
+ struct xdr_stream *xdr = &resp->xdr;
+
count = min_t(u32, count, svc_max_payload(rqstp));
- /* Convert byte count to number of words (i.e. >> 2),
- * and reserve room for the NULL ptr & eof flag (-2 words) */
- resp->buflen = (count >> 2) - 2;
+ memset(buf, 0, sizeof(*buf));
- resp->buffer = page_address(*rqstp->rq_next_page);
+ /* Reserve room for the NULL ptr & eof flag (-2 words) */
+ buf->buflen = count - XDR_UNIT * 2;
+ buf->pages = rqstp->rq_next_page;
while (count > 0) {
rqstp->rq_next_page++;
count -= PAGE_SIZE;
}
+
+ /* This is xdr_init_encode(), but it assumes that
+ * the head kvec has already been consumed. */
+ xdr_set_scratch_buffer(xdr, NULL, 0);
+ xdr->buf = buf;
+ xdr->page_ptr = buf->pages;
+ xdr->iov = NULL;
+ xdr->p = page_address(*buf->pages);
+ xdr->end = xdr->p + (PAGE_SIZE >> 2);
+ xdr->rqst = NULL;
}
/*
@@ -460,10 +475,7 @@ nfsd3_proc_readdir(struct svc_rqst *rqstp)
{
struct nfsd3_readdirargs *argp = rqstp->rq_argp;
struct nfsd3_readdirres *resp = rqstp->rq_resp;
- int count = 0;
loff_t offset;
- struct page **p;
- caddr_t page_addr = NULL;
dprintk("nfsd: READDIR(3) %s %d bytes at %d\n",
SVCFH_fmt(&argp->fh),
@@ -471,39 +483,18 @@ nfsd3_proc_readdir(struct svc_rqst *rqstp)
nfsd3_init_dirlist_pages(rqstp, resp, argp->count);
- /* Read directory and encode entries on the fly */
fh_copy(&resp->fh, &argp->fh);
-
resp->common.err = nfs_ok;
+ resp->cookie_offset = 0;
resp->rqstp = rqstp;
offset = argp->cookie;
-
resp->status = nfsd_readdir(rqstp, &resp->fh, &offset,
- &resp->common, nfs3svc_encode_entry);
+ &resp->common, nfs3svc_encode_entry3);
memcpy(resp->verf, argp->verf, 8);
- count = 0;
- for (p = rqstp->rq_respages + 1; p < rqstp->rq_next_page; p++) {
- page_addr = page_address(*p);
+ nfs3svc_encode_cookie3(resp, offset);
- if (((caddr_t)resp->buffer >= page_addr) &&
- ((caddr_t)resp->buffer < page_addr + PAGE_SIZE)) {
- count += (caddr_t)resp->buffer - page_addr;
- break;
- }
- count += PAGE_SIZE;
- }
- resp->count = count >> 2;
- if (resp->offset) {
- if (unlikely(resp->offset1)) {
- /* we ended up with offset on a page boundary */
- *resp->offset = htonl(offset >> 32);
- *resp->offset1 = htonl(offset & 0xffffffff);
- resp->offset1 = NULL;
- } else {
- xdr_encode_hyper(resp->offset, offset);
- }
- resp->offset = NULL;
- }
+ /* Recycle only pages that were part of the reply */
+ rqstp->rq_next_page = resp->xdr.page_ptr + 1;
return rpc_success;
}
@@ -517,10 +508,7 @@ nfsd3_proc_readdirplus(struct svc_rqst *rqstp)
{
struct nfsd3_readdirargs *argp = rqstp->rq_argp;
struct nfsd3_readdirres *resp = rqstp->rq_resp;
- int count = 0;
loff_t offset;
- struct page **p;
- caddr_t page_addr = NULL;
dprintk("nfsd: READDIR+(3) %s %d bytes at %d\n",
SVCFH_fmt(&argp->fh),
@@ -528,10 +516,9 @@ nfsd3_proc_readdirplus(struct svc_rqst *rqstp)
nfsd3_init_dirlist_pages(rqstp, resp, argp->count);
- /* Read directory and encode entries on the fly */
fh_copy(&resp->fh, &argp->fh);
-
resp->common.err = nfs_ok;
+ resp->cookie_offset = 0;
resp->rqstp = rqstp;
offset = argp->cookie;
@@ -545,30 +532,12 @@ nfsd3_proc_readdirplus(struct svc_rqst *rqstp)
}
resp->status = nfsd_readdir(rqstp, &resp->fh, &offset,
- &resp->common, nfs3svc_encode_entry_plus);
+ &resp->common, nfs3svc_encode_entryplus3);
memcpy(resp->verf, argp->verf, 8);
- for (p = rqstp->rq_respages + 1; p < rqstp->rq_next_page; p++) {
- page_addr = page_address(*p);
+ nfs3svc_encode_cookie3(resp, offset);
- if (((caddr_t)resp->buffer >= page_addr) &&
- ((caddr_t)resp->buffer < page_addr + PAGE_SIZE)) {
- count += (caddr_t)resp->buffer - page_addr;
- break;
- }
- count += PAGE_SIZE;
- }
- resp->count = count >> 2;
- if (resp->offset) {
- if (unlikely(resp->offset1)) {
- /* we ended up with offset on a page boundary */
- *resp->offset = htonl(offset >> 32);
- *resp->offset1 = htonl(offset & 0xffffffff);
- resp->offset1 = NULL;
- } else {
- xdr_encode_hyper(resp->offset, offset);
- }
- resp->offset = NULL;
- }
+ /* Recycle only pages that were part of the reply */
+ rqstp->rq_next_page = resp->xdr.page_ptr + 1;
out:
return rpc_success;
@@ -736,7 +705,7 @@ static const struct svc_procedure nfsd_procedures3[22] = {
[NFS3PROC_GETATTR] = {
.pc_func = nfsd3_proc_getattr,
.pc_decode = nfs3svc_decode_fhandleargs,
- .pc_encode = nfs3svc_encode_attrstatres,
+ .pc_encode = nfs3svc_encode_getattrres,
.pc_release = nfs3svc_release_fhandle,
.pc_argsize = sizeof(struct nfsd_fhandle),
.pc_ressize = sizeof(struct nfsd3_attrstatres),
@@ -758,7 +727,7 @@ static const struct svc_procedure nfsd_procedures3[22] = {
[NFS3PROC_LOOKUP] = {
.pc_func = nfsd3_proc_lookup,
.pc_decode = nfs3svc_decode_diropargs,
- .pc_encode = nfs3svc_encode_diropres,
+ .pc_encode = nfs3svc_encode_lookupres,
.pc_release = nfs3svc_release_fhandle2,
.pc_argsize = sizeof(struct nfsd3_diropargs),
.pc_ressize = sizeof(struct nfsd3_diropres),
diff --git a/fs/nfsd/nfs3xdr.c b/fs/nfsd/nfs3xdr.c
index 9d9a01ce0b27..0a5ebc52e6a9 100644
--- a/fs/nfsd/nfs3xdr.c
+++ b/fs/nfsd/nfs3xdr.c
@@ -14,13 +14,26 @@
#include "netns.h"
#include "vfs.h"
-#define NFSDDBG_FACILITY NFSDDBG_XDR
+/*
+ * Force construction of an empty post-op attr
+ */
+static const struct svc_fh nfs3svc_null_fh = {
+ .fh_no_wcc = true,
+};
+/*
+ * time_delta. {1, 0} means the server is accurate only
+ * to the nearest second.
+ */
+static const struct timespec64 nfs3svc_time_delta = {
+ .tv_sec = 1,
+ .tv_nsec = 0,
+};
/*
* Mapping of S_IF* types to NFS file types
*/
-static u32 nfs3_ftypes[] = {
+static const u32 nfs3_ftypes[] = {
NF3NON, NF3FIFO, NF3CHR, NF3BAD,
NF3DIR, NF3BAD, NF3BLK, NF3BAD,
NF3REG, NF3BAD, NF3LNK, NF3BAD,
@@ -33,9 +46,11 @@ static u32 nfs3_ftypes[] = {
*/
static __be32 *
-encode_time3(__be32 *p, struct timespec64 *time)
+encode_nfstime3(__be32 *p, const struct timespec64 *time)
{
- *p++ = htonl((u32) time->tv_sec); *p++ = htonl(time->tv_nsec);
+ *p++ = cpu_to_be32((u32)time->tv_sec);
+ *p++ = cpu_to_be32(time->tv_nsec);
+
return p;
}
@@ -82,14 +97,80 @@ svcxdr_decode_nfs_fh3(struct xdr_stream *xdr, struct svc_fh *fhp)
return true;
}
-static __be32 *
-encode_fh(__be32 *p, struct svc_fh *fhp)
+/**
+ * svcxdr_encode_nfsstat3 - Encode an NFSv3 status code
+ * @xdr: XDR stream
+ * @status: status value to encode
+ *
+ * Return values:
+ * %false: Send buffer space was exhausted
+ * %true: Success
+ */
+bool
+svcxdr_encode_nfsstat3(struct xdr_stream *xdr, __be32 status)
+{
+ __be32 *p;
+
+ p = xdr_reserve_space(xdr, sizeof(status));
+ if (!p)
+ return false;
+ *p = status;
+
+ return true;
+}
+
+static bool
+svcxdr_encode_nfs_fh3(struct xdr_stream *xdr, const struct svc_fh *fhp)
{
- unsigned int size = fhp->fh_handle.fh_size;
- *p++ = htonl(size);
- if (size) p[XDR_QUADLEN(size)-1]=0;
+ u32 size = fhp->fh_handle.fh_size;
+ __be32 *p;
+
+ p = xdr_reserve_space(xdr, XDR_UNIT + size);
+ if (!p)
+ return false;
+ *p++ = cpu_to_be32(size);
+ if (size)
+ p[XDR_QUADLEN(size) - 1] = 0;
memcpy(p, &fhp->fh_handle.fh_base, size);
- return p + XDR_QUADLEN(size);
+
+ return true;
+}
+
+static bool
+svcxdr_encode_post_op_fh3(struct xdr_stream *xdr, const struct svc_fh *fhp)
+{
+ if (xdr_stream_encode_item_present(xdr) < 0)
+ return false;
+ if (!svcxdr_encode_nfs_fh3(xdr, fhp))
+ return false;
+
+ return true;
+}
+
+static bool
+svcxdr_encode_cookieverf3(struct xdr_stream *xdr, const __be32 *verf)
+{
+ __be32 *p;
+
+ p = xdr_reserve_space(xdr, NFS3_COOKIEVERFSIZE);
+ if (!p)
+ return false;
+ memcpy(p, verf, NFS3_COOKIEVERFSIZE);
+
+ return true;
+}
+
+static bool
+svcxdr_encode_writeverf3(struct xdr_stream *xdr, const __be32 *verf)
+{
+ __be32 *p;
+
+ p = xdr_reserve_space(xdr, NFS3_WRITEVERFSIZE);
+ if (!p)
+ return false;
+ memcpy(p, verf, NFS3_WRITEVERFSIZE);
+
+ return true;
}
static bool
@@ -253,115 +334,157 @@ svcxdr_decode_devicedata3(struct svc_rqst *rqstp, struct xdr_stream *xdr,
svcxdr_decode_specdata3(xdr, args);
}
-static __be32 *encode_fsid(__be32 *p, struct svc_fh *fhp)
+static bool
+svcxdr_encode_fattr3(struct svc_rqst *rqstp, struct xdr_stream *xdr,
+ const struct svc_fh *fhp, const struct kstat *stat)
{
- u64 f;
+ struct user_namespace *userns = nfsd_user_namespace(rqstp);
+ __be32 *p;
+ u64 fsid;
+
+ p = xdr_reserve_space(xdr, XDR_UNIT * 21);
+ if (!p)
+ return false;
+
+ *p++ = cpu_to_be32(nfs3_ftypes[(stat->mode & S_IFMT) >> 12]);
+ *p++ = cpu_to_be32((u32)(stat->mode & S_IALLUGO));
+ *p++ = cpu_to_be32((u32)stat->nlink);
+ *p++ = cpu_to_be32((u32)from_kuid_munged(userns, stat->uid));
+ *p++ = cpu_to_be32((u32)from_kgid_munged(userns, stat->gid));
+ if (S_ISLNK(stat->mode) && stat->size > NFS3_MAXPATHLEN)
+ p = xdr_encode_hyper(p, (u64)NFS3_MAXPATHLEN);
+ else
+ p = xdr_encode_hyper(p, (u64)stat->size);
+
+ /* used */
+ p = xdr_encode_hyper(p, ((u64)stat->blocks) << 9);
+
+ /* rdev */
+ *p++ = cpu_to_be32((u32)MAJOR(stat->rdev));
+ *p++ = cpu_to_be32((u32)MINOR(stat->rdev));
+
switch(fsid_source(fhp)) {
- default:
- case FSIDSOURCE_DEV:
- p = xdr_encode_hyper(p, (u64)huge_encode_dev
- (fhp->fh_dentry->d_sb->s_dev));
- break;
case FSIDSOURCE_FSID:
- p = xdr_encode_hyper(p, (u64) fhp->fh_export->ex_fsid);
+ fsid = (u64)fhp->fh_export->ex_fsid;
break;
case FSIDSOURCE_UUID:
- f = ((u64*)fhp->fh_export->ex_uuid)[0];
- f ^= ((u64*)fhp->fh_export->ex_uuid)[1];
- p = xdr_encode_hyper(p, f);
+ fsid = ((u64 *)fhp->fh_export->ex_uuid)[0];
+ fsid ^= ((u64 *)fhp->fh_export->ex_uuid)[1];
break;
+ default:
+ fsid = (u64)huge_encode_dev(fhp->fh_dentry->d_sb->s_dev);
}
- return p;
-}
+ p = xdr_encode_hyper(p, fsid);
-static __be32 *
-encode_fattr3(struct svc_rqst *rqstp, __be32 *p, struct svc_fh *fhp,
- struct kstat *stat)
-{
- struct user_namespace *userns = nfsd_user_namespace(rqstp);
- *p++ = htonl(nfs3_ftypes[(stat->mode & S_IFMT) >> 12]);
- *p++ = htonl((u32) (stat->mode & S_IALLUGO));
- *p++ = htonl((u32) stat->nlink);
- *p++ = htonl((u32) from_kuid_munged(userns, stat->uid));
- *p++ = htonl((u32) from_kgid_munged(userns, stat->gid));
- if (S_ISLNK(stat->mode) && stat->size > NFS3_MAXPATHLEN) {
- p = xdr_encode_hyper(p, (u64) NFS3_MAXPATHLEN);
- } else {
- p = xdr_encode_hyper(p, (u64) stat->size);
- }
- p = xdr_encode_hyper(p, ((u64)stat->blocks) << 9);
- *p++ = htonl((u32) MAJOR(stat->rdev));
- *p++ = htonl((u32) MINOR(stat->rdev));
- p = encode_fsid(p, fhp);
+ /* fileid */
p = xdr_encode_hyper(p, stat->ino);
- p = encode_time3(p, &stat->atime);
- p = encode_time3(p, &stat->mtime);
- p = encode_time3(p, &stat->ctime);
- return p;
+ p = encode_nfstime3(p, &stat->atime);
+ p = encode_nfstime3(p, &stat->mtime);
+ encode_nfstime3(p, &stat->ctime);
+
+ return true;
}
-static __be32 *
-encode_saved_post_attr(struct svc_rqst *rqstp, __be32 *p, struct svc_fh *fhp)
+static bool
+svcxdr_encode_wcc_attr(struct xdr_stream *xdr, const struct svc_fh *fhp)
{
- /* Attributes to follow */
- *p++ = xdr_one;
- return encode_fattr3(rqstp, p, fhp, &fhp->fh_post_attr);
+ __be32 *p;
+
+ p = xdr_reserve_space(xdr, XDR_UNIT * 6);
+ if (!p)
+ return false;
+ p = xdr_encode_hyper(p, (u64)fhp->fh_pre_size);
+ p = encode_nfstime3(p, &fhp->fh_pre_mtime);
+ encode_nfstime3(p, &fhp->fh_pre_ctime);
+
+ return true;
}
-/*
- * Encode post-operation attributes.
- * The inode may be NULL if the call failed because of a stale file
- * handle. In this case, no attributes are returned.
- */
-static __be32 *
-encode_post_op_attr(struct svc_rqst *rqstp, __be32 *p, struct svc_fh *fhp)
+static bool
+svcxdr_encode_pre_op_attr(struct xdr_stream *xdr, const struct svc_fh *fhp)
{
- struct dentry *dentry = fhp->fh_dentry;
- if (!fhp->fh_no_wcc && dentry && d_really_is_positive(dentry)) {
- __be32 err;
- struct kstat stat;
-
- err = fh_getattr(fhp, &stat);
- if (!err) {
- *p++ = xdr_one; /* attributes follow */
- lease_get_mtime(d_inode(dentry), &stat.mtime);
- return encode_fattr3(rqstp, p, fhp, &stat);
- }
+ if (!fhp->fh_pre_saved) {
+ if (xdr_stream_encode_item_absent(xdr) < 0)
+ return false;
+ return true;
}
- *p++ = xdr_zero;
- return p;
+
+ if (xdr_stream_encode_item_present(xdr) < 0)
+ return false;
+ return svcxdr_encode_wcc_attr(xdr, fhp);
}
-/* Helper for NFSv3 ACLs */
-__be32 *
-nfs3svc_encode_post_op_attr(struct svc_rqst *rqstp, __be32 *p, struct svc_fh *fhp)
+/**
+ * svcxdr_encode_post_op_attr - Encode NFSv3 post-op attributes
+ * @rqstp: Context of a completed RPC transaction
+ * @xdr: XDR stream
+ * @fhp: File handle to encode
+ *
+ * Return values:
+ * %false: Send buffer space was exhausted
+ * %true: Success
+ */
+bool
+svcxdr_encode_post_op_attr(struct svc_rqst *rqstp, struct xdr_stream *xdr,
+ const struct svc_fh *fhp)
{
- return encode_post_op_attr(rqstp, p, fhp);
+ struct dentry *dentry = fhp->fh_dentry;
+ struct kstat stat;
+
+ /*
+ * The inode may be NULL if the call failed because of a
+ * stale file handle. In this case, no attributes are
+ * returned.
+ */
+ if (fhp->fh_no_wcc || !dentry || !d_really_is_positive(dentry))
+ goto no_post_op_attrs;
+ if (fh_getattr(fhp, &stat) != nfs_ok)
+ goto no_post_op_attrs;
+
+ if (xdr_stream_encode_item_present(xdr) < 0)
+ return false;
+ lease_get_mtime(d_inode(dentry), &stat.mtime);
+ if (!svcxdr_encode_fattr3(rqstp, xdr, fhp, &stat))
+ return false;
+
+ return true;
+
+no_post_op_attrs:
+ return xdr_stream_encode_item_absent(xdr) > 0;
}
/*
- * Enocde weak cache consistency data
+ * Encode weak cache consistency data
*/
-static __be32 *
-encode_wcc_data(struct svc_rqst *rqstp, __be32 *p, struct svc_fh *fhp)
+static bool
+svcxdr_encode_wcc_data(struct svc_rqst *rqstp, struct xdr_stream *xdr,
+ const struct svc_fh *fhp)
{
- struct dentry *dentry = fhp->fh_dentry;
-
- if (dentry && d_really_is_positive(dentry) && fhp->fh_post_saved) {
- if (fhp->fh_pre_saved) {
- *p++ = xdr_one;
- p = xdr_encode_hyper(p, (u64) fhp->fh_pre_size);
- p = encode_time3(p, &fhp->fh_pre_mtime);
- p = encode_time3(p, &fhp->fh_pre_ctime);
- } else {
- *p++ = xdr_zero;
- }
- return encode_saved_post_attr(rqstp, p, fhp);
- }
- /* no pre- or post-attrs */
- *p++ = xdr_zero;
- return encode_post_op_attr(rqstp, p, fhp);
+ struct dentry *dentry = fhp->fh_dentry;
+
+ if (!dentry || !d_really_is_positive(dentry) || !fhp->fh_post_saved)
+ goto neither;
+
+ /* before */
+ if (!svcxdr_encode_pre_op_attr(xdr, fhp))
+ return false;
+
+ /* after */
+ if (xdr_stream_encode_item_present(xdr) < 0)
+ return false;
+ if (!svcxdr_encode_fattr3(rqstp, xdr, fhp, &fhp->fh_post_attr))
+ return false;
+
+ return true;
+
+neither:
+ if (xdr_stream_encode_item_absent(xdr) < 0)
+ return false;
+ if (!svcxdr_encode_post_op_attr(rqstp, xdr, fhp))
+ return false;
+
+ return true;
}
static bool fs_supports_change_attribute(struct super_block *sb)
@@ -713,210 +836,252 @@ nfs3svc_decode_commitargs(struct svc_rqst *rqstp, __be32 *p)
/* GETATTR */
int
-nfs3svc_encode_attrstat(struct svc_rqst *rqstp, __be32 *p)
+nfs3svc_encode_getattrres(struct svc_rqst *rqstp, __be32 *p)
{
+ struct xdr_stream *xdr = &rqstp->rq_res_stream;
struct nfsd3_attrstat *resp = rqstp->rq_resp;
- *p++ = resp->status;
- if (resp->status == 0) {
- lease_get_mtime(d_inode(resp->fh.fh_dentry),
- &resp->stat.mtime);
- p = encode_fattr3(rqstp, p, &resp->fh, &resp->stat);
+ if (!svcxdr_encode_nfsstat3(xdr, resp->status))
+ return 0;
+ switch (resp->status) {
+ case nfs_ok:
+ lease_get_mtime(d_inode(resp->fh.fh_dentry), &resp->stat.mtime);
+ if (!svcxdr_encode_fattr3(rqstp, xdr, &resp->fh, &resp->stat))
+ return 0;
+ break;
}
- return xdr_ressize_check(rqstp, p);
+
+ return 1;
}
/* SETATTR, REMOVE, RMDIR */
int
nfs3svc_encode_wccstat(struct svc_rqst *rqstp, __be32 *p)
{
+ struct xdr_stream *xdr = &rqstp->rq_res_stream;
struct nfsd3_attrstat *resp = rqstp->rq_resp;
- *p++ = resp->status;
- p = encode_wcc_data(rqstp, p, &resp->fh);
- return xdr_ressize_check(rqstp, p);
+ return svcxdr_encode_nfsstat3(xdr, resp->status) &&
+ svcxdr_encode_wcc_data(rqstp, xdr, &resp->fh);
}
/* LOOKUP */
-int
-nfs3svc_encode_diropres(struct svc_rqst *rqstp, __be32 *p)
+int nfs3svc_encode_lookupres(struct svc_rqst *rqstp, __be32 *p)
{
+ struct xdr_stream *xdr = &rqstp->rq_res_stream;
struct nfsd3_diropres *resp = rqstp->rq_resp;
- *p++ = resp->status;
- if (resp->status == 0) {
- p = encode_fh(p, &resp->fh);
- p = encode_post_op_attr(rqstp, p, &resp->fh);
+ if (!svcxdr_encode_nfsstat3(xdr, resp->status))
+ return 0;
+ switch (resp->status) {
+ case nfs_ok:
+ if (!svcxdr_encode_nfs_fh3(xdr, &resp->fh))
+ return 0;
+ if (!svcxdr_encode_post_op_attr(rqstp, xdr, &resp->fh))
+ return 0;
+ if (!svcxdr_encode_post_op_attr(rqstp, xdr, &resp->dirfh))
+ return 0;
+ break;
+ default:
+ if (!svcxdr_encode_post_op_attr(rqstp, xdr, &resp->dirfh))
+ return 0;
}
- p = encode_post_op_attr(rqstp, p, &resp->dirfh);
- return xdr_ressize_check(rqstp, p);
+
+ return 1;
}
/* ACCESS */
int
nfs3svc_encode_accessres(struct svc_rqst *rqstp, __be32 *p)
{
+ struct xdr_stream *xdr = &rqstp->rq_res_stream;
struct nfsd3_accessres *resp = rqstp->rq_resp;
- *p++ = resp->status;
- p = encode_post_op_attr(rqstp, p, &resp->fh);
- if (resp->status == 0)
- *p++ = htonl(resp->access);
- return xdr_ressize_check(rqstp, p);
+ if (!svcxdr_encode_nfsstat3(xdr, resp->status))
+ return 0;
+ switch (resp->status) {
+ case nfs_ok:
+ if (!svcxdr_encode_post_op_attr(rqstp, xdr, &resp->fh))
+ return 0;
+ if (xdr_stream_encode_u32(xdr, resp->access) < 0)
+ return 0;
+ break;
+ default:
+ if (!svcxdr_encode_post_op_attr(rqstp, xdr, &resp->fh))
+ return 0;
+ }
+
+ return 1;
}
/* READLINK */
int
nfs3svc_encode_readlinkres(struct svc_rqst *rqstp, __be32 *p)
{
+ struct xdr_stream *xdr = &rqstp->rq_res_stream;
struct nfsd3_readlinkres *resp = rqstp->rq_resp;
struct kvec *head = rqstp->rq_res.head;
- *p++ = resp->status;
- p = encode_post_op_attr(rqstp, p, &resp->fh);
- if (resp->status == 0) {
- *p++ = htonl(resp->len);
- xdr_ressize_check(rqstp, p);
- rqstp->rq_res.page_len = resp->len;
- if (resp->len & 3) {
- /* need to pad the tail */
- rqstp->rq_res.tail[0].iov_base = p;
- *p = 0;
- rqstp->rq_res.tail[0].iov_len = 4 - (resp->len&3);
- }
- if (svc_encode_result_payload(rqstp, head->iov_len, resp->len))
+ if (!svcxdr_encode_nfsstat3(xdr, resp->status))
+ return 0;
+ switch (resp->status) {
+ case nfs_ok:
+ if (!svcxdr_encode_post_op_attr(rqstp, xdr, &resp->fh))
return 0;
- return 1;
- } else
- return xdr_ressize_check(rqstp, p);
+ if (xdr_stream_encode_u32(xdr, resp->len) < 0)
+ return 0;
+ xdr_write_pages(xdr, resp->pages, 0, resp->len);
+ if (svc_encode_result_payload(rqstp, head->iov_len, resp->len) < 0)
+ return 0;
+ break;
+ default:
+ if (!svcxdr_encode_post_op_attr(rqstp, xdr, &resp->fh))
+ return 0;
+ }
+
+ return 1;
}
/* READ */
int
nfs3svc_encode_readres(struct svc_rqst *rqstp, __be32 *p)
{
+ struct xdr_stream *xdr = &rqstp->rq_res_stream;
struct nfsd3_readres *resp = rqstp->rq_resp;
struct kvec *head = rqstp->rq_res.head;
- *p++ = resp->status;
- p = encode_post_op_attr(rqstp, p, &resp->fh);
- if (resp->status == 0) {
- *p++ = htonl(resp->count);
- *p++ = htonl(resp->eof);
- *p++ = htonl(resp->count); /* xdr opaque count */
- xdr_ressize_check(rqstp, p);
- /* now update rqstp->rq_res to reflect data as well */
- rqstp->rq_res.page_len = resp->count;
- if (resp->count & 3) {
- /* need to pad the tail */
- rqstp->rq_res.tail[0].iov_base = p;
- *p = 0;
- rqstp->rq_res.tail[0].iov_len = 4 - (resp->count & 3);
- }
- if (svc_encode_result_payload(rqstp, head->iov_len,
- resp->count))
+ if (!svcxdr_encode_nfsstat3(xdr, resp->status))
+ return 0;
+ switch (resp->status) {
+ case nfs_ok:
+ if (!svcxdr_encode_post_op_attr(rqstp, xdr, &resp->fh))
return 0;
- return 1;
- } else
- return xdr_ressize_check(rqstp, p);
+ if (xdr_stream_encode_u32(xdr, resp->count) < 0)
+ return 0;
+ if (xdr_stream_encode_bool(xdr, resp->eof) < 0)
+ return 0;
+ if (xdr_stream_encode_u32(xdr, resp->count) < 0)
+ return 0;
+ xdr_write_pages(xdr, resp->pages, rqstp->rq_res.page_base,
+ resp->count);
+ if (svc_encode_result_payload(rqstp, head->iov_len, resp->count) < 0)
+ return 0;
+ break;
+ default:
+ if (!svcxdr_encode_post_op_attr(rqstp, xdr, &resp->fh))
+ return 0;
+ }
+
+ return 1;
}
/* WRITE */
int
nfs3svc_encode_writeres(struct svc_rqst *rqstp, __be32 *p)
{
+ struct xdr_stream *xdr = &rqstp->rq_res_stream;
struct nfsd3_writeres *resp = rqstp->rq_resp;
- *p++ = resp->status;
- p = encode_wcc_data(rqstp, p, &resp->fh);
- if (resp->status == 0) {
- *p++ = htonl(resp->count);
- *p++ = htonl(resp->committed);
- *p++ = resp->verf[0];
- *p++ = resp->verf[1];
+ if (!svcxdr_encode_nfsstat3(xdr, resp->status))
+ return 0;
+ switch (resp->status) {
+ case nfs_ok:
+ if (!svcxdr_encode_wcc_data(rqstp, xdr, &resp->fh))
+ return 0;
+ if (xdr_stream_encode_u32(xdr, resp->count) < 0)
+ return 0;
+ if (xdr_stream_encode_u32(xdr, resp->committed) < 0)
+ return 0;
+ if (!svcxdr_encode_writeverf3(xdr, resp->verf))
+ return 0;
+ break;
+ default:
+ if (!svcxdr_encode_wcc_data(rqstp, xdr, &resp->fh))
+ return 0;
}
- return xdr_ressize_check(rqstp, p);
+
+ return 1;
}
/* CREATE, MKDIR, SYMLINK, MKNOD */
int
nfs3svc_encode_createres(struct svc_rqst *rqstp, __be32 *p)
{
+ struct xdr_stream *xdr = &rqstp->rq_res_stream;
struct nfsd3_diropres *resp = rqstp->rq_resp;
- *p++ = resp->status;
- if (resp->status == 0) {
- *p++ = xdr_one;
- p = encode_fh(p, &resp->fh);
- p = encode_post_op_attr(rqstp, p, &resp->fh);
+ if (!svcxdr_encode_nfsstat3(xdr, resp->status))
+ return 0;
+ switch (resp->status) {
+ case nfs_ok:
+ if (!svcxdr_encode_post_op_fh3(xdr, &resp->fh))
+ return 0;
+ if (!svcxdr_encode_post_op_attr(rqstp, xdr, &resp->fh))
+ return 0;
+ if (!svcxdr_encode_wcc_data(rqstp, xdr, &resp->dirfh))
+ return 0;
+ break;
+ default:
+ if (!svcxdr_encode_wcc_data(rqstp, xdr, &resp->dirfh))
+ return 0;
}
- p = encode_wcc_data(rqstp, p, &resp->dirfh);
- return xdr_ressize_check(rqstp, p);
+
+ return 1;
}
/* RENAME */
int
nfs3svc_encode_renameres(struct svc_rqst *rqstp, __be32 *p)
{
+ struct xdr_stream *xdr = &rqstp->rq_res_stream;
struct nfsd3_renameres *resp = rqstp->rq_resp;
- *p++ = resp->status;
- p = encode_wcc_data(rqstp, p, &resp->ffh);
- p = encode_wcc_data(rqstp, p, &resp->tfh);
- return xdr_ressize_check(rqstp, p);
+ return svcxdr_encode_nfsstat3(xdr, resp->status) &&
+ svcxdr_encode_wcc_data(rqstp, xdr, &resp->ffh) &&
+ svcxdr_encode_wcc_data(rqstp, xdr, &resp->tfh);
}
/* LINK */
int
nfs3svc_encode_linkres(struct svc_rqst *rqstp, __be32 *p)
{
+ struct xdr_stream *xdr = &rqstp->rq_res_stream;
struct nfsd3_linkres *resp = rqstp->rq_resp;
- *p++ = resp->status;
- p = encode_post_op_attr(rqstp, p, &resp->fh);
- p = encode_wcc_data(rqstp, p, &resp->tfh);
- return xdr_ressize_check(rqstp, p);
+ return svcxdr_encode_nfsstat3(xdr, resp->status) &&
+ svcxdr_encode_post_op_attr(rqstp, xdr, &resp->fh) &&
+ svcxdr_encode_wcc_data(rqstp, xdr, &resp->tfh);
}
/* READDIR */
int
nfs3svc_encode_readdirres(struct svc_rqst *rqstp, __be32 *p)
{
+ struct xdr_stream *xdr = &rqstp->rq_res_stream;
struct nfsd3_readdirres *resp = rqstp->rq_resp;
+ struct xdr_buf *dirlist = &resp->dirlist;
- *p++ = resp->status;
- p = encode_post_op_attr(rqstp, p, &resp->fh);
-
- if (resp->status == 0) {
- /* stupid readdir cookie */
- memcpy(p, resp->verf, 8); p += 2;
- xdr_ressize_check(rqstp, p);
- if (rqstp->rq_res.head[0].iov_len + (2<<2) > PAGE_SIZE)
- return 1; /*No room for trailer */
- rqstp->rq_res.page_len = (resp->count) << 2;
-
- /* add the 'tail' to the end of the 'head' page - page 0. */
- rqstp->rq_res.tail[0].iov_base = p;
- *p++ = 0; /* no more entries */
- *p++ = htonl(resp->common.err == nfserr_eof);
- rqstp->rq_res.tail[0].iov_len = 2<<2;
- return 1;
- } else
- return xdr_ressize_check(rqstp, p);
-}
-
-static __be32 *
-encode_entry_baggage(struct nfsd3_readdirres *cd, __be32 *p, const char *name,
- int namlen, u64 ino)
-{
- *p++ = xdr_one; /* mark entry present */
- p = xdr_encode_hyper(p, ino); /* file id */
- p = xdr_encode_array(p, name, namlen);/* name length & name */
-
- cd->offset = p; /* remember pointer */
- p = xdr_encode_hyper(p, NFS_OFFSET_MAX);/* offset of next entry */
+ if (!svcxdr_encode_nfsstat3(xdr, resp->status))
+ return 0;
+ switch (resp->status) {
+ case nfs_ok:
+ if (!svcxdr_encode_post_op_attr(rqstp, xdr, &resp->fh))
+ return 0;
+ if (!svcxdr_encode_cookieverf3(xdr, resp->verf))
+ return 0;
+ xdr_write_pages(xdr, dirlist->pages, 0, dirlist->len);
+ /* no more entries */
+ if (xdr_stream_encode_item_absent(xdr) < 0)
+ return 0;
+ if (xdr_stream_encode_bool(xdr, resp->common.err == nfserr_eof) < 0)
+ return 0;
+ break;
+ default:
+ if (!svcxdr_encode_post_op_attr(rqstp, xdr, &resp->fh))
+ return 0;
+ }
- return p;
+ return 1;
}
static __be32
@@ -957,267 +1122,327 @@ out:
return rv;
}
-static __be32 *encode_entryplus_baggage(struct nfsd3_readdirres *cd, __be32 *p, const char *name, int namlen, u64 ino)
+/**
+ * nfs3svc_encode_cookie3 - Encode a directory offset cookie
+ * @resp: readdir result context
+ * @offset: offset cookie to encode
+ *
+ * The buffer space for the offset cookie has already been reserved
+ * by svcxdr_encode_entry3_common().
+ */
+void nfs3svc_encode_cookie3(struct nfsd3_readdirres *resp, u64 offset)
{
- struct svc_fh *fh = &cd->scratch;
- __be32 err;
-
- fh_init(fh, NFS3_FHSIZE);
- err = compose_entry_fh(cd, fh, name, namlen, ino);
- if (err) {
- *p++ = 0;
- *p++ = 0;
- goto out;
- }
- p = encode_post_op_attr(cd->rqstp, p, fh);
- *p++ = xdr_one; /* yes, a file handle follows */
- p = encode_fh(p, fh);
-out:
- fh_put(fh);
- return p;
-}
+ __be64 cookie = cpu_to_be64(offset);
-/*
- * Encode a directory entry. This one works for both normal readdir
- * and readdirplus.
- * The normal readdir reply requires 2 (fileid) + 1 (stringlen)
- * + string + 2 (cookie) + 1 (next) words, i.e. 6 + strlen.
- *
- * The readdirplus baggage is 1+21 words for post_op_attr, plus the
- * file handle.
- */
+ if (!resp->cookie_offset)
+ return;
+ write_bytes_to_xdr_buf(&resp->dirlist, resp->cookie_offset, &cookie,
+ sizeof(cookie));
+ resp->cookie_offset = 0;
+}
-#define NFS3_ENTRY_BAGGAGE (2 + 1 + 2 + 1)
-#define NFS3_ENTRYPLUS_BAGGAGE (1 + 21 + 1 + (NFS3_FHSIZE >> 2))
-static int
-encode_entry(struct readdir_cd *ccd, const char *name, int namlen,
- loff_t offset, u64 ino, unsigned int d_type, int plus)
+static bool
+svcxdr_encode_entry3_common(struct nfsd3_readdirres *resp, const char *name,
+ int namlen, loff_t offset, u64 ino)
{
- struct nfsd3_readdirres *cd = container_of(ccd, struct nfsd3_readdirres,
- common);
- __be32 *p = cd->buffer;
- caddr_t curr_page_addr = NULL;
- struct page ** page;
- int slen; /* string (name) length */
- int elen; /* estimated entry length in words */
- int num_entry_words = 0; /* actual number of words */
-
- if (cd->offset) {
- u64 offset64 = offset;
-
- if (unlikely(cd->offset1)) {
- /* we ended up with offset on a page boundary */
- *cd->offset = htonl(offset64 >> 32);
- *cd->offset1 = htonl(offset64 & 0xffffffff);
- cd->offset1 = NULL;
- } else {
- xdr_encode_hyper(cd->offset, offset64);
- }
- cd->offset = NULL;
- }
+ struct xdr_buf *dirlist = &resp->dirlist;
+ struct xdr_stream *xdr = &resp->xdr;
- /*
- dprintk("encode_entry(%.*s @%ld%s)\n",
- namlen, name, (long) offset, plus? " plus" : "");
- */
-
- /* truncate filename if too long */
- namlen = min(namlen, NFS3_MAXNAMLEN);
+ if (xdr_stream_encode_item_present(xdr) < 0)
+ return false;
+ /* fileid */
+ if (xdr_stream_encode_u64(xdr, ino) < 0)
+ return false;
+ /* name */
+ if (xdr_stream_encode_opaque(xdr, name, min(namlen, NFS3_MAXNAMLEN)) < 0)
+ return false;
+ /* cookie */
+ resp->cookie_offset = dirlist->len;
+ if (xdr_stream_encode_u64(xdr, NFS_OFFSET_MAX) < 0)
+ return false;
- slen = XDR_QUADLEN(namlen);
- elen = slen + NFS3_ENTRY_BAGGAGE
- + (plus? NFS3_ENTRYPLUS_BAGGAGE : 0);
+ return true;
+}
- if (cd->buflen < elen) {
- cd->common.err = nfserr_toosmall;
- return -EINVAL;
- }
+/**
+ * nfs3svc_encode_entry3 - encode one NFSv3 READDIR entry
+ * @data: directory context
+ * @name: name of the object to be encoded
+ * @namlen: length of that name, in bytes
+ * @offset: the offset of the previous entry
+ * @ino: the fileid of this entry
+ * @d_type: unused
+ *
+ * Return values:
+ * %0: Entry was successfully encoded.
+ * %-EINVAL: An encoding problem occured, secondary status code in resp->common.err
+ *
+ * On exit, the following fields are updated:
+ * - resp->xdr
+ * - resp->common.err
+ * - resp->cookie_offset
+ */
+int nfs3svc_encode_entry3(void *data, const char *name, int namlen,
+ loff_t offset, u64 ino, unsigned int d_type)
+{
+ struct readdir_cd *ccd = data;
+ struct nfsd3_readdirres *resp = container_of(ccd,
+ struct nfsd3_readdirres,
+ common);
+ unsigned int starting_length = resp->dirlist.len;
- /* determine which page in rq_respages[] we are currently filling */
- for (page = cd->rqstp->rq_respages + 1;
- page < cd->rqstp->rq_next_page; page++) {
- curr_page_addr = page_address(*page);
+ /* The offset cookie for the previous entry */
+ nfs3svc_encode_cookie3(resp, offset);
- if (((caddr_t)cd->buffer >= curr_page_addr) &&
- ((caddr_t)cd->buffer < curr_page_addr + PAGE_SIZE))
- break;
- }
+ if (!svcxdr_encode_entry3_common(resp, name, namlen, offset, ino))
+ goto out_toosmall;
- if ((caddr_t)(cd->buffer + elen) < (curr_page_addr + PAGE_SIZE)) {
- /* encode entry in current page */
+ xdr_commit_encode(&resp->xdr);
+ resp->common.err = nfs_ok;
+ return 0;
- p = encode_entry_baggage(cd, p, name, namlen, ino);
+out_toosmall:
+ resp->cookie_offset = 0;
+ resp->common.err = nfserr_toosmall;
+ resp->dirlist.len = starting_length;
+ return -EINVAL;
+}
- if (plus)
- p = encode_entryplus_baggage(cd, p, name, namlen, ino);
- num_entry_words = p - cd->buffer;
- } else if (*(page+1) != NULL) {
- /* temporarily encode entry into next page, then move back to
- * current and next page in rq_respages[] */
- __be32 *p1, *tmp;
- int len1, len2;
+static bool
+svcxdr_encode_entry3_plus(struct nfsd3_readdirres *resp, const char *name,
+ int namlen, u64 ino)
+{
+ struct xdr_stream *xdr = &resp->xdr;
+ struct svc_fh *fhp = &resp->scratch;
+ bool result;
- /* grab next page for temporary storage of entry */
- p1 = tmp = page_address(*(page+1));
+ result = false;
+ fh_init(fhp, NFS3_FHSIZE);
+ if (compose_entry_fh(resp, fhp, name, namlen, ino) != nfs_ok)
+ goto out_noattrs;
- p1 = encode_entry_baggage(cd, p1, name, namlen, ino);
+ if (!svcxdr_encode_post_op_attr(resp->rqstp, xdr, fhp))
+ goto out;
+ if (!svcxdr_encode_post_op_fh3(xdr, fhp))
+ goto out;
+ result = true;
- if (plus)
- p1 = encode_entryplus_baggage(cd, p1, name, namlen, ino);
+out:
+ fh_put(fhp);
+ return result;
- /* determine entry word length and lengths to go in pages */
- num_entry_words = p1 - tmp;
- len1 = curr_page_addr + PAGE_SIZE - (caddr_t)cd->buffer;
- if ((num_entry_words << 2) < len1) {
- /* the actual number of words in the entry is less
- * than elen and can still fit in the current page
- */
- memmove(p, tmp, num_entry_words << 2);
- p += num_entry_words;
-
- /* update offset */
- cd->offset = cd->buffer + (cd->offset - tmp);
- } else {
- unsigned int offset_r = (cd->offset - tmp) << 2;
-
- /* update pointer to offset location.
- * This is a 64bit quantity, so we need to
- * deal with 3 cases:
- * - entirely in first page
- * - entirely in second page
- * - 4 bytes in each page
- */
- if (offset_r + 8 <= len1) {
- cd->offset = p + (cd->offset - tmp);
- } else if (offset_r >= len1) {
- cd->offset -= len1 >> 2;
- } else {
- /* sitting on the fence */
- BUG_ON(offset_r != len1 - 4);
- cd->offset = p + (cd->offset - tmp);
- cd->offset1 = tmp;
- }
-
- len2 = (num_entry_words << 2) - len1;
-
- /* move from temp page to current and next pages */
- memmove(p, tmp, len1);
- memmove(tmp, (caddr_t)tmp+len1, len2);
-
- p = tmp + (len2 >> 2);
- }
- }
- else {
- cd->common.err = nfserr_toosmall;
- return -EINVAL;
- }
+out_noattrs:
+ if (xdr_stream_encode_item_absent(xdr) < 0)
+ return false;
+ if (xdr_stream_encode_item_absent(xdr) < 0)
+ return false;
+ return true;
+}
- cd->buflen -= num_entry_words;
- cd->buffer = p;
- cd->common.err = nfs_ok;
+/**
+ * nfs3svc_encode_entryplus3 - encode one NFSv3 READDIRPLUS entry
+ * @data: directory context
+ * @name: name of the object to be encoded
+ * @namlen: length of that name, in bytes
+ * @offset: the offset of the previous entry
+ * @ino: the fileid of this entry
+ * @d_type: unused
+ *
+ * Return values:
+ * %0: Entry was successfully encoded.
+ * %-EINVAL: An encoding problem occured, secondary status code in resp->common.err
+ *
+ * On exit, the following fields are updated:
+ * - resp->xdr
+ * - resp->common.err
+ * - resp->cookie_offset
+ */
+int nfs3svc_encode_entryplus3(void *data, const char *name, int namlen,
+ loff_t offset, u64 ino, unsigned int d_type)
+{
+ struct readdir_cd *ccd = data;
+ struct nfsd3_readdirres *resp = container_of(ccd,
+ struct nfsd3_readdirres,
+ common);
+ unsigned int starting_length = resp->dirlist.len;
+
+ /* The offset cookie for the previous entry */
+ nfs3svc_encode_cookie3(resp, offset);
+
+ if (!svcxdr_encode_entry3_common(resp, name, namlen, offset, ino))
+ goto out_toosmall;
+ if (!svcxdr_encode_entry3_plus(resp, name, namlen, ino))
+ goto out_toosmall;
+
+ xdr_commit_encode(&resp->xdr);
+ resp->common.err = nfs_ok;
return 0;
+out_toosmall:
+ resp->cookie_offset = 0;
+ resp->common.err = nfserr_toosmall;
+ resp->dirlist.len = starting_length;
+ return -EINVAL;
}
-int
-nfs3svc_encode_entry(void *cd, const char *name,
- int namlen, loff_t offset, u64 ino, unsigned int d_type)
+static bool
+svcxdr_encode_fsstat3resok(struct xdr_stream *xdr,
+ const struct nfsd3_fsstatres *resp)
{
- return encode_entry(cd, name, namlen, offset, ino, d_type, 0);
-}
+ const struct kstatfs *s = &resp->stats;
+ u64 bs = s->f_bsize;
+ __be32 *p;
-int
-nfs3svc_encode_entry_plus(void *cd, const char *name,
- int namlen, loff_t offset, u64 ino,
- unsigned int d_type)
-{
- return encode_entry(cd, name, namlen, offset, ino, d_type, 1);
+ p = xdr_reserve_space(xdr, XDR_UNIT * 13);
+ if (!p)
+ return false;
+ p = xdr_encode_hyper(p, bs * s->f_blocks); /* total bytes */
+ p = xdr_encode_hyper(p, bs * s->f_bfree); /* free bytes */
+ p = xdr_encode_hyper(p, bs * s->f_bavail); /* user available bytes */
+ p = xdr_encode_hyper(p, s->f_files); /* total inodes */
+ p = xdr_encode_hyper(p, s->f_ffree); /* free inodes */
+ p = xdr_encode_hyper(p, s->f_ffree); /* user available inodes */
+ *p = cpu_to_be32(resp->invarsec); /* mean unchanged time */
+
+ return true;
}
/* FSSTAT */
int
nfs3svc_encode_fsstatres(struct svc_rqst *rqstp, __be32 *p)
{
+ struct xdr_stream *xdr = &rqstp->rq_res_stream;
struct nfsd3_fsstatres *resp = rqstp->rq_resp;
- struct kstatfs *s = &resp->stats;
- u64 bs = s->f_bsize;
-
- *p++ = resp->status;
- *p++ = xdr_zero; /* no post_op_attr */
-
- if (resp->status == 0) {
- p = xdr_encode_hyper(p, bs * s->f_blocks); /* total bytes */
- p = xdr_encode_hyper(p, bs * s->f_bfree); /* free bytes */
- p = xdr_encode_hyper(p, bs * s->f_bavail); /* user available bytes */
- p = xdr_encode_hyper(p, s->f_files); /* total inodes */
- p = xdr_encode_hyper(p, s->f_ffree); /* free inodes */
- p = xdr_encode_hyper(p, s->f_ffree); /* user available inodes */
- *p++ = htonl(resp->invarsec); /* mean unchanged time */
+
+ if (!svcxdr_encode_nfsstat3(xdr, resp->status))
+ return 0;
+ switch (resp->status) {
+ case nfs_ok:
+ if (!svcxdr_encode_post_op_attr(rqstp, xdr, &nfs3svc_null_fh))
+ return 0;
+ if (!svcxdr_encode_fsstat3resok(xdr, resp))
+ return 0;
+ break;
+ default:
+ if (!svcxdr_encode_post_op_attr(rqstp, xdr, &nfs3svc_null_fh))
+ return 0;
}
- return xdr_ressize_check(rqstp, p);
+
+ return 1;
+}
+
+static bool
+svcxdr_encode_fsinfo3resok(struct xdr_stream *xdr,
+ const struct nfsd3_fsinfores *resp)
+{
+ __be32 *p;
+
+ p = xdr_reserve_space(xdr, XDR_UNIT * 12);
+ if (!p)
+ return false;
+ *p++ = cpu_to_be32(resp->f_rtmax);
+ *p++ = cpu_to_be32(resp->f_rtpref);
+ *p++ = cpu_to_be32(resp->f_rtmult);
+ *p++ = cpu_to_be32(resp->f_wtmax);
+ *p++ = cpu_to_be32(resp->f_wtpref);
+ *p++ = cpu_to_be32(resp->f_wtmult);
+ *p++ = cpu_to_be32(resp->f_dtpref);
+ p = xdr_encode_hyper(p, resp->f_maxfilesize);
+ p = encode_nfstime3(p, &nfs3svc_time_delta);
+ *p = cpu_to_be32(resp->f_properties);
+
+ return true;
}
/* FSINFO */
int
nfs3svc_encode_fsinfores(struct svc_rqst *rqstp, __be32 *p)
{
+ struct xdr_stream *xdr = &rqstp->rq_res_stream;
struct nfsd3_fsinfores *resp = rqstp->rq_resp;
- *p++ = resp->status;
- *p++ = xdr_zero; /* no post_op_attr */
-
- if (resp->status == 0) {
- *p++ = htonl(resp->f_rtmax);
- *p++ = htonl(resp->f_rtpref);
- *p++ = htonl(resp->f_rtmult);
- *p++ = htonl(resp->f_wtmax);
- *p++ = htonl(resp->f_wtpref);
- *p++ = htonl(resp->f_wtmult);
- *p++ = htonl(resp->f_dtpref);
- p = xdr_encode_hyper(p, resp->f_maxfilesize);
- *p++ = xdr_one;
- *p++ = xdr_zero;
- *p++ = htonl(resp->f_properties);
+ if (!svcxdr_encode_nfsstat3(xdr, resp->status))
+ return 0;
+ switch (resp->status) {
+ case nfs_ok:
+ if (!svcxdr_encode_post_op_attr(rqstp, xdr, &nfs3svc_null_fh))
+ return 0;
+ if (!svcxdr_encode_fsinfo3resok(xdr, resp))
+ return 0;
+ break;
+ default:
+ if (!svcxdr_encode_post_op_attr(rqstp, xdr, &nfs3svc_null_fh))
+ return 0;
}
- return xdr_ressize_check(rqstp, p);
+ return 1;
+}
+
+static bool
+svcxdr_encode_pathconf3resok(struct xdr_stream *xdr,
+ const struct nfsd3_pathconfres *resp)
+{
+ __be32 *p;
+
+ p = xdr_reserve_space(xdr, XDR_UNIT * 6);
+ if (!p)
+ return false;
+ *p++ = cpu_to_be32(resp->p_link_max);
+ *p++ = cpu_to_be32(resp->p_name_max);
+ p = xdr_encode_bool(p, resp->p_no_trunc);
+ p = xdr_encode_bool(p, resp->p_chown_restricted);
+ p = xdr_encode_bool(p, resp->p_case_insensitive);
+ xdr_encode_bool(p, resp->p_case_preserving);
+
+ return true;
}
/* PATHCONF */
int
nfs3svc_encode_pathconfres(struct svc_rqst *rqstp, __be32 *p)
{
+ struct xdr_stream *xdr = &rqstp->rq_res_stream;
struct nfsd3_pathconfres *resp = rqstp->rq_resp;
- *p++ = resp->status;
- *p++ = xdr_zero; /* no post_op_attr */
-
- if (resp->status == 0) {
- *p++ = htonl(resp->p_link_max);
- *p++ = htonl(resp->p_name_max);
- *p++ = htonl(resp->p_no_trunc);
- *p++ = htonl(resp->p_chown_restricted);
- *p++ = htonl(resp->p_case_insensitive);
- *p++ = htonl(resp->p_case_preserving);
+ if (!svcxdr_encode_nfsstat3(xdr, resp->status))
+ return 0;
+ switch (resp->status) {
+ case nfs_ok:
+ if (!svcxdr_encode_post_op_attr(rqstp, xdr, &nfs3svc_null_fh))
+ return 0;
+ if (!svcxdr_encode_pathconf3resok(xdr, resp))
+ return 0;
+ break;
+ default:
+ if (!svcxdr_encode_post_op_attr(rqstp, xdr, &nfs3svc_null_fh))
+ return 0;
}
- return xdr_ressize_check(rqstp, p);
+ return 1;
}
/* COMMIT */
int
nfs3svc_encode_commitres(struct svc_rqst *rqstp, __be32 *p)
{
+ struct xdr_stream *xdr = &rqstp->rq_res_stream;
struct nfsd3_commitres *resp = rqstp->rq_resp;
- *p++ = resp->status;
- p = encode_wcc_data(rqstp, p, &resp->fh);
- /* Write verifier */
- if (resp->status == 0) {
- *p++ = resp->verf[0];
- *p++ = resp->verf[1];
+ if (!svcxdr_encode_nfsstat3(xdr, resp->status))
+ return 0;
+ switch (resp->status) {
+ case nfs_ok:
+ if (!svcxdr_encode_wcc_data(rqstp, xdr, &resp->fh))
+ return 0;
+ if (!svcxdr_encode_writeverf3(xdr, resp->verf))
+ return 0;
+ break;
+ default:
+ if (!svcxdr_encode_wcc_data(rqstp, xdr, &resp->fh))
+ return 0;
}
- return xdr_ressize_check(rqstp, p);
+
+ return 1;
}
/*
diff --git a/fs/nfsd/nfs4callback.c b/fs/nfsd/nfs4callback.c
index 052be5bf9ef5..7325592b456e 100644
--- a/fs/nfsd/nfs4callback.c
+++ b/fs/nfsd/nfs4callback.c
@@ -1189,6 +1189,7 @@ static void nfsd4_cb_done(struct rpc_task *task, void *calldata)
switch (task->tk_status) {
case -EIO:
case -ETIMEDOUT:
+ case -EACCES:
nfsd4_mark_cb_down(clp, task->tk_status);
}
break;
diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c
index acdb3cd806a1..daf43b980d4b 100644
--- a/fs/nfsd/nfs4proc.c
+++ b/fs/nfsd/nfs4proc.c
@@ -1302,7 +1302,7 @@ nfsd4_cleanup_inter_ssc(struct vfsmount *ss_mnt, struct nfsd_file *src,
struct nfsd_file *dst)
{
nfs42_ssc_close(src->nf_file);
- /* 'src' is freed by nfsd4_do_async_copy */
+ fput(src->nf_file);
nfsd_file_put(dst);
mntput(ss_mnt);
}
@@ -1383,10 +1383,13 @@ static void nfsd4_init_copy_res(struct nfsd4_copy *copy, bool sync)
static ssize_t _nfsd_copy_file_range(struct nfsd4_copy *copy)
{
ssize_t bytes_copied = 0;
- size_t bytes_total = copy->cp_count;
+ u64 bytes_total = copy->cp_count;
u64 src_pos = copy->cp_src_pos;
u64 dst_pos = copy->cp_dst_pos;
+ /* See RFC 7862 p.67: */
+ if (bytes_total == 0)
+ bytes_total = ULLONG_MAX;
do {
if (kthread_should_stop())
break;
@@ -1538,8 +1541,8 @@ nfsd4_copy(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
if (!nfs4_init_copy_state(nn, copy))
goto out_err;
refcount_set(&async_copy->refcount, 1);
- memcpy(&copy->cp_res.cb_stateid, &copy->cp_stateid,
- sizeof(copy->cp_stateid));
+ memcpy(&copy->cp_res.cb_stateid, &copy->cp_stateid.stid,
+ sizeof(copy->cp_res.cb_stateid));
dup_copy_fields(copy, async_copy);
async_copy->copy_task = kthread_create(nfsd4_do_async_copy,
async_copy, "%s", "copy thread");
@@ -2262,25 +2265,6 @@ static bool need_wrongsec_check(struct svc_rqst *rqstp)
return !(nextd->op_flags & OP_HANDLES_WRONGSEC);
}
-static void svcxdr_init_encode(struct svc_rqst *rqstp,
- struct nfsd4_compoundres *resp)
-{
- struct xdr_stream *xdr = &resp->xdr;
- struct xdr_buf *buf = &rqstp->rq_res;
- struct kvec *head = buf->head;
-
- xdr->buf = buf;
- xdr->iov = head;
- xdr->p = head->iov_base + head->iov_len;
- xdr->end = head->iov_base + PAGE_SIZE - rqstp->rq_auth_slack;
- /* Tail and page_len should be zero at this point: */
- buf->len = buf->head[0].iov_len;
- xdr_reset_scratch_buffer(xdr);
- xdr->page_ptr = buf->pages - 1;
- buf->buflen = PAGE_SIZE * (1 + rqstp->rq_page_end - buf->pages)
- - rqstp->rq_auth_slack;
-}
-
#ifdef CONFIG_NFSD_V4_2_INTER_SSC
static void
check_if_stalefh_allowed(struct nfsd4_compoundargs *args)
@@ -2335,10 +2319,14 @@ nfsd4_proc_compound(struct svc_rqst *rqstp)
struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id);
__be32 status;
- svcxdr_init_encode(rqstp, resp);
- resp->tagp = resp->xdr.p;
+ resp->xdr = &rqstp->rq_res_stream;
+
+ /* reserve space for: NFS status code */
+ xdr_reserve_space(resp->xdr, XDR_UNIT);
+
+ resp->tagp = resp->xdr->p;
/* reserve space for: taglen, tag, and opcnt */
- xdr_reserve_space(&resp->xdr, 8 + args->taglen);
+ xdr_reserve_space(resp->xdr, XDR_UNIT * 2 + args->taglen);
resp->taglen = args->taglen;
resp->tag = args->tag;
resp->rqstp = rqstp;
@@ -2444,7 +2432,7 @@ nfsd4_proc_compound(struct svc_rqst *rqstp)
encode_op:
if (op->status == nfserr_replay_me) {
op->replay = &cstate->replay_owner->so_replay;
- nfsd4_encode_replay(&resp->xdr, op);
+ nfsd4_encode_replay(resp->xdr, op);
status = op->status = op->replay->rp_status;
} else {
nfsd4_encode_operation(resp, op);
diff --git a/fs/nfsd/nfs4recover.c b/fs/nfsd/nfs4recover.c
index 891395c6c7d3..6fedc49726bf 100644
--- a/fs/nfsd/nfs4recover.c
+++ b/fs/nfsd/nfs4recover.c
@@ -626,7 +626,7 @@ nfsd4_legacy_tracking_init(struct net *net)
status = nfsd4_load_reboot_recovery_data(net);
if (status)
goto err;
- printk("NFSD: Using legacy client tracking operations.\n");
+ pr_info("NFSD: Using legacy client tracking operations.\n");
return 0;
err:
@@ -1028,7 +1028,7 @@ nfsd4_init_cld_pipe(struct net *net)
status = __nfsd4_init_cld_pipe(net);
if (!status)
- printk("NFSD: Using old nfsdcld client tracking operations.\n");
+ pr_info("NFSD: Using old nfsdcld client tracking operations.\n");
return status;
}
@@ -1605,7 +1605,7 @@ nfsd4_cld_tracking_init(struct net *net)
nfs4_release_reclaim(nn);
goto err_remove;
} else
- printk("NFSD: Using nfsdcld client tracking operations.\n");
+ pr_info("NFSD: Using nfsdcld client tracking operations.\n");
return 0;
err_remove:
@@ -1864,7 +1864,7 @@ nfsd4_umh_cltrack_init(struct net *net)
ret = nfsd4_umh_cltrack_upcall("init", NULL, grace_start, NULL);
kfree(grace_start);
if (!ret)
- printk("NFSD: Using UMH upcall client tracking operations.\n");
+ pr_info("NFSD: Using UMH upcall client tracking operations.\n");
return ret;
}
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 423fd6683f3a..7698172ac0c7 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -43,6 +43,7 @@
#include <linux/sunrpc/addr.h>
#include <linux/jhash.h>
#include <linux/string_helpers.h>
+#include <linux/fsnotify.h>
#include "xdr4.h"
#include "xdr4cb.h"
#include "vfs.h"
@@ -2352,6 +2353,10 @@ static int client_info_show(struct seq_file *m, void *v)
memcpy(&clid, &clp->cl_clientid, sizeof(clid));
seq_printf(m, "clientid: 0x%llx\n", clid);
seq_printf(m, "address: \"%pISpc\"\n", (struct sockaddr *)&clp->cl_addr);
+ if (test_bit(NFSD4_CLIENT_CONFIRMED, &clp->cl_flags))
+ seq_puts(m, "status: confirmed\n");
+ else
+ seq_puts(m, "status: unconfirmed\n");
seq_printf(m, "name: ");
seq_quote_mem(m, clp->cl_name.data, clp->cl_name.len);
seq_printf(m, "\nminor version: %d\n", clp->cl_minorversion);
@@ -2702,6 +2707,7 @@ static struct nfs4_client *create_client(struct xdr_netobj name,
int ret;
struct net *net = SVC_NET(rqstp);
struct nfsd_net *nn = net_generic(net, nfsd_net_id);
+ struct dentry *dentries[ARRAY_SIZE(client_files)];
clp = alloc_client(name);
if (clp == NULL)
@@ -2721,9 +2727,11 @@ static struct nfs4_client *create_client(struct xdr_netobj name,
memcpy(&clp->cl_addr, sa, sizeof(struct sockaddr_storage));
clp->cl_cb_session = NULL;
clp->net = net;
- clp->cl_nfsd_dentry = nfsd_client_mkdir(nn, &clp->cl_nfsdfs,
- clp->cl_clientid.cl_id - nn->clientid_base,
- client_files);
+ clp->cl_nfsd_dentry = nfsd_client_mkdir(
+ nn, &clp->cl_nfsdfs,
+ clp->cl_clientid.cl_id - nn->clientid_base,
+ client_files, dentries);
+ clp->cl_nfsd_info_dentry = dentries[0];
if (!clp->cl_nfsd_dentry) {
free_client(clp);
return NULL;
@@ -2798,7 +2806,10 @@ move_to_confirmed(struct nfs4_client *clp)
list_move(&clp->cl_idhash, &nn->conf_id_hashtbl[idhashval]);
rb_erase(&clp->cl_namenode, &nn->unconf_name_tree);
add_clp_to_name_tree(clp, &nn->conf_name_tree);
- set_bit(NFSD4_CLIENT_CONFIRMED, &clp->cl_flags);
+ if (!test_and_set_bit(NFSD4_CLIENT_CONFIRMED, &clp->cl_flags) &&
+ clp->cl_nfsd_dentry &&
+ clp->cl_nfsd_info_dentry)
+ fsnotify_dentry(clp->cl_nfsd_info_dentry, FS_MODIFY);
renew_client_locked(clp);
}
@@ -2903,7 +2914,7 @@ out_err:
static void
nfsd4_store_cache_entry(struct nfsd4_compoundres *resp)
{
- struct xdr_buf *buf = resp->xdr.buf;
+ struct xdr_buf *buf = resp->xdr->buf;
struct nfsd4_slot *slot = resp->cstate.slot;
unsigned int base;
@@ -2973,7 +2984,7 @@ nfsd4_replay_cache_entry(struct nfsd4_compoundres *resp,
struct nfsd4_sequence *seq)
{
struct nfsd4_slot *slot = resp->cstate.slot;
- struct xdr_stream *xdr = &resp->xdr;
+ struct xdr_stream *xdr = resp->xdr;
__be32 *p;
__be32 status;
@@ -3708,7 +3719,7 @@ nfsd4_sequence(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
{
struct nfsd4_sequence *seq = &u->sequence;
struct nfsd4_compoundres *resp = rqstp->rq_resp;
- struct xdr_stream *xdr = &resp->xdr;
+ struct xdr_stream *xdr = resp->xdr;
struct nfsd4_session *session;
struct nfs4_client *clp;
struct nfsd4_slot *slot;
@@ -4940,31 +4951,6 @@ static struct file_lock *nfs4_alloc_init_lease(struct nfs4_delegation *dp,
return fl;
}
-static int nfsd4_check_conflicting_opens(struct nfs4_client *clp,
- struct nfs4_file *fp)
-{
- struct nfs4_clnt_odstate *co;
- struct file *f = fp->fi_deleg_file->nf_file;
- struct inode *ino = locks_inode(f);
- int writes = atomic_read(&ino->i_writecount);
-
- if (fp->fi_fds[O_WRONLY])
- writes--;
- if (fp->fi_fds[O_RDWR])
- writes--;
- if (writes > 0)
- return -EAGAIN;
- spin_lock(&fp->fi_lock);
- list_for_each_entry(co, &fp->fi_clnt_odstate, co_perfile) {
- if (co->co_client != clp) {
- spin_unlock(&fp->fi_lock);
- return -EAGAIN;
- }
- }
- spin_unlock(&fp->fi_lock);
- return 0;
-}
-
static struct nfs4_delegation *
nfs4_set_delegation(struct nfs4_client *clp, struct svc_fh *fh,
struct nfs4_file *fp, struct nfs4_clnt_odstate *odstate)
@@ -4984,12 +4970,9 @@ nfs4_set_delegation(struct nfs4_client *clp, struct svc_fh *fh,
nf = find_readable_file(fp);
if (!nf) {
- /*
- * We probably could attempt another open and get a read
- * delegation, but for now, don't bother until the
- * client actually sends us one.
- */
- return ERR_PTR(-EAGAIN);
+ /* We should always have a readable file here */
+ WARN_ON_ONCE(1);
+ return ERR_PTR(-EBADF);
}
spin_lock(&state_lock);
spin_lock(&fp->fi_lock);
@@ -5019,19 +5002,11 @@ nfs4_set_delegation(struct nfs4_client *clp, struct svc_fh *fh,
if (!fl)
goto out_clnt_odstate;
- status = nfsd4_check_conflicting_opens(clp, fp);
- if (status) {
- locks_free_lock(fl);
- goto out_clnt_odstate;
- }
status = vfs_setlease(fp->fi_deleg_file->nf_file, fl->fl_type, &fl, NULL);
if (fl)
locks_free_lock(fl);
if (status)
goto out_clnt_odstate;
- status = nfsd4_check_conflicting_opens(clp, fp);
- if (status)
- goto out_clnt_odstate;
spin_lock(&state_lock);
spin_lock(&fp->fi_lock);
@@ -5113,6 +5088,17 @@ nfs4_open_delegation(struct svc_fh *fh, struct nfsd4_open *open,
goto out_no_deleg;
if (!cb_up || !(oo->oo_flags & NFS4_OO_CONFIRMED))
goto out_no_deleg;
+ /*
+ * Also, if the file was opened for write or
+ * create, there's a good chance the client's
+ * about to write to it, resulting in an
+ * immediate recall (since we don't support
+ * write delegations):
+ */
+ if (open->op_share_access & NFS4_SHARE_ACCESS_WRITE)
+ goto out_no_deleg;
+ if (open->op_create == NFS4_OPEN_CREATE)
+ goto out_no_deleg;
break;
default:
goto out_no_deleg;
@@ -5363,6 +5349,22 @@ static bool clients_still_reclaiming(struct nfsd_net *nn)
return true;
}
+struct laundry_time {
+ time64_t cutoff;
+ time64_t new_timeo;
+};
+
+static bool state_expired(struct laundry_time *lt, time64_t last_refresh)
+{
+ time64_t time_remaining;
+
+ if (last_refresh < lt->cutoff)
+ return true;
+ time_remaining = last_refresh - lt->cutoff;
+ lt->new_timeo = min(lt->new_timeo, time_remaining);
+ return false;
+}
+
static time64_t
nfs4_laundromat(struct nfsd_net *nn)
{
@@ -5372,14 +5374,16 @@ nfs4_laundromat(struct nfsd_net *nn)
struct nfs4_ol_stateid *stp;
struct nfsd4_blocked_lock *nbl;
struct list_head *pos, *next, reaplist;
- time64_t cutoff = ktime_get_boottime_seconds() - nn->nfsd4_lease;
- time64_t t, new_timeo = nn->nfsd4_lease;
+ struct laundry_time lt = {
+ .cutoff = ktime_get_boottime_seconds() - nn->nfsd4_lease,
+ .new_timeo = nn->nfsd4_lease
+ };
struct nfs4_cpntf_state *cps;
copy_stateid_t *cps_t;
int i;
if (clients_still_reclaiming(nn)) {
- new_timeo = 0;
+ lt.new_timeo = 0;
goto out;
}
nfsd4_end_grace(nn);
@@ -5389,7 +5393,7 @@ nfs4_laundromat(struct nfsd_net *nn)
idr_for_each_entry(&nn->s2s_cp_stateids, cps_t, i) {
cps = container_of(cps_t, struct nfs4_cpntf_state, cp_stateid);
if (cps->cp_stateid.sc_type == NFS4_COPYNOTIFY_STID &&
- cps->cpntf_time > cutoff)
+ state_expired(&lt, cps->cpntf_time))
_free_cpntf_state_locked(nn, cps);
}
spin_unlock(&nn->s2s_cp_lock);
@@ -5397,11 +5401,8 @@ nfs4_laundromat(struct nfsd_net *nn)
spin_lock(&nn->client_lock);
list_for_each_safe(pos, next, &nn->client_lru) {
clp = list_entry(pos, struct nfs4_client, cl_lru);
- if (clp->cl_time > cutoff) {
- t = clp->cl_time - cutoff;
- new_timeo = min(new_timeo, t);
+ if (!state_expired(&lt, clp->cl_time))
break;
- }
if (mark_client_expired_locked(clp)) {
trace_nfsd_clid_expired(&clp->cl_clientid);
continue;
@@ -5418,11 +5419,8 @@ nfs4_laundromat(struct nfsd_net *nn)
spin_lock(&state_lock);
list_for_each_safe(pos, next, &nn->del_recall_lru) {
dp = list_entry (pos, struct nfs4_delegation, dl_recall_lru);
- if (dp->dl_time > cutoff) {
- t = dp->dl_time - cutoff;
- new_timeo = min(new_timeo, t);
+ if (!state_expired(&lt, dp->dl_time))
break;
- }
WARN_ON(!unhash_delegation_locked(dp));
list_add(&dp->dl_recall_lru, &reaplist);
}
@@ -5438,11 +5436,8 @@ nfs4_laundromat(struct nfsd_net *nn)
while (!list_empty(&nn->close_lru)) {
oo = list_first_entry(&nn->close_lru, struct nfs4_openowner,
oo_close_lru);
- if (oo->oo_time > cutoff) {
- t = oo->oo_time - cutoff;
- new_timeo = min(new_timeo, t);
+ if (!state_expired(&lt, oo->oo_time))
break;
- }
list_del_init(&oo->oo_close_lru);
stp = oo->oo_last_closed_stid;
oo->oo_last_closed_stid = NULL;
@@ -5468,11 +5463,8 @@ nfs4_laundromat(struct nfsd_net *nn)
while (!list_empty(&nn->blocked_locks_lru)) {
nbl = list_first_entry(&nn->blocked_locks_lru,
struct nfsd4_blocked_lock, nbl_lru);
- if (nbl->nbl_time > cutoff) {
- t = nbl->nbl_time - cutoff;
- new_timeo = min(new_timeo, t);
+ if (!state_expired(&lt, nbl->nbl_time))
break;
- }
list_move(&nbl->nbl_lru, &reaplist);
list_del_init(&nbl->nbl_list);
}
@@ -5485,8 +5477,7 @@ nfs4_laundromat(struct nfsd_net *nn)
free_blocked_lock(nbl);
}
out:
- new_timeo = max_t(time64_t, new_timeo, NFSD_LAUNDROMAT_MINTIMEOUT);
- return new_timeo;
+ return max_t(time64_t, lt.new_timeo, NFSD_LAUNDROMAT_MINTIMEOUT);
}
static struct workqueue_struct *laundry_wq;
@@ -7346,14 +7337,9 @@ nfs4_state_start_net(struct net *net)
struct nfsd_net *nn = net_generic(net, nfsd_net_id);
int ret;
- ret = get_nfsdfs(net);
- if (ret)
- return ret;
ret = nfs4_state_create_net(net);
- if (ret) {
- mntput(nn->nfsd_mnt);
+ if (ret)
return ret;
- }
locks_start_grace(net, &nn->nfsd4_manager);
nfsd4_client_tracking_init(net);
if (nn->track_reclaim_completes && nn->reclaim_str_hashtbl_size == 0)
@@ -7423,7 +7409,6 @@ nfs4_state_shutdown_net(struct net *net)
nfsd4_client_tracking_exit(net);
nfs4_state_destroy_net(net);
- mntput(nn->nfsd_mnt);
}
void
diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c
index eaaa1605b5b5..e0f06d3cbd44 100644
--- a/fs/nfsd/nfs4xdr.c
+++ b/fs/nfsd/nfs4xdr.c
@@ -3581,7 +3581,7 @@ nfsd4_encode_stateid(struct xdr_stream *xdr, stateid_t *sid)
static __be32
nfsd4_encode_access(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_access *access)
{
- struct xdr_stream *xdr = &resp->xdr;
+ struct xdr_stream *xdr = resp->xdr;
__be32 *p;
p = xdr_reserve_space(xdr, 8);
@@ -3594,7 +3594,7 @@ nfsd4_encode_access(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_
static __be32 nfsd4_encode_bind_conn_to_session(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_bind_conn_to_session *bcts)
{
- struct xdr_stream *xdr = &resp->xdr;
+ struct xdr_stream *xdr = resp->xdr;
__be32 *p;
p = xdr_reserve_space(xdr, NFS4_MAX_SESSIONID_LEN + 8);
@@ -3611,7 +3611,7 @@ static __be32 nfsd4_encode_bind_conn_to_session(struct nfsd4_compoundres *resp,
static __be32
nfsd4_encode_close(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_close *close)
{
- struct xdr_stream *xdr = &resp->xdr;
+ struct xdr_stream *xdr = resp->xdr;
return nfsd4_encode_stateid(xdr, &close->cl_stateid);
}
@@ -3620,7 +3620,7 @@ nfsd4_encode_close(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_c
static __be32
nfsd4_encode_commit(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_commit *commit)
{
- struct xdr_stream *xdr = &resp->xdr;
+ struct xdr_stream *xdr = resp->xdr;
__be32 *p;
p = xdr_reserve_space(xdr, NFS4_VERIFIER_SIZE);
@@ -3634,7 +3634,7 @@ nfsd4_encode_commit(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_
static __be32
nfsd4_encode_create(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_create *create)
{
- struct xdr_stream *xdr = &resp->xdr;
+ struct xdr_stream *xdr = resp->xdr;
__be32 *p;
p = xdr_reserve_space(xdr, 20);
@@ -3649,7 +3649,7 @@ static __be32
nfsd4_encode_getattr(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_getattr *getattr)
{
struct svc_fh *fhp = getattr->ga_fhp;
- struct xdr_stream *xdr = &resp->xdr;
+ struct xdr_stream *xdr = resp->xdr;
return nfsd4_encode_fattr(xdr, fhp, fhp->fh_export, fhp->fh_dentry,
getattr->ga_bmval, resp->rqstp, 0);
@@ -3658,7 +3658,7 @@ nfsd4_encode_getattr(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4
static __be32
nfsd4_encode_getfh(struct nfsd4_compoundres *resp, __be32 nfserr, struct svc_fh **fhpp)
{
- struct xdr_stream *xdr = &resp->xdr;
+ struct xdr_stream *xdr = resp->xdr;
struct svc_fh *fhp = *fhpp;
unsigned int len;
__be32 *p;
@@ -3713,7 +3713,7 @@ again:
static __be32
nfsd4_encode_lock(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_lock *lock)
{
- struct xdr_stream *xdr = &resp->xdr;
+ struct xdr_stream *xdr = resp->xdr;
if (!nfserr)
nfserr = nfsd4_encode_stateid(xdr, &lock->lk_resp_stateid);
@@ -3726,7 +3726,7 @@ nfsd4_encode_lock(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_lo
static __be32
nfsd4_encode_lockt(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_lockt *lockt)
{
- struct xdr_stream *xdr = &resp->xdr;
+ struct xdr_stream *xdr = resp->xdr;
if (nfserr == nfserr_denied)
nfsd4_encode_lock_denied(xdr, &lockt->lt_denied);
@@ -3736,7 +3736,7 @@ nfsd4_encode_lockt(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_l
static __be32
nfsd4_encode_locku(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_locku *locku)
{
- struct xdr_stream *xdr = &resp->xdr;
+ struct xdr_stream *xdr = resp->xdr;
return nfsd4_encode_stateid(xdr, &locku->lu_stateid);
}
@@ -3745,7 +3745,7 @@ nfsd4_encode_locku(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_l
static __be32
nfsd4_encode_link(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_link *link)
{
- struct xdr_stream *xdr = &resp->xdr;
+ struct xdr_stream *xdr = resp->xdr;
__be32 *p;
p = xdr_reserve_space(xdr, 20);
@@ -3759,7 +3759,7 @@ nfsd4_encode_link(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_li
static __be32
nfsd4_encode_open(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_open *open)
{
- struct xdr_stream *xdr = &resp->xdr;
+ struct xdr_stream *xdr = resp->xdr;
__be32 *p;
nfserr = nfsd4_encode_stateid(xdr, &open->op_stateid);
@@ -3853,7 +3853,7 @@ nfsd4_encode_open(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_op
static __be32
nfsd4_encode_open_confirm(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_open_confirm *oc)
{
- struct xdr_stream *xdr = &resp->xdr;
+ struct xdr_stream *xdr = resp->xdr;
return nfsd4_encode_stateid(xdr, &oc->oc_resp_stateid);
}
@@ -3861,7 +3861,7 @@ nfsd4_encode_open_confirm(struct nfsd4_compoundres *resp, __be32 nfserr, struct
static __be32
nfsd4_encode_open_downgrade(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_open_downgrade *od)
{
- struct xdr_stream *xdr = &resp->xdr;
+ struct xdr_stream *xdr = resp->xdr;
return nfsd4_encode_stateid(xdr, &od->od_stateid);
}
@@ -3871,7 +3871,7 @@ static __be32 nfsd4_encode_splice_read(
struct nfsd4_read *read,
struct file *file, unsigned long maxcount)
{
- struct xdr_stream *xdr = &resp->xdr;
+ struct xdr_stream *xdr = resp->xdr;
struct xdr_buf *buf = xdr->buf;
int status, space_left;
u32 eof;
@@ -3937,7 +3937,7 @@ static __be32 nfsd4_encode_readv(struct nfsd4_compoundres *resp,
struct nfsd4_read *read,
struct file *file, unsigned long maxcount)
{
- struct xdr_stream *xdr = &resp->xdr;
+ struct xdr_stream *xdr = resp->xdr;
u32 eof;
int starting_len = xdr->buf->len - 8;
__be32 nfserr;
@@ -3976,7 +3976,7 @@ nfsd4_encode_read(struct nfsd4_compoundres *resp, __be32 nfserr,
struct nfsd4_read *read)
{
unsigned long maxcount;
- struct xdr_stream *xdr = &resp->xdr;
+ struct xdr_stream *xdr = resp->xdr;
struct file *file;
int starting_len = xdr->buf->len;
__be32 *p;
@@ -3990,7 +3990,7 @@ nfsd4_encode_read(struct nfsd4_compoundres *resp, __be32 nfserr,
WARN_ON_ONCE(test_bit(RQ_SPLICE_OK, &resp->rqstp->rq_flags));
return nfserr_resource;
}
- if (resp->xdr.buf->page_len &&
+ if (resp->xdr->buf->page_len &&
test_bit(RQ_SPLICE_OK, &resp->rqstp->rq_flags)) {
WARN_ON_ONCE(1);
return nfserr_resource;
@@ -4020,7 +4020,7 @@ nfsd4_encode_readlink(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd
int maxcount;
__be32 wire_count;
int zero = 0;
- struct xdr_stream *xdr = &resp->xdr;
+ struct xdr_stream *xdr = resp->xdr;
int length_offset = xdr->buf->len;
int status;
__be32 *p;
@@ -4072,7 +4072,7 @@ nfsd4_encode_readdir(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4
int bytes_left;
loff_t offset;
__be64 wire_offset;
- struct xdr_stream *xdr = &resp->xdr;
+ struct xdr_stream *xdr = resp->xdr;
int starting_len = xdr->buf->len;
__be32 *p;
@@ -4083,8 +4083,8 @@ nfsd4_encode_readdir(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4
/* XXX: Following NFSv3, we ignore the READDIR verifier for now. */
*p++ = cpu_to_be32(0);
*p++ = cpu_to_be32(0);
- resp->xdr.buf->head[0].iov_len = ((char *)resp->xdr.p)
- - (char *)resp->xdr.buf->head[0].iov_base;
+ xdr->buf->head[0].iov_len = (char *)xdr->p -
+ (char *)xdr->buf->head[0].iov_base;
/*
* Number of bytes left for directory entries allowing for the
@@ -4159,7 +4159,7 @@ err_no_verf:
static __be32
nfsd4_encode_remove(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_remove *remove)
{
- struct xdr_stream *xdr = &resp->xdr;
+ struct xdr_stream *xdr = resp->xdr;
__be32 *p;
p = xdr_reserve_space(xdr, 20);
@@ -4172,7 +4172,7 @@ nfsd4_encode_remove(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_
static __be32
nfsd4_encode_rename(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_rename *rename)
{
- struct xdr_stream *xdr = &resp->xdr;
+ struct xdr_stream *xdr = resp->xdr;
__be32 *p;
p = xdr_reserve_space(xdr, 40);
@@ -4255,7 +4255,7 @@ static __be32
nfsd4_encode_secinfo(struct nfsd4_compoundres *resp, __be32 nfserr,
struct nfsd4_secinfo *secinfo)
{
- struct xdr_stream *xdr = &resp->xdr;
+ struct xdr_stream *xdr = resp->xdr;
return nfsd4_do_encode_secinfo(xdr, secinfo->si_exp);
}
@@ -4264,7 +4264,7 @@ static __be32
nfsd4_encode_secinfo_no_name(struct nfsd4_compoundres *resp, __be32 nfserr,
struct nfsd4_secinfo_no_name *secinfo)
{
- struct xdr_stream *xdr = &resp->xdr;
+ struct xdr_stream *xdr = resp->xdr;
return nfsd4_do_encode_secinfo(xdr, secinfo->sin_exp);
}
@@ -4276,7 +4276,7 @@ nfsd4_encode_secinfo_no_name(struct nfsd4_compoundres *resp, __be32 nfserr,
static __be32
nfsd4_encode_setattr(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_setattr *setattr)
{
- struct xdr_stream *xdr = &resp->xdr;
+ struct xdr_stream *xdr = resp->xdr;
__be32 *p;
p = xdr_reserve_space(xdr, 16);
@@ -4300,7 +4300,7 @@ nfsd4_encode_setattr(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4
static __be32
nfsd4_encode_setclientid(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_setclientid *scd)
{
- struct xdr_stream *xdr = &resp->xdr;
+ struct xdr_stream *xdr = resp->xdr;
__be32 *p;
if (!nfserr) {
@@ -4324,7 +4324,7 @@ nfsd4_encode_setclientid(struct nfsd4_compoundres *resp, __be32 nfserr, struct n
static __be32
nfsd4_encode_write(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_write *write)
{
- struct xdr_stream *xdr = &resp->xdr;
+ struct xdr_stream *xdr = resp->xdr;
__be32 *p;
p = xdr_reserve_space(xdr, 16);
@@ -4341,7 +4341,7 @@ static __be32
nfsd4_encode_exchange_id(struct nfsd4_compoundres *resp, __be32 nfserr,
struct nfsd4_exchange_id *exid)
{
- struct xdr_stream *xdr = &resp->xdr;
+ struct xdr_stream *xdr = resp->xdr;
__be32 *p;
char *major_id;
char *server_scope;
@@ -4419,7 +4419,7 @@ static __be32
nfsd4_encode_create_session(struct nfsd4_compoundres *resp, __be32 nfserr,
struct nfsd4_create_session *sess)
{
- struct xdr_stream *xdr = &resp->xdr;
+ struct xdr_stream *xdr = resp->xdr;
__be32 *p;
p = xdr_reserve_space(xdr, 24);
@@ -4472,7 +4472,7 @@ static __be32
nfsd4_encode_sequence(struct nfsd4_compoundres *resp, __be32 nfserr,
struct nfsd4_sequence *seq)
{
- struct xdr_stream *xdr = &resp->xdr;
+ struct xdr_stream *xdr = resp->xdr;
__be32 *p;
p = xdr_reserve_space(xdr, NFS4_MAX_SESSIONID_LEN + 20);
@@ -4495,7 +4495,7 @@ static __be32
nfsd4_encode_test_stateid(struct nfsd4_compoundres *resp, __be32 nfserr,
struct nfsd4_test_stateid *test_stateid)
{
- struct xdr_stream *xdr = &resp->xdr;
+ struct xdr_stream *xdr = resp->xdr;
struct nfsd4_test_stateid_id *stateid, *next;
__be32 *p;
@@ -4516,7 +4516,7 @@ static __be32
nfsd4_encode_getdeviceinfo(struct nfsd4_compoundres *resp, __be32 nfserr,
struct nfsd4_getdeviceinfo *gdev)
{
- struct xdr_stream *xdr = &resp->xdr;
+ struct xdr_stream *xdr = resp->xdr;
const struct nfsd4_layout_ops *ops;
u32 starting_len = xdr->buf->len, needed_len;
__be32 *p;
@@ -4572,7 +4572,7 @@ static __be32
nfsd4_encode_layoutget(struct nfsd4_compoundres *resp, __be32 nfserr,
struct nfsd4_layoutget *lgp)
{
- struct xdr_stream *xdr = &resp->xdr;
+ struct xdr_stream *xdr = resp->xdr;
const struct nfsd4_layout_ops *ops;
__be32 *p;
@@ -4599,7 +4599,7 @@ static __be32
nfsd4_encode_layoutcommit(struct nfsd4_compoundres *resp, __be32 nfserr,
struct nfsd4_layoutcommit *lcp)
{
- struct xdr_stream *xdr = &resp->xdr;
+ struct xdr_stream *xdr = resp->xdr;
__be32 *p;
p = xdr_reserve_space(xdr, 4);
@@ -4620,7 +4620,7 @@ static __be32
nfsd4_encode_layoutreturn(struct nfsd4_compoundres *resp, __be32 nfserr,
struct nfsd4_layoutreturn *lrp)
{
- struct xdr_stream *xdr = &resp->xdr;
+ struct xdr_stream *xdr = resp->xdr;
__be32 *p;
p = xdr_reserve_space(xdr, 4);
@@ -4638,7 +4638,7 @@ nfsd42_encode_write_res(struct nfsd4_compoundres *resp,
struct nfsd42_write_res *write, bool sync)
{
__be32 *p;
- p = xdr_reserve_space(&resp->xdr, 4);
+ p = xdr_reserve_space(resp->xdr, 4);
if (!p)
return nfserr_resource;
@@ -4647,11 +4647,11 @@ nfsd42_encode_write_res(struct nfsd4_compoundres *resp,
else {
__be32 nfserr;
*p++ = cpu_to_be32(1);
- nfserr = nfsd4_encode_stateid(&resp->xdr, &write->cb_stateid);
+ nfserr = nfsd4_encode_stateid(resp->xdr, &write->cb_stateid);
if (nfserr)
return nfserr;
}
- p = xdr_reserve_space(&resp->xdr, 8 + 4 + NFS4_VERIFIER_SIZE);
+ p = xdr_reserve_space(resp->xdr, 8 + 4 + NFS4_VERIFIER_SIZE);
if (!p)
return nfserr_resource;
@@ -4665,7 +4665,7 @@ nfsd42_encode_write_res(struct nfsd4_compoundres *resp,
static __be32
nfsd42_encode_nl4_server(struct nfsd4_compoundres *resp, struct nl4_server *ns)
{
- struct xdr_stream *xdr = &resp->xdr;
+ struct xdr_stream *xdr = resp->xdr;
struct nfs42_netaddr *addr;
__be32 *p;
@@ -4713,7 +4713,7 @@ nfsd4_encode_copy(struct nfsd4_compoundres *resp, __be32 nfserr,
if (nfserr)
return nfserr;
- p = xdr_reserve_space(&resp->xdr, 4 + 4);
+ p = xdr_reserve_space(resp->xdr, 4 + 4);
*p++ = xdr_one; /* cr_consecutive */
*p++ = cpu_to_be32(copy->cp_synchronous);
return 0;
@@ -4723,7 +4723,7 @@ static __be32
nfsd4_encode_offload_status(struct nfsd4_compoundres *resp, __be32 nfserr,
struct nfsd4_offload_status *os)
{
- struct xdr_stream *xdr = &resp->xdr;
+ struct xdr_stream *xdr = resp->xdr;
__be32 *p;
p = xdr_reserve_space(xdr, 8 + 4);
@@ -4740,7 +4740,7 @@ nfsd4_encode_read_plus_data(struct nfsd4_compoundres *resp,
unsigned long *maxcount, u32 *eof,
loff_t *pos)
{
- struct xdr_stream *xdr = &resp->xdr;
+ struct xdr_stream *xdr = resp->xdr;
struct file *file = read->rd_nf->nf_file;
int starting_len = xdr->buf->len;
loff_t hole_pos;
@@ -4799,7 +4799,7 @@ nfsd4_encode_read_plus_hole(struct nfsd4_compoundres *resp,
count = data_pos - read->rd_offset;
/* Content type, offset, byte count */
- p = xdr_reserve_space(&resp->xdr, 4 + 8 + 8);
+ p = xdr_reserve_space(resp->xdr, 4 + 8 + 8);
if (!p)
return nfserr_resource;
@@ -4817,7 +4817,7 @@ nfsd4_encode_read_plus(struct nfsd4_compoundres *resp, __be32 nfserr,
struct nfsd4_read *read)
{
unsigned long maxcount, count;
- struct xdr_stream *xdr = &resp->xdr;
+ struct xdr_stream *xdr = resp->xdr;
struct file *file;
int starting_len = xdr->buf->len;
int last_segment = xdr->buf->len;
@@ -4888,7 +4888,7 @@ static __be32
nfsd4_encode_copy_notify(struct nfsd4_compoundres *resp, __be32 nfserr,
struct nfsd4_copy_notify *cn)
{
- struct xdr_stream *xdr = &resp->xdr;
+ struct xdr_stream *xdr = resp->xdr;
__be32 *p;
if (nfserr)
@@ -4924,7 +4924,7 @@ nfsd4_encode_seek(struct nfsd4_compoundres *resp, __be32 nfserr,
{
__be32 *p;
- p = xdr_reserve_space(&resp->xdr, 4 + 8);
+ p = xdr_reserve_space(resp->xdr, 4 + 8);
*p++ = cpu_to_be32(seek->seek_eof);
p = xdr_encode_hyper(p, seek->seek_pos);
@@ -4985,7 +4985,7 @@ static __be32
nfsd4_encode_getxattr(struct nfsd4_compoundres *resp, __be32 nfserr,
struct nfsd4_getxattr *getxattr)
{
- struct xdr_stream *xdr = &resp->xdr;
+ struct xdr_stream *xdr = resp->xdr;
__be32 *p, err;
p = xdr_reserve_space(xdr, 4);
@@ -5009,7 +5009,7 @@ static __be32
nfsd4_encode_setxattr(struct nfsd4_compoundres *resp, __be32 nfserr,
struct nfsd4_setxattr *setxattr)
{
- struct xdr_stream *xdr = &resp->xdr;
+ struct xdr_stream *xdr = resp->xdr;
__be32 *p;
p = xdr_reserve_space(xdr, 20);
@@ -5050,7 +5050,7 @@ static __be32
nfsd4_encode_listxattrs(struct nfsd4_compoundres *resp, __be32 nfserr,
struct nfsd4_listxattrs *listxattrs)
{
- struct xdr_stream *xdr = &resp->xdr;
+ struct xdr_stream *xdr = resp->xdr;
u32 cookie_offset, count_offset, eof;
u32 left, xdrleft, slen, count;
u32 xdrlen, offset;
@@ -5161,7 +5161,7 @@ static __be32
nfsd4_encode_removexattr(struct nfsd4_compoundres *resp, __be32 nfserr,
struct nfsd4_removexattr *removexattr)
{
- struct xdr_stream *xdr = &resp->xdr;
+ struct xdr_stream *xdr = resp->xdr;
__be32 *p;
p = xdr_reserve_space(xdr, 20);
@@ -5301,7 +5301,7 @@ __be32 nfsd4_check_resp_size(struct nfsd4_compoundres *resp, u32 respsize)
void
nfsd4_encode_operation(struct nfsd4_compoundres *resp, struct nfsd4_op *op)
{
- struct xdr_stream *xdr = &resp->xdr;
+ struct xdr_stream *xdr = resp->xdr;
struct nfs4_stateowner *so = resp->cstate.replay_owner;
struct svc_rqst *rqstp = resp->rqstp;
const struct nfsd4_operation *opdesc = op->opdesc;
@@ -5430,14 +5430,14 @@ int
nfs4svc_encode_compoundres(struct svc_rqst *rqstp, __be32 *p)
{
struct nfsd4_compoundres *resp = rqstp->rq_resp;
- struct xdr_buf *buf = resp->xdr.buf;
+ struct xdr_buf *buf = resp->xdr->buf;
WARN_ON_ONCE(buf->len != buf->head[0].iov_len + buf->page_len +
buf->tail[0].iov_len);
*p = resp->cstate.status;
- rqstp->rq_next_page = resp->xdr.page_ptr + 1;
+ rqstp->rq_next_page = resp->xdr->page_ptr + 1;
p = resp->tagp;
*p++ = htonl(resp->taglen);
diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c
index ef86ed23af82..853bf50a2a9b 100644
--- a/fs/nfsd/nfsctl.c
+++ b/fs/nfsd/nfsctl.c
@@ -1266,7 +1266,8 @@ static void nfsdfs_remove_files(struct dentry *root)
/* XXX: cut'n'paste from simple_fill_super; figure out if we could share
* code instead. */
static int nfsdfs_create_files(struct dentry *root,
- const struct tree_descr *files)
+ const struct tree_descr *files,
+ struct dentry **fdentries)
{
struct inode *dir = d_inode(root);
struct inode *inode;
@@ -1275,8 +1276,6 @@ static int nfsdfs_create_files(struct dentry *root,
inode_lock(dir);
for (i = 0; files->name && files->name[0]; i++, files++) {
- if (!files->name)
- continue;
dentry = d_alloc_name(root, files->name);
if (!dentry)
goto out;
@@ -1290,6 +1289,8 @@ static int nfsdfs_create_files(struct dentry *root,
inode->i_private = __get_nfsdfs_client(dir);
d_add(dentry, inode);
fsnotify_create(dir, dentry);
+ if (fdentries)
+ fdentries[i] = dentry;
}
inode_unlock(dir);
return 0;
@@ -1301,8 +1302,9 @@ out:
/* on success, returns positive number unique to that client. */
struct dentry *nfsd_client_mkdir(struct nfsd_net *nn,
- struct nfsdfs_client *ncl, u32 id,
- const struct tree_descr *files)
+ struct nfsdfs_client *ncl, u32 id,
+ const struct tree_descr *files,
+ struct dentry **fdentries)
{
struct dentry *dentry;
char name[11];
@@ -1313,7 +1315,7 @@ struct dentry *nfsd_client_mkdir(struct nfsd_net *nn,
dentry = nfsd_mkdir(nn->nfsd_client_dir, ncl, name);
if (IS_ERR(dentry)) /* XXX: tossing errors? */
return NULL;
- ret = nfsdfs_create_files(dentry, files);
+ ret = nfsdfs_create_files(dentry, files, fdentries);
if (ret) {
nfsd_client_rmdir(dentry);
return NULL;
@@ -1416,6 +1418,8 @@ static void nfsd_umount(struct super_block *sb)
{
struct net *net = sb->s_fs_info;
+ nfsd_shutdown_threads(net);
+
kill_litter_super(sb);
put_net(net);
}
@@ -1428,18 +1432,6 @@ static struct file_system_type nfsd_fs_type = {
};
MODULE_ALIAS_FS("nfsd");
-int get_nfsdfs(struct net *net)
-{
- struct nfsd_net *nn = net_generic(net, nfsd_net_id);
- struct vfsmount *mnt;
-
- mnt = vfs_kern_mount(&nfsd_fs_type, SB_KERNMOUNT, "nfsd", NULL);
- if (IS_ERR(mnt))
- return PTR_ERR(mnt);
- nn->nfsd_mnt = mnt;
- return 0;
-}
-
#ifdef CONFIG_PROC_FS
static int create_proc_exports_entry(void)
{
diff --git a/fs/nfsd/nfsd.h b/fs/nfsd/nfsd.h
index 8bdc37aa2c2e..14dbfa75059d 100644
--- a/fs/nfsd/nfsd.h
+++ b/fs/nfsd/nfsd.h
@@ -93,13 +93,12 @@ int nfsd_get_nrthreads(int n, int *, struct net *);
int nfsd_set_nrthreads(int n, int *, struct net *);
int nfsd_pool_stats_open(struct inode *, struct file *);
int nfsd_pool_stats_release(struct inode *, struct file *);
+void nfsd_shutdown_threads(struct net *net);
void nfsd_destroy(struct net *net);
bool i_am_nfsd(void);
-int get_nfsdfs(struct net *);
-
struct nfsdfs_client {
struct kref cl_ref;
void (*cl_release)(struct kref *kref);
@@ -107,7 +106,9 @@ struct nfsdfs_client {
struct nfsdfs_client *get_nfsdfs_client(struct inode *);
struct dentry *nfsd_client_mkdir(struct nfsd_net *nn,
- struct nfsdfs_client *ncl, u32 id, const struct tree_descr *);
+ struct nfsdfs_client *ncl, u32 id,
+ const struct tree_descr *,
+ struct dentry **fdentries);
void nfsd_client_rmdir(struct dentry *dentry);
diff --git a/fs/nfsd/nfsfh.c b/fs/nfsd/nfsfh.c
index 10b44421eace..c475d2271f9c 100644
--- a/fs/nfsd/nfsfh.c
+++ b/fs/nfsd/nfsfh.c
@@ -711,7 +711,7 @@ char * SVCFH_fmt(struct svc_fh *fhp)
return buf;
}
-enum fsid_source fsid_source(struct svc_fh *fhp)
+enum fsid_source fsid_source(const struct svc_fh *fhp)
{
if (fhp->fh_handle.fh_version != 1)
return FSIDSOURCE_DEV;
diff --git a/fs/nfsd/nfsfh.h b/fs/nfsd/nfsfh.h
index f58933519f38..aff2cda5c6c3 100644
--- a/fs/nfsd/nfsfh.h
+++ b/fs/nfsd/nfsfh.h
@@ -82,7 +82,7 @@ enum fsid_source {
FSIDSOURCE_FSID,
FSIDSOURCE_UUID,
};
-extern enum fsid_source fsid_source(struct svc_fh *fhp);
+extern enum fsid_source fsid_source(const struct svc_fh *fhp);
/*
diff --git a/fs/nfsd/nfsproc.c b/fs/nfsd/nfsproc.c
index a8d5449dd0e9..60d7c59e7935 100644
--- a/fs/nfsd/nfsproc.c
+++ b/fs/nfsd/nfsproc.c
@@ -151,13 +151,14 @@ nfsd_proc_readlink(struct svc_rqst *rqstp)
{
struct nfsd_fhandle *argp = rqstp->rq_argp;
struct nfsd_readlinkres *resp = rqstp->rq_resp;
- char *buffer = page_address(*(rqstp->rq_next_page++));
dprintk("nfsd: READLINK %s\n", SVCFH_fmt(&argp->fh));
/* Read the symlink. */
resp->len = NFS_MAXPATHLEN;
- resp->status = nfsd_readlink(rqstp, &argp->fh, buffer, &resp->len);
+ resp->page = *(rqstp->rq_next_page++);
+ resp->status = nfsd_readlink(rqstp, &argp->fh,
+ page_address(resp->page), &resp->len);
fh_put(&argp->fh);
return rpc_success;
@@ -184,6 +185,7 @@ nfsd_proc_read(struct svc_rqst *rqstp)
v = 0;
len = argp->count;
+ resp->pages = rqstp->rq_next_page;
while (len > 0) {
struct page *page = *(rqstp->rq_next_page++);
@@ -381,7 +383,7 @@ nfsd_proc_create(struct svc_rqst *rqstp)
/* Make sure the type and device matches */
resp->status = nfserr_exist;
- if (inode && type != (inode->i_mode & S_IFMT))
+ if (inode && inode_wrong_type(inode, type))
goto out_unlock;
}
@@ -557,14 +559,27 @@ static void nfsd_init_dirlist_pages(struct svc_rqst *rqstp,
struct nfsd_readdirres *resp,
int count)
{
+ struct xdr_buf *buf = &resp->dirlist;
+ struct xdr_stream *xdr = &resp->xdr;
+
count = min_t(u32, count, PAGE_SIZE);
- /* Convert byte count to number of words (i.e. >> 2),
- * and reserve room for the NULL ptr & eof flag (-2 words) */
- resp->buflen = (count >> 2) - 2;
+ memset(buf, 0, sizeof(*buf));
- resp->buffer = page_address(*rqstp->rq_next_page);
+ /* Reserve room for the NULL ptr & eof flag (-2 words) */
+ buf->buflen = count - sizeof(__be32) * 2;
+ buf->pages = rqstp->rq_next_page;
rqstp->rq_next_page++;
+
+ /* This is xdr_init_encode(), but it assumes that
+ * the head kvec has already been consumed. */
+ xdr_set_scratch_buffer(xdr, NULL, 0);
+ xdr->buf = buf;
+ xdr->page_ptr = buf->pages;
+ xdr->iov = NULL;
+ xdr->p = page_address(*buf->pages);
+ xdr->end = xdr->p + (PAGE_SIZE >> 2);
+ xdr->rqst = NULL;
}
/*
@@ -576,25 +591,19 @@ nfsd_proc_readdir(struct svc_rqst *rqstp)
struct nfsd_readdirargs *argp = rqstp->rq_argp;
struct nfsd_readdirres *resp = rqstp->rq_resp;
loff_t offset;
- __be32 *buffer;
dprintk("nfsd: READDIR %s %d bytes at %d\n",
SVCFH_fmt(&argp->fh),
argp->count, argp->cookie);
nfsd_init_dirlist_pages(rqstp, resp, argp->count);
- buffer = resp->buffer;
- resp->offset = NULL;
resp->common.err = nfs_ok;
- /* Read directory and encode entries on the fly */
+ resp->cookie_offset = 0;
offset = argp->cookie;
resp->status = nfsd_readdir(rqstp, &argp->fh, &offset,
&resp->common, nfssvc_encode_entry);
-
- resp->count = resp->buffer - buffer;
- if (resp->offset)
- *resp->offset = htonl(offset);
+ nfssvc_encode_nfscookie(resp, offset);
fh_put(&argp->fh);
return rpc_success;
@@ -640,7 +649,7 @@ static const struct svc_procedure nfsd_procedures2[18] = {
[NFSPROC_GETATTR] = {
.pc_func = nfsd_proc_getattr,
.pc_decode = nfssvc_decode_fhandleargs,
- .pc_encode = nfssvc_encode_attrstat,
+ .pc_encode = nfssvc_encode_attrstatres,
.pc_release = nfssvc_release_attrstat,
.pc_argsize = sizeof(struct nfsd_fhandle),
.pc_ressize = sizeof(struct nfsd_attrstat),
@@ -651,7 +660,7 @@ static const struct svc_procedure nfsd_procedures2[18] = {
[NFSPROC_SETATTR] = {
.pc_func = nfsd_proc_setattr,
.pc_decode = nfssvc_decode_sattrargs,
- .pc_encode = nfssvc_encode_attrstat,
+ .pc_encode = nfssvc_encode_attrstatres,
.pc_release = nfssvc_release_attrstat,
.pc_argsize = sizeof(struct nfsd_sattrargs),
.pc_ressize = sizeof(struct nfsd_attrstat),
@@ -714,7 +723,7 @@ static const struct svc_procedure nfsd_procedures2[18] = {
[NFSPROC_WRITE] = {
.pc_func = nfsd_proc_write,
.pc_decode = nfssvc_decode_writeargs,
- .pc_encode = nfssvc_encode_attrstat,
+ .pc_encode = nfssvc_encode_attrstatres,
.pc_release = nfssvc_release_attrstat,
.pc_argsize = sizeof(struct nfsd_writeargs),
.pc_ressize = sizeof(struct nfsd_attrstat),
@@ -736,7 +745,7 @@ static const struct svc_procedure nfsd_procedures2[18] = {
[NFSPROC_REMOVE] = {
.pc_func = nfsd_proc_remove,
.pc_decode = nfssvc_decode_diropargs,
- .pc_encode = nfssvc_encode_stat,
+ .pc_encode = nfssvc_encode_statres,
.pc_argsize = sizeof(struct nfsd_diropargs),
.pc_ressize = sizeof(struct nfsd_stat),
.pc_cachetype = RC_REPLSTAT,
@@ -746,7 +755,7 @@ static const struct svc_procedure nfsd_procedures2[18] = {
[NFSPROC_RENAME] = {
.pc_func = nfsd_proc_rename,
.pc_decode = nfssvc_decode_renameargs,
- .pc_encode = nfssvc_encode_stat,
+ .pc_encode = nfssvc_encode_statres,
.pc_argsize = sizeof(struct nfsd_renameargs),
.pc_ressize = sizeof(struct nfsd_stat),
.pc_cachetype = RC_REPLSTAT,
@@ -756,7 +765,7 @@ static const struct svc_procedure nfsd_procedures2[18] = {
[NFSPROC_LINK] = {
.pc_func = nfsd_proc_link,
.pc_decode = nfssvc_decode_linkargs,
- .pc_encode = nfssvc_encode_stat,
+ .pc_encode = nfssvc_encode_statres,
.pc_argsize = sizeof(struct nfsd_linkargs),
.pc_ressize = sizeof(struct nfsd_stat),
.pc_cachetype = RC_REPLSTAT,
@@ -766,7 +775,7 @@ static const struct svc_procedure nfsd_procedures2[18] = {
[NFSPROC_SYMLINK] = {
.pc_func = nfsd_proc_symlink,
.pc_decode = nfssvc_decode_symlinkargs,
- .pc_encode = nfssvc_encode_stat,
+ .pc_encode = nfssvc_encode_statres,
.pc_argsize = sizeof(struct nfsd_symlinkargs),
.pc_ressize = sizeof(struct nfsd_stat),
.pc_cachetype = RC_REPLSTAT,
@@ -787,7 +796,7 @@ static const struct svc_procedure nfsd_procedures2[18] = {
[NFSPROC_RMDIR] = {
.pc_func = nfsd_proc_rmdir,
.pc_decode = nfssvc_decode_diropargs,
- .pc_encode = nfssvc_encode_stat,
+ .pc_encode = nfssvc_encode_statres,
.pc_argsize = sizeof(struct nfsd_diropargs),
.pc_ressize = sizeof(struct nfsd_stat),
.pc_cachetype = RC_REPLSTAT,
diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c
index 6de406322106..82ba034fa579 100644
--- a/fs/nfsd/nfssvc.c
+++ b/fs/nfsd/nfssvc.c
@@ -84,7 +84,7 @@ DEFINE_MUTEX(nfsd_mutex);
* version 4.1 DRC caches.
* nfsd_drc_pages_used tracks the current version 4.1 DRC memory usage.
*/
-spinlock_t nfsd_drc_lock;
+DEFINE_SPINLOCK(nfsd_drc_lock);
unsigned long nfsd_drc_max_mem;
unsigned long nfsd_drc_mem_used;
@@ -563,7 +563,6 @@ static void set_max_drc(void)
nfsd_drc_max_mem = (nr_free_buffer_pages()
>> NFSD_DRC_SIZE_SHIFT) * PAGE_SIZE;
nfsd_drc_mem_used = 0;
- spin_lock_init(&nfsd_drc_lock);
dprintk("%s nfsd_drc_max_mem %lu \n", __func__, nfsd_drc_max_mem);
}
@@ -596,6 +595,37 @@ static const struct svc_serv_ops nfsd_thread_sv_ops = {
.svo_module = THIS_MODULE,
};
+static void nfsd_complete_shutdown(struct net *net)
+{
+ struct nfsd_net *nn = net_generic(net, nfsd_net_id);
+
+ WARN_ON(!mutex_is_locked(&nfsd_mutex));
+
+ nn->nfsd_serv = NULL;
+ complete(&nn->nfsd_shutdown_complete);
+}
+
+void nfsd_shutdown_threads(struct net *net)
+{
+ struct nfsd_net *nn = net_generic(net, nfsd_net_id);
+ struct svc_serv *serv;
+
+ mutex_lock(&nfsd_mutex);
+ serv = nn->nfsd_serv;
+ if (serv == NULL) {
+ mutex_unlock(&nfsd_mutex);
+ return;
+ }
+
+ svc_get(serv);
+ /* Kill outstanding nfsd threads */
+ serv->sv_ops->svo_setup(serv, NULL, 0);
+ nfsd_destroy(net);
+ mutex_unlock(&nfsd_mutex);
+ /* Wait for shutdown of nfsd_serv to complete */
+ wait_for_completion(&nn->nfsd_shutdown_complete);
+}
+
bool i_am_nfsd(void)
{
return kthread_func(current) == nfsd;
@@ -618,11 +648,13 @@ int nfsd_create_serv(struct net *net)
&nfsd_thread_sv_ops);
if (nn->nfsd_serv == NULL)
return -ENOMEM;
+ init_completion(&nn->nfsd_shutdown_complete);
nn->nfsd_serv->sv_maxconn = nn->max_connections;
error = svc_bind(nn->nfsd_serv, net);
if (error < 0) {
svc_destroy(nn->nfsd_serv);
+ nfsd_complete_shutdown(net);
return error;
}
@@ -671,7 +703,7 @@ void nfsd_destroy(struct net *net)
svc_shutdown_net(nn->nfsd_serv, net);
svc_destroy(nn->nfsd_serv);
if (destroy)
- nn->nfsd_serv = NULL;
+ nfsd_complete_shutdown(net);
}
int nfsd_set_nrthreads(int n, int *nthreads, struct net *net)
@@ -997,7 +1029,7 @@ int nfsd_dispatch(struct svc_rqst *rqstp, __be32 *statp)
* NFSv4 does some encoding while processing
*/
p = resv->iov_base + resv->iov_len;
- resv->iov_len += sizeof(__be32);
+ svcxdr_init_encode(rqstp);
*statp = proc->pc_func(rqstp);
if (*statp == rpc_drop_reply || test_bit(RQ_DROPME, &rqstp->rq_flags))
@@ -1052,7 +1084,7 @@ int nfssvc_decode_voidarg(struct svc_rqst *rqstp, __be32 *p)
*/
int nfssvc_encode_voidres(struct svc_rqst *rqstp, __be32 *p)
{
- return xdr_ressize_check(rqstp, p);
+ return 1;
}
int nfsd_pool_stats_open(struct inode *inode, struct file *file)
diff --git a/fs/nfsd/nfsxdr.c b/fs/nfsd/nfsxdr.c
index 5d79ef6a0c7f..a06c05fe3b42 100644
--- a/fs/nfsd/nfsxdr.c
+++ b/fs/nfsd/nfsxdr.c
@@ -9,12 +9,10 @@
#include "xdr.h"
#include "auth.h"
-#define NFSDDBG_FACILITY NFSDDBG_XDR
-
/*
* Mapping of S_IF* types to NFS file types
*/
-static u32 nfs_ftypes[] = {
+static const u32 nfs_ftypes[] = {
NFNON, NFCHR, NFCHR, NFBAD,
NFDIR, NFBAD, NFBLK, NFBAD,
NFREG, NFBAD, NFLNK, NFBAD,
@@ -27,6 +25,28 @@ static u32 nfs_ftypes[] = {
*/
/**
+ * svcxdr_encode_stat - Encode an NFSv2 status code
+ * @xdr: XDR stream
+ * @status: status value to encode
+ *
+ * Return values:
+ * %false: Send buffer space was exhausted
+ * %true: Success
+ */
+bool
+svcxdr_encode_stat(struct xdr_stream *xdr, __be32 status)
+{
+ __be32 *p;
+
+ p = xdr_reserve_space(xdr, sizeof(status));
+ if (!p)
+ return false;
+ *p = status;
+
+ return true;
+}
+
+/**
* svcxdr_decode_fhandle - Decode an NFSv2 file handle
* @xdr: XDR stream positioned at an encoded NFSv2 FH
* @fhp: OUT: filled-in server file handle
@@ -50,11 +70,28 @@ svcxdr_decode_fhandle(struct xdr_stream *xdr, struct svc_fh *fhp)
return true;
}
-static __be32 *
-encode_fh(__be32 *p, struct svc_fh *fhp)
+static bool
+svcxdr_encode_fhandle(struct xdr_stream *xdr, const struct svc_fh *fhp)
{
+ __be32 *p;
+
+ p = xdr_reserve_space(xdr, NFS_FHSIZE);
+ if (!p)
+ return false;
memcpy(p, &fhp->fh_handle.fh_base, NFS_FHSIZE);
- return p + (NFS_FHSIZE>> 2);
+
+ return true;
+}
+
+static __be32 *
+encode_timeval(__be32 *p, const struct timespec64 *time)
+{
+ *p++ = cpu_to_be32((u32)time->tv_sec);
+ if (time->tv_nsec)
+ *p++ = cpu_to_be32(time->tv_nsec / NSEC_PER_USEC);
+ else
+ *p++ = xdr_zero;
+ return p;
}
static bool
@@ -162,68 +199,73 @@ svcxdr_decode_sattr(struct svc_rqst *rqstp, struct xdr_stream *xdr,
return true;
}
-static __be32 *
-encode_fattr(struct svc_rqst *rqstp, __be32 *p, struct svc_fh *fhp,
- struct kstat *stat)
+/**
+ * svcxdr_encode_fattr - Encode NFSv2 file attributes
+ * @rqstp: Context of a completed RPC transaction
+ * @xdr: XDR stream
+ * @fhp: File handle to encode
+ * @stat: Attributes to encode
+ *
+ * Return values:
+ * %false: Send buffer space was exhausted
+ * %true: Success
+ */
+bool
+svcxdr_encode_fattr(struct svc_rqst *rqstp, struct xdr_stream *xdr,
+ const struct svc_fh *fhp, const struct kstat *stat)
{
struct user_namespace *userns = nfsd_user_namespace(rqstp);
- struct dentry *dentry = fhp->fh_dentry;
- int type;
+ struct dentry *dentry = fhp->fh_dentry;
+ int type = stat->mode & S_IFMT;
struct timespec64 time;
- u32 f;
+ __be32 *p;
+ u32 fsid;
- type = (stat->mode & S_IFMT);
+ p = xdr_reserve_space(xdr, XDR_UNIT * 17);
+ if (!p)
+ return false;
- *p++ = htonl(nfs_ftypes[type >> 12]);
- *p++ = htonl((u32) stat->mode);
- *p++ = htonl((u32) stat->nlink);
- *p++ = htonl((u32) from_kuid_munged(userns, stat->uid));
- *p++ = htonl((u32) from_kgid_munged(userns, stat->gid));
+ *p++ = cpu_to_be32(nfs_ftypes[type >> 12]);
+ *p++ = cpu_to_be32((u32)stat->mode);
+ *p++ = cpu_to_be32((u32)stat->nlink);
+ *p++ = cpu_to_be32((u32)from_kuid_munged(userns, stat->uid));
+ *p++ = cpu_to_be32((u32)from_kgid_munged(userns, stat->gid));
- if (S_ISLNK(type) && stat->size > NFS_MAXPATHLEN) {
- *p++ = htonl(NFS_MAXPATHLEN);
- } else {
- *p++ = htonl((u32) stat->size);
- }
- *p++ = htonl((u32) stat->blksize);
+ if (S_ISLNK(type) && stat->size > NFS_MAXPATHLEN)
+ *p++ = cpu_to_be32(NFS_MAXPATHLEN);
+ else
+ *p++ = cpu_to_be32((u32) stat->size);
+ *p++ = cpu_to_be32((u32) stat->blksize);
if (S_ISCHR(type) || S_ISBLK(type))
- *p++ = htonl(new_encode_dev(stat->rdev));
+ *p++ = cpu_to_be32(new_encode_dev(stat->rdev));
else
- *p++ = htonl(0xffffffff);
- *p++ = htonl((u32) stat->blocks);
+ *p++ = cpu_to_be32(0xffffffff);
+ *p++ = cpu_to_be32((u32)stat->blocks);
+
switch (fsid_source(fhp)) {
- default:
- case FSIDSOURCE_DEV:
- *p++ = htonl(new_encode_dev(stat->dev));
- break;
case FSIDSOURCE_FSID:
- *p++ = htonl((u32) fhp->fh_export->ex_fsid);
+ fsid = (u32)fhp->fh_export->ex_fsid;
break;
case FSIDSOURCE_UUID:
- f = ((u32*)fhp->fh_export->ex_uuid)[0];
- f ^= ((u32*)fhp->fh_export->ex_uuid)[1];
- f ^= ((u32*)fhp->fh_export->ex_uuid)[2];
- f ^= ((u32*)fhp->fh_export->ex_uuid)[3];
- *p++ = htonl(f);
+ fsid = ((u32 *)fhp->fh_export->ex_uuid)[0];
+ fsid ^= ((u32 *)fhp->fh_export->ex_uuid)[1];
+ fsid ^= ((u32 *)fhp->fh_export->ex_uuid)[2];
+ fsid ^= ((u32 *)fhp->fh_export->ex_uuid)[3];
+ break;
+ default:
+ fsid = new_encode_dev(stat->dev);
break;
}
- *p++ = htonl((u32) stat->ino);
- *p++ = htonl((u32) stat->atime.tv_sec);
- *p++ = htonl(stat->atime.tv_nsec ? stat->atime.tv_nsec / 1000 : 0);
- time = stat->mtime;
- lease_get_mtime(d_inode(dentry), &time);
- *p++ = htonl((u32) time.tv_sec);
- *p++ = htonl(time.tv_nsec ? time.tv_nsec / 1000 : 0);
- *p++ = htonl((u32) stat->ctime.tv_sec);
- *p++ = htonl(stat->ctime.tv_nsec ? stat->ctime.tv_nsec / 1000 : 0);
+ *p++ = cpu_to_be32(fsid);
- return p;
-}
+ *p++ = cpu_to_be32((u32)stat->ino);
+ p = encode_timeval(p, &stat->atime);
+ time = stat->mtime;
+ lease_get_mtime(d_inode(dentry), &time);
+ p = encode_timeval(p, &time);
+ encode_timeval(p, &stat->ctime);
-/* Helper function for NFSv2 ACL code */
-__be32 *nfs2svc_encode_fattr(struct svc_rqst *rqstp, __be32 *p, struct svc_fh *fhp, struct kstat *stat)
-{
- return encode_fattr(rqstp, p, fhp, stat);
+ return true;
}
/*
@@ -390,106 +432,118 @@ nfssvc_decode_readdirargs(struct svc_rqst *rqstp, __be32 *p)
*/
int
-nfssvc_encode_stat(struct svc_rqst *rqstp, __be32 *p)
+nfssvc_encode_statres(struct svc_rqst *rqstp, __be32 *p)
{
+ struct xdr_stream *xdr = &rqstp->rq_res_stream;
struct nfsd_stat *resp = rqstp->rq_resp;
- *p++ = resp->status;
- return xdr_ressize_check(rqstp, p);
+ return svcxdr_encode_stat(xdr, resp->status);
}
int
-nfssvc_encode_attrstat(struct svc_rqst *rqstp, __be32 *p)
+nfssvc_encode_attrstatres(struct svc_rqst *rqstp, __be32 *p)
{
+ struct xdr_stream *xdr = &rqstp->rq_res_stream;
struct nfsd_attrstat *resp = rqstp->rq_resp;
- *p++ = resp->status;
- if (resp->status != nfs_ok)
- goto out;
- p = encode_fattr(rqstp, p, &resp->fh, &resp->stat);
-out:
- return xdr_ressize_check(rqstp, p);
+ if (!svcxdr_encode_stat(xdr, resp->status))
+ return 0;
+ switch (resp->status) {
+ case nfs_ok:
+ if (!svcxdr_encode_fattr(rqstp, xdr, &resp->fh, &resp->stat))
+ return 0;
+ break;
+ }
+
+ return 1;
}
int
nfssvc_encode_diropres(struct svc_rqst *rqstp, __be32 *p)
{
+ struct xdr_stream *xdr = &rqstp->rq_res_stream;
struct nfsd_diropres *resp = rqstp->rq_resp;
- *p++ = resp->status;
- if (resp->status != nfs_ok)
- goto out;
- p = encode_fh(p, &resp->fh);
- p = encode_fattr(rqstp, p, &resp->fh, &resp->stat);
-out:
- return xdr_ressize_check(rqstp, p);
+ if (!svcxdr_encode_stat(xdr, resp->status))
+ return 0;
+ switch (resp->status) {
+ case nfs_ok:
+ if (!svcxdr_encode_fhandle(xdr, &resp->fh))
+ return 0;
+ if (!svcxdr_encode_fattr(rqstp, xdr, &resp->fh, &resp->stat))
+ return 0;
+ break;
+ }
+
+ return 1;
}
int
nfssvc_encode_readlinkres(struct svc_rqst *rqstp, __be32 *p)
{
+ struct xdr_stream *xdr = &rqstp->rq_res_stream;
struct nfsd_readlinkres *resp = rqstp->rq_resp;
struct kvec *head = rqstp->rq_res.head;
- *p++ = resp->status;
- if (resp->status != nfs_ok)
- return xdr_ressize_check(rqstp, p);
-
- *p++ = htonl(resp->len);
- xdr_ressize_check(rqstp, p);
- rqstp->rq_res.page_len = resp->len;
- if (resp->len & 3) {
- /* need to pad the tail */
- rqstp->rq_res.tail[0].iov_base = p;
- *p = 0;
- rqstp->rq_res.tail[0].iov_len = 4 - (resp->len&3);
- }
- if (svc_encode_result_payload(rqstp, head->iov_len, resp->len))
+ if (!svcxdr_encode_stat(xdr, resp->status))
return 0;
+ switch (resp->status) {
+ case nfs_ok:
+ if (xdr_stream_encode_u32(xdr, resp->len) < 0)
+ return 0;
+ xdr_write_pages(xdr, &resp->page, 0, resp->len);
+ if (svc_encode_result_payload(rqstp, head->iov_len, resp->len) < 0)
+ return 0;
+ break;
+ }
+
return 1;
}
int
nfssvc_encode_readres(struct svc_rqst *rqstp, __be32 *p)
{
+ struct xdr_stream *xdr = &rqstp->rq_res_stream;
struct nfsd_readres *resp = rqstp->rq_resp;
struct kvec *head = rqstp->rq_res.head;
- *p++ = resp->status;
- if (resp->status != nfs_ok)
- return xdr_ressize_check(rqstp, p);
-
- p = encode_fattr(rqstp, p, &resp->fh, &resp->stat);
- *p++ = htonl(resp->count);
- xdr_ressize_check(rqstp, p);
-
- /* now update rqstp->rq_res to reflect data as well */
- rqstp->rq_res.page_len = resp->count;
- if (resp->count & 3) {
- /* need to pad the tail */
- rqstp->rq_res.tail[0].iov_base = p;
- *p = 0;
- rqstp->rq_res.tail[0].iov_len = 4 - (resp->count&3);
- }
- if (svc_encode_result_payload(rqstp, head->iov_len, resp->count))
+ if (!svcxdr_encode_stat(xdr, resp->status))
return 0;
+ switch (resp->status) {
+ case nfs_ok:
+ if (!svcxdr_encode_fattr(rqstp, xdr, &resp->fh, &resp->stat))
+ return 0;
+ if (xdr_stream_encode_u32(xdr, resp->count) < 0)
+ return 0;
+ xdr_write_pages(xdr, resp->pages, rqstp->rq_res.page_base,
+ resp->count);
+ if (svc_encode_result_payload(rqstp, head->iov_len, resp->count) < 0)
+ return 0;
+ break;
+ }
+
return 1;
}
int
nfssvc_encode_readdirres(struct svc_rqst *rqstp, __be32 *p)
{
+ struct xdr_stream *xdr = &rqstp->rq_res_stream;
struct nfsd_readdirres *resp = rqstp->rq_resp;
+ struct xdr_buf *dirlist = &resp->dirlist;
- *p++ = resp->status;
- if (resp->status != nfs_ok)
- return xdr_ressize_check(rqstp, p);
-
- xdr_ressize_check(rqstp, p);
- p = resp->buffer;
- *p++ = 0; /* no more entries */
- *p++ = htonl((resp->common.err == nfserr_eof));
- rqstp->rq_res.page_len = (((unsigned long)p-1) & ~PAGE_MASK)+1;
+ if (!svcxdr_encode_stat(xdr, resp->status))
+ return 0;
+ switch (resp->status) {
+ case nfs_ok:
+ xdr_write_pages(xdr, dirlist->pages, 0, dirlist->len);
+ /* no more entries */
+ if (xdr_stream_encode_item_absent(xdr) < 0)
+ return 0;
+ if (xdr_stream_encode_bool(xdr, resp->common.err == nfserr_eof) < 0)
+ return 0;
+ break;
+ }
return 1;
}
@@ -497,64 +551,113 @@ nfssvc_encode_readdirres(struct svc_rqst *rqstp, __be32 *p)
int
nfssvc_encode_statfsres(struct svc_rqst *rqstp, __be32 *p)
{
+ struct xdr_stream *xdr = &rqstp->rq_res_stream;
struct nfsd_statfsres *resp = rqstp->rq_resp;
struct kstatfs *stat = &resp->stats;
- *p++ = resp->status;
- if (resp->status != nfs_ok)
- return xdr_ressize_check(rqstp, p);
+ if (!svcxdr_encode_stat(xdr, resp->status))
+ return 0;
+ switch (resp->status) {
+ case nfs_ok:
+ p = xdr_reserve_space(xdr, XDR_UNIT * 5);
+ if (!p)
+ return 0;
+ *p++ = cpu_to_be32(NFSSVC_MAXBLKSIZE_V2);
+ *p++ = cpu_to_be32(stat->f_bsize);
+ *p++ = cpu_to_be32(stat->f_blocks);
+ *p++ = cpu_to_be32(stat->f_bfree);
+ *p = cpu_to_be32(stat->f_bavail);
+ break;
+ }
- *p++ = htonl(NFSSVC_MAXBLKSIZE_V2); /* max transfer size */
- *p++ = htonl(stat->f_bsize);
- *p++ = htonl(stat->f_blocks);
- *p++ = htonl(stat->f_bfree);
- *p++ = htonl(stat->f_bavail);
- return xdr_ressize_check(rqstp, p);
+ return 1;
}
-int
-nfssvc_encode_entry(void *ccdv, const char *name,
- int namlen, loff_t offset, u64 ino, unsigned int d_type)
+/**
+ * nfssvc_encode_nfscookie - Encode a directory offset cookie
+ * @resp: readdir result context
+ * @offset: offset cookie to encode
+ *
+ * The buffer space for the offset cookie has already been reserved
+ * by svcxdr_encode_entry_common().
+ */
+void nfssvc_encode_nfscookie(struct nfsd_readdirres *resp, u32 offset)
{
- struct readdir_cd *ccd = ccdv;
- struct nfsd_readdirres *cd = container_of(ccd, struct nfsd_readdirres, common);
- __be32 *p = cd->buffer;
- int buflen, slen;
+ __be32 cookie = cpu_to_be32(offset);
- /*
- dprintk("nfsd: entry(%.*s off %ld ino %ld)\n",
- namlen, name, offset, ino);
- */
+ if (!resp->cookie_offset)
+ return;
- if (offset > ~((u32) 0)) {
- cd->common.err = nfserr_fbig;
- return -EINVAL;
- }
- if (cd->offset)
- *cd->offset = htonl(offset);
+ write_bytes_to_xdr_buf(&resp->dirlist, resp->cookie_offset, &cookie,
+ sizeof(cookie));
+ resp->cookie_offset = 0;
+}
- /* truncate filename */
- namlen = min(namlen, NFS2_MAXNAMLEN);
- slen = XDR_QUADLEN(namlen);
+static bool
+svcxdr_encode_entry_common(struct nfsd_readdirres *resp, const char *name,
+ int namlen, loff_t offset, u64 ino)
+{
+ struct xdr_buf *dirlist = &resp->dirlist;
+ struct xdr_stream *xdr = &resp->xdr;
- if ((buflen = cd->buflen - slen - 4) < 0) {
- cd->common.err = nfserr_toosmall;
- return -EINVAL;
- }
- if (ino > ~((u32) 0)) {
- cd->common.err = nfserr_fbig;
- return -EINVAL;
- }
- *p++ = xdr_one; /* mark entry present */
- *p++ = htonl((u32) ino); /* file id */
- p = xdr_encode_array(p, name, namlen);/* name length & name */
- cd->offset = p; /* remember pointer */
- *p++ = htonl(~0U); /* offset of next entry */
-
- cd->buflen = buflen;
- cd->buffer = p;
- cd->common.err = nfs_ok;
+ if (xdr_stream_encode_item_present(xdr) < 0)
+ return false;
+ /* fileid */
+ if (xdr_stream_encode_u32(xdr, (u32)ino) < 0)
+ return false;
+ /* name */
+ if (xdr_stream_encode_opaque(xdr, name, min(namlen, NFS2_MAXNAMLEN)) < 0)
+ return false;
+ /* cookie */
+ resp->cookie_offset = dirlist->len;
+ if (xdr_stream_encode_u32(xdr, ~0U) < 0)
+ return false;
+
+ return true;
+}
+
+/**
+ * nfssvc_encode_entry - encode one NFSv2 READDIR entry
+ * @data: directory context
+ * @name: name of the object to be encoded
+ * @namlen: length of that name, in bytes
+ * @offset: the offset of the previous entry
+ * @ino: the fileid of this entry
+ * @d_type: unused
+ *
+ * Return values:
+ * %0: Entry was successfully encoded.
+ * %-EINVAL: An encoding problem occured, secondary status code in resp->common.err
+ *
+ * On exit, the following fields are updated:
+ * - resp->xdr
+ * - resp->common.err
+ * - resp->cookie_offset
+ */
+int nfssvc_encode_entry(void *data, const char *name, int namlen,
+ loff_t offset, u64 ino, unsigned int d_type)
+{
+ struct readdir_cd *ccd = data;
+ struct nfsd_readdirres *resp = container_of(ccd,
+ struct nfsd_readdirres,
+ common);
+ unsigned int starting_length = resp->dirlist.len;
+
+ /* The offset cookie for the previous entry */
+ nfssvc_encode_nfscookie(resp, offset);
+
+ if (!svcxdr_encode_entry_common(resp, name, namlen, offset, ino))
+ goto out_toosmall;
+
+ xdr_commit_encode(&resp->xdr);
+ resp->common.err = nfs_ok;
return 0;
+
+out_toosmall:
+ resp->cookie_offset = 0;
+ resp->common.err = nfserr_toosmall;
+ resp->dirlist.len = starting_length;
+ return -EINVAL;
}
/*
diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h
index 73deea353169..54cab651ac1d 100644
--- a/fs/nfsd/state.h
+++ b/fs/nfsd/state.h
@@ -371,6 +371,10 @@ struct nfs4_client {
/* debugging info directory under nfsd/clients/ : */
struct dentry *cl_nfsd_dentry;
+ /* 'info' file within that directory. Ref is not counted,
+ * but will remain valid iff cl_nfsd_dentry != NULL
+ */
+ struct dentry *cl_nfsd_info_dentry;
/* for nfs41 callbacks */
/* We currently support a single back channel with a single slot */
diff --git a/fs/nfsd/trace.h b/fs/nfsd/trace.h
index 92a0973dd671..27a93ebd1d80 100644
--- a/fs/nfsd/trace.h
+++ b/fs/nfsd/trace.h
@@ -391,6 +391,30 @@ DEFINE_EVENT(nfsd_err_class, nfsd_##name, \
DEFINE_NFSD_ERR_EVENT(read_err);
DEFINE_NFSD_ERR_EVENT(write_err);
+TRACE_EVENT(nfsd_dirent,
+ TP_PROTO(struct svc_fh *fhp,
+ u64 ino,
+ const char *name,
+ int namlen),
+ TP_ARGS(fhp, ino, name, namlen),
+ TP_STRUCT__entry(
+ __field(u32, fh_hash)
+ __field(u64, ino)
+ __field(int, len)
+ __dynamic_array(unsigned char, name, namlen)
+ ),
+ TP_fast_assign(
+ __entry->fh_hash = fhp ? knfsd_fh_hash(&fhp->fh_handle) : 0;
+ __entry->ino = ino;
+ __entry->len = namlen;
+ memcpy(__get_str(name), name, namlen);
+ __assign_str(name, name);
+ ),
+ TP_printk("fh_hash=0x%08x ino=%llu name=%.*s",
+ __entry->fh_hash, __entry->ino,
+ __entry->len, __get_str(name))
+)
+
#include "state.h"
#include "filecache.h"
#include "vfs.h"
diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c
index fd6be35a1642..15adf1f6ab21 100644
--- a/fs/nfsd/vfs.c
+++ b/fs/nfsd/vfs.c
@@ -1968,8 +1968,9 @@ static int nfsd_buffered_filldir(struct dir_context *ctx, const char *name,
return 0;
}
-static __be32 nfsd_buffered_readdir(struct file *file, nfsd_filldir_t func,
- struct readdir_cd *cdp, loff_t *offsetp)
+static __be32 nfsd_buffered_readdir(struct file *file, struct svc_fh *fhp,
+ nfsd_filldir_t func, struct readdir_cd *cdp,
+ loff_t *offsetp)
{
struct buffered_dirent *de;
int host_err;
@@ -2015,6 +2016,8 @@ static __be32 nfsd_buffered_readdir(struct file *file, nfsd_filldir_t func,
if (cdp->err != nfs_ok)
break;
+ trace_nfsd_dirent(fhp, de->ino, de->name, de->namlen);
+
reclen = ALIGN(sizeof(*de) + de->namlen,
sizeof(u64));
size -= reclen;
@@ -2062,7 +2065,7 @@ nfsd_readdir(struct svc_rqst *rqstp, struct svc_fh *fhp, loff_t *offsetp,
goto out_close;
}
- err = nfsd_buffered_readdir(file, func, cdp, offsetp);
+ err = nfsd_buffered_readdir(file, fhp, func, cdp, offsetp);
if (err == nfserr_eof || err == nfserr_toosmall)
err = nfs_ok; /* can still be found in ->err */
diff --git a/fs/nfsd/vfs.h b/fs/nfsd/vfs.h
index a2442ebe5acf..b21b76e6b9a8 100644
--- a/fs/nfsd/vfs.h
+++ b/fs/nfsd/vfs.h
@@ -152,7 +152,7 @@ static inline void fh_drop_write(struct svc_fh *fh)
}
}
-static inline __be32 fh_getattr(struct svc_fh *fh, struct kstat *stat)
+static inline __be32 fh_getattr(const struct svc_fh *fh, struct kstat *stat)
{
struct path p = {.mnt = fh->fh_export->ex_path.mnt,
.dentry = fh->fh_dentry};
diff --git a/fs/nfsd/xdr.h b/fs/nfsd/xdr.h
index 3018b52b6d5e..f45b4bc93f52 100644
--- a/fs/nfsd/xdr.h
+++ b/fs/nfsd/xdr.h
@@ -94,6 +94,7 @@ struct nfsd_diropres {
struct nfsd_readlinkres {
__be32 status;
int len;
+ struct page *page;
};
struct nfsd_readres {
@@ -101,17 +102,20 @@ struct nfsd_readres {
struct svc_fh fh;
unsigned long count;
struct kstat stat;
+ struct page **pages;
};
struct nfsd_readdirres {
+ /* Components of the reply */
__be32 status;
int count;
+ /* Used to encode the reply's entry list */
+ struct xdr_stream xdr;
+ struct xdr_buf dirlist;
struct readdir_cd common;
- __be32 * buffer;
- int buflen;
- __be32 * offset;
+ unsigned int cookie_offset;
};
struct nfsd_statfsres {
@@ -147,23 +151,26 @@ int nfssvc_decode_renameargs(struct svc_rqst *, __be32 *);
int nfssvc_decode_linkargs(struct svc_rqst *, __be32 *);
int nfssvc_decode_symlinkargs(struct svc_rqst *, __be32 *);
int nfssvc_decode_readdirargs(struct svc_rqst *, __be32 *);
-int nfssvc_encode_stat(struct svc_rqst *, __be32 *);
-int nfssvc_encode_attrstat(struct svc_rqst *, __be32 *);
+int nfssvc_encode_statres(struct svc_rqst *, __be32 *);
+int nfssvc_encode_attrstatres(struct svc_rqst *, __be32 *);
int nfssvc_encode_diropres(struct svc_rqst *, __be32 *);
int nfssvc_encode_readlinkres(struct svc_rqst *, __be32 *);
int nfssvc_encode_readres(struct svc_rqst *, __be32 *);
int nfssvc_encode_statfsres(struct svc_rqst *, __be32 *);
int nfssvc_encode_readdirres(struct svc_rqst *, __be32 *);
-int nfssvc_encode_entry(void *, const char *name,
- int namlen, loff_t offset, u64 ino, unsigned int);
+void nfssvc_encode_nfscookie(struct nfsd_readdirres *resp, u32 offset);
+int nfssvc_encode_entry(void *data, const char *name, int namlen,
+ loff_t offset, u64 ino, unsigned int d_type);
void nfssvc_release_attrstat(struct svc_rqst *rqstp);
void nfssvc_release_diropres(struct svc_rqst *rqstp);
void nfssvc_release_readres(struct svc_rqst *rqstp);
/* Helper functions for NFSv2 ACL code */
-__be32 *nfs2svc_encode_fattr(struct svc_rqst *rqstp, __be32 *p, struct svc_fh *fhp, struct kstat *stat);
bool svcxdr_decode_fhandle(struct xdr_stream *xdr, struct svc_fh *fhp);
+bool svcxdr_encode_stat(struct xdr_stream *xdr, __be32 status);
+bool svcxdr_encode_fattr(struct svc_rqst *rqstp, struct xdr_stream *xdr,
+ const struct svc_fh *fhp, const struct kstat *stat);
#endif /* LINUX_NFSD_H */
diff --git a/fs/nfsd/xdr3.h b/fs/nfsd/xdr3.h
index 3e1578953f54..933008382bbe 100644
--- a/fs/nfsd/xdr3.h
+++ b/fs/nfsd/xdr3.h
@@ -137,6 +137,7 @@ struct nfsd3_readlinkres {
__be32 status;
struct svc_fh fh;
__u32 len;
+ struct page **pages;
};
struct nfsd3_readres {
@@ -144,6 +145,7 @@ struct nfsd3_readres {
struct svc_fh fh;
unsigned long count;
__u32 eof;
+ struct page **pages;
};
struct nfsd3_writeres {
@@ -167,19 +169,17 @@ struct nfsd3_linkres {
};
struct nfsd3_readdirres {
+ /* Components of the reply */
__be32 status;
struct svc_fh fh;
- /* Just to save kmalloc on every readdirplus entry (svc_fh is a
- * little large for the stack): */
- struct svc_fh scratch;
- int count;
__be32 verf[2];
+ /* Used to encode the reply's entry list */
+ struct xdr_stream xdr;
+ struct xdr_buf dirlist;
+ struct svc_fh scratch;
struct readdir_cd common;
- __be32 * buffer;
- int buflen;
- __be32 * offset;
- __be32 * offset1;
+ unsigned int cookie_offset;
struct svc_rqst * rqstp;
};
@@ -280,9 +280,9 @@ int nfs3svc_decode_symlinkargs(struct svc_rqst *, __be32 *);
int nfs3svc_decode_readdirargs(struct svc_rqst *, __be32 *);
int nfs3svc_decode_readdirplusargs(struct svc_rqst *, __be32 *);
int nfs3svc_decode_commitargs(struct svc_rqst *, __be32 *);
-int nfs3svc_encode_attrstat(struct svc_rqst *, __be32 *);
+int nfs3svc_encode_getattrres(struct svc_rqst *, __be32 *);
int nfs3svc_encode_wccstat(struct svc_rqst *, __be32 *);
-int nfs3svc_encode_diropres(struct svc_rqst *, __be32 *);
+int nfs3svc_encode_lookupres(struct svc_rqst *, __be32 *);
int nfs3svc_encode_accessres(struct svc_rqst *, __be32 *);
int nfs3svc_encode_readlinkres(struct svc_rqst *, __be32 *);
int nfs3svc_encode_readres(struct svc_rqst *, __be32 *);
@@ -298,15 +298,16 @@ int nfs3svc_encode_commitres(struct svc_rqst *, __be32 *);
void nfs3svc_release_fhandle(struct svc_rqst *);
void nfs3svc_release_fhandle2(struct svc_rqst *);
-int nfs3svc_encode_entry(void *, const char *name,
- int namlen, loff_t offset, u64 ino,
- unsigned int);
-int nfs3svc_encode_entry_plus(void *, const char *name,
- int namlen, loff_t offset, u64 ino,
- unsigned int);
+
+void nfs3svc_encode_cookie3(struct nfsd3_readdirres *resp, u64 offset);
+int nfs3svc_encode_entry3(void *data, const char *name, int namlen,
+ loff_t offset, u64 ino, unsigned int d_type);
+int nfs3svc_encode_entryplus3(void *data, const char *name, int namlen,
+ loff_t offset, u64 ino, unsigned int d_type);
/* Helper functions for NFSv3 ACL code */
-__be32 *nfs3svc_encode_post_op_attr(struct svc_rqst *rqstp, __be32 *p,
- struct svc_fh *fhp);
bool svcxdr_decode_nfs_fh3(struct xdr_stream *xdr, struct svc_fh *fhp);
+bool svcxdr_encode_nfsstat3(struct xdr_stream *xdr, __be32 status);
+bool svcxdr_encode_post_op_attr(struct svc_rqst *rqstp, struct xdr_stream *xdr,
+ const struct svc_fh *fhp);
#endif /* _LINUX_NFSD_XDR3_H */
diff --git a/fs/nfsd/xdr4.h b/fs/nfsd/xdr4.h
index c300885ae75d..fe540a3415c6 100644
--- a/fs/nfsd/xdr4.h
+++ b/fs/nfsd/xdr4.h
@@ -698,7 +698,7 @@ struct nfsd4_compoundargs {
struct nfsd4_compoundres {
/* scratch variables for XDR encode */
- struct xdr_stream xdr;
+ struct xdr_stream *xdr;
struct svc_rqst * rqstp;
u32 taglen;
diff --git a/fs/nilfs2/file.c b/fs/nilfs2/file.c
index e1bd592ce700..7cf765258fda 100644
--- a/fs/nilfs2/file.c
+++ b/fs/nilfs2/file.c
@@ -148,6 +148,8 @@ const struct inode_operations nilfs_file_inode_operations = {
.setattr = nilfs_setattr,
.permission = nilfs_permission,
.fiemap = nilfs_fiemap,
+ .fileattr_get = nilfs_fileattr_get,
+ .fileattr_set = nilfs_fileattr_set,
};
/* end of file */
diff --git a/fs/nilfs2/ioctl.c b/fs/nilfs2/ioctl.c
index b053b40315bf..3fcb9357bbfd 100644
--- a/fs/nilfs2/ioctl.c
+++ b/fs/nilfs2/ioctl.c
@@ -16,6 +16,7 @@
#include <linux/compat.h> /* compat_ptr() */
#include <linux/mount.h> /* mnt_want_write_file(), mnt_drop_write_file() */
#include <linux/buffer_head.h>
+#include <linux/fileattr.h>
#include "nilfs.h"
#include "segment.h"
#include "bmap.h"
@@ -113,51 +114,39 @@ static int nilfs_ioctl_wrap_copy(struct the_nilfs *nilfs,
}
/**
- * nilfs_ioctl_getflags - ioctl to support lsattr
+ * nilfs_fileattr_get - ioctl to support lsattr
*/
-static int nilfs_ioctl_getflags(struct inode *inode, void __user *argp)
+int nilfs_fileattr_get(struct dentry *dentry, struct fileattr *fa)
{
- unsigned int flags = NILFS_I(inode)->i_flags & FS_FL_USER_VISIBLE;
+ struct inode *inode = d_inode(dentry);
- return put_user(flags, (int __user *)argp);
+ fileattr_fill_flags(fa, NILFS_I(inode)->i_flags & FS_FL_USER_VISIBLE);
+
+ return 0;
}
/**
- * nilfs_ioctl_setflags - ioctl to support chattr
+ * nilfs_fileattr_set - ioctl to support chattr
*/
-static int nilfs_ioctl_setflags(struct inode *inode, struct file *filp,
- void __user *argp)
+int nilfs_fileattr_set(struct user_namespace *mnt_userns,
+ struct dentry *dentry, struct fileattr *fa)
{
+ struct inode *inode = d_inode(dentry);
struct nilfs_transaction_info ti;
unsigned int flags, oldflags;
int ret;
- if (!inode_owner_or_capable(&init_user_ns, inode))
- return -EACCES;
-
- if (get_user(flags, (int __user *)argp))
- return -EFAULT;
-
- ret = mnt_want_write_file(filp);
- if (ret)
- return ret;
-
- flags = nilfs_mask_flags(inode->i_mode, flags);
-
- inode_lock(inode);
-
- oldflags = NILFS_I(inode)->i_flags;
+ if (fileattr_has_fsx(fa))
+ return -EOPNOTSUPP;
- ret = vfs_ioc_setflags_prepare(inode, oldflags, flags);
- if (ret)
- goto out;
+ flags = nilfs_mask_flags(inode->i_mode, fa->flags);
ret = nilfs_transaction_begin(inode->i_sb, &ti, 0);
if (ret)
- goto out;
+ return ret;
- NILFS_I(inode)->i_flags = (oldflags & ~FS_FL_USER_MODIFIABLE) |
- (flags & FS_FL_USER_MODIFIABLE);
+ oldflags = NILFS_I(inode)->i_flags & ~FS_FL_USER_MODIFIABLE;
+ NILFS_I(inode)->i_flags = oldflags | (flags & FS_FL_USER_MODIFIABLE);
nilfs_set_inode_flags(inode);
inode->i_ctime = current_time(inode);
@@ -165,11 +154,7 @@ static int nilfs_ioctl_setflags(struct inode *inode, struct file *filp,
nilfs_set_transaction_flag(NILFS_TI_SYNC);
nilfs_mark_inode_dirty(inode);
- ret = nilfs_transaction_commit(inode->i_sb);
-out:
- inode_unlock(inode);
- mnt_drop_write_file(filp);
- return ret;
+ return nilfs_transaction_commit(inode->i_sb);
}
/**
@@ -1282,10 +1267,6 @@ long nilfs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
void __user *argp = (void __user *)arg;
switch (cmd) {
- case FS_IOC_GETFLAGS:
- return nilfs_ioctl_getflags(inode, argp);
- case FS_IOC_SETFLAGS:
- return nilfs_ioctl_setflags(inode, filp, argp);
case FS_IOC_GETVERSION:
return nilfs_ioctl_getversion(inode, argp);
case NILFS_IOCTL_CHANGE_CPMODE:
@@ -1331,12 +1312,6 @@ long nilfs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
long nilfs_compat_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
{
switch (cmd) {
- case FS_IOC32_GETFLAGS:
- cmd = FS_IOC_GETFLAGS;
- break;
- case FS_IOC32_SETFLAGS:
- cmd = FS_IOC_SETFLAGS;
- break;
case FS_IOC32_GETVERSION:
cmd = FS_IOC_GETVERSION;
break;
diff --git a/fs/nilfs2/namei.c b/fs/nilfs2/namei.c
index ecace5f96a95..91eebeb0c48b 100644
--- a/fs/nilfs2/namei.c
+++ b/fs/nilfs2/namei.c
@@ -440,10 +440,9 @@ static struct dentry *nilfs_get_parent(struct dentry *child)
{
unsigned long ino;
struct inode *inode;
- struct qstr dotdot = QSTR_INIT("..", 2);
struct nilfs_root *root;
- ino = nilfs_inode_by_name(d_inode(child), &dotdot);
+ ino = nilfs_inode_by_name(d_inode(child), &dotdot_name);
if (!ino)
return ERR_PTR(-ENOENT);
@@ -552,6 +551,8 @@ const struct inode_operations nilfs_dir_inode_operations = {
.setattr = nilfs_setattr,
.permission = nilfs_permission,
.fiemap = nilfs_fiemap,
+ .fileattr_get = nilfs_fileattr_get,
+ .fileattr_set = nilfs_fileattr_set,
};
const struct inode_operations nilfs_special_inode_operations = {
diff --git a/fs/nilfs2/nilfs.h b/fs/nilfs2/nilfs.h
index c4a45a081ade..60b21b6eeac0 100644
--- a/fs/nilfs2/nilfs.h
+++ b/fs/nilfs2/nilfs.h
@@ -243,6 +243,9 @@ extern void nilfs_set_link(struct inode *, struct nilfs_dir_entry *,
extern int nilfs_sync_file(struct file *, loff_t, loff_t, int);
/* ioctl.c */
+int nilfs_fileattr_get(struct dentry *dentry, struct fileattr *m);
+int nilfs_fileattr_set(struct user_namespace *mnt_userns,
+ struct dentry *dentry, struct fileattr *fa);
long nilfs_ioctl(struct file *, unsigned int, unsigned long);
long nilfs_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg);
int nilfs_ioctl_prepare_clean_segments(struct the_nilfs *, struct nilfs_argv *,
diff --git a/fs/notify/fanotify/fanotify.c b/fs/notify/fanotify/fanotify.c
index 1192c9953620..057abd2cf887 100644
--- a/fs/notify/fanotify/fanotify.c
+++ b/fs/notify/fanotify/fanotify.c
@@ -14,6 +14,7 @@
#include <linux/audit.h>
#include <linux/sched/mm.h>
#include <linux/statfs.h>
+#include <linux/stringhash.h>
#include "fanotify.h"
@@ -22,12 +23,24 @@ static bool fanotify_path_equal(struct path *p1, struct path *p2)
return p1->mnt == p2->mnt && p1->dentry == p2->dentry;
}
+static unsigned int fanotify_hash_path(const struct path *path)
+{
+ return hash_ptr(path->dentry, FANOTIFY_EVENT_HASH_BITS) ^
+ hash_ptr(path->mnt, FANOTIFY_EVENT_HASH_BITS);
+}
+
static inline bool fanotify_fsid_equal(__kernel_fsid_t *fsid1,
__kernel_fsid_t *fsid2)
{
return fsid1->val[0] == fsid2->val[0] && fsid1->val[1] == fsid2->val[1];
}
+static unsigned int fanotify_hash_fsid(__kernel_fsid_t *fsid)
+{
+ return hash_32(fsid->val[0], FANOTIFY_EVENT_HASH_BITS) ^
+ hash_32(fsid->val[1], FANOTIFY_EVENT_HASH_BITS);
+}
+
static bool fanotify_fh_equal(struct fanotify_fh *fh1,
struct fanotify_fh *fh2)
{
@@ -38,6 +51,16 @@ static bool fanotify_fh_equal(struct fanotify_fh *fh1,
!memcmp(fanotify_fh_buf(fh1), fanotify_fh_buf(fh2), fh1->len);
}
+static unsigned int fanotify_hash_fh(struct fanotify_fh *fh)
+{
+ long salt = (long)fh->type | (long)fh->len << 8;
+
+ /*
+ * full_name_hash() works long by long, so it handles fh buf optimally.
+ */
+ return full_name_hash((void *)salt, fanotify_fh_buf(fh), fh->len);
+}
+
static bool fanotify_fid_event_equal(struct fanotify_fid_event *ffe1,
struct fanotify_fid_event *ffe2)
{
@@ -88,16 +111,12 @@ static bool fanotify_name_event_equal(struct fanotify_name_event *fne1,
return fanotify_info_equal(info1, info2);
}
-static bool fanotify_should_merge(struct fsnotify_event *old_fsn,
- struct fsnotify_event *new_fsn)
+static bool fanotify_should_merge(struct fanotify_event *old,
+ struct fanotify_event *new)
{
- struct fanotify_event *old, *new;
-
- pr_debug("%s: old=%p new=%p\n", __func__, old_fsn, new_fsn);
- old = FANOTIFY_E(old_fsn);
- new = FANOTIFY_E(new_fsn);
+ pr_debug("%s: old=%p new=%p\n", __func__, old, new);
- if (old_fsn->objectid != new_fsn->objectid ||
+ if (old->hash != new->hash ||
old->type != new->type || old->pid != new->pid)
return false;
@@ -129,14 +148,20 @@ static bool fanotify_should_merge(struct fsnotify_event *old_fsn,
return false;
}
+/* Limit event merges to limit CPU overhead per event */
+#define FANOTIFY_MAX_MERGE_EVENTS 128
+
/* and the list better be locked by something too! */
-static int fanotify_merge(struct list_head *list, struct fsnotify_event *event)
+static int fanotify_merge(struct fsnotify_group *group,
+ struct fsnotify_event *event)
{
- struct fsnotify_event *test_event;
- struct fanotify_event *new;
+ struct fanotify_event *old, *new = FANOTIFY_E(event);
+ unsigned int bucket = fanotify_event_hash_bucket(group, new);
+ struct hlist_head *hlist = &group->fanotify_data.merge_hash[bucket];
+ int i = 0;
- pr_debug("%s: list=%p event=%p\n", __func__, list, event);
- new = FANOTIFY_E(event);
+ pr_debug("%s: group=%p event=%p bucket=%u\n", __func__,
+ group, event, bucket);
/*
* Don't merge a permission event with any other event so that we know
@@ -146,9 +171,11 @@ static int fanotify_merge(struct list_head *list, struct fsnotify_event *event)
if (fanotify_is_perm_event(new->mask))
return 0;
- list_for_each_entry_reverse(test_event, list, list) {
- if (fanotify_should_merge(test_event, event)) {
- FANOTIFY_E(test_event)->mask |= new->mask;
+ hlist_for_each_entry(old, hlist, merge_list) {
+ if (++i > FANOTIFY_MAX_MERGE_EVENTS)
+ break;
+ if (fanotify_should_merge(old, new)) {
+ old->mask |= new->mask;
return 1;
}
}
@@ -184,8 +211,11 @@ static int fanotify_get_response(struct fsnotify_group *group,
return ret;
}
/* Event not yet reported? Just remove it. */
- if (event->state == FAN_EVENT_INIT)
+ if (event->state == FAN_EVENT_INIT) {
fsnotify_remove_queued_event(group, &event->fae.fse);
+ /* Permission events are not supposed to be hashed */
+ WARN_ON_ONCE(!hlist_unhashed(&event->fae.merge_list));
+ }
/*
* Event may be also answered in case signal delivery raced
* with wakeup. In that case we have nothing to do besides
@@ -329,7 +359,8 @@ static int fanotify_encode_fh_len(struct inode *inode)
* Return 0 on failure to encode.
*/
static int fanotify_encode_fh(struct fanotify_fh *fh, struct inode *inode,
- unsigned int fh_len, gfp_t gfp)
+ unsigned int fh_len, unsigned int *hash,
+ gfp_t gfp)
{
int dwords, type = 0;
char *ext_buf = NULL;
@@ -372,6 +403,9 @@ static int fanotify_encode_fh(struct fanotify_fh *fh, struct inode *inode,
fh->type = type;
fh->len = fh_len;
+ /* Mix fh into event merge key */
+ *hash ^= fanotify_hash_fh(fh);
+
return FANOTIFY_FH_HDR_LEN + fh_len;
out_err:
@@ -425,6 +459,7 @@ static struct inode *fanotify_dfid_inode(u32 event_mask, const void *data,
}
static struct fanotify_event *fanotify_alloc_path_event(const struct path *path,
+ unsigned int *hash,
gfp_t gfp)
{
struct fanotify_path_event *pevent;
@@ -435,6 +470,7 @@ static struct fanotify_event *fanotify_alloc_path_event(const struct path *path,
pevent->fae.type = FANOTIFY_EVENT_TYPE_PATH;
pevent->path = *path;
+ *hash ^= fanotify_hash_path(path);
path_get(path);
return &pevent->fae;
@@ -460,6 +496,7 @@ static struct fanotify_event *fanotify_alloc_perm_event(const struct path *path,
static struct fanotify_event *fanotify_alloc_fid_event(struct inode *id,
__kernel_fsid_t *fsid,
+ unsigned int *hash,
gfp_t gfp)
{
struct fanotify_fid_event *ffe;
@@ -470,16 +507,18 @@ static struct fanotify_event *fanotify_alloc_fid_event(struct inode *id,
ffe->fae.type = FANOTIFY_EVENT_TYPE_FID;
ffe->fsid = *fsid;
+ *hash ^= fanotify_hash_fsid(fsid);
fanotify_encode_fh(&ffe->object_fh, id, fanotify_encode_fh_len(id),
- gfp);
+ hash, gfp);
return &ffe->fae;
}
static struct fanotify_event *fanotify_alloc_name_event(struct inode *id,
__kernel_fsid_t *fsid,
- const struct qstr *file_name,
+ const struct qstr *name,
struct inode *child,
+ unsigned int *hash,
gfp_t gfp)
{
struct fanotify_name_event *fne;
@@ -492,24 +531,30 @@ static struct fanotify_event *fanotify_alloc_name_event(struct inode *id,
size = sizeof(*fne) + FANOTIFY_FH_HDR_LEN + dir_fh_len;
if (child_fh_len)
size += FANOTIFY_FH_HDR_LEN + child_fh_len;
- if (file_name)
- size += file_name->len + 1;
+ if (name)
+ size += name->len + 1;
fne = kmalloc(size, gfp);
if (!fne)
return NULL;
fne->fae.type = FANOTIFY_EVENT_TYPE_FID_NAME;
fne->fsid = *fsid;
+ *hash ^= fanotify_hash_fsid(fsid);
info = &fne->info;
fanotify_info_init(info);
dfh = fanotify_info_dir_fh(info);
- info->dir_fh_totlen = fanotify_encode_fh(dfh, id, dir_fh_len, 0);
+ info->dir_fh_totlen = fanotify_encode_fh(dfh, id, dir_fh_len, hash, 0);
if (child_fh_len) {
ffh = fanotify_info_file_fh(info);
- info->file_fh_totlen = fanotify_encode_fh(ffh, child, child_fh_len, 0);
+ info->file_fh_totlen = fanotify_encode_fh(ffh, child,
+ child_fh_len, hash, 0);
+ }
+ if (name) {
+ long salt = name->len;
+
+ fanotify_info_copy_name(info, name);
+ *hash ^= full_name_hash((void *)salt, name->name, name->len);
}
- if (file_name)
- fanotify_info_copy_name(info, file_name);
pr_debug("%s: ino=%lu size=%u dir_fh_len=%u child_fh_len=%u name_len=%u name='%.*s'\n",
__func__, id->i_ino, size, dir_fh_len, child_fh_len,
@@ -533,6 +578,9 @@ static struct fanotify_event *fanotify_alloc_event(struct fsnotify_group *group,
struct mem_cgroup *old_memcg;
struct inode *child = NULL;
bool name_event = false;
+ unsigned int hash = 0;
+ bool ondir = mask & FAN_ONDIR;
+ struct pid *pid;
if ((fid_mode & FAN_REPORT_DIR_FID) && dirid) {
/*
@@ -540,8 +588,7 @@ static struct fanotify_event *fanotify_alloc_event(struct fsnotify_group *group,
* report the child fid for events reported on a non-dir child
* in addition to reporting the parent fid and maybe child name.
*/
- if ((fid_mode & FAN_REPORT_FID) &&
- id != dirid && !(mask & FAN_ONDIR))
+ if ((fid_mode & FAN_REPORT_FID) && id != dirid && !ondir)
child = id;
id = dirid;
@@ -562,8 +609,7 @@ static struct fanotify_event *fanotify_alloc_event(struct fsnotify_group *group,
if (!(fid_mode & FAN_REPORT_NAME)) {
name_event = !!child;
file_name = NULL;
- } else if ((mask & ALL_FSNOTIFY_DIRENT_EVENTS) ||
- !(mask & FAN_ONDIR)) {
+ } else if ((mask & ALL_FSNOTIFY_DIRENT_EVENTS) || !ondir) {
name_event = true;
}
}
@@ -586,26 +632,25 @@ static struct fanotify_event *fanotify_alloc_event(struct fsnotify_group *group,
event = fanotify_alloc_perm_event(path, gfp);
} else if (name_event && (file_name || child)) {
event = fanotify_alloc_name_event(id, fsid, file_name, child,
- gfp);
+ &hash, gfp);
} else if (fid_mode) {
- event = fanotify_alloc_fid_event(id, fsid, gfp);
+ event = fanotify_alloc_fid_event(id, fsid, &hash, gfp);
} else {
- event = fanotify_alloc_path_event(path, gfp);
+ event = fanotify_alloc_path_event(path, &hash, gfp);
}
if (!event)
goto out;
- /*
- * Use the victim inode instead of the watching inode as the id for
- * event queue, so event reported on parent is merged with event
- * reported on child when both directory and child watches exist.
- */
- fanotify_init_event(event, (unsigned long)id, mask);
if (FAN_GROUP_FLAG(group, FAN_REPORT_TID))
- event->pid = get_pid(task_pid(current));
+ pid = get_pid(task_pid(current));
else
- event->pid = get_pid(task_tgid(current));
+ pid = get_pid(task_tgid(current));
+
+ /* Mix event info, FAN_ONDIR flag and pid into event merge key */
+ hash ^= hash_long((unsigned long)pid | ondir, FANOTIFY_EVENT_HASH_BITS);
+ fanotify_init_event(event, hash, mask);
+ event->pid = pid;
out:
set_active_memcg(old_memcg);
@@ -645,6 +690,24 @@ static __kernel_fsid_t fanotify_get_fsid(struct fsnotify_iter_info *iter_info)
return fsid;
}
+/*
+ * Add an event to hash table for faster merge.
+ */
+static void fanotify_insert_event(struct fsnotify_group *group,
+ struct fsnotify_event *fsn_event)
+{
+ struct fanotify_event *event = FANOTIFY_E(fsn_event);
+ unsigned int bucket = fanotify_event_hash_bucket(group, event);
+ struct hlist_head *hlist = &group->fanotify_data.merge_hash[bucket];
+
+ assert_spin_locked(&group->notification_lock);
+
+ pr_debug("%s: group=%p event=%p bucket=%u\n", __func__,
+ group, event, bucket);
+
+ hlist_add_head(&event->merge_list, hlist);
+}
+
static int fanotify_handle_event(struct fsnotify_group *group, u32 mask,
const void *data, int data_type,
struct inode *dir,
@@ -715,7 +778,9 @@ static int fanotify_handle_event(struct fsnotify_group *group, u32 mask,
}
fsn_event = &event->fse;
- ret = fsnotify_add_event(group, fsn_event, fanotify_merge);
+ ret = fsnotify_add_event(group, fsn_event, fanotify_merge,
+ fanotify_is_hashed_event(mask) ?
+ fanotify_insert_event : NULL);
if (ret) {
/* Permission events shouldn't be merged */
BUG_ON(ret == 1 && mask & FANOTIFY_PERM_EVENTS);
@@ -736,11 +801,10 @@ finish:
static void fanotify_free_group_priv(struct fsnotify_group *group)
{
- struct user_struct *user;
-
- user = group->fanotify_data.user;
- atomic_dec(&user->fanotify_listeners);
- free_uid(user);
+ kfree(group->fanotify_data.merge_hash);
+ if (group->fanotify_data.ucounts)
+ dec_ucount(group->fanotify_data.ucounts,
+ UCOUNT_FANOTIFY_GROUPS);
}
static void fanotify_free_path_event(struct fanotify_event *event)
@@ -796,6 +860,13 @@ static void fanotify_free_event(struct fsnotify_event *fsn_event)
}
}
+static void fanotify_freeing_mark(struct fsnotify_mark *mark,
+ struct fsnotify_group *group)
+{
+ if (!FAN_GROUP_FLAG(group, FAN_UNLIMITED_MARKS))
+ dec_ucount(group->fanotify_data.ucounts, UCOUNT_FANOTIFY_MARKS);
+}
+
static void fanotify_free_mark(struct fsnotify_mark *fsn_mark)
{
kmem_cache_free(fanotify_mark_cache, fsn_mark);
@@ -805,5 +876,6 @@ const struct fsnotify_ops fanotify_fsnotify_ops = {
.handle_event = fanotify_handle_event,
.free_group_priv = fanotify_free_group_priv,
.free_event = fanotify_free_event,
+ .freeing_mark = fanotify_freeing_mark,
.free_mark = fanotify_free_mark,
};
diff --git a/fs/notify/fanotify/fanotify.h b/fs/notify/fanotify/fanotify.h
index 896c819a1786..4a5e555dc3d2 100644
--- a/fs/notify/fanotify/fanotify.h
+++ b/fs/notify/fanotify/fanotify.h
@@ -3,6 +3,7 @@
#include <linux/path.h>
#include <linux/slab.h>
#include <linux/exportfs.h>
+#include <linux/hashtable.h>
extern struct kmem_cache *fanotify_mark_cache;
extern struct kmem_cache *fanotify_fid_event_cachep;
@@ -115,6 +116,11 @@ static inline void fanotify_info_init(struct fanotify_info *info)
info->name_len = 0;
}
+static inline unsigned int fanotify_info_len(struct fanotify_info *info)
+{
+ return info->dir_fh_totlen + info->file_fh_totlen + info->name_len;
+}
+
static inline void fanotify_info_copy_name(struct fanotify_info *info,
const struct qstr *name)
{
@@ -135,19 +141,31 @@ enum fanotify_event_type {
FANOTIFY_EVENT_TYPE_PATH,
FANOTIFY_EVENT_TYPE_PATH_PERM,
FANOTIFY_EVENT_TYPE_OVERFLOW, /* struct fanotify_event */
+ __FANOTIFY_EVENT_TYPE_NUM
};
+#define FANOTIFY_EVENT_TYPE_BITS \
+ (ilog2(__FANOTIFY_EVENT_TYPE_NUM - 1) + 1)
+#define FANOTIFY_EVENT_HASH_BITS \
+ (32 - FANOTIFY_EVENT_TYPE_BITS)
+
struct fanotify_event {
struct fsnotify_event fse;
+ struct hlist_node merge_list; /* List for hashed merge */
u32 mask;
- enum fanotify_event_type type;
+ struct {
+ unsigned int type : FANOTIFY_EVENT_TYPE_BITS;
+ unsigned int hash : FANOTIFY_EVENT_HASH_BITS;
+ };
struct pid *pid;
};
static inline void fanotify_init_event(struct fanotify_event *event,
- unsigned long id, u32 mask)
+ unsigned int hash, u32 mask)
{
- fsnotify_init_event(&event->fse, id);
+ fsnotify_init_event(&event->fse);
+ INIT_HLIST_NODE(&event->merge_list);
+ event->hash = hash;
event->mask = mask;
event->pid = NULL;
}
@@ -284,3 +302,25 @@ static inline struct path *fanotify_event_path(struct fanotify_event *event)
else
return NULL;
}
+
+/*
+ * Use 128 size hash table to speed up events merge.
+ */
+#define FANOTIFY_HTABLE_BITS (7)
+#define FANOTIFY_HTABLE_SIZE (1 << FANOTIFY_HTABLE_BITS)
+#define FANOTIFY_HTABLE_MASK (FANOTIFY_HTABLE_SIZE - 1)
+
+/*
+ * Permission events and overflow event do not get merged - don't hash them.
+ */
+static inline bool fanotify_is_hashed_event(u32 mask)
+{
+ return !fanotify_is_perm_event(mask) && !(mask & FS_Q_OVERFLOW);
+}
+
+static inline unsigned int fanotify_event_hash_bucket(
+ struct fsnotify_group *group,
+ struct fanotify_event *event)
+{
+ return event->hash & FANOTIFY_HTABLE_MASK;
+}
diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c
index 9e0c1afac8bd..71fefb30e015 100644
--- a/fs/notify/fanotify/fanotify_user.c
+++ b/fs/notify/fanotify/fanotify_user.c
@@ -27,8 +27,61 @@
#include "fanotify.h"
#define FANOTIFY_DEFAULT_MAX_EVENTS 16384
-#define FANOTIFY_DEFAULT_MAX_MARKS 8192
-#define FANOTIFY_DEFAULT_MAX_LISTENERS 128
+#define FANOTIFY_OLD_DEFAULT_MAX_MARKS 8192
+#define FANOTIFY_DEFAULT_MAX_GROUPS 128
+
+/*
+ * Legacy fanotify marks limits (8192) is per group and we introduced a tunable
+ * limit of marks per user, similar to inotify. Effectively, the legacy limit
+ * of fanotify marks per user is <max marks per group> * <max groups per user>.
+ * This default limit (1M) also happens to match the increased limit of inotify
+ * max_user_watches since v5.10.
+ */
+#define FANOTIFY_DEFAULT_MAX_USER_MARKS \
+ (FANOTIFY_OLD_DEFAULT_MAX_MARKS * FANOTIFY_DEFAULT_MAX_GROUPS)
+
+/*
+ * Most of the memory cost of adding an inode mark is pinning the marked inode.
+ * The size of the filesystem inode struct is not uniform across filesystems,
+ * so double the size of a VFS inode is used as a conservative approximation.
+ */
+#define INODE_MARK_COST (2 * sizeof(struct inode))
+
+/* configurable via /proc/sys/fs/fanotify/ */
+static int fanotify_max_queued_events __read_mostly;
+
+#ifdef CONFIG_SYSCTL
+
+#include <linux/sysctl.h>
+
+struct ctl_table fanotify_table[] = {
+ {
+ .procname = "max_user_groups",
+ .data = &init_user_ns.ucount_max[UCOUNT_FANOTIFY_GROUPS],
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec_minmax,
+ .extra1 = SYSCTL_ZERO,
+ },
+ {
+ .procname = "max_user_marks",
+ .data = &init_user_ns.ucount_max[UCOUNT_FANOTIFY_MARKS],
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec_minmax,
+ .extra1 = SYSCTL_ZERO,
+ },
+ {
+ .procname = "max_queued_events",
+ .data = &fanotify_max_queued_events,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec_minmax,
+ .extra1 = SYSCTL_ZERO
+ },
+ { }
+};
+#endif /* CONFIG_SYSCTL */
/*
* All flags that may be specified in parameter event_f_flags of fanotify_init.
@@ -90,6 +143,23 @@ static int fanotify_event_info_len(unsigned int fid_mode,
}
/*
+ * Remove an hashed event from merge hash table.
+ */
+static void fanotify_unhash_event(struct fsnotify_group *group,
+ struct fanotify_event *event)
+{
+ assert_spin_locked(&group->notification_lock);
+
+ pr_debug("%s: group=%p event=%p bucket=%u\n", __func__,
+ group, event, fanotify_event_hash_bucket(group, event));
+
+ if (WARN_ON_ONCE(hlist_unhashed(&event->merge_list)))
+ return;
+
+ hlist_del_init(&event->merge_list);
+}
+
+/*
* Get an fanotify notification event if one exists and is small
* enough to fit in "count". Return an error pointer if the count
* is not large enough. When permission event is dequeued, its state is
@@ -100,26 +170,34 @@ static struct fanotify_event *get_one_event(struct fsnotify_group *group,
{
size_t event_size = FAN_EVENT_METADATA_LEN;
struct fanotify_event *event = NULL;
+ struct fsnotify_event *fsn_event;
unsigned int fid_mode = FAN_GROUP_FLAG(group, FANOTIFY_FID_BITS);
pr_debug("%s: group=%p count=%zd\n", __func__, group, count);
spin_lock(&group->notification_lock);
- if (fsnotify_notify_queue_is_empty(group))
+ fsn_event = fsnotify_peek_first_event(group);
+ if (!fsn_event)
goto out;
- if (fid_mode) {
- event_size += fanotify_event_info_len(fid_mode,
- FANOTIFY_E(fsnotify_peek_first_event(group)));
- }
+ event = FANOTIFY_E(fsn_event);
+ if (fid_mode)
+ event_size += fanotify_event_info_len(fid_mode, event);
if (event_size > count) {
event = ERR_PTR(-EINVAL);
goto out;
}
- event = FANOTIFY_E(fsnotify_remove_first_event(group));
+
+ /*
+ * Held the notification_lock the whole time, so this is the
+ * same event we peeked above.
+ */
+ fsnotify_remove_first_event(group);
if (fanotify_is_perm_event(event->mask))
FANOTIFY_PERM(event)->state = FAN_EVENT_REPORTED;
+ if (fanotify_is_hashed_event(event->mask))
+ fanotify_unhash_event(group, event);
out:
spin_unlock(&group->notification_lock);
return event;
@@ -341,6 +419,14 @@ static ssize_t copy_event_to_user(struct fsnotify_group *group,
metadata.reserved = 0;
metadata.mask = event->mask & FANOTIFY_OUTGOING_EVENTS;
metadata.pid = pid_vnr(event->pid);
+ /*
+ * For an unprivileged listener, event->pid can be used to identify the
+ * events generated by the listener process itself, without disclosing
+ * the pids of other processes.
+ */
+ if (!capable(CAP_SYS_ADMIN) &&
+ task_tgid(current) != event->pid)
+ metadata.pid = 0;
if (path && path->mnt && path->dentry) {
fd = create_fd(group, path, &f);
@@ -573,6 +659,7 @@ static ssize_t fanotify_write(struct file *file, const char __user *buf, size_t
static int fanotify_release(struct inode *ignored, struct file *file)
{
struct fsnotify_group *group = file->private_data;
+ struct fsnotify_event *fsn_event;
/*
* Stop new events from arriving in the notification queue. since
@@ -601,13 +688,12 @@ static int fanotify_release(struct inode *ignored, struct file *file)
* dequeue them and set the response. They will be freed once the
* response is consumed and fanotify_get_response() returns.
*/
- while (!fsnotify_notify_queue_is_empty(group)) {
- struct fanotify_event *event;
+ while ((fsn_event = fsnotify_remove_first_event(group))) {
+ struct fanotify_event *event = FANOTIFY_E(fsn_event);
- event = FANOTIFY_E(fsnotify_remove_first_event(group));
if (!(event->mask & FANOTIFY_PERM_EVENTS)) {
spin_unlock(&group->notification_lock);
- fsnotify_destroy_event(group, &event->fse);
+ fsnotify_destroy_event(group, fsn_event);
} else {
finish_permission_event(group, FANOTIFY_PERM(event),
FAN_ALLOW);
@@ -822,24 +908,38 @@ static struct fsnotify_mark *fanotify_add_new_mark(struct fsnotify_group *group,
unsigned int type,
__kernel_fsid_t *fsid)
{
+ struct ucounts *ucounts = group->fanotify_data.ucounts;
struct fsnotify_mark *mark;
int ret;
- if (atomic_read(&group->num_marks) > group->fanotify_data.max_marks)
+ /*
+ * Enforce per user marks limits per user in all containing user ns.
+ * A group with FAN_UNLIMITED_MARKS does not contribute to mark count
+ * in the limited groups account.
+ */
+ if (!FAN_GROUP_FLAG(group, FAN_UNLIMITED_MARKS) &&
+ !inc_ucount(ucounts->ns, ucounts->uid, UCOUNT_FANOTIFY_MARKS))
return ERR_PTR(-ENOSPC);
mark = kmem_cache_alloc(fanotify_mark_cache, GFP_KERNEL);
- if (!mark)
- return ERR_PTR(-ENOMEM);
+ if (!mark) {
+ ret = -ENOMEM;
+ goto out_dec_ucounts;
+ }
fsnotify_init_mark(mark, group);
ret = fsnotify_add_mark_locked(mark, connp, type, 0, fsid);
if (ret) {
fsnotify_put_mark(mark);
- return ERR_PTR(ret);
+ goto out_dec_ucounts;
}
return mark;
+
+out_dec_ucounts:
+ if (!FAN_GROUP_FLAG(group, FAN_UNLIMITED_MARKS))
+ dec_ucount(ucounts, UCOUNT_FANOTIFY_MARKS);
+ return ERR_PTR(ret);
}
@@ -919,20 +1019,41 @@ static struct fsnotify_event *fanotify_alloc_overflow_event(void)
return &oevent->fse;
}
+static struct hlist_head *fanotify_alloc_merge_hash(void)
+{
+ struct hlist_head *hash;
+
+ hash = kmalloc(sizeof(struct hlist_head) << FANOTIFY_HTABLE_BITS,
+ GFP_KERNEL_ACCOUNT);
+ if (!hash)
+ return NULL;
+
+ __hash_init(hash, FANOTIFY_HTABLE_SIZE);
+
+ return hash;
+}
+
/* fanotify syscalls */
SYSCALL_DEFINE2(fanotify_init, unsigned int, flags, unsigned int, event_f_flags)
{
struct fsnotify_group *group;
int f_flags, fd;
- struct user_struct *user;
unsigned int fid_mode = flags & FANOTIFY_FID_BITS;
unsigned int class = flags & FANOTIFY_CLASS_BITS;
pr_debug("%s: flags=%x event_f_flags=%x\n",
__func__, flags, event_f_flags);
- if (!capable(CAP_SYS_ADMIN))
- return -EPERM;
+ if (!capable(CAP_SYS_ADMIN)) {
+ /*
+ * An unprivileged user can setup an fanotify group with
+ * limited functionality - an unprivileged group is limited to
+ * notification events with file handles and it cannot use
+ * unlimited queue/marks.
+ */
+ if ((flags & FANOTIFY_ADMIN_INIT_FLAGS) || !fid_mode)
+ return -EPERM;
+ }
#ifdef CONFIG_AUDITSYSCALL
if (flags & ~(FANOTIFY_INIT_FLAGS | FAN_ENABLE_AUDIT))
@@ -963,12 +1084,6 @@ SYSCALL_DEFINE2(fanotify_init, unsigned int, flags, unsigned int, event_f_flags)
if ((fid_mode & FAN_REPORT_NAME) && !(fid_mode & FAN_REPORT_DIR_FID))
return -EINVAL;
- user = get_current_user();
- if (atomic_read(&user->fanotify_listeners) > FANOTIFY_DEFAULT_MAX_LISTENERS) {
- free_uid(user);
- return -EMFILE;
- }
-
f_flags = O_RDWR | FMODE_NONOTIFY;
if (flags & FAN_CLOEXEC)
f_flags |= O_CLOEXEC;
@@ -978,15 +1093,27 @@ SYSCALL_DEFINE2(fanotify_init, unsigned int, flags, unsigned int, event_f_flags)
/* fsnotify_alloc_group takes a ref. Dropped in fanotify_release */
group = fsnotify_alloc_user_group(&fanotify_fsnotify_ops);
if (IS_ERR(group)) {
- free_uid(user);
return PTR_ERR(group);
}
- group->fanotify_data.user = user;
+ /* Enforce groups limits per user in all containing user ns */
+ group->fanotify_data.ucounts = inc_ucount(current_user_ns(),
+ current_euid(),
+ UCOUNT_FANOTIFY_GROUPS);
+ if (!group->fanotify_data.ucounts) {
+ fd = -EMFILE;
+ goto out_destroy_group;
+ }
+
group->fanotify_data.flags = flags;
- atomic_inc(&user->fanotify_listeners);
group->memcg = get_mem_cgroup_from_mm(current->mm);
+ group->fanotify_data.merge_hash = fanotify_alloc_merge_hash();
+ if (!group->fanotify_data.merge_hash) {
+ fd = -ENOMEM;
+ goto out_destroy_group;
+ }
+
group->overflow_event = fanotify_alloc_overflow_event();
if (unlikely(!group->overflow_event)) {
fd = -ENOMEM;
@@ -1019,16 +1146,13 @@ SYSCALL_DEFINE2(fanotify_init, unsigned int, flags, unsigned int, event_f_flags)
goto out_destroy_group;
group->max_events = UINT_MAX;
} else {
- group->max_events = FANOTIFY_DEFAULT_MAX_EVENTS;
+ group->max_events = fanotify_max_queued_events;
}
if (flags & FAN_UNLIMITED_MARKS) {
fd = -EPERM;
if (!capable(CAP_SYS_ADMIN))
goto out_destroy_group;
- group->fanotify_data.max_marks = UINT_MAX;
- } else {
- group->fanotify_data.max_marks = FANOTIFY_DEFAULT_MAX_MARKS;
}
if (flags & FAN_ENABLE_AUDIT) {
@@ -1126,7 +1250,7 @@ static int do_fanotify_mark(int fanotify_fd, unsigned int flags, __u64 mask,
__func__, fanotify_fd, flags, dfd, pathname, mask);
/* we only use the lower 32 bits as of right now. */
- if (mask & ((__u64)0xffffffff << 32))
+ if (upper_32_bits(mask))
return -EINVAL;
if (flags & ~FANOTIFY_MARK_FLAGS)
@@ -1181,6 +1305,15 @@ static int do_fanotify_mark(int fanotify_fd, unsigned int flags, __u64 mask,
group = f.file->private_data;
/*
+ * An unprivileged user is not allowed to watch a mount point nor
+ * a filesystem.
+ */
+ ret = -EPERM;
+ if (!capable(CAP_SYS_ADMIN) &&
+ mark_type != FAN_MARK_INODE)
+ goto fput_and_out;
+
+ /*
* group->priority == FS_PRIO_0 == FAN_CLASS_NOTIF. These are not
* allowed to set permissions events.
*/
@@ -1312,6 +1445,21 @@ SYSCALL32_DEFINE6(fanotify_mark,
*/
static int __init fanotify_user_setup(void)
{
+ struct sysinfo si;
+ int max_marks;
+
+ si_meminfo(&si);
+ /*
+ * Allow up to 1% of addressable memory to be accounted for per user
+ * marks limited to the range [8192, 1048576]. mount and sb marks are
+ * a lot cheaper than inode marks, but there is no reason for a user
+ * to have many of those, so calculate by the cost of inode marks.
+ */
+ max_marks = (((si.totalram - si.totalhigh) / 100) << PAGE_SHIFT) /
+ INODE_MARK_COST;
+ max_marks = clamp(max_marks, FANOTIFY_OLD_DEFAULT_MAX_MARKS,
+ FANOTIFY_DEFAULT_MAX_USER_MARKS);
+
BUILD_BUG_ON(HWEIGHT32(FANOTIFY_INIT_FLAGS) != 10);
BUILD_BUG_ON(HWEIGHT32(FANOTIFY_MARK_FLAGS) != 9);
@@ -1326,6 +1474,11 @@ static int __init fanotify_user_setup(void)
KMEM_CACHE(fanotify_perm_event, SLAB_PANIC);
}
+ fanotify_max_queued_events = FANOTIFY_DEFAULT_MAX_EVENTS;
+ init_user_ns.ucount_max[UCOUNT_FANOTIFY_GROUPS] =
+ FANOTIFY_DEFAULT_MAX_GROUPS;
+ init_user_ns.ucount_max[UCOUNT_FANOTIFY_MARKS] = max_marks;
+
return 0;
}
device_initcall(fanotify_user_setup);
diff --git a/fs/notify/fdinfo.c b/fs/notify/fdinfo.c
index f0d6b54be412..a712b2aaa9ac 100644
--- a/fs/notify/fdinfo.c
+++ b/fs/notify/fdinfo.c
@@ -144,7 +144,8 @@ void fanotify_show_fdinfo(struct seq_file *m, struct file *f)
struct fsnotify_group *group = f->private_data;
seq_printf(m, "fanotify flags:%x event-flags:%x\n",
- group->fanotify_data.flags, group->fanotify_data.f_flags);
+ group->fanotify_data.flags,
+ group->fanotify_data.f_flags);
show_fdinfo(m, f, fanotify_fdinfo);
}
diff --git a/fs/notify/group.c b/fs/notify/group.c
index ffd723ffe46d..fb89c351295d 100644
--- a/fs/notify/group.c
+++ b/fs/notify/group.c
@@ -122,7 +122,6 @@ static struct fsnotify_group *__fsnotify_alloc_group(
/* set to 0 when there a no external references to this group */
refcount_set(&group->refcnt, 1);
- atomic_set(&group->num_marks, 0);
atomic_set(&group->user_waits, 0);
spin_lock_init(&group->notification_lock);
diff --git a/fs/notify/inotify/inotify_fsnotify.c b/fs/notify/inotify/inotify_fsnotify.c
index 1901d799909b..d1a64daa0171 100644
--- a/fs/notify/inotify/inotify_fsnotify.c
+++ b/fs/notify/inotify/inotify_fsnotify.c
@@ -46,9 +46,10 @@ static bool event_compare(struct fsnotify_event *old_fsn,
return false;
}
-static int inotify_merge(struct list_head *list,
- struct fsnotify_event *event)
+static int inotify_merge(struct fsnotify_group *group,
+ struct fsnotify_event *event)
{
+ struct list_head *list = &group->notification_list;
struct fsnotify_event *last_event;
last_event = list_entry(list->prev, struct fsnotify_event, list);
@@ -107,7 +108,7 @@ int inotify_handle_inode_event(struct fsnotify_mark *inode_mark, u32 mask,
mask &= ~IN_ISDIR;
fsn_event = &event->fse;
- fsnotify_init_event(fsn_event, 0);
+ fsnotify_init_event(fsn_event);
event->mask = mask;
event->wd = i_mark->wd;
event->sync_cookie = cookie;
@@ -115,7 +116,7 @@ int inotify_handle_inode_event(struct fsnotify_mark *inode_mark, u32 mask,
if (len)
strcpy(event->name, name->name);
- ret = fsnotify_add_event(group, fsn_event, inotify_merge);
+ ret = fsnotify_add_event(group, fsn_event, inotify_merge, NULL);
if (ret) {
/* Our event wasn't used in the end. Free it. */
fsnotify_destroy_event(group, fsn_event);
diff --git a/fs/notify/inotify/inotify_user.c b/fs/notify/inotify/inotify_user.c
index c71be4fb7dc5..98f61b31745a 100644
--- a/fs/notify/inotify/inotify_user.c
+++ b/fs/notify/inotify/inotify_user.c
@@ -146,10 +146,9 @@ static struct fsnotify_event *get_one_event(struct fsnotify_group *group,
size_t event_size = sizeof(struct inotify_event);
struct fsnotify_event *event;
- if (fsnotify_notify_queue_is_empty(group))
- return NULL;
-
event = fsnotify_peek_first_event(group);
+ if (!event)
+ return NULL;
pr_debug("%s: group=%p event=%p\n", __func__, group, event);
@@ -642,7 +641,7 @@ static struct fsnotify_group *inotify_new_group(unsigned int max_events)
return ERR_PTR(-ENOMEM);
}
group->overflow_event = &oevent->fse;
- fsnotify_init_event(group->overflow_event, 0);
+ fsnotify_init_event(group->overflow_event);
oevent->mask = FS_Q_OVERFLOW;
oevent->wd = -1;
oevent->sync_cookie = 0;
diff --git a/fs/notify/mark.c b/fs/notify/mark.c
index 8387937b9d01..d32ab349db74 100644
--- a/fs/notify/mark.c
+++ b/fs/notify/mark.c
@@ -391,8 +391,6 @@ void fsnotify_detach_mark(struct fsnotify_mark *mark)
list_del_init(&mark->g_list);
spin_unlock(&mark->lock);
- atomic_dec(&group->num_marks);
-
/* Drop mark reference acquired in fsnotify_add_mark_locked() */
fsnotify_put_mark(mark);
}
@@ -656,7 +654,6 @@ int fsnotify_add_mark_locked(struct fsnotify_mark *mark,
mark->flags |= FSNOTIFY_MARK_FLAG_ALIVE | FSNOTIFY_MARK_FLAG_ATTACHED;
list_add(&mark->g_list, &group->marks_list);
- atomic_inc(&group->num_marks);
fsnotify_get_mark(mark); /* for g_list */
spin_unlock(&mark->lock);
@@ -674,7 +671,6 @@ err:
FSNOTIFY_MARK_FLAG_ATTACHED);
list_del_init(&mark->g_list);
spin_unlock(&mark->lock);
- atomic_dec(&group->num_marks);
fsnotify_put_mark(mark);
return ret;
diff --git a/fs/notify/notification.c b/fs/notify/notification.c
index 75d79d6d3ef0..32f45543b9c6 100644
--- a/fs/notify/notification.c
+++ b/fs/notify/notification.c
@@ -47,13 +47,6 @@ u32 fsnotify_get_cookie(void)
}
EXPORT_SYMBOL_GPL(fsnotify_get_cookie);
-/* return true if the notify queue is empty, false otherwise */
-bool fsnotify_notify_queue_is_empty(struct fsnotify_group *group)
-{
- assert_spin_locked(&group->notification_lock);
- return list_empty(&group->notification_list) ? true : false;
-}
-
void fsnotify_destroy_event(struct fsnotify_group *group,
struct fsnotify_event *event)
{
@@ -75,16 +68,22 @@ void fsnotify_destroy_event(struct fsnotify_group *group,
}
/*
- * Add an event to the group notification queue. The group can later pull this
- * event off the queue to deal with. The function returns 0 if the event was
- * added to the queue, 1 if the event was merged with some other queued event,
+ * Try to add an event to the notification queue.
+ * The group can later pull this event off the queue to deal with.
+ * The group can use the @merge hook to merge the event with a queued event.
+ * The group can use the @insert hook to insert the event into hash table.
+ * The function returns:
+ * 0 if the event was added to a queue
+ * 1 if the event was merged with some other queued event
* 2 if the event was not queued - either the queue of events has overflown
- * or the group is shutting down.
+ * or the group is shutting down.
*/
int fsnotify_add_event(struct fsnotify_group *group,
struct fsnotify_event *event,
- int (*merge)(struct list_head *,
- struct fsnotify_event *))
+ int (*merge)(struct fsnotify_group *,
+ struct fsnotify_event *),
+ void (*insert)(struct fsnotify_group *,
+ struct fsnotify_event *))
{
int ret = 0;
struct list_head *list = &group->notification_list;
@@ -111,7 +110,7 @@ int fsnotify_add_event(struct fsnotify_group *group,
}
if (!list_empty(list) && merge) {
- ret = merge(list, event);
+ ret = merge(group, event);
if (ret) {
spin_unlock(&group->notification_lock);
return ret;
@@ -121,6 +120,8 @@ int fsnotify_add_event(struct fsnotify_group *group,
queue:
group->q_len++;
list_add_tail(&event->list, list);
+ if (insert)
+ insert(group, event);
spin_unlock(&group->notification_lock);
wake_up(&group->notification_waitq);
@@ -141,33 +142,36 @@ void fsnotify_remove_queued_event(struct fsnotify_group *group,
}
/*
- * Remove and return the first event from the notification list. It is the
- * responsibility of the caller to destroy the obtained event
+ * Return the first event on the notification list without removing it.
+ * Returns NULL if the list is empty.
*/
-struct fsnotify_event *fsnotify_remove_first_event(struct fsnotify_group *group)
+struct fsnotify_event *fsnotify_peek_first_event(struct fsnotify_group *group)
{
- struct fsnotify_event *event;
-
assert_spin_locked(&group->notification_lock);
- pr_debug("%s: group=%p\n", __func__, group);
+ if (fsnotify_notify_queue_is_empty(group))
+ return NULL;
- event = list_first_entry(&group->notification_list,
- struct fsnotify_event, list);
- fsnotify_remove_queued_event(group, event);
- return event;
+ return list_first_entry(&group->notification_list,
+ struct fsnotify_event, list);
}
/*
- * This will not remove the event, that must be done with
- * fsnotify_remove_first_event()
+ * Remove and return the first event from the notification list. It is the
+ * responsibility of the caller to destroy the obtained event
*/
-struct fsnotify_event *fsnotify_peek_first_event(struct fsnotify_group *group)
+struct fsnotify_event *fsnotify_remove_first_event(struct fsnotify_group *group)
{
- assert_spin_locked(&group->notification_lock);
+ struct fsnotify_event *event = fsnotify_peek_first_event(group);
- return list_first_entry(&group->notification_list,
- struct fsnotify_event, list);
+ if (!event)
+ return NULL;
+
+ pr_debug("%s: group=%p event=%p\n", __func__, group, event);
+
+ fsnotify_remove_queued_event(group, event);
+
+ return event;
}
/*
diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c
index 3bfb4147895a..ad20403b383f 100644
--- a/fs/ocfs2/aops.c
+++ b/fs/ocfs2/aops.c
@@ -2295,7 +2295,7 @@ static int ocfs2_dio_end_io_write(struct inode *inode,
struct ocfs2_alloc_context *meta_ac = NULL;
handle_t *handle = NULL;
loff_t end = offset + bytes;
- int ret = 0, credits = 0, locked = 0;
+ int ret = 0, credits = 0;
ocfs2_init_dealloc_ctxt(&dealloc);
@@ -2306,13 +2306,6 @@ static int ocfs2_dio_end_io_write(struct inode *inode,
!dwc->dw_orphaned)
goto out;
- /* ocfs2_file_write_iter will get i_mutex, so we need not lock if we
- * are in that context. */
- if (dwc->dw_writer_pid != task_pid_nr(current)) {
- inode_lock(inode);
- locked = 1;
- }
-
ret = ocfs2_inode_lock(inode, &di_bh, 1);
if (ret < 0) {
mlog_errno(ret);
@@ -2393,8 +2386,6 @@ out:
if (meta_ac)
ocfs2_free_alloc_context(meta_ac);
ocfs2_run_deallocs(osb, &dealloc);
- if (locked)
- inode_unlock(inode);
ocfs2_dio_free_write_ctx(inode, dwc);
return ret;
diff --git a/fs/ocfs2/blockcheck.c b/fs/ocfs2/blockcheck.c
index 6e07ddb0e3c0..dabfef9c2bc0 100644
--- a/fs/ocfs2/blockcheck.c
+++ b/fs/ocfs2/blockcheck.c
@@ -229,7 +229,7 @@ static int blockcheck_u64_get(void *data, u64 *val)
*val = *(u64 *)data;
return 0;
}
-DEFINE_SIMPLE_ATTRIBUTE(blockcheck_fops, blockcheck_u64_get, NULL, "%llu\n");
+DEFINE_DEBUGFS_ATTRIBUTE(blockcheck_fops, blockcheck_u64_get, NULL, "%llu\n");
static void ocfs2_blockcheck_debug_remove(struct ocfs2_blockcheck_stats *stats)
{
diff --git a/fs/ocfs2/dlm/dlmrecovery.c b/fs/ocfs2/dlm/dlmrecovery.c
index 4b566e88582f..afc51736686c 100644
--- a/fs/ocfs2/dlm/dlmrecovery.c
+++ b/fs/ocfs2/dlm/dlmrecovery.c
@@ -126,13 +126,6 @@ static inline void __dlm_reset_recovery(struct dlm_ctxt *dlm)
dlm_set_reco_master(dlm, O2NM_INVALID_NODE_NUM);
}
-static inline void dlm_reset_recovery(struct dlm_ctxt *dlm)
-{
- spin_lock(&dlm->spinlock);
- __dlm_reset_recovery(dlm);
- spin_unlock(&dlm->spinlock);
-}
-
/* Worker function used during recovery. */
void dlm_dispatch_work(struct work_struct *work)
{
diff --git a/fs/ocfs2/dlmglue.c b/fs/ocfs2/dlmglue.c
index 8e3a369086db..0fbe8bf7190f 100644
--- a/fs/ocfs2/dlmglue.c
+++ b/fs/ocfs2/dlmglue.c
@@ -2204,7 +2204,7 @@ static void ocfs2_unpack_timespec(struct timespec64 *spec,
spec->tv_nsec = packed_time & OCFS2_NSEC_MASK;
}
-static void ocfs2_refresh_inode_from_lvb(struct inode *inode)
+static int ocfs2_refresh_inode_from_lvb(struct inode *inode)
{
struct ocfs2_inode_info *oi = OCFS2_I(inode);
struct ocfs2_lock_res *lockres = &oi->ip_inode_lockres;
@@ -2213,6 +2213,8 @@ static void ocfs2_refresh_inode_from_lvb(struct inode *inode)
mlog_meta_lvb(0, lockres);
lvb = ocfs2_dlm_lvb(&lockres->l_lksb);
+ if (inode_wrong_type(inode, be16_to_cpu(lvb->lvb_imode)))
+ return -ESTALE;
/* We're safe here without the lockres lock... */
spin_lock(&oi->ip_lock);
@@ -2240,6 +2242,7 @@ static void ocfs2_refresh_inode_from_lvb(struct inode *inode)
ocfs2_unpack_timespec(&inode->i_ctime,
be64_to_cpu(lvb->lvb_ictime_packed));
spin_unlock(&oi->ip_lock);
+ return 0;
}
static inline int ocfs2_meta_lvb_is_trustable(struct inode *inode,
@@ -2342,7 +2345,8 @@ static int ocfs2_inode_lock_update(struct inode *inode,
if (ocfs2_meta_lvb_is_trustable(inode, lockres)) {
mlog(0, "Trusting LVB on inode %llu\n",
(unsigned long long)oi->ip_blkno);
- ocfs2_refresh_inode_from_lvb(inode);
+ status = ocfs2_refresh_inode_from_lvb(inode);
+ goto bail_refresh;
} else {
/* Boo, we have to go to disk. */
/* read bh, cast, ocfs2_refresh_inode */
@@ -2352,6 +2356,10 @@ static int ocfs2_inode_lock_update(struct inode *inode,
goto bail_refresh;
}
fe = (struct ocfs2_dinode *) (*bh)->b_data;
+ if (inode_wrong_type(inode, le16_to_cpu(fe->i_mode))) {
+ status = -ESTALE;
+ goto bail_refresh;
+ }
/* This is a good chance to make sure we're not
* locking an invalid object. ocfs2_read_inode_block()
diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c
index 6611c64ca0be..db8a6265b749 100644
--- a/fs/ocfs2/file.c
+++ b/fs/ocfs2/file.c
@@ -1245,22 +1245,24 @@ int ocfs2_setattr(struct user_namespace *mnt_userns, struct dentry *dentry,
goto bail_unlock;
}
}
+ down_write(&OCFS2_I(inode)->ip_alloc_sem);
handle = ocfs2_start_trans(osb, OCFS2_INODE_UPDATE_CREDITS +
2 * ocfs2_quota_trans_credits(sb));
if (IS_ERR(handle)) {
status = PTR_ERR(handle);
mlog_errno(status);
- goto bail_unlock;
+ goto bail_unlock_alloc;
}
status = __dquot_transfer(inode, transfer_to);
if (status < 0)
goto bail_commit;
} else {
+ down_write(&OCFS2_I(inode)->ip_alloc_sem);
handle = ocfs2_start_trans(osb, OCFS2_INODE_UPDATE_CREDITS);
if (IS_ERR(handle)) {
status = PTR_ERR(handle);
mlog_errno(status);
- goto bail_unlock;
+ goto bail_unlock_alloc;
}
}
@@ -1273,6 +1275,8 @@ int ocfs2_setattr(struct user_namespace *mnt_userns, struct dentry *dentry,
bail_commit:
ocfs2_commit_trans(osb, handle);
+bail_unlock_alloc:
+ up_write(&OCFS2_I(inode)->ip_alloc_sem);
bail_unlock:
if (status && inode_locked) {
ocfs2_inode_unlock_tracker(inode, 1, &oh, had_lock);
@@ -2645,6 +2649,8 @@ const struct inode_operations ocfs2_file_iops = {
.fiemap = ocfs2_fiemap,
.get_acl = ocfs2_iop_get_acl,
.set_acl = ocfs2_iop_set_acl,
+ .fileattr_get = ocfs2_fileattr_get,
+ .fileattr_set = ocfs2_fileattr_set,
};
const struct inode_operations ocfs2_special_file_iops = {
diff --git a/fs/ocfs2/ioctl.c b/fs/ocfs2/ioctl.c
index 50c9b30ee9f6..f59461d85da4 100644
--- a/fs/ocfs2/ioctl.c
+++ b/fs/ocfs2/ioctl.c
@@ -10,6 +10,7 @@
#include <linux/mount.h>
#include <linux/blkdev.h>
#include <linux/compat.h>
+#include <linux/fileattr.h>
#include <cluster/masklog.h>
@@ -61,8 +62,10 @@ static inline int o2info_coherent(struct ocfs2_info_request *req)
return (!(req->ir_flags & OCFS2_INFO_FL_NON_COHERENT));
}
-static int ocfs2_get_inode_attr(struct inode *inode, unsigned *flags)
+int ocfs2_fileattr_get(struct dentry *dentry, struct fileattr *fa)
{
+ struct inode *inode = d_inode(dentry);
+ unsigned int flags;
int status;
status = ocfs2_inode_lock(inode, NULL, 0);
@@ -71,15 +74,19 @@ static int ocfs2_get_inode_attr(struct inode *inode, unsigned *flags)
return status;
}
ocfs2_get_inode_flags(OCFS2_I(inode));
- *flags = OCFS2_I(inode)->ip_attr;
+ flags = OCFS2_I(inode)->ip_attr;
ocfs2_inode_unlock(inode, 0);
+ fileattr_fill_flags(fa, flags & OCFS2_FL_VISIBLE);
+
return status;
}
-static int ocfs2_set_inode_attr(struct inode *inode, unsigned flags,
- unsigned mask)
+int ocfs2_fileattr_set(struct user_namespace *mnt_userns,
+ struct dentry *dentry, struct fileattr *fa)
{
+ struct inode *inode = d_inode(dentry);
+ unsigned int flags = fa->flags;
struct ocfs2_inode_info *ocfs2_inode = OCFS2_I(inode);
struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
handle_t *handle = NULL;
@@ -87,7 +94,8 @@ static int ocfs2_set_inode_attr(struct inode *inode, unsigned flags,
unsigned oldflags;
int status;
- inode_lock(inode);
+ if (fileattr_has_fsx(fa))
+ return -EOPNOTSUPP;
status = ocfs2_inode_lock(inode, &bh, 1);
if (status < 0) {
@@ -95,19 +103,17 @@ static int ocfs2_set_inode_attr(struct inode *inode, unsigned flags,
goto bail;
}
- status = -EACCES;
- if (!inode_owner_or_capable(&init_user_ns, inode))
- goto bail_unlock;
-
if (!S_ISDIR(inode->i_mode))
flags &= ~OCFS2_DIRSYNC_FL;
oldflags = ocfs2_inode->ip_attr;
- flags = flags & mask;
- flags |= oldflags & ~mask;
+ flags = flags & OCFS2_FL_MODIFIABLE;
+ flags |= oldflags & ~OCFS2_FL_MODIFIABLE;
- status = vfs_ioc_setflags_prepare(inode, oldflags, flags);
- if (status)
+ /* Check already done by VFS, but repeat with ocfs lock */
+ status = -EPERM;
+ if ((flags ^ oldflags) & (FS_APPEND_FL | FS_IMMUTABLE_FL) &&
+ !capable(CAP_LINUX_IMMUTABLE))
goto bail_unlock;
handle = ocfs2_start_trans(osb, OCFS2_INODE_UPDATE_CREDITS);
@@ -129,8 +135,6 @@ static int ocfs2_set_inode_attr(struct inode *inode, unsigned flags,
bail_unlock:
ocfs2_inode_unlock(inode, 1);
bail:
- inode_unlock(inode);
-
brelse(bh);
return status;
@@ -836,7 +840,6 @@ bail:
long ocfs2_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
{
struct inode *inode = file_inode(filp);
- unsigned int flags;
int new_clusters;
int status;
struct ocfs2_space_resv sr;
@@ -849,24 +852,6 @@ long ocfs2_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
void __user *argp = (void __user *)arg;
switch (cmd) {
- case OCFS2_IOC_GETFLAGS:
- status = ocfs2_get_inode_attr(inode, &flags);
- if (status < 0)
- return status;
-
- flags &= OCFS2_FL_VISIBLE;
- return put_user(flags, (int __user *) arg);
- case OCFS2_IOC_SETFLAGS:
- if (get_user(flags, (int __user *) arg))
- return -EFAULT;
-
- status = mnt_want_write_file(filp);
- if (status)
- return status;
- status = ocfs2_set_inode_attr(inode, flags,
- OCFS2_FL_MODIFIABLE);
- mnt_drop_write_file(filp);
- return status;
case OCFS2_IOC_RESVSP:
case OCFS2_IOC_RESVSP64:
case OCFS2_IOC_UNRESVSP:
@@ -959,12 +944,6 @@ long ocfs2_compat_ioctl(struct file *file, unsigned cmd, unsigned long arg)
void __user *argp = (void __user *)arg;
switch (cmd) {
- case OCFS2_IOC32_GETFLAGS:
- cmd = OCFS2_IOC_GETFLAGS;
- break;
- case OCFS2_IOC32_SETFLAGS:
- cmd = OCFS2_IOC_SETFLAGS;
- break;
case OCFS2_IOC_RESVSP:
case OCFS2_IOC_RESVSP64:
case OCFS2_IOC_UNRESVSP:
diff --git a/fs/ocfs2/ioctl.h b/fs/ocfs2/ioctl.h
index 9f5e4d95e37f..0297c8846945 100644
--- a/fs/ocfs2/ioctl.h
+++ b/fs/ocfs2/ioctl.h
@@ -11,6 +11,9 @@
#ifndef OCFS2_IOCTL_PROTO_H
#define OCFS2_IOCTL_PROTO_H
+int ocfs2_fileattr_get(struct dentry *dentry, struct fileattr *fa);
+int ocfs2_fileattr_set(struct user_namespace *mnt_userns,
+ struct dentry *dentry, struct fileattr *fa);
long ocfs2_ioctl(struct file *filp, unsigned int cmd, unsigned long arg);
long ocfs2_compat_ioctl(struct file *file, unsigned cmd, unsigned long arg);
diff --git a/fs/ocfs2/namei.c b/fs/ocfs2/namei.c
index 3abdd36da2e2..05ced86580d1 100644
--- a/fs/ocfs2/namei.c
+++ b/fs/ocfs2/namei.c
@@ -50,6 +50,7 @@
#include "xattr.h"
#include "acl.h"
#include "ocfs2_trace.h"
+#include "ioctl.h"
#include "buffer_head_io.h"
@@ -2918,4 +2919,6 @@ const struct inode_operations ocfs2_dir_iops = {
.fiemap = ocfs2_fiemap,
.get_acl = ocfs2_iop_get_acl,
.set_acl = ocfs2_iop_set_acl,
+ .fileattr_get = ocfs2_fileattr_get,
+ .fileattr_set = ocfs2_fileattr_set,
};
diff --git a/fs/ocfs2/ocfs2_ioctl.h b/fs/ocfs2/ocfs2_ioctl.h
index d7b31734f6be..273616bd4f19 100644
--- a/fs/ocfs2/ocfs2_ioctl.h
+++ b/fs/ocfs2/ocfs2_ioctl.h
@@ -13,14 +13,6 @@
#define OCFS2_IOCTL_H
/*
- * ioctl commands
- */
-#define OCFS2_IOC_GETFLAGS FS_IOC_GETFLAGS
-#define OCFS2_IOC_SETFLAGS FS_IOC_SETFLAGS
-#define OCFS2_IOC32_GETFLAGS FS_IOC32_GETFLAGS
-#define OCFS2_IOC32_SETFLAGS FS_IOC32_SETFLAGS
-
-/*
* Space reservation / allocation / free ioctls and argument structure
* are designed to be compatible with XFS.
*
diff --git a/fs/ocfs2/stack_o2cb.c b/fs/ocfs2/stack_o2cb.c
index dbf8b5735808..f70012038383 100644
--- a/fs/ocfs2/stack_o2cb.c
+++ b/fs/ocfs2/stack_o2cb.c
@@ -59,31 +59,31 @@ static inline int mode_to_o2dlm(int mode)
return mode;
}
-#define map_flag(_generic, _o2dlm) \
- if (flags & (_generic)) { \
- flags &= ~(_generic); \
- o2dlm_flags |= (_o2dlm); \
- }
static int flags_to_o2dlm(u32 flags)
{
int o2dlm_flags = 0;
- map_flag(DLM_LKF_NOQUEUE, LKM_NOQUEUE);
- map_flag(DLM_LKF_CANCEL, LKM_CANCEL);
- map_flag(DLM_LKF_CONVERT, LKM_CONVERT);
- map_flag(DLM_LKF_VALBLK, LKM_VALBLK);
- map_flag(DLM_LKF_IVVALBLK, LKM_INVVALBLK);
- map_flag(DLM_LKF_ORPHAN, LKM_ORPHAN);
- map_flag(DLM_LKF_FORCEUNLOCK, LKM_FORCE);
- map_flag(DLM_LKF_TIMEOUT, LKM_TIMEOUT);
- map_flag(DLM_LKF_LOCAL, LKM_LOCAL);
-
- /* map_flag() should have cleared every flag passed in */
- BUG_ON(flags != 0);
+ if (flags & DLM_LKF_NOQUEUE)
+ o2dlm_flags |= LKM_NOQUEUE;
+ if (flags & DLM_LKF_CANCEL)
+ o2dlm_flags |= LKM_CANCEL;
+ if (flags & DLM_LKF_CONVERT)
+ o2dlm_flags |= LKM_CONVERT;
+ if (flags & DLM_LKF_VALBLK)
+ o2dlm_flags |= LKM_VALBLK;
+ if (flags & DLM_LKF_IVVALBLK)
+ o2dlm_flags |= LKM_INVVALBLK;
+ if (flags & DLM_LKF_ORPHAN)
+ o2dlm_flags |= LKM_ORPHAN;
+ if (flags & DLM_LKF_FORCEUNLOCK)
+ o2dlm_flags |= LKM_FORCE;
+ if (flags & DLM_LKF_TIMEOUT)
+ o2dlm_flags |= LKM_TIMEOUT;
+ if (flags & DLM_LKF_LOCAL)
+ o2dlm_flags |= LKM_LOCAL;
return o2dlm_flags;
}
-#undef map_flag
/*
* Map an o2dlm status to standard errno values.
diff --git a/fs/ocfs2/stackglue.c b/fs/ocfs2/stackglue.c
index a191094694c6..8d33ebc6b6fc 100644
--- a/fs/ocfs2/stackglue.c
+++ b/fs/ocfs2/stackglue.c
@@ -731,7 +731,7 @@ static void __exit ocfs2_stack_glue_exit(void)
}
MODULE_AUTHOR("Oracle");
-MODULE_DESCRIPTION("ocfs2 cluter stack glue layer");
+MODULE_DESCRIPTION("ocfs2 cluster stack glue layer");
MODULE_LICENSE("GPL");
module_init(ocfs2_stack_glue_init);
module_exit(ocfs2_stack_glue_exit);
diff --git a/fs/openpromfs/inode.c b/fs/openpromfs/inode.c
index 40c8c2e32fa3..f825176ff4ed 100644
--- a/fs/openpromfs/inode.c
+++ b/fs/openpromfs/inode.c
@@ -236,27 +236,31 @@ found:
mutex_unlock(&op_mutex);
if (IS_ERR(inode))
return ERR_CAST(inode);
- ent_oi = OP_I(inode);
- ent_oi->type = ent_type;
- ent_oi->u = ent_data;
-
- switch (ent_type) {
- case op_inode_node:
- inode->i_mode = S_IFDIR | S_IRUGO | S_IXUGO;
- inode->i_op = &openprom_inode_operations;
- inode->i_fop = &openprom_operations;
- set_nlink(inode, 2);
- break;
- case op_inode_prop:
- if (of_node_name_eq(dp, "options") && (len == 17) &&
- !strncmp (name, "security-password", 17))
- inode->i_mode = S_IFREG | S_IRUSR | S_IWUSR;
- else
- inode->i_mode = S_IFREG | S_IRUGO;
- inode->i_fop = &openpromfs_prop_ops;
- set_nlink(inode, 1);
- inode->i_size = ent_oi->u.prop->length;
- break;
+ if (inode->i_state & I_NEW) {
+ inode->i_mtime = inode->i_atime = inode->i_ctime = current_time(inode);
+ ent_oi = OP_I(inode);
+ ent_oi->type = ent_type;
+ ent_oi->u = ent_data;
+
+ switch (ent_type) {
+ case op_inode_node:
+ inode->i_mode = S_IFDIR | S_IRUGO | S_IXUGO;
+ inode->i_op = &openprom_inode_operations;
+ inode->i_fop = &openprom_operations;
+ set_nlink(inode, 2);
+ break;
+ case op_inode_prop:
+ if (of_node_name_eq(dp, "options") && (len == 17) &&
+ !strncmp (name, "security-password", 17))
+ inode->i_mode = S_IFREG | S_IRUSR | S_IWUSR;
+ else
+ inode->i_mode = S_IFREG | S_IRUGO;
+ inode->i_fop = &openpromfs_prop_ops;
+ set_nlink(inode, 1);
+ inode->i_size = ent_oi->u.prop->length;
+ break;
+ }
+ unlock_new_inode(inode);
}
return d_splice_alias(inode, dentry);
@@ -345,20 +349,9 @@ static void openprom_free_inode(struct inode *inode)
static struct inode *openprom_iget(struct super_block *sb, ino_t ino)
{
- struct inode *inode;
-
- inode = iget_locked(sb, ino);
+ struct inode *inode = iget_locked(sb, ino);
if (!inode)
- return ERR_PTR(-ENOMEM);
- if (inode->i_state & I_NEW) {
- inode->i_mtime = inode->i_atime = inode->i_ctime = current_time(inode);
- if (inode->i_ino == OPENPROM_ROOT_INO) {
- inode->i_op = &openprom_inode_operations;
- inode->i_fop = &openprom_operations;
- inode->i_mode = S_IFDIR | S_IRUGO | S_IXUGO;
- }
- unlock_new_inode(inode);
- }
+ inode = ERR_PTR(-ENOMEM);
return inode;
}
@@ -394,9 +387,15 @@ static int openprom_fill_super(struct super_block *s, struct fs_context *fc)
goto out_no_root;
}
+ root_inode->i_mtime = root_inode->i_atime =
+ root_inode->i_ctime = current_time(root_inode);
+ root_inode->i_op = &openprom_inode_operations;
+ root_inode->i_fop = &openprom_operations;
+ root_inode->i_mode = S_IFDIR | S_IRUGO | S_IXUGO;
oi = OP_I(root_inode);
oi->type = op_inode_node;
oi->u.node = of_find_node_by_path("/");
+ unlock_new_inode(root_inode);
s->s_root = d_make_root(root_inode);
if (!s->s_root)
diff --git a/fs/orangefs/file.c b/fs/orangefs/file.c
index 9b28a7132466..86810e5d7914 100644
--- a/fs/orangefs/file.c
+++ b/fs/orangefs/file.c
@@ -248,21 +248,7 @@ populate_shared_memory:
* or it can pointers to struct page's
*/
- /*
- * When reading, readahead_size will only be zero when
- * we're doing O_DIRECT, otherwise we got here from
- * orangefs_readpage.
- *
- * If we got here from orangefs_readpage we want to
- * copy either a page or the whole file into the io
- * vector, whichever is smaller.
- */
- if (readahead_size)
- copy_amount =
- min(new_op->downcall.resp.io.amt_complete,
- (__s64)PAGE_SIZE);
- else
- copy_amount = new_op->downcall.resp.io.amt_complete;
+ copy_amount = new_op->downcall.resp.io.amt_complete;
ret = orangefs_bufmap_copy_to_iovec(iter, buffer_index,
copy_amount);
@@ -283,19 +269,11 @@ populate_shared_memory:
out:
if (buffer_index >= 0) {
- if ((readahead_size) && (type == ORANGEFS_IO_READ)) {
- /* readpage */
- *index_return = buffer_index;
- gossip_debug(GOSSIP_FILE_DEBUG,
- "%s: hold on to buffer_index :%d:\n",
- __func__, buffer_index);
- } else {
- /* O_DIRECT */
- orangefs_bufmap_put(buffer_index);
- gossip_debug(GOSSIP_FILE_DEBUG,
- "%s(%pU): PUT buffer_index %d\n",
- __func__, handle, buffer_index);
- }
+ orangefs_bufmap_put(buffer_index);
+ gossip_debug(GOSSIP_FILE_DEBUG,
+ "%s(%pU): PUT buffer_index %d\n",
+ __func__, handle, buffer_index);
+ buffer_index = -1;
}
op_release(new_op);
return ret;
@@ -375,84 +353,6 @@ static ssize_t orangefs_file_write_iter(struct kiocb *iocb,
return ret;
}
-static int orangefs_getflags(struct inode *inode, unsigned long *uval)
-{
- __u64 val = 0;
- int ret;
-
- ret = orangefs_inode_getxattr(inode,
- "user.pvfs2.meta_hint",
- &val, sizeof(val));
- if (ret < 0 && ret != -ENODATA)
- return ret;
- else if (ret == -ENODATA)
- val = 0;
- *uval = val;
- return 0;
-}
-
-/*
- * Perform a miscellaneous operation on a file.
- */
-static long orangefs_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
-{
- struct inode *inode = file_inode(file);
- int ret = -ENOTTY;
- __u64 val = 0;
- unsigned long uval;
-
- gossip_debug(GOSSIP_FILE_DEBUG,
- "orangefs_ioctl: called with cmd %d\n",
- cmd);
-
- /*
- * we understand some general ioctls on files, such as the immutable
- * and append flags
- */
- if (cmd == FS_IOC_GETFLAGS) {
- ret = orangefs_getflags(inode, &uval);
- if (ret)
- return ret;
- gossip_debug(GOSSIP_FILE_DEBUG,
- "orangefs_ioctl: FS_IOC_GETFLAGS: %llu\n",
- (unsigned long long)uval);
- return put_user(uval, (int __user *)arg);
- } else if (cmd == FS_IOC_SETFLAGS) {
- unsigned long old_uval;
-
- ret = 0;
- if (get_user(uval, (int __user *)arg))
- return -EFAULT;
- /*
- * ORANGEFS_MIRROR_FL is set internally when the mirroring mode
- * is turned on for a file. The user is not allowed to turn
- * on this bit, but the bit is present if the user first gets
- * the flags and then updates the flags with some new
- * settings. So, we ignore it in the following edit. bligon.
- */
- if ((uval & ~ORANGEFS_MIRROR_FL) &
- (~(FS_IMMUTABLE_FL | FS_APPEND_FL | FS_NOATIME_FL))) {
- gossip_err("orangefs_ioctl: the FS_IOC_SETFLAGS only supports setting one of FS_IMMUTABLE_FL|FS_APPEND_FL|FS_NOATIME_FL\n");
- return -EINVAL;
- }
- ret = orangefs_getflags(inode, &old_uval);
- if (ret)
- return ret;
- ret = vfs_ioc_setflags_prepare(inode, old_uval, uval);
- if (ret)
- return ret;
- val = uval;
- gossip_debug(GOSSIP_FILE_DEBUG,
- "orangefs_ioctl: FS_IOC_SETFLAGS: %llu\n",
- (unsigned long long)val);
- ret = orangefs_inode_setxattr(inode,
- "user.pvfs2.meta_hint",
- &val, sizeof(val), 0);
- }
-
- return ret;
-}
-
static vm_fault_t orangefs_fault(struct vm_fault *vmf)
{
struct file *file = vmf->vma->vm_file;
@@ -657,7 +557,6 @@ const struct file_operations orangefs_file_operations = {
.read_iter = orangefs_file_read_iter,
.write_iter = orangefs_file_write_iter,
.lock = orangefs_lock,
- .unlocked_ioctl = orangefs_ioctl,
.mmap = orangefs_file_mmap,
.open = generic_file_open,
.splice_read = generic_file_splice_read,
diff --git a/fs/orangefs/inode.c b/fs/orangefs/inode.c
index 5079cfafa8d7..6bf35a0d61f3 100644
--- a/fs/orangefs/inode.c
+++ b/fs/orangefs/inode.c
@@ -11,6 +11,7 @@
*/
#include <linux/bvec.h>
+#include <linux/fileattr.h>
#include "protocol.h"
#include "orangefs-kernel.h"
#include "orangefs-bufmap.h"
@@ -244,6 +245,50 @@ static int orangefs_writepages(struct address_space *mapping,
static int orangefs_launder_page(struct page *);
+static void orangefs_readahead(struct readahead_control *rac)
+{
+ loff_t offset;
+ struct iov_iter iter;
+ struct file *file = rac->file;
+ struct inode *inode = file->f_mapping->host;
+ struct xarray *i_pages;
+ struct page *page;
+ loff_t new_start = readahead_pos(rac);
+ int ret;
+ size_t new_len = 0;
+
+ loff_t bytes_remaining = inode->i_size - readahead_pos(rac);
+ loff_t pages_remaining = bytes_remaining / PAGE_SIZE;
+
+ if (pages_remaining >= 1024)
+ new_len = 4194304;
+ else if (pages_remaining > readahead_count(rac))
+ new_len = bytes_remaining;
+
+ if (new_len)
+ readahead_expand(rac, new_start, new_len);
+
+ offset = readahead_pos(rac);
+ i_pages = &file->f_mapping->i_pages;
+
+ iov_iter_xarray(&iter, READ, i_pages, offset, readahead_length(rac));
+
+ /* read in the pages. */
+ if ((ret = wait_for_direct_io(ORANGEFS_IO_READ, inode,
+ &offset, &iter, readahead_length(rac),
+ inode->i_size, NULL, NULL, file)) < 0)
+ gossip_debug(GOSSIP_FILE_DEBUG,
+ "%s: wait_for_direct_io failed. \n", __func__);
+ else
+ ret = 0;
+
+ /* clean up. */
+ while ((page = readahead_page(rac))) {
+ page_endio(page, false, ret);
+ put_page(page);
+ }
+}
+
static int orangefs_readpage(struct file *file, struct page *page)
{
struct inode *inode = page->mapping->host;
@@ -251,44 +296,24 @@ static int orangefs_readpage(struct file *file, struct page *page)
struct bio_vec bv;
ssize_t ret;
loff_t off; /* offset into this page */
- pgoff_t index; /* which page */
- struct page *next_page;
- char *kaddr;
- loff_t read_size;
- int buffer_index = -1; /* orangefs shared memory slot */
- int slot_index; /* index into slot */
- int remaining;
-
- /*
- * Get up to this many bytes from Orangefs at a time and try
- * to fill them into the page cache at once. Tests with dd made
- * this seem like a reasonable static number, if there was
- * interest perhaps this number could be made setable through
- * sysfs...
- */
- read_size = 524288;
if (PageDirty(page))
orangefs_launder_page(page);
off = page_offset(page);
- index = off >> PAGE_SHIFT;
bv.bv_page = page;
bv.bv_len = PAGE_SIZE;
bv.bv_offset = 0;
iov_iter_bvec(&iter, READ, &bv, 1, PAGE_SIZE);
ret = wait_for_direct_io(ORANGEFS_IO_READ, inode, &off, &iter,
- read_size, inode->i_size, NULL, &buffer_index, file);
- remaining = ret;
+ PAGE_SIZE, inode->i_size, NULL, NULL, file);
/* this will only zero remaining unread portions of the page data */
iov_iter_zero(~0U, &iter);
/* takes care of potential aliasing */
flush_dcache_page(page);
if (ret < 0) {
SetPageError(page);
- unlock_page(page);
- goto out;
} else {
SetPageUptodate(page);
if (PageError(page))
@@ -297,60 +322,7 @@ static int orangefs_readpage(struct file *file, struct page *page)
}
/* unlock the page after the ->readpage() routine completes */
unlock_page(page);
-
- if (remaining > PAGE_SIZE) {
- slot_index = 0;
- while ((remaining - PAGE_SIZE) >= PAGE_SIZE) {
- remaining -= PAGE_SIZE;
- /*
- * It is an optimization to try and fill more than one
- * page... by now we've already gotten the single
- * page we were after, if stuff doesn't seem to
- * be going our way at this point just return
- * and hope for the best.
- *
- * If we look for pages and they're already there is
- * one reason to give up, and if they're not there
- * and we can't create them is another reason.
- */
-
- index++;
- slot_index++;
- next_page = find_get_page(inode->i_mapping, index);
- if (next_page) {
- gossip_debug(GOSSIP_FILE_DEBUG,
- "%s: found next page, quitting\n",
- __func__);
- put_page(next_page);
- goto out;
- }
- next_page = find_or_create_page(inode->i_mapping,
- index,
- GFP_KERNEL);
- /*
- * I've never hit this, leave it as a printk for
- * now so it will be obvious.
- */
- if (!next_page) {
- printk("%s: can't create next page, quitting\n",
- __func__);
- goto out;
- }
- kaddr = kmap_atomic(next_page);
- orangefs_bufmap_page_fill(kaddr,
- buffer_index,
- slot_index);
- kunmap_atomic(kaddr);
- SetPageUptodate(next_page);
- unlock_page(next_page);
- put_page(next_page);
- }
- }
-
-out:
- if (buffer_index != -1)
- orangefs_bufmap_put(buffer_index);
- return ret;
+ return ret;
}
static int orangefs_write_begin(struct file *file,
@@ -659,6 +631,7 @@ out:
/** ORANGEFS2 implementation of address space operations */
static const struct address_space_operations orangefs_address_operations = {
.writepage = orangefs_writepage,
+ .readahead = orangefs_readahead,
.readpage = orangefs_readpage,
.writepages = orangefs_writepages,
.set_page_dirty = __set_page_dirty_nobuffers,
@@ -954,6 +927,53 @@ int orangefs_update_time(struct inode *inode, struct timespec64 *time, int flags
return __orangefs_setattr(inode, &iattr);
}
+static int orangefs_fileattr_get(struct dentry *dentry, struct fileattr *fa)
+{
+ u64 val = 0;
+ int ret;
+
+ gossip_debug(GOSSIP_FILE_DEBUG, "%s: called on %pd\n", __func__,
+ dentry);
+
+ ret = orangefs_inode_getxattr(d_inode(dentry),
+ "user.pvfs2.meta_hint",
+ &val, sizeof(val));
+ if (ret < 0 && ret != -ENODATA)
+ return ret;
+
+ gossip_debug(GOSSIP_FILE_DEBUG, "%s: flags=%u\n", __func__, (u32) val);
+
+ fileattr_fill_flags(fa, val);
+ return 0;
+}
+
+static int orangefs_fileattr_set(struct user_namespace *mnt_userns,
+ struct dentry *dentry, struct fileattr *fa)
+{
+ u64 val = 0;
+
+ gossip_debug(GOSSIP_FILE_DEBUG, "%s: called on %pd\n", __func__,
+ dentry);
+ /*
+ * ORANGEFS_MIRROR_FL is set internally when the mirroring mode is
+ * turned on for a file. The user is not allowed to turn on this bit,
+ * but the bit is present if the user first gets the flags and then
+ * updates the flags with some new settings. So, we ignore it in the
+ * following edit. bligon.
+ */
+ if (fileattr_has_fsx(fa) ||
+ (fa->flags & ~(FS_IMMUTABLE_FL | FS_APPEND_FL | FS_NOATIME_FL | ORANGEFS_MIRROR_FL))) {
+ gossip_err("%s: only supports setting one of FS_IMMUTABLE_FL|FS_APPEND_FL|FS_NOATIME_FL\n",
+ __func__);
+ return -EOPNOTSUPP;
+ }
+ val = fa->flags;
+ gossip_debug(GOSSIP_FILE_DEBUG, "%s: flags=%u\n", __func__, (u32) val);
+ return orangefs_inode_setxattr(d_inode(dentry),
+ "user.pvfs2.meta_hint",
+ &val, sizeof(val), 0);
+}
+
/* ORANGEFS2 implementation of VFS inode operations for files */
static const struct inode_operations orangefs_file_inode_operations = {
.get_acl = orangefs_get_acl,
@@ -963,6 +983,8 @@ static const struct inode_operations orangefs_file_inode_operations = {
.listxattr = orangefs_listxattr,
.permission = orangefs_permission,
.update_time = orangefs_update_time,
+ .fileattr_get = orangefs_fileattr_get,
+ .fileattr_set = orangefs_fileattr_set,
};
static int orangefs_init_iops(struct inode *inode)
diff --git a/fs/orangefs/orangefs-mod.c b/fs/orangefs/orangefs-mod.c
index 74a3d6337ef4..cd7297815f91 100644
--- a/fs/orangefs/orangefs-mod.c
+++ b/fs/orangefs/orangefs-mod.c
@@ -31,7 +31,7 @@ static ulong module_parm_debug_mask;
__u64 orangefs_gossip_debug_mask;
int op_timeout_secs = ORANGEFS_DEFAULT_OP_TIMEOUT_SECS;
int slot_timeout_secs = ORANGEFS_DEFAULT_SLOT_TIMEOUT_SECS;
-int orangefs_cache_timeout_msecs = 50;
+int orangefs_cache_timeout_msecs = 500;
int orangefs_dcache_timeout_msecs = 50;
int orangefs_getattr_timeout_msecs = 50;
diff --git a/fs/orangefs/orangefs-utils.c b/fs/orangefs/orangefs-utils.c
index d4b7ae763186..46b7dcff18ac 100644
--- a/fs/orangefs/orangefs-utils.c
+++ b/fs/orangefs/orangefs-utils.c
@@ -221,7 +221,7 @@ static int orangefs_inode_is_stale(struct inode *inode,
* If the inode type or symlink target have changed then this
* inode is stale.
*/
- if (type == -1 || !(inode->i_mode & type)) {
+ if (type == -1 || inode_wrong_type(inode, type)) {
orangefs_make_bad_inode(inode);
return 1;
}
diff --git a/fs/overlayfs/copy_up.c b/fs/overlayfs/copy_up.c
index 0b2891c6c71e..2846b943e80c 100644
--- a/fs/overlayfs/copy_up.c
+++ b/fs/overlayfs/copy_up.c
@@ -932,7 +932,7 @@ static int ovl_copy_up_one(struct dentry *parent, struct dentry *dentry,
static int ovl_copy_up_flags(struct dentry *dentry, int flags)
{
int err = 0;
- const struct cred *old_cred = ovl_override_creds(dentry->d_sb);
+ const struct cred *old_cred;
bool disconnected = (dentry->d_flags & DCACHE_DISCONNECTED);
/*
@@ -943,6 +943,7 @@ static int ovl_copy_up_flags(struct dentry *dentry, int flags)
if (WARN_ON(disconnected && d_is_dir(dentry)))
return -EIO;
+ old_cred = ovl_override_creds(dentry->d_sb);
while (!err) {
struct dentry *next;
struct dentry *parent = NULL;
diff --git a/fs/overlayfs/dir.c b/fs/overlayfs/dir.c
index 836f14b9d3a6..93efe7048a77 100644
--- a/fs/overlayfs/dir.c
+++ b/fs/overlayfs/dir.c
@@ -1301,4 +1301,6 @@ const struct inode_operations ovl_dir_inode_operations = {
.listxattr = ovl_listxattr,
.get_acl = ovl_get_acl,
.update_time = ovl_update_time,
+ .fileattr_get = ovl_fileattr_get,
+ .fileattr_set = ovl_fileattr_set,
};
diff --git a/fs/overlayfs/file.c b/fs/overlayfs/file.c
index dbfb35fb0ff7..4d53d3b7e5fe 100644
--- a/fs/overlayfs/file.c
+++ b/fs/overlayfs/file.c
@@ -430,20 +430,11 @@ static int ovl_mmap(struct file *file, struct vm_area_struct *vma)
if (WARN_ON(file != vma->vm_file))
return -EIO;
- vma->vm_file = get_file(realfile);
+ vma_set_file(vma, realfile);
old_cred = ovl_override_creds(file_inode(file)->i_sb);
ret = call_mmap(vma->vm_file, vma);
revert_creds(old_cred);
-
- if (ret) {
- /* Drop reference count from new vm_file value */
- fput(realfile);
- } else {
- /* Drop reference count from previous vm_file value */
- fput(file);
- }
-
ovl_file_accessed(file);
return ret;
@@ -491,112 +482,6 @@ static int ovl_fadvise(struct file *file, loff_t offset, loff_t len, int advice)
return ret;
}
-static long ovl_real_ioctl(struct file *file, unsigned int cmd,
- unsigned long arg)
-{
- struct fd real;
- long ret;
-
- ret = ovl_real_fdget(file, &real);
- if (ret)
- return ret;
-
- ret = security_file_ioctl(real.file, cmd, arg);
- if (!ret) {
- /*
- * Don't override creds, since we currently can't safely check
- * permissions before doing so.
- */
- ret = vfs_ioctl(real.file, cmd, arg);
- }
-
- fdput(real);
-
- return ret;
-}
-
-static long ovl_ioctl_set_flags(struct file *file, unsigned int cmd,
- unsigned long arg)
-{
- long ret;
- struct inode *inode = file_inode(file);
-
- if (!inode_owner_or_capable(&init_user_ns, inode))
- return -EACCES;
-
- ret = mnt_want_write_file(file);
- if (ret)
- return ret;
-
- inode_lock(inode);
-
- /*
- * Prevent copy up if immutable and has no CAP_LINUX_IMMUTABLE
- * capability.
- */
- ret = -EPERM;
- if (!ovl_has_upperdata(inode) && IS_IMMUTABLE(inode) &&
- !capable(CAP_LINUX_IMMUTABLE))
- goto unlock;
-
- ret = ovl_maybe_copy_up(file_dentry(file), O_WRONLY);
- if (ret)
- goto unlock;
-
- ret = ovl_real_ioctl(file, cmd, arg);
-
- ovl_copyflags(ovl_inode_real(inode), inode);
-unlock:
- inode_unlock(inode);
-
- mnt_drop_write_file(file);
-
- return ret;
-
-}
-
-long ovl_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
-{
- long ret;
-
- switch (cmd) {
- case FS_IOC_GETFLAGS:
- case FS_IOC_FSGETXATTR:
- ret = ovl_real_ioctl(file, cmd, arg);
- break;
-
- case FS_IOC_FSSETXATTR:
- case FS_IOC_SETFLAGS:
- ret = ovl_ioctl_set_flags(file, cmd, arg);
- break;
-
- default:
- ret = -ENOTTY;
- }
-
- return ret;
-}
-
-#ifdef CONFIG_COMPAT
-long ovl_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
-{
- switch (cmd) {
- case FS_IOC32_GETFLAGS:
- cmd = FS_IOC_GETFLAGS;
- break;
-
- case FS_IOC32_SETFLAGS:
- cmd = FS_IOC_SETFLAGS;
- break;
-
- default:
- return -ENOIOCTLCMD;
- }
-
- return ovl_ioctl(file, cmd, arg);
-}
-#endif
-
enum ovl_copyop {
OVL_COPY,
OVL_CLONE,
@@ -686,6 +571,26 @@ static loff_t ovl_remap_file_range(struct file *file_in, loff_t pos_in,
remap_flags, op);
}
+static int ovl_flush(struct file *file, fl_owner_t id)
+{
+ struct fd real;
+ const struct cred *old_cred;
+ int err;
+
+ err = ovl_real_fdget(file, &real);
+ if (err)
+ return err;
+
+ if (real.file->f_op->flush) {
+ old_cred = ovl_override_creds(file_inode(file)->i_sb);
+ err = real.file->f_op->flush(real.file, id);
+ revert_creds(old_cred);
+ }
+ fdput(real);
+
+ return err;
+}
+
const struct file_operations ovl_file_operations = {
.open = ovl_open,
.release = ovl_release,
@@ -696,10 +601,7 @@ const struct file_operations ovl_file_operations = {
.mmap = ovl_mmap,
.fallocate = ovl_fallocate,
.fadvise = ovl_fadvise,
- .unlocked_ioctl = ovl_ioctl,
-#ifdef CONFIG_COMPAT
- .compat_ioctl = ovl_compat_ioctl,
-#endif
+ .flush = ovl_flush,
.splice_read = generic_file_splice_read,
.splice_write = iter_file_splice_write,
diff --git a/fs/overlayfs/inode.c b/fs/overlayfs/inode.c
index 003cf83bf78a..5e828a1c98a8 100644
--- a/fs/overlayfs/inode.c
+++ b/fs/overlayfs/inode.c
@@ -11,6 +11,8 @@
#include <linux/posix_acl.h>
#include <linux/ratelimit.h>
#include <linux/fiemap.h>
+#include <linux/fileattr.h>
+#include <linux/security.h>
#include "overlayfs.h"
@@ -95,7 +97,7 @@ out:
return err;
}
-static int ovl_map_dev_ino(struct dentry *dentry, struct kstat *stat, int fsid)
+static void ovl_map_dev_ino(struct dentry *dentry, struct kstat *stat, int fsid)
{
bool samefs = ovl_same_fs(dentry->d_sb);
unsigned int xinobits = ovl_xino_bits(dentry->d_sb);
@@ -108,21 +110,21 @@ static int ovl_map_dev_ino(struct dentry *dentry, struct kstat *stat, int fsid)
* which is friendly to du -x.
*/
stat->dev = dentry->d_sb->s_dev;
- return 0;
+ return;
} else if (xinobits) {
/*
* All inode numbers of underlying fs should not be using the
* high xinobits, so we use high xinobits to partition the
* overlay st_ino address space. The high bits holds the fsid
* (upper fsid is 0). The lowest xinobit is reserved for mapping
- * the non-peresistent inode numbers range in case of overflow.
+ * the non-persistent inode numbers range in case of overflow.
* This way all overlay inode numbers are unique and use the
* overlay st_dev.
*/
if (likely(!(stat->ino >> xinoshift))) {
stat->ino |= ((u64)fsid) << (xinoshift + 1);
stat->dev = dentry->d_sb->s_dev;
- return 0;
+ return;
} else if (ovl_xino_warn(dentry->d_sb)) {
pr_warn_ratelimited("inode number too big (%pd2, ino=%llu, xinobits=%d)\n",
dentry, stat->ino, xinobits);
@@ -151,8 +153,6 @@ static int ovl_map_dev_ino(struct dentry *dentry, struct kstat *stat, int fsid)
*/
stat->dev = OVL_FS(dentry->d_sb)->fs[fsid].pseudo_dev;
}
-
- return 0;
}
int ovl_getattr(struct user_namespace *mnt_userns, const struct path *path,
@@ -251,9 +251,7 @@ int ovl_getattr(struct user_namespace *mnt_userns, const struct path *path,
}
}
- err = ovl_map_dev_ino(dentry, stat, fsid);
- if (err)
- goto out;
+ ovl_map_dev_ino(dentry, stat, fsid);
/*
* It's probably not worth it to count subdirs to get the
@@ -408,7 +406,7 @@ static bool ovl_can_list(struct super_block *sb, const char *s)
if (ovl_is_private_xattr(sb, s))
return false;
- /* List all non-trusted xatts */
+ /* List all non-trusted xattrs */
if (strncmp(s, XATTR_TRUSTED_PREFIX, XATTR_TRUSTED_PREFIX_LEN) != 0)
return true;
@@ -500,6 +498,79 @@ static int ovl_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
return err;
}
+/*
+ * Work around the fact that security_file_ioctl() takes a file argument.
+ * Introducing security_inode_fileattr_get/set() hooks would solve this issue
+ * properly.
+ */
+static int ovl_security_fileattr(struct dentry *dentry, struct fileattr *fa,
+ bool set)
+{
+ struct path realpath;
+ struct file *file;
+ unsigned int cmd;
+ int err;
+
+ ovl_path_real(dentry, &realpath);
+ file = dentry_open(&realpath, O_RDONLY, current_cred());
+ if (IS_ERR(file))
+ return PTR_ERR(file);
+
+ if (set)
+ cmd = fa->fsx_valid ? FS_IOC_FSSETXATTR : FS_IOC_SETFLAGS;
+ else
+ cmd = fa->fsx_valid ? FS_IOC_FSGETXATTR : FS_IOC_GETFLAGS;
+
+ err = security_file_ioctl(file, cmd, 0);
+ fput(file);
+
+ return err;
+}
+
+int ovl_fileattr_set(struct user_namespace *mnt_userns,
+ struct dentry *dentry, struct fileattr *fa)
+{
+ struct inode *inode = d_inode(dentry);
+ struct dentry *upperdentry;
+ const struct cred *old_cred;
+ int err;
+
+ err = ovl_want_write(dentry);
+ if (err)
+ goto out;
+
+ err = ovl_copy_up(dentry);
+ if (!err) {
+ upperdentry = ovl_dentry_upper(dentry);
+
+ old_cred = ovl_override_creds(inode->i_sb);
+ err = ovl_security_fileattr(dentry, fa, true);
+ if (!err)
+ err = vfs_fileattr_set(&init_user_ns, upperdentry, fa);
+ revert_creds(old_cred);
+ ovl_copyflags(ovl_inode_real(inode), inode);
+ }
+ ovl_drop_write(dentry);
+out:
+ return err;
+}
+
+int ovl_fileattr_get(struct dentry *dentry, struct fileattr *fa)
+{
+ struct inode *inode = d_inode(dentry);
+ struct dentry *realdentry = ovl_dentry_real(dentry);
+ const struct cred *old_cred;
+ int err;
+
+ old_cred = ovl_override_creds(inode->i_sb);
+ err = ovl_security_fileattr(dentry, fa, false);
+ if (!err)
+ err = vfs_fileattr_get(realdentry, fa);
+ revert_creds(old_cred);
+
+ return err;
+}
+
static const struct inode_operations ovl_file_inode_operations = {
.setattr = ovl_setattr,
.permission = ovl_permission,
@@ -508,6 +579,8 @@ static const struct inode_operations ovl_file_inode_operations = {
.get_acl = ovl_get_acl,
.update_time = ovl_update_time,
.fiemap = ovl_fiemap,
+ .fileattr_get = ovl_fileattr_get,
+ .fileattr_set = ovl_fileattr_set,
};
static const struct inode_operations ovl_symlink_inode_operations = {
@@ -538,7 +611,7 @@ static const struct address_space_operations ovl_aops = {
* stackable i_mutex locks according to stack level of the super
* block instance. An overlayfs instance can never be in stack
* depth 0 (there is always a real fs below it). An overlayfs
- * inode lock will use the lockdep annotaion ovl_i_mutex_key[depth].
+ * inode lock will use the lockdep annotation ovl_i_mutex_key[depth].
*
* For example, here is a snip from /proc/lockdep_chains after
* dir_iterate of nested overlayfs:
diff --git a/fs/overlayfs/namei.c b/fs/overlayfs/namei.c
index 3fe05fb5d145..210cd6f66e28 100644
--- a/fs/overlayfs/namei.c
+++ b/fs/overlayfs/namei.c
@@ -371,7 +371,7 @@ int ovl_check_origin_fh(struct ovl_fs *ofs, struct ovl_fh *fh, bool connected,
return PTR_ERR(origin);
if (upperdentry && !ovl_is_whiteout(upperdentry) &&
- ((d_inode(origin)->i_mode ^ d_inode(upperdentry)->i_mode) & S_IFMT))
+ inode_wrong_type(d_inode(upperdentry), d_inode(origin)->i_mode))
goto invalid;
if (!*stackp)
@@ -730,7 +730,7 @@ struct dentry *ovl_lookup_index(struct ovl_fs *ofs, struct dentry *upper,
index = ERR_PTR(-ESTALE);
goto out;
} else if (ovl_dentry_weird(index) || ovl_is_whiteout(index) ||
- ((inode->i_mode ^ d_inode(origin)->i_mode) & S_IFMT)) {
+ inode_wrong_type(inode, d_inode(origin)->i_mode)) {
/*
* Index should always be of the same file type as origin
* except for the case of a whiteout index. A whiteout
@@ -919,6 +919,7 @@ struct dentry *ovl_lookup(struct inode *dir, struct dentry *dentry,
continue;
if ((uppermetacopy || d.metacopy) && !ofs->config.metacopy) {
+ dput(this);
err = -EPERM;
pr_warn_ratelimited("refusing to follow metacopy origin for (%pd2)\n", dentry);
goto out_put;
diff --git a/fs/overlayfs/overlayfs.h b/fs/overlayfs/overlayfs.h
index 95cff83786a5..6ec73db4bf9e 100644
--- a/fs/overlayfs/overlayfs.h
+++ b/fs/overlayfs/overlayfs.h
@@ -186,7 +186,12 @@ static inline ssize_t ovl_do_getxattr(struct ovl_fs *ofs, struct dentry *dentry,
size_t size)
{
const char *name = ovl_xattr(ofs, ox);
- return vfs_getxattr(&init_user_ns, dentry, name, value, size);
+ int err = vfs_getxattr(&init_user_ns, dentry, name, value, size);
+ int len = (value && err > 0) ? err : 0;
+
+ pr_debug("getxattr(%pd2, \"%s\", \"%*pE\", %zu, 0) = %i\n",
+ dentry, name, min(len, 48), value, size, err);
+ return err;
}
static inline int ovl_do_setxattr(struct ovl_fs *ofs, struct dentry *dentry,
@@ -319,9 +324,6 @@ int ovl_check_setxattr(struct dentry *dentry, struct dentry *upperdentry,
enum ovl_xattr ox, const void *value, size_t size,
int xerr);
int ovl_set_impure(struct dentry *dentry, struct dentry *upperdentry);
-void ovl_set_flag(unsigned long flag, struct inode *inode);
-void ovl_clear_flag(unsigned long flag, struct inode *inode);
-bool ovl_test_flag(unsigned long flag, struct inode *inode);
bool ovl_inuse_trylock(struct dentry *dentry);
void ovl_inuse_unlock(struct dentry *dentry);
bool ovl_is_inuse(struct dentry *dentry);
@@ -335,6 +337,21 @@ char *ovl_get_redirect_xattr(struct ovl_fs *ofs, struct dentry *dentry,
int padding);
int ovl_sync_status(struct ovl_fs *ofs);
+static inline void ovl_set_flag(unsigned long flag, struct inode *inode)
+{
+ set_bit(flag, &OVL_I(inode)->flags);
+}
+
+static inline void ovl_clear_flag(unsigned long flag, struct inode *inode)
+{
+ clear_bit(flag, &OVL_I(inode)->flags);
+}
+
+static inline bool ovl_test_flag(unsigned long flag, struct inode *inode)
+{
+ return test_bit(flag, &OVL_I(inode)->flags);
+}
+
static inline bool ovl_is_impuredir(struct super_block *sb,
struct dentry *dentry)
{
@@ -439,6 +456,18 @@ int ovl_workdir_cleanup(struct inode *dir, struct vfsmount *mnt,
struct dentry *dentry, int level);
int ovl_indexdir_cleanup(struct ovl_fs *ofs);
+/*
+ * Can we iterate real dir directly?
+ *
+ * Non-merge dir may contain whiteouts from a time it was a merge upper, before
+ * lower dir was removed under it and possibly before it was rotated from upper
+ * to lower layer.
+ */
+static inline bool ovl_dir_is_real(struct dentry *dir)
+{
+ return !ovl_test_flag(OVL_WHITEOUTS, d_inode(dir));
+}
+
/* inode.c */
int ovl_set_nlink_upper(struct dentry *dentry);
int ovl_set_nlink_lower(struct dentry *dentry);
@@ -519,8 +548,9 @@ struct dentry *ovl_create_temp(struct dentry *workdir, struct ovl_cattr *attr);
extern const struct file_operations ovl_file_operations;
int __init ovl_aio_request_cache_init(void);
void ovl_aio_request_cache_destroy(void);
-long ovl_ioctl(struct file *file, unsigned int cmd, unsigned long arg);
-long ovl_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg);
+int ovl_fileattr_get(struct dentry *dentry, struct fileattr *fa);
+int ovl_fileattr_set(struct user_namespace *mnt_userns,
+ struct dentry *dentry, struct fileattr *fa);
/* copy_up.c */
int ovl_copy_up(struct dentry *dentry);
diff --git a/fs/overlayfs/readdir.c b/fs/overlayfs/readdir.c
index f404a78e6b60..e8ad2c2c77dd 100644
--- a/fs/overlayfs/readdir.c
+++ b/fs/overlayfs/readdir.c
@@ -319,18 +319,6 @@ static inline int ovl_dir_read(struct path *realpath,
return err;
}
-/*
- * Can we iterate real dir directly?
- *
- * Non-merge dir may contain whiteouts from a time it was a merge upper, before
- * lower dir was removed under it and possibly before it was rotated from upper
- * to lower layer.
- */
-static bool ovl_dir_is_real(struct dentry *dir)
-{
- return !ovl_test_flag(OVL_WHITEOUTS, d_inode(dir));
-}
-
static void ovl_dir_reset(struct file *file)
{
struct ovl_dir_file *od = file->private_data;
@@ -963,10 +951,6 @@ const struct file_operations ovl_dir_operations = {
.llseek = ovl_dir_llseek,
.fsync = ovl_dir_fsync,
.release = ovl_dir_release,
- .unlocked_ioctl = ovl_ioctl,
-#ifdef CONFIG_COMPAT
- .compat_ioctl = ovl_compat_ioctl,
-#endif
};
int ovl_check_empty_dir(struct dentry *dentry, struct list_head *list)
diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c
index fdd72f1a9c5e..b01d4147520d 100644
--- a/fs/overlayfs/super.c
+++ b/fs/overlayfs/super.c
@@ -380,6 +380,8 @@ static int ovl_show_options(struct seq_file *m, struct dentry *dentry)
ofs->config.metacopy ? "on" : "off");
if (ofs->config.ovl_volatile)
seq_puts(m, ",volatile");
+ if (ofs->config.userxattr)
+ seq_puts(m, ",userxattr");
return 0;
}
@@ -945,6 +947,16 @@ static int ovl_lower_dir(const char *name, struct path *path,
pr_warn("fs on '%s' does not support file handles, falling back to index=off,nfs_export=off.\n",
name);
}
+ /*
+ * Decoding origin file handle is required for persistent st_ino.
+ * Without persistent st_ino, xino=auto falls back to xino=off.
+ */
+ if (ofs->config.xino == OVL_XINO_AUTO &&
+ ofs->config.upperdir && !fh_type) {
+ ofs->config.xino = OVL_XINO_OFF;
+ pr_warn("fs on '%s' does not support file handles, falling back to xino=off.\n",
+ name);
+ }
/* Check if lower fs has 32bit inode numbers */
if (fh_type != FILEID_INO32_GEN)
@@ -1042,9 +1054,6 @@ ovl_posix_acl_xattr_set(const struct xattr_handler *handler,
}
err = ovl_xattr_set(dentry, inode, handler->name, value, size, flags);
- if (!err)
- ovl_copyattr(ovl_inode_real(inode), inode);
-
return err;
out_acl_release:
@@ -1185,8 +1194,8 @@ static int ovl_get_upper(struct super_block *sb, struct ovl_fs *ofs,
if (err)
goto out;
- /* Upper fs should not be r/o */
- if (sb_rdonly(upperpath->mnt->mnt_sb)) {
+ /* Upperdir path should not be r/o */
+ if (__mnt_is_readonly(upperpath->mnt)) {
pr_err("upper fs is r/o, try multi-lower layers mount\n");
err = -EINVAL;
goto out;
@@ -1401,9 +1410,19 @@ static int ovl_make_workdir(struct super_block *sb, struct ovl_fs *ofs,
err = ovl_do_setxattr(ofs, ofs->workdir, OVL_XATTR_OPAQUE, "0", 1);
if (err) {
ofs->noxattr = true;
- ofs->config.index = false;
- ofs->config.metacopy = false;
- pr_warn("upper fs does not support xattr, falling back to index=off and metacopy=off.\n");
+ if (ofs->config.index || ofs->config.metacopy) {
+ ofs->config.index = false;
+ ofs->config.metacopy = false;
+ pr_warn("upper fs does not support xattr, falling back to index=off,metacopy=off.\n");
+ }
+ /*
+ * xattr support is required for persistent st_ino.
+ * Without persistent st_ino, xino=auto falls back to xino=off.
+ */
+ if (ofs->config.xino == OVL_XINO_AUTO) {
+ ofs->config.xino = OVL_XINO_OFF;
+ pr_warn("upper fs does not support xattr, falling back to xino=off.\n");
+ }
err = 0;
} else {
ovl_do_removexattr(ofs, ofs->workdir, OVL_XATTR_OPAQUE);
@@ -1580,7 +1599,8 @@ static bool ovl_lower_uuid_ok(struct ovl_fs *ofs, const uuid_t *uuid)
* user opted-in to one of the new features that require following the
* lower inode of non-dir upper.
*/
- if (!ofs->config.index && !ofs->config.metacopy && !ofs->config.xino &&
+ if (!ofs->config.index && !ofs->config.metacopy &&
+ ofs->config.xino != OVL_XINO_ON &&
uuid_is_null(uuid))
return false;
@@ -1609,6 +1629,7 @@ static int ovl_get_fsid(struct ovl_fs *ofs, const struct path *path)
dev_t dev;
int err;
bool bad_uuid = false;
+ bool warn = false;
for (i = 0; i < ofs->numfs; i++) {
if (ofs->fs[i].sb == sb)
@@ -1617,13 +1638,20 @@ static int ovl_get_fsid(struct ovl_fs *ofs, const struct path *path)
if (!ovl_lower_uuid_ok(ofs, &sb->s_uuid)) {
bad_uuid = true;
+ if (ofs->config.xino == OVL_XINO_AUTO) {
+ ofs->config.xino = OVL_XINO_OFF;
+ warn = true;
+ }
if (ofs->config.index || ofs->config.nfs_export) {
ofs->config.index = false;
ofs->config.nfs_export = false;
- pr_warn("%s uuid detected in lower fs '%pd2', falling back to index=off,nfs_export=off.\n",
+ warn = true;
+ }
+ if (warn) {
+ pr_warn("%s uuid detected in lower fs '%pd2', falling back to xino=%s,index=off,nfs_export=off.\n",
uuid_is_null(&sb->s_uuid) ? "null" :
"conflicting",
- path->dentry);
+ path->dentry, ovl_xino_str[ofs->config.xino]);
}
}
@@ -1826,7 +1854,8 @@ out_err:
* - upper/work dir of any overlayfs instance
*/
static int ovl_check_layer(struct super_block *sb, struct ovl_fs *ofs,
- struct dentry *dentry, const char *name)
+ struct dentry *dentry, const char *name,
+ bool is_lower)
{
struct dentry *next = dentry, *parent;
int err = 0;
@@ -1838,7 +1867,7 @@ static int ovl_check_layer(struct super_block *sb, struct ovl_fs *ofs,
/* Walk back ancestors to root (inclusive) looking for traps */
while (!err && parent != next) {
- if (ovl_lookup_trap_inode(sb, parent)) {
+ if (is_lower && ovl_lookup_trap_inode(sb, parent)) {
err = -ELOOP;
pr_err("overlapping %s path\n", name);
} else if (ovl_is_inuse(parent)) {
@@ -1864,7 +1893,7 @@ static int ovl_check_overlapping_layers(struct super_block *sb,
if (ovl_upper_mnt(ofs)) {
err = ovl_check_layer(sb, ofs, ovl_upper_mnt(ofs)->mnt_root,
- "upperdir");
+ "upperdir", false);
if (err)
return err;
@@ -1875,7 +1904,8 @@ static int ovl_check_overlapping_layers(struct super_block *sb,
* workbasedir. In that case, we already have their traps in
* inode cache and we will catch that case on lookup.
*/
- err = ovl_check_layer(sb, ofs, ofs->workbasedir, "workdir");
+ err = ovl_check_layer(sb, ofs, ofs->workbasedir, "workdir",
+ false);
if (err)
return err;
}
@@ -1883,7 +1913,7 @@ static int ovl_check_overlapping_layers(struct super_block *sb,
for (i = 1; i < ofs->numlayer; i++) {
err = ovl_check_layer(sb, ofs,
ofs->layers[i].mnt->mnt_root,
- "lowerdir");
+ "lowerdir", true);
if (err)
return err;
}
@@ -1952,6 +1982,7 @@ static int ovl_fill_super(struct super_block *sb, void *data, int silent)
if (!ofs)
goto out;
+ err = -ENOMEM;
ofs->creator_cred = cred = prepare_creds();
if (!cred)
goto out_err;
@@ -1980,6 +2011,7 @@ static int ovl_fill_super(struct super_block *sb, void *data, int silent)
if (!splitlower)
goto out_err;
+ err = -EINVAL;
numlower = ovl_split_lowerdirs(splitlower);
if (numlower > OVL_MAX_STACK) {
pr_err("too many lower directories, limit is %d\n",
@@ -1987,6 +2019,7 @@ static int ovl_fill_super(struct super_block *sb, void *data, int silent)
goto out_err;
}
+ err = -ENOMEM;
layers = kcalloc(numlower + 1, sizeof(struct ovl_layer), GFP_KERNEL);
if (!layers)
goto out_err;
@@ -2013,6 +2046,7 @@ static int ovl_fill_super(struct super_block *sb, void *data, int silent)
if (ofs->config.upperdir) {
struct super_block *upper_sb;
+ err = -EINVAL;
if (!ofs->config.workdir) {
pr_err("missing 'workdir'\n");
goto out_err;
diff --git a/fs/overlayfs/util.c b/fs/overlayfs/util.c
index 7f5a01a11f97..b9d03627f364 100644
--- a/fs/overlayfs/util.c
+++ b/fs/overlayfs/util.c
@@ -214,7 +214,7 @@ const struct ovl_layer *ovl_layer_lower(struct dentry *dentry)
/*
* ovl_dentry_lower() could return either a data dentry or metacopy dentry
- * dependig on what is stored in lowerstack[0]. At times we need to find
+ * depending on what is stored in lowerstack[0]. At times we need to find
* lower dentry which has data (and not metacopy dentry). This helper
* returns the lower data dentry.
*/
@@ -422,18 +422,20 @@ void ovl_inode_update(struct inode *inode, struct dentry *upperdentry)
}
}
-static void ovl_dentry_version_inc(struct dentry *dentry, bool impurity)
+static void ovl_dir_version_inc(struct dentry *dentry, bool impurity)
{
struct inode *inode = d_inode(dentry);
WARN_ON(!inode_is_locked(inode));
+ WARN_ON(!d_is_dir(dentry));
/*
- * Version is used by readdir code to keep cache consistent. For merge
- * dirs all changes need to be noted. For non-merge dirs, cache only
- * contains impure (ones which have been copied up and have origins)
- * entries, so only need to note changes to impure entries.
+ * Version is used by readdir code to keep cache consistent.
+ * For merge dirs (or dirs with origin) all changes need to be noted.
+ * For non-merge dirs, cache contains only impure entries (i.e. ones
+ * which have been copied up and have origins), so only need to note
+ * changes to impure entries.
*/
- if (OVL_TYPE_MERGE(ovl_path_type(dentry)) || impurity)
+ if (!ovl_dir_is_real(dentry) || impurity)
OVL_I(inode)->version++;
}
@@ -442,7 +444,7 @@ void ovl_dir_modified(struct dentry *dentry, bool impurity)
/* Copy mtime/ctime */
ovl_copyattr(d_inode(ovl_dentry_upper(dentry)), d_inode(dentry));
- ovl_dentry_version_inc(dentry, impurity);
+ ovl_dir_version_inc(dentry, impurity);
}
u64 ovl_dentry_version_get(struct dentry *dentry)
@@ -638,21 +640,6 @@ int ovl_set_impure(struct dentry *dentry, struct dentry *upperdentry)
return err;
}
-void ovl_set_flag(unsigned long flag, struct inode *inode)
-{
- set_bit(flag, &OVL_I(inode)->flags);
-}
-
-void ovl_clear_flag(unsigned long flag, struct inode *inode)
-{
- clear_bit(flag, &OVL_I(inode)->flags);
-}
-
-bool ovl_test_flag(unsigned long flag, struct inode *inode)
-{
- return test_bit(flag, &OVL_I(inode)->flags);
-}
-
/**
* Caller must hold a reference to inode to prevent it from being freed while
* it is marked inuse.
diff --git a/fs/proc/array.c b/fs/proc/array.c
index bb87e4d89cd8..7ec59171f197 100644
--- a/fs/proc/array.c
+++ b/fs/proc/array.c
@@ -342,9 +342,11 @@ static inline void task_seccomp(struct seq_file *m, struct task_struct *p)
seq_put_decimal_ull(m, "NoNewPrivs:\t", task_no_new_privs(p));
#ifdef CONFIG_SECCOMP
seq_put_decimal_ull(m, "\nSeccomp:\t", p->seccomp.mode);
+#ifdef CONFIG_SECCOMP_FILTER
seq_put_decimal_ull(m, "\nSeccomp_filters:\t",
atomic_read(&p->seccomp.filter_count));
#endif
+#endif
seq_puts(m, "\nSpeculation_Store_Bypass:\t");
switch (arch_prctl_spec_ctrl_get(p, PR_SPEC_STORE_BYPASS)) {
case -EINVAL:
diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c
index 984e42f8cb11..66c7dd11bd7c 100644
--- a/fs/proc/proc_sysctl.c
+++ b/fs/proc/proc_sysctl.c
@@ -94,14 +94,9 @@ static void sysctl_print_dir(struct ctl_dir *dir)
static int namecmp(const char *name1, int len1, const char *name2, int len2)
{
- int minlen;
int cmp;
- minlen = len1;
- if (minlen > len2)
- minlen = len2;
-
- cmp = memcmp(name1, name2, minlen);
+ cmp = memcmp(name1, name2, min(len1, len2));
if (cmp == 0)
cmp = len1 - len2;
return cmp;
@@ -1108,6 +1103,11 @@ static int sysctl_check_table_array(const char *path, struct ctl_table *table)
err |= sysctl_err(path, table, "array not allowed");
}
+ if (table->proc_handler == proc_dou8vec_minmax) {
+ if (table->maxlen != sizeof(u8))
+ err |= sysctl_err(path, table, "array not allowed");
+ }
+
return err;
}
@@ -1123,6 +1123,7 @@ static int sysctl_check_table(const char *path, struct ctl_table *table)
(table->proc_handler == proc_douintvec) ||
(table->proc_handler == proc_douintvec_minmax) ||
(table->proc_handler == proc_dointvec_minmax) ||
+ (table->proc_handler == proc_dou8vec_minmax) ||
(table->proc_handler == proc_dointvec_jiffies) ||
(table->proc_handler == proc_dointvec_userhz_jiffies) ||
(table->proc_handler == proc_dointvec_ms_jiffies) ||
diff --git a/fs/pstore/platform.c b/fs/pstore/platform.c
index d963ae7902f9..b9614db48b1d 100644
--- a/fs/pstore/platform.c
+++ b/fs/pstore/platform.c
@@ -385,6 +385,7 @@ void pstore_record_init(struct pstore_record *record,
static void pstore_dump(struct kmsg_dumper *dumper,
enum kmsg_dump_reason reason)
{
+ struct kmsg_dump_iter iter;
unsigned long total = 0;
const char *why;
unsigned int part = 1;
@@ -405,6 +406,8 @@ static void pstore_dump(struct kmsg_dumper *dumper,
}
}
+ kmsg_dump_rewind(&iter);
+
oopscount++;
while (total < kmsg_bytes) {
char *dst;
@@ -435,7 +438,7 @@ static void pstore_dump(struct kmsg_dumper *dumper,
dst_size -= header_size;
/* Write dump contents. */
- if (!kmsg_dump_get_buffer(dumper, true, dst + header_size,
+ if (!kmsg_dump_get_buffer(&iter, true, dst + header_size,
dst_size, &dump_size))
break;
diff --git a/fs/pstore/ram.c b/fs/pstore/ram.c
index ca6d8a867285..fefe3d391d3a 100644
--- a/fs/pstore/ram.c
+++ b/fs/pstore/ram.c
@@ -56,7 +56,7 @@ MODULE_PARM_DESC(mem_size,
static unsigned int mem_type;
module_param(mem_type, uint, 0400);
MODULE_PARM_DESC(mem_type,
- "set to 1 to try to use unbuffered memory (default 0)");
+ "memory type: 0=write-combined (default), 1=unbuffered, 2=cached");
static int ramoops_max_reason = -1;
module_param_named(max_reason, ramoops_max_reason, int, 0400);
@@ -648,6 +648,10 @@ static int ramoops_parse_dt(struct platform_device *pdev,
pdata->mem_size = resource_size(res);
pdata->mem_address = res->start;
+ /*
+ * Setting "unbuffered" is deprecated and will be ignored if
+ * "mem_type" is also specified.
+ */
pdata->mem_type = of_property_read_bool(of_node, "unbuffered");
/*
* Setting "no-dump-oops" is deprecated and will be ignored if
@@ -666,6 +670,7 @@ static int ramoops_parse_dt(struct platform_device *pdev,
field = value; \
}
+ parse_u32("mem-type", pdata->record_size, pdata->mem_type);
parse_u32("record-size", pdata->record_size, 0);
parse_u32("console-size", pdata->console_size, 0);
parse_u32("ftrace-size", pdata->ftrace_size, 0);
diff --git a/fs/pstore/ram_core.c b/fs/pstore/ram_core.c
index fff363bfd484..fe5305028c6e 100644
--- a/fs/pstore/ram_core.c
+++ b/fs/pstore/ram_core.c
@@ -396,6 +396,10 @@ void persistent_ram_zap(struct persistent_ram_zone *prz)
persistent_ram_update_header_ecc(prz);
}
+#define MEM_TYPE_WCOMBINE 0
+#define MEM_TYPE_NONCACHED 1
+#define MEM_TYPE_NORMAL 2
+
static void *persistent_ram_vmap(phys_addr_t start, size_t size,
unsigned int memtype)
{
@@ -409,10 +413,20 @@ static void *persistent_ram_vmap(phys_addr_t start, size_t size,
page_start = start - offset_in_page(start);
page_count = DIV_ROUND_UP(size + offset_in_page(start), PAGE_SIZE);
- if (memtype)
+ switch (memtype) {
+ case MEM_TYPE_NORMAL:
+ prot = PAGE_KERNEL;
+ break;
+ case MEM_TYPE_NONCACHED:
prot = pgprot_noncached(PAGE_KERNEL);
- else
+ break;
+ case MEM_TYPE_WCOMBINE:
prot = pgprot_writecombine(PAGE_KERNEL);
+ break;
+ default:
+ pr_err("invalid mem_type=%d\n", memtype);
+ return NULL;
+ }
pages = kmalloc_array(page_count, sizeof(struct page *), GFP_KERNEL);
if (!pages) {
diff --git a/fs/quota/quota.c b/fs/quota/quota.c
index 6d16b2be5ac4..05e4bd9ab6d6 100644
--- a/fs/quota/quota.c
+++ b/fs/quota/quota.c
@@ -17,6 +17,7 @@
#include <linux/capability.h>
#include <linux/quotaops.h>
#include <linux/types.h>
+#include <linux/mount.h>
#include <linux/writeback.h>
#include <linux/nospec.h>
#include "compat.h"
@@ -471,6 +472,7 @@ static int quota_getstatev(struct super_block *sb, int type,
fqs->qs_rtbtimelimit = state.s_state[type].rt_spc_timelimit;
fqs->qs_bwarnlimit = state.s_state[type].spc_warnlimit;
fqs->qs_iwarnlimit = state.s_state[type].ino_warnlimit;
+ fqs->qs_rtbwarnlimit = state.s_state[type].rt_spc_warnlimit;
/* Inodes may be allocated even if inactive; copy out if present */
if (state.s_state[USRQUOTA].ino) {
@@ -827,8 +829,6 @@ static int do_quotactl(struct super_block *sb, int type, int cmd, qid_t id,
}
}
-#ifdef CONFIG_BLOCK
-
/* Return 1 if 'cmd' will block on frozen filesystem */
static int quotactl_cmd_write(int cmd)
{
@@ -850,7 +850,6 @@ static int quotactl_cmd_write(int cmd)
}
return 1;
}
-#endif /* CONFIG_BLOCK */
/* Return true if quotactl command is manipulating quota on/off state */
static bool quotactl_cmd_onoff(int cmd)
@@ -968,3 +967,48 @@ out:
path_put(pathp);
return ret;
}
+
+SYSCALL_DEFINE4(quotactl_path, unsigned int, cmd, const char __user *,
+ mountpoint, qid_t, id, void __user *, addr)
+{
+ struct super_block *sb;
+ struct path mountpath;
+ unsigned int cmds = cmd >> SUBCMDSHIFT;
+ unsigned int type = cmd & SUBCMDMASK;
+ int ret;
+
+ if (type >= MAXQUOTAS)
+ return -EINVAL;
+
+ ret = user_path_at(AT_FDCWD, mountpoint,
+ LOOKUP_FOLLOW | LOOKUP_AUTOMOUNT, &mountpath);
+ if (ret)
+ return ret;
+
+ sb = mountpath.mnt->mnt_sb;
+
+ if (quotactl_cmd_write(cmds)) {
+ ret = mnt_want_write(mountpath.mnt);
+ if (ret)
+ goto out;
+ }
+
+ if (quotactl_cmd_onoff(cmds))
+ down_write(&sb->s_umount);
+ else
+ down_read(&sb->s_umount);
+
+ ret = do_quotactl(sb, type, cmds, id, addr, ERR_PTR(-EINVAL));
+
+ if (quotactl_cmd_onoff(cmds))
+ up_write(&sb->s_umount);
+ else
+ up_read(&sb->s_umount);
+
+ if (quotactl_cmd_write(cmds))
+ mnt_drop_write(mountpath.mnt);
+out:
+ path_put(&mountpath);
+
+ return ret;
+}
diff --git a/fs/readdir.c b/fs/readdir.c
index 19434b3c982c..09e8ed7d4161 100644
--- a/fs/readdir.c
+++ b/fs/readdir.c
@@ -150,6 +150,9 @@ static int fillonedir(struct dir_context *ctx, const char *name, int namlen,
if (buf->result)
return -EINVAL;
+ buf->result = verify_dirent_name(name, namlen);
+ if (buf->result < 0)
+ return buf->result;
d_ino = ino;
if (sizeof(d_ino) < sizeof(ino) && d_ino != ino) {
buf->result = -EOVERFLOW;
@@ -405,6 +408,9 @@ static int compat_fillonedir(struct dir_context *ctx, const char *name,
if (buf->result)
return -EINVAL;
+ buf->result = verify_dirent_name(name, namlen);
+ if (buf->result < 0)
+ return buf->result;
d_ino = ino;
if (sizeof(d_ino) < sizeof(ino) && d_ino != ino) {
buf->result = -EOVERFLOW;
diff --git a/fs/reiserfs/file.c b/fs/reiserfs/file.c
index 1db0254bc38b..203a47232707 100644
--- a/fs/reiserfs/file.c
+++ b/fs/reiserfs/file.c
@@ -258,4 +258,6 @@ const struct inode_operations reiserfs_file_inode_operations = {
.permission = reiserfs_permission,
.get_acl = reiserfs_get_acl,
.set_acl = reiserfs_set_acl,
+ .fileattr_get = reiserfs_fileattr_get,
+ .fileattr_set = reiserfs_fileattr_set,
};
diff --git a/fs/reiserfs/ioctl.c b/fs/reiserfs/ioctl.c
index 4f1cbd930179..4b86ecf5817e 100644
--- a/fs/reiserfs/ioctl.c
+++ b/fs/reiserfs/ioctl.c
@@ -10,6 +10,59 @@
#include <linux/uaccess.h>
#include <linux/pagemap.h>
#include <linux/compat.h>
+#include <linux/fileattr.h>
+
+int reiserfs_fileattr_get(struct dentry *dentry, struct fileattr *fa)
+{
+ struct inode *inode = d_inode(dentry);
+
+ if (!reiserfs_attrs(inode->i_sb))
+ return -ENOTTY;
+
+ fileattr_fill_flags(fa, REISERFS_I(inode)->i_attrs);
+
+ return 0;
+}
+
+int reiserfs_fileattr_set(struct user_namespace *mnt_userns,
+ struct dentry *dentry, struct fileattr *fa)
+{
+ struct inode *inode = d_inode(dentry);
+ unsigned int flags = fa->flags;
+ int err;
+
+ reiserfs_write_lock(inode->i_sb);
+
+ err = -ENOTTY;
+ if (!reiserfs_attrs(inode->i_sb))
+ goto unlock;
+
+ err = -EOPNOTSUPP;
+ if (fileattr_has_fsx(fa))
+ goto unlock;
+
+ /*
+ * Is it quota file? Do not allow user to mess with it
+ */
+ err = -EPERM;
+ if (IS_NOQUOTA(inode))
+ goto unlock;
+
+ if ((flags & REISERFS_NOTAIL_FL) && S_ISREG(inode->i_mode)) {
+ err = reiserfs_unpack(inode);
+ if (err)
+ goto unlock;
+ }
+ sd_attrs_to_i_attrs(flags, inode);
+ REISERFS_I(inode)->i_attrs = flags;
+ inode->i_ctime = current_time(inode);
+ mark_inode_dirty(inode);
+ err = 0;
+unlock:
+ reiserfs_write_unlock(inode->i_sb);
+
+ return err;
+}
/*
* reiserfs_ioctl - handler for ioctl for inode
@@ -23,7 +76,6 @@
long reiserfs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
{
struct inode *inode = file_inode(filp);
- unsigned int flags;
int err = 0;
reiserfs_write_lock(inode->i_sb);
@@ -32,7 +84,7 @@ long reiserfs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
case REISERFS_IOC_UNPACK:
if (S_ISREG(inode->i_mode)) {
if (arg)
- err = reiserfs_unpack(inode, filp);
+ err = reiserfs_unpack(inode);
} else
err = -ENOTTY;
break;
@@ -40,63 +92,6 @@ long reiserfs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
* following two cases are taken from fs/ext2/ioctl.c by Remy
* Card (card@masi.ibp.fr)
*/
- case REISERFS_IOC_GETFLAGS:
- if (!reiserfs_attrs(inode->i_sb)) {
- err = -ENOTTY;
- break;
- }
-
- flags = REISERFS_I(inode)->i_attrs;
- err = put_user(flags, (int __user *)arg);
- break;
- case REISERFS_IOC_SETFLAGS:{
- if (!reiserfs_attrs(inode->i_sb)) {
- err = -ENOTTY;
- break;
- }
-
- err = mnt_want_write_file(filp);
- if (err)
- break;
-
- if (!inode_owner_or_capable(&init_user_ns, inode)) {
- err = -EPERM;
- goto setflags_out;
- }
- if (get_user(flags, (int __user *)arg)) {
- err = -EFAULT;
- goto setflags_out;
- }
- /*
- * Is it quota file? Do not allow user to mess with it
- */
- if (IS_NOQUOTA(inode)) {
- err = -EPERM;
- goto setflags_out;
- }
- err = vfs_ioc_setflags_prepare(inode,
- REISERFS_I(inode)->i_attrs,
- flags);
- if (err)
- goto setflags_out;
- if ((flags & REISERFS_NOTAIL_FL) &&
- S_ISREG(inode->i_mode)) {
- int result;
-
- result = reiserfs_unpack(inode, filp);
- if (result) {
- err = result;
- goto setflags_out;
- }
- }
- sd_attrs_to_i_attrs(flags, inode);
- REISERFS_I(inode)->i_attrs = flags;
- inode->i_ctime = current_time(inode);
- mark_inode_dirty(inode);
-setflags_out:
- mnt_drop_write_file(filp);
- break;
- }
case REISERFS_IOC_GETVERSION:
err = put_user(inode->i_generation, (int __user *)arg);
break;
@@ -138,12 +133,6 @@ long reiserfs_compat_ioctl(struct file *file, unsigned int cmd,
case REISERFS_IOC32_UNPACK:
cmd = REISERFS_IOC_UNPACK;
break;
- case REISERFS_IOC32_GETFLAGS:
- cmd = REISERFS_IOC_GETFLAGS;
- break;
- case REISERFS_IOC32_SETFLAGS:
- cmd = REISERFS_IOC_SETFLAGS;
- break;
case REISERFS_IOC32_GETVERSION:
cmd = REISERFS_IOC_GETVERSION;
break;
@@ -165,7 +154,7 @@ int reiserfs_commit_write(struct file *f, struct page *page,
* Function try to convert tail from direct item into indirect.
* It set up nopack attribute in the REISERFS_I(inode)->nopack
*/
-int reiserfs_unpack(struct inode *inode, struct file *filp)
+int reiserfs_unpack(struct inode *inode)
{
int retval = 0;
int index;
diff --git a/fs/reiserfs/journal.c b/fs/reiserfs/journal.c
index e98f99338f8f..9edc8e2b154e 100644
--- a/fs/reiserfs/journal.c
+++ b/fs/reiserfs/journal.c
@@ -461,7 +461,6 @@ int reiserfs_in_journal(struct super_block *sb,
b_blocknr_t * next_zero_bit)
{
struct reiserfs_journal *journal = SB_JOURNAL(sb);
- struct reiserfs_journal_cnode *cn;
struct reiserfs_list_bitmap *jb;
int i;
unsigned long bl;
@@ -497,13 +496,12 @@ int reiserfs_in_journal(struct super_block *sb,
bl = bmap_nr * (sb->s_blocksize << 3) + bit_nr;
/* is it in any old transactions? */
if (search_all
- && (cn =
- get_journal_hash_dev(sb, journal->j_list_hash_table, bl))) {
+ && (get_journal_hash_dev(sb, journal->j_list_hash_table, bl))) {
return 1;
}
/* is it in the current transaction. This should never happen */
- if ((cn = get_journal_hash_dev(sb, journal->j_hash_table, bl))) {
+ if ((get_journal_hash_dev(sb, journal->j_hash_table, bl))) {
BUG();
return 1;
}
diff --git a/fs/reiserfs/namei.c b/fs/reiserfs/namei.c
index e6eb05e2b2f1..017db70d0f48 100644
--- a/fs/reiserfs/namei.c
+++ b/fs/reiserfs/namei.c
@@ -1660,6 +1660,8 @@ const struct inode_operations reiserfs_dir_inode_operations = {
.permission = reiserfs_permission,
.get_acl = reiserfs_get_acl,
.set_acl = reiserfs_set_acl,
+ .fileattr_get = reiserfs_fileattr_get,
+ .fileattr_set = reiserfs_fileattr_set,
};
/*
diff --git a/fs/reiserfs/reiserfs.h b/fs/reiserfs/reiserfs.h
index 0ca2ac62e534..3aa928ec527a 100644
--- a/fs/reiserfs/reiserfs.h
+++ b/fs/reiserfs/reiserfs.h
@@ -18,8 +18,6 @@
/* the 32 bit compat definitions with int argument */
#define REISERFS_IOC32_UNPACK _IOW(0xCD, 1, int)
-#define REISERFS_IOC32_GETFLAGS FS_IOC32_GETFLAGS
-#define REISERFS_IOC32_SETFLAGS FS_IOC32_SETFLAGS
#define REISERFS_IOC32_GETVERSION FS_IOC32_GETVERSION
#define REISERFS_IOC32_SETVERSION FS_IOC32_SETVERSION
@@ -3408,7 +3406,10 @@ __u32 r5_hash(const signed char *msg, int len);
#define SPARE_SPACE 500
/* prototypes from ioctl.c */
+int reiserfs_fileattr_get(struct dentry *dentry, struct fileattr *fa);
+int reiserfs_fileattr_set(struct user_namespace *mnt_userns,
+ struct dentry *dentry, struct fileattr *fa);
long reiserfs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg);
long reiserfs_compat_ioctl(struct file *filp,
unsigned int cmd, unsigned long arg);
-int reiserfs_unpack(struct inode *inode, struct file *filp);
+int reiserfs_unpack(struct inode *inode);
diff --git a/fs/reiserfs/super.c b/fs/reiserfs/super.c
index 1b9c7a387dc7..3ffafc73acf0 100644
--- a/fs/reiserfs/super.c
+++ b/fs/reiserfs/super.c
@@ -2408,7 +2408,7 @@ static int reiserfs_quota_on(struct super_block *sb, int type, int format_id,
* IO to work
*/
if (!(REISERFS_I(inode)->i_flags & i_nopack_mask)) {
- err = reiserfs_unpack(inode, NULL);
+ err = reiserfs_unpack(inode);
if (err) {
reiserfs_warning(sb, "super-6520",
"Unpacking tail of quota file failed"
diff --git a/fs/reiserfs/xattr.h b/fs/reiserfs/xattr.h
index 9b3b06da568c..e47fde1182de 100644
--- a/fs/reiserfs/xattr.h
+++ b/fs/reiserfs/xattr.h
@@ -44,7 +44,7 @@ void reiserfs_security_free(struct reiserfs_security_handle *sec);
static inline int reiserfs_xattrs_initialized(struct super_block *sb)
{
- return REISERFS_SB(sb)->priv_root != NULL;
+ return REISERFS_SB(sb)->priv_root && REISERFS_SB(sb)->xattr_root;
}
#define xattr_size(size) ((size) + sizeof(struct reiserfs_xattr_header))
diff --git a/fs/select.c b/fs/select.c
index 37aaa8317f3a..945896d0ac9e 100644
--- a/fs/select.c
+++ b/fs/select.c
@@ -1055,10 +1055,9 @@ static long do_restart_poll(struct restart_block *restart_block)
ret = do_sys_poll(ufds, nfds, to);
- if (ret == -ERESTARTNOHAND) {
- restart_block->fn = do_restart_poll;
- ret = -ERESTART_RESTARTBLOCK;
- }
+ if (ret == -ERESTARTNOHAND)
+ ret = set_restart_fn(restart_block, do_restart_poll);
+
return ret;
}
@@ -1080,7 +1079,6 @@ SYSCALL_DEFINE3(poll, struct pollfd __user *, ufds, unsigned int, nfds,
struct restart_block *restart_block;
restart_block = &current->restart_block;
- restart_block->fn = do_restart_poll;
restart_block->poll.ufds = ufds;
restart_block->poll.nfds = nfds;
@@ -1091,7 +1089,7 @@ SYSCALL_DEFINE3(poll, struct pollfd __user *, ufds, unsigned int, nfds,
} else
restart_block->poll.has_timeout = 0;
- ret = -ERESTART_RESTARTBLOCK;
+ ret = set_restart_fn(restart_block, do_restart_poll);
}
return ret;
}
diff --git a/fs/seq_file.c b/fs/seq_file.c
index cb11a34fb871..5059248f2d64 100644
--- a/fs/seq_file.c
+++ b/fs/seq_file.c
@@ -412,6 +412,24 @@ void seq_printf(struct seq_file *m, const char *f, ...)
}
EXPORT_SYMBOL(seq_printf);
+#ifdef CONFIG_BINARY_PRINTF
+void seq_bprintf(struct seq_file *m, const char *f, const u32 *binary)
+{
+ int len;
+
+ if (m->count < m->size) {
+ len = bstr_printf(m->buf + m->count, m->size - m->count, f,
+ binary);
+ if (m->count + len < m->size) {
+ m->count += len;
+ return;
+ }
+ }
+ seq_set_overflow(m);
+}
+EXPORT_SYMBOL(seq_bprintf);
+#endif /* CONFIG_BINARY_PRINTF */
+
/**
* mangle_path - mangle and copy path to buffer beginning
* @s: buffer start
diff --git a/fs/signalfd.c b/fs/signalfd.c
index 456046e15873..040a1142915f 100644
--- a/fs/signalfd.c
+++ b/fs/signalfd.c
@@ -134,6 +134,10 @@ static int signalfd_copyinfo(struct signalfd_siginfo __user *uinfo,
#endif
new.ssi_addr_lsb = (short) kinfo->si_addr_lsb;
break;
+ case SIL_PERF_EVENT:
+ new.ssi_addr = (long) kinfo->si_addr;
+ new.ssi_perf = kinfo->si_perf;
+ break;
case SIL_CHLD:
new.ssi_pid = kinfo->si_pid;
new.ssi_uid = kinfo->si_uid;
diff --git a/fs/squashfs/export.c b/fs/squashfs/export.c
index eb02072d28dd..723763746238 100644
--- a/fs/squashfs/export.c
+++ b/fs/squashfs/export.c
@@ -152,14 +152,18 @@ __le64 *squashfs_read_inode_lookup_table(struct super_block *sb,
start = le64_to_cpu(table[n]);
end = le64_to_cpu(table[n + 1]);
- if (start >= end || (end - start) > SQUASHFS_METADATA_SIZE) {
+ if (start >= end
+ || (end - start) >
+ (SQUASHFS_METADATA_SIZE + SQUASHFS_BLOCK_OFFSET)) {
kfree(table);
return ERR_PTR(-EINVAL);
}
}
start = le64_to_cpu(table[indexes - 1]);
- if (start >= lookup_table_start || (lookup_table_start - start) > SQUASHFS_METADATA_SIZE) {
+ if (start >= lookup_table_start ||
+ (lookup_table_start - start) >
+ (SQUASHFS_METADATA_SIZE + SQUASHFS_BLOCK_OFFSET)) {
kfree(table);
return ERR_PTR(-EINVAL);
}
diff --git a/fs/squashfs/id.c b/fs/squashfs/id.c
index 11581bf31af4..ea5387679723 100644
--- a/fs/squashfs/id.c
+++ b/fs/squashfs/id.c
@@ -97,14 +97,16 @@ __le64 *squashfs_read_id_index_table(struct super_block *sb,
start = le64_to_cpu(table[n]);
end = le64_to_cpu(table[n + 1]);
- if (start >= end || (end - start) > SQUASHFS_METADATA_SIZE) {
+ if (start >= end || (end - start) >
+ (SQUASHFS_METADATA_SIZE + SQUASHFS_BLOCK_OFFSET)) {
kfree(table);
return ERR_PTR(-EINVAL);
}
}
start = le64_to_cpu(table[indexes - 1]);
- if (start >= id_table_start || (id_table_start - start) > SQUASHFS_METADATA_SIZE) {
+ if (start >= id_table_start || (id_table_start - start) >
+ (SQUASHFS_METADATA_SIZE + SQUASHFS_BLOCK_OFFSET)) {
kfree(table);
return ERR_PTR(-EINVAL);
}
diff --git a/fs/squashfs/squashfs_fs.h b/fs/squashfs/squashfs_fs.h
index 8d64edb80ebf..b3fdc8212c5f 100644
--- a/fs/squashfs/squashfs_fs.h
+++ b/fs/squashfs/squashfs_fs.h
@@ -17,6 +17,7 @@
/* size of metadata (inode and directory) blocks */
#define SQUASHFS_METADATA_SIZE 8192
+#define SQUASHFS_BLOCK_OFFSET 2
/* default size of block device I/O */
#ifdef CONFIG_SQUASHFS_4K_DEVBLK_SIZE
diff --git a/fs/squashfs/xattr_id.c b/fs/squashfs/xattr_id.c
index ead66670b41a..087cab8c78f4 100644
--- a/fs/squashfs/xattr_id.c
+++ b/fs/squashfs/xattr_id.c
@@ -109,14 +109,16 @@ __le64 *squashfs_read_xattr_id_table(struct super_block *sb, u64 table_start,
start = le64_to_cpu(table[n]);
end = le64_to_cpu(table[n + 1]);
- if (start >= end || (end - start) > SQUASHFS_METADATA_SIZE) {
+ if (start >= end || (end - start) >
+ (SQUASHFS_METADATA_SIZE + SQUASHFS_BLOCK_OFFSET)) {
kfree(table);
return ERR_PTR(-EINVAL);
}
}
start = le64_to_cpu(table[indexes - 1]);
- if (start >= table_start || (table_start - start) > SQUASHFS_METADATA_SIZE) {
+ if (start >= table_start || (table_start - start) >
+ (SQUASHFS_METADATA_SIZE + SQUASHFS_BLOCK_OFFSET)) {
kfree(table);
return ERR_PTR(-EINVAL);
}
diff --git a/fs/stat.c b/fs/stat.c
index fbc171d038aa..1fa38bdec1a6 100644
--- a/fs/stat.c
+++ b/fs/stat.c
@@ -86,12 +86,20 @@ int vfs_getattr_nosec(const struct path *path, struct kstat *stat,
/* SB_NOATIME means filesystem supplies dummy atime value */
if (inode->i_sb->s_flags & SB_NOATIME)
stat->result_mask &= ~STATX_ATIME;
+
+ /*
+ * Note: If you add another clause to set an attribute flag, please
+ * update attributes_mask below.
+ */
if (IS_AUTOMOUNT(inode))
stat->attributes |= STATX_ATTR_AUTOMOUNT;
if (IS_DAX(inode))
stat->attributes |= STATX_ATTR_DAX;
+ stat->attributes_mask |= (STATX_ATTR_AUTOMOUNT |
+ STATX_ATTR_DAX);
+
mnt_userns = mnt_user_ns(path->mnt);
if (inode->i_op->getattr)
return inode->i_op->getattr(mnt_userns, path, stat,
diff --git a/fs/super.c b/fs/super.c
index 8c1baca35c16..11b7e7213fd1 100644
--- a/fs/super.c
+++ b/fs/super.c
@@ -454,6 +454,7 @@ void generic_shutdown_super(struct super_block *sb)
evict_inodes(sb);
/* only nonzero refcount inodes can have marks */
fsnotify_sb_delete(sb);
+ security_sb_delete(sb);
if (sb->s_dio_done_wq) {
destroy_workqueue(sb->s_dio_done_wq);
diff --git a/fs/tracefs/inode.c b/fs/tracefs/inode.c
index 4b83cbded559..1261e8b41edb 100644
--- a/fs/tracefs/inode.c
+++ b/fs/tracefs/inode.c
@@ -477,7 +477,7 @@ struct dentry *tracefs_create_dir(const char *name, struct dentry *parent)
*
* The instances directory is special as it allows for mkdir and rmdir to
* to be done by userspace. When a mkdir or rmdir is performed, the inode
- * locks are released and the methhods passed in (@mkdir and @rmdir) are
+ * locks are released and the methods passed in (@mkdir and @rmdir) are
* called without locks and with the name of the directory being created
* within the instances directory.
*
diff --git a/fs/ubifs/dir.c b/fs/ubifs/dir.c
index d9d8d7794eff..5bd8482e660a 100644
--- a/fs/ubifs/dir.c
+++ b/fs/ubifs/dir.c
@@ -1637,6 +1637,8 @@ const struct inode_operations ubifs_dir_inode_operations = {
.listxattr = ubifs_listxattr,
.update_time = ubifs_update_time,
.tmpfile = ubifs_tmpfile,
+ .fileattr_get = ubifs_fileattr_get,
+ .fileattr_set = ubifs_fileattr_set,
};
const struct file_operations ubifs_dir_operations = {
diff --git a/fs/ubifs/file.c b/fs/ubifs/file.c
index 0e4b4be3aa26..2e4e1d159969 100644
--- a/fs/ubifs/file.c
+++ b/fs/ubifs/file.c
@@ -1648,6 +1648,8 @@ const struct inode_operations ubifs_file_inode_operations = {
.getattr = ubifs_getattr,
.listxattr = ubifs_listxattr,
.update_time = ubifs_update_time,
+ .fileattr_get = ubifs_fileattr_get,
+ .fileattr_set = ubifs_fileattr_set,
};
const struct inode_operations ubifs_symlink_inode_operations = {
diff --git a/fs/ubifs/gc.c b/fs/ubifs/gc.c
index a4aaeea63893..dc3e26e9ed7b 100644
--- a/fs/ubifs/gc.c
+++ b/fs/ubifs/gc.c
@@ -102,7 +102,8 @@ static int switch_gc_head(struct ubifs_info *c)
* This function compares data nodes @a and @b. Returns %1 if @a has greater
* inode or block number, and %-1 otherwise.
*/
-static int data_nodes_cmp(void *priv, struct list_head *a, struct list_head *b)
+static int data_nodes_cmp(void *priv, const struct list_head *a,
+ const struct list_head *b)
{
ino_t inuma, inumb;
struct ubifs_info *c = priv;
@@ -145,8 +146,8 @@ static int data_nodes_cmp(void *priv, struct list_head *a, struct list_head *b)
* first and sorted by length in descending order. Directory entry nodes go
* after inode nodes and are sorted in ascending hash valuer order.
*/
-static int nondata_nodes_cmp(void *priv, struct list_head *a,
- struct list_head *b)
+static int nondata_nodes_cmp(void *priv, const struct list_head *a,
+ const struct list_head *b)
{
ino_t inuma, inumb;
struct ubifs_info *c = priv;
diff --git a/fs/ubifs/ioctl.c b/fs/ubifs/ioctl.c
index 2326d5122beb..c6a863487780 100644
--- a/fs/ubifs/ioctl.c
+++ b/fs/ubifs/ioctl.c
@@ -14,6 +14,7 @@
#include <linux/compat.h>
#include <linux/mount.h>
+#include <linux/fileattr.h>
#include "ubifs.h"
/* Need to be kept consistent with checked flags in ioctl2ubifs() */
@@ -103,7 +104,7 @@ static int ubifs2ioctl(int ubifs_flags)
static int setflags(struct inode *inode, int flags)
{
- int oldflags, err, release;
+ int err, release;
struct ubifs_inode *ui = ubifs_inode(inode);
struct ubifs_info *c = inode->i_sb->s_fs_info;
struct ubifs_budget_req req = { .dirtied_ino = 1,
@@ -114,11 +115,6 @@ static int setflags(struct inode *inode, int flags)
return err;
mutex_lock(&ui->ui_mutex);
- oldflags = ubifs2ioctl(ui->flags);
- err = vfs_ioc_setflags_prepare(inode, oldflags, flags);
- if (err)
- goto out_unlock;
-
ui->flags &= ~ioctl2ubifs(UBIFS_SETTABLE_IOCTL_FLAGS);
ui->flags |= ioctl2ubifs(flags);
ubifs_set_inode_flags(inode);
@@ -132,54 +128,52 @@ static int setflags(struct inode *inode, int flags)
if (IS_SYNC(inode))
err = write_inode_now(inode, 1);
return err;
+}
-out_unlock:
- mutex_unlock(&ui->ui_mutex);
- ubifs_release_budget(c, &req);
- return err;
+int ubifs_fileattr_get(struct dentry *dentry, struct fileattr *fa)
+{
+ struct inode *inode = d_inode(dentry);
+ int flags = ubifs2ioctl(ubifs_inode(inode)->flags);
+
+ if (d_is_special(dentry))
+ return -ENOTTY;
+
+ dbg_gen("get flags: %#x, i_flags %#x", flags, inode->i_flags);
+ fileattr_fill_flags(fa, flags);
+
+ return 0;
}
-long ubifs_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
+int ubifs_fileattr_set(struct user_namespace *mnt_userns,
+ struct dentry *dentry, struct fileattr *fa)
{
- int flags, err;
- struct inode *inode = file_inode(file);
+ struct inode *inode = d_inode(dentry);
+ int flags = fa->flags;
- switch (cmd) {
- case FS_IOC_GETFLAGS:
- flags = ubifs2ioctl(ubifs_inode(inode)->flags);
+ if (d_is_special(dentry))
+ return -ENOTTY;
- dbg_gen("get flags: %#x, i_flags %#x", flags, inode->i_flags);
- return put_user(flags, (int __user *) arg);
+ if (fileattr_has_fsx(fa))
+ return -EOPNOTSUPP;
- case FS_IOC_SETFLAGS: {
- if (IS_RDONLY(inode))
- return -EROFS;
+ if (flags & ~UBIFS_GETTABLE_IOCTL_FLAGS)
+ return -EOPNOTSUPP;
- if (!inode_owner_or_capable(&init_user_ns, inode))
- return -EACCES;
+ flags &= UBIFS_SETTABLE_IOCTL_FLAGS;
- if (get_user(flags, (int __user *) arg))
- return -EFAULT;
+ if (!S_ISDIR(inode->i_mode))
+ flags &= ~FS_DIRSYNC_FL;
- if (flags & ~UBIFS_GETTABLE_IOCTL_FLAGS)
- return -EOPNOTSUPP;
- flags &= UBIFS_SETTABLE_IOCTL_FLAGS;
+ dbg_gen("set flags: %#x, i_flags %#x", flags, inode->i_flags);
+ return setflags(inode, flags);
+}
- if (!S_ISDIR(inode->i_mode))
- flags &= ~FS_DIRSYNC_FL;
+long ubifs_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
+{
+ int err;
+ struct inode *inode = file_inode(file);
- /*
- * Make sure the file-system is read-write and make sure it
- * will not become read-only while we are changing the flags.
- */
- err = mnt_want_write_file(file);
- if (err)
- return err;
- dbg_gen("set flags: %#x, i_flags %#x", flags, inode->i_flags);
- err = setflags(inode, flags);
- mnt_drop_write_file(file);
- return err;
- }
+ switch (cmd) {
case FS_IOC_SET_ENCRYPTION_POLICY: {
struct ubifs_info *c = inode->i_sb->s_fs_info;
diff --git a/fs/ubifs/replay.c b/fs/ubifs/replay.c
index 0f8a6a16421b..4d17e5382b74 100644
--- a/fs/ubifs/replay.c
+++ b/fs/ubifs/replay.c
@@ -298,8 +298,8 @@ static int apply_replay_entry(struct ubifs_info *c, struct replay_entry *r)
* entries @a and @b by comparing their sequence numer. Returns %1 if @a has
* greater sequence number and %-1 otherwise.
*/
-static int replay_entries_cmp(void *priv, struct list_head *a,
- struct list_head *b)
+static int replay_entries_cmp(void *priv, const struct list_head *a,
+ const struct list_head *b)
{
struct ubifs_info *c = priv;
struct replay_entry *ra, *rb;
diff --git a/fs/ubifs/ubifs.h b/fs/ubifs/ubifs.h
index 7fdfdbda4b8a..b65c599a386a 100644
--- a/fs/ubifs/ubifs.h
+++ b/fs/ubifs/ubifs.h
@@ -2053,6 +2053,9 @@ int ubifs_recover_size(struct ubifs_info *c, bool in_place);
void ubifs_destroy_size_tree(struct ubifs_info *c);
/* ioctl.c */
+int ubifs_fileattr_get(struct dentry *dentry, struct fileattr *fa);
+int ubifs_fileattr_set(struct user_namespace *mnt_userns,
+ struct dentry *dentry, struct fileattr *fa);
long ubifs_ioctl(struct file *file, unsigned int cmd, unsigned long arg);
void ubifs_set_inode_flags(struct inode *inode);
#ifdef CONFIG_COMPAT
diff --git a/fs/udf/namei.c b/fs/udf/namei.c
index f146b3089f3d..3ae9f1e91984 100644
--- a/fs/udf/namei.c
+++ b/fs/udf/namei.c
@@ -1215,11 +1215,10 @@ static struct dentry *udf_get_parent(struct dentry *child)
{
struct kernel_lb_addr tloc;
struct inode *inode = NULL;
- struct qstr dotdot = QSTR_INIT("..", 2);
struct fileIdentDesc cfi;
struct udf_fileident_bh fibh;
- if (!udf_find_entry(d_inode(child), &dotdot, &fibh, &cfi))
+ if (!udf_find_entry(d_inode(child), &dotdot_name, &fibh, &cfi))
return ERR_PTR(-EACCES);
if (fibh.sbh != fibh.ebh)
diff --git a/fs/ufs/super.c b/fs/ufs/super.c
index 983558b572c7..74028b5a7b0a 100644
--- a/fs/ufs/super.c
+++ b/fs/ufs/super.c
@@ -128,10 +128,9 @@ static struct dentry *ufs_fh_to_parent(struct super_block *sb, struct fid *fid,
static struct dentry *ufs_get_parent(struct dentry *child)
{
- struct qstr dot_dot = QSTR_INIT("..", 2);
ino_t ino;
- ino = ufs_inode_by_name(d_inode(child), &dot_dot);
+ ino = ufs_inode_by_name(d_inode(child), &dotdot_name);
if (!ino)
return ERR_PTR(-ENOENT);
return d_obtain_alias(ufs_iget(child->d_sb, ino));
diff --git a/fs/vboxsf/dir.c b/fs/vboxsf/dir.c
index 7aee0ec63ade..eac6788fc6cf 100644
--- a/fs/vboxsf/dir.c
+++ b/fs/vboxsf/dir.c
@@ -225,7 +225,7 @@ static struct dentry *vboxsf_dir_lookup(struct inode *parent,
} else {
inode = vboxsf_new_inode(parent->i_sb);
if (!IS_ERR(inode))
- vboxsf_init_inode(sbi, inode, &fsinfo);
+ vboxsf_init_inode(sbi, inode, &fsinfo, false);
}
return d_splice_alias(inode, dentry);
@@ -245,7 +245,7 @@ static int vboxsf_dir_instantiate(struct inode *parent, struct dentry *dentry,
sf_i = VBOXSF_I(inode);
/* The host may have given us different attr then requested */
sf_i->force_restat = 1;
- vboxsf_init_inode(sbi, inode, info);
+ vboxsf_init_inode(sbi, inode, info, false);
d_instantiate(dentry, inode);
diff --git a/fs/vboxsf/super.c b/fs/vboxsf/super.c
index d7816c01a4f6..4f5e59f06284 100644
--- a/fs/vboxsf/super.c
+++ b/fs/vboxsf/super.c
@@ -207,7 +207,7 @@ static int vboxsf_fill_super(struct super_block *sb, struct fs_context *fc)
err = -ENOMEM;
goto fail_unmap;
}
- vboxsf_init_inode(sbi, iroot, &sbi->root_info);
+ vboxsf_init_inode(sbi, iroot, &sbi->root_info, false);
unlock_new_inode(iroot);
droot = d_make_root(iroot);
@@ -418,7 +418,7 @@ static int vboxsf_reconfigure(struct fs_context *fc)
/* Apply changed options to the root inode */
sbi->o = ctx->o;
- vboxsf_init_inode(sbi, iroot, &sbi->root_info);
+ vboxsf_init_inode(sbi, iroot, &sbi->root_info, true);
return 0;
}
diff --git a/fs/vboxsf/utils.c b/fs/vboxsf/utils.c
index 3b847e3fba24..aec2ebf7d25a 100644
--- a/fs/vboxsf/utils.c
+++ b/fs/vboxsf/utils.c
@@ -45,12 +45,12 @@ struct inode *vboxsf_new_inode(struct super_block *sb)
}
/* set [inode] attributes based on [info], uid/gid based on [sbi] */
-void vboxsf_init_inode(struct vboxsf_sbi *sbi, struct inode *inode,
- const struct shfl_fsobjinfo *info)
+int vboxsf_init_inode(struct vboxsf_sbi *sbi, struct inode *inode,
+ const struct shfl_fsobjinfo *info, bool reinit)
{
const struct shfl_fsobjattr *attr;
s64 allocated;
- int mode;
+ umode_t mode;
attr = &info->attr;
@@ -75,29 +75,44 @@ void vboxsf_init_inode(struct vboxsf_sbi *sbi, struct inode *inode,
inode->i_mapping->a_ops = &vboxsf_reg_aops;
if (SHFL_IS_DIRECTORY(attr->mode)) {
- inode->i_mode = sbi->o.dmode_set ? sbi->o.dmode : mode;
- inode->i_mode &= ~sbi->o.dmask;
- inode->i_mode |= S_IFDIR;
- inode->i_op = &vboxsf_dir_iops;
- inode->i_fop = &vboxsf_dir_fops;
- /*
- * XXX: this probably should be set to the number of entries
- * in the directory plus two (. ..)
- */
- set_nlink(inode, 1);
+ if (sbi->o.dmode_set)
+ mode = sbi->o.dmode;
+ mode &= ~sbi->o.dmask;
+ mode |= S_IFDIR;
+ if (!reinit) {
+ inode->i_op = &vboxsf_dir_iops;
+ inode->i_fop = &vboxsf_dir_fops;
+ /*
+ * XXX: this probably should be set to the number of entries
+ * in the directory plus two (. ..)
+ */
+ set_nlink(inode, 1);
+ } else if (!S_ISDIR(inode->i_mode))
+ return -ESTALE;
+ inode->i_mode = mode;
} else if (SHFL_IS_SYMLINK(attr->mode)) {
- inode->i_mode = sbi->o.fmode_set ? sbi->o.fmode : mode;
- inode->i_mode &= ~sbi->o.fmask;
- inode->i_mode |= S_IFLNK;
- inode->i_op = &vboxsf_lnk_iops;
- set_nlink(inode, 1);
+ if (sbi->o.fmode_set)
+ mode = sbi->o.fmode;
+ mode &= ~sbi->o.fmask;
+ mode |= S_IFLNK;
+ if (!reinit) {
+ inode->i_op = &vboxsf_lnk_iops;
+ set_nlink(inode, 1);
+ } else if (!S_ISLNK(inode->i_mode))
+ return -ESTALE;
+ inode->i_mode = mode;
} else {
- inode->i_mode = sbi->o.fmode_set ? sbi->o.fmode : mode;
- inode->i_mode &= ~sbi->o.fmask;
- inode->i_mode |= S_IFREG;
- inode->i_op = &vboxsf_reg_iops;
- inode->i_fop = &vboxsf_reg_fops;
- set_nlink(inode, 1);
+ if (sbi->o.fmode_set)
+ mode = sbi->o.fmode;
+ mode &= ~sbi->o.fmask;
+ mode |= S_IFREG;
+ if (!reinit) {
+ inode->i_op = &vboxsf_reg_iops;
+ inode->i_fop = &vboxsf_reg_fops;
+ set_nlink(inode, 1);
+ } else if (!S_ISREG(inode->i_mode))
+ return -ESTALE;
+ inode->i_mode = mode;
}
inode->i_uid = sbi->o.uid;
@@ -116,6 +131,7 @@ void vboxsf_init_inode(struct vboxsf_sbi *sbi, struct inode *inode,
info->change_time.ns_relative_to_unix_epoch);
inode->i_mtime = ns_to_timespec64(
info->modification_time.ns_relative_to_unix_epoch);
+ return 0;
}
int vboxsf_create_at_dentry(struct dentry *dentry,
@@ -199,7 +215,9 @@ int vboxsf_inode_revalidate(struct dentry *dentry)
dentry->d_time = jiffies;
sf_i->force_restat = 0;
- vboxsf_init_inode(sbi, inode, &info);
+ err = vboxsf_init_inode(sbi, inode, &info, true);
+ if (err)
+ return err;
/*
* If the file was changed on the host side we need to invalidate the
diff --git a/fs/vboxsf/vfsmod.h b/fs/vboxsf/vfsmod.h
index 760524e78c88..6a7a9cedebc6 100644
--- a/fs/vboxsf/vfsmod.h
+++ b/fs/vboxsf/vfsmod.h
@@ -82,8 +82,8 @@ extern const struct dentry_operations vboxsf_dentry_ops;
/* from utils.c */
struct inode *vboxsf_new_inode(struct super_block *sb);
-void vboxsf_init_inode(struct vboxsf_sbi *sbi, struct inode *inode,
- const struct shfl_fsobjinfo *info);
+int vboxsf_init_inode(struct vboxsf_sbi *sbi, struct inode *inode,
+ const struct shfl_fsobjinfo *info, bool reinit);
int vboxsf_create_at_dentry(struct dentry *dentry,
struct shfl_createparms *params);
int vboxsf_stat(struct vboxsf_sbi *sbi, struct shfl_string *path,
diff --git a/fs/verity/Kconfig b/fs/verity/Kconfig
index 88fb25119899..24d1b54de807 100644
--- a/fs/verity/Kconfig
+++ b/fs/verity/Kconfig
@@ -3,9 +3,13 @@
config FS_VERITY
bool "FS Verity (read-only file-based authenticity protection)"
select CRYPTO
- # SHA-256 is selected as it's intended to be the default hash algorithm.
+ # SHA-256 is implied as it's intended to be the default hash algorithm.
# To avoid bloat, other wanted algorithms must be selected explicitly.
- select CRYPTO_SHA256
+ # Note that CRYPTO_SHA256 denotes the generic C implementation, but
+ # some architectures provided optimized implementations of the same
+ # algorithm that may be used instead. In this case, CRYPTO_SHA256 may
+ # be omitted even if SHA-256 is being used.
+ imply CRYPTO_SHA256
help
This option enables fs-verity. fs-verity is the dm-verity
mechanism implemented at the file level. On supported
diff --git a/fs/xattr.c b/fs/xattr.c
index b3444e06cded..5c8c5175b385 100644
--- a/fs/xattr.c
+++ b/fs/xattr.c
@@ -186,12 +186,12 @@ EXPORT_SYMBOL(__vfs_setxattr);
* __vfs_setxattr_noperm - perform setxattr operation without performing
* permission checks.
*
- * @mnt_userns - user namespace of the mount the inode was found from
- * @dentry - object to perform setxattr on
- * @name - xattr name to set
- * @value - value to set @name to
- * @size - size of @value
- * @flags - flags to pass into filesystem operations
+ * @mnt_userns: user namespace of the mount the inode was found from
+ * @dentry: object to perform setxattr on
+ * @name: xattr name to set
+ * @value: value to set @name to
+ * @size: size of @value
+ * @flags: flags to pass into filesystem operations
*
* returns the result of the internal setxattr or setsecurity operations.
*
@@ -242,6 +242,7 @@ int __vfs_setxattr_noperm(struct user_namespace *mnt_userns,
* __vfs_setxattr_locked - set an extended attribute while holding the inode
* lock
*
+ * @mnt_userns: user namespace of the mount of the target inode
* @dentry: object to perform setxattr on
* @name: xattr name to set
* @value: value to set @name to
@@ -473,6 +474,7 @@ EXPORT_SYMBOL(__vfs_removexattr);
* __vfs_removexattr_locked - set an extended attribute while holding the inode
* lock
*
+ * @mnt_userns: user namespace of the mount of the target inode
* @dentry: object to perform setxattr on
* @name: name of xattr to remove
* @delegated_inode: on return, will contain an inode pointer that
diff --git a/fs/xfs/libxfs/xfs_ag.c b/fs/xfs/libxfs/xfs_ag.c
index 9331f3516afa..c68a36688474 100644
--- a/fs/xfs/libxfs/xfs_ag.c
+++ b/fs/xfs/libxfs/xfs_ag.c
@@ -22,6 +22,11 @@
#include "xfs_ag.h"
#include "xfs_ag_resv.h"
#include "xfs_health.h"
+#include "xfs_error.h"
+#include "xfs_bmap.h"
+#include "xfs_defer.h"
+#include "xfs_log_format.h"
+#include "xfs_trans.h"
static int
xfs_get_aghdr_buf(
@@ -485,6 +490,116 @@ xfs_ag_init_headers(
return error;
}
+int
+xfs_ag_shrink_space(
+ struct xfs_mount *mp,
+ struct xfs_trans **tpp,
+ xfs_agnumber_t agno,
+ xfs_extlen_t delta)
+{
+ struct xfs_alloc_arg args = {
+ .tp = *tpp,
+ .mp = mp,
+ .type = XFS_ALLOCTYPE_THIS_BNO,
+ .minlen = delta,
+ .maxlen = delta,
+ .oinfo = XFS_RMAP_OINFO_SKIP_UPDATE,
+ .resv = XFS_AG_RESV_NONE,
+ .prod = 1
+ };
+ struct xfs_buf *agibp, *agfbp;
+ struct xfs_agi *agi;
+ struct xfs_agf *agf;
+ int error, err2;
+
+ ASSERT(agno == mp->m_sb.sb_agcount - 1);
+ error = xfs_ialloc_read_agi(mp, *tpp, agno, &agibp);
+ if (error)
+ return error;
+
+ agi = agibp->b_addr;
+
+ error = xfs_alloc_read_agf(mp, *tpp, agno, 0, &agfbp);
+ if (error)
+ return error;
+
+ agf = agfbp->b_addr;
+ /* some extra paranoid checks before we shrink the ag */
+ if (XFS_IS_CORRUPT(mp, agf->agf_length != agi->agi_length))
+ return -EFSCORRUPTED;
+ if (delta >= agi->agi_length)
+ return -EINVAL;
+
+ args.fsbno = XFS_AGB_TO_FSB(mp, agno,
+ be32_to_cpu(agi->agi_length) - delta);
+
+ /*
+ * Disable perag reservations so it doesn't cause the allocation request
+ * to fail. We'll reestablish reservation before we return.
+ */
+ error = xfs_ag_resv_free(agibp->b_pag);
+ if (error)
+ return error;
+
+ /* internal log shouldn't also show up in the free space btrees */
+ error = xfs_alloc_vextent(&args);
+ if (!error && args.agbno == NULLAGBLOCK)
+ error = -ENOSPC;
+
+ if (error) {
+ /*
+ * if extent allocation fails, need to roll the transaction to
+ * ensure that the AGFL fixup has been committed anyway.
+ */
+ xfs_trans_bhold(*tpp, agfbp);
+ err2 = xfs_trans_roll(tpp);
+ if (err2)
+ return err2;
+ xfs_trans_bjoin(*tpp, agfbp);
+ goto resv_init_out;
+ }
+
+ /*
+ * if successfully deleted from freespace btrees, need to confirm
+ * per-AG reservation works as expected.
+ */
+ be32_add_cpu(&agi->agi_length, -delta);
+ be32_add_cpu(&agf->agf_length, -delta);
+
+ err2 = xfs_ag_resv_init(agibp->b_pag, *tpp);
+ if (err2) {
+ be32_add_cpu(&agi->agi_length, delta);
+ be32_add_cpu(&agf->agf_length, delta);
+ if (err2 != -ENOSPC)
+ goto resv_err;
+
+ __xfs_bmap_add_free(*tpp, args.fsbno, delta, NULL, true);
+
+ /*
+ * Roll the transaction before trying to re-init the per-ag
+ * reservation. The new transaction is clean so it will cancel
+ * without any side effects.
+ */
+ error = xfs_defer_finish(tpp);
+ if (error)
+ return error;
+
+ error = -ENOSPC;
+ goto resv_init_out;
+ }
+ xfs_ialloc_log_agi(*tpp, agibp, XFS_AGI_LENGTH);
+ xfs_alloc_log_agf(*tpp, agfbp, XFS_AGF_LENGTH);
+ return 0;
+resv_init_out:
+ err2 = xfs_ag_resv_init(agibp->b_pag, *tpp);
+ if (!err2)
+ return error;
+resv_err:
+ xfs_warn(mp, "Error %d reserving per-AG metadata reserve pool.", err2);
+ xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_INCORE);
+ return err2;
+}
+
/*
* Extent the AG indicated by the @id by the length passed in
*/
diff --git a/fs/xfs/libxfs/xfs_ag.h b/fs/xfs/libxfs/xfs_ag.h
index 5166322807e7..4535de1d88ea 100644
--- a/fs/xfs/libxfs/xfs_ag.h
+++ b/fs/xfs/libxfs/xfs_ag.h
@@ -24,6 +24,8 @@ struct aghdr_init_data {
};
int xfs_ag_init_headers(struct xfs_mount *mp, struct aghdr_init_data *id);
+int xfs_ag_shrink_space(struct xfs_mount *mp, struct xfs_trans **tpp,
+ xfs_agnumber_t agno, xfs_extlen_t delta);
int xfs_ag_extend_space(struct xfs_mount *mp, struct xfs_trans *tp,
struct aghdr_init_data *id, xfs_extlen_t len);
int xfs_ag_get_geometry(struct xfs_mount *mp, xfs_agnumber_t agno,
diff --git a/fs/xfs/libxfs/xfs_ag_resv.c b/fs/xfs/libxfs/xfs_ag_resv.c
index fdfe6dc0d307..6c5f8d10589c 100644
--- a/fs/xfs/libxfs/xfs_ag_resv.c
+++ b/fs/xfs/libxfs/xfs_ag_resv.c
@@ -211,7 +211,11 @@ __xfs_ag_resv_init(
ASSERT(0);
return -EINVAL;
}
- error = xfs_mod_fdblocks(mp, -(int64_t)hidden_space, true);
+
+ if (XFS_TEST_ERROR(false, mp, XFS_ERRTAG_AG_RESV_FAIL))
+ error = -ENOSPC;
+ else
+ error = xfs_mod_fdblocks(mp, -(int64_t)hidden_space, true);
if (error) {
trace_xfs_ag_resv_init_error(pag->pag_mount, pag->pag_agno,
error, _RET_IP_);
diff --git a/fs/xfs/libxfs/xfs_alloc.c b/fs/xfs/libxfs/xfs_alloc.c
index 0c623d3c1036..aaa19101bb2a 100644
--- a/fs/xfs/libxfs/xfs_alloc.c
+++ b/fs/xfs/libxfs/xfs_alloc.c
@@ -2906,13 +2906,13 @@ xfs_agf_verify(
if (be32_to_cpu(agf->agf_levels[XFS_BTNUM_BNO]) < 1 ||
be32_to_cpu(agf->agf_levels[XFS_BTNUM_CNT]) < 1 ||
- be32_to_cpu(agf->agf_levels[XFS_BTNUM_BNO]) > XFS_BTREE_MAXLEVELS ||
- be32_to_cpu(agf->agf_levels[XFS_BTNUM_CNT]) > XFS_BTREE_MAXLEVELS)
+ be32_to_cpu(agf->agf_levels[XFS_BTNUM_BNO]) > mp->m_ag_maxlevels ||
+ be32_to_cpu(agf->agf_levels[XFS_BTNUM_CNT]) > mp->m_ag_maxlevels)
return __this_address;
if (xfs_sb_version_hasrmapbt(&mp->m_sb) &&
(be32_to_cpu(agf->agf_levels[XFS_BTNUM_RMAP]) < 1 ||
- be32_to_cpu(agf->agf_levels[XFS_BTNUM_RMAP]) > XFS_BTREE_MAXLEVELS))
+ be32_to_cpu(agf->agf_levels[XFS_BTNUM_RMAP]) > mp->m_rmap_maxlevels))
return __this_address;
if (xfs_sb_version_hasrmapbt(&mp->m_sb) &&
@@ -2939,7 +2939,7 @@ xfs_agf_verify(
if (xfs_sb_version_hasreflink(&mp->m_sb) &&
(be32_to_cpu(agf->agf_refcount_level) < 1 ||
- be32_to_cpu(agf->agf_refcount_level) > XFS_BTREE_MAXLEVELS))
+ be32_to_cpu(agf->agf_refcount_level) > mp->m_refc_maxlevels))
return __this_address;
return NULL;
diff --git a/fs/xfs/libxfs/xfs_attr.c b/fs/xfs/libxfs/xfs_attr.c
index 472b3039eabb..96146f425e50 100644
--- a/fs/xfs/libxfs/xfs_attr.c
+++ b/fs/xfs/libxfs/xfs_attr.c
@@ -70,6 +70,26 @@ xfs_inode_hasattr(
return 1;
}
+/*
+ * Returns true if the there is exactly only block in the attr fork, in which
+ * case the attribute fork consists of a single leaf block entry.
+ */
+bool
+xfs_attr_is_leaf(
+ struct xfs_inode *ip)
+{
+ struct xfs_ifork *ifp = ip->i_afp;
+ struct xfs_iext_cursor icur;
+ struct xfs_bmbt_irec imap;
+
+ if (ifp->if_nextents != 1 || ifp->if_format != XFS_DINODE_FMT_EXTENTS)
+ return false;
+
+ xfs_iext_first(ifp, &icur);
+ xfs_iext_get_extent(ifp, &icur, &imap);
+ return imap.br_startoff == 0 && imap.br_blockcount == 1;
+}
+
/*========================================================================
* Overall external interface routines.
*========================================================================*/
@@ -89,7 +109,7 @@ xfs_attr_get_ilocked(
if (args->dp->i_afp->if_format == XFS_DINODE_FMT_LOCAL)
return xfs_attr_shortform_getvalue(args);
- if (xfs_bmap_one_block(args->dp, XFS_ATTR_FORK))
+ if (xfs_attr_is_leaf(args->dp))
return xfs_attr_leaf_get(args);
return xfs_attr_node_get(args);
}
@@ -293,7 +313,7 @@ xfs_attr_set_args(
return error;
}
- if (xfs_bmap_one_block(dp, XFS_ATTR_FORK)) {
+ if (xfs_attr_is_leaf(dp)) {
error = xfs_attr_leaf_addname(args);
if (error != -ENOSPC)
return error;
@@ -342,12 +362,10 @@ xfs_has_attr(
if (!xfs_inode_hasattr(dp))
return -ENOATTR;
- if (dp->i_afp->if_format == XFS_DINODE_FMT_LOCAL) {
- ASSERT(dp->i_afp->if_flags & XFS_IFINLINE);
+ if (dp->i_afp->if_format == XFS_DINODE_FMT_LOCAL)
return xfs_attr_sf_findname(args, NULL, NULL);
- }
- if (xfs_bmap_one_block(dp, XFS_ATTR_FORK)) {
+ if (xfs_attr_is_leaf(dp)) {
error = xfs_attr_leaf_hasname(args, &bp);
if (bp)
@@ -366,21 +384,14 @@ int
xfs_attr_remove_args(
struct xfs_da_args *args)
{
- struct xfs_inode *dp = args->dp;
- int error;
-
- if (!xfs_inode_hasattr(dp)) {
- error = -ENOATTR;
- } else if (dp->i_afp->if_format == XFS_DINODE_FMT_LOCAL) {
- ASSERT(dp->i_afp->if_flags & XFS_IFINLINE);
- error = xfs_attr_shortform_remove(args);
- } else if (xfs_bmap_one_block(dp, XFS_ATTR_FORK)) {
- error = xfs_attr_leaf_removename(args);
- } else {
- error = xfs_attr_node_removename(args);
- }
+ if (!xfs_inode_hasattr(args->dp))
+ return -ENOATTR;
- return error;
+ if (args->dp->i_afp->if_format == XFS_DINODE_FMT_LOCAL)
+ return xfs_attr_shortform_remove(args);
+ if (xfs_attr_is_leaf(args->dp))
+ return xfs_attr_leaf_removename(args);
+ return xfs_attr_node_removename(args);
}
/*
@@ -928,6 +939,7 @@ restart:
* Search to see if name already exists, and get back a pointer
* to where it should go.
*/
+ error = 0;
retval = xfs_attr_node_hasname(args, &state);
if (retval != -ENOATTR && retval != -EEXIST)
goto out;
@@ -1282,7 +1294,7 @@ xfs_attr_node_removename(
/*
* If the result is small enough, push it all into the inode.
*/
- if (xfs_bmap_one_block(dp, XFS_ATTR_FORK))
+ if (xfs_attr_is_leaf(dp))
error = xfs_attr_node_shrink(args, state);
out:
diff --git a/fs/xfs/libxfs/xfs_attr.h b/fs/xfs/libxfs/xfs_attr.h
index 3e97a935e712..2b1f61987a9d 100644
--- a/fs/xfs/libxfs/xfs_attr.h
+++ b/fs/xfs/libxfs/xfs_attr.h
@@ -85,6 +85,7 @@ int xfs_attr_inactive(struct xfs_inode *dp);
int xfs_attr_list_ilocked(struct xfs_attr_list_context *);
int xfs_attr_list(struct xfs_attr_list_context *);
int xfs_inode_hasattr(struct xfs_inode *ip);
+bool xfs_attr_is_leaf(struct xfs_inode *ip);
int xfs_attr_get_ilocked(struct xfs_da_args *args);
int xfs_attr_get(struct xfs_da_args *args);
int xfs_attr_set(struct xfs_da_args *args);
diff --git a/fs/xfs/libxfs/xfs_attr_leaf.c b/fs/xfs/libxfs/xfs_attr_leaf.c
index d6ef69ab1c67..556184b63061 100644
--- a/fs/xfs/libxfs/xfs_attr_leaf.c
+++ b/fs/xfs/libxfs/xfs_attr_leaf.c
@@ -518,10 +518,10 @@ xfs_attr_copy_value(
* Query whether the total requested number of attr fork bytes of extended
* attribute space will be able to fit inline.
*
- * Returns zero if not, else the di_forkoff fork offset to be used in the
+ * Returns zero if not, else the i_forkoff fork offset to be used in the
* literal area for attribute data once the new bytes have been added.
*
- * di_forkoff must be 8 byte aligned, hence is stored as a >>3 value;
+ * i_forkoff must be 8 byte aligned, hence is stored as a >>3 value;
* special case for dev/uuid inodes, they have fixed size data forks.
*/
int
@@ -560,7 +560,7 @@ xfs_attr_shortform_bytesfit(
* literal area rebalancing.
*/
if (bytes <= XFS_IFORK_ASIZE(dp))
- return dp->i_d.di_forkoff;
+ return dp->i_forkoff;
/*
* For attr2 we can try to move the forkoff if there is space in the
@@ -581,7 +581,7 @@ xfs_attr_shortform_bytesfit(
* minimum offset only needs to be the space required for
* the btree root.
*/
- if (!dp->i_d.di_forkoff && dp->i_df.if_bytes >
+ if (!dp->i_forkoff && dp->i_df.if_bytes >
xfs_default_attroffset(dp))
dsize = XFS_BMDR_SPACE_CALC(MINDBTPTRS);
break;
@@ -592,10 +592,10 @@ xfs_attr_shortform_bytesfit(
* minforkoff to where the btree root can finish so we have
* plenty of room for attrs
*/
- if (dp->i_d.di_forkoff) {
- if (offset < dp->i_d.di_forkoff)
+ if (dp->i_forkoff) {
+ if (offset < dp->i_forkoff)
return 0;
- return dp->i_d.di_forkoff;
+ return dp->i_forkoff;
}
dsize = XFS_BMAP_BROOT_SPACE(mp, dp->i_df.if_broot);
break;
@@ -651,13 +651,8 @@ xfs_attr_shortform_create(
trace_xfs_attr_sf_create(args);
ASSERT(ifp->if_bytes == 0);
- if (ifp->if_format == XFS_DINODE_FMT_EXTENTS) {
- ifp->if_flags &= ~XFS_IFEXTENTS; /* just in case */
+ if (ifp->if_format == XFS_DINODE_FMT_EXTENTS)
ifp->if_format = XFS_DINODE_FMT_LOCAL;
- ifp->if_flags |= XFS_IFINLINE;
- } else {
- ASSERT(ifp->if_flags & XFS_IFINLINE);
- }
xfs_idata_realloc(dp, sizeof(*hdr), XFS_ATTR_FORK);
hdr = (struct xfs_attr_sf_hdr *)ifp->if_u1.if_data;
memset(hdr, 0, sizeof(*hdr));
@@ -730,10 +725,10 @@ xfs_attr_shortform_add(
dp = args->dp;
mp = dp->i_mount;
- dp->i_d.di_forkoff = forkoff;
+ dp->i_forkoff = forkoff;
ifp = dp->i_afp;
- ASSERT(ifp->if_flags & XFS_IFINLINE);
+ ASSERT(ifp->if_format == XFS_DINODE_FMT_LOCAL);
sf = (struct xfs_attr_shortform *)ifp->if_u1.if_data;
if (xfs_attr_sf_findname(args, &sfe, NULL) == -EEXIST)
ASSERT(0);
@@ -770,7 +765,7 @@ xfs_attr_fork_remove(
xfs_idestroy_fork(ip->i_afp);
kmem_cache_free(xfs_ifork_zone, ip->i_afp);
ip->i_afp = NULL;
- ip->i_d.di_forkoff = 0;
+ ip->i_forkoff = 0;
xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
}
@@ -821,8 +816,8 @@ xfs_attr_shortform_remove(
xfs_attr_fork_remove(dp, args->trans);
} else {
xfs_idata_realloc(dp, -size, XFS_ATTR_FORK);
- dp->i_d.di_forkoff = xfs_attr_shortform_bytesfit(dp, totsize);
- ASSERT(dp->i_d.di_forkoff);
+ dp->i_forkoff = xfs_attr_shortform_bytesfit(dp, totsize);
+ ASSERT(dp->i_forkoff);
ASSERT(totsize > sizeof(xfs_attr_sf_hdr_t) ||
(args->op_flags & XFS_DA_OP_ADDNAME) ||
!(mp->m_flags & XFS_MOUNT_ATTR2) ||
@@ -851,7 +846,7 @@ xfs_attr_shortform_lookup(xfs_da_args_t *args)
trace_xfs_attr_sf_lookup(args);
ifp = args->dp->i_afp;
- ASSERT(ifp->if_flags & XFS_IFINLINE);
+ ASSERT(ifp->if_format == XFS_DINODE_FMT_LOCAL);
sf = (struct xfs_attr_shortform *)ifp->if_u1.if_data;
sfe = &sf->list[0];
for (i = 0; i < sf->hdr.count;
@@ -878,7 +873,7 @@ xfs_attr_shortform_getvalue(
struct xfs_attr_sf_entry *sfe;
int i;
- ASSERT(args->dp->i_afp->if_flags == XFS_IFINLINE);
+ ASSERT(args->dp->i_afp->if_format == XFS_DINODE_FMT_LOCAL);
sf = (struct xfs_attr_shortform *)args->dp->i_afp->if_u1.if_data;
sfe = &sf->list[0];
for (i = 0; i < sf->hdr.count;
diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c
index e0905ad171f0..7e3b9b01431e 100644
--- a/fs/xfs/libxfs/xfs_bmap.c
+++ b/fs/xfs/libxfs/xfs_bmap.c
@@ -66,13 +66,13 @@ xfs_bmap_compute_maxlevels(
* either a signed 32-bit number for the data fork, or a signed 16-bit
* number for the attr fork.
*
- * Note that we can no longer assume that if we are in ATTR1 that
- * the fork offset of all the inodes will be
- * (xfs_default_attroffset(ip) >> 3) because we could have mounted
- * with ATTR2 and then mounted back with ATTR1, keeping the
- * di_forkoff's fixed but probably at various positions. Therefore,
- * for both ATTR1 and ATTR2 we have to assume the worst case scenario
- * of a minimum size available.
+ * Note that we can no longer assume that if we are in ATTR1 that the
+ * fork offset of all the inodes will be
+ * (xfs_default_attroffset(ip) >> 3) because we could have mounted with
+ * ATTR2 and then mounted back with ATTR1, keeping the i_forkoff's fixed
+ * but probably at various positions. Therefore, for both ATTR1 and
+ * ATTR2 we have to assume the worst case scenario of a minimum size
+ * available.
*/
if (whichfork == XFS_DATA_FORK) {
maxleafents = MAXEXTNUM;
@@ -94,6 +94,15 @@ xfs_bmap_compute_maxlevels(
mp->m_bm_maxlevels[whichfork] = level;
}
+unsigned int
+xfs_bmap_compute_attr_offset(
+ struct xfs_mount *mp)
+{
+ if (mp->m_sb.sb_inodesize == 256)
+ return XFS_LITINO(mp) - XFS_BMDR_SPACE_CALC(MINABTPTRS);
+ return XFS_BMDR_SPACE_CALC(6 * MINABTPTRS);
+}
+
STATIC int /* error */
xfs_bmbt_lookup_eq(
struct xfs_btree_cur *cur,
@@ -192,22 +201,15 @@ uint
xfs_default_attroffset(
struct xfs_inode *ip)
{
- struct xfs_mount *mp = ip->i_mount;
- uint offset;
-
- if (mp->m_sb.sb_inodesize == 256)
- offset = XFS_LITINO(mp) - XFS_BMDR_SPACE_CALC(MINABTPTRS);
- else
- offset = XFS_BMDR_SPACE_CALC(6 * MINABTPTRS);
-
- ASSERT(offset < XFS_LITINO(mp));
- return offset;
+ if (ip->i_df.if_format == XFS_DINODE_FMT_DEV)
+ return roundup(sizeof(xfs_dev_t), 8);
+ return M_IGEO(ip->i_mount)->attr_fork_offset;
}
/*
- * Helper routine to reset inode di_forkoff field when switching
- * attribute fork from local to extent format - we reset it where
- * possible to make space available for inline data fork extents.
+ * Helper routine to reset inode i_forkoff field when switching attribute fork
+ * from local to extent format - we reset it where possible to make space
+ * available for inline data fork extents.
*/
STATIC void
xfs_bmap_forkoff_reset(
@@ -219,8 +221,8 @@ xfs_bmap_forkoff_reset(
ip->i_df.if_format != XFS_DINODE_FMT_BTREE) {
uint dfl_forkoff = xfs_default_attroffset(ip) >> 3;
- if (dfl_forkoff > ip->i_d.di_forkoff)
- ip->i_d.di_forkoff = dfl_forkoff;
+ if (dfl_forkoff > ip->i_forkoff)
+ ip->i_forkoff = dfl_forkoff;
}
}
@@ -603,7 +605,7 @@ xfs_bmap_btree_to_extents(
ASSERT(cur);
ASSERT(whichfork != XFS_COW_FORK);
- ASSERT(ifp->if_flags & XFS_IFEXTENTS);
+ ASSERT(!xfs_need_iread_extents(ifp));
ASSERT(ifp->if_format == XFS_DINODE_FMT_BTREE);
ASSERT(be16_to_cpu(rblock->bb_level) == 1);
ASSERT(be16_to_cpu(rblock->bb_numrecs) == 1);
@@ -624,14 +626,13 @@ xfs_bmap_btree_to_extents(
return error;
xfs_rmap_ino_bmbt_owner(&oinfo, ip->i_ino, whichfork);
xfs_bmap_add_free(cur->bc_tp, cbno, 1, &oinfo);
- ip->i_d.di_nblocks--;
+ ip->i_nblocks--;
xfs_trans_mod_dquot_byino(tp, ip, XFS_TRANS_DQ_BCOUNT, -1L);
xfs_trans_binval(tp, cbp);
if (cur->bc_bufs[0] == cbp)
cur->bc_bufs[0] = NULL;
xfs_iroot_realloc(ip, -1, whichfork);
ASSERT(ifp->if_broot == NULL);
- ASSERT((ifp->if_flags & XFS_IFBROOT) == 0);
ifp->if_format = XFS_DINODE_FMT_EXTENTS;
*logflagsp |= XFS_ILOG_CORE | xfs_ilog_fext(whichfork);
return 0;
@@ -675,7 +676,6 @@ xfs_bmap_extents_to_btree(
* to expand the root.
*/
xfs_iroot_realloc(ip, 1, whichfork);
- ifp->if_flags |= XFS_IFBROOT;
/*
* Fill in the root.
@@ -726,7 +726,7 @@ xfs_bmap_extents_to_btree(
args.agno >= XFS_FSB_TO_AGNO(mp, tp->t_firstblock));
tp->t_firstblock = args.fsbno;
cur->bc_ino.allocated++;
- ip->i_d.di_nblocks++;
+ ip->i_nblocks++;
xfs_trans_mod_dquot_byino(tp, ip, XFS_TRANS_DQ_BCOUNT, 1L);
error = xfs_trans_get_buf(tp, mp->m_ddev_targp,
XFS_FSB_TO_DADDR(mp, args.fsbno),
@@ -805,8 +805,6 @@ xfs_bmap_local_to_extents_empty(
ASSERT(ifp->if_nextents == 0);
xfs_bmap_forkoff_reset(ip, whichfork);
- ifp->if_flags &= ~XFS_IFINLINE;
- ifp->if_flags |= XFS_IFEXTENTS;
ifp->if_u1.if_root = NULL;
ifp->if_height = 0;
ifp->if_format = XFS_DINODE_FMT_EXTENTS;
@@ -850,7 +848,6 @@ xfs_bmap_local_to_extents(
flags = 0;
error = 0;
- ASSERT((ifp->if_flags & (XFS_IFINLINE|XFS_IFEXTENTS)) == XFS_IFINLINE);
memset(&args, 0, sizeof(args));
args.tp = tp;
args.mp = ip->i_mount;
@@ -908,7 +905,7 @@ xfs_bmap_local_to_extents(
xfs_iext_insert(ip, &icur, &rec, 0);
ifp->if_nextents = 1;
- ip->i_d.di_nblocks = 1;
+ ip->i_nblocks = 1;
xfs_trans_mod_dquot_byino(tp, ip,
XFS_TRANS_DQ_BCOUNT, 1L);
flags |= xfs_ilog_fext(whichfork);
@@ -927,13 +924,15 @@ xfs_bmap_add_attrfork_btree(
xfs_inode_t *ip, /* incore inode pointer */
int *flags) /* inode logging flags */
{
+ struct xfs_btree_block *block = ip->i_df.if_broot;
xfs_btree_cur_t *cur; /* btree cursor */
int error; /* error return value */
xfs_mount_t *mp; /* file system mount struct */
int stat; /* newroot status */
mp = ip->i_mount;
- if (ip->i_df.if_broot_bytes <= XFS_IFORK_DSIZE(ip))
+
+ if (XFS_BMAP_BMDR_SPACE(block) <= XFS_IFORK_DSIZE(ip))
*flags |= XFS_ILOG_DBROOT;
else {
cur = xfs_bmbt_init_cursor(mp, tp, ip, XFS_DATA_FORK);
@@ -1027,23 +1026,27 @@ xfs_bmap_add_attrfork_local(
return -EFSCORRUPTED;
}
-/* Set an inode attr fork off based on the format */
+/*
+ * Set an inode attr fork offset based on the format of the data fork.
+ */
int
xfs_bmap_set_attrforkoff(
struct xfs_inode *ip,
int size,
int *version)
{
+ int default_size = xfs_default_attroffset(ip) >> 3;
+
switch (ip->i_df.if_format) {
case XFS_DINODE_FMT_DEV:
- ip->i_d.di_forkoff = roundup(sizeof(xfs_dev_t), 8) >> 3;
+ ip->i_forkoff = default_size;
break;
case XFS_DINODE_FMT_LOCAL:
case XFS_DINODE_FMT_EXTENTS:
case XFS_DINODE_FMT_BTREE:
- ip->i_d.di_forkoff = xfs_attr_shortform_bytesfit(ip, size);
- if (!ip->i_d.di_forkoff)
- ip->i_d.di_forkoff = xfs_default_attroffset(ip) >> 3;
+ ip->i_forkoff = xfs_attr_shortform_bytesfit(ip, size);
+ if (!ip->i_forkoff)
+ ip->i_forkoff = default_size;
else if ((ip->i_mount->m_flags & XFS_MOUNT_ATTR2) && version)
*version = 2;
break;
@@ -1092,11 +1095,7 @@ xfs_bmap_add_attrfork(
goto trans_cancel;
ASSERT(ip->i_afp == NULL);
- ip->i_afp = kmem_cache_zalloc(xfs_ifork_zone,
- GFP_KERNEL | __GFP_NOFAIL);
-
- ip->i_afp->if_format = XFS_DINODE_FMT_EXTENTS;
- ip->i_afp->if_flags = XFS_IFEXTENTS;
+ ip->i_afp = xfs_ifork_alloc(XFS_DINODE_FMT_EXTENTS, 0);
logflags = 0;
switch (ip->i_df.if_format) {
case XFS_DINODE_FMT_LOCAL:
@@ -1222,12 +1221,10 @@ xfs_iread_extents(
struct xfs_btree_cur *cur;
int error;
- ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL));
+ if (!xfs_need_iread_extents(ifp))
+ return 0;
- if (XFS_IS_CORRUPT(mp, ifp->if_format != XFS_DINODE_FMT_BTREE)) {
- error = -EFSCORRUPTED;
- goto out;
- }
+ ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL));
ir.loaded = 0;
xfs_iext_first(ifp, &ir.icur);
@@ -1243,8 +1240,6 @@ xfs_iread_extents(
goto out;
}
ASSERT(ir.loaded == xfs_iext_count(ifp));
-
- ifp->if_flags |= XFS_IFEXTENTS;
return 0;
out:
xfs_iext_destroy(ifp);
@@ -1279,11 +1274,9 @@ xfs_bmap_first_unused(
ASSERT(xfs_ifork_has_extents(ifp));
- if (!(ifp->if_flags & XFS_IFEXTENTS)) {
- error = xfs_iread_extents(tp, ip, whichfork);
- if (error)
- return error;
- }
+ error = xfs_iread_extents(tp, ip, whichfork);
+ if (error)
+ return error;
lowest = max = *first_unused;
for_each_xfs_iext(ifp, &icur, &got) {
@@ -1331,11 +1324,9 @@ xfs_bmap_last_before(
return -EFSCORRUPTED;
}
- if (!(ifp->if_flags & XFS_IFEXTENTS)) {
- error = xfs_iread_extents(tp, ip, whichfork);
- if (error)
- return error;
- }
+ error = xfs_iread_extents(tp, ip, whichfork);
+ if (error)
+ return error;
if (!xfs_iext_lookup_extent_before(ip, ifp, last_block, &icur, &got))
*last_block = 0;
@@ -1354,11 +1345,9 @@ xfs_bmap_last_extent(
struct xfs_iext_cursor icur;
int error;
- if (!(ifp->if_flags & XFS_IFEXTENTS)) {
- error = xfs_iread_extents(tp, ip, whichfork);
- if (error)
- return error;
- }
+ error = xfs_iread_extents(tp, ip, whichfork);
+ if (error)
+ return error;
xfs_iext_last(ifp, &icur);
if (!xfs_iext_get_extent(ifp, &icur, rec))
@@ -1440,38 +1429,6 @@ xfs_bmap_last_offset(
}
/*
- * Returns whether the selected fork of the inode has exactly one
- * block or not. For the data fork we check this matches di_size,
- * implying the file's range is 0..bsize-1.
- */
-int /* 1=>1 block, 0=>otherwise */
-xfs_bmap_one_block(
- struct xfs_inode *ip, /* incore inode */
- int whichfork) /* data or attr fork */
-{
- struct xfs_ifork *ifp = XFS_IFORK_PTR(ip, whichfork);
- int rval; /* return value */
- struct xfs_bmbt_irec s; /* internal version of extent */
- struct xfs_iext_cursor icur;
-
-#ifndef DEBUG
- if (whichfork == XFS_DATA_FORK)
- return XFS_ISIZE(ip) == ip->i_mount->m_sb.sb_blocksize;
-#endif /* !DEBUG */
- if (ifp->if_nextents != 1)
- return 0;
- if (ifp->if_format != XFS_DINODE_FMT_EXTENTS)
- return 0;
- ASSERT(ifp->if_flags & XFS_IFEXTENTS);
- xfs_iext_first(ifp, &icur);
- xfs_iext_get_extent(ifp, &icur, &s);
- rval = s.br_startoff == 0 && s.br_blockcount == 1;
- if (rval && whichfork == XFS_DATA_FORK)
- ASSERT(XFS_ISIZE(ip) == ip->i_mount->m_sb.sb_blocksize);
- return rval;
-}
-
-/*
* Extent tree manipulation functions used during allocation.
*/
@@ -2938,7 +2895,7 @@ done:
*/
/*
- * Adjust the size of the new extent based on di_extsize and rt extsize.
+ * Adjust the size of the new extent based on i_extsize and rt extsize.
*/
int
xfs_bmap_extsize_align(
@@ -3444,7 +3401,7 @@ xfs_bmap_btalloc_accounting(
}
/* data/attr fork only */
- ap->ip->i_d.di_nblocks += args->len;
+ ap->ip->i_nblocks += args->len;
xfs_trans_log_inode(ap->tp, ap->ip, XFS_ILOG_CORE);
if (ap->wasdel) {
ap->ip->i_delayed_blks -= args->len;
@@ -3586,7 +3543,8 @@ xfs_bmap_exact_minlen_extent_alloc(
args.fsbno = ap->blkno;
args.oinfo = XFS_RMAP_OINFO_SKIP_UPDATE;
args.type = XFS_ALLOCTYPE_FIRST_AG;
- args.total = args.minlen = args.maxlen = ap->minlen;
+ args.minlen = args.maxlen = ap->minlen;
+ args.total = ap->total;
args.alignment = 1;
args.minalignslop = 0;
@@ -3985,11 +3943,9 @@ xfs_bmapi_read(
XFS_STATS_INC(mp, xs_blk_mapr);
- if (!(ifp->if_flags & XFS_IFEXTENTS)) {
- error = xfs_iread_extents(NULL, ip, whichfork);
- if (error)
- return error;
- }
+ error = xfs_iread_extents(NULL, ip, whichfork);
+ if (error)
+ return error;
if (!xfs_iext_lookup_extent(ip, ifp, bno, &icur, &got))
eof = true;
@@ -4227,7 +4183,7 @@ xfs_bmapi_allocate(
return error;
}
- if ((ifp->if_flags & XFS_IFBROOT) && !bma->cur)
+ if (ifp->if_format == XFS_DINODE_FMT_BTREE && !bma->cur)
bma->cur = xfs_bmbt_init_cursor(mp, bma->tp, bma->ip, whichfork);
/*
* Bump the number of extents we've allocated
@@ -4300,7 +4256,7 @@ xfs_bmapi_convert_unwritten(
* Modify (by adding) the state flag, if writing.
*/
ASSERT(mval->br_blockcount <= len);
- if ((ifp->if_flags & XFS_IFBROOT) && !bma->cur) {
+ if (ifp->if_format == XFS_DINODE_FMT_BTREE && !bma->cur) {
bma->cur = xfs_bmbt_init_cursor(bma->ip->i_mount, bma->tp,
bma->ip, whichfork);
}
@@ -4469,11 +4425,9 @@ xfs_bmapi_write(
XFS_STATS_INC(mp, xs_blk_mapw);
- if (!(ifp->if_flags & XFS_IFEXTENTS)) {
- error = xfs_iread_extents(tp, ip, whichfork);
- if (error)
- goto error0;
- }
+ error = xfs_iread_extents(tp, ip, whichfork);
+ if (error)
+ goto error0;
if (!xfs_iext_lookup_extent(ip, ifp, bno, &bma.icur, &bma.got))
eof = true;
@@ -4752,11 +4706,9 @@ xfs_bmapi_remap(
if (XFS_FORCED_SHUTDOWN(mp))
return -EIO;
- if (!(ifp->if_flags & XFS_IFEXTENTS)) {
- error = xfs_iread_extents(tp, ip, whichfork);
- if (error)
- return error;
- }
+ error = xfs_iread_extents(tp, ip, whichfork);
+ if (error)
+ return error;
if (xfs_iext_lookup_extent(ip, ifp, bno, &icur, &got)) {
/* make sure we only reflink into a hole. */
@@ -4764,10 +4716,10 @@ xfs_bmapi_remap(
ASSERT(got.br_startoff - bno >= len);
}
- ip->i_d.di_nblocks += len;
+ ip->i_nblocks += len;
xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
- if (ifp->if_flags & XFS_IFBROOT) {
+ if (ifp->if_format == XFS_DINODE_FMT_BTREE) {
cur = xfs_bmbt_init_cursor(mp, tp, ip, whichfork);
cur->bc_ino.flags = 0;
}
@@ -5355,7 +5307,7 @@ xfs_bmap_del_extent_real(
* Adjust inode # blocks in the file.
*/
if (nblks)
- ip->i_d.di_nblocks -= nblks;
+ ip->i_nblocks -= nblks;
/*
* Adjust quota data.
*/
@@ -5427,9 +5379,10 @@ __xfs_bunmapi(
else
max_len = len;
- if (!(ifp->if_flags & XFS_IFEXTENTS) &&
- (error = xfs_iread_extents(tp, ip, whichfork)))
+ error = xfs_iread_extents(tp, ip, whichfork);
+ if (error)
return error;
+
if (xfs_iext_count(ifp) == 0) {
*rlen = 0;
return 0;
@@ -5445,7 +5398,7 @@ __xfs_bunmapi(
end--;
logflags = 0;
- if (ifp->if_flags & XFS_IFBROOT) {
+ if (ifp->if_format == XFS_DINODE_FMT_BTREE) {
ASSERT(ifp->if_format == XFS_DINODE_FMT_BTREE);
cur = xfs_bmbt_init_cursor(mp, tp, ip, whichfork);
cur->bc_ino.flags = 0;
@@ -5915,13 +5868,11 @@ xfs_bmap_collapse_extents(
ASSERT(xfs_isilocked(ip, XFS_IOLOCK_EXCL | XFS_ILOCK_EXCL));
- if (!(ifp->if_flags & XFS_IFEXTENTS)) {
- error = xfs_iread_extents(tp, ip, whichfork);
- if (error)
- return error;
- }
+ error = xfs_iread_extents(tp, ip, whichfork);
+ if (error)
+ return error;
- if (ifp->if_flags & XFS_IFBROOT) {
+ if (ifp->if_format == XFS_DINODE_FMT_BTREE) {
cur = xfs_bmbt_init_cursor(mp, tp, ip, whichfork);
cur->bc_ino.flags = 0;
}
@@ -6032,13 +5983,11 @@ xfs_bmap_insert_extents(
ASSERT(xfs_isilocked(ip, XFS_IOLOCK_EXCL | XFS_ILOCK_EXCL));
- if (!(ifp->if_flags & XFS_IFEXTENTS)) {
- error = xfs_iread_extents(tp, ip, whichfork);
- if (error)
- return error;
- }
+ error = xfs_iread_extents(tp, ip, whichfork);
+ if (error)
+ return error;
- if (ifp->if_flags & XFS_IFBROOT) {
+ if (ifp->if_format == XFS_DINODE_FMT_BTREE) {
cur = xfs_bmbt_init_cursor(mp, tp, ip, whichfork);
cur->bc_ino.flags = 0;
}
@@ -6135,12 +6084,10 @@ xfs_bmap_split_extent(
if (XFS_FORCED_SHUTDOWN(mp))
return -EIO;
- if (!(ifp->if_flags & XFS_IFEXTENTS)) {
- /* Read in all the extents */
- error = xfs_iread_extents(tp, ip, whichfork);
- if (error)
- return error;
- }
+ /* Read in all the extents */
+ error = xfs_iread_extents(tp, ip, whichfork);
+ if (error)
+ return error;
/*
* If there are not extents, or split_fsb lies in a hole we are done.
@@ -6155,7 +6102,7 @@ xfs_bmap_split_extent(
new.br_blockcount = got.br_blockcount - gotblkcnt;
new.br_state = got.br_state;
- if (ifp->if_flags & XFS_IFBROOT) {
+ if (ifp->if_format == XFS_DINODE_FMT_BTREE) {
cur = xfs_bmbt_init_cursor(mp, tp, ip, whichfork);
cur->bc_ino.flags = 0;
error = xfs_bmbt_lookup_eq(cur, &got, &i);
diff --git a/fs/xfs/libxfs/xfs_bmap.h b/fs/xfs/libxfs/xfs_bmap.h
index 6747e97a7949..f9a390ecfb1d 100644
--- a/fs/xfs/libxfs/xfs_bmap.h
+++ b/fs/xfs/libxfs/xfs_bmap.h
@@ -185,6 +185,7 @@ static inline bool xfs_bmap_is_written_extent(struct xfs_bmbt_irec *irec)
void xfs_trim_extent(struct xfs_bmbt_irec *irec, xfs_fileoff_t bno,
xfs_filblks_t len);
+unsigned int xfs_bmap_compute_attr_offset(struct xfs_mount *mp);
int xfs_bmap_add_attrfork(struct xfs_inode *ip, int size, int rsvd);
int xfs_bmap_set_attrforkoff(struct xfs_inode *ip, int size, int *version);
void xfs_bmap_local_to_extents_empty(struct xfs_trans *tp,
@@ -199,7 +200,6 @@ int xfs_bmap_last_before(struct xfs_trans *tp, struct xfs_inode *ip,
xfs_fileoff_t *last_block, int whichfork);
int xfs_bmap_last_offset(struct xfs_inode *ip, xfs_fileoff_t *unused,
int whichfork);
-int xfs_bmap_one_block(struct xfs_inode *ip, int whichfork);
int xfs_bmapi_read(struct xfs_inode *ip, xfs_fileoff_t bno,
xfs_filblks_t len, struct xfs_bmbt_irec *mval,
int *nmap, int flags);
diff --git a/fs/xfs/libxfs/xfs_bmap_btree.c b/fs/xfs/libxfs/xfs_bmap_btree.c
index 976659190d27..1ceba020940e 100644
--- a/fs/xfs/libxfs/xfs_bmap_btree.c
+++ b/fs/xfs/libxfs/xfs_bmap_btree.c
@@ -183,7 +183,7 @@ xfs_bmbt_update_cursor(
struct xfs_btree_cur *dst)
{
ASSERT((dst->bc_tp->t_firstblock != NULLFSBLOCK) ||
- (dst->bc_ino.ip->i_d.di_flags & XFS_DIFLAG_REALTIME));
+ (dst->bc_ino.ip->i_diflags & XFS_DIFLAG_REALTIME));
dst->bc_ino.allocated += src->bc_ino.allocated;
dst->bc_tp->t_firstblock = src->bc_tp->t_firstblock;
@@ -260,7 +260,7 @@ xfs_bmbt_alloc_block(
ASSERT(args.len == 1);
cur->bc_tp->t_firstblock = args.fsbno;
cur->bc_ino.allocated++;
- cur->bc_ino.ip->i_d.di_nblocks++;
+ cur->bc_ino.ip->i_nblocks++;
xfs_trans_log_inode(args.tp, cur->bc_ino.ip, XFS_ILOG_CORE);
xfs_trans_mod_dquot_byino(args.tp, cur->bc_ino.ip,
XFS_TRANS_DQ_BCOUNT, 1L);
@@ -287,7 +287,7 @@ xfs_bmbt_free_block(
xfs_rmap_ino_bmbt_owner(&oinfo, ip->i_ino, cur->bc_ino.whichfork);
xfs_bmap_add_free(cur->bc_tp, fsbno, 1, &oinfo);
- ip->i_d.di_nblocks--;
+ ip->i_nblocks--;
xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
xfs_trans_mod_dquot_byino(tp, ip, XFS_TRANS_DQ_BCOUNT, -1L);
diff --git a/fs/xfs/libxfs/xfs_btree_staging.c b/fs/xfs/libxfs/xfs_btree_staging.c
index f464a7c7cf22..aa8dc9521c39 100644
--- a/fs/xfs/libxfs/xfs_btree_staging.c
+++ b/fs/xfs/libxfs/xfs_btree_staging.c
@@ -387,7 +387,6 @@ xfs_btree_bload_prep_block(
new_size = bbl->iroot_size(cur, nr_this_block, priv);
ifp->if_broot = kmem_zalloc(new_size, 0);
ifp->if_broot_bytes = (int)new_size;
- ifp->if_flags |= XFS_IFBROOT;
/* Initialize it and send it out. */
xfs_btree_init_block_int(cur->bc_mp, ifp->if_broot,
diff --git a/fs/xfs/libxfs/xfs_da_btree.c b/fs/xfs/libxfs/xfs_da_btree.c
index e46bc03365db..83ac9771bfb5 100644
--- a/fs/xfs/libxfs/xfs_da_btree.c
+++ b/fs/xfs/libxfs/xfs_da_btree.c
@@ -2145,7 +2145,7 @@ xfs_da_grow_inode_int(
struct xfs_trans *tp = args->trans;
struct xfs_inode *dp = args->dp;
int w = args->whichfork;
- xfs_rfsblock_t nblks = dp->i_d.di_nblocks;
+ xfs_rfsblock_t nblks = dp->i_nblocks;
struct xfs_bmbt_irec map, *mapp;
int nmap, error, got, i, mapi;
@@ -2211,7 +2211,7 @@ xfs_da_grow_inode_int(
}
/* account for newly allocated blocks in reserved blocks total */
- args->total -= dp->i_d.di_nblocks - nblks;
+ args->total -= dp->i_nblocks - nblks;
out_free_map:
if (mapp != &map)
diff --git a/fs/xfs/libxfs/xfs_dir2.c b/fs/xfs/libxfs/xfs_dir2.c
index 612a9c5e41b1..050bdcc4fe73 100644
--- a/fs/xfs/libxfs/xfs_dir2.c
+++ b/fs/xfs/libxfs/xfs_dir2.c
@@ -179,9 +179,9 @@ xfs_dir_isempty(
xfs_dir2_sf_hdr_t *sfp;
ASSERT(S_ISDIR(VFS_I(dp)->i_mode));
- if (dp->i_d.di_size == 0) /* might happen during shutdown. */
+ if (dp->i_disk_size == 0) /* might happen during shutdown. */
return 1;
- if (dp->i_d.di_size > XFS_IFORK_DSIZE(dp))
+ if (dp->i_disk_size > XFS_IFORK_DSIZE(dp))
return 0;
sfp = (xfs_dir2_sf_hdr_t *)dp->i_df.if_u1.if_data;
return !sfp->count;
@@ -584,8 +584,8 @@ xfs_dir2_grow_inode(
xfs_fsize_t size; /* directory file (data) size */
size = XFS_FSB_TO_B(mp, bno + count);
- if (size > dp->i_d.di_size) {
- dp->i_d.di_size = size;
+ if (size > dp->i_disk_size) {
+ dp->i_disk_size = size;
xfs_trans_log_inode(args->trans, dp, XFS_ILOG_CORE);
}
}
@@ -608,7 +608,7 @@ xfs_dir2_isblock(
rval = XFS_FSB_TO_B(args->dp->i_mount, last) == args->geo->blksize;
if (XFS_IS_CORRUPT(args->dp->i_mount,
rval != 0 &&
- args->dp->i_d.di_size != args->geo->blksize))
+ args->dp->i_disk_size != args->geo->blksize))
return -EFSCORRUPTED;
*vp = rval;
return 0;
@@ -687,7 +687,7 @@ xfs_dir2_shrink_inode(
/*
* If the block isn't the last one in the directory, we're done.
*/
- if (dp->i_d.di_size > xfs_dir2_db_off_to_byte(args->geo, db + 1, 0))
+ if (dp->i_disk_size > xfs_dir2_db_off_to_byte(args->geo, db + 1, 0))
return 0;
bno = da;
if ((error = xfs_bmap_last_before(tp, dp, &bno, XFS_DATA_FORK))) {
@@ -703,7 +703,7 @@ xfs_dir2_shrink_inode(
/*
* Set the size to the new last block.
*/
- dp->i_d.di_size = XFS_FSB_TO_B(mp, bno);
+ dp->i_disk_size = XFS_FSB_TO_B(mp, bno);
xfs_trans_log_inode(tp, dp, XFS_ILOG_CORE);
return 0;
}
diff --git a/fs/xfs/libxfs/xfs_dir2_block.c b/fs/xfs/libxfs/xfs_dir2_block.c
index 5b59d3f7746b..75e1421f69c4 100644
--- a/fs/xfs/libxfs/xfs_dir2_block.c
+++ b/fs/xfs/libxfs/xfs_dir2_block.c
@@ -961,7 +961,7 @@ xfs_dir2_leaf_to_block(
* been left behind during no-space-reservation operations.
* These will show up in the leaf bests table.
*/
- while (dp->i_d.di_size > args->geo->blksize) {
+ while (dp->i_disk_size > args->geo->blksize) {
int hdrsz;
hdrsz = args->geo->data_entry_offset;
@@ -1096,14 +1096,14 @@ xfs_dir2_sf_to_block(
trace_xfs_dir2_sf_to_block(args);
- ASSERT(ifp->if_flags & XFS_IFINLINE);
- ASSERT(dp->i_d.di_size >= offsetof(struct xfs_dir2_sf_hdr, parent));
+ ASSERT(ifp->if_format == XFS_DINODE_FMT_LOCAL);
+ ASSERT(dp->i_disk_size >= offsetof(struct xfs_dir2_sf_hdr, parent));
oldsfp = (xfs_dir2_sf_hdr_t *)ifp->if_u1.if_data;
- ASSERT(ifp->if_bytes == dp->i_d.di_size);
+ ASSERT(ifp->if_bytes == dp->i_disk_size);
ASSERT(ifp->if_u1.if_data != NULL);
- ASSERT(dp->i_d.di_size >= xfs_dir2_sf_hdr_size(oldsfp->i8count));
+ ASSERT(dp->i_disk_size >= xfs_dir2_sf_hdr_size(oldsfp->i8count));
ASSERT(dp->i_df.if_nextents == 0);
/*
@@ -1115,7 +1115,7 @@ xfs_dir2_sf_to_block(
xfs_idata_realloc(dp, -ifp->if_bytes, XFS_DATA_FORK);
xfs_bmap_local_to_extents_empty(tp, dp, XFS_DATA_FORK);
- dp->i_d.di_size = 0;
+ dp->i_disk_size = 0;
/*
* Add block 0 to the inode.
diff --git a/fs/xfs/libxfs/xfs_dir2_data.c b/fs/xfs/libxfs/xfs_dir2_data.c
index 375b3edb2ad2..e67fa086f2c1 100644
--- a/fs/xfs/libxfs/xfs_dir2_data.c
+++ b/fs/xfs/libxfs/xfs_dir2_data.c
@@ -218,7 +218,7 @@ __xfs_dir3_data_check(
*/
if (dep->namelen == 0)
return __this_address;
- if (xfs_dir_ino_validate(mp, be64_to_cpu(dep->inumber)))
+ if (!xfs_verify_dir_ino(mp, be64_to_cpu(dep->inumber)))
return __this_address;
if (offset + xfs_dir2_data_entsize(mp, dep->namelen) > end)
return __this_address;
diff --git a/fs/xfs/libxfs/xfs_dir2_leaf.c b/fs/xfs/libxfs/xfs_dir2_leaf.c
index 95d2a3f92d75..5369d8bb2593 100644
--- a/fs/xfs/libxfs/xfs_dir2_leaf.c
+++ b/fs/xfs/libxfs/xfs_dir2_leaf.c
@@ -113,7 +113,7 @@ xfs_dir3_leaf1_check(
} else if (leafhdr.magic != XFS_DIR2_LEAF1_MAGIC)
return __this_address;
- return xfs_dir3_leaf_check_int(dp->i_mount, &leafhdr, leaf);
+ return xfs_dir3_leaf_check_int(dp->i_mount, &leafhdr, leaf, false);
}
static inline void
@@ -139,7 +139,8 @@ xfs_failaddr_t
xfs_dir3_leaf_check_int(
struct xfs_mount *mp,
struct xfs_dir3_icleaf_hdr *hdr,
- struct xfs_dir2_leaf *leaf)
+ struct xfs_dir2_leaf *leaf,
+ bool expensive_checking)
{
struct xfs_da_geometry *geo = mp->m_dir_geo;
xfs_dir2_leaf_tail_t *ltp;
@@ -151,7 +152,7 @@ xfs_dir3_leaf_check_int(
/*
* XXX (dgc): This value is not restrictive enough.
* Should factor in the size of the bests table as well.
- * We can deduce a value for that from di_size.
+ * We can deduce a value for that from i_disk_size.
*/
if (hdr->count > geo->leaf_max_ents)
return __this_address;
@@ -162,6 +163,9 @@ xfs_dir3_leaf_check_int(
(char *)&hdr->ents[hdr->count] > (char *)xfs_dir2_leaf_bests_p(ltp))
return __this_address;
+ if (!expensive_checking)
+ return NULL;
+
/* Check hash value order, count stale entries. */
for (i = stale = 0; i < hdr->count; i++) {
if (i + 1 < hdr->count) {
@@ -195,7 +199,7 @@ xfs_dir3_leaf_verify(
return fa;
xfs_dir2_leaf_hdr_from_disk(mp, &leafhdr, bp->b_addr);
- return xfs_dir3_leaf_check_int(mp, &leafhdr, bp->b_addr);
+ return xfs_dir3_leaf_check_int(mp, &leafhdr, bp->b_addr, true);
}
static void
diff --git a/fs/xfs/libxfs/xfs_dir2_node.c b/fs/xfs/libxfs/xfs_dir2_node.c
index 5d51265d29d6..d0520afb913a 100644
--- a/fs/xfs/libxfs/xfs_dir2_node.c
+++ b/fs/xfs/libxfs/xfs_dir2_node.c
@@ -73,7 +73,7 @@ xfs_dir3_leafn_check(
} else if (leafhdr.magic != XFS_DIR2_LEAFN_MAGIC)
return __this_address;
- return xfs_dir3_leaf_check_int(dp->i_mount, &leafhdr, leaf);
+ return xfs_dir3_leaf_check_int(dp->i_mount, &leafhdr, leaf, false);
}
static inline void
@@ -441,7 +441,7 @@ xfs_dir2_leaf_to_node(
leaf = lbp->b_addr;
ltp = xfs_dir2_leaf_tail_p(args->geo, leaf);
if (be32_to_cpu(ltp->bestcount) >
- (uint)dp->i_d.di_size / args->geo->blksize) {
+ (uint)dp->i_disk_size / args->geo->blksize) {
xfs_buf_mark_corrupt(lbp);
return -EFSCORRUPTED;
}
diff --git a/fs/xfs/libxfs/xfs_dir2_priv.h b/fs/xfs/libxfs/xfs_dir2_priv.h
index 44c6a77cba05..94943ce49cab 100644
--- a/fs/xfs/libxfs/xfs_dir2_priv.h
+++ b/fs/xfs/libxfs/xfs_dir2_priv.h
@@ -127,7 +127,8 @@ xfs_dir3_leaf_find_entry(struct xfs_dir3_icleaf_hdr *leafhdr,
extern int xfs_dir2_node_to_leaf(struct xfs_da_state *state);
extern xfs_failaddr_t xfs_dir3_leaf_check_int(struct xfs_mount *mp,
- struct xfs_dir3_icleaf_hdr *hdr, struct xfs_dir2_leaf *leaf);
+ struct xfs_dir3_icleaf_hdr *hdr, struct xfs_dir2_leaf *leaf,
+ bool expensive_checks);
/* xfs_dir2_node.c */
void xfs_dir2_free_hdr_from_disk(struct xfs_mount *mp,
diff --git a/fs/xfs/libxfs/xfs_dir2_sf.c b/fs/xfs/libxfs/xfs_dir2_sf.c
index 8c4f76bba88b..46d18bf9d5e1 100644
--- a/fs/xfs/libxfs/xfs_dir2_sf.c
+++ b/fs/xfs/libxfs/xfs_dir2_sf.c
@@ -344,7 +344,7 @@ xfs_dir2_block_to_sf(
ASSERT(dp->i_df.if_bytes == 0);
xfs_init_local_fork(dp, XFS_DATA_FORK, sfp, size);
dp->i_df.if_format = XFS_DINODE_FMT_LOCAL;
- dp->i_d.di_size = size;
+ dp->i_disk_size = size;
logflags |= XFS_ILOG_DDATA;
xfs_dir2_sf_check(args);
@@ -367,7 +367,7 @@ xfs_dir2_sf_addname(
xfs_inode_t *dp; /* incore directory inode */
int error; /* error return value */
int incr_isize; /* total change in size */
- int new_isize; /* di_size after adding name */
+ int new_isize; /* size after adding name */
int objchange; /* changing to 8-byte inodes */
xfs_dir2_data_aoff_t offset = 0; /* offset for new entry */
int pick; /* which algorithm to use */
@@ -378,12 +378,12 @@ xfs_dir2_sf_addname(
ASSERT(xfs_dir2_sf_lookup(args) == -ENOENT);
dp = args->dp;
- ASSERT(dp->i_df.if_flags & XFS_IFINLINE);
- ASSERT(dp->i_d.di_size >= offsetof(struct xfs_dir2_sf_hdr, parent));
- ASSERT(dp->i_df.if_bytes == dp->i_d.di_size);
+ ASSERT(dp->i_df.if_format == XFS_DINODE_FMT_LOCAL);
+ ASSERT(dp->i_disk_size >= offsetof(struct xfs_dir2_sf_hdr, parent));
+ ASSERT(dp->i_df.if_bytes == dp->i_disk_size);
ASSERT(dp->i_df.if_u1.if_data != NULL);
sfp = (xfs_dir2_sf_hdr_t *)dp->i_df.if_u1.if_data;
- ASSERT(dp->i_d.di_size >= xfs_dir2_sf_hdr_size(sfp->i8count));
+ ASSERT(dp->i_disk_size >= xfs_dir2_sf_hdr_size(sfp->i8count));
/*
* Compute entry (and change in) size.
*/
@@ -401,7 +401,7 @@ xfs_dir2_sf_addname(
objchange = 1;
}
- new_isize = (int)dp->i_d.di_size + incr_isize;
+ new_isize = (int)dp->i_disk_size + incr_isize;
/*
* Won't fit as shortform any more (due to size),
* or the pick routine says it won't (due to offset values).
@@ -492,7 +492,7 @@ xfs_dir2_sf_addname_easy(
sfp->count++;
if (args->inumber > XFS_DIR2_MAX_SHORT_INUM)
sfp->i8count++;
- dp->i_d.di_size = new_isize;
+ dp->i_disk_size = new_isize;
xfs_dir2_sf_check(args);
}
@@ -519,7 +519,7 @@ xfs_dir2_sf_addname_hard(
int nbytes; /* temp for byte copies */
xfs_dir2_data_aoff_t new_offset; /* next offset value */
xfs_dir2_data_aoff_t offset; /* current offset value */
- int old_isize; /* previous di_size */
+ int old_isize; /* previous size */
xfs_dir2_sf_entry_t *oldsfep; /* entry in original dir */
xfs_dir2_sf_hdr_t *oldsfp; /* original shortform dir */
xfs_dir2_sf_entry_t *sfep; /* entry in new dir */
@@ -529,7 +529,7 @@ xfs_dir2_sf_addname_hard(
* Copy the old directory to the stack buffer.
*/
sfp = (xfs_dir2_sf_hdr_t *)dp->i_df.if_u1.if_data;
- old_isize = (int)dp->i_d.di_size;
+ old_isize = (int)dp->i_disk_size;
buf = kmem_alloc(old_isize, 0);
oldsfp = (xfs_dir2_sf_hdr_t *)buf;
memcpy(oldsfp, sfp, old_isize);
@@ -586,7 +586,7 @@ xfs_dir2_sf_addname_hard(
memcpy(sfep, oldsfep, old_isize - nbytes);
}
kmem_free(buf);
- dp->i_d.di_size = new_isize;
+ dp->i_disk_size = new_isize;
xfs_dir2_sf_check(args);
}
@@ -697,7 +697,7 @@ xfs_dir2_sf_check(
ASSERT(xfs_dir2_sf_get_ftype(mp, sfep) < XFS_DIR3_FT_MAX);
}
ASSERT(i8count == sfp->i8count);
- ASSERT((char *)sfep - (char *)sfp == dp->i_d.di_size);
+ ASSERT((char *)sfep - (char *)sfp == dp->i_disk_size);
ASSERT(offset +
(sfp->count + 2) * (uint)sizeof(xfs_dir2_leaf_entry_t) +
(uint)sizeof(xfs_dir2_block_tail_t) <= args->geo->blksize);
@@ -821,18 +821,16 @@ xfs_dir2_sf_create(
dp = args->dp;
ASSERT(dp != NULL);
- ASSERT(dp->i_d.di_size == 0);
+ ASSERT(dp->i_disk_size == 0);
/*
* If it's currently a zero-length extent file,
* convert it to local format.
*/
if (dp->i_df.if_format == XFS_DINODE_FMT_EXTENTS) {
- dp->i_df.if_flags &= ~XFS_IFEXTENTS; /* just in case */
dp->i_df.if_format = XFS_DINODE_FMT_LOCAL;
xfs_trans_log_inode(args->trans, dp, XFS_ILOG_CORE);
- dp->i_df.if_flags |= XFS_IFINLINE;
}
- ASSERT(dp->i_df.if_flags & XFS_IFINLINE);
+ ASSERT(dp->i_df.if_format == XFS_DINODE_FMT_LOCAL);
ASSERT(dp->i_df.if_bytes == 0);
i8count = pino > XFS_DIR2_MAX_SHORT_INUM;
size = xfs_dir2_sf_hdr_size(i8count);
@@ -850,7 +848,7 @@ xfs_dir2_sf_create(
*/
xfs_dir2_sf_put_parent_ino(sfp, pino);
sfp->count = 0;
- dp->i_d.di_size = size;
+ dp->i_disk_size = size;
xfs_dir2_sf_check(args);
xfs_trans_log_inode(args->trans, dp, XFS_ILOG_CORE | XFS_ILOG_DDATA);
return 0;
@@ -877,12 +875,12 @@ xfs_dir2_sf_lookup(
xfs_dir2_sf_check(args);
- ASSERT(dp->i_df.if_flags & XFS_IFINLINE);
- ASSERT(dp->i_d.di_size >= offsetof(struct xfs_dir2_sf_hdr, parent));
- ASSERT(dp->i_df.if_bytes == dp->i_d.di_size);
+ ASSERT(dp->i_df.if_format == XFS_DINODE_FMT_LOCAL);
+ ASSERT(dp->i_disk_size >= offsetof(struct xfs_dir2_sf_hdr, parent));
+ ASSERT(dp->i_df.if_bytes == dp->i_disk_size);
ASSERT(dp->i_df.if_u1.if_data != NULL);
sfp = (xfs_dir2_sf_hdr_t *)dp->i_df.if_u1.if_data;
- ASSERT(dp->i_d.di_size >= xfs_dir2_sf_hdr_size(sfp->i8count));
+ ASSERT(dp->i_disk_size >= xfs_dir2_sf_hdr_size(sfp->i8count));
/*
* Special case for .
*/
@@ -954,8 +952,8 @@ xfs_dir2_sf_removename(
trace_xfs_dir2_sf_removename(args);
- ASSERT(dp->i_df.if_flags & XFS_IFINLINE);
- oldsize = (int)dp->i_d.di_size;
+ ASSERT(dp->i_df.if_format == XFS_DINODE_FMT_LOCAL);
+ oldsize = (int)dp->i_disk_size;
ASSERT(oldsize >= offsetof(struct xfs_dir2_sf_hdr, parent));
ASSERT(dp->i_df.if_bytes == oldsize);
ASSERT(dp->i_df.if_u1.if_data != NULL);
@@ -995,7 +993,7 @@ xfs_dir2_sf_removename(
* Fix up the header and file size.
*/
sfp->count--;
- dp->i_d.di_size = newsize;
+ dp->i_disk_size = newsize;
/*
* Reallocate, making it smaller.
*/
@@ -1053,12 +1051,12 @@ xfs_dir2_sf_replace(
trace_xfs_dir2_sf_replace(args);
- ASSERT(dp->i_df.if_flags & XFS_IFINLINE);
- ASSERT(dp->i_d.di_size >= offsetof(struct xfs_dir2_sf_hdr, parent));
- ASSERT(dp->i_df.if_bytes == dp->i_d.di_size);
+ ASSERT(dp->i_df.if_format == XFS_DINODE_FMT_LOCAL);
+ ASSERT(dp->i_disk_size >= offsetof(struct xfs_dir2_sf_hdr, parent));
+ ASSERT(dp->i_df.if_bytes == dp->i_disk_size);
ASSERT(dp->i_df.if_u1.if_data != NULL);
sfp = (xfs_dir2_sf_hdr_t *)dp->i_df.if_u1.if_data;
- ASSERT(dp->i_d.di_size >= xfs_dir2_sf_hdr_size(sfp->i8count));
+ ASSERT(dp->i_disk_size >= xfs_dir2_sf_hdr_size(sfp->i8count));
/*
* New inode number is large, and need to convert to 8-byte inodes.
@@ -1219,7 +1217,7 @@ xfs_dir2_sf_toino4(
* Clean up the inode.
*/
kmem_free(buf);
- dp->i_d.di_size = newsize;
+ dp->i_disk_size = newsize;
xfs_trans_log_inode(args->trans, dp, XFS_ILOG_CORE | XFS_ILOG_DDATA);
}
@@ -1292,6 +1290,6 @@ xfs_dir2_sf_toino8(
* Clean up the inode.
*/
kmem_free(buf);
- dp->i_d.di_size = newsize;
+ dp->i_disk_size = newsize;
xfs_trans_log_inode(args->trans, dp, XFS_ILOG_CORE | XFS_ILOG_DDATA);
}
diff --git a/fs/xfs/libxfs/xfs_errortag.h b/fs/xfs/libxfs/xfs_errortag.h
index 6ca9084b6934..a23a52e643ad 100644
--- a/fs/xfs/libxfs/xfs_errortag.h
+++ b/fs/xfs/libxfs/xfs_errortag.h
@@ -58,7 +58,8 @@
#define XFS_ERRTAG_BUF_IOERROR 35
#define XFS_ERRTAG_REDUCE_MAX_IEXTENTS 36
#define XFS_ERRTAG_BMAP_ALLOC_MINLEN_EXTENT 37
-#define XFS_ERRTAG_MAX 38
+#define XFS_ERRTAG_AG_RESV_FAIL 38
+#define XFS_ERRTAG_MAX 39
/*
* Random factors for above tags, 1 means always, 2 means 1/2 time, etc.
@@ -101,5 +102,6 @@
#define XFS_RANDOM_BUF_IOERROR XFS_RANDOM_DEFAULT
#define XFS_RANDOM_REDUCE_MAX_IEXTENTS 1
#define XFS_RANDOM_BMAP_ALLOC_MINLEN_EXTENT 1
+#define XFS_RANDOM_AG_RESV_FAIL 1
#endif /* __XFS_ERRORTAG_H_ */
diff --git a/fs/xfs/libxfs/xfs_format.h b/fs/xfs/libxfs/xfs_format.h
index 630388b72dbe..76e2461b9e66 100644
--- a/fs/xfs/libxfs/xfs_format.h
+++ b/fs/xfs/libxfs/xfs_format.h
@@ -955,9 +955,8 @@ static inline time64_t xfs_bigtime_to_unix(uint64_t ondisk_seconds)
* attribute use the XFS_DFORK_DPTR, XFS_DFORK_APTR, and XFS_DFORK_PTR macros
* below.
*
- * There is a very similar struct icdinode in xfs_inode which matches the
- * layout of the first 96 bytes of this structure, but is kept in native
- * format instead of big endian.
+ * There is a very similar struct xfs_log_dinode which matches the layout of
+ * this structure, but is kept in native format instead of big endian.
*
* Note: di_flushiter is only used by v1/2 inodes - it's effectively a zeroed
* padding field for v3 inodes.
diff --git a/fs/xfs/libxfs/xfs_fs.h b/fs/xfs/libxfs/xfs_fs.h
index 6fad140d4c8e..a83bdd0c47a8 100644
--- a/fs/xfs/libxfs/xfs_fs.h
+++ b/fs/xfs/libxfs/xfs_fs.h
@@ -65,7 +65,7 @@ struct getbmapx {
/* bmv_iflags values - set by XFS_IOC_GETBMAPX caller. */
#define BMV_IF_ATTRFORK 0x1 /* return attr fork rather than data */
-#define BMV_IF_NO_DMAPI_READ 0x2 /* Do not generate DMAPI read event */
+#define BMV_IF_NO_DMAPI_READ 0x2 /* Deprecated */
#define BMV_IF_PREALLOC 0x4 /* rtn status BMV_OF_PREALLOC if req */
#define BMV_IF_DELALLOC 0x8 /* rtn status BMV_OF_DELALLOC if req */
#define BMV_IF_NO_HOLES 0x10 /* Do not return holes */
@@ -770,8 +770,6 @@ struct xfs_scrub_metadata {
/*
* ioctl commands that are used by Linux filesystems
*/
-#define XFS_IOC_GETXFLAGS FS_IOC_GETFLAGS
-#define XFS_IOC_SETXFLAGS FS_IOC_SETFLAGS
#define XFS_IOC_GETVERSION FS_IOC_GETVERSION
/*
@@ -782,8 +780,6 @@ struct xfs_scrub_metadata {
#define XFS_IOC_ALLOCSP _IOW ('X', 10, struct xfs_flock64)
#define XFS_IOC_FREESP _IOW ('X', 11, struct xfs_flock64)
#define XFS_IOC_DIOINFO _IOR ('X', 30, struct dioattr)
-#define XFS_IOC_FSGETXATTR FS_IOC_FSGETXATTR
-#define XFS_IOC_FSSETXATTR FS_IOC_FSSETXATTR
#define XFS_IOC_ALLOCSP64 _IOW ('X', 36, struct xfs_flock64)
#define XFS_IOC_FREESP64 _IOW ('X', 37, struct xfs_flock64)
#define XFS_IOC_GETBMAP _IOWR('X', 38, struct getbmap)
diff --git a/fs/xfs/libxfs/xfs_ialloc.c b/fs/xfs/libxfs/xfs_ialloc.c
index 69b228fce81a..eefdb518fe64 100644
--- a/fs/xfs/libxfs/xfs_ialloc.c
+++ b/fs/xfs/libxfs/xfs_ialloc.c
@@ -2535,12 +2535,12 @@ xfs_agi_verify(
return __this_address;
if (be32_to_cpu(agi->agi_level) < 1 ||
- be32_to_cpu(agi->agi_level) > XFS_BTREE_MAXLEVELS)
+ be32_to_cpu(agi->agi_level) > M_IGEO(mp)->inobt_maxlevels)
return __this_address;
if (xfs_sb_version_hasfinobt(&mp->m_sb) &&
(be32_to_cpu(agi->agi_free_level) < 1 ||
- be32_to_cpu(agi->agi_free_level) > XFS_BTREE_MAXLEVELS))
+ be32_to_cpu(agi->agi_free_level) > M_IGEO(mp)->inobt_maxlevels))
return __this_address;
/*
diff --git a/fs/xfs/libxfs/xfs_iext_tree.c b/fs/xfs/libxfs/xfs_iext_tree.c
index b4164256993d..773cf4349428 100644
--- a/fs/xfs/libxfs/xfs_iext_tree.c
+++ b/fs/xfs/libxfs/xfs_iext_tree.c
@@ -8,9 +8,9 @@
#include "xfs_format.h"
#include "xfs_bit.h"
#include "xfs_log_format.h"
-#include "xfs_inode.h"
#include "xfs_trans_resv.h"
#include "xfs_mount.h"
+#include "xfs_inode.h"
#include "xfs_trace.h"
/*
diff --git a/fs/xfs/libxfs/xfs_inode_buf.c b/fs/xfs/libxfs/xfs_inode_buf.c
index 4d7410e49db4..5c9a7440d9e4 100644
--- a/fs/xfs/libxfs/xfs_inode_buf.c
+++ b/fs/xfs/libxfs/xfs_inode_buf.c
@@ -124,37 +124,18 @@ const struct xfs_buf_ops xfs_inode_buf_ra_ops = {
/*
* This routine is called to map an inode to the buffer containing the on-disk
* version of the inode. It returns a pointer to the buffer containing the
- * on-disk inode in the bpp parameter, and in the dipp parameter it returns a
- * pointer to the on-disk inode within that buffer.
- *
- * If a non-zero error is returned, then the contents of bpp and dipp are
- * undefined.
+ * on-disk inode in the bpp parameter.
*/
int
xfs_imap_to_bp(
struct xfs_mount *mp,
struct xfs_trans *tp,
struct xfs_imap *imap,
- struct xfs_dinode **dipp,
- struct xfs_buf **bpp,
- uint buf_flags)
+ struct xfs_buf **bpp)
{
- struct xfs_buf *bp;
- int error;
-
- buf_flags |= XBF_UNMAPPED;
- error = xfs_trans_read_buf(mp, tp, mp->m_ddev_targp, imap->im_blkno,
- (int)imap->im_len, buf_flags, &bp,
+ return xfs_trans_read_buf(mp, tp, mp->m_ddev_targp, imap->im_blkno,
+ imap->im_len, XBF_UNMAPPED, bpp,
&xfs_inode_buf_ops);
- if (error) {
- ASSERT(error != -EAGAIN || (buf_flags & XBF_TRYLOCK));
- return error;
- }
-
- *bpp = bp;
- if (dipp)
- *dipp = xfs_buf_offset(bp, imap->im_boffset);
- return 0;
}
static inline struct timespec64 xfs_inode_decode_bigtime(uint64_t ts)
@@ -192,7 +173,6 @@ xfs_inode_from_disk(
struct xfs_inode *ip,
struct xfs_dinode *from)
{
- struct xfs_icdinode *to = &ip->i_d;
struct inode *inode = VFS_I(ip);
int error;
xfs_failaddr_t fa;
@@ -212,7 +192,8 @@ xfs_inode_from_disk(
* inode. If the inode is unused, mode is zero and we shouldn't mess
* with the uninitialized part of it.
*/
- to->di_flushiter = be16_to_cpu(from->di_flushiter);
+ if (!xfs_sb_version_has_v3inode(&ip->i_mount->m_sb))
+ ip->i_flushiter = be16_to_cpu(from->di_flushiter);
inode->i_generation = be32_to_cpu(from->di_gen);
inode->i_mode = be16_to_cpu(from->di_mode);
if (!inode->i_mode)
@@ -225,10 +206,10 @@ xfs_inode_from_disk(
*/
if (unlikely(from->di_version == 1)) {
set_nlink(inode, be16_to_cpu(from->di_onlink));
- to->di_projid = 0;
+ ip->i_projid = 0;
} else {
set_nlink(inode, be32_to_cpu(from->di_nlink));
- to->di_projid = (prid_t)be16_to_cpu(from->di_projid_hi) << 16 |
+ ip->i_projid = (prid_t)be16_to_cpu(from->di_projid_hi) << 16 |
be16_to_cpu(from->di_projid_lo);
}
@@ -245,20 +226,21 @@ xfs_inode_from_disk(
inode->i_mtime = xfs_inode_from_disk_ts(from, from->di_mtime);
inode->i_ctime = xfs_inode_from_disk_ts(from, from->di_ctime);
- to->di_size = be64_to_cpu(from->di_size);
- to->di_nblocks = be64_to_cpu(from->di_nblocks);
- to->di_extsize = be32_to_cpu(from->di_extsize);
- to->di_forkoff = from->di_forkoff;
- to->di_dmevmask = be32_to_cpu(from->di_dmevmask);
- to->di_dmstate = be16_to_cpu(from->di_dmstate);
- to->di_flags = be16_to_cpu(from->di_flags);
+ ip->i_disk_size = be64_to_cpu(from->di_size);
+ ip->i_nblocks = be64_to_cpu(from->di_nblocks);
+ ip->i_extsize = be32_to_cpu(from->di_extsize);
+ ip->i_forkoff = from->di_forkoff;
+ ip->i_diflags = be16_to_cpu(from->di_flags);
+
+ if (from->di_dmevmask || from->di_dmstate)
+ xfs_iflags_set(ip, XFS_IPRESERVE_DM_FIELDS);
if (xfs_sb_version_has_v3inode(&ip->i_mount->m_sb)) {
inode_set_iversion_queried(inode,
be64_to_cpu(from->di_changecount));
- to->di_crtime = xfs_inode_from_disk_ts(from, from->di_crtime);
- to->di_flags2 = be64_to_cpu(from->di_flags2);
- to->di_cowextsize = be32_to_cpu(from->di_cowextsize);
+ ip->i_crtime = xfs_inode_from_disk_ts(from, from->di_crtime);
+ ip->i_diflags2 = be64_to_cpu(from->di_flags2);
+ ip->i_cowextsize = be32_to_cpu(from->di_cowextsize);
}
error = xfs_iformat_data_fork(ip, from);
@@ -303,7 +285,6 @@ xfs_inode_to_disk(
struct xfs_dinode *to,
xfs_lsn_t lsn)
{
- struct xfs_icdinode *from = &ip->i_d;
struct inode *inode = VFS_I(ip);
to->di_magic = cpu_to_be16(XFS_DINODE_MAGIC);
@@ -312,8 +293,8 @@ xfs_inode_to_disk(
to->di_format = xfs_ifork_format(&ip->i_df);
to->di_uid = cpu_to_be32(i_uid_read(inode));
to->di_gid = cpu_to_be32(i_gid_read(inode));
- to->di_projid_lo = cpu_to_be16(from->di_projid & 0xffff);
- to->di_projid_hi = cpu_to_be16(from->di_projid >> 16);
+ to->di_projid_lo = cpu_to_be16(ip->i_projid & 0xffff);
+ to->di_projid_hi = cpu_to_be16(ip->i_projid >> 16);
memset(to->di_pad, 0, sizeof(to->di_pad));
to->di_atime = xfs_inode_to_disk_ts(ip, inode->i_atime);
@@ -323,23 +304,21 @@ xfs_inode_to_disk(
to->di_gen = cpu_to_be32(inode->i_generation);
to->di_mode = cpu_to_be16(inode->i_mode);
- to->di_size = cpu_to_be64(from->di_size);
- to->di_nblocks = cpu_to_be64(from->di_nblocks);
- to->di_extsize = cpu_to_be32(from->di_extsize);
+ to->di_size = cpu_to_be64(ip->i_disk_size);
+ to->di_nblocks = cpu_to_be64(ip->i_nblocks);
+ to->di_extsize = cpu_to_be32(ip->i_extsize);
to->di_nextents = cpu_to_be32(xfs_ifork_nextents(&ip->i_df));
to->di_anextents = cpu_to_be16(xfs_ifork_nextents(ip->i_afp));
- to->di_forkoff = from->di_forkoff;
+ to->di_forkoff = ip->i_forkoff;
to->di_aformat = xfs_ifork_format(ip->i_afp);
- to->di_dmevmask = cpu_to_be32(from->di_dmevmask);
- to->di_dmstate = cpu_to_be16(from->di_dmstate);
- to->di_flags = cpu_to_be16(from->di_flags);
+ to->di_flags = cpu_to_be16(ip->i_diflags);
if (xfs_sb_version_has_v3inode(&ip->i_mount->m_sb)) {
to->di_version = 3;
to->di_changecount = cpu_to_be64(inode_peek_iversion(inode));
- to->di_crtime = xfs_inode_to_disk_ts(ip, from->di_crtime);
- to->di_flags2 = cpu_to_be64(from->di_flags2);
- to->di_cowextsize = cpu_to_be32(from->di_cowextsize);
+ to->di_crtime = xfs_inode_to_disk_ts(ip, ip->i_crtime);
+ to->di_flags2 = cpu_to_be64(ip->i_diflags2);
+ to->di_cowextsize = cpu_to_be32(ip->i_cowextsize);
to->di_ino = cpu_to_be64(ip->i_ino);
to->di_lsn = cpu_to_be64(lsn);
memset(to->di_pad2, 0, sizeof(to->di_pad2));
@@ -347,7 +326,7 @@ xfs_inode_to_disk(
to->di_flushiter = 0;
} else {
to->di_version = 2;
- to->di_flushiter = cpu_to_be16(from->di_flushiter);
+ to->di_flushiter = cpu_to_be16(ip->i_flushiter);
}
}
diff --git a/fs/xfs/libxfs/xfs_inode_buf.h b/fs/xfs/libxfs/xfs_inode_buf.h
index ef5eaf33d146..7f865bb4df84 100644
--- a/fs/xfs/libxfs/xfs_inode_buf.h
+++ b/fs/xfs/libxfs/xfs_inode_buf.h
@@ -10,34 +10,6 @@ struct xfs_inode;
struct xfs_dinode;
/*
- * In memory representation of the XFS inode. This is held in the in-core struct
- * xfs_inode and represents the current on disk values but the structure is not
- * in on-disk format. That is, this structure is always translated to on-disk
- * format specific structures at the appropriate time.
- */
-struct xfs_icdinode {
- uint16_t di_flushiter; /* incremented on flush */
- prid_t di_projid; /* owner's project id */
- xfs_fsize_t di_size; /* number of bytes in file */
- xfs_rfsblock_t di_nblocks; /* # of direct & btree blocks used */
- xfs_extlen_t di_extsize; /* basic/minimum extent size for file */
- uint8_t di_forkoff; /* attr fork offs, <<3 for 64b align */
- uint32_t di_dmevmask; /* DMIG event mask */
- uint16_t di_dmstate; /* DMIG state info */
- uint16_t di_flags; /* random flags, XFS_DIFLAG_... */
-
- uint64_t di_flags2; /* more random flags */
- uint32_t di_cowextsize; /* basic cow extent size for file */
-
- struct timespec64 di_crtime; /* time created */
-};
-
-static inline bool xfs_icdinode_has_bigtime(const struct xfs_icdinode *icd)
-{
- return icd->di_flags2 & XFS_DIFLAG2_BIGTIME;
-}
-
-/*
* Inode location information. Stored in the inode and passed to
* xfs_imap_to_bp() to get a buffer and dinode for a given inode.
*/
@@ -47,9 +19,8 @@ struct xfs_imap {
unsigned short im_boffset; /* inode offset in block in bytes */
};
-int xfs_imap_to_bp(struct xfs_mount *, struct xfs_trans *,
- struct xfs_imap *, struct xfs_dinode **,
- struct xfs_buf **, uint);
+int xfs_imap_to_bp(struct xfs_mount *mp, struct xfs_trans *tp,
+ struct xfs_imap *imap, struct xfs_buf **bpp);
void xfs_dinode_calc_crc(struct xfs_mount *, struct xfs_dinode *);
void xfs_inode_to_disk(struct xfs_inode *ip, struct xfs_dinode *to,
xfs_lsn_t lsn);
diff --git a/fs/xfs/libxfs/xfs_inode_fork.c b/fs/xfs/libxfs/xfs_inode_fork.c
index e080d7e07643..1d174909f9bd 100644
--- a/fs/xfs/libxfs/xfs_inode_fork.c
+++ b/fs/xfs/libxfs/xfs_inode_fork.c
@@ -60,8 +60,6 @@ xfs_init_local_fork(
}
ifp->if_bytes = size;
- ifp->if_flags &= ~(XFS_IFEXTENTS | XFS_IFBROOT);
- ifp->if_flags |= XFS_IFINLINE;
}
/*
@@ -151,7 +149,6 @@ xfs_iformat_extents(
xfs_iext_next(ifp, &icur);
}
}
- ifp->if_flags |= XFS_IFEXTENTS;
return 0;
}
@@ -194,8 +191,8 @@ xfs_iformat_btree(
nrecs == 0 ||
XFS_BMDR_SPACE_CALC(nrecs) >
XFS_DFORK_SIZE(dip, mp, whichfork) ||
- ifp->if_nextents > ip->i_d.di_nblocks) ||
- level == 0 || level > XFS_BTREE_MAXLEVELS) {
+ ifp->if_nextents > ip->i_nblocks) ||
+ level == 0 || level > XFS_BM_MAXLEVELS(mp, whichfork)) {
xfs_warn(mp, "corrupt inode %Lu (btree).",
(unsigned long long) ip->i_ino);
xfs_inode_verifier_error(ip, -EFSCORRUPTED,
@@ -213,8 +210,6 @@ xfs_iformat_btree(
*/
xfs_bmdr_to_bmbt(ip, dfp, XFS_DFORK_SIZE(dip, ip->i_mount, whichfork),
ifp->if_broot, size);
- ifp->if_flags &= ~XFS_IFEXTENTS;
- ifp->if_flags |= XFS_IFBROOT;
ifp->if_bytes = 0;
ifp->if_u1.if_root = NULL;
@@ -242,7 +237,7 @@ xfs_iformat_data_fork(
case S_IFCHR:
case S_IFBLK:
case S_IFSOCK:
- ip->i_d.di_size = 0;
+ ip->i_disk_size = 0;
inode->i_rdev = xfs_to_linux_dev_t(xfs_dinode_get_rdev(dip));
return 0;
case S_IFREG:
@@ -282,6 +277,19 @@ xfs_dfork_attr_shortform_size(
return be16_to_cpu(atp->hdr.totsize);
}
+struct xfs_ifork *
+xfs_ifork_alloc(
+ enum xfs_dinode_fmt format,
+ xfs_extnum_t nextents)
+{
+ struct xfs_ifork *ifp;
+
+ ifp = kmem_cache_zalloc(xfs_ifork_zone, GFP_NOFS | __GFP_NOFAIL);
+ ifp->if_format = format;
+ ifp->if_nextents = nextents;
+ return ifp;
+}
+
int
xfs_iformat_attr_fork(
struct xfs_inode *ip,
@@ -293,11 +301,8 @@ xfs_iformat_attr_fork(
* Initialize the extent count early, as the per-format routines may
* depend on it.
*/
- ip->i_afp = kmem_cache_zalloc(xfs_ifork_zone, GFP_NOFS | __GFP_NOFAIL);
- ip->i_afp->if_format = dip->di_aformat;
- if (unlikely(ip->i_afp->if_format == 0)) /* pre IRIX 6.2 file system */
- ip->i_afp->if_format = XFS_DINODE_FMT_EXTENTS;
- ip->i_afp->if_nextents = be16_to_cpu(dip->di_anextents);
+ ip->i_afp = xfs_ifork_alloc(dip->di_aformat,
+ be16_to_cpu(dip->di_anextents));
switch (ip->i_afp->if_format) {
case XFS_DINODE_FMT_LOCAL:
@@ -423,7 +428,6 @@ xfs_iroot_realloc(
XFS_BMBT_BLOCK_LEN(ip->i_mount));
} else {
new_broot = NULL;
- ifp->if_flags &= ~XFS_IFBROOT;
}
/*
@@ -512,17 +516,16 @@ xfs_idestroy_fork(
ifp->if_broot = NULL;
}
- /*
- * If the format is local, then we can't have an extents array so just
- * look for an inline data array. If we're not local then we may or may
- * not have an extents list, so check and free it up if we do.
- */
- if (ifp->if_format == XFS_DINODE_FMT_LOCAL) {
+ switch (ifp->if_format) {
+ case XFS_DINODE_FMT_LOCAL:
kmem_free(ifp->if_u1.if_data);
ifp->if_u1.if_data = NULL;
- } else if (ifp->if_flags & XFS_IFEXTENTS) {
+ break;
+ case XFS_DINODE_FMT_EXTENTS:
+ case XFS_DINODE_FMT_BTREE:
if (ifp->if_height)
xfs_iext_destroy(ifp);
+ break;
}
}
@@ -616,8 +619,6 @@ xfs_iflush_fork(
break;
case XFS_DINODE_FMT_EXTENTS:
- ASSERT((ifp->if_flags & XFS_IFEXTENTS) ||
- !(iip->ili_fields & extflag[whichfork]));
if ((iip->ili_fields & extflag[whichfork]) &&
(ifp->if_bytes > 0)) {
ASSERT(ifp->if_nextents > 0);
@@ -677,7 +678,6 @@ xfs_ifork_init_cow(
ip->i_cowfp = kmem_cache_zalloc(xfs_ifork_zone,
GFP_NOFS | __GFP_NOFAIL);
- ip->i_cowfp->if_flags = XFS_IFEXTENTS;
ip->i_cowfp->if_format = XFS_DINODE_FMT_EXTENTS;
}
diff --git a/fs/xfs/libxfs/xfs_inode_fork.h b/fs/xfs/libxfs/xfs_inode_fork.h
index 9e2137cd7372..a6f7897b6887 100644
--- a/fs/xfs/libxfs/xfs_inode_fork.h
+++ b/fs/xfs/libxfs/xfs_inode_fork.h
@@ -22,19 +22,11 @@ struct xfs_ifork {
char *if_data; /* inline file data */
} if_u1;
short if_broot_bytes; /* bytes allocated for root */
- unsigned char if_flags; /* per-fork flags */
int8_t if_format; /* format of this fork */
xfs_extnum_t if_nextents; /* # of extents in this fork */
};
/*
- * Per-fork incore inode flags.
- */
-#define XFS_IFINLINE 0x01 /* Inline data is read in */
-#define XFS_IFEXTENTS 0x02 /* All extent pointers are read in */
-#define XFS_IFBROOT 0x04 /* i_broot points to the bmap b-tree root */
-
-/*
* Worst-case increase in the fork extent count when we're adding a single
* extent to a fork and there's no possibility of splitting an existing mapping.
*/
@@ -99,8 +91,8 @@ struct xfs_ifork {
* Fork handling.
*/
-#define XFS_IFORK_Q(ip) ((ip)->i_d.di_forkoff != 0)
-#define XFS_IFORK_BOFF(ip) ((int)((ip)->i_d.di_forkoff << 3))
+#define XFS_IFORK_Q(ip) ((ip)->i_forkoff != 0)
+#define XFS_IFORK_BOFF(ip) ((int)((ip)->i_forkoff << 3))
#define XFS_IFORK_PTR(ip,w) \
((w) == XFS_DATA_FORK ? \
@@ -141,6 +133,8 @@ static inline int8_t xfs_ifork_format(struct xfs_ifork *ifp)
return ifp->if_format;
}
+struct xfs_ifork *xfs_ifork_alloc(enum xfs_dinode_fmt format,
+ xfs_extnum_t nextents);
struct xfs_ifork *xfs_iext_state_to_fork(struct xfs_inode *ip, int state);
int xfs_iformat_data_fork(struct xfs_inode *, struct xfs_dinode *);
@@ -236,4 +230,10 @@ int xfs_ifork_verify_local_attr(struct xfs_inode *ip);
int xfs_iext_count_may_overflow(struct xfs_inode *ip, int whichfork,
int nr_to_add);
+/* returns true if the fork has extents but they are not read in yet. */
+static inline bool xfs_need_iread_extents(struct xfs_ifork *ifp)
+{
+ return ifp->if_format == XFS_DINODE_FMT_BTREE && ifp->if_height == 0;
+}
+
#endif /* __XFS_INODE_FORK_H__ */
diff --git a/fs/xfs/libxfs/xfs_rtbitmap.c b/fs/xfs/libxfs/xfs_rtbitmap.c
index fe3a49575ff3..483375c6a735 100644
--- a/fs/xfs/libxfs/xfs_rtbitmap.c
+++ b/fs/xfs/libxfs/xfs_rtbitmap.c
@@ -997,8 +997,8 @@ xfs_rtfree_extent(
*/
if (tp->t_frextents_delta + mp->m_sb.sb_frextents ==
mp->m_sb.sb_rextents) {
- if (!(mp->m_rbmip->i_d.di_flags & XFS_DIFLAG_NEWRTBM))
- mp->m_rbmip->i_d.di_flags |= XFS_DIFLAG_NEWRTBM;
+ if (!(mp->m_rbmip->i_diflags & XFS_DIFLAG_NEWRTBM))
+ mp->m_rbmip->i_diflags |= XFS_DIFLAG_NEWRTBM;
*(uint64_t *)&VFS_I(mp->m_rbmip)->i_atime = 0;
xfs_trans_log_inode(tp, mp->m_rbmip, XFS_ILOG_CORE);
}
diff --git a/fs/xfs/libxfs/xfs_shared.h b/fs/xfs/libxfs/xfs_shared.h
index 8c61a461bf7b..782fdd08f759 100644
--- a/fs/xfs/libxfs/xfs_shared.h
+++ b/fs/xfs/libxfs/xfs_shared.h
@@ -176,8 +176,12 @@ struct xfs_ino_geometry {
unsigned int agino_log; /* #bits for agino in inum */
+ /* precomputed default inode attribute fork offset */
+ unsigned int attr_fork_offset;
+
/* precomputed value for di_flags2 */
uint64_t new_diflags2;
+
};
#endif /* __XFS_SHARED_H__ */
diff --git a/fs/xfs/libxfs/xfs_trans_inode.c b/fs/xfs/libxfs/xfs_trans_inode.c
index 90f1d5645052..78324e043e25 100644
--- a/fs/xfs/libxfs/xfs_trans_inode.c
+++ b/fs/xfs/libxfs/xfs_trans_inode.c
@@ -70,7 +70,7 @@ xfs_trans_ichgtime(
if (flags & XFS_ICHGTIME_CHG)
inode->i_ctime = tv;
if (flags & XFS_ICHGTIME_CREATE)
- ip->i_d.di_crtime = tv;
+ ip->i_crtime = tv;
}
/*
@@ -138,7 +138,7 @@ xfs_trans_log_inode(
if ((flags & (XFS_ILOG_CORE | XFS_ILOG_TIMESTAMP)) &&
xfs_sb_version_hasbigtime(&ip->i_mount->m_sb) &&
!xfs_inode_has_bigtime(ip)) {
- ip->i_d.di_flags2 |= XFS_DIFLAG2_BIGTIME;
+ ip->i_diflags2 |= XFS_DIFLAG2_BIGTIME;
flags |= XFS_ILOG_CORE;
}
@@ -164,8 +164,7 @@ xfs_trans_log_inode(
* here.
*/
spin_unlock(&iip->ili_lock);
- error = xfs_imap_to_bp(ip->i_mount, tp, &ip->i_imap, NULL,
- &bp, 0);
+ error = xfs_imap_to_bp(ip->i_mount, tp, &ip->i_imap, &bp);
if (error) {
xfs_force_shutdown(ip->i_mount, SHUTDOWN_META_IO_ERROR);
return;
diff --git a/fs/xfs/libxfs/xfs_types.c b/fs/xfs/libxfs/xfs_types.c
index b254fbeaaa50..04801362e1a7 100644
--- a/fs/xfs/libxfs/xfs_types.c
+++ b/fs/xfs/libxfs/xfs_types.c
@@ -13,7 +13,7 @@
#include "xfs_mount.h"
/* Find the size of the AG, in blocks. */
-xfs_agblock_t
+inline xfs_agblock_t
xfs_ag_block_count(
struct xfs_mount *mp,
xfs_agnumber_t agno)
@@ -29,7 +29,7 @@ xfs_ag_block_count(
* Verify that an AG block number pointer neither points outside the AG
* nor points at static metadata.
*/
-bool
+inline bool
xfs_verify_agbno(
struct xfs_mount *mp,
xfs_agnumber_t agno,
@@ -49,7 +49,7 @@ xfs_verify_agbno(
* Verify that an FS block number pointer neither points outside the
* filesystem nor points at static AG metadata.
*/
-bool
+inline bool
xfs_verify_fsbno(
struct xfs_mount *mp,
xfs_fsblock_t fsbno)
@@ -85,7 +85,7 @@ xfs_verify_fsbext(
}
/* Calculate the first and last possible inode number in an AG. */
-void
+inline void
xfs_agino_range(
struct xfs_mount *mp,
xfs_agnumber_t agno,
@@ -116,7 +116,7 @@ xfs_agino_range(
* Verify that an AG inode number pointer neither points outside the AG
* nor points at static metadata.
*/
-bool
+inline bool
xfs_verify_agino(
struct xfs_mount *mp,
xfs_agnumber_t agno,
@@ -146,7 +146,7 @@ xfs_verify_agino_or_null(
* Verify that an FS inode number pointer neither points outside the
* filesystem nor points at static AG metadata.
*/
-bool
+inline bool
xfs_verify_ino(
struct xfs_mount *mp,
xfs_ino_t ino)
@@ -162,7 +162,7 @@ xfs_verify_ino(
}
/* Is this an internal inode number? */
-bool
+inline bool
xfs_internal_inum(
struct xfs_mount *mp,
xfs_ino_t ino)
@@ -190,7 +190,7 @@ xfs_verify_dir_ino(
* Verify that an realtime block number pointer doesn't point off the
* end of the realtime device.
*/
-bool
+inline bool
xfs_verify_rtbno(
struct xfs_mount *mp,
xfs_rtblock_t rtbno)
@@ -215,7 +215,7 @@ xfs_verify_rtext(
}
/* Calculate the range of valid icount values. */
-void
+inline void
xfs_icount_range(
struct xfs_mount *mp,
unsigned long long *min,
diff --git a/fs/xfs/scrub/agheader.c b/fs/xfs/scrub/agheader.c
index ae8e2e0ac64a..749faa17f8e2 100644
--- a/fs/xfs/scrub/agheader.c
+++ b/fs/xfs/scrub/agheader.c
@@ -477,16 +477,13 @@ xchk_agf_xref(
{
struct xfs_mount *mp = sc->mp;
xfs_agblock_t agbno;
- int error;
if (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)
return;
agbno = XFS_AGF_BLOCK(mp);
- error = xchk_ag_btcur_init(sc, &sc->sa);
- if (error)
- return;
+ xchk_ag_btcur_init(sc, &sc->sa);
xchk_xref_is_used_space(sc, agbno, 1);
xchk_agf_xref_freeblks(sc);
@@ -508,7 +505,7 @@ xchk_agf(
struct xfs_mount *mp = sc->mp;
struct xfs_agf *agf;
struct xfs_perag *pag;
- xfs_agnumber_t agno;
+ xfs_agnumber_t agno = sc->sm->sm_agno;
xfs_agblock_t agbno;
xfs_agblock_t eoag;
xfs_agblock_t agfl_first;
@@ -518,9 +515,7 @@ xchk_agf(
int level;
int error = 0;
- agno = sc->sa.agno = sc->sm->sm_agno;
- error = xchk_ag_read_headers(sc, agno, &sc->sa.agi_bp,
- &sc->sa.agf_bp, &sc->sa.agfl_bp);
+ error = xchk_ag_read_headers(sc, agno, &sc->sa);
if (!xchk_process_error(sc, agno, XFS_AGF_BLOCK(sc->mp), &error))
goto out;
xchk_buffer_recheck(sc, sc->sa.agf_bp);
@@ -662,16 +657,13 @@ xchk_agfl_xref(
{
struct xfs_mount *mp = sc->mp;
xfs_agblock_t agbno;
- int error;
if (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)
return;
agbno = XFS_AGFL_BLOCK(mp);
- error = xchk_ag_btcur_init(sc, &sc->sa);
- if (error)
- return;
+ xchk_ag_btcur_init(sc, &sc->sa);
xchk_xref_is_used_space(sc, agbno, 1);
xchk_xref_is_not_inode_chunk(sc, agbno, 1);
@@ -691,14 +683,12 @@ xchk_agfl(
{
struct xchk_agfl_info sai;
struct xfs_agf *agf;
- xfs_agnumber_t agno;
+ xfs_agnumber_t agno = sc->sm->sm_agno;
unsigned int agflcount;
unsigned int i;
int error;
- agno = sc->sa.agno = sc->sm->sm_agno;
- error = xchk_ag_read_headers(sc, agno, &sc->sa.agi_bp,
- &sc->sa.agf_bp, &sc->sa.agfl_bp);
+ error = xchk_ag_read_headers(sc, agno, &sc->sa);
if (!xchk_process_error(sc, agno, XFS_AGFL_BLOCK(sc->mp), &error))
goto out;
if (!sc->sa.agf_bp)
@@ -817,16 +807,13 @@ xchk_agi_xref(
{
struct xfs_mount *mp = sc->mp;
xfs_agblock_t agbno;
- int error;
if (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)
return;
agbno = XFS_AGI_BLOCK(mp);
- error = xchk_ag_btcur_init(sc, &sc->sa);
- if (error)
- return;
+ xchk_ag_btcur_init(sc, &sc->sa);
xchk_xref_is_used_space(sc, agbno, 1);
xchk_xref_is_not_inode_chunk(sc, agbno, 1);
@@ -846,7 +833,7 @@ xchk_agi(
struct xfs_mount *mp = sc->mp;
struct xfs_agi *agi;
struct xfs_perag *pag;
- xfs_agnumber_t agno;
+ xfs_agnumber_t agno = sc->sm->sm_agno;
xfs_agblock_t agbno;
xfs_agblock_t eoag;
xfs_agino_t agino;
@@ -857,9 +844,7 @@ xchk_agi(
int level;
int error = 0;
- agno = sc->sa.agno = sc->sm->sm_agno;
- error = xchk_ag_read_headers(sc, agno, &sc->sa.agi_bp,
- &sc->sa.agf_bp, &sc->sa.agfl_bp);
+ error = xchk_ag_read_headers(sc, agno, &sc->sa);
if (!xchk_process_error(sc, agno, XFS_AGI_BLOCK(sc->mp), &error))
goto out;
xchk_buffer_recheck(sc, sc->sa.agi_bp);
diff --git a/fs/xfs/scrub/alloc.c b/fs/xfs/scrub/alloc.c
index 73d924e47565..2720bd7fe53b 100644
--- a/fs/xfs/scrub/alloc.c
+++ b/fs/xfs/scrub/alloc.c
@@ -21,10 +21,9 @@
*/
int
xchk_setup_ag_allocbt(
- struct xfs_scrub *sc,
- struct xfs_inode *ip)
+ struct xfs_scrub *sc)
{
- return xchk_setup_ag_btree(sc, ip, false);
+ return xchk_setup_ag_btree(sc, false);
}
/* Free space btree scrubber. */
diff --git a/fs/xfs/scrub/attr.c b/fs/xfs/scrub/attr.c
index 9faddb334a2c..552af0cf8482 100644
--- a/fs/xfs/scrub/attr.c
+++ b/fs/xfs/scrub/attr.c
@@ -69,8 +69,7 @@ xchk_setup_xattr_buf(
/* Set us up to scrub an inode's extended attributes. */
int
xchk_setup_xattr(
- struct xfs_scrub *sc,
- struct xfs_inode *ip)
+ struct xfs_scrub *sc)
{
int error;
@@ -85,7 +84,7 @@ xchk_setup_xattr(
return error;
}
- return xchk_setup_inode_contents(sc, ip, 0);
+ return xchk_setup_inode_contents(sc, 0);
}
/* Extended Attributes */
diff --git a/fs/xfs/scrub/bitmap.c b/fs/xfs/scrub/bitmap.c
index f88694f22d05..813b5f219113 100644
--- a/fs/xfs/scrub/bitmap.c
+++ b/fs/xfs/scrub/bitmap.c
@@ -63,8 +63,8 @@ xbitmap_init(
static int
xbitmap_range_cmp(
void *priv,
- struct list_head *a,
- struct list_head *b)
+ const struct list_head *a,
+ const struct list_head *b)
{
struct xbitmap_range *ap;
struct xbitmap_range *bp;
diff --git a/fs/xfs/scrub/bmap.c b/fs/xfs/scrub/bmap.c
index 33559c3a4bc3..b5ebf1d1b4db 100644
--- a/fs/xfs/scrub/bmap.c
+++ b/fs/xfs/scrub/bmap.c
@@ -26,12 +26,11 @@
/* Set us up with an inode's bmap. */
int
xchk_setup_inode_bmap(
- struct xfs_scrub *sc,
- struct xfs_inode *ip)
+ struct xfs_scrub *sc)
{
int error;
- error = xchk_get_inode(sc, ip);
+ error = xchk_get_inode(sc);
if (error)
goto out;
@@ -448,12 +447,11 @@ xchk_bmap_btree(
int error;
/* Load the incore bmap cache if it's not loaded. */
- info->was_loaded = ifp->if_flags & XFS_IFEXTENTS;
- if (!info->was_loaded) {
- error = xfs_iread_extents(sc->tp, ip, whichfork);
- if (!xchk_fblock_process_error(sc, whichfork, 0, &error))
- goto out;
- }
+ info->was_loaded = !xfs_need_iread_extents(ifp);
+
+ error = xfs_iread_extents(sc->tp, ip, whichfork);
+ if (!xchk_fblock_process_error(sc, whichfork, 0, &error))
+ goto out;
/* Check the btree structure. */
cur = xfs_bmbt_init_cursor(mp, sc->tp, ip, whichfork);
@@ -675,10 +673,6 @@ xchk_bmap(
/* No mappings to check. */
goto out;
case XFS_DINODE_FMT_EXTENTS:
- if (!(ifp->if_flags & XFS_IFEXTENTS)) {
- xchk_fblock_set_corrupt(sc, whichfork, 0);
- goto out;
- }
break;
case XFS_DINODE_FMT_BTREE:
if (whichfork == XFS_COW_FORK) {
diff --git a/fs/xfs/scrub/btree.c b/fs/xfs/scrub/btree.c
index debf392e0515..a94bd8122c60 100644
--- a/fs/xfs/scrub/btree.c
+++ b/fs/xfs/scrub/btree.c
@@ -9,6 +9,7 @@
#include "xfs_format.h"
#include "xfs_trans_resv.h"
#include "xfs_mount.h"
+#include "xfs_inode.h"
#include "xfs_btree.h"
#include "scrub/scrub.h"
#include "scrub/common.h"
@@ -442,6 +443,30 @@ xchk_btree_check_owner(
return xchk_btree_check_block_owner(bs, level, XFS_BUF_ADDR(bp));
}
+/* Decide if we want to check minrecs of a btree block in the inode root. */
+static inline bool
+xchk_btree_check_iroot_minrecs(
+ struct xchk_btree *bs)
+{
+ /*
+ * xfs_bmap_add_attrfork_btree had an implementation bug wherein it
+ * would miscalculate the space required for the data fork bmbt root
+ * when adding an attr fork, and promote the iroot contents to an
+ * external block unnecessarily. This went unnoticed for many years
+ * until scrub found filesystems in this state. Inode rooted btrees are
+ * not supposed to have immediate child blocks that are small enough
+ * that the contents could fit in the inode root, but we can't fail
+ * existing filesystems, so instead we disable the check for data fork
+ * bmap btrees when there's an attr fork.
+ */
+ if (bs->cur->bc_btnum == XFS_BTNUM_BMAP &&
+ bs->cur->bc_ino.whichfork == XFS_DATA_FORK &&
+ XFS_IFORK_Q(bs->sc->ip))
+ return false;
+
+ return true;
+}
+
/*
* Check that this btree block has at least minrecs records or is one of the
* special blocks that don't require that.
@@ -475,8 +500,9 @@ xchk_btree_check_minrecs(
root_block = xfs_btree_get_block(cur, root_level, &root_bp);
root_maxrecs = cur->bc_ops->get_dmaxrecs(cur, root_level);
- if (be16_to_cpu(root_block->bb_numrecs) != 1 ||
- numrecs <= root_maxrecs)
+ if (xchk_btree_check_iroot_minrecs(bs) &&
+ (be16_to_cpu(root_block->bb_numrecs) != 1 ||
+ numrecs <= root_maxrecs))
xchk_btree_set_corrupt(bs->sc, cur, level);
return;
}
diff --git a/fs/xfs/scrub/common.c b/fs/xfs/scrub/common.c
index 53456f3de881..aa874607618a 100644
--- a/fs/xfs/scrub/common.c
+++ b/fs/xfs/scrub/common.c
@@ -402,22 +402,22 @@ int
xchk_ag_read_headers(
struct xfs_scrub *sc,
xfs_agnumber_t agno,
- struct xfs_buf **agi,
- struct xfs_buf **agf,
- struct xfs_buf **agfl)
+ struct xchk_ag *sa)
{
struct xfs_mount *mp = sc->mp;
int error;
- error = xfs_ialloc_read_agi(mp, sc->tp, agno, agi);
+ sa->agno = agno;
+
+ error = xfs_ialloc_read_agi(mp, sc->tp, agno, &sa->agi_bp);
if (error && want_ag_read_header_failure(sc, XFS_SCRUB_TYPE_AGI))
goto out;
- error = xfs_alloc_read_agf(mp, sc->tp, agno, 0, agf);
+ error = xfs_alloc_read_agf(mp, sc->tp, agno, 0, &sa->agf_bp);
if (error && want_ag_read_header_failure(sc, XFS_SCRUB_TYPE_AGF))
goto out;
- error = xfs_alloc_read_agfl(mp, sc->tp, agno, agfl);
+ error = xfs_alloc_read_agfl(mp, sc->tp, agno, &sa->agfl_bp);
if (error && want_ag_read_header_failure(sc, XFS_SCRUB_TYPE_AGFL))
goto out;
error = 0;
@@ -452,7 +452,7 @@ xchk_ag_btcur_free(
}
/* Initialize all the btree cursors for an AG. */
-int
+void
xchk_ag_btcur_init(
struct xfs_scrub *sc,
struct xchk_ag *sa)
@@ -502,8 +502,6 @@ xchk_ag_btcur_init(
sa->refc_cur = xfs_refcountbt_init_cursor(mp, sc->tp,
sa->agf_bp, agno);
}
-
- return 0;
}
/* Release the AG header context and btree cursors. */
@@ -547,13 +545,12 @@ xchk_ag_init(
{
int error;
- sa->agno = agno;
- error = xchk_ag_read_headers(sc, agno, &sa->agi_bp,
- &sa->agf_bp, &sa->agfl_bp);
+ error = xchk_ag_read_headers(sc, agno, sa);
if (error)
return error;
- return xchk_ag_btcur_init(sc, sa);
+ xchk_ag_btcur_init(sc, sa);
+ return 0;
}
/*
@@ -596,8 +593,7 @@ xchk_trans_alloc(
/* Set us up with a transaction and an empty context. */
int
xchk_setup_fs(
- struct xfs_scrub *sc,
- struct xfs_inode *ip)
+ struct xfs_scrub *sc)
{
uint resblks;
@@ -609,7 +605,6 @@ xchk_setup_fs(
int
xchk_setup_ag_btree(
struct xfs_scrub *sc,
- struct xfs_inode *ip,
bool force_log)
{
struct xfs_mount *mp = sc->mp;
@@ -627,7 +622,7 @@ xchk_setup_ag_btree(
return error;
}
- error = xchk_setup_fs(sc, ip);
+ error = xchk_setup_fs(sc);
if (error)
return error;
@@ -655,11 +650,11 @@ xchk_checkpoint_log(
*/
int
xchk_get_inode(
- struct xfs_scrub *sc,
- struct xfs_inode *ip_in)
+ struct xfs_scrub *sc)
{
struct xfs_imap imap;
struct xfs_mount *mp = sc->mp;
+ struct xfs_inode *ip_in = XFS_I(file_inode(sc->file));
struct xfs_inode *ip = NULL;
int error;
@@ -720,12 +715,11 @@ xchk_get_inode(
int
xchk_setup_inode_contents(
struct xfs_scrub *sc,
- struct xfs_inode *ip,
unsigned int resblks)
{
int error;
- error = xchk_get_inode(sc, ip);
+ error = xchk_get_inode(sc);
if (error)
return error;
@@ -821,7 +815,7 @@ xchk_metadata_inode_forks(
return 0;
/* Metadata inodes don't live on the rt device. */
- if (sc->ip->i_d.di_flags & XFS_DIFLAG_REALTIME) {
+ if (sc->ip->i_diflags & XFS_DIFLAG_REALTIME) {
xchk_ino_set_corrupt(sc, sc->ip->i_ino);
return 0;
}
diff --git a/fs/xfs/scrub/common.h b/fs/xfs/scrub/common.h
index 2e50d146105d..0410faf7d735 100644
--- a/fs/xfs/scrub/common.h
+++ b/fs/xfs/scrub/common.h
@@ -72,66 +72,52 @@ bool xchk_should_check_xref(struct xfs_scrub *sc, int *error,
struct xfs_btree_cur **curpp);
/* Setup functions */
-int xchk_setup_fs(struct xfs_scrub *sc, struct xfs_inode *ip);
-int xchk_setup_ag_allocbt(struct xfs_scrub *sc,
- struct xfs_inode *ip);
-int xchk_setup_ag_iallocbt(struct xfs_scrub *sc,
- struct xfs_inode *ip);
-int xchk_setup_ag_rmapbt(struct xfs_scrub *sc,
- struct xfs_inode *ip);
-int xchk_setup_ag_refcountbt(struct xfs_scrub *sc,
- struct xfs_inode *ip);
-int xchk_setup_inode(struct xfs_scrub *sc,
- struct xfs_inode *ip);
-int xchk_setup_inode_bmap(struct xfs_scrub *sc,
- struct xfs_inode *ip);
-int xchk_setup_inode_bmap_data(struct xfs_scrub *sc,
- struct xfs_inode *ip);
-int xchk_setup_directory(struct xfs_scrub *sc,
- struct xfs_inode *ip);
-int xchk_setup_xattr(struct xfs_scrub *sc,
- struct xfs_inode *ip);
-int xchk_setup_symlink(struct xfs_scrub *sc,
- struct xfs_inode *ip);
-int xchk_setup_parent(struct xfs_scrub *sc,
- struct xfs_inode *ip);
+int xchk_setup_fs(struct xfs_scrub *sc);
+int xchk_setup_ag_allocbt(struct xfs_scrub *sc);
+int xchk_setup_ag_iallocbt(struct xfs_scrub *sc);
+int xchk_setup_ag_rmapbt(struct xfs_scrub *sc);
+int xchk_setup_ag_refcountbt(struct xfs_scrub *sc);
+int xchk_setup_inode(struct xfs_scrub *sc);
+int xchk_setup_inode_bmap(struct xfs_scrub *sc);
+int xchk_setup_inode_bmap_data(struct xfs_scrub *sc);
+int xchk_setup_directory(struct xfs_scrub *sc);
+int xchk_setup_xattr(struct xfs_scrub *sc);
+int xchk_setup_symlink(struct xfs_scrub *sc);
+int xchk_setup_parent(struct xfs_scrub *sc);
#ifdef CONFIG_XFS_RT
-int xchk_setup_rt(struct xfs_scrub *sc, struct xfs_inode *ip);
+int xchk_setup_rt(struct xfs_scrub *sc);
#else
static inline int
-xchk_setup_rt(struct xfs_scrub *sc, struct xfs_inode *ip)
+xchk_setup_rt(struct xfs_scrub *sc)
{
return -ENOENT;
}
#endif
#ifdef CONFIG_XFS_QUOTA
-int xchk_setup_quota(struct xfs_scrub *sc, struct xfs_inode *ip);
+int xchk_setup_quota(struct xfs_scrub *sc);
#else
static inline int
-xchk_setup_quota(struct xfs_scrub *sc, struct xfs_inode *ip)
+xchk_setup_quota(struct xfs_scrub *sc)
{
return -ENOENT;
}
#endif
-int xchk_setup_fscounters(struct xfs_scrub *sc, struct xfs_inode *ip);
+int xchk_setup_fscounters(struct xfs_scrub *sc);
void xchk_ag_free(struct xfs_scrub *sc, struct xchk_ag *sa);
int xchk_ag_init(struct xfs_scrub *sc, xfs_agnumber_t agno,
struct xchk_ag *sa);
void xchk_perag_get(struct xfs_mount *mp, struct xchk_ag *sa);
int xchk_ag_read_headers(struct xfs_scrub *sc, xfs_agnumber_t agno,
- struct xfs_buf **agi, struct xfs_buf **agf,
- struct xfs_buf **agfl);
+ struct xchk_ag *sa);
void xchk_ag_btcur_free(struct xchk_ag *sa);
-int xchk_ag_btcur_init(struct xfs_scrub *sc, struct xchk_ag *sa);
+void xchk_ag_btcur_init(struct xfs_scrub *sc, struct xchk_ag *sa);
int xchk_count_rmap_ownedby_ag(struct xfs_scrub *sc, struct xfs_btree_cur *cur,
const struct xfs_owner_info *oinfo, xfs_filblks_t *blocks);
-int xchk_setup_ag_btree(struct xfs_scrub *sc, struct xfs_inode *ip,
- bool force_log);
-int xchk_get_inode(struct xfs_scrub *sc, struct xfs_inode *ip_in);
-int xchk_setup_inode_contents(struct xfs_scrub *sc, struct xfs_inode *ip,
- unsigned int resblks);
+int xchk_setup_ag_btree(struct xfs_scrub *sc, bool force_log);
+int xchk_get_inode(struct xfs_scrub *sc);
+int xchk_setup_inode_contents(struct xfs_scrub *sc, unsigned int resblks);
void xchk_buffer_recheck(struct xfs_scrub *sc, struct xfs_buf *bp);
/*
diff --git a/fs/xfs/scrub/dir.c b/fs/xfs/scrub/dir.c
index 178b3455a170..28dda391d5df 100644
--- a/fs/xfs/scrub/dir.c
+++ b/fs/xfs/scrub/dir.c
@@ -22,10 +22,9 @@
/* Set us up to scrub directories. */
int
xchk_setup_directory(
- struct xfs_scrub *sc,
- struct xfs_inode *ip)
+ struct xfs_scrub *sc)
{
- return xchk_setup_inode_contents(sc, ip, 0);
+ return xchk_setup_inode_contents(sc, 0);
}
/* Directories */
@@ -538,7 +537,7 @@ xchk_directory_leaf1_bestfree(
* There should be as many bestfree slots as there are dir data
* blocks that can fit under i_size.
*/
- if (bestcount != xfs_dir2_byte_to_db(geo, sc->ip->i_d.di_size)) {
+ if (bestcount != xfs_dir2_byte_to_db(geo, sc->ip->i_disk_size)) {
xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, lblk);
goto out;
}
@@ -694,15 +693,6 @@ xchk_directory_blocks(
/* Iterate all the data extents in the directory... */
found = xfs_iext_lookup_extent(sc->ip, ifp, lblk, &icur, &got);
while (found && !(sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)) {
- /* Block directories only have a single block at offset 0. */
- if (is_block &&
- (got.br_startoff > 0 ||
- got.br_blockcount != args.geo->fsbcount)) {
- xchk_fblock_set_corrupt(sc, XFS_DATA_FORK,
- got.br_startoff);
- break;
- }
-
/* No more data blocks... */
if (got.br_startoff >= leaf_lblk)
break;
@@ -817,7 +807,7 @@ xchk_directory(
return -ENOENT;
/* Plausible size? */
- if (sc->ip->i_d.di_size < xfs_dir2_sf_hdr_size(0)) {
+ if (sc->ip->i_disk_size < xfs_dir2_sf_hdr_size(0)) {
xchk_ino_set_corrupt(sc, sc->ip->i_ino);
goto out;
}
@@ -843,7 +833,7 @@ xchk_directory(
* Userspace usually asks for a 32k buffer, so we will too.
*/
bufsize = (size_t)min_t(loff_t, XFS_READDIR_BUFSIZE,
- sc->ip->i_d.di_size);
+ sc->ip->i_disk_size);
/*
* Look up every name in this directory by hash.
diff --git a/fs/xfs/scrub/fscounters.c b/fs/xfs/scrub/fscounters.c
index ec2064ed3c30..7b4386c78fbf 100644
--- a/fs/xfs/scrub/fscounters.c
+++ b/fs/xfs/scrub/fscounters.c
@@ -116,8 +116,7 @@ next_loop_perag:
int
xchk_setup_fscounters(
- struct xfs_scrub *sc,
- struct xfs_inode *ip)
+ struct xfs_scrub *sc)
{
struct xchk_fscounters *fsc;
int error;
diff --git a/fs/xfs/scrub/health.c b/fs/xfs/scrub/health.c
index 83d27cdf579b..3de59b5c2ce6 100644
--- a/fs/xfs/scrub/health.c
+++ b/fs/xfs/scrub/health.c
@@ -133,7 +133,8 @@ xchk_update_health(
if (!sc->sick_mask)
return;
- bad = (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT);
+ bad = (sc->sm->sm_flags & (XFS_SCRUB_OFLAG_CORRUPT |
+ XFS_SCRUB_OFLAG_XCORRUPT));
switch (type_to_health_flag[sc->sm->sm_type].group) {
case XHG_AG:
pag = xfs_perag_get(sc->mp, sc->sm->sm_agno);
diff --git a/fs/xfs/scrub/ialloc.c b/fs/xfs/scrub/ialloc.c
index 6517d67e8d51..8d9f3fb0cd22 100644
--- a/fs/xfs/scrub/ialloc.c
+++ b/fs/xfs/scrub/ialloc.c
@@ -29,10 +29,9 @@
*/
int
xchk_setup_ag_iallocbt(
- struct xfs_scrub *sc,
- struct xfs_inode *ip)
+ struct xfs_scrub *sc)
{
- return xchk_setup_ag_btree(sc, ip, sc->flags & XCHK_TRY_HARDER);
+ return xchk_setup_ag_btree(sc, sc->flags & XCHK_TRY_HARDER);
}
/* Inode btree scrubber. */
@@ -212,7 +211,6 @@ xchk_iallocbt_check_cluster(
{
struct xfs_imap imap;
struct xfs_mount *mp = bs->cur->bc_mp;
- struct xfs_dinode *dip;
struct xfs_buf *cluster_bp;
unsigned int nr_inodes;
xfs_agnumber_t agno = bs->cur->bc_ag.agno;
@@ -278,7 +276,7 @@ xchk_iallocbt_check_cluster(
&XFS_RMAP_OINFO_INODES);
/* Grab the inode cluster buffer. */
- error = xfs_imap_to_bp(mp, bs->cur->bc_tp, &imap, &dip, &cluster_bp, 0);
+ error = xfs_imap_to_bp(mp, bs->cur->bc_tp, &imap, &cluster_bp);
if (!xchk_btree_xref_process_error(bs->sc, bs->cur, 0, &error))
return error;
diff --git a/fs/xfs/scrub/inode.c b/fs/xfs/scrub/inode.c
index faf65eb5bd31..61f90b2c9430 100644
--- a/fs/xfs/scrub/inode.c
+++ b/fs/xfs/scrub/inode.c
@@ -28,8 +28,7 @@
*/
int
xchk_setup_inode(
- struct xfs_scrub *sc,
- struct xfs_inode *ip)
+ struct xfs_scrub *sc)
{
int error;
@@ -37,7 +36,7 @@ xchk_setup_inode(
* Try to get the inode. If the verifiers fail, we try again
* in raw mode.
*/
- error = xchk_get_inode(sc, ip);
+ error = xchk_get_inode(sc);
switch (error) {
case 0:
break;
diff --git a/fs/xfs/scrub/parent.c b/fs/xfs/scrub/parent.c
index 66c35f6dfc24..ab182a5cd0c0 100644
--- a/fs/xfs/scrub/parent.c
+++ b/fs/xfs/scrub/parent.c
@@ -20,10 +20,9 @@
/* Set us up to scrub parents. */
int
xchk_setup_parent(
- struct xfs_scrub *sc,
- struct xfs_inode *ip)
+ struct xfs_scrub *sc)
{
- return xchk_setup_inode_contents(sc, ip, 0);
+ return xchk_setup_inode_contents(sc, 0);
}
/* Parent pointers */
@@ -102,7 +101,7 @@ xchk_parent_count_parent_dentries(
* scanned.
*/
bufsize = (size_t)min_t(loff_t, XFS_READDIR_BUFSIZE,
- parent->i_d.di_size);
+ parent->i_disk_size);
oldpos = 0;
while (true) {
error = xfs_readdir(sc->tp, parent, &spc.dc, bufsize);
diff --git a/fs/xfs/scrub/quota.c b/fs/xfs/scrub/quota.c
index e34ca20ae8e4..acbb9839d42f 100644
--- a/fs/xfs/scrub/quota.c
+++ b/fs/xfs/scrub/quota.c
@@ -37,8 +37,7 @@ xchk_quota_to_dqtype(
/* Set us up to scrub a quota. */
int
xchk_setup_quota(
- struct xfs_scrub *sc,
- struct xfs_inode *ip)
+ struct xfs_scrub *sc)
{
xfs_dqtype_t dqtype;
int error;
@@ -53,7 +52,7 @@ xchk_setup_quota(
mutex_lock(&sc->mp->m_quotainfo->qi_quotaofflock);
if (!xfs_this_quota_on(sc->mp, dqtype))
return -ENOENT;
- error = xchk_setup_fs(sc, ip);
+ error = xchk_setup_fs(sc);
if (error)
return error;
sc->ip = xfs_quota_inode(sc->mp, dqtype);
@@ -85,7 +84,7 @@ xchk_quota_item(
int error = 0;
if (xchk_should_terminate(sc, &error))
- return error;
+ return -ECANCELED;
/*
* Except for the root dquot, the actual dquot we got must either have
@@ -162,7 +161,7 @@ xchk_quota_item(
out:
if (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)
- return -EFSCORRUPTED;
+ return -ECANCELED;
return 0;
}
@@ -238,6 +237,8 @@ xchk_quota(
error = xfs_qm_dqiterate(mp, dqtype, xchk_quota_item, &sqi);
sc->ilock_flags = XFS_ILOCK_EXCL;
xfs_ilock(sc->ip, sc->ilock_flags);
+ if (error == -ECANCELED)
+ error = 0;
if (!xchk_fblock_process_error(sc, XFS_DATA_FORK,
sqi.last_id * qi->qi_dqperchunk, &error))
goto out;
diff --git a/fs/xfs/scrub/refcount.c b/fs/xfs/scrub/refcount.c
index dd672e6bbc75..744530a66c0c 100644
--- a/fs/xfs/scrub/refcount.c
+++ b/fs/xfs/scrub/refcount.c
@@ -19,10 +19,9 @@
*/
int
xchk_setup_ag_refcountbt(
- struct xfs_scrub *sc,
- struct xfs_inode *ip)
+ struct xfs_scrub *sc)
{
- return xchk_setup_ag_btree(sc, ip, false);
+ return xchk_setup_ag_btree(sc, false);
}
/* Reference count btree scrubber. */
diff --git a/fs/xfs/scrub/repair.c b/fs/xfs/scrub/repair.c
index 25e86c71e7b9..c2857d854c83 100644
--- a/fs/xfs/scrub/repair.c
+++ b/fs/xfs/scrub/repair.c
@@ -37,19 +37,18 @@
*/
int
xrep_attempt(
- struct xfs_inode *ip,
struct xfs_scrub *sc)
{
int error = 0;
- trace_xrep_attempt(ip, sc->sm, error);
+ trace_xrep_attempt(XFS_I(file_inode(sc->file)), sc->sm, error);
xchk_ag_btcur_free(&sc->sa);
/* Repair whatever's broken. */
ASSERT(sc->ops->repair);
error = sc->ops->repair(sc);
- trace_xrep_done(ip, sc->sm, error);
+ trace_xrep_done(XFS_I(file_inode(sc->file)), sc->sm, error);
switch (error) {
case 0:
/*
@@ -207,7 +206,11 @@ xrep_calc_ag_resblks(
/* Now grab the block counters from the AGF. */
error = xfs_alloc_read_agf(mp, NULL, sm->sm_agno, 0, &bp);
- if (!error) {
+ if (error) {
+ aglen = xfs_ag_block_count(mp, sm->sm_agno);
+ freelen = aglen;
+ usedlen = aglen;
+ } else {
struct xfs_agf *agf = bp->b_addr;
aglen = be32_to_cpu(agf->agf_length);
diff --git a/fs/xfs/scrub/repair.h b/fs/xfs/scrub/repair.h
index fe77de01abe0..3bb152d52a07 100644
--- a/fs/xfs/scrub/repair.h
+++ b/fs/xfs/scrub/repair.h
@@ -17,7 +17,7 @@ static inline int xrep_notsupported(struct xfs_scrub *sc)
/* Repair helpers */
-int xrep_attempt(struct xfs_inode *ip, struct xfs_scrub *sc);
+int xrep_attempt(struct xfs_scrub *sc);
void xrep_failure(struct xfs_mount *mp);
int xrep_roll_ag_trans(struct xfs_scrub *sc);
bool xrep_ag_has_space(struct xfs_perag *pag, xfs_extlen_t nr_blocks,
@@ -64,8 +64,8 @@ int xrep_agi(struct xfs_scrub *sc);
#else
-static inline int xrep_attempt(
- struct xfs_inode *ip,
+static inline int
+xrep_attempt(
struct xfs_scrub *sc)
{
return -EOPNOTSUPP;
diff --git a/fs/xfs/scrub/rmap.c b/fs/xfs/scrub/rmap.c
index f4fcb4719f41..a4f17477c5d1 100644
--- a/fs/xfs/scrub/rmap.c
+++ b/fs/xfs/scrub/rmap.c
@@ -21,10 +21,9 @@
*/
int
xchk_setup_ag_rmapbt(
- struct xfs_scrub *sc,
- struct xfs_inode *ip)
+ struct xfs_scrub *sc)
{
- return xchk_setup_ag_btree(sc, ip, false);
+ return xchk_setup_ag_btree(sc, false);
}
/* Reverse-mapping scrubber. */
diff --git a/fs/xfs/scrub/rtbitmap.c b/fs/xfs/scrub/rtbitmap.c
index d409ca592178..37c0e2266c85 100644
--- a/fs/xfs/scrub/rtbitmap.c
+++ b/fs/xfs/scrub/rtbitmap.c
@@ -20,12 +20,11 @@
/* Set us up with the realtime metadata locked. */
int
xchk_setup_rt(
- struct xfs_scrub *sc,
- struct xfs_inode *ip)
+ struct xfs_scrub *sc)
{
int error;
- error = xchk_setup_fs(sc, ip);
+ error = xchk_setup_fs(sc);
if (error)
return error;
@@ -100,7 +99,7 @@ xchk_rtbitmap(
int error;
/* Is the size of the rtbitmap correct? */
- if (sc->mp->m_rbmip->i_d.di_size !=
+ if (sc->mp->m_rbmip->i_disk_size !=
XFS_FSB_TO_B(sc->mp, sc->mp->m_sb.sb_rbmblocks)) {
xchk_ino_set_corrupt(sc, sc->mp->m_rbmip->i_ino);
return 0;
diff --git a/fs/xfs/scrub/scrub.c b/fs/xfs/scrub/scrub.c
index 8ebf35b115ce..0e542636227c 100644
--- a/fs/xfs/scrub/scrub.c
+++ b/fs/xfs/scrub/scrub.c
@@ -149,9 +149,10 @@ xchk_probe(
STATIC int
xchk_teardown(
struct xfs_scrub *sc,
- struct xfs_inode *ip_in,
int error)
{
+ struct xfs_inode *ip_in = XFS_I(file_inode(sc->file));
+
xchk_ag_free(sc, &sc->sa);
if (sc->tp) {
if (error == 0 && (sc->sm->sm_flags & XFS_SCRUB_IFLAG_REPAIR))
@@ -168,7 +169,8 @@ xchk_teardown(
xfs_irele(sc->ip);
sc->ip = NULL;
}
- sb_end_write(sc->mp->m_super);
+ if (sc->sm->sm_flags & XFS_SCRUB_IFLAG_REPAIR)
+ mnt_drop_write_file(sc->file);
if (sc->flags & XCHK_REAPING_DISABLED)
xchk_start_reaping(sc);
if (sc->flags & XCHK_HAS_QUOTAOFFLOCK) {
@@ -456,23 +458,25 @@ static inline void xchk_postmortem(struct xfs_scrub *sc)
/* Dispatch metadata scrubbing. */
int
xfs_scrub_metadata(
- struct xfs_inode *ip,
+ struct file *file,
struct xfs_scrub_metadata *sm)
{
struct xfs_scrub sc = {
- .mp = ip->i_mount,
+ .file = file,
.sm = sm,
.sa = {
.agno = NULLAGNUMBER,
},
};
- struct xfs_mount *mp = ip->i_mount;
+ struct xfs_mount *mp = XFS_I(file_inode(file))->i_mount;
int error = 0;
+ sc.mp = mp;
+
BUILD_BUG_ON(sizeof(meta_scrub_ops) !=
(sizeof(struct xchk_meta_ops) * XFS_SCRUB_TYPE_NR));
- trace_xchk_start(ip, sm, error);
+ trace_xchk_start(XFS_I(file_inode(file)), sm, error);
/* Forbidden if we are shut down or mounted norecovery. */
error = -ESHUTDOWN;
@@ -492,15 +496,17 @@ xfs_scrub_metadata(
sc.sick_mask = xchk_health_mask_for_scrub_type(sm->sm_type);
retry_op:
/*
- * If freeze runs concurrently with a scrub, the freeze can be delayed
- * indefinitely as we walk the filesystem and iterate over metadata
- * buffers. Freeze quiesces the log (which waits for the buffer LRU to
- * be emptied) and that won't happen while checking is running.
+ * When repairs are allowed, prevent freezing or readonly remount while
+ * scrub is running with a real transaction.
*/
- sb_start_write(mp->m_super);
+ if (sm->sm_flags & XFS_SCRUB_IFLAG_REPAIR) {
+ error = mnt_want_write_file(sc.file);
+ if (error)
+ goto out;
+ }
/* Set up for the operation. */
- error = sc.ops->setup(&sc, ip);
+ error = sc.ops->setup(&sc);
if (error)
goto out_teardown;
@@ -512,12 +518,12 @@ retry_op:
* Tear down everything we hold, then set up again with
* preparation for worst-case scenarios.
*/
- error = xchk_teardown(&sc, ip, 0);
+ error = xchk_teardown(&sc, 0);
if (error)
goto out;
sc.flags |= XCHK_TRY_HARDER;
goto retry_op;
- } else if (error)
+ } else if (error || (sm->sm_flags & XFS_SCRUB_OFLAG_INCOMPLETE))
goto out_teardown;
xchk_update_health(&sc);
@@ -546,14 +552,14 @@ retry_op:
* If it's broken, userspace wants us to fix it, and we haven't
* already tried to fix it, then attempt a repair.
*/
- error = xrep_attempt(ip, &sc);
+ error = xrep_attempt(&sc);
if (error == -EAGAIN) {
/*
* Either the repair function succeeded or it couldn't
* get all the resources it needs; either way, we go
* back to the beginning and call the scrub function.
*/
- error = xchk_teardown(&sc, ip, 0);
+ error = xchk_teardown(&sc, 0);
if (error) {
xrep_failure(mp);
goto out;
@@ -565,9 +571,9 @@ retry_op:
out_nofix:
xchk_postmortem(&sc);
out_teardown:
- error = xchk_teardown(&sc, ip, error);
+ error = xchk_teardown(&sc, error);
out:
- trace_xchk_done(ip, sm, error);
+ trace_xchk_done(XFS_I(file_inode(file)), sm, error);
if (error == -EFSCORRUPTED || error == -EFSBADCRC) {
sm->sm_flags |= XFS_SCRUB_OFLAG_CORRUPT;
error = 0;
diff --git a/fs/xfs/scrub/scrub.h b/fs/xfs/scrub/scrub.h
index ad1ceb44a628..08a483cb46e2 100644
--- a/fs/xfs/scrub/scrub.h
+++ b/fs/xfs/scrub/scrub.h
@@ -18,8 +18,7 @@ enum xchk_type {
struct xchk_meta_ops {
/* Acquire whatever resources are needed for the operation. */
- int (*setup)(struct xfs_scrub *,
- struct xfs_inode *);
+ int (*setup)(struct xfs_scrub *sc);
/* Examine metadata for errors. */
int (*scrub)(struct xfs_scrub *);
@@ -59,7 +58,18 @@ struct xfs_scrub {
struct xfs_scrub_metadata *sm;
const struct xchk_meta_ops *ops;
struct xfs_trans *tp;
+
+ /* File that scrub was called with. */
+ struct file *file;
+
+ /*
+ * File that is undergoing the scrub operation. This can differ from
+ * the file that scrub was called with if we're checking file-based fs
+ * metadata (e.g. rt bitmaps) or if we're doing a scrub-by-handle for
+ * something that can't be opened directly (e.g. symlinks).
+ */
struct xfs_inode *ip;
+
void *buf;
uint ilock_flags;
diff --git a/fs/xfs/scrub/symlink.c b/fs/xfs/scrub/symlink.c
index c08be5ede066..599ee277bba2 100644
--- a/fs/xfs/scrub/symlink.c
+++ b/fs/xfs/scrub/symlink.c
@@ -18,15 +18,14 @@
/* Set us up to scrub a symbolic link. */
int
xchk_setup_symlink(
- struct xfs_scrub *sc,
- struct xfs_inode *ip)
+ struct xfs_scrub *sc)
{
/* Allocate the buffer without the inode lock held. */
sc->buf = kvzalloc(XFS_SYMLINK_MAXLEN + 1, GFP_KERNEL);
if (!sc->buf)
return -ENOMEM;
- return xchk_setup_inode_contents(sc, ip, 0);
+ return xchk_setup_inode_contents(sc, 0);
}
/* Symbolic links. */
@@ -43,7 +42,7 @@ xchk_symlink(
if (!S_ISLNK(VFS_I(ip)->i_mode))
return -ENOENT;
ifp = XFS_IFORK_PTR(ip, XFS_DATA_FORK);
- len = ip->i_d.di_size;
+ len = ip->i_disk_size;
/* Plausible size? */
if (len > XFS_SYMLINK_MAXLEN || len <= 0) {
@@ -52,7 +51,7 @@ xchk_symlink(
}
/* Inline symlink? */
- if (ifp->if_flags & XFS_IFINLINE) {
+ if (ifp->if_format == XFS_DINODE_FMT_LOCAL) {
if (len > XFS_IFORK_DSIZE(ip) ||
len > strnlen(ifp->if_u1.if_data, XFS_IFORK_DSIZE(ip)))
xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, 0);
diff --git a/fs/xfs/scrub/xfs_scrub.h b/fs/xfs/scrub/xfs_scrub.h
index 2897ba3a17e6..2ceae614ade8 100644
--- a/fs/xfs/scrub/xfs_scrub.h
+++ b/fs/xfs/scrub/xfs_scrub.h
@@ -7,9 +7,9 @@
#define __XFS_SCRUB_H__
#ifndef CONFIG_XFS_ONLINE_SCRUB
-# define xfs_scrub_metadata(ip, sm) (-ENOTTY)
+# define xfs_scrub_metadata(file, sm) (-ENOTTY)
#else
-int xfs_scrub_metadata(struct xfs_inode *ip, struct xfs_scrub_metadata *sm);
+int xfs_scrub_metadata(struct file *file, struct xfs_scrub_metadata *sm);
#endif /* CONFIG_XFS_ONLINE_SCRUB */
#endif /* __XFS_SCRUB_H__ */
diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c
index b4186d666157..9b08db45ce85 100644
--- a/fs/xfs/xfs_aops.c
+++ b/fs/xfs/xfs_aops.c
@@ -36,47 +36,26 @@ XFS_WPC(struct iomap_writepage_ctx *ctx)
static inline bool xfs_ioend_is_append(struct iomap_ioend *ioend)
{
return ioend->io_offset + ioend->io_size >
- XFS_I(ioend->io_inode)->i_d.di_size;
-}
-
-STATIC int
-xfs_setfilesize_trans_alloc(
- struct iomap_ioend *ioend)
-{
- struct xfs_mount *mp = XFS_I(ioend->io_inode)->i_mount;
- struct xfs_trans *tp;
- int error;
-
- error = xfs_trans_alloc(mp, &M_RES(mp)->tr_fsyncts, 0, 0, 0, &tp);
- if (error)
- return error;
-
- ioend->io_private = tp;
-
- /*
- * We may pass freeze protection with a transaction. So tell lockdep
- * we released it.
- */
- __sb_writers_release(ioend->io_inode->i_sb, SB_FREEZE_FS);
- /*
- * We hand off the transaction to the completion thread now, so
- * clear the flag here.
- */
- xfs_trans_clear_context(tp);
- return 0;
+ XFS_I(ioend->io_inode)->i_disk_size;
}
/*
* Update on-disk file size now that data has been written to disk.
*/
-STATIC int
-__xfs_setfilesize(
+int
+xfs_setfilesize(
struct xfs_inode *ip,
- struct xfs_trans *tp,
xfs_off_t offset,
size_t size)
{
+ struct xfs_mount *mp = ip->i_mount;
+ struct xfs_trans *tp;
xfs_fsize_t isize;
+ int error;
+
+ error = xfs_trans_alloc(mp, &M_RES(mp)->tr_fsyncts, 0, 0, 0, &tp);
+ if (error)
+ return error;
xfs_ilock(ip, XFS_ILOCK_EXCL);
isize = xfs_new_eof(ip, offset + size);
@@ -88,55 +67,13 @@ __xfs_setfilesize(
trace_xfs_setfilesize(ip, offset, size);
- ip->i_d.di_size = isize;
+ ip->i_disk_size = isize;
xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL);
xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
return xfs_trans_commit(tp);
}
-int
-xfs_setfilesize(
- struct xfs_inode *ip,
- xfs_off_t offset,
- size_t size)
-{
- struct xfs_mount *mp = ip->i_mount;
- struct xfs_trans *tp;
- int error;
-
- error = xfs_trans_alloc(mp, &M_RES(mp)->tr_fsyncts, 0, 0, 0, &tp);
- if (error)
- return error;
-
- return __xfs_setfilesize(ip, tp, offset, size);
-}
-
-STATIC int
-xfs_setfilesize_ioend(
- struct iomap_ioend *ioend,
- int error)
-{
- struct xfs_inode *ip = XFS_I(ioend->io_inode);
- struct xfs_trans *tp = ioend->io_private;
-
- /*
- * The transaction may have been allocated in the I/O submission thread,
- * thus we need to mark ourselves as being in a transaction manually.
- * Similarly for freeze protection.
- */
- xfs_trans_set_context(tp);
- __sb_writers_acquired(VFS_I(ip)->i_sb, SB_FREEZE_FS);
-
- /* we abort the update if there was an IO error */
- if (error) {
- xfs_trans_cancel(tp);
- return error;
- }
-
- return __xfs_setfilesize(ip, tp, ioend->io_offset, ioend->io_size);
-}
-
/*
* IO write completion.
*/
@@ -158,7 +95,7 @@ xfs_end_ioend(
nofs_flag = memalloc_nofs_save();
/*
- * Just clean up the in-memory strutures if the fs has been shut down.
+ * Just clean up the in-memory structures if the fs has been shut down.
*/
if (XFS_FORCED_SHUTDOWN(ip->i_mount)) {
error = -EIO;
@@ -182,35 +119,14 @@ xfs_end_ioend(
error = xfs_reflink_end_cow(ip, offset, size);
else if (ioend->io_type == IOMAP_UNWRITTEN)
error = xfs_iomap_write_unwritten(ip, offset, size, false);
- else
- ASSERT(!xfs_ioend_is_append(ioend) || ioend->io_private);
+ if (!error && xfs_ioend_is_append(ioend))
+ error = xfs_setfilesize(ip, ioend->io_offset, ioend->io_size);
done:
- if (ioend->io_private)
- error = xfs_setfilesize_ioend(ioend, error);
iomap_finish_ioends(ioend, error);
memalloc_nofs_restore(nofs_flag);
}
-/*
- * If the to be merged ioend has a preallocated transaction for file
- * size updates we need to ensure the ioend it is merged into also
- * has one. If it already has one we can simply cancel the transaction
- * as it is guaranteed to be clean.
- */
-static void
-xfs_ioend_merge_private(
- struct iomap_ioend *ioend,
- struct iomap_ioend *next)
-{
- if (!ioend->io_private) {
- ioend->io_private = next->io_private;
- next->io_private = NULL;
- } else {
- xfs_setfilesize_ioend(next, -ECANCELED);
- }
-}
-
/* Finish all pending io completions. */
void
xfs_end_io(
@@ -230,18 +146,11 @@ xfs_end_io(
while ((ioend = list_first_entry_or_null(&tmp, struct iomap_ioend,
io_list))) {
list_del_init(&ioend->io_list);
- iomap_ioend_try_merge(ioend, &tmp, xfs_ioend_merge_private);
+ iomap_ioend_try_merge(ioend, &tmp, NULL);
xfs_end_ioend(ioend);
}
}
-static inline bool xfs_ioend_needs_workqueue(struct iomap_ioend *ioend)
-{
- return ioend->io_private ||
- ioend->io_type == IOMAP_UNWRITTEN ||
- (ioend->io_flags & IOMAP_F_SHARED);
-}
-
STATIC void
xfs_end_bio(
struct bio *bio)
@@ -250,8 +159,6 @@ xfs_end_bio(
struct xfs_inode *ip = XFS_I(ioend->io_inode);
unsigned long flags;
- ASSERT(xfs_ioend_needs_workqueue(ioend));
-
spin_lock_irqsave(&ip->i_ioend_lock, flags);
if (list_empty(&ip->i_ioend_list))
WARN_ON_ONCE(!queue_work(ip->i_mount->m_unwritten_workqueue,
@@ -384,8 +291,7 @@ retry:
cow_fsb = NULLFILEOFF;
whichfork = XFS_DATA_FORK;
xfs_ilock(ip, XFS_ILOCK_SHARED);
- ASSERT(ip->i_df.if_format != XFS_DINODE_FMT_BTREE ||
- (ip->i_df.if_flags & XFS_IFEXTENTS));
+ ASSERT(!xfs_need_iread_extents(&ip->i_df));
/*
* Check if this is offset is covered by a COW extents, and if yes use
@@ -501,17 +407,11 @@ xfs_prepare_ioend(
ioend->io_offset, ioend->io_size);
}
- /* Reserve log space if we might write beyond the on-disk inode size. */
- if (!status &&
- ((ioend->io_flags & IOMAP_F_SHARED) ||
- ioend->io_type != IOMAP_UNWRITTEN) &&
- xfs_ioend_is_append(ioend) &&
- !ioend->io_private)
- status = xfs_setfilesize_trans_alloc(ioend);
-
memalloc_nofs_restore(nofs_flag);
- if (xfs_ioend_needs_workqueue(ioend))
+ /* send ioends that might require a transaction to the completion wq */
+ if (xfs_ioend_is_append(ioend) || ioend->io_type == IOMAP_UNWRITTEN ||
+ (ioend->io_flags & IOMAP_F_SHARED))
ioend->io_bio->bi_end_io = xfs_end_bio;
return status;
}
diff --git a/fs/xfs/xfs_attr_list.c b/fs/xfs/xfs_attr_list.c
index 8f8837fe21cf..25dcc98d50e6 100644
--- a/fs/xfs/xfs_attr_list.c
+++ b/fs/xfs/xfs_attr_list.c
@@ -514,7 +514,7 @@ xfs_attr_list_ilocked(
return 0;
if (dp->i_afp->if_format == XFS_DINODE_FMT_LOCAL)
return xfs_attr_shortform_list(context);
- if (xfs_bmap_one_block(dp, XFS_ATTR_FORK))
+ if (xfs_attr_is_leaf(dp))
return xfs_attr_leaf_list(context);
return xfs_attr_node_list(context);
}
diff --git a/fs/xfs/xfs_bmap_item.c b/fs/xfs/xfs_bmap_item.c
index 2344757ede63..e3a691937e92 100644
--- a/fs/xfs/xfs_bmap_item.c
+++ b/fs/xfs/xfs_bmap_item.c
@@ -265,8 +265,8 @@ xfs_trans_log_finish_bmap_update(
static int
xfs_bmap_update_diff_items(
void *priv,
- struct list_head *a,
- struct list_head *b)
+ const struct list_head *a,
+ const struct list_head *b)
{
struct xfs_bmap_intent *ba;
struct xfs_bmap_intent *bb;
diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c
index e7d68318e6a5..a5e9d7d34023 100644
--- a/fs/xfs/xfs_bmap_util.c
+++ b/fs/xfs/xfs_bmap_util.c
@@ -154,7 +154,7 @@ xfs_bmap_rtalloc(
ap->blkno *= mp->m_sb.sb_rextsize;
ralen *= mp->m_sb.sb_rextsize;
ap->length = ralen;
- ap->ip->i_d.di_nblocks += ralen;
+ ap->ip->i_nblocks += ralen;
xfs_trans_log_inode(ap->tp, ap->ip, XFS_ILOG_CORE);
if (ap->wasdel)
ap->ip->i_delayed_blks -= ralen;
@@ -225,11 +225,9 @@ xfs_bmap_count_blocks(
switch (ifp->if_format) {
case XFS_DINODE_FMT_BTREE:
- if (!(ifp->if_flags & XFS_IFEXTENTS)) {
- error = xfs_iread_extents(tp, ip, whichfork);
- if (error)
- return error;
- }
+ error = xfs_iread_extents(tp, ip, whichfork);
+ if (error)
+ return error;
cur = xfs_bmbt_init_cursor(mp, tp, ip, whichfork);
error = xfs_btree_count_blocks(cur, &btblocks);
@@ -423,7 +421,7 @@ xfs_getbmap(
break;
case XFS_DATA_FORK:
if (!(iflags & BMV_IF_DELALLOC) &&
- (ip->i_delayed_blks || XFS_ISIZE(ip) > ip->i_d.di_size)) {
+ (ip->i_delayed_blks || XFS_ISIZE(ip) > ip->i_disk_size)) {
error = filemap_write_and_wait(VFS_I(ip)->i_mapping);
if (error)
goto out_unlock_iolock;
@@ -439,7 +437,7 @@ xfs_getbmap(
}
if (xfs_get_extsz_hint(ip) ||
- (ip->i_d.di_flags &
+ (ip->i_diflags &
(XFS_DIFLAG_PREALLOC | XFS_DIFLAG_APPEND)))
max_len = mp->m_super->s_maxbytes;
else
@@ -471,11 +469,9 @@ xfs_getbmap(
first_bno = bno = XFS_BB_TO_FSBT(mp, bmv->bmv_offset);
len = XFS_BB_TO_FSB(mp, bmv->bmv_length);
- if (!(ifp->if_flags & XFS_IFEXTENTS)) {
- error = xfs_iread_extents(NULL, ip, whichfork);
- if (error)
- goto out_unlock_ilock;
- }
+ error = xfs_iread_extents(NULL, ip, whichfork);
+ if (error)
+ goto out_unlock_ilock;
if (!xfs_iext_lookup_extent(ip, ifp, bno, &icur, &got)) {
/*
@@ -558,7 +554,7 @@ xfs_bmap_punch_delalloc_range(
struct xfs_iext_cursor icur;
int error = 0;
- ASSERT(ifp->if_flags & XFS_IFEXTENTS);
+ ASSERT(!xfs_need_iread_extents(ifp));
xfs_ilock(ip, XFS_ILOCK_EXCL);
if (!xfs_iext_lookup_extent_before(ip, ifp, &end_fsb, &icur, &got))
@@ -597,8 +593,24 @@ out_unlock:
* regular files that are marked preallocated or append-only.
*/
bool
-xfs_can_free_eofblocks(struct xfs_inode *ip, bool force)
+xfs_can_free_eofblocks(
+ struct xfs_inode *ip,
+ bool force)
{
+ struct xfs_bmbt_irec imap;
+ struct xfs_mount *mp = ip->i_mount;
+ xfs_fileoff_t end_fsb;
+ xfs_fileoff_t last_fsb;
+ int nimaps = 1;
+ int error;
+
+ /*
+ * Caller must either hold the exclusive io lock; or be inactivating
+ * the inode, which guarantees there are no other users of the inode.
+ */
+ ASSERT(xfs_isilocked(ip, XFS_IOLOCK_EXCL) ||
+ (VFS_I(ip)->i_state & I_FREEING));
+
/* prealloc/delalloc exists only on regular files */
if (!S_ISREG(VFS_I(ip)->i_mode))
return false;
@@ -613,18 +625,43 @@ xfs_can_free_eofblocks(struct xfs_inode *ip, bool force)
return false;
/* If we haven't read in the extent list, then don't do it now. */
- if (!(ip->i_df.if_flags & XFS_IFEXTENTS))
+ if (xfs_need_iread_extents(&ip->i_df))
return false;
/*
* Do not free real preallocated or append-only files unless the file
* has delalloc blocks and we are forced to remove them.
*/
- if (ip->i_d.di_flags & (XFS_DIFLAG_PREALLOC | XFS_DIFLAG_APPEND))
+ if (ip->i_diflags & (XFS_DIFLAG_PREALLOC | XFS_DIFLAG_APPEND))
if (!force || ip->i_delayed_blks == 0)
return false;
- return true;
+ /*
+ * Do not try to free post-EOF blocks if EOF is beyond the end of the
+ * range supported by the page cache, because the truncation will loop
+ * forever.
+ */
+ end_fsb = XFS_B_TO_FSB(mp, (xfs_ufsize_t)XFS_ISIZE(ip));
+ last_fsb = XFS_B_TO_FSB(mp, mp->m_super->s_maxbytes);
+ if (last_fsb <= end_fsb)
+ return false;
+
+ /*
+ * Look up the mapping for the first block past EOF. If we can't find
+ * it, there's nothing to free.
+ */
+ xfs_ilock(ip, XFS_ILOCK_SHARED);
+ error = xfs_bmapi_read(ip, end_fsb, last_fsb - end_fsb, &imap, &nimaps,
+ 0);
+ xfs_iunlock(ip, XFS_ILOCK_SHARED);
+ if (error || nimaps == 0)
+ return false;
+
+ /*
+ * If there's a real mapping there or there are delayed allocation
+ * reservations, then we have post-EOF blocks to try to free.
+ */
+ return imap.br_startblock != HOLESTARTBLOCK || ip->i_delayed_blks;
}
/*
@@ -637,78 +674,52 @@ xfs_free_eofblocks(
struct xfs_inode *ip)
{
struct xfs_trans *tp;
- int error;
- xfs_fileoff_t end_fsb;
- xfs_fileoff_t last_fsb;
- xfs_filblks_t map_len;
- int nimaps;
- struct xfs_bmbt_irec imap;
struct xfs_mount *mp = ip->i_mount;
+ int error;
- /*
- * Figure out if there are any blocks beyond the end
- * of the file. If not, then there is nothing to do.
- */
- end_fsb = XFS_B_TO_FSB(mp, (xfs_ufsize_t)XFS_ISIZE(ip));
- last_fsb = XFS_B_TO_FSB(mp, mp->m_super->s_maxbytes);
- if (last_fsb <= end_fsb)
- return 0;
- map_len = last_fsb - end_fsb;
+ /* Attach the dquots to the inode up front. */
+ error = xfs_qm_dqattach(ip);
+ if (error)
+ return error;
- nimaps = 1;
- xfs_ilock(ip, XFS_ILOCK_SHARED);
- error = xfs_bmapi_read(ip, end_fsb, map_len, &imap, &nimaps, 0);
- xfs_iunlock(ip, XFS_ILOCK_SHARED);
+ /* Wait on dio to ensure i_size has settled. */
+ inode_dio_wait(VFS_I(ip));
- /*
- * If there are blocks after the end of file, truncate the file to its
- * current size to free them up.
- */
- if (!error && (nimaps != 0) &&
- (imap.br_startblock != HOLESTARTBLOCK ||
- ip->i_delayed_blks)) {
- /*
- * Attach the dquots to the inode up front.
- */
- error = xfs_qm_dqattach(ip);
- if (error)
- return error;
+ error = xfs_trans_alloc(mp, &M_RES(mp)->tr_itruncate, 0, 0, 0, &tp);
+ if (error) {
+ ASSERT(XFS_FORCED_SHUTDOWN(mp));
+ return error;
+ }
- /* wait on dio to ensure i_size has settled */
- inode_dio_wait(VFS_I(ip));
+ xfs_ilock(ip, XFS_ILOCK_EXCL);
+ xfs_trans_ijoin(tp, ip, 0);
- error = xfs_trans_alloc(mp, &M_RES(mp)->tr_itruncate, 0, 0, 0,
- &tp);
- if (error) {
- ASSERT(XFS_FORCED_SHUTDOWN(mp));
- return error;
- }
+ /*
+ * Do not update the on-disk file size. If we update the on-disk file
+ * size and then the system crashes before the contents of the file are
+ * flushed to disk then the files may be full of holes (ie NULL files
+ * bug).
+ */
+ error = xfs_itruncate_extents_flags(&tp, ip, XFS_DATA_FORK,
+ XFS_ISIZE(ip), XFS_BMAPI_NODISCARD);
+ if (error)
+ goto err_cancel;
- xfs_ilock(ip, XFS_ILOCK_EXCL);
- xfs_trans_ijoin(tp, ip, 0);
+ error = xfs_trans_commit(tp);
+ if (error)
+ goto out_unlock;
- /*
- * Do not update the on-disk file size. If we update the
- * on-disk file size and then the system crashes before the
- * contents of the file are flushed to disk then the files
- * may be full of holes (ie NULL files bug).
- */
- error = xfs_itruncate_extents_flags(&tp, ip, XFS_DATA_FORK,
- XFS_ISIZE(ip), XFS_BMAPI_NODISCARD);
- if (error) {
- /*
- * If we get an error at this point we simply don't
- * bother truncating the file.
- */
- xfs_trans_cancel(tp);
- } else {
- error = xfs_trans_commit(tp);
- if (!error)
- xfs_inode_clear_eofblocks_tag(ip);
- }
+ xfs_inode_clear_eofblocks_tag(ip);
+ goto out_unlock;
- xfs_iunlock(ip, XFS_ILOCK_EXCL);
- }
+err_cancel:
+ /*
+ * If we get an error at this point we simply don't
+ * bother truncating the file.
+ */
+ xfs_trans_cancel(tp);
+out_unlock:
+ xfs_iunlock(ip, XFS_ILOCK_EXCL);
return error;
}
@@ -1208,7 +1219,7 @@ xfs_swap_extents_check_format(
if (XFS_IS_QUOTA_ON(ip->i_mount) &&
(!uid_eq(VFS_I(ip)->i_uid, VFS_I(tip)->i_uid) ||
!gid_eq(VFS_I(ip)->i_gid, VFS_I(tip)->i_gid) ||
- ip->i_d.di_projid != tip->i_d.di_projid))
+ ip->i_projid != tip->i_projid))
return -EINVAL;
/* Should never get a local format */
@@ -1323,9 +1334,9 @@ xfs_swap_extent_rmap(
* rmap functions when we go to fix up the rmaps. The flags
* will be switch for reals later.
*/
- tip_flags2 = tip->i_d.di_flags2;
- if (ip->i_d.di_flags2 & XFS_DIFLAG2_REFLINK)
- tip->i_d.di_flags2 |= XFS_DIFLAG2_REFLINK;
+ tip_flags2 = tip->i_diflags2;
+ if (ip->i_diflags2 & XFS_DIFLAG2_REFLINK)
+ tip->i_diflags2 |= XFS_DIFLAG2_REFLINK;
offset_fsb = 0;
end_fsb = XFS_B_TO_FSB(ip->i_mount, i_size_read(VFS_I(ip)));
@@ -1412,12 +1423,12 @@ xfs_swap_extent_rmap(
offset_fsb += ilen;
}
- tip->i_d.di_flags2 = tip_flags2;
+ tip->i_diflags2 = tip_flags2;
return 0;
out:
trace_xfs_swap_extent_rmap_error(ip, error, _RET_IP_);
- tip->i_d.di_flags2 = tip_flags2;
+ tip->i_diflags2 = tip_flags2;
return error;
}
@@ -1476,9 +1487,9 @@ xfs_swap_extent_forks(
/*
* Fix the on-disk inode values
*/
- tmp = (uint64_t)ip->i_d.di_nblocks;
- ip->i_d.di_nblocks = tip->i_d.di_nblocks - taforkblks + aforkblks;
- tip->i_d.di_nblocks = tmp + taforkblks - aforkblks;
+ tmp = (uint64_t)ip->i_nblocks;
+ ip->i_nblocks = tip->i_nblocks - taforkblks + aforkblks;
+ tip->i_nblocks = tmp + taforkblks - aforkblks;
/*
* The extents in the source inode could still contain speculative
@@ -1663,8 +1674,8 @@ xfs_swap_extents(
/* Verify all data are being swapped */
if (sxp->sx_offset != 0 ||
- sxp->sx_length != ip->i_d.di_size ||
- sxp->sx_length != tip->i_d.di_size) {
+ sxp->sx_length != ip->i_disk_size ||
+ sxp->sx_length != tip->i_disk_size) {
error = -EFAULT;
goto out_trans_cancel;
}
@@ -1715,13 +1726,13 @@ xfs_swap_extents(
goto out_trans_cancel;
/* Do we have to swap reflink flags? */
- if ((ip->i_d.di_flags2 & XFS_DIFLAG2_REFLINK) ^
- (tip->i_d.di_flags2 & XFS_DIFLAG2_REFLINK)) {
- f = ip->i_d.di_flags2 & XFS_DIFLAG2_REFLINK;
- ip->i_d.di_flags2 &= ~XFS_DIFLAG2_REFLINK;
- ip->i_d.di_flags2 |= tip->i_d.di_flags2 & XFS_DIFLAG2_REFLINK;
- tip->i_d.di_flags2 &= ~XFS_DIFLAG2_REFLINK;
- tip->i_d.di_flags2 |= f & XFS_DIFLAG2_REFLINK;
+ if ((ip->i_diflags2 & XFS_DIFLAG2_REFLINK) ^
+ (tip->i_diflags2 & XFS_DIFLAG2_REFLINK)) {
+ f = ip->i_diflags2 & XFS_DIFLAG2_REFLINK;
+ ip->i_diflags2 &= ~XFS_DIFLAG2_REFLINK;
+ ip->i_diflags2 |= tip->i_diflags2 & XFS_DIFLAG2_REFLINK;
+ tip->i_diflags2 &= ~XFS_DIFLAG2_REFLINK;
+ tip->i_diflags2 |= f & XFS_DIFLAG2_REFLINK;
}
/* Swap the cow forks. */
diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c
index 37a1d12762d8..592800c8852f 100644
--- a/fs/xfs/xfs_buf.c
+++ b/fs/xfs/xfs_buf.c
@@ -2124,9 +2124,9 @@ xfs_buf_delwri_queue(
*/
static int
xfs_buf_cmp(
- void *priv,
- struct list_head *a,
- struct list_head *b)
+ void *priv,
+ const struct list_head *a,
+ const struct list_head *b)
{
struct xfs_buf *ap = container_of(a, struct xfs_buf, b_list);
struct xfs_buf *bp = container_of(b, struct xfs_buf, b_list);
diff --git a/fs/xfs/xfs_buf_item.c b/fs/xfs/xfs_buf_item.c
index dc0be2a639cc..fb69879e4b2b 100644
--- a/fs/xfs/xfs_buf_item.c
+++ b/fs/xfs/xfs_buf_item.c
@@ -55,6 +55,24 @@ xfs_buf_log_format_size(
(blfp->blf_map_size * sizeof(blfp->blf_data_map[0]));
}
+static inline bool
+xfs_buf_item_straddle(
+ struct xfs_buf *bp,
+ uint offset,
+ int first_bit,
+ int nbits)
+{
+ void *first, *last;
+
+ first = xfs_buf_offset(bp, offset + (first_bit << XFS_BLF_SHIFT));
+ last = xfs_buf_offset(bp,
+ offset + ((first_bit + nbits) << XFS_BLF_SHIFT));
+
+ if (last - first != nbits * XFS_BLF_CHUNK)
+ return true;
+ return false;
+}
+
/*
* This returns the number of log iovecs needed to log the
* given buf log item.
@@ -69,24 +87,56 @@ STATIC void
xfs_buf_item_size_segment(
struct xfs_buf_log_item *bip,
struct xfs_buf_log_format *blfp,
+ uint offset,
int *nvecs,
int *nbytes)
{
struct xfs_buf *bp = bip->bli_buf;
+ int first_bit;
+ int nbits;
int next_bit;
int last_bit;
- last_bit = xfs_next_bit(blfp->blf_data_map, blfp->blf_map_size, 0);
- if (last_bit == -1)
+ first_bit = xfs_next_bit(blfp->blf_data_map, blfp->blf_map_size, 0);
+ if (first_bit == -1)
return;
- /*
- * initial count for a dirty buffer is 2 vectors - the format structure
- * and the first dirty region.
- */
- *nvecs += 2;
- *nbytes += xfs_buf_log_format_size(blfp) + XFS_BLF_CHUNK;
+ (*nvecs)++;
+ *nbytes += xfs_buf_log_format_size(blfp);
+
+ do {
+ nbits = xfs_contig_bits(blfp->blf_data_map,
+ blfp->blf_map_size, first_bit);
+ ASSERT(nbits > 0);
+ /*
+ * Straddling a page is rare because we don't log contiguous
+ * chunks of unmapped buffers anywhere.
+ */
+ if (nbits > 1 &&
+ xfs_buf_item_straddle(bp, offset, first_bit, nbits))
+ goto slow_scan;
+
+ (*nvecs)++;
+ *nbytes += nbits * XFS_BLF_CHUNK;
+
+ /*
+ * This takes the bit number to start looking from and
+ * returns the next set bit from there. It returns -1
+ * if there are no more bits set or the start bit is
+ * beyond the end of the bitmap.
+ */
+ first_bit = xfs_next_bit(blfp->blf_data_map, blfp->blf_map_size,
+ (uint)first_bit + nbits + 1);
+ } while (first_bit != -1);
+
+ return;
+
+slow_scan:
+ /* Count the first bit we jumped out of the above loop from */
+ (*nvecs)++;
+ *nbytes += XFS_BLF_CHUNK;
+ last_bit = first_bit;
while (last_bit != -1) {
/*
* This takes the bit number to start looking from and
@@ -103,16 +153,15 @@ xfs_buf_item_size_segment(
*/
if (next_bit == -1) {
break;
- } else if (next_bit != last_bit + 1) {
- last_bit = next_bit;
- (*nvecs)++;
- } else if (xfs_buf_offset(bp, next_bit * XFS_BLF_CHUNK) !=
- (xfs_buf_offset(bp, last_bit * XFS_BLF_CHUNK) +
- XFS_BLF_CHUNK)) {
+ } else if (next_bit != last_bit + 1 ||
+ xfs_buf_item_straddle(bp, offset, first_bit, nbits)) {
last_bit = next_bit;
+ first_bit = next_bit;
(*nvecs)++;
+ nbits = 1;
} else {
last_bit++;
+ nbits++;
}
*nbytes += XFS_BLF_CHUNK;
}
@@ -142,7 +191,10 @@ xfs_buf_item_size(
int *nbytes)
{
struct xfs_buf_log_item *bip = BUF_ITEM(lip);
+ struct xfs_buf *bp = bip->bli_buf;
int i;
+ int bytes;
+ uint offset = 0;
ASSERT(atomic_read(&bip->bli_refcount) > 0);
if (bip->bli_flags & XFS_BLI_STALE) {
@@ -174,7 +226,7 @@ xfs_buf_item_size(
}
/*
- * the vector count is based on the number of buffer vectors we have
+ * The vector count is based on the number of buffer vectors we have
* dirty bits in. This will only be greater than one when we have a
* compound buffer with more than one segment dirty. Hence for compound
* buffers we need to track which segment the dirty bits correspond to,
@@ -182,10 +234,19 @@ xfs_buf_item_size(
* count for the extra buf log format structure that will need to be
* written.
*/
+ bytes = 0;
for (i = 0; i < bip->bli_format_count; i++) {
- xfs_buf_item_size_segment(bip, &bip->bli_formats[i],
- nvecs, nbytes);
+ xfs_buf_item_size_segment(bip, &bip->bli_formats[i], offset,
+ nvecs, &bytes);
+ offset += BBTOB(bp->b_maps[i].bm_len);
}
+
+ /*
+ * Round up the buffer size required to minimise the number of memory
+ * allocations that need to be done as this item grows when relogged by
+ * repeated modifications.
+ */
+ *nbytes = round_up(bytes, 512);
trace_xfs_buf_item_size(bip);
}
@@ -204,18 +265,6 @@ xfs_buf_item_copy_iovec(
nbits * XFS_BLF_CHUNK);
}
-static inline bool
-xfs_buf_item_straddle(
- struct xfs_buf *bp,
- uint offset,
- int next_bit,
- int last_bit)
-{
- return xfs_buf_offset(bp, offset + (next_bit << XFS_BLF_SHIFT)) !=
- (xfs_buf_offset(bp, offset + (last_bit << XFS_BLF_SHIFT)) +
- XFS_BLF_CHUNK);
-}
-
static void
xfs_buf_item_format_segment(
struct xfs_buf_log_item *bip,
@@ -268,6 +317,38 @@ xfs_buf_item_format_segment(
/*
* Fill in an iovec for each set of contiguous chunks.
*/
+ do {
+ ASSERT(first_bit >= 0);
+ nbits = xfs_contig_bits(blfp->blf_data_map,
+ blfp->blf_map_size, first_bit);
+ ASSERT(nbits > 0);
+
+ /*
+ * Straddling a page is rare because we don't log contiguous
+ * chunks of unmapped buffers anywhere.
+ */
+ if (nbits > 1 &&
+ xfs_buf_item_straddle(bp, offset, first_bit, nbits))
+ goto slow_scan;
+
+ xfs_buf_item_copy_iovec(lv, vecp, bp, offset,
+ first_bit, nbits);
+ blfp->blf_size++;
+
+ /*
+ * This takes the bit number to start looking from and
+ * returns the next set bit from there. It returns -1
+ * if there are no more bits set or the start bit is
+ * beyond the end of the bitmap.
+ */
+ first_bit = xfs_next_bit(blfp->blf_data_map, blfp->blf_map_size,
+ (uint)first_bit + nbits + 1);
+ } while (first_bit != -1);
+
+ return;
+
+slow_scan:
+ ASSERT(bp->b_addr == NULL);
last_bit = first_bit;
nbits = 1;
for (;;) {
@@ -292,7 +373,7 @@ xfs_buf_item_format_segment(
blfp->blf_size++;
break;
} else if (next_bit != last_bit + 1 ||
- xfs_buf_item_straddle(bp, offset, next_bit, last_bit)) {
+ xfs_buf_item_straddle(bp, offset, first_bit, nbits)) {
xfs_buf_item_copy_iovec(lv, vecp, bp, offset,
first_bit, nbits);
blfp->blf_size++;
diff --git a/fs/xfs/xfs_dir2_readdir.c b/fs/xfs/xfs_dir2_readdir.c
index 66deddd5e296..da1cc683560c 100644
--- a/fs/xfs/xfs_dir2_readdir.c
+++ b/fs/xfs/xfs_dir2_readdir.c
@@ -57,8 +57,8 @@ xfs_dir2_sf_getdents(
xfs_ino_t ino;
struct xfs_da_geometry *geo = args->geo;
- ASSERT(dp->i_df.if_flags & XFS_IFINLINE);
- ASSERT(dp->i_df.if_bytes == dp->i_d.di_size);
+ ASSERT(dp->i_df.if_format == XFS_DINODE_FMT_LOCAL);
+ ASSERT(dp->i_df.if_bytes == dp->i_disk_size);
ASSERT(dp->i_df.if_u1.if_data != NULL);
sfp = (xfs_dir2_sf_hdr_t *)dp->i_df.if_u1.if_data;
@@ -258,11 +258,9 @@ xfs_dir2_leaf_readbuf(
int ra_want;
int error = 0;
- if (!(ifp->if_flags & XFS_IFEXTENTS)) {
- error = xfs_iread_extents(args->trans, dp, XFS_DATA_FORK);
- if (error)
- goto out;
- }
+ error = xfs_iread_extents(args->trans, dp, XFS_DATA_FORK);
+ if (error)
+ goto out;
/*
* Look for mapped directory blocks at or above the current offset.
diff --git a/fs/xfs/xfs_dquot.c b/fs/xfs/xfs_dquot.c
index bd8379b98374..ecd5059d6928 100644
--- a/fs/xfs/xfs_dquot.c
+++ b/fs/xfs/xfs_dquot.c
@@ -748,11 +748,9 @@ xfs_dq_get_next_id(
start = (xfs_fsblock_t)next_id / mp->m_quotainfo->qi_dqperchunk;
lock_flags = xfs_ilock_data_map_shared(quotip);
- if (!(quotip->i_df.if_flags & XFS_IFEXTENTS)) {
- error = xfs_iread_extents(NULL, quotip, XFS_DATA_FORK);
- if (error)
- return error;
- }
+ error = xfs_iread_extents(NULL, quotip, XFS_DATA_FORK);
+ if (error)
+ return error;
if (xfs_iext_lookup_extent(quotip, &quotip->i_df, start, &cur, &got)) {
/* contiguous chunk, bump startoff for the id calculation */
@@ -953,7 +951,7 @@ xfs_qm_id_for_quotatype(
case XFS_DQTYPE_GROUP:
return i_gid_read(VFS_I(ip));
case XFS_DQTYPE_PROJ:
- return ip->i_d.di_projid;
+ return ip->i_projid;
}
ASSERT(0);
return 0;
diff --git a/fs/xfs/xfs_error.c b/fs/xfs/xfs_error.c
index 185b4915b7bf..ce3bc1b291a1 100644
--- a/fs/xfs/xfs_error.c
+++ b/fs/xfs/xfs_error.c
@@ -56,6 +56,7 @@ static unsigned int xfs_errortag_random_default[] = {
XFS_RANDOM_BUF_IOERROR,
XFS_RANDOM_REDUCE_MAX_IEXTENTS,
XFS_RANDOM_BMAP_ALLOC_MINLEN_EXTENT,
+ XFS_RANDOM_AG_RESV_FAIL,
};
struct xfs_errortag_attr {
@@ -168,6 +169,7 @@ XFS_ERRORTAG_ATTR_RW(iunlink_fallback, XFS_ERRTAG_IUNLINK_FALLBACK);
XFS_ERRORTAG_ATTR_RW(buf_ioerror, XFS_ERRTAG_BUF_IOERROR);
XFS_ERRORTAG_ATTR_RW(reduce_max_iextents, XFS_ERRTAG_REDUCE_MAX_IEXTENTS);
XFS_ERRORTAG_ATTR_RW(bmap_alloc_minlen_extent, XFS_ERRTAG_BMAP_ALLOC_MINLEN_EXTENT);
+XFS_ERRORTAG_ATTR_RW(ag_resv_fail, XFS_ERRTAG_AG_RESV_FAIL);
static struct attribute *xfs_errortag_attrs[] = {
XFS_ERRORTAG_ATTR_LIST(noerror),
@@ -208,6 +210,7 @@ static struct attribute *xfs_errortag_attrs[] = {
XFS_ERRORTAG_ATTR_LIST(buf_ioerror),
XFS_ERRORTAG_ATTR_LIST(reduce_max_iextents),
XFS_ERRORTAG_ATTR_LIST(bmap_alloc_minlen_extent),
+ XFS_ERRORTAG_ATTR_LIST(ag_resv_fail),
NULL,
};
@@ -299,6 +302,8 @@ xfs_errortag_add(
struct xfs_mount *mp,
unsigned int error_tag)
{
+ BUILD_BUG_ON(ARRAY_SIZE(xfs_errortag_random_default) != XFS_ERRTAG_MAX);
+
if (error_tag >= XFS_ERRTAG_MAX)
return -EINVAL;
diff --git a/fs/xfs/xfs_extent_busy.c b/fs/xfs/xfs_extent_busy.c
index ef17c1f6db32..a4075685d9eb 100644
--- a/fs/xfs/xfs_extent_busy.c
+++ b/fs/xfs/xfs_extent_busy.c
@@ -629,8 +629,8 @@ xfs_extent_busy_wait_all(
int
xfs_extent_busy_ag_cmp(
void *priv,
- struct list_head *l1,
- struct list_head *l2)
+ const struct list_head *l1,
+ const struct list_head *l2)
{
struct xfs_extent_busy *b1 =
container_of(l1, struct xfs_extent_busy, list);
diff --git a/fs/xfs/xfs_extent_busy.h b/fs/xfs/xfs_extent_busy.h
index 990ab3891971..8aea07100092 100644
--- a/fs/xfs/xfs_extent_busy.h
+++ b/fs/xfs/xfs_extent_busy.h
@@ -58,7 +58,8 @@ void
xfs_extent_busy_wait_all(struct xfs_mount *mp);
int
-xfs_extent_busy_ag_cmp(void *priv, struct list_head *a, struct list_head *b);
+xfs_extent_busy_ag_cmp(void *priv, const struct list_head *a,
+ const struct list_head *b);
static inline void xfs_extent_busy_sort(struct list_head *list)
{
diff --git a/fs/xfs/xfs_extfree_item.c b/fs/xfs/xfs_extfree_item.c
index 93223ebb3372..2424230ca2c3 100644
--- a/fs/xfs/xfs_extfree_item.c
+++ b/fs/xfs/xfs_extfree_item.c
@@ -397,8 +397,8 @@ xfs_trans_free_extent(
static int
xfs_extent_free_diff_items(
void *priv,
- struct list_head *a,
- struct list_head *b)
+ const struct list_head *a,
+ const struct list_head *b)
{
struct xfs_mount *mp = priv;
struct xfs_extent_free_item *ra;
diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index a007ca0711d9..396ef36dcd0a 100644
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -90,9 +90,9 @@ xfs_update_prealloc_flags(
}
if (flags & XFS_PREALLOC_SET)
- ip->i_d.di_flags |= XFS_DIFLAG_PREALLOC;
+ ip->i_diflags |= XFS_DIFLAG_PREALLOC;
if (flags & XFS_PREALLOC_CLEAR)
- ip->i_d.di_flags &= ~XFS_DIFLAG_PREALLOC;
+ ip->i_diflags &= ~XFS_DIFLAG_PREALLOC;
xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
if (flags & XFS_PREALLOC_SYNC)
@@ -1159,10 +1159,10 @@ xfs_file_remap_range(
*/
cowextsize = 0;
if (pos_in == 0 && len == i_size_read(inode_in) &&
- (src->i_d.di_flags2 & XFS_DIFLAG2_COWEXTSIZE) &&
+ (src->i_diflags2 & XFS_DIFLAG2_COWEXTSIZE) &&
pos_out == 0 && len >= i_size_read(inode_out) &&
- !(dest->i_d.di_flags2 & XFS_DIFLAG2_COWEXTSIZE))
- cowextsize = src->i_d.di_cowextsize;
+ !(dest->i_diflags2 & XFS_DIFLAG2_COWEXTSIZE))
+ cowextsize = src->i_cowextsize;
ret = xfs_reflink_update_dest(dest, pos_out + len, cowextsize,
remap_flags);
@@ -1244,7 +1244,7 @@ xfs_file_readdir(
* point we can change the ->readdir prototype to include the
* buffer size. For now we use the current glibc buffer size.
*/
- bufsize = (size_t)min_t(loff_t, XFS_READDIR_BUFSIZE, ip->i_d.di_size);
+ bufsize = (size_t)min_t(loff_t, XFS_READDIR_BUFSIZE, ip->i_disk_size);
return xfs_readdir(NULL, ip, ctx, bufsize);
}
diff --git a/fs/xfs/xfs_filestream.h b/fs/xfs/xfs_filestream.h
index 5cc7665e93c9..3af963743e4d 100644
--- a/fs/xfs/xfs_filestream.h
+++ b/fs/xfs/xfs_filestream.h
@@ -22,7 +22,7 @@ xfs_inode_is_filestream(
struct xfs_inode *ip)
{
return (ip->i_mount->m_flags & XFS_MOUNT_FILESTREAMS) ||
- (ip->i_d.di_flags & XFS_DIFLAG_FILESTREAM);
+ (ip->i_diflags & XFS_DIFLAG_FILESTREAM);
}
#endif /* __XFS_FILESTREAM_H__ */
diff --git a/fs/xfs/xfs_fsmap.c b/fs/xfs/xfs_fsmap.c
index 9ce5e7d5bf8f..34f2b971ce43 100644
--- a/fs/xfs/xfs_fsmap.c
+++ b/fs/xfs/xfs_fsmap.c
@@ -904,14 +904,6 @@ xfs_getfsmap(
info.fsmap_recs = fsmap_recs;
info.head = head;
- /*
- * If fsmap runs concurrently with a scrub, the freeze can be delayed
- * indefinitely as we walk the rmapbt and iterate over metadata
- * buffers. Freeze quiesces the log (which waits for the buffer LRU to
- * be emptied) and that won't happen while we're reading buffers.
- */
- sb_start_write(mp->m_super);
-
/* For each device we support... */
for (i = 0; i < XFS_GETFSMAP_DEVS; i++) {
/* Is this device within the range the user asked for? */
@@ -934,6 +926,11 @@ xfs_getfsmap(
if (handlers[i].dev > head->fmh_keys[0].fmr_device)
memset(&dkeys[0], 0, sizeof(struct xfs_fsmap));
+ /*
+ * Grab an empty transaction so that we can use its recursive
+ * buffer locking abilities to detect cycles in the rmapbt
+ * without deadlocking.
+ */
error = xfs_trans_alloc_empty(mp, &tp);
if (error)
break;
@@ -951,7 +948,6 @@ xfs_getfsmap(
if (tp)
xfs_trans_cancel(tp);
- sb_end_write(mp->m_super);
head->fmh_oflags = FMH_OF_DEV_T;
return error;
}
diff --git a/fs/xfs/xfs_fsops.c b/fs/xfs/xfs_fsops.c
index a2a407039227..b33c894b6cf3 100644
--- a/fs/xfs/xfs_fsops.c
+++ b/fs/xfs/xfs_fsops.c
@@ -21,6 +21,64 @@
#include "xfs_ag_resv.h"
/*
+ * Write new AG headers to disk. Non-transactional, but need to be
+ * written and completed prior to the growfs transaction being logged.
+ * To do this, we use a delayed write buffer list and wait for
+ * submission and IO completion of the list as a whole. This allows the
+ * IO subsystem to merge all the AG headers in a single AG into a single
+ * IO and hide most of the latency of the IO from us.
+ *
+ * This also means that if we get an error whilst building the buffer
+ * list to write, we can cancel the entire list without having written
+ * anything.
+ */
+static int
+xfs_resizefs_init_new_ags(
+ struct xfs_trans *tp,
+ struct aghdr_init_data *id,
+ xfs_agnumber_t oagcount,
+ xfs_agnumber_t nagcount,
+ xfs_rfsblock_t delta,
+ bool *lastag_extended)
+{
+ struct xfs_mount *mp = tp->t_mountp;
+ xfs_rfsblock_t nb = mp->m_sb.sb_dblocks + delta;
+ int error;
+
+ *lastag_extended = false;
+
+ INIT_LIST_HEAD(&id->buffer_list);
+ for (id->agno = nagcount - 1;
+ id->agno >= oagcount;
+ id->agno--, delta -= id->agsize) {
+
+ if (id->agno == nagcount - 1)
+ id->agsize = nb - (id->agno *
+ (xfs_rfsblock_t)mp->m_sb.sb_agblocks);
+ else
+ id->agsize = mp->m_sb.sb_agblocks;
+
+ error = xfs_ag_init_headers(mp, id);
+ if (error) {
+ xfs_buf_delwri_cancel(&id->buffer_list);
+ return error;
+ }
+ }
+
+ error = xfs_buf_delwri_submit(&id->buffer_list);
+ if (error)
+ return error;
+
+ xfs_trans_agblocks_delta(tp, id->nfree);
+
+ if (delta) {
+ *lastag_extended = true;
+ error = xfs_ag_extend_space(mp, tp, id, delta);
+ }
+ return error;
+}
+
+/*
* growfs operations
*/
static int
@@ -33,22 +91,25 @@ xfs_growfs_data_private(
xfs_agnumber_t nagcount;
xfs_agnumber_t nagimax = 0;
xfs_rfsblock_t nb, nb_div, nb_mod;
- xfs_rfsblock_t delta;
+ int64_t delta;
+ bool lastag_extended;
xfs_agnumber_t oagcount;
struct xfs_trans *tp;
struct aghdr_init_data id = {};
nb = in->newblocks;
- if (nb < mp->m_sb.sb_dblocks)
- return -EINVAL;
- if ((error = xfs_sb_validate_fsb_count(&mp->m_sb, nb)))
+ error = xfs_sb_validate_fsb_count(&mp->m_sb, nb);
+ if (error)
return error;
- error = xfs_buf_read_uncached(mp->m_ddev_targp,
+
+ if (nb > mp->m_sb.sb_dblocks) {
+ error = xfs_buf_read_uncached(mp->m_ddev_targp,
XFS_FSB_TO_BB(mp, nb) - XFS_FSS_TO_BB(mp, 1),
XFS_FSS_TO_BB(mp, 1), 0, &bp, NULL);
- if (error)
- return error;
- xfs_buf_relse(bp);
+ if (error)
+ return error;
+ xfs_buf_relse(bp);
+ }
nb_div = nb;
nb_mod = do_div(nb_div, mp->m_sb.sb_agblocks);
@@ -56,10 +117,16 @@ xfs_growfs_data_private(
if (nb_mod && nb_mod < XFS_MIN_AG_BLOCKS) {
nagcount--;
nb = (xfs_rfsblock_t)nagcount * mp->m_sb.sb_agblocks;
- if (nb < mp->m_sb.sb_dblocks)
- return -EINVAL;
}
delta = nb - mp->m_sb.sb_dblocks;
+ /*
+ * Reject filesystems with a single AG because they are not
+ * supported, and reject a shrink operation that would cause a
+ * filesystem to become unsupported.
+ */
+ if (delta < 0 && nagcount < 2)
+ return -EINVAL;
+
oagcount = mp->m_sb.sb_agcount;
/* allocate the new per-ag structures */
@@ -67,55 +134,34 @@ xfs_growfs_data_private(
error = xfs_initialize_perag(mp, nagcount, &nagimax);
if (error)
return error;
+ } else if (nagcount < oagcount) {
+ /* TODO: shrinking the entire AGs hasn't yet completed */
+ return -EINVAL;
}
error = xfs_trans_alloc(mp, &M_RES(mp)->tr_growdata,
- XFS_GROWFS_SPACE_RES(mp), 0, XFS_TRANS_RESERVE, &tp);
+ (delta > 0 ? XFS_GROWFS_SPACE_RES(mp) : -delta), 0,
+ XFS_TRANS_RESERVE, &tp);
if (error)
return error;
- /*
- * Write new AG headers to disk. Non-transactional, but need to be
- * written and completed prior to the growfs transaction being logged.
- * To do this, we use a delayed write buffer list and wait for
- * submission and IO completion of the list as a whole. This allows the
- * IO subsystem to merge all the AG headers in a single AG into a single
- * IO and hide most of the latency of the IO from us.
- *
- * This also means that if we get an error whilst building the buffer
- * list to write, we can cancel the entire list without having written
- * anything.
- */
- INIT_LIST_HEAD(&id.buffer_list);
- for (id.agno = nagcount - 1;
- id.agno >= oagcount;
- id.agno--, delta -= id.agsize) {
-
- if (id.agno == nagcount - 1)
- id.agsize = nb -
- (id.agno * (xfs_rfsblock_t)mp->m_sb.sb_agblocks);
- else
- id.agsize = mp->m_sb.sb_agblocks;
+ if (delta > 0) {
+ error = xfs_resizefs_init_new_ags(tp, &id, oagcount, nagcount,
+ delta, &lastag_extended);
+ } else {
+ static struct ratelimit_state shrink_warning = \
+ RATELIMIT_STATE_INIT("shrink_warning", 86400 * HZ, 1);
+ ratelimit_set_flags(&shrink_warning, RATELIMIT_MSG_ON_RELEASE);
- error = xfs_ag_init_headers(mp, &id);
- if (error) {
- xfs_buf_delwri_cancel(&id.buffer_list);
- goto out_trans_cancel;
- }
+ if (__ratelimit(&shrink_warning))
+ xfs_alert(mp,
+ "EXPERIMENTAL online shrink feature in use. Use at your own risk!");
+
+ error = xfs_ag_shrink_space(mp, &tp, nagcount - 1, -delta);
}
- error = xfs_buf_delwri_submit(&id.buffer_list);
if (error)
goto out_trans_cancel;
- xfs_trans_agblocks_delta(tp, id.nfree);
-
- /* If there are new blocks in the old last AG, extend it. */
- if (delta) {
- error = xfs_ag_extend_space(mp, tp, &id, delta);
- if (error)
- goto out_trans_cancel;
- }
-
/*
* Update changed superblock fields transactionally. These are not
* seen by the rest of the world until the transaction commit applies
@@ -123,11 +169,19 @@ xfs_growfs_data_private(
*/
if (nagcount > oagcount)
xfs_trans_mod_sb(tp, XFS_TRANS_SB_AGCOUNT, nagcount - oagcount);
- if (nb > mp->m_sb.sb_dblocks)
- xfs_trans_mod_sb(tp, XFS_TRANS_SB_DBLOCKS,
- nb - mp->m_sb.sb_dblocks);
+ if (delta)
+ xfs_trans_mod_sb(tp, XFS_TRANS_SB_DBLOCKS, delta);
if (id.nfree)
xfs_trans_mod_sb(tp, XFS_TRANS_SB_FDBLOCKS, id.nfree);
+
+ /*
+ * Sync sb counters now to reflect the updated values. This is
+ * particularly important for shrink because the write verifier
+ * will fail if sb_fdblocks is ever larger than sb_dblocks.
+ */
+ if (xfs_sb_version_haslazysbcount(&mp->m_sb))
+ xfs_log_sb(tp);
+
xfs_trans_set_sync(tp);
error = xfs_trans_commit(tp);
if (error)
@@ -139,28 +193,29 @@ xfs_growfs_data_private(
xfs_set_low_space_thresholds(mp);
mp->m_alloc_set_aside = xfs_alloc_set_aside(mp);
- /*
- * If we expanded the last AG, free the per-AG reservation
- * so we can reinitialize it with the new size.
- */
- if (delta) {
- struct xfs_perag *pag;
-
- pag = xfs_perag_get(mp, id.agno);
- error = xfs_ag_resv_free(pag);
- xfs_perag_put(pag);
- if (error)
- return error;
+ if (delta > 0) {
+ /*
+ * If we expanded the last AG, free the per-AG reservation
+ * so we can reinitialize it with the new size.
+ */
+ if (lastag_extended) {
+ struct xfs_perag *pag;
+
+ pag = xfs_perag_get(mp, id.agno);
+ error = xfs_ag_resv_free(pag);
+ xfs_perag_put(pag);
+ if (error)
+ return error;
+ }
+ /*
+ * Reserve AG metadata blocks. ENOSPC here does not mean there
+ * was a growfs failure, just that there still isn't space for
+ * new user data after the grow has been run.
+ */
+ error = xfs_fs_reserve_ag_blocks(mp);
+ if (error == -ENOSPC)
+ error = 0;
}
-
- /*
- * Reserve AG metadata blocks. ENOSPC here does not mean there was a
- * growfs failure, just that there still isn't space for new user data
- * after the grow has been run.
- */
- error = xfs_fs_reserve_ag_blocks(mp);
- if (error == -ENOSPC)
- error = 0;
return error;
out_trans_cancel:
diff --git a/fs/xfs/xfs_icache.c b/fs/xfs/xfs_icache.c
index 1d7720a0c068..3c81daca0e9a 100644
--- a/fs/xfs/xfs_icache.c
+++ b/fs/xfs/xfs_icache.c
@@ -63,7 +63,9 @@ xfs_inode_alloc(
memset(&ip->i_df, 0, sizeof(ip->i_df));
ip->i_flags = 0;
ip->i_delayed_blks = 0;
- memset(&ip->i_d, 0, sizeof(ip->i_d));
+ ip->i_diflags2 = mp->m_ino_geo.new_diflags2;
+ ip->i_nblocks = 0;
+ ip->i_forkoff = 0;
ip->i_sick = 0;
ip->i_checked = 0;
INIT_WORK(&ip->i_ioend_work, xfs_end_io);
@@ -307,7 +309,7 @@ xfs_iget_check_free_state(
return -EFSCORRUPTED;
}
- if (ip->i_d.di_nblocks != 0) {
+ if (ip->i_nblocks != 0) {
xfs_warn(ip->i_mount,
"Corruption detected! Free inode 0x%llx has blocks allocated!",
ip->i_ino);
@@ -497,7 +499,7 @@ xfs_iget_cache_miss(
* simply build the new inode core with a random generation number.
*
* For version 4 (and older) superblocks, log recovery is dependent on
- * the di_flushiter field being initialised from the current on-disk
+ * the i_flushiter field being initialised from the current on-disk
* value and hence we must also read the inode off disk even when
* initializing new inodes.
*/
@@ -505,14 +507,14 @@ xfs_iget_cache_miss(
(flags & XFS_IGET_CREATE) && !(mp->m_flags & XFS_MOUNT_IKEEP)) {
VFS_I(ip)->i_generation = prandom_u32();
} else {
- struct xfs_dinode *dip;
struct xfs_buf *bp;
- error = xfs_imap_to_bp(mp, tp, &ip->i_imap, &dip, &bp, 0);
+ error = xfs_imap_to_bp(mp, tp, &ip->i_imap, &bp);
if (error)
goto out_destroy;
- error = xfs_inode_from_disk(ip, dip);
+ error = xfs_inode_from_disk(ip,
+ xfs_buf_offset(bp, ip->i_imap.im_boffset));
if (!error)
xfs_buf_set_ref(bp, XFS_INO_REF);
xfs_trans_brelse(tp, bp);
@@ -1202,7 +1204,7 @@ xfs_inode_match_id(
return false;
if ((eofb->eof_flags & XFS_EOF_FLAGS_PRID) &&
- ip->i_d.di_projid != eofb->eof_prid)
+ ip->i_projid != eofb->eof_prid)
return false;
return true;
@@ -1226,7 +1228,7 @@ xfs_inode_match_id_union(
return true;
if ((eofb->eof_flags & XFS_EOF_FLAGS_PRID) &&
- ip->i_d.di_projid == eofb->eof_prid)
+ ip->i_projid == eofb->eof_prid)
return true;
return false;
@@ -1294,13 +1296,6 @@ xfs_inode_free_eofblocks(
if (!xfs_iflags_test(ip, XFS_IEOFBLOCKS))
return 0;
- if (!xfs_can_free_eofblocks(ip, false)) {
- /* inode could be preallocated or append-only */
- trace_xfs_inode_free_eofblocks_invalid(ip);
- xfs_inode_clear_eofblocks_tag(ip);
- return 0;
- }
-
/*
* If the mapping is dirty the operation can block and wait for some
* time. Unless we are waiting, skip it.
@@ -1322,7 +1317,13 @@ xfs_inode_free_eofblocks(
}
*lockflags |= XFS_IOLOCK_EXCL;
- return xfs_free_eofblocks(ip);
+ if (xfs_can_free_eofblocks(ip, false))
+ return xfs_free_eofblocks(ip);
+
+ /* inode could be preallocated or append-only */
+ trace_xfs_inode_free_eofblocks_invalid(ip);
+ xfs_inode_clear_eofblocks_tag(ip);
+ return 0;
}
/*
@@ -1335,7 +1336,7 @@ xfs_blockgc_queue(
{
rcu_read_lock();
if (radix_tree_tagged(&pag->pag_ici_root, XFS_ICI_BLOCKGC_TAG))
- queue_delayed_work(pag->pag_mount->m_blockgc_workqueue,
+ queue_delayed_work(pag->pag_mount->m_gc_workqueue,
&pag->pag_blockgc_work,
msecs_to_jiffies(xfs_blockgc_secs * 1000));
rcu_read_unlock();
diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
index 46a861d55e48..0369eb22c1bb 100644
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -60,8 +60,8 @@ xfs_get_extsz_hint(
*/
if (xfs_is_always_cow_inode(ip))
return 0;
- if ((ip->i_d.di_flags & XFS_DIFLAG_EXTSIZE) && ip->i_d.di_extsize)
- return ip->i_d.di_extsize;
+ if ((ip->i_diflags & XFS_DIFLAG_EXTSIZE) && ip->i_extsize)
+ return ip->i_extsize;
if (XFS_IS_REALTIME_INODE(ip))
return ip->i_mount->m_sb.sb_rextsize;
return 0;
@@ -80,8 +80,8 @@ xfs_get_cowextsz_hint(
xfs_extlen_t a, b;
a = 0;
- if (ip->i_d.di_flags2 & XFS_DIFLAG2_COWEXTSIZE)
- a = ip->i_d.di_cowextsize;
+ if (ip->i_diflags2 & XFS_DIFLAG2_COWEXTSIZE)
+ a = ip->i_cowextsize;
b = xfs_get_extsz_hint(ip);
a = max(a, b);
@@ -111,8 +111,7 @@ xfs_ilock_data_map_shared(
{
uint lock_mode = XFS_ILOCK_SHARED;
- if (ip->i_df.if_format == XFS_DINODE_FMT_BTREE &&
- (ip->i_df.if_flags & XFS_IFEXTENTS) == 0)
+ if (xfs_need_iread_extents(&ip->i_df))
lock_mode = XFS_ILOCK_EXCL;
xfs_ilock(ip, lock_mode);
return lock_mode;
@@ -124,9 +123,7 @@ xfs_ilock_attr_map_shared(
{
uint lock_mode = XFS_ILOCK_SHARED;
- if (ip->i_afp &&
- ip->i_afp->if_format == XFS_DINODE_FMT_BTREE &&
- (ip->i_afp->if_flags & XFS_IFEXTENTS) == 0)
+ if (ip->i_afp && xfs_need_iread_extents(ip->i_afp))
lock_mode = XFS_ILOCK_EXCL;
xfs_ilock(ip, lock_mode);
return lock_mode;
@@ -598,67 +595,55 @@ xfs_lock_two_inodes(
}
}
-STATIC uint
-_xfs_dic2xflags(
- uint16_t di_flags,
- uint64_t di_flags2,
- bool has_attr)
+uint
+xfs_ip2xflags(
+ struct xfs_inode *ip)
{
uint flags = 0;
- if (di_flags & XFS_DIFLAG_ANY) {
- if (di_flags & XFS_DIFLAG_REALTIME)
+ if (ip->i_diflags & XFS_DIFLAG_ANY) {
+ if (ip->i_diflags & XFS_DIFLAG_REALTIME)
flags |= FS_XFLAG_REALTIME;
- if (di_flags & XFS_DIFLAG_PREALLOC)
+ if (ip->i_diflags & XFS_DIFLAG_PREALLOC)
flags |= FS_XFLAG_PREALLOC;
- if (di_flags & XFS_DIFLAG_IMMUTABLE)
+ if (ip->i_diflags & XFS_DIFLAG_IMMUTABLE)
flags |= FS_XFLAG_IMMUTABLE;
- if (di_flags & XFS_DIFLAG_APPEND)
+ if (ip->i_diflags & XFS_DIFLAG_APPEND)
flags |= FS_XFLAG_APPEND;
- if (di_flags & XFS_DIFLAG_SYNC)
+ if (ip->i_diflags & XFS_DIFLAG_SYNC)
flags |= FS_XFLAG_SYNC;
- if (di_flags & XFS_DIFLAG_NOATIME)
+ if (ip->i_diflags & XFS_DIFLAG_NOATIME)
flags |= FS_XFLAG_NOATIME;
- if (di_flags & XFS_DIFLAG_NODUMP)
+ if (ip->i_diflags & XFS_DIFLAG_NODUMP)
flags |= FS_XFLAG_NODUMP;
- if (di_flags & XFS_DIFLAG_RTINHERIT)
+ if (ip->i_diflags & XFS_DIFLAG_RTINHERIT)
flags |= FS_XFLAG_RTINHERIT;
- if (di_flags & XFS_DIFLAG_PROJINHERIT)
+ if (ip->i_diflags & XFS_DIFLAG_PROJINHERIT)
flags |= FS_XFLAG_PROJINHERIT;
- if (di_flags & XFS_DIFLAG_NOSYMLINKS)
+ if (ip->i_diflags & XFS_DIFLAG_NOSYMLINKS)
flags |= FS_XFLAG_NOSYMLINKS;
- if (di_flags & XFS_DIFLAG_EXTSIZE)
+ if (ip->i_diflags & XFS_DIFLAG_EXTSIZE)
flags |= FS_XFLAG_EXTSIZE;
- if (di_flags & XFS_DIFLAG_EXTSZINHERIT)
+ if (ip->i_diflags & XFS_DIFLAG_EXTSZINHERIT)
flags |= FS_XFLAG_EXTSZINHERIT;
- if (di_flags & XFS_DIFLAG_NODEFRAG)
+ if (ip->i_diflags & XFS_DIFLAG_NODEFRAG)
flags |= FS_XFLAG_NODEFRAG;
- if (di_flags & XFS_DIFLAG_FILESTREAM)
+ if (ip->i_diflags & XFS_DIFLAG_FILESTREAM)
flags |= FS_XFLAG_FILESTREAM;
}
- if (di_flags2 & XFS_DIFLAG2_ANY) {
- if (di_flags2 & XFS_DIFLAG2_DAX)
+ if (ip->i_diflags2 & XFS_DIFLAG2_ANY) {
+ if (ip->i_diflags2 & XFS_DIFLAG2_DAX)
flags |= FS_XFLAG_DAX;
- if (di_flags2 & XFS_DIFLAG2_COWEXTSIZE)
+ if (ip->i_diflags2 & XFS_DIFLAG2_COWEXTSIZE)
flags |= FS_XFLAG_COWEXTSIZE;
}
- if (has_attr)
+ if (XFS_IFORK_Q(ip))
flags |= FS_XFLAG_HASATTR;
-
return flags;
}
-uint
-xfs_ip2xflags(
- struct xfs_inode *ip)
-{
- struct xfs_icdinode *dic = &ip->i_d;
-
- return _xfs_dic2xflags(dic->di_flags, dic->di_flags2, XFS_IFORK_Q(ip));
-}
-
/*
* Lookups up an inode from "name". If ci_name is not NULL, then a CI match
* is allowed, otherwise it has to be an exact match. If a CI match is found,
@@ -708,42 +693,42 @@ xfs_inode_inherit_flags(
umode_t mode = VFS_I(ip)->i_mode;
if (S_ISDIR(mode)) {
- if (pip->i_d.di_flags & XFS_DIFLAG_RTINHERIT)
+ if (pip->i_diflags & XFS_DIFLAG_RTINHERIT)
di_flags |= XFS_DIFLAG_RTINHERIT;
- if (pip->i_d.di_flags & XFS_DIFLAG_EXTSZINHERIT) {
+ if (pip->i_diflags & XFS_DIFLAG_EXTSZINHERIT) {
di_flags |= XFS_DIFLAG_EXTSZINHERIT;
- ip->i_d.di_extsize = pip->i_d.di_extsize;
+ ip->i_extsize = pip->i_extsize;
}
- if (pip->i_d.di_flags & XFS_DIFLAG_PROJINHERIT)
+ if (pip->i_diflags & XFS_DIFLAG_PROJINHERIT)
di_flags |= XFS_DIFLAG_PROJINHERIT;
} else if (S_ISREG(mode)) {
- if ((pip->i_d.di_flags & XFS_DIFLAG_RTINHERIT) &&
+ if ((pip->i_diflags & XFS_DIFLAG_RTINHERIT) &&
xfs_sb_version_hasrealtime(&ip->i_mount->m_sb))
di_flags |= XFS_DIFLAG_REALTIME;
- if (pip->i_d.di_flags & XFS_DIFLAG_EXTSZINHERIT) {
+ if (pip->i_diflags & XFS_DIFLAG_EXTSZINHERIT) {
di_flags |= XFS_DIFLAG_EXTSIZE;
- ip->i_d.di_extsize = pip->i_d.di_extsize;
+ ip->i_extsize = pip->i_extsize;
}
}
- if ((pip->i_d.di_flags & XFS_DIFLAG_NOATIME) &&
+ if ((pip->i_diflags & XFS_DIFLAG_NOATIME) &&
xfs_inherit_noatime)
di_flags |= XFS_DIFLAG_NOATIME;
- if ((pip->i_d.di_flags & XFS_DIFLAG_NODUMP) &&
+ if ((pip->i_diflags & XFS_DIFLAG_NODUMP) &&
xfs_inherit_nodump)
di_flags |= XFS_DIFLAG_NODUMP;
- if ((pip->i_d.di_flags & XFS_DIFLAG_SYNC) &&
+ if ((pip->i_diflags & XFS_DIFLAG_SYNC) &&
xfs_inherit_sync)
di_flags |= XFS_DIFLAG_SYNC;
- if ((pip->i_d.di_flags & XFS_DIFLAG_NOSYMLINKS) &&
+ if ((pip->i_diflags & XFS_DIFLAG_NOSYMLINKS) &&
xfs_inherit_nosymlinks)
di_flags |= XFS_DIFLAG_NOSYMLINKS;
- if ((pip->i_d.di_flags & XFS_DIFLAG_NODEFRAG) &&
+ if ((pip->i_diflags & XFS_DIFLAG_NODEFRAG) &&
xfs_inherit_nodefrag)
di_flags |= XFS_DIFLAG_NODEFRAG;
- if (pip->i_d.di_flags & XFS_DIFLAG_FILESTREAM)
+ if (pip->i_diflags & XFS_DIFLAG_FILESTREAM)
di_flags |= XFS_DIFLAG_FILESTREAM;
- ip->i_d.di_flags |= di_flags;
+ ip->i_diflags |= di_flags;
}
/* Propagate di_flags2 from a parent inode to a child inode. */
@@ -752,12 +737,12 @@ xfs_inode_inherit_flags2(
struct xfs_inode *ip,
const struct xfs_inode *pip)
{
- if (pip->i_d.di_flags2 & XFS_DIFLAG2_COWEXTSIZE) {
- ip->i_d.di_flags2 |= XFS_DIFLAG2_COWEXTSIZE;
- ip->i_d.di_cowextsize = pip->i_d.di_cowextsize;
+ if (pip->i_diflags2 & XFS_DIFLAG2_COWEXTSIZE) {
+ ip->i_diflags2 |= XFS_DIFLAG2_COWEXTSIZE;
+ ip->i_cowextsize = pip->i_cowextsize;
}
- if (pip->i_d.di_flags2 & XFS_DIFLAG2_DAX)
- ip->i_d.di_flags2 |= XFS_DIFLAG2_DAX;
+ if (pip->i_diflags2 & XFS_DIFLAG2_DAX)
+ ip->i_diflags2 |= XFS_DIFLAG2_DAX;
}
/*
@@ -774,6 +759,7 @@ xfs_init_new_inode(
xfs_nlink_t nlink,
dev_t rdev,
prid_t prid,
+ bool init_xattrs,
struct xfs_inode **ipp)
{
struct inode *dir = pip ? VFS_I(pip) : NULL;
@@ -808,11 +794,11 @@ xfs_init_new_inode(
inode = VFS_I(ip);
set_nlink(inode, nlink);
inode->i_rdev = rdev;
- ip->i_d.di_projid = prid;
+ ip->i_projid = prid;
if (dir && !(dir->i_mode & S_ISGID) &&
(mp->m_flags & XFS_MOUNT_GRPID)) {
- inode->i_uid = fsuid_into_mnt(mnt_userns);
+ inode_fsuid_set(inode, mnt_userns);
inode->i_gid = dir->i_gid;
inode->i_mode = mode;
} else {
@@ -829,25 +815,22 @@ xfs_init_new_inode(
!in_group_p(i_gid_into_mnt(mnt_userns, inode)))
inode->i_mode &= ~S_ISGID;
- ip->i_d.di_size = 0;
+ ip->i_disk_size = 0;
ip->i_df.if_nextents = 0;
- ASSERT(ip->i_d.di_nblocks == 0);
+ ASSERT(ip->i_nblocks == 0);
tv = current_time(inode);
inode->i_mtime = tv;
inode->i_atime = tv;
inode->i_ctime = tv;
- ip->i_d.di_extsize = 0;
- ip->i_d.di_dmevmask = 0;
- ip->i_d.di_dmstate = 0;
- ip->i_d.di_flags = 0;
+ ip->i_extsize = 0;
+ ip->i_diflags = 0;
if (xfs_sb_version_has_v3inode(&mp->m_sb)) {
inode_set_iversion(inode, 1);
- ip->i_d.di_flags2 = mp->m_ino_geo.new_diflags2;
- ip->i_d.di_cowextsize = 0;
- ip->i_d.di_crtime = tv;
+ ip->i_cowextsize = 0;
+ ip->i_crtime = tv;
}
flags = XFS_ILOG_CORE;
@@ -857,19 +840,17 @@ xfs_init_new_inode(
case S_IFBLK:
case S_IFSOCK:
ip->i_df.if_format = XFS_DINODE_FMT_DEV;
- ip->i_df.if_flags = 0;
flags |= XFS_ILOG_DEV;
break;
case S_IFREG:
case S_IFDIR:
- if (pip && (pip->i_d.di_flags & XFS_DIFLAG_ANY))
+ if (pip && (pip->i_diflags & XFS_DIFLAG_ANY))
xfs_inode_inherit_flags(ip, pip);
- if (pip && (pip->i_d.di_flags2 & XFS_DIFLAG2_ANY))
+ if (pip && (pip->i_diflags2 & XFS_DIFLAG2_ANY))
xfs_inode_inherit_flags2(ip, pip);
/* FALLTHROUGH */
case S_IFLNK:
ip->i_df.if_format = XFS_DINODE_FMT_EXTENTS;
- ip->i_df.if_flags = XFS_IFEXTENTS;
ip->i_df.if_bytes = 0;
ip->i_df.if_u1.if_root = NULL;
break;
@@ -878,6 +859,20 @@ xfs_init_new_inode(
}
/*
+ * If we need to create attributes immediately after allocating the
+ * inode, initialise an empty attribute fork right now. We use the
+ * default fork offset for attributes here as we don't know exactly what
+ * size or how many attributes we might be adding. We can do this
+ * safely here because we know the data fork is completely empty and
+ * this saves us from needing to run a separate transaction to set the
+ * fork offset in the immediate future.
+ */
+ if (init_xattrs && xfs_sb_version_hasattr(&mp->m_sb)) {
+ ip->i_forkoff = xfs_default_attroffset(ip) >> 3;
+ ip->i_afp = xfs_ifork_alloc(XFS_DINODE_FMT_EXTENTS, 0);
+ }
+
+ /*
* Log the new values stuffed into the inode.
*/
xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL);
@@ -910,6 +905,7 @@ xfs_dir_ialloc(
xfs_nlink_t nlink,
dev_t rdev,
prid_t prid,
+ bool init_xattrs,
struct xfs_inode **ipp)
{
struct xfs_buf *agibp;
@@ -937,7 +933,7 @@ xfs_dir_ialloc(
ASSERT(ino != NULLFSINO);
return xfs_init_new_inode(mnt_userns, *tpp, dp, ino, mode, nlink, rdev,
- prid, ipp);
+ prid, init_xattrs, ipp);
}
/*
@@ -982,6 +978,7 @@ xfs_create(
struct xfs_name *name,
umode_t mode,
dev_t rdev,
+ bool init_xattrs,
xfs_inode_t **ipp)
{
int is_dir = S_ISDIR(mode);
@@ -1007,9 +1004,10 @@ xfs_create(
/*
* Make sure that we have allocated dquot(s) on disk.
*/
- error = xfs_qm_vop_dqalloc(dp, current_fsuid(), current_fsgid(), prid,
- XFS_QMOPT_QUOTALL | XFS_QMOPT_INHERIT,
- &udqp, &gdqp, &pdqp);
+ error = xfs_qm_vop_dqalloc(dp, mapped_fsuid(mnt_userns),
+ mapped_fsgid(mnt_userns), prid,
+ XFS_QMOPT_QUOTALL | XFS_QMOPT_INHERIT,
+ &udqp, &gdqp, &pdqp);
if (error)
return error;
@@ -1052,7 +1050,7 @@ xfs_create(
* pointing to itself.
*/
error = xfs_dir_ialloc(mnt_userns, &tp, dp, mode, is_dir ? 2 : 1, rdev,
- prid, &ip);
+ prid, init_xattrs, &ip);
if (error)
goto out_trans_cancel;
@@ -1157,9 +1155,10 @@ xfs_create_tmpfile(
/*
* Make sure that we have allocated dquot(s) on disk.
*/
- error = xfs_qm_vop_dqalloc(dp, current_fsuid(), current_fsgid(), prid,
- XFS_QMOPT_QUOTALL | XFS_QMOPT_INHERIT,
- &udqp, &gdqp, &pdqp);
+ error = xfs_qm_vop_dqalloc(dp, mapped_fsuid(mnt_userns),
+ mapped_fsgid(mnt_userns), prid,
+ XFS_QMOPT_QUOTALL | XFS_QMOPT_INHERIT,
+ &udqp, &gdqp, &pdqp);
if (error)
return error;
@@ -1171,7 +1170,8 @@ xfs_create_tmpfile(
if (error)
goto out_release_dquots;
- error = xfs_dir_ialloc(mnt_userns, &tp, dp, mode, 0, 0, prid, &ip);
+ error = xfs_dir_ialloc(mnt_userns, &tp, dp, mode, 0, 0, prid,
+ false, &ip);
if (error)
goto out_trans_cancel;
@@ -1270,8 +1270,8 @@ xfs_link(
* creation in our tree when the project IDs are the same; else
* the tree quota mechanism could be circumvented.
*/
- if (unlikely((tdp->i_d.di_flags & XFS_DIFLAG_PROJINHERIT) &&
- tdp->i_d.di_projid != sip->i_d.di_projid)) {
+ if (unlikely((tdp->i_diflags & XFS_DIFLAG_PROJINHERIT) &&
+ tdp->i_projid != sip->i_projid)) {
error = -EXDEV;
goto error_return;
}
@@ -1329,7 +1329,7 @@ xfs_itruncate_clear_reflink_flags(
dfork = XFS_IFORK_PTR(ip, XFS_DATA_FORK);
cfork = XFS_IFORK_PTR(ip, XFS_COW_FORK);
if (dfork->if_bytes == 0 && cfork->if_bytes == 0)
- ip->i_d.di_flags2 &= ~XFS_DIFLAG2_REFLINK;
+ ip->i_diflags2 &= ~XFS_DIFLAG2_REFLINK;
if (cfork->if_bytes == 0)
xfs_inode_clear_cowblocks_tag(ip);
}
@@ -1440,7 +1440,7 @@ xfs_release(
xfs_inode_t *ip)
{
xfs_mount_t *mp = ip->i_mount;
- int error;
+ int error = 0;
if (!S_ISREG(VFS_I(ip)->i_mode) || (VFS_I(ip)->i_mode == 0))
return 0;
@@ -1476,8 +1476,16 @@ xfs_release(
if (VFS_I(ip)->i_nlink == 0)
return 0;
- if (xfs_can_free_eofblocks(ip, false)) {
+ /*
+ * If we can't get the iolock just skip truncating the blocks past EOF
+ * because we could deadlock with the mmap_lock otherwise. We'll get
+ * another chance to drop them once the last reference to the inode is
+ * dropped, so we'll never leak blocks permanently.
+ */
+ if (!xfs_ilock_nowait(ip, XFS_IOLOCK_EXCL))
+ return 0;
+ if (xfs_can_free_eofblocks(ip, false)) {
/*
* Check if the inode is being opened, written and closed
* frequently and we have delayed allocation blocks outstanding
@@ -1493,26 +1501,20 @@ xfs_release(
* place.
*/
if (xfs_iflags_test(ip, XFS_IDIRTY_RELEASE))
- return 0;
- /*
- * If we can't get the iolock just skip truncating the blocks
- * past EOF because we could deadlock with the mmap_lock
- * otherwise. We'll get another chance to drop them once the
- * last reference to the inode is dropped, so we'll never leak
- * blocks permanently.
- */
- if (xfs_ilock_nowait(ip, XFS_IOLOCK_EXCL)) {
- error = xfs_free_eofblocks(ip);
- xfs_iunlock(ip, XFS_IOLOCK_EXCL);
- if (error)
- return error;
- }
+ goto out_unlock;
+
+ error = xfs_free_eofblocks(ip);
+ if (error)
+ goto out_unlock;
/* delalloc blocks after truncation means it really is dirty */
if (ip->i_delayed_blks)
xfs_iflags_set(ip, XFS_IDIRTY_RELEASE);
}
- return 0;
+
+out_unlock:
+ xfs_iunlock(ip, XFS_IOLOCK_EXCL);
+ return error;
}
/*
@@ -1541,7 +1543,7 @@ xfs_inactive_truncate(
* of a system crash before the truncate completes. See the related
* comment in xfs_vn_setattr_size() for details.
*/
- ip->i_d.di_size = 0;
+ ip->i_disk_size = 0;
xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
error = xfs_itruncate_extents(&tp, ip, XFS_DATA_FORK, 0);
@@ -1695,6 +1697,10 @@ xfs_inactive(
if (mp->m_flags & XFS_MOUNT_RDONLY)
return;
+ /* Metadata inodes require explicit resource cleanup. */
+ if (xfs_is_metadata_inode(ip))
+ return;
+
/* Try to clean out the cow blocks if there are any. */
if (xfs_inode_has_cow_data(ip))
xfs_reflink_cancel_cow_range(ip, 0, NULLFILEOFF, true);
@@ -1716,7 +1722,7 @@ xfs_inactive(
}
if (S_ISREG(VFS_I(ip)->i_mode) &&
- (ip->i_d.di_size != 0 || XFS_ISIZE(ip) != 0 ||
+ (ip->i_disk_size != 0 || XFS_ISIZE(ip) != 0 ||
ip->i_df.if_nextents > 0 || ip->i_delayed_blks > 0))
truncate = 1;
@@ -1743,7 +1749,7 @@ xfs_inactive(
}
ASSERT(!ip->i_afp);
- ASSERT(ip->i_d.di_forkoff == 0);
+ ASSERT(ip->i_forkoff == 0);
/*
* Free the inode.
@@ -2051,9 +2057,10 @@ xfs_iunlink_update_inode(
ASSERT(xfs_verify_agino_or_null(mp, agno, next_agino));
- error = xfs_imap_to_bp(mp, tp, &ip->i_imap, &dip, &ibp, 0);
+ error = xfs_imap_to_bp(mp, tp, &ip->i_imap, &ibp);
if (error)
return error;
+ dip = xfs_buf_offset(ibp, ip->i_imap.im_boffset);
/* Make sure the old pointer isn't garbage. */
old_value = be32_to_cpu(dip->di_next_unlinked);
@@ -2178,13 +2185,14 @@ xfs_iunlink_map_ino(
return error;
}
- error = xfs_imap_to_bp(mp, tp, imap, dipp, bpp, 0);
+ error = xfs_imap_to_bp(mp, tp, imap, bpp);
if (error) {
xfs_warn(mp, "%s: xfs_imap_to_bp returned error %d.",
__func__, error);
return error;
}
+ *dipp = xfs_buf_offset(*bpp, imap->im_boffset);
return 0;
}
@@ -2562,8 +2570,8 @@ xfs_ifree(
ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL));
ASSERT(VFS_I(ip)->i_nlink == 0);
ASSERT(ip->i_df.if_nextents == 0);
- ASSERT(ip->i_d.di_size == 0 || !S_ISREG(VFS_I(ip)->i_mode));
- ASSERT(ip->i_d.di_nblocks == 0);
+ ASSERT(ip->i_disk_size == 0 || !S_ISREG(VFS_I(ip)->i_mode));
+ ASSERT(ip->i_nblocks == 0);
/*
* Pull the on-disk inode from the AGI unlinked list.
@@ -2588,11 +2596,12 @@ xfs_ifree(
}
VFS_I(ip)->i_mode = 0; /* mark incore inode as free */
- ip->i_d.di_flags = 0;
- ip->i_d.di_flags2 = ip->i_mount->m_ino_geo.new_diflags2;
- ip->i_d.di_dmevmask = 0;
- ip->i_d.di_forkoff = 0; /* mark the attr fork not in use */
+ ip->i_diflags = 0;
+ ip->i_diflags2 = ip->i_mount->m_ino_geo.new_diflags2;
+ ip->i_forkoff = 0; /* mark the attr fork not in use */
ip->i_df.if_format = XFS_DINODE_FMT_EXTENTS;
+ if (xfs_iflags_test(ip, XFS_IPRESERVE_DM_FIELDS))
+ xfs_iflags_clear(ip, XFS_IPRESERVE_DM_FIELDS);
/* Don't attempt to replay owner changes for a deleted inode */
spin_lock(&iip->ili_lock);
@@ -2868,7 +2877,7 @@ xfs_finish_rename(
/*
* xfs_cross_rename()
*
- * responsible for handling RENAME_EXCHANGE flag in renameat2() sytemcall
+ * responsible for handling RENAME_EXCHANGE flag in renameat2() syscall
*/
STATIC int
xfs_cross_rename(
@@ -3101,8 +3110,8 @@ xfs_rename(
* into our tree when the project IDs are the same; else the
* tree quota mechanism would be circumvented.
*/
- if (unlikely((target_dp->i_d.di_flags & XFS_DIFLAG_PROJINHERIT) &&
- target_dp->i_d.di_projid != src_ip->i_d.di_projid)) {
+ if (unlikely((target_dp->i_diflags & XFS_DIFLAG_PROJINHERIT) &&
+ target_dp->i_projid != src_ip->i_projid)) {
error = -EXDEV;
goto out_trans_cancel;
}
@@ -3412,34 +3421,33 @@ xfs_iflush(
}
}
if (XFS_TEST_ERROR(ip->i_df.if_nextents + xfs_ifork_nextents(ip->i_afp) >
- ip->i_d.di_nblocks, mp, XFS_ERRTAG_IFLUSH_5)) {
+ ip->i_nblocks, mp, XFS_ERRTAG_IFLUSH_5)) {
xfs_alert_tag(mp, XFS_PTAG_IFLUSH,
"%s: detected corrupt incore inode %Lu, "
"total extents = %d, nblocks = %Ld, ptr "PTR_FMT,
__func__, ip->i_ino,
ip->i_df.if_nextents + xfs_ifork_nextents(ip->i_afp),
- ip->i_d.di_nblocks, ip);
+ ip->i_nblocks, ip);
goto flush_out;
}
- if (XFS_TEST_ERROR(ip->i_d.di_forkoff > mp->m_sb.sb_inodesize,
+ if (XFS_TEST_ERROR(ip->i_forkoff > mp->m_sb.sb_inodesize,
mp, XFS_ERRTAG_IFLUSH_6)) {
xfs_alert_tag(mp, XFS_PTAG_IFLUSH,
"%s: bad inode %Lu, forkoff 0x%x, ptr "PTR_FMT,
- __func__, ip->i_ino, ip->i_d.di_forkoff, ip);
+ __func__, ip->i_ino, ip->i_forkoff, ip);
goto flush_out;
}
/*
- * Inode item log recovery for v2 inodes are dependent on the
- * di_flushiter count for correct sequencing. We bump the flush
- * iteration count so we can detect flushes which postdate a log record
- * during recovery. This is redundant as we now log every change and
- * hence this can't happen but we need to still do it to ensure
- * backwards compatibility with old kernels that predate logging all
- * inode changes.
+ * Inode item log recovery for v2 inodes are dependent on the flushiter
+ * count for correct sequencing. We bump the flush iteration count so
+ * we can detect flushes which postdate a log record during recovery.
+ * This is redundant as we now log every change and hence this can't
+ * happen but we need to still do it to ensure backwards compatibility
+ * with old kernels that predate logging all inode changes.
*/
if (!xfs_sb_version_has_v3inode(&mp->m_sb))
- ip->i_d.di_flushiter++;
+ ip->i_flushiter++;
/*
* If there are inline format data / attr forks attached to this inode,
@@ -3460,8 +3468,10 @@ xfs_iflush(
xfs_inode_to_disk(ip, dip, iip->ili_item.li_lsn);
/* Wrap, we never let the log put out DI_MAX_FLUSH */
- if (ip->i_d.di_flushiter == DI_MAX_FLUSH)
- ip->i_d.di_flushiter = 0;
+ if (!xfs_sb_version_has_v3inode(&mp->m_sb)) {
+ if (ip->i_flushiter == DI_MAX_FLUSH)
+ ip->i_flushiter = 0;
+ }
xfs_iflush_fork(ip, dip, iip, XFS_DATA_FORK);
if (XFS_IFORK_Q(ip))
diff --git a/fs/xfs/xfs_inode.h b/fs/xfs/xfs_inode.h
index 88ee4c3930ae..ca826cfba91c 100644
--- a/fs/xfs/xfs_inode.h
+++ b/fs/xfs/xfs_inode.h
@@ -54,8 +54,19 @@ typedef struct xfs_inode {
/* Miscellaneous state. */
unsigned long i_flags; /* see defined flags below */
uint64_t i_delayed_blks; /* count of delay alloc blks */
-
- struct xfs_icdinode i_d; /* most of ondisk inode */
+ xfs_fsize_t i_disk_size; /* number of bytes in file */
+ xfs_rfsblock_t i_nblocks; /* # of direct & btree blocks */
+ prid_t i_projid; /* owner's project id */
+ xfs_extlen_t i_extsize; /* basic/minimum extent size */
+ /* cowextsize is only used for v3 inodes, flushiter for v1/2 */
+ union {
+ xfs_extlen_t i_cowextsize; /* basic cow extent size */
+ uint16_t i_flushiter; /* incremented on flush */
+ };
+ uint8_t i_forkoff; /* attr fork offset >> 3 */
+ uint16_t i_diflags; /* XFS_DIFLAG_... */
+ uint64_t i_diflags2; /* XFS_DIFLAG2_... */
+ struct timespec64 i_crtime; /* time created */
/* VFS inode */
struct inode i_vnode; /* embedded VFS inode */
@@ -87,7 +98,7 @@ static inline xfs_fsize_t XFS_ISIZE(struct xfs_inode *ip)
{
if (S_ISREG(VFS_I(ip)->i_mode))
return i_size_read(VFS_I(ip));
- return ip->i_d.di_size;
+ return ip->i_disk_size;
}
/*
@@ -101,7 +112,7 @@ xfs_new_eof(struct xfs_inode *ip, xfs_fsize_t new_size)
if (new_size > i_size || new_size < 0)
new_size = i_size;
- return new_size > ip->i_d.di_size ? new_size : 0;
+ return new_size > ip->i_disk_size ? new_size : 0;
}
/*
@@ -174,15 +185,23 @@ xfs_iflags_test_and_set(xfs_inode_t *ip, unsigned short flags)
static inline prid_t
xfs_get_initial_prid(struct xfs_inode *dp)
{
- if (dp->i_d.di_flags & XFS_DIFLAG_PROJINHERIT)
- return dp->i_d.di_projid;
+ if (dp->i_diflags & XFS_DIFLAG_PROJINHERIT)
+ return dp->i_projid;
return XFS_PROJID_DEFAULT;
}
static inline bool xfs_is_reflink_inode(struct xfs_inode *ip)
{
- return ip->i_d.di_flags2 & XFS_DIFLAG2_REFLINK;
+ return ip->i_diflags2 & XFS_DIFLAG2_REFLINK;
+}
+
+static inline bool xfs_is_metadata_inode(struct xfs_inode *ip)
+{
+ struct xfs_mount *mp = ip->i_mount;
+
+ return ip == mp->m_rbmip || ip == mp->m_rsumip ||
+ xfs_is_quota_inode(&mp->m_sb, ip->i_ino);
}
/*
@@ -196,7 +215,7 @@ static inline bool xfs_inode_has_cow_data(struct xfs_inode *ip)
static inline bool xfs_inode_has_bigtime(struct xfs_inode *ip)
{
- return ip->i_d.di_flags2 & XFS_DIFLAG2_BIGTIME;
+ return ip->i_diflags2 & XFS_DIFLAG2_BIGTIME;
}
/*
@@ -214,6 +233,7 @@ static inline bool xfs_inode_has_bigtime(struct xfs_inode *ip)
#define XFS_IRECLAIMABLE (1 << 2) /* inode can be reclaimed */
#define __XFS_INEW_BIT 3 /* inode has just been allocated */
#define XFS_INEW (1 << __XFS_INEW_BIT)
+#define XFS_IPRESERVE_DM_FIELDS (1 << 4) /* has legacy DMAPI fields set */
#define XFS_ITRUNCATED (1 << 5) /* truncated down so flush-on-close */
#define XFS_IDIRTY_RELEASE (1 << 6) /* dirty release already seen */
#define XFS_IFLUSHING (1 << 7) /* inode is being flushed */
@@ -371,7 +391,8 @@ int xfs_lookup(struct xfs_inode *dp, struct xfs_name *name,
struct xfs_inode **ipp, struct xfs_name *ci_name);
int xfs_create(struct user_namespace *mnt_userns,
struct xfs_inode *dp, struct xfs_name *name,
- umode_t mode, dev_t rdev, struct xfs_inode **ipp);
+ umode_t mode, dev_t rdev, bool need_xattr,
+ struct xfs_inode **ipp);
int xfs_create_tmpfile(struct user_namespace *mnt_userns,
struct xfs_inode *dp, umode_t mode,
struct xfs_inode **ipp);
@@ -413,7 +434,8 @@ xfs_extlen_t xfs_get_cowextsz_hint(struct xfs_inode *ip);
int xfs_dir_ialloc(struct user_namespace *mnt_userns,
struct xfs_trans **tpp, struct xfs_inode *dp,
umode_t mode, xfs_nlink_t nlink, dev_t dev,
- prid_t prid, struct xfs_inode **ipp);
+ prid_t prid, bool need_xattr,
+ struct xfs_inode **ipp);
static inline int
xfs_itruncate_extents(
diff --git a/fs/xfs/xfs_inode_item.c b/fs/xfs/xfs_inode_item.c
index 17e20a6d8b4e..c1b32680f71c 100644
--- a/fs/xfs/xfs_inode_item.c
+++ b/fs/xfs/xfs_inode_item.c
@@ -196,7 +196,7 @@ xfs_inode_item_format_data_fork(
*/
data_bytes = roundup(ip->i_df.if_bytes, 4);
ASSERT(ip->i_df.if_u1.if_data != NULL);
- ASSERT(ip->i_d.di_size > 0);
+ ASSERT(ip->i_disk_size > 0);
xlog_copy_iovec(lv, vecp, XLOG_REG_TYPE_ILOCAL,
ip->i_df.if_u1.if_data, data_bytes);
ilf->ilf_dsize = (unsigned)data_bytes;
@@ -317,21 +317,47 @@ xfs_inode_to_log_dinode_ts(
return its;
}
+/*
+ * The legacy DMAPI fields are only present in the on-disk and in-log inodes,
+ * but not in the in-memory one. But we are guaranteed to have an inode buffer
+ * in memory when logging an inode, so we can just copy it from the on-disk
+ * inode to the in-log inode here so that recovery of file system with these
+ * fields set to non-zero values doesn't lose them. For all other cases we zero
+ * the fields.
+ */
+static void
+xfs_copy_dm_fields_to_log_dinode(
+ struct xfs_inode *ip,
+ struct xfs_log_dinode *to)
+{
+ struct xfs_dinode *dip;
+
+ dip = xfs_buf_offset(ip->i_itemp->ili_item.li_buf,
+ ip->i_imap.im_boffset);
+
+ if (xfs_iflags_test(ip, XFS_IPRESERVE_DM_FIELDS)) {
+ to->di_dmevmask = be32_to_cpu(dip->di_dmevmask);
+ to->di_dmstate = be16_to_cpu(dip->di_dmstate);
+ } else {
+ to->di_dmevmask = 0;
+ to->di_dmstate = 0;
+ }
+}
+
static void
xfs_inode_to_log_dinode(
struct xfs_inode *ip,
struct xfs_log_dinode *to,
xfs_lsn_t lsn)
{
- struct xfs_icdinode *from = &ip->i_d;
struct inode *inode = VFS_I(ip);
to->di_magic = XFS_DINODE_MAGIC;
to->di_format = xfs_ifork_format(&ip->i_df);
to->di_uid = i_uid_read(inode);
to->di_gid = i_gid_read(inode);
- to->di_projid_lo = from->di_projid & 0xffff;
- to->di_projid_hi = from->di_projid >> 16;
+ to->di_projid_lo = ip->i_projid & 0xffff;
+ to->di_projid_hi = ip->i_projid >> 16;
memset(to->di_pad, 0, sizeof(to->di_pad));
memset(to->di_pad3, 0, sizeof(to->di_pad3));
@@ -342,16 +368,16 @@ xfs_inode_to_log_dinode(
to->di_gen = inode->i_generation;
to->di_mode = inode->i_mode;
- to->di_size = from->di_size;
- to->di_nblocks = from->di_nblocks;
- to->di_extsize = from->di_extsize;
+ to->di_size = ip->i_disk_size;
+ to->di_nblocks = ip->i_nblocks;
+ to->di_extsize = ip->i_extsize;
to->di_nextents = xfs_ifork_nextents(&ip->i_df);
to->di_anextents = xfs_ifork_nextents(ip->i_afp);
- to->di_forkoff = from->di_forkoff;
+ to->di_forkoff = ip->i_forkoff;
to->di_aformat = xfs_ifork_format(ip->i_afp);
- to->di_dmevmask = from->di_dmevmask;
- to->di_dmstate = from->di_dmstate;
- to->di_flags = from->di_flags;
+ to->di_flags = ip->i_diflags;
+
+ xfs_copy_dm_fields_to_log_dinode(ip, to);
/* log a dummy value to ensure log structure is fully initialised */
to->di_next_unlinked = NULLAGINO;
@@ -359,9 +385,9 @@ xfs_inode_to_log_dinode(
if (xfs_sb_version_has_v3inode(&ip->i_mount->m_sb)) {
to->di_version = 3;
to->di_changecount = inode_peek_iversion(inode);
- to->di_crtime = xfs_inode_to_log_dinode_ts(ip, from->di_crtime);
- to->di_flags2 = from->di_flags2;
- to->di_cowextsize = from->di_cowextsize;
+ to->di_crtime = xfs_inode_to_log_dinode_ts(ip, ip->i_crtime);
+ to->di_flags2 = ip->i_diflags2;
+ to->di_cowextsize = ip->i_cowextsize;
to->di_ino = ip->i_ino;
to->di_lsn = lsn;
memset(to->di_pad2, 0, sizeof(to->di_pad2));
@@ -369,7 +395,7 @@ xfs_inode_to_log_dinode(
to->di_flushiter = 0;
} else {
to->di_version = 2;
- to->di_flushiter = from->di_flushiter;
+ to->di_flushiter = ip->i_flushiter;
}
}
diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c
index 99dfe89a8d08..3925bfcb2365 100644
--- a/fs/xfs/xfs_ioctl.c
+++ b/fs/xfs/xfs_ioctl.c
@@ -40,6 +40,7 @@
#include <linux/mount.h>
#include <linux/namei.h>
+#include <linux/fileattr.h>
/*
* xfs_find_handle maps from userspace xfs_fsop_handlereq structure to
@@ -1053,97 +1054,55 @@ xfs_ioc_ag_geometry(
* Linux extended inode flags interface.
*/
-STATIC unsigned int
-xfs_merge_ioc_xflags(
- unsigned int flags,
- unsigned int start)
-{
- unsigned int xflags = start;
-
- if (flags & FS_IMMUTABLE_FL)
- xflags |= FS_XFLAG_IMMUTABLE;
- else
- xflags &= ~FS_XFLAG_IMMUTABLE;
- if (flags & FS_APPEND_FL)
- xflags |= FS_XFLAG_APPEND;
- else
- xflags &= ~FS_XFLAG_APPEND;
- if (flags & FS_SYNC_FL)
- xflags |= FS_XFLAG_SYNC;
- else
- xflags &= ~FS_XFLAG_SYNC;
- if (flags & FS_NOATIME_FL)
- xflags |= FS_XFLAG_NOATIME;
- else
- xflags &= ~FS_XFLAG_NOATIME;
- if (flags & FS_NODUMP_FL)
- xflags |= FS_XFLAG_NODUMP;
- else
- xflags &= ~FS_XFLAG_NODUMP;
- if (flags & FS_DAX_FL)
- xflags |= FS_XFLAG_DAX;
- else
- xflags &= ~FS_XFLAG_DAX;
-
- return xflags;
-}
-
-STATIC unsigned int
-xfs_di2lxflags(
- uint16_t di_flags,
- uint64_t di_flags2)
-{
- unsigned int flags = 0;
-
- if (di_flags & XFS_DIFLAG_IMMUTABLE)
- flags |= FS_IMMUTABLE_FL;
- if (di_flags & XFS_DIFLAG_APPEND)
- flags |= FS_APPEND_FL;
- if (di_flags & XFS_DIFLAG_SYNC)
- flags |= FS_SYNC_FL;
- if (di_flags & XFS_DIFLAG_NOATIME)
- flags |= FS_NOATIME_FL;
- if (di_flags & XFS_DIFLAG_NODUMP)
- flags |= FS_NODUMP_FL;
- if (di_flags2 & XFS_DIFLAG2_DAX) {
- flags |= FS_DAX_FL;
- }
- return flags;
-}
-
static void
xfs_fill_fsxattr(
struct xfs_inode *ip,
- bool attr,
- struct fsxattr *fa)
+ int whichfork,
+ struct fileattr *fa)
{
- struct xfs_ifork *ifp = attr ? ip->i_afp : &ip->i_df;
-
- simple_fill_fsxattr(fa, xfs_ip2xflags(ip));
- fa->fsx_extsize = ip->i_d.di_extsize << ip->i_mount->m_sb.sb_blocklog;
- fa->fsx_cowextsize = ip->i_d.di_cowextsize <<
- ip->i_mount->m_sb.sb_blocklog;
- fa->fsx_projid = ip->i_d.di_projid;
- if (ifp && (ifp->if_flags & XFS_IFEXTENTS))
+ struct xfs_mount *mp = ip->i_mount;
+ struct xfs_ifork *ifp = XFS_IFORK_PTR(ip, whichfork);
+
+ fileattr_fill_xflags(fa, xfs_ip2xflags(ip));
+
+ fa->fsx_extsize = XFS_FSB_TO_B(mp, ip->i_extsize);
+ if (ip->i_diflags2 & XFS_DIFLAG2_COWEXTSIZE)
+ fa->fsx_cowextsize = XFS_FSB_TO_B(mp, ip->i_cowextsize);
+ fa->fsx_projid = ip->i_projid;
+ if (ifp && !xfs_need_iread_extents(ifp))
fa->fsx_nextents = xfs_iext_count(ifp);
else
fa->fsx_nextents = xfs_ifork_nextents(ifp);
}
STATIC int
-xfs_ioc_fsgetxattr(
+xfs_ioc_fsgetxattra(
xfs_inode_t *ip,
- int attr,
void __user *arg)
{
- struct fsxattr fa;
+ struct fileattr fa;
xfs_ilock(ip, XFS_ILOCK_SHARED);
- xfs_fill_fsxattr(ip, attr, &fa);
+ xfs_fill_fsxattr(ip, XFS_ATTR_FORK, &fa);
+ xfs_iunlock(ip, XFS_ILOCK_SHARED);
+
+ return copy_fsxattr_to_user(&fa, arg);
+}
+
+int
+xfs_fileattr_get(
+ struct dentry *dentry,
+ struct fileattr *fa)
+{
+ struct xfs_inode *ip = XFS_I(d_inode(dentry));
+
+ if (d_is_special(dentry))
+ return -ENOTTY;
+
+ xfs_ilock(ip, XFS_ILOCK_SHARED);
+ xfs_fill_fsxattr(ip, XFS_DATA_FORK, fa);
xfs_iunlock(ip, XFS_ILOCK_SHARED);
- if (copy_to_user(arg, &fa, sizeof(fa)))
- return -EFAULT;
return 0;
}
@@ -1154,7 +1113,7 @@ xfs_flags2diflags(
{
/* can't set PREALLOC this way, just preserve it */
uint16_t di_flags =
- (ip->i_d.di_flags & XFS_DIFLAG_PREALLOC);
+ (ip->i_diflags & XFS_DIFLAG_PREALLOC);
if (xflags & FS_XFLAG_IMMUTABLE)
di_flags |= XFS_DIFLAG_IMMUTABLE;
@@ -1195,8 +1154,8 @@ xfs_flags2diflags2(
unsigned int xflags)
{
uint64_t di_flags2 =
- (ip->i_d.di_flags2 & (XFS_DIFLAG2_REFLINK |
- XFS_DIFLAG2_BIGTIME));
+ (ip->i_diflags2 & (XFS_DIFLAG2_REFLINK |
+ XFS_DIFLAG2_BIGTIME));
if (xflags & FS_XFLAG_DAX)
di_flags2 |= XFS_DIFLAG2_DAX;
@@ -1210,10 +1169,10 @@ static int
xfs_ioctl_setattr_xflags(
struct xfs_trans *tp,
struct xfs_inode *ip,
- struct fsxattr *fa)
+ struct fileattr *fa)
{
struct xfs_mount *mp = ip->i_mount;
- uint64_t di_flags2;
+ uint64_t i_flags2;
/* Can't change realtime flag if any extents are allocated. */
if ((ip->i_df.if_nextents || ip->i_delayed_blks) &&
@@ -1223,25 +1182,25 @@ xfs_ioctl_setattr_xflags(
/* If realtime flag is set then must have realtime device */
if (fa->fsx_xflags & FS_XFLAG_REALTIME) {
if (mp->m_sb.sb_rblocks == 0 || mp->m_sb.sb_rextsize == 0 ||
- (ip->i_d.di_extsize % mp->m_sb.sb_rextsize))
+ (ip->i_extsize % mp->m_sb.sb_rextsize))
return -EINVAL;
}
/* Clear reflink if we are actually able to set the rt flag. */
if ((fa->fsx_xflags & FS_XFLAG_REALTIME) && xfs_is_reflink_inode(ip))
- ip->i_d.di_flags2 &= ~XFS_DIFLAG2_REFLINK;
+ ip->i_diflags2 &= ~XFS_DIFLAG2_REFLINK;
/* Don't allow us to set DAX mode for a reflinked file for now. */
if ((fa->fsx_xflags & FS_XFLAG_DAX) && xfs_is_reflink_inode(ip))
return -EINVAL;
/* diflags2 only valid for v3 inodes. */
- di_flags2 = xfs_flags2diflags2(ip, fa->fsx_xflags);
- if (di_flags2 && !xfs_sb_version_has_v3inode(&mp->m_sb))
+ i_flags2 = xfs_flags2diflags2(ip, fa->fsx_xflags);
+ if (i_flags2 && !xfs_sb_version_has_v3inode(&mp->m_sb))
return -EINVAL;
- ip->i_d.di_flags = xfs_flags2diflags(ip, fa->fsx_xflags);
- ip->i_d.di_flags2 = di_flags2;
+ ip->i_diflags = xfs_flags2diflags(ip, fa->fsx_xflags);
+ ip->i_diflags2 = i_flags2;
xfs_diflags_to_iflags(ip, false);
xfs_trans_ichgtime(tp, ip, XFS_ICHGTIME_CHG);
@@ -1253,7 +1212,7 @@ xfs_ioctl_setattr_xflags(
static void
xfs_ioctl_setattr_prepare_dax(
struct xfs_inode *ip,
- struct fsxattr *fa)
+ struct fileattr *fa)
{
struct xfs_mount *mp = ip->i_mount;
struct inode *inode = VFS_I(ip);
@@ -1266,9 +1225,9 @@ xfs_ioctl_setattr_prepare_dax(
return;
if (((fa->fsx_xflags & FS_XFLAG_DAX) &&
- !(ip->i_d.di_flags2 & XFS_DIFLAG2_DAX)) ||
+ !(ip->i_diflags2 & XFS_DIFLAG2_DAX)) ||
(!(fa->fsx_xflags & FS_XFLAG_DAX) &&
- (ip->i_d.di_flags2 & XFS_DIFLAG2_DAX)))
+ (ip->i_diflags2 & XFS_DIFLAG2_DAX)))
d_mark_dontcache(inode);
}
@@ -1280,10 +1239,9 @@ xfs_ioctl_setattr_prepare_dax(
*/
static struct xfs_trans *
xfs_ioctl_setattr_get_trans(
- struct file *file,
+ struct xfs_inode *ip,
struct xfs_dquot *pdqp)
{
- struct xfs_inode *ip = XFS_I(file_inode(file));
struct xfs_mount *mp = ip->i_mount;
struct xfs_trans *tp;
int error = -EROFS;
@@ -1299,24 +1257,11 @@ xfs_ioctl_setattr_get_trans(
if (error)
goto out_error;
- /*
- * CAP_FOWNER overrides the following restrictions:
- *
- * The user ID of the calling process must be equal to the file owner
- * ID, except in cases where the CAP_FSETID capability is applicable.
- */
- if (!inode_owner_or_capable(file_mnt_user_ns(file), VFS_I(ip))) {
- error = -EPERM;
- goto out_cancel;
- }
-
if (mp->m_flags & XFS_MOUNT_WSYNC)
xfs_trans_set_sync(tp);
return tp;
-out_cancel:
- xfs_trans_cancel(tp);
out_error:
return ERR_PTR(error);
}
@@ -1340,14 +1285,17 @@ out_error:
static int
xfs_ioctl_setattr_check_extsize(
struct xfs_inode *ip,
- struct fsxattr *fa)
+ struct fileattr *fa)
{
struct xfs_mount *mp = ip->i_mount;
xfs_extlen_t size;
xfs_fsblock_t extsize_fsb;
+ if (!fa->fsx_valid)
+ return 0;
+
if (S_ISREG(VFS_I(ip)->i_mode) && ip->i_df.if_nextents &&
- ((ip->i_d.di_extsize << mp->m_sb.sb_blocklog) != fa->fsx_extsize))
+ ((ip->i_extsize << mp->m_sb.sb_blocklog) != fa->fsx_extsize))
return -EINVAL;
if (fa->fsx_extsize == 0)
@@ -1390,12 +1338,15 @@ xfs_ioctl_setattr_check_extsize(
static int
xfs_ioctl_setattr_check_cowextsize(
struct xfs_inode *ip,
- struct fsxattr *fa)
+ struct fileattr *fa)
{
struct xfs_mount *mp = ip->i_mount;
xfs_extlen_t size;
xfs_fsblock_t cowextsize_fsb;
+ if (!fa->fsx_valid)
+ return 0;
+
if (!(fa->fsx_xflags & FS_XFLAG_COWEXTSIZE))
return 0;
@@ -1422,8 +1373,11 @@ xfs_ioctl_setattr_check_cowextsize(
static int
xfs_ioctl_setattr_check_projid(
struct xfs_inode *ip,
- struct fsxattr *fa)
+ struct fileattr *fa)
{
+ if (!fa->fsx_valid)
+ return 0;
+
/* Disallow 32bit project ids if projid32bit feature is not enabled. */
if (fa->fsx_projid > (uint16_t)-1 &&
!xfs_sb_version_hasprojid32bit(&ip->i_mount->m_sb))
@@ -1431,14 +1385,13 @@ xfs_ioctl_setattr_check_projid(
return 0;
}
-STATIC int
-xfs_ioctl_setattr(
- struct file *file,
- struct fsxattr *fa)
+int
+xfs_fileattr_set(
+ struct user_namespace *mnt_userns,
+ struct dentry *dentry,
+ struct fileattr *fa)
{
- struct user_namespace *mnt_userns = file_mnt_user_ns(file);
- struct xfs_inode *ip = XFS_I(file_inode(file));
- struct fsxattr old_fa;
+ struct xfs_inode *ip = XFS_I(d_inode(dentry));
struct xfs_mount *mp = ip->i_mount;
struct xfs_trans *tp;
struct xfs_dquot *pdqp = NULL;
@@ -1447,6 +1400,16 @@ xfs_ioctl_setattr(
trace_xfs_ioctl_setattr(ip);
+ if (d_is_special(dentry))
+ return -ENOTTY;
+
+ if (!fa->fsx_valid) {
+ if (fa->flags & ~(FS_IMMUTABLE_FL | FS_APPEND_FL |
+ FS_NOATIME_FL | FS_NODUMP_FL |
+ FS_SYNC_FL | FS_DAX_FL | FS_PROJINHERIT_FL))
+ return -EOPNOTSUPP;
+ }
+
error = xfs_ioctl_setattr_check_projid(ip, fa);
if (error)
return error;
@@ -1459,7 +1422,7 @@ xfs_ioctl_setattr(
* If the IDs do change before we take the ilock, we're covered
* because the i_*dquot fields will get updated anyway.
*/
- if (XFS_IS_QUOTA_ON(mp)) {
+ if (fa->fsx_valid && XFS_IS_QUOTA_ON(mp)) {
error = xfs_qm_vop_dqalloc(ip, VFS_I(ip)->i_uid,
VFS_I(ip)->i_gid, fa->fsx_projid,
XFS_QMOPT_PQUOTA, NULL, NULL, &pdqp);
@@ -1469,17 +1432,12 @@ xfs_ioctl_setattr(
xfs_ioctl_setattr_prepare_dax(ip, fa);
- tp = xfs_ioctl_setattr_get_trans(file, pdqp);
+ tp = xfs_ioctl_setattr_get_trans(ip, pdqp);
if (IS_ERR(tp)) {
error = PTR_ERR(tp);
goto error_free_dquots;
}
- xfs_fill_fsxattr(ip, false, &old_fa);
- error = vfs_ioc_fssetxattr_check(VFS_I(ip), &old_fa, fa);
- if (error)
- goto error_trans_cancel;
-
error = xfs_ioctl_setattr_check_extsize(ip, fa);
if (error)
goto error_trans_cancel;
@@ -1492,6 +1450,8 @@ xfs_ioctl_setattr(
if (error)
goto error_trans_cancel;
+ if (!fa->fsx_valid)
+ goto skip_xattr;
/*
* Change file ownership. Must be the owner or privileged. CAP_FSETID
* overrides the following restrictions:
@@ -1505,12 +1465,12 @@ xfs_ioctl_setattr(
VFS_I(ip)->i_mode &= ~(S_ISUID|S_ISGID);
/* Change the ownerships and register project quota modifications */
- if (ip->i_d.di_projid != fa->fsx_projid) {
+ if (ip->i_projid != fa->fsx_projid) {
if (XFS_IS_QUOTA_RUNNING(mp) && XFS_IS_PQUOTA_ON(mp)) {
olddquot = xfs_qm_vop_chown(tp, ip,
&ip->i_pdquot, pdqp);
}
- ip->i_d.di_projid = fa->fsx_projid;
+ ip->i_projid = fa->fsx_projid;
}
/*
@@ -1518,17 +1478,19 @@ xfs_ioctl_setattr(
* extent size hint should be set on the inode. If no extent size flags
* are set on the inode then unconditionally clear the extent size hint.
*/
- if (ip->i_d.di_flags & (XFS_DIFLAG_EXTSIZE | XFS_DIFLAG_EXTSZINHERIT))
- ip->i_d.di_extsize = fa->fsx_extsize >> mp->m_sb.sb_blocklog;
- else
- ip->i_d.di_extsize = 0;
- if (xfs_sb_version_has_v3inode(&mp->m_sb) &&
- (ip->i_d.di_flags2 & XFS_DIFLAG2_COWEXTSIZE))
- ip->i_d.di_cowextsize = fa->fsx_cowextsize >>
- mp->m_sb.sb_blocklog;
+ if (ip->i_diflags & (XFS_DIFLAG_EXTSIZE | XFS_DIFLAG_EXTSZINHERIT))
+ ip->i_extsize = XFS_B_TO_FSB(mp, fa->fsx_extsize);
else
- ip->i_d.di_cowextsize = 0;
+ ip->i_extsize = 0;
+
+ if (xfs_sb_version_has_v3inode(&mp->m_sb)) {
+ if (ip->i_diflags2 & XFS_DIFLAG2_COWEXTSIZE)
+ ip->i_cowextsize = XFS_B_TO_FSB(mp, fa->fsx_cowextsize);
+ else
+ ip->i_cowextsize = 0;
+ }
+skip_xattr:
error = xfs_trans_commit(tp);
/*
@@ -1546,91 +1508,6 @@ error_free_dquots:
return error;
}
-STATIC int
-xfs_ioc_fssetxattr(
- struct file *filp,
- void __user *arg)
-{
- struct fsxattr fa;
- int error;
-
- if (copy_from_user(&fa, arg, sizeof(fa)))
- return -EFAULT;
-
- error = mnt_want_write_file(filp);
- if (error)
- return error;
- error = xfs_ioctl_setattr(filp, &fa);
- mnt_drop_write_file(filp);
- return error;
-}
-
-STATIC int
-xfs_ioc_getxflags(
- xfs_inode_t *ip,
- void __user *arg)
-{
- unsigned int flags;
-
- flags = xfs_di2lxflags(ip->i_d.di_flags, ip->i_d.di_flags2);
- if (copy_to_user(arg, &flags, sizeof(flags)))
- return -EFAULT;
- return 0;
-}
-
-STATIC int
-xfs_ioc_setxflags(
- struct xfs_inode *ip,
- struct file *filp,
- void __user *arg)
-{
- struct xfs_trans *tp;
- struct fsxattr fa;
- struct fsxattr old_fa;
- unsigned int flags;
- int error;
-
- if (copy_from_user(&flags, arg, sizeof(flags)))
- return -EFAULT;
-
- if (flags & ~(FS_IMMUTABLE_FL | FS_APPEND_FL | \
- FS_NOATIME_FL | FS_NODUMP_FL | \
- FS_SYNC_FL | FS_DAX_FL))
- return -EOPNOTSUPP;
-
- fa.fsx_xflags = xfs_merge_ioc_xflags(flags, xfs_ip2xflags(ip));
-
- error = mnt_want_write_file(filp);
- if (error)
- return error;
-
- xfs_ioctl_setattr_prepare_dax(ip, &fa);
-
- tp = xfs_ioctl_setattr_get_trans(filp, NULL);
- if (IS_ERR(tp)) {
- error = PTR_ERR(tp);
- goto out_drop_write;
- }
-
- xfs_fill_fsxattr(ip, false, &old_fa);
- error = vfs_ioc_fssetxattr_check(VFS_I(ip), &old_fa, &fa);
- if (error) {
- xfs_trans_cancel(tp);
- goto out_drop_write;
- }
-
- error = xfs_ioctl_setattr_xflags(tp, ip, &fa);
- if (error) {
- xfs_trans_cancel(tp);
- goto out_drop_write;
- }
-
- error = xfs_trans_commit(tp);
-out_drop_write:
- mnt_drop_write_file(filp);
- return error;
-}
-
static bool
xfs_getbmap_format(
struct kgetbmap *p,
@@ -1669,8 +1546,6 @@ xfs_ioc_getbmap(
bmx.bmv_iflags = BMV_IF_ATTRFORK;
/*FALLTHRU*/
case XFS_IOC_GETBMAP:
- if (file->f_mode & FMODE_NOCMTIME)
- bmx.bmv_iflags |= BMV_IF_NO_DMAPI_READ;
/* struct getbmap is a strict subset of struct getbmapx. */
recsize = sizeof(struct getbmap);
break;
@@ -1846,7 +1721,7 @@ out_free:
STATIC int
xfs_ioc_scrub_metadata(
- struct xfs_inode *ip,
+ struct file *file,
void __user *arg)
{
struct xfs_scrub_metadata scrub;
@@ -1858,7 +1733,7 @@ xfs_ioc_scrub_metadata(
if (copy_from_user(&scrub, arg, sizeof(scrub)))
return -EFAULT;
- error = xfs_scrub_metadata(ip, &scrub);
+ error = xfs_scrub_metadata(file, &scrub);
if (error)
return error;
@@ -2137,16 +2012,8 @@ xfs_file_ioctl(
case XFS_IOC_GETVERSION:
return put_user(inode->i_generation, (int __user *)arg);
- case XFS_IOC_FSGETXATTR:
- return xfs_ioc_fsgetxattr(ip, 0, arg);
case XFS_IOC_FSGETXATTRA:
- return xfs_ioc_fsgetxattr(ip, 1, arg);
- case XFS_IOC_FSSETXATTR:
- return xfs_ioc_fssetxattr(filp, arg);
- case XFS_IOC_GETXFLAGS:
- return xfs_ioc_getxflags(ip, arg);
- case XFS_IOC_SETXFLAGS:
- return xfs_ioc_setxflags(ip, filp, arg);
+ return xfs_ioc_fsgetxattra(ip, arg);
case XFS_IOC_GETBMAP:
case XFS_IOC_GETBMAPA:
@@ -2157,7 +2024,7 @@ xfs_file_ioctl(
return xfs_ioc_getfsmap(ip, arg);
case XFS_IOC_SCRUB_METADATA:
- return xfs_ioc_scrub_metadata(ip, arg);
+ return xfs_ioc_scrub_metadata(filp, arg);
case XFS_IOC_FD_TO_HANDLE:
case XFS_IOC_PATH_TO_HANDLE:
diff --git a/fs/xfs/xfs_ioctl.h b/fs/xfs/xfs_ioctl.h
index bab6a5a92407..28453a6d4461 100644
--- a/fs/xfs/xfs_ioctl.h
+++ b/fs/xfs/xfs_ioctl.h
@@ -47,6 +47,17 @@ xfs_handle_to_dentry(
void __user *uhandle,
u32 hlen);
+extern int
+xfs_fileattr_get(
+ struct dentry *dentry,
+ struct fileattr *fa);
+
+extern int
+xfs_fileattr_set(
+ struct user_namespace *mnt_userns,
+ struct dentry *dentry,
+ struct fileattr *fa);
+
extern long
xfs_file_ioctl(
struct file *filp,
diff --git a/fs/xfs/xfs_ioctl32.c b/fs/xfs/xfs_ioctl32.c
index 33c09ec8e6c0..e6506773ba55 100644
--- a/fs/xfs/xfs_ioctl32.c
+++ b/fs/xfs/xfs_ioctl32.c
@@ -484,8 +484,6 @@ xfs_file_compat_ioctl(
}
#endif
/* long changes size, but xfs only copiese out 32 bits */
- case XFS_IOC_GETXFLAGS_32:
- case XFS_IOC_SETXFLAGS_32:
case XFS_IOC_GETVERSION_32:
cmd = _NATIVE_IOC(cmd, long);
return xfs_file_ioctl(filp, cmd, p);
diff --git a/fs/xfs/xfs_ioctl32.h b/fs/xfs/xfs_ioctl32.h
index 053de7d894cd..9929482bf358 100644
--- a/fs/xfs/xfs_ioctl32.h
+++ b/fs/xfs/xfs_ioctl32.h
@@ -17,8 +17,6 @@
*/
/* stock kernel-level ioctls we support */
-#define XFS_IOC_GETXFLAGS_32 FS_IOC32_GETFLAGS
-#define XFS_IOC_SETXFLAGS_32 FS_IOC32_SETFLAGS
#define XFS_IOC_GETVERSION_32 FS_IOC32_GETVERSION
/*
diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c
index e17ab7f42928..d154f42e2dc6 100644
--- a/fs/xfs/xfs_iomap.c
+++ b/fs/xfs/xfs_iomap.c
@@ -159,7 +159,7 @@ xfs_iomap_eof_align_last_fsb(
struct xfs_bmbt_irec irec;
struct xfs_iext_cursor icur;
- ASSERT(ifp->if_flags & XFS_IFEXTENTS);
+ ASSERT(!xfs_need_iread_extents(ifp));
/*
* Always round up the allocation request to the extent hint boundary.
@@ -198,6 +198,7 @@ xfs_iomap_write_direct(
bool force = false;
int error;
int bmapi_flags = XFS_BMAPI_PREALLOC;
+ int nr_exts = XFS_IEXT_ADD_NOSPLIT_CNT;
ASSERT(count_fsb > 0);
@@ -232,6 +233,7 @@ xfs_iomap_write_direct(
bmapi_flags = XFS_BMAPI_CONVERT | XFS_BMAPI_ZERO;
if (imap->br_state == XFS_EXT_UNWRITTEN) {
force = true;
+ nr_exts = XFS_IEXT_WRITE_UNWRITTEN_CNT;
dblocks = XFS_DIOSTRAT_SPACE_RES(mp, 0) << 1;
}
}
@@ -241,8 +243,7 @@ xfs_iomap_write_direct(
if (error)
return error;
- error = xfs_iext_count_may_overflow(ip, XFS_DATA_FORK,
- XFS_IEXT_ADD_NOSPLIT_CNT);
+ error = xfs_iext_count_may_overflow(ip, XFS_DATA_FORK, nr_exts);
if (error)
goto out_trans_cancel;
@@ -572,7 +573,7 @@ xfs_iomap_write_unwritten(
i_size_write(inode, i_size);
i_size = xfs_new_eof(ip, i_size);
if (i_size) {
- ip->i_d.di_size = i_size;
+ ip->i_disk_size = i_size;
xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
}
@@ -666,7 +667,7 @@ xfs_ilock_for_iomap(
* is an opencoded xfs_ilock_data_map_shared() call but with
* non-blocking behaviour.
*/
- if (!(ip->i_df.if_flags & XFS_IFEXTENTS)) {
+ if (xfs_need_iread_extents(&ip->i_df)) {
if (flags & IOMAP_NOWAIT)
return -EAGAIN;
mode = XFS_ILOCK_EXCL;
@@ -893,11 +894,9 @@ xfs_buffered_write_iomap_begin(
XFS_STATS_INC(mp, xs_blk_mapw);
- if (!(ip->i_df.if_flags & XFS_IFEXTENTS)) {
- error = xfs_iread_extents(NULL, ip, XFS_DATA_FORK);
- if (error)
- goto out_unlock;
- }
+ error = xfs_iread_extents(NULL, ip, XFS_DATA_FORK);
+ if (error)
+ goto out_unlock;
/*
* Search the data fork first to look up our source mapping. We
@@ -1208,11 +1207,9 @@ xfs_seek_iomap_begin(
return -EIO;
lockmode = xfs_ilock_data_map_shared(ip);
- if (!(ip->i_df.if_flags & XFS_IFEXTENTS)) {
- error = xfs_iread_extents(NULL, ip, XFS_DATA_FORK);
- if (error)
- goto out_unlock;
- }
+ error = xfs_iread_extents(NULL, ip, XFS_DATA_FORK);
+ if (error)
+ goto out_unlock;
if (xfs_iext_lookup_extent(ip, &ip->i_df, offset_fsb, &icur, &imap)) {
/*
diff --git a/fs/xfs/xfs_iops.c b/fs/xfs/xfs_iops.c
index 66ebccb5a6ff..dfe24b7f26e5 100644
--- a/fs/xfs/xfs_iops.c
+++ b/fs/xfs/xfs_iops.c
@@ -21,6 +21,7 @@
#include "xfs_dir2.h"
#include "xfs_iomap.h"
#include "xfs_error.h"
+#include "xfs_ioctl.h"
#include <linux/posix_acl.h>
#include <linux/security.h>
@@ -126,6 +127,37 @@ xfs_cleanup_inode(
xfs_remove(XFS_I(dir), &teardown, XFS_I(inode));
}
+/*
+ * Check to see if we are likely to need an extended attribute to be added to
+ * the inode we are about to allocate. This allows the attribute fork to be
+ * created during the inode allocation, reducing the number of transactions we
+ * need to do in this fast path.
+ *
+ * The security checks are optimistic, but not guaranteed. The two LSMs that
+ * require xattrs to be added here (selinux and smack) are also the only two
+ * LSMs that add a sb->s_security structure to the superblock. Hence if security
+ * is enabled and sb->s_security is set, we have a pretty good idea that we are
+ * going to be asked to add a security xattr immediately after allocating the
+ * xfs inode and instantiating the VFS inode.
+ */
+static inline bool
+xfs_create_need_xattr(
+ struct inode *dir,
+ struct posix_acl *default_acl,
+ struct posix_acl *acl)
+{
+ if (acl)
+ return true;
+ if (default_acl)
+ return true;
+#if IS_ENABLED(CONFIG_SECURITY)
+ if (dir->i_sb->s_security)
+ return true;
+#endif
+ return false;
+}
+
+
STATIC int
xfs_generic_create(
struct user_namespace *mnt_userns,
@@ -163,7 +195,8 @@ xfs_generic_create(
if (!tmpfile) {
error = xfs_create(mnt_userns, XFS_I(dir), &name, mode, rdev,
- &ip);
+ xfs_create_need_xattr(dir, default_acl, acl),
+ &ip);
} else {
error = xfs_create_tmpfile(mnt_userns, XFS_I(dir), mode, &ip);
}
@@ -487,7 +520,7 @@ xfs_vn_get_link_inline(
struct xfs_inode *ip = XFS_I(inode);
char *link;
- ASSERT(ip->i_df.if_flags & XFS_IFINLINE);
+ ASSERT(ip->i_df.if_format == XFS_DINODE_FMT_LOCAL);
/*
* The VFS crashes on a NULL pointer, so return -EFSCORRUPTED if
@@ -562,13 +595,12 @@ xfs_vn_getattr(
stat->atime = inode->i_atime;
stat->mtime = inode->i_mtime;
stat->ctime = inode->i_ctime;
- stat->blocks =
- XFS_FSB_TO_BB(mp, ip->i_d.di_nblocks + ip->i_delayed_blks);
+ stat->blocks = XFS_FSB_TO_BB(mp, ip->i_nblocks + ip->i_delayed_blks);
if (xfs_sb_version_has_v3inode(&mp->m_sb)) {
if (request_mask & STATX_BTIME) {
stat->result_mask |= STATX_BTIME;
- stat->btime = ip->i_d.di_crtime;
+ stat->btime = ip->i_crtime;
}
}
@@ -576,11 +608,11 @@ xfs_vn_getattr(
* Note: If you add another clause to set an attribute flag, please
* update attributes_mask below.
*/
- if (ip->i_d.di_flags & XFS_DIFLAG_IMMUTABLE)
+ if (ip->i_diflags & XFS_DIFLAG_IMMUTABLE)
stat->attributes |= STATX_ATTR_IMMUTABLE;
- if (ip->i_d.di_flags & XFS_DIFLAG_APPEND)
+ if (ip->i_diflags & XFS_DIFLAG_APPEND)
stat->attributes |= STATX_ATTR_APPEND;
- if (ip->i_d.di_flags & XFS_DIFLAG_NODUMP)
+ if (ip->i_diflags & XFS_DIFLAG_NODUMP)
stat->attributes |= STATX_ATTR_NODUMP;
stat->attributes_mask |= (STATX_ATTR_IMMUTABLE |
@@ -705,7 +737,7 @@ xfs_setattr_nonsize(
*/
ASSERT(udqp == NULL);
ASSERT(gdqp == NULL);
- error = xfs_qm_vop_dqalloc(ip, uid, gid, ip->i_d.di_projid,
+ error = xfs_qm_vop_dqalloc(ip, uid, gid, ip->i_projid,
qflags, &udqp, &gdqp, NULL);
if (error)
return error;
@@ -917,8 +949,8 @@ xfs_setattr_size(
* operation.
*
* And we update in-core i_size and truncate page cache beyond newsize
- * before writeback the [di_size, newsize] range, so we're guaranteed
- * not to write stale data past the new EOF on truncate down.
+ * before writeback the [i_disk_size, newsize] range, so we're
+ * guaranteed not to write stale data past the new EOF on truncate down.
*/
truncate_setsize(inode, newsize);
@@ -931,9 +963,9 @@ xfs_setattr_size(
* otherwise those blocks may not be zeroed after a crash.
*/
if (did_zeroing ||
- (newsize > ip->i_d.di_size && oldsize != ip->i_d.di_size)) {
+ (newsize > ip->i_disk_size && oldsize != ip->i_disk_size)) {
error = filemap_write_and_wait_range(VFS_I(ip)->i_mapping,
- ip->i_d.di_size, newsize - 1);
+ ip->i_disk_size, newsize - 1);
if (error)
return error;
}
@@ -975,7 +1007,7 @@ xfs_setattr_size(
* permanent before actually freeing any blocks it doesn't matter if
* they get written to.
*/
- ip->i_d.di_size = newsize;
+ ip->i_disk_size = newsize;
xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
if (newsize <= oldsize) {
@@ -1152,6 +1184,8 @@ static const struct inode_operations xfs_inode_operations = {
.listxattr = xfs_vn_listxattr,
.fiemap = xfs_vn_fiemap,
.update_time = xfs_vn_update_time,
+ .fileattr_get = xfs_fileattr_get,
+ .fileattr_set = xfs_fileattr_set,
};
static const struct inode_operations xfs_dir_inode_operations = {
@@ -1177,6 +1211,8 @@ static const struct inode_operations xfs_dir_inode_operations = {
.listxattr = xfs_vn_listxattr,
.update_time = xfs_vn_update_time,
.tmpfile = xfs_vn_tmpfile,
+ .fileattr_get = xfs_fileattr_get,
+ .fileattr_set = xfs_fileattr_set,
};
static const struct inode_operations xfs_dir_ci_inode_operations = {
@@ -1202,6 +1238,8 @@ static const struct inode_operations xfs_dir_ci_inode_operations = {
.listxattr = xfs_vn_listxattr,
.update_time = xfs_vn_update_time,
.tmpfile = xfs_vn_tmpfile,
+ .fileattr_get = xfs_fileattr_get,
+ .fileattr_set = xfs_fileattr_set,
};
static const struct inode_operations xfs_symlink_inode_operations = {
@@ -1255,7 +1293,7 @@ xfs_inode_should_enable_dax(
return false;
if (ip->i_mount->m_flags & XFS_MOUNT_DAX_ALWAYS)
return true;
- if (ip->i_d.di_flags2 & XFS_DIFLAG2_DAX)
+ if (ip->i_diflags2 & XFS_DIFLAG2_DAX)
return true;
return false;
}
@@ -1312,7 +1350,7 @@ xfs_setup_inode(
/* make the inode look hashed for the writeback code */
inode_fake_hash(inode);
- i_size_write(inode, ip->i_d.di_size);
+ i_size_write(inode, ip->i_disk_size);
xfs_diflags_to_iflags(ip, true);
if (S_ISDIR(inode->i_mode)) {
@@ -1370,7 +1408,7 @@ xfs_setup_iops(
inode->i_fop = &xfs_dir_file_operations;
break;
case S_IFLNK:
- if (ip->i_df.if_flags & XFS_IFINLINE)
+ if (ip->i_df.if_format == XFS_DINODE_FMT_LOCAL)
inode->i_op = &xfs_inline_symlink_inode_operations;
else
inode->i_op = &xfs_symlink_inode_operations;
diff --git a/fs/xfs/xfs_itable.c b/fs/xfs/xfs_itable.c
index ca310a125d1e..f331975a16de 100644
--- a/fs/xfs/xfs_itable.c
+++ b/fs/xfs/xfs_itable.c
@@ -60,7 +60,6 @@ xfs_bulkstat_one_int(
struct xfs_bstat_chunk *bc)
{
struct user_namespace *sb_userns = mp->m_super->s_user_ns;
- struct xfs_icdinode *dic; /* dinode core info pointer */
struct xfs_inode *ip; /* incore inode pointer */
struct inode *inode;
struct xfs_bulkstat *buf = bc->buf;
@@ -81,16 +80,14 @@ xfs_bulkstat_one_int(
ASSERT(ip->i_imap.im_blkno != 0);
inode = VFS_I(ip);
- dic = &ip->i_d;
-
/* xfs_iget returns the following without needing
* further change.
*/
- buf->bs_projectid = ip->i_d.di_projid;
+ buf->bs_projectid = ip->i_projid;
buf->bs_ino = ino;
buf->bs_uid = from_kuid(sb_userns, i_uid_into_mnt(mnt_userns, inode));
buf->bs_gid = from_kgid(sb_userns, i_gid_into_mnt(mnt_userns, inode));
- buf->bs_size = dic->di_size;
+ buf->bs_size = ip->i_disk_size;
buf->bs_nlink = inode->i_nlink;
buf->bs_atime = inode->i_atime.tv_sec;
@@ -99,13 +96,11 @@ xfs_bulkstat_one_int(
buf->bs_mtime_nsec = inode->i_mtime.tv_nsec;
buf->bs_ctime = inode->i_ctime.tv_sec;
buf->bs_ctime_nsec = inode->i_ctime.tv_nsec;
- buf->bs_btime = dic->di_crtime.tv_sec;
- buf->bs_btime_nsec = dic->di_crtime.tv_nsec;
buf->bs_gen = inode->i_generation;
buf->bs_mode = inode->i_mode;
buf->bs_xflags = xfs_ip2xflags(ip);
- buf->bs_extsize_blks = dic->di_extsize;
+ buf->bs_extsize_blks = ip->i_extsize;
buf->bs_extents = xfs_ifork_nextents(&ip->i_df);
xfs_bulkstat_health(ip, buf);
buf->bs_aextents = xfs_ifork_nextents(ip->i_afp);
@@ -113,8 +108,10 @@ xfs_bulkstat_one_int(
buf->bs_version = XFS_BULKSTAT_VERSION_V5;
if (xfs_sb_version_has_v3inode(&mp->m_sb)) {
- if (dic->di_flags2 & XFS_DIFLAG2_COWEXTSIZE)
- buf->bs_cowextsize_blks = dic->di_cowextsize;
+ buf->bs_btime = ip->i_crtime.tv_sec;
+ buf->bs_btime_nsec = ip->i_crtime.tv_nsec;
+ if (ip->i_diflags2 & XFS_DIFLAG2_COWEXTSIZE)
+ buf->bs_cowextsize_blks = ip->i_cowextsize;
}
switch (ip->i_df.if_format) {
@@ -132,7 +129,7 @@ xfs_bulkstat_one_int(
case XFS_DINODE_FMT_BTREE:
buf->bs_rdev = 0;
buf->bs_blksize = mp->m_sb.sb_blocksize;
- buf->bs_blocks = dic->di_nblocks + ip->i_delayed_blks;
+ buf->bs_blocks = ip->i_nblocks + ip->i_delayed_blks;
break;
}
xfs_iunlock(ip, XFS_ILOCK_SHARED);
@@ -168,6 +165,12 @@ xfs_bulkstat_one(
};
int error;
+ if (breq->mnt_userns != &init_user_ns) {
+ xfs_warn_ratelimited(breq->mp,
+ "bulkstat not supported inside of idmapped mounts.");
+ return -EINVAL;
+ }
+
ASSERT(breq->icount == 1);
bc.buf = kmem_zalloc(sizeof(struct xfs_bulkstat),
diff --git a/fs/xfs/xfs_linux.h b/fs/xfs/xfs_linux.h
index af6be9b9ccdf..7688663b9773 100644
--- a/fs/xfs/xfs_linux.h
+++ b/fs/xfs/xfs_linux.h
@@ -233,7 +233,7 @@ int xfs_rw_bdev(struct block_device *bdev, sector_t sector, unsigned int count,
* configured realtime device.
*/
#define XFS_IS_REALTIME_INODE(ip) \
- (((ip)->i_d.di_flags & XFS_DIFLAG_REALTIME) && \
+ (((ip)->i_diflags & XFS_DIFLAG_REALTIME) && \
(ip)->i_mount->m_rtdev_targp)
#define XFS_IS_REALTIME_MOUNT(mp) ((mp)->m_rtdev_targp ? 1 : 0)
#else
diff --git a/fs/xfs/xfs_log_recover.c b/fs/xfs/xfs_log_recover.c
index 97f31308de03..e5dd1c0c2f03 100644
--- a/fs/xfs/xfs_log_recover.c
+++ b/fs/xfs/xfs_log_recover.c
@@ -2683,9 +2683,10 @@ xlog_recover_process_one_iunlink(
/*
* Get the on disk inode to find the next inode in the bucket.
*/
- error = xfs_imap_to_bp(mp, NULL, &ip->i_imap, &dip, &ibp, 0);
+ error = xfs_imap_to_bp(mp, NULL, &ip->i_imap, &ibp);
if (error)
goto fail_iput;
+ dip = xfs_buf_offset(ibp, ip->i_imap.im_boffset);
xfs_iflags_clear(ip, XFS_IRECOVERY);
ASSERT(VFS_I(ip)->i_nlink == 0);
@@ -2695,12 +2696,6 @@ xlog_recover_process_one_iunlink(
agino = be32_to_cpu(dip->di_next_unlinked);
xfs_buf_relse(ibp);
- /*
- * Prevent any DMAPI event from being sent when the reference on
- * the inode is dropped.
- */
- ip->i_d.di_dmevmask = 0;
-
xfs_irele(ip);
return agino;
@@ -2736,7 +2731,7 @@ xlog_recover_process_one_iunlink(
* of log space.
*
* This behaviour is bad for latency on single CPU and non-preemptible kernels,
- * and can prevent other filesytem work (such as CIL pushes) from running. This
+ * and can prevent other filesystem work (such as CIL pushes) from running. This
* can lead to deadlocks if the recovery process runs out of log reservation
* space. Hence we need to yield the CPU when there is other kernel work
* scheduled on this CPU to ensure other scheduled work can run without undue
@@ -3404,7 +3399,7 @@ xlog_recover(
/*
* Delay log recovery if the debug hook is set. This is debug
- * instrumention to coordinate simulation of I/O failures with
+ * instrumentation to coordinate simulation of I/O failures with
* log recovery.
*/
if (xfs_globals.log_recovery_delay) {
diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c
index 52370d0a3f43..cb1e2c4702c3 100644
--- a/fs/xfs/xfs_mount.c
+++ b/fs/xfs/xfs_mount.c
@@ -635,6 +635,59 @@ xfs_check_summary_counts(
}
/*
+ * Flush and reclaim dirty inodes in preparation for unmount. Inodes and
+ * internal inode structures can be sitting in the CIL and AIL at this point,
+ * so we need to unpin them, write them back and/or reclaim them before unmount
+ * can proceed.
+ *
+ * An inode cluster that has been freed can have its buffer still pinned in
+ * memory because the transaction is still sitting in a iclog. The stale inodes
+ * on that buffer will be pinned to the buffer until the transaction hits the
+ * disk and the callbacks run. Pushing the AIL will skip the stale inodes and
+ * may never see the pinned buffer, so nothing will push out the iclog and
+ * unpin the buffer.
+ *
+ * Hence we need to force the log to unpin everything first. However, log
+ * forces don't wait for the discards they issue to complete, so we have to
+ * explicitly wait for them to complete here as well.
+ *
+ * Then we can tell the world we are unmounting so that error handling knows
+ * that the filesystem is going away and we should error out anything that we
+ * have been retrying in the background. This will prevent never-ending
+ * retries in AIL pushing from hanging the unmount.
+ *
+ * Finally, we can push the AIL to clean all the remaining dirty objects, then
+ * reclaim the remaining inodes that are still in memory at this point in time.
+ */
+static void
+xfs_unmount_flush_inodes(
+ struct xfs_mount *mp)
+{
+ xfs_log_force(mp, XFS_LOG_SYNC);
+ xfs_extent_busy_wait_all(mp);
+ flush_workqueue(xfs_discard_wq);
+
+ mp->m_flags |= XFS_MOUNT_UNMOUNTING;
+
+ xfs_ail_push_all_sync(mp->m_ail);
+ cancel_delayed_work_sync(&mp->m_reclaim_work);
+ xfs_reclaim_inodes(mp);
+ xfs_health_unmount(mp);
+}
+
+static void
+xfs_mount_setup_inode_geom(
+ struct xfs_mount *mp)
+{
+ struct xfs_ino_geometry *igeo = M_IGEO(mp);
+
+ igeo->attr_fork_offset = xfs_bmap_compute_attr_offset(mp);
+ ASSERT(igeo->attr_fork_offset < XFS_LITINO(mp));
+
+ xfs_ialloc_setup_geometry(mp);
+}
+
+/*
* This function does the following on an initial mount of a file system:
* - reads the superblock from disk and init the mount struct
* - if we're a 32-bit kernel, do a size check on the superblock
@@ -717,7 +770,7 @@ xfs_mountfs(
xfs_alloc_compute_maxlevels(mp);
xfs_bmap_compute_maxlevels(mp, XFS_DATA_FORK);
xfs_bmap_compute_maxlevels(mp, XFS_ATTR_FORK);
- xfs_ialloc_setup_geometry(mp);
+ xfs_mount_setup_inode_geom(mp);
xfs_rmapbt_compute_maxlevels(mp);
xfs_refcountbt_compute_maxlevels(mp);
@@ -1008,7 +1061,7 @@ xfs_mountfs(
/* Clean out dquots that might be in memory after quotacheck. */
xfs_qm_unmount(mp);
/*
- * Cancel all delayed reclaim work and reclaim the inodes directly.
+ * Flush all inode reclamation work and flush the log.
* We have to do this /after/ rtunmount and qm_unmount because those
* two will have scheduled delayed reclaim for the rt/quota inodes.
*
@@ -1018,11 +1071,8 @@ xfs_mountfs(
* qm_unmount_quotas and therefore rely on qm_unmount to release the
* quota inodes.
*/
- cancel_delayed_work_sync(&mp->m_reclaim_work);
- xfs_reclaim_inodes(mp);
- xfs_health_unmount(mp);
+ xfs_unmount_flush_inodes(mp);
out_log_dealloc:
- mp->m_flags |= XFS_MOUNT_UNMOUNTING;
xfs_log_mount_cancel(mp);
out_fail_wait:
if (mp->m_logdev_targp && mp->m_logdev_targp != mp->m_ddev_targp)
@@ -1063,47 +1113,7 @@ xfs_unmountfs(
xfs_rtunmount_inodes(mp);
xfs_irele(mp->m_rootip);
- /*
- * We can potentially deadlock here if we have an inode cluster
- * that has been freed has its buffer still pinned in memory because
- * the transaction is still sitting in a iclog. The stale inodes
- * on that buffer will be pinned to the buffer until the
- * transaction hits the disk and the callbacks run. Pushing the AIL will
- * skip the stale inodes and may never see the pinned buffer, so
- * nothing will push out the iclog and unpin the buffer. Hence we
- * need to force the log here to ensure all items are flushed into the
- * AIL before we go any further.
- */
- xfs_log_force(mp, XFS_LOG_SYNC);
-
- /*
- * Wait for all busy extents to be freed, including completion of
- * any discard operation.
- */
- xfs_extent_busy_wait_all(mp);
- flush_workqueue(xfs_discard_wq);
-
- /*
- * We now need to tell the world we are unmounting. This will allow
- * us to detect that the filesystem is going away and we should error
- * out anything that we have been retrying in the background. This will
- * prevent neverending retries in AIL pushing from hanging the unmount.
- */
- mp->m_flags |= XFS_MOUNT_UNMOUNTING;
-
- /*
- * Flush all pending changes from the AIL.
- */
- xfs_ail_push_all_sync(mp->m_ail);
-
- /*
- * Reclaim all inodes. At this point there should be no dirty inodes and
- * none should be pinned or locked. Stop background inode reclaim here
- * if it is still running.
- */
- cancel_delayed_work_sync(&mp->m_reclaim_work);
- xfs_reclaim_inodes(mp);
- xfs_health_unmount(mp);
+ xfs_unmount_flush_inodes(mp);
xfs_qm_unmount(mp);
diff --git a/fs/xfs/xfs_mount.h b/fs/xfs/xfs_mount.h
index 659ad95fe3e0..81829d19596e 100644
--- a/fs/xfs/xfs_mount.h
+++ b/fs/xfs/xfs_mount.h
@@ -93,7 +93,7 @@ typedef struct xfs_mount {
struct workqueue_struct *m_unwritten_workqueue;
struct workqueue_struct *m_cil_workqueue;
struct workqueue_struct *m_reclaim_workqueue;
- struct workqueue_struct *m_blockgc_workqueue;
+ struct workqueue_struct *m_gc_workqueue;
struct workqueue_struct *m_sync_workqueue;
int m_bsize; /* fs logical block size */
diff --git a/fs/xfs/xfs_pnfs.c b/fs/xfs/xfs_pnfs.c
index f3082a957d5e..956cca24e67f 100644
--- a/fs/xfs/xfs_pnfs.c
+++ b/fs/xfs/xfs_pnfs.c
@@ -286,7 +286,7 @@ xfs_fs_commit_blocks(
xfs_setattr_time(ip, iattr);
if (update_isize) {
i_size_write(inode, iattr->ia_size);
- ip->i_d.di_size = iattr->ia_size;
+ ip->i_disk_size = iattr->ia_size;
}
xfs_trans_set_sync(tp);
diff --git a/fs/xfs/xfs_qm.c b/fs/xfs/xfs_qm.c
index bfa4164990b1..4bf949a89d0d 100644
--- a/fs/xfs/xfs_qm.c
+++ b/fs/xfs/xfs_qm.c
@@ -788,7 +788,7 @@ xfs_qm_qino_alloc(
if (need_alloc) {
error = xfs_dir_ialloc(&init_user_ns, &tp, NULL, S_IFREG, 1, 0,
- 0, ipp);
+ 0, false, ipp);
if (error) {
xfs_trans_cancel(tp);
return error;
@@ -992,7 +992,7 @@ xfs_qm_reset_dqcounts_buf(
* trans_reserve. But, this gets called during quotacheck, and that
* happens only at mount time which is single threaded.
*/
- if (qip->i_d.di_nblocks == 0)
+ if (qip->i_nblocks == 0)
return 0;
map = kmem_alloc(XFS_DQITER_MAP_SIZE * sizeof(*map), 0);
@@ -1165,16 +1165,14 @@ xfs_qm_dqusage_adjust(
if (XFS_IS_REALTIME_INODE(ip)) {
struct xfs_ifork *ifp = XFS_IFORK_PTR(ip, XFS_DATA_FORK);
- if (!(ifp->if_flags & XFS_IFEXTENTS)) {
- error = xfs_iread_extents(tp, ip, XFS_DATA_FORK);
- if (error)
- goto error0;
- }
+ error = xfs_iread_extents(tp, ip, XFS_DATA_FORK);
+ if (error)
+ goto error0;
xfs_bmap_count_leaves(ifp, &rtblks);
}
- nblks = (xfs_qcnt_t)ip->i_d.di_nblocks - rtblks;
+ nblks = (xfs_qcnt_t)ip->i_nblocks - rtblks;
/*
* Add the (disk blocks and inode) resources occupied by this
@@ -1716,7 +1714,7 @@ xfs_qm_vop_dqalloc(
}
if ((flags & XFS_QMOPT_PQUOTA) && XFS_IS_PQUOTA_ON(mp)) {
ASSERT(O_pdqpp);
- if (ip->i_d.di_projid != prid) {
+ if (ip->i_projid != prid) {
xfs_iunlock(ip, lockflags);
error = xfs_qm_dqget(mp, prid,
XFS_DQTYPE_PROJ, true, &pq);
@@ -1779,11 +1777,11 @@ xfs_qm_vop_chown(
ASSERT(prevdq);
ASSERT(prevdq != newdq);
- xfs_trans_mod_dquot(tp, prevdq, bfield, -(ip->i_d.di_nblocks));
+ xfs_trans_mod_dquot(tp, prevdq, bfield, -(ip->i_nblocks));
xfs_trans_mod_dquot(tp, prevdq, XFS_TRANS_DQ_ICOUNT, -1);
/* the sparkling new dquot */
- xfs_trans_mod_dquot(tp, newdq, bfield, ip->i_d.di_nblocks);
+ xfs_trans_mod_dquot(tp, newdq, bfield, ip->i_nblocks);
xfs_trans_mod_dquot(tp, newdq, XFS_TRANS_DQ_ICOUNT, 1);
/*
@@ -1877,7 +1875,7 @@ xfs_qm_vop_create_dqattach(
}
if (pdqp && XFS_IS_PQUOTA_ON(mp)) {
ASSERT(ip->i_pdquot == NULL);
- ASSERT(ip->i_d.di_projid == pdqp->q_id);
+ ASSERT(ip->i_projid == pdqp->q_id);
ip->i_pdquot = xfs_qm_dqhold(pdqp);
xfs_trans_mod_dquot(tp, pdqp, XFS_TRANS_DQ_ICOUNT, 1);
diff --git a/fs/xfs/xfs_qm_bhv.c b/fs/xfs/xfs_qm_bhv.c
index 639398091ad6..df00dfbf5c9d 100644
--- a/fs/xfs/xfs_qm_bhv.c
+++ b/fs/xfs/xfs_qm_bhv.c
@@ -60,7 +60,7 @@ xfs_qm_statvfs(
struct xfs_mount *mp = ip->i_mount;
struct xfs_dquot *dqp;
- if (!xfs_qm_dqget(mp, ip->i_d.di_projid, XFS_DQTYPE_PROJ, false, &dqp)) {
+ if (!xfs_qm_dqget(mp, ip->i_projid, XFS_DQTYPE_PROJ, false, &dqp)) {
xfs_fill_statvfs_from_dquot(statp, dqp);
xfs_qm_dqput(dqp);
}
diff --git a/fs/xfs/xfs_qm_syscalls.c b/fs/xfs/xfs_qm_syscalls.c
index ca1b57d291dc..11f1e2fbf22f 100644
--- a/fs/xfs/xfs_qm_syscalls.c
+++ b/fs/xfs/xfs_qm_syscalls.c
@@ -293,7 +293,7 @@ xfs_qm_scall_trunc_qfile(
xfs_ilock(ip, XFS_ILOCK_EXCL);
xfs_trans_ijoin(tp, ip, 0);
- ip->i_d.di_size = 0;
+ ip->i_disk_size = 0;
xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
error = xfs_itruncate_extents(&tp, ip, XFS_DATA_FORK, 0);
diff --git a/fs/xfs/xfs_quotaops.c b/fs/xfs/xfs_quotaops.c
index d27c0e852c0b..88d70c236a54 100644
--- a/fs/xfs/xfs_quotaops.c
+++ b/fs/xfs/xfs_quotaops.c
@@ -35,7 +35,7 @@ xfs_qm_fill_state(
tempqip = true;
}
tstate->flags |= QCI_SYSFILE;
- tstate->blocks = ip->i_d.di_nblocks;
+ tstate->blocks = ip->i_nblocks;
tstate->nextents = ip->i_df.if_nextents;
tstate->spc_timelimit = (u32)defq->blk.time;
tstate->ino_timelimit = (u32)defq->ino.time;
diff --git a/fs/xfs/xfs_refcount_item.c b/fs/xfs/xfs_refcount_item.c
index 07ebccbbf4df..746f4eda724c 100644
--- a/fs/xfs/xfs_refcount_item.c
+++ b/fs/xfs/xfs_refcount_item.c
@@ -269,8 +269,8 @@ xfs_trans_log_finish_refcount_update(
static int
xfs_refcount_update_diff_items(
void *priv,
- struct list_head *a,
- struct list_head *b)
+ const struct list_head *a,
+ const struct list_head *b)
{
struct xfs_mount *mp = priv;
struct xfs_refcount_intent *ra;
diff --git a/fs/xfs/xfs_reflink.c b/fs/xfs/xfs_reflink.c
index 725c7d8e4438..4dd4af6ac2ef 100644
--- a/fs/xfs/xfs_reflink.c
+++ b/fs/xfs/xfs_reflink.c
@@ -874,7 +874,7 @@ xfs_reflink_set_inode_flag(
if (!xfs_is_reflink_inode(src)) {
trace_xfs_reflink_set_inode_flag(src);
xfs_trans_ijoin(tp, src, XFS_ILOCK_EXCL);
- src->i_d.di_flags2 |= XFS_DIFLAG2_REFLINK;
+ src->i_diflags2 |= XFS_DIFLAG2_REFLINK;
xfs_trans_log_inode(tp, src, XFS_ILOG_CORE);
xfs_ifork_init_cow(src);
} else
@@ -886,7 +886,7 @@ xfs_reflink_set_inode_flag(
if (!xfs_is_reflink_inode(dest)) {
trace_xfs_reflink_set_inode_flag(dest);
xfs_trans_ijoin(tp, dest, XFS_ILOCK_EXCL);
- dest->i_d.di_flags2 |= XFS_DIFLAG2_REFLINK;
+ dest->i_diflags2 |= XFS_DIFLAG2_REFLINK;
xfs_trans_log_inode(tp, dest, XFS_ILOG_CORE);
xfs_ifork_init_cow(dest);
} else
@@ -930,12 +930,12 @@ xfs_reflink_update_dest(
if (newlen > i_size_read(VFS_I(dest))) {
trace_xfs_reflink_update_inode_size(dest, newlen);
i_size_write(VFS_I(dest), newlen);
- dest->i_d.di_size = newlen;
+ dest->i_disk_size = newlen;
}
if (cowextsize) {
- dest->i_d.di_cowextsize = cowextsize;
- dest->i_d.di_flags2 |= XFS_DIFLAG2_COWEXTSIZE;
+ dest->i_cowextsize = cowextsize;
+ dest->i_diflags2 |= XFS_DIFLAG2_COWEXTSIZE;
}
xfs_trans_log_inode(tp, dest, XFS_ILOG_CORE);
@@ -1156,7 +1156,7 @@ xfs_reflink_remap_extent(
if (newlen > i_size_read(VFS_I(ip))) {
trace_xfs_reflink_update_inode_size(ip, newlen);
i_size_write(VFS_I(ip), newlen);
- ip->i_d.di_size = newlen;
+ ip->i_disk_size = newlen;
xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
}
@@ -1392,11 +1392,9 @@ xfs_reflink_inode_has_shared_extents(
int error;
ifp = XFS_IFORK_PTR(ip, XFS_DATA_FORK);
- if (!(ifp->if_flags & XFS_IFEXTENTS)) {
- error = xfs_iread_extents(tp, ip, XFS_DATA_FORK);
- if (error)
- return error;
- }
+ error = xfs_iread_extents(tp, ip, XFS_DATA_FORK);
+ if (error)
+ return error;
*has_shared = false;
found = xfs_iext_lookup_extent(ip, ifp, 0, &icur, &got);
@@ -1455,7 +1453,7 @@ xfs_reflink_clear_inode_flag(
/* Clear the inode flag. */
trace_xfs_reflink_unset_inode_flag(ip);
- ip->i_d.di_flags2 &= ~XFS_DIFLAG2_REFLINK;
+ ip->i_diflags2 &= ~XFS_DIFLAG2_REFLINK;
xfs_inode_clear_cowblocks_tag(ip);
xfs_trans_log_inode(*tpp, ip, XFS_ILOG_CORE);
diff --git a/fs/xfs/xfs_rmap_item.c b/fs/xfs/xfs_rmap_item.c
index 49cebd68b672..dc4f0c9f0897 100644
--- a/fs/xfs/xfs_rmap_item.c
+++ b/fs/xfs/xfs_rmap_item.c
@@ -337,8 +337,8 @@ xfs_trans_log_finish_rmap_update(
static int
xfs_rmap_update_diff_items(
void *priv,
- struct list_head *a,
- struct list_head *b)
+ const struct list_head *a,
+ const struct list_head *b)
{
struct xfs_mount *mp = priv;
struct xfs_rmap_intent *ra;
diff --git a/fs/xfs/xfs_rtalloc.c b/fs/xfs/xfs_rtalloc.c
index 161b0e8992ba..4e7be6b4ca8e 100644
--- a/fs/xfs/xfs_rtalloc.c
+++ b/fs/xfs/xfs_rtalloc.c
@@ -966,8 +966,8 @@ xfs_growfs_rt(
* Get the old block counts for bitmap and summary inodes.
* These can't change since other growfs callers are locked out.
*/
- rbmblocks = XFS_B_TO_FSB(mp, mp->m_rbmip->i_d.di_size);
- rsumblocks = XFS_B_TO_FSB(mp, mp->m_rsumip->i_d.di_size);
+ rbmblocks = XFS_B_TO_FSB(mp, mp->m_rbmip->i_disk_size);
+ rsumblocks = XFS_B_TO_FSB(mp, mp->m_rsumip->i_disk_size);
/*
* Allocate space to the bitmap and summary files, as necessary.
*/
@@ -1036,9 +1036,9 @@ xfs_growfs_rt(
* to update the incore size so that inode inactivation won't
* punch what it thinks are "posteof" blocks.
*/
- mp->m_rbmip->i_d.di_size =
+ mp->m_rbmip->i_disk_size =
nsbp->sb_rbmblocks * nsbp->sb_blocksize;
- i_size_write(VFS_I(mp->m_rbmip), mp->m_rbmip->i_d.di_size);
+ i_size_write(VFS_I(mp->m_rbmip), mp->m_rbmip->i_disk_size);
xfs_trans_log_inode(tp, mp->m_rbmip, XFS_ILOG_CORE);
/*
* Get the summary inode into the transaction.
@@ -1050,8 +1050,8 @@ xfs_growfs_rt(
* incore size so that inode inactivation won't punch what it
* thinks are "posteof" blocks.
*/
- mp->m_rsumip->i_d.di_size = nmp->m_rsumsize;
- i_size_write(VFS_I(mp->m_rsumip), mp->m_rsumip->i_d.di_size);
+ mp->m_rsumip->i_disk_size = nmp->m_rsumsize;
+ i_size_write(VFS_I(mp->m_rsumip), mp->m_rsumip->i_disk_size);
xfs_trans_log_inode(tp, mp->m_rsumip, XFS_ILOG_CORE);
/*
* Copy summary data from old to new sizes.
@@ -1318,8 +1318,8 @@ xfs_rtpick_extent(
ASSERT(xfs_isilocked(mp->m_rbmip, XFS_ILOCK_EXCL));
seqp = (uint64_t *)&VFS_I(mp->m_rbmip)->i_atime;
- if (!(mp->m_rbmip->i_d.di_flags & XFS_DIFLAG_NEWRTBM)) {
- mp->m_rbmip->i_d.di_flags |= XFS_DIFLAG_NEWRTBM;
+ if (!(mp->m_rbmip->i_diflags & XFS_DIFLAG_NEWRTBM)) {
+ mp->m_rbmip->i_diflags |= XFS_DIFLAG_NEWRTBM;
*seqp = 0;
}
seq = *seqp;
diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c
index e5e0713bebcd..a2dab05332ac 100644
--- a/fs/xfs/xfs_super.c
+++ b/fs/xfs/xfs_super.c
@@ -519,10 +519,10 @@ xfs_init_mount_workqueues(
if (!mp->m_reclaim_workqueue)
goto out_destroy_cil;
- mp->m_blockgc_workqueue = alloc_workqueue("xfs-blockgc/%s",
+ mp->m_gc_workqueue = alloc_workqueue("xfs-gc/%s",
WQ_SYSFS | WQ_UNBOUND | WQ_FREEZABLE | WQ_MEM_RECLAIM,
0, mp->m_super->s_id);
- if (!mp->m_blockgc_workqueue)
+ if (!mp->m_gc_workqueue)
goto out_destroy_reclaim;
mp->m_sync_workqueue = alloc_workqueue("xfs-sync/%s",
@@ -533,7 +533,7 @@ xfs_init_mount_workqueues(
return 0;
out_destroy_eofb:
- destroy_workqueue(mp->m_blockgc_workqueue);
+ destroy_workqueue(mp->m_gc_workqueue);
out_destroy_reclaim:
destroy_workqueue(mp->m_reclaim_workqueue);
out_destroy_cil:
@@ -551,7 +551,7 @@ xfs_destroy_mount_workqueues(
struct xfs_mount *mp)
{
destroy_workqueue(mp->m_sync_workqueue);
- destroy_workqueue(mp->m_blockgc_workqueue);
+ destroy_workqueue(mp->m_gc_workqueue);
destroy_workqueue(mp->m_reclaim_workqueue);
destroy_workqueue(mp->m_cil_workqueue);
destroy_workqueue(mp->m_unwritten_workqueue);
@@ -834,13 +834,13 @@ xfs_fs_statfs(
statp->f_ffree = max_t(int64_t, ffree, 0);
- if ((ip->i_d.di_flags & XFS_DIFLAG_PROJINHERIT) &&
+ if ((ip->i_diflags & XFS_DIFLAG_PROJINHERIT) &&
((mp->m_qflags & (XFS_PQUOTA_ACCT|XFS_PQUOTA_ENFD))) ==
(XFS_PQUOTA_ACCT|XFS_PQUOTA_ENFD))
xfs_qm_statvfs(ip, statp);
if (XFS_IS_REALTIME_MOUNT(mp) &&
- (ip->i_d.di_flags & (XFS_DIFLAG_RTINHERIT | XFS_DIFLAG_REALTIME))) {
+ (ip->i_diflags & (XFS_DIFLAG_RTINHERIT | XFS_DIFLAG_REALTIME))) {
statp->f_blocks = sbp->sb_rblocks;
statp->f_bavail = statp->f_bfree =
sbp->sb_frextents * sbp->sb_rextsize;
@@ -1126,6 +1126,22 @@ suffix_kstrtoint(
return ret;
}
+static inline void
+xfs_fs_warn_deprecated(
+ struct fs_context *fc,
+ struct fs_parameter *param,
+ uint64_t flag,
+ bool value)
+{
+ /* Don't print the warning if reconfiguring and current mount point
+ * already had the flag set
+ */
+ if ((fc->purpose & FS_CONTEXT_FOR_RECONFIGURE) &&
+ !!(XFS_M(fc->root->d_sb)->m_flags & flag) == value)
+ return;
+ xfs_warn(fc->s_fs_info, "%s mount option is deprecated.", param->key);
+}
+
/*
* Set mount state from a mount option.
*
@@ -1136,7 +1152,7 @@ xfs_fs_parse_param(
struct fs_context *fc,
struct fs_parameter *param)
{
- struct xfs_mount *mp = fc->s_fs_info;
+ struct xfs_mount *parsing_mp = fc->s_fs_info;
struct fs_parse_result result;
int size = 0;
int opt;
@@ -1147,142 +1163,142 @@ xfs_fs_parse_param(
switch (opt) {
case Opt_logbufs:
- mp->m_logbufs = result.uint_32;
+ parsing_mp->m_logbufs = result.uint_32;
return 0;
case Opt_logbsize:
- if (suffix_kstrtoint(param->string, 10, &mp->m_logbsize))
+ if (suffix_kstrtoint(param->string, 10, &parsing_mp->m_logbsize))
return -EINVAL;
return 0;
case Opt_logdev:
- kfree(mp->m_logname);
- mp->m_logname = kstrdup(param->string, GFP_KERNEL);
- if (!mp->m_logname)
+ kfree(parsing_mp->m_logname);
+ parsing_mp->m_logname = kstrdup(param->string, GFP_KERNEL);
+ if (!parsing_mp->m_logname)
return -ENOMEM;
return 0;
case Opt_rtdev:
- kfree(mp->m_rtname);
- mp->m_rtname = kstrdup(param->string, GFP_KERNEL);
- if (!mp->m_rtname)
+ kfree(parsing_mp->m_rtname);
+ parsing_mp->m_rtname = kstrdup(param->string, GFP_KERNEL);
+ if (!parsing_mp->m_rtname)
return -ENOMEM;
return 0;
case Opt_allocsize:
if (suffix_kstrtoint(param->string, 10, &size))
return -EINVAL;
- mp->m_allocsize_log = ffs(size) - 1;
- mp->m_flags |= XFS_MOUNT_ALLOCSIZE;
+ parsing_mp->m_allocsize_log = ffs(size) - 1;
+ parsing_mp->m_flags |= XFS_MOUNT_ALLOCSIZE;
return 0;
case Opt_grpid:
case Opt_bsdgroups:
- mp->m_flags |= XFS_MOUNT_GRPID;
+ parsing_mp->m_flags |= XFS_MOUNT_GRPID;
return 0;
case Opt_nogrpid:
case Opt_sysvgroups:
- mp->m_flags &= ~XFS_MOUNT_GRPID;
+ parsing_mp->m_flags &= ~XFS_MOUNT_GRPID;
return 0;
case Opt_wsync:
- mp->m_flags |= XFS_MOUNT_WSYNC;
+ parsing_mp->m_flags |= XFS_MOUNT_WSYNC;
return 0;
case Opt_norecovery:
- mp->m_flags |= XFS_MOUNT_NORECOVERY;
+ parsing_mp->m_flags |= XFS_MOUNT_NORECOVERY;
return 0;
case Opt_noalign:
- mp->m_flags |= XFS_MOUNT_NOALIGN;
+ parsing_mp->m_flags |= XFS_MOUNT_NOALIGN;
return 0;
case Opt_swalloc:
- mp->m_flags |= XFS_MOUNT_SWALLOC;
+ parsing_mp->m_flags |= XFS_MOUNT_SWALLOC;
return 0;
case Opt_sunit:
- mp->m_dalign = result.uint_32;
+ parsing_mp->m_dalign = result.uint_32;
return 0;
case Opt_swidth:
- mp->m_swidth = result.uint_32;
+ parsing_mp->m_swidth = result.uint_32;
return 0;
case Opt_inode32:
- mp->m_flags |= XFS_MOUNT_SMALL_INUMS;
+ parsing_mp->m_flags |= XFS_MOUNT_SMALL_INUMS;
return 0;
case Opt_inode64:
- mp->m_flags &= ~XFS_MOUNT_SMALL_INUMS;
+ parsing_mp->m_flags &= ~XFS_MOUNT_SMALL_INUMS;
return 0;
case Opt_nouuid:
- mp->m_flags |= XFS_MOUNT_NOUUID;
+ parsing_mp->m_flags |= XFS_MOUNT_NOUUID;
return 0;
case Opt_largeio:
- mp->m_flags |= XFS_MOUNT_LARGEIO;
+ parsing_mp->m_flags |= XFS_MOUNT_LARGEIO;
return 0;
case Opt_nolargeio:
- mp->m_flags &= ~XFS_MOUNT_LARGEIO;
+ parsing_mp->m_flags &= ~XFS_MOUNT_LARGEIO;
return 0;
case Opt_filestreams:
- mp->m_flags |= XFS_MOUNT_FILESTREAMS;
+ parsing_mp->m_flags |= XFS_MOUNT_FILESTREAMS;
return 0;
case Opt_noquota:
- mp->m_qflags &= ~XFS_ALL_QUOTA_ACCT;
- mp->m_qflags &= ~XFS_ALL_QUOTA_ENFD;
- mp->m_qflags &= ~XFS_ALL_QUOTA_ACTIVE;
+ parsing_mp->m_qflags &= ~XFS_ALL_QUOTA_ACCT;
+ parsing_mp->m_qflags &= ~XFS_ALL_QUOTA_ENFD;
+ parsing_mp->m_qflags &= ~XFS_ALL_QUOTA_ACTIVE;
return 0;
case Opt_quota:
case Opt_uquota:
case Opt_usrquota:
- mp->m_qflags |= (XFS_UQUOTA_ACCT | XFS_UQUOTA_ACTIVE |
+ parsing_mp->m_qflags |= (XFS_UQUOTA_ACCT | XFS_UQUOTA_ACTIVE |
XFS_UQUOTA_ENFD);
return 0;
case Opt_qnoenforce:
case Opt_uqnoenforce:
- mp->m_qflags |= (XFS_UQUOTA_ACCT | XFS_UQUOTA_ACTIVE);
- mp->m_qflags &= ~XFS_UQUOTA_ENFD;
+ parsing_mp->m_qflags |= (XFS_UQUOTA_ACCT | XFS_UQUOTA_ACTIVE);
+ parsing_mp->m_qflags &= ~XFS_UQUOTA_ENFD;
return 0;
case Opt_pquota:
case Opt_prjquota:
- mp->m_qflags |= (XFS_PQUOTA_ACCT | XFS_PQUOTA_ACTIVE |
+ parsing_mp->m_qflags |= (XFS_PQUOTA_ACCT | XFS_PQUOTA_ACTIVE |
XFS_PQUOTA_ENFD);
return 0;
case Opt_pqnoenforce:
- mp->m_qflags |= (XFS_PQUOTA_ACCT | XFS_PQUOTA_ACTIVE);
- mp->m_qflags &= ~XFS_PQUOTA_ENFD;
+ parsing_mp->m_qflags |= (XFS_PQUOTA_ACCT | XFS_PQUOTA_ACTIVE);
+ parsing_mp->m_qflags &= ~XFS_PQUOTA_ENFD;
return 0;
case Opt_gquota:
case Opt_grpquota:
- mp->m_qflags |= (XFS_GQUOTA_ACCT | XFS_GQUOTA_ACTIVE |
+ parsing_mp->m_qflags |= (XFS_GQUOTA_ACCT | XFS_GQUOTA_ACTIVE |
XFS_GQUOTA_ENFD);
return 0;
case Opt_gqnoenforce:
- mp->m_qflags |= (XFS_GQUOTA_ACCT | XFS_GQUOTA_ACTIVE);
- mp->m_qflags &= ~XFS_GQUOTA_ENFD;
+ parsing_mp->m_qflags |= (XFS_GQUOTA_ACCT | XFS_GQUOTA_ACTIVE);
+ parsing_mp->m_qflags &= ~XFS_GQUOTA_ENFD;
return 0;
case Opt_discard:
- mp->m_flags |= XFS_MOUNT_DISCARD;
+ parsing_mp->m_flags |= XFS_MOUNT_DISCARD;
return 0;
case Opt_nodiscard:
- mp->m_flags &= ~XFS_MOUNT_DISCARD;
+ parsing_mp->m_flags &= ~XFS_MOUNT_DISCARD;
return 0;
#ifdef CONFIG_FS_DAX
case Opt_dax:
- xfs_mount_set_dax_mode(mp, XFS_DAX_ALWAYS);
+ xfs_mount_set_dax_mode(parsing_mp, XFS_DAX_ALWAYS);
return 0;
case Opt_dax_enum:
- xfs_mount_set_dax_mode(mp, result.uint_32);
+ xfs_mount_set_dax_mode(parsing_mp, result.uint_32);
return 0;
#endif
/* Following mount options will be removed in September 2025 */
case Opt_ikeep:
- xfs_warn(mp, "%s mount option is deprecated.", param->key);
- mp->m_flags |= XFS_MOUNT_IKEEP;
+ xfs_fs_warn_deprecated(fc, param, XFS_MOUNT_IKEEP, true);
+ parsing_mp->m_flags |= XFS_MOUNT_IKEEP;
return 0;
case Opt_noikeep:
- xfs_warn(mp, "%s mount option is deprecated.", param->key);
- mp->m_flags &= ~XFS_MOUNT_IKEEP;
+ xfs_fs_warn_deprecated(fc, param, XFS_MOUNT_IKEEP, false);
+ parsing_mp->m_flags &= ~XFS_MOUNT_IKEEP;
return 0;
case Opt_attr2:
- xfs_warn(mp, "%s mount option is deprecated.", param->key);
- mp->m_flags |= XFS_MOUNT_ATTR2;
+ xfs_fs_warn_deprecated(fc, param, XFS_MOUNT_ATTR2, true);
+ parsing_mp->m_flags |= XFS_MOUNT_ATTR2;
return 0;
case Opt_noattr2:
- xfs_warn(mp, "%s mount option is deprecated.", param->key);
- mp->m_flags &= ~XFS_MOUNT_ATTR2;
- mp->m_flags |= XFS_MOUNT_NOATTR2;
+ xfs_fs_warn_deprecated(fc, param, XFS_MOUNT_NOATTR2, true);
+ parsing_mp->m_flags &= ~XFS_MOUNT_ATTR2;
+ parsing_mp->m_flags |= XFS_MOUNT_NOATTR2;
return 0;
default:
- xfs_warn(mp, "unknown mount option [%s].", param->key);
+ xfs_warn(parsing_mp, "unknown mount option [%s].", param->key);
return -EINVAL;
}
@@ -1918,7 +1934,7 @@ xfs_init_zones(void)
if (!xfs_ifork_zone)
goto out_destroy_da_state_zone;
- xfs_trans_zone = kmem_cache_create("xf_trans",
+ xfs_trans_zone = kmem_cache_create("xfs_trans",
sizeof(struct xfs_trans),
0, 0, NULL);
if (!xfs_trans_zone)
diff --git a/fs/xfs/xfs_super.h b/fs/xfs/xfs_super.h
index 1ca484b8357f..d2b40dc60dfc 100644
--- a/fs/xfs/xfs_super.h
+++ b/fs/xfs/xfs_super.h
@@ -86,7 +86,6 @@ struct xfs_mount;
struct xfs_buftarg;
struct block_device;
-extern void xfs_quiesce_attr(struct xfs_mount *mp);
extern void xfs_flush_inodes(struct xfs_mount *mp);
extern void xfs_blkdev_issue_flush(struct xfs_buftarg *);
extern xfs_agnumber_t xfs_set_inode_alloc(struct xfs_mount *,
diff --git a/fs/xfs/xfs_symlink.c b/fs/xfs/xfs_symlink.c
index 1379013d74b8..99fbec32c10a 100644
--- a/fs/xfs/xfs_symlink.c
+++ b/fs/xfs/xfs_symlink.c
@@ -33,7 +33,7 @@ xfs_readlink_bmap_ilocked(
struct xfs_buf *bp;
xfs_daddr_t d;
char *cur_chunk;
- int pathlen = ip->i_d.di_size;
+ int pathlen = ip->i_disk_size;
int nmaps = XFS_SYMLINK_MAPS;
int byte_cnt;
int n;
@@ -86,7 +86,7 @@ xfs_readlink_bmap_ilocked(
}
ASSERT(pathlen == 0);
- link[ip->i_d.di_size] = '\0';
+ link[ip->i_disk_size] = '\0';
error = 0;
out:
@@ -104,14 +104,14 @@ xfs_readlink(
trace_xfs_readlink(ip);
- ASSERT(!(ip->i_df.if_flags & XFS_IFINLINE));
+ ASSERT(ip->i_df.if_format != XFS_DINODE_FMT_LOCAL);
if (XFS_FORCED_SHUTDOWN(mp))
return -EIO;
xfs_ilock(ip, XFS_ILOCK_SHARED);
- pathlen = ip->i_d.di_size;
+ pathlen = ip->i_disk_size;
if (!pathlen)
goto out;
@@ -182,7 +182,8 @@ xfs_symlink(
/*
* Make sure that we have allocated dquot(s) on disk.
*/
- error = xfs_qm_vop_dqalloc(dp, current_fsuid(), current_fsgid(), prid,
+ error = xfs_qm_vop_dqalloc(dp, mapped_fsuid(mnt_userns),
+ mapped_fsgid(mnt_userns), prid,
XFS_QMOPT_QUOTALL | XFS_QMOPT_INHERIT,
&udqp, &gdqp, &pdqp);
if (error)
@@ -209,7 +210,7 @@ xfs_symlink(
/*
* Check whether the directory allows new symlinks or not.
*/
- if (dp->i_d.di_flags & XFS_DIFLAG_NOSYMLINKS) {
+ if (dp->i_diflags & XFS_DIFLAG_NOSYMLINKS) {
error = -EPERM;
goto out_trans_cancel;
}
@@ -223,7 +224,7 @@ xfs_symlink(
* Allocate an inode for the symlink.
*/
error = xfs_dir_ialloc(mnt_userns, &tp, dp, S_IFLNK | (mode & ~S_IFMT),
- 1, 0, prid, &ip);
+ 1, 0, prid, false, &ip);
if (error)
goto out_trans_cancel;
@@ -249,7 +250,7 @@ xfs_symlink(
if (pathlen <= XFS_IFORK_DSIZE(ip)) {
xfs_init_local_fork(ip, XFS_DATA_FORK, target_path, pathlen);
- ip->i_d.di_size = pathlen;
+ ip->i_disk_size = pathlen;
ip->i_df.if_format = XFS_DINODE_FMT_LOCAL;
xfs_trans_log_inode(tp, ip, XFS_ILOG_DDATA | XFS_ILOG_CORE);
} else {
@@ -264,7 +265,7 @@ xfs_symlink(
goto out_trans_cancel;
resblks -= fs_blocks;
- ip->i_d.di_size = pathlen;
+ ip->i_disk_size = pathlen;
xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
cur_chunk = target_path;
@@ -299,7 +300,7 @@ xfs_symlink(
}
ASSERT(pathlen == 0);
}
- i_size_write(VFS_I(ip), ip->i_d.di_size);
+ i_size_write(VFS_I(ip), ip->i_disk_size);
/*
* Create the directory entry for the symlink.
@@ -376,7 +377,7 @@ xfs_inactive_symlink_rmt(
xfs_trans_t *tp;
mp = ip->i_mount;
- ASSERT(ip->i_df.if_flags & XFS_IFEXTENTS);
+ ASSERT(!xfs_need_iread_extents(&ip->i_df));
/*
* We're freeing a symlink that has some
* blocks allocated to it. Free the
@@ -399,8 +400,8 @@ xfs_inactive_symlink_rmt(
* locked for the second transaction. In the error paths we need it
* held so the cancel won't rele it, see below.
*/
- size = (int)ip->i_d.di_size;
- ip->i_d.di_size = 0;
+ size = (int)ip->i_disk_size;
+ ip->i_disk_size = 0;
VFS_I(ip)->i_mode = (VFS_I(ip)->i_mode & ~S_IFMT) | S_IFREG;
xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
/*
@@ -476,7 +477,7 @@ xfs_inactive_symlink(
return -EIO;
xfs_ilock(ip, XFS_ILOCK_EXCL);
- pathlen = (int)ip->i_d.di_size;
+ pathlen = (int)ip->i_disk_size;
ASSERT(pathlen);
if (pathlen <= 0 || pathlen > XFS_SYMLINK_MAXLEN) {
@@ -491,7 +492,7 @@ xfs_inactive_symlink(
* Inline fork state gets removed by xfs_difree() so we have nothing to
* do here in that case.
*/
- if (ip->i_df.if_flags & XFS_IFINLINE) {
+ if (ip->i_df.if_format == XFS_DINODE_FMT_LOCAL) {
xfs_iunlock(ip, XFS_ILOCK_EXCL);
return 0;
}
diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h
index e74bbb648f83..808ae337b222 100644
--- a/fs/xfs/xfs_trace.h
+++ b/fs/xfs/xfs_trace.h
@@ -1298,7 +1298,7 @@ DECLARE_EVENT_CLASS(xfs_file_class,
TP_fast_assign(
__entry->dev = file_inode(iocb->ki_filp)->i_sb->s_dev;
__entry->ino = XFS_I(file_inode(iocb->ki_filp))->i_ino;
- __entry->size = XFS_I(file_inode(iocb->ki_filp))->i_d.di_size;
+ __entry->size = XFS_I(file_inode(iocb->ki_filp))->i_disk_size;
__entry->offset = iocb->ki_pos;
__entry->count = iov_iter_count(iter);
),
@@ -1341,7 +1341,7 @@ DECLARE_EVENT_CLASS(xfs_imap_class,
TP_fast_assign(
__entry->dev = VFS_I(ip)->i_sb->s_dev;
__entry->ino = ip->i_ino;
- __entry->size = ip->i_d.di_size;
+ __entry->size = ip->i_disk_size;
__entry->offset = offset;
__entry->count = count;
__entry->whichfork = whichfork;
@@ -1387,7 +1387,7 @@ DECLARE_EVENT_CLASS(xfs_simple_io_class,
__entry->dev = VFS_I(ip)->i_sb->s_dev;
__entry->ino = ip->i_ino;
__entry->isize = VFS_I(ip)->i_size;
- __entry->disize = ip->i_d.di_size;
+ __entry->disize = ip->i_disk_size;
__entry->offset = offset;
__entry->count = count;
),
@@ -1425,7 +1425,7 @@ DECLARE_EVENT_CLASS(xfs_itrunc_class,
TP_fast_assign(
__entry->dev = VFS_I(ip)->i_sb->s_dev;
__entry->ino = ip->i_ino;
- __entry->size = ip->i_d.di_size;
+ __entry->size = ip->i_disk_size;
__entry->new_size = new_size;
),
TP_printk("dev %d:%d ino 0x%llx size 0x%llx new_size 0x%llx",
@@ -1455,7 +1455,7 @@ TRACE_EVENT(xfs_pagecache_inval,
TP_fast_assign(
__entry->dev = VFS_I(ip)->i_sb->s_dev;
__entry->ino = ip->i_ino;
- __entry->size = ip->i_d.di_size;
+ __entry->size = ip->i_disk_size;
__entry->start = start;
__entry->finish = finish;
),
@@ -1483,7 +1483,7 @@ TRACE_EVENT(xfs_bunmap,
TP_fast_assign(
__entry->dev = VFS_I(ip)->i_sb->s_dev;
__entry->ino = ip->i_ino;
- __entry->size = ip->i_d.di_size;
+ __entry->size = ip->i_disk_size;
__entry->bno = bno;
__entry->len = len;
__entry->caller_ip = caller_ip;
@@ -3145,12 +3145,12 @@ DECLARE_EVENT_CLASS(xfs_double_io_class,
__entry->dev = VFS_I(src)->i_sb->s_dev;
__entry->src_ino = src->i_ino;
__entry->src_isize = VFS_I(src)->i_size;
- __entry->src_disize = src->i_d.di_size;
+ __entry->src_disize = src->i_disk_size;
__entry->src_offset = soffset;
__entry->len = len;
__entry->dest_ino = dest->i_ino;
__entry->dest_isize = VFS_I(dest)->i_size;
- __entry->dest_disize = dest->i_d.di_size;
+ __entry->dest_disize = dest->i_disk_size;
__entry->dest_offset = doffset;
),
TP_printk("dev %d:%d count %zd "
diff --git a/fs/xfs/xfs_trans.c b/fs/xfs/xfs_trans.c
index b22a09e9daee..bcc978011869 100644
--- a/fs/xfs/xfs_trans.c
+++ b/fs/xfs/xfs_trans.c
@@ -436,7 +436,6 @@ xfs_trans_mod_sb(
tp->t_res_frextents_delta += delta;
break;
case XFS_TRANS_SB_DBLOCKS:
- ASSERT(delta > 0);
tp->t_dblocks_delta += delta;
break;
case XFS_TRANS_SB_AGCOUNT:
@@ -618,19 +617,12 @@ xfs_trans_unreserve_and_mod_sb(
ASSERT(!error);
}
- if (idelta) {
+ if (idelta)
percpu_counter_add_batch(&mp->m_icount, idelta,
XFS_ICOUNT_BATCH);
- if (idelta < 0)
- ASSERT(__percpu_counter_compare(&mp->m_icount, 0,
- XFS_ICOUNT_BATCH) >= 0);
- }
- if (ifreedelta) {
+ if (ifreedelta)
percpu_counter_add(&mp->m_ifree, ifreedelta);
- if (ifreedelta < 0)
- ASSERT(percpu_counter_compare(&mp->m_ifree, 0) >= 0);
- }
if (rtxdelta == 0 && !(tp->t_flags & XFS_TRANS_SB_DIRTY))
return;
@@ -1197,7 +1189,7 @@ retry:
* though that part is only semi-transactional.
*/
error = xfs_trans_reserve_quota_bydquots(tp, mp, udqp, gdqp,
- pdqp, ip->i_d.di_nblocks + ip->i_delayed_blks,
+ pdqp, ip->i_nblocks + ip->i_delayed_blks,
1, qflags);
if ((error == -EDQUOT || error == -ENOSPC) && !retried) {
xfs_trans_cancel(tp);
diff --git a/fs/xfs/xfs_xattr.c b/fs/xfs/xfs_xattr.c
index 12be32f66dc1..0d050f8829ef 100644
--- a/fs/xfs/xfs_xattr.c
+++ b/fs/xfs/xfs_xattr.c
@@ -9,6 +9,8 @@
#include "xfs_format.h"
#include "xfs_log_format.h"
#include "xfs_da_format.h"
+#include "xfs_trans_resv.h"
+#include "xfs_mount.h"
#include "xfs_inode.h"
#include "xfs_attr.h"
#include "xfs_acl.h"
diff --git a/fs/zonefs/super.c b/fs/zonefs/super.c
index 0fe76f376dee..cd145d318b17 100644
--- a/fs/zonefs/super.c
+++ b/fs/zonefs/super.c
@@ -165,6 +165,21 @@ static int zonefs_writepages(struct address_space *mapping,
return iomap_writepages(mapping, wbc, &wpc, &zonefs_writeback_ops);
}
+static int zonefs_swap_activate(struct swap_info_struct *sis,
+ struct file *swap_file, sector_t *span)
+{
+ struct inode *inode = file_inode(swap_file);
+ struct zonefs_inode_info *zi = ZONEFS_I(inode);
+
+ if (zi->i_ztype != ZONEFS_ZTYPE_CNV) {
+ zonefs_err(inode->i_sb,
+ "swap file: not a conventional zone file\n");
+ return -EINVAL;
+ }
+
+ return iomap_swapfile_activate(sis, swap_file, span, &zonefs_iomap_ops);
+}
+
static const struct address_space_operations zonefs_file_aops = {
.readpage = zonefs_readpage,
.readahead = zonefs_readahead,
@@ -177,6 +192,7 @@ static const struct address_space_operations zonefs_file_aops = {
.is_partially_uptodate = iomap_is_partially_uptodate,
.error_remove_page = generic_error_remove_page,
.direct_IO = noop_direct_IO,
+ .swap_activate = zonefs_swap_activate,
};
static void zonefs_update_stats(struct inode *inode, loff_t new_isize)
@@ -728,6 +744,68 @@ out_release:
}
/*
+ * Do not exceed the LFS limits nor the file zone size. If pos is under the
+ * limit it becomes a short access. If it exceeds the limit, return -EFBIG.
+ */
+static loff_t zonefs_write_check_limits(struct file *file, loff_t pos,
+ loff_t count)
+{
+ struct inode *inode = file_inode(file);
+ struct zonefs_inode_info *zi = ZONEFS_I(inode);
+ loff_t limit = rlimit(RLIMIT_FSIZE);
+ loff_t max_size = zi->i_max_size;
+
+ if (limit != RLIM_INFINITY) {
+ if (pos >= limit) {
+ send_sig(SIGXFSZ, current, 0);
+ return -EFBIG;
+ }
+ count = min(count, limit - pos);
+ }
+
+ if (!(file->f_flags & O_LARGEFILE))
+ max_size = min_t(loff_t, MAX_NON_LFS, max_size);
+
+ if (unlikely(pos >= max_size))
+ return -EFBIG;
+
+ return min(count, max_size - pos);
+}
+
+static ssize_t zonefs_write_checks(struct kiocb *iocb, struct iov_iter *from)
+{
+ struct file *file = iocb->ki_filp;
+ struct inode *inode = file_inode(file);
+ struct zonefs_inode_info *zi = ZONEFS_I(inode);
+ loff_t count;
+
+ if (IS_SWAPFILE(inode))
+ return -ETXTBSY;
+
+ if (!iov_iter_count(from))
+ return 0;
+
+ if ((iocb->ki_flags & IOCB_NOWAIT) && !(iocb->ki_flags & IOCB_DIRECT))
+ return -EINVAL;
+
+ if (iocb->ki_flags & IOCB_APPEND) {
+ if (zi->i_ztype != ZONEFS_ZTYPE_SEQ)
+ return -EINVAL;
+ mutex_lock(&zi->i_truncate_mutex);
+ iocb->ki_pos = zi->i_wpoffset;
+ mutex_unlock(&zi->i_truncate_mutex);
+ }
+
+ count = zonefs_write_check_limits(file, iocb->ki_pos,
+ iov_iter_count(from));
+ if (count < 0)
+ return count;
+
+ iov_iter_truncate(from, count);
+ return iov_iter_count(from);
+}
+
+/*
* Handle direct writes. For sequential zone files, this is the only possible
* write path. For these files, check that the user is issuing writes
* sequentially from the end of the file. This code assumes that the block layer
@@ -744,8 +822,7 @@ static ssize_t zonefs_file_dio_write(struct kiocb *iocb, struct iov_iter *from)
struct super_block *sb = inode->i_sb;
bool sync = is_sync_kiocb(iocb);
bool append = false;
- size_t count;
- ssize_t ret;
+ ssize_t ret, count;
/*
* For async direct IOs to sequential zone files, refuse IOCB_NOWAIT
@@ -763,12 +840,11 @@ static ssize_t zonefs_file_dio_write(struct kiocb *iocb, struct iov_iter *from)
inode_lock(inode);
}
- ret = generic_write_checks(iocb, from);
- if (ret <= 0)
+ count = zonefs_write_checks(iocb, from);
+ if (count <= 0) {
+ ret = count;
goto inode_unlock;
-
- iov_iter_truncate(from, zi->i_max_size - iocb->ki_pos);
- count = iov_iter_count(from);
+ }
if ((iocb->ki_pos | count) & (sb->s_blocksize - 1)) {
ret = -EINVAL;
@@ -828,12 +904,10 @@ static ssize_t zonefs_file_buffered_write(struct kiocb *iocb,
inode_lock(inode);
}
- ret = generic_write_checks(iocb, from);
+ ret = zonefs_write_checks(iocb, from);
if (ret <= 0)
goto inode_unlock;
- iov_iter_truncate(from, zi->i_max_size - iocb->ki_pos);
-
ret = iomap_file_buffered_write(iocb, from, &zonefs_iomap_ops);
if (ret > 0)
iocb->ki_pos += ret;
@@ -966,9 +1040,7 @@ static int zonefs_open_zone(struct inode *inode)
mutex_lock(&zi->i_truncate_mutex);
- zi->i_wr_refcnt++;
- if (zi->i_wr_refcnt == 1) {
-
+ if (!zi->i_wr_refcnt) {
if (atomic_inc_return(&sbi->s_open_zones) > sbi->s_max_open_zones) {
atomic_dec(&sbi->s_open_zones);
ret = -EBUSY;
@@ -978,7 +1050,6 @@ static int zonefs_open_zone(struct inode *inode)
if (i_size_read(inode) < zi->i_max_size) {
ret = zonefs_zone_mgmt(inode, REQ_OP_ZONE_OPEN);
if (ret) {
- zi->i_wr_refcnt--;
atomic_dec(&sbi->s_open_zones);
goto unlock;
}
@@ -986,6 +1057,8 @@ static int zonefs_open_zone(struct inode *inode)
}
}
+ zi->i_wr_refcnt++;
+
unlock:
mutex_unlock(&zi->i_truncate_mutex);
@@ -1104,7 +1177,6 @@ static int zonefs_statfs(struct dentry *dentry, struct kstatfs *buf)
struct super_block *sb = dentry->d_sb;
struct zonefs_sb_info *sbi = ZONEFS_SB(sb);
enum zonefs_ztype t;
- u64 fsid;
buf->f_type = ZONEFS_MAGIC;
buf->f_bsize = sb->s_blocksize;
@@ -1127,9 +1199,7 @@ static int zonefs_statfs(struct dentry *dentry, struct kstatfs *buf)
spin_unlock(&sbi->s_lock);
- fsid = le64_to_cpup((void *)sbi->s_uuid.b) ^
- le64_to_cpup((void *)sbi->s_uuid.b + sizeof(u64));
- buf->f_fsid = u64_to_fsid(fsid);
+ buf->f_fsid = uuid_to_fsid(sbi->s_uuid.b);
return 0;
}