summaryrefslogtreecommitdiffstats
path: root/fs
diff options
context:
space:
mode:
Diffstat (limited to 'fs')
-rw-r--r--fs/9p/vfs_addr.c2
-rw-r--r--fs/9p/vfs_dentry.c2
-rw-r--r--fs/9p/vfs_dir.c1
-rw-r--r--fs/9p/vfs_file.c1
-rw-r--r--fs/9p/vfs_inode.c2
-rw-r--r--fs/9p/vfs_super.c2
-rw-r--r--fs/Kconfig6
-rw-r--r--fs/Kconfig.binfmt2
-rw-r--r--fs/Makefile4
-rw-r--r--fs/adfs/super.c3
-rw-r--r--fs/affs/file.c6
-rw-r--r--fs/affs/inode.c2
-rw-r--r--fs/affs/super.c9
-rw-r--r--fs/afs/Makefile3
-rw-r--r--fs/afs/afs.h23
-rw-r--r--fs/afs/afs_fs.h7
-rw-r--r--fs/afs/callback.c10
-rw-r--r--fs/afs/cell.c1
-rw-r--r--fs/afs/dir.c38
-rw-r--r--fs/afs/file.c105
-rw-r--r--fs/afs/fsclient.c878
-rw-r--r--fs/afs/inode.c75
-rw-r--r--fs/afs/internal.h104
-rw-r--r--fs/afs/main.c3
-rw-r--r--fs/afs/misc.c1
-rw-r--r--fs/afs/mntpt.c5
-rw-r--r--fs/afs/proc.c1
-rw-r--r--fs/afs/rxrpc.c80
-rw-r--r--fs/afs/security.c13
-rw-r--r--fs/afs/server.c3
-rw-r--r--fs/afs/super.c67
-rw-r--r--fs/afs/vlocation.c1
-rw-r--r--fs/afs/vnode.c207
-rw-r--r--fs/afs/volume.c1
-rw-r--r--fs/afs/write.c827
-rw-r--r--fs/aio.c35
-rw-r--r--fs/anon_inodes.c200
-rw-r--r--fs/attr.c1
-rw-r--r--fs/autofs/autofs_i.h4
-rw-r--r--fs/autofs/inode.c47
-rw-r--r--fs/autofs/root.c83
-rw-r--r--fs/autofs4/inode.c17
-rw-r--r--fs/autofs4/root.c19
-rw-r--r--fs/bad_inode.c1
-rw-r--r--fs/befs/linuxvfs.c6
-rw-r--r--fs/bfs/inode.c3
-rw-r--r--fs/binfmt_elf.c5
-rw-r--r--fs/binfmt_elf_fdpic.c1
-rw-r--r--fs/binfmt_em86.c1
-rw-r--r--fs/binfmt_flat.c2
-rw-r--r--fs/binfmt_misc.c19
-rw-r--r--fs/binfmt_script.c1
-rw-r--r--fs/block_dev.c19
-rw-r--r--fs/buffer.c85
-rw-r--r--fs/cifs/cifs_debug.c252
-rw-r--r--fs/cifs/cifs_unicode.c12
-rw-r--r--fs/cifs/cifsfs.c8
-rw-r--r--fs/cifs/cifssmb.c4
-rw-r--r--fs/cifs/connect.c16
-rw-r--r--fs/cifs/dir.c184
-rw-r--r--fs/cifs/fcntl.c46
-rw-r--r--fs/cifs/file.c1
-rw-r--r--fs/cifs/inode.c5
-rw-r--r--fs/cifs/ioctl.c29
-rw-r--r--fs/cifs/readdir.c1
-rw-r--r--fs/cifs/rfc1002pdu.h2
-rw-r--r--fs/coda/cache.c1
-rw-r--r--fs/coda/inode.c3
-rw-r--r--fs/coda/upcall.c2
-rw-r--r--fs/compat.c286
-rw-r--r--fs/compat_ioctl.c1040
-rw-r--r--fs/configfs/file.c33
-rw-r--r--fs/configfs/inode.c1
-rw-r--r--fs/dcache.c136
-rw-r--r--fs/devpts/inode.c5
-rw-r--r--fs/direct-io.c12
-rw-r--r--fs/dquot.c8
-rw-r--r--fs/ecryptfs/ecryptfs_kernel.h2
-rw-r--r--fs/ecryptfs/file.c60
-rw-r--r--fs/ecryptfs/inode.c66
-rw-r--r--fs/ecryptfs/main.c3
-rw-r--r--fs/ecryptfs/messaging.c2
-rw-r--r--fs/ecryptfs/mmap.c89
-rw-r--r--fs/efs/super.c3
-rw-r--r--fs/eventfd.c226
-rw-r--r--fs/eventpoll.c1615
-rw-r--r--fs/exec.c73
-rw-r--r--fs/exportfs/expfs.c1
-rw-r--r--fs/ext2/dir.c1
-rw-r--r--fs/ext2/ext2.h1
-rw-r--r--fs/ext2/fsync.c1
-rw-r--r--fs/ext2/inode.c26
-rw-r--r--fs/ext2/ioctl.c1
-rw-r--r--fs/ext2/super.c17
-rw-r--r--fs/ext2/xattr_security.c1
-rw-r--r--fs/ext2/xattr_trusted.c1
-rw-r--r--fs/ext3/dir.c1
-rw-r--r--fs/ext3/inode.c43
-rw-r--r--fs/ext3/ioctl.c1
-rw-r--r--fs/ext3/namei.c27
-rw-r--r--fs/ext3/resize.c1
-rw-r--r--fs/ext3/super.c10
-rw-r--r--fs/ext3/xattr_security.c1
-rw-r--r--fs/ext3/xattr_trusted.c1
-rw-r--r--fs/ext3/xattr_user.c1
-rw-r--r--fs/ext4/balloc.c6
-rw-r--r--fs/ext4/dir.c1
-rw-r--r--fs/ext4/extents.c149
-rw-r--r--fs/ext4/inode.c15
-rw-r--r--fs/ext4/namei.c31
-rw-r--r--fs/ext4/resize.c1
-rw-r--r--fs/ext4/super.c12
-rw-r--r--fs/ext4/xattr_security.c1
-rw-r--r--fs/ext4/xattr_trusted.c1
-rw-r--r--fs/ext4/xattr_user.c1
-rw-r--r--fs/fat/cache.c3
-rw-r--r--fs/fat/dir.c199
-rw-r--r--fs/fat/inode.c35
-rw-r--r--fs/fifo.c2
-rw-r--r--fs/file_table.c1
-rw-r--r--fs/filesystems.c21
-rw-r--r--fs/freevxfs/vxfs_bmap.c2
-rw-r--r--fs/freevxfs/vxfs_inode.c2
-rw-r--r--fs/fuse/dir.c2
-rw-r--r--fs/fuse/file.c5
-rw-r--r--fs/fuse/inode.c8
-rw-r--r--fs/gfs2/glock.h1
-rw-r--r--fs/gfs2/glops.c5
-rw-r--r--fs/gfs2/locking/nolock/main.c1
-rw-r--r--fs/gfs2/main.c34
-rw-r--r--fs/gfs2/ops_dentry.c1
-rw-r--r--fs/gfs2/ops_file.c1
-rw-r--r--fs/hfs/btree.c3
-rw-r--r--fs/hfs/inode.c1
-rw-r--r--fs/hfs/super.c3
-rw-r--r--fs/hfsplus/btree.c3
-rw-r--r--fs/hfsplus/inode.c1
-rw-r--r--fs/hfsplus/super.c3
-rw-r--r--fs/hostfs/hostfs.h15
-rw-r--r--fs/hostfs/hostfs_kern.c192
-rw-r--r--fs/hostfs/hostfs_user.c229
-rw-r--r--fs/hpfs/buffer.c2
-rw-r--r--fs/hpfs/namei.c2
-rw-r--r--fs/hpfs/super.c9
-rw-r--r--fs/hugetlbfs/inode.c10
-rw-r--r--fs/inode.c47
-rw-r--r--fs/inotify.c2
-rw-r--r--fs/internal.h10
-rw-r--r--fs/ioctl.c16
-rw-r--r--fs/isofs/inode.c3
-rw-r--r--fs/jbd/checkpoint.c2
-rw-r--r--fs/jbd/commit.c1
-rw-r--r--fs/jbd/journal.c14
-rw-r--r--fs/jbd/recovery.c2
-rw-r--r--fs/jbd/revoke.c3
-rw-r--r--fs/jbd/transaction.c3
-rw-r--r--fs/jbd2/checkpoint.c2
-rw-r--r--fs/jbd2/commit.c1
-rw-r--r--fs/jbd2/journal.c14
-rw-r--r--fs/jbd2/recovery.c2
-rw-r--r--fs/jbd2/revoke.c3
-rw-r--r--fs/jbd2/transaction.c3
-rw-r--r--fs/jffs2/histo_mips.h2
-rw-r--r--fs/jffs2/readinode.c123
-rw-r--r--fs/jffs2/super.c200
-rw-r--r--fs/jffs2/wbuf.c5
-rw-r--r--fs/jffs2/xattr.c6
-rw-r--r--fs/jfs/inode.c1
-rw-r--r--fs/jfs/ioctl.c2
-rw-r--r--fs/jfs/jfs_dmap.c2
-rw-r--r--fs/jfs/jfs_imap.c6
-rw-r--r--fs/jfs/jfs_inode.c18
-rw-r--r--fs/jfs/jfs_inode.h1
-rw-r--r--fs/jfs/jfs_lock.h2
-rw-r--r--fs/jfs/jfs_logmgr.c10
-rw-r--r--fs/jfs/jfs_metapage.c18
-rw-r--r--fs/jfs/jfs_txnmgr.c7
-rw-r--r--fs/jfs/super.c22
-rw-r--r--fs/libfs.c28
-rw-r--r--fs/lockd/clntlock.c2
-rw-r--r--fs/lockd/clntproc.c1
-rw-r--r--fs/lockd/host.c2
-rw-r--r--fs/lockd/xdr.c4
-rw-r--r--fs/lockd/xdr4.c6
-rw-r--r--fs/locks.c8
-rw-r--r--fs/minix/bitmap.c1
-rw-r--r--fs/minix/inode.c3
-rw-r--r--fs/mpage.c201
-rw-r--r--fs/namei.c22
-rw-r--r--fs/namespace.c41
-rw-r--r--fs/ncpfs/file.c2
-rw-r--r--fs/ncpfs/inode.c6
-rw-r--r--fs/ncpfs/ioctl.c1
-rw-r--r--fs/nfs/callback.h4
-rw-r--r--fs/nfs/client.c3
-rw-r--r--fs/nfs/delegation.c2
-rw-r--r--fs/nfs/dir.c42
-rw-r--r--fs/nfs/direct.c66
-rw-r--r--fs/nfs/file.c1
-rw-r--r--fs/nfs/getroot.c2
-rw-r--r--fs/nfs/idmap.c4
-rw-r--r--fs/nfs/inode.c33
-rw-r--r--fs/nfs/nfs2xdr.c1
-rw-r--r--fs/nfs/nfs3proc.c1
-rw-r--r--fs/nfs/nfs4proc.c4
-rw-r--r--fs/nfs/nfs4renewd.c1
-rw-r--r--fs/nfs/nfs4state.c2
-rw-r--r--fs/nfs/nfs4xdr.c107
-rw-r--r--fs/nfs/pagelist.c28
-rw-r--r--fs/nfs/proc.c1
-rw-r--r--fs/nfs/read.c10
-rw-r--r--fs/nfs/symlink.c1
-rw-r--r--fs/nfs/write.c17
-rw-r--r--fs/nfsd/Makefile1
-rw-r--r--fs/nfsd/export.c14
-rw-r--r--fs/nfsd/nfs3proc.c2
-rw-r--r--fs/nfsd/nfs3xdr.c71
-rw-r--r--fs/nfsd/nfs4acl.c17
-rw-r--r--fs/nfsd/nfs4callback.c1
-rw-r--r--fs/nfsd/nfs4idmap.c1
-rw-r--r--fs/nfsd/nfs4recover.c2
-rw-r--r--fs/nfsd/nfs4state.c2
-rw-r--r--fs/nfsd/nfs4xdr.c1
-rw-r--r--fs/nfsd/nfsfh.c57
-rw-r--r--fs/nfsd/nfsproc.c2
-rw-r--r--fs/nfsd/nfssvc.c2
-rw-r--r--fs/nfsd/nfsxdr.c53
-rw-r--r--fs/ntfs/aops.c36
-rw-r--r--fs/ntfs/dir.c1
-rw-r--r--fs/ntfs/file.c81
-rw-r--r--fs/ntfs/inode.c3
-rw-r--r--fs/ntfs/super.c3
-rw-r--r--fs/ocfs2/aops.c31
-rw-r--r--fs/ocfs2/cluster/masklog.c2
-rw-r--r--fs/ocfs2/dlm/dlmfs.c9
-rw-r--r--fs/ocfs2/dlmglue.c1
-rw-r--r--fs/ocfs2/file.c33
-rw-r--r--fs/ocfs2/inode.c1
-rw-r--r--fs/ocfs2/localalloc.c7
-rw-r--r--fs/ocfs2/slot_map.c1
-rw-r--r--fs/ocfs2/super.c38
-rw-r--r--fs/ocfs2/vote.c1
-rw-r--r--fs/open.c4
-rw-r--r--fs/openpromfs/inode.c3
-rw-r--r--fs/partitions/Kconfig21
-rw-r--r--fs/partitions/Makefile1
-rw-r--r--fs/partitions/check.c4
-rw-r--r--fs/partitions/efi.c12
-rw-r--r--fs/partitions/ldm.c206
-rw-r--r--fs/partitions/ldm.h6
-rw-r--r--fs/partitions/sysv68.c92
-rw-r--r--fs/partitions/sysv68.h1
-rw-r--r--fs/pipe.c18
-rw-r--r--fs/pnode.c2
-rw-r--r--fs/proc/array.c4
-rw-r--r--fs/proc/base.c268
-rw-r--r--fs/proc/generic.c13
-rw-r--r--fs/proc/inode.c17
-rw-r--r--fs/proc/internal.h2
-rw-r--r--fs/proc/proc_misc.c10
-rw-r--r--fs/proc/proc_sysctl.c7
-rw-r--r--fs/proc/proc_tty.c3
-rw-r--r--fs/proc/task_mmu.c17
-rw-r--r--fs/proc/task_nommu.c7
-rw-r--r--fs/qnx4/inode.c3
-rw-r--r--fs/quota.c24
-rw-r--r--fs/ramfs/file-nommu.c8
-rw-r--r--fs/ramfs/inode.c3
-rw-r--r--fs/read_write.c16
-rw-r--r--fs/readdir.c9
-rw-r--r--fs/reiserfs/dir.c3
-rw-r--r--fs/reiserfs/file.c40
-rw-r--r--fs/reiserfs/inode.c13
-rw-r--r--fs/reiserfs/journal.c6
-rw-r--r--fs/reiserfs/namei.c1
-rw-r--r--fs/reiserfs/procfs.c3
-rw-r--r--fs/reiserfs/resize.c4
-rw-r--r--fs/reiserfs/stree.c1
-rw-r--r--fs/reiserfs/super.c17
-rw-r--r--fs/romfs/inode.c7
-rw-r--r--fs/select.c13
-rw-r--r--fs/signalfd.c380
-rw-r--r--fs/smbfs/dir.c1
-rw-r--r--fs/smbfs/file.c1
-rw-r--r--fs/smbfs/inode.c4
-rw-r--r--fs/smbfs/request.c8
-rw-r--r--fs/smbfs/smbiod.c3
-rw-r--r--fs/smbfs/sock.c1
-rw-r--r--fs/smbfs/symlink.c1
-rw-r--r--fs/splice.c109
-rw-r--r--fs/stat.c1
-rw-r--r--fs/super.c27
-rw-r--r--fs/sync.c10
-rw-r--r--fs/sysfs/dir.c38
-rw-r--r--fs/sysfs/file.c33
-rw-r--r--fs/sysfs/inode.c22
-rw-r--r--fs/sysfs/mount.c1
-rw-r--r--fs/sysfs/sysfs.h2
-rw-r--r--fs/sysv/inode.c3
-rw-r--r--fs/sysv/namei.c1
-rw-r--r--fs/timerfd.c225
-rw-r--r--fs/udf/balloc.c177
-rw-r--r--fs/udf/dir.c39
-rw-r--r--fs/udf/directory.c30
-rw-r--r--fs/udf/file.c1
-rw-r--r--fs/udf/fsync.c1
-rw-r--r--fs/udf/inode.c598
-rw-r--r--fs/udf/misc.c6
-rw-r--r--fs/udf/namei.c227
-rw-r--r--fs/udf/partition.c2
-rw-r--r--fs/udf/super.c83
-rw-r--r--fs/udf/symlink.c2
-rw-r--r--fs/udf/truncate.c275
-rw-r--r--fs/udf/udf_sb.h2
-rw-r--r--fs/udf/udfdecl.h26
-rw-r--r--fs/ufs/dir.c1
-rw-r--r--fs/ufs/super.c3
-rw-r--r--fs/utimes.c162
-rw-r--r--fs/xattr.c3
-rw-r--r--fs/xfs/linux-2.6/mrlock.h12
-rw-r--r--fs/xfs/linux-2.6/xfs_aops.c109
-rw-r--r--fs/xfs/linux-2.6/xfs_buf.c10
-rw-r--r--fs/xfs/linux-2.6/xfs_buf.h3
-rw-r--r--fs/xfs/linux-2.6/xfs_fs_subr.c21
-rw-r--r--fs/xfs/linux-2.6/xfs_fs_subr.h2
-rw-r--r--fs/xfs/linux-2.6/xfs_lrw.c187
-rw-r--r--fs/xfs/linux-2.6/xfs_super.c3
-rw-r--r--fs/xfs/linux-2.6/xfs_vnode.h2
-rw-r--r--fs/xfs/quota/xfs_dquot.c3
-rw-r--r--fs/xfs/quota/xfs_qm.c16
-rw-r--r--fs/xfs/quota/xfs_qm_syscalls.c19
-rw-r--r--fs/xfs/quota/xfs_trans_dquot.c4
-rw-r--r--fs/xfs/support/debug.c17
-rw-r--r--fs/xfs/support/debug.h2
-rw-r--r--fs/xfs/xfs_alloc.c2
-rw-r--r--fs/xfs/xfs_attr.c12
-rw-r--r--fs/xfs/xfs_attr_leaf.c2
-rw-r--r--fs/xfs/xfs_bmap.c28
-rw-r--r--fs/xfs/xfs_dfrag.c6
-rw-r--r--fs/xfs/xfs_dir2_block.c14
-rw-r--r--fs/xfs/xfs_dir2_data.c7
-rw-r--r--fs/xfs/xfs_dir2_data.h2
-rw-r--r--fs/xfs/xfs_dir2_leaf.c7
-rw-r--r--fs/xfs/xfs_dir2_node.c4
-rw-r--r--fs/xfs/xfs_error.c2
-rw-r--r--fs/xfs/xfs_fsops.c4
-rw-r--r--fs/xfs/xfs_iget.c15
-rw-r--r--fs/xfs/xfs_inode.c58
-rw-r--r--fs/xfs/xfs_inode.h65
-rw-r--r--fs/xfs/xfs_iocore.c2
-rw-r--r--fs/xfs/xfs_iomap.c15
-rw-r--r--fs/xfs/xfs_iomap.h1
-rw-r--r--fs/xfs/xfs_itable.c2
-rw-r--r--fs/xfs/xfs_log_recover.c15
-rw-r--r--fs/xfs/xfs_mount.c5
-rw-r--r--fs/xfs/xfs_qmops.c2
-rw-r--r--fs/xfs/xfs_quota.h3
-rw-r--r--fs/xfs/xfs_rename.c2
-rw-r--r--fs/xfs/xfs_rtalloc.c6
-rw-r--r--fs/xfs/xfs_rw.c4
-rw-r--r--fs/xfs/xfs_trans.c6
-rw-r--r--fs/xfs/xfs_trans.h4
-rw-r--r--fs/xfs/xfs_utils.c11
-rw-r--r--fs/xfs/xfs_vfsops.c6
-rw-r--r--fs/xfs/xfs_vnodeops.c125
365 files changed, 9290 insertions, 5060 deletions
diff --git a/fs/9p/vfs_addr.c b/fs/9p/vfs_addr.c
index bed48fa9652..9ac4ffe9ac7 100644
--- a/fs/9p/vfs_addr.c
+++ b/fs/9p/vfs_addr.c
@@ -29,10 +29,10 @@
#include <linux/file.h>
#include <linux/stat.h>
#include <linux/string.h>
-#include <linux/smp_lock.h>
#include <linux/inet.h>
#include <linux/pagemap.h>
#include <linux/idr.h>
+#include <linux/sched.h>
#include "debug.h"
#include "v9fs.h"
diff --git a/fs/9p/vfs_dentry.c b/fs/9p/vfs_dentry.c
index ddffd8aa902..d93960429c0 100644
--- a/fs/9p/vfs_dentry.c
+++ b/fs/9p/vfs_dentry.c
@@ -30,10 +30,10 @@
#include <linux/pagemap.h>
#include <linux/stat.h>
#include <linux/string.h>
-#include <linux/smp_lock.h>
#include <linux/inet.h>
#include <linux/namei.h>
#include <linux/idr.h>
+#include <linux/sched.h>
#include "debug.h"
#include "v9fs.h"
diff --git a/fs/9p/vfs_dir.c b/fs/9p/vfs_dir.c
index 3129688143e..1dd86ee90bc 100644
--- a/fs/9p/vfs_dir.c
+++ b/fs/9p/vfs_dir.c
@@ -29,7 +29,6 @@
#include <linux/file.h>
#include <linux/stat.h>
#include <linux/string.h>
-#include <linux/smp_lock.h>
#include <linux/sched.h>
#include <linux/inet.h>
#include <linux/idr.h>
diff --git a/fs/9p/vfs_file.c b/fs/9p/vfs_file.c
index c7b67725384..6e7678e4852 100644
--- a/fs/9p/vfs_file.c
+++ b/fs/9p/vfs_file.c
@@ -30,7 +30,6 @@
#include <linux/file.h>
#include <linux/stat.h>
#include <linux/string.h>
-#include <linux/smp_lock.h>
#include <linux/inet.h>
#include <linux/list.h>
#include <asm/uaccess.h>
diff --git a/fs/9p/vfs_inode.c b/fs/9p/vfs_inode.c
index b01b0a45793..c76cd8fa3f6 100644
--- a/fs/9p/vfs_inode.c
+++ b/fs/9p/vfs_inode.c
@@ -30,10 +30,10 @@
#include <linux/pagemap.h>
#include <linux/stat.h>
#include <linux/string.h>
-#include <linux/smp_lock.h>
#include <linux/inet.h>
#include <linux/namei.h>
#include <linux/idr.h>
+#include <linux/sched.h>
#include "debug.h"
#include "v9fs.h"
diff --git a/fs/9p/vfs_super.c b/fs/9p/vfs_super.c
index 0ec42f66545..7bdf8b32684 100644
--- a/fs/9p/vfs_super.c
+++ b/fs/9p/vfs_super.c
@@ -31,12 +31,12 @@
#include <linux/file.h>
#include <linux/stat.h>
#include <linux/string.h>
-#include <linux/smp_lock.h>
#include <linux/inet.h>
#include <linux/pagemap.h>
#include <linux/seq_file.h>
#include <linux/mount.h>
#include <linux/idr.h>
+#include <linux/sched.h>
#include "debug.h"
#include "v9fs.h"
diff --git a/fs/Kconfig b/fs/Kconfig
index 8ea7b04c661..0fa0c1193e8 100644
--- a/fs/Kconfig
+++ b/fs/Kconfig
@@ -314,7 +314,7 @@ config REISERFS_CHECK
config REISERFS_PROC_INFO
bool "Stats in /proc/fs/reiserfs"
- depends on REISERFS_FS
+ depends on REISERFS_FS && PROC_FS
help
Create under /proc/fs/reiserfs a hierarchy of files, displaying
various ReiserFS statistics and internal data at the expense of
@@ -724,10 +724,6 @@ config FAT_FS
file system and use GNU tar's M option. GNU tar is a program
available for Unix and DOS ("man tar" or "info tar").
- It is now also becoming possible to read and write compressed FAT
- file systems; read <file:Documentation/filesystems/fat_cvf.txt> for
- details.
-
The FAT support will enlarge your kernel by about 37 KB. If unsure,
say Y.
diff --git a/fs/Kconfig.binfmt b/fs/Kconfig.binfmt
index 74c64409ddb..d4fc6095466 100644
--- a/fs/Kconfig.binfmt
+++ b/fs/Kconfig.binfmt
@@ -38,7 +38,7 @@ config BINFMT_ELF_FDPIC
config BINFMT_FLAT
tristate "Kernel support for flat binaries"
- depends on !MMU || SUPERH
+ depends on !MMU
help
Support uClinux FLAT format binaries.
diff --git a/fs/Makefile b/fs/Makefile
index 9edf4112bee..720c29d57a6 100644
--- a/fs/Makefile
+++ b/fs/Makefile
@@ -22,6 +22,10 @@ endif
obj-$(CONFIG_INOTIFY) += inotify.o
obj-$(CONFIG_INOTIFY_USER) += inotify_user.o
obj-$(CONFIG_EPOLL) += eventpoll.o
+obj-$(CONFIG_ANON_INODES) += anon_inodes.o
+obj-$(CONFIG_SIGNALFD) += signalfd.o
+obj-$(CONFIG_TIMERFD) += timerfd.o
+obj-$(CONFIG_EVENTFD) += eventfd.o
obj-$(CONFIG_COMPAT) += compat.o compat_ioctl.o
nfsd-$(CONFIG_NFSD) := nfsctl.o
diff --git a/fs/adfs/super.c b/fs/adfs/super.c
index 30c29650849..de2ed5ca335 100644
--- a/fs/adfs/super.c
+++ b/fs/adfs/super.c
@@ -232,8 +232,7 @@ static void init_once(void * foo, struct kmem_cache * cachep, unsigned long flag
{
struct adfs_inode_info *ei = (struct adfs_inode_info *) foo;
- if (flags & SLAB_CTOR_CONSTRUCTOR)
- inode_init_once(&ei->vfs_inode);
+ inode_init_once(&ei->vfs_inode);
}
static int init_inodecache(void)
diff --git a/fs/affs/file.c b/fs/affs/file.c
index 4aa8079e71b..c8796906f58 100644
--- a/fs/affs/file.c
+++ b/fs/affs/file.c
@@ -628,11 +628,7 @@ static int affs_prepare_write_ofs(struct file *file, struct page *page, unsigned
return err;
}
if (to < PAGE_CACHE_SIZE) {
- char *kaddr = kmap_atomic(page, KM_USER0);
-
- memset(kaddr + to, 0, PAGE_CACHE_SIZE - to);
- flush_dcache_page(page);
- kunmap_atomic(kaddr, KM_USER0);
+ zero_user_page(page, to, PAGE_CACHE_SIZE - to, KM_USER0);
if (size > offset + to) {
if (size < offset + PAGE_CACHE_SIZE)
tmp = size & ~PAGE_CACHE_MASK;
diff --git a/fs/affs/inode.c b/fs/affs/inode.c
index c5b9d73c084..4609a6c13fe 100644
--- a/fs/affs/inode.c
+++ b/fs/affs/inode.c
@@ -9,7 +9,7 @@
*
* (C) 1991 Linus Torvalds - minix filesystem
*/
-
+#include <linux/sched.h>
#include "affs.h"
extern const struct inode_operations affs_symlink_inode_operations;
diff --git a/fs/affs/super.c b/fs/affs/super.c
index beff7d21e6e..6d0ebc32153 100644
--- a/fs/affs/super.c
+++ b/fs/affs/super.c
@@ -15,6 +15,7 @@
#include <linux/statfs.h>
#include <linux/parser.h>
#include <linux/magic.h>
+#include <linux/sched.h>
#include "affs.h"
extern struct timezone sys_tz;
@@ -87,11 +88,9 @@ static void init_once(void * foo, struct kmem_cache * cachep, unsigned long flag
{
struct affs_inode_info *ei = (struct affs_inode_info *) foo;
- if (flags & SLAB_CTOR_CONSTRUCTOR) {
- init_MUTEX(&ei->i_link_lock);
- init_MUTEX(&ei->i_ext_lock);
- inode_init_once(&ei->vfs_inode);
- }
+ init_MUTEX(&ei->i_link_lock);
+ init_MUTEX(&ei->i_ext_lock);
+ inode_init_once(&ei->vfs_inode);
}
static int init_inodecache(void)
diff --git a/fs/afs/Makefile b/fs/afs/Makefile
index cf83e5d6351..73ce561f3ea 100644
--- a/fs/afs/Makefile
+++ b/fs/afs/Makefile
@@ -22,6 +22,7 @@ kafs-objs := \
vlclient.o \
vlocation.o \
vnode.o \
- volume.o
+ volume.o \
+ write.o
obj-$(CONFIG_AFS_FS) := kafs.o
diff --git a/fs/afs/afs.h b/fs/afs/afs.h
index 52d0752265b..24525794814 100644
--- a/fs/afs/afs.h
+++ b/fs/afs/afs.h
@@ -16,6 +16,9 @@
#define AFS_MAXCELLNAME 64 /* maximum length of a cell name */
#define AFS_MAXVOLNAME 64 /* maximum length of a volume name */
+#define AFSNAMEMAX 256 /* maximum length of a filename plus NUL */
+#define AFSPATHMAX 1024 /* maximum length of a pathname plus NUL */
+#define AFSOPAQUEMAX 1024 /* maximum length of an opaque field */
typedef unsigned afs_volid_t;
typedef unsigned afs_vnodeid_t;
@@ -143,4 +146,24 @@ struct afs_volsync {
time_t creation; /* volume creation time */
};
+/*
+ * AFS volume status record
+ */
+struct afs_volume_status {
+ u32 vid; /* volume ID */
+ u32 parent_id; /* parent volume ID */
+ u8 online; /* true if volume currently online and available */
+ u8 in_service; /* true if volume currently in service */
+ u8 blessed; /* same as in_service */
+ u8 needs_salvage; /* true if consistency checking required */
+ u32 type; /* volume type (afs_voltype_t) */
+ u32 min_quota; /* minimum space set aside (blocks) */
+ u32 max_quota; /* maximum space this volume may occupy (blocks) */
+ u32 blocks_in_use; /* space this volume currently occupies (blocks) */
+ u32 part_blocks_avail; /* space available in volume's partition */
+ u32 part_max_blocks; /* size of volume's partition */
+};
+
+#define AFS_BLOCK_SIZE 1024
+
#endif /* AFS_H */
diff --git a/fs/afs/afs_fs.h b/fs/afs/afs_fs.h
index 89e0d1650a7..a18c374ebe0 100644
--- a/fs/afs/afs_fs.h
+++ b/fs/afs/afs_fs.h
@@ -18,6 +18,8 @@
enum AFS_FS_Operations {
FSFETCHDATA = 130, /* AFS Fetch file data */
FSFETCHSTATUS = 132, /* AFS Fetch file status */
+ FSSTOREDATA = 133, /* AFS Store file data */
+ FSSTORESTATUS = 135, /* AFS Store file status */
FSREMOVEFILE = 136, /* AFS Remove a file */
FSCREATEFILE = 137, /* AFS Create a file */
FSRENAME = 138, /* AFS Rename or move a file or directory */
@@ -26,9 +28,12 @@ enum AFS_FS_Operations {
FSMAKEDIR = 141, /* AFS Create a directory */
FSREMOVEDIR = 142, /* AFS Remove a directory */
FSGIVEUPCALLBACKS = 147, /* AFS Discard callback promises */
- FSGETVOLUMEINFO = 148, /* AFS Get root volume information */
+ FSGETVOLUMEINFO = 148, /* AFS Get information about a volume */
+ FSGETVOLUMESTATUS = 149, /* AFS Get volume status information */
FSGETROOTVOLUME = 151, /* AFS Get root volume name */
FSLOOKUP = 161, /* AFS lookup file in directory */
+ FSFETCHDATA64 = 65537, /* AFS Fetch file data */
+ FSSTOREDATA64 = 65538, /* AFS Store file data */
};
enum AFS_FS_Errors {
diff --git a/fs/afs/callback.c b/fs/afs/callback.c
index 9bdbf36a9aa..bacf518c6fa 100644
--- a/fs/afs/callback.c
+++ b/fs/afs/callback.c
@@ -17,6 +17,7 @@
#include <linux/module.h>
#include <linux/init.h>
#include <linux/circ_buf.h>
+#include <linux/sched.h>
#include "internal.h"
unsigned afs_vnode_update_timeout = 10;
@@ -44,7 +45,7 @@ void afs_init_callback_state(struct afs_server *server)
while (!RB_EMPTY_ROOT(&server->cb_promises)) {
vnode = rb_entry(server->cb_promises.rb_node,
struct afs_vnode, cb_promise);
- _debug("UNPROMISE { vid=%x vn=%u uq=%u}",
+ _debug("UNPROMISE { vid=%x:%u uq=%u}",
vnode->fid.vid, vnode->fid.vnode, vnode->fid.unique);
rb_erase(&vnode->cb_promise, &server->cb_promises);
vnode->cb_promised = false;
@@ -84,11 +85,8 @@ void afs_broken_callback_work(struct work_struct *work)
/* if the vnode's data version number changed then its contents
* are different */
- if (test_and_clear_bit(AFS_VNODE_ZAP_DATA, &vnode->flags)) {
- _debug("zap data {%x:%u}",
- vnode->fid.vid, vnode->fid.vnode);
- invalidate_remote_inode(&vnode->vfs_inode);
- }
+ if (test_and_clear_bit(AFS_VNODE_ZAP_DATA, &vnode->flags))
+ afs_zap_data(vnode);
}
out:
diff --git a/fs/afs/cell.c b/fs/afs/cell.c
index 9b1311a1df5..175a567db78 100644
--- a/fs/afs/cell.c
+++ b/fs/afs/cell.c
@@ -13,6 +13,7 @@
#include <linux/slab.h>
#include <linux/key.h>
#include <linux/ctype.h>
+#include <linux/sched.h>
#include <keys/rxrpc-type.h>
#include "internal.h"
diff --git a/fs/afs/dir.c b/fs/afs/dir.c
index 0c1e902f17a..546c59522eb 100644
--- a/fs/afs/dir.c
+++ b/fs/afs/dir.c
@@ -16,6 +16,7 @@
#include <linux/fs.h>
#include <linux/pagemap.h>
#include <linux/ctype.h>
+#include <linux/sched.h>
#include "internal.h"
static struct dentry *afs_lookup(struct inode *dir, struct dentry *dentry,
@@ -55,7 +56,8 @@ const struct inode_operations afs_dir_inode_operations = {
.rmdir = afs_rmdir,
.rename = afs_rename,
.permission = afs_permission,
- .getattr = afs_inode_getattr,
+ .getattr = afs_getattr,
+ .setattr = afs_setattr,
};
static struct dentry_operations afs_fs_dentry_operations = {
@@ -491,12 +493,12 @@ static struct dentry *afs_lookup(struct inode *dir, struct dentry *dentry,
vnode = AFS_FS_I(dir);
- _enter("{%x:%d},%p{%s},",
+ _enter("{%x:%u},%p{%s},",
vnode->fid.vid, vnode->fid.vnode, dentry, dentry->d_name.name);
ASSERTCMP(dentry->d_inode, ==, NULL);
- if (dentry->d_name.len > 255) {
+ if (dentry->d_name.len >= AFSNAMEMAX) {
_leave(" = -ENAMETOOLONG");
return ERR_PTR(-ENAMETOOLONG);
}
@@ -731,11 +733,11 @@ static int afs_mkdir(struct inode *dir, struct dentry *dentry, int mode)
dvnode = AFS_FS_I(dir);
- _enter("{%x:%d},{%s},%o",
+ _enter("{%x:%u},{%s},%o",
dvnode->fid.vid, dvnode->fid.vnode, dentry->d_name.name, mode);
ret = -ENAMETOOLONG;
- if (dentry->d_name.len > 255)
+ if (dentry->d_name.len >= AFSNAMEMAX)
goto error;
key = afs_request_key(dvnode->volume->cell);
@@ -796,11 +798,11 @@ static int afs_rmdir(struct inode *dir, struct dentry *dentry)
dvnode = AFS_FS_I(dir);
- _enter("{%x:%d},{%s}",
+ _enter("{%x:%u},{%s}",
dvnode->fid.vid, dvnode->fid.vnode, dentry->d_name.name);
ret = -ENAMETOOLONG;
- if (dentry->d_name.len > 255)
+ if (dentry->d_name.len >= AFSNAMEMAX)
goto error;
key = afs_request_key(dvnode->volume->cell);
@@ -842,11 +844,11 @@ static int afs_unlink(struct inode *dir, struct dentry *dentry)
dvnode = AFS_FS_I(dir);
- _enter("{%x:%d},{%s}",
+ _enter("{%x:%u},{%s}",
dvnode->fid.vid, dvnode->fid.vnode, dentry->d_name.name);
ret = -ENAMETOOLONG;
- if (dentry->d_name.len > 255)
+ if (dentry->d_name.len >= AFSNAMEMAX)
goto error;
key = afs_request_key(dvnode->volume->cell);
@@ -916,11 +918,11 @@ static int afs_create(struct inode *dir, struct dentry *dentry, int mode,
dvnode = AFS_FS_I(dir);
- _enter("{%x:%d},{%s},%o,",
+ _enter("{%x:%u},{%s},%o,",
dvnode->fid.vid, dvnode->fid.vnode, dentry->d_name.name, mode);
ret = -ENAMETOOLONG;
- if (dentry->d_name.len > 255)
+ if (dentry->d_name.len >= AFSNAMEMAX)
goto error;
key = afs_request_key(dvnode->volume->cell);
@@ -983,13 +985,13 @@ static int afs_link(struct dentry *from, struct inode *dir,
vnode = AFS_FS_I(from->d_inode);
dvnode = AFS_FS_I(dir);
- _enter("{%x:%d},{%x:%d},{%s}",
+ _enter("{%x:%u},{%x:%u},{%s}",
vnode->fid.vid, vnode->fid.vnode,
dvnode->fid.vid, dvnode->fid.vnode,
dentry->d_name.name);
ret = -ENAMETOOLONG;
- if (dentry->d_name.len > 255)
+ if (dentry->d_name.len >= AFSNAMEMAX)
goto error;
key = afs_request_key(dvnode->volume->cell);
@@ -1032,16 +1034,16 @@ static int afs_symlink(struct inode *dir, struct dentry *dentry,
dvnode = AFS_FS_I(dir);
- _enter("{%x:%d},{%s},%s",
+ _enter("{%x:%u},{%s},%s",
dvnode->fid.vid, dvnode->fid.vnode, dentry->d_name.name,
content);
ret = -ENAMETOOLONG;
- if (dentry->d_name.len > 255)
+ if (dentry->d_name.len >= AFSNAMEMAX)
goto error;
ret = -EINVAL;
- if (strlen(content) > 1023)
+ if (strlen(content) >= AFSPATHMAX)
goto error;
key = afs_request_key(dvnode->volume->cell);
@@ -1104,14 +1106,14 @@ static int afs_rename(struct inode *old_dir, struct dentry *old_dentry,
orig_dvnode = AFS_FS_I(old_dir);
new_dvnode = AFS_FS_I(new_dir);
- _enter("{%x:%d},{%x:%d},{%x:%d},{%s}",
+ _enter("{%x:%u},{%x:%u},{%x:%u},{%s}",
orig_dvnode->fid.vid, orig_dvnode->fid.vnode,
vnode->fid.vid, vnode->fid.vnode,
new_dvnode->fid.vid, new_dvnode->fid.vnode,
new_dentry->d_name.name);
ret = -ENAMETOOLONG;
- if (new_dentry->d_name.len > 255)
+ if (new_dentry->d_name.len >= AFSNAMEMAX)
goto error;
key = afs_request_key(orig_dvnode->volume->cell);
diff --git a/fs/afs/file.c b/fs/afs/file.c
index ae256498f4f..9c0e721d9fc 100644
--- a/fs/afs/file.c
+++ b/fs/afs/file.c
@@ -15,32 +15,43 @@
#include <linux/slab.h>
#include <linux/fs.h>
#include <linux/pagemap.h>
+#include <linux/writeback.h>
#include "internal.h"
-static int afs_file_readpage(struct file *file, struct page *page);
-static void afs_file_invalidatepage(struct page *page, unsigned long offset);
-static int afs_file_releasepage(struct page *page, gfp_t gfp_flags);
+static int afs_readpage(struct file *file, struct page *page);
+static void afs_invalidatepage(struct page *page, unsigned long offset);
+static int afs_releasepage(struct page *page, gfp_t gfp_flags);
+static int afs_launder_page(struct page *page);
const struct file_operations afs_file_operations = {
.open = afs_open,
.release = afs_release,
.llseek = generic_file_llseek,
.read = do_sync_read,
+ .write = do_sync_write,
.aio_read = generic_file_aio_read,
+ .aio_write = afs_file_write,
.mmap = generic_file_readonly_mmap,
.sendfile = generic_file_sendfile,
+ .fsync = afs_fsync,
};
const struct inode_operations afs_file_inode_operations = {
- .getattr = afs_inode_getattr,
+ .getattr = afs_getattr,
+ .setattr = afs_setattr,
.permission = afs_permission,
};
const struct address_space_operations afs_fs_aops = {
- .readpage = afs_file_readpage,
- .set_page_dirty = __set_page_dirty_nobuffers,
- .releasepage = afs_file_releasepage,
- .invalidatepage = afs_file_invalidatepage,
+ .readpage = afs_readpage,
+ .set_page_dirty = afs_set_page_dirty,
+ .launder_page = afs_launder_page,
+ .releasepage = afs_releasepage,
+ .invalidatepage = afs_invalidatepage,
+ .prepare_write = afs_prepare_write,
+ .commit_write = afs_commit_write,
+ .writepage = afs_writepage,
+ .writepages = afs_writepages,
};
/*
@@ -52,7 +63,7 @@ int afs_open(struct inode *inode, struct file *file)
struct key *key;
int ret;
- _enter("{%x:%x},", vnode->fid.vid, vnode->fid.vnode);
+ _enter("{%x:%u},", vnode->fid.vid, vnode->fid.vnode);
key = afs_request_key(vnode->volume->cell);
if (IS_ERR(key)) {
@@ -78,7 +89,7 @@ int afs_release(struct inode *inode, struct file *file)
{
struct afs_vnode *vnode = AFS_FS_I(inode);
- _enter("{%x:%x},", vnode->fid.vid, vnode->fid.vnode);
+ _enter("{%x:%u},", vnode->fid.vid, vnode->fid.vnode);
key_put(file->private_data);
_leave(" = 0");
@@ -89,10 +100,10 @@ int afs_release(struct inode *inode, struct file *file)
* deal with notification that a page was read from the cache
*/
#ifdef AFS_CACHING_SUPPORT
-static void afs_file_readpage_read_complete(void *cookie_data,
- struct page *page,
- void *data,
- int error)
+static void afs_readpage_read_complete(void *cookie_data,
+ struct page *page,
+ void *data,
+ int error)
{
_enter("%p,%p,%p,%d", cookie_data, page, data, error);
@@ -109,10 +120,10 @@ static void afs_file_readpage_read_complete(void *cookie_data,
* deal with notification that a page was written to the cache
*/
#ifdef AFS_CACHING_SUPPORT
-static void afs_file_readpage_write_complete(void *cookie_data,
- struct page *page,
- void *data,
- int error)
+static void afs_readpage_write_complete(void *cookie_data,
+ struct page *page,
+ void *data,
+ int error)
{
_enter("%p,%p,%p,%d", cookie_data, page, data, error);
@@ -121,9 +132,9 @@ static void afs_file_readpage_write_complete(void *cookie_data,
#endif
/*
- * AFS read page from file (or symlink)
+ * AFS read page from file, directory or symlink
*/
-static int afs_file_readpage(struct file *file, struct page *page)
+static int afs_readpage(struct file *file, struct page *page)
{
struct afs_vnode *vnode;
struct inode *inode;
@@ -219,26 +230,9 @@ error:
}
/*
- * get a page cookie for the specified page
- */
-#ifdef AFS_CACHING_SUPPORT
-int afs_cache_get_page_cookie(struct page *page,
- struct cachefs_page **_page_cookie)
-{
- int ret;
-
- _enter("");
- ret = cachefs_page_get_private(page,_page_cookie, GFP_NOIO);
-
- _leave(" = %d", ret);
- return ret;
-}
-#endif
-
-/*
* invalidate part or all of a page
*/
-static void afs_file_invalidatepage(struct page *page, unsigned long offset)
+static void afs_invalidatepage(struct page *page, unsigned long offset)
{
int ret = 1;
@@ -247,11 +241,6 @@ static void afs_file_invalidatepage(struct page *page, unsigned long offset)
BUG_ON(!PageLocked(page));
if (PagePrivate(page)) {
-#ifdef AFS_CACHING_SUPPORT
- struct afs_vnode *vnode = AFS_FS_I(page->mapping->host);
- cachefs_uncache_page(vnode->cache,page);
-#endif
-
/* We release buffers only if the entire page is being
* invalidated.
* The get_block cached value has been unconditionally
@@ -272,25 +261,33 @@ static void afs_file_invalidatepage(struct page *page, unsigned long offset)
}
/*
+ * write back a dirty page
+ */
+static int afs_launder_page(struct page *page)
+{
+ _enter("{%lu}", page->index);
+
+ return 0;
+}
+
+/*
* release a page and cleanup its private data
*/
-static int afs_file_releasepage(struct page *page, gfp_t gfp_flags)
+static int afs_releasepage(struct page *page, gfp_t gfp_flags)
{
- struct cachefs_page *pageio;
+ struct afs_vnode *vnode = AFS_FS_I(page->mapping->host);
+ struct afs_writeback *wb;
- _enter("{%lu},%x", page->index, gfp_flags);
+ _enter("{{%x:%u}[%lu],%lx},%x",
+ vnode->fid.vid, vnode->fid.vnode, page->index, page->flags,
+ gfp_flags);
if (PagePrivate(page)) {
-#ifdef AFS_CACHING_SUPPORT
- struct afs_vnode *vnode = AFS_FS_I(page->mapping->host);
- cachefs_uncache_page(vnode->cache, page);
-#endif
-
- pageio = (struct cachefs_page *) page_private(page);
+ wb = (struct afs_writeback *) page_private(page);
+ ASSERT(wb != NULL);
set_page_private(page, 0);
ClearPagePrivate(page);
-
- kfree(pageio);
+ afs_put_writeback(wb);
}
_leave(" = 0");
diff --git a/fs/afs/fsclient.c b/fs/afs/fsclient.c
index e54e6c2ad34..5dff1308b6f 100644
--- a/fs/afs/fsclient.c
+++ b/fs/afs/fsclient.c
@@ -33,8 +33,10 @@ static void xdr_decode_AFSFid(const __be32 **_bp, struct afs_fid *fid)
*/
static void xdr_decode_AFSFetchStatus(const __be32 **_bp,
struct afs_file_status *status,
- struct afs_vnode *vnode)
+ struct afs_vnode *vnode,
+ afs_dataversion_t *store_version)
{
+ afs_dataversion_t expected_version;
const __be32 *bp = *_bp;
umode_t mode;
u64 data_version, size;
@@ -101,7 +103,11 @@ static void xdr_decode_AFSFetchStatus(const __be32 **_bp,
vnode->vfs_inode.i_atime = vnode->vfs_inode.i_ctime;
}
- if (status->data_version != data_version) {
+ expected_version = status->data_version;
+ if (store_version)
+ expected_version = *store_version;
+
+ if (expected_version != data_version) {
status->data_version = data_version;
if (vnode && !test_bit(AFS_VNODE_UNSET, &vnode->flags)) {
_debug("vnode modified %llx on {%x:%u}",
@@ -110,6 +116,8 @@ static void xdr_decode_AFSFetchStatus(const __be32 **_bp,
set_bit(AFS_VNODE_MODIFIED, &vnode->flags);
set_bit(AFS_VNODE_ZAP_DATA, &vnode->flags);
}
+ } else if (store_version) {
+ status->data_version = data_version;
}
}
@@ -156,6 +164,67 @@ static void xdr_decode_AFSVolSync(const __be32 **_bp,
}
/*
+ * encode the requested attributes into an AFSStoreStatus block
+ */
+static void xdr_encode_AFS_StoreStatus(__be32 **_bp, struct iattr *attr)
+{
+ __be32 *bp = *_bp;
+ u32 mask = 0, mtime = 0, owner = 0, group = 0, mode = 0;
+
+ mask = 0;
+ if (attr->ia_valid & ATTR_MTIME) {
+ mask |= AFS_SET_MTIME;
+ mtime = attr->ia_mtime.tv_sec;
+ }
+
+ if (attr->ia_valid & ATTR_UID) {
+ mask |= AFS_SET_OWNER;
+ owner = attr->ia_uid;
+ }
+
+ if (attr->ia_valid & ATTR_GID) {
+ mask |= AFS_SET_GROUP;
+ group = attr->ia_gid;
+ }
+
+ if (attr->ia_valid & ATTR_MODE) {
+ mask |= AFS_SET_MODE;
+ mode = attr->ia_mode & S_IALLUGO;
+ }
+
+ *bp++ = htonl(mask);
+ *bp++ = htonl(mtime);
+ *bp++ = htonl(owner);
+ *bp++ = htonl(group);
+ *bp++ = htonl(mode);
+ *bp++ = 0; /* segment size */
+ *_bp = bp;
+}
+
+/*
+ * decode an AFSFetchVolumeStatus block
+ */
+static void xdr_decode_AFSFetchVolumeStatus(const __be32 **_bp,
+ struct afs_volume_status *vs)
+{
+ const __be32 *bp = *_bp;
+
+ vs->vid = ntohl(*bp++);
+ vs->parent_id = ntohl(*bp++);
+ vs->online = ntohl(*bp++);
+ vs->in_service = ntohl(*bp++);
+ vs->blessed = ntohl(*bp++);
+ vs->needs_salvage = ntohl(*bp++);
+ vs->type = ntohl(*bp++);
+ vs->min_quota = ntohl(*bp++);
+ vs->max_quota = ntohl(*bp++);
+ vs->blocks_in_use = ntohl(*bp++);
+ vs->part_blocks_avail = ntohl(*bp++);
+ vs->part_max_blocks = ntohl(*bp++);
+ *_bp = bp;
+}
+
+/*
* deliver reply data to an FS.FetchStatus
*/
static int afs_deliver_fs_fetch_status(struct afs_call *call,
@@ -175,7 +244,7 @@ static int afs_deliver_fs_fetch_status(struct afs_call *call,
/* unmarshall the reply once we've received all of it */
bp = call->buffer;
- xdr_decode_AFSFetchStatus(&bp, &vnode->status, vnode);
+ xdr_decode_AFSFetchStatus(&bp, &vnode->status, vnode, NULL);
xdr_decode_AFSCallBack(&bp, vnode);
if (call->reply2)
xdr_decode_AFSVolSync(&bp, call->reply2);
@@ -206,7 +275,7 @@ int afs_fs_fetch_file_status(struct afs_server *server,
struct afs_call *call;
__be32 *bp;
- _enter(",%x,{%x:%d},,",
+ _enter(",%x,{%x:%u},,",
key_serial(key), vnode->fid.vid, vnode->fid.vnode);
call = afs_alloc_flat_call(&afs_RXFSFetchStatus, 16, (21 + 3 + 6) * 4);
@@ -247,9 +316,33 @@ static int afs_deliver_fs_fetch_data(struct afs_call *call,
case 0:
call->offset = 0;
call->unmarshall++;
+ if (call->operation_ID != FSFETCHDATA64) {
+ call->unmarshall++;
+ goto no_msw;
+ }
- /* extract the returned data length */
+ /* extract the upper part of the returned data length of an
+ * FSFETCHDATA64 op (which should always be 0 using this
+ * client) */
case 1:
+ _debug("extract data length (MSW)");
+ ret = afs_extract_data(call, skb, last, &call->tmp, 4);
+ switch (ret) {
+ case 0: break;
+ case -EAGAIN: return 0;
+ default: return ret;
+ }
+
+ call->count = ntohl(call->tmp);
+ _debug("DATA length MSW: %u", call->count);
+ if (call->count > 0)
+ return -EBADMSG;
+ call->offset = 0;
+ call->unmarshall++;
+
+ no_msw:
+ /* extract the returned data length */
+ case 2:
_debug("extract data length");
ret = afs_extract_data(call, skb, last, &call->tmp, 4);
switch (ret) {
@@ -265,32 +358,27 @@ static int afs_deliver_fs_fetch_data(struct afs_call *call,
call->offset = 0;
call->unmarshall++;
- if (call->count < PAGE_SIZE) {
+ /* extract the returned data */
+ case 3:
+ _debug("extract data");
+ if (call->count > 0) {
page = call->reply3;
buffer = kmap_atomic(page, KM_USER0);
- memset(buffer + PAGE_SIZE - call->count, 0,
- call->count);
+ ret = afs_extract_data(call, skb, last, buffer,
+ call->count);
kunmap_atomic(buffer, KM_USER0);
- }
-
- /* extract the returned data */
- case 2:
- _debug("extract data");
- page = call->reply3;
- buffer = kmap_atomic(page, KM_USER0);
- ret = afs_extract_data(call, skb, last, buffer, call->count);
- kunmap_atomic(buffer, KM_USER0);
- switch (ret) {
- case 0: break;
- case -EAGAIN: return 0;
- default: return ret;
+ switch (ret) {
+ case 0: break;
+ case -EAGAIN: return 0;
+ default: return ret;
+ }
}
call->offset = 0;
call->unmarshall++;
/* extract the metadata */
- case 3:
+ case 4:
ret = afs_extract_data(call, skb, last, call->buffer,
(21 + 3 + 6) * 4);
switch (ret) {
@@ -300,7 +388,7 @@ static int afs_deliver_fs_fetch_data(struct afs_call *call,
}
bp = call->buffer;
- xdr_decode_AFSFetchStatus(&bp, &vnode->status, vnode);
+ xdr_decode_AFSFetchStatus(&bp, &vnode->status, vnode, NULL);
xdr_decode_AFSCallBack(&bp, vnode);
if (call->reply2)
xdr_decode_AFSVolSync(&bp, call->reply2);
@@ -308,7 +396,7 @@ static int afs_deliver_fs_fetch_data(struct afs_call *call,
call->offset = 0;
call->unmarshall++;
- case 4:
+ case 5:
_debug("trailer");
if (skb->len != 0)
return -EBADMSG;
@@ -318,6 +406,14 @@ static int afs_deliver_fs_fetch_data(struct afs_call *call,
if (!last)
return 0;
+ if (call->count < PAGE_SIZE) {
+ _debug("clear");
+ page = call->reply3;
+ buffer = kmap_atomic(page, KM_USER0);
+ memset(buffer + call->count, 0, PAGE_SIZE - call->count);
+ kunmap_atomic(buffer, KM_USER0);
+ }
+
_leave(" = 0 [done]");
return 0;
}
@@ -332,6 +428,56 @@ static const struct afs_call_type afs_RXFSFetchData = {
.destructor = afs_flat_call_destructor,
};
+static const struct afs_call_type afs_RXFSFetchData64 = {
+ .name = "FS.FetchData64",
+ .deliver = afs_deliver_fs_fetch_data,
+ .abort_to_error = afs_abort_to_error,
+ .destructor = afs_flat_call_destructor,
+};
+
+/*
+ * fetch data from a very large file
+ */
+static int afs_fs_fetch_data64(struct afs_server *server,
+ struct key *key,
+ struct afs_vnode *vnode,
+ off_t offset, size_t length,
+ struct page *buffer,
+ const struct afs_wait_mode *wait_mode)
+{
+ struct afs_call *call;
+ __be32 *bp;
+
+ _enter("");
+
+ ASSERTCMP(length, <, ULONG_MAX);
+
+ call = afs_alloc_flat_call(&afs_RXFSFetchData64, 32, (21 + 3 + 6) * 4);
+ if (!call)
+ return -ENOMEM;
+
+ call->key = key;
+ call->reply = vnode;
+ call->reply2 = NULL; /* volsync */
+ call->reply3 = buffer;
+ call->service_id = FS_SERVICE;
+ call->port = htons(AFS_FS_PORT);
+ call->operation_ID = FSFETCHDATA64;
+
+ /* marshall the parameters */
+ bp = call->request;
+ bp[0] = htonl(FSFETCHDATA64);
+ bp[1] = htonl(vnode->fid.vid);
+ bp[2] = htonl(vnode->fid.vnode);
+ bp[3] = htonl(vnode->fid.unique);
+ bp[4] = htonl(upper_32_bits(offset));
+ bp[5] = htonl((u32) offset);
+ bp[6] = 0;
+ bp[7] = htonl((u32) length);
+
+ return afs_make_call(&server->addr, call, GFP_NOFS, wait_mode);
+}
+
/*
* fetch data from a file
*/
@@ -345,6 +491,10 @@ int afs_fs_fetch_data(struct afs_server *server,
struct afs_call *call;
__be32 *bp;
+ if (upper_32_bits(offset) || upper_32_bits(offset + length))
+ return afs_fs_fetch_data64(server, key, vnode, offset, length,
+ buffer, wait_mode);
+
_enter("");
call = afs_alloc_flat_call(&afs_RXFSFetchData, 24, (21 + 3 + 6) * 4);
@@ -357,6 +507,7 @@ int afs_fs_fetch_data(struct afs_server *server,
call->reply3 = buffer;
call->service_id = FS_SERVICE;
call->port = htons(AFS_FS_PORT);
+ call->operation_ID = FSFETCHDATA;
/* marshall the parameters */
bp = call->request;
@@ -476,8 +627,8 @@ static int afs_deliver_fs_create_vnode(struct afs_call *call,
/* unmarshall the reply once we've received all of it */
bp = call->buffer;
xdr_decode_AFSFid(&bp, call->reply2);
- xdr_decode_AFSFetchStatus(&bp, call->reply3, NULL);
- xdr_decode_AFSFetchStatus(&bp, &vnode->status, vnode);
+ xdr_decode_AFSFetchStatus(&bp, call->reply3, NULL, NULL);
+ xdr_decode_AFSFetchStatus(&bp, &vnode->status, vnode, NULL);
xdr_decode_AFSCallBack_raw(&bp, call->reply4);
/* xdr_decode_AFSVolSync(&bp, call->replyX); */
@@ -574,7 +725,7 @@ static int afs_deliver_fs_remove(struct afs_call *call,
/* unmarshall the reply once we've received all of it */
bp = call->buffer;
- xdr_decode_AFSFetchStatus(&bp, &vnode->status, vnode);
+ xdr_decode_AFSFetchStatus(&bp, &vnode->status, vnode, NULL);
/* xdr_decode_AFSVolSync(&bp, call->replyX); */
_leave(" = 0 [done]");
@@ -657,8 +808,8 @@ static int afs_deliver_fs_link(struct afs_call *call,
/* unmarshall the reply once we've received all of it */
bp = call->buffer;
- xdr_decode_AFSFetchStatus(&bp, &vnode->status, vnode);
- xdr_decode_AFSFetchStatus(&bp, &dvnode->status, dvnode);
+ xdr_decode_AFSFetchStatus(&bp, &vnode->status, vnode, NULL);
+ xdr_decode_AFSFetchStatus(&bp, &dvnode->status, dvnode, NULL);
/* xdr_decode_AFSVolSync(&bp, call->replyX); */
_leave(" = 0 [done]");
@@ -746,8 +897,8 @@ static int afs_deliver_fs_symlink(struct afs_call *call,
/* unmarshall the reply once we've received all of it */
bp = call->buffer;
xdr_decode_AFSFid(&bp, call->reply2);
- xdr_decode_AFSFetchStatus(&bp, call->reply3, NULL);
- xdr_decode_AFSFetchStatus(&bp, &vnode->status, vnode);
+ xdr_decode_AFSFetchStatus(&bp, call->reply3, NULL, NULL);
+ xdr_decode_AFSFetchStatus(&bp, &vnode->status, vnode, NULL);
/* xdr_decode_AFSVolSync(&bp, call->replyX); */
_leave(" = 0 [done]");
@@ -852,9 +1003,10 @@ static int afs_deliver_fs_rename(struct afs_call *call,
/* unmarshall the reply once we've received all of it */
bp = call->buffer;
- xdr_decode_AFSFetchStatus(&bp, &orig_dvnode->status, orig_dvnode);
+ xdr_decode_AFSFetchStatus(&bp, &orig_dvnode->status, orig_dvnode, NULL);
if (new_dvnode != orig_dvnode)
- xdr_decode_AFSFetchStatus(&bp, &new_dvnode->status, new_dvnode);
+ xdr_decode_AFSFetchStatus(&bp, &new_dvnode->status, new_dvnode,
+ NULL);
/* xdr_decode_AFSVolSync(&bp, call->replyX); */
_leave(" = 0 [done]");
@@ -936,3 +1088,663 @@ int afs_fs_rename(struct afs_server *server,
return afs_make_call(&server->addr, call, GFP_NOFS, wait_mode);
}
+
+/*
+ * deliver reply data to an FS.StoreData
+ */
+static int afs_deliver_fs_store_data(struct afs_call *call,
+ struct sk_buff *skb, bool last)
+{
+ struct afs_vnode *vnode = call->reply;
+ const __be32 *bp;
+
+ _enter(",,%u", last);
+
+ afs_transfer_reply(call, skb);
+ if (!last) {
+ _leave(" = 0 [more]");
+ return 0;
+ }
+
+ if (call->reply_size != call->reply_max) {
+ _leave(" = -EBADMSG [%u != %u]",
+ call->reply_size, call->reply_max);
+ return -EBADMSG;
+ }
+
+ /* unmarshall the reply once we've received all of it */
+ bp = call->buffer;
+ xdr_decode_AFSFetchStatus(&bp, &vnode->status, vnode,
+ &call->store_version);
+ /* xdr_decode_AFSVolSync(&bp, call->replyX); */
+
+ afs_pages_written_back(vnode, call);
+
+ _leave(" = 0 [done]");
+ return 0;
+}
+
+/*
+ * FS.StoreData operation type
+ */
+static const struct afs_call_type afs_RXFSStoreData = {
+ .name = "FS.StoreData",
+ .deliver = afs_deliver_fs_store_data,
+ .abort_to_error = afs_abort_to_error,
+ .destructor = afs_flat_call_destructor,
+};
+
+static const struct afs_call_type afs_RXFSStoreData64 = {
+ .name = "FS.StoreData64",
+ .deliver = afs_deliver_fs_store_data,
+ .abort_to_error = afs_abort_to_error,
+ .destructor = afs_flat_call_destructor,
+};
+
+/*
+ * store a set of pages to a very large file
+ */
+static int afs_fs_store_data64(struct afs_server *server,
+ struct afs_writeback *wb,
+ pgoff_t first, pgoff_t last,
+ unsigned offset, unsigned to,
+ loff_t size, loff_t pos, loff_t i_size,
+ const struct afs_wait_mode *wait_mode)
+{
+ struct afs_vnode *vnode = wb->vnode;
+ struct afs_call *call;
+ __be32 *bp;
+
+ _enter(",%x,{%x:%u},,",
+ key_serial(wb->key), vnode->fid.vid, vnode->fid.vnode);
+
+ call = afs_alloc_flat_call(&afs_RXFSStoreData64,
+ (4 + 6 + 3 * 2) * 4,
+ (21 + 6) * 4);
+ if (!call)
+ return -ENOMEM;
+
+ call->wb = wb;
+ call->key = wb->key;
+ call->reply = vnode;
+ call->service_id = FS_SERVICE;
+ call->port = htons(AFS_FS_PORT);
+ call->mapping = vnode->vfs_inode.i_mapping;
+ call->first = first;
+ call->last = last;
+ call->first_offset = offset;
+ call->last_to = to;
+ call->send_pages = true;
+ call->store_version = vnode->status.data_version + 1;
+
+ /* marshall the parameters */
+ bp = call->request;
+ *bp++ = htonl(FSSTOREDATA64);
+ *bp++ = htonl(vnode->fid.vid);
+ *bp++ = htonl(vnode->fid.vnode);
+ *bp++ = htonl(vnode->fid.unique);
+
+ *bp++ = 0; /* mask */
+ *bp++ = 0; /* mtime */
+ *bp++ = 0; /* owner */
+ *bp++ = 0; /* group */
+ *bp++ = 0; /* unix mode */
+ *bp++ = 0; /* segment size */
+
+ *bp++ = htonl(pos >> 32);
+ *bp++ = htonl((u32) pos);
+ *bp++ = htonl(size >> 32);
+ *bp++ = htonl((u32) size);
+ *bp++ = htonl(i_size >> 32);
+ *bp++ = htonl((u32) i_size);
+
+ return afs_make_call(&server->addr, call, GFP_NOFS, wait_mode);
+}
+
+/*
+ * store a set of pages
+ */
+int afs_fs_store_data(struct afs_server *server, struct afs_writeback *wb,
+ pgoff_t first, pgoff_t last,
+ unsigned offset, unsigned to,
+ const struct afs_wait_mode *wait_mode)
+{
+ struct afs_vnode *vnode = wb->vnode;
+ struct afs_call *call;
+ loff_t size, pos, i_size;
+ __be32 *bp;
+
+ _enter(",%x,{%x:%u},,",
+ key_serial(wb->key), vnode->fid.vid, vnode->fid.vnode);
+
+ size = to - offset;
+ if (first != last)
+ size += (loff_t)(last - first) << PAGE_SHIFT;
+ pos = (loff_t)first << PAGE_SHIFT;
+ pos += offset;
+
+ i_size = i_size_read(&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);
+
+ if (pos >> 32 || i_size >> 32 || size >> 32 || (pos + size) >> 32)
+ return afs_fs_store_data64(server, wb, first, last, offset, to,
+ size, pos, i_size, wait_mode);
+
+ call = afs_alloc_flat_call(&afs_RXFSStoreData,
+ (4 + 6 + 3) * 4,
+ (21 + 6) * 4);
+ if (!call)
+ return -ENOMEM;
+
+ call->wb = wb;
+ call->key = wb->key;
+ call->reply = vnode;
+ call->service_id = FS_SERVICE;
+ call->port = htons(AFS_FS_PORT);
+ call->mapping = vnode->vfs_inode.i_mapping;
+ call->first = first;
+ call->last = last;
+ call->first_offset = offset;
+ call->last_to = to;
+ call->send_pages = true;
+ call->store_version = vnode->status.data_version + 1;
+
+ /* marshall the parameters */
+ bp = call->request;
+ *bp++ = htonl(FSSTOREDATA);
+ *bp++ = htonl(vnode->fid.vid);
+ *bp++ = htonl(vnode->fid.vnode);
+ *bp++ = htonl(vnode->fid.unique);
+
+ *bp++ = 0; /* mask */
+ *bp++ = 0; /* mtime */
+ *bp++ = 0; /* owner */
+ *bp++ = 0; /* group */
+ *bp++ = 0; /* unix mode */
+ *bp++ = 0; /* segment size */
+
+ *bp++ = htonl(pos);
+ *bp++ = htonl(size);
+ *bp++ = htonl(i_size);
+
+ return afs_make_call(&server->addr, call, GFP_NOFS, wait_mode);
+}
+
+/*
+ * deliver reply data to an FS.StoreStatus
+ */
+static int afs_deliver_fs_store_status(struct afs_call *call,
+ struct sk_buff *skb, bool last)
+{
+ afs_dataversion_t *store_version;
+ struct afs_vnode *vnode = call->reply;
+ const __be32 *bp;
+
+ _enter(",,%u", last);
+
+ afs_transfer_reply(call, skb);
+ if (!last) {
+ _leave(" = 0 [more]");
+ return 0;
+ }
+
+ if (call->reply_size != call->reply_max) {
+ _leave(" = -EBADMSG [%u != %u]",
+ call->reply_size, call->reply_max);
+ return -EBADMSG;
+ }
+
+ /* unmarshall the reply once we've received all of it */
+ store_version = NULL;
+ if (call->operation_ID == FSSTOREDATA)
+ store_version = &call->store_version;
+
+ bp = call->buffer;
+ xdr_decode_AFSFetchStatus(&bp, &vnode->status, vnode, store_version);
+ /* xdr_decode_AFSVolSync(&bp, call->replyX); */
+
+ _leave(" = 0 [done]");
+ return 0;
+}
+
+/*
+ * FS.StoreStatus operation type
+ */
+static const struct afs_call_type afs_RXFSStoreStatus = {
+ .name = "FS.StoreStatus",
+ .deliver = afs_deliver_fs_store_status,
+ .abort_to_error = afs_abort_to_error,
+ .destructor = afs_flat_call_destructor,
+};
+
+static const struct afs_call_type afs_RXFSStoreData_as_Status = {
+ .name = "FS.StoreData",
+ .deliver = afs_deliver_fs_store_status,
+ .abort_to_error = afs_abort_to_error,
+ .destructor = afs_flat_call_destructor,
+};
+
+static const struct afs_call_type afs_RXFSStoreData64_as_Status = {
+ .name = "FS.StoreData64",
+ .deliver = afs_deliver_fs_store_status,
+ .abort_to_error = afs_abort_to_error,
+ .destructor = afs_flat_call_destructor,
+};
+
+/*
+ * set the attributes on a very large file, using FS.StoreData rather than
+ * FS.StoreStatus so as to alter the file size also
+ */
+static int afs_fs_setattr_size64(struct afs_server *server, struct key *key,
+ struct afs_vnode *vnode, struct iattr *attr,
+ const struct afs_wait_mode *wait_mode)
+{
+ struct afs_call *call;
+ __be32 *bp;
+
+ _enter(",%x,{%x:%u},,",
+ key_serial(key), vnode->fid.vid, vnode->fid.vnode);
+
+ ASSERT(attr->ia_valid & ATTR_SIZE);
+
+ call = afs_alloc_flat_call(&afs_RXFSStoreData64_as_Status,
+ (4 + 6 + 3 * 2) * 4,
+ (21 + 6) * 4);
+ if (!call)
+ return -ENOMEM;
+
+ call->key = key;
+ call->reply = vnode;
+ call->service_id = FS_SERVICE;
+ call->port = htons(AFS_FS_PORT);
+ call->store_version = vnode->status.data_version + 1;
+ call->operation_ID = FSSTOREDATA;
+
+ /* marshall the parameters */
+ bp = call->request;
+ *bp++ = htonl(FSSTOREDATA64);
+ *bp++ = htonl(vnode->fid.vid);
+ *bp++ = htonl(vnode->fid.vnode);
+ *bp++ = htonl(vnode->fid.unique);
+
+ xdr_encode_AFS_StoreStatus(&bp, attr);
+
+ *bp++ = 0; /* position of start of write */
+ *bp++ = 0;
+ *bp++ = 0; /* size of write */
+ *bp++ = 0;
+ *bp++ = htonl(attr->ia_size >> 32); /* new file length */
+ *bp++ = htonl((u32) attr->ia_size);
+
+ return afs_make_call(&server->addr, call, GFP_NOFS, wait_mode);
+}
+
+/*
+ * set the attributes on a file, using FS.StoreData rather than FS.StoreStatus
+ * so as to alter the file size also
+ */
+static int afs_fs_setattr_size(struct afs_server *server, struct key *key,
+ struct afs_vnode *vnode, struct iattr *attr,
+ const struct afs_wait_mode *wait_mode)
+{
+ struct afs_call *call;
+ __be32 *bp;
+
+ _enter(",%x,{%x:%u},,",
+ key_serial(key), vnode->fid.vid, vnode->fid.vnode);
+
+ ASSERT(attr->ia_valid & ATTR_SIZE);
+ if (attr->ia_size >> 32)
+ return afs_fs_setattr_size64(server, key, vnode, attr,
+ wait_mode);
+
+ call = afs_alloc_flat_call(&afs_RXFSStoreData_as_Status,
+ (4 + 6 + 3) * 4,
+ (21 + 6) * 4);
+ if (!call)
+ return -ENOMEM;
+
+ call->key = key;
+ call->reply = vnode;
+ call->service_id = FS_SERVICE;
+ call->port = htons(AFS_FS_PORT);
+ call->store_version = vnode->status.data_version + 1;
+ call->operation_ID = FSSTOREDATA;
+
+ /* marshall the parameters */
+ bp = call->request;
+ *bp++ = htonl(FSSTOREDATA);
+ *bp++ = htonl(vnode->fid.vid);
+ *bp++ = htonl(vnode->fid.vnode);
+ *bp++ = htonl(vnode->fid.unique);
+
+ xdr_encode_AFS_StoreStatus(&bp, attr);
+
+ *bp++ = 0; /* position of start of write */
+ *bp++ = 0; /* size of write */
+ *bp++ = htonl(attr->ia_size); /* new file length */
+
+ return afs_make_call(&server->addr, call, GFP_NOFS, wait_mode);
+}
+
+/*
+ * set the attributes on a file, using FS.StoreData if there's a change in file
+ * size, and FS.StoreStatus otherwise
+ */
+int afs_fs_setattr(struct afs_server *server, struct key *key,
+ struct afs_vnode *vnode, struct iattr *attr,
+ const struct afs_wait_mode *wait_mode)
+{
+ struct afs_call *call;
+ __be32 *bp;
+
+ if (attr->ia_valid & ATTR_SIZE)
+ return afs_fs_setattr_size(server, key, vnode, attr,
+ wait_mode);
+
+ _enter(",%x,{%x:%u},,",
+ key_serial(key), vnode->fid.vid, vnode->fid.vnode);
+
+ call = afs_alloc_flat_call(&afs_RXFSStoreStatus,
+ (4 + 6) * 4,
+ (21 + 6) * 4);
+ if (!call)
+ return -ENOMEM;
+
+ call->key = key;
+ call->reply = vnode;
+ call->service_id = FS_SERVICE;
+ call->port = htons(AFS_FS_PORT);
+ call->operation_ID = FSSTORESTATUS;
+
+ /* marshall the parameters */
+ bp = call->request;
+ *bp++ = htonl(FSSTORESTATUS);
+ *bp++ = htonl(vnode->fid.vid);
+ *bp++ = htonl(vnode->fid.vnode);
+ *bp++ = htonl(vnode->fid.unique);
+
+ xdr_encode_AFS_StoreStatus(&bp, attr);
+
+ return afs_make_call(&server->addr, call, GFP_NOFS, wait_mode);
+}
+
+/*
+ * deliver reply data to an FS.GetVolumeStatus
+ */
+static int afs_deliver_fs_get_volume_status(struct afs_call *call,
+ struct sk_buff *skb, bool last)
+{
+ const __be32 *bp;
+ char *p;
+ int ret;
+
+ _enter("{%u},{%u},%d", call->unmarshall, skb->len, last);
+
+ switch (call->unmarshall) {
+ case 0:
+ call->offset = 0;
+ call->unmarshall++;
+
+ /* extract the returned status record */
+ case 1:
+ _debug("extract status");
+ ret = afs_extract_data(call, skb, last, call->buffer,
+ 12 * 4);
+ switch (ret) {
+ case 0: break;
+ case -EAGAIN: return 0;
+ default: return ret;
+ }
+
+ bp = call->buffer;
+ xdr_decode_AFSFetchVolumeStatus(&bp, call->reply2);
+ call->offset = 0;
+ call->unmarshall++;
+
+ /* extract the volume name length */
+ case 2:
+ ret = afs_extract_data(call, skb, last, &call->tmp, 4);
+ switch (ret) {
+ case 0: break;
+ case -EAGAIN: return 0;
+ default: return ret;
+ }
+
+ call->count = ntohl(call->tmp);
+ _debug("volname length: %u", call->count);
+ if (call->count >= AFSNAMEMAX)
+ return -EBADMSG;
+ call->offset = 0;
+ call->unmarshall++;
+
+ /* extract the volume name */
+ case 3:
+ _debug("extract volname");
+ if (call->count > 0) {
+ ret = afs_extract_data(call, skb, last, call->reply3,
+ call->count);
+ switch (ret) {
+ case 0: break;
+ case -EAGAIN: return 0;
+ default: return ret;
+ }
+ }
+
+ p = call->reply3;
+ p[call->count] = 0;
+ _debug("volname '%s'", p);
+
+ call->offset = 0;
+ call->unmarshall++;
+
+ /* extract the volume name padding */
+ if ((call->count & 3) == 0) {
+ call->unmarshall++;
+ goto no_volname_padding;
+ }
+ call->count = 4 - (call->count & 3);
+
+ case 4:
+ ret = afs_extract_data(call, skb, last, call->buffer,
+ call->count);
+ switch (ret) {
+ case 0: break;
+ case -EAGAIN: return 0;
+ default: return ret;
+ }
+
+ call->offset = 0;
+ call->unmarshall++;
+ no_volname_padding:
+
+ /* extract the offline message length */
+ case 5:
+ ret = afs_extract_data(call, skb, last, &call->tmp, 4);
+ switch (ret) {
+ case 0: break;
+ case -EAGAIN: return 0;
+ default: return ret;
+ }
+
+ call->count = ntohl(call->tmp);
+ _debug("offline msg length: %u", call->count);
+ if (call->count >= AFSNAMEMAX)
+ return -EBADMSG;
+ call->offset = 0;
+ call->unmarshall++;
+
+ /* extract the offline message */
+ case 6:
+ _debug("extract offline");
+ if (call->count > 0) {
+ ret = afs_extract_data(call, skb, last, call->reply3,
+ call->count);
+ switch (ret) {
+ case 0: break;
+ case -EAGAIN: return 0;
+ default: return ret;
+ }
+ }
+
+ p = call->reply3;
+ p[call->count] = 0;
+ _debug("offline '%s'", p);
+
+ call->offset = 0;
+ call->unmarshall++;
+
+ /* extract the offline message padding */
+ if ((call->count & 3) == 0) {
+ call->unmarshall++;
+ goto no_offline_padding;
+ }
+ call->count = 4 - (call->count & 3);
+
+ case 7:
+ ret = afs_extract_data(call, skb, last, call->buffer,
+ call->count);
+ switch (ret) {
+ case 0: break;
+ case -EAGAIN: return 0;
+ default: return ret;
+ }
+
+ call->offset = 0;
+ call->unmarshall++;
+ no_offline_padding:
+
+ /* extract the message of the day length */
+ case 8:
+ ret = afs_extract_data(call, skb, last, &call->tmp, 4);
+ switch (ret) {
+ case 0: break;
+ case -EAGAIN: return 0;
+ default: return ret;
+ }
+
+ call->count = ntohl(call->tmp);
+ _debug("motd length: %u", call->count);
+ if (call->count >= AFSNAMEMAX)
+ return -EBADMSG;
+ call->offset = 0;
+ call->unmarshall++;
+
+ /* extract the message of the day */
+ case 9:
+ _debug("extract motd");
+ if (call->count > 0) {
+ ret = afs_extract_data(call, skb, last, call->reply3,
+ call->count);
+ switch (ret) {
+ case 0: break;
+ case -EAGAIN: return 0;
+ default: return ret;
+ }
+ }
+
+ p = call->reply3;
+ p[call->count] = 0;
+ _debug("motd '%s'", p);
+
+ call->offset = 0;
+ call->unmarshall++;
+
+ /* extract the message of the day padding */
+ if ((call->count & 3) == 0) {
+ call->unmarshall++;
+ goto no_motd_padding;
+ }
+ call->count = 4 - (call->count & 3);
+
+ case 10:
+ ret = afs_extract_data(call, skb, last, call->buffer,
+ call->count);
+ switch (ret) {
+ case 0: break;
+ case -EAGAIN: return 0;
+ default: return ret;
+ }
+
+ call->offset = 0;
+ call->unmarshall++;
+ no_motd_padding:
+
+ case 11:
+ _debug("trailer %d", skb->len);
+ if (skb->len != 0)
+ return -EBADMSG;
+ break;
+ }
+
+ if (!last)
+ return 0;
+
+ _leave(" = 0 [done]");
+ return 0;
+}
+
+/*
+ * destroy an FS.GetVolumeStatus call
+ */
+static void afs_get_volume_status_call_destructor(struct afs_call *call)
+{
+ kfree(call->reply3);
+ call->reply3 = NULL;
+ afs_flat_call_destructor(call);
+}
+
+/*
+ * FS.GetVolumeStatus operation type
+ */
+static const struct afs_call_type afs_RXFSGetVolumeStatus = {
+ .name = "FS.GetVolumeStatus",
+ .deliver = afs_deliver_fs_get_volume_status,
+ .abort_to_error = afs_abort_to_error,
+ .destructor = afs_get_volume_status_call_destructor,
+};
+
+/*
+ * fetch the status of a volume
+ */
+int afs_fs_get_volume_status(struct afs_server *server,
+ struct key *key,
+ struct afs_vnode *vnode,
+ struct afs_volume_status *vs,
+ const struct afs_wait_mode *wait_mode)
+{
+ struct afs_call *call;
+ __be32 *bp;
+ void *tmpbuf;
+
+ _enter("");
+
+ tmpbuf = kmalloc(AFSOPAQUEMAX, GFP_KERNEL);
+ if (!tmpbuf)
+ return -ENOMEM;
+
+ call = afs_alloc_flat_call(&afs_RXFSGetVolumeStatus, 2 * 4, 12 * 4);
+ if (!call) {
+ kfree(tmpbuf);
+ return -ENOMEM;
+ }
+
+ call->key = key;
+ call->reply = vnode;
+ call->reply2 = vs;
+ call->reply3 = tmpbuf;
+ call->service_id = FS_SERVICE;
+ call->port = htons(AFS_FS_PORT);
+
+ /* marshall the parameters */
+ bp = call->request;
+ bp[0] = htonl(FSGETVOLUMESTATUS);
+ bp[1] = htonl(vnode->fid.vid);
+
+ return afs_make_call(&server->addr, call, GFP_NOFS, wait_mode);
+}
diff --git a/fs/afs/inode.c b/fs/afs/inode.c
index c184a4ee599..d196840127c 100644
--- a/fs/afs/inode.c
+++ b/fs/afs/inode.c
@@ -19,6 +19,7 @@
#include <linux/slab.h>
#include <linux/fs.h>
#include <linux/pagemap.h>
+#include <linux/sched.h>
#include "internal.h"
struct afs_iget_data {
@@ -125,7 +126,7 @@ struct inode *afs_iget(struct super_block *sb, struct key *key,
struct inode *inode;
int ret;
- _enter(",{%u,%u,%u},,", fid->vid, fid->vnode, fid->unique);
+ _enter(",{%x:%u.%u},,", fid->vid, fid->vnode, fid->unique);
as = sb->s_fs_info;
data.volume = as->volume;
@@ -204,6 +205,23 @@ bad_inode:
}
/*
+ * mark the data attached to an inode as obsolete due to a write on the server
+ * - might also want to ditch all the outstanding writes and dirty pages
+ */
+void afs_zap_data(struct afs_vnode *vnode)
+{
+ _enter("{%x:%u}", vnode->fid.vid, vnode->fid.vnode);
+
+ /* nuke all the non-dirty pages that aren't locked, mapped or being
+ * written back in a regular file and completely discard the pages in a
+ * directory or symlink */
+ if (S_ISREG(vnode->vfs_inode.i_mode))
+ invalidate_remote_inode(&vnode->vfs_inode);
+ else
+ invalidate_inode_pages2(vnode->vfs_inode.i_mapping);
+}
+
+/*
* validate a vnode/inode
* - there are several things we need to check
* - parent dir data changes (rm, rmdir, rename, mkdir, create, link,
@@ -258,10 +276,8 @@ int afs_validate(struct afs_vnode *vnode, struct key *key)
/* if the vnode's data version number changed then its contents are
* different */
- if (test_and_clear_bit(AFS_VNODE_ZAP_DATA, &vnode->flags)) {
- _debug("zap data {%x:%d}", vnode->fid.vid, vnode->fid.vnode);
- invalidate_remote_inode(&vnode->vfs_inode);
- }
+ if (test_and_clear_bit(AFS_VNODE_ZAP_DATA, &vnode->flags))
+ afs_zap_data(vnode);
clear_bit(AFS_VNODE_MODIFIED, &vnode->flags);
mutex_unlock(&vnode->validate_lock);
@@ -278,7 +294,7 @@ error_unlock:
/*
* read the attributes of an inode
*/
-int afs_inode_getattr(struct vfsmount *mnt, struct dentry *dentry,
+int afs_getattr(struct vfsmount *mnt, struct dentry *dentry,
struct kstat *stat)
{
struct inode *inode;
@@ -301,7 +317,7 @@ void afs_clear_inode(struct inode *inode)
vnode = AFS_FS_I(inode);
- _enter("{%x:%d.%d} v=%u x=%u t=%u }",
+ _enter("{%x:%u.%d} v=%u x=%u t=%u }",
vnode->fid.vid,
vnode->fid.vnode,
vnode->fid.unique,
@@ -323,6 +339,7 @@ void afs_clear_inode(struct inode *inode)
vnode->server = NULL;
}
+ ASSERT(list_empty(&vnode->writebacks));
ASSERT(!vnode->cb_promised);
#ifdef AFS_CACHING_SUPPORT
@@ -339,3 +356,47 @@ void afs_clear_inode(struct inode *inode)
_leave("");
}
+
+/*
+ * set the attributes of an inode
+ */
+int afs_setattr(struct dentry *dentry, struct iattr *attr)
+{
+ struct afs_vnode *vnode = AFS_FS_I(dentry->d_inode);
+ struct key *key;
+ int ret;
+
+ _enter("{%x:%u},{n=%s},%x",
+ vnode->fid.vid, vnode->fid.vnode, dentry->d_name.name,
+ attr->ia_valid);
+
+ if (!(attr->ia_valid & (ATTR_SIZE | ATTR_MODE | ATTR_UID | ATTR_GID |
+ ATTR_MTIME))) {
+ _leave(" = 0 [unsupported]");
+ return 0;
+ }
+
+ /* flush any dirty data outstanding on a regular file */
+ if (S_ISREG(vnode->vfs_inode.i_mode)) {
+ filemap_write_and_wait(vnode->vfs_inode.i_mapping);
+ afs_writeback_all(vnode);
+ }
+
+ if (attr->ia_valid & ATTR_FILE) {
+ key = attr->ia_file->private_data;
+ } else {
+ key = afs_request_key(vnode->volume->cell);
+ if (IS_ERR(key)) {
+ ret = PTR_ERR(key);
+ goto error;
+ }
+ }
+
+ ret = afs_vnode_setattr(vnode, key, attr);
+ if (!(attr->ia_valid & ATTR_FILE))
+ key_put(key);
+
+error:
+ _leave(" = %d", ret);
+ return ret;
+}
diff --git a/fs/afs/internal.h b/fs/afs/internal.h
index d90c158cd93..2c55dd94a1d 100644
--- a/fs/afs/internal.h
+++ b/fs/afs/internal.h
@@ -16,11 +16,15 @@
#include <linux/skbuff.h>
#include <linux/rxrpc.h>
#include <linux/key.h>
+#include <linux/workqueue.h>
+#include <linux/sched.h>
+
#include "afs.h"
#include "afs_vl.h"
#define AFS_CELL_MAX_ADDRS 15
+struct pagevec;
struct afs_call;
typedef enum {
@@ -75,12 +79,15 @@ struct afs_call {
struct key *key; /* security for this call */
struct afs_server *server; /* server affected by incoming CM call */
void *request; /* request data (first part) */
- void *request2; /* request data (second part) */
+ struct address_space *mapping; /* page set */
+ struct afs_writeback *wb; /* writeback being performed */
void *buffer; /* reply receive buffer */
void *reply; /* reply buffer (first part) */
void *reply2; /* reply buffer (second part) */
void *reply3; /* reply buffer (third part) */
void *reply4; /* reply buffer (fourth part) */
+ pgoff_t first; /* first page in mapping to deal with */
+ pgoff_t last; /* last page in mapping to deal with */
enum { /* call state */
AFS_CALL_REQUESTING, /* request is being sent for outgoing call */
AFS_CALL_AWAIT_REPLY, /* awaiting reply to outgoing call */
@@ -97,14 +104,18 @@ struct afs_call {
unsigned request_size; /* size of request data */
unsigned reply_max; /* maximum size of reply */
unsigned reply_size; /* current size of reply */
+ unsigned first_offset; /* offset into mapping[first] */
+ unsigned last_to; /* amount of mapping[last] */
unsigned short offset; /* offset into received data store */
unsigned char unmarshall; /* unmarshalling phase */
bool incoming; /* T if incoming call */
+ bool send_pages; /* T if data from mapping should be sent */
u16 service_id; /* RxRPC service ID to call */
__be16 port; /* target UDP port */
__be32 operation_ID; /* operation ID for an incoming call */
u32 count; /* count for use in unmarshalling */
__be32 tmp; /* place to extract temporary data */
+ afs_dataversion_t store_version; /* updated version expected from store */
};
struct afs_call_type {
@@ -124,6 +135,32 @@ struct afs_call_type {
};
/*
+ * record of an outstanding writeback on a vnode
+ */
+struct afs_writeback {
+ struct list_head link; /* link in vnode->writebacks */
+ struct work_struct writer; /* work item to perform the writeback */
+ struct afs_vnode *vnode; /* vnode to which this write applies */
+ struct key *key; /* owner of this write */
+ wait_queue_head_t waitq; /* completion and ready wait queue */
+ pgoff_t first; /* first page in batch */
+ pgoff_t point; /* last page in current store op */
+ pgoff_t last; /* last page in batch (inclusive) */
+ unsigned offset_first; /* offset into first page of start of write */
+ unsigned to_last; /* offset into last page of end of write */
+ int num_conflicts; /* count of conflicting writes in list */
+ int usage;
+ bool conflicts; /* T if has dependent conflicts */
+ enum {
+ AFS_WBACK_SYNCING, /* synchronisation being performed */
+ AFS_WBACK_PENDING, /* write pending */
+ AFS_WBACK_CONFLICTING, /* conflicting writes posted */
+ AFS_WBACK_WRITING, /* writing back */
+ AFS_WBACK_COMPLETE /* the writeback record has been unlinked */
+ } state __attribute__((packed));
+};
+
+/*
* AFS superblock private data
* - there's one superblock per volume
*/
@@ -305,6 +342,7 @@ struct afs_vnode {
wait_queue_head_t update_waitq; /* status fetch waitqueue */
int update_cnt; /* number of outstanding ops that will update the
* status */
+ spinlock_t writeback_lock; /* lock for writebacks */
spinlock_t lock; /* waitqueue/flags lock */
unsigned long flags;
#define AFS_VNODE_CB_BROKEN 0 /* set if vnode's callback was broken */
@@ -316,6 +354,8 @@ struct afs_vnode {
long acl_order; /* ACL check count (callback break count) */
+ struct list_head writebacks; /* alterations in pagecache that need writing */
+
/* outstanding callback notification on this file */
struct rb_node server_rb; /* link in server->fs_vnodes */
struct rb_node cb_promise; /* link in server->cb_promises */
@@ -433,10 +473,6 @@ extern const struct file_operations afs_file_operations;
extern int afs_open(struct inode *, struct file *);
extern int afs_release(struct inode *, struct file *);
-#ifdef AFS_CACHING_SUPPORT
-extern int afs_cache_get_page_cookie(struct page *, struct cachefs_page **);
-#endif
-
/*
* fsclient.c
*/
@@ -467,6 +503,16 @@ extern int afs_fs_rename(struct afs_server *, struct key *,
struct afs_vnode *, const char *,
struct afs_vnode *, const char *,
const struct afs_wait_mode *);
+extern int afs_fs_store_data(struct afs_server *, struct afs_writeback *,
+ pgoff_t, pgoff_t, unsigned, unsigned,
+ const struct afs_wait_mode *);
+extern int afs_fs_setattr(struct afs_server *, struct key *,
+ struct afs_vnode *, struct iattr *,
+ const struct afs_wait_mode *);
+extern int afs_fs_get_volume_status(struct afs_server *, struct key *,
+ struct afs_vnode *,
+ struct afs_volume_status *,
+ const struct afs_wait_mode *);
/*
* inode.c
@@ -474,10 +520,10 @@ extern int afs_fs_rename(struct afs_server *, struct key *,
extern struct inode *afs_iget(struct super_block *, struct key *,
struct afs_fid *, struct afs_file_status *,
struct afs_callback *);
+extern void afs_zap_data(struct afs_vnode *);
extern int afs_validate(struct afs_vnode *, struct key *);
-extern int afs_inode_getattr(struct vfsmount *, struct dentry *,
- struct kstat *);
-extern void afs_zap_permits(struct rcu_head *);
+extern int afs_getattr(struct vfsmount *, struct dentry *, struct kstat *);
+extern int afs_setattr(struct dentry *, struct iattr *);
extern void afs_clear_inode(struct inode *);
/*
@@ -533,6 +579,7 @@ extern int afs_extract_data(struct afs_call *, struct sk_buff *, bool, void *,
*/
extern void afs_clear_permits(struct afs_vnode *);
extern void afs_cache_permit(struct afs_vnode *, struct key *, long);
+extern void afs_zap_permits(struct rcu_head *);
extern struct key *afs_request_key(struct afs_cell *);
extern int afs_permission(struct inode *, int, struct nameidata *);
@@ -629,6 +676,11 @@ extern int afs_vnode_symlink(struct afs_vnode *, struct key *, const char *,
struct afs_file_status *, struct afs_server **);
extern int afs_vnode_rename(struct afs_vnode *, struct afs_vnode *,
struct key *, const char *, const char *);
+extern int afs_vnode_store_data(struct afs_writeback *, pgoff_t, pgoff_t,
+ unsigned, unsigned);
+extern int afs_vnode_setattr(struct afs_vnode *, struct key *, struct iattr *);
+extern int afs_vnode_get_volume_status(struct afs_vnode *, struct key *,
+ struct afs_volume_status *);
/*
* volume.c
@@ -645,6 +697,23 @@ extern struct afs_server *afs_volume_pick_fileserver(struct afs_vnode *);
extern int afs_volume_release_fileserver(struct afs_vnode *,
struct afs_server *, int);
+/*
+ * write.c
+ */
+extern int afs_set_page_dirty(struct page *);
+extern void afs_put_writeback(struct afs_writeback *);
+extern int afs_prepare_write(struct file *, struct page *, unsigned, unsigned);
+extern int afs_commit_write(struct file *, struct page *, unsigned, unsigned);
+extern int afs_writepage(struct page *, struct writeback_control *);
+extern int afs_writepages(struct address_space *, struct writeback_control *);
+extern int afs_write_inode(struct inode *, int);
+extern void afs_pages_written_back(struct afs_vnode *, struct afs_call *);
+extern ssize_t afs_file_write(struct kiocb *, const struct iovec *,
+ unsigned long, loff_t);
+extern int afs_writeback_all(struct afs_vnode *);
+extern int afs_fsync(struct file *, struct dentry *, int);
+
+
/*****************************************************************************/
/*
* debug tracing
@@ -726,6 +795,21 @@ do { \
} \
} while(0)
+#define ASSERTRANGE(L, OP1, N, OP2, H) \
+do { \
+ if (unlikely(!((L) OP1 (N)) || !((N) OP2 (H)))) { \
+ printk(KERN_ERR "\n"); \
+ printk(KERN_ERR "AFS: Assertion failed\n"); \
+ printk(KERN_ERR "%lu "#OP1" %lu "#OP2" %lu is false\n", \
+ (unsigned long)(L), (unsigned long)(N), \
+ (unsigned long)(H)); \
+ printk(KERN_ERR "0x%lx "#OP1" 0x%lx "#OP2" 0x%lx is false\n", \
+ (unsigned long)(L), (unsigned long)(N), \
+ (unsigned long)(H)); \
+ BUG(); \
+ } \
+} while(0)
+
#define ASSERTIF(C, X) \
do { \
if (unlikely((C) && !(X))) { \
@@ -758,6 +842,10 @@ do { \
do { \
} while(0)
+#define ASSERTRANGE(L, OP1, N, OP2, H) \
+do { \
+} while(0)
+
#define ASSERTIF(C, X) \
do { \
} while(0)
diff --git a/fs/afs/main.c b/fs/afs/main.c
index 80ec6fd19a7..cd21195bbb2 100644
--- a/fs/afs/main.c
+++ b/fs/afs/main.c
@@ -13,6 +13,7 @@
#include <linux/moduleparam.h>
#include <linux/init.h>
#include <linux/completion.h>
+#include <linux/sched.h>
#include "internal.h"
MODULE_DESCRIPTION("AFS Client File System");
@@ -149,6 +150,7 @@ error_cache:
afs_vlocation_purge();
afs_cell_purge();
afs_proc_cleanup();
+ rcu_barrier();
printk(KERN_ERR "kAFS: failed to register: %d\n", ret);
return ret;
}
@@ -176,6 +178,7 @@ static void __exit afs_exit(void)
cachefs_unregister_netfs(&afs_cache_netfs);
#endif
afs_proc_cleanup();
+ rcu_barrier();
}
module_exit(afs_exit);
diff --git a/fs/afs/misc.c b/fs/afs/misc.c
index cdb9792d816..d1a889c4074 100644
--- a/fs/afs/misc.c
+++ b/fs/afs/misc.c
@@ -22,6 +22,7 @@ int afs_abort_to_error(u32 abort_code)
{
switch (abort_code) {
case 13: return -EACCES;
+ case 27: return -EFBIG;
case 30: return -EROFS;
case VSALVAGE: return -EIO;
case VNOVNODE: return -ENOENT;
diff --git a/fs/afs/mntpt.c b/fs/afs/mntpt.c
index 034fcfd4e33..a3684dcc76e 100644
--- a/fs/afs/mntpt.c
+++ b/fs/afs/mntpt.c
@@ -36,7 +36,7 @@ const struct inode_operations afs_mntpt_inode_operations = {
.lookup = afs_mntpt_lookup,
.follow_link = afs_mntpt_follow_link,
.readlink = page_readlink,
- .getattr = afs_inode_getattr,
+ .getattr = afs_getattr,
};
static LIST_HEAD(afs_vfsmounts);
@@ -58,7 +58,8 @@ int afs_mntpt_check_symlink(struct afs_vnode *vnode, struct key *key)
char *buf;
int ret;
- _enter("{%u,%u}", vnode->fid.vnode, vnode->fid.unique);
+ _enter("{%x:%u,%u}",
+ vnode->fid.vid, vnode->fid.vnode, vnode->fid.unique);
/* read the contents of the symlink into the pagecache */
page = read_mapping_page(AFS_VNODE_TO_I(vnode)->i_mapping, 0, &file);
diff --git a/fs/afs/proc.c b/fs/afs/proc.c
index d5601f617cd..13df512aea9 100644
--- a/fs/afs/proc.c
+++ b/fs/afs/proc.c
@@ -13,6 +13,7 @@
#include <linux/module.h>
#include <linux/proc_fs.h>
#include <linux/seq_file.h>
+#include <linux/sched.h>
#include <asm/uaccess.h>
#include "internal.h"
diff --git a/fs/afs/rxrpc.c b/fs/afs/rxrpc.c
index 222c1a3abbb..1b36f45076a 100644
--- a/fs/afs/rxrpc.c
+++ b/fs/afs/rxrpc.c
@@ -237,6 +237,70 @@ void afs_flat_call_destructor(struct afs_call *call)
}
/*
+ * attach the data from a bunch of pages on an inode to a call
+ */
+int afs_send_pages(struct afs_call *call, struct msghdr *msg, struct kvec *iov)
+{
+ struct page *pages[8];
+ unsigned count, n, loop, offset, to;
+ pgoff_t first = call->first, last = call->last;
+ int ret;
+
+ _enter("");
+
+ offset = call->first_offset;
+ call->first_offset = 0;
+
+ do {
+ _debug("attach %lx-%lx", first, last);
+
+ count = last - first + 1;
+ if (count > ARRAY_SIZE(pages))
+ count = ARRAY_SIZE(pages);
+ n = find_get_pages_contig(call->mapping, first, count, pages);
+ ASSERTCMP(n, ==, count);
+
+ loop = 0;
+ do {
+ msg->msg_flags = 0;
+ to = PAGE_SIZE;
+ if (first + loop >= last)
+ to = call->last_to;
+ else
+ msg->msg_flags = MSG_MORE;
+ iov->iov_base = kmap(pages[loop]) + offset;
+ iov->iov_len = to - offset;
+ offset = 0;
+
+ _debug("- range %u-%u%s",
+ offset, to, msg->msg_flags ? " [more]" : "");
+ msg->msg_iov = (struct iovec *) iov;
+ msg->msg_iovlen = 1;
+
+ /* have to change the state *before* sending the last
+ * packet as RxRPC might give us the reply before it
+ * returns from sending the request */
+ if (first + loop >= last)
+ call->state = AFS_CALL_AWAIT_REPLY;
+ ret = rxrpc_kernel_send_data(call->rxcall, msg,
+ to - offset);
+ kunmap(pages[loop]);
+ if (ret < 0)
+ break;
+ } while (++loop < count);
+ first += count;
+
+ for (loop = 0; loop < count; loop++)
+ put_page(pages[loop]);
+ if (ret < 0)
+ break;
+ } while (first <= last);
+
+ _leave(" = %d", ret);
+ return ret;
+}
+
+/*
* initiate a call
*/
int afs_make_call(struct in_addr *addr, struct afs_call *call, gfp_t gfp,
@@ -253,8 +317,9 @@ int afs_make_call(struct in_addr *addr, struct afs_call *call, gfp_t gfp,
ASSERT(call->type != NULL);
ASSERT(call->type->name != NULL);
- _debug("MAKE %p{%s} [%d]",
- call, call->type->name, atomic_read(&afs_outstanding_calls));
+ _debug("____MAKE %p{%s,%x} [%d]____",
+ call, call->type->name, key_serial(call->key),
+ atomic_read(&afs_outstanding_calls));
call->wait_mode = wait_mode;
INIT_WORK(&call->async_work, afs_process_async_call);
@@ -289,16 +354,23 @@ int afs_make_call(struct in_addr *addr, struct afs_call *call, gfp_t gfp,
msg.msg_iovlen = 1;
msg.msg_control = NULL;
msg.msg_controllen = 0;
- msg.msg_flags = 0;
+ msg.msg_flags = (call->send_pages ? MSG_MORE : 0);
/* have to change the state *before* sending the last packet as RxRPC
* might give us the reply before it returns from sending the
* request */
- call->state = AFS_CALL_AWAIT_REPLY;
+ if (!call->send_pages)
+ call->state = AFS_CALL_AWAIT_REPLY;
ret = rxrpc_kernel_send_data(rxcall, &msg, call->request_size);
if (ret < 0)
goto error_do_abort;
+ if (call->send_pages) {
+ ret = afs_send_pages(call, &msg, iov);
+ if (ret < 0)
+ goto error_do_abort;
+ }
+
/* at this point, an async call may no longer exist as it may have
* already completed */
return wait_mode->wait(call);
diff --git a/fs/afs/security.c b/fs/afs/security.c
index f9f424d8045..566fe712c68 100644
--- a/fs/afs/security.c
+++ b/fs/afs/security.c
@@ -13,6 +13,7 @@
#include <linux/slab.h>
#include <linux/fs.h>
#include <linux/ctype.h>
+#include <linux/sched.h>
#include <keys/rxrpc-type.h>
#include "internal.h"
@@ -109,7 +110,7 @@ void afs_clear_permits(struct afs_vnode *vnode)
{
struct afs_permits *permits;
- _enter("{%x}", vnode->fid.vnode);
+ _enter("{%x:%u}", vnode->fid.vid, vnode->fid.vnode);
mutex_lock(&vnode->permits_lock);
permits = vnode->permits;
@@ -132,7 +133,8 @@ void afs_cache_permit(struct afs_vnode *vnode, struct key *key, long acl_order)
struct afs_vnode *auth_vnode;
int count, loop;
- _enter("{%x},%x,%lx", vnode->fid.vnode, key_serial(key), acl_order);
+ _enter("{%x:%u},%x,%lx",
+ vnode->fid.vid, vnode->fid.vnode, key_serial(key), acl_order);
auth_vnode = afs_get_auth_inode(vnode, key);
if (IS_ERR(auth_vnode)) {
@@ -220,7 +222,8 @@ static int afs_check_permit(struct afs_vnode *vnode, struct key *key,
bool valid;
int loop, ret;
- _enter("");
+ _enter("{%x:%u},%x",
+ vnode->fid.vid, vnode->fid.vnode, key_serial(key));
auth_vnode = afs_get_auth_inode(vnode, key);
if (IS_ERR(auth_vnode)) {
@@ -268,9 +271,9 @@ static int afs_check_permit(struct afs_vnode *vnode, struct key *key,
_leave(" = %d", ret);
return ret;
}
+ *_access = vnode->status.caller_access;
}
- *_access = vnode->status.caller_access;
iput(&auth_vnode->vfs_inode);
_leave(" = 0 [access %x]", *_access);
return 0;
@@ -288,7 +291,7 @@ int afs_permission(struct inode *inode, int mask, struct nameidata *nd)
struct key *key;
int ret;
- _enter("{{%x:%x},%lx},%x,",
+ _enter("{{%x:%u},%lx},%x,",
vnode->fid.vid, vnode->fid.vnode, vnode->flags, mask);
key = afs_request_key(vnode->volume->cell);
diff --git a/fs/afs/server.c b/fs/afs/server.c
index 96bb23b476a..231ae415027 100644
--- a/fs/afs/server.c
+++ b/fs/afs/server.c
@@ -252,6 +252,9 @@ static void afs_destroy_server(struct afs_server *server)
{
_enter("%p", server);
+ ASSERTIF(server->cb_break_head != server->cb_break_tail,
+ delayed_work_pending(&server->cb_break_work));
+
ASSERTCMP(server->fs_vnodes.rb_node, ==, NULL);
ASSERTCMP(server->cb_promises.rb_node, ==, NULL);
ASSERTCMP(server->cb_break_head, ==, server->cb_break_tail);
diff --git a/fs/afs/super.c b/fs/afs/super.c
index 7030d76155f..2e8496ba120 100644
--- a/fs/afs/super.c
+++ b/fs/afs/super.c
@@ -21,22 +21,21 @@
#include <linux/fs.h>
#include <linux/pagemap.h>
#include <linux/parser.h>
+#include <linux/statfs.h>
+#include <linux/sched.h>
#include "internal.h"
#define AFS_FS_MAGIC 0x6B414653 /* 'kAFS' */
static void afs_i_init_once(void *foo, struct kmem_cache *cachep,
unsigned long flags);
-
static int afs_get_sb(struct file_system_type *fs_type,
int flags, const char *dev_name,
void *data, struct vfsmount *mnt);
-
static struct inode *afs_alloc_inode(struct super_block *sb);
-
static void afs_put_super(struct super_block *sb);
-
static void afs_destroy_inode(struct inode *inode);
+static int afs_statfs(struct dentry *dentry, struct kstatfs *buf);
struct file_system_type afs_fs_type = {
.owner = THIS_MODULE,
@@ -47,9 +46,9 @@ struct file_system_type afs_fs_type = {
};
static const struct super_operations afs_super_ops = {
- .statfs = simple_statfs,
+ .statfs = afs_statfs,
.alloc_inode = afs_alloc_inode,
- .drop_inode = generic_delete_inode,
+ .write_inode = afs_write_inode,
.destroy_inode = afs_destroy_inode,
.clear_inode = afs_clear_inode,
.umount_begin = afs_umount_begin,
@@ -66,7 +65,7 @@ enum {
afs_opt_vol,
};
-static const match_table_t afs_options_list = {
+static match_table_t afs_options_list = {
{ afs_opt_cell, "cell=%s" },
{ afs_opt_rwpath, "rwpath" },
{ afs_opt_vol, "vol=%s" },
@@ -453,15 +452,15 @@ static void afs_i_init_once(void *_vnode, struct kmem_cache *cachep,
{
struct afs_vnode *vnode = _vnode;
- if (flags & SLAB_CTOR_CONSTRUCTOR) {
- memset(vnode, 0, sizeof(*vnode));
- inode_init_once(&vnode->vfs_inode);
- init_waitqueue_head(&vnode->update_waitq);
- mutex_init(&vnode->permits_lock);
- mutex_init(&vnode->validate_lock);
- spin_lock_init(&vnode->lock);
- INIT_WORK(&vnode->cb_broken_work, afs_broken_callback_work);
- }
+ memset(vnode, 0, sizeof(*vnode));
+ inode_init_once(&vnode->vfs_inode);
+ init_waitqueue_head(&vnode->update_waitq);
+ mutex_init(&vnode->permits_lock);
+ mutex_init(&vnode->validate_lock);
+ spin_lock_init(&vnode->writeback_lock);
+ spin_lock_init(&vnode->lock);
+ INIT_LIST_HEAD(&vnode->writebacks);
+ INIT_WORK(&vnode->cb_broken_work, afs_broken_callback_work);
}
/*
@@ -485,6 +484,7 @@ static struct inode *afs_alloc_inode(struct super_block *sb)
vnode->flags = 1 << AFS_VNODE_UNSET;
vnode->cb_promised = false;
+ _leave(" = %p", &vnode->vfs_inode);
return &vnode->vfs_inode;
}
@@ -495,7 +495,7 @@ static void afs_destroy_inode(struct inode *inode)
{
struct afs_vnode *vnode = AFS_FS_I(inode);
- _enter("{%lu}", inode->i_ino);
+ _enter("%p{%x:%u}", inode, vnode->fid.vid, vnode->fid.vnode);
_debug("DESTROY INODE %p", inode);
@@ -504,3 +504,36 @@ static void afs_destroy_inode(struct inode *inode)
kmem_cache_free(afs_inode_cachep, vnode);
atomic_dec(&afs_count_active_inodes);
}
+
+/*
+ * return information about an AFS volume
+ */
+static int afs_statfs(struct dentry *dentry, struct kstatfs *buf)
+{
+ struct afs_volume_status vs;
+ struct afs_vnode *vnode = AFS_FS_I(dentry->d_inode);
+ struct key *key;
+ int ret;
+
+ key = afs_request_key(vnode->volume->cell);
+ if (IS_ERR(key))
+ return PTR_ERR(key);
+
+ ret = afs_vnode_get_volume_status(vnode, key, &vs);
+ key_put(key);
+ if (ret < 0) {
+ _leave(" = %d", ret);
+ return ret;
+ }
+
+ buf->f_type = dentry->d_sb->s_magic;
+ buf->f_bsize = AFS_BLOCK_SIZE;
+ buf->f_namelen = AFSNAMEMAX - 1;
+
+ if (vs.max_quota == 0)
+ buf->f_blocks = vs.part_max_blocks;
+ else
+ buf->f_blocks = vs.max_quota;
+ buf->f_bavail = buf->f_bfree = buf->f_blocks - vs.blocks_in_use;
+ return 0;
+}
diff --git a/fs/afs/vlocation.c b/fs/afs/vlocation.c
index 3370cdb7256..09e3ad0fc7c 100644
--- a/fs/afs/vlocation.c
+++ b/fs/afs/vlocation.c
@@ -12,6 +12,7 @@
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/init.h>
+#include <linux/sched.h>
#include "internal.h"
unsigned afs_vlocation_timeout = 10; /* volume location timeout in seconds */
diff --git a/fs/afs/vnode.c b/fs/afs/vnode.c
index a1904ab8426..232c55dc245 100644
--- a/fs/afs/vnode.c
+++ b/fs/afs/vnode.c
@@ -14,6 +14,7 @@
#include <linux/init.h>
#include <linux/slab.h>
#include <linux/fs.h>
+#include <linux/sched.h>
#include "internal.h"
#if 0
@@ -175,24 +176,33 @@ static void afs_vnode_deleted_remotely(struct afs_vnode *vnode)
{
struct afs_server *server;
+ _enter("{%p}", vnode->server);
+
set_bit(AFS_VNODE_DELETED, &vnode->flags);
server = vnode->server;
- if (vnode->cb_promised) {
- spin_lock(&server->cb_lock);
+ if (server) {
if (vnode->cb_promised) {
- rb_erase(&vnode->cb_promise, &server->cb_promises);
- vnode->cb_promised = false;
+ spin_lock(&server->cb_lock);
+ if (vnode->cb_promised) {
+ rb_erase(&vnode->cb_promise,
+ &server->cb_promises);
+ vnode->cb_promised = false;
+ }
+ spin_unlock(&server->cb_lock);
}
- spin_unlock(&server->cb_lock);
- }
- spin_lock(&vnode->server->fs_lock);
- rb_erase(&vnode->server_rb, &vnode->server->fs_vnodes);
- spin_unlock(&vnode->server->fs_lock);
+ spin_lock(&server->fs_lock);
+ rb_erase(&vnode->server_rb, &server->fs_vnodes);
+ spin_unlock(&server->fs_lock);
- vnode->server = NULL;
- afs_put_server(server);
+ vnode->server = NULL;
+ afs_put_server(server);
+ } else {
+ ASSERT(!vnode->cb_promised);
+ }
+
+ _leave("");
}
/*
@@ -225,7 +235,7 @@ void afs_vnode_finalise_status_update(struct afs_vnode *vnode,
*/
static void afs_vnode_status_update_failed(struct afs_vnode *vnode, int ret)
{
- _enter("%p,%d", vnode, ret);
+ _enter("{%x:%u},%d", vnode->fid.vid, vnode->fid.vnode, ret);
spin_lock(&vnode->lock);
@@ -261,7 +271,7 @@ int afs_vnode_fetch_status(struct afs_vnode *vnode,
DECLARE_WAITQUEUE(myself, current);
- _enter("%s,{%u,%u,%u}",
+ _enter("%s,{%x:%u.%u}",
vnode->volume->vlocation->vldb.name,
vnode->fid.vid, vnode->fid.vnode, vnode->fid.unique);
@@ -389,7 +399,7 @@ int afs_vnode_fetch_data(struct afs_vnode *vnode, struct key *key,
struct afs_server *server;
int ret;
- _enter("%s{%u,%u,%u},%x,,,",
+ _enter("%s{%x:%u.%u},%x,,,",
vnode->volume->vlocation->vldb.name,
vnode->fid.vid,
vnode->fid.vnode,
@@ -446,7 +456,7 @@ int afs_vnode_create(struct afs_vnode *vnode, struct key *key,
struct afs_server *server;
int ret;
- _enter("%s{%u,%u,%u},%x,%s,,",
+ _enter("%s{%x:%u.%u},%x,%s,,",
vnode->volume->vlocation->vldb.name,
vnode->fid.vid,
vnode->fid.vnode,
@@ -502,7 +512,7 @@ int afs_vnode_remove(struct afs_vnode *vnode, struct key *key, const char *name,
struct afs_server *server;
int ret;
- _enter("%s{%u,%u,%u},%x,%s",
+ _enter("%s{%x:%u.%u},%x,%s",
vnode->volume->vlocation->vldb.name,
vnode->fid.vid,
vnode->fid.vnode,
@@ -557,7 +567,7 @@ extern int afs_vnode_link(struct afs_vnode *dvnode, struct afs_vnode *vnode,
struct afs_server *server;
int ret;
- _enter("%s{%u,%u,%u},%s{%u,%u,%u},%x,%s",
+ _enter("%s{%x:%u.%u},%s{%x:%u.%u},%x,%s",
dvnode->volume->vlocation->vldb.name,
dvnode->fid.vid,
dvnode->fid.vnode,
@@ -628,7 +638,7 @@ int afs_vnode_symlink(struct afs_vnode *vnode, struct key *key,
struct afs_server *server;
int ret;
- _enter("%s{%u,%u,%u},%x,%s,%s,,,",
+ _enter("%s{%x:%u.%u},%x,%s,%s,,,",
vnode->volume->vlocation->vldb.name,
vnode->fid.vid,
vnode->fid.vnode,
@@ -687,7 +697,7 @@ int afs_vnode_rename(struct afs_vnode *orig_dvnode,
struct afs_server *server;
int ret;
- _enter("%s{%u,%u,%u},%s{%u,%u,%u},%x,%s,%s",
+ _enter("%s{%x:%u.%u},%s{%u,%u,%u},%x,%s,%s",
orig_dvnode->volume->vlocation->vldb.name,
orig_dvnode->fid.vid,
orig_dvnode->fid.vnode,
@@ -753,3 +763,162 @@ no_server:
_leave(" = %ld [cnt %d]", PTR_ERR(server), orig_dvnode->update_cnt);
return PTR_ERR(server);
}
+
+/*
+ * write to a file
+ */
+int afs_vnode_store_data(struct afs_writeback *wb, pgoff_t first, pgoff_t last,
+ unsigned offset, unsigned to)
+{
+ struct afs_server *server;
+ struct afs_vnode *vnode = wb->vnode;
+ int ret;
+
+ _enter("%s{%x:%u.%u},%x,%lx,%lx,%x,%x",
+ vnode->volume->vlocation->vldb.name,
+ vnode->fid.vid,
+ vnode->fid.vnode,
+ vnode->fid.unique,
+ key_serial(wb->key),
+ first, last, offset, to);
+
+ /* this op will fetch the status */
+ spin_lock(&vnode->lock);
+ vnode->update_cnt++;
+ spin_unlock(&vnode->lock);
+
+ do {
+ /* pick a server to query */
+ server = afs_volume_pick_fileserver(vnode);
+ if (IS_ERR(server))
+ goto no_server;
+
+ _debug("USING SERVER: %08x\n", ntohl(server->addr.s_addr));
+
+ ret = afs_fs_store_data(server, wb, first, last, offset, to,
+ &afs_sync_call);
+
+ } while (!afs_volume_release_fileserver(vnode, server, ret));
+
+ /* adjust the flags */
+ if (ret == 0) {
+ afs_vnode_finalise_status_update(vnode, server);
+ afs_put_server(server);
+ } else {
+ afs_vnode_status_update_failed(vnode, ret);
+ }
+
+ _leave(" = %d", ret);
+ return ret;
+
+no_server:
+ spin_lock(&vnode->lock);
+ vnode->update_cnt--;
+ ASSERTCMP(vnode->update_cnt, >=, 0);
+ spin_unlock(&vnode->lock);
+ return PTR_ERR(server);
+}
+
+/*
+ * set the attributes on a file
+ */
+int afs_vnode_setattr(struct afs_vnode *vnode, struct key *key,
+ struct iattr *attr)
+{
+ struct afs_server *server;
+ int ret;
+
+ _enter("%s{%x:%u.%u},%x",
+ vnode->volume->vlocation->vldb.name,
+ vnode->fid.vid,
+ vnode->fid.vnode,
+ vnode->fid.unique,
+ key_serial(key));
+
+ /* this op will fetch the status */
+ spin_lock(&vnode->lock);
+ vnode->update_cnt++;
+ spin_unlock(&vnode->lock);
+
+ do {
+ /* pick a server to query */
+ server = afs_volume_pick_fileserver(vnode);
+ if (IS_ERR(server))
+ goto no_server;
+
+ _debug("USING SERVER: %08x\n", ntohl(server->addr.s_addr));
+
+ ret = afs_fs_setattr(server, key, vnode, attr, &afs_sync_call);
+
+ } while (!afs_volume_release_fileserver(vnode, server, ret));
+
+ /* adjust the flags */
+ if (ret == 0) {
+ afs_vnode_finalise_status_update(vnode, server);
+ afs_put_server(server);
+ } else {
+ afs_vnode_status_update_failed(vnode, ret);
+ }
+
+ _leave(" = %d", ret);
+ return ret;
+
+no_server:
+ spin_lock(&vnode->lock);
+ vnode->update_cnt--;
+ ASSERTCMP(vnode->update_cnt, >=, 0);
+ spin_unlock(&vnode->lock);
+ return PTR_ERR(server);
+}
+
+/*
+ * get the status of a volume
+ */
+int afs_vnode_get_volume_status(struct afs_vnode *vnode, struct key *key,
+ struct afs_volume_status *vs)
+{
+ struct afs_server *server;
+ int ret;
+
+ _enter("%s{%x:%u.%u},%x,",
+ vnode->volume->vlocation->vldb.name,
+ vnode->fid.vid,
+ vnode->fid.vnode,
+ vnode->fid.unique,
+ key_serial(key));
+
+ /* this op will fetch the status */
+ spin_lock(&vnode->lock);
+ vnode->update_cnt++;
+ spin_unlock(&vnode->lock);
+
+ do {
+ /* pick a server to query */
+ server = afs_volume_pick_fileserver(vnode);
+ if (IS_ERR(server))
+ goto no_server;
+
+ _debug("USING SERVER: %08x\n", ntohl(server->addr.s_addr));
+
+ ret = afs_fs_get_volume_status(server, key, vnode, vs, &afs_sync_call);
+
+ } while (!afs_volume_release_fileserver(vnode, server, ret));
+
+ /* adjust the flags */
+ if (ret == 0) {
+ afs_vnode_finalise_status_update(vnode, server);
+ afs_put_server(server);
+ } else {
+ afs_vnode_status_update_failed(vnode, ret);
+ }
+
+ _leave(" = %d", ret);
+ return ret;
+
+no_server:
+ spin_lock(&vnode->lock);
+ vnode->update_cnt--;
+ ASSERTCMP(vnode->update_cnt, >=, 0);
+ spin_unlock(&vnode->lock);
+ return PTR_ERR(server);
+}
diff --git a/fs/afs/volume.c b/fs/afs/volume.c
index dd160cada45..8bab0e3437f 100644
--- a/fs/afs/volume.c
+++ b/fs/afs/volume.c
@@ -15,6 +15,7 @@
#include <linux/slab.h>
#include <linux/fs.h>
#include <linux/pagemap.h>
+#include <linux/sched.h>
#include "internal.h"
static const char *afs_voltypes[] = { "R/W", "R/O", "BAK" };
diff --git a/fs/afs/write.c b/fs/afs/write.c
new file mode 100644
index 00000000000..a03b92a0fe1
--- /dev/null
+++ b/fs/afs/write.c
@@ -0,0 +1,827 @@
+/* handling of writes to regular files and writing back to the server
+ *
+ * Copyright (C) 2007 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#include <linux/slab.h>
+#include <linux/fs.h>
+#include <linux/pagemap.h>
+#include <linux/writeback.h>
+#include <linux/pagevec.h>
+#include "internal.h"
+
+static int afs_write_back_from_locked_page(struct afs_writeback *wb,
+ struct page *page);
+
+/*
+ * mark a page as having been made dirty and thus needing writeback
+ */
+int afs_set_page_dirty(struct page *page)
+{
+ _enter("");
+ return __set_page_dirty_nobuffers(page);
+}
+
+/*
+ * unlink a writeback record because its usage has reached zero
+ * - must be called with the wb->vnode->writeback_lock held
+ */
+static void afs_unlink_writeback(struct afs_writeback *wb)
+{
+ struct afs_writeback *front;
+ struct afs_vnode *vnode = wb->vnode;
+
+ list_del_init(&wb->link);
+ if (!list_empty(&vnode->writebacks)) {
+ /* if an fsync rises to the front of the queue then wake it
+ * up */
+ front = list_entry(vnode->writebacks.next,
+ struct afs_writeback, link);
+ if (front->state == AFS_WBACK_SYNCING) {
+ _debug("wake up sync");
+ front->state = AFS_WBACK_COMPLETE;
+ wake_up(&front->waitq);
+ }
+ }
+}
+
+/*
+ * free a writeback record
+ */
+static void afs_free_writeback(struct afs_writeback *wb)
+{
+ _enter("");
+ key_put(wb->key);
+ kfree(wb);
+}
+
+/*
+ * dispose of a reference to a writeback record
+ */
+void afs_put_writeback(struct afs_writeback *wb)
+{
+ struct afs_vnode *vnode = wb->vnode;
+
+ _enter("{%d}", wb->usage);
+
+ spin_lock(&vnode->writeback_lock);
+ if (--wb->usage == 0)
+ afs_unlink_writeback(wb);
+ else
+ wb = NULL;
+ spin_unlock(&vnode->writeback_lock);
+ if (wb)
+ afs_free_writeback(wb);
+}
+
+/*
+ * partly or wholly fill a page that's under preparation for writing
+ */
+static int afs_fill_page(struct afs_vnode *vnode, struct key *key,
+ unsigned start, unsigned len, struct page *page)
+{
+ int ret;
+
+ _enter(",,%u,%u", start, len);
+
+ ASSERTCMP(start + len, <=, PAGE_SIZE);
+
+ ret = afs_vnode_fetch_data(vnode, key, start, len, page);
+ 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 a page for being written to
+ */
+static int afs_prepare_page(struct afs_vnode *vnode, struct page *page,
+ struct key *key, unsigned offset, unsigned to)
+{
+ unsigned eof, tail, start, stop, len;
+ loff_t i_size, pos;
+ void *p;
+ int ret;
+
+ _enter("");
+
+ if (offset == 0 && to == PAGE_SIZE)
+ return 0;
+
+ p = kmap_atomic(page, KM_USER0);
+
+ i_size = i_size_read(&vnode->vfs_inode);
+ pos = (loff_t) page->index << PAGE_SHIFT;
+ if (pos >= i_size) {
+ /* partial write, page beyond EOF */
+ _debug("beyond");
+ if (offset > 0)
+ memset(p, 0, offset);
+ if (to < PAGE_SIZE)
+ memset(p + to, 0, PAGE_SIZE - to);
+ kunmap_atomic(p, KM_USER0);
+ return 0;
+ }
+
+ if (i_size - pos >= PAGE_SIZE) {
+ /* partial write, page entirely before EOF */
+ _debug("before");
+ tail = eof = PAGE_SIZE;
+ } else {
+ /* partial write, page overlaps EOF */
+ eof = i_size - pos;
+ _debug("overlap %u", eof);
+ tail = max(eof, to);
+ if (tail < PAGE_SIZE)
+ memset(p + tail, 0, PAGE_SIZE - tail);
+ if (offset > eof)
+ memset(p + eof, 0, PAGE_SIZE - eof);
+ }
+
+ kunmap_atomic(p, KM_USER0);
+
+ ret = 0;
+ if (offset > 0 || eof > to) {
+ /* need to fill one or two bits that aren't going to be written
+ * (cover both fillers in one read if there are two) */
+ start = (offset > 0) ? 0 : to;
+ stop = (eof > to) ? eof : offset;
+ len = stop - start;
+ _debug("wr=%u-%u av=0-%u rd=%u@%u",
+ offset, to, eof, start, len);
+ ret = afs_fill_page(vnode, key, start, len, page);
+ }
+
+ _leave(" = %d", ret);
+ return ret;
+}
+
+/*
+ * prepare to perform part of a write to a page
+ * - the caller holds the page locked, preventing it from being written out or
+ * modified by anyone else
+ */
+int afs_prepare_write(struct file *file, struct page *page,
+ unsigned offset, unsigned to)
+{
+ struct afs_writeback *candidate, *wb;
+ struct afs_vnode *vnode = AFS_FS_I(file->f_dentry->d_inode);
+ struct key *key = file->private_data;
+ pgoff_t index;
+ int ret;
+
+ _enter("{%x:%u},{%lx},%u,%u",
+ vnode->fid.vid, vnode->fid.vnode, page->index, offset, to);
+
+ candidate = kzalloc(sizeof(*candidate), GFP_KERNEL);
+ if (!candidate)
+ return -ENOMEM;
+ candidate->vnode = vnode;
+ candidate->first = candidate->last = page->index;
+ candidate->offset_first = offset;
+ candidate->to_last = to;
+ candidate->usage = 1;
+ candidate->state = AFS_WBACK_PENDING;
+ init_waitqueue_head(&candidate->waitq);
+
+ if (!PageUptodate(page)) {
+ _debug("not up to date");
+ ret = afs_prepare_page(vnode, page, key, offset, to);
+ if (ret < 0) {
+ kfree(candidate);
+ _leave(" = %d [prep]", ret);
+ return ret;
+ }
+ }
+
+try_again:
+ index = page->index;
+ spin_lock(&vnode->writeback_lock);
+
+ /* see if this page is already pending a writeback under a suitable key
+ * - if so we can just join onto that one */
+ wb = (struct afs_writeback *) page_private(page);
+ if (wb) {
+ if (wb->key == key && wb->state == AFS_WBACK_PENDING)
+ goto subsume_in_current_wb;
+ goto flush_conflicting_wb;
+ }
+
+ if (index > 0) {
+ /* see if we can find an already pending writeback that we can
+ * append this page to */
+ list_for_each_entry(wb, &vnode->writebacks, link) {
+ if (wb->last == index - 1 && wb->key == key &&
+ wb->state == AFS_WBACK_PENDING)
+ goto append_to_previous_wb;
+ }
+ }
+
+ list_add_tail(&candidate->link, &vnode->writebacks);
+ candidate->key = key_get(key);
+ spin_unlock(&vnode->writeback_lock);
+ SetPagePrivate(page);
+ set_page_private(page, (unsigned long) candidate);
+ _leave(" = 0 [new]");
+ return 0;
+
+subsume_in_current_wb:
+ _debug("subsume");
+ ASSERTRANGE(wb->first, <=, index, <=, wb->last);
+ if (index == wb->first && offset < wb->offset_first)
+ wb->offset_first = offset;
+ if (index == wb->last && to > wb->to_last)
+ wb->to_last = to;
+ spin_unlock(&vnode->writeback_lock);
+ kfree(candidate);
+ _leave(" = 0 [sub]");
+ return 0;
+
+append_to_previous_wb:
+ _debug("append into %lx-%lx", wb->first, wb->last);
+ wb->usage++;
+ wb->last++;
+ wb->to_last = to;
+ spin_unlock(&vnode->writeback_lock);
+ SetPagePrivate(page);
+ set_page_private(page, (unsigned long) wb);
+ kfree(candidate);
+ _leave(" = 0 [app]");
+ return 0;
+
+ /* the page is currently bound to another context, so if it's dirty we
+ * need to flush it before we can use the new context */
+flush_conflicting_wb:
+ _debug("flush conflict");
+ if (wb->state == AFS_WBACK_PENDING)
+ wb->state = AFS_WBACK_CONFLICTING;
+ spin_unlock(&vnode->writeback_lock);
+ if (PageDirty(page)) {
+ ret = afs_write_back_from_locked_page(wb, page);
+ if (ret < 0) {
+ afs_put_writeback(candidate);
+ _leave(" = %d", ret);
+ return ret;
+ }
+ }
+
+ /* the page holds a ref on the writeback record */
+ afs_put_writeback(wb);
+ set_page_private(page, 0);
+ ClearPagePrivate(page);
+ goto try_again;
+}
+
+/*
+ * finalise part of a write to a page
+ */
+int afs_commit_write(struct file *file, struct page *page,
+ unsigned offset, unsigned to)
+{
+ struct afs_vnode *vnode = AFS_FS_I(file->f_dentry->d_inode);
+ loff_t i_size, maybe_i_size;
+
+ _enter("{%x:%u},{%lx},%u,%u",
+ vnode->fid.vid, vnode->fid.vnode, page->index, offset, to);
+
+ maybe_i_size = (loff_t) page->index << PAGE_SHIFT;
+ maybe_i_size += to;
+
+ i_size = i_size_read(&vnode->vfs_inode);
+ if (maybe_i_size > i_size) {
+ spin_lock(&vnode->writeback_lock);
+ i_size = i_size_read(&vnode->vfs_inode);
+ if (maybe_i_size > i_size)
+ i_size_write(&vnode->vfs_inode, maybe_i_size);
+ spin_unlock(&vnode->writeback_lock);
+ }
+
+ SetPageUptodate(page);
+ set_page_dirty(page);
+ if (PageDirty(page))
+ _debug("dirtied");
+
+ return 0;
+}
+
+/*
+ * kill all the pages in the given range
+ */
+static void afs_kill_pages(struct afs_vnode *vnode, bool error,
+ pgoff_t first, pgoff_t last)
+{
+ struct pagevec pv;
+ unsigned count, loop;
+
+ _enter("{%x:%u},%lx-%lx",
+ vnode->fid.vid, vnode->fid.vnode, first, last);
+
+ pagevec_init(&pv, 0);
+
+ do {
+ _debug("kill %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++) {
+ ClearPageUptodate(pv.pages[loop]);
+ if (error)
+ SetPageError(pv.pages[loop]);
+ end_page_writeback(pv.pages[loop]);
+ }
+
+ __pagevec_release(&pv);
+ } while (first < last);
+
+ _leave("");
+}
+
+/*
+ * synchronously write back the locked page and any subsequent non-locked dirty
+ * pages also covered by the same writeback record
+ */
+static int afs_write_back_from_locked_page(struct afs_writeback *wb,
+ struct page *primary_page)
+{
+ struct page *pages[8], *page;
+ unsigned long count;
+ unsigned n, offset, to;
+ pgoff_t start, first, last;
+ int loop, ret;
+
+ _enter(",%lx", primary_page->index);
+
+ count = 1;
+ if (!clear_page_dirty_for_io(primary_page))
+ BUG();
+ if (test_set_page_writeback(primary_page))
+ BUG();
+
+ /* find all consecutive lockable dirty pages, 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;
+ if (start >= wb->last)
+ goto no_more;
+ start++;
+ do {
+ _debug("more %lx [%lx]", start, count);
+ n = wb->last - start + 1;
+ if (n > ARRAY_SIZE(pages))
+ n = ARRAY_SIZE(pages);
+ n = find_get_pages_contig(wb->vnode->vfs_inode.i_mapping,
+ start, n, 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;
+ }
+
+ for (loop = 0; loop < n; loop++) {
+ page = pages[loop];
+ if (page->index > wb->last)
+ break;
+ if (TestSetPageLocked(page))
+ break;
+ if (!PageDirty(page) ||
+ page_private(page) != (unsigned long) wb) {
+ unlock_page(page);
+ break;
+ }
+ if (!clear_page_dirty_for_io(page))
+ BUG();
+ if (test_set_page_writeback(page))
+ BUG();
+ 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 <= wb->last && count < 65536);
+
+no_more:
+ /* we now have a contiguous set of dirty pages, each with writeback set
+ * and the dirty mark cleared; the first page is locked and must remain
+ * so, all the rest are unlocked */
+ first = primary_page->index;
+ last = first + count - 1;
+
+ offset = (first == wb->first) ? wb->offset_first : 0;
+ to = (last == wb->last) ? wb->to_last : PAGE_SIZE;
+
+ _debug("write back %lx[%u..] to %lx[..%u]", first, offset, last, to);
+
+ ret = afs_vnode_store_data(wb, first, last, offset, to);
+ if (ret < 0) {
+ switch (ret) {
+ case -EDQUOT:
+ case -ENOSPC:
+ set_bit(AS_ENOSPC,
+ &wb->vnode->vfs_inode.i_mapping->flags);
+ break;
+ case -EROFS:
+ case -EIO:
+ case -EREMOTEIO:
+ case -EFBIG:
+ case -ENOENT:
+ case -ENOMEDIUM:
+ case -ENXIO:
+ afs_kill_pages(wb->vnode, true, first, last);
+ set_bit(AS_EIO, &wb->vnode->vfs_inode.i_mapping->flags);
+ break;
+ case -EACCES:
+ case -EPERM:
+ case -ENOKEY:
+ case -EKEYEXPIRED:
+ case -EKEYREJECTED:
+ case -EKEYREVOKED:
+ afs_kill_pages(wb->vnode, false, first, last);
+ break;
+ default:
+ break;
+ }
+ } else {
+ ret = count;
+ }
+
+ _leave(" = %d", ret);
+ return ret;
+}
+
+/*
+ * write a page back to the server
+ * - the caller locked the page for us
+ */
+int afs_writepage(struct page *page, struct writeback_control *wbc)
+{
+ struct backing_dev_info *bdi = page->mapping->backing_dev_info;
+ struct afs_writeback *wb;
+ int ret;
+
+ _enter("{%lx},", page->index);
+
+ wb = (struct afs_writeback *) page_private(page);
+ ASSERT(wb != NULL);
+
+ ret = afs_write_back_from_locked_page(wb, page);
+ unlock_page(page);
+ if (ret < 0) {
+ _leave(" = %d", ret);
+ return 0;
+ }
+
+ wbc->nr_to_write -= ret;
+ if (wbc->nonblocking && bdi_write_congested(bdi))
+ wbc->encountered_congestion = 1;
+
+ _leave(" = 0");
+ return 0;
+}
+
+/*
+ * write a region of pages back to the server
+ */
+int afs_writepages_region(struct address_space *mapping,
+ struct writeback_control *wbc,
+ pgoff_t index, pgoff_t end, pgoff_t *_next)
+{
+ struct backing_dev_info *bdi = mapping->backing_dev_info;
+ struct afs_writeback *wb;
+ struct page *page;
+ int ret, n;
+
+ _enter(",,%lx,%lx,", index, end);
+
+ do {
+ n = find_get_pages_tag(mapping, &index, PAGECACHE_TAG_DIRTY,
+ 1, &page);
+ if (!n)
+ break;
+
+ _debug("wback %lx", page->index);
+
+ if (page->index > end) {
+ *_next = index;
+ page_cache_release(page);
+ _leave(" = 0 [%lx]", *_next);
+ return 0;
+ }
+
+ /* at this point we hold neither mapping->tree_lock nor lock on
+ * the page itself: the page may be truncated or invalidated
+ * (changing page->mapping to NULL), or even swizzled back from
+ * swapper_space to tmpfs file mapping
+ */
+ lock_page(page);
+
+ if (page->mapping != mapping) {
+ unlock_page(page);
+ page_cache_release(page);
+ continue;
+ }
+
+ if (wbc->sync_mode != WB_SYNC_NONE)
+ wait_on_page_writeback(page);
+
+ if (PageWriteback(page) || !PageDirty(page)) {
+ unlock_page(page);
+ continue;
+ }
+
+ wb = (struct afs_writeback *) page_private(page);
+ ASSERT(wb != NULL);
+
+ spin_lock(&wb->vnode->writeback_lock);
+ wb->state = AFS_WBACK_WRITING;
+ spin_unlock(&wb->vnode->writeback_lock);
+
+ ret = afs_write_back_from_locked_page(wb, page);
+ unlock_page(page);
+ page_cache_release(page);
+ if (ret < 0) {
+ _leave(" = %d", ret);
+ return ret;
+ }
+
+ wbc->nr_to_write -= ret;
+
+ if (wbc->nonblocking && bdi_write_congested(bdi)) {
+ wbc->encountered_congestion = 1;
+ break;
+ }
+
+ cond_resched();
+ } while (index < end && wbc->nr_to_write > 0);
+
+ *_next = index;
+ _leave(" = 0 [%lx]", *_next);
+ return 0;
+}
+
+/*
+ * write some of the pending data back to the server
+ */
+int afs_writepages(struct address_space *mapping,
+ struct writeback_control *wbc)
+{
+ struct backing_dev_info *bdi = mapping->backing_dev_info;
+ pgoff_t start, end, next;
+ int ret;
+
+ _enter("");
+
+ if (wbc->nonblocking && bdi_write_congested(bdi)) {
+ wbc->encountered_congestion = 1;
+ _leave(" = 0 [congest]");
+ return 0;
+ }
+
+ if (wbc->range_cyclic) {
+ start = mapping->writeback_index;
+ end = -1;
+ ret = afs_writepages_region(mapping, wbc, start, end, &next);
+ if (start > 0 && wbc->nr_to_write > 0 && ret == 0 &&
+ !(wbc->nonblocking && wbc->encountered_congestion))
+ ret = afs_writepages_region(mapping, wbc, 0, start,
+ &next);
+ mapping->writeback_index = next;
+ } else if (wbc->range_start == 0 && wbc->range_end == LLONG_MAX) {
+ end = (pgoff_t)(LLONG_MAX >> PAGE_CACHE_SHIFT);
+ ret = afs_writepages_region(mapping, wbc, 0, end, &next);
+ if (wbc->nr_to_write > 0)
+ mapping->writeback_index = next;
+ } else {
+ start = wbc->range_start >> PAGE_CACHE_SHIFT;
+ end = wbc->range_end >> PAGE_CACHE_SHIFT;
+ ret = afs_writepages_region(mapping, wbc, start, end, &next);
+ }
+
+ _leave(" = %d", ret);
+ return ret;
+}
+
+/*
+ * write an inode back
+ */
+int afs_write_inode(struct inode *inode, int sync)
+{
+ struct afs_vnode *vnode = AFS_FS_I(inode);
+ int ret;
+
+ _enter("{%x:%u},", vnode->fid.vid, vnode->fid.vnode);
+
+ ret = 0;
+ if (sync) {
+ ret = filemap_fdatawait(inode->i_mapping);
+ if (ret < 0)
+ __mark_inode_dirty(inode, I_DIRTY_DATASYNC);
+ }
+
+ _leave(" = %d", ret);
+ return ret;
+}
+
+/*
+ * completion of write to server
+ */
+void afs_pages_written_back(struct afs_vnode *vnode, struct afs_call *call)
+{
+ struct afs_writeback *wb = call->wb;
+ struct pagevec pv;
+ unsigned count, loop;
+ pgoff_t first = call->first, last = call->last;
+ bool free_wb;
+
+ _enter("{%x:%u},{%lx-%lx}",
+ vnode->fid.vid, vnode->fid.vnode, first, last);
+
+ ASSERT(wb != NULL);
+
+ pagevec_init(&pv, 0);
+
+ do {
+ _debug("done %lx-%lx", first, last);
+
+ count = last - first + 1;
+ if (count > PAGEVEC_SIZE)
+ count = PAGEVEC_SIZE;
+ pv.nr = find_get_pages_contig(call->mapping, first, count,
+ pv.pages);
+ ASSERTCMP(pv.nr, ==, count);
+
+ spin_lock(&vnode->writeback_lock);
+ for (loop = 0; loop < count; loop++) {
+ struct page *page = pv.pages[loop];
+ end_page_writeback(page);
+ if (page_private(page) == (unsigned long) wb) {
+ set_page_private(page, 0);
+ ClearPagePrivate(page);
+ wb->usage--;
+ }
+ }
+ free_wb = false;
+ if (wb->usage == 0) {
+ afs_unlink_writeback(wb);
+ free_wb = true;
+ }
+ spin_unlock(&vnode->writeback_lock);
+ first += count;
+ if (free_wb) {
+ afs_free_writeback(wb);
+ wb = NULL;
+ }
+
+ __pagevec_release(&pv);
+ } while (first <= last);
+
+ _leave("");
+}
+
+/*
+ * write to an AFS file
+ */
+ssize_t afs_file_write(struct kiocb *iocb, const struct iovec *iov,
+ unsigned long nr_segs, loff_t pos)
+{
+ struct dentry *dentry = iocb->ki_filp->f_path.dentry;
+ struct afs_vnode *vnode = AFS_FS_I(dentry->d_inode);
+ ssize_t result;
+ size_t count = iov_length(iov, nr_segs);
+ int ret;
+
+ _enter("{%x.%u},{%zu},%lu,",
+ vnode->fid.vid, vnode->fid.vnode, count, nr_segs);
+
+ if (IS_SWAPFILE(&vnode->vfs_inode)) {
+ printk(KERN_INFO
+ "AFS: Attempt to write to active swap file!\n");
+ return -EBUSY;
+ }
+
+ if (!count)
+ return 0;
+
+ result = generic_file_aio_write(iocb, iov, nr_segs, pos);
+ if (IS_ERR_VALUE(result)) {
+ _leave(" = %zd", result);
+ return result;
+ }
+
+ /* return error values for O_SYNC and IS_SYNC() */
+ if (IS_SYNC(&vnode->vfs_inode) || iocb->ki_filp->f_flags & O_SYNC) {
+ ret = afs_fsync(iocb->ki_filp, dentry, 1);
+ if (ret < 0)
+ result = ret;
+ }
+
+ _leave(" = %zd", result);
+ return result;
+}
+
+/*
+ * flush the vnode to the fileserver
+ */
+int afs_writeback_all(struct afs_vnode *vnode)
+{
+ struct address_space *mapping = vnode->vfs_inode.i_mapping;
+ struct writeback_control wbc = {
+ .bdi = mapping->backing_dev_info,
+ .sync_mode = WB_SYNC_ALL,
+ .nr_to_write = LONG_MAX,
+ .for_writepages = 1,
+ .range_cyclic = 1,
+ };
+ int ret;
+
+ _enter("");
+
+ ret = mapping->a_ops->writepages(mapping, &wbc);
+ __mark_inode_dirty(mapping->host, I_DIRTY_PAGES);
+
+ _leave(" = %d", ret);
+ return ret;
+}
+
+/*
+ * flush any dirty pages for this process, and check for write errors.
+ * - the return status from this call provides a reliable indication of
+ * whether any write errors occurred for this process.
+ */
+int afs_fsync(struct file *file, struct dentry *dentry, int datasync)
+{
+ struct afs_writeback *wb, *xwb;
+ struct afs_vnode *vnode = AFS_FS_I(dentry->d_inode);
+ int ret;
+
+ _enter("{%x:%u},{n=%s},%d",
+ vnode->fid.vid, vnode->fid.vnode, dentry->d_name.name,
+ datasync);
+
+ /* use a writeback record as a marker in the queue - when this reaches
+ * the front of the queue, all the outstanding writes are either
+ * completed or rejected */
+ wb = kzalloc(sizeof(*wb), GFP_KERNEL);
+ if (!wb)
+ return -ENOMEM;
+ wb->vnode = vnode;
+ wb->first = 0;
+ wb->last = -1;
+ wb->offset_first = 0;
+ wb->to_last = PAGE_SIZE;
+ wb->usage = 1;
+ wb->state = AFS_WBACK_SYNCING;
+ init_waitqueue_head(&wb->waitq);
+
+ spin_lock(&vnode->writeback_lock);
+ list_for_each_entry(xwb, &vnode->writebacks, link) {
+ if (xwb->state == AFS_WBACK_PENDING)
+ xwb->state = AFS_WBACK_CONFLICTING;
+ }
+ list_add_tail(&wb->link, &vnode->writebacks);
+ spin_unlock(&vnode->writeback_lock);
+
+ /* push all the outstanding writebacks to the server */
+ ret = afs_writeback_all(vnode);
+ if (ret < 0) {
+ afs_put_writeback(wb);
+ _leave(" = %d [wb]", ret);
+ return ret;
+ }
+
+ /* wait for the preceding writes to actually complete */
+ ret = wait_event_interruptible(wb->waitq,
+ wb->state == AFS_WBACK_COMPLETE ||
+ vnode->writebacks.next == &wb->link);
+ afs_put_writeback(wb);
+ _leave(" = %d", ret);
+ return ret;
+}
diff --git a/fs/aio.c b/fs/aio.c
index b97ab8028b6..dbe699e9828 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -30,6 +30,7 @@
#include <linux/highmem.h>
#include <linux/workqueue.h>
#include <linux/security.h>
+#include <linux/eventfd.h>
#include <asm/kmap_types.h>
#include <asm/uaccess.h>
@@ -346,10 +347,9 @@ void fastcall exit_aio(struct mm_struct *mm)
wait_for_all_aios(ctx);
/*
- * this is an overkill, but ensures we don't leave
- * the ctx on the aio_wq
+ * Ensure we don't leave the ctx on the aio_wq
*/
- flush_workqueue(aio_wq);
+ cancel_work_sync(&ctx->wq.work);
if (1 != atomic_read(&ctx->users))
printk(KERN_DEBUG
@@ -372,7 +372,7 @@ void fastcall __put_ioctx(struct kioctx *ctx)
BUG_ON(ctx->reqs_active);
cancel_delayed_work(&ctx->wq);
- flush_workqueue(aio_wq);
+ cancel_work_sync(&ctx->wq.work);
aio_free_ring(ctx);
mmdrop(ctx->mm);
ctx->mm = NULL;
@@ -418,6 +418,7 @@ static struct kiocb fastcall *__aio_get_req(struct kioctx *ctx)
req->private = NULL;
req->ki_iovec = NULL;
INIT_LIST_HEAD(&req->ki_run_list);
+ req->ki_eventfd = ERR_PTR(-EINVAL);
/* Check if the completion queue has enough free space to
* accept an event from this io.
@@ -459,6 +460,8 @@ static inline void really_put_req(struct kioctx *ctx, struct kiocb *req)
{
assert_spin_locked(&ctx->ctx_lock);
+ if (!IS_ERR(req->ki_eventfd))
+ fput(req->ki_eventfd);
if (req->ki_dtor)
req->ki_dtor(req);
if (req->ki_iovec != &req->ki_inline_vec)
@@ -943,6 +946,14 @@ int fastcall aio_complete(struct kiocb *iocb, long res, long res2)
return 1;
}
+ /*
+ * Check if the user asked us to deliver the result through an
+ * eventfd. The eventfd_signal() function is safe to be called
+ * from IRQ context.
+ */
+ if (!IS_ERR(iocb->ki_eventfd))
+ eventfd_signal(iocb->ki_eventfd, 1);
+
info = &ctx->ring_info;
/* add a completion event to the ring buffer.
@@ -1527,8 +1538,7 @@ int fastcall io_submit_one(struct kioctx *ctx, struct iocb __user *user_iocb,
ssize_t ret;
/* enforce forwards compatibility on users */
- if (unlikely(iocb->aio_reserved1 || iocb->aio_reserved2 ||
- iocb->aio_reserved3)) {
+ if (unlikely(iocb->aio_reserved1 || iocb->aio_reserved2)) {
pr_debug("EINVAL: io_submit: reserve field set\n");
return -EINVAL;
}
@@ -1552,6 +1562,19 @@ int fastcall io_submit_one(struct kioctx *ctx, struct iocb __user *user_iocb,
fput(file);
return -EAGAIN;
}
+ if (iocb->aio_flags & IOCB_FLAG_RESFD) {
+ /*
+ * If the IOCB_FLAG_RESFD flag of aio_flags is set, get an
+ * instance of the file* now. The file descriptor must be
+ * an eventfd() fd, and will be signaled for each completed
+ * event using the eventfd_signal() function.
+ */
+ req->ki_eventfd = eventfd_fget((int) iocb->aio_resfd);
+ if (unlikely(IS_ERR(req->ki_eventfd))) {
+ ret = PTR_ERR(req->ki_eventfd);
+ goto out_put_req;
+ }
+ }
req->ki_filp = file;
ret = put_user(req->ki_key, &user_iocb->aio_key);
diff --git a/fs/anon_inodes.c b/fs/anon_inodes.c
new file mode 100644
index 00000000000..40fe3a3222e
--- /dev/null
+++ b/fs/anon_inodes.c
@@ -0,0 +1,200 @@
+/*
+ * fs/anon_inodes.c
+ *
+ * Copyright (C) 2007 Davide Libenzi <davidel@xmailserver.org>
+ *
+ * Thanks to Arnd Bergmann for code review and suggestions.
+ * More changes for Thomas Gleixner suggestions.
+ *
+ */
+
+#include <linux/file.h>
+#include <linux/poll.h>
+#include <linux/slab.h>
+#include <linux/init.h>
+#include <linux/fs.h>
+#include <linux/mount.h>
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/magic.h>
+#include <linux/anon_inodes.h>
+
+#include <asm/uaccess.h>
+
+static struct vfsmount *anon_inode_mnt __read_mostly;
+static struct inode *anon_inode_inode;
+static const struct file_operations anon_inode_fops;
+
+static int anon_inodefs_get_sb(struct file_system_type *fs_type, int flags,
+ const char *dev_name, void *data,
+ struct vfsmount *mnt)
+{
+ return get_sb_pseudo(fs_type, "anon_inode:", NULL, ANON_INODE_FS_MAGIC,
+ mnt);
+}
+
+static int anon_inodefs_delete_dentry(struct dentry *dentry)
+{
+ /*
+ * We faked vfs to believe the dentry was hashed when we created it.
+ * Now we restore the flag so that dput() will work correctly.
+ */
+ dentry->d_flags |= DCACHE_UNHASHED;
+ return 1;
+}
+
+static struct file_system_type anon_inode_fs_type = {
+ .name = "anon_inodefs",
+ .get_sb = anon_inodefs_get_sb,
+ .kill_sb = kill_anon_super,
+};
+static struct dentry_operations anon_inodefs_dentry_operations = {
+ .d_delete = anon_inodefs_delete_dentry,
+};
+
+/**
+ * anon_inode_getfd - creates a new file instance by hooking it up to and
+ * anonymous inode, and a dentry that describe the "class"
+ * of the file
+ *
+ * @pfd: [out] pointer to the file descriptor
+ * @dpinode: [out] pointer to the inode
+ * @pfile: [out] pointer to the file struct
+ * @name: [in] name of the "class" of the new file
+ * @fops [in] file operations for the new file
+ * @priv [in] private data for the new file (will be file's private_data)
+ *
+ * Creates a new file by hooking it on a single inode. This is useful for files
+ * that do not need to have a full-fledged inode in order to operate correctly.
+ * All the files created with anon_inode_getfd() will share a single inode, by
+ * hence saving memory and avoiding code duplication for the file/inode/dentry
+ * setup.
+ */
+int anon_inode_getfd(int *pfd, struct inode **pinode, struct file **pfile,
+ const char *name, const struct file_operations *fops,
+ void *priv)
+{
+ struct qstr this;
+ struct dentry *dentry;
+ struct inode *inode;
+ struct file *file;
+ int error, fd;
+
+ if (IS_ERR(anon_inode_inode))
+ return -ENODEV;
+ file = get_empty_filp();
+ if (!file)
+ return -ENFILE;
+
+ inode = igrab(anon_inode_inode);
+ if (IS_ERR(inode)) {
+ error = PTR_ERR(inode);
+ goto err_put_filp;
+ }
+
+ error = get_unused_fd();
+ if (error < 0)
+ goto err_iput;
+ fd = error;
+
+ /*
+ * Link the inode to a directory entry by creating a unique name
+ * using the inode sequence number.
+ */
+ error = -ENOMEM;
+ this.name = name;
+ this.len = strlen(name);
+ this.hash = 0;
+ dentry = d_alloc(anon_inode_mnt->mnt_sb->s_root, &this);
+ if (!dentry)
+ goto err_put_unused_fd;
+ dentry->d_op = &anon_inodefs_dentry_operations;
+ /* Do not publish this dentry inside the global dentry hash table */
+ dentry->d_flags &= ~DCACHE_UNHASHED;
+ d_instantiate(dentry, inode);
+
+ file->f_path.mnt = mntget(anon_inode_mnt);
+ file->f_path.dentry = dentry;
+ file->f_mapping = inode->i_mapping;
+
+ file->f_pos = 0;
+ file->f_flags = O_RDWR;
+ file->f_op = fops;
+ file->f_mode = FMODE_READ | FMODE_WRITE;
+ file->f_version = 0;
+ file->private_data = priv;
+
+ fd_install(fd, file);
+
+ *pfd = fd;
+ *pinode = inode;
+ *pfile = file;
+ return 0;
+
+err_put_unused_fd:
+ put_unused_fd(fd);
+err_iput:
+ iput(inode);
+err_put_filp:
+ put_filp(file);
+ return error;
+}
+
+/*
+ * A single inode exist for all anon_inode files. Contrary to pipes,
+ * anon_inode inodes has no per-instance data associated, so we can avoid
+ * the allocation of multiple of them.
+ */
+static struct inode *anon_inode_mkinode(void)
+{
+ struct inode *inode = new_inode(anon_inode_mnt->mnt_sb);
+
+ if (!inode)
+ return ERR_PTR(-ENOMEM);
+
+ inode->i_fop = &anon_inode_fops;
+
+ /*
+ * Mark the inode dirty from the very beginning,
+ * that way it will never be moved to the dirty
+ * list because mark_inode_dirty() will think
+ * that it already _is_ on the dirty list.
+ */
+ inode->i_state = I_DIRTY;
+ inode->i_mode = S_IRUSR | S_IWUSR;
+ inode->i_uid = current->fsuid;
+ inode->i_gid = current->fsgid;
+ inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME;
+ return inode;
+}
+
+static int __init anon_inode_init(void)
+{
+ int error;
+
+ error = register_filesystem(&anon_inode_fs_type);
+ if (error)
+ goto err_exit;
+ anon_inode_mnt = kern_mount(&anon_inode_fs_type);
+ if (IS_ERR(anon_inode_mnt)) {
+ error = PTR_ERR(anon_inode_mnt);
+ goto err_unregister_filesystem;
+ }
+ anon_inode_inode = anon_inode_mkinode();
+ if (IS_ERR(anon_inode_inode)) {
+ error = PTR_ERR(anon_inode_inode);
+ goto err_mntput;
+ }
+
+ return 0;
+
+err_mntput:
+ mntput(anon_inode_mnt);
+err_unregister_filesystem:
+ unregister_filesystem(&anon_inode_fs_type);
+err_exit:
+ panic(KERN_ERR "anon_inode_init() failed (%d)\n", error);
+}
+
+fs_initcall(anon_inode_init);
+
diff --git a/fs/attr.c b/fs/attr.c
index 97de9467087..a0a0c7b07ba 100644
--- a/fs/attr.c
+++ b/fs/attr.c
@@ -9,7 +9,6 @@
#include <linux/time.h>
#include <linux/mm.h>
#include <linux/string.h>
-#include <linux/smp_lock.h>
#include <linux/capability.h>
#include <linux/fsnotify.h>
#include <linux/fcntl.h>
diff --git a/fs/autofs/autofs_i.h b/fs/autofs/autofs_i.h
index 4ef544434b5..8b4cca3c470 100644
--- a/fs/autofs/autofs_i.h
+++ b/fs/autofs/autofs_i.h
@@ -101,7 +101,7 @@ struct autofs_symlink {
struct autofs_sb_info {
u32 magic;
struct file *pipe;
- pid_t oz_pgrp;
+ struct pid *oz_pgrp;
int catatonic;
struct super_block *sb;
unsigned long exp_timeout;
@@ -122,7 +122,7 @@ static inline struct autofs_sb_info *autofs_sbi(struct super_block *sb)
filesystem without "magic".) */
static inline int autofs_oz_mode(struct autofs_sb_info *sbi) {
- return sbi->catatonic || process_group(current) == sbi->oz_pgrp;
+ return sbi->catatonic || task_pgrp(current) == sbi->oz_pgrp;
}
/* Hash operations */
diff --git a/fs/autofs/inode.c b/fs/autofs/inode.c
index aa0b61ff827..e7204d71acc 100644
--- a/fs/autofs/inode.c
+++ b/fs/autofs/inode.c
@@ -34,12 +34,14 @@ void autofs_kill_sb(struct super_block *sb)
if (!sbi)
goto out_kill_sb;
- if ( !sbi->catatonic )
+ if (!sbi->catatonic)
autofs_catatonic_mode(sbi); /* Free wait queues, close pipe */
+ put_pid(sbi->oz_pgrp);
+
autofs_hash_nuke(sbi);
- for ( n = 0 ; n < AUTOFS_MAX_SYMLINKS ; n++ ) {
- if ( test_bit(n, sbi->symlink_bitmap) )
+ for (n = 0; n < AUTOFS_MAX_SYMLINKS; n++) {
+ if (test_bit(n, sbi->symlink_bitmap))
kfree(sbi->symlink[n].data);
}
@@ -69,7 +71,8 @@ static match_table_t autofs_tokens = {
{Opt_err, NULL}
};
-static int parse_options(char *options, int *pipefd, uid_t *uid, gid_t *gid, pid_t *pgrp, int *minproto, int *maxproto)
+static int parse_options(char *options, int *pipefd, uid_t *uid, gid_t *gid,
+ pid_t *pgrp, int *minproto, int *maxproto)
{
char *p;
substring_t args[MAX_OPT_ARGS];
@@ -138,9 +141,10 @@ int autofs_fill_super(struct super_block *s, void *data, int silent)
int pipefd;
struct autofs_sb_info *sbi;
int minproto, maxproto;
+ pid_t pgid;
sbi = kzalloc(sizeof(*sbi), GFP_KERNEL);
- if ( !sbi )
+ if (!sbi)
goto fail_unlock;
DPRINTK(("autofs: starting up, sbi = %p\n",sbi));
@@ -149,7 +153,6 @@ int autofs_fill_super(struct super_block *s, void *data, int silent)
sbi->pipe = NULL;
sbi->catatonic = 1;
sbi->exp_timeout = 0;
- sbi->oz_pgrp = process_group(current);
autofs_initialize_hash(&sbi->dirhash);
sbi->queues = NULL;
memset(sbi->symlink_bitmap, 0, sizeof(long)*AUTOFS_SYMLINK_BITMAP_LEN);
@@ -169,26 +172,36 @@ int autofs_fill_super(struct super_block *s, void *data, int silent)
goto fail_iput;
/* Can this call block? - WTF cares? s is locked. */
- if ( parse_options(data,&pipefd,&root_inode->i_uid,&root_inode->i_gid,&sbi->oz_pgrp,&minproto,&maxproto) ) {
+ if (parse_options(data, &pipefd, &root_inode->i_uid,
+ &root_inode->i_gid, &pgid, &minproto,
+ &maxproto)) {
printk("autofs: called with bogus options\n");
goto fail_dput;
}
/* Couldn't this be tested earlier? */
- if ( minproto > AUTOFS_PROTO_VERSION ||
- maxproto < AUTOFS_PROTO_VERSION ) {
+ if (minproto > AUTOFS_PROTO_VERSION ||
+ maxproto < AUTOFS_PROTO_VERSION) {
printk("autofs: kernel does not match daemon version\n");
goto fail_dput;
}
- DPRINTK(("autofs: pipe fd = %d, pgrp = %u\n", pipefd, sbi->oz_pgrp));
+ DPRINTK(("autofs: pipe fd = %d, pgrp = %u\n", pipefd, pgid));
+ sbi->oz_pgrp = find_get_pid(pgid);
+
+ if (!sbi->oz_pgrp) {
+ printk("autofs: could not find process group %d\n", pgid);
+ goto fail_dput;
+ }
+
pipe = fget(pipefd);
- if ( !pipe ) {
+ if (!pipe) {
printk("autofs: could not open pipe file descriptor\n");
- goto fail_dput;
+ goto fail_put_pid;
}
- if ( !pipe->f_op || !pipe->f_op->write )
+
+ if (!pipe->f_op || !pipe->f_op->write)
goto fail_fput;
sbi->pipe = pipe;
sbi->catatonic = 0;
@@ -202,6 +215,8 @@ int autofs_fill_super(struct super_block *s, void *data, int silent)
fail_fput:
printk("autofs: pipe file descriptor does not contain proper ops\n");
fput(pipe);
+fail_put_pid:
+ put_pid(sbi->oz_pgrp);
fail_dput:
dput(root);
goto fail_free;
@@ -230,7 +245,7 @@ static void autofs_read_inode(struct inode *inode)
inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME;
inode->i_blocks = 0;
- if ( ino == AUTOFS_ROOT_INO ) {
+ if (ino == AUTOFS_ROOT_INO) {
inode->i_mode = S_IFDIR | S_IRUGO | S_IXUGO | S_IWUSR;
inode->i_op = &autofs_root_inode_operations;
inode->i_fop = &autofs_root_operations;
@@ -241,12 +256,12 @@ static void autofs_read_inode(struct inode *inode)
inode->i_uid = inode->i_sb->s_root->d_inode->i_uid;
inode->i_gid = inode->i_sb->s_root->d_inode->i_gid;
- if ( ino >= AUTOFS_FIRST_SYMLINK && ino < AUTOFS_FIRST_DIR_INO ) {
+ if (ino >= AUTOFS_FIRST_SYMLINK && ino < AUTOFS_FIRST_DIR_INO) {
/* Symlink inode - should be in symlink list */
struct autofs_symlink *sl;
n = ino - AUTOFS_FIRST_SYMLINK;
- if ( n >= AUTOFS_MAX_SYMLINKS || !test_bit(n,sbi->symlink_bitmap)) {
+ if (n >= AUTOFS_MAX_SYMLINKS || !test_bit(n,sbi->symlink_bitmap)) {
printk("autofs: Looking for bad symlink inode %u\n", (unsigned int) ino);
return;
}
diff --git a/fs/autofs/root.c b/fs/autofs/root.c
index f2597205939..c1489533277 100644
--- a/fs/autofs/root.c
+++ b/fs/autofs/root.c
@@ -67,8 +67,8 @@ static int autofs_root_readdir(struct file *filp, void *dirent, filldir_t filldi
filp->f_pos = ++nr;
/* fall through */
default:
- while ( onr = nr, ent = autofs_hash_enum(dirhash,&nr,ent) ) {
- if ( !ent->dentry || d_mountpoint(ent->dentry) ) {
+ while (onr = nr, ent = autofs_hash_enum(dirhash,&nr,ent)) {
+ if (!ent->dentry || d_mountpoint(ent->dentry)) {
if (filldir(dirent,ent->name,ent->len,onr,ent->ino,DT_UNKNOWN) < 0)
goto out;
filp->f_pos = nr;
@@ -88,10 +88,10 @@ static int try_to_fill_dentry(struct dentry *dentry, struct super_block *sb, str
struct autofs_dir_ent *ent;
int status = 0;
- if ( !(ent = autofs_hash_lookup(&sbi->dirhash, &dentry->d_name)) ) {
+ if (!(ent = autofs_hash_lookup(&sbi->dirhash, &dentry->d_name))) {
do {
- if ( status && dentry->d_inode ) {
- if ( status != -ENOENT )
+ if (status && dentry->d_inode) {
+ if (status != -ENOENT)
printk("autofs warning: lookup failure on positive dentry, status = %d, name = %s\n", status, dentry->d_name.name);
return 0; /* Try to get the kernel to invalidate this dentry */
}
@@ -106,7 +106,7 @@ static int try_to_fill_dentry(struct dentry *dentry, struct super_block *sb, str
return 1;
}
status = autofs_wait(sbi, &dentry->d_name);
- } while (!(ent = autofs_hash_lookup(&sbi->dirhash, &dentry->d_name)) );
+ } while (!(ent = autofs_hash_lookup(&sbi->dirhash, &dentry->d_name)));
}
/* Abuse this field as a pointer to the directory entry, used to
@@ -124,13 +124,13 @@ static int try_to_fill_dentry(struct dentry *dentry, struct super_block *sb, str
/* If this is a directory that isn't a mount point, bitch at the
daemon and fix it in user space */
- if ( S_ISDIR(dentry->d_inode->i_mode) && !d_mountpoint(dentry) ) {
+ if (S_ISDIR(dentry->d_inode->i_mode) && !d_mountpoint(dentry)) {
return !autofs_wait(sbi, &dentry->d_name);
}
/* We don't update the usages for the autofs daemon itself, this
is necessary for recursive autofs mounts */
- if ( !autofs_oz_mode(sbi) ) {
+ if (!autofs_oz_mode(sbi)) {
autofs_update_usage(&sbi->dirhash,ent);
}
@@ -157,7 +157,7 @@ static int autofs_revalidate(struct dentry * dentry, struct nameidata *nd)
sbi = autofs_sbi(dir->i_sb);
/* Pending dentry */
- if ( dentry->d_flags & DCACHE_AUTOFS_PENDING ) {
+ if (dentry->d_flags & DCACHE_AUTOFS_PENDING) {
if (autofs_oz_mode(sbi))
res = 1;
else
@@ -173,7 +173,7 @@ static int autofs_revalidate(struct dentry * dentry, struct nameidata *nd)
}
/* Check for a non-mountpoint directory */
- if ( S_ISDIR(dentry->d_inode->i_mode) && !d_mountpoint(dentry) ) {
+ if (S_ISDIR(dentry->d_inode->i_mode) && !d_mountpoint(dentry)) {
if (autofs_oz_mode(sbi))
res = 1;
else
@@ -183,9 +183,9 @@ static int autofs_revalidate(struct dentry * dentry, struct nameidata *nd)
}
/* Update the usage list */
- if ( !autofs_oz_mode(sbi) ) {
+ if (!autofs_oz_mode(sbi)) {
ent = (struct autofs_dir_ent *) dentry->d_time;
- if ( ent )
+ if (ent)
autofs_update_usage(&sbi->dirhash,ent);
}
unlock_kernel();
@@ -213,8 +213,10 @@ static struct dentry *autofs_root_lookup(struct inode *dir, struct dentry *dentr
sbi = autofs_sbi(dir->i_sb);
oz_mode = autofs_oz_mode(sbi);
- DPRINTK(("autofs_lookup: pid = %u, pgrp = %u, catatonic = %d, oz_mode = %d\n",
- current->pid, process_group(current), sbi->catatonic, oz_mode));
+ DPRINTK(("autofs_lookup: pid = %u, pgrp = %u, catatonic = %d, "
+ "oz_mode = %d\n", pid_nr(task_pid(current)),
+ process_group(current), sbi->catatonic,
+ oz_mode));
/*
* Mark the dentry incomplete, but add it. This is needed so
@@ -258,7 +260,7 @@ static struct dentry *autofs_root_lookup(struct inode *dir, struct dentry *dentr
* doesn't do the right thing for all system calls, but it should
* be OK for the operations we permit from an autofs.
*/
- if ( dentry->d_inode && d_unhashed(dentry) )
+ if (dentry->d_inode && d_unhashed(dentry))
return ERR_PTR(-ENOENT);
return NULL;
@@ -277,18 +279,18 @@ static int autofs_root_symlink(struct inode *dir, struct dentry *dentry, const c
autofs_say(dentry->d_name.name,dentry->d_name.len);
lock_kernel();
- if ( !autofs_oz_mode(sbi) ) {
+ if (!autofs_oz_mode(sbi)) {
unlock_kernel();
return -EACCES;
}
- if ( autofs_hash_lookup(dh, &dentry->d_name) ) {
+ if (autofs_hash_lookup(dh, &dentry->d_name)) {
unlock_kernel();
return -EEXIST;
}
n = find_first_zero_bit(sbi->symlink_bitmap,AUTOFS_MAX_SYMLINKS);
- if ( n >= AUTOFS_MAX_SYMLINKS ) {
+ if (n >= AUTOFS_MAX_SYMLINKS) {
unlock_kernel();
return -ENOSPC;
}
@@ -297,14 +299,14 @@ static int autofs_root_symlink(struct inode *dir, struct dentry *dentry, const c
sl = &sbi->symlink[n];
sl->len = strlen(symname);
sl->data = kmalloc(slsize = sl->len+1, GFP_KERNEL);
- if ( !sl->data ) {
+ if (!sl->data) {
clear_bit(n,sbi->symlink_bitmap);
unlock_kernel();
return -ENOSPC;
}
ent = kmalloc(sizeof(struct autofs_dir_ent), GFP_KERNEL);
- if ( !ent ) {
+ if (!ent) {
kfree(sl->data);
clear_bit(n,sbi->symlink_bitmap);
unlock_kernel();
@@ -312,7 +314,7 @@ static int autofs_root_symlink(struct inode *dir, struct dentry *dentry, const c
}
ent->name = kmalloc(dentry->d_name.len+1, GFP_KERNEL);
- if ( !ent->name ) {
+ if (!ent->name) {
kfree(sl->data);
kfree(ent);
clear_bit(n,sbi->symlink_bitmap);
@@ -354,23 +356,23 @@ static int autofs_root_unlink(struct inode *dir, struct dentry *dentry)
/* This allows root to remove symlinks */
lock_kernel();
- if ( !autofs_oz_mode(sbi) && !capable(CAP_SYS_ADMIN) ) {
+ if (!autofs_oz_mode(sbi) && !capable(CAP_SYS_ADMIN)) {
unlock_kernel();
return -EACCES;
}
ent = autofs_hash_lookup(dh, &dentry->d_name);
- if ( !ent ) {
+ if (!ent) {
unlock_kernel();
return -ENOENT;
}
n = ent->ino - AUTOFS_FIRST_SYMLINK;
- if ( n >= AUTOFS_MAX_SYMLINKS ) {
+ if (n >= AUTOFS_MAX_SYMLINKS) {
unlock_kernel();
return -EISDIR; /* It's a directory, dummy */
}
- if ( !test_bit(n,sbi->symlink_bitmap) ) {
+ if (!test_bit(n,sbi->symlink_bitmap)) {
unlock_kernel();
return -EINVAL; /* Nonexistent symlink? Shouldn't happen */
}
@@ -392,23 +394,23 @@ static int autofs_root_rmdir(struct inode *dir, struct dentry *dentry)
struct autofs_dir_ent *ent;
lock_kernel();
- if ( !autofs_oz_mode(sbi) ) {
+ if (!autofs_oz_mode(sbi)) {
unlock_kernel();
return -EACCES;
}
ent = autofs_hash_lookup(dh, &dentry->d_name);
- if ( !ent ) {
+ if (!ent) {
unlock_kernel();
return -ENOENT;
}
- if ( (unsigned int)ent->ino < AUTOFS_FIRST_DIR_INO ) {
+ if ((unsigned int)ent->ino < AUTOFS_FIRST_DIR_INO) {
unlock_kernel();
return -ENOTDIR; /* Not a directory */
}
- if ( ent->dentry != dentry ) {
+ if (ent->dentry != dentry) {
printk("autofs_rmdir: odentry != dentry for entry %s\n", dentry->d_name.name);
}
@@ -429,18 +431,18 @@ static int autofs_root_mkdir(struct inode *dir, struct dentry *dentry, int mode)
ino_t ino;
lock_kernel();
- if ( !autofs_oz_mode(sbi) ) {
+ if (!autofs_oz_mode(sbi)) {
unlock_kernel();
return -EACCES;
}
ent = autofs_hash_lookup(dh, &dentry->d_name);
- if ( ent ) {
+ if (ent) {
unlock_kernel();
return -EEXIST;
}
- if ( sbi->next_dir_ino < AUTOFS_FIRST_DIR_INO ) {
+ if (sbi->next_dir_ino < AUTOFS_FIRST_DIR_INO) {
printk("autofs: Out of inode numbers -- what the heck did you do??\n");
unlock_kernel();
return -ENOSPC;
@@ -448,13 +450,13 @@ static int autofs_root_mkdir(struct inode *dir, struct dentry *dentry, int mode)
ino = sbi->next_dir_ino++;
ent = kmalloc(sizeof(struct autofs_dir_ent), GFP_KERNEL);
- if ( !ent ) {
+ if (!ent) {
unlock_kernel();
return -ENOSPC;
}
ent->name = kmalloc(dentry->d_name.len+1, GFP_KERNEL);
- if ( !ent->name ) {
+ if (!ent->name) {
kfree(ent);
unlock_kernel();
return -ENOSPC;
@@ -483,7 +485,7 @@ static inline int autofs_get_set_timeout(struct autofs_sb_info *sbi,
put_user(sbi->exp_timeout / HZ, p))
return -EFAULT;
- if ( ntimeout > ULONG_MAX/HZ )
+ if (ntimeout > ULONG_MAX/HZ)
sbi->exp_timeout = 0;
else
sbi->exp_timeout = ntimeout * HZ;
@@ -511,15 +513,14 @@ static inline int autofs_expire_run(struct super_block *sb,
pkt.hdr.proto_version = AUTOFS_PROTO_VERSION;
pkt.hdr.type = autofs_ptype_expire;
- if ( !sbi->exp_timeout ||
- !(ent = autofs_expire(sb,sbi,mnt)) )
+ if (!sbi->exp_timeout || !(ent = autofs_expire(sb,sbi,mnt)))
return -EAGAIN;
pkt.len = ent->len;
memcpy(pkt.name, ent->name, pkt.len);
pkt.name[pkt.len] = '\0';
- if ( copy_to_user(pkt_p, &pkt, sizeof(struct autofs_packet_expire)) )
+ if (copy_to_user(pkt_p, &pkt, sizeof(struct autofs_packet_expire)))
return -EFAULT;
return 0;
@@ -537,11 +538,11 @@ static int autofs_root_ioctl(struct inode *inode, struct file *filp,
DPRINTK(("autofs_ioctl: cmd = 0x%08x, arg = 0x%08lx, sbi = %p, pgrp = %u\n",cmd,arg,sbi,process_group(current)));
- if ( _IOC_TYPE(cmd) != _IOC_TYPE(AUTOFS_IOC_FIRST) ||
- _IOC_NR(cmd) - _IOC_NR(AUTOFS_IOC_FIRST) >= AUTOFS_IOC_COUNT )
+ if (_IOC_TYPE(cmd) != _IOC_TYPE(AUTOFS_IOC_FIRST) ||
+ _IOC_NR(cmd) - _IOC_NR(AUTOFS_IOC_FIRST) >= AUTOFS_IOC_COUNT)
return -ENOTTY;
- if ( !autofs_oz_mode(sbi) && !capable(CAP_SYS_ADMIN) )
+ if (!autofs_oz_mode(sbi) && !capable(CAP_SYS_ADMIN))
return -EPERM;
switch(cmd) {
diff --git a/fs/autofs4/inode.c b/fs/autofs4/inode.c
index 26063dc84a2..692364e8ffc 100644
--- a/fs/autofs4/inode.c
+++ b/fs/autofs4/inode.c
@@ -18,7 +18,6 @@
#include <linux/pagemap.h>
#include <linux/parser.h>
#include <linux/bitops.h>
-#include <linux/smp_lock.h>
#include <linux/magic.h>
#include "autofs_i.h"
#include <linux/module.h>
@@ -219,8 +218,7 @@ static match_table_t tokens = {
};
static int parse_options(char *options, int *pipefd, uid_t *uid, gid_t *gid,
- pid_t *pgrp, unsigned int *type,
- int *minproto, int *maxproto)
+ pid_t *pgrp, unsigned int *type, int *minproto, int *maxproto)
{
char *p;
substring_t args[MAX_OPT_ARGS];
@@ -315,7 +313,7 @@ int autofs4_fill_super(struct super_block *s, void *data, int silent)
struct autofs_info *ino;
sbi = kmalloc(sizeof(*sbi), GFP_KERNEL);
- if ( !sbi )
+ if (!sbi)
goto fail_unlock;
DPRINTK("starting up, sbi = %p",sbi);
@@ -364,10 +362,9 @@ int autofs4_fill_super(struct super_block *s, void *data, int silent)
root->d_fsdata = ino;
/* Can this call block? */
- if (parse_options(data, &pipefd,
- &root_inode->i_uid, &root_inode->i_gid,
- &sbi->oz_pgrp, &sbi->type,
- &sbi->min_proto, &sbi->max_proto)) {
+ if (parse_options(data, &pipefd, &root_inode->i_uid, &root_inode->i_gid,
+ &sbi->oz_pgrp, &sbi->type, &sbi->min_proto,
+ &sbi->max_proto)) {
printk("autofs: called with bogus options\n");
goto fail_dput;
}
@@ -397,11 +394,11 @@ int autofs4_fill_super(struct super_block *s, void *data, int silent)
DPRINTK("pipe fd = %d, pgrp = %u", pipefd, sbi->oz_pgrp);
pipe = fget(pipefd);
- if ( !pipe ) {
+ if (!pipe) {
printk("autofs: could not open pipe file descriptor\n");
goto fail_dput;
}
- if ( !pipe->f_op || !pipe->f_op->write )
+ if (!pipe->f_op || !pipe->f_op->write)
goto fail_fput;
sbi->pipe = pipe;
sbi->pipefd = pipefd;
diff --git a/fs/autofs4/root.c b/fs/autofs4/root.c
index d0e9b3a3905..2d4c8a3e604 100644
--- a/fs/autofs4/root.c
+++ b/fs/autofs4/root.c
@@ -17,7 +17,6 @@
#include <linux/stat.h>
#include <linux/param.h>
#include <linux/time.h>
-#include <linux/smp_lock.h>
#include "autofs_i.h"
static int autofs4_dir_symlink(struct inode *,struct dentry *,const char *);
@@ -760,7 +759,7 @@ static int autofs4_dir_unlink(struct inode *dir, struct dentry *dentry)
struct autofs_info *p_ino;
/* This allows root to remove symlinks */
- if ( !autofs4_oz_mode(sbi) && !capable(CAP_SYS_ADMIN) )
+ if (!autofs4_oz_mode(sbi) && !capable(CAP_SYS_ADMIN))
return -EACCES;
if (atomic_dec_and_test(&ino->count)) {
@@ -834,7 +833,7 @@ static int autofs4_dir_mkdir(struct inode *dir, struct dentry *dentry, int mode)
struct autofs_info *p_ino;
struct inode *inode;
- if ( !autofs4_oz_mode(sbi) )
+ if (!autofs4_oz_mode(sbi))
return -EACCES;
DPRINTK("dentry %p, creating %.*s",
@@ -872,11 +871,11 @@ static inline int autofs4_get_set_timeout(struct autofs_sb_info *sbi,
int rv;
unsigned long ntimeout;
- if ( (rv = get_user(ntimeout, p)) ||
- (rv = put_user(sbi->exp_timeout/HZ, p)) )
+ if ((rv = get_user(ntimeout, p)) ||
+ (rv = put_user(sbi->exp_timeout/HZ, p)))
return rv;
- if ( ntimeout > ULONG_MAX/HZ )
+ if (ntimeout > ULONG_MAX/HZ)
sbi->exp_timeout = 0;
else
sbi->exp_timeout = ntimeout * HZ;
@@ -907,7 +906,7 @@ static inline int autofs4_ask_reghost(struct autofs_sb_info *sbi, int __user *p)
DPRINTK("returning %d", sbi->needs_reghost);
status = put_user(sbi->needs_reghost, p);
- if ( status )
+ if (status)
return status;
sbi->needs_reghost = 0;
@@ -976,11 +975,11 @@ static int autofs4_root_ioctl(struct inode *inode, struct file *filp,
DPRINTK("cmd = 0x%08x, arg = 0x%08lx, sbi = %p, pgrp = %u",
cmd,arg,sbi,process_group(current));
- if ( _IOC_TYPE(cmd) != _IOC_TYPE(AUTOFS_IOC_FIRST) ||
- _IOC_NR(cmd) - _IOC_NR(AUTOFS_IOC_FIRST) >= AUTOFS_IOC_COUNT )
+ if (_IOC_TYPE(cmd) != _IOC_TYPE(AUTOFS_IOC_FIRST) ||
+ _IOC_NR(cmd) - _IOC_NR(AUTOFS_IOC_FIRST) >= AUTOFS_IOC_COUNT)
return -ENOTTY;
- if ( !autofs4_oz_mode(sbi) && !capable(CAP_SYS_ADMIN) )
+ if (!autofs4_oz_mode(sbi) && !capable(CAP_SYS_ADMIN))
return -EPERM;
switch(cmd) {
diff --git a/fs/bad_inode.c b/fs/bad_inode.c
index efeab2fab40..329ee473eed 100644
--- a/fs/bad_inode.c
+++ b/fs/bad_inode.c
@@ -12,7 +12,6 @@
#include <linux/module.h>
#include <linux/stat.h>
#include <linux/time.h>
-#include <linux/smp_lock.h>
#include <linux/namei.h>
#include <linux/poll.h>
diff --git a/fs/befs/linuxvfs.c b/fs/befs/linuxvfs.c
index fe96108a788..a5c5171c282 100644
--- a/fs/befs/linuxvfs.c
+++ b/fs/befs/linuxvfs.c
@@ -292,10 +292,8 @@ befs_destroy_inode(struct inode *inode)
static void init_once(void * foo, struct kmem_cache * cachep, unsigned long flags)
{
struct befs_inode_info *bi = (struct befs_inode_info *) foo;
-
- if (flags & SLAB_CTOR_CONSTRUCTOR) {
- inode_init_once(&bi->vfs_inode);
- }
+
+ inode_init_once(&bi->vfs_inode);
}
static void
diff --git a/fs/bfs/inode.c b/fs/bfs/inode.c
index edc08d89aab..58c7bd9f530 100644
--- a/fs/bfs/inode.c
+++ b/fs/bfs/inode.c
@@ -248,8 +248,7 @@ static void init_once(void * foo, struct kmem_cache * cachep, unsigned long flag
{
struct bfs_inode_info *bi = foo;
- if (flags & SLAB_CTOR_CONSTRUCTOR)
- inode_init_once(&bi->vfs_inode);
+ inode_init_once(&bi->vfs_inode);
}
static int init_inodecache(void)
diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c
index 9cc4f0a8aaa..fa8ea33ab0b 100644
--- a/fs/binfmt_elf.c
+++ b/fs/binfmt_elf.c
@@ -31,7 +31,6 @@
#include <linux/init.h>
#include <linux/highuid.h>
#include <linux/smp.h>
-#include <linux/smp_lock.h>
#include <linux/compiler.h>
#include <linux/highmem.h>
#include <linux/pagemap.h>
@@ -39,6 +38,7 @@
#include <linux/syscalls.h>
#include <linux/random.h>
#include <linux/elf.h>
+#include <linux/utsname.h>
#include <asm/uaccess.h>
#include <asm/param.h>
#include <asm/page.h>
@@ -871,6 +871,8 @@ static int load_elf_binary(struct linux_binprm *bprm, struct pt_regs *regs)
elf_prot, elf_flags);
if (BAD_ADDR(error)) {
send_sig(SIGKILL, current, 0);
+ retval = IS_ERR((void *)error) ?
+ PTR_ERR((void*)error) : -EINVAL;
goto out_free_dentry;
}
@@ -900,6 +902,7 @@ static int load_elf_binary(struct linux_binprm *bprm, struct pt_regs *regs)
TASK_SIZE - elf_ppnt->p_memsz < k) {
/* set_brk can never work. Avoid overflows. */
send_sig(SIGKILL, current, 0);
+ retval = -EINVAL;
goto out_free_dentry;
}
diff --git a/fs/binfmt_elf_fdpic.c b/fs/binfmt_elf_fdpic.c
index f3ddca4a387..9d62fbad3d4 100644
--- a/fs/binfmt_elf_fdpic.c
+++ b/fs/binfmt_elf_fdpic.c
@@ -30,7 +30,6 @@
#include <linux/personality.h>
#include <linux/ptrace.h>
#include <linux/init.h>
-#include <linux/smp_lock.h>
#include <linux/elf.h>
#include <linux/elf-fdpic.h>
#include <linux/elfcore.h>
diff --git a/fs/binfmt_em86.c b/fs/binfmt_em86.c
index 1f2d1ad6331..576dd7de227 100644
--- a/fs/binfmt_em86.c
+++ b/fs/binfmt_em86.c
@@ -12,7 +12,6 @@
#include <linux/string.h>
#include <linux/stat.h>
#include <linux/slab.h>
-#include <linux/smp_lock.h>
#include <linux/binfmts.h>
#include <linux/elf.h>
#include <linux/init.h>
diff --git a/fs/binfmt_flat.c b/fs/binfmt_flat.c
index 7b0265d7f3a..861141b4f6d 100644
--- a/fs/binfmt_flat.c
+++ b/fs/binfmt_flat.c
@@ -558,7 +558,7 @@ static int load_flat_file(struct linux_binprm * bprm,
if (!realdatastart)
realdatastart = (unsigned long) -ENOMEM;
printk("Unable to allocate RAM for process data, errno %d\n",
- (int)-datapos);
+ (int)-realdatastart);
do_munmap(current->mm, textpos, text_len);
ret = realdatastart;
goto err;
diff --git a/fs/binfmt_misc.c b/fs/binfmt_misc.c
index e6f57990b12..330fd3fe854 100644
--- a/fs/binfmt_misc.c
+++ b/fs/binfmt_misc.c
@@ -18,7 +18,7 @@
#include <linux/module.h>
#include <linux/init.h>
-
+#include <linux/sched.h>
#include <linux/binfmts.h>
#include <linux/slab.h>
#include <linux/ctype.h>
@@ -675,19 +675,8 @@ static ssize_t
bm_status_read(struct file *file, char __user *buf, size_t nbytes, loff_t *ppos)
{
char *s = enabled ? "enabled" : "disabled";
- int len = strlen(s);
- loff_t pos = *ppos;
- if (pos < 0)
- return -EINVAL;
- if (pos >= len)
- return 0;
- if (len < pos + nbytes)
- nbytes = len - pos;
- if (copy_to_user(buf, s + pos, nbytes))
- return -EFAULT;
- *ppos = pos + nbytes;
- return nbytes;
+ return simple_read_from_buffer(buf, nbytes, ppos, s, strlen(s));
}
static ssize_t bm_status_write(struct file * file, const char __user * buffer,
@@ -727,8 +716,8 @@ static const struct super_operations s_ops = {
static int bm_fill_super(struct super_block * sb, void * data, int silent)
{
static struct tree_descr bm_files[] = {
- [1] = {"status", &bm_status_operations, S_IWUSR|S_IRUGO},
- [2] = {"register", &bm_register_operations, S_IWUSR},
+ [2] = {"status", &bm_status_operations, S_IWUSR|S_IRUGO},
+ [3] = {"register", &bm_register_operations, S_IWUSR},
/* last one */ {""}
};
int err = simple_fill_super(sb, 0x42494e4d, bm_files);
diff --git a/fs/binfmt_script.c b/fs/binfmt_script.c
index 1edbcca25a7..304c88544d8 100644
--- a/fs/binfmt_script.c
+++ b/fs/binfmt_script.c
@@ -12,7 +12,6 @@
#include <linux/binfmts.h>
#include <linux/init.h>
#include <linux/file.h>
-#include <linux/smp_lock.h>
#include <linux/err.h>
#include <linux/fs.h>
diff --git a/fs/block_dev.c b/fs/block_dev.c
index f02b7bdd986..ea1480a16f5 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -22,6 +22,7 @@
#include <linux/mount.h>
#include <linux/uio.h>
#include <linux/namei.h>
+#include <linux/log2.h>
#include <asm/uaccess.h>
#include "internal.h"
@@ -67,7 +68,7 @@ static void kill_bdev(struct block_device *bdev)
int set_blocksize(struct block_device *bdev, int size)
{
/* Size must be a power of two, and between 512 and PAGE_SIZE */
- if (size > PAGE_SIZE || size < 512 || (size & (size-1)))
+ if (size > PAGE_SIZE || size < 512 || !is_power_of_2(size))
return -EINVAL;
/* Size cannot be smaller than the size supported by the device */
@@ -457,17 +458,15 @@ static void init_once(void * foo, struct kmem_cache * cachep, unsigned long flag
struct bdev_inode *ei = (struct bdev_inode *) foo;
struct block_device *bdev = &ei->bdev;
- if (flags & SLAB_CTOR_CONSTRUCTOR) {
- memset(bdev, 0, sizeof(*bdev));
- mutex_init(&bdev->bd_mutex);
- sema_init(&bdev->bd_mount_sem, 1);
- INIT_LIST_HEAD(&bdev->bd_inodes);
- INIT_LIST_HEAD(&bdev->bd_list);
+ memset(bdev, 0, sizeof(*bdev));
+ mutex_init(&bdev->bd_mutex);
+ sema_init(&bdev->bd_mount_sem, 1);
+ INIT_LIST_HEAD(&bdev->bd_inodes);
+ INIT_LIST_HEAD(&bdev->bd_list);
#ifdef CONFIG_SYSFS
- INIT_LIST_HEAD(&bdev->bd_holder_list);
+ INIT_LIST_HEAD(&bdev->bd_holder_list);
#endif
- inode_init_once(&ei->vfs_inode);
- }
+ inode_init_once(&ei->vfs_inode);
}
static inline void __bd_forget(struct inode *inode)
diff --git a/fs/buffer.c b/fs/buffer.c
index 7db24b9e544..aa68206bd51 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -24,7 +24,6 @@
#include <linux/mm.h>
#include <linux/percpu.h>
#include <linux/slab.h>
-#include <linux/smp_lock.h>
#include <linux/capability.h>
#include <linux/blkdev.h>
#include <linux/file.h>
@@ -982,7 +981,8 @@ grow_dev_page(struct block_device *bdev, sector_t block,
struct page *page;
struct buffer_head *bh;
- page = find_or_create_page(inode->i_mapping, index, GFP_NOFS);
+ page = find_or_create_page(inode->i_mapping, index,
+ mapping_gfp_mask(inode->i_mapping) & ~__GFP_FS);
if (!page)
return NULL;
@@ -1727,6 +1727,7 @@ recover:
} while ((bh = bh->b_this_page) != head);
SetPageError(page);
BUG_ON(PageWriteback(page));
+ mapping_set_error(page->mapping, err);
set_page_writeback(page);
do {
struct buffer_head *next = bh->b_this_page;
@@ -1846,13 +1847,8 @@ static int __block_prepare_write(struct inode *inode, struct page *page,
if (block_start >= to)
break;
if (buffer_new(bh)) {
- void *kaddr;
-
clear_buffer_new(bh);
- kaddr = kmap_atomic(page, KM_USER0);
- memset(kaddr+block_start, 0, bh->b_size);
- flush_dcache_page(page);
- kunmap_atomic(kaddr, KM_USER0);
+ zero_user_page(page, block_start, bh->b_size, KM_USER0);
set_buffer_uptodate(bh);
mark_buffer_dirty(bh);
}
@@ -1940,10 +1936,8 @@ int block_read_full_page(struct page *page, get_block_t *get_block)
SetPageError(page);
}
if (!buffer_mapped(bh)) {
- void *kaddr = kmap_atomic(page, KM_USER0);
- memset(kaddr + i * blocksize, 0, blocksize);
- flush_dcache_page(page);
- kunmap_atomic(kaddr, KM_USER0);
+ zero_user_page(page, i * blocksize, blocksize,
+ KM_USER0);
if (!err)
set_buffer_uptodate(bh);
continue;
@@ -2086,7 +2080,6 @@ int cont_prepare_write(struct page *page, unsigned offset,
long status;
unsigned zerofrom;
unsigned blocksize = 1 << inode->i_blkbits;
- void *kaddr;
while(page->index > (pgpos = *bytes>>PAGE_CACHE_SHIFT)) {
status = -ENOMEM;
@@ -2108,10 +2101,8 @@ int cont_prepare_write(struct page *page, unsigned offset,
PAGE_CACHE_SIZE, get_block);
if (status)
goto out_unmap;
- kaddr = kmap_atomic(new_page, KM_USER0);
- memset(kaddr+zerofrom, 0, PAGE_CACHE_SIZE-zerofrom);
- flush_dcache_page(new_page);
- kunmap_atomic(kaddr, KM_USER0);
+ zero_user_page(new_page, zerofrom, PAGE_CACHE_SIZE - zerofrom,
+ KM_USER0);
generic_commit_write(NULL, new_page, zerofrom, PAGE_CACHE_SIZE);
unlock_page(new_page);
page_cache_release(new_page);
@@ -2138,10 +2129,7 @@ int cont_prepare_write(struct page *page, unsigned offset,
if (status)
goto out1;
if (zerofrom < offset) {
- kaddr = kmap_atomic(page, KM_USER0);
- memset(kaddr+zerofrom, 0, offset-zerofrom);
- flush_dcache_page(page);
- kunmap_atomic(kaddr, KM_USER0);
+ zero_user_page(page, zerofrom, offset - zerofrom, KM_USER0);
__block_commit_write(inode, page, zerofrom, offset);
}
return 0;
@@ -2340,10 +2328,7 @@ failed:
* Error recovery is pretty slack. Clear the page and mark it dirty
* so we'll later zero out any blocks which _were_ allocated.
*/
- kaddr = kmap_atomic(page, KM_USER0);
- memset(kaddr, 0, PAGE_CACHE_SIZE);
- flush_dcache_page(page);
- kunmap_atomic(kaddr, KM_USER0);
+ zero_user_page(page, 0, PAGE_CACHE_SIZE, KM_USER0);
SetPageUptodate(page);
set_page_dirty(page);
return ret;
@@ -2382,7 +2367,6 @@ int nobh_writepage(struct page *page, get_block_t *get_block,
loff_t i_size = i_size_read(inode);
const pgoff_t end_index = i_size >> PAGE_CACHE_SHIFT;
unsigned offset;
- void *kaddr;
int ret;
/* Is the page fully inside i_size? */
@@ -2413,10 +2397,7 @@ int nobh_writepage(struct page *page, get_block_t *get_block,
* the page size, the remaining memory is zeroed when mapped, and
* writes to that region are not written out to the file."
*/
- kaddr = kmap_atomic(page, KM_USER0);
- memset(kaddr + offset, 0, PAGE_CACHE_SIZE - offset);
- flush_dcache_page(page);
- kunmap_atomic(kaddr, KM_USER0);
+ zero_user_page(page, offset, PAGE_CACHE_SIZE - offset, KM_USER0);
out:
ret = mpage_writepage(page, get_block, wbc);
if (ret == -EAGAIN)
@@ -2437,7 +2418,6 @@ int nobh_truncate_page(struct address_space *mapping, loff_t from)
unsigned to;
struct page *page;
const struct address_space_operations *a_ops = mapping->a_ops;
- char *kaddr;
int ret = 0;
if ((offset & (blocksize - 1)) == 0)
@@ -2451,10 +2431,8 @@ int nobh_truncate_page(struct address_space *mapping, loff_t from)
to = (offset + blocksize) & ~(blocksize - 1);
ret = a_ops->prepare_write(NULL, page, offset, to);
if (ret == 0) {
- kaddr = kmap_atomic(page, KM_USER0);
- memset(kaddr + offset, 0, PAGE_CACHE_SIZE - offset);
- flush_dcache_page(page);
- kunmap_atomic(kaddr, KM_USER0);
+ zero_user_page(page, offset, PAGE_CACHE_SIZE - offset,
+ KM_USER0);
/*
* It would be more correct to call aops->commit_write()
* here, but this is more efficient.
@@ -2480,7 +2458,6 @@ int block_truncate_page(struct address_space *mapping,
struct inode *inode = mapping->host;
struct page *page;
struct buffer_head *bh;
- void *kaddr;
int err;
blocksize = 1 << inode->i_blkbits;
@@ -2534,11 +2511,7 @@ int block_truncate_page(struct address_space *mapping,
goto unlock;
}
- kaddr = kmap_atomic(page, KM_USER0);
- memset(kaddr + offset, 0, length);
- flush_dcache_page(page);
- kunmap_atomic(kaddr, KM_USER0);
-
+ zero_user_page(page, offset, length, KM_USER0);
mark_buffer_dirty(bh);
err = 0;
@@ -2559,7 +2532,6 @@ int block_write_full_page(struct page *page, get_block_t *get_block,
loff_t i_size = i_size_read(inode);
const pgoff_t end_index = i_size >> PAGE_CACHE_SHIFT;
unsigned offset;
- void *kaddr;
/* Is the page fully inside i_size? */
if (page->index < end_index)
@@ -2585,10 +2557,7 @@ int block_write_full_page(struct page *page, get_block_t *get_block,
* the page size, the remaining memory is zeroed when mapped, and
* writes to that region are not written out to the file."
*/
- kaddr = kmap_atomic(page, KM_USER0);
- memset(kaddr + offset, 0, PAGE_CACHE_SIZE - offset);
- flush_dcache_page(page);
- kunmap_atomic(kaddr, KM_USER0);
+ zero_user_page(page, offset, PAGE_CACHE_SIZE - offset, KM_USER0);
return __block_write_full_page(inode, page, get_block, wbc);
}
@@ -2930,8 +2899,9 @@ static void recalc_bh_state(void)
struct buffer_head *alloc_buffer_head(gfp_t gfp_flags)
{
- struct buffer_head *ret = kmem_cache_alloc(bh_cachep, gfp_flags);
+ struct buffer_head *ret = kmem_cache_zalloc(bh_cachep, gfp_flags);
if (ret) {
+ INIT_LIST_HEAD(&ret->b_assoc_buffers);
get_cpu_var(bh_accounting).nr++;
recalc_bh_state();
put_cpu_var(bh_accounting);
@@ -2950,17 +2920,6 @@ void free_buffer_head(struct buffer_head *bh)
}
EXPORT_SYMBOL(free_buffer_head);
-static void
-init_buffer_head(void *data, struct kmem_cache *cachep, unsigned long flags)
-{
- if (flags & SLAB_CTOR_CONSTRUCTOR) {
- struct buffer_head * bh = (struct buffer_head *)data;
-
- memset(bh, 0, sizeof(*bh));
- INIT_LIST_HEAD(&bh->b_assoc_buffers);
- }
-}
-
static void buffer_exit_cpu(int cpu)
{
int i;
@@ -2978,7 +2937,7 @@ static void buffer_exit_cpu(int cpu)
static int buffer_cpu_notify(struct notifier_block *self,
unsigned long action, void *hcpu)
{
- if (action == CPU_DEAD)
+ if (action == CPU_DEAD || action == CPU_DEAD_FROZEN)
buffer_exit_cpu((unsigned long)hcpu);
return NOTIFY_OK;
}
@@ -2987,12 +2946,8 @@ void __init buffer_init(void)
{
int nrpages;
- bh_cachep = kmem_cache_create("buffer_head",
- sizeof(struct buffer_head), 0,
- (SLAB_RECLAIM_ACCOUNT|SLAB_PANIC|
- SLAB_MEM_SPREAD),
- init_buffer_head,
- NULL);
+ bh_cachep = KMEM_CACHE(buffer_head,
+ SLAB_RECLAIM_ACCOUNT|SLAB_PANIC|SLAB_MEM_SPREAD);
/*
* Limit the bh occupancy to 10% of ZONE_NORMAL
diff --git a/fs/cifs/cifs_debug.c b/fs/cifs/cifs_debug.c
index 6017c465440..07838b2ac1c 100644
--- a/fs/cifs/cifs_debug.c
+++ b/fs/cifs/cifs_debug.c
@@ -7,16 +7,16 @@
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
+ * the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
- *
+ *
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See
* the GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
+ * along with this program; if not, write to the Free Software
* Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
*/
#include <linux/fs.h>
@@ -39,7 +39,7 @@ cifs_dump_mem(char *label, void *data, int length)
char *charptr = data;
char buf[10], line[80];
- printk(KERN_DEBUG "%s: dump of %d bytes of data at 0x%p\n",
+ printk(KERN_DEBUG "%s: dump of %d bytes of data at 0x%p\n",
label, length, data);
for (i = 0; i < length; i += 16) {
line[0] = 0;
@@ -60,10 +60,10 @@ cifs_dump_mem(char *label, void *data, int length)
#ifdef CONFIG_CIFS_DEBUG2
void cifs_dump_detail(struct smb_hdr * smb)
{
- cERROR(1,("Cmd: %d Err: 0x%x Flags: 0x%x Flgs2: 0x%x Mid: %d Pid: %d",
+ cERROR(1, ("Cmd: %d Err: 0x%x Flags: 0x%x Flgs2: 0x%x Mid: %d Pid: %d",
smb->Command, smb->Status.CifsError,
smb->Flags, smb->Flags2, smb->Mid, smb->Pid));
- cERROR(1,("smb buf %p len %d", smb, smbCalcSize_LE(smb)));
+ cERROR(1, ("smb buf %p len %d", smb, smbCalcSize_LE(smb)));
}
@@ -72,36 +72,35 @@ void cifs_dump_mids(struct TCP_Server_Info * server)
struct list_head *tmp;
struct mid_q_entry * mid_entry;
- if(server == NULL)
+ if (server == NULL)
return;
- cERROR(1,("Dump pending requests:"));
+ cERROR(1, ("Dump pending requests:"));
spin_lock(&GlobalMid_Lock);
list_for_each(tmp, &server->pending_mid_q) {
mid_entry = list_entry(tmp, struct mid_q_entry, qhead);
- if(mid_entry) {
- cERROR(1,("State: %d Cmd: %d Pid: %d Tsk: %p Mid %d",
+ if (mid_entry) {
+ cERROR(1, ("State: %d Cmd: %d Pid: %d Tsk: %p Mid %d",
mid_entry->midState,
(int)mid_entry->command,
mid_entry->pid,
mid_entry->tsk,
mid_entry->mid));
#ifdef CONFIG_CIFS_STATS2
- cERROR(1,("IsLarge: %d buf: %p time rcv: %ld now: %ld",
+ cERROR(1, ("IsLarge: %d buf: %p time rcv: %ld now: %ld",
mid_entry->largeBuf,
mid_entry->resp_buf,
mid_entry->when_received,
jiffies));
#endif /* STATS2 */
- cERROR(1,("IsMult: %d IsEnd: %d", mid_entry->multiRsp,
+ cERROR(1, ("IsMult: %d IsEnd: %d", mid_entry->multiRsp,
mid_entry->multiEnd));
- if(mid_entry->resp_buf) {
+ if (mid_entry->resp_buf) {
cifs_dump_detail(mid_entry->resp_buf);
cifs_dump_mem("existing buf: ",
mid_entry->resp_buf,
62 /* fixme */);
}
-
}
}
spin_unlock(&GlobalMid_Lock);
@@ -129,9 +128,10 @@ cifs_debug_data_read(char *buf, char **beginBuffer, off_t offset,
"Display Internal CIFS Data Structures for Debugging\n"
"---------------------------------------------------\n");
buf += length;
- length = sprintf(buf,"CIFS Version %s\n",CIFS_VERSION);
+ length = sprintf(buf, "CIFS Version %s\n", CIFS_VERSION);
buf += length;
- length = sprintf(buf,"Active VFS Requests: %d\n", GlobalTotalActiveXid);
+ length = sprintf(buf,
+ "Active VFS Requests: %d\n", GlobalTotalActiveXid);
buf += length;
length = sprintf(buf, "Servers:");
buf += length;
@@ -141,7 +141,7 @@ cifs_debug_data_read(char *buf, char **beginBuffer, off_t offset,
list_for_each(tmp, &GlobalSMBSessionList) {
i++;
ses = list_entry(tmp, struct cifsSesInfo, cifsSessionList);
- if((ses->serverDomain == NULL) || (ses->serverOS == NULL) ||
+ if ((ses->serverDomain == NULL) || (ses->serverOS == NULL) ||
(ses->serverNOS == NULL)) {
buf += sprintf(buf, "\nentry for %s not fully "
"displayed\n\t", ses->serverName);
@@ -149,15 +149,18 @@ cifs_debug_data_read(char *buf, char **beginBuffer, off_t offset,
} else {
length =
sprintf(buf,
- "\n%d) Name: %s Domain: %s Mounts: %d OS: %s \n\tNOS: %s\tCapability: 0x%x\n\tSMB session status: %d\t",
+ "\n%d) Name: %s Domain: %s Mounts: %d OS:"
+ " %s \n\tNOS: %s\tCapability: 0x%x\n\tSMB"
+ " session status: %d\t",
i, ses->serverName, ses->serverDomain,
atomic_read(&ses->inUse),
ses->serverOS, ses->serverNOS,
- ses->capabilities,ses->status);
+ ses->capabilities, ses->status);
buf += length;
}
- if(ses->server) {
- buf += sprintf(buf, "TCP status: %d\n\tLocal Users To Server: %d SecMode: 0x%x Req On Wire: %d",
+ if (ses->server) {
+ buf += sprintf(buf, "TCP status: %d\n\tLocal Users To "
+ "Server: %d SecMode: 0x%x Req On Wire: %d",
ses->server->tcpStatus,
atomic_read(&ses->server->socketUseCount),
ses->server->secMode,
@@ -165,7 +168,7 @@ cifs_debug_data_read(char *buf, char **beginBuffer, off_t offset,
#ifdef CONFIG_CIFS_STATS2
buf += sprintf(buf, " In Send: %d In MaxReq Wait: %d",
- atomic_read(&ses->server->inSend),
+ atomic_read(&ses->server->inSend),
atomic_read(&ses->server->num_waiters));
#endif
@@ -177,17 +180,19 @@ cifs_debug_data_read(char *buf, char **beginBuffer, off_t offset,
mid_entry = list_entry(tmp1, struct
mid_q_entry,
qhead);
- if(mid_entry) {
- length = sprintf(buf,"State: %d com: %d pid: %d tsk: %p mid %d\n",
- mid_entry->midState,
- (int)mid_entry->command,
- mid_entry->pid,
- mid_entry->tsk,
- mid_entry->mid);
+ if (mid_entry) {
+ length = sprintf(buf,
+ "State: %d com: %d pid:"
+ " %d tsk: %p mid %d\n",
+ mid_entry->midState,
+ (int)mid_entry->command,
+ mid_entry->pid,
+ mid_entry->tsk,
+ mid_entry->mid);
buf += length;
}
}
- spin_unlock(&GlobalMid_Lock);
+ spin_unlock(&GlobalMid_Lock);
}
}
@@ -207,7 +212,8 @@ cifs_debug_data_read(char *buf, char **beginBuffer, off_t offset,
dev_type = le32_to_cpu(tcon->fsDevInfo.DeviceType);
length =
sprintf(buf,
- "\n%d) %s Uses: %d Type: %s DevInfo: 0x%x Attributes: 0x%x\nPathComponentMax: %d Status: %d",
+ "\n%d) %s Uses: %d Type: %s DevInfo: 0x%x "
+ "Attributes: 0x%x\nPathComponentMax: %d Status: %d",
i, tcon->treeName,
atomic_read(&tcon->useCount),
tcon->nativeFileSystem,
@@ -215,7 +221,7 @@ cifs_debug_data_read(char *buf, char **beginBuffer, off_t offset,
le32_to_cpu(tcon->fsAttrInfo.Attributes),
le32_to_cpu(tcon->fsAttrInfo.MaxPathNameComponentLength),
tcon->tidStatus);
- buf += length;
+ buf += length;
if (dev_type == FILE_DEVICE_DISK)
length = sprintf(buf, " type: DISK ");
else if (dev_type == FILE_DEVICE_CD_ROM)
@@ -224,7 +230,7 @@ cifs_debug_data_read(char *buf, char **beginBuffer, off_t offset,
length =
sprintf(buf, " type: %d ", dev_type);
buf += length;
- if(tcon->tidStatus == CifsNeedReconnect) {
+ if (tcon->tidStatus == CifsNeedReconnect) {
buf += sprintf(buf, "\tDISCONNECTED ");
length += 14;
}
@@ -238,9 +244,9 @@ cifs_debug_data_read(char *buf, char **beginBuffer, off_t offset,
/* Now calculate total size of returned data */
length = buf - original_buf;
- if(offset + count >= length)
+ if (offset + count >= length)
*eof = 1;
- if(length < offset) {
+ if (length < offset) {
*eof = 1;
return 0;
} else {
@@ -256,18 +262,18 @@ cifs_debug_data_read(char *buf, char **beginBuffer, off_t offset,
static int
cifs_stats_write(struct file *file, const char __user *buffer,
- unsigned long count, void *data)
+ unsigned long count, void *data)
{
- char c;
- int rc;
+ char c;
+ int rc;
struct list_head *tmp;
struct cifsTconInfo *tcon;
- rc = get_user(c, buffer);
- if (rc)
- return rc;
+ rc = get_user(c, buffer);
+ if (rc)
+ return rc;
- if (c == '1' || c == 'y' || c == 'Y' || c == '0') {
+ if (c == '1' || c == 'y' || c == 'Y' || c == '0') {
read_lock(&GlobalSMBSeslock);
#ifdef CONFIG_CIFS_STATS2
atomic_set(&totBufAllocCount, 0);
@@ -297,14 +303,14 @@ cifs_stats_write(struct file *file, const char __user *buffer,
read_unlock(&GlobalSMBSeslock);
}
- return count;
+ return count;
}
static int
cifs_stats_read(char *buf, char **beginBuffer, off_t offset,
int count, int *eof, void *data)
{
- int item_length,i,length;
+ int item_length, i, length;
struct list_head *tmp;
struct cifsTconInfo *tcon;
@@ -314,44 +320,44 @@ cifs_stats_read(char *buf, char **beginBuffer, off_t offset,
"Resources in use\nCIFS Session: %d\n",
sesInfoAllocCount.counter);
buf += length;
- item_length =
- sprintf(buf,"Share (unique mount targets): %d\n",
+ item_length =
+ sprintf(buf, "Share (unique mount targets): %d\n",
tconInfoAllocCount.counter);
length += item_length;
- buf += item_length;
- item_length =
- sprintf(buf,"SMB Request/Response Buffer: %d Pool size: %d\n",
+ buf += item_length;
+ item_length =
+ sprintf(buf, "SMB Request/Response Buffer: %d Pool size: %d\n",
bufAllocCount.counter,
cifs_min_rcv + tcpSesAllocCount.counter);
length += item_length;
buf += item_length;
- item_length =
- sprintf(buf,"SMB Small Req/Resp Buffer: %d Pool size: %d\n",
- smBufAllocCount.counter,cifs_min_small);
+ item_length =
+ sprintf(buf, "SMB Small Req/Resp Buffer: %d Pool size: %d\n",
+ smBufAllocCount.counter, cifs_min_small);
length += item_length;
buf += item_length;
#ifdef CONFIG_CIFS_STATS2
- item_length = sprintf(buf, "Total Large %d Small %d Allocations\n",
+ item_length = sprintf(buf, "Total Large %d Small %d Allocations\n",
atomic_read(&totBufAllocCount),
- atomic_read(&totSmBufAllocCount));
+ atomic_read(&totSmBufAllocCount));
length += item_length;
buf += item_length;
#endif /* CONFIG_CIFS_STATS2 */
- item_length =
- sprintf(buf,"Operations (MIDs): %d\n",
+ item_length =
+ sprintf(buf, "Operations (MIDs): %d\n",
midCount.counter);
length += item_length;
buf += item_length;
item_length = sprintf(buf,
"\n%d session %d share reconnects\n",
- tcpSesReconnectCount.counter,tconInfoReconnectCount.counter);
+ tcpSesReconnectCount.counter, tconInfoReconnectCount.counter);
length += item_length;
buf += item_length;
item_length = sprintf(buf,
"Total vfs operations: %d maximum at one time: %d\n",
- GlobalCurrentXid,GlobalMaxActiveXid);
+ GlobalCurrentXid, GlobalMaxActiveXid);
length += item_length;
buf += item_length;
@@ -360,10 +366,10 @@ cifs_stats_read(char *buf, char **beginBuffer, off_t offset,
list_for_each(tmp, &GlobalTreeConnectionList) {
i++;
tcon = list_entry(tmp, struct cifsTconInfo, cifsConnectionList);
- item_length = sprintf(buf,"\n%d) %s",i, tcon->treeName);
+ item_length = sprintf(buf, "\n%d) %s", i, tcon->treeName);
buf += item_length;
length += item_length;
- if(tcon->tidStatus == CifsNeedReconnect) {
+ if (tcon->tidStatus == CifsNeedReconnect) {
buf += sprintf(buf, "\tDISCONNECTED ");
length += 14;
}
@@ -380,15 +386,15 @@ cifs_stats_read(char *buf, char **beginBuffer, off_t offset,
item_length = sprintf(buf, "\nWrites: %d Bytes: %lld",
atomic_read(&tcon->num_writes),
(long long)(tcon->bytes_written));
- buf += item_length;
- length += item_length;
- item_length = sprintf(buf,
+ buf += item_length;
+ length += item_length;
+ item_length = sprintf(buf,
"\nLocks: %d HardLinks: %d Symlinks: %d",
- atomic_read(&tcon->num_locks),
+ atomic_read(&tcon->num_locks),
atomic_read(&tcon->num_hardlinks),
atomic_read(&tcon->num_symlinks));
- buf += item_length;
- length += item_length;
+ buf += item_length;
+ length += item_length;
item_length = sprintf(buf, "\nOpens: %d Closes: %d Deletes: %d",
atomic_read(&tcon->num_opens),
@@ -415,12 +421,12 @@ cifs_stats_read(char *buf, char **beginBuffer, off_t offset,
}
read_unlock(&GlobalSMBSeslock);
- buf += sprintf(buf,"\n");
+ buf += sprintf(buf, "\n");
length++;
- if(offset + count >= length)
+ if (offset + count >= length)
*eof = 1;
- if(length < offset) {
+ if (length < offset) {
*eof = 1;
return 0;
} else {
@@ -428,7 +434,7 @@ cifs_stats_read(char *buf, char **beginBuffer, off_t offset,
}
if (length > count)
length = count;
-
+
return length;
}
#endif
@@ -547,11 +553,11 @@ cifs_proc_clean(void)
remove_proc_entry("MultiuserMount", proc_fs_cifs);
remove_proc_entry("OplockEnabled", proc_fs_cifs);
/* remove_proc_entry("NTLMV2Enabled",proc_fs_cifs); */
- remove_proc_entry("SecurityFlags",proc_fs_cifs);
-/* remove_proc_entry("PacketSigningEnabled",proc_fs_cifs); */
- remove_proc_entry("LinuxExtensionsEnabled",proc_fs_cifs);
- remove_proc_entry("Experimental",proc_fs_cifs);
- remove_proc_entry("LookupCacheEnabled",proc_fs_cifs);
+ remove_proc_entry("SecurityFlags", proc_fs_cifs);
+/* remove_proc_entry("PacketSigningEnabled", proc_fs_cifs); */
+ remove_proc_entry("LinuxExtensionsEnabled", proc_fs_cifs);
+ remove_proc_entry("Experimental", proc_fs_cifs);
+ remove_proc_entry("LookupCacheEnabled", proc_fs_cifs);
remove_proc_entry("cifs", proc_root_fs);
}
@@ -590,7 +596,7 @@ cifsFYI_write(struct file *file, const char __user *buffer,
cifsFYI = 0;
else if (c == '1' || c == 'y' || c == 'Y')
cifsFYI = 1;
- else if((c > '1') && (c <= '9'))
+ else if ((c > '1') && (c <= '9'))
cifsFYI = (int) (c - '0'); /* see cifs_debug.h for meanings */
return count;
@@ -637,28 +643,28 @@ oplockEnabled_write(struct file *file, const char __user *buffer,
static int
experimEnabled_read(char *page, char **start, off_t off,
- int count, int *eof, void *data)
+ int count, int *eof, void *data)
{
- int len;
+ int len;
- len = sprintf(page, "%d\n", experimEnabled);
+ len = sprintf(page, "%d\n", experimEnabled);
- len -= off;
- *start = page + off;
+ len -= off;
+ *start = page + off;
- if (len > count)
- len = count;
- else
- *eof = 1;
+ if (len > count)
+ len = count;
+ else
+ *eof = 1;
- if (len < 0)
- len = 0;
+ if (len < 0)
+ len = 0;
- return len;
+ return len;
}
static int
experimEnabled_write(struct file *file, const char __user *buffer,
- unsigned long count, void *data)
+ unsigned long count, void *data)
{
char c;
int rc;
@@ -678,46 +684,46 @@ experimEnabled_write(struct file *file, const char __user *buffer,
static int
linuxExtensionsEnabled_read(char *page, char **start, off_t off,
- int count, int *eof, void *data)
+ int count, int *eof, void *data)
{
- int len;
+ int len;
- len = sprintf(page, "%d\n", linuxExtEnabled);
- len -= off;
- *start = page + off;
+ len = sprintf(page, "%d\n", linuxExtEnabled);
+ len -= off;
+ *start = page + off;
- if (len > count)
- len = count;
- else
- *eof = 1;
+ if (len > count)
+ len = count;
+ else
+ *eof = 1;
- if (len < 0)
- len = 0;
+ if (len < 0)
+ len = 0;
- return len;
+ return len;
}
static int
linuxExtensionsEnabled_write(struct file *file, const char __user *buffer,
- unsigned long count, void *data)
+ unsigned long count, void *data)
{
- char c;
- int rc;
-
- rc = get_user(c, buffer);
- if (rc)
- return rc;
- if (c == '0' || c == 'n' || c == 'N')
- linuxExtEnabled = 0;
- else if (c == '1' || c == 'y' || c == 'Y')
- linuxExtEnabled = 1;
-
- return count;
+ char c;
+ int rc;
+
+ rc = get_user(c, buffer);
+ if (rc)
+ return rc;
+ if (c == '0' || c == 'n' || c == 'N')
+ linuxExtEnabled = 0;
+ else if (c == '1' || c == 'y' || c == 'Y')
+ linuxExtEnabled = 1;
+
+ return count;
}
static int
lookupFlag_read(char *page, char **start, off_t off,
- int count, int *eof, void *data)
+ int count, int *eof, void *data)
{
int len;
@@ -860,15 +866,15 @@ security_flags_write(struct file *file, const char __user *buffer,
char flags_string[12];
char c;
- if((count < 1) || (count > 11))
+ if ((count < 1) || (count > 11))
return -EINVAL;
memset(flags_string, 0, 12);
- if(copy_from_user(flags_string, buffer, count))
+ if (copy_from_user(flags_string, buffer, count))
return -EFAULT;
- if(count < 3) {
+ if (count < 3) {
/* single char or single char followed by null */
c = flags_string[0];
if (c == '0' || c == 'n' || c == 'N')
@@ -881,15 +887,15 @@ security_flags_write(struct file *file, const char __user *buffer,
flags = simple_strtoul(flags_string, NULL, 0);
- cFYI(1,("sec flags 0x%x", flags));
+ cFYI(1, ("sec flags 0x%x", flags));
- if(flags <= 0) {
- cERROR(1,("invalid security flags %s",flags_string));
+ if (flags <= 0) {
+ cERROR(1, ("invalid security flags %s", flags_string));
return -EINVAL;
}
- if(flags & ~CIFSSEC_MASK) {
- cERROR(1,("attempt to set unsupported security flags 0x%x",
+ if (flags & ~CIFSSEC_MASK) {
+ cERROR(1, ("attempt to set unsupported security flags 0x%x",
flags & ~CIFSSEC_MASK));
return -EINVAL;
}
diff --git a/fs/cifs/cifs_unicode.c b/fs/cifs/cifs_unicode.c
index 793c4b95c16..701e9a9185f 100644
--- a/fs/cifs/cifs_unicode.c
+++ b/fs/cifs/cifs_unicode.c
@@ -6,16 +6,16 @@
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
+ * the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
- *
+ *
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See
* the GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
+ * along with this program; if not, write to the Free Software
* Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
*/
#include <linux/fs.h>
@@ -32,7 +32,7 @@
*
*/
int
-cifs_strfromUCS_le(char *to, const __le16 * from,
+cifs_strfromUCS_le(char *to, const __le16 * from,
int len, const struct nls_table *codepage)
{
int i;
@@ -66,7 +66,7 @@ cifs_strtoUCS(__le16 * to, const char *from, int len,
{
int charlen;
int i;
- wchar_t * wchar_to = (wchar_t *)to; /* needed to quiet sparse */
+ wchar_t * wchar_to = (wchar_t *)to; /* needed to quiet sparse */
for (i = 0; len && *from; i++, from += charlen, len -= charlen) {
@@ -79,7 +79,7 @@ cifs_strtoUCS(__le16 * to, const char *from, int len,
/* A question mark */
to[i] = cpu_to_le16(0x003f);
charlen = 1;
- } else
+ } else
to[i] = cpu_to_le16(wchar_to[i]);
}
diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c
index 8568e100953..7c04752b76c 100644
--- a/fs/cifs/cifsfs.c
+++ b/fs/cifs/cifsfs.c
@@ -701,10 +701,8 @@ cifs_init_once(void *inode, struct kmem_cache * cachep, unsigned long flags)
{
struct cifsInodeInfo *cifsi = inode;
- if (flags & SLAB_CTOR_CONSTRUCTOR) {
- inode_init_once(&cifsi->vfs_inode);
- INIT_LIST_HEAD(&cifsi->lockList);
- }
+ inode_init_once(&cifsi->vfs_inode);
+ INIT_LIST_HEAD(&cifsi->lockList);
}
static int
@@ -827,8 +825,8 @@ cifs_init_mids(void)
sizeof (struct oplock_q_entry), 0,
SLAB_HWCACHE_ALIGN, NULL, NULL);
if (cifs_oplock_cachep == NULL) {
- kmem_cache_destroy(cifs_mid_cachep);
mempool_destroy(cifs_mid_poolp);
+ kmem_cache_destroy(cifs_mid_cachep);
return -ENOMEM;
}
diff --git a/fs/cifs/cifssmb.c b/fs/cifs/cifssmb.c
index 14de58fa143..57419a17668 100644
--- a/fs/cifs/cifssmb.c
+++ b/fs/cifs/cifssmb.c
@@ -433,8 +433,8 @@ CIFSSMBNegotiate(unsigned int xid, struct cifsSesInfo *ses)
cFYI(1,("secFlags 0x%x",secFlags));
pSMB->hdr.Mid = GetNextMid(server);
- pSMB->hdr.Flags2 |= SMBFLG2_UNICODE;
- if((secFlags & CIFSSEC_MUST_KRB5) == CIFSSEC_MUST_KRB5)
+ pSMB->hdr.Flags2 |= (SMBFLG2_UNICODE | SMBFLG2_ERR_STATUS);
+ if ((secFlags & CIFSSEC_MUST_KRB5) == CIFSSEC_MUST_KRB5)
pSMB->hdr.Flags2 |= SMBFLG2_EXT_SEC;
count = 0;
diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c
index 216fb625843..f4e92661b22 100644
--- a/fs/cifs/connect.c
+++ b/fs/cifs/connect.c
@@ -2069,8 +2069,15 @@ cifs_mount(struct super_block *sb, struct cifs_sb_info *cifs_sb,
srvTcp->tcpStatus = CifsExiting;
spin_unlock(&GlobalMid_Lock);
if (srvTcp->tsk) {
+ struct task_struct *tsk;
+ /* If we could verify that kthread_stop would
+ always wake up processes blocked in
+ tcp in recv_mesg then we could remove the
+ send_sig call */
send_sig(SIGKILL,srvTcp->tsk,1);
- kthread_stop(srvTcp->tsk);
+ tsk = srvTcp->tsk;
+ if(tsk)
+ kthread_stop(tsk);
}
}
/* If find_unc succeeded then rc == 0 so we can not end */
@@ -2085,8 +2092,11 @@ cifs_mount(struct super_block *sb, struct cifs_sb_info *cifs_sb,
/* if the socketUseCount is now zero */
if ((temp_rc == -ESHUTDOWN) &&
(pSesInfo->server) && (pSesInfo->server->tsk)) {
+ struct task_struct *tsk;
send_sig(SIGKILL,pSesInfo->server->tsk,1);
- kthread_stop(pSesInfo->server->tsk);
+ tsk = pSesInfo->server->tsk;
+ if (tsk)
+ kthread_stop(tsk);
}
} else
cFYI(1, ("No session or bad tcon"));
@@ -3334,7 +3344,7 @@ cifs_umount(struct super_block *sb, struct cifs_sb_info *cifs_sb)
return 0;
} else if (rc == -ESHUTDOWN) {
cFYI(1,("Waking up socket by sending it signal"));
- if(cifsd_task) {
+ if (cifsd_task) {
send_sig(SIGKILL,cifsd_task,1);
kthread_stop(cifsd_task);
}
diff --git a/fs/cifs/dir.c b/fs/cifs/dir.c
index e5210519ac4..8e86aaceb68 100644
--- a/fs/cifs/dir.c
+++ b/fs/cifs/dir.c
@@ -2,7 +2,7 @@
* fs/cifs/dir.c
*
* vfs operations that deal with dentries
- *
+ *
* Copyright (C) International Business Machines Corp., 2002,2005
* Author(s): Steve French (sfrench@us.ibm.com)
*
@@ -34,11 +34,12 @@
static void
renew_parental_timestamps(struct dentry *direntry)
{
- /* BB check if there is a way to get the kernel to do this or if we really need this */
+ /* BB check if there is a way to get the kernel to do this or if we
+ really need this */
do {
direntry->d_time = jiffies;
direntry = direntry->d_parent;
- } while (!IS_ROOT(direntry));
+ } while (!IS_ROOT(direntry));
}
/* Note: caller must free return buffer */
@@ -51,7 +52,7 @@ build_path_from_dentry(struct dentry *direntry)
char *full_path;
char dirsep;
- if(direntry == NULL)
+ if (direntry == NULL)
return NULL; /* not much we can do if dentry is freed and
we need to reopen the file after it was closed implicitly
when the server crashed */
@@ -59,18 +60,18 @@ build_path_from_dentry(struct dentry *direntry)
dirsep = CIFS_DIR_SEP(CIFS_SB(direntry->d_sb));
pplen = CIFS_SB(direntry->d_sb)->prepathlen;
cifs_bp_rename_retry:
- namelen = pplen;
+ namelen = pplen;
for (temp = direntry; !IS_ROOT(temp);) {
namelen += (1 + temp->d_name.len);
temp = temp->d_parent;
- if(temp == NULL) {
- cERROR(1,("corrupt dentry"));
+ if (temp == NULL) {
+ cERROR(1, ("corrupt dentry"));
return NULL;
}
}
full_path = kmalloc(namelen+1, GFP_KERNEL);
- if(full_path == NULL)
+ if (full_path == NULL)
return full_path;
full_path[namelen] = 0; /* trailing null */
for (temp = direntry; !IS_ROOT(temp);) {
@@ -84,8 +85,8 @@ cifs_bp_rename_retry:
cFYI(0, ("name: %s", full_path + namelen));
}
temp = temp->d_parent;
- if(temp == NULL) {
- cERROR(1,("corrupt dentry"));
+ if (temp == NULL) {
+ cERROR(1, ("corrupt dentry"));
kfree(full_path);
return NULL;
}
@@ -94,7 +95,7 @@ cifs_bp_rename_retry:
cERROR(1,
("did not end path lookup where expected namelen is %d",
namelen));
- /* presumably this is only possible if racing with a rename
+ /* 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);
@@ -106,7 +107,7 @@ cifs_bp_rename_retry:
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 */
- strncpy(full_path,CIFS_SB(direntry->d_sb)->prepath,pplen);
+ strncpy(full_path, CIFS_SB(direntry->d_sb)->prepath, pplen);
return full_path;
}
@@ -147,12 +148,12 @@ cifs_create(struct inode *inode, struct dentry *direntry, int mode,
pTcon = cifs_sb->tcon;
full_path = build_path_from_dentry(direntry);
- if(full_path == NULL) {
+ if (full_path == NULL) {
FreeXid(xid);
return -ENOMEM;
}
- if(nd && (nd->flags & LOOKUP_OPEN)) {
+ if (nd && (nd->flags & LOOKUP_OPEN)) {
int oflags = nd->intent.open.flags;
desiredAccess = 0;
@@ -164,28 +165,29 @@ cifs_create(struct inode *inode, struct dentry *direntry, int mode,
write_only = TRUE;
}
- if((oflags & (O_CREAT | O_EXCL)) == (O_CREAT | O_EXCL))
+ if ((oflags & (O_CREAT | O_EXCL)) == (O_CREAT | O_EXCL))
disposition = FILE_CREATE;
- else if((oflags & (O_CREAT | O_TRUNC)) == (O_CREAT | O_TRUNC))
+ else if ((oflags & (O_CREAT | O_TRUNC)) == (O_CREAT | O_TRUNC))
disposition = FILE_OVERWRITE_IF;
- else if((oflags & O_CREAT) == O_CREAT)
+ else if ((oflags & O_CREAT) == O_CREAT)
disposition = FILE_OPEN_IF;
else {
- cFYI(1,("Create flag not set in create function"));
+ cFYI(1, ("Create flag not set in create function"));
}
}
- /* BB add processing to set equivalent of mode - e.g. via CreateX with ACLs */
+ /* BB add processing to set equivalent of mode - e.g. via CreateX with
+ ACLs */
if (oplockEnabled)
oplock = REQ_OPLOCK;
- buf = kmalloc(sizeof(FILE_ALL_INFO),GFP_KERNEL);
- if(buf == NULL) {
+ buf = kmalloc(sizeof(FILE_ALL_INFO), GFP_KERNEL);
+ if (buf == NULL) {
kfree(full_path);
FreeXid(xid);
return -ENOMEM;
}
- if (cifs_sb->tcon->ses->capabilities & CAP_NT_SMBS)
+ if (cifs_sb->tcon->ses->capabilities & CAP_NT_SMBS)
rc = CIFSSMBOpen(xid, pTcon, full_path, disposition,
desiredAccess, CREATE_NOT_DIR,
&fileHandle, &oplock, buf, cifs_sb->local_nls,
@@ -193,27 +195,28 @@ cifs_create(struct inode *inode, struct dentry *direntry, int mode,
else
rc = -EIO; /* no NT SMB support fall into legacy open below */
- if(rc == -EIO) {
+ if (rc == -EIO) {
/* old server, retry the open legacy style */
rc = SMBLegacyOpen(xid, pTcon, full_path, disposition,
desiredAccess, CREATE_NOT_DIR,
&fileHandle, &oplock, buf, cifs_sb->local_nls,
cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MAP_SPECIAL_CHR);
- }
+ }
if (rc) {
cFYI(1, ("cifs_create returned 0x%x", rc));
} else {
/* If Open reported that we actually created a file
then we now have to set the mode if possible */
if ((cifs_sb->tcon->ses->capabilities & CAP_UNIX) &&
- (oplock & CIFS_CREATE_ACTION))
- if(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SET_UID) {
+ (oplock & CIFS_CREATE_ACTION)) {
+ mode &= ~current->fs->umask;
+ if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SET_UID) {
CIFSSMBUnixSetPerms(xid, pTcon, full_path, mode,
(__u64)current->fsuid,
(__u64)current->fsgid,
0 /* dev */,
- cifs_sb->local_nls,
- cifs_sb->mnt_cifs_flags &
+ cifs_sb->local_nls,
+ cifs_sb->mnt_cifs_flags &
CIFS_MOUNT_MAP_SPECIAL_CHR);
} else {
CIFSSMBUnixSetPerms(xid, pTcon, full_path, mode,
@@ -221,26 +224,28 @@ cifs_create(struct inode *inode, struct dentry *direntry, int mode,
(__u64)-1,
0 /* dev */,
cifs_sb->local_nls,
- cifs_sb->mnt_cifs_flags &
+ cifs_sb->mnt_cifs_flags &
CIFS_MOUNT_MAP_SPECIAL_CHR);
}
- else {
- /* BB implement mode setting via Windows security descriptors */
- /* eg CIFSSMBWinSetPerms(xid,pTcon,full_path,mode,-1,-1,local_nls);*/
- /* could set r/o dos attribute if mode & 0222 == 0 */
+ } else {
+ /* BB implement mode setting via Windows security
+ descriptors e.g. */
+ /* CIFSSMBWinSetPerms(xid,pTcon,path,mode,-1,-1,nls);*/
+
+ /* Could set r/o dos attribute if mode & 0222 == 0 */
}
/* BB server might mask mode so we have to query for Unix case*/
if (pTcon->ses->capabilities & CAP_UNIX)
rc = cifs_get_inode_info_unix(&newinode, full_path,
- inode->i_sb,xid);
+ inode->i_sb, xid);
else {
rc = cifs_get_inode_info(&newinode, full_path,
- buf, inode->i_sb,xid);
- if(newinode) {
+ buf, inode->i_sb, xid);
+ if (newinode) {
newinode->i_mode = mode;
- if((oplock & CIFS_CREATE_ACTION) &&
- (cifs_sb->mnt_cifs_flags &
+ if ((oplock & CIFS_CREATE_ACTION) &&
+ (cifs_sb->mnt_cifs_flags &
CIFS_MOUNT_SET_UID)) {
newinode->i_uid = current->fsuid;
newinode->i_gid = current->fsgid;
@@ -259,14 +264,14 @@ cifs_create(struct inode *inode, struct dentry *direntry, int mode,
direntry->d_op = &cifs_dentry_ops;
d_instantiate(direntry, newinode);
}
- if((nd->flags & LOOKUP_OPEN) == FALSE) {
+ if ((nd->flags & LOOKUP_OPEN) == FALSE) {
/* mknod case - do not leave file open */
CIFSSMBClose(xid, pTcon, fileHandle);
- } else if(newinode) {
+ } else if (newinode) {
pCifsFile =
kzalloc(sizeof (struct cifsFileInfo), GFP_KERNEL);
-
- if(pCifsFile == NULL)
+
+ if (pCifsFile == NULL)
goto cifs_create_out;
pCifsFile->netfid = fileHandle;
pCifsFile->pid = current->tgid;
@@ -276,33 +281,33 @@ cifs_create(struct inode *inode, struct dentry *direntry, int mode,
init_MUTEX(&pCifsFile->fh_sem);
mutex_init(&pCifsFile->lock_mutex);
INIT_LIST_HEAD(&pCifsFile->llist);
- atomic_set(&pCifsFile->wrtPending,0);
+ atomic_set(&pCifsFile->wrtPending, 0);
- /* set the following in open now
+ /* set the following in open now
pCifsFile->pfile = file; */
write_lock(&GlobalSMBSeslock);
- list_add(&pCifsFile->tlist,&pTcon->openFileList);
+ list_add(&pCifsFile->tlist, &pTcon->openFileList);
pCifsInode = CIFS_I(newinode);
- if(pCifsInode) {
+ if (pCifsInode) {
/* if readable file instance put first in list*/
if (write_only == TRUE) {
- list_add_tail(&pCifsFile->flist,
+ list_add_tail(&pCifsFile->flist,
&pCifsInode->openFileList);
} else {
list_add(&pCifsFile->flist,
&pCifsInode->openFileList);
}
- if((oplock & 0xF) == OPLOCK_EXCLUSIVE) {
+ if ((oplock & 0xF) == OPLOCK_EXCLUSIVE) {
pCifsInode->clientCanCacheAll = TRUE;
pCifsInode->clientCanCacheRead = TRUE;
- cFYI(1,("Exclusive Oplock for inode %p",
+ cFYI(1, ("Exclusive Oplock inode %p",
newinode));
- } else if((oplock & 0xF) == OPLOCK_READ)
+ } else if ((oplock & 0xF) == OPLOCK_READ)
pCifsInode->clientCanCacheRead = TRUE;
}
write_unlock(&GlobalSMBSeslock);
}
- }
+ }
cifs_create_out:
kfree(buf);
kfree(full_path);
@@ -310,8 +315,8 @@ cifs_create_out:
return rc;
}
-int cifs_mknod(struct inode *inode, struct dentry *direntry, int mode,
- dev_t device_number)
+int cifs_mknod(struct inode *inode, struct dentry *direntry, int mode,
+ dev_t device_number)
{
int rc = -EPERM;
int xid;
@@ -329,43 +334,45 @@ int cifs_mknod(struct inode *inode, struct dentry *direntry, int mode,
pTcon = cifs_sb->tcon;
full_path = build_path_from_dentry(direntry);
- if(full_path == NULL)
+ if (full_path == NULL)
rc = -ENOMEM;
else if (pTcon->ses->capabilities & CAP_UNIX) {
- if(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SET_UID) {
+ mode &= ~current->fs->umask;
+ if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SET_UID) {
rc = CIFSSMBUnixSetPerms(xid, pTcon, full_path,
- mode,(__u64)current->fsuid,(__u64)current->fsgid,
+ mode, (__u64)current->fsuid,
+ (__u64)current->fsgid,
device_number, cifs_sb->local_nls,
- cifs_sb->mnt_cifs_flags &
+ cifs_sb->mnt_cifs_flags &
CIFS_MOUNT_MAP_SPECIAL_CHR);
} else {
rc = CIFSSMBUnixSetPerms(xid, pTcon,
full_path, mode, (__u64)-1, (__u64)-1,
device_number, cifs_sb->local_nls,
- cifs_sb->mnt_cifs_flags &
+ cifs_sb->mnt_cifs_flags &
CIFS_MOUNT_MAP_SPECIAL_CHR);
}
- if(!rc) {
+ if (!rc) {
rc = cifs_get_inode_info_unix(&newinode, full_path,
- inode->i_sb,xid);
+ inode->i_sb, xid);
if (pTcon->nocase)
direntry->d_op = &cifs_ci_dentry_ops;
else
direntry->d_op = &cifs_dentry_ops;
- if(rc == 0)
+ if (rc == 0)
d_instantiate(direntry, newinode);
}
} else {
- if(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_UNX_EMUL) {
+ if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_UNX_EMUL) {
int oplock = 0;
u16 fileHandle;
FILE_ALL_INFO * buf;
- cFYI(1,("sfu compat create special file"));
+ cFYI(1, ("sfu compat create special file"));
- buf = kmalloc(sizeof(FILE_ALL_INFO),GFP_KERNEL);
- if(buf == NULL) {
+ buf = kmalloc(sizeof(FILE_ALL_INFO), GFP_KERNEL);
+ if (buf == NULL) {
kfree(full_path);
FreeXid(xid);
return -ENOMEM;
@@ -373,39 +380,38 @@ int cifs_mknod(struct inode *inode, struct dentry *direntry, int mode,
rc = CIFSSMBOpen(xid, pTcon, full_path,
FILE_CREATE, /* fail if exists */
- GENERIC_WRITE /* BB would
+ GENERIC_WRITE /* BB would
WRITE_OWNER | WRITE_DAC be better? */,
/* Create a file and set the
file attribute to SYSTEM */
CREATE_NOT_DIR | CREATE_OPTION_SPECIAL,
&fileHandle, &oplock, buf,
cifs_sb->local_nls,
- cifs_sb->mnt_cifs_flags &
+ cifs_sb->mnt_cifs_flags &
CIFS_MOUNT_MAP_SPECIAL_CHR);
/* BB FIXME - add handling for backlevel servers
which need legacy open and check for all
- calls to SMBOpen for fallback to
- SMBLeagcyOpen */
- if(!rc) {
+ calls to SMBOpen for fallback to SMBLeagcyOpen */
+ if (!rc) {
/* BB Do not bother to decode buf since no
local inode yet to put timestamps in,
but we can reuse it safely */
int bytes_written;
struct win_dev *pdev;
pdev = (struct win_dev *)buf;
- if(S_ISCHR(mode)) {
+ if (S_ISCHR(mode)) {
memcpy(pdev->type, "IntxCHR", 8);
pdev->major =
cpu_to_le64(MAJOR(device_number));
- pdev->minor =
+ pdev->minor =
cpu_to_le64(MINOR(device_number));
rc = CIFSSMBWrite(xid, pTcon,
fileHandle,
sizeof(struct win_dev),
0, &bytes_written, (char *)pdev,
NULL, 0);
- } else if(S_ISBLK(mode)) {
+ } else if (S_ISBLK(mode)) {
memcpy(pdev->type, "IntxBLK", 8);
pdev->major =
cpu_to_le64(MAJOR(device_number));
@@ -432,7 +438,8 @@ int cifs_mknod(struct inode *inode, struct dentry *direntry, int mode,
struct dentry *
-cifs_lookup(struct inode *parent_dir_inode, struct dentry *direntry, struct nameidata *nd)
+cifs_lookup(struct inode *parent_dir_inode, struct dentry *direntry,
+ struct nameidata *nd)
{
int xid;
int rc = 0; /* to get around spurious gcc warning, set to zero here */
@@ -447,8 +454,6 @@ cifs_lookup(struct inode *parent_dir_inode, struct dentry *direntry, struct name
(" parent inode = 0x%p name is: %s and dentry = 0x%p",
parent_dir_inode, direntry->d_name.name, direntry));
- /* BB Add check of incoming data - e.g. frame not longer than maximum SMB - let server check the namelen BB */
-
/* check whether path exists */
cifs_sb = CIFS_SB(parent_dir_inode->i_sb);
@@ -472,7 +477,7 @@ cifs_lookup(struct inode *parent_dir_inode, struct dentry *direntry, struct name
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) {
+ if (full_path == NULL) {
FreeXid(xid);
return ERR_PTR(-ENOMEM);
}
@@ -487,10 +492,10 @@ cifs_lookup(struct inode *parent_dir_inode, struct dentry *direntry, struct name
if (pTcon->ses->capabilities & CAP_UNIX)
rc = cifs_get_inode_info_unix(&newInode, full_path,
- parent_dir_inode->i_sb,xid);
+ parent_dir_inode->i_sb, xid);
else
rc = cifs_get_inode_info(&newInode, full_path, NULL,
- parent_dir_inode->i_sb,xid);
+ parent_dir_inode->i_sb, xid);
if ((rc == 0) && (newInode != NULL)) {
if (pTcon->nocase)
@@ -499,7 +504,7 @@ cifs_lookup(struct inode *parent_dir_inode, struct dentry *direntry, struct name
direntry->d_op = &cifs_dentry_ops;
d_add(direntry, newInode);
- /* since paths are not looked up by component - the parent
+ /* since paths are not looked up by component - the parent
directories are presumed to be good here */
renew_parental_timestamps(direntry);
@@ -511,13 +516,13 @@ cifs_lookup(struct inode *parent_dir_inode, struct dentry *direntry, struct name
else
direntry->d_op = &cifs_dentry_ops;
d_add(direntry, NULL);
- /* if it was once a directory (but how can we tell?) we could do
- shrink_dcache_parent(direntry); */
+ /* if it was once a directory (but how can we tell?) we could do
+ shrink_dcache_parent(direntry); */
} else {
- cERROR(1,("Error 0x%x on cifs_get_inode_info in lookup of %s",
- rc,full_path));
- /* BB special case check for Access Denied - watch security
- exposure of returning dir info implicitly via different rc
+ cERROR(1, ("Error 0x%x on cifs_get_inode_info in lookup of %s",
+ rc, full_path));
+ /* BB special case check for Access Denied - watch security
+ exposure of returning dir info implicitly via different rc
if file exists or not but no access BB */
}
@@ -538,11 +543,11 @@ cifs_d_revalidate(struct dentry *direntry, struct nameidata *nd)
} else {
cFYI(1, ("neg dentry 0x%p name = %s",
direntry, direntry->d_name.name));
- if(time_after(jiffies, direntry->d_time + HZ) ||
+ if (time_after(jiffies, direntry->d_time + HZ) ||
!lookupCacheEnabled) {
d_drop(direntry);
isValid = 0;
- }
+ }
}
return isValid;
@@ -559,8 +564,7 @@ cifs_d_revalidate(struct dentry *direntry, struct nameidata *nd)
struct dentry_operations cifs_dentry_ops = {
.d_revalidate = cifs_d_revalidate,
-/* d_delete: cifs_d_delete, *//* not needed except for debugging */
- /* no need for d_hash, d_compare, d_release, d_iput ... yet. BB confirm this BB */
+/* d_delete: cifs_d_delete, */ /* not needed except for debugging */
};
static int cifs_ci_hash(struct dentry *dentry, struct qstr *q)
diff --git a/fs/cifs/fcntl.c b/fs/cifs/fcntl.c
index da12b482ebe..8e375bb4b37 100644
--- a/fs/cifs/fcntl.c
+++ b/fs/cifs/fcntl.c
@@ -2,7 +2,7 @@
* fs/cifs/fcntl.c
*
* vfs operations that deal with the file control API
- *
+ *
* Copyright (C) International Business Machines Corp., 2003,2004
* Author(s): Steve French (sfrench@us.ibm.com)
*
@@ -35,35 +35,34 @@ static __u32 convert_to_cifs_notify_flags(unsigned long fcntl_notify_flags)
/* No way on Linux VFS to ask to monitor xattr
changes (and no stream support either */
- if(fcntl_notify_flags & DN_ACCESS) {
+ if (fcntl_notify_flags & DN_ACCESS) {
cifs_ntfy_flags |= FILE_NOTIFY_CHANGE_LAST_ACCESS;
}
- if(fcntl_notify_flags & DN_MODIFY) {
+ if (fcntl_notify_flags & DN_MODIFY) {
/* What does this mean on directories? */
cifs_ntfy_flags |= FILE_NOTIFY_CHANGE_LAST_WRITE |
FILE_NOTIFY_CHANGE_SIZE;
}
- if(fcntl_notify_flags & DN_CREATE) {
- cifs_ntfy_flags |= FILE_NOTIFY_CHANGE_CREATION |
+ if (fcntl_notify_flags & DN_CREATE) {
+ cifs_ntfy_flags |= FILE_NOTIFY_CHANGE_CREATION |
FILE_NOTIFY_CHANGE_LAST_WRITE;
}
- if(fcntl_notify_flags & DN_DELETE) {
+ if (fcntl_notify_flags & DN_DELETE) {
cifs_ntfy_flags |= FILE_NOTIFY_CHANGE_LAST_WRITE;
}
- if(fcntl_notify_flags & DN_RENAME) {
+ if (fcntl_notify_flags & DN_RENAME) {
/* BB review this - checking various server behaviors */
- cifs_ntfy_flags |= FILE_NOTIFY_CHANGE_DIR_NAME |
+ cifs_ntfy_flags |= FILE_NOTIFY_CHANGE_DIR_NAME |
FILE_NOTIFY_CHANGE_FILE_NAME;
}
- if(fcntl_notify_flags & DN_ATTRIB) {
- cifs_ntfy_flags |= FILE_NOTIFY_CHANGE_SECURITY |
+ if (fcntl_notify_flags & DN_ATTRIB) {
+ cifs_ntfy_flags |= FILE_NOTIFY_CHANGE_SECURITY |
FILE_NOTIFY_CHANGE_ATTRIBUTES;
}
-/* if(fcntl_notify_flags & DN_MULTISHOT) {
+/* if (fcntl_notify_flags & DN_MULTISHOT) {
cifs_ntfy_flags |= ;
} */ /* BB fixme - not sure how to handle this with CIFS yet */
-
return cifs_ntfy_flags;
}
@@ -78,8 +77,7 @@ int cifs_dir_notify(struct file * file, unsigned long arg)
__u32 filter = FILE_NOTIFY_CHANGE_NAME | FILE_NOTIFY_CHANGE_ATTRIBUTES;
__u16 netfid;
-
- if(experimEnabled == 0)
+ if (experimEnabled == 0)
return 0;
xid = GetXid();
@@ -88,21 +86,21 @@ int cifs_dir_notify(struct file * file, unsigned long arg)
full_path = build_path_from_dentry(file->f_path.dentry);
- if(full_path == NULL) {
+ if (full_path == NULL) {
rc = -ENOMEM;
} else {
- cFYI(1,("dir notify on file %s Arg 0x%lx",full_path,arg));
- rc = CIFSSMBOpen(xid, pTcon, full_path, FILE_OPEN,
+ cFYI(1, ("dir notify on file %s Arg 0x%lx", full_path, arg));
+ rc = CIFSSMBOpen(xid, pTcon, full_path, FILE_OPEN,
GENERIC_READ | SYNCHRONIZE, 0 /* create options */,
- &netfid, &oplock,NULL, cifs_sb->local_nls,
+ &netfid, &oplock, NULL, cifs_sb->local_nls,
cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MAP_SPECIAL_CHR);
/* BB fixme - add this handle to a notify handle list */
- if(rc) {
- cFYI(1,("Could not open directory for notify"));
+ if (rc) {
+ cFYI(1, ("Could not open directory for notify"));
} else {
filter = convert_to_cifs_notify_flags(arg);
- if(filter != 0) {
- rc = CIFSSMBNotify(xid, pTcon,
+ if (filter != 0) {
+ rc = CIFSSMBNotify(xid, pTcon,
0 /* no subdirs */, netfid,
filter, file, arg & DN_MULTISHOT,
cifs_sb->local_nls);
@@ -113,10 +111,10 @@ int cifs_dir_notify(struct file * file, unsigned long arg)
it would close automatically but may be a way
to do it easily when inode freed or when
notify info is cleared/changed */
- cFYI(1,("notify rc %d",rc));
+ cFYI(1, ("notify rc %d", rc));
}
}
-
+
FreeXid(xid);
return rc;
}
diff --git a/fs/cifs/file.c b/fs/cifs/file.c
index b570530f97b..94d5b49049d 100644
--- a/fs/cifs/file.c
+++ b/fs/cifs/file.c
@@ -27,7 +27,6 @@
#include <linux/fcntl.h>
#include <linux/pagemap.h>
#include <linux/pagevec.h>
-#include <linux/smp_lock.h>
#include <linux/writeback.h>
#include <linux/task_io_accounting_ops.h>
#include <linux/delay.h>
diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c
index 3e87dad3367..f0ff12b3f39 100644
--- a/fs/cifs/inode.c
+++ b/fs/cifs/inode.c
@@ -986,7 +986,8 @@ mkdir_get_info:
* failed to get it from the server or was set bogus */
if ((direntry->d_inode) && (direntry->d_inode->i_nlink < 2))
direntry->d_inode->i_nlink = 2;
- if (cifs_sb->tcon->ses->capabilities & CAP_UNIX)
+ if (cifs_sb->tcon->ses->capabilities & CAP_UNIX) {
+ mode &= ~current->fs->umask;
if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SET_UID) {
CIFSSMBUnixSetPerms(xid, pTcon, full_path,
mode,
@@ -1004,7 +1005,7 @@ mkdir_get_info:
cifs_sb->mnt_cifs_flags &
CIFS_MOUNT_MAP_SPECIAL_CHR);
}
- else {
+ } else {
/* BB to be implemented via Windows secrty descriptors
eg CIFSSMBWinSetPerms(xid, pTcon, full_path, mode,
-1, -1, local_nls); */
diff --git a/fs/cifs/ioctl.c b/fs/cifs/ioctl.c
index e34c7db00f6..a414f1775ae 100644
--- a/fs/cifs/ioctl.c
+++ b/fs/cifs/ioctl.c
@@ -30,7 +30,7 @@
#define CIFS_IOC_CHECKUMOUNT _IO(0xCF, 2)
-int cifs_ioctl (struct inode * inode, struct file * filep,
+int cifs_ioctl (struct inode * inode, struct file * filep,
unsigned int command, unsigned long arg)
{
int rc = -ENOTTY; /* strange error - but the precedent */
@@ -47,13 +47,13 @@ int cifs_ioctl (struct inode * inode, struct file * filep,
xid = GetXid();
- cFYI(1,("ioctl file %p cmd %u arg %lu",filep,command,arg));
+ cFYI(1, ("ioctl file %p cmd %u arg %lu", filep, command, arg));
cifs_sb = CIFS_SB(inode->i_sb);
#ifdef CONFIG_CIFS_POSIX
tcon = cifs_sb->tcon;
- if(tcon)
+ if (tcon)
caps = le64_to_cpu(tcon->fsUnixInfo.Capability);
else {
rc = -EIO;
@@ -62,24 +62,24 @@ int cifs_ioctl (struct inode * inode, struct file * filep,
}
#endif /* CONFIG_CIFS_POSIX */
- switch(command) {
+ switch (command) {
case CIFS_IOC_CHECKUMOUNT:
- cFYI(1,("User unmount attempted"));
- if(cifs_sb->mnt_uid == current->uid)
+ cFYI(1, ("User unmount attempted"));
+ if (cifs_sb->mnt_uid == current->uid)
rc = 0;
else {
rc = -EACCES;
- cFYI(1,("uids do not match"));
+ cFYI(1, ("uids do not match"));
}
break;
#ifdef CONFIG_CIFS_POSIX
case FS_IOC_GETFLAGS:
- if(CIFS_UNIX_EXTATTR_CAP & caps) {
+ if (CIFS_UNIX_EXTATTR_CAP & caps) {
if (pSMBFile == NULL)
break;
rc = CIFSGetExtAttr(xid, tcon, pSMBFile->netfid,
&ExtAttrBits, &ExtAttrMask);
- if(rc == 0)
+ if (rc == 0)
rc = put_user(ExtAttrBits &
FS_FL_USER_VISIBLE,
(int __user *)arg);
@@ -87,8 +87,8 @@ int cifs_ioctl (struct inode * inode, struct file * filep,
break;
case FS_IOC_SETFLAGS:
- if(CIFS_UNIX_EXTATTR_CAP & caps) {
- if(get_user(ExtAttrBits,(int __user *)arg)) {
+ if (CIFS_UNIX_EXTATTR_CAP & caps) {
+ if (get_user(ExtAttrBits, (int __user *)arg)) {
rc = -EFAULT;
break;
}
@@ -96,16 +96,15 @@ int cifs_ioctl (struct inode * inode, struct file * filep,
break;
/* rc= CIFSGetExtAttr(xid,tcon,pSMBFile->netfid,
extAttrBits, &ExtAttrMask);*/
-
}
- cFYI(1,("set flags not implemented yet"));
+ cFYI(1, ("set flags not implemented yet"));
break;
#endif /* CONFIG_CIFS_POSIX */
default:
- cFYI(1,("unsupported ioctl"));
+ cFYI(1, ("unsupported ioctl"));
break;
}
FreeXid(xid);
return rc;
-}
+}
diff --git a/fs/cifs/readdir.c b/fs/cifs/readdir.c
index b5364f90d55..c08bda9fcac 100644
--- a/fs/cifs/readdir.c
+++ b/fs/cifs/readdir.c
@@ -23,7 +23,6 @@
#include <linux/fs.h>
#include <linux/pagemap.h>
#include <linux/stat.h>
-#include <linux/smp_lock.h>
#include "cifspdu.h"
#include "cifsglob.h"
#include "cifsproto.h"
diff --git a/fs/cifs/rfc1002pdu.h b/fs/cifs/rfc1002pdu.h
index aede606132a..8b69fcceb59 100644
--- a/fs/cifs/rfc1002pdu.h
+++ b/fs/cifs/rfc1002pdu.h
@@ -18,7 +18,7 @@
*
* You should have received a copy of the GNU Lesser General Public License
* along with this library; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
*/
/* NB: unlike smb/cifs packets, the RFC1002 structures are big endian */
diff --git a/fs/coda/cache.c b/fs/coda/cache.c
index 5d052713326..fcb88fa8d2f 100644
--- a/fs/coda/cache.c
+++ b/fs/coda/cache.c
@@ -16,6 +16,7 @@
#include <asm/uaccess.h>
#include <linux/string.h>
#include <linux/list.h>
+#include <linux/sched.h>
#include <linux/coda.h>
#include <linux/coda_linux.h>
diff --git a/fs/coda/inode.c b/fs/coda/inode.c
index 0aaff3651d1..dbff1bd4fb9 100644
--- a/fs/coda/inode.c
+++ b/fs/coda/inode.c
@@ -62,8 +62,7 @@ static void init_once(void * foo, struct kmem_cache * cachep, unsigned long flag
{
struct coda_inode_info *ei = (struct coda_inode_info *) foo;
- if (flags & SLAB_CTOR_CONSTRUCTOR)
- inode_init_once(&ei->vfs_inode);
+ inode_init_once(&ei->vfs_inode);
}
int coda_init_inodecache(void)
diff --git a/fs/coda/upcall.c b/fs/coda/upcall.c
index a5b5e631ba6..5faacdb1a47 100644
--- a/fs/coda/upcall.c
+++ b/fs/coda/upcall.c
@@ -16,7 +16,7 @@
#include <asm/system.h>
#include <linux/signal.h>
-
+#include <linux/sched.h>
#include <linux/types.h>
#include <linux/kernel.h>
#include <linux/mm.h>
diff --git a/fs/compat.c b/fs/compat.c
index 72e5e692382..4db6216e526 100644
--- a/fs/compat.c
+++ b/fs/compat.c
@@ -15,6 +15,7 @@
* published by the Free Software Foundation.
*/
+#include <linux/kernel.h>
#include <linux/linkage.h>
#include <linux/compat.h>
#include <linux/errno.h>
@@ -24,10 +25,8 @@
#include <linux/namei.h>
#include <linux/file.h>
#include <linux/vfs.h>
-#include <linux/ioctl32.h>
#include <linux/ioctl.h>
#include <linux/init.h>
-#include <linux/sockios.h> /* for SIOCDEVPRIVATE */
#include <linux/smb.h>
#include <linux/smb_mount.h>
#include <linux/ncp_mount.h>
@@ -45,13 +44,13 @@
#include <linux/personality.h>
#include <linux/rwsem.h>
#include <linux/tsacct_kern.h>
+#include <linux/security.h>
#include <linux/highmem.h>
+#include <linux/signal.h>
#include <linux/poll.h>
#include <linux/mm.h>
#include <linux/eventpoll.h>
-#include <net/sock.h> /* siocdevprivate_ioctl */
-
#include <asm/uaccess.h>
#include <asm/mmu_context.h>
#include <asm/ioctls.h>
@@ -79,30 +78,57 @@ int compat_printk(const char *fmt, ...)
*/
asmlinkage long compat_sys_utime(char __user *filename, struct compat_utimbuf __user *t)
{
- struct timeval tv[2];
+ struct timespec tv[2];
if (t) {
if (get_user(tv[0].tv_sec, &t->actime) ||
get_user(tv[1].tv_sec, &t->modtime))
return -EFAULT;
- tv[0].tv_usec = 0;
- tv[1].tv_usec = 0;
+ tv[0].tv_nsec = 0;
+ tv[1].tv_nsec = 0;
+ }
+ return do_utimes(AT_FDCWD, filename, t ? tv : NULL, 0);
+}
+
+asmlinkage long compat_sys_utimensat(unsigned int dfd, char __user *filename, struct compat_timespec __user *t, int flags)
+{
+ struct timespec tv[2];
+
+ if (t) {
+ if (get_compat_timespec(&tv[0], &t[0]) ||
+ get_compat_timespec(&tv[1], &t[1]))
+ return -EFAULT;
+
+ if ((tv[0].tv_nsec == UTIME_OMIT || tv[0].tv_nsec == UTIME_NOW)
+ && tv[0].tv_sec != 0)
+ return -EINVAL;
+ if ((tv[1].tv_nsec == UTIME_OMIT || tv[1].tv_nsec == UTIME_NOW)
+ && tv[1].tv_sec != 0)
+ return -EINVAL;
+
+ if (tv[0].tv_nsec == UTIME_OMIT && tv[1].tv_nsec == UTIME_OMIT)
+ return 0;
}
- return do_utimes(AT_FDCWD, filename, t ? tv : NULL);
+ return do_utimes(dfd, filename, t ? tv : NULL, flags);
}
asmlinkage long compat_sys_futimesat(unsigned int dfd, char __user *filename, struct compat_timeval __user *t)
{
- struct timeval tv[2];
+ struct timespec tv[2];
if (t) {
if (get_user(tv[0].tv_sec, &t[0].tv_sec) ||
- get_user(tv[0].tv_usec, &t[0].tv_usec) ||
+ get_user(tv[0].tv_nsec, &t[0].tv_usec) ||
get_user(tv[1].tv_sec, &t[1].tv_sec) ||
- get_user(tv[1].tv_usec, &t[1].tv_usec))
+ get_user(tv[1].tv_nsec, &t[1].tv_usec))
return -EFAULT;
+ if (tv[0].tv_nsec >= 1000000 || tv[0].tv_nsec < 0 ||
+ tv[1].tv_nsec >= 1000000 || tv[1].tv_nsec < 0)
+ return -EINVAL;
+ tv[0].tv_nsec *= 1000;
+ tv[1].tv_nsec *= 1000;
}
- return do_utimes(dfd, filename, t ? tv : NULL);
+ return do_utimes(dfd, filename, t ? tv : NULL, 0);
}
asmlinkage long compat_sys_utimes(char __user *filename, struct compat_timeval __user *t)
@@ -312,163 +338,6 @@ out:
return error;
}
-/* ioctl32 stuff, used by sparc64, parisc, s390x, ppc64, x86_64, MIPS */
-
-#define IOCTL_HASHSIZE 256
-static struct ioctl_trans *ioctl32_hash_table[IOCTL_HASHSIZE];
-
-static inline unsigned long ioctl32_hash(unsigned long cmd)
-{
- return (((cmd >> 6) ^ (cmd >> 4) ^ cmd)) % IOCTL_HASHSIZE;
-}
-
-static void ioctl32_insert_translation(struct ioctl_trans *trans)
-{
- unsigned long hash;
- struct ioctl_trans *t;
-
- hash = ioctl32_hash (trans->cmd);
- if (!ioctl32_hash_table[hash])
- ioctl32_hash_table[hash] = trans;
- else {
- t = ioctl32_hash_table[hash];
- while (t->next)
- t = t->next;
- trans->next = NULL;
- t->next = trans;
- }
-}
-
-static int __init init_sys32_ioctl(void)
-{
- int i;
-
- for (i = 0; i < ioctl_table_size; i++) {
- if (ioctl_start[i].next != 0) {
- printk("ioctl translation %d bad\n",i);
- return -1;
- }
-
- ioctl32_insert_translation(&ioctl_start[i]);
- }
- return 0;
-}
-
-__initcall(init_sys32_ioctl);
-
-static void compat_ioctl_error(struct file *filp, unsigned int fd,
- unsigned int cmd, unsigned long arg)
-{
- char buf[10];
- char *fn = "?";
- char *path;
-
- /* find the name of the device. */
- path = (char *)__get_free_page(GFP_KERNEL);
- if (path) {
- fn = d_path(filp->f_path.dentry, filp->f_path.mnt, path, PAGE_SIZE);
- if (IS_ERR(fn))
- fn = "?";
- }
-
- sprintf(buf,"'%c'", (cmd>>_IOC_TYPESHIFT) & _IOC_TYPEMASK);
- if (!isprint(buf[1]))
- sprintf(buf, "%02x", buf[1]);
- compat_printk("ioctl32(%s:%d): Unknown cmd fd(%d) "
- "cmd(%08x){t:%s;sz:%u} arg(%08x) on %s\n",
- current->comm, current->pid,
- (int)fd, (unsigned int)cmd, buf,
- (cmd >> _IOC_SIZESHIFT) & _IOC_SIZEMASK,
- (unsigned int)arg, fn);
-
- if (path)
- free_page((unsigned long)path);
-}
-
-asmlinkage long compat_sys_ioctl(unsigned int fd, unsigned int cmd,
- unsigned long arg)
-{
- struct file *filp;
- int error = -EBADF;
- struct ioctl_trans *t;
- int fput_needed;
-
- filp = fget_light(fd, &fput_needed);
- if (!filp)
- goto out;
-
- /* RED-PEN how should LSM module know it's handling 32bit? */
- error = security_file_ioctl(filp, cmd, arg);
- if (error)
- goto out_fput;
-
- /*
- * To allow the compat_ioctl handlers to be self contained
- * we need to check the common ioctls here first.
- * Just handle them with the standard handlers below.
- */
- switch (cmd) {
- case FIOCLEX:
- case FIONCLEX:
- case FIONBIO:
- case FIOASYNC:
- case FIOQSIZE:
- break;
-
- case FIBMAP:
- case FIGETBSZ:
- case FIONREAD:
- if (S_ISREG(filp->f_path.dentry->d_inode->i_mode))
- break;
- /*FALL THROUGH*/
-
- default:
- if (filp->f_op && filp->f_op->compat_ioctl) {
- error = filp->f_op->compat_ioctl(filp, cmd, arg);
- if (error != -ENOIOCTLCMD)
- goto out_fput;
- }
-
- if (!filp->f_op ||
- (!filp->f_op->ioctl && !filp->f_op->unlocked_ioctl))
- goto do_ioctl;
- break;
- }
-
- for (t = ioctl32_hash_table[ioctl32_hash(cmd)]; t; t = t->next) {
- if (t->cmd == cmd)
- goto found_handler;
- }
-
- if (S_ISSOCK(filp->f_path.dentry->d_inode->i_mode) &&
- cmd >= SIOCDEVPRIVATE && cmd <= (SIOCDEVPRIVATE + 15)) {
- error = siocdevprivate_ioctl(fd, cmd, arg);
- } else {
- static int count;
-
- if (++count <= 50)
- compat_ioctl_error(filp, fd, cmd, arg);
- error = -EINVAL;
- }
-
- goto out_fput;
-
- found_handler:
- if (t->handler) {
- lock_kernel();
- error = t->handler(fd, cmd, arg, filp);
- unlock_kernel();
- goto out_fput;
- }
-
- do_ioctl:
- error = vfs_ioctl(filp, fd, cmd, arg);
- out_fput:
- fput_light(filp, fput_needed);
- out:
- return error;
-}
-
static int get_compat_flock(struct flock *kfl, struct compat_flock __user *ufl)
{
if (!access_ok(VERIFY_READ, ufl, sizeof(*ufl)) ||
@@ -902,8 +771,6 @@ asmlinkage long compat_sys_mount(char __user * dev_name, char __user * dir_name,
}
#define NAME_OFFSET(de) ((int) ((de)->d_name - (char __user *) (de)))
-#define COMPAT_ROUND_UP(x) (((x)+sizeof(compat_long_t)-1) & \
- ~(sizeof(compat_long_t)-1))
struct compat_old_linux_dirent {
compat_ulong_t d_ino;
@@ -991,7 +858,7 @@ static int compat_filldir(void *__buf, const char *name, int namlen,
struct compat_linux_dirent __user * dirent;
struct compat_getdents_callback *buf = __buf;
compat_ulong_t d_ino;
- int reclen = COMPAT_ROUND_UP(NAME_OFFSET(dirent) + namlen + 2);
+ int reclen = ALIGN(NAME_OFFSET(dirent) + namlen + 2, sizeof(compat_long_t));
buf->error = -EINVAL; /* only used if we fail.. */
if (reclen > buf->count)
@@ -1066,7 +933,6 @@ out:
}
#ifndef __ARCH_OMIT_COMPAT_SYS_GETDENTS64
-#define COMPAT_ROUND_UP64(x) (((x)+sizeof(u64)-1) & ~(sizeof(u64)-1))
struct compat_getdents_callback64 {
struct linux_dirent64 __user *current_dir;
@@ -1081,7 +947,7 @@ static int compat_filldir64(void * __buf, const char * name, int namlen, loff_t
struct linux_dirent64 __user *dirent;
struct compat_getdents_callback64 *buf = __buf;
int jj = NAME_OFFSET(dirent);
- int reclen = COMPAT_ROUND_UP64(jj + namlen + 1);
+ int reclen = ALIGN(jj + namlen + 1, sizeof(u64));
u64 off;
buf->error = -EINVAL; /* only used if we fail.. */
@@ -1594,8 +1460,6 @@ out_ret:
#define __COMPAT_NFDBITS (8 * sizeof(compat_ulong_t))
-#define ROUND_UP(x,y) (((x)+(y)-1)/(y))
-
/*
* Ooo, nasty. We need here to frob 32-bit unsigned longs to
* 64-bit unsigned longs.
@@ -1604,7 +1468,7 @@ static
int compat_get_fd_set(unsigned long nr, compat_ulong_t __user *ufdset,
unsigned long *fdset)
{
- nr = ROUND_UP(nr, __COMPAT_NFDBITS);
+ nr = DIV_ROUND_UP(nr, __COMPAT_NFDBITS);
if (ufdset) {
unsigned long odd;
@@ -1638,7 +1502,7 @@ int compat_set_fd_set(unsigned long nr, compat_ulong_t __user *ufdset,
unsigned long *fdset)
{
unsigned long odd;
- nr = ROUND_UP(nr, __COMPAT_NFDBITS);
+ nr = DIV_ROUND_UP(nr, __COMPAT_NFDBITS);
if (!ufdset)
return 0;
@@ -1680,9 +1544,10 @@ int compat_core_sys_select(int n, compat_ulong_t __user *inp,
compat_ulong_t __user *outp, compat_ulong_t __user *exp, s64 *timeout)
{
fd_set_bits fds;
- char *bits;
+ void *bits;
int size, max_fds, ret = -EINVAL;
struct fdtable *fdt;
+ long stack_fds[SELECT_STACK_ALLOC/sizeof(long)];
if (n < 0)
goto out_nofds;
@@ -1700,11 +1565,14 @@ int compat_core_sys_select(int n, compat_ulong_t __user *inp,
* since we used fdset we need to allocate memory in units of
* long-words.
*/
- ret = -ENOMEM;
size = FDS_BYTES(n);
- bits = kmalloc(6 * size, GFP_KERNEL);
- if (!bits)
- goto out_nofds;
+ bits = stack_fds;
+ if (size > sizeof(stack_fds) / 6) {
+ bits = kmalloc(6 * size, GFP_KERNEL);
+ ret = -ENOMEM;
+ if (!bits)
+ goto out_nofds;
+ }
fds.in = (unsigned long *) bits;
fds.out = (unsigned long *) (bits + size);
fds.ex = (unsigned long *) (bits + 2*size);
@@ -1736,7 +1604,8 @@ int compat_core_sys_select(int n, compat_ulong_t __user *inp,
compat_set_fd_set(n, exp, fds.res_ex))
ret = -EFAULT;
out:
- kfree(bits);
+ if (bits != stack_fds)
+ kfree(bits);
out_nofds:
return ret;
}
@@ -1760,7 +1629,7 @@ asmlinkage long compat_sys_select(int n, compat_ulong_t __user *inp,
if ((u64)tv.tv_sec >= (u64)MAX_INT64_SECONDS)
timeout = -1; /* infinite */
else {
- timeout = ROUND_UP(tv.tv_usec, 1000000/HZ);
+ timeout = DIV_ROUND_UP(tv.tv_usec, 1000000/HZ);
timeout += tv.tv_sec * HZ;
}
}
@@ -1828,7 +1697,7 @@ asmlinkage long compat_sys_pselect7(int n, compat_ulong_t __user *inp,
do {
if (tsp) {
if ((unsigned long)ts.tv_sec < MAX_SELECT_SECONDS) {
- timeout = ROUND_UP(ts.tv_nsec, 1000000000/HZ);
+ timeout = DIV_ROUND_UP(ts.tv_nsec, 1000000000/HZ);
timeout += ts.tv_sec * (unsigned long)HZ;
ts.tv_sec = 0;
ts.tv_nsec = 0;
@@ -1924,7 +1793,7 @@ asmlinkage long compat_sys_ppoll(struct pollfd __user *ufds,
/* We assume that ts.tv_sec is always lower than
the number of seconds that can be expressed in
an s64. Otherwise the compiler bitches at us */
- timeout = ROUND_UP(ts.tv_nsec, 1000000000/HZ);
+ timeout = DIV_ROUND_UP(ts.tv_nsec, 1000000000/HZ);
timeout += ts.tv_sec * HZ;
}
@@ -2336,3 +2205,46 @@ asmlinkage long compat_sys_epoll_pwait(int epfd,
#endif /* TIF_RESTORE_SIGMASK */
#endif /* CONFIG_EPOLL */
+
+#ifdef CONFIG_SIGNALFD
+
+asmlinkage long compat_sys_signalfd(int ufd,
+ const compat_sigset_t __user *sigmask,
+ compat_size_t sigsetsize)
+{
+ compat_sigset_t ss32;
+ sigset_t tmp;
+ sigset_t __user *ksigmask;
+
+ if (sigsetsize != sizeof(compat_sigset_t))
+ return -EINVAL;
+ if (copy_from_user(&ss32, sigmask, sizeof(ss32)))
+ return -EFAULT;
+ sigset_from_compat(&tmp, &ss32);
+ ksigmask = compat_alloc_user_space(sizeof(sigset_t));
+ if (copy_to_user(ksigmask, &tmp, sizeof(sigset_t)))
+ return -EFAULT;
+
+ return sys_signalfd(ufd, ksigmask, sizeof(sigset_t));
+}
+
+#endif /* CONFIG_SIGNALFD */
+
+#ifdef CONFIG_TIMERFD
+
+asmlinkage long compat_sys_timerfd(int ufd, int clockid, int flags,
+ const struct compat_itimerspec __user *utmr)
+{
+ struct itimerspec t;
+ struct itimerspec __user *ut;
+
+ if (get_compat_itimerspec(&t, utmr))
+ return -EFAULT;
+ ut = compat_alloc_user_space(sizeof(*ut));
+ if (copy_to_user(ut, &t, sizeof(t)))
+ return -EFAULT;
+
+ return sys_timerfd(ufd, clockid, flags, ut);
+}
+
+#endif /* CONFIG_TIMERFD */
diff --git a/fs/compat_ioctl.c b/fs/compat_ioctl.c
index 464c04a9541..6b44cdc96fa 100644
--- a/fs/compat_ioctl.c
+++ b/fs/compat_ioctl.c
@@ -17,7 +17,6 @@
#include <linux/compiler.h>
#include <linux/sched.h>
#include <linux/smp.h>
-#include <linux/smp_lock.h>
#include <linux/ioctl.h>
#include <linux/if.h>
#include <linux/if_bridge.h>
@@ -58,7 +57,6 @@
#include <linux/serial.h>
#include <linux/if_tun.h>
#include <linux/ctype.h>
-#include <linux/ioctl32.h>
#include <linux/syscalls.h>
#include <linux/i2c.h>
#include <linux/i2c-dev.h>
@@ -66,7 +64,6 @@
#include <linux/atalk.h>
#include <linux/blktrace_api.h>
-#include <net/sock.h> /* siocdevprivate_ioctl */
#include <net/bluetooth/bluetooth.h>
#include <net/bluetooth/hci.h>
#include <net/bluetooth/rfcomm.h>
@@ -475,7 +472,7 @@ static int bond_ioctl(unsigned int fd, unsigned int cmd, unsigned long arg)
};
}
-int siocdevprivate_ioctl(unsigned int fd, unsigned int cmd, unsigned long arg)
+static int siocdevprivate_ioctl(unsigned int fd, unsigned int cmd, unsigned long arg)
{
struct ifreq __user *u_ifreq64;
struct ifreq32 __user *u_ifreq32 = compat_ptr(arg);
@@ -687,8 +684,10 @@ static int hdio_getgeo(unsigned int fd, unsigned int cmd, unsigned long arg)
if (!err) {
err = copy_to_user (ugeo, &geo, 4);
err |= __put_user (geo.start, &ugeo->start);
+ if (err)
+ err = -EFAULT;
}
- return err ? -EFAULT : 0;
+ return err;
}
static int hdio_ioctl_trans(unsigned int fd, unsigned int cmd, unsigned long arg)
@@ -1195,6 +1194,7 @@ static int vt_check(struct file *file)
{
struct tty_struct *tty;
struct inode *inode = file->f_path.dentry->d_inode;
+ struct vc_data *vc;
if (file->f_op->ioctl != tty_ioctl)
return -EINVAL;
@@ -1205,12 +1205,16 @@ static int vt_check(struct file *file)
if (tty->driver->ioctl != vt_ioctl)
return -EINVAL;
-
+
+ vc = (struct vc_data *)tty->driver_data;
+ if (!vc_cons_allocated(vc->vc_num)) /* impossible? */
+ return -ENOIOCTLCMD;
+
/*
* To have permissions to do most of the vt ioctls, we either have
- * to be the owner of the tty, or super-user.
+ * to be the owner of the tty, or have CAP_SYS_TTY_CONFIG.
*/
- if (current->signal->tty == tty || capable(CAP_SYS_ADMIN))
+ if (current->signal->tty == tty || capable(CAP_SYS_TTY_CONFIG))
return 1;
return 0;
}
@@ -1311,16 +1315,28 @@ static int do_unimap_ioctl(unsigned int fd, unsigned int cmd, unsigned long arg,
struct unimapdesc32 tmp;
struct unimapdesc32 __user *user_ud = compat_ptr(arg);
int perm = vt_check(file);
-
- if (perm < 0) return perm;
+ struct vc_data *vc;
+
+ if (perm < 0)
+ return perm;
if (copy_from_user(&tmp, user_ud, sizeof tmp))
return -EFAULT;
+ if (tmp.entries)
+ if (!access_ok(VERIFY_WRITE, compat_ptr(tmp.entries),
+ tmp.entry_ct*sizeof(struct unipair)))
+ return -EFAULT;
+ vc = ((struct tty_struct *)file->private_data)->driver_data;
switch (cmd) {
case PIO_UNIMAP:
- if (!perm) return -EPERM;
- return con_set_unimap(vc_cons[fg_console].d, tmp.entry_ct, compat_ptr(tmp.entries));
+ if (!perm)
+ return -EPERM;
+ return con_set_unimap(vc, tmp.entry_ct,
+ compat_ptr(tmp.entries));
case GIO_UNIMAP:
- return con_get_unimap(vc_cons[fg_console].d, tmp.entry_ct, &(user_ud->entry_ct), compat_ptr(tmp.entries));
+ if (!perm && fg_console != vc->vc_num)
+ return -EPERM;
+ return con_get_unimap(vc, tmp.entry_ct, &(user_ud->entry_ct),
+ compat_ptr(tmp.entries));
}
return 0;
}
@@ -2385,6 +2401,16 @@ lp_timeout_trans(unsigned int fd, unsigned int cmd, unsigned long arg)
return sys_ioctl(fd, cmd, (unsigned long)tn);
}
+
+typedef int (*ioctl_trans_handler_t)(unsigned int, unsigned int,
+ unsigned long, struct file *);
+
+struct ioctl_trans {
+ unsigned long cmd;
+ ioctl_trans_handler_t handler;
+ struct ioctl_trans *next;
+};
+
#define HANDLE_IOCTL(cmd,handler) \
{ (cmd), (ioctl_trans_handler_t)(handler) },
@@ -2405,8 +2431,835 @@ lp_timeout_trans(unsigned int fd, unsigned int cmd, unsigned long arg)
Most other reasons are not valid. */
#define IGNORE_IOCTL(cmd) COMPATIBLE_IOCTL(cmd)
-struct ioctl_trans ioctl_start[] = {
-#include <linux/compat_ioctl.h>
+static struct ioctl_trans ioctl_start[] = {
+/* compatible ioctls first */
+COMPATIBLE_IOCTL(0x4B50) /* KDGHWCLK - not in the kernel, but don't complain */
+COMPATIBLE_IOCTL(0x4B51) /* KDSHWCLK - not in the kernel, but don't complain */
+
+/* Big T */
+COMPATIBLE_IOCTL(TCGETA)
+COMPATIBLE_IOCTL(TCSETA)
+COMPATIBLE_IOCTL(TCSETAW)
+COMPATIBLE_IOCTL(TCSETAF)
+COMPATIBLE_IOCTL(TCSBRK)
+ULONG_IOCTL(TCSBRKP)
+COMPATIBLE_IOCTL(TCXONC)
+COMPATIBLE_IOCTL(TCFLSH)
+COMPATIBLE_IOCTL(TCGETS)
+COMPATIBLE_IOCTL(TCSETS)
+COMPATIBLE_IOCTL(TCSETSW)
+COMPATIBLE_IOCTL(TCSETSF)
+COMPATIBLE_IOCTL(TIOCLINUX)
+COMPATIBLE_IOCTL(TIOCSBRK)
+COMPATIBLE_IOCTL(TIOCCBRK)
+ULONG_IOCTL(TIOCMIWAIT)
+COMPATIBLE_IOCTL(TIOCGICOUNT)
+/* Little t */
+COMPATIBLE_IOCTL(TIOCGETD)
+COMPATIBLE_IOCTL(TIOCSETD)
+COMPATIBLE_IOCTL(TIOCEXCL)
+COMPATIBLE_IOCTL(TIOCNXCL)
+COMPATIBLE_IOCTL(TIOCCONS)
+COMPATIBLE_IOCTL(TIOCGSOFTCAR)
+COMPATIBLE_IOCTL(TIOCSSOFTCAR)
+COMPATIBLE_IOCTL(TIOCSWINSZ)
+COMPATIBLE_IOCTL(TIOCGWINSZ)
+COMPATIBLE_IOCTL(TIOCMGET)
+COMPATIBLE_IOCTL(TIOCMBIC)
+COMPATIBLE_IOCTL(TIOCMBIS)
+COMPATIBLE_IOCTL(TIOCMSET)
+COMPATIBLE_IOCTL(TIOCPKT)
+COMPATIBLE_IOCTL(TIOCNOTTY)
+COMPATIBLE_IOCTL(TIOCSTI)
+COMPATIBLE_IOCTL(TIOCOUTQ)
+COMPATIBLE_IOCTL(TIOCSPGRP)
+COMPATIBLE_IOCTL(TIOCGPGRP)
+ULONG_IOCTL(TIOCSCTTY)
+COMPATIBLE_IOCTL(TIOCGPTN)
+COMPATIBLE_IOCTL(TIOCSPTLCK)
+COMPATIBLE_IOCTL(TIOCSERGETLSR)
+/* Little f */
+COMPATIBLE_IOCTL(FIOCLEX)
+COMPATIBLE_IOCTL(FIONCLEX)
+COMPATIBLE_IOCTL(FIOASYNC)
+COMPATIBLE_IOCTL(FIONBIO)
+COMPATIBLE_IOCTL(FIONREAD) /* This is also TIOCINQ */
+/* 0x00 */
+COMPATIBLE_IOCTL(FIBMAP)
+COMPATIBLE_IOCTL(FIGETBSZ)
+/* 0x03 -- HD/IDE ioctl's used by hdparm and friends.
+ * Some need translations, these do not.
+ */
+COMPATIBLE_IOCTL(HDIO_GET_IDENTITY)
+COMPATIBLE_IOCTL(HDIO_DRIVE_TASK)
+COMPATIBLE_IOCTL(HDIO_DRIVE_CMD)
+ULONG_IOCTL(HDIO_SET_MULTCOUNT)
+ULONG_IOCTL(HDIO_SET_UNMASKINTR)
+ULONG_IOCTL(HDIO_SET_KEEPSETTINGS)
+ULONG_IOCTL(HDIO_SET_32BIT)
+ULONG_IOCTL(HDIO_SET_NOWERR)
+ULONG_IOCTL(HDIO_SET_DMA)
+ULONG_IOCTL(HDIO_SET_PIO_MODE)
+ULONG_IOCTL(HDIO_SET_NICE)
+ULONG_IOCTL(HDIO_SET_WCACHE)
+ULONG_IOCTL(HDIO_SET_ACOUSTIC)
+ULONG_IOCTL(HDIO_SET_BUSSTATE)
+ULONG_IOCTL(HDIO_SET_ADDRESS)
+COMPATIBLE_IOCTL(HDIO_SCAN_HWIF)
+/* 0x330 is reserved -- it used to be HDIO_GETGEO_BIG */
+COMPATIBLE_IOCTL(0x330)
+/* 0x02 -- Floppy ioctls */
+COMPATIBLE_IOCTL(FDMSGON)
+COMPATIBLE_IOCTL(FDMSGOFF)
+COMPATIBLE_IOCTL(FDSETEMSGTRESH)
+COMPATIBLE_IOCTL(FDFLUSH)
+COMPATIBLE_IOCTL(FDWERRORCLR)
+COMPATIBLE_IOCTL(FDSETMAXERRS)
+COMPATIBLE_IOCTL(FDGETMAXERRS)
+COMPATIBLE_IOCTL(FDGETDRVTYP)
+COMPATIBLE_IOCTL(FDEJECT)
+COMPATIBLE_IOCTL(FDCLRPRM)
+COMPATIBLE_IOCTL(FDFMTBEG)
+COMPATIBLE_IOCTL(FDFMTEND)
+COMPATIBLE_IOCTL(FDRESET)
+COMPATIBLE_IOCTL(FDTWADDLE)
+COMPATIBLE_IOCTL(FDFMTTRK)
+COMPATIBLE_IOCTL(FDRAWCMD)
+/* 0x12 */
+#ifdef CONFIG_BLOCK
+COMPATIBLE_IOCTL(BLKRASET)
+COMPATIBLE_IOCTL(BLKROSET)
+COMPATIBLE_IOCTL(BLKROGET)
+COMPATIBLE_IOCTL(BLKRRPART)
+COMPATIBLE_IOCTL(BLKFLSBUF)
+COMPATIBLE_IOCTL(BLKSECTSET)
+COMPATIBLE_IOCTL(BLKSSZGET)
+COMPATIBLE_IOCTL(BLKTRACESTART)
+COMPATIBLE_IOCTL(BLKTRACESTOP)
+COMPATIBLE_IOCTL(BLKTRACESETUP)
+COMPATIBLE_IOCTL(BLKTRACETEARDOWN)
+ULONG_IOCTL(BLKRASET)
+ULONG_IOCTL(BLKFRASET)
+#endif
+/* RAID */
+COMPATIBLE_IOCTL(RAID_VERSION)
+COMPATIBLE_IOCTL(GET_ARRAY_INFO)
+COMPATIBLE_IOCTL(GET_DISK_INFO)
+COMPATIBLE_IOCTL(PRINT_RAID_DEBUG)
+COMPATIBLE_IOCTL(RAID_AUTORUN)
+COMPATIBLE_IOCTL(CLEAR_ARRAY)
+COMPATIBLE_IOCTL(ADD_NEW_DISK)
+ULONG_IOCTL(HOT_REMOVE_DISK)
+COMPATIBLE_IOCTL(SET_ARRAY_INFO)
+COMPATIBLE_IOCTL(SET_DISK_INFO)
+COMPATIBLE_IOCTL(WRITE_RAID_INFO)
+COMPATIBLE_IOCTL(UNPROTECT_ARRAY)
+COMPATIBLE_IOCTL(PROTECT_ARRAY)
+ULONG_IOCTL(HOT_ADD_DISK)
+ULONG_IOCTL(SET_DISK_FAULTY)
+COMPATIBLE_IOCTL(RUN_ARRAY)
+COMPATIBLE_IOCTL(STOP_ARRAY)
+COMPATIBLE_IOCTL(STOP_ARRAY_RO)
+COMPATIBLE_IOCTL(RESTART_ARRAY_RW)
+COMPATIBLE_IOCTL(GET_BITMAP_FILE)
+ULONG_IOCTL(SET_BITMAP_FILE)
+/* DM */
+COMPATIBLE_IOCTL(DM_VERSION_32)
+COMPATIBLE_IOCTL(DM_REMOVE_ALL_32)
+COMPATIBLE_IOCTL(DM_LIST_DEVICES_32)
+COMPATIBLE_IOCTL(DM_DEV_CREATE_32)
+COMPATIBLE_IOCTL(DM_DEV_REMOVE_32)
+COMPATIBLE_IOCTL(DM_DEV_RENAME_32)
+COMPATIBLE_IOCTL(DM_DEV_SUSPEND_32)
+COMPATIBLE_IOCTL(DM_DEV_STATUS_32)
+COMPATIBLE_IOCTL(DM_DEV_WAIT_32)
+COMPATIBLE_IOCTL(DM_TABLE_LOAD_32)
+COMPATIBLE_IOCTL(DM_TABLE_CLEAR_32)
+COMPATIBLE_IOCTL(DM_TABLE_DEPS_32)
+COMPATIBLE_IOCTL(DM_TABLE_STATUS_32)
+COMPATIBLE_IOCTL(DM_LIST_VERSIONS_32)
+COMPATIBLE_IOCTL(DM_TARGET_MSG_32)
+COMPATIBLE_IOCTL(DM_DEV_SET_GEOMETRY_32)
+COMPATIBLE_IOCTL(DM_VERSION)
+COMPATIBLE_IOCTL(DM_REMOVE_ALL)
+COMPATIBLE_IOCTL(DM_LIST_DEVICES)
+COMPATIBLE_IOCTL(DM_DEV_CREATE)
+COMPATIBLE_IOCTL(DM_DEV_REMOVE)
+COMPATIBLE_IOCTL(DM_DEV_RENAME)
+COMPATIBLE_IOCTL(DM_DEV_SUSPEND)
+COMPATIBLE_IOCTL(DM_DEV_STATUS)
+COMPATIBLE_IOCTL(DM_DEV_WAIT)
+COMPATIBLE_IOCTL(DM_TABLE_LOAD)
+COMPATIBLE_IOCTL(DM_TABLE_CLEAR)
+COMPATIBLE_IOCTL(DM_TABLE_DEPS)
+COMPATIBLE_IOCTL(DM_TABLE_STATUS)
+COMPATIBLE_IOCTL(DM_LIST_VERSIONS)
+COMPATIBLE_IOCTL(DM_TARGET_MSG)
+COMPATIBLE_IOCTL(DM_DEV_SET_GEOMETRY)
+/* Big K */
+COMPATIBLE_IOCTL(PIO_FONT)
+COMPATIBLE_IOCTL(GIO_FONT)
+ULONG_IOCTL(KDSIGACCEPT)
+COMPATIBLE_IOCTL(KDGETKEYCODE)
+COMPATIBLE_IOCTL(KDSETKEYCODE)
+ULONG_IOCTL(KIOCSOUND)
+ULONG_IOCTL(KDMKTONE)
+COMPATIBLE_IOCTL(KDGKBTYPE)
+ULONG_IOCTL(KDSETMODE)
+COMPATIBLE_IOCTL(KDGETMODE)
+ULONG_IOCTL(KDSKBMODE)
+COMPATIBLE_IOCTL(KDGKBMODE)
+ULONG_IOCTL(KDSKBMETA)
+COMPATIBLE_IOCTL(KDGKBMETA)
+COMPATIBLE_IOCTL(KDGKBENT)
+COMPATIBLE_IOCTL(KDSKBENT)
+COMPATIBLE_IOCTL(KDGKBSENT)
+COMPATIBLE_IOCTL(KDSKBSENT)
+COMPATIBLE_IOCTL(KDGKBDIACR)
+COMPATIBLE_IOCTL(KDSKBDIACR)
+COMPATIBLE_IOCTL(KDKBDREP)
+COMPATIBLE_IOCTL(KDGKBLED)
+ULONG_IOCTL(KDSKBLED)
+COMPATIBLE_IOCTL(KDGETLED)
+ULONG_IOCTL(KDSETLED)
+COMPATIBLE_IOCTL(GIO_SCRNMAP)
+COMPATIBLE_IOCTL(PIO_SCRNMAP)
+COMPATIBLE_IOCTL(GIO_UNISCRNMAP)
+COMPATIBLE_IOCTL(PIO_UNISCRNMAP)
+COMPATIBLE_IOCTL(PIO_FONTRESET)
+COMPATIBLE_IOCTL(PIO_UNIMAPCLR)
+/* Big S */
+COMPATIBLE_IOCTL(SCSI_IOCTL_GET_IDLUN)
+COMPATIBLE_IOCTL(SCSI_IOCTL_DOORLOCK)
+COMPATIBLE_IOCTL(SCSI_IOCTL_DOORUNLOCK)
+COMPATIBLE_IOCTL(SCSI_IOCTL_TEST_UNIT_READY)
+COMPATIBLE_IOCTL(SCSI_IOCTL_GET_BUS_NUMBER)
+COMPATIBLE_IOCTL(SCSI_IOCTL_SEND_COMMAND)
+COMPATIBLE_IOCTL(SCSI_IOCTL_PROBE_HOST)
+COMPATIBLE_IOCTL(SCSI_IOCTL_GET_PCI)
+/* Big T */
+COMPATIBLE_IOCTL(TUNSETNOCSUM)
+COMPATIBLE_IOCTL(TUNSETDEBUG)
+COMPATIBLE_IOCTL(TUNSETPERSIST)
+COMPATIBLE_IOCTL(TUNSETOWNER)
+/* Big V */
+COMPATIBLE_IOCTL(VT_SETMODE)
+COMPATIBLE_IOCTL(VT_GETMODE)
+COMPATIBLE_IOCTL(VT_GETSTATE)
+COMPATIBLE_IOCTL(VT_OPENQRY)
+ULONG_IOCTL(VT_ACTIVATE)
+ULONG_IOCTL(VT_WAITACTIVE)
+ULONG_IOCTL(VT_RELDISP)
+ULONG_IOCTL(VT_DISALLOCATE)
+COMPATIBLE_IOCTL(VT_RESIZE)
+COMPATIBLE_IOCTL(VT_RESIZEX)
+COMPATIBLE_IOCTL(VT_LOCKSWITCH)
+COMPATIBLE_IOCTL(VT_UNLOCKSWITCH)
+COMPATIBLE_IOCTL(VT_GETHIFONTMASK)
+/* Little p (/dev/rtc, /dev/envctrl, etc.) */
+COMPATIBLE_IOCTL(RTC_AIE_ON)
+COMPATIBLE_IOCTL(RTC_AIE_OFF)
+COMPATIBLE_IOCTL(RTC_UIE_ON)
+COMPATIBLE_IOCTL(RTC_UIE_OFF)
+COMPATIBLE_IOCTL(RTC_PIE_ON)
+COMPATIBLE_IOCTL(RTC_PIE_OFF)
+COMPATIBLE_IOCTL(RTC_WIE_ON)
+COMPATIBLE_IOCTL(RTC_WIE_OFF)
+COMPATIBLE_IOCTL(RTC_ALM_SET)
+COMPATIBLE_IOCTL(RTC_ALM_READ)
+COMPATIBLE_IOCTL(RTC_RD_TIME)
+COMPATIBLE_IOCTL(RTC_SET_TIME)
+COMPATIBLE_IOCTL(RTC_WKALM_SET)
+COMPATIBLE_IOCTL(RTC_WKALM_RD)
+/*
+ * These two are only for the sbus rtc driver, but
+ * hwclock tries them on every rtc device first when
+ * running on sparc. On other architectures the entries
+ * are useless but harmless.
+ */
+COMPATIBLE_IOCTL(_IOR('p', 20, int[7])) /* RTCGET */
+COMPATIBLE_IOCTL(_IOW('p', 21, int[7])) /* RTCSET */
+/* Little m */
+COMPATIBLE_IOCTL(MTIOCTOP)
+/* Socket level stuff */
+COMPATIBLE_IOCTL(FIOQSIZE)
+COMPATIBLE_IOCTL(FIOSETOWN)
+COMPATIBLE_IOCTL(SIOCSPGRP)
+COMPATIBLE_IOCTL(FIOGETOWN)
+COMPATIBLE_IOCTL(SIOCGPGRP)
+COMPATIBLE_IOCTL(SIOCATMARK)
+COMPATIBLE_IOCTL(SIOCSIFLINK)
+COMPATIBLE_IOCTL(SIOCSIFENCAP)
+COMPATIBLE_IOCTL(SIOCGIFENCAP)
+COMPATIBLE_IOCTL(SIOCSIFNAME)
+COMPATIBLE_IOCTL(SIOCSARP)
+COMPATIBLE_IOCTL(SIOCGARP)
+COMPATIBLE_IOCTL(SIOCDARP)
+COMPATIBLE_IOCTL(SIOCSRARP)
+COMPATIBLE_IOCTL(SIOCGRARP)
+COMPATIBLE_IOCTL(SIOCDRARP)
+COMPATIBLE_IOCTL(SIOCADDDLCI)
+COMPATIBLE_IOCTL(SIOCDELDLCI)
+COMPATIBLE_IOCTL(SIOCGMIIPHY)
+COMPATIBLE_IOCTL(SIOCGMIIREG)
+COMPATIBLE_IOCTL(SIOCSMIIREG)
+COMPATIBLE_IOCTL(SIOCGIFVLAN)
+COMPATIBLE_IOCTL(SIOCSIFVLAN)
+COMPATIBLE_IOCTL(SIOCBRADDBR)
+COMPATIBLE_IOCTL(SIOCBRDELBR)
+/* SG stuff */
+COMPATIBLE_IOCTL(SG_SET_TIMEOUT)
+COMPATIBLE_IOCTL(SG_GET_TIMEOUT)
+COMPATIBLE_IOCTL(SG_EMULATED_HOST)
+ULONG_IOCTL(SG_SET_TRANSFORM)
+COMPATIBLE_IOCTL(SG_GET_TRANSFORM)
+COMPATIBLE_IOCTL(SG_SET_RESERVED_SIZE)
+COMPATIBLE_IOCTL(SG_GET_RESERVED_SIZE)
+COMPATIBLE_IOCTL(SG_GET_SCSI_ID)
+COMPATIBLE_IOCTL(SG_SET_FORCE_LOW_DMA)
+COMPATIBLE_IOCTL(SG_GET_LOW_DMA)
+COMPATIBLE_IOCTL(SG_SET_FORCE_PACK_ID)
+COMPATIBLE_IOCTL(SG_GET_PACK_ID)
+COMPATIBLE_IOCTL(SG_GET_NUM_WAITING)
+COMPATIBLE_IOCTL(SG_SET_DEBUG)
+COMPATIBLE_IOCTL(SG_GET_SG_TABLESIZE)
+COMPATIBLE_IOCTL(SG_GET_COMMAND_Q)
+COMPATIBLE_IOCTL(SG_SET_COMMAND_Q)
+COMPATIBLE_IOCTL(SG_GET_VERSION_NUM)
+COMPATIBLE_IOCTL(SG_NEXT_CMD_LEN)
+COMPATIBLE_IOCTL(SG_SCSI_RESET)
+COMPATIBLE_IOCTL(SG_GET_REQUEST_TABLE)
+COMPATIBLE_IOCTL(SG_SET_KEEP_ORPHAN)
+COMPATIBLE_IOCTL(SG_GET_KEEP_ORPHAN)
+/* PPP stuff */
+COMPATIBLE_IOCTL(PPPIOCGFLAGS)
+COMPATIBLE_IOCTL(PPPIOCSFLAGS)
+COMPATIBLE_IOCTL(PPPIOCGASYNCMAP)
+COMPATIBLE_IOCTL(PPPIOCSASYNCMAP)
+COMPATIBLE_IOCTL(PPPIOCGUNIT)
+COMPATIBLE_IOCTL(PPPIOCGRASYNCMAP)
+COMPATIBLE_IOCTL(PPPIOCSRASYNCMAP)
+COMPATIBLE_IOCTL(PPPIOCGMRU)
+COMPATIBLE_IOCTL(PPPIOCSMRU)
+COMPATIBLE_IOCTL(PPPIOCSMAXCID)
+COMPATIBLE_IOCTL(PPPIOCGXASYNCMAP)
+COMPATIBLE_IOCTL(PPPIOCSXASYNCMAP)
+COMPATIBLE_IOCTL(PPPIOCXFERUNIT)
+/* PPPIOCSCOMPRESS is translated */
+COMPATIBLE_IOCTL(PPPIOCGNPMODE)
+COMPATIBLE_IOCTL(PPPIOCSNPMODE)
+COMPATIBLE_IOCTL(PPPIOCGDEBUG)
+COMPATIBLE_IOCTL(PPPIOCSDEBUG)
+/* PPPIOCSPASS is translated */
+/* PPPIOCSACTIVE is translated */
+/* PPPIOCGIDLE is translated */
+COMPATIBLE_IOCTL(PPPIOCNEWUNIT)
+COMPATIBLE_IOCTL(PPPIOCATTACH)
+COMPATIBLE_IOCTL(PPPIOCDETACH)
+COMPATIBLE_IOCTL(PPPIOCSMRRU)
+COMPATIBLE_IOCTL(PPPIOCCONNECT)
+COMPATIBLE_IOCTL(PPPIOCDISCONN)
+COMPATIBLE_IOCTL(PPPIOCATTCHAN)
+COMPATIBLE_IOCTL(PPPIOCGCHAN)
+/* PPPOX */
+COMPATIBLE_IOCTL(PPPOEIOCSFWD)
+COMPATIBLE_IOCTL(PPPOEIOCDFWD)
+/* LP */
+COMPATIBLE_IOCTL(LPGETSTATUS)
+/* ppdev */
+COMPATIBLE_IOCTL(PPSETMODE)
+COMPATIBLE_IOCTL(PPRSTATUS)
+COMPATIBLE_IOCTL(PPRCONTROL)
+COMPATIBLE_IOCTL(PPWCONTROL)
+COMPATIBLE_IOCTL(PPFCONTROL)
+COMPATIBLE_IOCTL(PPRDATA)
+COMPATIBLE_IOCTL(PPWDATA)
+COMPATIBLE_IOCTL(PPCLAIM)
+COMPATIBLE_IOCTL(PPRELEASE)
+COMPATIBLE_IOCTL(PPYIELD)
+COMPATIBLE_IOCTL(PPEXCL)
+COMPATIBLE_IOCTL(PPDATADIR)
+COMPATIBLE_IOCTL(PPNEGOT)
+COMPATIBLE_IOCTL(PPWCTLONIRQ)
+COMPATIBLE_IOCTL(PPCLRIRQ)
+COMPATIBLE_IOCTL(PPSETPHASE)
+COMPATIBLE_IOCTL(PPGETMODES)
+COMPATIBLE_IOCTL(PPGETMODE)
+COMPATIBLE_IOCTL(PPGETPHASE)
+COMPATIBLE_IOCTL(PPGETFLAGS)
+COMPATIBLE_IOCTL(PPSETFLAGS)
+/* CDROM stuff */
+COMPATIBLE_IOCTL(CDROMPAUSE)
+COMPATIBLE_IOCTL(CDROMRESUME)
+COMPATIBLE_IOCTL(CDROMPLAYMSF)
+COMPATIBLE_IOCTL(CDROMPLAYTRKIND)
+COMPATIBLE_IOCTL(CDROMREADTOCHDR)
+COMPATIBLE_IOCTL(CDROMREADTOCENTRY)
+COMPATIBLE_IOCTL(CDROMSTOP)
+COMPATIBLE_IOCTL(CDROMSTART)
+COMPATIBLE_IOCTL(CDROMEJECT)
+COMPATIBLE_IOCTL(CDROMVOLCTRL)
+COMPATIBLE_IOCTL(CDROMSUBCHNL)
+ULONG_IOCTL(CDROMEJECT_SW)
+COMPATIBLE_IOCTL(CDROMMULTISESSION)
+COMPATIBLE_IOCTL(CDROM_GET_MCN)
+COMPATIBLE_IOCTL(CDROMRESET)
+COMPATIBLE_IOCTL(CDROMVOLREAD)
+COMPATIBLE_IOCTL(CDROMSEEK)
+COMPATIBLE_IOCTL(CDROMPLAYBLK)
+COMPATIBLE_IOCTL(CDROMCLOSETRAY)
+ULONG_IOCTL(CDROM_SET_OPTIONS)
+ULONG_IOCTL(CDROM_CLEAR_OPTIONS)
+ULONG_IOCTL(CDROM_SELECT_SPEED)
+ULONG_IOCTL(CDROM_SELECT_DISC)
+ULONG_IOCTL(CDROM_MEDIA_CHANGED)
+ULONG_IOCTL(CDROM_DRIVE_STATUS)
+COMPATIBLE_IOCTL(CDROM_DISC_STATUS)
+COMPATIBLE_IOCTL(CDROM_CHANGER_NSLOTS)
+ULONG_IOCTL(CDROM_LOCKDOOR)
+ULONG_IOCTL(CDROM_DEBUG)
+COMPATIBLE_IOCTL(CDROM_GET_CAPABILITY)
+/* Ignore cdrom.h about these next 5 ioctls, they absolutely do
+ * not take a struct cdrom_read, instead they take a struct cdrom_msf
+ * which is compatible.
+ */
+COMPATIBLE_IOCTL(CDROMREADMODE2)
+COMPATIBLE_IOCTL(CDROMREADMODE1)
+COMPATIBLE_IOCTL(CDROMREADRAW)
+COMPATIBLE_IOCTL(CDROMREADCOOKED)
+COMPATIBLE_IOCTL(CDROMREADALL)
+/* DVD ioctls */
+COMPATIBLE_IOCTL(DVD_READ_STRUCT)
+COMPATIBLE_IOCTL(DVD_WRITE_STRUCT)
+COMPATIBLE_IOCTL(DVD_AUTH)
+/* pktcdvd */
+COMPATIBLE_IOCTL(PACKET_CTRL_CMD)
+/* Big A */
+/* sparc only */
+/* Big Q for sound/OSS */
+COMPATIBLE_IOCTL(SNDCTL_SEQ_RESET)
+COMPATIBLE_IOCTL(SNDCTL_SEQ_SYNC)
+COMPATIBLE_IOCTL(SNDCTL_SYNTH_INFO)
+COMPATIBLE_IOCTL(SNDCTL_SEQ_CTRLRATE)
+COMPATIBLE_IOCTL(SNDCTL_SEQ_GETOUTCOUNT)
+COMPATIBLE_IOCTL(SNDCTL_SEQ_GETINCOUNT)
+COMPATIBLE_IOCTL(SNDCTL_SEQ_PERCMODE)
+COMPATIBLE_IOCTL(SNDCTL_FM_LOAD_INSTR)
+COMPATIBLE_IOCTL(SNDCTL_SEQ_TESTMIDI)
+COMPATIBLE_IOCTL(SNDCTL_SEQ_RESETSAMPLES)
+COMPATIBLE_IOCTL(SNDCTL_SEQ_NRSYNTHS)
+COMPATIBLE_IOCTL(SNDCTL_SEQ_NRMIDIS)
+COMPATIBLE_IOCTL(SNDCTL_MIDI_INFO)
+COMPATIBLE_IOCTL(SNDCTL_SEQ_THRESHOLD)
+COMPATIBLE_IOCTL(SNDCTL_SYNTH_MEMAVL)
+COMPATIBLE_IOCTL(SNDCTL_FM_4OP_ENABLE)
+COMPATIBLE_IOCTL(SNDCTL_SEQ_PANIC)
+COMPATIBLE_IOCTL(SNDCTL_SEQ_OUTOFBAND)
+COMPATIBLE_IOCTL(SNDCTL_SEQ_GETTIME)
+COMPATIBLE_IOCTL(SNDCTL_SYNTH_ID)
+COMPATIBLE_IOCTL(SNDCTL_SYNTH_CONTROL)
+COMPATIBLE_IOCTL(SNDCTL_SYNTH_REMOVESAMPLE)
+/* Big T for sound/OSS */
+COMPATIBLE_IOCTL(SNDCTL_TMR_TIMEBASE)
+COMPATIBLE_IOCTL(SNDCTL_TMR_START)
+COMPATIBLE_IOCTL(SNDCTL_TMR_STOP)
+COMPATIBLE_IOCTL(SNDCTL_TMR_CONTINUE)
+COMPATIBLE_IOCTL(SNDCTL_TMR_TEMPO)
+COMPATIBLE_IOCTL(SNDCTL_TMR_SOURCE)
+COMPATIBLE_IOCTL(SNDCTL_TMR_METRONOME)
+COMPATIBLE_IOCTL(SNDCTL_TMR_SELECT)
+/* Little m for sound/OSS */
+COMPATIBLE_IOCTL(SNDCTL_MIDI_PRETIME)
+COMPATIBLE_IOCTL(SNDCTL_MIDI_MPUMODE)
+COMPATIBLE_IOCTL(SNDCTL_MIDI_MPUCMD)
+/* Big P for sound/OSS */
+COMPATIBLE_IOCTL(SNDCTL_DSP_RESET)
+COMPATIBLE_IOCTL(SNDCTL_DSP_SYNC)
+COMPATIBLE_IOCTL(SNDCTL_DSP_SPEED)
+COMPATIBLE_IOCTL(SNDCTL_DSP_STEREO)
+COMPATIBLE_IOCTL(SNDCTL_DSP_GETBLKSIZE)
+COMPATIBLE_IOCTL(SNDCTL_DSP_CHANNELS)
+COMPATIBLE_IOCTL(SOUND_PCM_WRITE_FILTER)
+COMPATIBLE_IOCTL(SNDCTL_DSP_POST)
+COMPATIBLE_IOCTL(SNDCTL_DSP_SUBDIVIDE)
+COMPATIBLE_IOCTL(SNDCTL_DSP_SETFRAGMENT)
+COMPATIBLE_IOCTL(SNDCTL_DSP_GETFMTS)
+COMPATIBLE_IOCTL(SNDCTL_DSP_SETFMT)
+COMPATIBLE_IOCTL(SNDCTL_DSP_GETOSPACE)
+COMPATIBLE_IOCTL(SNDCTL_DSP_GETISPACE)
+COMPATIBLE_IOCTL(SNDCTL_DSP_NONBLOCK)
+COMPATIBLE_IOCTL(SNDCTL_DSP_GETCAPS)
+COMPATIBLE_IOCTL(SNDCTL_DSP_GETTRIGGER)
+COMPATIBLE_IOCTL(SNDCTL_DSP_SETTRIGGER)
+COMPATIBLE_IOCTL(SNDCTL_DSP_GETIPTR)
+COMPATIBLE_IOCTL(SNDCTL_DSP_GETOPTR)
+/* SNDCTL_DSP_MAPINBUF, XXX needs translation */
+/* SNDCTL_DSP_MAPOUTBUF, XXX needs translation */
+COMPATIBLE_IOCTL(SNDCTL_DSP_SETSYNCRO)
+COMPATIBLE_IOCTL(SNDCTL_DSP_SETDUPLEX)
+COMPATIBLE_IOCTL(SNDCTL_DSP_GETODELAY)
+COMPATIBLE_IOCTL(SNDCTL_DSP_PROFILE)
+COMPATIBLE_IOCTL(SOUND_PCM_READ_RATE)
+COMPATIBLE_IOCTL(SOUND_PCM_READ_CHANNELS)
+COMPATIBLE_IOCTL(SOUND_PCM_READ_BITS)
+COMPATIBLE_IOCTL(SOUND_PCM_READ_FILTER)
+/* Big C for sound/OSS */
+COMPATIBLE_IOCTL(SNDCTL_COPR_RESET)
+COMPATIBLE_IOCTL(SNDCTL_COPR_LOAD)
+COMPATIBLE_IOCTL(SNDCTL_COPR_RDATA)
+COMPATIBLE_IOCTL(SNDCTL_COPR_RCODE)
+COMPATIBLE_IOCTL(SNDCTL_COPR_WDATA)
+COMPATIBLE_IOCTL(SNDCTL_COPR_WCODE)
+COMPATIBLE_IOCTL(SNDCTL_COPR_RUN)
+COMPATIBLE_IOCTL(SNDCTL_COPR_HALT)
+COMPATIBLE_IOCTL(SNDCTL_COPR_SENDMSG)
+COMPATIBLE_IOCTL(SNDCTL_COPR_RCVMSG)
+/* Big M for sound/OSS */
+COMPATIBLE_IOCTL(SOUND_MIXER_READ_VOLUME)
+COMPATIBLE_IOCTL(SOUND_MIXER_READ_BASS)
+COMPATIBLE_IOCTL(SOUND_MIXER_READ_TREBLE)
+COMPATIBLE_IOCTL(SOUND_MIXER_READ_SYNTH)
+COMPATIBLE_IOCTL(SOUND_MIXER_READ_PCM)
+COMPATIBLE_IOCTL(SOUND_MIXER_READ_SPEAKER)
+COMPATIBLE_IOCTL(SOUND_MIXER_READ_LINE)
+COMPATIBLE_IOCTL(SOUND_MIXER_READ_MIC)
+COMPATIBLE_IOCTL(SOUND_MIXER_READ_CD)
+COMPATIBLE_IOCTL(SOUND_MIXER_READ_IMIX)
+COMPATIBLE_IOCTL(SOUND_MIXER_READ_ALTPCM)
+COMPATIBLE_IOCTL(SOUND_MIXER_READ_RECLEV)
+COMPATIBLE_IOCTL(SOUND_MIXER_READ_IGAIN)
+COMPATIBLE_IOCTL(SOUND_MIXER_READ_OGAIN)
+COMPATIBLE_IOCTL(SOUND_MIXER_READ_LINE1)
+COMPATIBLE_IOCTL(SOUND_MIXER_READ_LINE2)
+COMPATIBLE_IOCTL(SOUND_MIXER_READ_LINE3)
+COMPATIBLE_IOCTL(MIXER_READ(SOUND_MIXER_DIGITAL1))
+COMPATIBLE_IOCTL(MIXER_READ(SOUND_MIXER_DIGITAL2))
+COMPATIBLE_IOCTL(MIXER_READ(SOUND_MIXER_DIGITAL3))
+COMPATIBLE_IOCTL(MIXER_READ(SOUND_MIXER_PHONEIN))
+COMPATIBLE_IOCTL(MIXER_READ(SOUND_MIXER_PHONEOUT))
+COMPATIBLE_IOCTL(MIXER_READ(SOUND_MIXER_VIDEO))
+COMPATIBLE_IOCTL(MIXER_READ(SOUND_MIXER_RADIO))
+COMPATIBLE_IOCTL(MIXER_READ(SOUND_MIXER_MONITOR))
+COMPATIBLE_IOCTL(SOUND_MIXER_READ_MUTE)
+/* SOUND_MIXER_READ_ENHANCE, same value as READ_MUTE */
+/* SOUND_MIXER_READ_LOUD, same value as READ_MUTE */
+COMPATIBLE_IOCTL(SOUND_MIXER_READ_RECSRC)
+COMPATIBLE_IOCTL(SOUND_MIXER_READ_DEVMASK)
+COMPATIBLE_IOCTL(SOUND_MIXER_READ_RECMASK)
+COMPATIBLE_IOCTL(SOUND_MIXER_READ_STEREODEVS)
+COMPATIBLE_IOCTL(SOUND_MIXER_READ_CAPS)
+COMPATIBLE_IOCTL(SOUND_MIXER_WRITE_VOLUME)
+COMPATIBLE_IOCTL(SOUND_MIXER_WRITE_BASS)
+COMPATIBLE_IOCTL(SOUND_MIXER_WRITE_TREBLE)
+COMPATIBLE_IOCTL(SOUND_MIXER_WRITE_SYNTH)
+COMPATIBLE_IOCTL(SOUND_MIXER_WRITE_PCM)
+COMPATIBLE_IOCTL(SOUND_MIXER_WRITE_SPEAKER)
+COMPATIBLE_IOCTL(SOUND_MIXER_WRITE_LINE)
+COMPATIBLE_IOCTL(SOUND_MIXER_WRITE_MIC)
+COMPATIBLE_IOCTL(SOUND_MIXER_WRITE_CD)
+COMPATIBLE_IOCTL(SOUND_MIXER_WRITE_IMIX)
+COMPATIBLE_IOCTL(SOUND_MIXER_WRITE_ALTPCM)
+COMPATIBLE_IOCTL(SOUND_MIXER_WRITE_RECLEV)
+COMPATIBLE_IOCTL(SOUND_MIXER_WRITE_IGAIN)
+COMPATIBLE_IOCTL(SOUND_MIXER_WRITE_OGAIN)
+COMPATIBLE_IOCTL(SOUND_MIXER_WRITE_LINE1)
+COMPATIBLE_IOCTL(SOUND_MIXER_WRITE_LINE2)
+COMPATIBLE_IOCTL(SOUND_MIXER_WRITE_LINE3)
+COMPATIBLE_IOCTL(MIXER_WRITE(SOUND_MIXER_DIGITAL1))
+COMPATIBLE_IOCTL(MIXER_WRITE(SOUND_MIXER_DIGITAL2))
+COMPATIBLE_IOCTL(MIXER_WRITE(SOUND_MIXER_DIGITAL3))
+COMPATIBLE_IOCTL(MIXER_WRITE(SOUND_MIXER_PHONEIN))
+COMPATIBLE_IOCTL(MIXER_WRITE(SOUND_MIXER_PHONEOUT))
+COMPATIBLE_IOCTL(MIXER_WRITE(SOUND_MIXER_VIDEO))
+COMPATIBLE_IOCTL(MIXER_WRITE(SOUND_MIXER_RADIO))
+COMPATIBLE_IOCTL(MIXER_WRITE(SOUND_MIXER_MONITOR))
+COMPATIBLE_IOCTL(SOUND_MIXER_WRITE_MUTE)
+/* SOUND_MIXER_WRITE_ENHANCE, same value as WRITE_MUTE */
+/* SOUND_MIXER_WRITE_LOUD, same value as WRITE_MUTE */
+COMPATIBLE_IOCTL(SOUND_MIXER_WRITE_RECSRC)
+COMPATIBLE_IOCTL(SOUND_MIXER_INFO)
+COMPATIBLE_IOCTL(SOUND_OLD_MIXER_INFO)
+COMPATIBLE_IOCTL(SOUND_MIXER_ACCESS)
+COMPATIBLE_IOCTL(SOUND_MIXER_AGC)
+COMPATIBLE_IOCTL(SOUND_MIXER_3DSE)
+COMPATIBLE_IOCTL(SOUND_MIXER_PRIVATE1)
+COMPATIBLE_IOCTL(SOUND_MIXER_PRIVATE2)
+COMPATIBLE_IOCTL(SOUND_MIXER_PRIVATE3)
+COMPATIBLE_IOCTL(SOUND_MIXER_PRIVATE4)
+COMPATIBLE_IOCTL(SOUND_MIXER_PRIVATE5)
+COMPATIBLE_IOCTL(SOUND_MIXER_GETLEVELS)
+COMPATIBLE_IOCTL(SOUND_MIXER_SETLEVELS)
+COMPATIBLE_IOCTL(OSS_GETVERSION)
+/* AUTOFS */
+ULONG_IOCTL(AUTOFS_IOC_READY)
+ULONG_IOCTL(AUTOFS_IOC_FAIL)
+COMPATIBLE_IOCTL(AUTOFS_IOC_CATATONIC)
+COMPATIBLE_IOCTL(AUTOFS_IOC_PROTOVER)
+COMPATIBLE_IOCTL(AUTOFS_IOC_EXPIRE)
+COMPATIBLE_IOCTL(AUTOFS_IOC_EXPIRE_MULTI)
+COMPATIBLE_IOCTL(AUTOFS_IOC_PROTOSUBVER)
+COMPATIBLE_IOCTL(AUTOFS_IOC_ASKREGHOST)
+COMPATIBLE_IOCTL(AUTOFS_IOC_TOGGLEREGHOST)
+COMPATIBLE_IOCTL(AUTOFS_IOC_ASKUMOUNT)
+/* Raw devices */
+COMPATIBLE_IOCTL(RAW_SETBIND)
+COMPATIBLE_IOCTL(RAW_GETBIND)
+/* SMB ioctls which do not need any translations */
+COMPATIBLE_IOCTL(SMB_IOC_NEWCONN)
+/* Little a */
+COMPATIBLE_IOCTL(ATMSIGD_CTRL)
+COMPATIBLE_IOCTL(ATMARPD_CTRL)
+COMPATIBLE_IOCTL(ATMLEC_CTRL)
+COMPATIBLE_IOCTL(ATMLEC_MCAST)
+COMPATIBLE_IOCTL(ATMLEC_DATA)
+COMPATIBLE_IOCTL(ATM_SETSC)
+COMPATIBLE_IOCTL(SIOCSIFATMTCP)
+COMPATIBLE_IOCTL(SIOCMKCLIP)
+COMPATIBLE_IOCTL(ATMARP_MKIP)
+COMPATIBLE_IOCTL(ATMARP_SETENTRY)
+COMPATIBLE_IOCTL(ATMARP_ENCAP)
+COMPATIBLE_IOCTL(ATMTCP_CREATE)
+COMPATIBLE_IOCTL(ATMTCP_REMOVE)
+COMPATIBLE_IOCTL(ATMMPC_CTRL)
+COMPATIBLE_IOCTL(ATMMPC_DATA)
+/* Watchdog */
+COMPATIBLE_IOCTL(WDIOC_GETSUPPORT)
+COMPATIBLE_IOCTL(WDIOC_GETSTATUS)
+COMPATIBLE_IOCTL(WDIOC_GETBOOTSTATUS)
+COMPATIBLE_IOCTL(WDIOC_GETTEMP)
+COMPATIBLE_IOCTL(WDIOC_SETOPTIONS)
+COMPATIBLE_IOCTL(WDIOC_KEEPALIVE)
+COMPATIBLE_IOCTL(WDIOC_SETTIMEOUT)
+COMPATIBLE_IOCTL(WDIOC_GETTIMEOUT)
+/* Big R */
+COMPATIBLE_IOCTL(RNDGETENTCNT)
+COMPATIBLE_IOCTL(RNDADDTOENTCNT)
+COMPATIBLE_IOCTL(RNDGETPOOL)
+COMPATIBLE_IOCTL(RNDADDENTROPY)
+COMPATIBLE_IOCTL(RNDZAPENTCNT)
+COMPATIBLE_IOCTL(RNDCLEARPOOL)
+/* Bluetooth */
+COMPATIBLE_IOCTL(HCIDEVUP)
+COMPATIBLE_IOCTL(HCIDEVDOWN)
+COMPATIBLE_IOCTL(HCIDEVRESET)
+COMPATIBLE_IOCTL(HCIDEVRESTAT)
+COMPATIBLE_IOCTL(HCIGETDEVLIST)
+COMPATIBLE_IOCTL(HCIGETDEVINFO)
+COMPATIBLE_IOCTL(HCIGETCONNLIST)
+COMPATIBLE_IOCTL(HCIGETCONNINFO)
+COMPATIBLE_IOCTL(HCISETRAW)
+COMPATIBLE_IOCTL(HCISETSCAN)
+COMPATIBLE_IOCTL(HCISETAUTH)
+COMPATIBLE_IOCTL(HCISETENCRYPT)
+COMPATIBLE_IOCTL(HCISETPTYPE)
+COMPATIBLE_IOCTL(HCISETLINKPOL)
+COMPATIBLE_IOCTL(HCISETLINKMODE)
+COMPATIBLE_IOCTL(HCISETACLMTU)
+COMPATIBLE_IOCTL(HCISETSCOMTU)
+COMPATIBLE_IOCTL(HCIINQUIRY)
+COMPATIBLE_IOCTL(HCIUARTSETPROTO)
+COMPATIBLE_IOCTL(HCIUARTGETPROTO)
+COMPATIBLE_IOCTL(RFCOMMCREATEDEV)
+COMPATIBLE_IOCTL(RFCOMMRELEASEDEV)
+COMPATIBLE_IOCTL(RFCOMMGETDEVLIST)
+COMPATIBLE_IOCTL(RFCOMMGETDEVINFO)
+COMPATIBLE_IOCTL(RFCOMMSTEALDLC)
+COMPATIBLE_IOCTL(BNEPCONNADD)
+COMPATIBLE_IOCTL(BNEPCONNDEL)
+COMPATIBLE_IOCTL(BNEPGETCONNLIST)
+COMPATIBLE_IOCTL(BNEPGETCONNINFO)
+COMPATIBLE_IOCTL(CMTPCONNADD)
+COMPATIBLE_IOCTL(CMTPCONNDEL)
+COMPATIBLE_IOCTL(CMTPGETCONNLIST)
+COMPATIBLE_IOCTL(CMTPGETCONNINFO)
+COMPATIBLE_IOCTL(HIDPCONNADD)
+COMPATIBLE_IOCTL(HIDPCONNDEL)
+COMPATIBLE_IOCTL(HIDPGETCONNLIST)
+COMPATIBLE_IOCTL(HIDPGETCONNINFO)
+/* CAPI */
+COMPATIBLE_IOCTL(CAPI_REGISTER)
+COMPATIBLE_IOCTL(CAPI_GET_MANUFACTURER)
+COMPATIBLE_IOCTL(CAPI_GET_VERSION)
+COMPATIBLE_IOCTL(CAPI_GET_SERIAL)
+COMPATIBLE_IOCTL(CAPI_GET_PROFILE)
+COMPATIBLE_IOCTL(CAPI_MANUFACTURER_CMD)
+COMPATIBLE_IOCTL(CAPI_GET_ERRCODE)
+COMPATIBLE_IOCTL(CAPI_INSTALLED)
+COMPATIBLE_IOCTL(CAPI_GET_FLAGS)
+COMPATIBLE_IOCTL(CAPI_SET_FLAGS)
+COMPATIBLE_IOCTL(CAPI_CLR_FLAGS)
+COMPATIBLE_IOCTL(CAPI_NCCI_OPENCOUNT)
+COMPATIBLE_IOCTL(CAPI_NCCI_GETUNIT)
+/* Siemens Gigaset */
+COMPATIBLE_IOCTL(GIGASET_REDIR)
+COMPATIBLE_IOCTL(GIGASET_CONFIG)
+COMPATIBLE_IOCTL(GIGASET_BRKCHARS)
+COMPATIBLE_IOCTL(GIGASET_VERSION)
+/* Misc. */
+COMPATIBLE_IOCTL(0x41545900) /* ATYIO_CLKR */
+COMPATIBLE_IOCTL(0x41545901) /* ATYIO_CLKW */
+COMPATIBLE_IOCTL(PCIIOC_CONTROLLER)
+COMPATIBLE_IOCTL(PCIIOC_MMAP_IS_IO)
+COMPATIBLE_IOCTL(PCIIOC_MMAP_IS_MEM)
+COMPATIBLE_IOCTL(PCIIOC_WRITE_COMBINE)
+/* USB */
+COMPATIBLE_IOCTL(USBDEVFS_RESETEP)
+COMPATIBLE_IOCTL(USBDEVFS_SETINTERFACE)
+COMPATIBLE_IOCTL(USBDEVFS_SETCONFIGURATION)
+COMPATIBLE_IOCTL(USBDEVFS_GETDRIVER)
+COMPATIBLE_IOCTL(USBDEVFS_DISCARDURB)
+COMPATIBLE_IOCTL(USBDEVFS_CLAIMINTERFACE)
+COMPATIBLE_IOCTL(USBDEVFS_RELEASEINTERFACE)
+COMPATIBLE_IOCTL(USBDEVFS_CONNECTINFO)
+COMPATIBLE_IOCTL(USBDEVFS_HUB_PORTINFO)
+COMPATIBLE_IOCTL(USBDEVFS_RESET)
+COMPATIBLE_IOCTL(USBDEVFS_SUBMITURB32)
+COMPATIBLE_IOCTL(USBDEVFS_REAPURB32)
+COMPATIBLE_IOCTL(USBDEVFS_REAPURBNDELAY32)
+COMPATIBLE_IOCTL(USBDEVFS_CLEAR_HALT)
+/* MTD */
+COMPATIBLE_IOCTL(MEMGETINFO)
+COMPATIBLE_IOCTL(MEMERASE)
+COMPATIBLE_IOCTL(MEMLOCK)
+COMPATIBLE_IOCTL(MEMUNLOCK)
+COMPATIBLE_IOCTL(MEMGETREGIONCOUNT)
+COMPATIBLE_IOCTL(MEMGETREGIONINFO)
+COMPATIBLE_IOCTL(MEMGETBADBLOCK)
+COMPATIBLE_IOCTL(MEMSETBADBLOCK)
+/* NBD */
+ULONG_IOCTL(NBD_SET_SOCK)
+ULONG_IOCTL(NBD_SET_BLKSIZE)
+ULONG_IOCTL(NBD_SET_SIZE)
+COMPATIBLE_IOCTL(NBD_DO_IT)
+COMPATIBLE_IOCTL(NBD_CLEAR_SOCK)
+COMPATIBLE_IOCTL(NBD_CLEAR_QUE)
+COMPATIBLE_IOCTL(NBD_PRINT_DEBUG)
+ULONG_IOCTL(NBD_SET_SIZE_BLOCKS)
+COMPATIBLE_IOCTL(NBD_DISCONNECT)
+/* i2c */
+COMPATIBLE_IOCTL(I2C_SLAVE)
+COMPATIBLE_IOCTL(I2C_SLAVE_FORCE)
+COMPATIBLE_IOCTL(I2C_TENBIT)
+COMPATIBLE_IOCTL(I2C_PEC)
+COMPATIBLE_IOCTL(I2C_RETRIES)
+COMPATIBLE_IOCTL(I2C_TIMEOUT)
+/* wireless */
+COMPATIBLE_IOCTL(SIOCSIWCOMMIT)
+COMPATIBLE_IOCTL(SIOCGIWNAME)
+COMPATIBLE_IOCTL(SIOCSIWNWID)
+COMPATIBLE_IOCTL(SIOCGIWNWID)
+COMPATIBLE_IOCTL(SIOCSIWFREQ)
+COMPATIBLE_IOCTL(SIOCGIWFREQ)
+COMPATIBLE_IOCTL(SIOCSIWMODE)
+COMPATIBLE_IOCTL(SIOCGIWMODE)
+COMPATIBLE_IOCTL(SIOCSIWSENS)
+COMPATIBLE_IOCTL(SIOCGIWSENS)
+COMPATIBLE_IOCTL(SIOCSIWRANGE)
+COMPATIBLE_IOCTL(SIOCSIWPRIV)
+COMPATIBLE_IOCTL(SIOCGIWPRIV)
+COMPATIBLE_IOCTL(SIOCSIWSTATS)
+COMPATIBLE_IOCTL(SIOCGIWSTATS)
+COMPATIBLE_IOCTL(SIOCSIWAP)
+COMPATIBLE_IOCTL(SIOCGIWAP)
+COMPATIBLE_IOCTL(SIOCSIWSCAN)
+COMPATIBLE_IOCTL(SIOCSIWRATE)
+COMPATIBLE_IOCTL(SIOCGIWRATE)
+COMPATIBLE_IOCTL(SIOCSIWRTS)
+COMPATIBLE_IOCTL(SIOCGIWRTS)
+COMPATIBLE_IOCTL(SIOCSIWFRAG)
+COMPATIBLE_IOCTL(SIOCGIWFRAG)
+COMPATIBLE_IOCTL(SIOCSIWTXPOW)
+COMPATIBLE_IOCTL(SIOCGIWTXPOW)
+COMPATIBLE_IOCTL(SIOCSIWRETRY)
+COMPATIBLE_IOCTL(SIOCGIWRETRY)
+COMPATIBLE_IOCTL(SIOCSIWPOWER)
+COMPATIBLE_IOCTL(SIOCGIWPOWER)
+/* hiddev */
+COMPATIBLE_IOCTL(HIDIOCGVERSION)
+COMPATIBLE_IOCTL(HIDIOCAPPLICATION)
+COMPATIBLE_IOCTL(HIDIOCGDEVINFO)
+COMPATIBLE_IOCTL(HIDIOCGSTRING)
+COMPATIBLE_IOCTL(HIDIOCINITREPORT)
+COMPATIBLE_IOCTL(HIDIOCGREPORT)
+COMPATIBLE_IOCTL(HIDIOCSREPORT)
+COMPATIBLE_IOCTL(HIDIOCGREPORTINFO)
+COMPATIBLE_IOCTL(HIDIOCGFIELDINFO)
+COMPATIBLE_IOCTL(HIDIOCGUSAGE)
+COMPATIBLE_IOCTL(HIDIOCSUSAGE)
+COMPATIBLE_IOCTL(HIDIOCGUCODE)
+COMPATIBLE_IOCTL(HIDIOCGFLAG)
+COMPATIBLE_IOCTL(HIDIOCSFLAG)
+COMPATIBLE_IOCTL(HIDIOCGCOLLECTIONINDEX)
+COMPATIBLE_IOCTL(HIDIOCGCOLLECTIONINFO)
+/* dvb */
+COMPATIBLE_IOCTL(AUDIO_STOP)
+COMPATIBLE_IOCTL(AUDIO_PLAY)
+COMPATIBLE_IOCTL(AUDIO_PAUSE)
+COMPATIBLE_IOCTL(AUDIO_CONTINUE)
+COMPATIBLE_IOCTL(AUDIO_SELECT_SOURCE)
+COMPATIBLE_IOCTL(AUDIO_SET_MUTE)
+COMPATIBLE_IOCTL(AUDIO_SET_AV_SYNC)
+COMPATIBLE_IOCTL(AUDIO_SET_BYPASS_MODE)
+COMPATIBLE_IOCTL(AUDIO_CHANNEL_SELECT)
+COMPATIBLE_IOCTL(AUDIO_GET_STATUS)
+COMPATIBLE_IOCTL(AUDIO_GET_CAPABILITIES)
+COMPATIBLE_IOCTL(AUDIO_CLEAR_BUFFER)
+COMPATIBLE_IOCTL(AUDIO_SET_ID)
+COMPATIBLE_IOCTL(AUDIO_SET_MIXER)
+COMPATIBLE_IOCTL(AUDIO_SET_STREAMTYPE)
+COMPATIBLE_IOCTL(AUDIO_SET_EXT_ID)
+COMPATIBLE_IOCTL(AUDIO_SET_ATTRIBUTES)
+COMPATIBLE_IOCTL(AUDIO_SET_KARAOKE)
+COMPATIBLE_IOCTL(DMX_START)
+COMPATIBLE_IOCTL(DMX_STOP)
+COMPATIBLE_IOCTL(DMX_SET_FILTER)
+COMPATIBLE_IOCTL(DMX_SET_PES_FILTER)
+COMPATIBLE_IOCTL(DMX_SET_BUFFER_SIZE)
+COMPATIBLE_IOCTL(DMX_GET_PES_PIDS)
+COMPATIBLE_IOCTL(DMX_GET_CAPS)
+COMPATIBLE_IOCTL(DMX_SET_SOURCE)
+COMPATIBLE_IOCTL(DMX_GET_STC)
+COMPATIBLE_IOCTL(FE_GET_INFO)
+COMPATIBLE_IOCTL(FE_DISEQC_RESET_OVERLOAD)
+COMPATIBLE_IOCTL(FE_DISEQC_SEND_MASTER_CMD)
+COMPATIBLE_IOCTL(FE_DISEQC_RECV_SLAVE_REPLY)
+COMPATIBLE_IOCTL(FE_DISEQC_SEND_BURST)
+COMPATIBLE_IOCTL(FE_SET_TONE)
+COMPATIBLE_IOCTL(FE_SET_VOLTAGE)
+COMPATIBLE_IOCTL(FE_ENABLE_HIGH_LNB_VOLTAGE)
+COMPATIBLE_IOCTL(FE_READ_STATUS)
+COMPATIBLE_IOCTL(FE_READ_BER)
+COMPATIBLE_IOCTL(FE_READ_SIGNAL_STRENGTH)
+COMPATIBLE_IOCTL(FE_READ_SNR)
+COMPATIBLE_IOCTL(FE_READ_UNCORRECTED_BLOCKS)
+COMPATIBLE_IOCTL(FE_SET_FRONTEND)
+COMPATIBLE_IOCTL(FE_GET_FRONTEND)
+COMPATIBLE_IOCTL(FE_GET_EVENT)
+COMPATIBLE_IOCTL(FE_DISHNETWORK_SEND_LEGACY_CMD)
+COMPATIBLE_IOCTL(VIDEO_STOP)
+COMPATIBLE_IOCTL(VIDEO_PLAY)
+COMPATIBLE_IOCTL(VIDEO_FREEZE)
+COMPATIBLE_IOCTL(VIDEO_CONTINUE)
+COMPATIBLE_IOCTL(VIDEO_SELECT_SOURCE)
+COMPATIBLE_IOCTL(VIDEO_SET_BLANK)
+COMPATIBLE_IOCTL(VIDEO_GET_STATUS)
+COMPATIBLE_IOCTL(VIDEO_SET_DISPLAY_FORMAT)
+COMPATIBLE_IOCTL(VIDEO_FAST_FORWARD)
+COMPATIBLE_IOCTL(VIDEO_SLOWMOTION)
+COMPATIBLE_IOCTL(VIDEO_GET_CAPABILITIES)
+COMPATIBLE_IOCTL(VIDEO_CLEAR_BUFFER)
+COMPATIBLE_IOCTL(VIDEO_SET_ID)
+COMPATIBLE_IOCTL(VIDEO_SET_STREAMTYPE)
+COMPATIBLE_IOCTL(VIDEO_SET_FORMAT)
+COMPATIBLE_IOCTL(VIDEO_SET_SYSTEM)
+COMPATIBLE_IOCTL(VIDEO_SET_HIGHLIGHT)
+COMPATIBLE_IOCTL(VIDEO_SET_SPU)
+COMPATIBLE_IOCTL(VIDEO_GET_NAVI)
+COMPATIBLE_IOCTL(VIDEO_SET_ATTRIBUTES)
+COMPATIBLE_IOCTL(VIDEO_GET_SIZE)
+COMPATIBLE_IOCTL(VIDEO_GET_FRAME_RATE)
+
+/* now things that need handlers */
HANDLE_IOCTL(MEMREADOOB32, mtd_rw_oob)
HANDLE_IOCTL(MEMWRITEOOB32, mtd_rw_oob)
#ifdef CONFIG_NET
@@ -2638,4 +3491,159 @@ IGNORE_IOCTL(VFAT_IOCTL_READDIR_BOTH32)
IGNORE_IOCTL(VFAT_IOCTL_READDIR_SHORT32)
};
-int ioctl_table_size = ARRAY_SIZE(ioctl_start);
+#define IOCTL_HASHSIZE 256
+static struct ioctl_trans *ioctl32_hash_table[IOCTL_HASHSIZE];
+
+static inline unsigned long ioctl32_hash(unsigned long cmd)
+{
+ return (((cmd >> 6) ^ (cmd >> 4) ^ cmd)) % IOCTL_HASHSIZE;
+}
+
+static void compat_ioctl_error(struct file *filp, unsigned int fd,
+ unsigned int cmd, unsigned long arg)
+{
+ char buf[10];
+ char *fn = "?";
+ char *path;
+
+ /* find the name of the device. */
+ path = (char *)__get_free_page(GFP_KERNEL);
+ if (path) {
+ fn = d_path(filp->f_path.dentry, filp->f_path.mnt, path, PAGE_SIZE);
+ if (IS_ERR(fn))
+ fn = "?";
+ }
+
+ sprintf(buf,"'%c'", (cmd>>_IOC_TYPESHIFT) & _IOC_TYPEMASK);
+ if (!isprint(buf[1]))
+ sprintf(buf, "%02x", buf[1]);
+ compat_printk("ioctl32(%s:%d): Unknown cmd fd(%d) "
+ "cmd(%08x){t:%s;sz:%u} arg(%08x) on %s\n",
+ current->comm, current->pid,
+ (int)fd, (unsigned int)cmd, buf,
+ (cmd >> _IOC_SIZESHIFT) & _IOC_SIZEMASK,
+ (unsigned int)arg, fn);
+
+ if (path)
+ free_page((unsigned long)path);
+}
+
+asmlinkage long compat_sys_ioctl(unsigned int fd, unsigned int cmd,
+ unsigned long arg)
+{
+ struct file *filp;
+ int error = -EBADF;
+ struct ioctl_trans *t;
+ int fput_needed;
+
+ filp = fget_light(fd, &fput_needed);
+ if (!filp)
+ goto out;
+
+ /* RED-PEN how should LSM module know it's handling 32bit? */
+ error = security_file_ioctl(filp, cmd, arg);
+ if (error)
+ goto out_fput;
+
+ /*
+ * To allow the compat_ioctl handlers to be self contained
+ * we need to check the common ioctls here first.
+ * Just handle them with the standard handlers below.
+ */
+ switch (cmd) {
+ case FIOCLEX:
+ case FIONCLEX:
+ case FIONBIO:
+ case FIOASYNC:
+ case FIOQSIZE:
+ break;
+
+ case FIBMAP:
+ case FIGETBSZ:
+ case FIONREAD:
+ if (S_ISREG(filp->f_path.dentry->d_inode->i_mode))
+ break;
+ /*FALL THROUGH*/
+
+ default:
+ if (filp->f_op && filp->f_op->compat_ioctl) {
+ error = filp->f_op->compat_ioctl(filp, cmd, arg);
+ if (error != -ENOIOCTLCMD)
+ goto out_fput;
+ }
+
+ if (!filp->f_op ||
+ (!filp->f_op->ioctl && !filp->f_op->unlocked_ioctl))
+ goto do_ioctl;
+ break;
+ }
+
+ for (t = ioctl32_hash_table[ioctl32_hash(cmd)]; t; t = t->next) {
+ if (t->cmd == cmd)
+ goto found_handler;
+ }
+
+#ifdef CONFIG_NET
+ if (S_ISSOCK(filp->f_path.dentry->d_inode->i_mode) &&
+ cmd >= SIOCDEVPRIVATE && cmd <= (SIOCDEVPRIVATE + 15)) {
+ error = siocdevprivate_ioctl(fd, cmd, arg);
+ } else
+#endif
+ {
+ static int count;
+
+ if (++count <= 50)
+ compat_ioctl_error(filp, fd, cmd, arg);
+ error = -EINVAL;
+ }
+
+ goto out_fput;
+
+ found_handler:
+ if (t->handler) {
+ lock_kernel();
+ error = t->handler(fd, cmd, arg, filp);
+ unlock_kernel();
+ goto out_fput;
+ }
+
+ do_ioctl:
+ error = vfs_ioctl(filp, fd, cmd, arg);
+ out_fput:
+ fput_light(filp, fput_needed);
+ out:
+ return error;
+}
+
+static void ioctl32_insert_translation(struct ioctl_trans *trans)
+{
+ unsigned long hash;
+ struct ioctl_trans *t;
+
+ hash = ioctl32_hash (trans->cmd);
+ if (!ioctl32_hash_table[hash])
+ ioctl32_hash_table[hash] = trans;
+ else {
+ t = ioctl32_hash_table[hash];
+ while (t->next)
+ t = t->next;
+ trans->next = NULL;
+ t->next = trans;
+ }
+}
+
+static int __init init_sys32_ioctl(void)
+{
+ int i;
+
+ for (i = 0; i < ARRAY_SIZE(ioctl_start); i++) {
+ if (ioctl_start[i].next != 0) {
+ printk("ioctl translation %d bad\n",i);
+ return -1;
+ }
+
+ ioctl32_insert_translation(&ioctl_start[i]);
+ }
+ return 0;
+}
+__initcall(init_sys32_ioctl);
diff --git a/fs/configfs/file.c b/fs/configfs/file.c
index d98be5e0132..3527c7c6def 100644
--- a/fs/configfs/file.c
+++ b/fs/configfs/file.c
@@ -77,36 +77,6 @@ static int fill_read_buffer(struct dentry * dentry, struct configfs_buffer * buf
return ret;
}
-
-/**
- * flush_read_buffer - push buffer to userspace.
- * @buffer: data buffer for file.
- * @userbuf: user-passed buffer.
- * @count: number of bytes requested.
- * @ppos: file position.
- *
- * Copy the buffer we filled in fill_read_buffer() to userspace.
- * This is done at the reader's leisure, copying and advancing
- * the amount they specify each time.
- * This may be called continuously until the buffer is empty.
- */
-static int flush_read_buffer(struct configfs_buffer * buffer, char __user * buf,
- size_t count, loff_t * ppos)
-{
- int error;
-
- if (*ppos > buffer->count)
- return 0;
-
- if (count > (buffer->count - *ppos))
- count = buffer->count - *ppos;
-
- error = copy_to_user(buf,buffer->page + *ppos,count);
- if (!error)
- *ppos += count;
- return error ? -EFAULT : count;
-}
-
/**
* configfs_read_file - read an attribute.
* @file: file pointer.
@@ -139,7 +109,8 @@ configfs_read_file(struct file *file, char __user *buf, size_t count, loff_t *pp
}
pr_debug("%s: count = %zd, ppos = %lld, buf = %s\n",
__FUNCTION__, count, *ppos, buffer->page);
- retval = flush_read_buffer(buffer,buf,count,ppos);
+ retval = simple_read_from_buffer(buf, count, ppos, buffer->page,
+ buffer->count);
out:
up(&buffer->sem);
return retval;
diff --git a/fs/configfs/inode.c b/fs/configfs/inode.c
index 2ec9beac17c..ddc003a9d21 100644
--- a/fs/configfs/inode.c
+++ b/fs/configfs/inode.c
@@ -32,6 +32,7 @@
#include <linux/namei.h>
#include <linux/backing-dev.h>
#include <linux/capability.h>
+#include <linux/sched.h>
#include <linux/configfs.h>
#include "configfs_internal.h"
diff --git a/fs/dcache.c b/fs/dcache.c
index d1bf5d8aeb5..0e73aa0a0e8 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -21,7 +21,6 @@
#include <linux/fsnotify.h>
#include <linux/slab.h>
#include <linux/init.h>
-#include <linux/smp_lock.h>
#include <linux/hash.h>
#include <linux/cache.h>
#include <linux/module.h>
@@ -121,6 +120,28 @@ static void dentry_iput(struct dentry * dentry)
}
}
+/**
+ * d_kill - kill dentry and return parent
+ * @dentry: dentry to kill
+ *
+ * Called with dcache_lock and d_lock, releases both. The dentry must
+ * already be unhashed and removed from the LRU.
+ *
+ * If this is the root of the dentry tree, return NULL.
+ */
+static struct dentry *d_kill(struct dentry *dentry)
+{
+ struct dentry *parent;
+
+ list_del(&dentry->d_u.d_child);
+ dentry_stat.nr_dentry--; /* For d_free, below */
+ /*drops the locks, at that point nobody can reach this dentry */
+ dentry_iput(dentry);
+ parent = dentry->d_parent;
+ d_free(dentry);
+ return dentry == parent ? NULL : parent;
+}
+
/*
* This is dput
*
@@ -189,28 +210,17 @@ repeat:
unhash_it:
__d_drop(dentry);
-
-kill_it: {
- struct dentry *parent;
-
- /* If dentry was on d_lru list
- * delete it from there
- */
- if (!list_empty(&dentry->d_lru)) {
- list_del(&dentry->d_lru);
- dentry_stat.nr_unused--;
- }
- list_del(&dentry->d_u.d_child);
- dentry_stat.nr_dentry--; /* For d_free, below */
- /*drops the locks, at that point nobody can reach this dentry */
- dentry_iput(dentry);
- parent = dentry->d_parent;
- d_free(dentry);
- if (dentry == parent)
- return;
- dentry = parent;
- goto repeat;
+kill_it:
+ /* If dentry was on d_lru list
+ * delete it from there
+ */
+ if (!list_empty(&dentry->d_lru)) {
+ list_del(&dentry->d_lru);
+ dentry_stat.nr_unused--;
}
+ dentry = d_kill(dentry);
+ if (dentry)
+ goto repeat;
}
/**
@@ -371,22 +381,40 @@ restart:
* Throw away a dentry - free the inode, dput the parent. This requires that
* the LRU list has already been removed.
*
+ * If prune_parents is true, try to prune ancestors as well.
+ *
* Called with dcache_lock, drops it and then regains.
* Called with dentry->d_lock held, drops it.
*/
-static void prune_one_dentry(struct dentry * dentry)
+static void prune_one_dentry(struct dentry * dentry, int prune_parents)
{
- struct dentry * parent;
-
__d_drop(dentry);
- list_del(&dentry->d_u.d_child);
- dentry_stat.nr_dentry--; /* For d_free, below */
- dentry_iput(dentry);
- parent = dentry->d_parent;
- d_free(dentry);
- if (parent != dentry)
- dput(parent);
+ dentry = d_kill(dentry);
+ if (!prune_parents) {
+ dput(dentry);
+ spin_lock(&dcache_lock);
+ return;
+ }
+
+ /*
+ * Prune ancestors. Locking is simpler than in dput(),
+ * because dcache_lock needs to be taken anyway.
+ */
spin_lock(&dcache_lock);
+ while (dentry) {
+ if (!atomic_dec_and_lock(&dentry->d_count, &dentry->d_lock))
+ return;
+
+ if (dentry->d_op && dentry->d_op->d_delete)
+ dentry->d_op->d_delete(dentry);
+ if (!list_empty(&dentry->d_lru)) {
+ list_del(&dentry->d_lru);
+ dentry_stat.nr_unused--;
+ }
+ __d_drop(dentry);
+ dentry = d_kill(dentry);
+ spin_lock(&dcache_lock);
+ }
}
/**
@@ -394,6 +422,7 @@ static void prune_one_dentry(struct dentry * dentry)
* @count: number of entries to try and free
* @sb: if given, ignore dentries for other superblocks
* which are being unmounted.
+ * @prune_parents: if true, try to prune ancestors as well in one go
*
* Shrink the dcache. This is done when we need
* more memory, or simply when we need to unmount
@@ -404,7 +433,7 @@ static void prune_one_dentry(struct dentry * dentry)
* all the dentries are in use.
*/
-static void prune_dcache(int count, struct super_block *sb)
+static void prune_dcache(int count, struct super_block *sb, int prune_parents)
{
spin_lock(&dcache_lock);
for (; count ; count--) {
@@ -464,7 +493,7 @@ static void prune_dcache(int count, struct super_block *sb)
* without taking the s_umount lock (I already hold it).
*/
if (sb && dentry->d_sb == sb) {
- prune_one_dentry(dentry);
+ prune_one_dentry(dentry, prune_parents);
continue;
}
/*
@@ -479,7 +508,7 @@ static void prune_dcache(int count, struct super_block *sb)
s_umount = &dentry->d_sb->s_umount;
if (down_read_trylock(s_umount)) {
if (dentry->d_sb->s_root != NULL) {
- prune_one_dentry(dentry);
+ prune_one_dentry(dentry, prune_parents);
up_read(s_umount);
continue;
}
@@ -550,7 +579,7 @@ repeat:
spin_unlock(&dentry->d_lock);
continue;
}
- prune_one_dentry(dentry);
+ prune_one_dentry(dentry, 1);
cond_resched_lock(&dcache_lock);
goto repeat;
}
@@ -829,7 +858,7 @@ void shrink_dcache_parent(struct dentry * parent)
int found;
while ((found = select_parent(parent)) != 0)
- prune_dcache(found, parent->d_sb);
+ prune_dcache(found, parent->d_sb, 1);
}
/*
@@ -849,7 +878,7 @@ static int shrink_dcache_memory(int nr, gfp_t gfp_mask)
if (nr) {
if (!(gfp_mask & __GFP_FS))
return -1;
- prune_dcache(nr, NULL);
+ prune_dcache(nr, NULL, 1);
}
return (dentry_stat.nr_unused / 100) * sysctl_vfs_cache_pressure;
}
@@ -1823,6 +1852,16 @@ char * d_path(struct dentry *dentry, struct vfsmount *vfsmnt,
struct vfsmount *rootmnt;
struct dentry *root;
+ /*
+ * We have various synthetic filesystems that never get mounted. On
+ * these filesystems dentries are never used for lookup purposes, and
+ * thus don't need to be hashed. They also don't need a name until a
+ * user wants to identify the object in /proc/pid/fd/. The little hack
+ * below allows us to generate a name for these objects on demand:
+ */
+ if (dentry->d_op && dentry->d_op->d_dname)
+ return dentry->d_op->d_dname(dentry, buf, buflen);
+
read_lock(&current->fs->lock);
rootmnt = mntget(current->fs->rootmnt);
root = dget(current->fs->root);
@@ -1836,6 +1875,27 @@ char * d_path(struct dentry *dentry, struct vfsmount *vfsmnt,
}
/*
+ * Helper function for dentry_operations.d_dname() members
+ */
+char *dynamic_dname(struct dentry *dentry, char *buffer, int buflen,
+ const char *fmt, ...)
+{
+ va_list args;
+ char temp[64];
+ int sz;
+
+ va_start(args, fmt);
+ sz = vsnprintf(temp, sizeof(temp), fmt, args) + 1;
+ va_end(args);
+
+ if (sz > sizeof(temp) || sz > buflen)
+ return ERR_PTR(-ENAMETOOLONG);
+
+ buffer += buflen - sz;
+ return memcpy(buffer, temp, sz);
+}
+
+/*
* NOTE! The user-level library version returns a
* character pointer. The kernel system call just
* returns the length of the buffer filled (which
diff --git a/fs/devpts/inode.c b/fs/devpts/inode.c
index 643e57b622b..06ef9a255c7 100644
--- a/fs/devpts/inode.c
+++ b/fs/devpts/inode.c
@@ -19,6 +19,7 @@
#include <linux/tty.h>
#include <linux/devpts_fs.h>
#include <linux/parser.h>
+#include <linux/fsnotify.h>
#define DEVPTS_SUPER_MAGIC 0x1cd1
@@ -178,8 +179,10 @@ int devpts_pty_new(struct tty_struct *tty)
inode->i_private = tty;
dentry = get_node(number);
- if (!IS_ERR(dentry) && !dentry->d_inode)
+ if (!IS_ERR(dentry) && !dentry->d_inode) {
d_instantiate(dentry, inode);
+ fsnotify_create(devpts_root->d_inode, dentry);
+ }
mutex_unlock(&devpts_root->d_inode->i_mutex);
diff --git a/fs/direct-io.c b/fs/direct-io.c
index d9d0833444f..52bb2638f7a 100644
--- a/fs/direct-io.c
+++ b/fs/direct-io.c
@@ -439,7 +439,7 @@ static int dio_bio_complete(struct dio *dio, struct bio *bio)
* Wait on and process all in-flight BIOs. This must only be called once
* all bios have been issued so that the refcount can only decrease.
* This just waits for all bios to make it through dio_bio_complete. IO
- * errors are propogated through dio->io_error and should be propogated via
+ * errors are propagated through dio->io_error and should be propagated via
* dio_complete().
*/
static void dio_await_completion(struct dio *dio)
@@ -867,7 +867,6 @@ static int do_direct_IO(struct dio *dio)
do_holes:
/* Handle holes */
if (!buffer_mapped(map_bh)) {
- char *kaddr;
loff_t i_size_aligned;
/* AKPM: eargh, -ENOTBLK is a hack */
@@ -888,11 +887,8 @@ do_holes:
page_cache_release(page);
goto out;
}
- kaddr = kmap_atomic(page, KM_USER0);
- memset(kaddr + (block_in_page << blkbits),
- 0, 1 << blkbits);
- flush_dcache_page(page);
- kunmap_atomic(kaddr, KM_USER0);
+ zero_user_page(page, block_in_page << blkbits,
+ 1 << blkbits, KM_USER0);
dio->block_in_file++;
block_in_page++;
goto next_block;
@@ -1110,7 +1106,7 @@ direct_io_worker(int rw, struct kiocb *iocb, struct inode *inode,
spin_lock_irqsave(&dio->bio_lock, flags);
ret2 = --dio->refcount;
spin_unlock_irqrestore(&dio->bio_lock, flags);
- BUG_ON(!dio->is_async && ret2 != 0);
+
if (ret2 == 0) {
ret = dio_complete(dio, offset, ret);
kfree(dio);
diff --git a/fs/dquot.c b/fs/dquot.c
index 0a5febc159f..8819d281500 100644
--- a/fs/dquot.c
+++ b/fs/dquot.c
@@ -69,7 +69,6 @@
#include <linux/file.h>
#include <linux/slab.h>
#include <linux/sysctl.h>
-#include <linux/smp_lock.h>
#include <linux/init.h>
#include <linux/module.h>
#include <linux/proc_fs.h>
@@ -475,7 +474,7 @@ int vfs_quota_sync(struct super_block *sb, int type)
spin_lock(&dq_list_lock);
dirty = &dqopt->info[cnt].dqi_dirty_list;
while (!list_empty(dirty)) {
- dquot = list_entry(dirty->next, struct dquot, dq_dirty);
+ dquot = list_first_entry(dirty, struct dquot, dq_dirty);
/* Dirty and inactive can be only bad dquot... */
if (!test_bit(DQ_ACTIVE_B, &dquot->dq_flags)) {
clear_dquot_dirty(dquot);
@@ -721,7 +720,8 @@ static inline int dqput_blocks(struct dquot *dquot)
/* Remove references to dquots from inode - add dquot to list for freeing if needed */
/* We can't race with anybody because we hold dqptr_sem for writing... */
-int remove_inode_dquot_ref(struct inode *inode, int type, struct list_head *tofree_head)
+static int remove_inode_dquot_ref(struct inode *inode, int type,
+ struct list_head *tofree_head)
{
struct dquot *dquot = inode->i_dquot[type];
@@ -1421,7 +1421,7 @@ int vfs_quota_off(struct super_block *sb, int type)
/* If quota was reenabled in the meantime, we have
* nothing to do */
if (!sb_has_quota_enabled(sb, cnt)) {
- mutex_lock(&toputinode[cnt]->i_mutex);
+ mutex_lock_nested(&toputinode[cnt]->i_mutex, I_MUTEX_QUOTA);
toputinode[cnt]->i_flags &= ~(S_IMMUTABLE |
S_NOATIME | S_NOQUOTA);
truncate_inode_pages(&toputinode[cnt]->i_data, 0);
diff --git a/fs/ecryptfs/ecryptfs_kernel.h b/fs/ecryptfs/ecryptfs_kernel.h
index 403e3bad145..1b9dd9a96f1 100644
--- a/fs/ecryptfs/ecryptfs_kernel.h
+++ b/fs/ecryptfs/ecryptfs_kernel.h
@@ -580,5 +580,7 @@ void
ecryptfs_write_header_metadata(char *virt,
struct ecryptfs_crypt_stat *crypt_stat,
size_t *written);
+int ecryptfs_write_zeros(struct file *file, pgoff_t index, int start,
+ int num_zeros);
#endif /* #ifndef ECRYPTFS_KERNEL_H */
diff --git a/fs/ecryptfs/file.c b/fs/ecryptfs/file.c
index 7a7d25d541e..59288d81707 100644
--- a/fs/ecryptfs/file.c
+++ b/fs/ecryptfs/file.c
@@ -28,69 +28,11 @@
#include <linux/mount.h>
#include <linux/pagemap.h>
#include <linux/security.h>
-#include <linux/smp_lock.h>
#include <linux/compat.h>
#include <linux/fs_stack.h>
#include "ecryptfs_kernel.h"
/**
- * ecryptfs_llseek
- * @file: File we are seeking in
- * @offset: The offset to seek to
- * @origin: 2 - offset from i_size; 1 - offset from f_pos
- *
- * Returns the position we have seeked to, or negative on error
- */
-static loff_t ecryptfs_llseek(struct file *file, loff_t offset, int origin)
-{
- loff_t rv;
- loff_t new_end_pos;
- int rc;
- int expanding_file = 0;
- struct inode *inode = file->f_mapping->host;
-
- /* If our offset is past the end of our file, we're going to
- * need to grow it so we have a valid length of 0's */
- new_end_pos = offset;
- switch (origin) {
- case 2:
- new_end_pos += i_size_read(inode);
- expanding_file = 1;
- break;
- case 1:
- new_end_pos += file->f_pos;
- if (new_end_pos > i_size_read(inode)) {
- ecryptfs_printk(KERN_DEBUG, "new_end_pos(=[0x%.16x]) "
- "> i_size_read(inode)(=[0x%.16x])\n",
- new_end_pos, i_size_read(inode));
- expanding_file = 1;
- }
- break;
- default:
- if (new_end_pos > i_size_read(inode)) {
- ecryptfs_printk(KERN_DEBUG, "new_end_pos(=[0x%.16x]) "
- "> i_size_read(inode)(=[0x%.16x])\n",
- new_end_pos, i_size_read(inode));
- expanding_file = 1;
- }
- }
- ecryptfs_printk(KERN_DEBUG, "new_end_pos = [0x%.16x]\n", new_end_pos);
- if (expanding_file) {
- rc = ecryptfs_truncate(file->f_path.dentry, new_end_pos);
- if (rc) {
- rv = rc;
- ecryptfs_printk(KERN_ERR, "Error on attempt to "
- "truncate to (higher) offset [0x%.16x];"
- " rc = [%d]\n", new_end_pos, rc);
- goto out;
- }
- }
- rv = generic_file_llseek(file, offset, origin);
-out:
- return rv;
-}
-
-/**
* ecryptfs_read_update_atime
*
* generic_file_read updates the atime of upper layer inode. But, it
@@ -426,7 +368,7 @@ const struct file_operations ecryptfs_dir_fops = {
};
const struct file_operations ecryptfs_main_fops = {
- .llseek = ecryptfs_llseek,
+ .llseek = generic_file_llseek,
.read = do_sync_read,
.aio_read = ecryptfs_read_update_atime,
.write = do_sync_write,
diff --git a/fs/ecryptfs/inode.c b/fs/ecryptfs/inode.c
index 1548be26b5e..83e94fedd4e 100644
--- a/fs/ecryptfs/inode.c
+++ b/fs/ecryptfs/inode.c
@@ -800,6 +800,25 @@ int ecryptfs_truncate(struct dentry *dentry, loff_t new_length)
goto out_fput;
}
} else { /* new_length < i_size_read(inode) */
+ pgoff_t index = 0;
+ int end_pos_in_page = -1;
+
+ if (new_length != 0) {
+ index = ((new_length - 1) >> PAGE_CACHE_SHIFT);
+ end_pos_in_page = ((new_length - 1) & ~PAGE_CACHE_MASK);
+ }
+ if (end_pos_in_page != (PAGE_CACHE_SIZE - 1)) {
+ if ((rc = ecryptfs_write_zeros(&fake_ecryptfs_file,
+ index,
+ (end_pos_in_page + 1),
+ ((PAGE_CACHE_SIZE - 1)
+ - end_pos_in_page)))) {
+ printk(KERN_ERR "Error attempting to zero out "
+ "the remainder of the end page on "
+ "reducing truncate; rc = [%d]\n", rc);
+ goto out_fput;
+ }
+ }
vmtruncate(inode, new_length);
rc = ecryptfs_write_inode_size_to_metadata(
lower_file, lower_dentry->d_inode, inode, dentry,
@@ -875,9 +894,54 @@ static int ecryptfs_setattr(struct dentry *dentry, struct iattr *ia)
struct ecryptfs_crypt_stat *crypt_stat;
crypt_stat = &ecryptfs_inode_to_private(dentry->d_inode)->crypt_stat;
- lower_dentry = ecryptfs_dentry_to_lower(dentry);
+ if (!(crypt_stat->flags & ECRYPTFS_STRUCT_INITIALIZED))
+ ecryptfs_init_crypt_stat(crypt_stat);
inode = dentry->d_inode;
lower_inode = ecryptfs_inode_to_lower(inode);
+ lower_dentry = ecryptfs_dentry_to_lower(dentry);
+ mutex_lock(&crypt_stat->cs_mutex);
+ if (S_ISDIR(dentry->d_inode->i_mode))
+ crypt_stat->flags &= ~(ECRYPTFS_ENCRYPTED);
+ else if (!(crypt_stat->flags & ECRYPTFS_POLICY_APPLIED)
+ || !(crypt_stat->flags & ECRYPTFS_KEY_VALID)) {
+ struct vfsmount *lower_mnt;
+ struct file *lower_file = NULL;
+ struct ecryptfs_mount_crypt_stat *mount_crypt_stat;
+ int lower_flags;
+
+ lower_mnt = ecryptfs_dentry_to_lower_mnt(dentry);
+ lower_flags = O_RDONLY;
+ if ((rc = ecryptfs_open_lower_file(&lower_file, lower_dentry,
+ lower_mnt, lower_flags))) {
+ printk(KERN_ERR
+ "Error opening lower file; rc = [%d]\n", rc);
+ mutex_unlock(&crypt_stat->cs_mutex);
+ goto out;
+ }
+ mount_crypt_stat = &ecryptfs_superblock_to_private(
+ dentry->d_sb)->mount_crypt_stat;
+ if ((rc = ecryptfs_read_metadata(dentry, lower_file))) {
+ if (!(mount_crypt_stat->flags
+ & ECRYPTFS_PLAINTEXT_PASSTHROUGH_ENABLED)) {
+ rc = -EIO;
+ printk(KERN_WARNING "Attempt to read file that "
+ "is not in a valid eCryptfs format, "
+ "and plaintext passthrough mode is not "
+ "enabled; returning -EIO\n");
+
+ mutex_unlock(&crypt_stat->cs_mutex);
+ fput(lower_file);
+ goto out;
+ }
+ rc = 0;
+ crypt_stat->flags &= ~(ECRYPTFS_ENCRYPTED);
+ mutex_unlock(&crypt_stat->cs_mutex);
+ fput(lower_file);
+ goto out;
+ }
+ fput(lower_file);
+ }
+ mutex_unlock(&crypt_stat->cs_mutex);
if (ia->ia_valid & ATTR_SIZE) {
ecryptfs_printk(KERN_DEBUG,
"ia->ia_valid = [0x%x] ATTR_SIZE" " = [0x%x]\n",
diff --git a/fs/ecryptfs/main.c b/fs/ecryptfs/main.c
index 8cbf3f69ebe..606128f5c92 100644
--- a/fs/ecryptfs/main.c
+++ b/fs/ecryptfs/main.c
@@ -583,8 +583,7 @@ inode_info_init_once(void *vptr, struct kmem_cache *cachep, unsigned long flags)
{
struct ecryptfs_inode_info *ei = (struct ecryptfs_inode_info *)vptr;
- if (flags & SLAB_CTOR_CONSTRUCTOR)
- inode_init_once(&ei->vfs_inode);
+ inode_init_once(&ei->vfs_inode);
}
static struct ecryptfs_cache_info {
diff --git a/fs/ecryptfs/messaging.c b/fs/ecryptfs/messaging.c
index 3baf253be95..a9d87c47f72 100644
--- a/fs/ecryptfs/messaging.c
+++ b/fs/ecryptfs/messaging.c
@@ -19,7 +19,7 @@
* Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA
* 02111-1307, USA.
*/
-
+#include <linux/sched.h>
#include "ecryptfs_kernel.h"
static LIST_HEAD(ecryptfs_msg_ctx_free_list);
diff --git a/fs/ecryptfs/mmap.c b/fs/ecryptfs/mmap.c
index 0770c4b66f5..7d5a43cb0d5 100644
--- a/fs/ecryptfs/mmap.c
+++ b/fs/ecryptfs/mmap.c
@@ -56,9 +56,6 @@ static struct page *ecryptfs_get1page(struct file *file, int index)
return read_mapping_page(mapping, index, (void *)file);
}
-static
-int write_zeros(struct file *file, pgoff_t index, int start, int num_zeros);
-
/**
* ecryptfs_fill_zeros
* @file: The ecryptfs file
@@ -101,10 +98,13 @@ int ecryptfs_fill_zeros(struct file *file, loff_t new_length)
if (old_end_page_index == new_end_page_index) {
/* Start and end are in the same page; we just need to
* set a portion of the existing page to zero's */
- rc = write_zeros(file, index, (old_end_pos_in_page + 1),
- (new_end_pos_in_page - old_end_pos_in_page));
+ rc = ecryptfs_write_zeros(file, index,
+ (old_end_pos_in_page + 1),
+ (new_end_pos_in_page
+ - old_end_pos_in_page));
if (rc)
- ecryptfs_printk(KERN_ERR, "write_zeros(file=[%p], "
+ ecryptfs_printk(KERN_ERR, "ecryptfs_write_zeros("
+ "file=[%p], "
"index=[0x%.16x], "
"old_end_pos_in_page=[d], "
"(PAGE_CACHE_SIZE - new_end_pos_in_page"
@@ -117,10 +117,10 @@ int ecryptfs_fill_zeros(struct file *file, loff_t new_length)
goto out;
}
/* Fill the remainder of the previous last page with zeros */
- rc = write_zeros(file, index, (old_end_pos_in_page + 1),
+ rc = ecryptfs_write_zeros(file, index, (old_end_pos_in_page + 1),
((PAGE_CACHE_SIZE - 1) - old_end_pos_in_page));
if (rc) {
- ecryptfs_printk(KERN_ERR, "write_zeros(file=[%p], "
+ ecryptfs_printk(KERN_ERR, "ecryptfs_write_zeros(file=[%p], "
"index=[0x%.16x], old_end_pos_in_page=[d], "
"(PAGE_CACHE_SIZE - old_end_pos_in_page)=[d]) "
"returned [%d]\n", file, index,
@@ -131,9 +131,10 @@ int ecryptfs_fill_zeros(struct file *file, loff_t new_length)
index++;
while (index < new_end_page_index) {
/* Fill all intermediate pages with zeros */
- rc = write_zeros(file, index, 0, PAGE_CACHE_SIZE);
+ rc = ecryptfs_write_zeros(file, index, 0, PAGE_CACHE_SIZE);
if (rc) {
- ecryptfs_printk(KERN_ERR, "write_zeros(file=[%p], "
+ ecryptfs_printk(KERN_ERR, "ecryptfs_write_zeros("
+ "file=[%p], "
"index=[0x%.16x], "
"old_end_pos_in_page=[d], "
"(PAGE_CACHE_SIZE - new_end_pos_in_page"
@@ -149,9 +150,9 @@ int ecryptfs_fill_zeros(struct file *file, loff_t new_length)
}
/* Fill the portion at the beginning of the last new page with
* zero's */
- rc = write_zeros(file, index, 0, (new_end_pos_in_page + 1));
+ rc = ecryptfs_write_zeros(file, index, 0, (new_end_pos_in_page + 1));
if (rc) {
- ecryptfs_printk(KERN_ERR, "write_zeros(file="
+ ecryptfs_printk(KERN_ERR, "ecryptfs_write_zeros(file="
"[%p], index=[0x%.16x], 0, "
"new_end_pos_in_page=[%d]"
"returned [%d]\n", file, index,
@@ -364,22 +365,39 @@ static int fill_zeros_to_end_of_page(struct page *page, unsigned int to)
{
struct inode *inode = page->mapping->host;
int end_byte_in_page;
- char *page_virt;
if ((i_size_read(inode) / PAGE_CACHE_SIZE) != page->index)
goto out;
end_byte_in_page = i_size_read(inode) % PAGE_CACHE_SIZE;
if (to > end_byte_in_page)
end_byte_in_page = to;
- page_virt = kmap_atomic(page, KM_USER0);
- memset((page_virt + end_byte_in_page), 0,
- (PAGE_CACHE_SIZE - end_byte_in_page));
- kunmap_atomic(page_virt, KM_USER0);
- flush_dcache_page(page);
+ zero_user_page(page, end_byte_in_page,
+ PAGE_CACHE_SIZE - end_byte_in_page, KM_USER0);
out:
return 0;
}
+/**
+ * eCryptfs does not currently support holes. When writing after a
+ * seek past the end of the file, eCryptfs fills in 0's through to the
+ * current location. The code to fill in the 0's to all the
+ * intermediate pages calls ecryptfs_prepare_write_no_truncate().
+ */
+static int
+ecryptfs_prepare_write_no_truncate(struct file *file, struct page *page,
+ unsigned from, unsigned to)
+{
+ int rc = 0;
+
+ if (from == 0 && to == PAGE_CACHE_SIZE)
+ goto out; /* If we are writing a full page, it will be
+ up to date. */
+ if (!PageUptodate(page))
+ rc = ecryptfs_do_readpage(file, page, page->index);
+out:
+ return rc;
+}
+
static int ecryptfs_prepare_write(struct file *file, struct page *page,
unsigned from, unsigned to)
{
@@ -390,6 +408,23 @@ static int ecryptfs_prepare_write(struct file *file, struct page *page,
up to date. */
if (!PageUptodate(page))
rc = ecryptfs_do_readpage(file, page, page->index);
+ if (page->index != 0) {
+ loff_t end_of_prev_pg_pos =
+ (((loff_t)page->index << PAGE_CACHE_SHIFT) - 1);
+
+ if (end_of_prev_pg_pos > i_size_read(page->mapping->host)) {
+ rc = ecryptfs_truncate(file->f_path.dentry,
+ end_of_prev_pg_pos);
+ if (rc) {
+ printk(KERN_ERR "Error on attempt to "
+ "truncate to (higher) offset [%lld];"
+ " rc = [%d]\n", end_of_prev_pg_pos, rc);
+ goto out;
+ }
+ }
+ if (end_of_prev_pg_pos + 1 > i_size_read(page->mapping->host))
+ zero_user_page(page, 0, PAGE_CACHE_SIZE, KM_USER0);
+ }
out:
return rc;
}
@@ -725,7 +760,7 @@ out:
}
/**
- * write_zeros
+ * ecryptfs_write_zeros
* @file: The ecryptfs file
* @index: The index in which we are writing
* @start: The position after the last block of data
@@ -735,12 +770,11 @@ out:
*
* (start + num_zeros) must be less than or equal to PAGE_CACHE_SIZE
*/
-static
-int write_zeros(struct file *file, pgoff_t index, int start, int num_zeros)
+int
+ecryptfs_write_zeros(struct file *file, pgoff_t index, int start, int num_zeros)
{
int rc = 0;
struct page *tmp_page;
- char *tmp_page_virt;
tmp_page = ecryptfs_get1page(file, index);
if (IS_ERR(tmp_page)) {
@@ -749,18 +783,15 @@ int write_zeros(struct file *file, pgoff_t index, int start, int num_zeros)
rc = PTR_ERR(tmp_page);
goto out;
}
- rc = ecryptfs_prepare_write(file, tmp_page, start, start + num_zeros);
- if (rc) {
+ if ((rc = ecryptfs_prepare_write_no_truncate(file, tmp_page, start,
+ (start + num_zeros)))) {
ecryptfs_printk(KERN_ERR, "Error preparing to write zero's "
- "to remainder of page at index [0x%.16x]\n",
+ "to page at index [0x%.16x]\n",
index);
page_cache_release(tmp_page);
goto out;
}
- tmp_page_virt = kmap_atomic(tmp_page, KM_USER0);
- memset(((char *)tmp_page_virt + start), 0, num_zeros);
- kunmap_atomic(tmp_page_virt, KM_USER0);
- flush_dcache_page(tmp_page);
+ zero_user_page(tmp_page, start, num_zeros, KM_USER0);
rc = ecryptfs_commit_write(file, tmp_page, start, start + num_zeros);
if (rc < 0) {
ecryptfs_printk(KERN_ERR, "Error attempting to write zero's "
diff --git a/fs/efs/super.c b/fs/efs/super.c
index ba7a8b9da0c..e0a6839e68a 100644
--- a/fs/efs/super.c
+++ b/fs/efs/super.c
@@ -72,8 +72,7 @@ static void init_once(void * foo, struct kmem_cache * cachep, unsigned long flag
{
struct efs_inode_info *ei = (struct efs_inode_info *) foo;
- if (flags & SLAB_CTOR_CONSTRUCTOR)
- inode_init_once(&ei->vfs_inode);
+ inode_init_once(&ei->vfs_inode);
}
static int init_inodecache(void)
diff --git a/fs/eventfd.c b/fs/eventfd.c
new file mode 100644
index 00000000000..2ce19c000d2
--- /dev/null
+++ b/fs/eventfd.c
@@ -0,0 +1,226 @@
+/*
+ * fs/eventfd.c
+ *
+ * Copyright (C) 2007 Davide Libenzi <davidel@xmailserver.org>
+ *
+ */
+
+#include <linux/file.h>
+#include <linux/poll.h>
+#include <linux/init.h>
+#include <linux/fs.h>
+#include <linux/sched.h>
+#include <linux/kernel.h>
+#include <linux/list.h>
+#include <linux/spinlock.h>
+#include <linux/anon_inodes.h>
+#include <linux/eventfd.h>
+
+struct eventfd_ctx {
+ wait_queue_head_t wqh;
+ /*
+ * Every time that a write(2) is performed on an eventfd, the
+ * value of the __u64 being written is added to "count" and a
+ * wakeup is performed on "wqh". A read(2) will return the "count"
+ * value to userspace, and will reset "count" to zero. The kernel
+ * size eventfd_signal() also, adds to the "count" counter and
+ * issue a wakeup.
+ */
+ __u64 count;
+};
+
+/*
+ * Adds "n" to the eventfd counter "count". Returns "n" in case of
+ * success, or a value lower then "n" in case of coutner overflow.
+ * This function is supposed to be called by the kernel in paths
+ * that do not allow sleeping. In this function we allow the counter
+ * to reach the ULLONG_MAX value, and we signal this as overflow
+ * condition by returining a POLLERR to poll(2).
+ */
+int eventfd_signal(struct file *file, int n)
+{
+ struct eventfd_ctx *ctx = file->private_data;
+ unsigned long flags;
+
+ if (n < 0)
+ return -EINVAL;
+ spin_lock_irqsave(&ctx->wqh.lock, flags);
+ if (ULLONG_MAX - ctx->count < n)
+ n = (int) (ULLONG_MAX - ctx->count);
+ ctx->count += n;
+ if (waitqueue_active(&ctx->wqh))
+ wake_up_locked(&ctx->wqh);
+ spin_unlock_irqrestore(&ctx->wqh.lock, flags);
+
+ return n;
+}
+
+static int eventfd_release(struct inode *inode, struct file *file)
+{
+ kfree(file->private_data);
+ return 0;
+}
+
+static unsigned int eventfd_poll(struct file *file, poll_table *wait)
+{
+ struct eventfd_ctx *ctx = file->private_data;
+ unsigned int events = 0;
+ unsigned long flags;
+
+ poll_wait(file, &ctx->wqh, wait);
+
+ spin_lock_irqsave(&ctx->wqh.lock, flags);
+ if (ctx->count > 0)
+ events |= POLLIN;
+ if (ctx->count == ULLONG_MAX)
+ events |= POLLERR;
+ if (ULLONG_MAX - 1 > ctx->count)
+ events |= POLLOUT;
+ spin_unlock_irqrestore(&ctx->wqh.lock, flags);
+
+ return events;
+}
+
+static ssize_t eventfd_read(struct file *file, char __user *buf, size_t count,
+ loff_t *ppos)
+{
+ struct eventfd_ctx *ctx = file->private_data;
+ ssize_t res;
+ __u64 ucnt;
+ DECLARE_WAITQUEUE(wait, current);
+
+ if (count < sizeof(ucnt))
+ return -EINVAL;
+ spin_lock_irq(&ctx->wqh.lock);
+ res = -EAGAIN;
+ ucnt = ctx->count;
+ if (ucnt > 0)
+ res = sizeof(ucnt);
+ else if (!(file->f_flags & O_NONBLOCK)) {
+ __add_wait_queue(&ctx->wqh, &wait);
+ for (res = 0;;) {
+ set_current_state(TASK_INTERRUPTIBLE);
+ if (ctx->count > 0) {
+ ucnt = ctx->count;
+ res = sizeof(ucnt);
+ break;
+ }
+ if (signal_pending(current)) {
+ res = -ERESTARTSYS;
+ break;
+ }
+ spin_unlock_irq(&ctx->wqh.lock);
+ schedule();
+ spin_lock_irq(&ctx->wqh.lock);
+ }
+ __remove_wait_queue(&ctx->wqh, &wait);
+ __set_current_state(TASK_RUNNING);
+ }
+ if (res > 0) {
+ ctx->count = 0;
+ if (waitqueue_active(&ctx->wqh))
+ wake_up_locked(&ctx->wqh);
+ }
+ spin_unlock_irq(&ctx->wqh.lock);
+ if (res > 0 && put_user(ucnt, (__u64 __user *) buf))
+ return -EFAULT;
+
+ return res;
+}
+
+static ssize_t eventfd_write(struct file *file, const char __user *buf, size_t count,
+ loff_t *ppos)
+{
+ struct eventfd_ctx *ctx = file->private_data;
+ ssize_t res;
+ __u64 ucnt;
+ DECLARE_WAITQUEUE(wait, current);
+
+ if (count < sizeof(ucnt))
+ return -EINVAL;
+ if (copy_from_user(&ucnt, buf, sizeof(ucnt)))
+ return -EFAULT;
+ if (ucnt == ULLONG_MAX)
+ return -EINVAL;
+ spin_lock_irq(&ctx->wqh.lock);
+ res = -EAGAIN;
+ if (ULLONG_MAX - ctx->count > ucnt)
+ res = sizeof(ucnt);
+ else if (!(file->f_flags & O_NONBLOCK)) {
+ __add_wait_queue(&ctx->wqh, &wait);
+ for (res = 0;;) {
+ set_current_state(TASK_INTERRUPTIBLE);
+ if (ULLONG_MAX - ctx->count > ucnt) {
+ res = sizeof(ucnt);
+ break;
+ }
+ if (signal_pending(current)) {
+ res = -ERESTARTSYS;
+ break;
+ }
+ spin_unlock_irq(&ctx->wqh.lock);
+ schedule();
+ spin_lock_irq(&ctx->wqh.lock);
+ }
+ __remove_wait_queue(&ctx->wqh, &wait);
+ __set_current_state(TASK_RUNNING);
+ }
+ if (res > 0) {
+ ctx->count += ucnt;
+ if (waitqueue_active(&ctx->wqh))
+ wake_up_locked(&ctx->wqh);
+ }
+ spin_unlock_irq(&ctx->wqh.lock);
+
+ return res;
+}
+
+static const struct file_operations eventfd_fops = {
+ .release = eventfd_release,
+ .poll = eventfd_poll,
+ .read = eventfd_read,
+ .write = eventfd_write,
+};
+
+struct file *eventfd_fget(int fd)
+{
+ struct file *file;
+
+ file = fget(fd);
+ if (!file)
+ return ERR_PTR(-EBADF);
+ if (file->f_op != &eventfd_fops) {
+ fput(file);
+ return ERR_PTR(-EINVAL);
+ }
+
+ return file;
+}
+
+asmlinkage long sys_eventfd(unsigned int count)
+{
+ int error, fd;
+ struct eventfd_ctx *ctx;
+ struct file *file;
+ struct inode *inode;
+
+ ctx = kmalloc(sizeof(*ctx), GFP_KERNEL);
+ if (!ctx)
+ return -ENOMEM;
+
+ init_waitqueue_head(&ctx->wqh);
+ ctx->count = count;
+
+ /*
+ * When we call this, the initialization must be complete, since
+ * anon_inode_getfd() will install the fd.
+ */
+ error = anon_inode_getfd(&fd, &inode, &file, "[eventfd]",
+ &eventfd_fops, ctx);
+ if (!error)
+ return fd;
+
+ kfree(ctx);
+ return error;
+}
+
diff --git a/fs/eventpoll.c b/fs/eventpoll.c
index 3ae644e7e86..0b73cd45a06 100644
--- a/fs/eventpoll.c
+++ b/fs/eventpoll.c
@@ -1,6 +1,6 @@
/*
- * fs/eventpoll.c ( Efficent event polling implementation )
- * Copyright (C) 2001,...,2006 Davide Libenzi
+ * fs/eventpoll.c (Efficent event polling implementation)
+ * Copyright (C) 2001,...,2007 Davide Libenzi
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
@@ -11,7 +11,6 @@
*
*/
-#include <linux/module.h>
#include <linux/init.h>
#include <linux/kernel.h>
#include <linux/sched.h>
@@ -22,34 +21,31 @@
#include <linux/mm.h>
#include <linux/slab.h>
#include <linux/poll.h>
-#include <linux/smp_lock.h>
#include <linux/string.h>
#include <linux/list.h>
#include <linux/hash.h>
#include <linux/spinlock.h>
#include <linux/syscalls.h>
-#include <linux/rwsem.h>
#include <linux/rbtree.h>
#include <linux/wait.h>
#include <linux/eventpoll.h>
#include <linux/mount.h>
#include <linux/bitops.h>
#include <linux/mutex.h>
+#include <linux/anon_inodes.h>
#include <asm/uaccess.h>
#include <asm/system.h>
#include <asm/io.h>
#include <asm/mman.h>
#include <asm/atomic.h>
-#include <asm/semaphore.h>
-
/*
* LOCKING:
* There are three level of locking required by epoll :
*
* 1) epmutex (mutex)
- * 2) ep->sem (rw_semaphore)
- * 3) ep->lock (rw_lock)
+ * 2) ep->mtx (mutex)
+ * 3) ep->lock (spinlock)
*
* The acquire order is the one listed above, from 1 to 3.
* We need a spinlock (ep->lock) because we manipulate objects
@@ -59,25 +55,22 @@
* a spinlock. During the event transfer loop (from kernel to
* user space) we could end up sleeping due a copy_to_user(), so
* we need a lock that will allow us to sleep. This lock is a
- * read-write semaphore (ep->sem). It is acquired on read during
- * the event transfer loop and in write during epoll_ctl(EPOLL_CTL_DEL)
- * and during eventpoll_release_file(). Then we also need a global
- * semaphore to serialize eventpoll_release_file() and ep_free().
- * This semaphore is acquired by ep_free() during the epoll file
+ * mutex (ep->mtx). It is acquired during the event transfer loop,
+ * during epoll_ctl(EPOLL_CTL_DEL) and during eventpoll_release_file().
+ * Then we also need a global mutex to serialize eventpoll_release_file()
+ * and ep_free().
+ * This mutex is acquired by ep_free() during the epoll file
* cleanup path and it is also acquired by eventpoll_release_file()
* if a file has been pushed inside an epoll set and it is then
* close()d without a previous call toepoll_ctl(EPOLL_CTL_DEL).
- * It is possible to drop the "ep->sem" and to use the global
- * semaphore "epmutex" (together with "ep->lock") to have it working,
- * but having "ep->sem" will make the interface more scalable.
+ * It is possible to drop the "ep->mtx" and to use the global
+ * mutex "epmutex" (together with "ep->lock") to have it working,
+ * but having "ep->mtx" will make the interface more scalable.
* Events that require holding "epmutex" are very rare, while for
- * normal operations the epoll private "ep->sem" will guarantee
- * a greater scalability.
+ * normal operations the epoll private "ep->mtx" will guarantee
+ * a better scalability.
*/
-
-#define EVENTPOLLFS_MAGIC 0x03111965 /* My birthday should work for this :) */
-
#define DEBUG_EPOLL 0
#if DEBUG_EPOLL > 0
@@ -107,6 +100,7 @@
#define EP_MAX_EVENTS (INT_MAX / sizeof(struct epoll_event))
+#define EP_UNACTIVE_PTR ((void *) -1L)
struct epoll_filefd {
struct file *file;
@@ -117,7 +111,7 @@ struct epoll_filefd {
* Node that is linked into the "wake_task_list" member of the "struct poll_safewake".
* It is used to keep track on all tasks that are currently inside the wake_up() code
* to 1) short-circuit the one coming from the same task and same wait queue head
- * ( loop ) 2) allow a maximum number of epoll descriptors inclusion nesting
+ * (loop) 2) allow a maximum number of epoll descriptors inclusion nesting
* 3) let go the ones coming from other tasks.
*/
struct wake_task_node {
@@ -136,21 +130,57 @@ struct poll_safewake {
};
/*
+ * Each file descriptor added to the eventpoll interface will
+ * have an entry of this type linked to the "rbr" RB tree.
+ */
+struct epitem {
+ /* RB tree node used to link this structure to the eventpoll RB tree */
+ struct rb_node rbn;
+
+ /* List header used to link this structure to the eventpoll ready list */
+ struct list_head rdllink;
+
+ /*
+ * Works together "struct eventpoll"->ovflist in keeping the
+ * single linked chain of items.
+ */
+ struct epitem *next;
+
+ /* The file descriptor information this item refers to */
+ struct epoll_filefd ffd;
+
+ /* Number of active wait queue attached to poll operations */
+ int nwait;
+
+ /* List containing poll wait queues */
+ struct list_head pwqlist;
+
+ /* The "container" of this item */
+ struct eventpoll *ep;
+
+ /* List header used to link this item to the "struct file" items list */
+ struct list_head fllink;
+
+ /* The structure that describe the interested events and the source fd */
+ struct epoll_event event;
+};
+
+/*
* This structure is stored inside the "private_data" member of the file
* structure and rapresent the main data sructure for the eventpoll
* interface.
*/
struct eventpoll {
/* Protect the this structure access */
- rwlock_t lock;
+ spinlock_t lock;
/*
- * This semaphore is used to ensure that files are not removed
- * while epoll is using them. This is read-held during the event
- * collection loop and it is write-held during the file cleanup
- * path, the epoll file exit code and the ctl operations.
+ * This mutex is used to ensure that files are not removed
+ * while epoll is using them. This is held during the event
+ * collection loop, the file cleanup path, the epoll file exit
+ * code and the ctl operations.
*/
- struct rw_semaphore sem;
+ struct mutex mtx;
/* Wait queue used by sys_epoll_wait() */
wait_queue_head_t wq;
@@ -161,8 +191,15 @@ struct eventpoll {
/* List of ready file descriptors */
struct list_head rdllist;
- /* RB-Tree root used to store monitored fd structs */
+ /* RB tree root used to store monitored fd structs */
struct rb_root rbr;
+
+ /*
+ * This is a single linked list that chains all the "struct epitem" that
+ * happened while transfering ready events to userspace w/out
+ * holding ->lock.
+ */
+ struct epitem *ovflist;
};
/* Wait structure used by the poll hooks */
@@ -183,99 +220,14 @@ struct eppoll_entry {
wait_queue_head_t *whead;
};
-/*
- * Each file descriptor added to the eventpoll interface will
- * have an entry of this type linked to the hash.
- */
-struct epitem {
- /* RB-Tree node used to link this structure to the eventpoll rb-tree */
- struct rb_node rbn;
-
- /* List header used to link this structure to the eventpoll ready list */
- struct list_head rdllink;
-
- /* The file descriptor information this item refers to */
- struct epoll_filefd ffd;
-
- /* Number of active wait queue attached to poll operations */
- int nwait;
-
- /* List containing poll wait queues */
- struct list_head pwqlist;
-
- /* The "container" of this item */
- struct eventpoll *ep;
-
- /* The structure that describe the interested events and the source fd */
- struct epoll_event event;
-
- /*
- * Used to keep track of the usage count of the structure. This avoids
- * that the structure will desappear from underneath our processing.
- */
- atomic_t usecnt;
-
- /* List header used to link this item to the "struct file" items list */
- struct list_head fllink;
-
- /* List header used to link the item to the transfer list */
- struct list_head txlink;
-
- /*
- * This is used during the collection/transfer of events to userspace
- * to pin items empty events set.
- */
- unsigned int revents;
-};
-
/* Wrapper struct used by poll queueing */
struct ep_pqueue {
poll_table pt;
struct epitem *epi;
};
-
-
-static void ep_poll_safewake_init(struct poll_safewake *psw);
-static void ep_poll_safewake(struct poll_safewake *psw, wait_queue_head_t *wq);
-static int ep_getfd(int *efd, struct inode **einode, struct file **efile,
- struct eventpoll *ep);
-static int ep_alloc(struct eventpoll **pep);
-static void ep_free(struct eventpoll *ep);
-static struct epitem *ep_find(struct eventpoll *ep, struct file *file, int fd);
-static void ep_use_epitem(struct epitem *epi);
-static void ep_release_epitem(struct epitem *epi);
-static void ep_ptable_queue_proc(struct file *file, wait_queue_head_t *whead,
- poll_table *pt);
-static void ep_rbtree_insert(struct eventpoll *ep, struct epitem *epi);
-static int ep_insert(struct eventpoll *ep, struct epoll_event *event,
- struct file *tfile, int fd);
-static int ep_modify(struct eventpoll *ep, struct epitem *epi,
- struct epoll_event *event);
-static void ep_unregister_pollwait(struct eventpoll *ep, struct epitem *epi);
-static int ep_unlink(struct eventpoll *ep, struct epitem *epi);
-static int ep_remove(struct eventpoll *ep, struct epitem *epi);
-static int ep_poll_callback(wait_queue_t *wait, unsigned mode, int sync, void *key);
-static int ep_eventpoll_close(struct inode *inode, struct file *file);
-static unsigned int ep_eventpoll_poll(struct file *file, poll_table *wait);
-static int ep_collect_ready_items(struct eventpoll *ep,
- struct list_head *txlist, int maxevents);
-static int ep_send_events(struct eventpoll *ep, struct list_head *txlist,
- struct epoll_event __user *events);
-static void ep_reinject_items(struct eventpoll *ep, struct list_head *txlist);
-static int ep_events_transfer(struct eventpoll *ep,
- struct epoll_event __user *events,
- int maxevents);
-static int ep_poll(struct eventpoll *ep, struct epoll_event __user *events,
- int maxevents, long timeout);
-static int eventpollfs_delete_dentry(struct dentry *dentry);
-static struct inode *ep_eventpoll_inode(void);
-static int eventpollfs_get_sb(struct file_system_type *fs_type,
- int flags, const char *dev_name,
- void *data, struct vfsmount *mnt);
-
/*
- * This semaphore is used to serialize ep_free() and eventpoll_release_file().
+ * This mutex is used to serialize ep_free() and eventpoll_release_file().
*/
static struct mutex epmutex;
@@ -288,39 +240,8 @@ static struct kmem_cache *epi_cache __read_mostly;
/* Slab cache used to allocate "struct eppoll_entry" */
static struct kmem_cache *pwq_cache __read_mostly;
-/* Virtual fs used to allocate inodes for eventpoll files */
-static struct vfsmount *eventpoll_mnt __read_mostly;
-
-/* File callbacks that implement the eventpoll file behaviour */
-static const struct file_operations eventpoll_fops = {
- .release = ep_eventpoll_close,
- .poll = ep_eventpoll_poll
-};
-
-/*
- * This is used to register the virtual file system from where
- * eventpoll inodes are allocated.
- */
-static struct file_system_type eventpoll_fs_type = {
- .name = "eventpollfs",
- .get_sb = eventpollfs_get_sb,
- .kill_sb = kill_anon_super,
-};
-
-/* Very basic directory entry operations for the eventpoll virtual file system */
-static struct dentry_operations eventpollfs_dentry_operations = {
- .d_delete = eventpollfs_delete_dentry,
-};
-
-
-/* Fast test to see if the file is an evenpoll file */
-static inline int is_file_epoll(struct file *f)
-{
- return f->f_op == &eventpoll_fops;
-}
-
-/* Setup the structure that is used as key for the rb-tree */
+/* Setup the structure that is used as key for the RB tree */
static inline void ep_set_ffd(struct epoll_filefd *ffd,
struct file *file, int fd)
{
@@ -328,7 +249,7 @@ static inline void ep_set_ffd(struct epoll_filefd *ffd,
ffd->fd = fd;
}
-/* Compare rb-tree keys */
+/* Compare RB tree keys */
static inline int ep_cmp_ffd(struct epoll_filefd *p1,
struct epoll_filefd *p2)
{
@@ -336,36 +257,25 @@ static inline int ep_cmp_ffd(struct epoll_filefd *p1,
(p1->file < p2->file ? -1 : p1->fd - p2->fd));
}
-/* Special initialization for the rb-tree node to detect linkage */
+/* Special initialization for the RB tree node to detect linkage */
static inline void ep_rb_initnode(struct rb_node *n)
{
rb_set_parent(n, n);
}
-/* Removes a node from the rb-tree and marks it for a fast is-linked check */
+/* Removes a node from the RB tree and marks it for a fast is-linked check */
static inline void ep_rb_erase(struct rb_node *n, struct rb_root *r)
{
rb_erase(n, r);
rb_set_parent(n, n);
}
-/* Fast check to verify that the item is linked to the main rb-tree */
+/* Fast check to verify that the item is linked to the main RB tree */
static inline int ep_rb_linked(struct rb_node *n)
{
return rb_parent(n) != n;
}
-/*
- * Remove the item from the list and perform its initialization.
- * This is useful for us because we can test if the item is linked
- * using "ep_is_linked(p)".
- */
-static inline void ep_list_del(struct list_head *p)
-{
- list_del(p);
- INIT_LIST_HEAD(p);
-}
-
/* Tells us if the item is currently linked */
static inline int ep_is_linked(struct list_head *p)
{
@@ -385,7 +295,7 @@ static inline struct epitem * ep_item_from_epqueue(poll_table *p)
}
/* Tells if the epoll_ctl(2) operation needs an event copy from userspace */
-static inline int ep_op_hash_event(int op)
+static inline int ep_op_has_event(int op)
{
return op != EPOLL_CTL_DEL;
}
@@ -398,7 +308,6 @@ static void ep_poll_safewake_init(struct poll_safewake *psw)
spin_lock_init(&psw->lock);
}
-
/*
* Perform a safe wake up of the poll wait list. The problem is that
* with the new callback'd wake up system, it is possible that the
@@ -453,378 +362,195 @@ static void ep_poll_safewake(struct poll_safewake *psw, wait_queue_head_t *wq)
spin_unlock_irqrestore(&psw->lock, flags);
}
-
/*
- * This is called from eventpoll_release() to unlink files from the eventpoll
- * interface. We need to have this facility to cleanup correctly files that are
- * closed without being removed from the eventpoll interface.
+ * This function unregister poll callbacks from the associated file descriptor.
+ * Since this must be called without holding "ep->lock" the atomic exchange trick
+ * will protect us from multiple unregister.
*/
-void eventpoll_release_file(struct file *file)
+static void ep_unregister_pollwait(struct eventpoll *ep, struct epitem *epi)
{
- struct list_head *lsthead = &file->f_ep_links;
- struct eventpoll *ep;
- struct epitem *epi;
+ int nwait;
+ struct list_head *lsthead = &epi->pwqlist;
+ struct eppoll_entry *pwq;
- /*
- * We don't want to get "file->f_ep_lock" because it is not
- * necessary. It is not necessary because we're in the "struct file"
- * cleanup path, and this means that noone is using this file anymore.
- * The only hit might come from ep_free() but by holding the semaphore
- * will correctly serialize the operation. We do need to acquire
- * "ep->sem" after "epmutex" because ep_remove() requires it when called
- * from anywhere but ep_free().
- */
- mutex_lock(&epmutex);
+ /* This is called without locks, so we need the atomic exchange */
+ nwait = xchg(&epi->nwait, 0);
- while (!list_empty(lsthead)) {
- epi = list_entry(lsthead->next, struct epitem, fllink);
+ if (nwait) {
+ while (!list_empty(lsthead)) {
+ pwq = list_first_entry(lsthead, struct eppoll_entry, llink);
- ep = epi->ep;
- ep_list_del(&epi->fllink);
- down_write(&ep->sem);
- ep_remove(ep, epi);
- up_write(&ep->sem);
+ list_del_init(&pwq->llink);
+ remove_wait_queue(pwq->whead, &pwq->wait);
+ kmem_cache_free(pwq_cache, pwq);
+ }
}
-
- mutex_unlock(&epmutex);
}
-
/*
- * It opens an eventpoll file descriptor by suggesting a storage of "size"
- * file descriptors. The size parameter is just an hint about how to size
- * data structures. It won't prevent the user to store more than "size"
- * file descriptors inside the epoll interface. It is the kernel part of
- * the userspace epoll_create(2).
+ * Removes a "struct epitem" from the eventpoll RB tree and deallocates
+ * all the associated resources. Must be called with "mtx" held.
*/
-asmlinkage long sys_epoll_create(int size)
+static int ep_remove(struct eventpoll *ep, struct epitem *epi)
{
- int error, fd = -1;
- struct eventpoll *ep;
- struct inode *inode;
- struct file *file;
-
- DNPRINTK(3, (KERN_INFO "[%p] eventpoll: sys_epoll_create(%d)\n",
- current, size));
+ unsigned long flags;
+ struct file *file = epi->ffd.file;
/*
- * Sanity check on the size parameter, and create the internal data
- * structure ( "struct eventpoll" ).
+ * Removes poll wait queue hooks. We _have_ to do this without holding
+ * the "ep->lock" otherwise a deadlock might occur. This because of the
+ * sequence of the lock acquisition. Here we do "ep->lock" then the wait
+ * queue head lock when unregistering the wait queue. The wakeup callback
+ * will run by holding the wait queue head lock and will call our callback
+ * that will try to get "ep->lock".
*/
- error = -EINVAL;
- if (size <= 0 || (error = ep_alloc(&ep)) != 0)
- goto eexit_1;
+ ep_unregister_pollwait(ep, epi);
- /*
- * Creates all the items needed to setup an eventpoll file. That is,
- * a file structure, and inode and a free file descriptor.
- */
- error = ep_getfd(&fd, &inode, &file, ep);
- if (error)
- goto eexit_2;
+ /* Remove the current item from the list of epoll hooks */
+ spin_lock(&file->f_ep_lock);
+ if (ep_is_linked(&epi->fllink))
+ list_del_init(&epi->fllink);
+ spin_unlock(&file->f_ep_lock);
- DNPRINTK(3, (KERN_INFO "[%p] eventpoll: sys_epoll_create(%d) = %d\n",
- current, size, fd));
+ if (ep_rb_linked(&epi->rbn))
+ ep_rb_erase(&epi->rbn, &ep->rbr);
- return fd;
+ spin_lock_irqsave(&ep->lock, flags);
+ if (ep_is_linked(&epi->rdllink))
+ list_del_init(&epi->rdllink);
+ spin_unlock_irqrestore(&ep->lock, flags);
-eexit_2:
- ep_free(ep);
- kfree(ep);
-eexit_1:
- DNPRINTK(3, (KERN_INFO "[%p] eventpoll: sys_epoll_create(%d) = %d\n",
- current, size, error));
- return error;
-}
+ /* At this point it is safe to free the eventpoll item */
+ kmem_cache_free(epi_cache, epi);
+ DNPRINTK(3, (KERN_INFO "[%p] eventpoll: ep_remove(%p, %p)\n",
+ current, ep, file));
-/*
- * The following function implements the controller interface for
- * the eventpoll file that enables the insertion/removal/change of
- * file descriptors inside the interest set. It represents
- * the kernel part of the user space epoll_ctl(2).
- */
-asmlinkage long
-sys_epoll_ctl(int epfd, int op, int fd, struct epoll_event __user *event)
+ return 0;
+}
+
+static void ep_free(struct eventpoll *ep)
{
- int error;
- struct file *file, *tfile;
- struct eventpoll *ep;
+ struct rb_node *rbp;
struct epitem *epi;
- struct epoll_event epds;
- DNPRINTK(3, (KERN_INFO "[%p] eventpoll: sys_epoll_ctl(%d, %d, %d, %p)\n",
- current, epfd, op, fd, event));
-
- error = -EFAULT;
- if (ep_op_hash_event(op) &&
- copy_from_user(&epds, event, sizeof(struct epoll_event)))
- goto eexit_1;
-
- /* Get the "struct file *" for the eventpoll file */
- error = -EBADF;
- file = fget(epfd);
- if (!file)
- goto eexit_1;
-
- /* Get the "struct file *" for the target file */
- tfile = fget(fd);
- if (!tfile)
- goto eexit_2;
-
- /* The target file descriptor must support poll */
- error = -EPERM;
- if (!tfile->f_op || !tfile->f_op->poll)
- goto eexit_3;
+ /* We need to release all tasks waiting for these file */
+ if (waitqueue_active(&ep->poll_wait))
+ ep_poll_safewake(&psw, &ep->poll_wait);
/*
- * We have to check that the file structure underneath the file descriptor
- * the user passed to us _is_ an eventpoll file. And also we do not permit
- * adding an epoll file descriptor inside itself.
+ * We need to lock this because we could be hit by
+ * eventpoll_release_file() while we're freeing the "struct eventpoll".
+ * We do not need to hold "ep->mtx" here because the epoll file
+ * is on the way to be removed and no one has references to it
+ * anymore. The only hit might come from eventpoll_release_file() but
+ * holding "epmutex" is sufficent here.
*/
- error = -EINVAL;
- if (file == tfile || !is_file_epoll(file))
- goto eexit_3;
+ mutex_lock(&epmutex);
/*
- * At this point it is safe to assume that the "private_data" contains
- * our own data structure.
+ * Walks through the whole tree by unregistering poll callbacks.
*/
- ep = file->private_data;
-
- down_write(&ep->sem);
-
- /* Try to lookup the file inside our hash table */
- epi = ep_find(ep, tfile, fd);
-
- error = -EINVAL;
- switch (op) {
- case EPOLL_CTL_ADD:
- if (!epi) {
- epds.events |= POLLERR | POLLHUP;
+ for (rbp = rb_first(&ep->rbr); rbp; rbp = rb_next(rbp)) {
+ epi = rb_entry(rbp, struct epitem, rbn);
- error = ep_insert(ep, &epds, tfile, fd);
- } else
- error = -EEXIST;
- break;
- case EPOLL_CTL_DEL:
- if (epi)
- error = ep_remove(ep, epi);
- else
- error = -ENOENT;
- break;
- case EPOLL_CTL_MOD:
- if (epi) {
- epds.events |= POLLERR | POLLHUP;
- error = ep_modify(ep, epi, &epds);
- } else
- error = -ENOENT;
- break;
+ ep_unregister_pollwait(ep, epi);
}
/*
- * The function ep_find() increments the usage count of the structure
- * so, if this is not NULL, we need to release it.
+ * Walks through the whole tree by freeing each "struct epitem". At this
+ * point we are sure no poll callbacks will be lingering around, and also by
+ * holding "epmutex" we can be sure that no file cleanup code will hit
+ * us during this operation. So we can avoid the lock on "ep->lock".
*/
- if (epi)
- ep_release_epitem(epi);
-
- up_write(&ep->sem);
-
-eexit_3:
- fput(tfile);
-eexit_2:
- fput(file);
-eexit_1:
- DNPRINTK(3, (KERN_INFO "[%p] eventpoll: sys_epoll_ctl(%d, %d, %d, %p) = %d\n",
- current, epfd, op, fd, event, error));
+ while ((rbp = rb_first(&ep->rbr)) != 0) {
+ epi = rb_entry(rbp, struct epitem, rbn);
+ ep_remove(ep, epi);
+ }
- return error;
+ mutex_unlock(&epmutex);
+ mutex_destroy(&ep->mtx);
+ kfree(ep);
}
-
-/*
- * Implement the event wait interface for the eventpoll file. It is the kernel
- * part of the user space epoll_wait(2).
- */
-asmlinkage long sys_epoll_wait(int epfd, struct epoll_event __user *events,
- int maxevents, int timeout)
+static int ep_eventpoll_release(struct inode *inode, struct file *file)
{
- int error;
- struct file *file;
- struct eventpoll *ep;
-
- DNPRINTK(3, (KERN_INFO "[%p] eventpoll: sys_epoll_wait(%d, %p, %d, %d)\n",
- current, epfd, events, maxevents, timeout));
-
- /* The maximum number of event must be greater than zero */
- if (maxevents <= 0 || maxevents > EP_MAX_EVENTS)
- return -EINVAL;
-
- /* Verify that the area passed by the user is writeable */
- if (!access_ok(VERIFY_WRITE, events, maxevents * sizeof(struct epoll_event))) {
- error = -EFAULT;
- goto eexit_1;
- }
+ struct eventpoll *ep = file->private_data;
- /* Get the "struct file *" for the eventpoll file */
- error = -EBADF;
- file = fget(epfd);
- if (!file)
- goto eexit_1;
+ if (ep)
+ ep_free(ep);
- /*
- * We have to check that the file structure underneath the fd
- * the user passed to us _is_ an eventpoll file.
- */
- error = -EINVAL;
- if (!is_file_epoll(file))
- goto eexit_2;
+ DNPRINTK(3, (KERN_INFO "[%p] eventpoll: close() ep=%p\n", current, ep));
+ return 0;
+}
- /*
- * At this point it is safe to assume that the "private_data" contains
- * our own data structure.
- */
- ep = file->private_data;
+static unsigned int ep_eventpoll_poll(struct file *file, poll_table *wait)
+{
+ unsigned int pollflags = 0;
+ unsigned long flags;
+ struct eventpoll *ep = file->private_data;
- /* Time to fish for events ... */
- error = ep_poll(ep, events, maxevents, timeout);
+ /* Insert inside our poll wait queue */
+ poll_wait(file, &ep->poll_wait, wait);
-eexit_2:
- fput(file);
-eexit_1:
- DNPRINTK(3, (KERN_INFO "[%p] eventpoll: sys_epoll_wait(%d, %p, %d, %d) = %d\n",
- current, epfd, events, maxevents, timeout, error));
+ /* Check our condition */
+ spin_lock_irqsave(&ep->lock, flags);
+ if (!list_empty(&ep->rdllist))
+ pollflags = POLLIN | POLLRDNORM;
+ spin_unlock_irqrestore(&ep->lock, flags);
- return error;
+ return pollflags;
}
+/* File callbacks that implement the eventpoll file behaviour */
+static const struct file_operations eventpoll_fops = {
+ .release = ep_eventpoll_release,
+ .poll = ep_eventpoll_poll
+};
-#ifdef TIF_RESTORE_SIGMASK
+/* Fast test to see if the file is an evenpoll file */
+static inline int is_file_epoll(struct file *f)
+{
+ return f->f_op == &eventpoll_fops;
+}
/*
- * Implement the event wait interface for the eventpoll file. It is the kernel
- * part of the user space epoll_pwait(2).
+ * This is called from eventpoll_release() to unlink files from the eventpoll
+ * interface. We need to have this facility to cleanup correctly files that are
+ * closed without being removed from the eventpoll interface.
*/
-asmlinkage long sys_epoll_pwait(int epfd, struct epoll_event __user *events,
- int maxevents, int timeout, const sigset_t __user *sigmask,
- size_t sigsetsize)
+void eventpoll_release_file(struct file *file)
{
- int error;
- sigset_t ksigmask, sigsaved;
-
- /*
- * If the caller wants a certain signal mask to be set during the wait,
- * we apply it here.
- */
- if (sigmask) {
- if (sigsetsize != sizeof(sigset_t))
- return -EINVAL;
- if (copy_from_user(&ksigmask, sigmask, sizeof(ksigmask)))
- return -EFAULT;
- sigdelsetmask(&ksigmask, sigmask(SIGKILL) | sigmask(SIGSTOP));
- sigprocmask(SIG_SETMASK, &ksigmask, &sigsaved);
- }
-
- error = sys_epoll_wait(epfd, events, maxevents, timeout);
+ struct list_head *lsthead = &file->f_ep_links;
+ struct eventpoll *ep;
+ struct epitem *epi;
/*
- * If we changed the signal mask, we need to restore the original one.
- * In case we've got a signal while waiting, we do not restore the
- * signal mask yet, and we allow do_signal() to deliver the signal on
- * the way back to userspace, before the signal mask is restored.
+ * We don't want to get "file->f_ep_lock" because it is not
+ * necessary. It is not necessary because we're in the "struct file"
+ * cleanup path, and this means that noone is using this file anymore.
+ * So, for example, epoll_ctl() cannot hit here sicne if we reach this
+ * point, the file counter already went to zero and fget() would fail.
+ * The only hit might come from ep_free() but by holding the mutex
+ * will correctly serialize the operation. We do need to acquire
+ * "ep->mtx" after "epmutex" because ep_remove() requires it when called
+ * from anywhere but ep_free().
*/
- if (sigmask) {
- if (error == -EINTR) {
- memcpy(&current->saved_sigmask, &sigsaved,
- sizeof(sigsaved));
- set_thread_flag(TIF_RESTORE_SIGMASK);
- } else
- sigprocmask(SIG_SETMASK, &sigsaved, NULL);
- }
-
- return error;
-}
-
-#endif /* #ifdef TIF_RESTORE_SIGMASK */
-
-
-/*
- * Creates the file descriptor to be used by the epoll interface.
- */
-static int ep_getfd(int *efd, struct inode **einode, struct file **efile,
- struct eventpoll *ep)
-{
- struct qstr this;
- char name[32];
- struct dentry *dentry;
- struct inode *inode;
- struct file *file;
- int error, fd;
+ mutex_lock(&epmutex);
- /* Get an ready to use file */
- error = -ENFILE;
- file = get_empty_filp();
- if (!file)
- goto eexit_1;
+ while (!list_empty(lsthead)) {
+ epi = list_first_entry(lsthead, struct epitem, fllink);
- /* Allocates an inode from the eventpoll file system */
- inode = ep_eventpoll_inode();
- if (IS_ERR(inode)) {
- error = PTR_ERR(inode);
- goto eexit_2;
+ ep = epi->ep;
+ list_del_init(&epi->fllink);
+ mutex_lock(&ep->mtx);
+ ep_remove(ep, epi);
+ mutex_unlock(&ep->mtx);
}
- /* Allocates a free descriptor to plug the file onto */
- error = get_unused_fd();
- if (error < 0)
- goto eexit_3;
- fd = error;
-
- /*
- * Link the inode to a directory entry by creating a unique name
- * using the inode number.
- */
- error = -ENOMEM;
- sprintf(name, "[%lu]", inode->i_ino);
- this.name = name;
- this.len = strlen(name);
- this.hash = inode->i_ino;
- dentry = d_alloc(eventpoll_mnt->mnt_sb->s_root, &this);
- if (!dentry)
- goto eexit_4;
- dentry->d_op = &eventpollfs_dentry_operations;
- d_add(dentry, inode);
- file->f_path.mnt = mntget(eventpoll_mnt);
- file->f_path.dentry = dentry;
- file->f_mapping = inode->i_mapping;
-
- file->f_pos = 0;
- file->f_flags = O_RDONLY;
- file->f_op = &eventpoll_fops;
- file->f_mode = FMODE_READ;
- file->f_version = 0;
- file->private_data = ep;
-
- /* Install the new setup file into the allocated fd. */
- fd_install(fd, file);
-
- *efd = fd;
- *einode = inode;
- *efile = file;
- return 0;
-
-eexit_4:
- put_unused_fd(fd);
-eexit_3:
- iput(inode);
-eexit_2:
- put_filp(file);
-eexit_1:
- return error;
+ mutex_unlock(&epmutex);
}
-
static int ep_alloc(struct eventpoll **pep)
{
struct eventpoll *ep = kzalloc(sizeof(*ep), GFP_KERNEL);
@@ -832,12 +558,13 @@ static int ep_alloc(struct eventpoll **pep)
if (!ep)
return -ENOMEM;
- rwlock_init(&ep->lock);
- init_rwsem(&ep->sem);
+ spin_lock_init(&ep->lock);
+ mutex_init(&ep->mtx);
init_waitqueue_head(&ep->wq);
init_waitqueue_head(&ep->poll_wait);
INIT_LIST_HEAD(&ep->rdllist);
ep->rbr = RB_ROOT;
+ ep->ovflist = EP_UNACTIVE_PTR;
*pep = ep;
@@ -846,65 +573,19 @@ static int ep_alloc(struct eventpoll **pep)
return 0;
}
-
-static void ep_free(struct eventpoll *ep)
-{
- struct rb_node *rbp;
- struct epitem *epi;
-
- /* We need to release all tasks waiting for these file */
- if (waitqueue_active(&ep->poll_wait))
- ep_poll_safewake(&psw, &ep->poll_wait);
-
- /*
- * We need to lock this because we could be hit by
- * eventpoll_release_file() while we're freeing the "struct eventpoll".
- * We do not need to hold "ep->sem" here because the epoll file
- * is on the way to be removed and no one has references to it
- * anymore. The only hit might come from eventpoll_release_file() but
- * holding "epmutex" is sufficent here.
- */
- mutex_lock(&epmutex);
-
- /*
- * Walks through the whole tree by unregistering poll callbacks.
- */
- for (rbp = rb_first(&ep->rbr); rbp; rbp = rb_next(rbp)) {
- epi = rb_entry(rbp, struct epitem, rbn);
-
- ep_unregister_pollwait(ep, epi);
- }
-
- /*
- * Walks through the whole hash by freeing each "struct epitem". At this
- * point we are sure no poll callbacks will be lingering around, and also by
- * write-holding "sem" we can be sure that no file cleanup code will hit
- * us during this operation. So we can avoid the lock on "ep->lock".
- */
- while ((rbp = rb_first(&ep->rbr)) != 0) {
- epi = rb_entry(rbp, struct epitem, rbn);
- ep_remove(ep, epi);
- }
-
- mutex_unlock(&epmutex);
-}
-
-
/*
- * Search the file inside the eventpoll hash. It add usage count to
- * the returned item, so the caller must call ep_release_epitem()
- * after finished using the "struct epitem".
+ * Search the file inside the eventpoll tree. The RB tree operations
+ * are protected by the "mtx" mutex, and ep_find() must be called with
+ * "mtx" held.
*/
static struct epitem *ep_find(struct eventpoll *ep, struct file *file, int fd)
{
int kcmp;
- unsigned long flags;
struct rb_node *rbp;
struct epitem *epi, *epir = NULL;
struct epoll_filefd ffd;
ep_set_ffd(&ffd, file, fd);
- read_lock_irqsave(&ep->lock, flags);
for (rbp = ep->rbr.rb_node; rbp; ) {
epi = rb_entry(rbp, struct epitem, rbn);
kcmp = ep_cmp_ffd(&ffd, &epi->ffd);
@@ -913,12 +594,10 @@ static struct epitem *ep_find(struct eventpoll *ep, struct file *file, int fd)
else if (kcmp < 0)
rbp = rbp->rb_left;
else {
- ep_use_epitem(epi);
epir = epi;
break;
}
}
- read_unlock_irqrestore(&ep->lock, flags);
DNPRINTK(3, (KERN_INFO "[%p] eventpoll: ep_find(%p) -> %p\n",
current, file, epir));
@@ -926,30 +605,72 @@ static struct epitem *ep_find(struct eventpoll *ep, struct file *file, int fd)
return epir;
}
-
/*
- * Increment the usage count of the "struct epitem" making it sure
- * that the user will have a valid pointer to reference.
+ * This is the callback that is passed to the wait queue wakeup
+ * machanism. It is called by the stored file descriptors when they
+ * have events to report.
*/
-static void ep_use_epitem(struct epitem *epi)
+static int ep_poll_callback(wait_queue_t *wait, unsigned mode, int sync, void *key)
{
+ int pwake = 0;
+ unsigned long flags;
+ struct epitem *epi = ep_item_from_wait(wait);
+ struct eventpoll *ep = epi->ep;
- atomic_inc(&epi->usecnt);
-}
+ DNPRINTK(3, (KERN_INFO "[%p] eventpoll: poll_callback(%p) epi=%p ep=%p\n",
+ current, epi->ffd.file, epi, ep));
+ spin_lock_irqsave(&ep->lock, flags);
-/*
- * Decrement ( release ) the usage count by signaling that the user
- * has finished using the structure. It might lead to freeing the
- * structure itself if the count goes to zero.
- */
-static void ep_release_epitem(struct epitem *epi)
-{
+ /*
+ * If the event mask does not contain any poll(2) event, we consider the
+ * descriptor to be disabled. This condition is likely the effect of the
+ * EPOLLONESHOT bit that disables the descriptor when an event is received,
+ * until the next EPOLL_CTL_MOD will be issued.
+ */
+ if (!(epi->event.events & ~EP_PRIVATE_BITS))
+ goto out_unlock;
- if (atomic_dec_and_test(&epi->usecnt))
- kmem_cache_free(epi_cache, epi);
-}
+ /*
+ * If we are trasfering events to userspace, we can hold no locks
+ * (because we're accessing user memory, and because of linux f_op->poll()
+ * semantics). All the events that happens during that period of time are
+ * chained in ep->ovflist and requeued later on.
+ */
+ if (unlikely(ep->ovflist != EP_UNACTIVE_PTR)) {
+ if (epi->next == EP_UNACTIVE_PTR) {
+ epi->next = ep->ovflist;
+ ep->ovflist = epi;
+ }
+ goto out_unlock;
+ }
+ /* If this file is already in the ready list we exit soon */
+ if (ep_is_linked(&epi->rdllink))
+ goto is_linked;
+
+ list_add_tail(&epi->rdllink, &ep->rdllist);
+
+is_linked:
+ /*
+ * Wake up ( if active ) both the eventpoll wait list and the ->poll()
+ * wait list.
+ */
+ if (waitqueue_active(&ep->wq))
+ __wake_up_locked(&ep->wq, TASK_UNINTERRUPTIBLE |
+ TASK_INTERRUPTIBLE);
+ if (waitqueue_active(&ep->poll_wait))
+ pwake++;
+
+out_unlock:
+ spin_unlock_irqrestore(&ep->lock, flags);
+
+ /* We have to call this outside the lock */
+ if (pwake)
+ ep_poll_safewake(&psw, &ep->poll_wait);
+
+ return 1;
+}
/*
* This is the callback that is used to add our wait queue to the
@@ -974,7 +695,6 @@ static void ep_ptable_queue_proc(struct file *file, wait_queue_head_t *whead,
}
}
-
static void ep_rbtree_insert(struct eventpoll *ep, struct epitem *epi)
{
int kcmp;
@@ -994,7 +714,9 @@ static void ep_rbtree_insert(struct eventpoll *ep, struct epitem *epi)
rb_insert_color(&epi->rbn, &ep->rbr);
}
-
+/*
+ * Must be called with "mtx" held.
+ */
static int ep_insert(struct eventpoll *ep, struct epoll_event *event,
struct file *tfile, int fd)
{
@@ -1005,19 +727,18 @@ static int ep_insert(struct eventpoll *ep, struct epoll_event *event,
error = -ENOMEM;
if (!(epi = kmem_cache_alloc(epi_cache, GFP_KERNEL)))
- goto eexit_1;
+ goto error_return;
/* Item initialization follow here ... */
ep_rb_initnode(&epi->rbn);
INIT_LIST_HEAD(&epi->rdllink);
INIT_LIST_HEAD(&epi->fllink);
- INIT_LIST_HEAD(&epi->txlink);
INIT_LIST_HEAD(&epi->pwqlist);
epi->ep = ep;
ep_set_ffd(&epi->ffd, tfile, fd);
epi->event = *event;
- atomic_set(&epi->usecnt, 1);
epi->nwait = 0;
+ epi->next = EP_UNACTIVE_PTR;
/* Initialize the poll table using the queue callback */
epq.epi = epi;
@@ -1026,7 +747,9 @@ static int ep_insert(struct eventpoll *ep, struct epoll_event *event,
/*
* Attach the item to the poll hooks and get current event bits.
* We can safely use the file* here because its usage count has
- * been increased by the caller of this function.
+ * been increased by the caller of this function. Note that after
+ * this operation completes, the poll callback can start hitting
+ * the new item.
*/
revents = tfile->f_op->poll(tfile, &epq.pt);
@@ -1036,19 +759,22 @@ static int ep_insert(struct eventpoll *ep, struct epoll_event *event,
* high memory pressure.
*/
if (epi->nwait < 0)
- goto eexit_2;
+ goto error_unregister;
/* Add the current item to the list of active epoll hook for this file */
spin_lock(&tfile->f_ep_lock);
list_add_tail(&epi->fllink, &tfile->f_ep_links);
spin_unlock(&tfile->f_ep_lock);
- /* We have to drop the new item inside our item list to keep track of it */
- write_lock_irqsave(&ep->lock, flags);
-
- /* Add the current item to the rb-tree */
+ /*
+ * Add the current item to the RB tree. All RB tree operations are
+ * protected by "mtx", and ep_insert() is called with "mtx" held.
+ */
ep_rbtree_insert(ep, epi);
+ /* We have to drop the new item inside our item list to keep track of it */
+ spin_lock_irqsave(&ep->lock, flags);
+
/* If the file is already "ready" we drop it inside the ready list */
if ((revents & event->events) && !ep_is_linked(&epi->rdllink)) {
list_add_tail(&epi->rdllink, &ep->rdllist);
@@ -1060,7 +786,7 @@ static int ep_insert(struct eventpoll *ep, struct epoll_event *event,
pwake++;
}
- write_unlock_irqrestore(&ep->lock, flags);
+ spin_unlock_irqrestore(&ep->lock, flags);
/* We have to call this outside the lock */
if (pwake)
@@ -1071,27 +797,28 @@ static int ep_insert(struct eventpoll *ep, struct epoll_event *event,
return 0;
-eexit_2:
+error_unregister:
ep_unregister_pollwait(ep, epi);
/*
* We need to do this because an event could have been arrived on some
- * allocated wait queue.
+ * allocated wait queue. Note that we don't care about the ep->ovflist
+ * list, since that is used/cleaned only inside a section bound by "mtx".
+ * And ep_insert() is called with "mtx" held.
*/
- write_lock_irqsave(&ep->lock, flags);
+ spin_lock_irqsave(&ep->lock, flags);
if (ep_is_linked(&epi->rdllink))
- ep_list_del(&epi->rdllink);
- write_unlock_irqrestore(&ep->lock, flags);
+ list_del_init(&epi->rdllink);
+ spin_unlock_irqrestore(&ep->lock, flags);
kmem_cache_free(epi_cache, epi);
-eexit_1:
+error_return:
return error;
}
-
/*
* Modify the interest event mask by dropping an event if the new mask
- * has a match in the current file status.
+ * has a match in the current file status. Must be called with "mtx" held.
*/
static int ep_modify(struct eventpoll *ep, struct epitem *epi, struct epoll_event *event)
{
@@ -1113,36 +840,28 @@ static int ep_modify(struct eventpoll *ep, struct epitem *epi, struct epoll_even
*/
revents = epi->ffd.file->f_op->poll(epi->ffd.file, NULL);
- write_lock_irqsave(&ep->lock, flags);
+ spin_lock_irqsave(&ep->lock, flags);
/* Copy the data member from inside the lock */
epi->event.data = event->data;
/*
- * If the item is not linked to the hash it means that it's on its
- * way toward the removal. Do nothing in this case.
+ * If the item is "hot" and it is not registered inside the ready
+ * list, push it inside.
*/
- if (ep_rb_linked(&epi->rbn)) {
- /*
- * If the item is "hot" and it is not registered inside the ready
- * list, push it inside. If the item is not "hot" and it is currently
- * registered inside the ready list, unlink it.
- */
- if (revents & event->events) {
- if (!ep_is_linked(&epi->rdllink)) {
- list_add_tail(&epi->rdllink, &ep->rdllist);
-
- /* Notify waiting tasks that events are available */
- if (waitqueue_active(&ep->wq))
- __wake_up_locked(&ep->wq, TASK_UNINTERRUPTIBLE |
- TASK_INTERRUPTIBLE);
- if (waitqueue_active(&ep->poll_wait))
- pwake++;
- }
+ if (revents & event->events) {
+ if (!ep_is_linked(&epi->rdllink)) {
+ list_add_tail(&epi->rdllink, &ep->rdllist);
+
+ /* Notify waiting tasks that events are available */
+ if (waitqueue_active(&ep->wq))
+ __wake_up_locked(&ep->wq, TASK_UNINTERRUPTIBLE |
+ TASK_INTERRUPTIBLE);
+ if (waitqueue_active(&ep->poll_wait))
+ pwake++;
}
}
-
- write_unlock_irqrestore(&ep->lock, flags);
+ spin_unlock_irqrestore(&ep->lock, flags);
/* We have to call this outside the lock */
if (pwake)
@@ -1151,350 +870,113 @@ static int ep_modify(struct eventpoll *ep, struct epitem *epi, struct epoll_even
return 0;
}
-
-/*
- * This function unregister poll callbacks from the associated file descriptor.
- * Since this must be called without holding "ep->lock" the atomic exchange trick
- * will protect us from multiple unregister.
- */
-static void ep_unregister_pollwait(struct eventpoll *ep, struct epitem *epi)
-{
- int nwait;
- struct list_head *lsthead = &epi->pwqlist;
- struct eppoll_entry *pwq;
-
- /* This is called without locks, so we need the atomic exchange */
- nwait = xchg(&epi->nwait, 0);
-
- if (nwait) {
- while (!list_empty(lsthead)) {
- pwq = list_entry(lsthead->next, struct eppoll_entry, llink);
-
- ep_list_del(&pwq->llink);
- remove_wait_queue(pwq->whead, &pwq->wait);
- kmem_cache_free(pwq_cache, pwq);
- }
- }
-}
-
-
-/*
- * Unlink the "struct epitem" from all places it might have been hooked up.
- * This function must be called with write IRQ lock on "ep->lock".
- */
-static int ep_unlink(struct eventpoll *ep, struct epitem *epi)
+static int ep_send_events(struct eventpoll *ep, struct epoll_event __user *events,
+ int maxevents)
{
- int error;
-
- /*
- * It can happen that this one is called for an item already unlinked.
- * The check protect us from doing a double unlink ( crash ).
- */
- error = -ENOENT;
- if (!ep_rb_linked(&epi->rbn))
- goto eexit_1;
-
- /*
- * Clear the event mask for the unlinked item. This will avoid item
- * notifications to be sent after the unlink operation from inside
- * the kernel->userspace event transfer loop.
- */
- epi->event.events = 0;
-
- /*
- * At this point is safe to do the job, unlink the item from our rb-tree.
- * This operation togheter with the above check closes the door to
- * double unlinks.
- */
- ep_rb_erase(&epi->rbn, &ep->rbr);
-
- /*
- * If the item we are going to remove is inside the ready file descriptors
- * we want to remove it from this list to avoid stale events.
- */
- if (ep_is_linked(&epi->rdllink))
- ep_list_del(&epi->rdllink);
-
- error = 0;
-eexit_1:
-
- DNPRINTK(3, (KERN_INFO "[%p] eventpoll: ep_unlink(%p, %p) = %d\n",
- current, ep, epi->ffd.file, error));
-
- return error;
-}
-
-
-/*
- * Removes a "struct epitem" from the eventpoll hash and deallocates
- * all the associated resources.
- */
-static int ep_remove(struct eventpoll *ep, struct epitem *epi)
-{
- int error;
- unsigned long flags;
- struct file *file = epi->ffd.file;
-
- /*
- * Removes poll wait queue hooks. We _have_ to do this without holding
- * the "ep->lock" otherwise a deadlock might occur. This because of the
- * sequence of the lock acquisition. Here we do "ep->lock" then the wait
- * queue head lock when unregistering the wait queue. The wakeup callback
- * will run by holding the wait queue head lock and will call our callback
- * that will try to get "ep->lock".
- */
- ep_unregister_pollwait(ep, epi);
-
- /* Remove the current item from the list of epoll hooks */
- spin_lock(&file->f_ep_lock);
- if (ep_is_linked(&epi->fllink))
- ep_list_del(&epi->fllink);
- spin_unlock(&file->f_ep_lock);
-
- /* We need to acquire the write IRQ lock before calling ep_unlink() */
- write_lock_irqsave(&ep->lock, flags);
-
- /* Really unlink the item from the hash */
- error = ep_unlink(ep, epi);
-
- write_unlock_irqrestore(&ep->lock, flags);
-
- if (error)
- goto eexit_1;
-
- /* At this point it is safe to free the eventpoll item */
- ep_release_epitem(epi);
-
- error = 0;
-eexit_1:
- DNPRINTK(3, (KERN_INFO "[%p] eventpoll: ep_remove(%p, %p) = %d\n",
- current, ep, file, error));
-
- return error;
-}
-
-
-/*
- * This is the callback that is passed to the wait queue wakeup
- * machanism. It is called by the stored file descriptors when they
- * have events to report.
- */
-static int ep_poll_callback(wait_queue_t *wait, unsigned mode, int sync, void *key)
-{
- int pwake = 0;
+ int eventcnt, error = -EFAULT, pwake = 0;
+ unsigned int revents;
unsigned long flags;
- struct epitem *epi = ep_item_from_wait(wait);
- struct eventpoll *ep = epi->ep;
-
- DNPRINTK(3, (KERN_INFO "[%p] eventpoll: poll_callback(%p) epi=%p ep=%p\n",
- current, epi->ffd.file, epi, ep));
+ struct epitem *epi, *nepi;
+ struct list_head txlist;
- write_lock_irqsave(&ep->lock, flags);
+ INIT_LIST_HEAD(&txlist);
/*
- * If the event mask does not contain any poll(2) event, we consider the
- * descriptor to be disabled. This condition is likely the effect of the
- * EPOLLONESHOT bit that disables the descriptor when an event is received,
- * until the next EPOLL_CTL_MOD will be issued.
+ * We need to lock this because we could be hit by
+ * eventpoll_release_file() and epoll_ctl(EPOLL_CTL_DEL).
*/
- if (!(epi->event.events & ~EP_PRIVATE_BITS))
- goto is_disabled;
+ mutex_lock(&ep->mtx);
- /* If this file is already in the ready list we exit soon */
- if (ep_is_linked(&epi->rdllink))
- goto is_linked;
-
- list_add_tail(&epi->rdllink, &ep->rdllist);
-
-is_linked:
/*
- * Wake up ( if active ) both the eventpoll wait list and the ->poll()
- * wait list.
+ * Steal the ready list, and re-init the original one to the
+ * empty list. Also, set ep->ovflist to NULL so that events
+ * happening while looping w/out locks, are not lost. We cannot
+ * have the poll callback to queue directly on ep->rdllist,
+ * because we are doing it in the loop below, in a lockless way.
*/
- if (waitqueue_active(&ep->wq))
- __wake_up_locked(&ep->wq, TASK_UNINTERRUPTIBLE |
- TASK_INTERRUPTIBLE);
- if (waitqueue_active(&ep->poll_wait))
- pwake++;
-
-is_disabled:
- write_unlock_irqrestore(&ep->lock, flags);
-
- /* We have to call this outside the lock */
- if (pwake)
- ep_poll_safewake(&psw, &ep->poll_wait);
-
- return 1;
-}
-
-
-static int ep_eventpoll_close(struct inode *inode, struct file *file)
-{
- struct eventpoll *ep = file->private_data;
-
- if (ep) {
- ep_free(ep);
- kfree(ep);
- }
-
- DNPRINTK(3, (KERN_INFO "[%p] eventpoll: close() ep=%p\n", current, ep));
- return 0;
-}
-
-
-static unsigned int ep_eventpoll_poll(struct file *file, poll_table *wait)
-{
- unsigned int pollflags = 0;
- unsigned long flags;
- struct eventpoll *ep = file->private_data;
-
- /* Insert inside our poll wait queue */
- poll_wait(file, &ep->poll_wait, wait);
-
- /* Check our condition */
- read_lock_irqsave(&ep->lock, flags);
- if (!list_empty(&ep->rdllist))
- pollflags = POLLIN | POLLRDNORM;
- read_unlock_irqrestore(&ep->lock, flags);
-
- return pollflags;
-}
-
-
-/*
- * Since we have to release the lock during the __copy_to_user() operation and
- * during the f_op->poll() call, we try to collect the maximum number of items
- * by reducing the irqlock/irqunlock switching rate.
- */
-static int ep_collect_ready_items(struct eventpoll *ep, struct list_head *txlist, int maxevents)
-{
- int nepi;
- unsigned long flags;
- struct list_head *lsthead = &ep->rdllist, *lnk;
- struct epitem *epi;
-
- write_lock_irqsave(&ep->lock, flags);
-
- for (nepi = 0, lnk = lsthead->next; lnk != lsthead && nepi < maxevents;) {
- epi = list_entry(lnk, struct epitem, rdllink);
-
- lnk = lnk->next;
-
- /* If this file is already in the ready list we exit soon */
- if (!ep_is_linked(&epi->txlink)) {
- /*
- * This is initialized in this way so that the default
- * behaviour of the reinjecting code will be to push back
- * the item inside the ready list.
- */
- epi->revents = epi->event.events;
-
- /* Link the ready item into the transfer list */
- list_add(&epi->txlink, txlist);
- nepi++;
-
- /*
- * Unlink the item from the ready list.
- */
- ep_list_del(&epi->rdllink);
- }
- }
-
- write_unlock_irqrestore(&ep->lock, flags);
-
- return nepi;
-}
-
-
-/*
- * This function is called without holding the "ep->lock" since the call to
- * __copy_to_user() might sleep, and also f_op->poll() might reenable the IRQ
- * because of the way poll() is traditionally implemented in Linux.
- */
-static int ep_send_events(struct eventpoll *ep, struct list_head *txlist,
- struct epoll_event __user *events)
-{
- int eventcnt = 0;
- unsigned int revents;
- struct list_head *lnk;
- struct epitem *epi;
+ spin_lock_irqsave(&ep->lock, flags);
+ list_splice(&ep->rdllist, &txlist);
+ INIT_LIST_HEAD(&ep->rdllist);
+ ep->ovflist = NULL;
+ spin_unlock_irqrestore(&ep->lock, flags);
/*
* We can loop without lock because this is a task private list.
- * The test done during the collection loop will guarantee us that
- * another task will not try to collect this file. Also, items
- * cannot vanish during the loop because we are holding "sem".
+ * We just splice'd out the ep->rdllist in ep_collect_ready_items().
+ * Items cannot vanish during the loop because we are holding "mtx".
*/
- list_for_each(lnk, txlist) {
- epi = list_entry(lnk, struct epitem, txlink);
+ for (eventcnt = 0; !list_empty(&txlist) && eventcnt < maxevents;) {
+ epi = list_first_entry(&txlist, struct epitem, rdllink);
+
+ list_del_init(&epi->rdllink);
/*
* Get the ready file event set. We can safely use the file
- * because we are holding the "sem" in read and this will
- * guarantee that both the file and the item will not vanish.
+ * because we are holding the "mtx" and this will guarantee
+ * that both the file and the item will not vanish.
*/
revents = epi->ffd.file->f_op->poll(epi->ffd.file, NULL);
+ revents &= epi->event.events;
/*
- * Set the return event set for the current file descriptor.
- * Note that only the task task was successfully able to link
- * the item to its "txlist" will write this field.
+ * Is the event mask intersect the caller-requested one,
+ * deliver the event to userspace. Again, we are holding
+ * "mtx", so no operations coming from userspace can change
+ * the item.
*/
- epi->revents = revents & epi->event.events;
-
- if (epi->revents) {
- if (__put_user(epi->revents,
+ if (revents) {
+ if (__put_user(revents,
&events[eventcnt].events) ||
__put_user(epi->event.data,
&events[eventcnt].data))
- return -EFAULT;
+ goto errxit;
if (epi->event.events & EPOLLONESHOT)
epi->event.events &= EP_PRIVATE_BITS;
eventcnt++;
}
+ /*
+ * At this point, noone can insert into ep->rdllist besides
+ * us. The epoll_ctl() callers are locked out by us holding
+ * "mtx" and the poll callback will queue them in ep->ovflist.
+ */
+ if (!(epi->event.events & EPOLLET) &&
+ (revents & epi->event.events))
+ list_add_tail(&epi->rdllink, &ep->rdllist);
}
- return eventcnt;
-}
-
-
-/*
- * Walk through the transfer list we collected with ep_collect_ready_items()
- * and, if 1) the item is still "alive" 2) its event set is not empty 3) it's
- * not already linked, links it to the ready list. Same as above, we are holding
- * "sem" so items cannot vanish underneath our nose.
- */
-static void ep_reinject_items(struct eventpoll *ep, struct list_head *txlist)
-{
- int ricnt = 0, pwake = 0;
- unsigned long flags;
- struct epitem *epi;
-
- write_lock_irqsave(&ep->lock, flags);
-
- while (!list_empty(txlist)) {
- epi = list_entry(txlist->next, struct epitem, txlink);
+ error = 0;
- /* Unlink the current item from the transfer list */
- ep_list_del(&epi->txlink);
+errxit:
- /*
- * If the item is no more linked to the interest set, we don't
- * have to push it inside the ready list because the following
- * ep_release_epitem() is going to drop it. Also, if the current
- * item is set to have an Edge Triggered behaviour, we don't have
- * to push it back either.
- */
- if (ep_rb_linked(&epi->rbn) && !(epi->event.events & EPOLLET) &&
- (epi->revents & epi->event.events) && !ep_is_linked(&epi->rdllink)) {
+ spin_lock_irqsave(&ep->lock, flags);
+ /*
+ * During the time we spent in the loop above, some other events
+ * might have been queued by the poll callback. We re-insert them
+ * here (in case they are not already queued, or they're one-shot).
+ */
+ for (nepi = ep->ovflist; (epi = nepi) != NULL;
+ nepi = epi->next, epi->next = EP_UNACTIVE_PTR) {
+ if (!ep_is_linked(&epi->rdllink) &&
+ (epi->event.events & ~EP_PRIVATE_BITS))
list_add_tail(&epi->rdllink, &ep->rdllist);
- ricnt++;
- }
}
+ /*
+ * We need to set back ep->ovflist to EP_UNACTIVE_PTR, so that after
+ * releasing the lock, events will be queued in the normal way inside
+ * ep->rdllist.
+ */
+ ep->ovflist = EP_UNACTIVE_PTR;
- if (ricnt) {
+ /*
+ * In case of error in the event-send loop, or in case the number of
+ * ready events exceeds the userspace limit, we need to splice the
+ * "txlist" back inside ep->rdllist.
+ */
+ list_splice(&txlist, &ep->rdllist);
+
+ if (!list_empty(&ep->rdllist)) {
/*
- * Wake up ( if active ) both the eventpoll wait list and the ->poll()
- * wait list.
+ * Wake up (if active) both the eventpoll wait list and the ->poll()
+ * wait list (delayed after we release the lock).
*/
if (waitqueue_active(&ep->wq))
__wake_up_locked(&ep->wq, TASK_UNINTERRUPTIBLE |
@@ -1502,47 +984,17 @@ static void ep_reinject_items(struct eventpoll *ep, struct list_head *txlist)
if (waitqueue_active(&ep->poll_wait))
pwake++;
}
+ spin_unlock_irqrestore(&ep->lock, flags);
- write_unlock_irqrestore(&ep->lock, flags);
+ mutex_unlock(&ep->mtx);
/* We have to call this outside the lock */
if (pwake)
ep_poll_safewake(&psw, &ep->poll_wait);
-}
-
-/*
- * Perform the transfer of events to user space.
- */
-static int ep_events_transfer(struct eventpoll *ep,
- struct epoll_event __user *events, int maxevents)
-{
- int eventcnt = 0;
- struct list_head txlist;
-
- INIT_LIST_HEAD(&txlist);
-
- /*
- * We need to lock this because we could be hit by
- * eventpoll_release_file() and epoll_ctl(EPOLL_CTL_DEL).
- */
- down_read(&ep->sem);
-
- /* Collect/extract ready items */
- if (ep_collect_ready_items(ep, &txlist, maxevents) > 0) {
- /* Build result set in userspace */
- eventcnt = ep_send_events(ep, &txlist, events);
-
- /* Reinject ready items into the ready list */
- ep_reinject_items(ep, &txlist);
- }
-
- up_read(&ep->sem);
-
- return eventcnt;
+ return eventcnt == 0 ? error: eventcnt;
}
-
static int ep_poll(struct eventpoll *ep, struct epoll_event __user *events,
int maxevents, long timeout)
{
@@ -1560,7 +1012,7 @@ static int ep_poll(struct eventpoll *ep, struct epoll_event __user *events,
MAX_SCHEDULE_TIMEOUT : (timeout * HZ + 999) / 1000;
retry:
- write_lock_irqsave(&ep->lock, flags);
+ spin_lock_irqsave(&ep->lock, flags);
res = 0;
if (list_empty(&ep->rdllist)) {
@@ -1570,6 +1022,7 @@ retry:
* ep_poll_callback() when events will become available.
*/
init_waitqueue_entry(&wait, current);
+ wait.flags |= WQ_FLAG_EXCLUSIVE;
__add_wait_queue(&ep->wq, &wait);
for (;;) {
@@ -1586,9 +1039,9 @@ retry:
break;
}
- write_unlock_irqrestore(&ep->lock, flags);
+ spin_unlock_irqrestore(&ep->lock, flags);
jtimeout = schedule_timeout(jtimeout);
- write_lock_irqsave(&ep->lock, flags);
+ spin_lock_irqsave(&ep->lock, flags);
}
__remove_wait_queue(&ep->wq, &wait);
@@ -1598,7 +1051,7 @@ retry:
/* Is it worth to try to dig for events ? */
eavail = !list_empty(&ep->rdllist);
- write_unlock_irqrestore(&ep->lock, flags);
+ spin_unlock_irqrestore(&ep->lock, flags);
/*
* Try to transfer events to user space. In case we get 0 events and
@@ -1606,61 +1059,263 @@ retry:
* more luck.
*/
if (!res && eavail &&
- !(res = ep_events_transfer(ep, events, maxevents)) && jtimeout)
+ !(res = ep_send_events(ep, events, maxevents)) && jtimeout)
goto retry;
return res;
}
-
-static int eventpollfs_delete_dentry(struct dentry *dentry)
+/*
+ * It opens an eventpoll file descriptor. The "size" parameter is there
+ * for historical reasons, when epoll was using an hash instead of an
+ * RB tree. With the current implementation, the "size" parameter is ignored
+ * (besides sanity checks).
+ */
+asmlinkage long sys_epoll_create(int size)
{
+ int error, fd = -1;
+ struct eventpoll *ep;
+ struct inode *inode;
+ struct file *file;
- return 1;
+ DNPRINTK(3, (KERN_INFO "[%p] eventpoll: sys_epoll_create(%d)\n",
+ current, size));
+
+ /*
+ * Sanity check on the size parameter, and create the internal data
+ * structure ( "struct eventpoll" ).
+ */
+ error = -EINVAL;
+ if (size <= 0 || (error = ep_alloc(&ep)) != 0)
+ goto error_return;
+
+ /*
+ * Creates all the items needed to setup an eventpoll file. That is,
+ * a file structure, and inode and a free file descriptor.
+ */
+ error = anon_inode_getfd(&fd, &inode, &file, "[eventpoll]",
+ &eventpoll_fops, ep);
+ if (error)
+ goto error_free;
+
+ DNPRINTK(3, (KERN_INFO "[%p] eventpoll: sys_epoll_create(%d) = %d\n",
+ current, size, fd));
+
+ return fd;
+
+error_free:
+ ep_free(ep);
+error_return:
+ DNPRINTK(3, (KERN_INFO "[%p] eventpoll: sys_epoll_create(%d) = %d\n",
+ current, size, error));
+ return error;
}
+/*
+ * The following function implements the controller interface for
+ * the eventpoll file that enables the insertion/removal/change of
+ * file descriptors inside the interest set.
+ */
+asmlinkage long sys_epoll_ctl(int epfd, int op, int fd,
+ struct epoll_event __user *event)
+{
+ int error;
+ struct file *file, *tfile;
+ struct eventpoll *ep;
+ struct epitem *epi;
+ struct epoll_event epds;
+
+ DNPRINTK(3, (KERN_INFO "[%p] eventpoll: sys_epoll_ctl(%d, %d, %d, %p)\n",
+ current, epfd, op, fd, event));
-static struct inode *ep_eventpoll_inode(void)
+ error = -EFAULT;
+ if (ep_op_has_event(op) &&
+ copy_from_user(&epds, event, sizeof(struct epoll_event)))
+ goto error_return;
+
+ /* Get the "struct file *" for the eventpoll file */
+ error = -EBADF;
+ file = fget(epfd);
+ if (!file)
+ goto error_return;
+
+ /* Get the "struct file *" for the target file */
+ tfile = fget(fd);
+ if (!tfile)
+ goto error_fput;
+
+ /* The target file descriptor must support poll */
+ error = -EPERM;
+ if (!tfile->f_op || !tfile->f_op->poll)
+ goto error_tgt_fput;
+
+ /*
+ * We have to check that the file structure underneath the file descriptor
+ * the user passed to us _is_ an eventpoll file. And also we do not permit
+ * adding an epoll file descriptor inside itself.
+ */
+ error = -EINVAL;
+ if (file == tfile || !is_file_epoll(file))
+ goto error_tgt_fput;
+
+ /*
+ * At this point it is safe to assume that the "private_data" contains
+ * our own data structure.
+ */
+ ep = file->private_data;
+
+ mutex_lock(&ep->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.
+ */
+ epi = ep_find(ep, tfile, fd);
+
+ error = -EINVAL;
+ switch (op) {
+ case EPOLL_CTL_ADD:
+ if (!epi) {
+ epds.events |= POLLERR | POLLHUP;
+
+ error = ep_insert(ep, &epds, tfile, fd);
+ } else
+ error = -EEXIST;
+ break;
+ case EPOLL_CTL_DEL:
+ if (epi)
+ error = ep_remove(ep, epi);
+ else
+ error = -ENOENT;
+ break;
+ case EPOLL_CTL_MOD:
+ if (epi) {
+ epds.events |= POLLERR | POLLHUP;
+ error = ep_modify(ep, epi, &epds);
+ } else
+ error = -ENOENT;
+ break;
+ }
+ mutex_unlock(&ep->mtx);
+
+error_tgt_fput:
+ fput(tfile);
+error_fput:
+ fput(file);
+error_return:
+ DNPRINTK(3, (KERN_INFO "[%p] eventpoll: sys_epoll_ctl(%d, %d, %d, %p) = %d\n",
+ current, epfd, op, fd, event, error));
+
+ return error;
+}
+
+/*
+ * Implement the event wait interface for the eventpoll file. It is the kernel
+ * part of the user space epoll_wait(2).
+ */
+asmlinkage long sys_epoll_wait(int epfd, struct epoll_event __user *events,
+ int maxevents, int timeout)
{
- int error = -ENOMEM;
- struct inode *inode = new_inode(eventpoll_mnt->mnt_sb);
+ int error;
+ struct file *file;
+ struct eventpoll *ep;
+
+ DNPRINTK(3, (KERN_INFO "[%p] eventpoll: sys_epoll_wait(%d, %p, %d, %d)\n",
+ current, epfd, events, maxevents, timeout));
+
+ /* The maximum number of event must be greater than zero */
+ if (maxevents <= 0 || maxevents > EP_MAX_EVENTS)
+ return -EINVAL;
- if (!inode)
- goto eexit_1;
+ /* Verify that the area passed by the user is writeable */
+ if (!access_ok(VERIFY_WRITE, events, maxevents * sizeof(struct epoll_event))) {
+ error = -EFAULT;
+ goto error_return;
+ }
+
+ /* Get the "struct file *" for the eventpoll file */
+ error = -EBADF;
+ file = fget(epfd);
+ if (!file)
+ goto error_return;
- inode->i_fop = &eventpoll_fops;
+ /*
+ * We have to check that the file structure underneath the fd
+ * the user passed to us _is_ an eventpoll file.
+ */
+ error = -EINVAL;
+ if (!is_file_epoll(file))
+ goto error_fput;
/*
- * Mark the inode dirty from the very beginning,
- * that way it will never be moved to the dirty
- * list because mark_inode_dirty() will think
- * that it already _is_ on the dirty list.
+ * At this point it is safe to assume that the "private_data" contains
+ * our own data structure.
*/
- inode->i_state = I_DIRTY;
- inode->i_mode = S_IRUSR | S_IWUSR;
- inode->i_uid = current->fsuid;
- inode->i_gid = current->fsgid;
- inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME;
- return inode;
-
-eexit_1:
- return ERR_PTR(error);
+ ep = file->private_data;
+
+ /* Time to fish for events ... */
+ error = ep_poll(ep, events, maxevents, timeout);
+
+error_fput:
+ fput(file);
+error_return:
+ DNPRINTK(3, (KERN_INFO "[%p] eventpoll: sys_epoll_wait(%d, %p, %d, %d) = %d\n",
+ current, epfd, events, maxevents, timeout, error));
+
+ return error;
}
+#ifdef TIF_RESTORE_SIGMASK
-static int
-eventpollfs_get_sb(struct file_system_type *fs_type, int flags,
- const char *dev_name, void *data, struct vfsmount *mnt)
+/*
+ * Implement the event wait interface for the eventpoll file. It is the kernel
+ * part of the user space epoll_pwait(2).
+ */
+asmlinkage long sys_epoll_pwait(int epfd, struct epoll_event __user *events,
+ int maxevents, int timeout, const sigset_t __user *sigmask,
+ size_t sigsetsize)
{
- return get_sb_pseudo(fs_type, "eventpoll:", NULL, EVENTPOLLFS_MAGIC,
- mnt);
+ int error;
+ sigset_t ksigmask, sigsaved;
+
+ /*
+ * If the caller wants a certain signal mask to be set during the wait,
+ * we apply it here.
+ */
+ if (sigmask) {
+ if (sigsetsize != sizeof(sigset_t))
+ return -EINVAL;
+ if (copy_from_user(&ksigmask, sigmask, sizeof(ksigmask)))
+ return -EFAULT;
+ sigdelsetmask(&ksigmask, sigmask(SIGKILL) | sigmask(SIGSTOP));
+ sigprocmask(SIG_SETMASK, &ksigmask, &sigsaved);
+ }
+
+ error = sys_epoll_wait(epfd, events, maxevents, timeout);
+
+ /*
+ * If we changed the signal mask, we need to restore the original one.
+ * In case we've got a signal while waiting, we do not restore the
+ * signal mask yet, and we allow do_signal() to deliver the signal on
+ * the way back to userspace, before the signal mask is restored.
+ */
+ if (sigmask) {
+ if (error == -EINTR) {
+ memcpy(&current->saved_sigmask, &sigsaved,
+ sizeof(sigsaved));
+ set_thread_flag(TIF_RESTORE_SIGMASK);
+ } else
+ sigprocmask(SIG_SETMASK, &sigsaved, NULL);
+ }
+
+ return error;
}
+#endif /* #ifdef TIF_RESTORE_SIGMASK */
static int __init eventpoll_init(void)
{
- int error;
-
mutex_init(&epmutex);
/* Initialize the structure used to perform safe poll wait head wake ups */
@@ -1676,39 +1331,7 @@ static int __init eventpoll_init(void)
sizeof(struct eppoll_entry), 0,
EPI_SLAB_DEBUG|SLAB_PANIC, NULL, NULL);
- /*
- * Register the virtual file system that will be the source of inodes
- * for the eventpoll files
- */
- error = register_filesystem(&eventpoll_fs_type);
- if (error)
- goto epanic;
-
- /* Mount the above commented virtual file system */
- eventpoll_mnt = kern_mount(&eventpoll_fs_type);
- error = PTR_ERR(eventpoll_mnt);
- if (IS_ERR(eventpoll_mnt))
- goto epanic;
-
- DNPRINTK(3, (KERN_INFO "[%p] eventpoll: successfully initialized.\n",
- current));
return 0;
-
-epanic:
- panic("eventpoll_init() failed\n");
}
+fs_initcall(eventpoll_init);
-
-static void __exit eventpoll_exit(void)
-{
- /* Undo all operations done inside eventpoll_init() */
- unregister_filesystem(&eventpoll_fs_type);
- mntput(eventpoll_mnt);
- kmem_cache_destroy(pwq_cache);
- kmem_cache_destroy(epi_cache);
-}
-
-module_init(eventpoll_init);
-module_exit(eventpoll_exit);
-
-MODULE_LICENSE("GPL");
diff --git a/fs/exec.c b/fs/exec.c
index 3155e915307..f20561ff452 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -50,6 +50,7 @@
#include <linux/tsacct_kern.h>
#include <linux/cn_proc.h>
#include <linux/audit.h>
+#include <linux/signalfd.h>
#include <asm/uaccess.h>
#include <asm/mmu_context.h>
@@ -59,7 +60,7 @@
#endif
int core_uses_pid;
-char core_pattern[128] = "core";
+char core_pattern[CORENAME_MAX_SIZE] = "core";
int suid_dumpable = 0;
EXPORT_SYMBOL(suid_dumpable);
@@ -100,6 +101,7 @@ int unregister_binfmt(struct linux_binfmt * fmt)
while (*tmp) {
if (fmt == *tmp) {
*tmp = fmt->next;
+ fmt->next = NULL;
write_unlock(&binfmt_lock);
return 0;
}
@@ -132,6 +134,9 @@ asmlinkage long sys_uselib(const char __user * library)
if (error)
goto out;
+ error = -EACCES;
+ if (nd.mnt->mnt_flags & MNT_NOEXEC)
+ goto exit;
error = -EINVAL;
if (!S_ISREG(nd.dentry->d_inode->i_mode))
goto exit;
@@ -581,6 +586,13 @@ static int de_thread(struct task_struct *tsk)
int count;
/*
+ * Tell all the sighand listeners that this sighand has
+ * been detached. The signalfd_detach() function grabs the
+ * sighand lock, if signal listeners are present on the sighand.
+ */
+ signalfd_detach(tsk);
+
+ /*
* If we don't share sighandlers, then we aren't sharing anything
* and we can just re-use it all.
*/
@@ -701,7 +713,7 @@ static int de_thread(struct task_struct *tsk)
*/
detach_pid(tsk, PIDTYPE_PID);
tsk->pid = leader->pid;
- attach_pid(tsk, PIDTYPE_PID, tsk->pid);
+ attach_pid(tsk, PIDTYPE_PID, find_pid(tsk->pid));
transfer_pid(leader, tsk, PIDTYPE_PGID);
transfer_pid(leader, tsk, PIDTYPE_SID);
list_replace_rcu(&leader->tasks, &tsk->tasks);
@@ -756,8 +768,7 @@ no_thread_group:
spin_unlock(&oldsighand->siglock);
write_unlock_irq(&tasklist_lock);
- if (atomic_dec_and_test(&oldsighand->count))
- kmem_cache_free(sighand_cachep, oldsighand);
+ __cleanup_sighand(oldsighand);
}
BUG_ON(!thread_group_leader(tsk));
@@ -982,33 +993,51 @@ void compute_creds(struct linux_binprm *bprm)
task_unlock(current);
security_bprm_post_apply_creds(bprm);
}
-
EXPORT_SYMBOL(compute_creds);
+/*
+ * Arguments are '\0' separated strings found at the location bprm->p
+ * points to; chop off the first by relocating brpm->p to right after
+ * the first '\0' encountered.
+ */
void remove_arg_zero(struct linux_binprm *bprm)
{
if (bprm->argc) {
- unsigned long offset;
- char * kaddr;
- struct page *page;
+ char ch;
+
+ do {
+ unsigned long offset;
+ unsigned long index;
+ char *kaddr;
+ struct page *page;
- offset = bprm->p % PAGE_SIZE;
- goto inside;
+ offset = bprm->p & ~PAGE_MASK;
+ index = bprm->p >> PAGE_SHIFT;
- while (bprm->p++, *(kaddr+offset++)) {
- if (offset != PAGE_SIZE)
- continue;
- offset = 0;
- kunmap_atomic(kaddr, KM_USER0);
-inside:
- page = bprm->page[bprm->p/PAGE_SIZE];
+ page = bprm->page[index];
kaddr = kmap_atomic(page, KM_USER0);
- }
- kunmap_atomic(kaddr, KM_USER0);
+
+ /* run through page until we reach end or find NUL */
+ do {
+ ch = *(kaddr + offset);
+
+ /* discard that character... */
+ bprm->p++;
+ offset++;
+ } while (offset < PAGE_SIZE && ch != '\0');
+
+ kunmap_atomic(kaddr, KM_USER0);
+
+ /* free the old page */
+ if (offset == PAGE_SIZE) {
+ __free_page(page);
+ bprm->page[index] = NULL;
+ }
+ } while (ch != '\0');
+
bprm->argc--;
}
}
-
EXPORT_SYMBOL(remove_arg_zero);
/*
@@ -1238,8 +1267,6 @@ int set_binfmt(struct linux_binfmt *new)
EXPORT_SYMBOL(set_binfmt);
-#define CORENAME_MAX_SIZE 64
-
/* format_corename will inspect the pattern parameter, and output a
* name into corename, which must have space for at least
* CORENAME_MAX_SIZE bytes plus one byte for the zero terminator.
@@ -1469,6 +1496,8 @@ int do_coredump(long signr, int exit_code, struct pt_regs * regs)
int flag = 0;
int ispipe = 0;
+ audit_core_dumps(signr);
+
binfmt = current->binfmt;
if (!binfmt || !binfmt->core_dump)
goto fail;
diff --git a/fs/exportfs/expfs.c b/fs/exportfs/expfs.c
index 93e77c3d249..e98f6cd7200 100644
--- a/fs/exportfs/expfs.c
+++ b/fs/exportfs/expfs.c
@@ -2,7 +2,6 @@
#include <linux/fs.h>
#include <linux/file.h>
#include <linux/module.h>
-#include <linux/smp_lock.h>
#include <linux/namei.h>
struct export_operations export_op_default;
diff --git a/fs/ext2/dir.c b/fs/ext2/dir.c
index 1d1e7e30d70..2bf49d7ef84 100644
--- a/fs/ext2/dir.c
+++ b/fs/ext2/dir.c
@@ -23,7 +23,6 @@
#include "ext2.h"
#include <linux/pagemap.h>
-#include <linux/smp_lock.h>
typedef struct ext2_dir_entry_2 ext2_dirent;
diff --git a/fs/ext2/ext2.h b/fs/ext2/ext2.h
index e2a0ea50af1..9fd0ec5ba0d 100644
--- a/fs/ext2/ext2.h
+++ b/fs/ext2/ext2.h
@@ -133,6 +133,7 @@ extern int ext2_get_block(struct inode *, sector_t, struct buffer_head *, int);
extern void ext2_truncate (struct inode *);
extern int ext2_setattr (struct dentry *, struct iattr *);
extern void ext2_set_inode_flags(struct inode *inode);
+extern void ext2_get_inode_flags(struct ext2_inode_info *);
/* ioctl.c */
extern int ext2_ioctl (struct inode *, struct file *, unsigned int,
diff --git a/fs/ext2/fsync.c b/fs/ext2/fsync.c
index 7806b9e8155..fc66c93fcb5 100644
--- a/fs/ext2/fsync.c
+++ b/fs/ext2/fsync.c
@@ -23,7 +23,6 @@
*/
#include "ext2.h"
-#include <linux/smp_lock.h>
#include <linux/buffer_head.h> /* for sync_mapping_buffers() */
diff --git a/fs/ext2/inode.c b/fs/ext2/inode.c
index dd4e14c221e..0079b2cd531 100644
--- a/fs/ext2/inode.c
+++ b/fs/ext2/inode.c
@@ -1055,6 +1055,25 @@ void ext2_set_inode_flags(struct inode *inode)
inode->i_flags |= S_DIRSYNC;
}
+/* Propagate flags from i_flags to EXT2_I(inode)->i_flags */
+void ext2_get_inode_flags(struct ext2_inode_info *ei)
+{
+ unsigned int flags = ei->vfs_inode.i_flags;
+
+ ei->i_flags &= ~(EXT2_SYNC_FL|EXT2_APPEND_FL|
+ EXT2_IMMUTABLE_FL|EXT2_NOATIME_FL|EXT2_DIRSYNC_FL);
+ if (flags & S_SYNC)
+ ei->i_flags |= EXT2_SYNC_FL;
+ if (flags & S_APPEND)
+ ei->i_flags |= EXT2_APPEND_FL;
+ if (flags & S_IMMUTABLE)
+ ei->i_flags |= EXT2_IMMUTABLE_FL;
+ if (flags & S_NOATIME)
+ ei->i_flags |= EXT2_NOATIME_FL;
+ if (flags & S_DIRSYNC)
+ ei->i_flags |= EXT2_DIRSYNC_FL;
+}
+
void ext2_read_inode (struct inode * inode)
{
struct ext2_inode_info *ei = EXT2_I(inode);
@@ -1079,9 +1098,9 @@ void ext2_read_inode (struct inode * inode)
}
inode->i_nlink = le16_to_cpu(raw_inode->i_links_count);
inode->i_size = le32_to_cpu(raw_inode->i_size);
- inode->i_atime.tv_sec = le32_to_cpu(raw_inode->i_atime);
- inode->i_ctime.tv_sec = le32_to_cpu(raw_inode->i_ctime);
- inode->i_mtime.tv_sec = le32_to_cpu(raw_inode->i_mtime);
+ inode->i_atime.tv_sec = (signed)le32_to_cpu(raw_inode->i_atime);
+ inode->i_ctime.tv_sec = (signed)le32_to_cpu(raw_inode->i_ctime);
+ inode->i_mtime.tv_sec = (signed)le32_to_cpu(raw_inode->i_mtime);
inode->i_atime.tv_nsec = inode->i_mtime.tv_nsec = inode->i_ctime.tv_nsec = 0;
ei->i_dtime = le32_to_cpu(raw_inode->i_dtime);
/* We now have enough fields to check if the inode was active or not.
@@ -1188,6 +1207,7 @@ static int ext2_update_inode(struct inode * inode, int do_sync)
if (ei->i_state & EXT2_STATE_NEW)
memset(raw_inode, 0, EXT2_SB(sb)->s_inode_size);
+ ext2_get_inode_flags(ei);
raw_inode->i_mode = cpu_to_le16(inode->i_mode);
if (!(test_opt(sb, NO_UID32))) {
raw_inode->i_uid_low = cpu_to_le16(low_16_bits(uid));
diff --git a/fs/ext2/ioctl.c b/fs/ext2/ioctl.c
index 4b099d31071..e85c4821823 100644
--- a/fs/ext2/ioctl.c
+++ b/fs/ext2/ioctl.c
@@ -27,6 +27,7 @@ int ext2_ioctl (struct inode * inode, struct file * filp, unsigned int cmd,
switch (cmd) {
case EXT2_IOC_GETFLAGS:
+ ext2_get_inode_flags(ei);
flags = ei->i_flags & EXT2_FL_USER_VISIBLE;
return put_user(flags, (int __user *) arg);
case EXT2_IOC_SETFLAGS: {
diff --git a/fs/ext2/super.c b/fs/ext2/super.c
index 685a1c28717..5de5061eb33 100644
--- a/fs/ext2/super.c
+++ b/fs/ext2/super.c
@@ -160,13 +160,11 @@ static void init_once(void * foo, struct kmem_cache * cachep, unsigned long flag
{
struct ext2_inode_info *ei = (struct ext2_inode_info *) foo;
- if (flags & SLAB_CTOR_CONSTRUCTOR) {
- rwlock_init(&ei->i_meta_lock);
+ rwlock_init(&ei->i_meta_lock);
#ifdef CONFIG_EXT2_FS_XATTR
- init_rwsem(&ei->xattr_sem);
+ init_rwsem(&ei->xattr_sem);
#endif
- inode_init_once(&ei->vfs_inode);
- }
+ inode_init_once(&ei->vfs_inode);
}
static int init_inodecache(void)
@@ -1040,6 +1038,15 @@ static int ext2_remount (struct super_block * sb, int * flags, char * data)
sb->s_flags = (sb->s_flags & ~MS_POSIXACL) |
((sbi->s_mount_opt & EXT2_MOUNT_POSIX_ACL) ? MS_POSIXACL : 0);
+ ext2_xip_verify_sb(sb); /* see if bdev supports xip, unset
+ EXT2_MOUNT_XIP if not */
+
+ if ((ext2_use_xip(sb)) && (sb->s_blocksize != PAGE_SIZE)) {
+ printk("XIP: Unsupported blocksize\n");
+ err = -EINVAL;
+ goto restore_opts;
+ }
+
es = sbi->s_es;
if (((sbi->s_mount_opt & EXT2_MOUNT_XIP) !=
(old_mount_opt & EXT2_MOUNT_XIP)) &&
diff --git a/fs/ext2/xattr_security.c b/fs/ext2/xattr_security.c
index a2661279847..eaa23d2d521 100644
--- a/fs/ext2/xattr_security.c
+++ b/fs/ext2/xattr_security.c
@@ -6,7 +6,6 @@
#include <linux/module.h>
#include <linux/string.h>
#include <linux/fs.h>
-#include <linux/smp_lock.h>
#include <linux/ext2_fs.h>
#include <linux/security.h>
#include "xattr.h"
diff --git a/fs/ext2/xattr_trusted.c b/fs/ext2/xattr_trusted.c
index f28a6a499c9..83ee149f353 100644
--- a/fs/ext2/xattr_trusted.c
+++ b/fs/ext2/xattr_trusted.c
@@ -9,7 +9,6 @@
#include <linux/string.h>
#include <linux/capability.h>
#include <linux/fs.h>
-#include <linux/smp_lock.h>
#include <linux/ext2_fs.h>
#include "xattr.h"
diff --git a/fs/ext3/dir.c b/fs/ext3/dir.c
index 665adee99b3..852869840f2 100644
--- a/fs/ext3/dir.c
+++ b/fs/ext3/dir.c
@@ -25,7 +25,6 @@
#include <linux/jbd.h>
#include <linux/ext3_fs.h>
#include <linux/buffer_head.h>
-#include <linux/smp_lock.h>
#include <linux/slab.h>
#include <linux/rbtree.h>
diff --git a/fs/ext3/inode.c b/fs/ext3/inode.c
index a5b150f7e8a..2a85ddee474 100644
--- a/fs/ext3/inode.c
+++ b/fs/ext3/inode.c
@@ -27,7 +27,6 @@
#include <linux/time.h>
#include <linux/ext3_jbd.h>
#include <linux/jbd.h>
-#include <linux/smp_lock.h>
#include <linux/highuid.h>
#include <linux/pagemap.h>
#include <linux/quotaops.h>
@@ -1768,7 +1767,6 @@ static int ext3_block_truncate_page(handle_t *handle, struct page *page,
struct inode *inode = mapping->host;
struct buffer_head *bh;
int err = 0;
- void *kaddr;
blocksize = inode->i_sb->s_blocksize;
length = blocksize - (offset & (blocksize - 1));
@@ -1780,10 +1778,7 @@ static int ext3_block_truncate_page(handle_t *handle, struct page *page,
*/
if (!page_has_buffers(page) && test_opt(inode->i_sb, NOBH) &&
ext3_should_writeback_data(inode) && PageUptodate(page)) {
- kaddr = kmap_atomic(page, KM_USER0);
- memset(kaddr + offset, 0, length);
- flush_dcache_page(page);
- kunmap_atomic(kaddr, KM_USER0);
+ zero_user_page(page, offset, length, KM_USER0);
set_page_dirty(page);
goto unlock;
}
@@ -1836,11 +1831,7 @@ static int ext3_block_truncate_page(handle_t *handle, struct page *page,
goto unlock;
}
- kaddr = kmap_atomic(page, KM_USER0);
- memset(kaddr + offset, 0, length);
- flush_dcache_page(page);
- kunmap_atomic(kaddr, KM_USER0);
-
+ zero_user_page(page, offset, length, KM_USER0);
BUFFER_TRACE(bh, "zeroed end of block");
err = 0;
@@ -2581,6 +2572,25 @@ void ext3_set_inode_flags(struct inode *inode)
inode->i_flags |= S_DIRSYNC;
}
+/* Propagate flags from i_flags to EXT3_I(inode)->i_flags */
+void ext3_get_inode_flags(struct ext3_inode_info *ei)
+{
+ unsigned int flags = ei->vfs_inode.i_flags;
+
+ ei->i_flags &= ~(EXT3_SYNC_FL|EXT3_APPEND_FL|
+ EXT3_IMMUTABLE_FL|EXT3_NOATIME_FL|EXT3_DIRSYNC_FL);
+ if (flags & S_SYNC)
+ ei->i_flags |= EXT3_SYNC_FL;
+ if (flags & S_APPEND)
+ ei->i_flags |= EXT3_APPEND_FL;
+ if (flags & S_IMMUTABLE)
+ ei->i_flags |= EXT3_IMMUTABLE_FL;
+ if (flags & S_NOATIME)
+ ei->i_flags |= EXT3_NOATIME_FL;
+ if (flags & S_DIRSYNC)
+ ei->i_flags |= EXT3_DIRSYNC_FL;
+}
+
void ext3_read_inode(struct inode * inode)
{
struct ext3_iloc iloc;
@@ -2608,9 +2618,9 @@ void ext3_read_inode(struct inode * inode)
}
inode->i_nlink = le16_to_cpu(raw_inode->i_links_count);
inode->i_size = le32_to_cpu(raw_inode->i_size);
- inode->i_atime.tv_sec = le32_to_cpu(raw_inode->i_atime);
- inode->i_ctime.tv_sec = le32_to_cpu(raw_inode->i_ctime);
- inode->i_mtime.tv_sec = le32_to_cpu(raw_inode->i_mtime);
+ inode->i_atime.tv_sec = (signed)le32_to_cpu(raw_inode->i_atime);
+ inode->i_ctime.tv_sec = (signed)le32_to_cpu(raw_inode->i_ctime);
+ inode->i_mtime.tv_sec = (signed)le32_to_cpu(raw_inode->i_mtime);
inode->i_atime.tv_nsec = inode->i_ctime.tv_nsec = inode->i_mtime.tv_nsec = 0;
ei->i_state = 0;
@@ -2667,8 +2677,10 @@ void ext3_read_inode(struct inode * inode)
*/
ei->i_extra_isize = le16_to_cpu(raw_inode->i_extra_isize);
if (EXT3_GOOD_OLD_INODE_SIZE + ei->i_extra_isize >
- EXT3_INODE_SIZE(inode->i_sb))
+ EXT3_INODE_SIZE(inode->i_sb)) {
+ brelse (bh);
goto bad_inode;
+ }
if (ei->i_extra_isize == 0) {
/* The extra space is currently unused. Use it. */
ei->i_extra_isize = sizeof(struct ext3_inode) -
@@ -2736,6 +2748,7 @@ static int ext3_do_update_inode(handle_t *handle,
if (ei->i_state & EXT3_STATE_NEW)
memset(raw_inode, 0, EXT3_SB(inode->i_sb)->s_inode_size);
+ ext3_get_inode_flags(ei);
raw_inode->i_mode = cpu_to_le16(inode->i_mode);
if(!(test_opt(inode->i_sb, NO_UID32))) {
raw_inode->i_uid_low = cpu_to_le16(low_16_bits(inode->i_uid));
diff --git a/fs/ext3/ioctl.c b/fs/ext3/ioctl.c
index 9b8090d94e6..965006dba6b 100644
--- a/fs/ext3/ioctl.c
+++ b/fs/ext3/ioctl.c
@@ -28,6 +28,7 @@ int ext3_ioctl (struct inode * inode, struct file * filp, unsigned int cmd,
switch (cmd) {
case EXT3_IOC_GETFLAGS:
+ ext3_get_inode_flags(ei);
flags = ei->i_flags & EXT3_FL_USER_VISIBLE;
return put_user(flags, (int __user *) arg);
case EXT3_IOC_SETFLAGS: {
diff --git a/fs/ext3/namei.c b/fs/ext3/namei.c
index 49159f13cc1..9bb046df827 100644
--- a/fs/ext3/namei.c
+++ b/fs/ext3/namei.c
@@ -36,7 +36,6 @@
#include <linux/quotaops.h>
#include <linux/buffer_head.h>
#include <linux/bio.h>
-#include <linux/smp_lock.h>
#include "namei.h"
#include "xattr.h"
@@ -969,6 +968,7 @@ static struct buffer_head * ext3_dx_find_entry(struct dentry *dentry,
(block<<EXT3_BLOCK_SIZE_BITS(sb))
+((char *)de - bh->b_data))) {
brelse (bh);
+ *err = ERR_BAD_DX_DIR;
goto errout;
}
*res_dir = de;
@@ -1134,9 +1134,9 @@ static struct ext3_dir_entry_2 *do_split(handle_t *handle, struct inode *dir,
char *data1 = (*bh)->b_data, *data2;
unsigned split;
struct ext3_dir_entry_2 *de = NULL, *de2;
- int err;
+ int err = 0;
- bh2 = ext3_append (handle, dir, &newblock, error);
+ bh2 = ext3_append (handle, dir, &newblock, &err);
if (!(bh2)) {
brelse(*bh);
*bh = NULL;
@@ -1145,14 +1145,9 @@ static struct ext3_dir_entry_2 *do_split(handle_t *handle, struct inode *dir,
BUFFER_TRACE(*bh, "get_write_access");
err = ext3_journal_get_write_access(handle, *bh);
- if (err) {
- journal_error:
- brelse(*bh);
- brelse(bh2);
- *bh = NULL;
- ext3_std_error(dir->i_sb, err);
- goto errout;
- }
+ if (err)
+ goto journal_error;
+
BUFFER_TRACE(frame->bh, "get_write_access");
err = ext3_journal_get_write_access(handle, frame->bh);
if (err)
@@ -1195,8 +1190,16 @@ static struct ext3_dir_entry_2 *do_split(handle_t *handle, struct inode *dir,
goto journal_error;
brelse (bh2);
dxtrace(dx_show_index ("frame", frame->entries));
-errout:
return de;
+
+journal_error:
+ brelse(*bh);
+ brelse(bh2);
+ *bh = NULL;
+ ext3_std_error(dir->i_sb, err);
+errout:
+ *error = err;
+ return NULL;
}
#endif
diff --git a/fs/ext3/resize.c b/fs/ext3/resize.c
index ecf89904c11..2c97e09c6c6 100644
--- a/fs/ext3/resize.c
+++ b/fs/ext3/resize.c
@@ -11,7 +11,6 @@
#define EXT3FS_DEBUG
-#include <linux/smp_lock.h>
#include <linux/ext3_jbd.h>
#include <linux/errno.h>
diff --git a/fs/ext3/super.c b/fs/ext3/super.c
index 54d3c904125..6e3062913a9 100644
--- a/fs/ext3/super.c
+++ b/fs/ext3/super.c
@@ -466,14 +466,12 @@ static void init_once(void * foo, struct kmem_cache * cachep, unsigned long flag
{
struct ext3_inode_info *ei = (struct ext3_inode_info *) foo;
- if (flags & SLAB_CTOR_CONSTRUCTOR) {
- INIT_LIST_HEAD(&ei->i_orphan);
+ INIT_LIST_HEAD(&ei->i_orphan);
#ifdef CONFIG_EXT3_FS_XATTR
- init_rwsem(&ei->xattr_sem);
+ init_rwsem(&ei->xattr_sem);
#endif
- mutex_init(&ei->truncate_mutex);
- inode_init_once(&ei->vfs_inode);
- }
+ mutex_init(&ei->truncate_mutex);
+ inode_init_once(&ei->vfs_inode);
}
static int init_inodecache(void)
diff --git a/fs/ext3/xattr_security.c b/fs/ext3/xattr_security.c
index b9c40c15647..821efaf2b94 100644
--- a/fs/ext3/xattr_security.c
+++ b/fs/ext3/xattr_security.c
@@ -6,7 +6,6 @@
#include <linux/module.h>
#include <linux/string.h>
#include <linux/fs.h>
-#include <linux/smp_lock.h>
#include <linux/ext3_jbd.h>
#include <linux/ext3_fs.h>
#include <linux/security.h>
diff --git a/fs/ext3/xattr_trusted.c b/fs/ext3/xattr_trusted.c
index 86d91f1186d..0327497a55c 100644
--- a/fs/ext3/xattr_trusted.c
+++ b/fs/ext3/xattr_trusted.c
@@ -9,7 +9,6 @@
#include <linux/string.h>
#include <linux/capability.h>
#include <linux/fs.h>
-#include <linux/smp_lock.h>
#include <linux/ext3_jbd.h>
#include <linux/ext3_fs.h>
#include "xattr.h"
diff --git a/fs/ext3/xattr_user.c b/fs/ext3/xattr_user.c
index a85a0a17c4f..1abd8f92c44 100644
--- a/fs/ext3/xattr_user.c
+++ b/fs/ext3/xattr_user.c
@@ -8,7 +8,6 @@
#include <linux/module.h>
#include <linux/string.h>
#include <linux/fs.h>
-#include <linux/smp_lock.h>
#include <linux/ext3_jbd.h>
#include <linux/ext3_fs.h>
#include "xattr.h"
diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c
index 8a23483ca8d..3b64bb16c72 100644
--- a/fs/ext4/balloc.c
+++ b/fs/ext4/balloc.c
@@ -30,15 +30,15 @@
void ext4_get_group_no_and_offset(struct super_block *sb, ext4_fsblk_t blocknr,
unsigned long *blockgrpp, ext4_grpblk_t *offsetp)
{
- struct ext4_super_block *es = EXT4_SB(sb)->s_es;
+ struct ext4_super_block *es = EXT4_SB(sb)->s_es;
ext4_grpblk_t offset;
- blocknr = blocknr - le32_to_cpu(es->s_first_data_block);
+ blocknr = blocknr - le32_to_cpu(es->s_first_data_block);
offset = do_div(blocknr, EXT4_BLOCKS_PER_GROUP(sb));
if (offsetp)
*offsetp = offset;
if (blockgrpp)
- *blockgrpp = blocknr;
+ *blockgrpp = blocknr;
}
diff --git a/fs/ext4/dir.c b/fs/ext4/dir.c
index da80368b66f..e8ad06e2831 100644
--- a/fs/ext4/dir.c
+++ b/fs/ext4/dir.c
@@ -25,7 +25,6 @@
#include <linux/jbd2.h>
#include <linux/ext4_fs.h>
#include <linux/buffer_head.h>
-#include <linux/smp_lock.h>
#include <linux/slab.h>
#include <linux/rbtree.h>
diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index 7916b50f9a1..b9ce2412907 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -34,7 +34,6 @@
#include <linux/time.h>
#include <linux/ext4_jbd2.h>
#include <linux/jbd.h>
-#include <linux/smp_lock.h>
#include <linux/highuid.h>
#include <linux/pagemap.h>
#include <linux/quotaops.h>
@@ -375,7 +374,7 @@ ext4_ext_binsearch_idx(struct inode *inode, struct ext4_ext_path *path, int bloc
le32_to_cpu(ix[-1].ei_block));
}
BUG_ON(k && le32_to_cpu(ix->ei_block)
- <= le32_to_cpu(ix[-1].ei_block));
+ <= le32_to_cpu(ix[-1].ei_block));
if (block < le32_to_cpu(ix->ei_block))
break;
chix = ix;
@@ -424,8 +423,8 @@ ext4_ext_binsearch(struct inode *inode, struct ext4_ext_path *path, int block)
path->p_ext = l - 1;
ext_debug(" -> %d:%llu:%d ",
- le32_to_cpu(path->p_ext->ee_block),
- ext_pblock(path->p_ext),
+ le32_to_cpu(path->p_ext->ee_block),
+ ext_pblock(path->p_ext),
le16_to_cpu(path->p_ext->ee_len));
#ifdef CHECK_BINSEARCH
@@ -436,7 +435,7 @@ ext4_ext_binsearch(struct inode *inode, struct ext4_ext_path *path, int block)
chex = ex = EXT_FIRST_EXTENT(eh);
for (k = 0; k < le16_to_cpu(eh->eh_entries); k++, ex++) {
BUG_ON(k && le32_to_cpu(ex->ee_block)
- <= le32_to_cpu(ex[-1].ee_block));
+ <= le32_to_cpu(ex[-1].ee_block));
if (block < le32_to_cpu(ex->ee_block))
break;
chex = ex;
@@ -578,7 +577,7 @@ static int ext4_ext_insert_index(handle_t *handle, struct inode *inode,
curp->p_hdr->eh_entries = cpu_to_le16(le16_to_cpu(curp->p_hdr->eh_entries)+1);
BUG_ON(le16_to_cpu(curp->p_hdr->eh_entries)
- > le16_to_cpu(curp->p_hdr->eh_max));
+ > le16_to_cpu(curp->p_hdr->eh_max));
BUG_ON(ix > EXT_LAST_INDEX(curp->p_hdr));
err = ext4_ext_dirty(handle, inode, curp);
@@ -622,12 +621,12 @@ static int ext4_ext_split(handle_t *handle, struct inode *inode,
border = path[depth].p_ext[1].ee_block;
ext_debug("leaf will be split."
" next leaf starts at %d\n",
- le32_to_cpu(border));
+ le32_to_cpu(border));
} else {
border = newext->ee_block;
ext_debug("leaf will be added."
" next leaf starts at %d\n",
- le32_to_cpu(border));
+ le32_to_cpu(border));
}
/*
@@ -685,9 +684,9 @@ static int ext4_ext_split(handle_t *handle, struct inode *inode,
while (path[depth].p_ext <=
EXT_MAX_EXTENT(path[depth].p_hdr)) {
ext_debug("move %d:%llu:%d in new leaf %llu\n",
- le32_to_cpu(path[depth].p_ext->ee_block),
- ext_pblock(path[depth].p_ext),
- le16_to_cpu(path[depth].p_ext->ee_len),
+ le32_to_cpu(path[depth].p_ext->ee_block),
+ ext_pblock(path[depth].p_ext),
+ le16_to_cpu(path[depth].p_ext->ee_len),
newblock);
/*memmove(ex++, path[depth].p_ext++,
sizeof(struct ext4_extent));
@@ -766,9 +765,9 @@ static int ext4_ext_split(handle_t *handle, struct inode *inode,
EXT_LAST_INDEX(path[i].p_hdr));
while (path[i].p_idx <= EXT_MAX_INDEX(path[i].p_hdr)) {
ext_debug("%d: move %d:%d in new index %llu\n", i,
- le32_to_cpu(path[i].p_idx->ei_block),
- idx_pblock(path[i].p_idx),
- newblock);
+ le32_to_cpu(path[i].p_idx->ei_block),
+ idx_pblock(path[i].p_idx),
+ newblock);
/*memmove(++fidx, path[i].p_idx++,
sizeof(struct ext4_extent_idx));
neh->eh_entries++;
@@ -1129,6 +1128,55 @@ ext4_can_extents_be_merged(struct inode *inode, struct ext4_extent *ex1,
}
/*
+ * check if a portion of the "newext" extent overlaps with an
+ * existing extent.
+ *
+ * If there is an overlap discovered, it updates the length of the newext
+ * such that there will be no overlap, and then returns 1.
+ * If there is no overlap found, it returns 0.
+ */
+unsigned int ext4_ext_check_overlap(struct inode *inode,
+ struct ext4_extent *newext,
+ struct ext4_ext_path *path)
+{
+ unsigned long b1, b2;
+ unsigned int depth, len1;
+ unsigned int ret = 0;
+
+ b1 = le32_to_cpu(newext->ee_block);
+ len1 = le16_to_cpu(newext->ee_len);
+ depth = ext_depth(inode);
+ if (!path[depth].p_ext)
+ goto out;
+ b2 = le32_to_cpu(path[depth].p_ext->ee_block);
+
+ /*
+ * get the next allocated block if the extent in the path
+ * is before the requested block(s)
+ */
+ if (b2 < b1) {
+ b2 = ext4_ext_next_allocated_block(path);
+ if (b2 == EXT_MAX_BLOCK)
+ goto out;
+ }
+
+ /* check for wrap through zero */
+ if (b1 + len1 < b1) {
+ len1 = EXT_MAX_BLOCK - b1;
+ newext->ee_len = cpu_to_le16(len1);
+ ret = 1;
+ }
+
+ /* check for overlap */
+ if (b1 + len1 > b2) {
+ newext->ee_len = cpu_to_le16(b2 - b1);
+ ret = 1;
+ }
+out:
+ return ret;
+}
+
+/*
* ext4_ext_insert_extent:
* tries to merge requsted extent into the existing extent or
* inserts requested extent as new one into the tree,
@@ -1213,12 +1261,12 @@ has_space:
if (!nearex) {
/* there is no extent in this leaf, create first one */
ext_debug("first extent in the leaf: %d:%llu:%d\n",
- le32_to_cpu(newext->ee_block),
- ext_pblock(newext),
- le16_to_cpu(newext->ee_len));
+ le32_to_cpu(newext->ee_block),
+ ext_pblock(newext),
+ le16_to_cpu(newext->ee_len));
path[depth].p_ext = EXT_FIRST_EXTENT(eh);
} else if (le32_to_cpu(newext->ee_block)
- > le32_to_cpu(nearex->ee_block)) {
+ > le32_to_cpu(nearex->ee_block)) {
/* BUG_ON(newext->ee_block == nearex->ee_block); */
if (nearex != EXT_LAST_EXTENT(eh)) {
len = EXT_MAX_EXTENT(eh) - nearex;
@@ -1226,9 +1274,9 @@ has_space:
len = len < 0 ? 0 : len;
ext_debug("insert %d:%llu:%d after: nearest 0x%p, "
"move %d from 0x%p to 0x%p\n",
- le32_to_cpu(newext->ee_block),
- ext_pblock(newext),
- le16_to_cpu(newext->ee_len),
+ le32_to_cpu(newext->ee_block),
+ ext_pblock(newext),
+ le16_to_cpu(newext->ee_len),
nearex, len, nearex + 1, nearex + 2);
memmove(nearex + 2, nearex + 1, len);
}
@@ -1359,9 +1407,9 @@ int ext4_ext_walk_space(struct inode *inode, unsigned long block,
cbex.ec_start = 0;
cbex.ec_type = EXT4_EXT_CACHE_GAP;
} else {
- cbex.ec_block = le32_to_cpu(ex->ee_block);
- cbex.ec_len = le16_to_cpu(ex->ee_len);
- cbex.ec_start = ext_pblock(ex);
+ cbex.ec_block = le32_to_cpu(ex->ee_block);
+ cbex.ec_len = le16_to_cpu(ex->ee_len);
+ cbex.ec_start = ext_pblock(ex);
cbex.ec_type = EXT4_EXT_CACHE_EXTENT;
}
@@ -1432,16 +1480,16 @@ ext4_ext_put_gap_in_cache(struct inode *inode, struct ext4_ext_path *path,
len = le32_to_cpu(ex->ee_block) - block;
ext_debug("cache gap(before): %lu [%lu:%lu]",
(unsigned long) block,
- (unsigned long) le32_to_cpu(ex->ee_block),
- (unsigned long) le16_to_cpu(ex->ee_len));
+ (unsigned long) le32_to_cpu(ex->ee_block),
+ (unsigned long) le16_to_cpu(ex->ee_len));
} else if (block >= le32_to_cpu(ex->ee_block)
- + le16_to_cpu(ex->ee_len)) {
- lblock = le32_to_cpu(ex->ee_block)
- + le16_to_cpu(ex->ee_len);
+ + le16_to_cpu(ex->ee_len)) {
+ lblock = le32_to_cpu(ex->ee_block)
+ + le16_to_cpu(ex->ee_len);
len = ext4_ext_next_allocated_block(path);
ext_debug("cache gap(after): [%lu:%lu] %lu",
- (unsigned long) le32_to_cpu(ex->ee_block),
- (unsigned long) le16_to_cpu(ex->ee_len),
+ (unsigned long) le32_to_cpu(ex->ee_block),
+ (unsigned long) le16_to_cpu(ex->ee_len),
(unsigned long) block);
BUG_ON(len == lblock);
len = len - lblock;
@@ -1469,9 +1517,9 @@ ext4_ext_in_cache(struct inode *inode, unsigned long block,
BUG_ON(cex->ec_type != EXT4_EXT_CACHE_GAP &&
cex->ec_type != EXT4_EXT_CACHE_EXTENT);
if (block >= cex->ec_block && block < cex->ec_block + cex->ec_len) {
- ex->ee_block = cpu_to_le32(cex->ec_block);
+ ex->ee_block = cpu_to_le32(cex->ec_block);
ext4_ext_store_pblock(ex, cex->ec_start);
- ex->ee_len = cpu_to_le16(cex->ec_len);
+ ex->ee_len = cpu_to_le16(cex->ec_len);
ext_debug("%lu cached by %lu:%lu:%llu\n",
(unsigned long) block,
(unsigned long) cex->ec_block,
@@ -1957,9 +2005,9 @@ int ext4_ext_get_blocks(handle_t *handle, struct inode *inode,
/* we should allocate requested block */
} else if (goal == EXT4_EXT_CACHE_EXTENT) {
/* block is already allocated */
- newblock = iblock
- - le32_to_cpu(newex.ee_block)
- + ext_pblock(&newex);
+ newblock = iblock
+ - le32_to_cpu(newex.ee_block)
+ + ext_pblock(&newex);
/* number of remaining blocks in the extent */
allocated = le16_to_cpu(newex.ee_len) -
(iblock - le32_to_cpu(newex.ee_block));
@@ -1988,7 +2036,7 @@ int ext4_ext_get_blocks(handle_t *handle, struct inode *inode,
ex = path[depth].p_ext;
if (ex) {
- unsigned long ee_block = le32_to_cpu(ex->ee_block);
+ unsigned long ee_block = le32_to_cpu(ex->ee_block);
ext4_fsblk_t ee_start = ext_pblock(ex);
unsigned short ee_len = le16_to_cpu(ex->ee_len);
@@ -2001,7 +2049,7 @@ int ext4_ext_get_blocks(handle_t *handle, struct inode *inode,
if (ee_len > EXT_MAX_LEN)
goto out2;
/* if found extent covers block, simply return it */
- if (iblock >= ee_block && iblock < ee_block + ee_len) {
+ if (iblock >= ee_block && iblock < ee_block + ee_len) {
newblock = iblock - ee_block + ee_start;
/* number of remaining blocks in the extent */
allocated = ee_len - (iblock - ee_block);
@@ -2032,7 +2080,15 @@ int ext4_ext_get_blocks(handle_t *handle, struct inode *inode,
/* allocate new block */
goal = ext4_ext_find_goal(inode, path, iblock);
- allocated = max_blocks;
+
+ /* Check if we can really insert (iblock)::(iblock+max_blocks) extent */
+ newex.ee_block = cpu_to_le32(iblock);
+ newex.ee_len = cpu_to_le16(max_blocks);
+ err = ext4_ext_check_overlap(inode, &newex, path);
+ if (err)
+ allocated = le16_to_cpu(newex.ee_len);
+ else
+ allocated = max_blocks;
newblock = ext4_new_blocks(handle, inode, goal, &allocated, &err);
if (!newblock)
goto out2;
@@ -2040,12 +2096,15 @@ int ext4_ext_get_blocks(handle_t *handle, struct inode *inode,
goal, newblock, allocated);
/* try to insert new extent into found leaf and return */
- newex.ee_block = cpu_to_le32(iblock);
ext4_ext_store_pblock(&newex, newblock);
newex.ee_len = cpu_to_le16(allocated);
err = ext4_ext_insert_extent(handle, inode, path, &newex);
- if (err)
+ if (err) {
+ /* free data blocks we just allocated */
+ ext4_free_blocks(handle, inode, ext_pblock(&newex),
+ le16_to_cpu(newex.ee_len));
goto out2;
+ }
if (extend_disksize && inode->i_size > EXT4_I(inode)->i_disksize)
EXT4_I(inode)->i_disksize = inode->i_size;
@@ -2158,11 +2217,3 @@ int ext4_ext_writepage_trans_blocks(struct inode *inode, int num)
return needed;
}
-
-EXPORT_SYMBOL(ext4_mark_inode_dirty);
-EXPORT_SYMBOL(ext4_ext_invalidate_cache);
-EXPORT_SYMBOL(ext4_ext_insert_extent);
-EXPORT_SYMBOL(ext4_ext_walk_space);
-EXPORT_SYMBOL(ext4_ext_find_goal);
-EXPORT_SYMBOL(ext4_ext_calc_credits_for_insert);
-
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 810b6d6474b..8416fa28c42 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -27,7 +27,6 @@
#include <linux/time.h>
#include <linux/ext4_jbd2.h>
#include <linux/jbd2.h>
-#include <linux/smp_lock.h>
#include <linux/highuid.h>
#include <linux/pagemap.h>
#include <linux/quotaops.h>
@@ -256,8 +255,8 @@ static int verify_chain(Indirect *from, Indirect *to)
* @inode: inode in question (we are only interested in its superblock)
* @i_block: block number to be parsed
* @offsets: array to store the offsets in
- * @boundary: set this non-zero if the referred-to block is likely to be
- * followed (on disk) by an indirect block.
+ * @boundary: set this non-zero if the referred-to block is likely to be
+ * followed (on disk) by an indirect block.
*
* To store the locations of file's data ext4 uses a data structure common
* for UNIX filesystems - tree of pointers anchored in the inode, with
@@ -2611,9 +2610,9 @@ void ext4_read_inode(struct inode * inode)
}
inode->i_nlink = le16_to_cpu(raw_inode->i_links_count);
inode->i_size = le32_to_cpu(raw_inode->i_size);
- inode->i_atime.tv_sec = le32_to_cpu(raw_inode->i_atime);
- inode->i_ctime.tv_sec = le32_to_cpu(raw_inode->i_ctime);
- inode->i_mtime.tv_sec = le32_to_cpu(raw_inode->i_mtime);
+ inode->i_atime.tv_sec = (signed)le32_to_cpu(raw_inode->i_atime);
+ inode->i_ctime.tv_sec = (signed)le32_to_cpu(raw_inode->i_ctime);
+ inode->i_mtime.tv_sec = (signed)le32_to_cpu(raw_inode->i_mtime);
inode->i_atime.tv_nsec = inode->i_ctime.tv_nsec = inode->i_mtime.tv_nsec = 0;
ei->i_state = 0;
@@ -2674,8 +2673,10 @@ void ext4_read_inode(struct inode * inode)
*/
ei->i_extra_isize = le16_to_cpu(raw_inode->i_extra_isize);
if (EXT4_GOOD_OLD_INODE_SIZE + ei->i_extra_isize >
- EXT4_INODE_SIZE(inode->i_sb))
+ EXT4_INODE_SIZE(inode->i_sb)) {
+ brelse (bh);
goto bad_inode;
+ }
if (ei->i_extra_isize == 0) {
/* The extra space is currently unused. Use it. */
ei->i_extra_isize = sizeof(struct ext4_inode) -
diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c
index e7e1d79a7d7..2811e5720ad 100644
--- a/fs/ext4/namei.c
+++ b/fs/ext4/namei.c
@@ -36,7 +36,6 @@
#include <linux/quotaops.h>
#include <linux/buffer_head.h>
#include <linux/bio.h>
-#include <linux/smp_lock.h>
#include "namei.h"
#include "xattr.h"
@@ -47,7 +46,7 @@
*/
#define NAMEI_RA_CHUNKS 2
#define NAMEI_RA_BLOCKS 4
-#define NAMEI_RA_SIZE (NAMEI_RA_CHUNKS * NAMEI_RA_BLOCKS)
+#define NAMEI_RA_SIZE (NAMEI_RA_CHUNKS * NAMEI_RA_BLOCKS)
#define NAMEI_RA_INDEX(c,b) (((c) * NAMEI_RA_BLOCKS) + (b))
static struct buffer_head *ext4_append(handle_t *handle,
@@ -242,7 +241,7 @@ static inline unsigned dx_node_limit (struct inode *dir)
static void dx_show_index (char * label, struct dx_entry *entries)
{
int i, n = dx_get_count (entries);
- printk("%s index ", label);
+ printk("%s index ", label);
for (i = 0; i < n; i++) {
printk("%x->%u ", i? dx_get_hash(entries + i) :
0, dx_get_block(entries + i));
@@ -967,6 +966,7 @@ static struct buffer_head * ext4_dx_find_entry(struct dentry *dentry,
(block<<EXT4_BLOCK_SIZE_BITS(sb))
+((char *)de - bh->b_data))) {
brelse (bh);
+ *err = ERR_BAD_DX_DIR;
goto errout;
}
*res_dir = de;
@@ -1132,9 +1132,9 @@ static struct ext4_dir_entry_2 *do_split(handle_t *handle, struct inode *dir,
char *data1 = (*bh)->b_data, *data2;
unsigned split;
struct ext4_dir_entry_2 *de = NULL, *de2;
- int err;
+ int err = 0;
- bh2 = ext4_append (handle, dir, &newblock, error);
+ bh2 = ext4_append (handle, dir, &newblock, &err);
if (!(bh2)) {
brelse(*bh);
*bh = NULL;
@@ -1143,14 +1143,9 @@ static struct ext4_dir_entry_2 *do_split(handle_t *handle, struct inode *dir,
BUFFER_TRACE(*bh, "get_write_access");
err = ext4_journal_get_write_access(handle, *bh);
- if (err) {
- journal_error:
- brelse(*bh);
- brelse(bh2);
- *bh = NULL;
- ext4_std_error(dir->i_sb, err);
- goto errout;
- }
+ if (err)
+ goto journal_error;
+
BUFFER_TRACE(frame->bh, "get_write_access");
err = ext4_journal_get_write_access(handle, frame->bh);
if (err)
@@ -1193,8 +1188,16 @@ static struct ext4_dir_entry_2 *do_split(handle_t *handle, struct inode *dir,
goto journal_error;
brelse (bh2);
dxtrace(dx_show_index ("frame", frame->entries));
-errout:
return de;
+
+journal_error:
+ brelse(*bh);
+ brelse(bh2);
+ *bh = NULL;
+ ext4_std_error(dir->i_sb, err);
+errout:
+ *error = err;
+ return NULL;
}
#endif
diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c
index ea99f6c97f5..aa11d7dbe97 100644
--- a/fs/ext4/resize.c
+++ b/fs/ext4/resize.c
@@ -11,7 +11,6 @@
#define EXT4FS_DEBUG
-#include <linux/smp_lock.h>
#include <linux/ext4_jbd2.h>
#include <linux/errno.h>
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 71912693235..175b68c6096 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -517,14 +517,12 @@ static void init_once(void * foo, struct kmem_cache * cachep, unsigned long flag
{
struct ext4_inode_info *ei = (struct ext4_inode_info *) foo;
- if (flags & SLAB_CTOR_CONSTRUCTOR) {
- INIT_LIST_HEAD(&ei->i_orphan);
+ INIT_LIST_HEAD(&ei->i_orphan);
#ifdef CONFIG_EXT4DEV_FS_XATTR
- init_rwsem(&ei->xattr_sem);
+ init_rwsem(&ei->xattr_sem);
#endif
- mutex_init(&ei->truncate_mutex);
- inode_init_once(&ei->vfs_inode);
- }
+ mutex_init(&ei->truncate_mutex);
+ inode_init_once(&ei->vfs_inode);
}
static int init_inodecache(void)
@@ -1987,7 +1985,7 @@ static journal_t *ext4_get_dev_journal(struct super_block *sb,
if (bd_claim(bdev, sb)) {
printk(KERN_ERR
- "EXT4: failed to claim external journal device.\n");
+ "EXT4: failed to claim external journal device.\n");
blkdev_put(bdev);
return NULL;
}
diff --git a/fs/ext4/xattr_security.c b/fs/ext4/xattr_security.c
index b6a6861951f..f17eaf2321b 100644
--- a/fs/ext4/xattr_security.c
+++ b/fs/ext4/xattr_security.c
@@ -6,7 +6,6 @@
#include <linux/module.h>
#include <linux/string.h>
#include <linux/fs.h>
-#include <linux/smp_lock.h>
#include <linux/ext4_jbd2.h>
#include <linux/ext4_fs.h>
#include <linux/security.h>
diff --git a/fs/ext4/xattr_trusted.c b/fs/ext4/xattr_trusted.c
index b76f2dbc82d..e0f05acdafe 100644
--- a/fs/ext4/xattr_trusted.c
+++ b/fs/ext4/xattr_trusted.c
@@ -9,7 +9,6 @@
#include <linux/string.h>
#include <linux/capability.h>
#include <linux/fs.h>
-#include <linux/smp_lock.h>
#include <linux/ext4_jbd2.h>
#include <linux/ext4_fs.h>
#include "xattr.h"
diff --git a/fs/ext4/xattr_user.c b/fs/ext4/xattr_user.c
index c53cded0761..7ed3d8ebf09 100644
--- a/fs/ext4/xattr_user.c
+++ b/fs/ext4/xattr_user.c
@@ -8,7 +8,6 @@
#include <linux/module.h>
#include <linux/string.h>
#include <linux/fs.h>
-#include <linux/smp_lock.h>
#include <linux/ext4_jbd2.h>
#include <linux/ext4_fs.h>
#include "xattr.h"
diff --git a/fs/fat/cache.c b/fs/fat/cache.c
index 1959143c1d2..3c9c8a15ec7 100644
--- a/fs/fat/cache.c
+++ b/fs/fat/cache.c
@@ -40,8 +40,7 @@ static void init_once(void *foo, struct kmem_cache *cachep, unsigned long flags)
{
struct fat_cache *cache = (struct fat_cache *)foo;
- if (flags & SLAB_CTOR_CONSTRUCTOR)
- INIT_LIST_HEAD(&cache->cache_list);
+ INIT_LIST_HEAD(&cache->cache_list);
}
int __init fat_cache_init(void)
diff --git a/fs/fat/dir.c b/fs/fat/dir.c
index c16af246d24..ccf161dffb6 100644
--- a/fs/fat/dir.c
+++ b/fs/fat/dir.c
@@ -422,7 +422,7 @@ EODir:
EXPORT_SYMBOL_GPL(fat_search_long);
struct fat_ioctl_filldir_callback {
- struct dirent __user *dirent;
+ void __user *dirent;
int result;
/* for dir ioctl */
const char *longname;
@@ -647,62 +647,85 @@ static int fat_readdir(struct file *filp, void *dirent, filldir_t filldir)
return __fat_readdir(inode, filp, dirent, filldir, 0, 0);
}
-static int fat_ioctl_filldir(void *__buf, const char *name, int name_len,
- loff_t offset, u64 ino, unsigned int d_type)
+#define FAT_IOCTL_FILLDIR_FUNC(func, dirent_type) \
+static int func(void *__buf, const char *name, int name_len, \
+ loff_t offset, u64 ino, unsigned int d_type) \
+{ \
+ struct fat_ioctl_filldir_callback *buf = __buf; \
+ struct dirent_type __user *d1 = buf->dirent; \
+ struct dirent_type __user *d2 = d1 + 1; \
+ \
+ if (buf->result) \
+ return -EINVAL; \
+ buf->result++; \
+ \
+ if (name != NULL) { \
+ /* dirent has only short name */ \
+ if (name_len >= sizeof(d1->d_name)) \
+ name_len = sizeof(d1->d_name) - 1; \
+ \
+ if (put_user(0, d2->d_name) || \
+ put_user(0, &d2->d_reclen) || \
+ copy_to_user(d1->d_name, name, name_len) || \
+ put_user(0, d1->d_name + name_len) || \
+ put_user(name_len, &d1->d_reclen)) \
+ goto efault; \
+ } else { \
+ /* dirent has short and long name */ \
+ const char *longname = buf->longname; \
+ int long_len = buf->long_len; \
+ const char *shortname = buf->shortname; \
+ int short_len = buf->short_len; \
+ \
+ if (long_len >= sizeof(d1->d_name)) \
+ long_len = sizeof(d1->d_name) - 1; \
+ if (short_len >= sizeof(d1->d_name)) \
+ short_len = sizeof(d1->d_name) - 1; \
+ \
+ if (copy_to_user(d2->d_name, longname, long_len) || \
+ put_user(0, d2->d_name + long_len) || \
+ put_user(long_len, &d2->d_reclen) || \
+ put_user(ino, &d2->d_ino) || \
+ put_user(offset, &d2->d_off) || \
+ copy_to_user(d1->d_name, shortname, short_len) || \
+ put_user(0, d1->d_name + short_len) || \
+ put_user(short_len, &d1->d_reclen)) \
+ goto efault; \
+ } \
+ return 0; \
+efault: \
+ buf->result = -EFAULT; \
+ return -EFAULT; \
+}
+
+FAT_IOCTL_FILLDIR_FUNC(fat_ioctl_filldir, dirent)
+
+static int fat_ioctl_readdir(struct inode *inode, struct file *filp,
+ void __user *dirent, filldir_t filldir,
+ int short_only, int both)
{
- struct fat_ioctl_filldir_callback *buf = __buf;
- struct dirent __user *d1 = buf->dirent;
- struct dirent __user *d2 = d1 + 1;
-
- if (buf->result)
- return -EINVAL;
- buf->result++;
-
- if (name != NULL) {
- /* dirent has only short name */
- if (name_len >= sizeof(d1->d_name))
- name_len = sizeof(d1->d_name) - 1;
-
- if (put_user(0, d2->d_name) ||
- put_user(0, &d2->d_reclen) ||
- copy_to_user(d1->d_name, name, name_len) ||
- put_user(0, d1->d_name + name_len) ||
- put_user(name_len, &d1->d_reclen))
- goto efault;
- } else {
- /* dirent has short and long name */
- const char *longname = buf->longname;
- int long_len = buf->long_len;
- const char *shortname = buf->shortname;
- int short_len = buf->short_len;
-
- if (long_len >= sizeof(d1->d_name))
- long_len = sizeof(d1->d_name) - 1;
- if (short_len >= sizeof(d1->d_name))
- short_len = sizeof(d1->d_name) - 1;
-
- if (copy_to_user(d2->d_name, longname, long_len) ||
- put_user(0, d2->d_name + long_len) ||
- put_user(long_len, &d2->d_reclen) ||
- put_user(ino, &d2->d_ino) ||
- put_user(offset, &d2->d_off) ||
- copy_to_user(d1->d_name, shortname, short_len) ||
- put_user(0, d1->d_name + short_len) ||
- put_user(short_len, &d1->d_reclen))
- goto efault;
+ struct fat_ioctl_filldir_callback buf;
+ int ret;
+
+ buf.dirent = dirent;
+ buf.result = 0;
+ mutex_lock(&inode->i_mutex);
+ ret = -ENOENT;
+ if (!IS_DEADDIR(inode)) {
+ ret = __fat_readdir(inode, filp, &buf, filldir,
+ short_only, both);
}
- return 0;
-efault:
- buf->result = -EFAULT;
- return -EFAULT;
+ mutex_unlock(&inode->i_mutex);
+ if (ret >= 0)
+ ret = buf.result;
+ return ret;
}
-static int fat_dir_ioctl(struct inode * inode, struct file * filp,
- unsigned int cmd, unsigned long arg)
+static int fat_dir_ioctl(struct inode *inode, struct file *filp,
+ unsigned int cmd, unsigned long arg)
{
- struct fat_ioctl_filldir_callback buf;
- struct dirent __user *d1;
- int ret, short_only, both;
+ struct dirent __user *d1 = (struct dirent __user *)arg;
+ int short_only, both;
switch (cmd) {
case VFAT_IOCTL_READDIR_SHORT:
@@ -717,7 +740,6 @@ static int fat_dir_ioctl(struct inode * inode, struct file * filp,
return fat_generic_ioctl(inode, filp, cmd, arg);
}
- d1 = (struct dirent __user *)arg;
if (!access_ok(VERIFY_WRITE, d1, sizeof(struct dirent[2])))
return -EFAULT;
/*
@@ -728,69 +750,48 @@ static int fat_dir_ioctl(struct inode * inode, struct file * filp,
if (put_user(0, &d1->d_reclen))
return -EFAULT;
- buf.dirent = d1;
- buf.result = 0;
- mutex_lock(&inode->i_mutex);
- ret = -ENOENT;
- if (!IS_DEADDIR(inode)) {
- ret = __fat_readdir(inode, filp, &buf, fat_ioctl_filldir,
- short_only, both);
- }
- mutex_unlock(&inode->i_mutex);
- if (ret >= 0)
- ret = buf.result;
- return ret;
+ return fat_ioctl_readdir(inode, filp, d1, fat_ioctl_filldir,
+ short_only, both);
}
#ifdef CONFIG_COMPAT
#define VFAT_IOCTL_READDIR_BOTH32 _IOR('r', 1, struct compat_dirent[2])
#define VFAT_IOCTL_READDIR_SHORT32 _IOR('r', 2, struct compat_dirent[2])
-static long fat_compat_put_dirent32(struct dirent *d,
- struct compat_dirent __user *d32)
-{
- if (!access_ok(VERIFY_WRITE, d32, sizeof(struct compat_dirent)))
- return -EFAULT;
-
- __put_user(d->d_ino, &d32->d_ino);
- __put_user(d->d_off, &d32->d_off);
- __put_user(d->d_reclen, &d32->d_reclen);
- if (__copy_to_user(d32->d_name, d->d_name, d->d_reclen))
- return -EFAULT;
+FAT_IOCTL_FILLDIR_FUNC(fat_compat_ioctl_filldir, compat_dirent)
- return 0;
-}
-
-static long fat_compat_dir_ioctl(struct file *file, unsigned cmd,
+static long fat_compat_dir_ioctl(struct file *filp, unsigned cmd,
unsigned long arg)
{
- struct compat_dirent __user *p = compat_ptr(arg);
- int ret;
- mm_segment_t oldfs = get_fs();
- struct dirent d[2];
+ struct inode *inode = filp->f_path.dentry->d_inode;
+ struct compat_dirent __user *d1 = compat_ptr(arg);
+ int short_only, both;
switch (cmd) {
- case VFAT_IOCTL_READDIR_BOTH32:
- cmd = VFAT_IOCTL_READDIR_BOTH;
- break;
case VFAT_IOCTL_READDIR_SHORT32:
- cmd = VFAT_IOCTL_READDIR_SHORT;
+ short_only = 1;
+ both = 0;
+ break;
+ case VFAT_IOCTL_READDIR_BOTH32:
+ short_only = 0;
+ both = 1;
break;
default:
return -ENOIOCTLCMD;
}
- set_fs(KERNEL_DS);
- lock_kernel();
- ret = fat_dir_ioctl(file->f_path.dentry->d_inode, file,
- cmd, (unsigned long) &d);
- unlock_kernel();
- set_fs(oldfs);
- if (ret >= 0) {
- ret |= fat_compat_put_dirent32(&d[0], p);
- ret |= fat_compat_put_dirent32(&d[1], p + 1);
- }
- return ret;
+ if (!access_ok(VERIFY_WRITE, d1, sizeof(struct compat_dirent[2])))
+ return -EFAULT;
+ /*
+ * Yes, we don't need this put_user() absolutely. However old
+ * code didn't return the right value. So, app use this value,
+ * in order to check whether it is EOF.
+ */
+ if (put_user(0, &d1->d_reclen))
+ return -EFAULT;
+
+ return fat_ioctl_readdir(inode, filp, d1, fat_compat_ioctl_filldir,
+ short_only, both);
}
#endif /* CONFIG_COMPAT */
diff --git a/fs/fat/inode.c b/fs/fat/inode.c
index 65cb54bde48..479722d8966 100644
--- a/fs/fat/inode.c
+++ b/fs/fat/inode.c
@@ -25,6 +25,7 @@
#include <linux/parser.h>
#include <linux/uio.h>
#include <linux/writeback.h>
+#include <linux/log2.h>
#include <asm/unaligned.h>
#ifndef CONFIG_FAT_DEFAULT_IOCHARSET
@@ -499,14 +500,12 @@ static void init_once(void * foo, struct kmem_cache * cachep, unsigned long flag
{
struct msdos_inode_info *ei = (struct msdos_inode_info *)foo;
- if (flags & SLAB_CTOR_CONSTRUCTOR) {
- spin_lock_init(&ei->cache_lru_lock);
- ei->nr_caches = 0;
- ei->cache_valid_id = FAT_CACHE_VALID + 1;
- INIT_LIST_HEAD(&ei->cache_lru);
- INIT_HLIST_NODE(&ei->i_fat_hash);
- inode_init_once(&ei->vfs_inode);
- }
+ spin_lock_init(&ei->cache_lru_lock);
+ ei->nr_caches = 0;
+ ei->cache_valid_id = FAT_CACHE_VALID + 1;
+ INIT_LIST_HEAD(&ei->cache_lru);
+ INIT_HLIST_NODE(&ei->i_fat_hash);
+ inode_init_once(&ei->vfs_inode);
}
static int __init fat_init_inodecache(void)
@@ -824,6 +823,8 @@ static int fat_show_options(struct seq_file *m, struct vfsmount *mnt)
}
if (opts->name_check != 'n')
seq_printf(m, ",check=%c", opts->name_check);
+ if (opts->usefree)
+ seq_puts(m, ",usefree");
if (opts->quiet)
seq_puts(m, ",quiet");
if (opts->showexec)
@@ -849,7 +850,7 @@ static int fat_show_options(struct seq_file *m, struct vfsmount *mnt)
enum {
Opt_check_n, Opt_check_r, Opt_check_s, Opt_uid, Opt_gid,
- Opt_umask, Opt_dmask, Opt_fmask, Opt_codepage, Opt_nocase,
+ Opt_umask, Opt_dmask, Opt_fmask, Opt_codepage, Opt_usefree, Opt_nocase,
Opt_quiet, Opt_showexec, Opt_debug, Opt_immutable,
Opt_dots, Opt_nodots,
Opt_charset, Opt_shortname_lower, Opt_shortname_win95,
@@ -871,6 +872,7 @@ static match_table_t fat_tokens = {
{Opt_dmask, "dmask=%o"},
{Opt_fmask, "fmask=%o"},
{Opt_codepage, "codepage=%u"},
+ {Opt_usefree, "usefree"},
{Opt_nocase, "nocase"},
{Opt_quiet, "quiet"},
{Opt_showexec, "showexec"},
@@ -950,7 +952,7 @@ static int parse_options(char *options, int is_vfat, int silent, int *debug,
opts->quiet = opts->showexec = opts->sys_immutable = opts->dotsOK = 0;
opts->utf8 = opts->unicode_xlate = 0;
opts->numtail = 1;
- opts->nocase = 0;
+ opts->usefree = opts->nocase = 0;
*debug = 0;
if (!options)
@@ -978,6 +980,9 @@ static int parse_options(char *options, int is_vfat, int silent, int *debug,
case Opt_check_n:
opts->name_check = 'n';
break;
+ case Opt_usefree:
+ opts->usefree = 1;
+ break;
case Opt_nocase:
if (!is_vfat)
opts->nocase = 1;
@@ -1217,8 +1222,7 @@ int fat_fill_super(struct super_block *sb, void *data, int silent,
}
logical_sector_size =
le16_to_cpu(get_unaligned((__le16 *)&b->sector_size));
- if (!logical_sector_size
- || (logical_sector_size & (logical_sector_size - 1))
+ if (!is_power_of_2(logical_sector_size)
|| (logical_sector_size < 512)
|| (PAGE_CACHE_SIZE < logical_sector_size)) {
if (!silent)
@@ -1228,8 +1232,7 @@ int fat_fill_super(struct super_block *sb, void *data, int silent,
goto out_invalid;
}
sbi->sec_per_clus = b->sec_per_clus;
- if (!sbi->sec_per_clus
- || (sbi->sec_per_clus & (sbi->sec_per_clus - 1))) {
+ if (!is_power_of_2(sbi->sec_per_clus)) {
if (!silent)
printk(KERN_ERR "FAT: bogus sectors per cluster %u\n",
sbi->sec_per_clus);
@@ -1305,7 +1308,9 @@ int fat_fill_super(struct super_block *sb, void *data, int silent,
le32_to_cpu(fsinfo->signature2),
sbi->fsinfo_sector);
} else {
- sbi->free_clusters = le32_to_cpu(fsinfo->free_clusters);
+ if (sbi->options.usefree)
+ sbi->free_clusters =
+ le32_to_cpu(fsinfo->free_clusters);
sbi->prev_free = le32_to_cpu(fsinfo->next_cluster);
}
diff --git a/fs/fifo.c b/fs/fifo.c
index 49035b174b4..9785e36f81e 100644
--- a/fs/fifo.c
+++ b/fs/fifo.c
@@ -11,8 +11,8 @@
#include <linux/mm.h>
#include <linux/slab.h>
-#include <linux/smp_lock.h>
#include <linux/fs.h>
+#include <linux/sched.h>
#include <linux/pipe_fs_i.h>
static void wait_for_partner(struct inode* inode, unsigned int *cnt)
diff --git a/fs/file_table.c b/fs/file_table.c
index 4c17a18d8c1..d17fd691b83 100644
--- a/fs/file_table.c
+++ b/fs/file_table.c
@@ -10,7 +10,6 @@
#include <linux/file.h>
#include <linux/init.h>
#include <linux/module.h>
-#include <linux/smp_lock.h>
#include <linux/fs.h>
#include <linux/security.h>
#include <linux/eventpoll.h>
diff --git a/fs/filesystems.c b/fs/filesystems.c
index 7a4f61aa05f..f37f8726283 100644
--- a/fs/filesystems.c
+++ b/fs/filesystems.c
@@ -41,11 +41,12 @@ void put_filesystem(struct file_system_type *fs)
module_put(fs->owner);
}
-static struct file_system_type **find_filesystem(const char *name)
+static struct file_system_type **find_filesystem(const char *name, unsigned len)
{
struct file_system_type **p;
for (p=&file_systems; *p; p=&(*p)->next)
- if (strcmp((*p)->name,name) == 0)
+ if (strlen((*p)->name) == len &&
+ strncmp((*p)->name, name, len) == 0)
break;
return p;
}
@@ -68,11 +69,12 @@ int register_filesystem(struct file_system_type * fs)
int res = 0;
struct file_system_type ** p;
+ BUG_ON(strchr(fs->name, '.'));
if (fs->next)
return -EBUSY;
INIT_LIST_HEAD(&fs->fs_supers);
write_lock(&file_systems_lock);
- p = find_filesystem(fs->name);
+ p = find_filesystem(fs->name, strlen(fs->name));
if (*p)
res = -EBUSY;
else
@@ -215,19 +217,26 @@ int get_filesystem_list(char * buf)
struct file_system_type *get_fs_type(const char *name)
{
struct file_system_type *fs;
+ const char *dot = strchr(name, '.');
+ unsigned len = dot ? dot - name : strlen(name);
read_lock(&file_systems_lock);
- fs = *(find_filesystem(name));
+ fs = *(find_filesystem(name, len));
if (fs && !try_module_get(fs->owner))
fs = NULL;
read_unlock(&file_systems_lock);
- if (!fs && (request_module("%s", name) == 0)) {
+ if (!fs && (request_module("%.*s", len, name) == 0)) {
read_lock(&file_systems_lock);
- fs = *(find_filesystem(name));
+ fs = *(find_filesystem(name, len));
if (fs && !try_module_get(fs->owner))
fs = NULL;
read_unlock(&file_systems_lock);
}
+
+ if (dot && fs && !(fs->fs_flags & FS_HAS_SUBTYPE)) {
+ put_filesystem(fs);
+ fs = NULL;
+ }
return fs;
}
diff --git a/fs/freevxfs/vxfs_bmap.c b/fs/freevxfs/vxfs_bmap.c
index 2d71128bd8d..f86fd3cacd5 100644
--- a/fs/freevxfs/vxfs_bmap.c
+++ b/fs/freevxfs/vxfs_bmap.c
@@ -137,7 +137,7 @@ vxfs_bmap_indir(struct inode *ip, long indir, int size, long block)
bp = sb_bread(ip->i_sb,
indir + (i / VXFS_TYPED_PER_BLOCK(ip->i_sb)));
- if (!buffer_mapped(bp))
+ if (!bp || !buffer_mapped(bp))
return 0;
typ = ((struct vxfs_typed *)bp->b_data) +
diff --git a/fs/freevxfs/vxfs_inode.c b/fs/freevxfs/vxfs_inode.c
index 098a915fd9a..d1f7c5b5b3c 100644
--- a/fs/freevxfs/vxfs_inode.c
+++ b/fs/freevxfs/vxfs_inode.c
@@ -99,7 +99,7 @@ vxfs_blkiget(struct super_block *sbp, u_long extent, ino_t ino)
offset = ((ino % (sbp->s_blocksize / VXFS_ISIZE)) * VXFS_ISIZE);
bp = sb_bread(sbp, block);
- if (buffer_mapped(bp)) {
+ if (bp && buffer_mapped(bp)) {
struct vxfs_inode_info *vip;
struct vxfs_dinode *dip;
diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c
index 8890eba1db5..bd5a772d8cc 100644
--- a/fs/fuse/dir.c
+++ b/fs/fuse/dir.c
@@ -485,7 +485,7 @@ static int fuse_mknod(struct inode *dir, struct dentry *entry, int mode,
static int fuse_create(struct inode *dir, struct dentry *entry, int mode,
struct nameidata *nd)
{
- if (nd && (nd->flags & LOOKUP_CREATE)) {
+ if (nd && (nd->flags & LOOKUP_OPEN)) {
int err = fuse_create_open(dir, entry, mode, nd);
if (err != -ENOSYS)
return err;
diff --git a/fs/fuse/file.c b/fs/fuse/file.c
index acfad65a6e8..adf7995232b 100644
--- a/fs/fuse/file.c
+++ b/fs/fuse/file.c
@@ -11,6 +11,7 @@
#include <linux/pagemap.h>
#include <linux/slab.h>
#include <linux/kernel.h>
+#include <linux/sched.h>
static const struct file_operations fuse_direct_io_file_operations;
@@ -609,7 +610,9 @@ static ssize_t fuse_direct_write(struct file *file, const char __user *buf,
ssize_t res;
/* Don't allow parallel writes to the same file */
mutex_lock(&inode->i_mutex);
- res = fuse_direct_io(file, buf, count, ppos, 1);
+ res = generic_write_checks(file, ppos, &count, 0);
+ if (!res)
+ res = fuse_direct_io(file, buf, count, ppos, 1);
mutex_unlock(&inode->i_mutex);
return res;
}
diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c
index d8003be56e0..cc5efc13496 100644
--- a/fs/fuse/inode.c
+++ b/fs/fuse/inode.c
@@ -17,6 +17,7 @@
#include <linux/parser.h>
#include <linux/statfs.h>
#include <linux/random.h>
+#include <linux/sched.h>
MODULE_AUTHOR("Miklos Szeredi <miklos@szeredi.hu>");
MODULE_DESCRIPTION("Filesystem in Userspace");
@@ -453,6 +454,7 @@ static const struct super_operations fuse_super_operations = {
.destroy_inode = fuse_destroy_inode,
.read_inode = fuse_read_inode,
.clear_inode = fuse_clear_inode,
+ .drop_inode = generic_delete_inode,
.remount_fs = fuse_remount_fs,
.put_super = fuse_put_super,
.umount_begin = fuse_umount_begin,
@@ -636,6 +638,7 @@ static int fuse_get_sb(struct file_system_type *fs_type,
static struct file_system_type fuse_fs_type = {
.owner = THIS_MODULE,
.name = "fuse",
+ .fs_flags = FS_HAS_SUBTYPE,
.get_sb = fuse_get_sb,
.kill_sb = kill_anon_super,
};
@@ -654,7 +657,7 @@ static struct file_system_type fuseblk_fs_type = {
.name = "fuseblk",
.get_sb = fuse_get_sb_blk,
.kill_sb = kill_block_super,
- .fs_flags = FS_REQUIRES_DEV,
+ .fs_flags = FS_REQUIRES_DEV | FS_HAS_SUBTYPE,
};
static inline int register_fuseblk(void)
@@ -685,8 +688,7 @@ static void fuse_inode_init_once(void *foo, struct kmem_cache *cachep,
{
struct inode * inode = foo;
- if (flags & SLAB_CTOR_CONSTRUCTOR)
- inode_init_once(inode);
+ inode_init_once(inode);
}
static int __init fuse_fs_init(void)
diff --git a/fs/gfs2/glock.h b/fs/gfs2/glock.h
index 11477ca3a3c..b3e152db70c 100644
--- a/fs/gfs2/glock.h
+++ b/fs/gfs2/glock.h
@@ -10,6 +10,7 @@
#ifndef __GLOCK_DOT_H__
#define __GLOCK_DOT_H__
+#include <linux/sched.h>
#include "incore.h"
/* Flags for lock requests; used in gfs2_holder gh_flag field.
diff --git a/fs/gfs2/glops.c b/fs/gfs2/glops.c
index 39c8ae23bd9..7b82657a991 100644
--- a/fs/gfs2/glops.c
+++ b/fs/gfs2/glops.c
@@ -163,10 +163,7 @@ static void inode_go_sync(struct gfs2_glock *gl)
if (ip) {
struct address_space *mapping = ip->i_inode.i_mapping;
int error = filemap_fdatawait(mapping);
- if (error == -ENOSPC)
- set_bit(AS_ENOSPC, &mapping->flags);
- else if (error)
- set_bit(AS_EIO, &mapping->flags);
+ mapping_set_error(mapping, error);
}
clear_bit(GLF_DIRTY, &gl->gl_flags);
gfs2_ail_empty_gl(gl);
diff --git a/fs/gfs2/locking/nolock/main.c b/fs/gfs2/locking/nolock/main.c
index 5cc1dfa7944..0d149c8c493 100644
--- a/fs/gfs2/locking/nolock/main.c
+++ b/fs/gfs2/locking/nolock/main.c
@@ -13,7 +13,6 @@
#include <linux/init.h>
#include <linux/types.h>
#include <linux/fs.h>
-#include <linux/smp_lock.h>
#include <linux/lm_interface.h>
struct nolock_lockspace {
diff --git a/fs/gfs2/main.c b/fs/gfs2/main.c
index e460487c055..787a0edef10 100644
--- a/fs/gfs2/main.c
+++ b/fs/gfs2/main.c
@@ -27,29 +27,27 @@
static void gfs2_init_inode_once(void *foo, struct kmem_cache *cachep, unsigned long flags)
{
struct gfs2_inode *ip = foo;
- if (flags & SLAB_CTOR_CONSTRUCTOR) {
- inode_init_once(&ip->i_inode);
- spin_lock_init(&ip->i_spin);
- init_rwsem(&ip->i_rw_mutex);
- memset(ip->i_cache, 0, sizeof(ip->i_cache));
- }
+
+ inode_init_once(&ip->i_inode);
+ spin_lock_init(&ip->i_spin);
+ init_rwsem(&ip->i_rw_mutex);
+ memset(ip->i_cache, 0, sizeof(ip->i_cache));
}
static void gfs2_init_glock_once(void *foo, struct kmem_cache *cachep, unsigned long flags)
{
struct gfs2_glock *gl = foo;
- if (flags & SLAB_CTOR_CONSTRUCTOR) {
- INIT_HLIST_NODE(&gl->gl_list);
- spin_lock_init(&gl->gl_spin);
- INIT_LIST_HEAD(&gl->gl_holders);
- INIT_LIST_HEAD(&gl->gl_waiters1);
- INIT_LIST_HEAD(&gl->gl_waiters3);
- gl->gl_lvb = NULL;
- atomic_set(&gl->gl_lvb_count, 0);
- INIT_LIST_HEAD(&gl->gl_reclaim);
- INIT_LIST_HEAD(&gl->gl_ail_list);
- atomic_set(&gl->gl_ail_count, 0);
- }
+
+ INIT_HLIST_NODE(&gl->gl_list);
+ spin_lock_init(&gl->gl_spin);
+ INIT_LIST_HEAD(&gl->gl_holders);
+ INIT_LIST_HEAD(&gl->gl_waiters1);
+ INIT_LIST_HEAD(&gl->gl_waiters3);
+ gl->gl_lvb = NULL;
+ atomic_set(&gl->gl_lvb_count, 0);
+ INIT_LIST_HEAD(&gl->gl_reclaim);
+ INIT_LIST_HEAD(&gl->gl_ail_list);
+ atomic_set(&gl->gl_ail_count, 0);
}
/**
diff --git a/fs/gfs2/ops_dentry.c b/fs/gfs2/ops_dentry.c
index c6bac6b6942..a6fdc52f554 100644
--- a/fs/gfs2/ops_dentry.c
+++ b/fs/gfs2/ops_dentry.c
@@ -11,7 +11,6 @@
#include <linux/spinlock.h>
#include <linux/completion.h>
#include <linux/buffer_head.h>
-#include <linux/smp_lock.h>
#include <linux/gfs2_ondisk.h>
#include <linux/crc32.h>
#include <linux/lm_interface.h>
diff --git a/fs/gfs2/ops_file.c b/fs/gfs2/ops_file.c
index 329c4dcdecd..064df880458 100644
--- a/fs/gfs2/ops_file.c
+++ b/fs/gfs2/ops_file.c
@@ -15,7 +15,6 @@
#include <linux/uio.h>
#include <linux/blkdev.h>
#include <linux/mm.h>
-#include <linux/smp_lock.h>
#include <linux/fs.h>
#include <linux/gfs2_ondisk.h>
#include <linux/ext2_fs.h>
diff --git a/fs/hfs/btree.c b/fs/hfs/btree.c
index 5fd0ed71f92..8a3a650abc8 100644
--- a/fs/hfs/btree.c
+++ b/fs/hfs/btree.c
@@ -9,6 +9,7 @@
*/
#include <linux/pagemap.h>
+#include <linux/log2.h>
#include "btree.h"
@@ -76,7 +77,7 @@ struct hfs_btree *hfs_btree_open(struct super_block *sb, u32 id, btree_keycmp ke
tree->depth = be16_to_cpu(head->depth);
size = tree->node_size;
- if (!size || size & (size - 1))
+ if (!is_power_of_2(size))
goto fail_page;
if (!tree->node_count)
goto fail_page;
diff --git a/fs/hfs/inode.c b/fs/hfs/inode.c
index fafcba59387..9a934db0bd8 100644
--- a/fs/hfs/inode.c
+++ b/fs/hfs/inode.c
@@ -13,6 +13,7 @@
#include <linux/pagemap.h>
#include <linux/mpage.h>
+#include <linux/sched.h>
#include "hfs_fs.h"
#include "btree.h"
diff --git a/fs/hfs/super.c b/fs/hfs/super.c
index 4f1888f16cf..92cf8751e42 100644
--- a/fs/hfs/super.c
+++ b/fs/hfs/super.c
@@ -434,8 +434,7 @@ static void hfs_init_once(void *p, struct kmem_cache *cachep, unsigned long flag
{
struct hfs_inode_info *i = p;
- if (flags & SLAB_CTOR_CONSTRUCTOR)
- inode_init_once(&i->vfs_inode);
+ inode_init_once(&i->vfs_inode);
}
static int __init init_hfs_fs(void)
diff --git a/fs/hfsplus/btree.c b/fs/hfsplus/btree.c
index a9b9e872e29..90ebab753d3 100644
--- a/fs/hfsplus/btree.c
+++ b/fs/hfsplus/btree.c
@@ -10,6 +10,7 @@
#include <linux/slab.h>
#include <linux/pagemap.h>
+#include <linux/log2.h>
#include "hfsplus_fs.h"
#include "hfsplus_raw.h"
@@ -69,7 +70,7 @@ struct hfs_btree *hfs_btree_open(struct super_block *sb, u32 id)
}
size = tree->node_size;
- if (!size || size & (size - 1))
+ if (!is_power_of_2(size))
goto fail_page;
if (!tree->node_count)
goto fail_page;
diff --git a/fs/hfsplus/inode.c b/fs/hfsplus/inode.c
index 642012ac337..45dab5d6cc1 100644
--- a/fs/hfsplus/inode.c
+++ b/fs/hfsplus/inode.c
@@ -12,6 +12,7 @@
#include <linux/fs.h>
#include <linux/pagemap.h>
#include <linux/mpage.h>
+#include <linux/sched.h>
#include "hfsplus_fs.h"
#include "hfsplus_raw.h"
diff --git a/fs/hfsplus/super.c b/fs/hfsplus/super.c
index 37afbec8a76..ebd1b380cbb 100644
--- a/fs/hfsplus/super.c
+++ b/fs/hfsplus/super.c
@@ -470,8 +470,7 @@ static void hfsplus_init_once(void *p, struct kmem_cache *cachep, unsigned long
{
struct hfsplus_inode_info *i = p;
- if (flags & SLAB_CTOR_CONSTRUCTOR)
- inode_init_once(&i->vfs_inode);
+ inode_init_once(&i->vfs_inode);
}
static int __init init_hfsplus_fs(void)
diff --git a/fs/hostfs/hostfs.h b/fs/hostfs/hostfs.h
index 70543b17e4c..06e5930515f 100644
--- a/fs/hostfs/hostfs.h
+++ b/fs/hostfs/hostfs.h
@@ -55,7 +55,7 @@ extern int stat_file(const char *path, unsigned long long *inode_out,
int *mode_out, int *nlink_out, int *uid_out, int *gid_out,
unsigned long long *size_out, struct timespec *atime_out,
struct timespec *mtime_out, struct timespec *ctime_out,
- int *blksize_out, unsigned long long *blocks_out);
+ int *blksize_out, unsigned long long *blocks_out, int fd);
extern int access_file(char *path, int r, int w, int x);
extern int open_file(char *path, int r, int w, int append);
extern int file_type(const char *path, int *maj, int *min);
@@ -71,7 +71,7 @@ extern int lseek_file(int fd, long long offset, int whence);
extern int fsync_file(int fd, int datasync);
extern int file_create(char *name, int ur, int uw, int ux, int gr,
int gw, int gx, int or, int ow, int ox);
-extern int set_attr(const char *file, struct hostfs_iattr *attrs);
+extern int set_attr(const char *file, struct hostfs_iattr *attrs, int fd);
extern int make_symlink(const char *from, const char *to);
extern int unlink_file(const char *file);
extern int do_mkdir(const char *file, int mode);
@@ -87,14 +87,3 @@ extern int do_statfs(char *root, long *bsize_out, long long *blocks_out,
long *spare_out);
#endif
-
-/*
- * Overrides for Emacs so that we follow Linus's tabbing style.
- * Emacs will notice this stuff at the end of the file and automatically
- * adjust the settings for this buffer only. This must remain at the end
- * of the file.
- * ---------------------------------------------------------------------------
- * Local variables:
- * c-file-style: "linux"
- * End:
- */
diff --git a/fs/hostfs/hostfs_kern.c b/fs/hostfs/hostfs_kern.c
index fd301a91012..8286491dbf3 100644
--- a/fs/hostfs/hostfs_kern.c
+++ b/fs/hostfs/hostfs_kern.c
@@ -1,5 +1,5 @@
/*
- * Copyright (C) 2000, 2001, 2002 Jeff Dike (jdike@karaya.com)
+ * Copyright (C) 2000 - 2007 Jeff Dike (jdike@{addtoit,linux.intel}.com)
* Licensed under the GPL
*
* Ported the filesystem routines to 2.5.
@@ -31,14 +31,14 @@ struct hostfs_inode_info {
static inline struct hostfs_inode_info *HOSTFS_I(struct inode *inode)
{
- return(list_entry(inode, struct hostfs_inode_info, vfs_inode));
+ return list_entry(inode, struct hostfs_inode_info, vfs_inode);
}
#define FILE_HOSTFS_I(file) HOSTFS_I((file)->f_path.dentry->d_inode)
int hostfs_d_delete(struct dentry *dentry)
{
- return(1);
+ return 1;
}
struct dentry_operations hostfs_dentry_ops = {
@@ -79,7 +79,7 @@ static int __init hostfs_args(char *options, int *add)
}
options = ptr;
}
- return(0);
+ return 0;
}
__uml_setup("hostfs=", hostfs_args,
@@ -110,7 +110,8 @@ static char *dentry_name(struct dentry *dentry, int extra)
root = HOSTFS_I(parent->d_inode)->host_filename;
len += strlen(root);
name = kmalloc(len + extra + 1, GFP_KERNEL);
- if(name == NULL) return(NULL);
+ if(name == NULL)
+ return NULL;
name[len] = '\0';
parent = dentry;
@@ -122,7 +123,7 @@ static char *dentry_name(struct dentry *dentry, int extra)
parent = parent->d_parent;
}
strncpy(name, root, strlen(root));
- return(name);
+ return name;
}
static char *inode_name(struct inode *ino, int extra)
@@ -130,7 +131,7 @@ static char *inode_name(struct inode *ino, int extra)
struct dentry *dentry;
dentry = list_entry(ino->i_dentry.next, struct dentry, d_alias);
- return(dentry_name(dentry, extra));
+ return dentry_name(dentry, extra);
}
static int read_name(struct inode *ino, char *name)
@@ -147,16 +148,16 @@ static int read_name(struct inode *ino, char *name)
err = stat_file(name, &i_ino, &i_mode, &i_nlink, &ino->i_uid,
&ino->i_gid, &i_size, &ino->i_atime, &ino->i_mtime,
- &ino->i_ctime, &i_blksize, &i_blocks);
+ &ino->i_ctime, &i_blksize, &i_blocks, -1);
if(err)
- return(err);
+ return err;
ino->i_ino = i_ino;
ino->i_mode = i_mode;
ino->i_nlink = i_nlink;
ino->i_size = i_size;
ino->i_blocks = i_blocks;
- return(0);
+ return 0;
}
static char *follow_link(char *link)
@@ -181,11 +182,11 @@ static char *follow_link(char *link)
goto out_free;
if(*name == '/')
- return(name);
+ return name;
end = strrchr(link, '/');
if(end == NULL)
- return(name);
+ return name;
*(end + 1) = '\0';
len = strlen(link) + strlen(name) + 1;
@@ -199,12 +200,12 @@ static char *follow_link(char *link)
sprintf(resolved, "%s%s", link, name);
kfree(name);
kfree(link);
- return(resolved);
+ return resolved;
out_free:
kfree(name);
out:
- return(ERR_PTR(n));
+ return ERR_PTR(n);
}
static int read_inode(struct inode *ino)
@@ -234,7 +235,7 @@ static int read_inode(struct inode *ino)
err = read_name(ino, name);
kfree(name);
out:
- return(err);
+ return err;
}
int hostfs_statfs(struct dentry *dentry, struct kstatfs *sf)
@@ -254,14 +255,15 @@ int hostfs_statfs(struct dentry *dentry, struct kstatfs *sf)
&sf->f_bsize, &f_blocks, &f_bfree, &f_bavail, &f_files,
&f_ffree, &sf->f_fsid, sizeof(sf->f_fsid),
&sf->f_namelen, sf->f_spare);
- if(err) return(err);
+ if(err)
+ return err;
sf->f_blocks = f_blocks;
sf->f_bfree = f_bfree;
sf->f_bavail = f_bavail;
sf->f_files = f_files;
sf->f_ffree = f_ffree;
sf->f_type = HOSTFS_SUPER_MAGIC;
- return(0);
+ return 0;
}
static struct inode *hostfs_alloc_inode(struct super_block *sb)
@@ -270,13 +272,13 @@ static struct inode *hostfs_alloc_inode(struct super_block *sb)
hi = kmalloc(sizeof(*hi), GFP_KERNEL);
if(hi == NULL)
- return(NULL);
+ return NULL;
*hi = ((struct hostfs_inode_info) { .host_filename = NULL,
.fd = -1,
.mode = 0 });
inode_init_once(&hi->vfs_inode);
- return(&hi->vfs_inode);
+ return &hi->vfs_inode;
}
static void hostfs_delete_inode(struct inode *inode)
@@ -325,10 +327,12 @@ int hostfs_readdir(struct file *file, void *ent, filldir_t filldir)
int error, len;
name = dentry_name(file->f_path.dentry, 0);
- if(name == NULL) return(-ENOMEM);
+ if(name == NULL)
+ return -ENOMEM;
dir = open_dir(name, &error);
kfree(name);
- if(dir == NULL) return(-error);
+ if(dir == NULL)
+ return -error;
next = file->f_pos;
while((name = read_dir(dir, &next, &ino, &len)) != NULL){
error = (*filldir)(ent, name, len, file->f_pos,
@@ -337,7 +341,7 @@ int hostfs_readdir(struct file *file, void *ent, filldir_t filldir)
file->f_pos = next;
}
close_dir(dir);
- return(0);
+ return 0;
}
int hostfs_file_open(struct inode *ino, struct file *file)
@@ -347,7 +351,7 @@ int hostfs_file_open(struct inode *ino, struct file *file)
mode = file->f_mode & (FMODE_READ | FMODE_WRITE);
if((mode & HOSTFS_I(ino)->mode) == mode)
- return(0);
+ return 0;
/* The file may already have been opened, but with the wrong access,
* so this resets things and reopens the file with the new access.
@@ -367,14 +371,15 @@ int hostfs_file_open(struct inode *ino, struct file *file)
name = dentry_name(file->f_path.dentry, 0);
if(name == NULL)
- return(-ENOMEM);
+ return -ENOMEM;
fd = open_file(name, r, w, append);
kfree(name);
- if(fd < 0) return(fd);
+ if(fd < 0)
+ return fd;
FILE_HOSTFS_I(file)->fd = fd;
- return(0);
+ return 0;
}
int hostfs_fsync(struct file *file, struct dentry *dentry, int datasync)
@@ -458,7 +463,7 @@ int hostfs_readpage(struct file *file, struct page *page)
out:
kunmap(page);
unlock_page(page);
- return(err);
+ return err;
}
int hostfs_prepare_write(struct file *file, struct page *page,
@@ -485,7 +490,7 @@ int hostfs_prepare_write(struct file *file, struct page *page,
err = 0;
out:
kunmap(page);
- return(err);
+ return err;
}
int hostfs_commit_write(struct file *file, struct page *page, unsigned from,
@@ -511,7 +516,7 @@ int hostfs_commit_write(struct file *file, struct page *page, unsigned from,
inode->i_size = start;
kunmap(page);
- return(err);
+ return err;
}
static const struct address_space_operations hostfs_aops = {
@@ -569,7 +574,7 @@ static int init_inode(struct inode *inode, struct dentry *dentry)
break;
}
out:
- return(err);
+ return err;
}
int hostfs_create(struct inode *dir, struct dentry *dentry, int mode,
@@ -607,16 +612,16 @@ int hostfs_create(struct inode *dir, struct dentry *dentry, int mode,
HOSTFS_I(inode)->fd = fd;
HOSTFS_I(inode)->mode = FMODE_READ | FMODE_WRITE;
d_instantiate(dentry, inode);
- return(0);
+ return 0;
out_put:
iput(inode);
out:
- return(error);
+ return error;
}
struct dentry *hostfs_lookup(struct inode *ino, struct dentry *dentry,
- struct nameidata *nd)
+ struct nameidata *nd)
{
struct inode *inode;
char *name;
@@ -647,44 +652,45 @@ struct dentry *hostfs_lookup(struct inode *ino, struct dentry *dentry,
d_add(dentry, inode);
dentry->d_op = &hostfs_dentry_ops;
- return(NULL);
+ return NULL;
out_put:
iput(inode);
out:
- return(ERR_PTR(err));
+ return ERR_PTR(err);
}
static char *inode_dentry_name(struct inode *ino, struct dentry *dentry)
{
- char *file;
+ char *file;
int len;
file = inode_name(ino, dentry->d_name.len + 1);
- if(file == NULL) return(NULL);
- strcat(file, "/");
+ if(file == NULL)
+ return NULL;
+ strcat(file, "/");
len = strlen(file);
- strncat(file, dentry->d_name.name, dentry->d_name.len);
+ strncat(file, dentry->d_name.name, dentry->d_name.len);
file[len + dentry->d_name.len] = '\0';
- return(file);
+ return file;
}
int hostfs_link(struct dentry *to, struct inode *ino, struct dentry *from)
{
- char *from_name, *to_name;
- int err;
+ char *from_name, *to_name;
+ int err;
- if((from_name = inode_dentry_name(ino, from)) == NULL)
- return(-ENOMEM);
- to_name = dentry_name(to, 0);
+ if((from_name = inode_dentry_name(ino, from)) == NULL)
+ return -ENOMEM;
+ to_name = dentry_name(to, 0);
if(to_name == NULL){
kfree(from_name);
- return(-ENOMEM);
+ return -ENOMEM;
}
- err = link_file(to_name, from_name);
- kfree(from_name);
- kfree(to_name);
- return(err);
+ err = link_file(to_name, from_name);
+ kfree(from_name);
+ kfree(to_name);
+ return err;
}
int hostfs_unlink(struct inode *ino, struct dentry *dentry)
@@ -692,13 +698,14 @@ int hostfs_unlink(struct inode *ino, struct dentry *dentry)
char *file;
int err;
- if((file = inode_dentry_name(ino, dentry)) == NULL) return(-ENOMEM);
+ if((file = inode_dentry_name(ino, dentry)) == NULL)
+ return -ENOMEM;
if(append)
- return(-EPERM);
+ return -EPERM;
err = unlink_file(file);
kfree(file);
- return(err);
+ return err;
}
int hostfs_symlink(struct inode *ino, struct dentry *dentry, const char *to)
@@ -706,10 +713,11 @@ int hostfs_symlink(struct inode *ino, struct dentry *dentry, const char *to)
char *file;
int err;
- if((file = inode_dentry_name(ino, dentry)) == NULL) return(-ENOMEM);
+ if((file = inode_dentry_name(ino, dentry)) == NULL)
+ return -ENOMEM;
err = make_symlink(file, to);
kfree(file);
- return(err);
+ return err;
}
int hostfs_mkdir(struct inode *ino, struct dentry *dentry, int mode)
@@ -717,10 +725,11 @@ int hostfs_mkdir(struct inode *ino, struct dentry *dentry, int mode)
char *file;
int err;
- if((file = inode_dentry_name(ino, dentry)) == NULL) return(-ENOMEM);
+ if((file = inode_dentry_name(ino, dentry)) == NULL)
+ return -ENOMEM;
err = do_mkdir(file, mode);
kfree(file);
- return(err);
+ return err;
}
int hostfs_rmdir(struct inode *ino, struct dentry *dentry)
@@ -728,10 +737,11 @@ int hostfs_rmdir(struct inode *ino, struct dentry *dentry)
char *file;
int err;
- if((file = inode_dentry_name(ino, dentry)) == NULL) return(-ENOMEM);
+ if((file = inode_dentry_name(ino, dentry)) == NULL)
+ return -ENOMEM;
err = do_rmdir(file);
kfree(file);
- return(err);
+ return err;
}
int hostfs_mknod(struct inode *dir, struct dentry *dentry, int mode, dev_t dev)
@@ -764,14 +774,14 @@ int hostfs_mknod(struct inode *dir, struct dentry *dentry, int mode, dev_t dev)
goto out_put;
d_instantiate(dentry, inode);
- return(0);
+ return 0;
out_free:
kfree(name);
out_put:
iput(inode);
out:
- return(err);
+ return err;
}
int hostfs_rename(struct inode *from_ino, struct dentry *from,
@@ -781,15 +791,15 @@ int hostfs_rename(struct inode *from_ino, struct dentry *from,
int err;
if((from_name = inode_dentry_name(from_ino, from)) == NULL)
- return(-ENOMEM);
+ return -ENOMEM;
if((to_name = inode_dentry_name(to_ino, to)) == NULL){
kfree(from_name);
- return(-ENOMEM);
+ return -ENOMEM;
}
err = rename_file(from_name, to_name);
kfree(from_name);
kfree(to_name);
- return(err);
+ return err;
}
int hostfs_permission(struct inode *ino, int desired, struct nameidata *nd)
@@ -801,7 +811,8 @@ int hostfs_permission(struct inode *ino, int desired, struct nameidata *nd)
if (desired & MAY_WRITE) w = 1;
if (desired & MAY_EXEC) x = 1;
name = inode_name(ino, 0);
- if (name == NULL) return(-ENOMEM);
+ if (name == NULL)
+ return -ENOMEM;
if (S_ISCHR(ino->i_mode) || S_ISBLK(ino->i_mode) ||
S_ISFIFO(ino->i_mode) || S_ISSOCK(ino->i_mode))
@@ -820,6 +831,8 @@ int hostfs_setattr(struct dentry *dentry, struct iattr *attr)
char *name;
int err;
+ int fd = HOSTFS_I(dentry->d_inode)->fd;
+
err = inode_change_ok(dentry->d_inode, attr);
if (err)
return err;
@@ -863,20 +876,21 @@ int hostfs_setattr(struct dentry *dentry, struct iattr *attr)
attrs.ia_valid |= HOSTFS_ATTR_MTIME_SET;
}
name = dentry_name(dentry, 0);
- if(name == NULL) return(-ENOMEM);
- err = set_attr(name, &attrs);
+ if(name == NULL)
+ return -ENOMEM;
+ err = set_attr(name, &attrs, fd);
kfree(name);
if(err)
- return(err);
+ return err;
- return(inode_setattr(dentry->d_inode, attr));
+ return inode_setattr(dentry->d_inode, attr);
}
int hostfs_getattr(struct vfsmount *mnt, struct dentry *dentry,
struct kstat *stat)
{
generic_fillattr(dentry->d_inode, stat);
- return(0);
+ return 0;
}
static const struct inode_operations hostfs_iops = {
@@ -915,7 +929,8 @@ int hostfs_link_readpage(struct file *file, struct page *page)
buffer = kmap(page);
name = inode_name(page->mapping->host, 0);
- if(name == NULL) return(-ENOMEM);
+ if(name == NULL)
+ return -ENOMEM;
err = do_readlink(name, buffer, PAGE_CACHE_SIZE);
kfree(name);
if(err == PAGE_CACHE_SIZE)
@@ -928,7 +943,7 @@ int hostfs_link_readpage(struct file *file, struct page *page)
}
kunmap(page);
unlock_page(page);
- return(err);
+ return err;
}
static const struct address_space_operations hostfs_link_aops = {
@@ -978,20 +993,20 @@ static int hostfs_fill_sb_common(struct super_block *sb, void *d, int silent)
err = read_inode(root_inode);
if(err){
- /* No iput in this case because the dput does that for us */
- dput(sb->s_root);
- sb->s_root = NULL;
+ /* No iput in this case because the dput does that for us */
+ dput(sb->s_root);
+ sb->s_root = NULL;
goto out;
- }
+ }
- return(0);
+ return 0;
- out_put:
- iput(root_inode);
- out_free:
+out_put:
+ iput(root_inode);
+out_free:
kfree(host_root_path);
- out:
- return(err);
+out:
+ return err;
}
static int hostfs_read_sb(struct file_system_type *type,
@@ -1011,7 +1026,7 @@ static struct file_system_type hostfs_type = {
static int __init init_hostfs(void)
{
- return(register_filesystem(&hostfs_type));
+ return register_filesystem(&hostfs_type);
}
static void __exit exit_hostfs(void)
@@ -1022,14 +1037,3 @@ static void __exit exit_hostfs(void)
module_init(init_hostfs)
module_exit(exit_hostfs)
MODULE_LICENSE("GPL");
-
-/*
- * Overrides for Emacs so that we follow Linus's tabbing style.
- * Emacs will notice this stuff at the end of the file and automatically
- * adjust the settings for this buffer only. This must remain at the end
- * of the file.
- * ---------------------------------------------------------------------------
- * Local variables:
- * c-file-style: "linux"
- * End:
- */
diff --git a/fs/hostfs/hostfs_user.c b/fs/hostfs/hostfs_user.c
index 1ed5ea389f1..5625e2481dd 100644
--- a/fs/hostfs/hostfs_user.c
+++ b/fs/hostfs/hostfs_user.c
@@ -1,5 +1,5 @@
/*
- * Copyright (C) 2000 Jeff Dike (jdike@karaya.com)
+ * Copyright (C) 2000 - 2007 Jeff Dike (jdike@{addtoit,linux.intel}.com)
* Licensed under the GPL
*/
@@ -21,12 +21,16 @@ int stat_file(const char *path, unsigned long long *inode_out, int *mode_out,
int *nlink_out, int *uid_out, int *gid_out,
unsigned long long *size_out, struct timespec *atime_out,
struct timespec *mtime_out, struct timespec *ctime_out,
- int *blksize_out, unsigned long long *blocks_out)
+ int *blksize_out, unsigned long long *blocks_out, int fd)
{
struct stat64 buf;
- if(lstat64(path, &buf) < 0)
- return(-errno);
+ if(fd >= 0) {
+ if (fstat64(fd, &buf) < 0)
+ return -errno;
+ } else if(lstat64(path, &buf) < 0) {
+ return -errno;
+ }
if(inode_out != NULL) *inode_out = buf.st_ino;
if(mode_out != NULL) *mode_out = buf.st_mode;
@@ -48,7 +52,7 @@ int stat_file(const char *path, unsigned long long *inode_out, int *mode_out,
}
if(blksize_out != NULL) *blksize_out = buf.st_blksize;
if(blocks_out != NULL) *blocks_out = buf.st_blocks;
- return(0);
+ return 0;
}
int file_type(const char *path, int *maj, int *min)
@@ -56,7 +60,7 @@ int file_type(const char *path, int *maj, int *min)
struct stat64 buf;
if(lstat64(path, &buf) < 0)
- return(-errno);
+ return -errno;
/*We cannot pass rdev as is because glibc and the kernel disagree
*about its definition.*/
if(maj != NULL)
@@ -64,13 +68,13 @@ int file_type(const char *path, int *maj, int *min)
if(min != NULL)
*min = minor(buf.st_rdev);
- if(S_ISDIR(buf.st_mode)) return(OS_TYPE_DIR);
- else if(S_ISLNK(buf.st_mode)) return(OS_TYPE_SYMLINK);
- else if(S_ISCHR(buf.st_mode)) return(OS_TYPE_CHARDEV);
- else if(S_ISBLK(buf.st_mode)) return(OS_TYPE_BLOCKDEV);
- else if(S_ISFIFO(buf.st_mode))return(OS_TYPE_FIFO);
- else if(S_ISSOCK(buf.st_mode))return(OS_TYPE_SOCK);
- else return(OS_TYPE_FILE);
+ if(S_ISDIR(buf.st_mode)) return OS_TYPE_DIR;
+ else if(S_ISLNK(buf.st_mode)) return OS_TYPE_SYMLINK;
+ else if(S_ISCHR(buf.st_mode)) return OS_TYPE_CHARDEV;
+ else if(S_ISBLK(buf.st_mode)) return OS_TYPE_BLOCKDEV;
+ else if(S_ISFIFO(buf.st_mode))return OS_TYPE_FIFO;
+ else if(S_ISSOCK(buf.st_mode))return OS_TYPE_SOCK;
+ else return OS_TYPE_FILE;
}
int access_file(char *path, int r, int w, int x)
@@ -80,8 +84,9 @@ int access_file(char *path, int r, int w, int x)
if(r) mode = R_OK;
if(w) mode |= W_OK;
if(x) mode |= X_OK;
- if(access(path, mode) != 0) return(-errno);
- else return(0);
+ if(access(path, mode) != 0)
+ return -errno;
+ else return 0;
}
int open_file(char *path, int r, int w, int append)
@@ -99,8 +104,9 @@ int open_file(char *path, int r, int w, int append)
if(append)
mode |= O_APPEND;
fd = open64(path, mode);
- if(fd < 0) return(-errno);
- else return(fd);
+ if(fd < 0)
+ return -errno;
+ else return fd;
}
void *open_dir(char *path, int *err_out)
@@ -109,8 +115,9 @@ void *open_dir(char *path, int *err_out)
dir = opendir(path);
*err_out = errno;
- if(dir == NULL) return(NULL);
- return(dir);
+ if(dir == NULL)
+ return NULL;
+ return dir;
}
char *read_dir(void *stream, unsigned long long *pos,
@@ -121,11 +128,12 @@ char *read_dir(void *stream, unsigned long long *pos,
seekdir(dir, *pos);
ent = readdir(dir);
- if(ent == NULL) return(NULL);
+ if(ent == NULL)
+ return NULL;
*len_out = strlen(ent->d_name);
*ino_out = ent->d_ino;
*pos = telldir(dir);
- return(ent->d_name);
+ return ent->d_name;
}
int read_file(int fd, unsigned long long *offset, char *buf, int len)
@@ -133,9 +141,10 @@ int read_file(int fd, unsigned long long *offset, char *buf, int len)
int n;
n = pread64(fd, buf, len, *offset);
- if(n < 0) return(-errno);
+ if(n < 0)
+ return -errno;
*offset += n;
- return(n);
+ return n;
}
int write_file(int fd, unsigned long long *offset, const char *buf, int len)
@@ -143,9 +152,10 @@ int write_file(int fd, unsigned long long *offset, const char *buf, int len)
int n;
n = pwrite64(fd, buf, len, *offset);
- if(n < 0) return(-errno);
+ if(n < 0)
+ return -errno;
*offset += n;
- return(n);
+ return n;
}
int lseek_file(int fd, long long offset, int whence)
@@ -154,8 +164,8 @@ int lseek_file(int fd, long long offset, int whence)
ret = lseek64(fd, offset, whence);
if(ret < 0)
- return(-errno);
- return(0);
+ return -errno;
+ return 0;
}
int fsync_file(int fd, int datasync)
@@ -198,65 +208,90 @@ int file_create(char *name, int ur, int uw, int ux, int gr,
mode |= ox ? S_IXOTH : 0;
fd = open64(name, O_CREAT | O_RDWR, mode);
if(fd < 0)
- return(-errno);
- return(fd);
+ return -errno;
+ return fd;
}
-int set_attr(const char *file, struct hostfs_iattr *attrs)
+int set_attr(const char *file, struct hostfs_iattr *attrs, int fd)
{
- struct utimbuf buf;
+ struct timeval times[2];
+ struct timespec atime_ts, mtime_ts;
int err, ma;
- if(attrs->ia_valid & HOSTFS_ATTR_MODE){
- if(chmod(file, attrs->ia_mode) != 0) return(-errno);
- }
- if(attrs->ia_valid & HOSTFS_ATTR_UID){
- if(chown(file, attrs->ia_uid, -1)) return(-errno);
+ if (attrs->ia_valid & HOSTFS_ATTR_MODE) {
+ if (fd >= 0) {
+ if (fchmod(fd, attrs->ia_mode) != 0)
+ return (-errno);
+ } else if (chmod(file, attrs->ia_mode) != 0) {
+ return -errno;
+ }
}
- if(attrs->ia_valid & HOSTFS_ATTR_GID){
- if(chown(file, -1, attrs->ia_gid)) return(-errno);
+ if (attrs->ia_valid & HOSTFS_ATTR_UID) {
+ if (fd >= 0) {
+ if (fchown(fd, attrs->ia_uid, -1))
+ return -errno;
+ } else if(chown(file, attrs->ia_uid, -1)) {
+ return -errno;
+ }
}
- if(attrs->ia_valid & HOSTFS_ATTR_SIZE){
- if(truncate(file, attrs->ia_size)) return(-errno);
+ if (attrs->ia_valid & HOSTFS_ATTR_GID) {
+ if (fd >= 0) {
+ if (fchown(fd, -1, attrs->ia_gid))
+ return -errno;
+ } else if (chown(file, -1, attrs->ia_gid)) {
+ return -errno;
+ }
}
- ma = HOSTFS_ATTR_ATIME_SET | HOSTFS_ATTR_MTIME_SET;
- if((attrs->ia_valid & ma) == ma){
- buf.actime = attrs->ia_atime.tv_sec;
- buf.modtime = attrs->ia_mtime.tv_sec;
- if(utime(file, &buf) != 0) return(-errno);
+ if (attrs->ia_valid & HOSTFS_ATTR_SIZE) {
+ if (fd >= 0) {
+ if (ftruncate(fd, attrs->ia_size))
+ return -errno;
+ } else if (truncate(file, attrs->ia_size)) {
+ return -errno;
+ }
}
- else {
- struct timespec ts;
-
- if(attrs->ia_valid & HOSTFS_ATTR_ATIME_SET){
- err = stat_file(file, NULL, NULL, NULL, NULL, NULL,
- NULL, NULL, &ts, NULL, NULL, NULL);
- if(err != 0)
- return(err);
- buf.actime = attrs->ia_atime.tv_sec;
- buf.modtime = ts.tv_sec;
- if(utime(file, &buf) != 0)
- return(-errno);
+
+ /* Update accessed and/or modified time, in two parts: first set
+ * times according to the changes to perform, and then call futimes()
+ * or utimes() to apply them. */
+ ma = (HOSTFS_ATTR_ATIME_SET | HOSTFS_ATTR_MTIME_SET);
+ if (attrs->ia_valid & ma) {
+ err = stat_file(file, NULL, NULL, NULL, NULL, NULL, NULL,
+ &atime_ts, &mtime_ts, NULL, NULL, NULL, fd);
+ if (err != 0)
+ return err;
+
+ times[0].tv_sec = atime_ts.tv_sec;
+ times[0].tv_usec = atime_ts.tv_nsec * 1000;
+ times[1].tv_sec = mtime_ts.tv_sec;
+ times[1].tv_usec = mtime_ts.tv_nsec * 1000;
+
+ if (attrs->ia_valid & HOSTFS_ATTR_ATIME_SET) {
+ times[0].tv_sec = attrs->ia_atime.tv_sec;
+ times[0].tv_usec = attrs->ia_atime.tv_nsec * 1000;
+ }
+ if (attrs->ia_valid & HOSTFS_ATTR_MTIME_SET) {
+ times[1].tv_sec = attrs->ia_mtime.tv_sec;
+ times[1].tv_usec = attrs->ia_mtime.tv_nsec * 1000;
}
- if(attrs->ia_valid & HOSTFS_ATTR_MTIME_SET){
- err = stat_file(file, NULL, NULL, NULL, NULL, NULL,
- NULL, &ts, NULL, NULL, NULL, NULL);
- if(err != 0)
- return(err);
- buf.actime = ts.tv_sec;
- buf.modtime = attrs->ia_mtime.tv_sec;
- if(utime(file, &buf) != 0)
- return(-errno);
+
+ if (fd >= 0) {
+ if (futimes(fd, times) != 0)
+ return -errno;
+ } else if (utimes(file, times) != 0) {
+ return -errno;
}
}
+
if(attrs->ia_valid & HOSTFS_ATTR_CTIME) ;
if(attrs->ia_valid & (HOSTFS_ATTR_ATIME | HOSTFS_ATTR_MTIME)){
err = stat_file(file, NULL, NULL, NULL, NULL, NULL, NULL,
&attrs->ia_atime, &attrs->ia_mtime, NULL,
- NULL, NULL);
- if(err != 0) return(err);
+ NULL, NULL, fd);
+ if(err != 0)
+ return err;
}
- return(0);
+ return 0;
}
int make_symlink(const char *from, const char *to)
@@ -264,8 +299,9 @@ int make_symlink(const char *from, const char *to)
int err;
err = symlink(to, from);
- if(err) return(-errno);
- return(0);
+ if(err)
+ return -errno;
+ return 0;
}
int unlink_file(const char *file)
@@ -273,8 +309,9 @@ int unlink_file(const char *file)
int err;
err = unlink(file);
- if(err) return(-errno);
- return(0);
+ if(err)
+ return -errno;
+ return 0;
}
int do_mkdir(const char *file, int mode)
@@ -282,8 +319,9 @@ int do_mkdir(const char *file, int mode)
int err;
err = mkdir(file, mode);
- if(err) return(-errno);
- return(0);
+ if(err)
+ return -errno;
+ return 0;
}
int do_rmdir(const char *file)
@@ -291,8 +329,9 @@ int do_rmdir(const char *file)
int err;
err = rmdir(file);
- if(err) return(-errno);
- return(0);
+ if(err)
+ return -errno;
+ return 0;
}
int do_mknod(const char *file, int mode, unsigned int major, unsigned int minor)
@@ -300,8 +339,9 @@ int do_mknod(const char *file, int mode, unsigned int major, unsigned int minor)
int err;
err = mknod(file, mode, makedev(major, minor));
- if(err) return(-errno);
- return(0);
+ if(err)
+ return -errno;
+ return 0;
}
int link_file(const char *to, const char *from)
@@ -309,8 +349,9 @@ int link_file(const char *to, const char *from)
int err;
err = link(to, from);
- if(err) return(-errno);
- return(0);
+ if(err)
+ return -errno;
+ return 0;
}
int do_readlink(char *file, char *buf, int size)
@@ -319,10 +360,10 @@ int do_readlink(char *file, char *buf, int size)
n = readlink(file, buf, size);
if(n < 0)
- return(-errno);
+ return -errno;
if(n < size)
buf[n] = '\0';
- return(n);
+ return n;
}
int rename_file(char *from, char *to)
@@ -330,8 +371,9 @@ int rename_file(char *from, char *to)
int err;
err = rename(from, to);
- if(err < 0) return(-errno);
- return(0);
+ if(err < 0)
+ return -errno;
+ return 0;
}
int do_statfs(char *root, long *bsize_out, long long *blocks_out,
@@ -344,7 +386,9 @@ int do_statfs(char *root, long *bsize_out, long long *blocks_out,
int err;
err = statfs64(root, &buf);
- if(err < 0) return(-errno);
+ if(err < 0)
+ return -errno;
+
*bsize_out = buf.f_bsize;
*blocks_out = buf.f_blocks;
*bfree_out = buf.f_bfree;
@@ -360,16 +404,5 @@ int do_statfs(char *root, long *bsize_out, long long *blocks_out,
spare_out[2] = buf.f_spare[2];
spare_out[3] = buf.f_spare[3];
spare_out[4] = buf.f_spare[4];
- return(0);
+ return 0;
}
-
-/*
- * Overrides for Emacs so that we follow Linus's tabbing style.
- * Emacs will notice this stuff at the end of the file and automatically
- * adjust the settings for this buffer only. This must remain at the end
- * of the file.
- * ---------------------------------------------------------------------------
- * Local variables:
- * c-file-style: "linux"
- * End:
- */
diff --git a/fs/hpfs/buffer.c b/fs/hpfs/buffer.c
index b52b7381d10..b6fca543544 100644
--- a/fs/hpfs/buffer.c
+++ b/fs/hpfs/buffer.c
@@ -5,7 +5,7 @@
*
* general buffer i/o
*/
-
+#include <linux/sched.h>
#include "hpfs_fn.h"
void hpfs_lock_creation(struct super_block *s)
diff --git a/fs/hpfs/namei.c b/fs/hpfs/namei.c
index 9953cf9a2f1..d256559b410 100644
--- a/fs/hpfs/namei.c
+++ b/fs/hpfs/namei.c
@@ -5,7 +5,7 @@
*
* adding & removing files & directories
*/
-
+#include <linux/sched.h>
#include "hpfs_fn.h"
static int hpfs_mkdir(struct inode *dir, struct dentry *dentry, int mode)
diff --git a/fs/hpfs/super.c b/fs/hpfs/super.c
index 1b95f39fbc3..29cc34abb2e 100644
--- a/fs/hpfs/super.c
+++ b/fs/hpfs/super.c
@@ -12,6 +12,7 @@
#include <linux/init.h>
#include <linux/statfs.h>
#include <linux/magic.h>
+#include <linux/sched.h>
/* Mark the filesystem dirty, so that chkdsk checks it when os/2 booted */
@@ -176,11 +177,9 @@ static void init_once(void * foo, struct kmem_cache * cachep, unsigned long flag
{
struct hpfs_inode_info *ei = (struct hpfs_inode_info *) foo;
- if (flags & SLAB_CTOR_CONSTRUCTOR) {
- mutex_init(&ei->i_mutex);
- mutex_init(&ei->i_parent_mutex);
- inode_init_once(&ei->vfs_inode);
- }
+ mutex_init(&ei->i_mutex);
+ mutex_init(&ei->i_parent_mutex);
+ inode_init_once(&ei->vfs_inode);
}
static int init_inodecache(void)
diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c
index 98959b87cdf..e6b46b3ac2f 100644
--- a/fs/hugetlbfs/inode.c
+++ b/fs/hugetlbfs/inode.c
@@ -556,8 +556,7 @@ static void init_once(void *foo, struct kmem_cache *cachep, unsigned long flags)
{
struct hugetlbfs_inode_info *ei = (struct hugetlbfs_inode_info *)foo;
- if (flags & SLAB_CTOR_CONSTRUCTOR)
- inode_init_once(&ei->vfs_inode);
+ inode_init_once(&ei->vfs_inode);
}
const struct file_operations hugetlbfs_file_operations = {
@@ -737,15 +736,13 @@ static int can_do_hugetlb_shm(void)
can_do_mlock());
}
-struct file *hugetlb_zero_setup(size_t size)
+struct file *hugetlb_file_setup(const char *name, size_t size)
{
int error = -ENOMEM;
struct file *file;
struct inode *inode;
struct dentry *dentry, *root;
struct qstr quick_string;
- char buf[16];
- static atomic_t counter;
if (!hugetlbfs_vfsmount)
return ERR_PTR(-ENOENT);
@@ -757,8 +754,7 @@ struct file *hugetlb_zero_setup(size_t size)
return ERR_PTR(-ENOMEM);
root = hugetlbfs_vfsmount->mnt_root;
- snprintf(buf, 16, "%u", atomic_inc_return(&counter));
- quick_string.name = buf;
+ quick_string.name = name;
quick_string.len = strlen(quick_string.name);
quick_string.hash = 0;
dentry = d_alloc(root, &quick_string);
diff --git a/fs/inode.c b/fs/inode.c
index b4296bf6273..9a012cc5b6c 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -213,8 +213,7 @@ static void init_once(void * foo, struct kmem_cache * cachep, unsigned long flag
{
struct inode * inode = (struct inode *) foo;
- if (flags & SLAB_CTOR_CONSTRUCTOR)
- inode_init_once(inode);
+ inode_init_once(inode);
}
/*
@@ -250,7 +249,7 @@ void clear_inode(struct inode *inode)
BUG_ON(inode->i_state & I_CLEAR);
wait_on_inode(inode);
DQUOT_DROP(inode);
- if (inode->i_sb && inode->i_sb->s_op->clear_inode)
+ if (inode->i_sb->s_op->clear_inode)
inode->i_sb->s_op->clear_inode(inode);
if (S_ISBLK(inode->i_mode) && inode->i_bdev)
bd_forget(inode);
@@ -275,7 +274,7 @@ static void dispose_list(struct list_head *head)
while (!list_empty(head)) {
struct inode *inode;
- inode = list_entry(head->next, struct inode, i_list);
+ inode = list_first_entry(head, struct inode, i_list);
list_del(&inode->i_list);
if (inode->i_data.nrpages)
@@ -524,7 +523,12 @@ repeat:
*/
struct inode *new_inode(struct super_block *sb)
{
- static unsigned long last_ino;
+ /*
+ * On a 32bit, non LFS stat() call, glibc will generate an EOVERFLOW
+ * error if st_ino won't fit in target struct field. Use 32bit counter
+ * here to attempt to avoid that.
+ */
+ static unsigned int last_ino;
struct inode * inode;
spin_lock_prefetch(&inode_lock);
@@ -683,27 +687,28 @@ static unsigned long hash(struct super_block *sb, unsigned long hashval)
*/
ino_t iunique(struct super_block *sb, ino_t max_reserved)
{
- static ino_t counter;
+ /*
+ * On a 32bit, non LFS stat() call, glibc will generate an EOVERFLOW
+ * error if st_ino won't fit in target struct field. Use 32bit counter
+ * here to attempt to avoid that.
+ */
+ static unsigned int counter;
struct inode *inode;
- struct hlist_head * head;
+ struct hlist_head *head;
ino_t res;
+
spin_lock(&inode_lock);
-retry:
- if (counter > max_reserved) {
- head = inode_hashtable + hash(sb,counter);
+ do {
+ if (counter <= max_reserved)
+ counter = max_reserved + 1;
res = counter++;
+ head = inode_hashtable + hash(sb, res);
inode = find_inode_fast(sb, head, res);
- if (!inode) {
- spin_unlock(&inode_lock);
- return res;
- }
- } else {
- counter = max_reserved + 1;
- }
- goto retry;
-
-}
+ } while (inode != NULL);
+ spin_unlock(&inode_lock);
+ return res;
+}
EXPORT_SYMBOL(iunique);
struct inode *igrab(struct inode *inode)
@@ -1040,7 +1045,7 @@ static void generic_forget_inode(struct inode *inode)
if (!(inode->i_state & (I_DIRTY|I_LOCK)))
list_move(&inode->i_list, &inode_unused);
inodes_stat.nr_unused++;
- if (!sb || (sb->s_flags & MS_ACTIVE)) {
+ if (sb->s_flags & MS_ACTIVE) {
spin_unlock(&inode_lock);
return;
}
diff --git a/fs/inotify.c b/fs/inotify.c
index f5099d86fd9..7457501b956 100644
--- a/fs/inotify.c
+++ b/fs/inotify.c
@@ -509,7 +509,7 @@ void inotify_destroy(struct inotify_handle *ih)
mutex_unlock(&ih->mutex);
break;
}
- watch = list_entry(watches->next, struct inotify_watch, h_list);
+ watch = list_first_entry(watches, struct inotify_watch, h_list);
get_inotify_watch(watch);
mutex_unlock(&ih->mutex);
diff --git a/fs/internal.h b/fs/internal.h
index ea00126c9a5..392e8ccd6fc 100644
--- a/fs/internal.h
+++ b/fs/internal.h
@@ -9,8 +9,6 @@
* 2 of the License, or (at your option) any later version.
*/
-#include <linux/ioctl32.h>
-
struct super_block;
/*
@@ -42,14 +40,6 @@ static inline int sb_is_blkdev_sb(struct super_block *sb)
extern void __init chrdev_init(void);
/*
- * compat_ioctl.c
- */
-#ifdef CONFIG_COMPAT
-extern struct ioctl_trans ioctl_start[];
-extern int ioctl_table_size;
-#endif
-
-/*
* namespace.c
*/
extern int copy_mount_options(const void __user *, unsigned long *);
diff --git a/fs/ioctl.c b/fs/ioctl.c
index ff61772ceed..8c90cbc903f 100644
--- a/fs/ioctl.c
+++ b/fs/ioctl.c
@@ -12,6 +12,7 @@
#include <linux/fs.h>
#include <linux/security.h>
#include <linux/module.h>
+#include <linux/kallsyms.h>
#include <asm/uaccess.h>
#include <asm/ioctls.h>
@@ -20,6 +21,7 @@ static long do_ioctl(struct file *filp, unsigned int cmd,
unsigned long arg)
{
int error = -ENOTTY;
+ void *f;
if (!filp->f_op)
goto out;
@@ -29,10 +31,16 @@ static long do_ioctl(struct file *filp, unsigned int cmd,
if (error == -ENOIOCTLCMD)
error = -EINVAL;
goto out;
- } else if (filp->f_op->ioctl) {
+ } else if ((f = filp->f_op->ioctl)) {
lock_kernel();
- error = filp->f_op->ioctl(filp->f_path.dentry->d_inode,
- filp, cmd, arg);
+ if (!filp->f_op->ioctl) {
+ printk("%s: ioctl %p disappeared\n", __FUNCTION__, f);
+ print_symbol("symbol: %s\n", (unsigned long)f);
+ dump_stack();
+ } else {
+ error = filp->f_op->ioctl(filp->f_path.dentry->d_inode,
+ filp, cmd, arg);
+ }
unlock_kernel();
}
@@ -67,8 +75,6 @@ static int file_ioctl(struct file *filp, unsigned int cmd,
return put_user(res, p);
}
case FIGETBSZ:
- if (inode->i_sb == NULL)
- return -EBADF;
return put_user(inode->i_sb->s_blocksize, p);
case FIONREAD:
return put_user(i_size_read(inode) - filp->f_pos, p);
diff --git a/fs/isofs/inode.c b/fs/isofs/inode.c
index e99f7ff4ecb..5c3eecf7542 100644
--- a/fs/isofs/inode.c
+++ b/fs/isofs/inode.c
@@ -77,8 +77,7 @@ static void init_once(void *foo, struct kmem_cache * cachep, unsigned long flags
{
struct iso_inode_info *ei = foo;
- if (flags & SLAB_CTOR_CONSTRUCTOR)
- inode_init_once(&ei->vfs_inode);
+ inode_init_once(&ei->vfs_inode);
}
static int init_inodecache(void)
diff --git a/fs/jbd/checkpoint.c b/fs/jbd/checkpoint.c
index 0208cc7ac5d..47552d4a632 100644
--- a/fs/jbd/checkpoint.c
+++ b/fs/jbd/checkpoint.c
@@ -1,5 +1,5 @@
/*
- * linux/fs/checkpoint.c
+ * linux/fs/jbd/checkpoint.c
*
* Written by Stephen C. Tweedie <sct@redhat.com>, 1999
*
diff --git a/fs/jbd/commit.c b/fs/jbd/commit.c
index be4648bc7a2..1facfaff97c 100644
--- a/fs/jbd/commit.c
+++ b/fs/jbd/commit.c
@@ -20,7 +20,6 @@
#include <linux/slab.h>
#include <linux/mm.h>
#include <linux/pagemap.h>
-#include <linux/smp_lock.h>
/*
* Default IO end handler for temporary BJ_IO buffer_heads.
diff --git a/fs/jbd/journal.c b/fs/jbd/journal.c
index 10fff944393..46fe7439fb9 100644
--- a/fs/jbd/journal.c
+++ b/fs/jbd/journal.c
@@ -28,7 +28,6 @@
#include <linux/jbd.h>
#include <linux/errno.h>
#include <linux/slab.h>
-#include <linux/smp_lock.h>
#include <linux/init.h>
#include <linux/mm.h>
#include <linux/freezer.h>
@@ -211,10 +210,16 @@ end_loop:
return 0;
}
-static void journal_start_thread(journal_t *journal)
+static int journal_start_thread(journal_t *journal)
{
- kthread_run(kjournald, journal, "kjournald");
+ struct task_struct *t;
+
+ t = kthread_run(kjournald, journal, "kjournald");
+ if (IS_ERR(t))
+ return PTR_ERR(t);
+
wait_event(journal->j_wait_done_commit, journal->j_task != 0);
+ return 0;
}
static void journal_kill_thread(journal_t *journal)
@@ -840,8 +845,7 @@ static int journal_reset(journal_t *journal)
/* Add the dynamic fields and write it to disk. */
journal_update_superblock(journal, 1);
- journal_start_thread(journal);
- return 0;
+ return journal_start_thread(journal);
}
/**
diff --git a/fs/jbd/recovery.c b/fs/jbd/recovery.c
index 11563fe2a52..2a5f4b833e3 100644
--- a/fs/jbd/recovery.c
+++ b/fs/jbd/recovery.c
@@ -1,5 +1,5 @@
/*
- * linux/fs/recovery.c
+ * linux/fs/jbd/recovery.c
*
* Written by Stephen C. Tweedie <sct@redhat.com>, 1999
*
diff --git a/fs/jbd/revoke.c b/fs/jbd/revoke.c
index d204ab394f3..824e3b7d4ec 100644
--- a/fs/jbd/revoke.c
+++ b/fs/jbd/revoke.c
@@ -1,5 +1,5 @@
/*
- * linux/fs/revoke.c
+ * linux/fs/jbd/revoke.c
*
* Written by Stephen C. Tweedie <sct@redhat.com>, 2000
*
@@ -66,7 +66,6 @@
#include <linux/errno.h>
#include <linux/slab.h>
#include <linux/list.h>
-#include <linux/smp_lock.h>
#include <linux/init.h>
#endif
diff --git a/fs/jbd/transaction.c b/fs/jbd/transaction.c
index cceaf57e377..772b6531a2a 100644
--- a/fs/jbd/transaction.c
+++ b/fs/jbd/transaction.c
@@ -1,5 +1,5 @@
/*
- * linux/fs/transaction.c
+ * linux/fs/jbd/transaction.c
*
* Written by Stephen C. Tweedie <sct@redhat.com>, 1998
*
@@ -23,7 +23,6 @@
#include <linux/errno.h>
#include <linux/slab.h>
#include <linux/timer.h>
-#include <linux/smp_lock.h>
#include <linux/mm.h>
#include <linux/highmem.h>
diff --git a/fs/jbd2/checkpoint.c b/fs/jbd2/checkpoint.c
index 68039fa9a56..3fccde7ba00 100644
--- a/fs/jbd2/checkpoint.c
+++ b/fs/jbd2/checkpoint.c
@@ -1,5 +1,5 @@
/*
- * linux/fs/checkpoint.c
+ * linux/fs/jbd2/checkpoint.c
*
* Written by Stephen C. Tweedie <sct@redhat.com>, 1999
*
diff --git a/fs/jbd2/commit.c b/fs/jbd2/commit.c
index 6bd8005e3d3..2856e1100a5 100644
--- a/fs/jbd2/commit.c
+++ b/fs/jbd2/commit.c
@@ -20,7 +20,6 @@
#include <linux/slab.h>
#include <linux/mm.h>
#include <linux/pagemap.h>
-#include <linux/smp_lock.h>
/*
* Default IO end handler for temporary BJ_IO buffer_heads.
diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c
index 44fc32bfd7f..78d63b818f0 100644
--- a/fs/jbd2/journal.c
+++ b/fs/jbd2/journal.c
@@ -28,7 +28,6 @@
#include <linux/jbd2.h>
#include <linux/errno.h>
#include <linux/slab.h>
-#include <linux/smp_lock.h>
#include <linux/init.h>
#include <linux/mm.h>
#include <linux/freezer.h>
@@ -211,10 +210,16 @@ end_loop:
return 0;
}
-static void jbd2_journal_start_thread(journal_t *journal)
+static int jbd2_journal_start_thread(journal_t *journal)
{
- kthread_run(kjournald2, journal, "kjournald2");
+ struct task_struct *t;
+
+ t = kthread_run(kjournald2, journal, "kjournald2");
+ if (IS_ERR(t))
+ return PTR_ERR(t);
+
wait_event(journal->j_wait_done_commit, journal->j_task != 0);
+ return 0;
}
static void journal_kill_thread(journal_t *journal)
@@ -840,8 +845,7 @@ static int journal_reset(journal_t *journal)
/* Add the dynamic fields and write it to disk. */
jbd2_journal_update_superblock(journal, 1);
- jbd2_journal_start_thread(journal);
- return 0;
+ return jbd2_journal_start_thread(journal);
}
/**
diff --git a/fs/jbd2/recovery.c b/fs/jbd2/recovery.c
index 9f10acafaf7..395c92a04ac 100644
--- a/fs/jbd2/recovery.c
+++ b/fs/jbd2/recovery.c
@@ -1,5 +1,5 @@
/*
- * linux/fs/recovery.c
+ * linux/fs/jbd2/recovery.c
*
* Written by Stephen C. Tweedie <sct@redhat.com>, 1999
*
diff --git a/fs/jbd2/revoke.c b/fs/jbd2/revoke.c
index f506646ad0f..9246e763da7 100644
--- a/fs/jbd2/revoke.c
+++ b/fs/jbd2/revoke.c
@@ -1,5 +1,5 @@
/*
- * linux/fs/revoke.c
+ * linux/fs/jbd2/revoke.c
*
* Written by Stephen C. Tweedie <sct@redhat.com>, 2000
*
@@ -66,7 +66,6 @@
#include <linux/errno.h>
#include <linux/slab.h>
#include <linux/list.h>
-#include <linux/smp_lock.h>
#include <linux/init.h>
#endif
diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c
index 3a8700153cb..7946ff43fc4 100644
--- a/fs/jbd2/transaction.c
+++ b/fs/jbd2/transaction.c
@@ -1,5 +1,5 @@
/*
- * linux/fs/transaction.c
+ * linux/fs/jbd2/transaction.c
*
* Written by Stephen C. Tweedie <sct@redhat.com>, 1998
*
@@ -23,7 +23,6 @@
#include <linux/errno.h>
#include <linux/slab.h>
#include <linux/timer.h>
-#include <linux/smp_lock.h>
#include <linux/mm.h>
#include <linux/highmem.h>
diff --git a/fs/jffs2/histo_mips.h b/fs/jffs2/histo_mips.h
deleted file mode 100644
index fa3dac19a10..00000000000
--- a/fs/jffs2/histo_mips.h
+++ /dev/null
@@ -1,2 +0,0 @@
-#define BIT_DIVIDER_MIPS 1043
-static int bits_mips[8] = { 277,249,290,267,229,341,212,241}; /* mips32 */
diff --git a/fs/jffs2/readinode.c b/fs/jffs2/readinode.c
index 6aff38930b5..7b363786c2d 100644
--- a/fs/jffs2/readinode.c
+++ b/fs/jffs2/readinode.c
@@ -210,8 +210,7 @@ static void jffs2_kill_tn(struct jffs2_sb_info *c, struct jffs2_tmp_dnode_info *
* offset, and the one with the smallest length will come first in the
* ordering.
*
- * Returns 0 if the node was inserted
- * 1 if the node is obsolete (because we can't mark it so yet)
+ * Returns 0 if the node was handled (including marking it obsolete)
* < 0 an if error occurred
*/
static int jffs2_add_tn_to_tree(struct jffs2_sb_info *c,
@@ -219,9 +218,9 @@ static int jffs2_add_tn_to_tree(struct jffs2_sb_info *c,
struct jffs2_tmp_dnode_info *tn)
{
uint32_t fn_end = tn->fn->ofs + tn->fn->size;
- struct jffs2_tmp_dnode_info *insert_point = NULL, *this;
+ struct jffs2_tmp_dnode_info *this;
- dbg_readinode("insert fragment %#04x-%#04x, ver %u\n", tn->fn->ofs, fn_end, tn->version);
+ dbg_readinode("insert fragment %#04x-%#04x, ver %u at %08x\n", tn->fn->ofs, fn_end, tn->version, ref_offset(tn->fn->raw));
/* If a node has zero dsize, we only have to keep if it if it might be the
node with highest version -- i.e. the one which will end up as f->metadata.
@@ -229,9 +228,16 @@ static int jffs2_add_tn_to_tree(struct jffs2_sb_info *c,
check anyway. */
if (!tn->fn->size) {
if (rii->mdata_tn) {
- /* We had a candidate mdata node already */
- dbg_readinode("kill old mdata with ver %d\n", rii->mdata_tn->version);
- jffs2_kill_tn(c, rii->mdata_tn);
+ if (rii->mdata_tn->version < tn->version) {
+ /* We had a candidate mdata node already */
+ dbg_readinode("kill old mdata with ver %d\n", rii->mdata_tn->version);
+ jffs2_kill_tn(c, rii->mdata_tn);
+ } else {
+ dbg_readinode("kill new mdata with ver %d (older than existing %d\n",
+ tn->version, rii->mdata_tn->version);
+ jffs2_kill_tn(c, tn);
+ return 0;
+ }
}
rii->mdata_tn = tn;
dbg_readinode("keep new mdata with ver %d\n", tn->version);
@@ -240,23 +246,16 @@ static int jffs2_add_tn_to_tree(struct jffs2_sb_info *c,
/* Find the earliest node which _may_ be relevant to this one */
this = jffs2_lookup_tn(&rii->tn_root, tn->fn->ofs);
- if (!this) {
- /* First addition to empty tree. $DEITY how I love the easy cases */
- rb_link_node(&tn->rb, NULL, &rii->tn_root.rb_node);
- rb_insert_color(&tn->rb, &rii->tn_root);
- dbg_readinode("keep new frag\n");
- return 0;
- }
-
- /* If we add a new node it'll be somewhere under here. */
- insert_point = this;
-
- /* If the node is coincident with another at a lower address,
- back up until the other node is found. It may be relevant */
- while (tn->overlapped)
- tn = tn_prev(tn);
+ if (this) {
+ /* If the node is coincident with another at a lower address,
+ back up until the other node is found. It may be relevant */
+ while (this->overlapped)
+ this = tn_prev(this);
- dbg_readinode("'this' found %#04x-%#04x (%s)\n", this->fn->ofs, this->fn->ofs + this->fn->size, this->fn ? "data" : "hole");
+ /* First node should never be marked overlapped */
+ BUG_ON(!this);
+ dbg_readinode("'this' found %#04x-%#04x (%s)\n", this->fn->ofs, this->fn->ofs + this->fn->size, this->fn ? "data" : "hole");
+ }
while (this) {
if (this->fn->ofs > fn_end)
@@ -274,11 +273,10 @@ static int jffs2_add_tn_to_tree(struct jffs2_sb_info *c,
return 0;
} else {
/* Who cares if the new one is good; keep it for now anyway. */
+ dbg_readinode("Like new node. Throw away old\n");
rb_replace_node(&this->rb, &tn->rb, &rii->tn_root);
- /* Same overlapping from in front and behind */
- tn->overlapped = this->overlapped;
jffs2_kill_tn(c, this);
- dbg_readinode("Like new node. Throw away old\n");
+ /* Same overlapping from in front and behind */
return 0;
}
}
@@ -291,13 +289,8 @@ static int jffs2_add_tn_to_tree(struct jffs2_sb_info *c,
jffs2_kill_tn(c, tn);
return 0;
}
- /* ... and is good. Kill 'this'... */
- rb_replace_node(&this->rb, &tn->rb, &rii->tn_root);
- tn->overlapped = this->overlapped;
- jffs2_kill_tn(c, this);
- /* ... and any subsequent nodes which are also overlapped */
- this = tn_next(tn);
- while (this && this->fn->ofs + this->fn->size < fn_end) {
+ /* ... and is good. Kill 'this' and any subsequent nodes which are also overlapped */
+ while (this && this->fn->ofs + this->fn->size <= fn_end) {
struct jffs2_tmp_dnode_info *next = tn_next(this);
if (this->version < tn->version) {
tn_erase(this, &rii->tn_root);
@@ -308,8 +301,8 @@ static int jffs2_add_tn_to_tree(struct jffs2_sb_info *c,
}
this = next;
}
- dbg_readinode("Done inserting new\n");
- return 0;
+ dbg_readinode("Done killing overlapped nodes\n");
+ continue;
}
if (this->version > tn->version &&
this->fn->ofs <= tn->fn->ofs &&
@@ -321,29 +314,21 @@ static int jffs2_add_tn_to_tree(struct jffs2_sb_info *c,
return 0;
}
/* ... but 'this' was bad. Replace it... */
- rb_replace_node(&this->rb, &tn->rb, &rii->tn_root);
dbg_readinode("Bad CRC on old overlapping node. Kill it\n");
+ tn_erase(this, &rii->tn_root);
jffs2_kill_tn(c, this);
- return 0;
+ break;
}
- /* We want to be inserted under the last node which is
- either at a lower offset _or_ has a smaller range */
- if (this->fn->ofs < tn->fn->ofs ||
- (this->fn->ofs == tn->fn->ofs &&
- this->fn->size <= tn->fn->size))
- insert_point = this;
this = tn_next(this);
}
- dbg_readinode("insert_point %p, ver %d, 0x%x-0x%x, ov %d\n",
- insert_point, insert_point->version, insert_point->fn->ofs,
- insert_point->fn->ofs+insert_point->fn->size,
- insert_point->overlapped);
+
/* We neither completely obsoleted nor were completely
- obsoleted by an earlier node. Insert under insert_point */
+ obsoleted by an earlier node. Insert into the tree */
{
- struct rb_node *parent = &insert_point->rb;
- struct rb_node **link = &parent;
+ struct rb_node *parent;
+ struct rb_node **link = &rii->tn_root.rb_node;
+ struct jffs2_tmp_dnode_info *insert_point = NULL;
while (*link) {
parent = *link;
@@ -359,6 +344,7 @@ static int jffs2_add_tn_to_tree(struct jffs2_sb_info *c,
rb_link_node(&tn->rb, &insert_point->rb, link);
rb_insert_color(&tn->rb, &rii->tn_root);
}
+
/* If there's anything behind that overlaps us, note it */
this = tn_prev(tn);
if (this) {
@@ -457,7 +443,7 @@ static int jffs2_build_inode_fragtree(struct jffs2_sb_info *c,
this = tn_last(&rii->tn_root);
while (this) {
dbg_readinode("tn %p ver %d range 0x%x-0x%x ov %d\n", this, this->version, this->fn->ofs,
- this->fn->ofs+this->fn->size, this->overlapped);
+ this->fn->ofs+this->fn->size, this->overlapped);
this = tn_prev(this);
}
#endif
@@ -483,7 +469,7 @@ static int jffs2_build_inode_fragtree(struct jffs2_sb_info *c,
vers_next = tn_prev(this);
eat_last(&ver_root, &this->rb);
if (check_tn_node(c, this)) {
- dbg_readinode("node ver %x, 0x%x-0x%x failed CRC\n",
+ dbg_readinode("node ver %d, 0x%x-0x%x failed CRC\n",
this->version, this->fn->ofs,
this->fn->ofs+this->fn->size);
jffs2_kill_tn(c, this);
@@ -496,7 +482,7 @@ static int jffs2_build_inode_fragtree(struct jffs2_sb_info *c,
high_ver = this->version;
rii->latest_ref = this->fn->raw;
}
- dbg_readinode("Add %p (v %x, 0x%x-0x%x, ov %d) to fragtree\n",
+ dbg_readinode("Add %p (v %d, 0x%x-0x%x, ov %d) to fragtree\n",
this, this->version, this->fn->ofs,
this->fn->ofs+this->fn->size, this->overlapped);
@@ -585,8 +571,7 @@ static struct jffs2_raw_node_ref *jffs2_first_valid_node(struct jffs2_raw_node_r
* Helper function for jffs2_get_inode_nodes().
* It is called every time an directory entry node is found.
*
- * Returns: 0 on succes;
- * 1 if the node should be marked obsolete;
+ * Returns: 0 on success;
* negative error code on failure.
*/
static inline int read_direntry(struct jffs2_sb_info *c, struct jffs2_raw_node_ref *ref,
@@ -693,8 +678,7 @@ static inline int read_direntry(struct jffs2_sb_info *c, struct jffs2_raw_node_r
* Helper function for jffs2_get_inode_nodes().
* It is called every time an inode node is found.
*
- * Returns: 0 on success;
- * 1 if the node should be marked obsolete;
+ * Returns: 0 on success (possibly after marking a bad node obsolete);
* negative error code on failure.
*/
static inline int read_dnode(struct jffs2_sb_info *c, struct jffs2_raw_node_ref *ref,
@@ -703,7 +687,7 @@ static inline int read_dnode(struct jffs2_sb_info *c, struct jffs2_raw_node_ref
{
struct jffs2_tmp_dnode_info *tn;
uint32_t len, csize;
- int ret = 1;
+ int ret = 0;
uint32_t crc;
/* Obsoleted. This cannot happen, surely? dwmw2 20020308 */
@@ -732,8 +716,9 @@ static inline int read_dnode(struct jffs2_sb_info *c, struct jffs2_raw_node_ref
/* Sanity checks */
if (unlikely(je32_to_cpu(rd->offset) > je32_to_cpu(rd->isize)) ||
unlikely(PAD(je32_to_cpu(rd->csize) + sizeof(*rd)) != PAD(je32_to_cpu(rd->totlen)))) {
- JFFS2_WARNING("inode node header CRC is corrupted at %#08x\n", ref_offset(ref));
- jffs2_dbg_dump_node(c, ref_offset(ref));
+ JFFS2_WARNING("inode node header CRC is corrupted at %#08x\n", ref_offset(ref));
+ jffs2_dbg_dump_node(c, ref_offset(ref));
+ jffs2_mark_node_obsolete(c, ref);
goto free_out;
}
@@ -788,6 +773,7 @@ static inline int read_dnode(struct jffs2_sb_info *c, struct jffs2_raw_node_ref
if (len >= csize && unlikely(tn->partial_crc != je32_to_cpu(rd->data_crc))) {
JFFS2_NOTICE("wrong data CRC in data node at 0x%08x: read %#08x, calculated %#08x.\n",
ref_offset(ref), tn->partial_crc, je32_to_cpu(rd->data_crc));
+ jffs2_mark_node_obsolete(c, ref);
goto free_out;
}
@@ -850,7 +836,7 @@ static inline int read_dnode(struct jffs2_sb_info *c, struct jffs2_raw_node_ref
return ret;
}
#ifdef JFFS2_DBG_READINODE_MESSAGES
- dbg_readinode("After adding ver %d:\n", tn->version);
+ dbg_readinode("After adding ver %d:\n", je32_to_cpu(rd->version));
tn = tn_first(&rii->tn_root);
while (tn) {
dbg_readinode("%p: v %d r 0x%x-0x%x ov %d\n",
@@ -867,7 +853,6 @@ static inline int read_dnode(struct jffs2_sb_info *c, struct jffs2_raw_node_ref
* It is called every time an unknown node is found.
*
* Returns: 0 on success;
- * 1 if the node should be marked obsolete;
* negative error code on failure.
*/
static inline int read_unknown(struct jffs2_sb_info *c, struct jffs2_raw_node_ref *ref, struct jffs2_unknown_node *un)
@@ -1064,7 +1049,8 @@ static int jffs2_get_inode_nodes(struct jffs2_sb_info *c, struct jffs2_inode_inf
case JFFS2_NODETYPE_DIRENT:
- if (JFFS2_MIN_NODE_HEADER < sizeof(struct jffs2_raw_dirent)) {
+ if (JFFS2_MIN_NODE_HEADER < sizeof(struct jffs2_raw_dirent) &&
+ len < sizeof(struct jffs2_raw_dirent)) {
err = read_more(c, ref, sizeof(struct jffs2_raw_dirent), &len, buf);
if (unlikely(err))
goto free_out;
@@ -1078,7 +1064,8 @@ static int jffs2_get_inode_nodes(struct jffs2_sb_info *c, struct jffs2_inode_inf
case JFFS2_NODETYPE_INODE:
- if (JFFS2_MIN_NODE_HEADER < sizeof(struct jffs2_raw_inode)) {
+ if (JFFS2_MIN_NODE_HEADER < sizeof(struct jffs2_raw_inode) &&
+ len < sizeof(struct jffs2_raw_inode)) {
err = read_more(c, ref, sizeof(struct jffs2_raw_inode), &len, buf);
if (unlikely(err))
goto free_out;
@@ -1091,17 +1078,15 @@ static int jffs2_get_inode_nodes(struct jffs2_sb_info *c, struct jffs2_inode_inf
break;
default:
- if (JFFS2_MIN_NODE_HEADER < sizeof(struct jffs2_unknown_node)) {
+ if (JFFS2_MIN_NODE_HEADER < sizeof(struct jffs2_unknown_node) &&
+ len < sizeof(struct jffs2_unknown_node)) {
err = read_more(c, ref, sizeof(struct jffs2_unknown_node), &len, buf);
if (unlikely(err))
goto free_out;
}
err = read_unknown(c, ref, &node->u);
- if (err == 1) {
- jffs2_mark_node_obsolete(c, ref);
- break;
- } else if (unlikely(err))
+ if (unlikely(err))
goto free_out;
}
diff --git a/fs/jffs2/super.c b/fs/jffs2/super.c
index 45368f8bbe7..e220d3bd610 100644
--- a/fs/jffs2/super.c
+++ b/fs/jffs2/super.c
@@ -19,7 +19,7 @@
#include <linux/mount.h>
#include <linux/jffs2.h>
#include <linux/pagemap.h>
-#include <linux/mtd/mtd.h>
+#include <linux/mtd/super.h>
#include <linux/ctype.h>
#include <linux/namei.h>
#include "compr.h"
@@ -47,10 +47,8 @@ static void jffs2_i_init_once(void * foo, struct kmem_cache * cachep, unsigned l
{
struct jffs2_inode_info *ei = (struct jffs2_inode_info *) foo;
- if (flags & SLAB_CTOR_CONSTRUCTOR) {
- init_MUTEX(&ei->sem);
- inode_init_once(&ei->vfs_inode);
- }
+ init_MUTEX(&ei->sem);
+ inode_init_once(&ei->vfs_inode);
}
static int jffs2_sync_fs(struct super_block *sb, int wait)
@@ -77,69 +75,27 @@ static const struct super_operations jffs2_super_operations =
.sync_fs = jffs2_sync_fs,
};
-static int jffs2_sb_compare(struct super_block *sb, void *data)
-{
- struct jffs2_sb_info *p = data;
- struct jffs2_sb_info *c = JFFS2_SB_INFO(sb);
-
- /* The superblocks are considered to be equivalent if the underlying MTD
- device is the same one */
- if (c->mtd == p->mtd) {
- D1(printk(KERN_DEBUG "jffs2_sb_compare: match on device %d (\"%s\")\n", p->mtd->index, p->mtd->name));
- return 1;
- } else {
- D1(printk(KERN_DEBUG "jffs2_sb_compare: No match, device %d (\"%s\"), device %d (\"%s\")\n",
- c->mtd->index, c->mtd->name, p->mtd->index, p->mtd->name));
- return 0;
- }
-}
-
-static int jffs2_sb_set(struct super_block *sb, void *data)
-{
- struct jffs2_sb_info *p = data;
-
- /* For persistence of NFS exports etc. we use the same s_dev
- each time we mount the device, don't just use an anonymous
- device */
- sb->s_fs_info = p;
- p->os_priv = sb;
- sb->s_dev = MKDEV(MTD_BLOCK_MAJOR, p->mtd->index);
-
- return 0;
-}
-
-static int jffs2_get_sb_mtd(struct file_system_type *fs_type,
- int flags, const char *dev_name,
- void *data, struct mtd_info *mtd,
- struct vfsmount *mnt)
+/*
+ * fill in the superblock
+ */
+static int jffs2_fill_super(struct super_block *sb, void *data, int silent)
{
- struct super_block *sb;
struct jffs2_sb_info *c;
- int ret;
+
+ D1(printk(KERN_DEBUG "jffs2_get_sb_mtd():"
+ " New superblock for device %d (\"%s\")\n",
+ sb->s_mtd->index, sb->s_mtd->name));
c = kzalloc(sizeof(*c), GFP_KERNEL);
if (!c)
return -ENOMEM;
- c->mtd = mtd;
- sb = sget(fs_type, jffs2_sb_compare, jffs2_sb_set, c);
-
- if (IS_ERR(sb))
- goto out_error;
-
- if (sb->s_root) {
- /* New mountpoint for JFFS2 which is already mounted */
- D1(printk(KERN_DEBUG "jffs2_get_sb_mtd(): Device %d (\"%s\") is already mounted\n",
- mtd->index, mtd->name));
- ret = simple_set_mnt(mnt, sb);
- goto out_put;
- }
+ c->mtd = sb->s_mtd;
+ c->os_priv = sb;
+ sb->s_fs_info = c;
- D1(printk(KERN_DEBUG "jffs2_get_sb_mtd(): New superblock for device %d (\"%s\")\n",
- mtd->index, mtd->name));
-
- /* Initialize JFFS2 superblock locks, the further initialization will be
- * done later */
+ /* Initialize JFFS2 superblock locks, the further initialization will
+ * be done later */
init_MUTEX(&c->alloc_sem);
init_MUTEX(&c->erase_free_sem);
init_waitqueue_head(&c->erase_wait);
@@ -148,133 +104,20 @@ static int jffs2_get_sb_mtd(struct file_system_type *fs_type,
spin_lock_init(&c->inocache_lock);
sb->s_op = &jffs2_super_operations;
- sb->s_flags = flags | MS_NOATIME;
+ sb->s_flags = sb->s_flags | MS_NOATIME;
sb->s_xattr = jffs2_xattr_handlers;
#ifdef CONFIG_JFFS2_FS_POSIX_ACL
sb->s_flags |= MS_POSIXACL;
#endif
- ret = jffs2_do_fill_super(sb, data, flags & MS_SILENT ? 1 : 0);
-
- if (ret) {
- /* Failure case... */
- up_write(&sb->s_umount);
- deactivate_super(sb);
- return ret;
- }
-
- sb->s_flags |= MS_ACTIVE;
- return simple_set_mnt(mnt, sb);
-
-out_error:
- ret = PTR_ERR(sb);
- out_put:
- kfree(c);
- put_mtd_device(mtd);
-
- return ret;
-}
-
-static int jffs2_get_sb_mtdnr(struct file_system_type *fs_type,
- int flags, const char *dev_name,
- void *data, int mtdnr,
- struct vfsmount *mnt)
-{
- struct mtd_info *mtd;
-
- mtd = get_mtd_device(NULL, mtdnr);
- if (IS_ERR(mtd)) {
- D1(printk(KERN_DEBUG "jffs2: MTD device #%u doesn't appear to exist\n", mtdnr));
- return PTR_ERR(mtd);
- }
-
- return jffs2_get_sb_mtd(fs_type, flags, dev_name, data, mtd, mnt);
+ return jffs2_do_fill_super(sb, data, silent);
}
static int jffs2_get_sb(struct file_system_type *fs_type,
int flags, const char *dev_name,
void *data, struct vfsmount *mnt)
{
- int err;
- struct nameidata nd;
- int mtdnr;
-
- if (!dev_name)
- return -EINVAL;
-
- D1(printk(KERN_DEBUG "jffs2_get_sb(): dev_name \"%s\"\n", dev_name));
-
- /* The preferred way of mounting in future; especially when
- CONFIG_BLK_DEV is implemented - we specify the underlying
- MTD device by number or by name, so that we don't require
- block device support to be present in the kernel. */
-
- /* FIXME: How to do the root fs this way? */
-
- if (dev_name[0] == 'm' && dev_name[1] == 't' && dev_name[2] == 'd') {
- /* Probably mounting without the blkdev crap */
- if (dev_name[3] == ':') {
- struct mtd_info *mtd;
-
- /* Mount by MTD device name */
- D1(printk(KERN_DEBUG "jffs2_get_sb(): mtd:%%s, name \"%s\"\n", dev_name+4));
- for (mtdnr = 0; mtdnr < MAX_MTD_DEVICES; mtdnr++) {
- mtd = get_mtd_device(NULL, mtdnr);
- if (!IS_ERR(mtd)) {
- if (!strcmp(mtd->name, dev_name+4))
- return jffs2_get_sb_mtd(fs_type, flags, dev_name, data, mtd, mnt);
- put_mtd_device(mtd);
- }
- }
- printk(KERN_NOTICE "jffs2_get_sb(): MTD device with name \"%s\" not found.\n", dev_name+4);
- } else if (isdigit(dev_name[3])) {
- /* Mount by MTD device number name */
- char *endptr;
-
- mtdnr = simple_strtoul(dev_name+3, &endptr, 0);
- if (!*endptr) {
- /* It was a valid number */
- D1(printk(KERN_DEBUG "jffs2_get_sb(): mtd%%d, mtdnr %d\n", mtdnr));
- return jffs2_get_sb_mtdnr(fs_type, flags, dev_name, data, mtdnr, mnt);
- }
- }
- }
-
- /* Try the old way - the hack where we allowed users to mount
- /dev/mtdblock$(n) but didn't actually _use_ the blkdev */
-
- err = path_lookup(dev_name, LOOKUP_FOLLOW, &nd);
-
- D1(printk(KERN_DEBUG "jffs2_get_sb(): path_lookup() returned %d, inode %p\n",
- err, nd.dentry->d_inode));
-
- if (err)
- return err;
-
- err = -EINVAL;
-
- if (!S_ISBLK(nd.dentry->d_inode->i_mode))
- goto out;
-
- if (nd.mnt->mnt_flags & MNT_NODEV) {
- err = -EACCES;
- goto out;
- }
-
- if (imajor(nd.dentry->d_inode) != MTD_BLOCK_MAJOR) {
- if (!(flags & MS_SILENT))
- printk(KERN_NOTICE "Attempt to mount non-MTD device \"%s\" as JFFS2\n",
- dev_name);
- goto out;
- }
-
- mtdnr = iminor(nd.dentry->d_inode);
- path_release(&nd);
-
- return jffs2_get_sb_mtdnr(fs_type, flags, dev_name, data, mtdnr, mnt);
-
-out:
- path_release(&nd);
- return err;
+ return get_sb_mtd(fs_type, flags, dev_name, data, jffs2_fill_super,
+ mnt);
}
static void jffs2_put_super (struct super_block *sb)
@@ -309,8 +152,7 @@ static void jffs2_kill_sb(struct super_block *sb)
struct jffs2_sb_info *c = JFFS2_SB_INFO(sb);
if (!(sb->s_flags & MS_RDONLY))
jffs2_stop_garbage_collect_thread(c);
- generic_shutdown_super(sb);
- put_mtd_device(c->mtd);
+ kill_mtd_super(sb);
kfree(c);
}
diff --git a/fs/jffs2/wbuf.c b/fs/jffs2/wbuf.c
index c556e85a565..91d1d0f1c66 100644
--- a/fs/jffs2/wbuf.c
+++ b/fs/jffs2/wbuf.c
@@ -637,7 +637,10 @@ static int __jffs2_flush_wbuf(struct jffs2_sb_info *c, int pad)
memset(c->wbuf,0xff,c->wbuf_pagesize);
/* adjust write buffer offset, else we get a non contiguous write bug */
- c->wbuf_ofs += c->wbuf_pagesize;
+ if (SECTOR_ADDR(c->wbuf_ofs) == SECTOR_ADDR(c->wbuf_ofs+c->wbuf_pagesize))
+ c->wbuf_ofs += c->wbuf_pagesize;
+ else
+ c->wbuf_ofs = 0xffffffff;
c->wbuf_len = 0;
return 0;
}
diff --git a/fs/jffs2/xattr.c b/fs/jffs2/xattr.c
index 78fc08893a6..e48665984cb 100644
--- a/fs/jffs2/xattr.c
+++ b/fs/jffs2/xattr.c
@@ -754,6 +754,10 @@ void jffs2_clear_xattr_subsystem(struct jffs2_sb_info *c)
list_del(&xd->xindex);
jffs2_free_xattr_datum(xd);
}
+ list_for_each_entry_safe(xd, _xd, &c->xattr_unchecked, xindex) {
+ list_del(&xd->xindex);
+ jffs2_free_xattr_datum(xd);
+ }
}
#define XREF_TMPHASH_SIZE (128)
@@ -825,7 +829,7 @@ void jffs2_build_xattr_subsystem(struct jffs2_sb_info *c)
ref->xd and ref->ic are not valid yet. */
xd = jffs2_find_xattr_datum(c, ref->xid);
ic = jffs2_get_ino_cache(c, ref->ino);
- if (!xd || !ic) {
+ if (!xd || !ic || !ic->nlink) {
dbg_xattr("xref(ino=%u, xid=%u, xseqno=%u) is orphan.\n",
ref->ino, ref->xid, ref->xseqno);
ref->xseqno |= XREF_DELETE_MARKER;
diff --git a/fs/jfs/inode.c b/fs/jfs/inode.c
index e285022f006..3467dde27e5 100644
--- a/fs/jfs/inode.c
+++ b/fs/jfs/inode.c
@@ -55,7 +55,6 @@ void jfs_read_inode(struct inode *inode)
inode->i_op = &jfs_file_inode_operations;
init_special_inode(inode, inode->i_mode, inode->i_rdev);
}
- jfs_set_inode_flags(inode);
}
/*
diff --git a/fs/jfs/ioctl.c b/fs/jfs/ioctl.c
index ed814b1ff4d..fe063af6fd2 100644
--- a/fs/jfs/ioctl.c
+++ b/fs/jfs/ioctl.c
@@ -59,6 +59,7 @@ int jfs_ioctl(struct inode * inode, struct file * filp, unsigned int cmd,
switch (cmd) {
case JFS_IOC_GETFLAGS:
+ jfs_get_inode_flags(jfs_inode);
flags = jfs_inode->mode2 & JFS_FL_USER_VISIBLE;
flags = jfs_map_ext2(flags, 0);
return put_user(flags, (int __user *) arg);
@@ -78,6 +79,7 @@ int jfs_ioctl(struct inode * inode, struct file * filp, unsigned int cmd,
if (!S_ISDIR(inode->i_mode))
flags &= ~JFS_DIRSYNC_FL;
+ jfs_get_inode_flags(jfs_inode);
oldflags = jfs_inode->mode2;
/*
diff --git a/fs/jfs/jfs_dmap.c b/fs/jfs/jfs_dmap.c
index 82b0544bd76..f3b1ebb2228 100644
--- a/fs/jfs/jfs_dmap.c
+++ b/fs/jfs/jfs_dmap.c
@@ -1507,7 +1507,7 @@ dbAllocAG(struct bmap * bmp, int agno, s64 nblocks, int l2nb, s64 * results)
if (l2nb < budmin) {
/* search the lower level dmap control pages to get
- * the starting block number of the the dmap that
+ * the starting block number of the dmap that
* contains or starts off the free space.
*/
if ((rc =
diff --git a/fs/jfs/jfs_imap.c b/fs/jfs/jfs_imap.c
index aa5124b643b..c6530227cda 100644
--- a/fs/jfs/jfs_imap.c
+++ b/fs/jfs/jfs_imap.c
@@ -386,7 +386,7 @@ int diRead(struct inode *ip)
return -EIO;
}
- /* locate the the disk inode requested */
+ /* locate the disk inode requested */
dp = (struct dinode *) mp->data;
dp += rel_inode;
@@ -1407,7 +1407,7 @@ int diAlloc(struct inode *pip, bool dir, struct inode *ip)
inum = pip->i_ino + 1;
ino = inum & (INOSPERIAG - 1);
- /* back off the the hint if it is outside of the iag */
+ /* back off the hint if it is outside of the iag */
if (ino == 0)
inum = pip->i_ino;
@@ -3078,6 +3078,7 @@ static int copy_from_dinode(struct dinode * dip, struct inode *ip)
jfs_ip->fileset = le32_to_cpu(dip->di_fileset);
jfs_ip->mode2 = le32_to_cpu(dip->di_mode);
+ jfs_set_inode_flags(ip);
ip->i_mode = le32_to_cpu(dip->di_mode) & 0xffff;
if (sbi->umask != -1) {
@@ -3174,6 +3175,7 @@ static void copy_to_dinode(struct dinode * dip, struct inode *ip)
dip->di_gid = cpu_to_le32(ip->i_gid);
else
dip->di_gid = cpu_to_le32(jfs_ip->saved_gid);
+ jfs_get_inode_flags(jfs_ip);
/*
* mode2 is only needed for storing the higher order bits.
* Trust i_mode for the lower order ones
diff --git a/fs/jfs/jfs_inode.c b/fs/jfs/jfs_inode.c
index 4c67ed97682..ed6574bee51 100644
--- a/fs/jfs/jfs_inode.c
+++ b/fs/jfs/jfs_inode.c
@@ -45,6 +45,24 @@ void jfs_set_inode_flags(struct inode *inode)
inode->i_flags |= S_SYNC;
}
+void jfs_get_inode_flags(struct jfs_inode_info *jfs_ip)
+{
+ unsigned int flags = jfs_ip->vfs_inode.i_flags;
+
+ jfs_ip->mode2 &= ~(JFS_IMMUTABLE_FL | JFS_APPEND_FL | JFS_NOATIME_FL |
+ JFS_DIRSYNC_FL | JFS_SYNC_FL);
+ if (flags & S_IMMUTABLE)
+ jfs_ip->mode2 |= JFS_IMMUTABLE_FL;
+ if (flags & S_APPEND)
+ jfs_ip->mode2 |= JFS_APPEND_FL;
+ if (flags & S_NOATIME)
+ jfs_ip->mode2 |= JFS_NOATIME_FL;
+ if (flags & S_DIRSYNC)
+ jfs_ip->mode2 |= JFS_DIRSYNC_FL;
+ if (flags & S_SYNC)
+ jfs_ip->mode2 |= JFS_SYNC_FL;
+}
+
/*
* NAME: ialloc()
*
diff --git a/fs/jfs/jfs_inode.h b/fs/jfs/jfs_inode.h
index 6802837f757..2374b595f2e 100644
--- a/fs/jfs/jfs_inode.h
+++ b/fs/jfs/jfs_inode.h
@@ -31,6 +31,7 @@ extern void jfs_truncate(struct inode *);
extern void jfs_truncate_nolock(struct inode *, loff_t);
extern void jfs_free_zero_link(struct inode *);
extern struct dentry *jfs_get_parent(struct dentry *dentry);
+extern void jfs_get_inode_flags(struct jfs_inode_info *);
extern void jfs_set_inode_flags(struct inode *);
extern int jfs_get_block(struct inode *, sector_t, struct buffer_head *, int);
diff --git a/fs/jfs/jfs_lock.h b/fs/jfs/jfs_lock.h
index df48ece4b7a..ecf04882265 100644
--- a/fs/jfs/jfs_lock.h
+++ b/fs/jfs/jfs_lock.h
@@ -45,7 +45,7 @@ do { \
io_schedule(); \
lock_cmd; \
} \
- current->state = TASK_RUNNING; \
+ __set_current_state(TASK_RUNNING); \
remove_wait_queue(&wq, &__wait); \
} while (0)
diff --git a/fs/jfs/jfs_logmgr.c b/fs/jfs/jfs_logmgr.c
index 5065baa530b..44a2f33cb98 100644
--- a/fs/jfs/jfs_logmgr.c
+++ b/fs/jfs/jfs_logmgr.c
@@ -62,7 +62,6 @@
#include <linux/fs.h>
#include <linux/blkdev.h>
#include <linux/interrupt.h>
-#include <linux/smp_lock.h>
#include <linux/completion.h>
#include <linux/kthread.h>
#include <linux/buffer_head.h> /* for sync_blockdev() */
@@ -1590,7 +1589,7 @@ void jfs_flush_journal(struct jfs_log *log, int wait)
set_current_state(TASK_UNINTERRUPTIBLE);
LOGGC_UNLOCK(log);
schedule();
- current->state = TASK_RUNNING;
+ __set_current_state(TASK_RUNNING);
LOGGC_LOCK(log);
remove_wait_queue(&target->gcwait, &__wait);
}
@@ -1961,7 +1960,7 @@ static void lbmfree(struct lbuf * bp)
/*
* NAME: lbmRedrive
*
- * FUNCTION: add a log buffer to the the log redrive list
+ * FUNCTION: add a log buffer to the log redrive list
*
* PARAMETER:
* bp - log buffer
@@ -2354,14 +2353,15 @@ int jfsIOWait(void *arg)
lbmStartIO(bp);
spin_lock_irq(&log_redrive_lock);
}
- spin_unlock_irq(&log_redrive_lock);
if (freezing(current)) {
+ spin_unlock_irq(&log_redrive_lock);
refrigerator();
} else {
set_current_state(TASK_INTERRUPTIBLE);
+ spin_unlock_irq(&log_redrive_lock);
schedule();
- current->state = TASK_RUNNING;
+ __set_current_state(TASK_RUNNING);
}
} while (!kthread_should_stop());
diff --git a/fs/jfs/jfs_metapage.c b/fs/jfs/jfs_metapage.c
index 6b3acb0b578..43d4f69afbe 100644
--- a/fs/jfs/jfs_metapage.c
+++ b/fs/jfs/jfs_metapage.c
@@ -184,16 +184,14 @@ static void init_once(void *foo, struct kmem_cache *cachep, unsigned long flags)
{
struct metapage *mp = (struct metapage *)foo;
- if (flags & SLAB_CTOR_CONSTRUCTOR) {
- mp->lid = 0;
- mp->lsn = 0;
- mp->flag = 0;
- mp->data = NULL;
- mp->clsn = 0;
- mp->log = NULL;
- set_bit(META_free, &mp->flag);
- init_waitqueue_head(&mp->wait);
- }
+ mp->lid = 0;
+ mp->lsn = 0;
+ mp->flag = 0;
+ mp->data = NULL;
+ mp->clsn = 0;
+ mp->log = NULL;
+ set_bit(META_free, &mp->flag);
+ init_waitqueue_head(&mp->wait);
}
static inline struct metapage *alloc_metapage(gfp_t gfp_mask)
diff --git a/fs/jfs/jfs_txnmgr.c b/fs/jfs/jfs_txnmgr.c
index 03893acbfda..25430d0b0d5 100644
--- a/fs/jfs/jfs_txnmgr.c
+++ b/fs/jfs/jfs_txnmgr.c
@@ -44,7 +44,6 @@
#include <linux/fs.h>
#include <linux/vmalloc.h>
-#include <linux/smp_lock.h>
#include <linux/completion.h>
#include <linux/freezer.h>
#include <linux/module.h>
@@ -136,7 +135,7 @@ static inline void TXN_SLEEP_DROP_LOCK(wait_queue_head_t * event)
set_current_state(TASK_UNINTERRUPTIBLE);
TXN_UNLOCK();
io_schedule();
- current->state = TASK_RUNNING;
+ __set_current_state(TASK_RUNNING);
remove_wait_queue(event, &wait);
}
@@ -2798,7 +2797,7 @@ int jfs_lazycommit(void *arg)
set_current_state(TASK_INTERRUPTIBLE);
LAZY_UNLOCK(flags);
schedule();
- current->state = TASK_RUNNING;
+ __set_current_state(TASK_RUNNING);
remove_wait_queue(&jfs_commit_thread_wait, &wq);
}
} while (!kthread_should_stop());
@@ -2990,7 +2989,7 @@ int jfs_sync(void *arg)
set_current_state(TASK_INTERRUPTIBLE);
TXN_UNLOCK();
schedule();
- current->state = TASK_RUNNING;
+ __set_current_state(TASK_RUNNING);
}
} while (!kthread_should_stop());
diff --git a/fs/jfs/super.c b/fs/jfs/super.c
index ea9dc3e65dc..20e4ac1c79a 100644
--- a/fs/jfs/super.c
+++ b/fs/jfs/super.c
@@ -752,20 +752,18 @@ static void init_once(void *foo, struct kmem_cache * cachep, unsigned long flags
{
struct jfs_inode_info *jfs_ip = (struct jfs_inode_info *) foo;
- if (flags & SLAB_CTOR_CONSTRUCTOR) {
- memset(jfs_ip, 0, sizeof(struct jfs_inode_info));
- INIT_LIST_HEAD(&jfs_ip->anon_inode_list);
- init_rwsem(&jfs_ip->rdwrlock);
- mutex_init(&jfs_ip->commit_mutex);
- init_rwsem(&jfs_ip->xattr_sem);
- spin_lock_init(&jfs_ip->ag_lock);
- jfs_ip->active_ag = -1;
+ memset(jfs_ip, 0, sizeof(struct jfs_inode_info));
+ INIT_LIST_HEAD(&jfs_ip->anon_inode_list);
+ init_rwsem(&jfs_ip->rdwrlock);
+ mutex_init(&jfs_ip->commit_mutex);
+ init_rwsem(&jfs_ip->xattr_sem);
+ spin_lock_init(&jfs_ip->ag_lock);
+ jfs_ip->active_ag = -1;
#ifdef CONFIG_JFS_POSIX_ACL
- jfs_ip->i_acl = JFS_ACL_NOT_CACHED;
- jfs_ip->i_default_acl = JFS_ACL_NOT_CACHED;
+ jfs_ip->i_acl = JFS_ACL_NOT_CACHED;
+ jfs_ip->i_default_acl = JFS_ACL_NOT_CACHED;
#endif
- inode_init_once(&jfs_ip->vfs_inode);
- }
+ inode_init_once(&jfs_ip->vfs_inode);
}
static int __init init_jfs_fs(void)
diff --git a/fs/libfs.c b/fs/libfs.c
index d93842d3c0a..5294de1f40c 100644
--- a/fs/libfs.c
+++ b/fs/libfs.c
@@ -159,7 +159,10 @@ int dcache_readdir(struct file * filp, void * dirent, filldir_t filldir)
continue;
spin_unlock(&dcache_lock);
- if (filldir(dirent, next->d_name.name, next->d_name.len, filp->f_pos, next->d_inode->i_ino, dt_type(next->d_inode)) < 0)
+ if (filldir(dirent, next->d_name.name,
+ next->d_name.len, filp->f_pos,
+ next->d_inode->i_ino,
+ dt_type(next->d_inode)) < 0)
return 0;
spin_lock(&dcache_lock);
/* next is still alive */
@@ -220,6 +223,12 @@ int get_sb_pseudo(struct file_system_type *fs_type, char *name,
root = new_inode(s);
if (!root)
goto Enomem;
+ /*
+ * since this is the first inode, make it number 1. New inodes created
+ * after this must take care not to collide with it (by passing
+ * max_reserved of 1 to iunique).
+ */
+ root->i_ino = 1;
root->i_mode = S_IFDIR | S_IRUSR | S_IWUSR;
root->i_uid = root->i_gid = 0;
root->i_atime = root->i_mtime = root->i_ctime = CURRENT_TIME;
@@ -360,6 +369,11 @@ int simple_commit_write(struct file *file, struct page *page,
return 0;
}
+/*
+ * the inodes created here are not hashed. If you use iunique to generate
+ * unique inode values later for this filesystem, then you must take care
+ * to pass it an appropriate max_reserved value to avoid collisions.
+ */
int simple_fill_super(struct super_block *s, int magic, struct tree_descr *files)
{
struct inode *inode;
@@ -376,6 +390,11 @@ int simple_fill_super(struct super_block *s, int magic, struct tree_descr *files
inode = new_inode(s);
if (!inode)
return -ENOMEM;
+ /*
+ * because the root inode is 1, the files array must not contain an
+ * entry at index 1
+ */
+ inode->i_ino = 1;
inode->i_mode = S_IFDIR | 0755;
inode->i_uid = inode->i_gid = 0;
inode->i_blocks = 0;
@@ -391,6 +410,13 @@ int simple_fill_super(struct super_block *s, int magic, struct tree_descr *files
for (i = 0; !files->name || files->name[0]; i++, files++) {
if (!files->name)
continue;
+
+ /* warn if it tries to conflict with the root inode */
+ if (unlikely(i == 1))
+ printk(KERN_WARNING "%s: %s passed in a files array"
+ "with an index of 1!\n", __func__,
+ s->s_type->name);
+
dentry = d_alloc_name(root, files->name);
if (!dentry)
goto out;
diff --git a/fs/lockd/clntlock.c b/fs/lockd/clntlock.c
index f4d45d4d835..d070b18e539 100644
--- a/fs/lockd/clntlock.c
+++ b/fs/lockd/clntlock.c
@@ -153,7 +153,7 @@ nlmclnt_recovery(struct nlm_host *host)
if (!host->h_reclaiming++) {
nlm_get_host(host);
__module_get(THIS_MODULE);
- if (kernel_thread(reclaimer, host, CLONE_KERNEL) < 0)
+ if (kernel_thread(reclaimer, host, CLONE_FS | CLONE_FILES) < 0)
module_put(THIS_MODULE);
}
}
diff --git a/fs/lockd/clntproc.c b/fs/lockd/clntproc.c
index a5c019e1a44..a10343bed16 100644
--- a/fs/lockd/clntproc.c
+++ b/fs/lockd/clntproc.c
@@ -12,7 +12,6 @@
#include <linux/fs.h>
#include <linux/nfs_fs.h>
#include <linux/utsname.h>
-#include <linux/smp_lock.h>
#include <linux/freezer.h>
#include <linux/sunrpc/clnt.h>
#include <linux/sunrpc/svc.h>
diff --git a/fs/lockd/host.c b/fs/lockd/host.c
index ad21c0713ef..96070bff93f 100644
--- a/fs/lockd/host.c
+++ b/fs/lockd/host.c
@@ -221,7 +221,7 @@ nlm_bind_host(struct nlm_host *host)
host->h_nextrebind - jiffies);
}
} else {
- unsigned long increment = nlmsvc_timeout * HZ;
+ unsigned long increment = nlmsvc_timeout;
struct rpc_timeout timeparms = {
.to_initval = increment,
.to_increment = increment,
diff --git a/fs/lockd/xdr.c b/fs/lockd/xdr.c
index 9702956d206..5316e307a49 100644
--- a/fs/lockd/xdr.c
+++ b/fs/lockd/xdr.c
@@ -586,10 +586,6 @@ static struct rpc_version nlm_version3 = {
.procs = nlm_procedures,
};
-#ifdef CONFIG_LOCKD_V4
-extern struct rpc_version nlm_version4;
-#endif
-
static struct rpc_version * nlm_versions[] = {
[1] = &nlm_version1,
[3] = &nlm_version3,
diff --git a/fs/lockd/xdr4.c b/fs/lockd/xdr4.c
index ce1efdbe1b3..846fc1d639d 100644
--- a/fs/lockd/xdr4.c
+++ b/fs/lockd/xdr4.c
@@ -123,7 +123,8 @@ static __be32 *
nlm4_decode_lock(__be32 *p, struct nlm_lock *lock)
{
struct file_lock *fl = &lock->fl;
- __s64 len, start, end;
+ __u64 len, start;
+ __s64 end;
if (!(p = xdr_decode_string_inplace(p, &lock->caller,
&lock->len, NLM_MAXSTRLEN))
@@ -417,7 +418,8 @@ nlm4clt_decode_testres(struct rpc_rqst *req, __be32 *p, struct nlm_res *resp)
if (resp->status == nlm_lck_denied) {
struct file_lock *fl = &resp->lock.fl;
u32 excl;
- s64 start, end, len;
+ __u64 start, len;
+ __s64 end;
memset(&resp->lock, 0, sizeof(resp->lock));
locks_init_lock(fl);
diff --git a/fs/locks.c b/fs/locks.c
index 671a034dc99..431a8b871fc 100644
--- a/fs/locks.c
+++ b/fs/locks.c
@@ -203,9 +203,6 @@ static void init_once(void *foo, struct kmem_cache *cache, unsigned long flags)
{
struct file_lock *lock = (struct file_lock *) foo;
- if (!(flags & SLAB_CTOR_CONSTRUCTOR))
- return;
-
locks_init_lock(lock);
}
@@ -669,7 +666,6 @@ posix_test_lock(struct file *filp, struct file_lock *fl)
{
struct file_lock *cfl;
- fl->fl_type = F_UNLCK;
lock_kernel();
for (cfl = filp->f_path.dentry->d_inode->i_flock; cfl; cfl = cfl->fl_next) {
if (!IS_POSIX(cfl))
@@ -681,7 +677,8 @@ posix_test_lock(struct file *filp, struct file_lock *fl)
__locks_copy_lock(fl, cfl);
unlock_kernel();
return 1;
- }
+ } else
+ fl->fl_type = F_UNLCK;
unlock_kernel();
return 0;
}
@@ -1632,6 +1629,7 @@ static int posix_lock_to_flock(struct flock *flock, struct file_lock *fl)
flock->l_len = fl->fl_end == OFFSET_MAX ? 0 :
fl->fl_end - fl->fl_start + 1;
flock->l_whence = 0;
+ flock->l_type = fl->fl_type;
return 0;
}
diff --git a/fs/minix/bitmap.c b/fs/minix/bitmap.c
index c4a554df7b7..99a12f12776 100644
--- a/fs/minix/bitmap.c
+++ b/fs/minix/bitmap.c
@@ -15,6 +15,7 @@
#include <linux/smp_lock.h>
#include <linux/buffer_head.h>
#include <linux/bitops.h>
+#include <linux/sched.h>
static int nibblemap[] = { 4,3,3,2,3,2,2,1,3,2,2,1,2,1,1,0 };
diff --git a/fs/minix/inode.c b/fs/minix/inode.c
index 2f4d43a2a31..be4044614ac 100644
--- a/fs/minix/inode.c
+++ b/fs/minix/inode.c
@@ -73,8 +73,7 @@ static void init_once(void * foo, struct kmem_cache * cachep, unsigned long flag
{
struct minix_inode_info *ei = (struct minix_inode_info *) foo;
- if (flags & SLAB_CTOR_CONSTRUCTOR)
- inode_init_once(&ei->vfs_inode);
+ inode_init_once(&ei->vfs_inode);
}
static int init_inodecache(void)
diff --git a/fs/mpage.c b/fs/mpage.c
index 692a3e578fc..c1698f2291a 100644
--- a/fs/mpage.c
+++ b/fs/mpage.c
@@ -284,11 +284,9 @@ do_mpage_readpage(struct bio *bio, struct page *page, unsigned nr_pages,
}
if (first_hole != blocks_per_page) {
- char *kaddr = kmap_atomic(page, KM_USER0);
- memset(kaddr + (first_hole << blkbits), 0,
- PAGE_CACHE_SIZE - (first_hole << blkbits));
- flush_dcache_page(page);
- kunmap_atomic(kaddr, KM_USER0);
+ zero_user_page(page, first_hole << blkbits,
+ PAGE_CACHE_SIZE - (first_hole << blkbits),
+ KM_USER0);
if (first_hole == 0) {
SetPageUptodate(page);
unlock_page(page);
@@ -456,11 +454,18 @@ EXPORT_SYMBOL(mpage_readpage);
* written, so it can intelligently allocate a suitably-sized BIO. For now,
* just allocate full-size (16-page) BIOs.
*/
-static struct bio *
-__mpage_writepage(struct bio *bio, struct page *page, get_block_t get_block,
- sector_t *last_block_in_bio, int *ret, struct writeback_control *wbc,
- writepage_t writepage_fn)
+struct mpage_data {
+ struct bio *bio;
+ sector_t last_block_in_bio;
+ get_block_t *get_block;
+ unsigned use_writepage;
+};
+
+static int __mpage_writepage(struct page *page, struct writeback_control *wbc,
+ void *data)
{
+ struct mpage_data *mpd = data;
+ struct bio *bio = mpd->bio;
struct address_space *mapping = page->mapping;
struct inode *inode = page->mapping->host;
const unsigned blkbits = inode->i_blkbits;
@@ -478,6 +483,7 @@ __mpage_writepage(struct bio *bio, struct page *page, get_block_t get_block,
int length;
struct buffer_head map_bh;
loff_t i_size = i_size_read(inode);
+ int ret = 0;
if (page_has_buffers(page)) {
struct buffer_head *head = page_buffers(page);
@@ -540,7 +546,7 @@ __mpage_writepage(struct bio *bio, struct page *page, get_block_t get_block,
map_bh.b_state = 0;
map_bh.b_size = 1 << blkbits;
- if (get_block(inode, block_in_file, &map_bh, 1))
+ if (mpd->get_block(inode, block_in_file, &map_bh, 1))
goto confused;
if (buffer_new(&map_bh))
unmap_underlying_metadata(map_bh.b_bdev,
@@ -576,20 +582,17 @@ page_is_mapped:
* written out to the file."
*/
unsigned offset = i_size & (PAGE_CACHE_SIZE - 1);
- char *kaddr;
if (page->index > end_index || !offset)
goto confused;
- kaddr = kmap_atomic(page, KM_USER0);
- memset(kaddr + offset, 0, PAGE_CACHE_SIZE - offset);
- flush_dcache_page(page);
- kunmap_atomic(kaddr, KM_USER0);
+ zero_user_page(page, offset, PAGE_CACHE_SIZE - offset,
+ KM_USER0);
}
/*
* This page will go to BIO. Do we need to send this BIO off first?
*/
- if (bio && *last_block_in_bio != blocks[0] - 1)
+ if (bio && mpd->last_block_in_bio != blocks[0] - 1)
bio = mpage_bio_submit(WRITE, bio);
alloc_new:
@@ -646,7 +649,7 @@ alloc_new:
boundary_block, 1 << blkbits);
}
} else {
- *last_block_in_bio = blocks[blocks_per_page - 1];
+ mpd->last_block_in_bio = blocks[blocks_per_page - 1];
}
goto out;
@@ -654,23 +657,19 @@ confused:
if (bio)
bio = mpage_bio_submit(WRITE, bio);
- if (writepage_fn) {
- *ret = (*writepage_fn)(page, wbc);
+ if (mpd->use_writepage) {
+ ret = mapping->a_ops->writepage(page, wbc);
} else {
- *ret = -EAGAIN;
+ ret = -EAGAIN;
goto out;
}
/*
* The caller has a ref on the inode, so *mapping is stable
*/
- if (*ret) {
- if (*ret == -ENOSPC)
- set_bit(AS_ENOSPC, &mapping->flags);
- else
- set_bit(AS_EIO, &mapping->flags);
- }
+ mapping_set_error(mapping, ret);
out:
- return bio;
+ mpd->bio = bio;
+ return ret;
}
/**
@@ -693,127 +692,27 @@ out:
* the call was made get new I/O started against them. If wbc->sync_mode is
* WB_SYNC_ALL then we were called for data integrity and we must wait for
* existing IO to complete.
- *
- * If you fix this you should check generic_writepages() also!
*/
int
mpage_writepages(struct address_space *mapping,
struct writeback_control *wbc, get_block_t get_block)
{
- struct backing_dev_info *bdi = mapping->backing_dev_info;
- struct bio *bio = NULL;
- sector_t last_block_in_bio = 0;
- int ret = 0;
- int done = 0;
- int (*writepage)(struct page *page, struct writeback_control *wbc);
- struct pagevec pvec;
- int nr_pages;
- pgoff_t index;
- pgoff_t end; /* Inclusive */
- int scanned = 0;
- int range_whole = 0;
-
- if (wbc->nonblocking && bdi_write_congested(bdi)) {
- wbc->encountered_congestion = 1;
- return 0;
- }
-
- writepage = NULL;
- if (get_block == NULL)
- writepage = mapping->a_ops->writepage;
-
- pagevec_init(&pvec, 0);
- if (wbc->range_cyclic) {
- index = mapping->writeback_index; /* Start from prev offset */
- end = -1;
- } else {
- index = wbc->range_start >> PAGE_CACHE_SHIFT;
- end = wbc->range_end >> PAGE_CACHE_SHIFT;
- if (wbc->range_start == 0 && wbc->range_end == LLONG_MAX)
- range_whole = 1;
- scanned = 1;
- }
-retry:
- while (!done && (index <= end) &&
- (nr_pages = pagevec_lookup_tag(&pvec, mapping, &index,
- PAGECACHE_TAG_DIRTY,
- min(end - index, (pgoff_t)PAGEVEC_SIZE-1) + 1))) {
- unsigned i;
-
- scanned = 1;
- for (i = 0; i < nr_pages; i++) {
- struct page *page = pvec.pages[i];
-
- /*
- * At this point we hold neither mapping->tree_lock nor
- * lock on the page itself: the page may be truncated or
- * invalidated (changing page->mapping to NULL), or even
- * swizzled back from swapper_space to tmpfs file
- * mapping
- */
-
- lock_page(page);
-
- if (unlikely(page->mapping != mapping)) {
- unlock_page(page);
- continue;
- }
-
- if (!wbc->range_cyclic && page->index > end) {
- done = 1;
- unlock_page(page);
- continue;
- }
-
- if (wbc->sync_mode != WB_SYNC_NONE)
- wait_on_page_writeback(page);
-
- if (PageWriteback(page) ||
- !clear_page_dirty_for_io(page)) {
- unlock_page(page);
- continue;
- }
-
- if (writepage) {
- ret = (*writepage)(page, wbc);
- if (ret) {
- if (ret == -ENOSPC)
- set_bit(AS_ENOSPC,
- &mapping->flags);
- else
- set_bit(AS_EIO,
- &mapping->flags);
- }
- } else {
- bio = __mpage_writepage(bio, page, get_block,
- &last_block_in_bio, &ret, wbc,
- page->mapping->a_ops->writepage);
- }
- if (unlikely(ret == AOP_WRITEPAGE_ACTIVATE))
- unlock_page(page);
- if (ret || (--(wbc->nr_to_write) <= 0))
- done = 1;
- if (wbc->nonblocking && bdi_write_congested(bdi)) {
- wbc->encountered_congestion = 1;
- done = 1;
- }
- }
- pagevec_release(&pvec);
- cond_resched();
+ int ret;
+
+ if (!get_block)
+ ret = generic_writepages(mapping, wbc);
+ else {
+ struct mpage_data mpd = {
+ .bio = NULL,
+ .last_block_in_bio = 0,
+ .get_block = get_block,
+ .use_writepage = 1,
+ };
+
+ ret = write_cache_pages(mapping, wbc, __mpage_writepage, &mpd);
+ if (mpd.bio)
+ mpage_bio_submit(WRITE, mpd.bio);
}
- if (!scanned && !done) {
- /*
- * We hit the last page and there is more work to be done: wrap
- * back to the start of the file
- */
- scanned = 1;
- index = 0;
- goto retry;
- }
- if (wbc->range_cyclic || (range_whole && wbc->nr_to_write > 0))
- mapping->writeback_index = index;
- if (bio)
- mpage_bio_submit(WRITE, bio);
return ret;
}
EXPORT_SYMBOL(mpage_writepages);
@@ -821,15 +720,15 @@ EXPORT_SYMBOL(mpage_writepages);
int mpage_writepage(struct page *page, get_block_t get_block,
struct writeback_control *wbc)
{
- int ret = 0;
- struct bio *bio;
- sector_t last_block_in_bio = 0;
-
- bio = __mpage_writepage(NULL, page, get_block,
- &last_block_in_bio, &ret, wbc, NULL);
- if (bio)
- mpage_bio_submit(WRITE, bio);
-
+ struct mpage_data mpd = {
+ .bio = NULL,
+ .last_block_in_bio = 0,
+ .get_block = get_block,
+ .use_writepage = 0,
+ };
+ int ret = __mpage_writepage(page, wbc, &mpd);
+ if (mpd.bio)
+ mpage_bio_submit(WRITE, mpd.bio);
return ret;
}
EXPORT_SYMBOL(mpage_writepage);
diff --git a/fs/namei.c b/fs/namei.c
index 94b2f60aec2..5e2d98d10c5 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -22,7 +22,6 @@
#include <linux/quotaops.h>
#include <linux/pagemap.h>
#include <linux/fsnotify.h>
-#include <linux/smp_lock.h>
#include <linux/personality.h>
#include <linux/security.h>
#include <linux/syscalls.h>
@@ -1153,14 +1152,12 @@ static int fastcall do_path_lookup(int dfd, const char *name,
fput_light(file, fput_needed);
}
- current->total_link_count = 0;
- retval = link_path_walk(name, nd);
+
+ retval = path_walk(name, nd);
out:
- if (likely(retval == 0)) {
- if (unlikely(!audit_dummy_context() && nd && nd->dentry &&
+ if (unlikely(!retval && !audit_dummy_context() && nd->dentry &&
nd->dentry->d_inode))
audit_inode(name, nd->dentry->d_inode);
- }
out_fail:
return retval;
@@ -1350,17 +1347,6 @@ struct dentry *lookup_one_len_kern(const char *name, struct dentry *base, int le
return __lookup_hash_kern(&this, base, NULL);
}
-/*
- * namei()
- *
- * is used by most simple commands to get the inode of a specified name.
- * Open, link etc use their own routines, but this is enough for things
- * like 'chmod' etc.
- *
- * namei exists in two versions: namei/lnamei. The only difference is
- * that namei follows links, while lnamei does not.
- * SMP-safe
- */
int fastcall __user_walk_fd(int dfd, const char __user *name, unsigned flags,
struct nameidata *nd)
{
@@ -1733,7 +1719,7 @@ do_last:
* It already exists.
*/
mutex_unlock(&dir->d_inode->i_mutex);
- audit_inode_update(path.dentry->d_inode);
+ audit_inode(pathname, path.dentry->d_inode);
error = -EEXIST;
if (flag & O_EXCL)
diff --git a/fs/namespace.c b/fs/namespace.c
index fd999cab7b5..b696e3a0d18 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -377,6 +377,10 @@ static int show_vfsmnt(struct seq_file *m, void *v)
seq_path(m, mnt, mnt->mnt_root, " \t\n\\");
seq_putc(m, ' ');
mangle(m, mnt->mnt_sb->s_type->name);
+ if (mnt->mnt_sb->s_subtype && mnt->mnt_sb->s_subtype[0]) {
+ seq_putc(m, '.');
+ mangle(m, mnt->mnt_sb->s_subtype);
+ }
seq_puts(m, mnt->mnt_sb->s_flags & MS_RDONLY ? " ro" : " rw");
for (fs_infop = fs_info; fs_infop->flag; fs_infop++) {
if (mnt->mnt_sb->s_flags & fs_infop->flag)
@@ -495,7 +499,7 @@ void release_mounts(struct list_head *head)
{
struct vfsmount *mnt;
while (!list_empty(head)) {
- mnt = list_entry(head->next, struct vfsmount, mnt_hash);
+ mnt = list_first_entry(head, struct vfsmount, mnt_hash);
list_del_init(&mnt->mnt_hash);
if (mnt->mnt_parent != mnt) {
struct dentry *dentry;
@@ -882,6 +886,9 @@ static int do_change_type(struct nameidata *nd, int flag)
int recurse = flag & MS_REC;
int type = flag & ~MS_REC;
+ if (!capable(CAP_SYS_ADMIN))
+ return -EPERM;
+
if (nd->dentry != nd->mnt->mnt_root)
return -EINVAL;
@@ -1173,7 +1180,7 @@ static void expire_mount_list(struct list_head *graveyard, struct list_head *mou
while (!list_empty(graveyard)) {
LIST_HEAD(umounts);
- mnt = list_entry(graveyard->next, struct vfsmount, mnt_expire);
+ mnt = list_first_entry(graveyard, struct vfsmount, mnt_expire);
list_del_init(&mnt->mnt_expire);
/* don't do anything if the namespace is dead - all the
@@ -1441,10 +1448,9 @@ dput_out:
* Allocate a new namespace structure and populate it with contents
* copied from the namespace of the passed in task structure.
*/
-struct mnt_namespace *dup_mnt_ns(struct task_struct *tsk,
+static struct mnt_namespace *dup_mnt_ns(struct mnt_namespace *mnt_ns,
struct fs_struct *fs)
{
- struct mnt_namespace *mnt_ns = tsk->nsproxy->mnt_ns;
struct mnt_namespace *new_ns;
struct vfsmount *rootmnt = NULL, *pwdmnt = NULL, *altrootmnt = NULL;
struct vfsmount *p, *q;
@@ -1509,36 +1515,21 @@ struct mnt_namespace *dup_mnt_ns(struct task_struct *tsk,
return new_ns;
}
-int copy_mnt_ns(int flags, struct task_struct *tsk)
+struct mnt_namespace *copy_mnt_ns(int flags, struct mnt_namespace *ns,
+ struct fs_struct *new_fs)
{
- struct mnt_namespace *ns = tsk->nsproxy->mnt_ns;
struct mnt_namespace *new_ns;
- int err = 0;
-
- if (!ns)
- return 0;
+ BUG_ON(!ns);
get_mnt_ns(ns);
if (!(flags & CLONE_NEWNS))
- return 0;
+ return ns;
- if (!capable(CAP_SYS_ADMIN)) {
- err = -EPERM;
- goto out;
- }
-
- new_ns = dup_mnt_ns(tsk, tsk->fs);
- if (!new_ns) {
- err = -ENOMEM;
- goto out;
- }
+ new_ns = dup_mnt_ns(ns, new_fs);
- tsk->nsproxy->mnt_ns = new_ns;
-
-out:
put_mnt_ns(ns);
- return err;
+ return new_ns;
}
asmlinkage long sys_mount(char __user * dev_name, char __user * dir_name,
diff --git a/fs/ncpfs/file.c b/fs/ncpfs/file.c
index 6b1f6d27099..d3152f8d95c 100644
--- a/fs/ncpfs/file.c
+++ b/fs/ncpfs/file.c
@@ -17,7 +17,7 @@
#include <linux/mm.h>
#include <linux/slab.h>
#include <linux/vmalloc.h>
-#include <linux/smp_lock.h>
+#include <linux/sched.h>
#include <linux/ncp_fs.h>
#include "ncplib_kernel.h"
diff --git a/fs/ncpfs/inode.c b/fs/ncpfs/inode.c
index c29f00ad495..cf06eb9f050 100644
--- a/fs/ncpfs/inode.c
+++ b/fs/ncpfs/inode.c
@@ -60,10 +60,8 @@ static void init_once(void * foo, struct kmem_cache * cachep, unsigned long flag
{
struct ncp_inode_info *ei = (struct ncp_inode_info *) foo;
- if (flags & SLAB_CTOR_CONSTRUCTOR) {
- mutex_init(&ei->open_mutex);
- inode_init_once(&ei->vfs_inode);
- }
+ mutex_init(&ei->open_mutex);
+ inode_init_once(&ei->vfs_inode);
}
static int init_inodecache(void)
diff --git a/fs/ncpfs/ioctl.c b/fs/ncpfs/ioctl.c
index 8843a83d4ef..c67b4bdcf71 100644
--- a/fs/ncpfs/ioctl.c
+++ b/fs/ncpfs/ioctl.c
@@ -17,6 +17,7 @@
#include <linux/highuid.h>
#include <linux/smp_lock.h>
#include <linux/vmalloc.h>
+#include <linux/sched.h>
#include <linux/ncp_fs.h>
diff --git a/fs/nfs/callback.h b/fs/nfs/callback.h
index db3d7919c60..c2bb14e053e 100644
--- a/fs/nfs/callback.h
+++ b/fs/nfs/callback.h
@@ -24,7 +24,7 @@ enum nfs4_callback_opnum {
};
struct cb_compound_hdr_arg {
- int taglen;
+ unsigned int taglen;
const char *tag;
unsigned int callback_ident;
unsigned nops;
@@ -32,7 +32,7 @@ struct cb_compound_hdr_arg {
struct cb_compound_hdr_res {
__be32 *status;
- int taglen;
+ unsigned int taglen;
const char *tag;
__be32 *nops;
};
diff --git a/fs/nfs/client.c b/fs/nfs/client.c
index 5bd03b97002..881fa490092 100644
--- a/fs/nfs/client.c
+++ b/fs/nfs/client.c
@@ -12,7 +12,7 @@
#include <linux/module.h>
#include <linux/init.h>
-
+#include <linux/sched.h>
#include <linux/time.h>
#include <linux/kernel.h>
#include <linux/mm.h>
@@ -27,7 +27,6 @@
#include <linux/nfs_mount.h>
#include <linux/nfs4_mount.h>
#include <linux/lockd/bind.h>
-#include <linux/smp_lock.h>
#include <linux/seq_file.h>
#include <linux/mount.h>
#include <linux/nfs_idmap.h>
diff --git a/fs/nfs/delegation.c b/fs/nfs/delegation.c
index 841c99a9b11..7f37d1bea83 100644
--- a/fs/nfs/delegation.c
+++ b/fs/nfs/delegation.c
@@ -226,7 +226,7 @@ restart:
spin_unlock(&clp->cl_lock);
}
-int nfs_do_expire_all_delegations(void *ptr)
+static int nfs_do_expire_all_delegations(void *ptr)
{
struct nfs_client *clp = ptr;
struct nfs_delegation *delegation;
diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index 625d8e5fb39..c27258b5d3e 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -33,12 +33,12 @@
#include <linux/pagevec.h>
#include <linux/namei.h>
#include <linux/mount.h>
+#include <linux/sched.h>
#include "nfs4_fs.h"
#include "delegation.h"
#include "iostat.h"
-#define NFS_PARANOIA 1
/* #define NFS_DEBUG_VERBOSE 1 */
static int nfs_opendir(struct inode *, struct file *);
@@ -608,7 +608,7 @@ static int nfs_readdir(struct file *filp, void *dirent, filldir_t filldir)
return res;
}
-loff_t nfs_llseek_dir(struct file *filp, loff_t offset, int origin)
+static loff_t nfs_llseek_dir(struct file *filp, loff_t offset, int origin)
{
mutex_lock(&filp->f_path.dentry->d_inode->i_mutex);
switch (origin) {
@@ -634,7 +634,7 @@ out:
* All directory operations under NFS are synchronous, so fsync()
* is a dummy operation.
*/
-int nfs_fsync_dir(struct file *filp, struct dentry *dentry, int datasync)
+static int nfs_fsync_dir(struct file *filp, struct dentry *dentry, int datasync)
{
dfprintk(VFS, "NFS: fsync_dir(%s/%s) datasync %d\n",
dentry->d_parent->d_name.name, dentry->d_name.name,
@@ -650,12 +650,15 @@ int nfs_fsync_dir(struct file *filp, struct dentry *dentry, int datasync)
*/
static int nfs_check_verifier(struct inode *dir, struct dentry *dentry)
{
+ unsigned long verf;
+
if (IS_ROOT(dentry))
return 1;
- if ((NFS_I(dir)->cache_validity & NFS_INO_INVALID_ATTR) != 0
- || nfs_attribute_timeout(dir))
+ verf = (unsigned long)dentry->d_fsdata;
+ if (nfs_caches_unstable(dir)
+ || verf != NFS_I(dir)->cache_change_attribute)
return 0;
- return nfs_verify_change_attribute(dir, (unsigned long)dentry->d_fsdata);
+ return 1;
}
static inline void nfs_set_verifier(struct dentry * dentry, unsigned long verf)
@@ -665,8 +668,7 @@ static inline void nfs_set_verifier(struct dentry * dentry, unsigned long verf)
static void nfs_refresh_verifier(struct dentry * dentry, unsigned long verf)
{
- if (time_after(verf, (unsigned long)dentry->d_fsdata))
- nfs_set_verifier(dentry, verf);
+ nfs_set_verifier(dentry, verf);
}
/*
@@ -765,6 +767,10 @@ static int nfs_lookup_revalidate(struct dentry * dentry, struct nameidata *nd)
nfs_inc_stats(dir, NFSIOS_DENTRYREVALIDATE);
inode = dentry->d_inode;
+ /* Revalidate parent directory attribute cache */
+ if (nfs_revalidate_inode(NFS_SERVER(dir), dir) < 0)
+ goto out_zap_parent;
+
if (!inode) {
if (nfs_neg_need_reval(dir, dentry, nd))
goto out_bad;
@@ -778,10 +784,6 @@ static int nfs_lookup_revalidate(struct dentry * dentry, struct nameidata *nd)
goto out_bad;
}
- /* Revalidate parent directory attribute cache */
- if (nfs_revalidate_inode(NFS_SERVER(dir), dir) < 0)
- goto out_zap_parent;
-
/* Force a full look up iff the parent directory has changed */
if (nfs_check_verifier(dir, dentry)) {
if (nfs_lookup_verify_inode(inode, nd))
@@ -1360,11 +1362,6 @@ static int nfs_sillyrename(struct inode *dir, struct dentry *dentry)
atomic_read(&dentry->d_count));
nfs_inc_stats(dir, NFSIOS_SILLYRENAME);
-#ifdef NFS_PARANOIA
-if (!dentry->d_inode)
-printk("NFS: silly-renaming %s/%s, negative dentry??\n",
-dentry->d_parent->d_name.name, dentry->d_name.name);
-#endif
/*
* We don't allow a dentry to be silly-renamed twice.
*/
@@ -1681,16 +1678,9 @@ static int nfs_rename(struct inode *old_dir, struct dentry *old_dentry,
new_inode = NULL;
/* instantiate the replacement target */
d_instantiate(new_dentry, NULL);
- } else if (atomic_read(&new_dentry->d_count) > 1) {
- /* dentry still busy? */
-#ifdef NFS_PARANOIA
- printk("nfs_rename: target %s/%s busy, d_count=%d\n",
- new_dentry->d_parent->d_name.name,
- new_dentry->d_name.name,
- atomic_read(&new_dentry->d_count));
-#endif
+ } else if (atomic_read(&new_dentry->d_count) > 1)
+ /* dentry still busy? */
goto out;
- }
} else
drop_nlink(new_inode);
diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c
index 889de60f8a8..00eee87510f 100644
--- a/fs/nfs/direct.c
+++ b/fs/nfs/direct.c
@@ -41,7 +41,6 @@
#include <linux/errno.h>
#include <linux/sched.h>
#include <linux/kernel.h>
-#include <linux/smp_lock.h>
#include <linux/file.h>
#include <linux/pagemap.h>
#include <linux/kref.h>
@@ -123,19 +122,25 @@ ssize_t nfs_direct_IO(int rw, struct kiocb *iocb, const struct iovec *iov, loff_
return -EINVAL;
}
-static void nfs_direct_dirty_pages(struct page **pages, int npages)
+static void nfs_direct_dirty_pages(struct page **pages, unsigned int pgbase, size_t count)
{
- int i;
+ unsigned int npages;
+ unsigned int i;
+
+ if (count == 0)
+ return;
+ pages += (pgbase >> PAGE_SHIFT);
+ npages = (count + (pgbase & ~PAGE_MASK) + PAGE_SIZE - 1) >> PAGE_SHIFT;
for (i = 0; i < npages; i++) {
struct page *page = pages[i];
if (!PageCompound(page))
- set_page_dirty_lock(page);
+ set_page_dirty(page);
}
}
-static void nfs_direct_release_pages(struct page **pages, int npages)
+static void nfs_direct_release_pages(struct page **pages, unsigned int npages)
{
- int i;
+ unsigned int i;
for (i = 0; i < npages; i++)
page_cache_release(pages[i]);
}
@@ -163,7 +168,7 @@ static inline struct nfs_direct_req *nfs_direct_req_alloc(void)
return dreq;
}
-static void nfs_direct_req_release(struct kref *kref)
+static void nfs_direct_req_free(struct kref *kref)
{
struct nfs_direct_req *dreq = container_of(kref, struct nfs_direct_req, kref);
@@ -172,6 +177,11 @@ static void nfs_direct_req_release(struct kref *kref)
kmem_cache_free(nfs_direct_cachep, dreq);
}
+static void nfs_direct_req_release(struct nfs_direct_req *dreq)
+{
+ kref_put(&dreq->kref, nfs_direct_req_free);
+}
+
/*
* Collects and returns the final error value/byte-count.
*/
@@ -191,7 +201,6 @@ static ssize_t nfs_direct_wait(struct nfs_direct_req *dreq)
result = dreq->count;
out:
- kref_put(&dreq->kref, nfs_direct_req_release);
return (ssize_t) result;
}
@@ -209,7 +218,7 @@ static void nfs_direct_complete(struct nfs_direct_req *dreq)
}
complete_all(&dreq->completion);
- kref_put(&dreq->kref, nfs_direct_req_release);
+ nfs_direct_req_release(dreq);
}
/*
@@ -225,17 +234,18 @@ static void nfs_direct_read_result(struct rpc_task *task, void *calldata)
if (nfs_readpage_result(task, data) != 0)
return;
- nfs_direct_dirty_pages(data->pagevec, data->npages);
- nfs_direct_release_pages(data->pagevec, data->npages);
-
spin_lock(&dreq->lock);
-
- if (likely(task->tk_status >= 0))
- dreq->count += data->res.count;
- else
+ if (unlikely(task->tk_status < 0)) {
dreq->error = task->tk_status;
-
- spin_unlock(&dreq->lock);
+ spin_unlock(&dreq->lock);
+ } else {
+ dreq->count += data->res.count;
+ spin_unlock(&dreq->lock);
+ nfs_direct_dirty_pages(data->pagevec,
+ data->args.pgbase,
+ data->res.count);
+ }
+ nfs_direct_release_pages(data->pagevec, data->npages);
if (put_dreq(dreq))
nfs_direct_complete(dreq);
@@ -280,9 +290,12 @@ static ssize_t nfs_direct_read_schedule(struct nfs_direct_req *dreq, unsigned lo
result = get_user_pages(current, current->mm, user_addr,
data->npages, 1, 0, data->pagevec, NULL);
up_read(&current->mm->mmap_sem);
- if (unlikely(result < data->npages)) {
- if (result > 0)
- nfs_direct_release_pages(data->pagevec, result);
+ if (result < 0) {
+ nfs_readdata_release(data);
+ break;
+ }
+ if ((unsigned)result < data->npages) {
+ nfs_direct_release_pages(data->pagevec, result);
nfs_readdata_release(data);
break;
}
@@ -360,6 +373,7 @@ static ssize_t nfs_direct_read(struct kiocb *iocb, unsigned long user_addr, size
if (!result)
result = nfs_direct_wait(dreq);
rpc_clnt_sigunmask(clnt, &oldset);
+ nfs_direct_req_release(dreq);
return result;
}
@@ -611,9 +625,12 @@ static ssize_t nfs_direct_write_schedule(struct nfs_direct_req *dreq, unsigned l
result = get_user_pages(current, current->mm, user_addr,
data->npages, 0, 0, data->pagevec, NULL);
up_read(&current->mm->mmap_sem);
- if (unlikely(result < data->npages)) {
- if (result > 0)
- nfs_direct_release_pages(data->pagevec, result);
+ if (result < 0) {
+ nfs_writedata_release(data);
+ break;
+ }
+ if ((unsigned)result < data->npages) {
+ nfs_direct_release_pages(data->pagevec, result);
nfs_writedata_release(data);
break;
}
@@ -704,6 +721,7 @@ static ssize_t nfs_direct_write(struct kiocb *iocb, unsigned long user_addr, siz
if (!result)
result = nfs_direct_wait(dreq);
rpc_clnt_sigunmask(clnt, &oldset);
+ nfs_direct_req_release(dreq);
return result;
}
diff --git a/fs/nfs/file.c b/fs/nfs/file.c
index 5eaee6dd040..9eb8eb4e4a0 100644
--- a/fs/nfs/file.c
+++ b/fs/nfs/file.c
@@ -27,6 +27,7 @@
#include <linux/slab.h>
#include <linux/pagemap.h>
#include <linux/smp_lock.h>
+#include <linux/aio.h>
#include <asm/uaccess.h>
#include <asm/system.h>
diff --git a/fs/nfs/getroot.c b/fs/nfs/getroot.c
index 6ef268f7c30..d1cbf0a0fbb 100644
--- a/fs/nfs/getroot.c
+++ b/fs/nfs/getroot.c
@@ -25,7 +25,6 @@
#include <linux/nfs_mount.h>
#include <linux/nfs4_mount.h>
#include <linux/lockd/bind.h>
-#include <linux/smp_lock.h>
#include <linux/seq_file.h>
#include <linux/mount.h>
#include <linux/nfs_idmap.h>
@@ -42,7 +41,6 @@
#include "internal.h"
#define NFSDBG_FACILITY NFSDBG_CLIENT
-#define NFS_PARANOIA 1
/*
* get an NFS2/NFS3 root dentry from the root filehandle
diff --git a/fs/nfs/idmap.c b/fs/nfs/idmap.c
index 9d4a6b2d199..d11eb055265 100644
--- a/fs/nfs/idmap.c
+++ b/fs/nfs/idmap.c
@@ -272,7 +272,7 @@ nfs_idmap_id(struct idmap *idmap, struct idmap_hashtable *h,
set_current_state(TASK_UNINTERRUPTIBLE);
mutex_unlock(&idmap->idmap_im_lock);
schedule();
- current->state = TASK_RUNNING;
+ __set_current_state(TASK_RUNNING);
remove_wait_queue(&idmap->idmap_wq, &wq);
mutex_lock(&idmap->idmap_im_lock);
@@ -333,7 +333,7 @@ nfs_idmap_name(struct idmap *idmap, struct idmap_hashtable *h,
set_current_state(TASK_UNINTERRUPTIBLE);
mutex_unlock(&idmap->idmap_im_lock);
schedule();
- current->state = TASK_RUNNING;
+ __set_current_state(TASK_RUNNING);
remove_wait_queue(&idmap->idmap_wq, &wq);
mutex_lock(&idmap->idmap_im_lock);
diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c
index 1e9a915d1fe..bd9f5a83659 100644
--- a/fs/nfs/inode.c
+++ b/fs/nfs/inode.c
@@ -15,7 +15,7 @@
#include <linux/module.h>
#include <linux/init.h>
-
+#include <linux/sched.h>
#include <linux/time.h>
#include <linux/kernel.h>
#include <linux/mm.h>
@@ -48,7 +48,6 @@
#include "internal.h"
#define NFSDBG_FACILITY NFSDBG_VFS
-#define NFS_PARANOIA 1
static void nfs_invalidate_inode(struct inode *);
static int nfs_update_inode(struct inode *, struct nfs_fattr *);
@@ -1075,10 +1074,8 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
/*
* Big trouble! The inode has become a different object.
*/
-#ifdef NFS_PARANOIA
printk(KERN_DEBUG "%s: inode %ld mode changed, %07o to %07o\n",
__FUNCTION__, inode->i_ino, inode->i_mode, fattr->mode);
-#endif
out_err:
/*
* No need to worry about unhashing the dentry, as the
@@ -1167,21 +1164,19 @@ static void init_once(void * foo, struct kmem_cache * cachep, unsigned long flag
{
struct nfs_inode *nfsi = (struct nfs_inode *) foo;
- if (flags & SLAB_CTOR_CONSTRUCTOR) {
- inode_init_once(&nfsi->vfs_inode);
- spin_lock_init(&nfsi->req_lock);
- INIT_LIST_HEAD(&nfsi->dirty);
- INIT_LIST_HEAD(&nfsi->commit);
- INIT_LIST_HEAD(&nfsi->open_files);
- INIT_LIST_HEAD(&nfsi->access_cache_entry_lru);
- INIT_LIST_HEAD(&nfsi->access_cache_inode_lru);
- INIT_RADIX_TREE(&nfsi->nfs_page_tree, GFP_ATOMIC);
- atomic_set(&nfsi->data_updates, 0);
- nfsi->ndirty = 0;
- nfsi->ncommit = 0;
- nfsi->npages = 0;
- nfs4_init_once(nfsi);
- }
+ inode_init_once(&nfsi->vfs_inode);
+ spin_lock_init(&nfsi->req_lock);
+ INIT_LIST_HEAD(&nfsi->dirty);
+ INIT_LIST_HEAD(&nfsi->commit);
+ INIT_LIST_HEAD(&nfsi->open_files);
+ INIT_LIST_HEAD(&nfsi->access_cache_entry_lru);
+ INIT_LIST_HEAD(&nfsi->access_cache_inode_lru);
+ INIT_RADIX_TREE(&nfsi->nfs_page_tree, GFP_ATOMIC);
+ atomic_set(&nfsi->data_updates, 0);
+ nfsi->ndirty = 0;
+ nfsi->ncommit = 0;
+ nfsi->npages = 0;
+ nfs4_init_once(nfsi);
}
static int __init nfs_init_inodecache(void)
diff --git a/fs/nfs/nfs2xdr.c b/fs/nfs/nfs2xdr.c
index abd9f8b4894..cd3ca7b5d3d 100644
--- a/fs/nfs/nfs2xdr.c
+++ b/fs/nfs/nfs2xdr.c
@@ -26,7 +26,6 @@
#include "internal.h"
#define NFSDBG_FACILITY NFSDBG_XDR
-/* #define NFS_PARANOIA 1 */
/* Mapping from NFS error code to "errno" error code. */
#define errno_NFSERR_IO EIO
diff --git a/fs/nfs/nfs3proc.c b/fs/nfs/nfs3proc.c
index 7d0371e2bad..45268d6def2 100644
--- a/fs/nfs/nfs3proc.c
+++ b/fs/nfs/nfs3proc.c
@@ -16,7 +16,6 @@
#include <linux/nfs_fs.h>
#include <linux/nfs_page.h>
#include <linux/lockd/bind.h>
-#include <linux/smp_lock.h>
#include <linux/nfs_mount.h>
#include "iostat.h"
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index d6a30e96578..648e0ac0f90 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -790,7 +790,7 @@ out:
return -EACCES;
}
-int nfs4_recover_expired_lease(struct nfs_server *server)
+static int nfs4_recover_expired_lease(struct nfs_server *server)
{
struct nfs_client *clp = server->nfs_client;
int ret;
@@ -2748,7 +2748,7 @@ static int nfs4_delay(struct rpc_clnt *clnt, long *timeout)
/* This is the error handling routine for processes that are allowed
* to sleep.
*/
-int nfs4_handle_exception(const struct nfs_server *server, int errorcode, struct nfs4_exception *exception)
+static int nfs4_handle_exception(const struct nfs_server *server, int errorcode, struct nfs4_exception *exception)
{
struct nfs_client *clp = server->nfs_client;
int ret = errorcode;
diff --git a/fs/nfs/nfs4renewd.c b/fs/nfs/nfs4renewd.c
index f5f4430fb2a..0505ca12403 100644
--- a/fs/nfs/nfs4renewd.c
+++ b/fs/nfs/nfs4renewd.c
@@ -43,7 +43,6 @@
* child task framework of the RPC layer?
*/
-#include <linux/smp_lock.h>
#include <linux/mm.h>
#include <linux/pagemap.h>
#include <linux/sunrpc/sched.h>
diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c
index 5fffbdfa971..8ed79d5c54f 100644
--- a/fs/nfs/nfs4state.c
+++ b/fs/nfs/nfs4state.c
@@ -104,7 +104,7 @@ struct rpc_cred *nfs4_get_renew_cred(struct nfs_client *clp)
return cred;
}
-struct rpc_cred *nfs4_get_setclientid_cred(struct nfs_client *clp)
+static struct rpc_cred *nfs4_get_setclientid_cred(struct nfs_client *clp)
{
struct nfs4_state_owner *sp;
diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c
index b8c28f2380a..8003c91ccb9 100644
--- a/fs/nfs/nfs4xdr.c
+++ b/fs/nfs/nfs4xdr.c
@@ -224,7 +224,8 @@ static int nfs4_stat_to_errno(int);
encode_getattr_maxsz)
#define NFS4_dec_setattr_sz (compound_decode_hdr_maxsz + \
decode_putfh_maxsz + \
- op_decode_hdr_maxsz + 3)
+ op_decode_hdr_maxsz + 3 + \
+ nfs4_fattr_maxsz)
#define NFS4_enc_fsinfo_sz (compound_encode_hdr_maxsz + \
encode_putfh_maxsz + \
encode_fsinfo_maxsz)
@@ -645,10 +646,10 @@ static int encode_close(struct xdr_stream *xdr, const struct nfs_closeargs *arg)
{
__be32 *p;
- RESERVE_SPACE(8+sizeof(arg->stateid->data));
+ RESERVE_SPACE(8+NFS4_STATEID_SIZE);
WRITE32(OP_CLOSE);
WRITE32(arg->seqid->sequence->counter);
- WRITEMEM(arg->stateid->data, sizeof(arg->stateid->data));
+ WRITEMEM(arg->stateid->data, NFS4_STATEID_SIZE);
return 0;
}
@@ -792,17 +793,17 @@ static int encode_lock(struct xdr_stream *xdr, const struct nfs_lock_args *args)
WRITE64(nfs4_lock_length(args->fl));
WRITE32(args->new_lock_owner);
if (args->new_lock_owner){
- RESERVE_SPACE(40);
+ RESERVE_SPACE(4+NFS4_STATEID_SIZE+20);
WRITE32(args->open_seqid->sequence->counter);
- WRITEMEM(args->open_stateid->data, sizeof(args->open_stateid->data));
+ WRITEMEM(args->open_stateid->data, NFS4_STATEID_SIZE);
WRITE32(args->lock_seqid->sequence->counter);
WRITE64(args->lock_owner.clientid);
WRITE32(4);
WRITE32(args->lock_owner.id);
}
else {
- RESERVE_SPACE(20);
- WRITEMEM(args->lock_stateid->data, sizeof(args->lock_stateid->data));
+ RESERVE_SPACE(NFS4_STATEID_SIZE+4);
+ WRITEMEM(args->lock_stateid->data, NFS4_STATEID_SIZE);
WRITE32(args->lock_seqid->sequence->counter);
}
@@ -829,11 +830,11 @@ static int encode_locku(struct xdr_stream *xdr, const struct nfs_locku_args *arg
{
__be32 *p;
- RESERVE_SPACE(44);
+ RESERVE_SPACE(12+NFS4_STATEID_SIZE+16);
WRITE32(OP_LOCKU);
WRITE32(nfs4_lock_type(args->fl, 0));
WRITE32(args->seqid->sequence->counter);
- WRITEMEM(args->stateid->data, sizeof(args->stateid->data));
+ WRITEMEM(args->stateid->data, NFS4_STATEID_SIZE);
WRITE64(args->fl->fl_start);
WRITE64(nfs4_lock_length(args->fl));
@@ -965,9 +966,9 @@ static inline void encode_claim_delegate_cur(struct xdr_stream *xdr, const struc
{
__be32 *p;
- RESERVE_SPACE(4+sizeof(stateid->data));
+ RESERVE_SPACE(4+NFS4_STATEID_SIZE);
WRITE32(NFS4_OPEN_CLAIM_DELEGATE_CUR);
- WRITEMEM(stateid->data, sizeof(stateid->data));
+ WRITEMEM(stateid->data, NFS4_STATEID_SIZE);
encode_string(xdr, name->len, name->name);
}
@@ -995,9 +996,9 @@ static int encode_open_confirm(struct xdr_stream *xdr, const struct nfs_open_con
{
__be32 *p;
- RESERVE_SPACE(8+sizeof(arg->stateid->data));
+ RESERVE_SPACE(4+NFS4_STATEID_SIZE+4);
WRITE32(OP_OPEN_CONFIRM);
- WRITEMEM(arg->stateid->data, sizeof(arg->stateid->data));
+ WRITEMEM(arg->stateid->data, NFS4_STATEID_SIZE);
WRITE32(arg->seqid->sequence->counter);
return 0;
@@ -1007,9 +1008,9 @@ static int encode_open_downgrade(struct xdr_stream *xdr, const struct nfs_closea
{
__be32 *p;
- RESERVE_SPACE(8+sizeof(arg->stateid->data));
+ RESERVE_SPACE(4+NFS4_STATEID_SIZE+4);
WRITE32(OP_OPEN_DOWNGRADE);
- WRITEMEM(arg->stateid->data, sizeof(arg->stateid->data));
+ WRITEMEM(arg->stateid->data, NFS4_STATEID_SIZE);
WRITE32(arg->seqid->sequence->counter);
encode_share_access(xdr, arg->open_flags);
return 0;
@@ -1044,12 +1045,12 @@ static void encode_stateid(struct xdr_stream *xdr, const struct nfs_open_context
nfs4_stateid stateid;
__be32 *p;
- RESERVE_SPACE(16);
+ RESERVE_SPACE(NFS4_STATEID_SIZE);
if (ctx->state != NULL) {
nfs4_copy_stateid(&stateid, ctx->state, ctx->lockowner);
- WRITEMEM(stateid.data, sizeof(stateid.data));
+ WRITEMEM(stateid.data, NFS4_STATEID_SIZE);
} else
- WRITEMEM(zero_stateid.data, sizeof(zero_stateid.data));
+ WRITEMEM(zero_stateid.data, NFS4_STATEID_SIZE);
}
static int encode_read(struct xdr_stream *xdr, const struct nfs_readargs *args)
@@ -1078,10 +1079,10 @@ static int encode_readdir(struct xdr_stream *xdr, const struct nfs4_readdir_arg
int replen;
__be32 *p;
- RESERVE_SPACE(32+sizeof(nfs4_verifier));
+ RESERVE_SPACE(12+NFS4_VERIFIER_SIZE+20);
WRITE32(OP_READDIR);
WRITE64(readdir->cookie);
- WRITEMEM(readdir->verifier.data, sizeof(readdir->verifier.data));
+ WRITEMEM(readdir->verifier.data, NFS4_VERIFIER_SIZE);
WRITE32(readdir->count >> 1); /* We're not doing readdirplus */
WRITE32(readdir->count);
WRITE32(2);
@@ -1189,9 +1190,9 @@ encode_setacl(struct xdr_stream *xdr, struct nfs_setaclargs *arg)
{
__be32 *p;
- RESERVE_SPACE(4+sizeof(zero_stateid.data));
+ RESERVE_SPACE(4+NFS4_STATEID_SIZE);
WRITE32(OP_SETATTR);
- WRITEMEM(zero_stateid.data, sizeof(zero_stateid.data));
+ WRITEMEM(zero_stateid.data, NFS4_STATEID_SIZE);
RESERVE_SPACE(2*4);
WRITE32(1);
WRITE32(FATTR4_WORD0_ACL);
@@ -1219,9 +1220,9 @@ static int encode_setattr(struct xdr_stream *xdr, const struct nfs_setattrargs *
int status;
__be32 *p;
- RESERVE_SPACE(4+sizeof(arg->stateid.data));
+ RESERVE_SPACE(4+NFS4_STATEID_SIZE);
WRITE32(OP_SETATTR);
- WRITEMEM(arg->stateid.data, sizeof(arg->stateid.data));
+ WRITEMEM(arg->stateid.data, NFS4_STATEID_SIZE);
if ((status = encode_attrs(xdr, arg->iap, server)))
return status;
@@ -1233,9 +1234,9 @@ static int encode_setclientid(struct xdr_stream *xdr, const struct nfs4_setclien
{
__be32 *p;
- RESERVE_SPACE(4 + sizeof(setclientid->sc_verifier->data));
+ RESERVE_SPACE(4 + NFS4_VERIFIER_SIZE);
WRITE32(OP_SETCLIENTID);
- WRITEMEM(setclientid->sc_verifier->data, sizeof(setclientid->sc_verifier->data));
+ WRITEMEM(setclientid->sc_verifier->data, NFS4_VERIFIER_SIZE);
encode_string(xdr, setclientid->sc_name_len, setclientid->sc_name);
RESERVE_SPACE(4);
@@ -1252,10 +1253,10 @@ static int encode_setclientid_confirm(struct xdr_stream *xdr, const struct nfs_c
{
__be32 *p;
- RESERVE_SPACE(12 + sizeof(client_state->cl_confirm.data));
+ RESERVE_SPACE(12 + NFS4_VERIFIER_SIZE);
WRITE32(OP_SETCLIENTID_CONFIRM);
WRITE64(client_state->cl_clientid);
- WRITEMEM(client_state->cl_confirm.data, sizeof(client_state->cl_confirm.data));
+ WRITEMEM(client_state->cl_confirm.data, NFS4_VERIFIER_SIZE);
return 0;
}
@@ -1283,10 +1284,10 @@ static int encode_delegreturn(struct xdr_stream *xdr, const nfs4_stateid *statei
{
__be32 *p;
- RESERVE_SPACE(20);
+ RESERVE_SPACE(4+NFS4_STATEID_SIZE);
WRITE32(OP_DELEGRETURN);
- WRITEMEM(stateid->data, sizeof(stateid->data));
+ WRITEMEM(stateid->data, NFS4_STATEID_SIZE);
return 0;
}
@@ -2079,9 +2080,11 @@ out:
#define READ_BUF(nbytes) do { \
p = xdr_inline_decode(xdr, nbytes); \
- if (!p) { \
- printk(KERN_WARNING "%s: reply buffer overflowed in line %d.", \
- __FUNCTION__, __LINE__); \
+ if (unlikely(!p)) { \
+ printk(KERN_INFO "%s: prematurely hit end of receive" \
+ " buffer\n", __FUNCTION__); \
+ printk(KERN_INFO "%s: xdr->p=%p, bytes=%u, xdr->end=%p\n", \
+ __FUNCTION__, xdr->p, nbytes, xdr->end); \
return -EIO; \
} \
} while (0)
@@ -2491,7 +2494,7 @@ static int decode_attr_fs_locations(struct xdr_stream *xdr, uint32_t *bitmap, st
int i;
dprintk("%s: using first %d of %d servers returned for location %d\n", __FUNCTION__, NFS4_FS_LOCATION_MAXSERVERS, m, res->nlocations);
for (i = loc->nservers; i < m; i++) {
- int len;
+ unsigned int len;
char *data;
status = decode_opaque_inline(xdr, &len, &data);
if (unlikely(status != 0))
@@ -2639,7 +2642,7 @@ static int decode_attr_nlink(struct xdr_stream *xdr, uint32_t *bitmap, uint32_t
return 0;
}
-static int decode_attr_owner(struct xdr_stream *xdr, uint32_t *bitmap, struct nfs_client *clp, int32_t *uid)
+static int decode_attr_owner(struct xdr_stream *xdr, uint32_t *bitmap, struct nfs_client *clp, uint32_t *uid)
{
uint32_t len;
__be32 *p;
@@ -2664,7 +2667,7 @@ static int decode_attr_owner(struct xdr_stream *xdr, uint32_t *bitmap, struct nf
return 0;
}
-static int decode_attr_group(struct xdr_stream *xdr, uint32_t *bitmap, struct nfs_client *clp, int32_t *gid)
+static int decode_attr_group(struct xdr_stream *xdr, uint32_t *bitmap, struct nfs_client *clp, uint32_t *gid)
{
uint32_t len;
__be32 *p;
@@ -2894,8 +2897,8 @@ static int decode_close(struct xdr_stream *xdr, struct nfs_closeres *res)
status = decode_op_hdr(xdr, OP_CLOSE);
if (status)
return status;
- READ_BUF(sizeof(res->stateid.data));
- COPYMEM(res->stateid.data, sizeof(res->stateid.data));
+ READ_BUF(NFS4_STATEID_SIZE);
+ COPYMEM(res->stateid.data, NFS4_STATEID_SIZE);
return 0;
}
@@ -3183,8 +3186,8 @@ static int decode_lock(struct xdr_stream *xdr, struct nfs_lock_res *res)
status = decode_op_hdr(xdr, OP_LOCK);
if (status == 0) {
- READ_BUF(sizeof(res->stateid.data));
- COPYMEM(res->stateid.data, sizeof(res->stateid.data));
+ READ_BUF(NFS4_STATEID_SIZE);
+ COPYMEM(res->stateid.data, NFS4_STATEID_SIZE);
} else if (status == -NFS4ERR_DENIED)
return decode_lock_denied(xdr, NULL);
return status;
@@ -3206,8 +3209,8 @@ static int decode_locku(struct xdr_stream *xdr, struct nfs_locku_res *res)
status = decode_op_hdr(xdr, OP_LOCKU);
if (status == 0) {
- READ_BUF(sizeof(res->stateid.data));
- COPYMEM(res->stateid.data, sizeof(res->stateid.data));
+ READ_BUF(NFS4_STATEID_SIZE);
+ COPYMEM(res->stateid.data, NFS4_STATEID_SIZE);
}
return status;
}
@@ -3248,8 +3251,8 @@ static int decode_delegation(struct xdr_stream *xdr, struct nfs_openres *res)
res->delegation_type = 0;
return 0;
}
- READ_BUF(20);
- COPYMEM(res->delegation.data, sizeof(res->delegation.data));
+ READ_BUF(NFS4_STATEID_SIZE+4);
+ COPYMEM(res->delegation.data, NFS4_STATEID_SIZE);
READ32(res->do_recall);
switch (delegation_type) {
case NFS4_OPEN_DELEGATE_READ:
@@ -3272,8 +3275,8 @@ static int decode_open(struct xdr_stream *xdr, struct nfs_openres *res)
status = decode_op_hdr(xdr, OP_OPEN);
if (status)
return status;
- READ_BUF(sizeof(res->stateid.data));
- COPYMEM(res->stateid.data, sizeof(res->stateid.data));
+ READ_BUF(NFS4_STATEID_SIZE);
+ COPYMEM(res->stateid.data, NFS4_STATEID_SIZE);
decode_change_info(xdr, &res->cinfo);
@@ -3299,8 +3302,8 @@ static int decode_open_confirm(struct xdr_stream *xdr, struct nfs_open_confirmre
status = decode_op_hdr(xdr, OP_OPEN_CONFIRM);
if (status)
return status;
- READ_BUF(sizeof(res->stateid.data));
- COPYMEM(res->stateid.data, sizeof(res->stateid.data));
+ READ_BUF(NFS4_STATEID_SIZE);
+ COPYMEM(res->stateid.data, NFS4_STATEID_SIZE);
return 0;
}
@@ -3312,8 +3315,8 @@ static int decode_open_downgrade(struct xdr_stream *xdr, struct nfs_closeres *re
status = decode_op_hdr(xdr, OP_OPEN_DOWNGRADE);
if (status)
return status;
- READ_BUF(sizeof(res->stateid.data));
- COPYMEM(res->stateid.data, sizeof(res->stateid.data));
+ READ_BUF(NFS4_STATEID_SIZE);
+ COPYMEM(res->stateid.data, NFS4_STATEID_SIZE);
return 0;
}
@@ -3587,9 +3590,9 @@ static int decode_setclientid(struct xdr_stream *xdr, struct nfs_client *clp)
}
READ32(nfserr);
if (nfserr == NFS_OK) {
- READ_BUF(8 + sizeof(clp->cl_confirm.data));
+ READ_BUF(8 + NFS4_VERIFIER_SIZE);
READ64(clp->cl_clientid);
- COPYMEM(clp->cl_confirm.data, sizeof(clp->cl_confirm.data));
+ COPYMEM(clp->cl_confirm.data, NFS4_VERIFIER_SIZE);
} else if (nfserr == NFSERR_CLID_INUSE) {
uint32_t len;
diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c
index 388950118f5..c5bb51a29e8 100644
--- a/fs/nfs/pagelist.c
+++ b/fs/nfs/pagelist.c
@@ -11,6 +11,7 @@
#include <linux/slab.h>
#include <linux/file.h>
+#include <linux/sched.h>
#include <linux/sunrpc/clnt.h>
#include <linux/nfs3.h>
#include <linux/nfs4.h>
@@ -20,8 +21,6 @@
#include "internal.h"
-#define NFS_PARANOIA 1
-
static struct kmem_cache *nfs_page_cachep;
static inline struct nfs_page *
@@ -167,11 +166,6 @@ nfs_release_request(struct nfs_page *req)
if (!atomic_dec_and_test(&req->wb_count))
return;
-#ifdef NFS_PARANOIA
- BUG_ON (!list_empty(&req->wb_list));
- BUG_ON (NFS_WBACK_BUSY(req));
-#endif
-
/* Release struct file or cached credential */
nfs_clear_request(req);
put_nfs_open_context(req->wb_context);
@@ -361,6 +355,26 @@ void nfs_pageio_complete(struct nfs_pageio_descriptor *desc)
nfs_pageio_doio(desc);
}
+/**
+ * nfs_pageio_cond_complete - Conditional I/O completion
+ * @desc: pointer to io descriptor
+ * @index: page index
+ *
+ * It is important to ensure that processes don't try to take locks
+ * on non-contiguous ranges of pages as that might deadlock. This
+ * function should be called before attempting to wait on a locked
+ * nfs_page. It will complete the I/O if the page index 'index'
+ * is not contiguous with the existing list of pages in 'desc'.
+ */
+void nfs_pageio_cond_complete(struct nfs_pageio_descriptor *desc, pgoff_t index)
+{
+ if (!list_empty(&desc->pg_list)) {
+ struct nfs_page *prev = nfs_list_entry(desc->pg_list.prev);
+ if (index != prev->wb_index + 1)
+ nfs_pageio_doio(desc);
+ }
+}
+
#define NFS_SCAN_MAXENTRIES 16
/**
* nfs_scan_list - Scan a list for matching requests
diff --git a/fs/nfs/proc.c b/fs/nfs/proc.c
index 1dcf56de948..7be0ee2782c 100644
--- a/fs/nfs/proc.c
+++ b/fs/nfs/proc.c
@@ -43,7 +43,6 @@
#include <linux/nfs_fs.h>
#include <linux/nfs_page.h>
#include <linux/lockd/bind.h>
-#include <linux/smp_lock.h>
#include "internal.h"
#define NFSDBG_FACILITY NFSDBG_PROC
diff --git a/fs/nfs/read.c b/fs/nfs/read.c
index 9a55807b2a7..7bd7cb95c03 100644
--- a/fs/nfs/read.c
+++ b/fs/nfs/read.c
@@ -79,7 +79,7 @@ void nfs_readdata_release(void *data)
static
int nfs_return_empty_page(struct page *page)
{
- memclear_highpage_flush(page, 0, PAGE_CACHE_SIZE);
+ zero_user_page(page, 0, PAGE_CACHE_SIZE, KM_USER0);
SetPageUptodate(page);
unlock_page(page);
return 0;
@@ -103,10 +103,10 @@ static void nfs_readpage_truncate_uninitialised_page(struct nfs_read_data *data)
pglen = PAGE_CACHE_SIZE - base;
for (;;) {
if (remainder <= pglen) {
- memclear_highpage_flush(*pages, base, remainder);
+ zero_user_page(*pages, base, remainder, KM_USER0);
break;
}
- memclear_highpage_flush(*pages, base, pglen);
+ zero_user_page(*pages, base, pglen, KM_USER0);
pages++;
remainder -= pglen;
pglen = PAGE_CACHE_SIZE;
@@ -130,7 +130,7 @@ static int nfs_readpage_async(struct nfs_open_context *ctx, struct inode *inode,
return PTR_ERR(new);
}
if (len < PAGE_CACHE_SIZE)
- memclear_highpage_flush(page, len, PAGE_CACHE_SIZE - len);
+ zero_user_page(page, len, PAGE_CACHE_SIZE - len, KM_USER0);
nfs_list_add_request(new, &one_request);
if (NFS_SERVER(inode)->rsize < PAGE_CACHE_SIZE)
@@ -532,7 +532,7 @@ readpage_async_filler(void *data, struct page *page)
return PTR_ERR(new);
}
if (len < PAGE_CACHE_SIZE)
- memclear_highpage_flush(page, len, PAGE_CACHE_SIZE - len);
+ zero_user_page(page, len, PAGE_CACHE_SIZE - len, KM_USER0);
nfs_pageio_add_request(desc->pgio, new);
return 0;
}
diff --git a/fs/nfs/symlink.c b/fs/nfs/symlink.c
index bc2821331c2..83e865a16ad 100644
--- a/fs/nfs/symlink.c
+++ b/fs/nfs/symlink.c
@@ -22,7 +22,6 @@
#include <linux/mm.h>
#include <linux/slab.h>
#include <linux/string.h>
-#include <linux/smp_lock.h>
#include <linux/namei.h>
/* Symlink caching in the page cache is even more simplistic
diff --git a/fs/nfs/write.c b/fs/nfs/write.c
index 5d44b8bd107..af344a158e0 100644
--- a/fs/nfs/write.c
+++ b/fs/nfs/write.c
@@ -21,7 +21,6 @@
#include <linux/backing-dev.h>
#include <asm/uaccess.h>
-#include <linux/smp_lock.h>
#include "delegation.h"
#include "internal.h"
@@ -59,7 +58,7 @@ struct nfs_write_data *nfs_commit_alloc(void)
return p;
}
-void nfs_commit_rcu_free(struct rcu_head *head)
+static void nfs_commit_rcu_free(struct rcu_head *head)
{
struct nfs_write_data *p = container_of(head, struct nfs_write_data, task.u.tk_rcu);
if (p && (p->pagevec != &p->page_array[0]))
@@ -169,7 +168,7 @@ static void nfs_mark_uptodate(struct page *page, unsigned int base, unsigned int
if (count != nfs_page_length(page))
return;
if (count != PAGE_CACHE_SIZE)
- memclear_highpage_flush(page, count, PAGE_CACHE_SIZE - count);
+ zero_user_page(page, count, PAGE_CACHE_SIZE - count, KM_USER0);
SetPageUptodate(page);
}
@@ -225,7 +224,7 @@ static int nfs_set_page_writeback(struct page *page)
struct inode *inode = page->mapping->host;
struct nfs_server *nfss = NFS_SERVER(inode);
- if (atomic_inc_return(&nfss->writeback) >
+ if (atomic_long_inc_return(&nfss->writeback) >
NFS_CONGESTION_ON_THRESH)
set_bdi_congested(&nfss->backing_dev_info, WRITE);
}
@@ -238,7 +237,7 @@ static void nfs_end_page_writeback(struct page *page)
struct nfs_server *nfss = NFS_SERVER(inode);
end_page_writeback(page);
- if (atomic_dec_return(&nfss->writeback) < NFS_CONGESTION_OFF_THRESH) {
+ if (atomic_long_dec_return(&nfss->writeback) < NFS_CONGESTION_OFF_THRESH) {
clear_bdi_congested(&nfss->backing_dev_info, WRITE);
congestion_end(WRITE);
}
@@ -274,8 +273,6 @@ static int nfs_page_async_flush(struct nfs_pageio_descriptor *pgio,
* request as dirty (in which case we don't care).
*/
spin_unlock(req_lock);
- /* Prevent deadlock! */
- nfs_pageio_complete(pgio);
ret = nfs_wait_on_request(req);
nfs_release_request(req);
if (ret != 0)
@@ -322,6 +319,8 @@ static int nfs_writepage_locked(struct page *page, struct writeback_control *wbc
pgio = &mypgio;
}
+ nfs_pageio_cond_complete(pgio, page->index);
+
err = nfs_page_async_flush(pgio, page);
if (err <= 0)
goto out;
@@ -330,6 +329,8 @@ static int nfs_writepage_locked(struct page *page, struct writeback_control *wbc
if (!offset)
goto out;
+ nfs_pageio_cond_complete(pgio, page->index);
+
ctx = nfs_find_open_context(inode, NULL, FMODE_WRITE);
if (ctx == NULL) {
err = -EBADF;
@@ -923,7 +924,7 @@ static int nfs_flush_one(struct inode *inode, struct list_head *head, unsigned i
return 0;
out_bad:
while (!list_empty(head)) {
- struct nfs_page *req = nfs_list_entry(head->next);
+ req = nfs_list_entry(head->next);
nfs_list_remove_request(req);
nfs_redirty_request(req);
nfs_end_page_writeback(req->wb_page);
diff --git a/fs/nfsd/Makefile b/fs/nfsd/Makefile
index ce341dc76d5..9b118ee2019 100644
--- a/fs/nfsd/Makefile
+++ b/fs/nfsd/Makefile
@@ -11,4 +11,3 @@ nfsd-$(CONFIG_NFSD_V3) += nfs3proc.o nfs3xdr.o
nfsd-$(CONFIG_NFSD_V3_ACL) += nfs3acl.o
nfsd-$(CONFIG_NFSD_V4) += nfs4proc.o nfs4xdr.o nfs4state.o nfs4idmap.o \
nfs4acl.o nfs4callback.o nfs4recover.o
-nfsd-objs := $(nfsd-y)
diff --git a/fs/nfsd/export.c b/fs/nfsd/export.c
index 6f24768272a..79bd03b8bbf 100644
--- a/fs/nfsd/export.c
+++ b/fs/nfsd/export.c
@@ -469,6 +469,13 @@ static int svc_export_parse(struct cache_detail *cd, char *mesg, int mlen)
nd.dentry = NULL;
exp.ex_path = NULL;
+ /* fs locations */
+ exp.ex_fslocs.locations = NULL;
+ exp.ex_fslocs.locations_count = 0;
+ exp.ex_fslocs.migrated = 0;
+
+ exp.ex_uuid = NULL;
+
if (mesg[mlen-1] != '\n')
return -EINVAL;
mesg[mlen-1] = 0;
@@ -509,13 +516,6 @@ static int svc_export_parse(struct cache_detail *cd, char *mesg, int mlen)
if (exp.h.expiry_time == 0)
goto out;
- /* fs locations */
- exp.ex_fslocs.locations = NULL;
- exp.ex_fslocs.locations_count = 0;
- exp.ex_fslocs.migrated = 0;
-
- exp.ex_uuid = NULL;
-
/* flags */
err = get_int(&mesg, &an_int);
if (err == -ENOENT)
diff --git a/fs/nfsd/nfs3proc.c b/fs/nfsd/nfs3proc.c
index 7f5bad0393b..eac82830bfd 100644
--- a/fs/nfsd/nfs3proc.c
+++ b/fs/nfsd/nfs3proc.c
@@ -177,7 +177,7 @@ nfsd3_proc_read(struct svc_rqst *rqstp, struct nfsd3_readargs *argp,
if (max_blocksize < resp->count)
resp->count = max_blocksize;
- svc_reserve(rqstp, ((1 + NFS3_POST_OP_ATTR_WORDS + 3)<<2) + resp->count +4);
+ svc_reserve_auth(rqstp, ((1 + NFS3_POST_OP_ATTR_WORDS + 3)<<2) + resp->count +4);
fh_copy(&resp->fh, &argp->fh);
nfserr = nfsd_read(rqstp, &resp->fh, NULL,
diff --git a/fs/nfsd/nfs3xdr.c b/fs/nfsd/nfs3xdr.c
index 7e4bb0af24d..10f6e7dcf63 100644
--- a/fs/nfsd/nfs3xdr.c
+++ b/fs/nfsd/nfs3xdr.c
@@ -239,7 +239,7 @@ static __be32 *
encode_post_op_attr(struct svc_rqst *rqstp, __be32 *p, struct svc_fh *fhp)
{
struct dentry *dentry = fhp->fh_dentry;
- if (dentry && dentry->d_inode != NULL) {
+ if (dentry && dentry->d_inode) {
int err;
struct kstat stat;
@@ -300,9 +300,9 @@ int
nfs3svc_decode_sattrargs(struct svc_rqst *rqstp, __be32 *p,
struct nfsd3_sattrargs *args)
{
- if (!(p = decode_fh(p, &args->fh))
- || !(p = decode_sattr3(p, &args->attrs)))
+ if (!(p = decode_fh(p, &args->fh)))
return 0;
+ p = decode_sattr3(p, &args->attrs);
if ((args->check_guard = ntohl(*p++)) != 0) {
struct timespec time;
@@ -343,9 +343,9 @@ nfs3svc_decode_readargs(struct svc_rqst *rqstp, __be32 *p,
int v,pn;
u32 max_blocksize = svc_max_payload(rqstp);
- if (!(p = decode_fh(p, &args->fh))
- || !(p = xdr_decode_hyper(p, &args->offset)))
+ if (!(p = decode_fh(p, &args->fh)))
return 0;
+ p = xdr_decode_hyper(p, &args->offset);
len = args->count = ntohl(*p++);
@@ -369,28 +369,44 @@ int
nfs3svc_decode_writeargs(struct svc_rqst *rqstp, __be32 *p,
struct nfsd3_writeargs *args)
{
- unsigned int len, v, hdr;
+ unsigned int len, v, hdr, dlen;
u32 max_blocksize = svc_max_payload(rqstp);
- if (!(p = decode_fh(p, &args->fh))
- || !(p = xdr_decode_hyper(p, &args->offset)))
+ if (!(p = decode_fh(p, &args->fh)))
return 0;
+ p = xdr_decode_hyper(p, &args->offset);
args->count = ntohl(*p++);
args->stable = ntohl(*p++);
len = args->len = ntohl(*p++);
+ /*
+ * The count must equal the amount of data passed.
+ */
+ if (args->count != args->len)
+ return 0;
+ /*
+ * Check to make sure that we got the right number of
+ * bytes.
+ */
hdr = (void*)p - rqstp->rq_arg.head[0].iov_base;
- if (rqstp->rq_arg.len < hdr ||
- rqstp->rq_arg.len - hdr < len)
+ dlen = rqstp->rq_arg.head[0].iov_len + rqstp->rq_arg.page_len
+ - hdr;
+ /*
+ * Round the length of the data which was specified up to
+ * the next multiple of XDR units and then compare that
+ * against the length which was actually received.
+ */
+ if (dlen != XDR_QUADLEN(len)*4)
return 0;
+ if (args->count > max_blocksize) {
+ args->count = max_blocksize;
+ len = args->len = max_blocksize;
+ }
rqstp->rq_vec[0].iov_base = (void*)p;
rqstp->rq_vec[0].iov_len = rqstp->rq_arg.head[0].iov_len - hdr;
-
- if (len > max_blocksize)
- len = max_blocksize;
- v= 0;
+ v = 0;
while (len > rqstp->rq_vec[v].iov_len) {
len -= rqstp->rq_vec[v].iov_len;
v++;
@@ -398,9 +414,8 @@ nfs3svc_decode_writeargs(struct svc_rqst *rqstp, __be32 *p,
rqstp->rq_vec[v].iov_len = PAGE_SIZE;
}
rqstp->rq_vec[v].iov_len = len;
- args->vlen = v+1;
-
- return args->count == args->len && rqstp->rq_vec[0].iov_len > 0;
+ args->vlen = v + 1;
+ return 1;
}
int
@@ -414,8 +429,7 @@ nfs3svc_decode_createargs(struct svc_rqst *rqstp, __be32 *p,
switch (args->createmode = ntohl(*p++)) {
case NFS3_CREATE_UNCHECKED:
case NFS3_CREATE_GUARDED:
- if (!(p = decode_sattr3(p, &args->attrs)))
- return 0;
+ p = decode_sattr3(p, &args->attrs);
break;
case NFS3_CREATE_EXCLUSIVE:
args->verf = p;
@@ -431,10 +445,10 @@ int
nfs3svc_decode_mkdirargs(struct svc_rqst *rqstp, __be32 *p,
struct nfsd3_createargs *args)
{
- if (!(p = decode_fh(p, &args->fh))
- || !(p = decode_filename(p, &args->name, &args->len))
- || !(p = decode_sattr3(p, &args->attrs)))
+ if (!(p = decode_fh(p, &args->fh)) ||
+ !(p = decode_filename(p, &args->name, &args->len)))
return 0;
+ p = decode_sattr3(p, &args->attrs);
return xdr_argsize_check(rqstp, p);
}
@@ -448,11 +462,12 @@ nfs3svc_decode_symlinkargs(struct svc_rqst *rqstp, __be32 *p,
char *old, *new;
struct kvec *vec;
- if (!(p = decode_fh(p, &args->ffh))
- || !(p = decode_filename(p, &args->fname, &args->flen))
- || !(p = decode_sattr3(p, &args->attrs))
+ if (!(p = decode_fh(p, &args->ffh)) ||
+ !(p = decode_filename(p, &args->fname, &args->flen))
)
return 0;
+ p = decode_sattr3(p, &args->attrs);
+
/* now decode the pathname, which might be larger than the first page.
* As we have to check for nul's anyway, we copy it into a new page
* This page appears in the rq_res.pages list, but as pages_len is always
@@ -502,10 +517,8 @@ nfs3svc_decode_mknodargs(struct svc_rqst *rqstp, __be32 *p,
args->ftype = ntohl(*p++);
if (args->ftype == NF3BLK || args->ftype == NF3CHR
- || args->ftype == NF3SOCK || args->ftype == NF3FIFO) {
- if (!(p = decode_sattr3(p, &args->attrs)))
- return 0;
- }
+ || args->ftype == NF3SOCK || args->ftype == NF3FIFO)
+ p = decode_sattr3(p, &args->attrs);
if (args->ftype == NF3BLK || args->ftype == NF3CHR) {
args->major = ntohl(*p++);
diff --git a/fs/nfsd/nfs4acl.c b/fs/nfsd/nfs4acl.c
index 673a53c014a..cc3b7badd48 100644
--- a/fs/nfsd/nfs4acl.c
+++ b/fs/nfsd/nfs4acl.c
@@ -137,7 +137,6 @@ struct ace_container {
static short ace2type(struct nfs4_ace *);
static void _posix_to_nfsv4_one(struct posix_acl *, struct nfs4_acl *,
unsigned int);
-void nfs4_acl_add_ace(struct nfs4_acl *, u32, u32, u32, int, uid_t);
struct nfs4_acl *
nfs4_acl_posix_to_nfsv4(struct posix_acl *pacl, struct posix_acl *dpacl,
@@ -785,21 +784,6 @@ nfs4_acl_new(int n)
return acl;
}
-void
-nfs4_acl_add_ace(struct nfs4_acl *acl, u32 type, u32 flag, u32 access_mask,
- int whotype, uid_t who)
-{
- struct nfs4_ace *ace = acl->aces + acl->naces;
-
- ace->type = type;
- ace->flag = flag;
- ace->access_mask = access_mask;
- ace->whotype = whotype;
- ace->who = who;
-
- acl->naces++;
-}
-
static struct {
char *string;
int stringlen;
@@ -851,6 +835,5 @@ nfs4_acl_write_who(int who, char *p)
}
EXPORT_SYMBOL(nfs4_acl_new);
-EXPORT_SYMBOL(nfs4_acl_add_ace);
EXPORT_SYMBOL(nfs4_acl_get_whotype);
EXPORT_SYMBOL(nfs4_acl_write_who);
diff --git a/fs/nfsd/nfs4callback.c b/fs/nfsd/nfs4callback.c
index 32ffea033c7..864090edc28 100644
--- a/fs/nfsd/nfs4callback.c
+++ b/fs/nfsd/nfs4callback.c
@@ -38,6 +38,7 @@
#include <linux/inet.h>
#include <linux/errno.h>
#include <linux/delay.h>
+#include <linux/sched.h>
#include <linux/sunrpc/xdr.h>
#include <linux/sunrpc/svc.h>
#include <linux/sunrpc/clnt.h>
diff --git a/fs/nfsd/nfs4idmap.c b/fs/nfsd/nfs4idmap.c
index e4a83d727af..45aa21ce678 100644
--- a/fs/nfsd/nfs4idmap.c
+++ b/fs/nfsd/nfs4idmap.c
@@ -46,7 +46,6 @@
#include <linux/nfs4.h>
#include <linux/nfs_fs.h>
#include <linux/nfs_page.h>
-#include <linux/smp_lock.h>
#include <linux/sunrpc/cache.h>
#include <linux/nfsd_idmap.h>
#include <linux/list.h>
diff --git a/fs/nfsd/nfs4recover.c b/fs/nfsd/nfs4recover.c
index c7774e3a946..ebd03cc0747 100644
--- a/fs/nfsd/nfs4recover.c
+++ b/fs/nfsd/nfs4recover.c
@@ -45,7 +45,7 @@
#include <asm/uaccess.h>
#include <asm/scatterlist.h>
#include <linux/crypto.h>
-
+#include <linux/sched.h>
#define NFSDDBG_FACILITY NFSDDBG_PROC
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 678f3be88ac..3cc8ce422ab 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -1326,8 +1326,6 @@ do_recall(void *__dp)
{
struct nfs4_delegation *dp = __dp;
- daemonize("nfsv4-recall");
-
nfsd4_cb_recall(dp);
return 0;
}
diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c
index 5d090f11f2b..15809dfd88a 100644
--- a/fs/nfsd/nfs4xdr.c
+++ b/fs/nfsd/nfs4xdr.c
@@ -44,7 +44,6 @@
#include <linux/param.h>
#include <linux/smp.h>
-#include <linux/smp_lock.h>
#include <linux/fs.h>
#include <linux/namei.h>
#include <linux/vfs.h>
diff --git a/fs/nfsd/nfsfh.c b/fs/nfsd/nfsfh.c
index 8d995bcef80..6ca2d24fc21 100644
--- a/fs/nfsd/nfsfh.c
+++ b/fs/nfsd/nfsfh.c
@@ -10,7 +10,6 @@
*/
#include <linux/slab.h>
-#include <linux/smp_lock.h>
#include <linux/fs.h>
#include <linux/unistd.h>
#include <linux/string.h>
@@ -324,7 +323,7 @@ fh_compose(struct svc_fh *fhp, struct svc_export *exp, struct dentry *dentry,
*
*/
- u8 version = 1;
+ u8 version;
u8 fsid_type = 0;
struct inode * inode = dentry->d_inode;
struct dentry *parent = dentry->d_parent;
@@ -342,15 +341,59 @@ fh_compose(struct svc_fh *fhp, struct svc_export *exp, struct dentry *dentry,
* the reference filehandle (if it is in the same export)
* or the export options.
*/
+ retry:
+ version = 1;
if (ref_fh && ref_fh->fh_export == exp) {
version = ref_fh->fh_handle.fh_version;
- if (version == 0xca)
+ fsid_type = ref_fh->fh_handle.fh_fsid_type;
+
+ if (ref_fh == fhp)
+ fh_put(ref_fh);
+ ref_fh = NULL;
+
+ switch (version) {
+ case 0xca:
fsid_type = FSID_DEV;
- else
- fsid_type = ref_fh->fh_handle.fh_fsid_type;
- /* We know this version/type works for this export
- * so there is no need for further checks.
+ break;
+ case 1:
+ break;
+ default:
+ goto retry;
+ }
+
+ /* Need to check that this type works for this
+ * export point. As the fsid -> filesystem mapping
+ * was guided by user-space, there is no guarantee
+ * that the filesystem actually supports that fsid
+ * type. If it doesn't we loop around again without
+ * ref_fh set.
*/
+ switch(fsid_type) {
+ case FSID_DEV:
+ if (!old_valid_dev(ex_dev))
+ goto retry;
+ /* FALL THROUGH */
+ case FSID_MAJOR_MINOR:
+ case FSID_ENCODE_DEV:
+ if (!(exp->ex_dentry->d_inode->i_sb->s_type->fs_flags
+ & FS_REQUIRES_DEV))
+ goto retry;
+ break;
+ case FSID_NUM:
+ if (! (exp->ex_flags & NFSEXP_FSID))
+ goto retry;
+ break;
+ case FSID_UUID8:
+ case FSID_UUID16:
+ if (!root_export)
+ goto retry;
+ /* fall through */
+ case FSID_UUID4_INUM:
+ case FSID_UUID16_INUM:
+ if (exp->ex_uuid == NULL)
+ goto retry;
+ break;
+ }
} else if (exp->ex_uuid) {
if (fhp->fh_maxsize >= 64) {
if (root_export)
diff --git a/fs/nfsd/nfsproc.c b/fs/nfsd/nfsproc.c
index 5cc2eec981b..b2c7147aa92 100644
--- a/fs/nfsd/nfsproc.c
+++ b/fs/nfsd/nfsproc.c
@@ -155,7 +155,7 @@ nfsd_proc_read(struct svc_rqst *rqstp, struct nfsd_readargs *argp,
argp->count);
argp->count = NFSSVC_MAXBLKSIZE_V2;
}
- svc_reserve(rqstp, (19<<2) + argp->count + 4);
+ svc_reserve_auth(rqstp, (19<<2) + argp->count + 4);
resp->count = argp->count;
nfserr = nfsd_read(rqstp, fh_copy(&resp->fh, &argp->fh), NULL,
diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c
index d7759ce6ed9..ff55950efb4 100644
--- a/fs/nfsd/nfssvc.c
+++ b/fs/nfsd/nfssvc.c
@@ -9,7 +9,7 @@
*/
#include <linux/module.h>
-
+#include <linux/sched.h>
#include <linux/time.h>
#include <linux/errno.h>
#include <linux/nfs.h>
diff --git a/fs/nfsd/nfsxdr.c b/fs/nfsd/nfsxdr.c
index 0c24b9e24fe..cb3e7fadb77 100644
--- a/fs/nfsd/nfsxdr.c
+++ b/fs/nfsd/nfsxdr.c
@@ -231,9 +231,10 @@ int
nfssvc_decode_sattrargs(struct svc_rqst *rqstp, __be32 *p,
struct nfsd_sattrargs *args)
{
- if (!(p = decode_fh(p, &args->fh))
- || !(p = decode_sattr(p, &args->attrs)))
+ p = decode_fh(p, &args->fh);
+ if (!p)
return 0;
+ p = decode_sattr(p, &args->attrs);
return xdr_argsize_check(rqstp, p);
}
@@ -284,8 +285,9 @@ int
nfssvc_decode_writeargs(struct svc_rqst *rqstp, __be32 *p,
struct nfsd_writeargs *args)
{
- unsigned int len;
+ unsigned int len, hdr, dlen;
int v;
+
if (!(p = decode_fh(p, &args->fh)))
return 0;
@@ -293,11 +295,30 @@ nfssvc_decode_writeargs(struct svc_rqst *rqstp, __be32 *p,
args->offset = ntohl(*p++); /* offset */
p++; /* totalcount */
len = args->len = ntohl(*p++);
- rqstp->rq_vec[0].iov_base = (void*)p;
- rqstp->rq_vec[0].iov_len = rqstp->rq_arg.head[0].iov_len -
- (((void*)p) - rqstp->rq_arg.head[0].iov_base);
+ /*
+ * The protocol specifies a maximum of 8192 bytes.
+ */
if (len > NFSSVC_MAXBLKSIZE_V2)
- len = NFSSVC_MAXBLKSIZE_V2;
+ return 0;
+
+ /*
+ * Check to make sure that we got the right number of
+ * bytes.
+ */
+ hdr = (void*)p - rqstp->rq_arg.head[0].iov_base;
+ dlen = rqstp->rq_arg.head[0].iov_len + rqstp->rq_arg.page_len
+ - hdr;
+
+ /*
+ * Round the length of the data which was specified up to
+ * the next multiple of XDR units and then compare that
+ * against the length which was actually received.
+ */
+ if (dlen != XDR_QUADLEN(len)*4)
+ return 0;
+
+ rqstp->rq_vec[0].iov_base = (void*)p;
+ rqstp->rq_vec[0].iov_len = rqstp->rq_arg.head[0].iov_len - hdr;
v = 0;
while (len > rqstp->rq_vec[v].iov_len) {
len -= rqstp->rq_vec[v].iov_len;
@@ -306,18 +327,18 @@ nfssvc_decode_writeargs(struct svc_rqst *rqstp, __be32 *p,
rqstp->rq_vec[v].iov_len = PAGE_SIZE;
}
rqstp->rq_vec[v].iov_len = len;
- args->vlen = v+1;
- return rqstp->rq_vec[0].iov_len > 0;
+ args->vlen = v + 1;
+ return 1;
}
int
nfssvc_decode_createargs(struct svc_rqst *rqstp, __be32 *p,
struct nfsd_createargs *args)
{
- if (!(p = decode_fh(p, &args->fh))
- || !(p = decode_filename(p, &args->name, &args->len))
- || !(p = decode_sattr(p, &args->attrs)))
+ if ( !(p = decode_fh(p, &args->fh))
+ || !(p = decode_filename(p, &args->name, &args->len)))
return 0;
+ p = decode_sattr(p, &args->attrs);
return xdr_argsize_check(rqstp, p);
}
@@ -361,11 +382,11 @@ int
nfssvc_decode_symlinkargs(struct svc_rqst *rqstp, __be32 *p,
struct nfsd_symlinkargs *args)
{
- if (!(p = decode_fh(p, &args->ffh))
- || !(p = decode_filename(p, &args->fname, &args->flen))
- || !(p = decode_pathname(p, &args->tname, &args->tlen))
- || !(p = decode_sattr(p, &args->attrs)))
+ if ( !(p = decode_fh(p, &args->ffh))
+ || !(p = decode_filename(p, &args->fname, &args->flen))
+ || !(p = decode_pathname(p, &args->tname, &args->tlen)))
return 0;
+ p = decode_sattr(p, &args->attrs);
return xdr_argsize_check(rqstp, p);
}
diff --git a/fs/ntfs/aops.c b/fs/ntfs/aops.c
index 629e7abdd84..6e5c2534f4b 100644
--- a/fs/ntfs/aops.c
+++ b/fs/ntfs/aops.c
@@ -86,19 +86,15 @@ static void ntfs_end_buffer_async_read(struct buffer_head *bh, int uptodate)
}
/* Check for the current buffer head overflowing. */
if (unlikely(file_ofs + bh->b_size > init_size)) {
- u8 *kaddr;
int ofs;
ofs = 0;
if (file_ofs < init_size)
ofs = init_size - file_ofs;
local_irq_save(flags);
- kaddr = kmap_atomic(page, KM_BIO_SRC_IRQ);
- memset(kaddr + bh_offset(bh) + ofs, 0,
- bh->b_size - ofs);
- kunmap_atomic(kaddr, KM_BIO_SRC_IRQ);
+ zero_user_page(page, bh_offset(bh) + ofs,
+ bh->b_size - ofs, KM_BIO_SRC_IRQ);
local_irq_restore(flags);
- flush_dcache_page(page);
}
} else {
clear_buffer_uptodate(bh);
@@ -245,8 +241,7 @@ static int ntfs_read_block(struct page *page)
rl = NULL;
nr = i = 0;
do {
- u8 *kaddr;
- int err;
+ int err = 0;
if (unlikely(buffer_uptodate(bh)))
continue;
@@ -254,7 +249,6 @@ static int ntfs_read_block(struct page *page)
arr[nr++] = bh;
continue;
}
- err = 0;
bh->b_bdev = vol->sb->s_bdev;
/* Is the block within the allowed limits? */
if (iblock < lblock) {
@@ -340,10 +334,7 @@ handle_hole:
bh->b_blocknr = -1UL;
clear_buffer_mapped(bh);
handle_zblock:
- kaddr = kmap_atomic(page, KM_USER0);
- memset(kaddr + i * blocksize, 0, blocksize);
- kunmap_atomic(kaddr, KM_USER0);
- flush_dcache_page(page);
+ zero_user_page(page, i * blocksize, blocksize, KM_USER0);
if (likely(!err))
set_buffer_uptodate(bh);
} while (i++, iblock++, (bh = bh->b_this_page) != head);
@@ -460,10 +451,7 @@ retry_readpage:
* ok to ignore the compressed flag here.
*/
if (unlikely(page->index > 0)) {
- kaddr = kmap_atomic(page, KM_USER0);
- memset(kaddr, 0, PAGE_CACHE_SIZE);
- flush_dcache_page(page);
- kunmap_atomic(kaddr, KM_USER0);
+ zero_user_page(page, 0, PAGE_CACHE_SIZE, KM_USER0);
goto done;
}
if (!NInoAttr(ni))
@@ -790,14 +778,10 @@ lock_retry_remap:
* uptodate so it can get discarded by the VM.
*/
if (err == -ENOENT || lcn == LCN_ENOENT) {
- u8 *kaddr;
-
bh->b_blocknr = -1;
clear_buffer_dirty(bh);
- kaddr = kmap_atomic(page, KM_USER0);
- memset(kaddr + bh_offset(bh), 0, blocksize);
- kunmap_atomic(kaddr, KM_USER0);
- flush_dcache_page(page);
+ zero_user_page(page, bh_offset(bh), blocksize,
+ KM_USER0);
set_buffer_uptodate(bh);
err = 0;
continue;
@@ -1422,10 +1406,8 @@ retry_writepage:
if (page->index >= (i_size >> PAGE_CACHE_SHIFT)) {
/* The page straddles i_size. */
unsigned int ofs = i_size & ~PAGE_CACHE_MASK;
- kaddr = kmap_atomic(page, KM_USER0);
- memset(kaddr + ofs, 0, PAGE_CACHE_SIZE - ofs);
- kunmap_atomic(kaddr, KM_USER0);
- flush_dcache_page(page);
+ zero_user_page(page, ofs, PAGE_CACHE_SIZE - ofs,
+ KM_USER0);
}
/* Handle mst protected attributes. */
if (NInoMstProtected(ni))
diff --git a/fs/ntfs/dir.c b/fs/ntfs/dir.c
index 74f99a6a369..34314b33dbd 100644
--- a/fs/ntfs/dir.c
+++ b/fs/ntfs/dir.c
@@ -20,7 +20,6 @@
* Foundation,Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
*/
-#include <linux/smp_lock.h>
#include <linux/buffer_head.h>
#include "dir.h"
diff --git a/fs/ntfs/file.c b/fs/ntfs/file.c
index dbbac559310..7ed56390b58 100644
--- a/fs/ntfs/file.c
+++ b/fs/ntfs/file.c
@@ -26,6 +26,7 @@
#include <linux/swap.h>
#include <linux/uio.h>
#include <linux/writeback.h>
+#include <linux/sched.h>
#include <asm/page.h>
#include <asm/uaccess.h>
@@ -606,11 +607,8 @@ do_next_page:
ntfs_submit_bh_for_read(bh);
*wait_bh++ = bh;
} else {
- u8 *kaddr = kmap_atomic(page, KM_USER0);
- memset(kaddr + bh_offset(bh), 0,
- blocksize);
- kunmap_atomic(kaddr, KM_USER0);
- flush_dcache_page(page);
+ zero_user_page(page, bh_offset(bh),
+ blocksize, KM_USER0);
set_buffer_uptodate(bh);
}
}
@@ -685,12 +683,9 @@ map_buffer_cached:
ntfs_submit_bh_for_read(bh);
*wait_bh++ = bh;
} else {
- u8 *kaddr = kmap_atomic(page,
- KM_USER0);
- memset(kaddr + bh_offset(bh),
- 0, blocksize);
- kunmap_atomic(kaddr, KM_USER0);
- flush_dcache_page(page);
+ zero_user_page(page,
+ bh_offset(bh),
+ blocksize, KM_USER0);
set_buffer_uptodate(bh);
}
}
@@ -708,11 +703,8 @@ map_buffer_cached:
*/
if (bh_end <= pos || bh_pos >= end) {
if (!buffer_uptodate(bh)) {
- u8 *kaddr = kmap_atomic(page, KM_USER0);
- memset(kaddr + bh_offset(bh), 0,
- blocksize);
- kunmap_atomic(kaddr, KM_USER0);
- flush_dcache_page(page);
+ zero_user_page(page, bh_offset(bh),
+ blocksize, KM_USER0);
set_buffer_uptodate(bh);
}
mark_buffer_dirty(bh);
@@ -751,10 +743,8 @@ map_buffer_cached:
if (!buffer_uptodate(bh))
set_buffer_uptodate(bh);
} else if (!buffer_uptodate(bh)) {
- u8 *kaddr = kmap_atomic(page, KM_USER0);
- memset(kaddr + bh_offset(bh), 0, blocksize);
- kunmap_atomic(kaddr, KM_USER0);
- flush_dcache_page(page);
+ zero_user_page(page, bh_offset(bh), blocksize,
+ KM_USER0);
set_buffer_uptodate(bh);
}
continue;
@@ -878,11 +868,8 @@ rl_not_mapped_enoent:
if (!buffer_uptodate(bh))
set_buffer_uptodate(bh);
} else if (!buffer_uptodate(bh)) {
- u8 *kaddr = kmap_atomic(page, KM_USER0);
- memset(kaddr + bh_offset(bh), 0,
- blocksize);
- kunmap_atomic(kaddr, KM_USER0);
- flush_dcache_page(page);
+ zero_user_page(page, bh_offset(bh),
+ blocksize, KM_USER0);
set_buffer_uptodate(bh);
}
continue;
@@ -1137,16 +1124,12 @@ rl_not_mapped_enoent:
* to zero the overflowing region.
*/
if (unlikely(bh_pos + blocksize > initialized_size)) {
- u8 *kaddr;
int ofs = 0;
if (likely(bh_pos < initialized_size))
ofs = initialized_size - bh_pos;
- kaddr = kmap_atomic(page, KM_USER0);
- memset(kaddr + bh_offset(bh) + ofs, 0,
- blocksize - ofs);
- kunmap_atomic(kaddr, KM_USER0);
- flush_dcache_page(page);
+ zero_user_page(page, bh_offset(bh) + ofs,
+ blocksize - ofs, KM_USER0);
}
} else /* if (unlikely(!buffer_uptodate(bh))) */
err = -EIO;
@@ -1286,11 +1269,8 @@ rl_not_mapped_enoent:
if (PageUptodate(page))
set_buffer_uptodate(bh);
else {
- u8 *kaddr = kmap_atomic(page, KM_USER0);
- memset(kaddr + bh_offset(bh), 0,
- blocksize);
- kunmap_atomic(kaddr, KM_USER0);
- flush_dcache_page(page);
+ zero_user_page(page, bh_offset(bh),
+ blocksize, KM_USER0);
set_buffer_uptodate(bh);
}
}
@@ -1350,9 +1330,7 @@ err_out:
len = PAGE_CACHE_SIZE;
if (len > bytes)
len = bytes;
- kaddr = kmap_atomic(*pages, KM_USER0);
- memset(kaddr, 0, len);
- kunmap_atomic(kaddr, KM_USER0);
+ zero_user_page(*pages, 0, len, KM_USER0);
}
goto out;
}
@@ -1473,9 +1451,7 @@ err_out:
len = PAGE_CACHE_SIZE;
if (len > bytes)
len = bytes;
- kaddr = kmap_atomic(*pages, KM_USER0);
- memset(kaddr, 0, len);
- kunmap_atomic(kaddr, KM_USER0);
+ zero_user_page(*pages, 0, len, KM_USER0);
}
goto out;
}
@@ -2129,28 +2105,13 @@ static ssize_t ntfs_file_aio_write_nolock(struct kiocb *iocb,
struct address_space *mapping = file->f_mapping;
struct inode *inode = mapping->host;
loff_t pos;
- unsigned long seg;
size_t count; /* after file limit checks */
ssize_t written, err;
count = 0;
- for (seg = 0; seg < nr_segs; seg++) {
- const struct iovec *iv = &iov[seg];
- /*
- * If any segment has a negative length, or the cumulative
- * length ever wraps negative then return -EINVAL.
- */
- count += iv->iov_len;
- if (unlikely((ssize_t)(count|iv->iov_len) < 0))
- return -EINVAL;
- if (access_ok(VERIFY_READ, iv->iov_base, iv->iov_len))
- continue;
- if (!seg)
- return -EFAULT;
- nr_segs = seg;
- count -= iv->iov_len; /* This segment is no good */
- break;
- }
+ err = generic_segment_checks(iov, &nr_segs, &count, VERIFY_READ);
+ if (err)
+ return err;
pos = *ppos;
vfs_check_frozen(inode->i_sb, SB_FREEZE_WRITE);
/* We can write back this queue in page reclaim. */
diff --git a/fs/ntfs/inode.c b/fs/ntfs/inode.c
index f8bf8da67ee..b532a730cec 100644
--- a/fs/ntfs/inode.c
+++ b/fs/ntfs/inode.c
@@ -27,7 +27,6 @@
#include <linux/pagemap.h>
#include <linux/quotaops.h>
#include <linux/slab.h>
-#include <linux/smp_lock.h>
#include "aops.h"
#include "attrib.h"
@@ -141,7 +140,7 @@ static int ntfs_init_locked_inode(struct inode *vi, ntfs_attr *na)
if (!ni->name)
return -ENOMEM;
memcpy(ni->name, na->name, i);
- ni->name[i] = 0;
+ ni->name[na->name_len] = 0;
}
return 0;
}
diff --git a/fs/ntfs/super.c b/fs/ntfs/super.c
index 21d834e5ed7..4566b918255 100644
--- a/fs/ntfs/super.c
+++ b/fs/ntfs/super.c
@@ -3085,8 +3085,7 @@ static void ntfs_big_inode_init_once(void *foo, struct kmem_cache *cachep,
{
ntfs_inode *ni = (ntfs_inode *)foo;
- if (flags & SLAB_CTOR_CONSTRUCTOR)
- inode_init_once(VFS_I(ni));
+ inode_init_once(VFS_I(ni));
}
/*
diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c
index 8e7cafb5fc6..a480b09c79b 100644
--- a/fs/ocfs2/aops.c
+++ b/fs/ocfs2/aops.c
@@ -222,7 +222,10 @@ static int ocfs2_readpage(struct file *file, struct page *page)
goto out;
}
- down_read(&OCFS2_I(inode)->ip_alloc_sem);
+ if (down_read_trylock(&OCFS2_I(inode)->ip_alloc_sem) == 0) {
+ ret = AOP_TRUNCATED_PAGE;
+ goto out_meta_unlock;
+ }
/*
* i_size might have just been updated as we grabed the meta lock. We
@@ -235,10 +238,7 @@ static int ocfs2_readpage(struct file *file, struct page *page)
* XXX sys_readahead() seems to get that wrong?
*/
if (start >= i_size_read(inode)) {
- char *addr = kmap(page);
- memset(addr, 0, PAGE_SIZE);
- flush_dcache_page(page);
- kunmap(page);
+ zero_user_page(page, 0, PAGE_SIZE, KM_USER0);
SetPageUptodate(page);
ret = 0;
goto out_alloc;
@@ -258,6 +258,7 @@ static int ocfs2_readpage(struct file *file, struct page *page)
ocfs2_data_unlock(inode, 0);
out_alloc:
up_read(&OCFS2_I(inode)->ip_alloc_sem);
+out_meta_unlock:
ocfs2_meta_unlock(inode, 0);
out:
if (unlock)
@@ -797,6 +798,11 @@ int ocfs2_map_and_write_splice_data(struct inode *inode,
}
to = from + bytes;
+ BUG_ON(from > PAGE_CACHE_SIZE);
+ BUG_ON(to > PAGE_CACHE_SIZE);
+ BUG_ON(from < cluster_start);
+ BUG_ON(to > cluster_end);
+
if (wc->w_this_page_new)
ret = ocfs2_map_page_blocks(wc->w_this_page, p_blkno, inode,
cluster_start, cluster_end, 1);
@@ -808,11 +814,6 @@ int ocfs2_map_and_write_splice_data(struct inode *inode,
goto out;
}
- BUG_ON(from > PAGE_CACHE_SIZE);
- BUG_ON(to > PAGE_CACHE_SIZE);
- BUG_ON(from > osb->s_clustersize);
- BUG_ON(to > osb->s_clustersize);
-
src = buf->ops->map(sp->s_pipe, buf, 1);
dst = kmap_atomic(wc->w_this_page, KM_USER1);
memcpy(dst + from, src + src_from, bytes);
@@ -889,6 +890,11 @@ int ocfs2_map_and_write_user_data(struct inode *inode,
to = from + bytes;
+ BUG_ON(from > PAGE_CACHE_SIZE);
+ BUG_ON(to > PAGE_CACHE_SIZE);
+ BUG_ON(from < cluster_start);
+ BUG_ON(to > cluster_end);
+
if (wc->w_this_page_new)
ret = ocfs2_map_page_blocks(wc->w_this_page, p_blkno, inode,
cluster_start, cluster_end, 1);
@@ -900,11 +906,6 @@ int ocfs2_map_and_write_user_data(struct inode *inode,
goto out;
}
- BUG_ON(from > PAGE_CACHE_SIZE);
- BUG_ON(to > PAGE_CACHE_SIZE);
- BUG_ON(from > osb->s_clustersize);
- BUG_ON(to > osb->s_clustersize);
-
dst = kmap(wc->w_this_page);
memcpy(dst + from, bp->b_src_buf + src_from, bytes);
kunmap(wc->w_this_page);
diff --git a/fs/ocfs2/cluster/masklog.c b/fs/ocfs2/cluster/masklog.c
index 2e975c0a35e..2b205f5d579 100644
--- a/fs/ocfs2/cluster/masklog.c
+++ b/fs/ocfs2/cluster/masklog.c
@@ -157,7 +157,7 @@ int mlog_sys_init(struct kset *o2cb_subsys)
}
mlog_attr_ptrs[i] = NULL;
- kobj_set_kset_s(&mlog_kset, o2cb_subsys);
+ kobj_set_kset_s(&mlog_kset, *o2cb_subsys);
return kset_register(&mlog_kset);
}
diff --git a/fs/ocfs2/dlm/dlmfs.c b/fs/ocfs2/dlm/dlmfs.c
index d4e46d067ed..fd8cb1badc9 100644
--- a/fs/ocfs2/dlm/dlmfs.c
+++ b/fs/ocfs2/dlm/dlmfs.c
@@ -42,7 +42,6 @@
#include <linux/highmem.h>
#include <linux/init.h>
#include <linux/string.h>
-#include <linux/smp_lock.h>
#include <linux/backing-dev.h>
#include <asm/uaccess.h>
@@ -263,12 +262,10 @@ static void dlmfs_init_once(void *foo,
struct dlmfs_inode_private *ip =
(struct dlmfs_inode_private *) foo;
- if (flags & SLAB_CTOR_CONSTRUCTOR) {
- ip->ip_dlm = NULL;
- ip->ip_parent = NULL;
+ ip->ip_dlm = NULL;
+ ip->ip_parent = NULL;
- inode_init_once(&ip->ip_vfs_inode);
- }
+ inode_init_once(&ip->ip_vfs_inode);
}
static struct inode *dlmfs_alloc_inode(struct super_block *sb)
diff --git a/fs/ocfs2/dlmglue.c b/fs/ocfs2/dlmglue.c
index 024777abc8e..d1bd305ef0d 100644
--- a/fs/ocfs2/dlmglue.c
+++ b/fs/ocfs2/dlmglue.c
@@ -27,7 +27,6 @@
#include <linux/slab.h>
#include <linux/highmem.h>
#include <linux/mm.h>
-#include <linux/smp_lock.h>
#include <linux/crc32.h>
#include <linux/kthread.h>
#include <linux/pagemap.h>
diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c
index 9395b4fa547..ac6c96431bb 100644
--- a/fs/ocfs2/file.c
+++ b/fs/ocfs2/file.c
@@ -326,6 +326,7 @@ static int ocfs2_truncate_file(struct inode *inode,
(unsigned long long)OCFS2_I(inode)->ip_blkno,
(unsigned long long)new_i_size);
+ unmap_mapping_range(inode->i_mapping, new_i_size + PAGE_SIZE - 1, 0, 1);
truncate_inode_pages(inode->i_mapping, new_i_size);
fe = (struct ocfs2_dinode *) di_bh->b_data;
@@ -1418,36 +1419,6 @@ out:
return total ? total : ret;
}
-static int ocfs2_check_iovec(const struct iovec *iov, size_t *counted,
- unsigned long *nr_segs)
-{
- size_t ocount; /* original count */
- unsigned long seg;
-
- ocount = 0;
- for (seg = 0; seg < *nr_segs; seg++) {
- const struct iovec *iv = &iov[seg];
-
- /*
- * If any segment has a negative length, or the cumulative
- * length ever wraps negative then return -EINVAL.
- */
- ocount += iv->iov_len;
- if (unlikely((ssize_t)(ocount|iv->iov_len) < 0))
- return -EINVAL;
- if (access_ok(VERIFY_READ, iv->iov_base, iv->iov_len))
- continue;
- if (seg == 0)
- return -EFAULT;
- *nr_segs = seg;
- ocount -= iv->iov_len; /* This segment is no good */
- break;
- }
-
- *counted = ocount;
- return 0;
-}
-
static ssize_t ocfs2_file_aio_write(struct kiocb *iocb,
const struct iovec *iov,
unsigned long nr_segs,
@@ -1470,7 +1441,7 @@ static ssize_t ocfs2_file_aio_write(struct kiocb *iocb,
if (iocb->ki_left == 0)
return 0;
- ret = ocfs2_check_iovec(iov, &ocount, &nr_segs);
+ ret = generic_segment_checks(iov, &nr_segs, &ocount, VERIFY_READ);
if (ret)
return ret;
diff --git a/fs/ocfs2/inode.c b/fs/ocfs2/inode.c
index bc844bfe607..c53a6763bbb 100644
--- a/fs/ocfs2/inode.c
+++ b/fs/ocfs2/inode.c
@@ -28,7 +28,6 @@
#include <linux/slab.h>
#include <linux/highmem.h>
#include <linux/pagemap.h>
-#include <linux/smp_lock.h>
#include <asm/byteorder.h>
diff --git a/fs/ocfs2/localalloc.c b/fs/ocfs2/localalloc.c
index 4dedd978910..545f7892cdf 100644
--- a/fs/ocfs2/localalloc.c
+++ b/fs/ocfs2/localalloc.c
@@ -471,9 +471,6 @@ int ocfs2_reserve_local_alloc_bits(struct ocfs2_super *osb,
mutex_lock(&local_alloc_inode->i_mutex);
- ac->ac_inode = local_alloc_inode;
- ac->ac_which = OCFS2_AC_USE_LOCAL;
-
if (osb->local_alloc_state != OCFS2_LA_ENABLED) {
status = -ENOSPC;
goto bail;
@@ -511,10 +508,14 @@ int ocfs2_reserve_local_alloc_bits(struct ocfs2_super *osb,
}
}
+ ac->ac_inode = local_alloc_inode;
+ ac->ac_which = OCFS2_AC_USE_LOCAL;
get_bh(osb->local_alloc_bh);
ac->ac_bh = osb->local_alloc_bh;
status = 0;
bail:
+ if (status < 0 && local_alloc_inode)
+ iput(local_alloc_inode);
mlog_exit(status);
return status;
diff --git a/fs/ocfs2/slot_map.c b/fs/ocfs2/slot_map.c
index d921a28329d..d8b79067dc1 100644
--- a/fs/ocfs2/slot_map.c
+++ b/fs/ocfs2/slot_map.c
@@ -26,7 +26,6 @@
#include <linux/types.h>
#include <linux/slab.h>
#include <linux/highmem.h>
-#include <linux/smp_lock.h>
#define MLOG_MASK_PREFIX ML_SUPER
#include <cluster/masklog.h>
diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c
index 7c5e3f5d663..86b559c7dce 100644
--- a/fs/ocfs2/super.c
+++ b/fs/ocfs2/super.c
@@ -937,31 +937,29 @@ static void ocfs2_inode_init_once(void *data,
{
struct ocfs2_inode_info *oi = data;
- if (flags & SLAB_CTOR_CONSTRUCTOR) {
- oi->ip_flags = 0;
- oi->ip_open_count = 0;
- spin_lock_init(&oi->ip_lock);
- ocfs2_extent_map_init(&oi->vfs_inode);
- INIT_LIST_HEAD(&oi->ip_io_markers);
- oi->ip_created_trans = 0;
- oi->ip_last_trans = 0;
- oi->ip_dir_start_lookup = 0;
+ oi->ip_flags = 0;
+ oi->ip_open_count = 0;
+ spin_lock_init(&oi->ip_lock);
+ ocfs2_extent_map_init(&oi->vfs_inode);
+ INIT_LIST_HEAD(&oi->ip_io_markers);
+ oi->ip_created_trans = 0;
+ oi->ip_last_trans = 0;
+ oi->ip_dir_start_lookup = 0;
- init_rwsem(&oi->ip_alloc_sem);
- mutex_init(&oi->ip_io_mutex);
+ init_rwsem(&oi->ip_alloc_sem);
+ mutex_init(&oi->ip_io_mutex);
- oi->ip_blkno = 0ULL;
- oi->ip_clusters = 0;
+ oi->ip_blkno = 0ULL;
+ oi->ip_clusters = 0;
- ocfs2_lock_res_init_once(&oi->ip_rw_lockres);
- ocfs2_lock_res_init_once(&oi->ip_meta_lockres);
- ocfs2_lock_res_init_once(&oi->ip_data_lockres);
- ocfs2_lock_res_init_once(&oi->ip_open_lockres);
+ ocfs2_lock_res_init_once(&oi->ip_rw_lockres);
+ ocfs2_lock_res_init_once(&oi->ip_meta_lockres);
+ ocfs2_lock_res_init_once(&oi->ip_data_lockres);
+ ocfs2_lock_res_init_once(&oi->ip_open_lockres);
- ocfs2_metadata_cache_init(&oi->vfs_inode);
+ ocfs2_metadata_cache_init(&oi->vfs_inode);
- inode_init_once(&oi->vfs_inode);
- }
+ inode_init_once(&oi->vfs_inode);
}
static int ocfs2_initialize_mem_caches(void)
diff --git a/fs/ocfs2/vote.c b/fs/ocfs2/vote.c
index 4f82a2f0efe..66a13ee63d4 100644
--- a/fs/ocfs2/vote.c
+++ b/fs/ocfs2/vote.c
@@ -26,7 +26,6 @@
#include <linux/types.h>
#include <linux/slab.h>
#include <linux/highmem.h>
-#include <linux/smp_lock.h>
#include <linux/kthread.h>
#include <cluster/heartbeat.h>
diff --git a/fs/open.c b/fs/open.c
index c989fb4cf7b..0d515d16197 100644
--- a/fs/open.c
+++ b/fs/open.c
@@ -7,7 +7,6 @@
#include <linux/string.h>
#include <linux/mm.h>
#include <linux/file.h>
-#include <linux/smp_lock.h>
#include <linux/quotaops.h>
#include <linux/fsnotify.h>
#include <linux/module.h>
@@ -211,6 +210,9 @@ int do_truncate(struct dentry *dentry, loff_t length, unsigned int time_attrs,
newattrs.ia_valid |= ATTR_FILE;
}
+ /* Remove suid/sgid on truncate too */
+ newattrs.ia_valid |= should_remove_suid(dentry);
+
mutex_lock(&dentry->d_inode->i_mutex);
err = notify_change(dentry, &newattrs);
mutex_unlock(&dentry->d_inode->i_mutex);
diff --git a/fs/openpromfs/inode.c b/fs/openpromfs/inode.c
index 731a90e9f0c..e62397341c3 100644
--- a/fs/openpromfs/inode.c
+++ b/fs/openpromfs/inode.c
@@ -419,8 +419,7 @@ static void op_inode_init_once(void *data, struct kmem_cache * cachep, unsigned
{
struct op_inode_info *oi = (struct op_inode_info *) data;
- if (flags & SLAB_CTOR_CONSTRUCTOR)
- inode_init_once(&oi->vfs_inode);
+ inode_init_once(&oi->vfs_inode);
}
static int __init init_openprom_fs(void)
diff --git a/fs/partitions/Kconfig b/fs/partitions/Kconfig
index 6e8bb66fe61..a99acd8de35 100644
--- a/fs/partitions/Kconfig
+++ b/fs/partitions/Kconfig
@@ -166,8 +166,12 @@ config LDM_PARTITION
depends on PARTITION_ADVANCED
---help---
Say Y here if you would like to use hard disks under Linux which
- were partitioned using Windows 2000's or XP's Logical Disk Manager.
- They are also known as "Dynamic Disks".
+ were partitioned using Windows 2000's/XP's or Vista's Logical Disk
+ Manager. They are also known as "Dynamic Disks".
+
+ Note this driver only supports Dynamic Disks with a protective MBR
+ label, i.e. DOS partition table. It does not support GPT labelled
+ Dynamic Disks yet as can be created with Vista.
Windows 2000 introduced the concept of Dynamic Disks to get around
the limitations of the PC's partitioning scheme. The Logical Disk
@@ -175,8 +179,8 @@ config LDM_PARTITION
mirrored, striped or RAID volumes, all without the need for
rebooting.
- Normal partitions are now called Basic Disks under Windows 2000 and
- XP.
+ Normal partitions are now called Basic Disks under Windows 2000, XP,
+ and Vista.
For a fuller description read <file:Documentation/ldm.txt>.
@@ -236,3 +240,12 @@ config EFI_PARTITION
help
Say Y here if you would like to use hard disks under Linux which
were partitioned using EFI GPT.
+
+config SYSV68_PARTITION
+ bool "SYSV68 partition table support" if PARTITION_ADVANCED
+ default y if VME
+ help
+ Say Y here if you would like to be able to read the hard disk
+ partition table format used by Motorola Delta machines (using
+ sysv68).
+ Otherwise, say N.
diff --git a/fs/partitions/Makefile b/fs/partitions/Makefile
index 67e665fdb7f..03af8eac51d 100644
--- a/fs/partitions/Makefile
+++ b/fs/partitions/Makefile
@@ -17,3 +17,4 @@ obj-$(CONFIG_ULTRIX_PARTITION) += ultrix.o
obj-$(CONFIG_IBM_PARTITION) += ibm.o
obj-$(CONFIG_EFI_PARTITION) += efi.o
obj-$(CONFIG_KARMA_PARTITION) += karma.o
+obj-$(CONFIG_SYSV68_PARTITION) += sysv68.o
diff --git a/fs/partitions/check.c b/fs/partitions/check.c
index 6b9dae3f0e6..9a3a058f355 100644
--- a/fs/partitions/check.c
+++ b/fs/partitions/check.c
@@ -34,6 +34,7 @@
#include "ultrix.h"
#include "efi.h"
#include "karma.h"
+#include "sysv68.h"
#ifdef CONFIG_BLK_DEV_MD
extern void md_autodetect_dev(dev_t dev);
@@ -105,6 +106,9 @@ static int (*check_part[])(struct parsed_partitions *, struct block_device *) =
#ifdef CONFIG_KARMA_PARTITION
karma_partition,
#endif
+#ifdef CONFIG_SYSV68_PARTITION
+ sysv68_partition,
+#endif
NULL
};
diff --git a/fs/partitions/efi.c b/fs/partitions/efi.c
index 1bea610078b..e7b07006bc4 100644
--- a/fs/partitions/efi.c
+++ b/fs/partitions/efi.c
@@ -152,7 +152,7 @@ last_lba(struct block_device *bdev)
}
static inline int
-pmbr_part_valid(struct partition *part, u64 lastlba)
+pmbr_part_valid(struct partition *part)
{
if (part->sys_ind == EFI_PMBR_OSTYPE_EFI_GPT &&
le32_to_cpu(part->start_sect) == 1UL)
@@ -163,7 +163,6 @@ pmbr_part_valid(struct partition *part, u64 lastlba)
/**
* is_pmbr_valid(): test Protective MBR for validity
* @mbr: pointer to a legacy mbr structure
- * @lastlba: last_lba for the whole device
*
* Description: Returns 1 if PMBR is valid, 0 otherwise.
* Validity depends on two things:
@@ -171,13 +170,13 @@ pmbr_part_valid(struct partition *part, u64 lastlba)
* 2) One partition of type 0xEE is found
*/
static int
-is_pmbr_valid(legacy_mbr *mbr, u64 lastlba)
+is_pmbr_valid(legacy_mbr *mbr)
{
int i;
if (!mbr || le16_to_cpu(mbr->signature) != MSDOS_MBR_SIGNATURE)
return 0;
for (i = 0; i < 4; i++)
- if (pmbr_part_valid(&mbr->partition_record[i], lastlba))
+ if (pmbr_part_valid(&mbr->partition_record[i]))
return 1;
return 0;
}
@@ -516,7 +515,7 @@ find_valid_gpt(struct block_device *bdev, gpt_header **gpt, gpt_entry **ptes)
int good_pgpt = 0, good_agpt = 0, good_pmbr = 0;
gpt_header *pgpt = NULL, *agpt = NULL;
gpt_entry *pptes = NULL, *aptes = NULL;
- legacy_mbr *legacymbr = NULL;
+ legacy_mbr *legacymbr;
u64 lastlba;
if (!bdev || !gpt || !ptes)
return 0;
@@ -528,9 +527,8 @@ find_valid_gpt(struct block_device *bdev, gpt_header **gpt, gpt_entry **ptes)
if (legacymbr) {
read_lba(bdev, 0, (u8 *) legacymbr,
sizeof (*legacymbr));
- good_pmbr = is_pmbr_valid(legacymbr, lastlba);
+ good_pmbr = is_pmbr_valid(legacymbr);
kfree(legacymbr);
- legacymbr=NULL;
}
if (!good_pmbr)
goto fail;
diff --git a/fs/partitions/ldm.c b/fs/partitions/ldm.c
index 1a60926a4cc..99873a2b4cb 100644
--- a/fs/partitions/ldm.c
+++ b/fs/partitions/ldm.c
@@ -2,10 +2,10 @@
* ldm - Support for Windows Logical Disk Manager (Dynamic Disks)
*
* Copyright (C) 2001,2002 Richard Russon <ldm@flatcap.org>
- * Copyright (c) 2001-2004 Anton Altaparmakov
+ * Copyright (c) 2001-2007 Anton Altaparmakov
* Copyright (C) 2001,2002 Jakob Kemi <jakob.kemi@telia.com>
*
- * Documentation is available at http://linux-ntfs.sf.net/ldm
+ * Documentation is available at http://www.linux-ntfs.org/content/view/19/37/
*
* This program is free software; you can redistribute it and/or modify it under
* the terms of the GNU General Public License as published by the Free Software
@@ -62,7 +62,6 @@ static void _ldm_printk (const char *level, const char *function,
printk ("%s%s(): %s\n", level, function, buf);
}
-
/**
* ldm_parse_hexbyte - Convert a ASCII hex number to a byte
* @src: Pointer to at least 2 characters to convert.
@@ -118,7 +117,6 @@ static bool ldm_parse_guid (const u8 *src, u8 *dest)
return true;
}
-
/**
* ldm_parse_privhead - Read the LDM Database PRIVHEAD structure
* @data: Raw database PRIVHEAD structure loaded from the device
@@ -130,46 +128,48 @@ static bool ldm_parse_guid (const u8 *src, u8 *dest)
* Return: 'true' @ph contains the PRIVHEAD data
* 'false' @ph contents are undefined
*/
-static bool ldm_parse_privhead (const u8 *data, struct privhead *ph)
+static bool ldm_parse_privhead(const u8 *data, struct privhead *ph)
{
- BUG_ON (!data || !ph);
+ bool is_vista = false;
- if (MAGIC_PRIVHEAD != BE64 (data)) {
- ldm_error ("Cannot find PRIVHEAD structure. LDM database is"
+ BUG_ON(!data || !ph);
+ if (MAGIC_PRIVHEAD != BE64(data)) {
+ ldm_error("Cannot find PRIVHEAD structure. LDM database is"
" corrupt. Aborting.");
return false;
}
-
- ph->ver_major = BE16 (data + 0x000C);
- ph->ver_minor = BE16 (data + 0x000E);
- ph->logical_disk_start = BE64 (data + 0x011B);
- ph->logical_disk_size = BE64 (data + 0x0123);
- ph->config_start = BE64 (data + 0x012B);
- ph->config_size = BE64 (data + 0x0133);
-
- if ((ph->ver_major != 2) || (ph->ver_minor != 11)) {
- ldm_error ("Expected PRIVHEAD version %d.%d, got %d.%d."
- " Aborting.", 2, 11, ph->ver_major, ph->ver_minor);
+ ph->ver_major = BE16(data + 0x000C);
+ ph->ver_minor = BE16(data + 0x000E);
+ ph->logical_disk_start = BE64(data + 0x011B);
+ ph->logical_disk_size = BE64(data + 0x0123);
+ ph->config_start = BE64(data + 0x012B);
+ ph->config_size = BE64(data + 0x0133);
+ /* Version 2.11 is Win2k/XP and version 2.12 is Vista. */
+ if (ph->ver_major == 2 && ph->ver_minor == 12)
+ is_vista = true;
+ if (!is_vista && (ph->ver_major != 2 || ph->ver_minor != 11)) {
+ ldm_error("Expected PRIVHEAD version 2.11 or 2.12, got %d.%d."
+ " Aborting.", ph->ver_major, ph->ver_minor);
return false;
}
+ ldm_debug("PRIVHEAD version %d.%d (Windows %s).", ph->ver_major,
+ ph->ver_minor, is_vista ? "Vista" : "2000/XP");
if (ph->config_size != LDM_DB_SIZE) { /* 1 MiB in sectors. */
- /* Warn the user and continue, carefully */
- ldm_info ("Database is normally %u bytes, it claims to "
+ /* Warn the user and continue, carefully. */
+ ldm_info("Database is normally %u bytes, it claims to "
"be %llu bytes.", LDM_DB_SIZE,
- (unsigned long long)ph->config_size );
+ (unsigned long long)ph->config_size);
}
- if ((ph->logical_disk_size == 0) ||
- (ph->logical_disk_start + ph->logical_disk_size > ph->config_start)) {
- ldm_error ("PRIVHEAD disk size doesn't match real disk size");
+ if ((ph->logical_disk_size == 0) || (ph->logical_disk_start +
+ ph->logical_disk_size > ph->config_start)) {
+ ldm_error("PRIVHEAD disk size doesn't match real disk size");
return false;
}
-
- if (!ldm_parse_guid (data + 0x0030, ph->disk_id)) {
- ldm_error ("PRIVHEAD contains an invalid GUID.");
+ if (!ldm_parse_guid(data + 0x0030, ph->disk_id)) {
+ ldm_error("PRIVHEAD contains an invalid GUID.");
return false;
}
-
- ldm_debug ("Parsed PRIVHEAD successfully.");
+ ldm_debug("Parsed PRIVHEAD successfully.");
return true;
}
@@ -409,7 +409,7 @@ out:
* Return: 'true' @toc1 contains validated TOCBLOCK info
* 'false' @toc1 contents are undefined
*/
-static bool ldm_validate_tocblocks (struct block_device *bdev,
+static bool ldm_validate_tocblocks(struct block_device *bdev,
unsigned long base, struct ldmdb *ldb)
{
static const int off[4] = { OFF_TOCB1, OFF_TOCB2, OFF_TOCB3, OFF_TOCB4};
@@ -417,54 +417,57 @@ static bool ldm_validate_tocblocks (struct block_device *bdev,
struct privhead *ph;
Sector sect;
u8 *data;
+ int i, nr_tbs;
bool result = false;
- int i;
- BUG_ON (!bdev || !ldb);
-
- ph = &ldb->ph;
+ BUG_ON(!bdev || !ldb);
+ ph = &ldb->ph;
tb[0] = &ldb->toc;
- tb[1] = kmalloc (sizeof (*tb[1]), GFP_KERNEL);
- tb[2] = kmalloc (sizeof (*tb[2]), GFP_KERNEL);
- tb[3] = kmalloc (sizeof (*tb[3]), GFP_KERNEL);
- if (!tb[1] || !tb[2] || !tb[3]) {
- ldm_crit ("Out of memory.");
- goto out;
+ tb[1] = kmalloc(sizeof(*tb[1]) * 3, GFP_KERNEL);
+ if (!tb[1]) {
+ ldm_crit("Out of memory.");
+ goto err;
}
-
- for (i = 0; i < 4; i++) /* Read and parse all four toc's. */
- {
- data = read_dev_sector (bdev, base + off[i], &sect);
+ tb[2] = (struct tocblock*)((u8*)tb[1] + sizeof(*tb[1]));
+ tb[3] = (struct tocblock*)((u8*)tb[2] + sizeof(*tb[2]));
+ /*
+ * Try to read and parse all four TOCBLOCKs.
+ *
+ * Windows Vista LDM v2.12 does not always have all four TOCBLOCKs so
+ * skip any that fail as long as we get at least one valid TOCBLOCK.
+ */
+ for (nr_tbs = i = 0; i < 4; i++) {
+ data = read_dev_sector(bdev, base + off[i], &sect);
if (!data) {
- ldm_crit ("Disk read failed.");
- goto out;
+ ldm_error("Disk read failed for TOCBLOCK %d.", i);
+ continue;
}
- result = ldm_parse_tocblock (data, tb[i]);
- put_dev_sector (sect);
- if (!result)
- goto out; /* Already logged */
+ if (ldm_parse_tocblock(data, tb[nr_tbs]))
+ nr_tbs++;
+ put_dev_sector(sect);
}
-
- /* Range check the toc against a privhead. */
+ if (!nr_tbs) {
+ ldm_crit("Failed to find a valid TOCBLOCK.");
+ goto err;
+ }
+ /* Range check the TOCBLOCK against a privhead. */
if (((tb[0]->bitmap1_start + tb[0]->bitmap1_size) > ph->config_size) ||
- ((tb[0]->bitmap2_start + tb[0]->bitmap2_size) > ph->config_size)) {
- ldm_crit ("The bitmaps are out of range. Giving up.");
- goto out;
+ ((tb[0]->bitmap2_start + tb[0]->bitmap2_size) >
+ ph->config_size)) {
+ ldm_crit("The bitmaps are out of range. Giving up.");
+ goto err;
}
-
- if (!ldm_compare_tocblocks (tb[0], tb[1]) || /* Compare all tocs. */
- !ldm_compare_tocblocks (tb[0], tb[2]) ||
- !ldm_compare_tocblocks (tb[0], tb[3])) {
- ldm_crit ("The TOCBLOCKs don't match.");
- goto out;
+ /* Compare all loaded TOCBLOCKs. */
+ for (i = 1; i < nr_tbs; i++) {
+ if (!ldm_compare_tocblocks(tb[0], tb[i])) {
+ ldm_crit("TOCBLOCKs 0 and %d do not match.", i);
+ goto err;
+ }
}
-
- ldm_debug ("Validated TOCBLOCKs successfully.");
+ ldm_debug("Validated %d TOCBLOCKs successfully.", nr_tbs);
result = true;
-out:
- kfree (tb[1]);
- kfree (tb[2]);
- kfree (tb[3]);
+err:
+ kfree(tb[1]);
return result;
}
@@ -566,7 +569,7 @@ static bool ldm_validate_partition_table (struct block_device *bdev)
p = (struct partition*)(data + 0x01BE);
for (i = 0; i < 4; i++, p++)
- if (SYS_IND (p) == WIN2K_DYNAMIC_PARTITION) {
+ if (SYS_IND (p) == LDM_PARTITION) {
result = true;
break;
}
@@ -975,44 +978,68 @@ static bool ldm_parse_dsk4 (const u8 *buffer, int buflen, struct vblk *vb)
* Return: 'true' @vb contains a Partition VBLK
* 'false' @vb contents are not defined
*/
-static bool ldm_parse_prt3 (const u8 *buffer, int buflen, struct vblk *vb)
+static bool ldm_parse_prt3(const u8 *buffer, int buflen, struct vblk *vb)
{
int r_objid, r_name, r_size, r_parent, r_diskid, r_index, len;
struct vblk_part *part;
- BUG_ON (!buffer || !vb);
-
- r_objid = ldm_relative (buffer, buflen, 0x18, 0);
- r_name = ldm_relative (buffer, buflen, 0x18, r_objid);
- r_size = ldm_relative (buffer, buflen, 0x34, r_name);
- r_parent = ldm_relative (buffer, buflen, 0x34, r_size);
- r_diskid = ldm_relative (buffer, buflen, 0x34, r_parent);
-
+ BUG_ON(!buffer || !vb);
+ r_objid = ldm_relative(buffer, buflen, 0x18, 0);
+ if (r_objid < 0) {
+ ldm_error("r_objid %d < 0", r_objid);
+ return false;
+ }
+ r_name = ldm_relative(buffer, buflen, 0x18, r_objid);
+ if (r_name < 0) {
+ ldm_error("r_name %d < 0", r_name);
+ return false;
+ }
+ r_size = ldm_relative(buffer, buflen, 0x34, r_name);
+ if (r_size < 0) {
+ ldm_error("r_size %d < 0", r_size);
+ return false;
+ }
+ r_parent = ldm_relative(buffer, buflen, 0x34, r_size);
+ if (r_parent < 0) {
+ ldm_error("r_parent %d < 0", r_parent);
+ return false;
+ }
+ r_diskid = ldm_relative(buffer, buflen, 0x34, r_parent);
+ if (r_diskid < 0) {
+ ldm_error("r_diskid %d < 0", r_diskid);
+ return false;
+ }
if (buffer[0x12] & VBLK_FLAG_PART_INDEX) {
- r_index = ldm_relative (buffer, buflen, 0x34, r_diskid);
+ r_index = ldm_relative(buffer, buflen, 0x34, r_diskid);
+ if (r_index < 0) {
+ ldm_error("r_index %d < 0", r_index);
+ return false;
+ }
len = r_index;
} else {
r_index = 0;
len = r_diskid;
}
- if (len < 0)
+ if (len < 0) {
+ ldm_error("len %d < 0", len);
return false;
-
+ }
len += VBLK_SIZE_PRT3;
- if (len != BE32 (buffer + 0x14))
+ if (len > BE32(buffer + 0x14)) {
+ ldm_error("len %d > BE32(buffer + 0x14) %d", len,
+ BE32(buffer + 0x14));
return false;
-
+ }
part = &vb->vblk.part;
- part->start = BE64 (buffer + 0x24 + r_name);
- part->volume_offset = BE64 (buffer + 0x2C + r_name);
- part->size = ldm_get_vnum (buffer + 0x34 + r_name);
- part->parent_id = ldm_get_vnum (buffer + 0x34 + r_size);
- part->disk_id = ldm_get_vnum (buffer + 0x34 + r_parent);
+ part->start = BE64(buffer + 0x24 + r_name);
+ part->volume_offset = BE64(buffer + 0x2C + r_name);
+ part->size = ldm_get_vnum(buffer + 0x34 + r_name);
+ part->parent_id = ldm_get_vnum(buffer + 0x34 + r_size);
+ part->disk_id = ldm_get_vnum(buffer + 0x34 + r_parent);
if (vb->flags & VBLK_FLAG_PART_INDEX)
part->partnum = buffer[0x35 + r_diskid];
else
part->partnum = 0;
-
return true;
}
@@ -1475,4 +1502,3 @@ out:
kfree (ldb);
return result;
}
-
diff --git a/fs/partitions/ldm.h b/fs/partitions/ldm.h
index 6e8d7952b8b..d2e6a304693 100644
--- a/fs/partitions/ldm.h
+++ b/fs/partitions/ldm.h
@@ -2,10 +2,10 @@
* ldm - Part of the Linux-NTFS project.
*
* Copyright (C) 2001,2002 Richard Russon <ldm@flatcap.org>
- * Copyright (C) 2001 Anton Altaparmakov <aia21@cantab.net>
+ * Copyright (c) 2001-2007 Anton Altaparmakov
* Copyright (C) 2001,2002 Jakob Kemi <jakob.kemi@telia.com>
*
- * Documentation is available at http://linux-ntfs.sf.net/ldm
+ * Documentation is available at http://www.linux-ntfs.org/content/view/19/37/
*
* This program is free software; you can redistribute it and/or modify it
* under the terms of the GNU General Public License as published by the Free
@@ -93,7 +93,7 @@ struct parsed_partitions;
#define OFF_VMDB 17 /* List of partitions. */
-#define WIN2K_DYNAMIC_PARTITION 0x42 /* Formerly SFS (Landis). */
+#define LDM_PARTITION 0x42 /* Formerly SFS (Landis). */
#define TOC_BITMAP1 "config" /* Names of the two defined */
#define TOC_BITMAP2 "log" /* bitmaps in the TOCBLOCK. */
diff --git a/fs/partitions/sysv68.c b/fs/partitions/sysv68.c
new file mode 100644
index 00000000000..4eba27b7864
--- /dev/null
+++ b/fs/partitions/sysv68.c
@@ -0,0 +1,92 @@
+/*
+ * fs/partitions/sysv68.c
+ *
+ * Copyright (C) 2007 Philippe De Muyter <phdm@macqel.be>
+ */
+
+#include "check.h"
+#include "sysv68.h"
+
+/*
+ * Volume ID structure: on first 256-bytes sector of disk
+ */
+
+struct volumeid {
+ u8 vid_unused[248];
+ u8 vid_mac[8]; /* ASCII string "MOTOROLA" */
+};
+
+/*
+ * config block: second 256-bytes sector on disk
+ */
+
+struct dkconfig {
+ u8 ios_unused0[128];
+ __be32 ios_slcblk; /* Slice table block number */
+ __be16 ios_slccnt; /* Number of entries in slice table */
+ u8 ios_unused1[122];
+};
+
+/*
+ * combined volumeid and dkconfig block
+ */
+
+struct dkblk0 {
+ struct volumeid dk_vid;
+ struct dkconfig dk_ios;
+};
+
+/*
+ * Slice Table Structure
+ */
+
+struct slice {
+ __be32 nblocks; /* slice size (in blocks) */
+ __be32 blkoff; /* block offset of slice */
+};
+
+
+int sysv68_partition(struct parsed_partitions *state, struct block_device *bdev)
+{
+ int i, slices;
+ int slot = 1;
+ Sector sect;
+ unsigned char *data;
+ struct dkblk0 *b;
+ struct slice *slice;
+
+ data = read_dev_sector(bdev, 0, &sect);
+ if (!data)
+ return -1;
+
+ b = (struct dkblk0 *)data;
+ if (memcmp(b->dk_vid.vid_mac, "MOTOROLA", sizeof(b->dk_vid.vid_mac))) {
+ put_dev_sector(sect);
+ return 0;
+ }
+ slices = be16_to_cpu(b->dk_ios.ios_slccnt);
+ i = be32_to_cpu(b->dk_ios.ios_slcblk);
+ put_dev_sector(sect);
+
+ data = read_dev_sector(bdev, i, &sect);
+ if (!data)
+ return -1;
+
+ slices -= 1; /* last slice is the whole disk */
+ printk("sysV68: %s(s%u)", state->name, slices);
+ slice = (struct slice *)data;
+ for (i = 0; i < slices; i++, slice++) {
+ if (slot == state->limit)
+ break;
+ if (be32_to_cpu(slice->nblocks)) {
+ put_partition(state, slot,
+ be32_to_cpu(slice->blkoff),
+ be32_to_cpu(slice->nblocks));
+ printk("(s%u)", i);
+ }
+ slot++;
+ }
+ printk("\n");
+ put_dev_sector(sect);
+ return 1;
+}
diff --git a/fs/partitions/sysv68.h b/fs/partitions/sysv68.h
new file mode 100644
index 00000000000..fa733f68431
--- /dev/null
+++ b/fs/partitions/sysv68.h
@@ -0,0 +1 @@
+extern int sysv68_partition(struct parsed_partitions *state, struct block_device *bdev);
diff --git a/fs/pipe.c b/fs/pipe.c
index ebafde7d6ab..3a89592bdf5 100644
--- a/fs/pipe.c
+++ b/fs/pipe.c
@@ -841,8 +841,18 @@ static int pipefs_delete_dentry(struct dentry *dentry)
return 0;
}
+/*
+ * pipefs_dname() is called from d_path().
+ */
+static char *pipefs_dname(struct dentry *dentry, char *buffer, int buflen)
+{
+ return dynamic_dname(dentry, buffer, buflen, "pipe:[%lu]",
+ dentry->d_inode->i_ino);
+}
+
static struct dentry_operations pipefs_dentry_operations = {
.d_delete = pipefs_delete_dentry,
+ .d_dname = pipefs_dname,
};
static struct inode * get_pipe_inode(void)
@@ -888,8 +898,7 @@ struct file *create_write_pipe(void)
struct inode *inode;
struct file *f;
struct dentry *dentry;
- char name[32];
- struct qstr this;
+ struct qstr name = { .name = "" };
f = get_empty_filp();
if (!f)
@@ -899,11 +908,8 @@ struct file *create_write_pipe(void)
if (!inode)
goto err_file;
- this.len = sprintf(name, "[%lu]", inode->i_ino);
- this.name = name;
- this.hash = 0;
err = -ENOMEM;
- dentry = d_alloc(pipe_mnt->mnt_sb->s_root, &this);
+ dentry = d_alloc(pipe_mnt->mnt_sb->s_root, &name);
if (!dentry)
goto err_inode;
diff --git a/fs/pnode.c b/fs/pnode.c
index 56aacead836..89940f243fc 100644
--- a/fs/pnode.c
+++ b/fs/pnode.c
@@ -59,7 +59,7 @@ static int do_make_slave(struct vfsmount *mnt)
} else {
struct list_head *p = &mnt->mnt_slave_list;
while (!list_empty(p)) {
- slave_mnt = list_entry(p->next,
+ slave_mnt = list_first_entry(p,
struct vfsmount, mnt_slave);
list_del_init(&slave_mnt->mnt_slave);
slave_mnt->mnt_master = NULL;
diff --git a/fs/proc/array.c b/fs/proc/array.c
index 07c9cdbcdca..74f30e0c038 100644
--- a/fs/proc/array.c
+++ b/fs/proc/array.c
@@ -410,9 +410,9 @@ static int do_task_stat(struct task_struct *task, char * buffer, int whole)
/* convert nsec -> ticks */
start_time = nsec_to_clock_t(start_time);
- res = sprintf(buffer,"%d (%s) %c %d %d %d %d %d %lu %lu \
+ res = sprintf(buffer,"%d (%s) %c %d %d %d %d %d %u %lu \
%lu %lu %lu %lu %lu %ld %ld %ld %ld %d 0 %llu %lu %ld %lu %lu %lu %lu %lu \
-%lu %lu %lu %lu %lu %lu %lu %lu %d %d %lu %lu %llu\n",
+%lu %lu %lu %lu %lu %lu %lu %lu %d %d %u %u %llu\n",
task->pid,
tcomm,
state,
diff --git a/fs/proc/base.c b/fs/proc/base.c
index ec158dd02b3..a5fa1fdafc4 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -61,9 +61,9 @@
#include <linux/namei.h>
#include <linux/mnt_namespace.h>
#include <linux/mm.h>
-#include <linux/smp_lock.h>
#include <linux/rcupdate.h>
#include <linux/kallsyms.h>
+#include <linux/module.h>
#include <linux/mount.h>
#include <linux/security.h>
#include <linux/ptrace.h>
@@ -90,8 +90,8 @@
#define PROC_NUMBUF 13
struct pid_entry {
- int len;
char *name;
+ int len;
mode_t mode;
const struct inode_operations *iop;
const struct file_operations *fop;
@@ -99,8 +99,8 @@ struct pid_entry {
};
#define NOD(NAME, MODE, IOP, FOP, OP) { \
- .len = sizeof(NAME) - 1, \
.name = (NAME), \
+ .len = sizeof(NAME) - 1, \
.mode = MODE, \
.iop = IOP, \
.fop = FOP, \
@@ -123,6 +123,9 @@ struct pid_entry {
NULL, &proc_info_file_operations, \
{ .proc_read = &proc_##OTYPE } )
+int maps_protect;
+EXPORT_SYMBOL(maps_protect);
+
static struct fs_struct *get_fs_struct(struct task_struct *task)
{
struct fs_struct *fs;
@@ -275,17 +278,15 @@ static int proc_pid_auxv(struct task_struct *task, char *buffer)
*/
static int proc_pid_wchan(struct task_struct *task, char *buffer)
{
- char *modname;
- const char *sym_name;
- unsigned long wchan, size, offset;
- char namebuf[KSYM_NAME_LEN+1];
+ unsigned long wchan;
+ char symname[KSYM_NAME_LEN+1];
wchan = get_wchan(task);
- sym_name = kallsyms_lookup(wchan, &size, &offset, &modname, namebuf);
- if (sym_name)
- return sprintf(buffer, "%s", sym_name);
- return sprintf(buffer, "%lu", wchan);
+ if (lookup_symbol_name(wchan, symname) < 0)
+ return sprintf(buffer, "%lu", wchan);
+ else
+ return sprintf(buffer, "%s", symname);
}
#endif /* CONFIG_KALLSYMS */
@@ -310,7 +311,9 @@ static int proc_oom_score(struct task_struct *task, char *buffer)
struct timespec uptime;
do_posix_clock_monotonic_gettime(&uptime);
+ read_lock(&tasklist_lock);
points = badness(task, uptime.tv_sec);
+ read_unlock(&tasklist_lock);
return sprintf(buffer, "%lu\n", points);
}
@@ -344,11 +347,8 @@ static int proc_setattr(struct dentry *dentry, struct iattr *attr)
return -EPERM;
error = inode_change_ok(inode, attr);
- if (!error) {
- error = security_inode_setattr(dentry, attr);
- if (!error)
- error = inode_setattr(inode, attr);
- }
+ if (!error)
+ error = inode_setattr(inode, attr);
return error;
}
@@ -660,7 +660,6 @@ static ssize_t oom_adjust_read(struct file *file, char __user *buf,
char buffer[PROC_NUMBUF];
size_t len;
int oom_adjust;
- loff_t __ppos = *ppos;
if (!task)
return -ESRCH;
@@ -668,14 +667,8 @@ static ssize_t oom_adjust_read(struct file *file, char __user *buf,
put_task_struct(task);
len = snprintf(buffer, sizeof(buffer), "%i\n", oom_adjust);
- if (__ppos >= len)
- return 0;
- if (count > len-__ppos)
- count = len-__ppos;
- if (copy_to_user(buf, buffer + __ppos, count))
- return -EFAULT;
- *ppos = __ppos + count;
- return count;
+
+ return simple_read_from_buffer(buf, count, ppos, buffer, len);
}
static ssize_t oom_adjust_write(struct file *file, const char __user *buf,
@@ -715,6 +708,7 @@ static const struct file_operations proc_oom_adjust_operations = {
.write = oom_adjust_write,
};
+#ifdef CONFIG_MMU
static ssize_t clear_refs_write(struct file *file, const char __user *buf,
size_t count, loff_t *ppos)
{
@@ -748,6 +742,7 @@ static ssize_t clear_refs_write(struct file *file, const char __user *buf,
static struct file_operations proc_clear_refs_operations = {
.write = clear_refs_write,
};
+#endif
#ifdef CONFIG_AUDITSYSCALL
#define TMPBUFLEN 21
@@ -823,7 +818,6 @@ static ssize_t seccomp_read(struct file *file, char __user *buf,
{
struct task_struct *tsk = get_proc_task(file->f_dentry->d_inode);
char __buf[20];
- loff_t __ppos = *ppos;
size_t len;
if (!tsk)
@@ -831,14 +825,8 @@ static ssize_t seccomp_read(struct file *file, char __user *buf,
/* no need to print the trailing zero, so use only len */
len = sprintf(__buf, "%u\n", tsk->seccomp.mode);
put_task_struct(tsk);
- if (__ppos >= len)
- return 0;
- if (count > len - __ppos)
- count = len - __ppos;
- if (copy_to_user(buf, __buf + __ppos, count))
- return -EFAULT;
- *ppos = __ppos + count;
- return count;
+
+ return simple_read_from_buffer(buf, count, ppos, __buf, len);
}
static ssize_t seccomp_write(struct file *file, const char __user *buf,
@@ -897,7 +885,6 @@ static ssize_t proc_fault_inject_read(struct file * file, char __user * buf,
char buffer[PROC_NUMBUF];
size_t len;
int make_it_fail;
- loff_t __ppos = *ppos;
if (!task)
return -ESRCH;
@@ -905,14 +892,8 @@ static ssize_t proc_fault_inject_read(struct file * file, char __user * buf,
put_task_struct(task);
len = snprintf(buffer, sizeof(buffer), "%i\n", make_it_fail);
- if (__ppos >= len)
- return 0;
- if (count > len-__ppos)
- count = len-__ppos;
- if (copy_to_user(buf, buffer + __ppos, count))
- return -EFAULT;
- *ppos = __ppos + count;
- return count;
+
+ return simple_read_from_buffer(buf, count, ppos, buffer, len);
}
static ssize_t proc_fault_inject_write(struct file * file,
@@ -975,7 +956,7 @@ static int do_proc_readlink(struct dentry *dentry, struct vfsmount *mnt,
if (!tmp)
return -ENOMEM;
-
+
inode = dentry->d_inode;
path = d_path(dentry, mnt, tmp, PAGE_SIZE);
len = PTR_ERR(path);
@@ -1155,7 +1136,8 @@ static struct dentry_operations pid_dentry_operations =
/* Lookups */
-typedef struct dentry *instantiate_t(struct inode *, struct dentry *, struct task_struct *, void *);
+typedef struct dentry *instantiate_t(struct inode *, struct dentry *,
+ struct task_struct *, const void *);
/*
* Fill a directory entry.
@@ -1171,7 +1153,7 @@ typedef struct dentry *instantiate_t(struct inode *, struct dentry *, struct tas
*/
static int proc_fill_cache(struct file *filp, void *dirent, filldir_t filldir,
char *name, int len,
- instantiate_t instantiate, struct task_struct *task, void *ptr)
+ instantiate_t instantiate, struct task_struct *task, const void *ptr)
{
struct dentry *child, *dir = filp->f_path.dentry;
struct inode *inode;
@@ -1233,7 +1215,10 @@ out:
return ~0U;
}
-static int proc_fd_link(struct inode *inode, struct dentry **dentry, struct vfsmount **mnt)
+#define PROC_FDINFO_MAX 64
+
+static int proc_fd_info(struct inode *inode, struct dentry **dentry,
+ struct vfsmount **mnt, char *info)
{
struct task_struct *task = get_proc_task(inode);
struct files_struct *files = NULL;
@@ -1252,8 +1237,16 @@ static int proc_fd_link(struct inode *inode, struct dentry **dentry, struct vfsm
spin_lock(&files->file_lock);
file = fcheck_files(files, fd);
if (file) {
- *mnt = mntget(file->f_path.mnt);
- *dentry = dget(file->f_path.dentry);
+ if (mnt)
+ *mnt = mntget(file->f_path.mnt);
+ if (dentry)
+ *dentry = dget(file->f_path.dentry);
+ if (info)
+ snprintf(info, PROC_FDINFO_MAX,
+ "pos:\t%lli\n"
+ "flags:\t0%o\n",
+ (long long) file->f_pos,
+ file->f_flags);
spin_unlock(&files->file_lock);
put_files_struct(files);
return 0;
@@ -1264,6 +1257,12 @@ static int proc_fd_link(struct inode *inode, struct dentry **dentry, struct vfsm
return -ENOENT;
}
+static int proc_fd_link(struct inode *inode, struct dentry **dentry,
+ struct vfsmount **mnt)
+{
+ return proc_fd_info(inode, dentry, mnt, NULL);
+}
+
static int tid_fd_revalidate(struct dentry *dentry, struct nameidata *nd)
{
struct inode *inode = dentry->d_inode;
@@ -1306,9 +1305,9 @@ static struct dentry_operations tid_fd_dentry_operations =
};
static struct dentry *proc_fd_instantiate(struct inode *dir,
- struct dentry *dentry, struct task_struct *task, void *ptr)
+ struct dentry *dentry, struct task_struct *task, const void *ptr)
{
- unsigned fd = *(unsigned *)ptr;
+ unsigned fd = *(const unsigned *)ptr;
struct file *file;
struct files_struct *files;
struct inode *inode;
@@ -1359,7 +1358,9 @@ out_iput:
goto out;
}
-static struct dentry *proc_lookupfd(struct inode * dir, struct dentry * dentry, struct nameidata *nd)
+static struct dentry *proc_lookupfd_common(struct inode *dir,
+ struct dentry *dentry,
+ instantiate_t instantiate)
{
struct task_struct *task = get_proc_task(dir);
unsigned fd = name_to_int(dentry);
@@ -1370,23 +1371,15 @@ static struct dentry *proc_lookupfd(struct inode * dir, struct dentry * dentry,
if (fd == ~0U)
goto out;
- result = proc_fd_instantiate(dir, dentry, task, &fd);
+ result = instantiate(dir, dentry, task, &fd);
out:
put_task_struct(task);
out_no_task:
return result;
}
-static int proc_fd_fill_cache(struct file *filp, void *dirent, filldir_t filldir,
- struct task_struct *task, int fd)
-{
- char name[PROC_NUMBUF];
- int len = snprintf(name, sizeof(name), "%d", fd);
- return proc_fill_cache(filp, dirent, filldir, name, len,
- proc_fd_instantiate, task, &fd);
-}
-
-static int proc_readfd(struct file * filp, void * dirent, filldir_t filldir)
+static int proc_readfd_common(struct file * filp, void * dirent,
+ filldir_t filldir, instantiate_t instantiate)
{
struct dentry *dentry = filp->f_path.dentry;
struct inode *inode = dentry->d_inode;
@@ -1422,12 +1415,17 @@ static int proc_readfd(struct file * filp, void * dirent, filldir_t filldir)
for (fd = filp->f_pos-2;
fd < fdt->max_fds;
fd++, filp->f_pos++) {
+ char name[PROC_NUMBUF];
+ int len;
if (!fcheck_files(files, fd))
continue;
rcu_read_unlock();
- if (proc_fd_fill_cache(filp, dirent, filldir, p, fd) < 0) {
+ len = snprintf(name, sizeof(name), "%d", fd);
+ if (proc_fill_cache(filp, dirent, filldir,
+ name, len, instantiate,
+ p, &fd) < 0) {
rcu_read_lock();
break;
}
@@ -1442,23 +1440,119 @@ out_no_task:
return retval;
}
+static struct dentry *proc_lookupfd(struct inode *dir, struct dentry *dentry,
+ struct nameidata *nd)
+{
+ return proc_lookupfd_common(dir, dentry, proc_fd_instantiate);
+}
+
+static int proc_readfd(struct file *filp, void *dirent, filldir_t filldir)
+{
+ return proc_readfd_common(filp, dirent, filldir, proc_fd_instantiate);
+}
+
+static ssize_t proc_fdinfo_read(struct file *file, char __user *buf,
+ size_t len, loff_t *ppos)
+{
+ char tmp[PROC_FDINFO_MAX];
+ int err = proc_fd_info(file->f_path.dentry->d_inode, NULL, NULL, tmp);
+ if (!err)
+ err = simple_read_from_buffer(buf, len, ppos, tmp, strlen(tmp));
+ return err;
+}
+
+static const struct file_operations proc_fdinfo_file_operations = {
+ .open = nonseekable_open,
+ .read = proc_fdinfo_read,
+};
+
static const struct file_operations proc_fd_operations = {
.read = generic_read_dir,
.readdir = proc_readfd,
};
/*
+ * /proc/pid/fd needs a special permission handler so that a process can still
+ * access /proc/self/fd after it has executed a setuid().
+ */
+static int proc_fd_permission(struct inode *inode, int mask,
+ struct nameidata *nd)
+{
+ int rv;
+
+ rv = generic_permission(inode, mask, NULL);
+ if (rv == 0)
+ return 0;
+ if (task_pid(current) == proc_pid(inode))
+ rv = 0;
+ return rv;
+}
+
+/*
* proc directories can do almost nothing..
*/
static const struct inode_operations proc_fd_inode_operations = {
.lookup = proc_lookupfd,
+ .permission = proc_fd_permission,
+ .setattr = proc_setattr,
+};
+
+static struct dentry *proc_fdinfo_instantiate(struct inode *dir,
+ struct dentry *dentry, struct task_struct *task, const void *ptr)
+{
+ unsigned fd = *(unsigned *)ptr;
+ struct inode *inode;
+ struct proc_inode *ei;
+ struct dentry *error = ERR_PTR(-ENOENT);
+
+ inode = proc_pid_make_inode(dir->i_sb, task);
+ if (!inode)
+ goto out;
+ ei = PROC_I(inode);
+ ei->fd = fd;
+ inode->i_mode = S_IFREG | S_IRUSR;
+ inode->i_fop = &proc_fdinfo_file_operations;
+ dentry->d_op = &tid_fd_dentry_operations;
+ d_add(dentry, inode);
+ /* Close the race of the process dying before we return the dentry */
+ if (tid_fd_revalidate(dentry, NULL))
+ error = NULL;
+
+ out:
+ return error;
+}
+
+static struct dentry *proc_lookupfdinfo(struct inode *dir,
+ struct dentry *dentry,
+ struct nameidata *nd)
+{
+ return proc_lookupfd_common(dir, dentry, proc_fdinfo_instantiate);
+}
+
+static int proc_readfdinfo(struct file *filp, void *dirent, filldir_t filldir)
+{
+ return proc_readfd_common(filp, dirent, filldir,
+ proc_fdinfo_instantiate);
+}
+
+static const struct file_operations proc_fdinfo_operations = {
+ .read = generic_read_dir,
+ .readdir = proc_readfdinfo,
+};
+
+/*
+ * proc directories can do almost nothing..
+ */
+static const struct inode_operations proc_fdinfo_inode_operations = {
+ .lookup = proc_lookupfdinfo,
.setattr = proc_setattr,
};
+
static struct dentry *proc_pident_instantiate(struct inode *dir,
- struct dentry *dentry, struct task_struct *task, void *ptr)
+ struct dentry *dentry, struct task_struct *task, const void *ptr)
{
- struct pid_entry *p = ptr;
+ const struct pid_entry *p = ptr;
struct inode *inode;
struct proc_inode *ei;
struct dentry *error = ERR_PTR(-EINVAL);
@@ -1487,13 +1581,13 @@ out:
static struct dentry *proc_pident_lookup(struct inode *dir,
struct dentry *dentry,
- struct pid_entry *ents,
+ const struct pid_entry *ents,
unsigned int nents)
{
struct inode *inode;
struct dentry *error;
struct task_struct *task = get_proc_task(dir);
- struct pid_entry *p, *last;
+ const struct pid_entry *p, *last;
error = ERR_PTR(-ENOENT);
inode = NULL;
@@ -1522,8 +1616,8 @@ out_no_task:
return error;
}
-static int proc_pident_fill_cache(struct file *filp, void *dirent, filldir_t filldir,
- struct task_struct *task, struct pid_entry *p)
+static int proc_pident_fill_cache(struct file *filp, void *dirent,
+ filldir_t filldir, struct task_struct *task, const struct pid_entry *p)
{
return proc_fill_cache(filp, dirent, filldir, p->name, p->len,
proc_pident_instantiate, task, p);
@@ -1531,14 +1625,14 @@ static int proc_pident_fill_cache(struct file *filp, void *dirent, filldir_t fil
static int proc_pident_readdir(struct file *filp,
void *dirent, filldir_t filldir,
- struct pid_entry *ents, unsigned int nents)
+ const struct pid_entry *ents, unsigned int nents)
{
int i;
int pid;
struct dentry *dentry = filp->f_path.dentry;
struct inode *inode = dentry->d_inode;
struct task_struct *task = get_proc_task(inode);
- struct pid_entry *p, *last;
+ const struct pid_entry *p, *last;
ino_t ino;
int ret;
@@ -1653,7 +1747,7 @@ static const struct file_operations proc_pid_attr_operations = {
.write = proc_pid_attr_write,
};
-static struct pid_entry attr_dir_stuff[] = {
+static const struct pid_entry attr_dir_stuff[] = {
REG("current", S_IRUGO|S_IWUGO, pid_attr),
REG("prev", S_IRUGO, pid_attr),
REG("exec", S_IRUGO|S_IWUGO, pid_attr),
@@ -1719,7 +1813,7 @@ static const struct inode_operations proc_self_inode_operations = {
* that properly belong to the /proc filesystem, as they describe
* describe something that is process related.
*/
-static struct pid_entry proc_base_stuff[] = {
+static const struct pid_entry proc_base_stuff[] = {
NOD("self", S_IFLNK|S_IRWXUGO,
&proc_self_inode_operations, NULL, {}),
};
@@ -1748,9 +1842,9 @@ static struct dentry_operations proc_base_dentry_operations =
};
static struct dentry *proc_base_instantiate(struct inode *dir,
- struct dentry *dentry, struct task_struct *task, void *ptr)
+ struct dentry *dentry, struct task_struct *task, const void *ptr)
{
- struct pid_entry *p = ptr;
+ const struct pid_entry *p = ptr;
struct inode *inode;
struct proc_inode *ei;
struct dentry *error = ERR_PTR(-EINVAL);
@@ -1798,7 +1892,7 @@ static struct dentry *proc_base_lookup(struct inode *dir, struct dentry *dentry)
{
struct dentry *error;
struct task_struct *task = get_proc_task(dir);
- struct pid_entry *p, *last;
+ const struct pid_entry *p, *last;
error = ERR_PTR(-ENOENT);
@@ -1824,8 +1918,8 @@ out_no_task:
return error;
}
-static int proc_base_fill_cache(struct file *filp, void *dirent, filldir_t filldir,
- struct task_struct *task, struct pid_entry *p)
+static int proc_base_fill_cache(struct file *filp, void *dirent,
+ filldir_t filldir, struct task_struct *task, const struct pid_entry *p)
{
return proc_fill_cache(filp, dirent, filldir, p->name, p->len,
proc_base_instantiate, task, p);
@@ -1862,9 +1956,10 @@ static int proc_pid_io_accounting(struct task_struct *task, char *buffer)
static const struct file_operations proc_task_operations;
static const struct inode_operations proc_task_inode_operations;
-static struct pid_entry tgid_base_stuff[] = {
+static const struct pid_entry tgid_base_stuff[] = {
DIR("task", S_IRUGO|S_IXUGO, task),
DIR("fd", S_IRUSR|S_IXUSR, fd),
+ DIR("fdinfo", S_IRUSR|S_IXUSR, fdinfo),
INF("environ", S_IRUSR, pid_environ),
INF("auxv", S_IRUSR, pid_auxv),
INF("status", S_IRUGO, pid_status),
@@ -2005,7 +2100,7 @@ out:
static struct dentry *proc_pid_instantiate(struct inode *dir,
struct dentry * dentry,
- struct task_struct *task, void *ptr)
+ struct task_struct *task, const void *ptr)
{
struct dentry *error = ERR_PTR(-ENOENT);
struct inode *inode;
@@ -2018,7 +2113,7 @@ static struct dentry *proc_pid_instantiate(struct inode *dir,
inode->i_op = &proc_tgid_base_inode_operations;
inode->i_fop = &proc_tgid_base_operations;
inode->i_flags|=S_IMMUTABLE;
- inode->i_nlink = 4;
+ inode->i_nlink = 5;
#ifdef CONFIG_SECURITY
inode->i_nlink += 1;
#endif
@@ -2120,7 +2215,7 @@ int proc_pid_readdir(struct file * filp, void * dirent, filldir_t filldir)
goto out_no_task;
for (; nr < ARRAY_SIZE(proc_base_stuff); filp->f_pos++, nr++) {
- struct pid_entry *p = &proc_base_stuff[nr];
+ const struct pid_entry *p = &proc_base_stuff[nr];
if (proc_base_fill_cache(filp, dirent, filldir, reaper, p) < 0)
goto out;
}
@@ -2146,8 +2241,9 @@ out_no_task:
/*
* Tasks
*/
-static struct pid_entry tid_base_stuff[] = {
+static const struct pid_entry tid_base_stuff[] = {
DIR("fd", S_IRUSR|S_IXUSR, fd),
+ DIR("fdinfo", S_IRUSR|S_IXUSR, fdinfo),
INF("environ", S_IRUSR, pid_environ),
INF("auxv", S_IRUSR, pid_auxv),
INF("status", S_IRUGO, pid_status),
@@ -2216,7 +2312,7 @@ static const struct inode_operations proc_tid_base_inode_operations = {
};
static struct dentry *proc_task_instantiate(struct inode *dir,
- struct dentry *dentry, struct task_struct *task, void *ptr)
+ struct dentry *dentry, struct task_struct *task, const void *ptr)
{
struct dentry *error = ERR_PTR(-ENOENT);
struct inode *inode;
@@ -2228,7 +2324,7 @@ static struct dentry *proc_task_instantiate(struct inode *dir,
inode->i_op = &proc_tid_base_inode_operations;
inode->i_fop = &proc_tid_base_operations;
inode->i_flags|=S_IMMUTABLE;
- inode->i_nlink = 3;
+ inode->i_nlink = 4;
#ifdef CONFIG_SECURITY
inode->i_nlink += 1;
#endif
diff --git a/fs/proc/generic.c b/fs/proc/generic.c
index 775fb21294d..8a40e15f5ec 100644
--- a/fs/proc/generic.c
+++ b/fs/proc/generic.c
@@ -398,6 +398,7 @@ struct dentry *proc_lookup(struct inode * dir, struct dentry *dentry, struct nam
if (!memcmp(dentry->d_name.name, de->name, de->namelen)) {
unsigned int ino = de->low_ino;
+ de_get(de);
spin_unlock(&proc_subdir_lock);
error = -EINVAL;
inode = proc_get_inode(dir->i_sb, ino, de);
@@ -414,6 +415,7 @@ struct dentry *proc_lookup(struct inode * dir, struct dentry *dentry, struct nam
d_add(dentry, inode);
return NULL;
}
+ de_put(de);
return ERR_PTR(error);
}
@@ -476,14 +478,21 @@ int proc_readdir(struct file * filp,
}
do {
+ struct proc_dir_entry *next;
+
/* filldir passes info to user space */
+ de_get(de);
spin_unlock(&proc_subdir_lock);
if (filldir(dirent, de->name, de->namelen, filp->f_pos,
- de->low_ino, de->mode >> 12) < 0)
+ de->low_ino, de->mode >> 12) < 0) {
+ de_put(de);
goto out;
+ }
spin_lock(&proc_subdir_lock);
filp->f_pos++;
- de = de->next;
+ next = de->next;
+ de_put(de);
+ de = next;
} while (de);
spin_unlock(&proc_subdir_lock);
}
diff --git a/fs/proc/inode.c b/fs/proc/inode.c
index 22b1158389a..d5ce65c68d7 100644
--- a/fs/proc/inode.c
+++ b/fs/proc/inode.c
@@ -21,7 +21,7 @@
#include "internal.h"
-static inline struct proc_dir_entry * de_get(struct proc_dir_entry *de)
+struct proc_dir_entry *de_get(struct proc_dir_entry *de)
{
if (de)
atomic_inc(&de->count);
@@ -31,7 +31,7 @@ static inline struct proc_dir_entry * de_get(struct proc_dir_entry *de)
/*
* Decrements the use count and checks for deferred deletion.
*/
-static void de_put(struct proc_dir_entry *de)
+void de_put(struct proc_dir_entry *de)
{
if (de) {
lock_kernel();
@@ -109,8 +109,7 @@ static void init_once(void * foo, struct kmem_cache * cachep, unsigned long flag
{
struct proc_inode *ei = (struct proc_inode *) foo;
- if (flags & SLAB_CTOR_CONSTRUCTOR)
- inode_init_once(&ei->vfs_inode);
+ inode_init_once(&ei->vfs_inode);
}
int __init proc_init_inodecache(void)
@@ -146,13 +145,6 @@ struct inode *proc_get_inode(struct super_block *sb, unsigned int ino,
{
struct inode * inode;
- /*
- * Increment the use count so the dir entry can't disappear.
- */
- de_get(de);
-
- WARN_ON(de && de->deleted);
-
if (de != NULL && !try_module_get(de->owner))
goto out_mod;
@@ -184,7 +176,6 @@ out_ino:
if (de != NULL)
module_put(de->owner);
out_mod:
- de_put(de);
return NULL;
}
@@ -199,6 +190,7 @@ int proc_fill_super(struct super_block *s, void *data, int silent)
s->s_op = &proc_sops;
s->s_time_gran = 1;
+ de_get(&proc_root);
root_inode = proc_get_inode(s, PROC_ROOT_INO, &proc_root);
if (!root_inode)
goto out_no_root;
@@ -212,6 +204,7 @@ int proc_fill_super(struct super_block *s, void *data, int silent)
out_no_root:
printk("proc_read_super: get root inode failed\n");
iput(root_inode);
+ de_put(&proc_root);
return -ENOMEM;
}
MODULE_LICENSE("GPL");
diff --git a/fs/proc/internal.h b/fs/proc/internal.h
index f771889183c..b215c3524fa 100644
--- a/fs/proc/internal.h
+++ b/fs/proc/internal.h
@@ -37,6 +37,8 @@ do { \
extern int nommu_vma_show(struct seq_file *, struct vm_area_struct *);
#endif
+extern int maps_protect;
+
extern void create_seq_entry(char *name, mode_t mode, const struct file_operations *f);
extern int proc_exe_link(struct inode *, struct dentry **, struct vfsmount **);
extern int proc_tid_stat(struct task_struct *, char *);
diff --git a/fs/proc/proc_misc.c b/fs/proc/proc_misc.c
index 75ec6523d29..5fd49e47f83 100644
--- a/fs/proc/proc_misc.c
+++ b/fs/proc/proc_misc.c
@@ -35,7 +35,6 @@
#include <linux/signal.h>
#include <linux/module.h>
#include <linux/init.h>
-#include <linux/smp_lock.h>
#include <linux/seq_file.h>
#include <linux/times.h>
#include <linux/profile.h>
@@ -429,18 +428,11 @@ static int slabstats_open(struct inode *inode, struct file *file)
return ret;
}
-static int slabstats_release(struct inode *inode, struct file *file)
-{
- struct seq_file *m = file->private_data;
- kfree(m->private);
- return seq_release(inode, file);
-}
-
static const struct file_operations proc_slabstats_operations = {
.open = slabstats_open,
.read = seq_read,
.llseek = seq_lseek,
- .release = slabstats_release,
+ .release = seq_release_private,
};
#endif
#endif
diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c
index 20e8cbb3436..680c429bfa2 100644
--- a/fs/proc/proc_sysctl.c
+++ b/fs/proc/proc_sysctl.c
@@ -429,11 +429,8 @@ static int proc_sys_setattr(struct dentry *dentry, struct iattr *attr)
return -EPERM;
error = inode_change_ok(inode, attr);
- if (!error) {
- error = security_inode_setattr(dentry, attr);
- if (!error)
- error = inode_setattr(inode, attr);
- }
+ if (!error)
+ error = inode_setattr(inode, attr);
return error;
}
diff --git a/fs/proc/proc_tty.c b/fs/proc/proc_tty.c
index c1bbfbeb035..b3a473b0a19 100644
--- a/fs/proc/proc_tty.c
+++ b/fs/proc/proc_tty.c
@@ -108,6 +108,8 @@ static void *t_start(struct seq_file *m, loff_t *pos)
{
struct list_head *p;
loff_t l = *pos;
+
+ mutex_lock(&tty_mutex);
list_for_each(p, &tty_drivers)
if (!l--)
return list_entry(p, struct tty_driver, tty_drivers);
@@ -124,6 +126,7 @@ static void *t_next(struct seq_file *m, void *v, loff_t *pos)
static void t_stop(struct seq_file *m, void *v)
{
+ mutex_unlock(&tty_mutex);
}
static struct seq_operations tty_drivers_op = {
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index 4008c060f7e..c24d81a5a04 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -3,6 +3,7 @@
#include <linux/mount.h>
#include <linux/seq_file.h>
#include <linux/highmem.h>
+#include <linux/ptrace.h>
#include <linux/pagemap.h>
#include <linux/mempolicy.h>
@@ -142,6 +143,9 @@ static int show_map_internal(struct seq_file *m, void *v, struct mem_size_stats
dev_t dev = 0;
int len;
+ if (maps_protect && !ptrace_may_attach(task))
+ return -EACCES;
+
if (file) {
struct inode *inode = vma->vm_file->f_path.dentry->d_inode;
dev = inode->i_sb->s_dev;
@@ -512,11 +516,22 @@ const struct file_operations proc_maps_operations = {
#ifdef CONFIG_NUMA
extern int show_numa_map(struct seq_file *m, void *v);
+static int show_numa_map_checked(struct seq_file *m, void *v)
+{
+ struct proc_maps_private *priv = m->private;
+ struct task_struct *task = priv->task;
+
+ if (maps_protect && !ptrace_may_attach(task))
+ return -EACCES;
+
+ return show_numa_map(m, v);
+}
+
static struct seq_operations proc_pid_numa_maps_op = {
.start = m_start,
.next = m_next,
.stop = m_stop,
- .show = show_numa_map
+ .show = show_numa_map_checked
};
static int numa_maps_open(struct inode *inode, struct file *file)
diff --git a/fs/proc/task_nommu.c b/fs/proc/task_nommu.c
index 7cddf6b8635..d8b8c7183c2 100644
--- a/fs/proc/task_nommu.c
+++ b/fs/proc/task_nommu.c
@@ -2,6 +2,7 @@
#include <linux/mm.h>
#include <linux/file.h>
#include <linux/mount.h>
+#include <linux/ptrace.h>
#include <linux/seq_file.h>
#include "internal.h"
@@ -143,6 +144,12 @@ out:
static int show_map(struct seq_file *m, void *_vml)
{
struct vm_list_struct *vml = _vml;
+ struct proc_maps_private *priv = m->private;
+ struct task_struct *task = priv->task;
+
+ if (maps_protect && !ptrace_may_attach(task))
+ return -EACCES;
+
return nommu_vma_show(m, vml->vma);
}
diff --git a/fs/qnx4/inode.c b/fs/qnx4/inode.c
index 75fc8498f2e..8d256eb1181 100644
--- a/fs/qnx4/inode.c
+++ b/fs/qnx4/inode.c
@@ -536,8 +536,7 @@ static void init_once(void *foo, struct kmem_cache * cachep,
{
struct qnx4_inode_info *ei = (struct qnx4_inode_info *) foo;
- if (flags & SLAB_CTOR_CONSTRUCTOR)
- inode_init_once(&ei->vfs_inode);
+ inode_init_once(&ei->vfs_inode);
}
static int init_inodecache(void)
diff --git a/fs/quota.c b/fs/quota.c
index b9dae76a0b6..9f237d6182c 100644
--- a/fs/quota.c
+++ b/fs/quota.c
@@ -11,7 +11,6 @@
#include <asm/current.h>
#include <asm/uaccess.h>
#include <linux/kernel.h>
-#include <linux/smp_lock.h>
#include <linux/security.h>
#include <linux/syscalls.h>
#include <linux/buffer_head.h>
@@ -158,7 +157,6 @@ static int check_quotactl_valid(struct super_block *sb, int type, int cmd, qid_t
static void quota_sync_sb(struct super_block *sb, int type)
{
int cnt;
- struct inode *discard[MAXQUOTAS];
sb->s_qcop->quota_sync(sb, type);
/* This is not very clever (and fast) but currently I don't know about
@@ -168,29 +166,21 @@ static void quota_sync_sb(struct super_block *sb, int type)
sb->s_op->sync_fs(sb, 1);
sync_blockdev(sb->s_bdev);
- /* Now when everything is written we can discard the pagecache so
- * that userspace sees the changes. We need i_mutex and so we could
- * not do it inside dqonoff_mutex. Moreover we need to be carefull
- * about races with quotaoff() (that is the reason why we have own
- * reference to inode). */
+ /*
+ * Now when everything is written we can discard the pagecache so
+ * that userspace sees the changes.
+ */
mutex_lock(&sb_dqopt(sb)->dqonoff_mutex);
for (cnt = 0; cnt < MAXQUOTAS; cnt++) {
- discard[cnt] = NULL;
if (type != -1 && cnt != type)
continue;
if (!sb_has_quota_enabled(sb, cnt))
continue;
- discard[cnt] = igrab(sb_dqopt(sb)->files[cnt]);
+ mutex_lock_nested(&sb_dqopt(sb)->files[cnt]->i_mutex, I_MUTEX_QUOTA);
+ truncate_inode_pages(&sb_dqopt(sb)->files[cnt]->i_data, 0);
+ mutex_unlock(&sb_dqopt(sb)->files[cnt]->i_mutex);
}
mutex_unlock(&sb_dqopt(sb)->dqonoff_mutex);
- for (cnt = 0; cnt < MAXQUOTAS; cnt++) {
- if (discard[cnt]) {
- mutex_lock(&discard[cnt]->i_mutex);
- truncate_inode_pages(&discard[cnt]->i_data, 0);
- mutex_unlock(&discard[cnt]->i_mutex);
- iput(discard[cnt]);
- }
- }
}
void sync_dquots(struct super_block *sb, int type)
diff --git a/fs/ramfs/file-nommu.c b/fs/ramfs/file-nommu.c
index d3fd7c6732d..5d258c40a2f 100644
--- a/fs/ramfs/file-nommu.c
+++ b/fs/ramfs/file-nommu.c
@@ -16,7 +16,6 @@
#include <linux/highmem.h>
#include <linux/init.h>
#include <linux/string.h>
-#include <linux/smp_lock.h>
#include <linux/backing-dev.h>
#include <linux/ramfs.h>
#include <linux/quotaops.h>
@@ -180,7 +179,7 @@ static int ramfs_nommu_resize(struct inode *inode, loff_t newsize, loff_t size)
return ret;
}
- ret = vmtruncate(inode, size);
+ ret = vmtruncate(inode, newsize);
return ret;
}
@@ -196,6 +195,11 @@ static int ramfs_nommu_setattr(struct dentry *dentry, struct iattr *ia)
unsigned int old_ia_valid = ia->ia_valid;
int ret = 0;
+ /* POSIX UID/GID verification for setting inode attributes */
+ ret = inode_change_ok(inode, ia);
+ if (ret)
+ return ret;
+
/* by providing our own setattr() method, we skip this quotaism */
if ((old_ia_valid & ATTR_UID && ia->ia_uid != inode->i_uid) ||
(old_ia_valid & ATTR_GID && ia->ia_gid != inode->i_gid))
diff --git a/fs/ramfs/inode.c b/fs/ramfs/inode.c
index ff1f7639707..d40d22b347b 100644
--- a/fs/ramfs/inode.c
+++ b/fs/ramfs/inode.c
@@ -30,10 +30,9 @@
#include <linux/time.h>
#include <linux/init.h>
#include <linux/string.h>
-#include <linux/smp_lock.h>
#include <linux/backing-dev.h>
#include <linux/ramfs.h>
-
+#include <linux/sched.h>
#include <asm/uaccess.h>
#include "internal.h"
diff --git a/fs/read_write.c b/fs/read_write.c
index 1f8dc373ede..4d03008f015 100644
--- a/fs/read_write.c
+++ b/fs/read_write.c
@@ -37,10 +37,10 @@ loff_t generic_file_llseek(struct file *file, loff_t offset, int origin)
mutex_lock(&inode->i_mutex);
switch (origin) {
- case 2:
+ case SEEK_END:
offset += inode->i_size;
break;
- case 1:
+ case SEEK_CUR:
offset += file->f_pos;
}
retval = -EINVAL;
@@ -63,10 +63,10 @@ loff_t remote_llseek(struct file *file, loff_t offset, int origin)
lock_kernel();
switch (origin) {
- case 2:
+ case SEEK_END:
offset += i_size_read(file->f_path.dentry->d_inode);
break;
- case 1:
+ case SEEK_CUR:
offset += file->f_pos;
}
retval = -EINVAL;
@@ -94,10 +94,10 @@ loff_t default_llseek(struct file *file, loff_t offset, int origin)
lock_kernel();
switch (origin) {
- case 2:
+ case SEEK_END:
offset += i_size_read(file->f_path.dentry->d_inode);
break;
- case 1:
+ case SEEK_CUR:
offset += file->f_pos;
}
retval = -EINVAL;
@@ -139,7 +139,7 @@ asmlinkage off_t sys_lseek(unsigned int fd, off_t offset, unsigned int origin)
goto bad;
retval = -EINVAL;
- if (origin <= 2) {
+ if (origin <= SEEK_MAX) {
loff_t res = vfs_llseek(file, offset, origin);
retval = res;
if (res != (loff_t)retval)
@@ -166,7 +166,7 @@ asmlinkage long sys_llseek(unsigned int fd, unsigned long offset_high,
goto bad;
retval = -EINVAL;
- if (origin > 2)
+ if (origin > SEEK_MAX)
goto out_putf;
offset = vfs_llseek(file, ((loff_t) offset_high << 32) | offset_low,
diff --git a/fs/readdir.c b/fs/readdir.c
index f39f5b31325..efe52e67657 100644
--- a/fs/readdir.c
+++ b/fs/readdir.c
@@ -4,13 +4,13 @@
* Copyright (C) 1995 Linus Torvalds
*/
+#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/time.h>
#include <linux/mm.h>
#include <linux/errno.h>
#include <linux/stat.h>
#include <linux/file.h>
-#include <linux/smp_lock.h>
#include <linux/fs.h>
#include <linux/dirent.h>
#include <linux/security.h>
@@ -52,7 +52,6 @@ EXPORT_SYMBOL(vfs_readdir);
* case (the low-level handlers don't need to care about this).
*/
#define NAME_OFFSET(de) ((int) ((de)->d_name - (char __user *) (de)))
-#define ROUND_UP(x) (((x)+sizeof(long)-1) & ~(sizeof(long)-1))
#ifdef __ARCH_WANT_OLD_READDIR
@@ -147,7 +146,7 @@ static int filldir(void * __buf, const char * name, int namlen, loff_t offset,
struct linux_dirent __user * dirent;
struct getdents_callback * buf = (struct getdents_callback *) __buf;
unsigned long d_ino;
- int reclen = ROUND_UP(NAME_OFFSET(dirent) + namlen + 2);
+ int reclen = ALIGN(NAME_OFFSET(dirent) + namlen + 2, sizeof(long));
buf->error = -EINVAL; /* only used if we fail.. */
if (reclen > buf->count)
@@ -220,8 +219,6 @@ out:
return error;
}
-#define ROUND_UP64(x) (((x)+sizeof(u64)-1) & ~(sizeof(u64)-1))
-
struct getdents_callback64 {
struct linux_dirent64 __user * current_dir;
struct linux_dirent64 __user * previous;
@@ -234,7 +231,7 @@ static int filldir64(void * __buf, const char * name, int namlen, loff_t offset,
{
struct linux_dirent64 __user *dirent;
struct getdents_callback64 * buf = (struct getdents_callback64 *) __buf;
- int reclen = ROUND_UP64(NAME_OFFSET(dirent) + namlen + 1);
+ int reclen = ALIGN(NAME_OFFSET(dirent) + namlen + 1, sizeof(u64));
buf->error = -EINVAL; /* only used if we fail.. */
if (reclen > buf->count)
diff --git a/fs/reiserfs/dir.c b/fs/reiserfs/dir.c
index 96a2f8889da..ffbfc2caaf2 100644
--- a/fs/reiserfs/dir.c
+++ b/fs/reiserfs/dir.c
@@ -7,11 +7,10 @@
#include <linux/fs.h>
#include <linux/reiserfs_fs.h>
#include <linux/stat.h>
-#include <linux/smp_lock.h>
#include <linux/buffer_head.h>
#include <asm/uaccess.h>
-extern struct reiserfs_key MIN_KEY;
+extern const struct reiserfs_key MIN_KEY;
static int reiserfs_readdir(struct file *, void *, filldir_t);
static int reiserfs_dir_fsync(struct file *filp, struct dentry *dentry,
diff --git a/fs/reiserfs/file.c b/fs/reiserfs/file.c
index abfada2f52d..9e451a68580 100644
--- a/fs/reiserfs/file.c
+++ b/fs/reiserfs/file.c
@@ -6,7 +6,6 @@
#include <linux/reiserfs_fs.h>
#include <linux/reiserfs_acl.h>
#include <linux/reiserfs_xattr.h>
-#include <linux/smp_lock.h>
#include <asm/uaccess.h>
#include <linux/pagemap.h>
#include <linux/swap.h>
@@ -1060,20 +1059,12 @@ static int reiserfs_prepare_file_region_for_write(struct inode *inode
maping blocks, since there is none, so we just zero out remaining
parts of first and last pages in write area (if needed) */
if ((pos & ~((loff_t) PAGE_CACHE_SIZE - 1)) > inode->i_size) {
- if (from != 0) { /* First page needs to be partially zeroed */
- char *kaddr = kmap_atomic(prepared_pages[0], KM_USER0);
- memset(kaddr, 0, from);
- kunmap_atomic(kaddr, KM_USER0);
- flush_dcache_page(prepared_pages[0]);
- }
- if (to != PAGE_CACHE_SIZE) { /* Last page needs to be partially zeroed */
- char *kaddr =
- kmap_atomic(prepared_pages[num_pages - 1],
- KM_USER0);
- memset(kaddr + to, 0, PAGE_CACHE_SIZE - to);
- kunmap_atomic(kaddr, KM_USER0);
- flush_dcache_page(prepared_pages[num_pages - 1]);
- }
+ if (from != 0) /* First page needs to be partially zeroed */
+ zero_user_page(prepared_pages[0], 0, from, KM_USER0);
+
+ if (to != PAGE_CACHE_SIZE) /* Last page needs to be partially zeroed */
+ zero_user_page(prepared_pages[num_pages-1], to,
+ PAGE_CACHE_SIZE - to, KM_USER0);
/* Since all blocks are new - use already calculated value */
return blocks;
@@ -1200,13 +1191,9 @@ static int reiserfs_prepare_file_region_for_write(struct inode *inode
ll_rw_block(READ, 1, &bh);
*wait_bh++ = bh;
} else { /* Not mapped, zero it */
- char *kaddr =
- kmap_atomic(prepared_pages[0],
- KM_USER0);
- memset(kaddr + block_start, 0,
- from - block_start);
- kunmap_atomic(kaddr, KM_USER0);
- flush_dcache_page(prepared_pages[0]);
+ zero_user_page(prepared_pages[0],
+ block_start,
+ from - block_start, KM_USER0);
set_buffer_uptodate(bh);
}
}
@@ -1238,13 +1225,8 @@ static int reiserfs_prepare_file_region_for_write(struct inode *inode
ll_rw_block(READ, 1, &bh);
*wait_bh++ = bh;
} else { /* Not mapped, zero it */
- char *kaddr =
- kmap_atomic(prepared_pages
- [num_pages - 1],
- KM_USER0);
- memset(kaddr + to, 0, block_end - to);
- kunmap_atomic(kaddr, KM_USER0);
- flush_dcache_page(prepared_pages[num_pages - 1]);
+ zero_user_page(prepared_pages[num_pages-1],
+ to, block_end - to, KM_USER0);
set_buffer_uptodate(bh);
}
}
diff --git a/fs/reiserfs/inode.c b/fs/reiserfs/inode.c
index 9fcbfe31697..1272d11399f 100644
--- a/fs/reiserfs/inode.c
+++ b/fs/reiserfs/inode.c
@@ -2148,13 +2148,8 @@ int reiserfs_truncate_file(struct inode *p_s_inode, int update_timestamps)
length = offset & (blocksize - 1);
/* if we are not on a block boundary */
if (length) {
- char *kaddr;
-
length = blocksize - length;
- kaddr = kmap_atomic(page, KM_USER0);
- memset(kaddr + offset, 0, length);
- flush_dcache_page(page);
- kunmap_atomic(kaddr, KM_USER0);
+ zero_user_page(page, offset, length, KM_USER0);
if (buffer_mapped(bh) && bh->b_blocknr != 0) {
mark_buffer_dirty(bh);
}
@@ -2370,7 +2365,6 @@ static int reiserfs_write_full_page(struct page *page,
** last byte in the file
*/
if (page->index >= end_index) {
- char *kaddr;
unsigned last_offset;
last_offset = inode->i_size & (PAGE_CACHE_SIZE - 1);
@@ -2379,10 +2373,7 @@ static int reiserfs_write_full_page(struct page *page,
unlock_page(page);
return 0;
}
- kaddr = kmap_atomic(page, KM_USER0);
- memset(kaddr + last_offset, 0, PAGE_CACHE_SIZE - last_offset);
- flush_dcache_page(page);
- kunmap_atomic(kaddr, KM_USER0);
+ zero_user_page(page, last_offset, PAGE_CACHE_SIZE - last_offset, KM_USER0);
}
bh = head;
block = page->index << (PAGE_CACHE_SHIFT - s->s_blocksize_bits);
diff --git a/fs/reiserfs/journal.c b/fs/reiserfs/journal.c
index 7280a23ef34..f25086aeef5 100644
--- a/fs/reiserfs/journal.c
+++ b/fs/reiserfs/journal.c
@@ -1110,7 +1110,7 @@ static int flush_commit_list(struct super_block *s,
if (!barrier) {
/* If there was a write error in the journal - we can't commit
* this transaction - it will be invalid and, if successful,
- * will just end up propogating the write error out to
+ * will just end up propagating the write error out to
* the file system. */
if (likely(!retval && !reiserfs_is_journal_aborted (journal))) {
if (buffer_dirty(jl->j_commit_bh))
@@ -1125,7 +1125,7 @@ static int flush_commit_list(struct super_block *s,
/* If there was a write error in the journal - we can't commit this
* transaction - it will be invalid and, if successful, will just end
- * up propogating the write error out to the filesystem. */
+ * up propagating the write error out to the filesystem. */
if (unlikely(!buffer_uptodate(jl->j_commit_bh))) {
#ifdef CONFIG_REISERFS_CHECK
reiserfs_warning(s, "journal-615: buffer write failed");
@@ -2918,7 +2918,7 @@ static void queue_log_writer(struct super_block *s)
set_current_state(TASK_UNINTERRUPTIBLE);
if (test_bit(J_WRITERS_QUEUED, &journal->j_state))
schedule();
- current->state = TASK_RUNNING;
+ __set_current_state(TASK_RUNNING);
remove_wait_queue(&journal->j_join_wait, &wait);
}
diff --git a/fs/reiserfs/namei.c b/fs/reiserfs/namei.c
index a2161840bc7..b378eea332c 100644
--- a/fs/reiserfs/namei.c
+++ b/fs/reiserfs/namei.c
@@ -16,7 +16,6 @@
#include <linux/reiserfs_fs.h>
#include <linux/reiserfs_acl.h>
#include <linux/reiserfs_xattr.h>
-#include <linux/smp_lock.h>
#include <linux/quotaops.h>
#define INC_DIR_INODE_NLINK(i) if (i->i_nlink != 1) { inc_nlink(i); if (i->i_nlink >= REISERFS_LINK_MAX) i->i_nlink=1; }
diff --git a/fs/reiserfs/procfs.c b/fs/reiserfs/procfs.c
index ecc9943202f..9aa7a06e093 100644
--- a/fs/reiserfs/procfs.c
+++ b/fs/reiserfs/procfs.c
@@ -16,11 +16,10 @@
#include <asm/uaccess.h>
#include <linux/reiserfs_fs.h>
#include <linux/reiserfs_fs_sb.h>
-#include <linux/smp_lock.h>
#include <linux/init.h>
#include <linux/proc_fs.h>
-#if defined( REISERFS_PROC_INFO )
+#ifdef CONFIG_REISERFS_PROC_INFO
/*
* LOCKING:
diff --git a/fs/reiserfs/resize.c b/fs/reiserfs/resize.c
index 315684793d1..976cc7887a0 100644
--- a/fs/reiserfs/resize.c
+++ b/fs/reiserfs/resize.c
@@ -131,6 +131,10 @@ int reiserfs_resize(struct super_block *s, unsigned long block_count_new)
/* don't use read_bitmap_block since it will cache
* the uninitialized bitmap */
bh = sb_bread(s, i * s->s_blocksize * 8);
+ if (!bh) {
+ vfree(bitmap);
+ return -EIO;
+ }
memset(bh->b_data, 0, sb_blocksize(sb));
reiserfs_test_and_set_le_bit(0, bh->b_data);
reiserfs_cache_bitmap_metadata(s, bh, bitmap + i);
diff --git a/fs/reiserfs/stree.c b/fs/reiserfs/stree.c
index afb21ea4530..b6f12593c39 100644
--- a/fs/reiserfs/stree.c
+++ b/fs/reiserfs/stree.c
@@ -53,7 +53,6 @@
#include <linux/string.h>
#include <linux/pagemap.h>
#include <linux/reiserfs_fs.h>
-#include <linux/smp_lock.h>
#include <linux/buffer_head.h>
#include <linux/quotaops.h>
diff --git a/fs/reiserfs/super.c b/fs/reiserfs/super.c
index 7054aaef049..b4ac9119200 100644
--- a/fs/reiserfs/super.c
+++ b/fs/reiserfs/super.c
@@ -18,7 +18,6 @@
#include <linux/reiserfs_fs.h>
#include <linux/reiserfs_acl.h>
#include <linux/reiserfs_xattr.h>
-#include <linux/smp_lock.h>
#include <linux/init.h>
#include <linux/blkdev.h>
#include <linux/buffer_head.h>
@@ -433,12 +432,13 @@ int remove_save_link(struct inode *inode, int truncate)
static void reiserfs_kill_sb(struct super_block *s)
{
if (REISERFS_SB(s)) {
+#ifdef CONFIG_REISERFS_FS_XATTR
if (REISERFS_SB(s)->xattr_root) {
d_invalidate(REISERFS_SB(s)->xattr_root);
dput(REISERFS_SB(s)->xattr_root);
REISERFS_SB(s)->xattr_root = NULL;
}
-
+#endif
if (REISERFS_SB(s)->priv_root) {
d_invalidate(REISERFS_SB(s)->priv_root);
dput(REISERFS_SB(s)->priv_root);
@@ -511,14 +511,12 @@ static void init_once(void *foo, struct kmem_cache * cachep, unsigned long flags
{
struct reiserfs_inode_info *ei = (struct reiserfs_inode_info *)foo;
- if (flags & SLAB_CTOR_CONSTRUCTOR) {
- INIT_LIST_HEAD(&ei->i_prealloc_list);
- inode_init_once(&ei->vfs_inode);
+ INIT_LIST_HEAD(&ei->i_prealloc_list);
+ inode_init_once(&ei->vfs_inode);
#ifdef CONFIG_REISERFS_FS_POSIX_ACL
- ei->i_acl_access = NULL;
- ei->i_acl_default = NULL;
+ ei->i_acl_access = NULL;
+ ei->i_acl_default = NULL;
#endif
- }
}
static int init_inodecache(void)
@@ -1562,9 +1560,10 @@ static int reiserfs_fill_super(struct super_block *s, void *data, int silent)
REISERFS_SB(s)->s_alloc_options.preallocmin = 0;
/* Preallocate by 16 blocks (17-1) at once */
REISERFS_SB(s)->s_alloc_options.preallocsize = 17;
+#ifdef CONFIG_REISERFS_FS_XATTR
/* Initialize the rwsem for xattr dir */
init_rwsem(&REISERFS_SB(s)->xattr_dir_sem);
-
+#endif
/* setup default block allocator options */
reiserfs_init_alloc_options(s);
diff --git a/fs/romfs/inode.c b/fs/romfs/inode.c
index 80428519027..2284e03342c 100644
--- a/fs/romfs/inode.c
+++ b/fs/romfs/inode.c
@@ -566,12 +566,11 @@ static void romfs_destroy_inode(struct inode *inode)
kmem_cache_free(romfs_inode_cachep, ROMFS_I(inode));
}
-static void init_once(void * foo, struct kmem_cache * cachep, unsigned long flags)
+static void init_once(void *foo, struct kmem_cache *cachep, unsigned long flags)
{
- struct romfs_inode_info *ei = (struct romfs_inode_info *) foo;
+ struct romfs_inode_info *ei = foo;
- if (flags & SLAB_CTOR_CONSTRUCTOR)
- inode_init_once(&ei->vfs_inode);
+ inode_init_once(&ei->vfs_inode);
}
static int init_inodecache(void)
diff --git a/fs/select.c b/fs/select.c
index fe0893afd93..a974082b082 100644
--- a/fs/select.c
+++ b/fs/select.c
@@ -14,10 +14,10 @@
* of fds to overcome nfds < 16390 descriptors limit (Tigran Aivazian).
*/
+#include <linux/kernel.h>
#include <linux/syscalls.h>
#include <linux/module.h>
#include <linux/slab.h>
-#include <linux/smp_lock.h>
#include <linux/poll.h>
#include <linux/personality.h> /* for STICKY_TIMEOUTS */
#include <linux/file.h>
@@ -26,7 +26,6 @@
#include <asm/uaccess.h>
-#define ROUND_UP(x,y) (((x)+(y)-1)/(y))
#define DEFAULT_POLLMASK (POLLIN | POLLOUT | POLLRDNORM | POLLWRNORM)
struct poll_table_page {
@@ -65,7 +64,7 @@ EXPORT_SYMBOL(poll_initwait);
static void free_poll_entry(struct poll_table_entry *entry)
{
- remove_wait_queue(entry->wait_address,&entry->wait);
+ remove_wait_queue(entry->wait_address, &entry->wait);
fput(entry->filp);
}
@@ -129,7 +128,7 @@ static void __pollwait(struct file *filp, wait_queue_head_t *wait_address,
entry->filp = filp;
entry->wait_address = wait_address;
init_waitqueue_entry(&entry->wait, current);
- add_wait_queue(wait_address,&entry->wait);
+ add_wait_queue(wait_address, &entry->wait);
}
#define FDS_IN(fds, n) (fds->in + n)
@@ -399,7 +398,7 @@ asmlinkage long sys_select(int n, fd_set __user *inp, fd_set __user *outp,
if ((u64)tv.tv_sec >= (u64)MAX_INT64_SECONDS)
timeout = -1; /* infinite */
else {
- timeout = ROUND_UP(tv.tv_usec, USEC_PER_SEC/HZ);
+ timeout = DIV_ROUND_UP(tv.tv_usec, USEC_PER_SEC/HZ);
timeout += tv.tv_sec * HZ;
}
}
@@ -454,7 +453,7 @@ asmlinkage long sys_pselect7(int n, fd_set __user *inp, fd_set __user *outp,
if ((u64)ts.tv_sec >= (u64)MAX_INT64_SECONDS)
timeout = -1; /* infinite */
else {
- timeout = ROUND_UP(ts.tv_nsec, NSEC_PER_SEC/HZ);
+ timeout = DIV_ROUND_UP(ts.tv_nsec, NSEC_PER_SEC/HZ);
timeout += ts.tv_sec * HZ;
}
}
@@ -776,7 +775,7 @@ asmlinkage long sys_ppoll(struct pollfd __user *ufds, unsigned int nfds,
if ((u64)ts.tv_sec >= (u64)MAX_INT64_SECONDS)
timeout = -1; /* infinite */
else {
- timeout = ROUND_UP(ts.tv_nsec, NSEC_PER_SEC/HZ);
+ timeout = DIV_ROUND_UP(ts.tv_nsec, NSEC_PER_SEC/HZ);
timeout += ts.tv_sec * HZ;
}
}
diff --git a/fs/signalfd.c b/fs/signalfd.c
new file mode 100644
index 00000000000..3b07f26d984
--- /dev/null
+++ b/fs/signalfd.c
@@ -0,0 +1,380 @@
+/*
+ * fs/signalfd.c
+ *
+ * Copyright (C) 2003 Linus Torvalds
+ *
+ * Mon Mar 5, 2007: Davide Libenzi <davidel@xmailserver.org>
+ * Changed ->read() to return a siginfo strcture instead of signal number.
+ * Fixed locking in ->poll().
+ * Added sighand-detach notification.
+ * Added fd re-use in sys_signalfd() syscall.
+ * Now using anonymous inode source.
+ * Thanks to Oleg Nesterov for useful code review and suggestions.
+ * More comments and suggestions from Arnd Bergmann.
+ * Sat May 19, 2007: Davi E. M. Arnaut <davi@haxent.com.br>
+ * Retrieve multiple signals with one read() call
+ */
+
+#include <linux/file.h>
+#include <linux/poll.h>
+#include <linux/init.h>
+#include <linux/fs.h>
+#include <linux/sched.h>
+#include <linux/kernel.h>
+#include <linux/signal.h>
+#include <linux/list.h>
+#include <linux/anon_inodes.h>
+#include <linux/signalfd.h>
+
+struct signalfd_ctx {
+ struct list_head lnk;
+ wait_queue_head_t wqh;
+ sigset_t sigmask;
+ struct task_struct *tsk;
+};
+
+struct signalfd_lockctx {
+ struct task_struct *tsk;
+ unsigned long flags;
+};
+
+/*
+ * Tries to acquire the sighand lock. We do not increment the sighand
+ * use count, and we do not even pin the task struct, so we need to
+ * do it inside an RCU read lock, and we must be prepared for the
+ * ctx->tsk going to NULL (in signalfd_deliver()), and for the sighand
+ * being detached. We return 0 if the sighand has been detached, or
+ * 1 if we were able to pin the sighand lock.
+ */
+static int signalfd_lock(struct signalfd_ctx *ctx, struct signalfd_lockctx *lk)
+{
+ struct sighand_struct *sighand = NULL;
+
+ rcu_read_lock();
+ lk->tsk = rcu_dereference(ctx->tsk);
+ if (likely(lk->tsk != NULL))
+ sighand = lock_task_sighand(lk->tsk, &lk->flags);
+ rcu_read_unlock();
+
+ if (sighand && !ctx->tsk) {
+ unlock_task_sighand(lk->tsk, &lk->flags);
+ sighand = NULL;
+ }
+
+ return sighand != NULL;
+}
+
+static void signalfd_unlock(struct signalfd_lockctx *lk)
+{
+ unlock_task_sighand(lk->tsk, &lk->flags);
+}
+
+/*
+ * This must be called with the sighand lock held.
+ */
+void signalfd_deliver(struct task_struct *tsk, int sig)
+{
+ struct sighand_struct *sighand = tsk->sighand;
+ struct signalfd_ctx *ctx, *tmp;
+
+ BUG_ON(!sig);
+ list_for_each_entry_safe(ctx, tmp, &sighand->signalfd_list, lnk) {
+ /*
+ * We use a negative signal value as a way to broadcast that the
+ * sighand has been orphaned, so that we can notify all the
+ * listeners about this. Remember the ctx->sigmask is inverted,
+ * so if the user is interested in a signal, that corresponding
+ * bit will be zero.
+ */
+ if (sig < 0) {
+ if (ctx->tsk == tsk) {
+ ctx->tsk = NULL;
+ list_del_init(&ctx->lnk);
+ wake_up(&ctx->wqh);
+ }
+ } else {
+ if (!sigismember(&ctx->sigmask, sig))
+ wake_up(&ctx->wqh);
+ }
+ }
+}
+
+static void signalfd_cleanup(struct signalfd_ctx *ctx)
+{
+ struct signalfd_lockctx lk;
+
+ /*
+ * This is tricky. If the sighand is gone, we do not need to remove
+ * context from the list, the list itself won't be there anymore.
+ */
+ if (signalfd_lock(ctx, &lk)) {
+ list_del(&ctx->lnk);
+ signalfd_unlock(&lk);
+ }
+ kfree(ctx);
+}
+
+static int signalfd_release(struct inode *inode, struct file *file)
+{
+ signalfd_cleanup(file->private_data);
+ return 0;
+}
+
+static unsigned int signalfd_poll(struct file *file, poll_table *wait)
+{
+ struct signalfd_ctx *ctx = file->private_data;
+ unsigned int events = 0;
+ struct signalfd_lockctx lk;
+
+ poll_wait(file, &ctx->wqh, wait);
+
+ /*
+ * Let the caller get a POLLIN in this case, ala socket recv() when
+ * the peer disconnects.
+ */
+ if (signalfd_lock(ctx, &lk)) {
+ if ((lk.tsk == current &&
+ next_signal(&lk.tsk->pending, &ctx->sigmask) > 0) ||
+ next_signal(&lk.tsk->signal->shared_pending,
+ &ctx->sigmask) > 0)
+ events |= POLLIN;
+ signalfd_unlock(&lk);
+ } else
+ events |= POLLIN;
+
+ return events;
+}
+
+/*
+ * Copied from copy_siginfo_to_user() in kernel/signal.c
+ */
+static int signalfd_copyinfo(struct signalfd_siginfo __user *uinfo,
+ siginfo_t const *kinfo)
+{
+ long err;
+
+ BUILD_BUG_ON(sizeof(struct signalfd_siginfo) != 128);
+
+ /*
+ * Unused memebers should be zero ...
+ */
+ err = __clear_user(uinfo, sizeof(*uinfo));
+
+ /*
+ * If you change siginfo_t structure, please be sure
+ * this code is fixed accordingly.
+ */
+ err |= __put_user(kinfo->si_signo, &uinfo->signo);
+ err |= __put_user(kinfo->si_errno, &uinfo->err);
+ err |= __put_user((short)kinfo->si_code, &uinfo->code);
+ switch (kinfo->si_code & __SI_MASK) {
+ case __SI_KILL:
+ err |= __put_user(kinfo->si_pid, &uinfo->pid);
+ err |= __put_user(kinfo->si_uid, &uinfo->uid);
+ break;
+ case __SI_TIMER:
+ err |= __put_user(kinfo->si_tid, &uinfo->tid);
+ err |= __put_user(kinfo->si_overrun, &uinfo->overrun);
+ err |= __put_user((long)kinfo->si_ptr, &uinfo->svptr);
+ break;
+ case __SI_POLL:
+ err |= __put_user(kinfo->si_band, &uinfo->band);
+ err |= __put_user(kinfo->si_fd, &uinfo->fd);
+ break;
+ case __SI_FAULT:
+ err |= __put_user((long)kinfo->si_addr, &uinfo->addr);
+#ifdef __ARCH_SI_TRAPNO
+ err |= __put_user(kinfo->si_trapno, &uinfo->trapno);
+#endif
+ break;
+ case __SI_CHLD:
+ err |= __put_user(kinfo->si_pid, &uinfo->pid);
+ err |= __put_user(kinfo->si_uid, &uinfo->uid);
+ err |= __put_user(kinfo->si_status, &uinfo->status);
+ err |= __put_user(kinfo->si_utime, &uinfo->utime);
+ err |= __put_user(kinfo->si_stime, &uinfo->stime);
+ break;
+ case __SI_RT: /* This is not generated by the kernel as of now. */
+ case __SI_MESGQ: /* But this is */
+ err |= __put_user(kinfo->si_pid, &uinfo->pid);
+ err |= __put_user(kinfo->si_uid, &uinfo->uid);
+ err |= __put_user((long)kinfo->si_ptr, &uinfo->svptr);
+ break;
+ default: /* this is just in case for now ... */
+ err |= __put_user(kinfo->si_pid, &uinfo->pid);
+ err |= __put_user(kinfo->si_uid, &uinfo->uid);
+ break;
+ }
+
+ return err ? -EFAULT: sizeof(*uinfo);
+}
+
+static ssize_t signalfd_dequeue(struct signalfd_ctx *ctx, siginfo_t *info,
+ int nonblock)
+{
+ ssize_t ret;
+ struct signalfd_lockctx lk;
+ DECLARE_WAITQUEUE(wait, current);
+
+ if (!signalfd_lock(ctx, &lk))
+ return 0;
+
+ ret = dequeue_signal(lk.tsk, &ctx->sigmask, info);
+ switch (ret) {
+ case 0:
+ if (!nonblock)
+ break;
+ ret = -EAGAIN;
+ default:
+ signalfd_unlock(&lk);
+ return ret;
+ }
+
+ add_wait_queue(&ctx->wqh, &wait);
+ for (;;) {
+ set_current_state(TASK_INTERRUPTIBLE);
+ ret = dequeue_signal(lk.tsk, &ctx->sigmask, info);
+ signalfd_unlock(&lk);
+ if (ret != 0)
+ break;
+ if (signal_pending(current)) {
+ ret = -ERESTARTSYS;
+ break;
+ }
+ schedule();
+ ret = signalfd_lock(ctx, &lk);
+ if (unlikely(!ret)) {
+ /*
+ * Let the caller read zero byte, ala socket
+ * recv() when the peer disconnect. This test
+ * must be done before doing a dequeue_signal(),
+ * because if the sighand has been orphaned,
+ * the dequeue_signal() call is going to crash
+ * because ->sighand will be long gone.
+ */
+ break;
+ }
+ }
+
+ remove_wait_queue(&ctx->wqh, &wait);
+ __set_current_state(TASK_RUNNING);
+
+ return ret;
+}
+
+/*
+ * Returns either the size of a "struct signalfd_siginfo", or zero if the
+ * sighand we are attached to, has been orphaned. The "count" parameter
+ * must be at least the size of a "struct signalfd_siginfo".
+ */
+static ssize_t signalfd_read(struct file *file, char __user *buf, size_t count,
+ loff_t *ppos)
+{
+ struct signalfd_ctx *ctx = file->private_data;
+ struct signalfd_siginfo __user *siginfo;
+ int nonblock = file->f_flags & O_NONBLOCK;
+ ssize_t ret, total = 0;
+ siginfo_t info;
+
+ count /= sizeof(struct signalfd_siginfo);
+ if (!count)
+ return -EINVAL;
+
+ siginfo = (struct signalfd_siginfo __user *) buf;
+
+ do {
+ ret = signalfd_dequeue(ctx, &info, nonblock);
+ if (unlikely(ret <= 0))
+ break;
+ ret = signalfd_copyinfo(siginfo, &info);
+ if (ret < 0)
+ break;
+ siginfo++;
+ total += ret;
+ nonblock = 1;
+ } while (--count);
+
+ return total ? total : ret;
+}
+
+static const struct file_operations signalfd_fops = {
+ .release = signalfd_release,
+ .poll = signalfd_poll,
+ .read = signalfd_read,
+};
+
+/*
+ * Create a file descriptor that is associated with our signal
+ * state. We can pass it around to others if we want to, but
+ * it will always be _our_ signal state.
+ */
+asmlinkage long sys_signalfd(int ufd, sigset_t __user *user_mask, size_t sizemask)
+{
+ int error;
+ sigset_t sigmask;
+ struct signalfd_ctx *ctx;
+ struct sighand_struct *sighand;
+ struct file *file;
+ struct inode *inode;
+ struct signalfd_lockctx lk;
+
+ if (sizemask != sizeof(sigset_t) ||
+ copy_from_user(&sigmask, user_mask, sizeof(sigmask)))
+ return error = -EINVAL;
+ sigdelsetmask(&sigmask, sigmask(SIGKILL) | sigmask(SIGSTOP));
+ signotset(&sigmask);
+
+ if (ufd == -1) {
+ ctx = kmalloc(sizeof(*ctx), GFP_KERNEL);
+ if (!ctx)
+ return -ENOMEM;
+
+ init_waitqueue_head(&ctx->wqh);
+ ctx->sigmask = sigmask;
+ ctx->tsk = current;
+
+ sighand = current->sighand;
+ /*
+ * Add this fd to the list of signal listeners.
+ */
+ spin_lock_irq(&sighand->siglock);
+ list_add_tail(&ctx->lnk, &sighand->signalfd_list);
+ spin_unlock_irq(&sighand->siglock);
+
+ /*
+ * When we call this, the initialization must be complete, since
+ * anon_inode_getfd() will install the fd.
+ */
+ error = anon_inode_getfd(&ufd, &inode, &file, "[signalfd]",
+ &signalfd_fops, ctx);
+ if (error)
+ goto err_fdalloc;
+ } else {
+ file = fget(ufd);
+ if (!file)
+ return -EBADF;
+ ctx = file->private_data;
+ if (file->f_op != &signalfd_fops) {
+ fput(file);
+ return -EINVAL;
+ }
+ /*
+ * We need to be prepared of the fact that the sighand this fd
+ * is attached to, has been detched. In that case signalfd_lock()
+ * will return 0, and we'll just skip setting the new mask.
+ */
+ if (signalfd_lock(ctx, &lk)) {
+ ctx->sigmask = sigmask;
+ signalfd_unlock(&lk);
+ }
+ wake_up(&ctx->wqh);
+ fput(file);
+ }
+
+ return ufd;
+
+err_fdalloc:
+ signalfd_cleanup(ctx);
+ return error;
+}
+
diff --git a/fs/smbfs/dir.c b/fs/smbfs/dir.c
index 50136b1a3ec..48da4fa6b7d 100644
--- a/fs/smbfs/dir.c
+++ b/fs/smbfs/dir.c
@@ -13,6 +13,7 @@
#include <linux/smp_lock.h>
#include <linux/ctype.h>
#include <linux/net.h>
+#include <linux/sched.h>
#include <linux/smb_fs.h>
#include <linux/smb_mount.h>
diff --git a/fs/smbfs/file.c b/fs/smbfs/file.c
index f161797160c..aea3f8aa54c 100644
--- a/fs/smbfs/file.c
+++ b/fs/smbfs/file.c
@@ -17,6 +17,7 @@
#include <linux/pagemap.h>
#include <linux/smp_lock.h>
#include <linux/net.h>
+#include <linux/aio.h>
#include <asm/uaccess.h>
#include <asm/system.h>
diff --git a/fs/smbfs/inode.c b/fs/smbfs/inode.c
index 424a3ddf86d..6724a6cf01f 100644
--- a/fs/smbfs/inode.c
+++ b/fs/smbfs/inode.c
@@ -25,6 +25,7 @@
#include <linux/net.h>
#include <linux/vfs.h>
#include <linux/highuid.h>
+#include <linux/sched.h>
#include <linux/smb_fs.h>
#include <linux/smbno.h>
#include <linux/smb_mount.h>
@@ -70,8 +71,7 @@ static void init_once(void * foo, struct kmem_cache * cachep, unsigned long flag
{
struct smb_inode_info *ei = (struct smb_inode_info *) foo;
- if (flags & SLAB_CTOR_CONSTRUCTOR)
- inode_init_once(&ei->vfs_inode);
+ inode_init_once(&ei->vfs_inode);
}
static int init_inodecache(void)
diff --git a/fs/smbfs/request.c b/fs/smbfs/request.c
index 723f7c66766..3f54a0f80fa 100644
--- a/fs/smbfs/request.c
+++ b/fs/smbfs/request.c
@@ -6,10 +6,12 @@
* Please add a note about your changes to smbfs in the ChangeLog file.
*/
+#include <linux/kernel.h>
#include <linux/types.h>
#include <linux/fs.h>
#include <linux/slab.h>
#include <linux/net.h>
+#include <linux/sched.h>
#include <linux/smb_fs.h>
#include <linux/smbno.h>
@@ -22,8 +24,6 @@
/* #define SMB_SLAB_DEBUG (SLAB_RED_ZONE | SLAB_POISON) */
#define SMB_SLAB_DEBUG 0
-#define ROUND_UP(x) (((x)+3) & ~3)
-
/* cache for request structures */
static struct kmem_cache *req_cachep;
@@ -200,8 +200,8 @@ static int smb_setup_trans2request(struct smb_request *req)
const int smb_parameters = 15;
const int header = SMB_HEADER_LEN + 2 * smb_parameters + 2;
- const int oparam = ROUND_UP(header + 3);
- const int odata = ROUND_UP(oparam + req->rq_lparm);
+ const int oparam = ALIGN(header + 3, sizeof(u32));
+ const int odata = ALIGN(oparam + req->rq_lparm, sizeof(u32));
const int bcc = (req->rq_data ? odata + req->rq_ldata :
oparam + req->rq_lparm) - header;
diff --git a/fs/smbfs/smbiod.c b/fs/smbfs/smbiod.c
index 89eaf31f1d4..67176af8515 100644
--- a/fs/smbfs/smbiod.c
+++ b/fs/smbfs/smbiod.c
@@ -16,7 +16,6 @@
#include <linux/init.h>
#include <linux/file.h>
#include <linux/dcache.h>
-#include <linux/smp_lock.h>
#include <linux/module.h>
#include <linux/net.h>
#include <linux/kthread.h>
@@ -299,8 +298,6 @@ out:
*/
static int smbiod(void *unused)
{
- allow_signal(SIGKILL);
-
VERBOSE("SMB Kernel thread starting (%d) ...\n", current->pid);
for (;;) {
diff --git a/fs/smbfs/sock.c b/fs/smbfs/sock.c
index 92ea6b2367d..e48bd8235a8 100644
--- a/fs/smbfs/sock.c
+++ b/fs/smbfs/sock.c
@@ -17,7 +17,6 @@
#include <linux/net.h>
#include <linux/mm.h>
#include <linux/netdevice.h>
-#include <linux/smp_lock.h>
#include <linux/workqueue.h>
#include <net/scm.h>
#include <net/tcp_states.h>
diff --git a/fs/smbfs/symlink.c b/fs/smbfs/symlink.c
index fea20ceb8a5..00b2909bd46 100644
--- a/fs/smbfs/symlink.c
+++ b/fs/smbfs/symlink.c
@@ -13,7 +13,6 @@
#include <linux/mm.h>
#include <linux/slab.h>
#include <linux/pagemap.h>
-#include <linux/smp_lock.h>
#include <linux/net.h>
#include <linux/namei.h>
diff --git a/fs/splice.c b/fs/splice.c
index 5428b0ff3b6..e7d7080de2f 100644
--- a/fs/splice.c
+++ b/fs/splice.c
@@ -176,6 +176,7 @@ static const struct pipe_buf_operations user_page_pipe_buf_ops = {
static ssize_t splice_to_pipe(struct pipe_inode_info *pipe,
struct splice_pipe_desc *spd)
{
+ unsigned int spd_pages = spd->nr_pages;
int ret, do_wakeup, page_nr;
ret = 0;
@@ -244,17 +245,18 @@ static ssize_t splice_to_pipe(struct pipe_inode_info *pipe,
pipe->waiting_writers--;
}
- if (pipe->inode)
+ if (pipe->inode) {
mutex_unlock(&pipe->inode->i_mutex);
- if (do_wakeup) {
- smp_mb();
- if (waitqueue_active(&pipe->wait))
- wake_up_interruptible(&pipe->wait);
- kill_fasync(&pipe->fasync_readers, SIGIO, POLL_IN);
+ if (do_wakeup) {
+ smp_mb();
+ if (waitqueue_active(&pipe->wait))
+ wake_up_interruptible(&pipe->wait);
+ kill_fasync(&pipe->fasync_readers, SIGIO, POLL_IN);
+ }
}
- while (page_nr < spd->nr_pages)
+ while (page_nr < spd_pages)
page_cache_release(spd->pages[page_nr++]);
return ret;
@@ -272,7 +274,6 @@ __generic_file_splice_read(struct file *in, loff_t *ppos,
struct page *page;
pgoff_t index, end_index;
loff_t isize;
- size_t total_len;
int error, page_nr;
struct splice_pipe_desc spd = {
.pages = pages,
@@ -289,18 +290,15 @@ __generic_file_splice_read(struct file *in, loff_t *ppos,
nr_pages = PIPE_BUFFERS;
/*
- * Initiate read-ahead on this page range. however, don't call into
- * read-ahead if this is a non-zero offset (we are likely doing small
- * chunk splice and the page is already there) for a single page.
+ * Don't try to 2nd guess the read-ahead logic, call into
+ * page_cache_readahead() like the page cache reads would do.
*/
- if (!loff || nr_pages > 1)
- page_cache_readahead(mapping, &in->f_ra, in, index, nr_pages);
+ page_cache_readahead(mapping, &in->f_ra, in, index, nr_pages);
/*
* Now fill in the holes:
*/
error = 0;
- total_len = 0;
/*
* Lookup the (hopefully) full range of pages we need.
@@ -378,10 +376,11 @@ __generic_file_splice_read(struct file *in, loff_t *ppos,
* If in nonblock mode then dont block on waiting
* for an in-flight io page
*/
- if (flags & SPLICE_F_NONBLOCK)
- break;
-
- lock_page(page);
+ if (flags & SPLICE_F_NONBLOCK) {
+ if (TestSetPageLocked(page))
+ break;
+ } else
+ lock_page(page);
/*
* page was truncated, stop here. if this isn't the
@@ -416,43 +415,47 @@ __generic_file_splice_read(struct file *in, loff_t *ppos,
break;
}
+ }
+fill_it:
+ /*
+ * i_size must be checked after PageUptodate.
+ */
+ isize = i_size_read(mapping->host);
+ end_index = (isize - 1) >> PAGE_CACHE_SHIFT;
+ if (unlikely(!isize || index > end_index))
+ break;
+
+ /*
+ * if this is the last page, see if we need to shrink
+ * the length and stop
+ */
+ if (end_index == index) {
+ unsigned int plen;
/*
- * i_size must be checked after ->readpage().
+ * max good bytes in this page
*/
- isize = i_size_read(mapping->host);
- end_index = (isize - 1) >> PAGE_CACHE_SHIFT;
- if (unlikely(!isize || index > end_index))
+ plen = ((isize - 1) & ~PAGE_CACHE_MASK) + 1;
+ if (plen <= loff)
break;
/*
- * if this is the last page, see if we need to shrink
- * the length and stop
+ * force quit after adding this page
*/
- if (end_index == index) {
- loff = PAGE_CACHE_SIZE - (isize & ~PAGE_CACHE_MASK);
- if (total_len + loff > isize)
- break;
- /*
- * force quit after adding this page
- */
- len = this_len;
- this_len = min(this_len, loff);
- loff = 0;
- }
+ this_len = min(this_len, plen - loff);
+ len = this_len;
}
-fill_it:
+
partial[page_nr].offset = loff;
partial[page_nr].len = this_len;
len -= this_len;
- total_len += this_len;
loff = 0;
spd.nr_pages++;
index++;
}
/*
- * Release any pages at the end, if we quit early. 'i' is how far
+ * Release any pages at the end, if we quit early. 'page_nr' is how far
* we got, 'nr_pages' is how many pages are in the map.
*/
while (page_nr < nr_pages)
@@ -479,10 +482,18 @@ ssize_t generic_file_splice_read(struct file *in, loff_t *ppos,
{
ssize_t spliced;
int ret;
+ loff_t isize, left;
+
+ isize = i_size_read(in->f_mapping->host);
+ if (unlikely(*ppos >= isize))
+ return 0;
+
+ left = isize - *ppos;
+ if (unlikely(left < len))
+ len = left;
ret = 0;
spliced = 0;
-
while (len) {
ret = __generic_file_splice_read(in, ppos, pipe, len, flags);
@@ -645,7 +656,6 @@ find_page:
* accessed, we are now done!
*/
mark_page_accessed(page);
- balance_dirty_pages_ratelimited(mapping);
out:
page_cache_release(page);
unlock_page(page);
@@ -803,7 +813,10 @@ generic_file_splice_write_nolock(struct pipe_inode_info *pipe, struct file *out,
ret = __splice_from_pipe(pipe, out, ppos, len, flags, pipe_to_file);
if (ret > 0) {
+ unsigned long nr_pages;
+
*ppos += ret;
+ nr_pages = (ret + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
/*
* If file or inode is SYNC and we actually wrote some data,
@@ -816,6 +829,7 @@ generic_file_splice_write_nolock(struct pipe_inode_info *pipe, struct file *out,
if (err)
ret = err;
}
+ balance_dirty_pages_ratelimited_nr(mapping, nr_pages);
}
return ret;
@@ -854,7 +868,10 @@ generic_file_splice_write(struct pipe_inode_info *pipe, struct file *out,
ret = splice_from_pipe(pipe, out, ppos, len, flags, pipe_to_file);
if (ret > 0) {
+ unsigned long nr_pages;
+
*ppos += ret;
+ nr_pages = (ret + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
/*
* If file or inode is SYNC and we actually wrote some data,
@@ -869,6 +886,7 @@ generic_file_splice_write(struct pipe_inode_info *pipe, struct file *out,
if (err)
ret = err;
}
+ balance_dirty_pages_ratelimited_nr(mapping, nr_pages);
}
return ret;
@@ -923,7 +941,6 @@ static long do_splice_to(struct file *in, loff_t *ppos,
struct pipe_inode_info *pipe, size_t len,
unsigned int flags)
{
- loff_t isize, left;
int ret;
if (unlikely(!in->f_op || !in->f_op->splice_read))
@@ -936,14 +953,6 @@ static long do_splice_to(struct file *in, loff_t *ppos,
if (unlikely(ret < 0))
return ret;
- isize = i_size_read(in->f_mapping->host);
- if (unlikely(*ppos >= isize))
- return 0;
-
- left = isize - *ppos;
- if (unlikely(left < len))
- len = left;
-
return in->f_op->splice_read(in, ppos, pipe, len, flags);
}
@@ -1059,8 +1068,6 @@ out_release:
return ret;
}
-EXPORT_SYMBOL(do_splice_direct);
-
/*
* After the inode slimming patch, i_pipe/i_bdev/i_cdev share the same
* location, so checking ->i_pipe is not enough to verify that this is a
diff --git a/fs/stat.c b/fs/stat.c
index 38a8cb2a28d..68510068a64 100644
--- a/fs/stat.c
+++ b/fs/stat.c
@@ -8,7 +8,6 @@
#include <linux/mm.h>
#include <linux/errno.h>
#include <linux/file.h>
-#include <linux/smp_lock.h>
#include <linux/highuid.h>
#include <linux/fs.h>
#include <linux/namei.h>
diff --git a/fs/super.c b/fs/super.c
index 8341e4e1d73..5260d620c55 100644
--- a/fs/super.c
+++ b/fs/super.c
@@ -107,6 +107,7 @@ out:
static inline void destroy_super(struct super_block *s)
{
security_sb_free(s);
+ kfree(s->s_subtype);
kfree(s);
}
@@ -907,6 +908,29 @@ out:
EXPORT_SYMBOL_GPL(vfs_kern_mount);
+static struct vfsmount *fs_set_subtype(struct vfsmount *mnt, const char *fstype)
+{
+ int err;
+ const char *subtype = strchr(fstype, '.');
+ if (subtype) {
+ subtype++;
+ err = -EINVAL;
+ if (!subtype[0])
+ goto err;
+ } else
+ subtype = "";
+
+ mnt->mnt_sb->s_subtype = kstrdup(subtype, GFP_KERNEL);
+ err = -ENOMEM;
+ if (!mnt->mnt_sb->s_subtype)
+ goto err;
+ return mnt;
+
+ err:
+ mntput(mnt);
+ return ERR_PTR(err);
+}
+
struct vfsmount *
do_kern_mount(const char *fstype, int flags, const char *name, void *data)
{
@@ -915,6 +939,9 @@ do_kern_mount(const char *fstype, int flags, const char *name, void *data)
if (!type)
return ERR_PTR(-ENODEV);
mnt = vfs_kern_mount(type, flags, name, data);
+ if (!IS_ERR(mnt) && (type->fs_flags & FS_HAS_SUBTYPE) &&
+ !mnt->mnt_sb->s_subtype)
+ mnt = fs_set_subtype(mnt, fstype);
put_filesystem(type);
return mnt;
}
diff --git a/fs/sync.c b/fs/sync.c
index 5cb9e7e4338..7cd005ea763 100644
--- a/fs/sync.c
+++ b/fs/sync.c
@@ -229,13 +229,21 @@ asmlinkage long sys_sync_file_range(int fd, loff_t offset, loff_t nbytes,
!S_ISLNK(i_mode))
goto out_put;
- ret = do_sync_file_range(file, offset, endbyte, flags);
+ ret = do_sync_mapping_range(file->f_mapping, offset, endbyte, flags);
out_put:
fput_light(file, fput_needed);
out:
return ret;
}
+/* It would be nice if people remember that not all the world's an i386
+ when they introduce new system calls */
+asmlinkage long sys_sync_file_range2(int fd, unsigned int flags,
+ loff_t offset, loff_t nbytes)
+{
+ return sys_sync_file_range(fd, offset, nbytes, flags);
+}
+
/*
* `endbyte' is inclusive
*/
diff --git a/fs/sysfs/dir.c b/fs/sysfs/dir.c
index 85a668680f8..c4342a01997 100644
--- a/fs/sysfs/dir.c
+++ b/fs/sysfs/dir.c
@@ -13,14 +13,26 @@
#include "sysfs.h"
DECLARE_RWSEM(sysfs_rename_sem);
+spinlock_t sysfs_lock = SPIN_LOCK_UNLOCKED;
static void sysfs_d_iput(struct dentry * dentry, struct inode * inode)
{
struct sysfs_dirent * sd = dentry->d_fsdata;
if (sd) {
- BUG_ON(sd->s_dentry != dentry);
- sd->s_dentry = NULL;
+ /* sd->s_dentry is protected with sysfs_lock. This
+ * allows sysfs_drop_dentry() to dereference it.
+ */
+ spin_lock(&sysfs_lock);
+
+ /* The dentry might have been deleted or another
+ * lookup could have happened updating sd->s_dentry to
+ * point the new dentry. Ignore if it isn't pointing
+ * to this dentry.
+ */
+ if (sd->s_dentry == dentry)
+ sd->s_dentry = NULL;
+ spin_unlock(&sysfs_lock);
sysfs_put(sd);
}
iput(inode);
@@ -30,6 +42,14 @@ static struct dentry_operations sysfs_dentry_ops = {
.d_iput = sysfs_d_iput,
};
+static unsigned int sysfs_inode_counter;
+ino_t sysfs_get_inum(void)
+{
+ if (unlikely(sysfs_inode_counter < 3))
+ sysfs_inode_counter = 3;
+ return sysfs_inode_counter++;
+}
+
/*
* Allocates a new sysfs_dirent and links it to the parent sysfs_dirent
*/
@@ -41,6 +61,7 @@ static struct sysfs_dirent * __sysfs_new_dirent(void * element)
if (!sd)
return NULL;
+ sd->s_ino = sysfs_get_inum();
atomic_set(&sd->s_count, 1);
atomic_set(&sd->s_event, 1);
INIT_LIST_HEAD(&sd->s_children);
@@ -238,7 +259,10 @@ static int sysfs_attach_attr(struct sysfs_dirent * sd, struct dentry * dentry)
}
dentry->d_fsdata = sysfs_get(sd);
+ /* protect sd->s_dentry against sysfs_d_iput */
+ spin_lock(&sysfs_lock);
sd->s_dentry = dentry;
+ spin_unlock(&sysfs_lock);
error = sysfs_create(dentry, (attr->mode & S_IALLUGO) | S_IFREG, init);
if (error) {
sysfs_put(sd);
@@ -260,7 +284,10 @@ static int sysfs_attach_link(struct sysfs_dirent * sd, struct dentry * dentry)
int err = 0;
dentry->d_fsdata = sysfs_get(sd);
+ /* protect sd->s_dentry against sysfs_d_iput */
+ spin_lock(&sysfs_lock);
sd->s_dentry = dentry;
+ spin_unlock(&sysfs_lock);
err = sysfs_create(dentry, S_IFLNK|S_IRWXUGO, init_symlink);
if (!err) {
dentry->d_op = &sysfs_dentry_ops;
@@ -509,7 +536,7 @@ static int sysfs_readdir(struct file * filp, void * dirent, filldir_t filldir)
switch (i) {
case 0:
- ino = dentry->d_inode->i_ino;
+ ino = parent_sd->s_ino;
if (filldir(dirent, ".", 1, i, ino, DT_DIR) < 0)
break;
filp->f_pos++;
@@ -538,10 +565,7 @@ static int sysfs_readdir(struct file * filp, void * dirent, filldir_t filldir)
name = sysfs_get_name(next);
len = strlen(name);
- if (next->s_dentry)
- ino = next->s_dentry->d_inode->i_ino;
- else
- ino = iunique(sysfs_sb, 2);
+ ino = next->s_ino;
if (filldir(dirent, name, len, filp->f_pos, ino,
dt_type(next)) < 0)
diff --git a/fs/sysfs/file.c b/fs/sysfs/file.c
index 0e637adc2b8..b502c7197ec 100644
--- a/fs/sysfs/file.c
+++ b/fs/sysfs/file.c
@@ -111,36 +111,6 @@ static int fill_read_buffer(struct dentry * dentry, struct sysfs_buffer * buffer
return ret;
}
-
-/**
- * flush_read_buffer - push buffer to userspace.
- * @buffer: data buffer for file.
- * @buf: user-passed buffer.
- * @count: number of bytes requested.
- * @ppos: file position.
- *
- * Copy the buffer we filled in fill_read_buffer() to userspace.
- * This is done at the reader's leisure, copying and advancing
- * the amount they specify each time.
- * This may be called continuously until the buffer is empty.
- */
-static int flush_read_buffer(struct sysfs_buffer * buffer, char __user * buf,
- size_t count, loff_t * ppos)
-{
- int error;
-
- if (*ppos > buffer->count)
- return 0;
-
- if (count > (buffer->count - *ppos))
- count = buffer->count - *ppos;
-
- error = copy_to_user(buf,buffer->page + *ppos,count);
- if (!error)
- *ppos += count;
- return error ? -EFAULT : count;
-}
-
/**
* sysfs_read_file - read an attribute.
* @file: file pointer.
@@ -177,7 +147,8 @@ sysfs_read_file(struct file *file, char __user *buf, size_t count, loff_t *ppos)
}
pr_debug("%s: count = %zd, ppos = %lld, buf = %s\n",
__FUNCTION__, count, *ppos, buffer->page);
- retval = flush_read_buffer(buffer,buf,count,ppos);
+ retval = simple_read_from_buffer(buf, count, ppos, buffer->page,
+ buffer->count);
out:
up(&buffer->sem);
return retval;
diff --git a/fs/sysfs/inode.c b/fs/sysfs/inode.c
index 4de5c6b8991..5266eec15f6 100644
--- a/fs/sysfs/inode.c
+++ b/fs/sysfs/inode.c
@@ -13,6 +13,7 @@
#include <linux/backing-dev.h>
#include <linux/capability.h>
#include <linux/errno.h>
+#include <linux/sched.h>
#include <asm/semaphore.h>
#include "sysfs.h"
@@ -140,6 +141,7 @@ struct inode * sysfs_new_inode(mode_t mode, struct sysfs_dirent * sd)
inode->i_mapping->a_ops = &sysfs_aops;
inode->i_mapping->backing_dev_info = &sysfs_backing_dev_info;
inode->i_op = &sysfs_inode_operations;
+ inode->i_ino = sd->s_ino;
lockdep_set_class(&inode->i_mutex, &sysfs_inode_imutex_key);
if (sd->s_iattr) {
@@ -244,13 +246,27 @@ static inline void orphan_all_buffers(struct inode *node)
*/
void sysfs_drop_dentry(struct sysfs_dirent * sd, struct dentry * parent)
{
- struct dentry * dentry = sd->s_dentry;
+ struct dentry *dentry = NULL;
struct inode *inode;
+ /* We're not holding a reference to ->s_dentry dentry but the
+ * field will stay valid as long as sysfs_lock is held.
+ */
+ spin_lock(&sysfs_lock);
+ spin_lock(&dcache_lock);
+
+ /* dget dentry if it's still alive */
+ if (sd->s_dentry && sd->s_dentry->d_inode)
+ dentry = dget_locked(sd->s_dentry);
+
+ spin_unlock(&dcache_lock);
+ spin_unlock(&sysfs_lock);
+
+ /* drop dentry */
if (dentry) {
spin_lock(&dcache_lock);
spin_lock(&dentry->d_lock);
- if (!(d_unhashed(dentry) && dentry->d_inode)) {
+ if (!d_unhashed(dentry) && dentry->d_inode) {
inode = dentry->d_inode;
spin_lock(&inode->i_lock);
__iget(inode);
@@ -266,6 +282,8 @@ void sysfs_drop_dentry(struct sysfs_dirent * sd, struct dentry * parent)
spin_unlock(&dentry->d_lock);
spin_unlock(&dcache_lock);
}
+
+ dput(dentry);
}
}
diff --git a/fs/sysfs/mount.c b/fs/sysfs/mount.c
index 23a48a38e6a..00ab9125d39 100644
--- a/fs/sysfs/mount.c
+++ b/fs/sysfs/mount.c
@@ -33,6 +33,7 @@ static struct sysfs_dirent sysfs_root = {
.s_element = NULL,
.s_type = SYSFS_ROOT,
.s_iattr = NULL,
+ .s_ino = 1,
};
static void sysfs_clear_inode(struct inode *inode)
diff --git a/fs/sysfs/sysfs.h b/fs/sysfs/sysfs.h
index a77c57e5a6d..502c949c402 100644
--- a/fs/sysfs/sysfs.h
+++ b/fs/sysfs/sysfs.h
@@ -5,6 +5,7 @@ struct sysfs_dirent {
void * s_element;
int s_type;
umode_t s_mode;
+ ino_t s_ino;
struct dentry * s_dentry;
struct iattr * s_iattr;
atomic_t s_event;
@@ -32,6 +33,7 @@ extern const unsigned char * sysfs_get_name(struct sysfs_dirent *sd);
extern void sysfs_drop_dentry(struct sysfs_dirent *sd, struct dentry *parent);
extern int sysfs_setattr(struct dentry *dentry, struct iattr *iattr);
+extern spinlock_t sysfs_lock;
extern struct rw_semaphore sysfs_rename_sem;
extern struct super_block * sysfs_sb;
extern const struct file_operations sysfs_dir_operations;
diff --git a/fs/sysv/inode.c b/fs/sysv/inode.c
index 3152d741560..56441169339 100644
--- a/fs/sysv/inode.c
+++ b/fs/sysv/inode.c
@@ -322,8 +322,7 @@ static void init_once(void *p, struct kmem_cache *cachep, unsigned long flags)
{
struct sysv_inode_info *si = (struct sysv_inode_info *)p;
- if (flags & SLAB_CTOR_CONSTRUCTOR)
- inode_init_once(&si->vfs_inode);
+ inode_init_once(&si->vfs_inode);
}
const struct super_operations sysv_sops = {
diff --git a/fs/sysv/namei.c b/fs/sysv/namei.c
index 4e48abbd2b5..6bd850b7641 100644
--- a/fs/sysv/namei.c
+++ b/fs/sysv/namei.c
@@ -13,7 +13,6 @@
*/
#include <linux/pagemap.h>
-#include <linux/smp_lock.h>
#include "sysv.h"
static int add_nondir(struct dentry *dentry, struct inode *inode)
diff --git a/fs/timerfd.c b/fs/timerfd.c
new file mode 100644
index 00000000000..af9eca5c023
--- /dev/null
+++ b/fs/timerfd.c
@@ -0,0 +1,225 @@
+/*
+ * fs/timerfd.c
+ *
+ * Copyright (C) 2007 Davide Libenzi <davidel@xmailserver.org>
+ *
+ *
+ * Thanks to Thomas Gleixner for code reviews and useful comments.
+ *
+ */
+
+#include <linux/file.h>
+#include <linux/poll.h>
+#include <linux/init.h>
+#include <linux/fs.h>
+#include <linux/sched.h>
+#include <linux/kernel.h>
+#include <linux/list.h>
+#include <linux/spinlock.h>
+#include <linux/time.h>
+#include <linux/hrtimer.h>
+#include <linux/anon_inodes.h>
+#include <linux/timerfd.h>
+
+struct timerfd_ctx {
+ struct hrtimer tmr;
+ ktime_t tintv;
+ wait_queue_head_t wqh;
+ int expired;
+};
+
+/*
+ * This gets called when the timer event triggers. We set the "expired"
+ * flag, but we do not re-arm the timer (in case it's necessary,
+ * tintv.tv64 != 0) until the timer is read.
+ */
+static enum hrtimer_restart timerfd_tmrproc(struct hrtimer *htmr)
+{
+ struct timerfd_ctx *ctx = container_of(htmr, struct timerfd_ctx, tmr);
+ unsigned long flags;
+
+ spin_lock_irqsave(&ctx->wqh.lock, flags);
+ ctx->expired = 1;
+ wake_up_locked(&ctx->wqh);
+ spin_unlock_irqrestore(&ctx->wqh.lock, flags);
+
+ return HRTIMER_NORESTART;
+}
+
+static void timerfd_setup(struct timerfd_ctx *ctx, int clockid, int flags,
+ const struct itimerspec *ktmr)
+{
+ enum hrtimer_mode htmode;
+ ktime_t texp;
+
+ htmode = (flags & TFD_TIMER_ABSTIME) ?
+ HRTIMER_MODE_ABS: HRTIMER_MODE_REL;
+
+ texp = timespec_to_ktime(ktmr->it_value);
+ ctx->expired = 0;
+ ctx->tintv = timespec_to_ktime(ktmr->it_interval);
+ hrtimer_init(&ctx->tmr, clockid, htmode);
+ ctx->tmr.expires = texp;
+ ctx->tmr.function = timerfd_tmrproc;
+ if (texp.tv64 != 0)
+ hrtimer_start(&ctx->tmr, texp, htmode);
+}
+
+static int timerfd_release(struct inode *inode, struct file *file)
+{
+ struct timerfd_ctx *ctx = file->private_data;
+
+ hrtimer_cancel(&ctx->tmr);
+ kfree(ctx);
+ return 0;
+}
+
+static unsigned int timerfd_poll(struct file *file, poll_table *wait)
+{
+ struct timerfd_ctx *ctx = file->private_data;
+ unsigned int events = 0;
+ unsigned long flags;
+
+ poll_wait(file, &ctx->wqh, wait);
+
+ spin_lock_irqsave(&ctx->wqh.lock, flags);
+ if (ctx->expired)
+ events |= POLLIN;
+ spin_unlock_irqrestore(&ctx->wqh.lock, flags);
+
+ return events;
+}
+
+static ssize_t timerfd_read(struct file *file, char __user *buf, size_t count,
+ loff_t *ppos)
+{
+ struct timerfd_ctx *ctx = file->private_data;
+ ssize_t res;
+ u32 ticks = 0;
+ DECLARE_WAITQUEUE(wait, current);
+
+ if (count < sizeof(ticks))
+ return -EINVAL;
+ spin_lock_irq(&ctx->wqh.lock);
+ res = -EAGAIN;
+ if (!ctx->expired && !(file->f_flags & O_NONBLOCK)) {
+ __add_wait_queue(&ctx->wqh, &wait);
+ for (res = 0;;) {
+ set_current_state(TASK_INTERRUPTIBLE);
+ if (ctx->expired) {
+ res = 0;
+ break;
+ }
+ if (signal_pending(current)) {
+ res = -ERESTARTSYS;
+ break;
+ }
+ spin_unlock_irq(&ctx->wqh.lock);
+ schedule();
+ spin_lock_irq(&ctx->wqh.lock);
+ }
+ __remove_wait_queue(&ctx->wqh, &wait);
+ __set_current_state(TASK_RUNNING);
+ }
+ if (ctx->expired) {
+ ctx->expired = 0;
+ if (ctx->tintv.tv64 != 0) {
+ /*
+ * If tintv.tv64 != 0, this is a periodic timer that
+ * needs to be re-armed. We avoid doing it in the timer
+ * callback to avoid DoS attacks specifying a very
+ * short timer period.
+ */
+ ticks = (u32)
+ hrtimer_forward(&ctx->tmr,
+ hrtimer_cb_get_time(&ctx->tmr),
+ ctx->tintv);
+ hrtimer_restart(&ctx->tmr);
+ } else
+ ticks = 1;
+ }
+ spin_unlock_irq(&ctx->wqh.lock);
+ if (ticks)
+ res = put_user(ticks, buf) ? -EFAULT: sizeof(ticks);
+ return res;
+}
+
+static const struct file_operations timerfd_fops = {
+ .release = timerfd_release,
+ .poll = timerfd_poll,
+ .read = timerfd_read,
+};
+
+asmlinkage long sys_timerfd(int ufd, int clockid, int flags,
+ const struct itimerspec __user *utmr)
+{
+ int error;
+ struct timerfd_ctx *ctx;
+ struct file *file;
+ struct inode *inode;
+ struct itimerspec ktmr;
+
+ if (copy_from_user(&ktmr, utmr, sizeof(ktmr)))
+ return -EFAULT;
+
+ if (clockid != CLOCK_MONOTONIC &&
+ clockid != CLOCK_REALTIME)
+ return -EINVAL;
+ if (!timespec_valid(&ktmr.it_value) ||
+ !timespec_valid(&ktmr.it_interval))
+ return -EINVAL;
+
+ if (ufd == -1) {
+ ctx = kmalloc(sizeof(*ctx), GFP_KERNEL);
+ if (!ctx)
+ return -ENOMEM;
+
+ init_waitqueue_head(&ctx->wqh);
+
+ timerfd_setup(ctx, clockid, flags, &ktmr);
+
+ /*
+ * When we call this, the initialization must be complete, since
+ * anon_inode_getfd() will install the fd.
+ */
+ error = anon_inode_getfd(&ufd, &inode, &file, "[timerfd]",
+ &timerfd_fops, ctx);
+ if (error)
+ goto err_tmrcancel;
+ } else {
+ file = fget(ufd);
+ if (!file)
+ return -EBADF;
+ ctx = file->private_data;
+ if (file->f_op != &timerfd_fops) {
+ fput(file);
+ return -EINVAL;
+ }
+ /*
+ * We need to stop the existing timer before reprogramming
+ * it to the new values.
+ */
+ for (;;) {
+ spin_lock_irq(&ctx->wqh.lock);
+ if (hrtimer_try_to_cancel(&ctx->tmr) >= 0)
+ break;
+ spin_unlock_irq(&ctx->wqh.lock);
+ cpu_relax();
+ }
+ /*
+ * Re-program the timer to the new value ...
+ */
+ timerfd_setup(ctx, clockid, flags, &ktmr);
+
+ spin_unlock_irq(&ctx->wqh.lock);
+ fput(file);
+ }
+
+ return ufd;
+
+err_tmrcancel:
+ hrtimer_cancel(&ctx->tmr);
+ kfree(ctx);
+ return error;
+}
+
diff --git a/fs/udf/balloc.c b/fs/udf/balloc.c
index ea521f846d9..4cec9101568 100644
--- a/fs/udf/balloc.c
+++ b/fs/udf/balloc.c
@@ -427,9 +427,9 @@ static void udf_table_free_blocks(struct super_block * sb,
{
struct udf_sb_info *sbi = UDF_SB(sb);
uint32_t start, end;
- uint32_t nextoffset, oextoffset, elen;
- kernel_lb_addr nbloc, obloc, eloc;
- struct buffer_head *obh, *nbh;
+ uint32_t elen;
+ kernel_lb_addr eloc;
+ struct extent_position oepos, epos;
int8_t etype;
int i;
@@ -457,14 +457,13 @@ static void udf_table_free_blocks(struct super_block * sb,
start = bloc.logicalBlockNum + offset;
end = bloc.logicalBlockNum + offset + count - 1;
- oextoffset = nextoffset = sizeof(struct unallocSpaceEntry);
+ epos.offset = oepos.offset = sizeof(struct unallocSpaceEntry);
elen = 0;
- obloc = nbloc = UDF_I_LOCATION(table);
-
- obh = nbh = NULL;
+ epos.block = oepos.block = UDF_I_LOCATION(table);
+ epos.bh = oepos.bh = NULL;
while (count && (etype =
- udf_next_aext(table, &nbloc, &nextoffset, &eloc, &elen, &nbh, 1)) != -1)
+ udf_next_aext(table, &epos, &eloc, &elen, 1)) != -1)
{
if (((eloc.logicalBlockNum + (elen >> sb->s_blocksize_bits)) ==
start))
@@ -482,7 +481,7 @@ static void udf_table_free_blocks(struct super_block * sb,
start += count;
count = 0;
}
- udf_write_aext(table, obloc, &oextoffset, eloc, elen, obh, 1);
+ udf_write_aext(table, &oepos, eloc, elen, 1);
}
else if (eloc.logicalBlockNum == (end + 1))
{
@@ -502,20 +501,20 @@ static void udf_table_free_blocks(struct super_block * sb,
end -= count;
count = 0;
}
- udf_write_aext(table, obloc, &oextoffset, eloc, elen, obh, 1);
+ udf_write_aext(table, &oepos, eloc, elen, 1);
}
- if (nbh != obh)
+ if (epos.bh != oepos.bh)
{
i = -1;
- obloc = nbloc;
- udf_release_data(obh);
- atomic_inc(&nbh->b_count);
- obh = nbh;
- oextoffset = 0;
+ oepos.block = epos.block;
+ brelse(oepos.bh);
+ get_bh(epos.bh);
+ oepos.bh = epos.bh;
+ oepos.offset = 0;
}
else
- oextoffset = nextoffset;
+ oepos.offset = epos.offset;
}
if (count)
@@ -547,55 +546,53 @@ static void udf_table_free_blocks(struct super_block * sb,
adsize = sizeof(long_ad);
else
{
- udf_release_data(obh);
- udf_release_data(nbh);
+ brelse(oepos.bh);
+ brelse(epos.bh);
goto error_return;
}
- if (nextoffset + (2 * adsize) > sb->s_blocksize)
+ if (epos.offset + (2 * adsize) > sb->s_blocksize)
{
char *sptr, *dptr;
int loffset;
- udf_release_data(obh);
- obh = nbh;
- obloc = nbloc;
- oextoffset = nextoffset;
+ brelse(oepos.bh);
+ oepos = epos;
/* Steal a block from the extent being free'd */
- nbloc.logicalBlockNum = eloc.logicalBlockNum;
+ epos.block.logicalBlockNum = eloc.logicalBlockNum;
eloc.logicalBlockNum ++;
elen -= sb->s_blocksize;
- if (!(nbh = udf_tread(sb,
- udf_get_lb_pblock(sb, nbloc, 0))))
+ if (!(epos.bh = udf_tread(sb,
+ udf_get_lb_pblock(sb, epos.block, 0))))
{
- udf_release_data(obh);
+ brelse(oepos.bh);
goto error_return;
}
- aed = (struct allocExtDesc *)(nbh->b_data);
- aed->previousAllocExtLocation = cpu_to_le32(obloc.logicalBlockNum);
- if (nextoffset + adsize > sb->s_blocksize)
+ aed = (struct allocExtDesc *)(epos.bh->b_data);
+ aed->previousAllocExtLocation = cpu_to_le32(oepos.block.logicalBlockNum);
+ if (epos.offset + adsize > sb->s_blocksize)
{
- loffset = nextoffset;
+ loffset = epos.offset;
aed->lengthAllocDescs = cpu_to_le32(adsize);
- sptr = UDF_I_DATA(inode) + nextoffset -
+ sptr = UDF_I_DATA(inode) + epos.offset -
udf_file_entry_alloc_offset(inode) +
UDF_I_LENEATTR(inode) - adsize;
- dptr = nbh->b_data + sizeof(struct allocExtDesc);
+ dptr = epos.bh->b_data + sizeof(struct allocExtDesc);
memcpy(dptr, sptr, adsize);
- nextoffset = sizeof(struct allocExtDesc) + adsize;
+ epos.offset = sizeof(struct allocExtDesc) + adsize;
}
else
{
- loffset = nextoffset + adsize;
+ loffset = epos.offset + adsize;
aed->lengthAllocDescs = cpu_to_le32(0);
- sptr = (obh)->b_data + nextoffset;
- nextoffset = sizeof(struct allocExtDesc);
+ sptr = oepos.bh->b_data + epos.offset;
+ epos.offset = sizeof(struct allocExtDesc);
- if (obh)
+ if (oepos.bh)
{
- aed = (struct allocExtDesc *)(obh)->b_data;
+ aed = (struct allocExtDesc *)oepos.bh->b_data;
aed->lengthAllocDescs =
cpu_to_le32(le32_to_cpu(aed->lengthAllocDescs) + adsize);
}
@@ -606,11 +603,11 @@ static void udf_table_free_blocks(struct super_block * sb,
}
}
if (UDF_SB_UDFREV(sb) >= 0x0200)
- udf_new_tag(nbh->b_data, TAG_IDENT_AED, 3, 1,
- nbloc.logicalBlockNum, sizeof(tag));
+ udf_new_tag(epos.bh->b_data, TAG_IDENT_AED, 3, 1,
+ epos.block.logicalBlockNum, sizeof(tag));
else
- udf_new_tag(nbh->b_data, TAG_IDENT_AED, 2, 1,
- nbloc.logicalBlockNum, sizeof(tag));
+ udf_new_tag(epos.bh->b_data, TAG_IDENT_AED, 2, 1,
+ epos.block.logicalBlockNum, sizeof(tag));
switch (UDF_I_ALLOCTYPE(table))
{
case ICBTAG_FLAG_AD_SHORT:
@@ -619,7 +616,7 @@ static void udf_table_free_blocks(struct super_block * sb,
sad->extLength = cpu_to_le32(
EXT_NEXT_EXTENT_ALLOCDECS |
sb->s_blocksize);
- sad->extPosition = cpu_to_le32(nbloc.logicalBlockNum);
+ sad->extPosition = cpu_to_le32(epos.block.logicalBlockNum);
break;
}
case ICBTAG_FLAG_AD_LONG:
@@ -628,14 +625,14 @@ static void udf_table_free_blocks(struct super_block * sb,
lad->extLength = cpu_to_le32(
EXT_NEXT_EXTENT_ALLOCDECS |
sb->s_blocksize);
- lad->extLocation = cpu_to_lelb(nbloc);
+ lad->extLocation = cpu_to_lelb(epos.block);
break;
}
}
- if (obh)
+ if (oepos.bh)
{
- udf_update_tag(obh->b_data, loffset);
- mark_buffer_dirty(obh);
+ udf_update_tag(oepos.bh->b_data, loffset);
+ mark_buffer_dirty(oepos.bh);
}
else
mark_inode_dirty(table);
@@ -643,26 +640,26 @@ static void udf_table_free_blocks(struct super_block * sb,
if (elen) /* It's possible that stealing the block emptied the extent */
{
- udf_write_aext(table, nbloc, &nextoffset, eloc, elen, nbh, 1);
+ udf_write_aext(table, &epos, eloc, elen, 1);
- if (!nbh)
+ if (!epos.bh)
{
UDF_I_LENALLOC(table) += adsize;
mark_inode_dirty(table);
}
else
{
- aed = (struct allocExtDesc *)nbh->b_data;
+ aed = (struct allocExtDesc *)epos.bh->b_data;
aed->lengthAllocDescs =
cpu_to_le32(le32_to_cpu(aed->lengthAllocDescs) + adsize);
- udf_update_tag(nbh->b_data, nextoffset);
- mark_buffer_dirty(nbh);
+ udf_update_tag(epos.bh->b_data, epos.offset);
+ mark_buffer_dirty(epos.bh);
}
}
}
- udf_release_data(nbh);
- udf_release_data(obh);
+ brelse(epos.bh);
+ brelse(oepos.bh);
error_return:
sb->s_dirt = 1;
@@ -677,9 +674,9 @@ static int udf_table_prealloc_blocks(struct super_block * sb,
{
struct udf_sb_info *sbi = UDF_SB(sb);
int alloc_count = 0;
- uint32_t extoffset, elen, adsize;
- kernel_lb_addr bloc, eloc;
- struct buffer_head *bh;
+ uint32_t elen, adsize;
+ kernel_lb_addr eloc;
+ struct extent_position epos;
int8_t etype = -1;
if (first_block < 0 || first_block >= UDF_SB_PARTLEN(sb, partition))
@@ -693,14 +690,13 @@ static int udf_table_prealloc_blocks(struct super_block * sb,
return 0;
mutex_lock(&sbi->s_alloc_mutex);
- extoffset = sizeof(struct unallocSpaceEntry);
- bloc = UDF_I_LOCATION(table);
-
- bh = NULL;
+ epos.offset = sizeof(struct unallocSpaceEntry);
+ epos.block = UDF_I_LOCATION(table);
+ epos.bh = NULL;
eloc.logicalBlockNum = 0xFFFFFFFF;
while (first_block != eloc.logicalBlockNum && (etype =
- udf_next_aext(table, &bloc, &extoffset, &eloc, &elen, &bh, 1)) != -1)
+ udf_next_aext(table, &epos, &eloc, &elen, 1)) != -1)
{
udf_debug("eloc=%d, elen=%d, first_block=%d\n",
eloc.logicalBlockNum, elen, first_block);
@@ -709,7 +705,7 @@ static int udf_table_prealloc_blocks(struct super_block * sb,
if (first_block == eloc.logicalBlockNum)
{
- extoffset -= adsize;
+ epos.offset -= adsize;
alloc_count = (elen >> sb->s_blocksize_bits);
if (inode && DQUOT_PREALLOC_BLOCK(inode, alloc_count > block_count ? block_count : alloc_count))
@@ -719,15 +715,15 @@ static int udf_table_prealloc_blocks(struct super_block * sb,
alloc_count = block_count;
eloc.logicalBlockNum += alloc_count;
elen -= (alloc_count << sb->s_blocksize_bits);
- udf_write_aext(table, bloc, &extoffset, eloc, (etype << 30) | elen, bh, 1);
+ udf_write_aext(table, &epos, eloc, (etype << 30) | elen, 1);
}
else
- udf_delete_aext(table, bloc, extoffset, eloc, (etype << 30) | elen, bh);
+ udf_delete_aext(table, epos, eloc, (etype << 30) | elen);
}
else
alloc_count = 0;
- udf_release_data(bh);
+ brelse(epos.bh);
if (alloc_count && UDF_SB_LVIDBH(sb))
{
@@ -747,9 +743,9 @@ static int udf_table_new_block(struct super_block * sb,
struct udf_sb_info *sbi = UDF_SB(sb);
uint32_t spread = 0xFFFFFFFF, nspread = 0xFFFFFFFF;
uint32_t newblock = 0, adsize;
- uint32_t extoffset, goal_extoffset, elen, goal_elen = 0;
- kernel_lb_addr bloc, goal_bloc, eloc, goal_eloc;
- struct buffer_head *bh, *goal_bh;
+ uint32_t elen, goal_elen = 0;
+ kernel_lb_addr eloc, goal_eloc;
+ struct extent_position epos, goal_epos;
int8_t etype;
*err = -ENOSPC;
@@ -770,14 +766,12 @@ static int udf_table_new_block(struct super_block * sb,
We store the buffer_head, bloc, and extoffset of the current closest
match and use that when we are done.
*/
-
- extoffset = sizeof(struct unallocSpaceEntry);
- bloc = UDF_I_LOCATION(table);
-
- goal_bh = bh = NULL;
+ epos.offset = sizeof(struct unallocSpaceEntry);
+ epos.block = UDF_I_LOCATION(table);
+ epos.bh = goal_epos.bh = NULL;
while (spread && (etype =
- udf_next_aext(table, &bloc, &extoffset, &eloc, &elen, &bh, 1)) != -1)
+ udf_next_aext(table, &epos, &eloc, &elen, 1)) != -1)
{
if (goal >= eloc.logicalBlockNum)
{
@@ -793,24 +787,24 @@ static int udf_table_new_block(struct super_block * sb,
if (nspread < spread)
{
spread = nspread;
- if (goal_bh != bh)
+ if (goal_epos.bh != epos.bh)
{
- udf_release_data(goal_bh);
- goal_bh = bh;
- atomic_inc(&goal_bh->b_count);
+ brelse(goal_epos.bh);
+ goal_epos.bh = epos.bh;
+ get_bh(goal_epos.bh);
}
- goal_bloc = bloc;
- goal_extoffset = extoffset - adsize;
+ goal_epos.block = epos.block;
+ goal_epos.offset = epos.offset - adsize;
goal_eloc = eloc;
goal_elen = (etype << 30) | elen;
}
}
- udf_release_data(bh);
+ brelse(epos.bh);
if (spread == 0xFFFFFFFF)
{
- udf_release_data(goal_bh);
+ brelse(goal_epos.bh);
mutex_unlock(&sbi->s_alloc_mutex);
return 0;
}
@@ -826,17 +820,17 @@ static int udf_table_new_block(struct super_block * sb,
if (inode && DQUOT_ALLOC_BLOCK(inode, 1))
{
- udf_release_data(goal_bh);
+ brelse(goal_epos.bh);
mutex_unlock(&sbi->s_alloc_mutex);
*err = -EDQUOT;
return 0;
}
if (goal_elen)
- udf_write_aext(table, goal_bloc, &goal_extoffset, goal_eloc, goal_elen, goal_bh, 1);
+ udf_write_aext(table, &goal_epos, goal_eloc, goal_elen, 1);
else
- udf_delete_aext(table, goal_bloc, goal_extoffset, goal_eloc, goal_elen, goal_bh);
- udf_release_data(goal_bh);
+ udf_delete_aext(table, goal_epos, goal_eloc, goal_elen);
+ brelse(goal_epos.bh);
if (UDF_SB_LVIDBH(sb))
{
@@ -921,11 +915,14 @@ inline int udf_new_block(struct super_block * sb,
struct inode * inode,
uint16_t partition, uint32_t goal, int *err)
{
+ int ret;
+
if (UDF_SB_PARTFLAGS(sb, partition) & UDF_PART_FLAG_UNALLOC_BITMAP)
{
- return udf_bitmap_new_block(sb, inode,
+ ret = udf_bitmap_new_block(sb, inode,
UDF_SB_PARTMAPS(sb)[partition].s_uspace.s_bitmap,
partition, goal, err);
+ return ret;
}
else if (UDF_SB_PARTFLAGS(sb, partition) & UDF_PART_FLAG_UNALLOC_TABLE)
{
diff --git a/fs/udf/dir.c b/fs/udf/dir.c
index 2391c9150c4..e45f86b5e7b 100644
--- a/fs/udf/dir.c
+++ b/fs/udf/dir.c
@@ -111,11 +111,13 @@ do_udf_readdir(struct inode * dir, struct file *filp, filldir_t filldir, void *d
uint16_t liu;
uint8_t lfi;
loff_t size = (udf_ext0_offset(dir) + dir->i_size) >> 2;
- struct buffer_head * bh = NULL, * tmp, * bha[16];
- kernel_lb_addr bloc, eloc;
- uint32_t extoffset, elen, offset;
+ struct buffer_head *tmp, *bha[16];
+ kernel_lb_addr eloc;
+ uint32_t elen;
+ sector_t offset;
int i, num;
unsigned int dt_type;
+ struct extent_position epos = { NULL, 0, {0, 0}};
if (nf_pos >= size)
return 0;
@@ -127,23 +129,22 @@ do_udf_readdir(struct inode * dir, struct file *filp, filldir_t filldir, void *d
if (UDF_I_ALLOCTYPE(dir) == ICBTAG_FLAG_AD_IN_ICB)
fibh.sbh = fibh.ebh = NULL;
else if (inode_bmap(dir, nf_pos >> (dir->i_sb->s_blocksize_bits - 2),
- &bloc, &extoffset, &eloc, &elen, &offset, &bh) == (EXT_RECORDED_ALLOCATED >> 30))
+ &epos, &eloc, &elen, &offset) == (EXT_RECORDED_ALLOCATED >> 30))
{
- offset >>= dir->i_sb->s_blocksize_bits;
block = udf_get_lb_pblock(dir->i_sb, eloc, offset);
if ((++offset << dir->i_sb->s_blocksize_bits) < elen)
{
if (UDF_I_ALLOCTYPE(dir) == ICBTAG_FLAG_AD_SHORT)
- extoffset -= sizeof(short_ad);
+ epos.offset -= sizeof(short_ad);
else if (UDF_I_ALLOCTYPE(dir) == ICBTAG_FLAG_AD_LONG)
- extoffset -= sizeof(long_ad);
+ epos.offset -= sizeof(long_ad);
}
else
offset = 0;
if (!(fibh.sbh = fibh.ebh = udf_tread(dir->i_sb, block)))
{
- udf_release_data(bh);
+ brelse(epos.bh);
return -EIO;
}
@@ -171,7 +172,7 @@ do_udf_readdir(struct inode * dir, struct file *filp, filldir_t filldir, void *d
}
else
{
- udf_release_data(bh);
+ brelse(epos.bh);
return -ENOENT;
}
@@ -179,14 +180,14 @@ do_udf_readdir(struct inode * dir, struct file *filp, filldir_t filldir, void *d
{
filp->f_pos = nf_pos + 1;
- fi = udf_fileident_read(dir, &nf_pos, &fibh, &cfi, &bloc, &extoffset, &eloc, &elen, &offset, &bh);
+ fi = udf_fileident_read(dir, &nf_pos, &fibh, &cfi, &epos, &eloc, &elen, &offset);
if (!fi)
{
if (fibh.sbh != fibh.ebh)
- udf_release_data(fibh.ebh);
- udf_release_data(fibh.sbh);
- udf_release_data(bh);
+ brelse(fibh.ebh);
+ brelse(fibh.sbh);
+ brelse(epos.bh);
return 0;
}
@@ -244,9 +245,9 @@ do_udf_readdir(struct inode * dir, struct file *filp, filldir_t filldir, void *d
if (filldir(dirent, fname, flen, filp->f_pos, iblock, dt_type) < 0)
{
if (fibh.sbh != fibh.ebh)
- udf_release_data(fibh.ebh);
- udf_release_data(fibh.sbh);
- udf_release_data(bh);
+ brelse(fibh.ebh);
+ brelse(fibh.sbh);
+ brelse(epos.bh);
return 0;
}
}
@@ -255,9 +256,9 @@ do_udf_readdir(struct inode * dir, struct file *filp, filldir_t filldir, void *d
filp->f_pos = nf_pos + 1;
if (fibh.sbh != fibh.ebh)
- udf_release_data(fibh.ebh);
- udf_release_data(fibh.sbh);
- udf_release_data(bh);
+ brelse(fibh.ebh);
+ brelse(fibh.sbh);
+ brelse(epos.bh);
return 0;
}
diff --git a/fs/udf/directory.c b/fs/udf/directory.c
index fe751a2a0e4..198caa33027 100644
--- a/fs/udf/directory.c
+++ b/fs/udf/directory.c
@@ -36,14 +36,14 @@ udf_filead_read(struct inode *dir, uint8_t *tmpad, uint8_t ad_size,
if (!ad)
{
- udf_release_data(*bh);
+ brelse(*bh);
*error = 1;
return NULL;
}
if (*offset == dir->i_sb->s_blocksize)
{
- udf_release_data(*bh);
+ brelse(*bh);
block = udf_get_lb_pblock(dir->i_sb, fe_loc, ++*pos);
if (!block)
return NULL;
@@ -57,7 +57,7 @@ udf_filead_read(struct inode *dir, uint8_t *tmpad, uint8_t ad_size,
remainder = dir->i_sb->s_blocksize - loffset;
memcpy((uint8_t *)ad, (*bh)->b_data + loffset, remainder);
- udf_release_data(*bh);
+ brelse(*bh);
block = udf_get_lb_pblock(dir->i_sb, fe_loc, ++*pos);
if (!block)
return NULL;
@@ -75,9 +75,9 @@ struct fileIdentDesc *
udf_fileident_read(struct inode *dir, loff_t *nf_pos,
struct udf_fileident_bh *fibh,
struct fileIdentDesc *cfi,
- kernel_lb_addr *bloc, uint32_t *extoffset,
+ struct extent_position *epos,
kernel_lb_addr *eloc, uint32_t *elen,
- uint32_t *offset, struct buffer_head **bh)
+ sector_t *offset)
{
struct fileIdentDesc *fi;
int i, num, block;
@@ -105,13 +105,11 @@ udf_fileident_read(struct inode *dir, loff_t *nf_pos,
if (fibh->eoffset == dir->i_sb->s_blocksize)
{
- int lextoffset = *extoffset;
+ int lextoffset = epos->offset;
- if (udf_next_aext(dir, bloc, extoffset, eloc, elen, bh, 1) !=
+ if (udf_next_aext(dir, epos, eloc, elen, 1) !=
(EXT_RECORDED_ALLOCATED >> 30))
- {
return NULL;
- }
block = udf_get_lb_pblock(dir->i_sb, *eloc, *offset);
@@ -120,9 +118,9 @@ udf_fileident_read(struct inode *dir, loff_t *nf_pos,
if ((*offset << dir->i_sb->s_blocksize_bits) >= *elen)
*offset = 0;
else
- *extoffset = lextoffset;
+ epos->offset = lextoffset;
- udf_release_data(fibh->sbh);
+ brelse(fibh->sbh);
if (!(fibh->sbh = fibh->ebh = udf_tread(dir->i_sb, block)))
return NULL;
fibh->soffset = fibh->eoffset = 0;
@@ -151,7 +149,7 @@ udf_fileident_read(struct inode *dir, loff_t *nf_pos,
}
else if (fibh->sbh != fibh->ebh)
{
- udf_release_data(fibh->sbh);
+ brelse(fibh->sbh);
fibh->sbh = fibh->ebh;
}
@@ -169,13 +167,11 @@ udf_fileident_read(struct inode *dir, loff_t *nf_pos,
}
else if (fibh->eoffset > dir->i_sb->s_blocksize)
{
- int lextoffset = *extoffset;
+ int lextoffset = epos->offset;
- if (udf_next_aext(dir, bloc, extoffset, eloc, elen, bh, 1) !=
+ if (udf_next_aext(dir, epos, eloc, elen, 1) !=
(EXT_RECORDED_ALLOCATED >> 30))
- {
return NULL;
- }
block = udf_get_lb_pblock(dir->i_sb, *eloc, *offset);
@@ -184,7 +180,7 @@ udf_fileident_read(struct inode *dir, loff_t *nf_pos,
if ((*offset << dir->i_sb->s_blocksize_bits) >= *elen)
*offset = 0;
else
- *extoffset = lextoffset;
+ epos->offset = lextoffset;
fibh->soffset -= dir->i_sb->s_blocksize;
fibh->eoffset -= dir->i_sb->s_blocksize;
diff --git a/fs/udf/file.c b/fs/udf/file.c
index 40d5047defe..51b5764685e 100644
--- a/fs/udf/file.c
+++ b/fs/udf/file.c
@@ -36,6 +36,7 @@
#include <linux/smp_lock.h>
#include <linux/pagemap.h>
#include <linux/buffer_head.h>
+#include <linux/aio.h>
#include "udf_i.h"
#include "udf_sb.h"
diff --git a/fs/udf/fsync.c b/fs/udf/fsync.c
index 5887d78cde4..6ded93e7c44 100644
--- a/fs/udf/fsync.c
+++ b/fs/udf/fsync.c
@@ -21,7 +21,6 @@
#include "udfdecl.h"
#include <linux/fs.h>
-#include <linux/smp_lock.h>
static int udf_fsync_inode(struct inode *, int);
diff --git a/fs/udf/inode.c b/fs/udf/inode.c
index ae21a0e59e9..bf7de0bdbab 100644
--- a/fs/udf/inode.c
+++ b/fs/udf/inode.c
@@ -49,10 +49,10 @@ MODULE_LICENSE("GPL");
static mode_t udf_convert_permissions(struct fileEntry *);
static int udf_update_inode(struct inode *, int);
static void udf_fill_inode(struct inode *, struct buffer_head *);
-static struct buffer_head *inode_getblk(struct inode *, long, int *,
+static struct buffer_head *inode_getblk(struct inode *, sector_t, int *,
long *, int *);
-static int8_t udf_insert_aext(struct inode *, kernel_lb_addr, int,
- kernel_lb_addr, uint32_t, struct buffer_head *);
+static int8_t udf_insert_aext(struct inode *, struct extent_position,
+ kernel_lb_addr, uint32_t);
static void udf_split_extents(struct inode *, int *, int, int,
kernel_long_ad [EXTENT_MERGE_SIZE], int *);
static void udf_prealloc_extents(struct inode *, int, int,
@@ -61,7 +61,7 @@ static void udf_merge_extents(struct inode *,
kernel_long_ad [EXTENT_MERGE_SIZE], int *);
static void udf_update_extents(struct inode *,
kernel_long_ad [EXTENT_MERGE_SIZE], int, int,
- kernel_lb_addr, uint32_t, struct buffer_head **);
+ struct extent_position *);
static int udf_get_block(struct inode *, sector_t, struct buffer_head *, int);
/*
@@ -100,14 +100,23 @@ no_delete:
clear_inode(inode);
}
+/*
+ * If we are going to release inode from memory, we discard preallocation and
+ * truncate last inode extent to proper length. We could use drop_inode() but
+ * it's called under inode_lock and thus we cannot mark inode dirty there. We
+ * use clear_inode() but we have to make sure to write inode as it's not written
+ * automatically.
+ */
void udf_clear_inode(struct inode *inode)
{
if (!(inode->i_sb->s_flags & MS_RDONLY)) {
lock_kernel();
+ /* Discard preallocation for directories, symlinks, etc. */
udf_discard_prealloc(inode);
+ udf_truncate_tail_extent(inode);
unlock_kernel();
+ write_inode_now(inode, 1);
}
-
kfree(UDF_I_DATA(inode));
UDF_I_DATA(inode) = NULL;
}
@@ -194,10 +203,11 @@ void udf_expand_file_adinicb(struct inode * inode, int newsize, int * err)
struct buffer_head * udf_expand_dir_adinicb(struct inode *inode, int *block, int *err)
{
int newblock;
- struct buffer_head *sbh = NULL, *dbh = NULL;
- kernel_lb_addr bloc, eloc;
- uint32_t elen, extoffset;
+ struct buffer_head *dbh = NULL;
+ kernel_lb_addr eloc;
+ uint32_t elen;
uint8_t alloctype;
+ struct extent_position epos;
struct udf_fileident_bh sfibh, dfibh;
loff_t f_pos = udf_ext0_offset(inode) >> 2;
@@ -237,16 +247,16 @@ struct buffer_head * udf_expand_dir_adinicb(struct inode *inode, int *block, int
mark_buffer_dirty_inode(dbh, inode);
sfibh.soffset = sfibh.eoffset = (f_pos & ((inode->i_sb->s_blocksize - 1) >> 2)) << 2;
- sbh = sfibh.sbh = sfibh.ebh = NULL;
+ sfibh.sbh = sfibh.ebh = NULL;
dfibh.soffset = dfibh.eoffset = 0;
dfibh.sbh = dfibh.ebh = dbh;
while ( (f_pos < size) )
{
UDF_I_ALLOCTYPE(inode) = ICBTAG_FLAG_AD_IN_ICB;
- sfi = udf_fileident_read(inode, &f_pos, &sfibh, &cfi, NULL, NULL, NULL, NULL, NULL, NULL);
+ sfi = udf_fileident_read(inode, &f_pos, &sfibh, &cfi, NULL, NULL, NULL, NULL);
if (!sfi)
{
- udf_release_data(dbh);
+ brelse(dbh);
return NULL;
}
UDF_I_ALLOCTYPE(inode) = alloctype;
@@ -258,7 +268,7 @@ struct buffer_head * udf_expand_dir_adinicb(struct inode *inode, int *block, int
sfi->fileIdent + le16_to_cpu(sfi->lengthOfImpUse)))
{
UDF_I_ALLOCTYPE(inode) = ICBTAG_FLAG_AD_IN_ICB;
- udf_release_data(dbh);
+ brelse(dbh);
return NULL;
}
}
@@ -266,16 +276,17 @@ struct buffer_head * udf_expand_dir_adinicb(struct inode *inode, int *block, int
memset(UDF_I_DATA(inode) + UDF_I_LENEATTR(inode), 0, UDF_I_LENALLOC(inode));
UDF_I_LENALLOC(inode) = 0;
- bloc = UDF_I_LOCATION(inode);
eloc.logicalBlockNum = *block;
eloc.partitionReferenceNum = UDF_I_LOCATION(inode).partitionReferenceNum;
elen = inode->i_size;
UDF_I_LENEXTENTS(inode) = elen;
- extoffset = udf_file_entry_alloc_offset(inode);
- udf_add_aext(inode, &bloc, &extoffset, eloc, elen, &sbh, 0);
+ epos.bh = NULL;
+ epos.block = UDF_I_LOCATION(inode);
+ epos.offset = udf_file_entry_alloc_offset(inode);
+ udf_add_aext(inode, &epos, eloc, elen, 0);
/* UniqueID stuff */
- udf_release_data(sbh);
+ brelse(epos.bh);
mark_inode_dirty(inode);
return dbh;
}
@@ -354,53 +365,153 @@ udf_getblk(struct inode *inode, long block, int create, int *err)
return NULL;
}
-static struct buffer_head * inode_getblk(struct inode * inode, long block,
+/* Extend the file by 'blocks' blocks, return the number of extents added */
+int udf_extend_file(struct inode *inode, struct extent_position *last_pos,
+ kernel_long_ad *last_ext, sector_t blocks)
+{
+ sector_t add;
+ int count = 0, fake = !(last_ext->extLength & UDF_EXTENT_LENGTH_MASK);
+ struct super_block *sb = inode->i_sb;
+ kernel_lb_addr prealloc_loc = {0, 0};
+ int prealloc_len = 0;
+
+ /* The previous extent is fake and we should not extend by anything
+ * - there's nothing to do... */
+ if (!blocks && fake)
+ return 0;
+ /* Round the last extent up to a multiple of block size */
+ if (last_ext->extLength & (sb->s_blocksize - 1)) {
+ last_ext->extLength =
+ (last_ext->extLength & UDF_EXTENT_FLAG_MASK) |
+ (((last_ext->extLength & UDF_EXTENT_LENGTH_MASK) +
+ sb->s_blocksize - 1) & ~(sb->s_blocksize - 1));
+ UDF_I_LENEXTENTS(inode) =
+ (UDF_I_LENEXTENTS(inode) + sb->s_blocksize - 1) &
+ ~(sb->s_blocksize - 1);
+ }
+ /* Last extent are just preallocated blocks? */
+ if ((last_ext->extLength & UDF_EXTENT_FLAG_MASK) == EXT_NOT_RECORDED_ALLOCATED) {
+ /* Save the extent so that we can reattach it to the end */
+ prealloc_loc = last_ext->extLocation;
+ prealloc_len = last_ext->extLength;
+ /* Mark the extent as a hole */
+ last_ext->extLength = EXT_NOT_RECORDED_NOT_ALLOCATED |
+ (last_ext->extLength & UDF_EXTENT_LENGTH_MASK);
+ last_ext->extLocation.logicalBlockNum = 0;
+ last_ext->extLocation.partitionReferenceNum = 0;
+ }
+ /* Can we merge with the previous extent? */
+ if ((last_ext->extLength & UDF_EXTENT_FLAG_MASK) == EXT_NOT_RECORDED_NOT_ALLOCATED) {
+ add = ((1<<30) - sb->s_blocksize - (last_ext->extLength &
+ UDF_EXTENT_LENGTH_MASK)) >> sb->s_blocksize_bits;
+ if (add > blocks)
+ add = blocks;
+ blocks -= add;
+ last_ext->extLength += add << sb->s_blocksize_bits;
+ }
+
+ if (fake) {
+ udf_add_aext(inode, last_pos, last_ext->extLocation,
+ last_ext->extLength, 1);
+ count++;
+ }
+ else
+ udf_write_aext(inode, last_pos, last_ext->extLocation, last_ext->extLength, 1);
+ /* Managed to do everything necessary? */
+ if (!blocks)
+ goto out;
+
+ /* All further extents will be NOT_RECORDED_NOT_ALLOCATED */
+ last_ext->extLocation.logicalBlockNum = 0;
+ last_ext->extLocation.partitionReferenceNum = 0;
+ add = (1 << (30-sb->s_blocksize_bits)) - 1;
+ last_ext->extLength = EXT_NOT_RECORDED_NOT_ALLOCATED | (add << sb->s_blocksize_bits);
+ /* Create enough extents to cover the whole hole */
+ while (blocks > add) {
+ blocks -= add;
+ if (udf_add_aext(inode, last_pos, last_ext->extLocation,
+ last_ext->extLength, 1) == -1)
+ return -1;
+ count++;
+ }
+ if (blocks) {
+ last_ext->extLength = EXT_NOT_RECORDED_NOT_ALLOCATED |
+ (blocks << sb->s_blocksize_bits);
+ if (udf_add_aext(inode, last_pos, last_ext->extLocation,
+ last_ext->extLength, 1) == -1)
+ return -1;
+ count++;
+ }
+out:
+ /* Do we have some preallocated blocks saved? */
+ if (prealloc_len) {
+ if (udf_add_aext(inode, last_pos, prealloc_loc, prealloc_len, 1) == -1)
+ return -1;
+ last_ext->extLocation = prealloc_loc;
+ last_ext->extLength = prealloc_len;
+ count++;
+ }
+ /* last_pos should point to the last written extent... */
+ if (UDF_I_ALLOCTYPE(inode) == ICBTAG_FLAG_AD_SHORT)
+ last_pos->offset -= sizeof(short_ad);
+ else if (UDF_I_ALLOCTYPE(inode) == ICBTAG_FLAG_AD_LONG)
+ last_pos->offset -= sizeof(long_ad);
+ else
+ return -1;
+ return count;
+}
+
+static struct buffer_head * inode_getblk(struct inode * inode, sector_t block,
int *err, long *phys, int *new)
{
- struct buffer_head *pbh = NULL, *cbh = NULL, *nbh = NULL, *result = NULL;
+ static sector_t last_block;
+ struct buffer_head *result = NULL;
kernel_long_ad laarr[EXTENT_MERGE_SIZE];
- uint32_t pextoffset = 0, cextoffset = 0, nextoffset = 0;
+ struct extent_position prev_epos, cur_epos, next_epos;
int count = 0, startnum = 0, endnum = 0;
- uint32_t elen = 0;
- kernel_lb_addr eloc, pbloc, cbloc, nbloc;
+ uint32_t elen = 0, tmpelen;
+ kernel_lb_addr eloc, tmpeloc;
int c = 1;
- uint64_t lbcount = 0, b_off = 0;
- uint32_t newblocknum, newblock, offset = 0;
+ loff_t lbcount = 0, b_off = 0;
+ uint32_t newblocknum, newblock;
+ sector_t offset = 0;
int8_t etype;
int goal = 0, pgoal = UDF_I_LOCATION(inode).logicalBlockNum;
- char lastblock = 0;
+ int lastblock = 0;
- pextoffset = cextoffset = nextoffset = udf_file_entry_alloc_offset(inode);
- b_off = (uint64_t)block << inode->i_sb->s_blocksize_bits;
- pbloc = cbloc = nbloc = UDF_I_LOCATION(inode);
+ prev_epos.offset = udf_file_entry_alloc_offset(inode);
+ prev_epos.block = UDF_I_LOCATION(inode);
+ prev_epos.bh = NULL;
+ cur_epos = next_epos = prev_epos;
+ b_off = (loff_t)block << inode->i_sb->s_blocksize_bits;
/* find the extent which contains the block we are looking for.
alternate between laarr[0] and laarr[1] for locations of the
current extent, and the previous extent */
do
{
- if (pbh != cbh)
+ if (prev_epos.bh != cur_epos.bh)
{
- udf_release_data(pbh);
- atomic_inc(&cbh->b_count);
- pbh = cbh;
+ brelse(prev_epos.bh);
+ get_bh(cur_epos.bh);
+ prev_epos.bh = cur_epos.bh;
}
- if (cbh != nbh)
+ if (cur_epos.bh != next_epos.bh)
{
- udf_release_data(cbh);
- atomic_inc(&nbh->b_count);
- cbh = nbh;
+ brelse(cur_epos.bh);
+ get_bh(next_epos.bh);
+ cur_epos.bh = next_epos.bh;
}
lbcount += elen;
- pbloc = cbloc;
- cbloc = nbloc;
+ prev_epos.block = cur_epos.block;
+ cur_epos.block = next_epos.block;
- pextoffset = cextoffset;
- cextoffset = nextoffset;
+ prev_epos.offset = cur_epos.offset;
+ cur_epos.offset = next_epos.offset;
- if ((etype = udf_next_aext(inode, &nbloc, &nextoffset, &eloc, &elen, &nbh, 1)) == -1)
+ if ((etype = udf_next_aext(inode, &next_epos, &eloc, &elen, 1)) == -1)
break;
c = !c;
@@ -418,6 +529,12 @@ static struct buffer_head * inode_getblk(struct inode * inode, long block,
b_off -= lbcount;
offset = b_off >> inode->i_sb->s_blocksize_bits;
+ /*
+ * Move prev_epos and cur_epos into indirect extent if we are at
+ * the pointer to it
+ */
+ udf_next_aext(inode, &prev_epos, &tmpeloc, &tmpelen, 0);
+ udf_next_aext(inode, &cur_epos, &tmpeloc, &tmpelen, 0);
/* if the extent is allocated and recorded, return the block
if the extent is not a multiple of the blocksize, round up */
@@ -429,54 +546,77 @@ static struct buffer_head * inode_getblk(struct inode * inode, long block,
elen = EXT_RECORDED_ALLOCATED |
((elen + inode->i_sb->s_blocksize - 1) &
~(inode->i_sb->s_blocksize - 1));
- etype = udf_write_aext(inode, nbloc, &cextoffset, eloc, elen, nbh, 1);
+ etype = udf_write_aext(inode, &cur_epos, eloc, elen, 1);
}
- udf_release_data(pbh);
- udf_release_data(cbh);
- udf_release_data(nbh);
+ brelse(prev_epos.bh);
+ brelse(cur_epos.bh);
+ brelse(next_epos.bh);
newblock = udf_get_lb_pblock(inode->i_sb, eloc, offset);
*phys = newblock;
return NULL;
}
+ last_block = block;
+ /* Are we beyond EOF? */
if (etype == -1)
{
- endnum = startnum = ((count > 1) ? 1 : count);
- if (laarr[c].extLength & (inode->i_sb->s_blocksize - 1))
- {
- laarr[c].extLength =
- (laarr[c].extLength & UDF_EXTENT_FLAG_MASK) |
- (((laarr[c].extLength & UDF_EXTENT_LENGTH_MASK) +
- inode->i_sb->s_blocksize - 1) &
- ~(inode->i_sb->s_blocksize - 1));
- UDF_I_LENEXTENTS(inode) =
- (UDF_I_LENEXTENTS(inode) + inode->i_sb->s_blocksize - 1) &
- ~(inode->i_sb->s_blocksize - 1);
+ int ret;
+
+ if (count) {
+ if (c)
+ laarr[0] = laarr[1];
+ startnum = 1;
+ }
+ else {
+ /* Create a fake extent when there's not one */
+ memset(&laarr[0].extLocation, 0x00, sizeof(kernel_lb_addr));
+ laarr[0].extLength = EXT_NOT_RECORDED_NOT_ALLOCATED;
+ /* Will udf_extend_file() create real extent from a fake one? */
+ startnum = (offset > 0);
+ }
+ /* Create extents for the hole between EOF and offset */
+ ret = udf_extend_file(inode, &prev_epos, laarr, offset);
+ if (ret == -1) {
+ brelse(prev_epos.bh);
+ brelse(cur_epos.bh);
+ brelse(next_epos.bh);
+ /* We don't really know the error here so we just make
+ * something up */
+ *err = -ENOSPC;
+ return NULL;
}
- c = !c;
- laarr[c].extLength = EXT_NOT_RECORDED_NOT_ALLOCATED |
- ((offset + 1) << inode->i_sb->s_blocksize_bits);
- memset(&laarr[c].extLocation, 0x00, sizeof(kernel_lb_addr));
- count ++;
- endnum ++;
+ c = 0;
+ offset = 0;
+ count += ret;
+ /* We are not covered by a preallocated extent? */
+ if ((laarr[0].extLength & UDF_EXTENT_FLAG_MASK) != EXT_NOT_RECORDED_ALLOCATED) {
+ /* Is there any real extent? - otherwise we overwrite
+ * the fake one... */
+ if (count)
+ c = !c;
+ laarr[c].extLength = EXT_NOT_RECORDED_NOT_ALLOCATED |
+ inode->i_sb->s_blocksize;
+ memset(&laarr[c].extLocation, 0x00, sizeof(kernel_lb_addr));
+ count ++;
+ endnum ++;
+ }
+ endnum = c+1;
lastblock = 1;
}
- else
+ else {
endnum = startnum = ((count > 2) ? 2 : count);
- /* if the current extent is in position 0, swap it with the previous */
- if (!c && count != 1)
- {
- laarr[2] = laarr[0];
- laarr[0] = laarr[1];
- laarr[1] = laarr[2];
- c = 1;
- }
+ /* if the current extent is in position 0, swap it with the previous */
+ if (!c && count != 1)
+ {
+ laarr[2] = laarr[0];
+ laarr[0] = laarr[1];
+ laarr[1] = laarr[2];
+ c = 1;
+ }
- /* if the current block is located in a extent, read the next extent */
- if (etype != -1)
- {
- if ((etype = udf_next_aext(inode, &nbloc, &nextoffset, &eloc, &elen, &nbh, 0)) != -1)
+ /* if the current block is located in an extent, read the next extent */
+ if ((etype = udf_next_aext(inode, &next_epos, &eloc, &elen, 0)) != -1)
{
laarr[c+1].extLength = (etype << 30) | elen;
laarr[c+1].extLocation = eloc;
@@ -484,11 +624,10 @@ static struct buffer_head * inode_getblk(struct inode * inode, long block,
startnum ++;
endnum ++;
}
- else
+ else {
lastblock = 1;
+ }
}
- udf_release_data(cbh);
- udf_release_data(nbh);
/* if the current extent is not recorded but allocated, get the
block in the extent corresponding to the requested block */
@@ -508,7 +647,7 @@ static struct buffer_head * inode_getblk(struct inode * inode, long block,
if (!(newblocknum = udf_new_block(inode->i_sb, inode,
UDF_I_LOCATION(inode).partitionReferenceNum, goal, err)))
{
- udf_release_data(pbh);
+ brelse(prev_epos.bh);
*err = -ENOSPC;
return NULL;
}
@@ -529,11 +668,11 @@ static struct buffer_head * inode_getblk(struct inode * inode, long block,
udf_merge_extents(inode, laarr, &endnum);
/* write back the new extents, inserting new extents if the new number
- of extents is greater than the old number, and deleting extents if
- the new number of extents is less than the old number */
- udf_update_extents(inode, laarr, startnum, endnum, pbloc, pextoffset, &pbh);
+ of extents is greater than the old number, and deleting extents if
+ the new number of extents is less than the old number */
+ udf_update_extents(inode, laarr, startnum, endnum, &prev_epos);
- udf_release_data(pbh);
+ brelse(prev_epos.bh);
if (!(newblock = udf_get_pblock(inode->i_sb, newblocknum,
UDF_I_LOCATION(inode).partitionReferenceNum, 0)))
@@ -795,7 +934,7 @@ static void udf_merge_extents(struct inode *inode,
static void udf_update_extents(struct inode *inode,
kernel_long_ad laarr[EXTENT_MERGE_SIZE], int startnum, int endnum,
- kernel_lb_addr pbloc, uint32_t pextoffset, struct buffer_head **pbh)
+ struct extent_position *epos)
{
int start = 0, i;
kernel_lb_addr tmploc;
@@ -804,28 +943,26 @@ static void udf_update_extents(struct inode *inode,
if (startnum > endnum)
{
for (i=0; i<(startnum-endnum); i++)
- {
- udf_delete_aext(inode, pbloc, pextoffset, laarr[i].extLocation,
- laarr[i].extLength, *pbh);
- }
+ udf_delete_aext(inode, *epos, laarr[i].extLocation,
+ laarr[i].extLength);
}
else if (startnum < endnum)
{
for (i=0; i<(endnum-startnum); i++)
{
- udf_insert_aext(inode, pbloc, pextoffset, laarr[i].extLocation,
- laarr[i].extLength, *pbh);
- udf_next_aext(inode, &pbloc, &pextoffset, &laarr[i].extLocation,
- &laarr[i].extLength, pbh, 1);
+ udf_insert_aext(inode, *epos, laarr[i].extLocation,
+ laarr[i].extLength);
+ udf_next_aext(inode, epos, &laarr[i].extLocation,
+ &laarr[i].extLength, 1);
start ++;
}
}
for (i=start; i<endnum; i++)
{
- udf_next_aext(inode, &pbloc, &pextoffset, &tmploc, &tmplen, pbh, 0);
- udf_write_aext(inode, pbloc, &pextoffset, laarr[i].extLocation,
- laarr[i].extLength, *pbh, 1);
+ udf_next_aext(inode, epos, &tmploc, &tmplen, 0);
+ udf_write_aext(inode, epos, laarr[i].extLocation,
+ laarr[i].extLength, 1);
}
}
@@ -931,7 +1068,7 @@ __udf_read_inode(struct inode *inode)
{
printk(KERN_ERR "udf: udf_read_inode(ino %ld) failed ident=%d\n",
inode->i_ino, ident);
- udf_release_data(bh);
+ brelse(bh);
make_bad_inode(inode);
return;
}
@@ -960,35 +1097,36 @@ __udf_read_inode(struct inode *inode)
ident == TAG_IDENT_EFE)
{
memcpy(&UDF_I_LOCATION(inode), &loc, sizeof(kernel_lb_addr));
- udf_release_data(bh);
- udf_release_data(ibh);
- udf_release_data(nbh);
+ brelse(bh);
+ brelse(ibh);
+ brelse(nbh);
__udf_read_inode(inode);
return;
}
else
{
- udf_release_data(nbh);
- udf_release_data(ibh);
+ brelse(nbh);
+ brelse(ibh);
}
}
else
- udf_release_data(ibh);
+ brelse(ibh);
}
}
else
- udf_release_data(ibh);
+ brelse(ibh);
}
else if (le16_to_cpu(fe->icbTag.strategyType) != 4)
{
printk(KERN_ERR "udf: unsupported strategy type: %d\n",
le16_to_cpu(fe->icbTag.strategyType));
- udf_release_data(bh);
+ brelse(bh);
make_bad_inode(inode);
return;
}
udf_fill_inode(inode, bh);
- udf_release_data(bh);
+
+ brelse(bh);
}
static void udf_fill_inode(struct inode *inode, struct buffer_head *bh)
@@ -1331,7 +1469,7 @@ udf_update_inode(struct inode *inode, int do_sync)
use->descTag.tagChecksum += ((uint8_t *)&(use->descTag))[i];
mark_buffer_dirty(bh);
- udf_release_data(bh);
+ brelse(bh);
return err;
}
@@ -1520,7 +1658,7 @@ udf_update_inode(struct inode *inode, int do_sync)
err = -EIO;
}
}
- udf_release_data(bh);
+ brelse(bh);
return err;
}
@@ -1556,8 +1694,8 @@ udf_iget(struct super_block *sb, kernel_lb_addr ino)
return NULL;
}
-int8_t udf_add_aext(struct inode *inode, kernel_lb_addr *bloc, int *extoffset,
- kernel_lb_addr eloc, uint32_t elen, struct buffer_head **bh, int inc)
+int8_t udf_add_aext(struct inode *inode, struct extent_position *epos,
+ kernel_lb_addr eloc, uint32_t elen, int inc)
{
int adsize;
short_ad *sad = NULL;
@@ -1566,10 +1704,10 @@ int8_t udf_add_aext(struct inode *inode, kernel_lb_addr *bloc, int *extoffset,
int8_t etype;
uint8_t *ptr;
- if (!*bh)
- ptr = UDF_I_DATA(inode) + *extoffset - udf_file_entry_alloc_offset(inode) + UDF_I_LENEATTR(inode);
+ if (!epos->bh)
+ ptr = UDF_I_DATA(inode) + epos->offset - udf_file_entry_alloc_offset(inode) + UDF_I_LENEATTR(inode);
else
- ptr = (*bh)->b_data + *extoffset;
+ ptr = epos->bh->b_data + epos->offset;
if (UDF_I_ALLOCTYPE(inode) == ICBTAG_FLAG_AD_SHORT)
adsize = sizeof(short_ad);
@@ -1578,20 +1716,20 @@ int8_t udf_add_aext(struct inode *inode, kernel_lb_addr *bloc, int *extoffset,
else
return -1;
- if (*extoffset + (2 * adsize) > inode->i_sb->s_blocksize)
+ if (epos->offset + (2 * adsize) > inode->i_sb->s_blocksize)
{
char *sptr, *dptr;
struct buffer_head *nbh;
int err, loffset;
- kernel_lb_addr obloc = *bloc;
+ kernel_lb_addr obloc = epos->block;
- if (!(bloc->logicalBlockNum = udf_new_block(inode->i_sb, NULL,
+ if (!(epos->block.logicalBlockNum = udf_new_block(inode->i_sb, NULL,
obloc.partitionReferenceNum, obloc.logicalBlockNum, &err)))
{
return -1;
}
if (!(nbh = udf_tgetblk(inode->i_sb, udf_get_lb_pblock(inode->i_sb,
- *bloc, 0))))
+ epos->block, 0))))
{
return -1;
}
@@ -1604,25 +1742,25 @@ int8_t udf_add_aext(struct inode *inode, kernel_lb_addr *bloc, int *extoffset,
aed = (struct allocExtDesc *)(nbh->b_data);
if (!UDF_QUERY_FLAG(inode->i_sb, UDF_FLAG_STRICT))
aed->previousAllocExtLocation = cpu_to_le32(obloc.logicalBlockNum);
- if (*extoffset + adsize > inode->i_sb->s_blocksize)
+ if (epos->offset + adsize > inode->i_sb->s_blocksize)
{
- loffset = *extoffset;
+ loffset = epos->offset;
aed->lengthAllocDescs = cpu_to_le32(adsize);
sptr = ptr - adsize;
dptr = nbh->b_data + sizeof(struct allocExtDesc);
memcpy(dptr, sptr, adsize);
- *extoffset = sizeof(struct allocExtDesc) + adsize;
+ epos->offset = sizeof(struct allocExtDesc) + adsize;
}
else
{
- loffset = *extoffset + adsize;
+ loffset = epos->offset + adsize;
aed->lengthAllocDescs = cpu_to_le32(0);
sptr = ptr;
- *extoffset = sizeof(struct allocExtDesc);
+ epos->offset = sizeof(struct allocExtDesc);
- if (*bh)
+ if (epos->bh)
{
- aed = (struct allocExtDesc *)(*bh)->b_data;
+ aed = (struct allocExtDesc *)epos->bh->b_data;
aed->lengthAllocDescs =
cpu_to_le32(le32_to_cpu(aed->lengthAllocDescs) + adsize);
}
@@ -1634,10 +1772,10 @@ int8_t udf_add_aext(struct inode *inode, kernel_lb_addr *bloc, int *extoffset,
}
if (UDF_SB_UDFREV(inode->i_sb) >= 0x0200)
udf_new_tag(nbh->b_data, TAG_IDENT_AED, 3, 1,
- bloc->logicalBlockNum, sizeof(tag));
+ epos->block.logicalBlockNum, sizeof(tag));
else
udf_new_tag(nbh->b_data, TAG_IDENT_AED, 2, 1,
- bloc->logicalBlockNum, sizeof(tag));
+ epos->block.logicalBlockNum, sizeof(tag));
switch (UDF_I_ALLOCTYPE(inode))
{
case ICBTAG_FLAG_AD_SHORT:
@@ -1646,7 +1784,7 @@ int8_t udf_add_aext(struct inode *inode, kernel_lb_addr *bloc, int *extoffset,
sad->extLength = cpu_to_le32(
EXT_NEXT_EXTENT_ALLOCDECS |
inode->i_sb->s_blocksize);
- sad->extPosition = cpu_to_le32(bloc->logicalBlockNum);
+ sad->extPosition = cpu_to_le32(epos->block.logicalBlockNum);
break;
}
case ICBTAG_FLAG_AD_LONG:
@@ -1655,60 +1793,57 @@ int8_t udf_add_aext(struct inode *inode, kernel_lb_addr *bloc, int *extoffset,
lad->extLength = cpu_to_le32(
EXT_NEXT_EXTENT_ALLOCDECS |
inode->i_sb->s_blocksize);
- lad->extLocation = cpu_to_lelb(*bloc);
+ lad->extLocation = cpu_to_lelb(epos->block);
memset(lad->impUse, 0x00, sizeof(lad->impUse));
break;
}
}
- if (*bh)
+ if (epos->bh)
{
if (!UDF_QUERY_FLAG(inode->i_sb, UDF_FLAG_STRICT) || UDF_SB_UDFREV(inode->i_sb) >= 0x0201)
- udf_update_tag((*bh)->b_data, loffset);
+ udf_update_tag(epos->bh->b_data, loffset);
else
- udf_update_tag((*bh)->b_data, sizeof(struct allocExtDesc));
- mark_buffer_dirty_inode(*bh, inode);
- udf_release_data(*bh);
+ udf_update_tag(epos->bh->b_data, sizeof(struct allocExtDesc));
+ mark_buffer_dirty_inode(epos->bh, inode);
+ brelse(epos->bh);
}
else
mark_inode_dirty(inode);
- *bh = nbh;
+ epos->bh = nbh;
}
- etype = udf_write_aext(inode, *bloc, extoffset, eloc, elen, *bh, inc);
+ etype = udf_write_aext(inode, epos, eloc, elen, inc);
- if (!*bh)
+ if (!epos->bh)
{
UDF_I_LENALLOC(inode) += adsize;
mark_inode_dirty(inode);
}
else
{
- aed = (struct allocExtDesc *)(*bh)->b_data;
+ aed = (struct allocExtDesc *)epos->bh->b_data;
aed->lengthAllocDescs =
cpu_to_le32(le32_to_cpu(aed->lengthAllocDescs) + adsize);
if (!UDF_QUERY_FLAG(inode->i_sb, UDF_FLAG_STRICT) || UDF_SB_UDFREV(inode->i_sb) >= 0x0201)
- udf_update_tag((*bh)->b_data, *extoffset + (inc ? 0 : adsize));
+ udf_update_tag(epos->bh->b_data, epos->offset + (inc ? 0 : adsize));
else
- udf_update_tag((*bh)->b_data, sizeof(struct allocExtDesc));
- mark_buffer_dirty_inode(*bh, inode);
+ udf_update_tag(epos->bh->b_data, sizeof(struct allocExtDesc));
+ mark_buffer_dirty_inode(epos->bh, inode);
}
return etype;
}
-int8_t udf_write_aext(struct inode *inode, kernel_lb_addr bloc, int *extoffset,
- kernel_lb_addr eloc, uint32_t elen, struct buffer_head *bh, int inc)
+int8_t udf_write_aext(struct inode *inode, struct extent_position *epos,
+ kernel_lb_addr eloc, uint32_t elen, int inc)
{
int adsize;
uint8_t *ptr;
- if (!bh)
- ptr = UDF_I_DATA(inode) + *extoffset - udf_file_entry_alloc_offset(inode) + UDF_I_LENEATTR(inode);
+ if (!epos->bh)
+ ptr = UDF_I_DATA(inode) + epos->offset - udf_file_entry_alloc_offset(inode) + UDF_I_LENEATTR(inode);
else
- {
- ptr = bh->b_data + *extoffset;
- atomic_inc(&bh->b_count);
- }
+ ptr = epos->bh->b_data + epos->offset;
switch (UDF_I_ALLOCTYPE(inode))
{
@@ -1733,40 +1868,39 @@ int8_t udf_write_aext(struct inode *inode, kernel_lb_addr bloc, int *extoffset,
return -1;
}
- if (bh)
+ if (epos->bh)
{
if (!UDF_QUERY_FLAG(inode->i_sb, UDF_FLAG_STRICT) || UDF_SB_UDFREV(inode->i_sb) >= 0x0201)
{
- struct allocExtDesc *aed = (struct allocExtDesc *)(bh)->b_data;
- udf_update_tag((bh)->b_data,
+ struct allocExtDesc *aed = (struct allocExtDesc *)epos->bh->b_data;
+ udf_update_tag(epos->bh->b_data,
le32_to_cpu(aed->lengthAllocDescs) + sizeof(struct allocExtDesc));
}
- mark_buffer_dirty_inode(bh, inode);
- udf_release_data(bh);
+ mark_buffer_dirty_inode(epos->bh, inode);
}
else
mark_inode_dirty(inode);
if (inc)
- *extoffset += adsize;
+ epos->offset += adsize;
return (elen >> 30);
}
-int8_t udf_next_aext(struct inode *inode, kernel_lb_addr *bloc, int *extoffset,
- kernel_lb_addr *eloc, uint32_t *elen, struct buffer_head **bh, int inc)
+int8_t udf_next_aext(struct inode *inode, struct extent_position *epos,
+ kernel_lb_addr *eloc, uint32_t *elen, int inc)
{
int8_t etype;
- while ((etype = udf_current_aext(inode, bloc, extoffset, eloc, elen, bh, inc)) ==
+ while ((etype = udf_current_aext(inode, epos, eloc, elen, inc)) ==
(EXT_NEXT_EXTENT_ALLOCDECS >> 30))
{
- *bloc = *eloc;
- *extoffset = sizeof(struct allocExtDesc);
- udf_release_data(*bh);
- if (!(*bh = udf_tread(inode->i_sb, udf_get_lb_pblock(inode->i_sb, *bloc, 0))))
+ epos->block = *eloc;
+ epos->offset = sizeof(struct allocExtDesc);
+ brelse(epos->bh);
+ if (!(epos->bh = udf_tread(inode->i_sb, udf_get_lb_pblock(inode->i_sb, epos->block, 0))))
{
udf_debug("reading block %d failed!\n",
- udf_get_lb_pblock(inode->i_sb, *bloc, 0));
+ udf_get_lb_pblock(inode->i_sb, epos->block, 0));
return -1;
}
}
@@ -1774,26 +1908,26 @@ int8_t udf_next_aext(struct inode *inode, kernel_lb_addr *bloc, int *extoffset,
return etype;
}
-int8_t udf_current_aext(struct inode *inode, kernel_lb_addr *bloc, int *extoffset,
- kernel_lb_addr *eloc, uint32_t *elen, struct buffer_head **bh, int inc)
+int8_t udf_current_aext(struct inode *inode, struct extent_position *epos,
+ kernel_lb_addr *eloc, uint32_t *elen, int inc)
{
int alen;
int8_t etype;
uint8_t *ptr;
- if (!*bh)
+ if (!epos->bh)
{
- if (!(*extoffset))
- *extoffset = udf_file_entry_alloc_offset(inode);
- ptr = UDF_I_DATA(inode) + *extoffset - udf_file_entry_alloc_offset(inode) + UDF_I_LENEATTR(inode);
+ if (!epos->offset)
+ epos->offset = udf_file_entry_alloc_offset(inode);
+ ptr = UDF_I_DATA(inode) + epos->offset - udf_file_entry_alloc_offset(inode) + UDF_I_LENEATTR(inode);
alen = udf_file_entry_alloc_offset(inode) + UDF_I_LENALLOC(inode);
}
else
{
- if (!(*extoffset))
- *extoffset = sizeof(struct allocExtDesc);
- ptr = (*bh)->b_data + *extoffset;
- alen = sizeof(struct allocExtDesc) + le32_to_cpu(((struct allocExtDesc *)(*bh)->b_data)->lengthAllocDescs);
+ if (!epos->offset)
+ epos->offset = sizeof(struct allocExtDesc);
+ ptr = epos->bh->b_data + epos->offset;
+ alen = sizeof(struct allocExtDesc) + le32_to_cpu(((struct allocExtDesc *)epos->bh->b_data)->lengthAllocDescs);
}
switch (UDF_I_ALLOCTYPE(inode))
@@ -1802,7 +1936,7 @@ int8_t udf_current_aext(struct inode *inode, kernel_lb_addr *bloc, int *extoffse
{
short_ad *sad;
- if (!(sad = udf_get_fileshortad(ptr, alen, extoffset, inc)))
+ if (!(sad = udf_get_fileshortad(ptr, alen, &epos->offset, inc)))
return -1;
etype = le32_to_cpu(sad->extLength) >> 30;
@@ -1815,7 +1949,7 @@ int8_t udf_current_aext(struct inode *inode, kernel_lb_addr *bloc, int *extoffse
{
long_ad *lad;
- if (!(lad = udf_get_filelongad(ptr, alen, extoffset, inc)))
+ if (!(lad = udf_get_filelongad(ptr, alen, &epos->offset, inc)))
return -1;
etype = le32_to_cpu(lad->extLength) >> 30;
@@ -1834,41 +1968,40 @@ int8_t udf_current_aext(struct inode *inode, kernel_lb_addr *bloc, int *extoffse
}
static int8_t
-udf_insert_aext(struct inode *inode, kernel_lb_addr bloc, int extoffset,
- kernel_lb_addr neloc, uint32_t nelen, struct buffer_head *bh)
+udf_insert_aext(struct inode *inode, struct extent_position epos,
+ kernel_lb_addr neloc, uint32_t nelen)
{
kernel_lb_addr oeloc;
uint32_t oelen;
int8_t etype;
- if (bh)
- atomic_inc(&bh->b_count);
+ if (epos.bh)
+ get_bh(epos.bh);
- while ((etype = udf_next_aext(inode, &bloc, &extoffset, &oeloc, &oelen, &bh, 0)) != -1)
+ while ((etype = udf_next_aext(inode, &epos, &oeloc, &oelen, 0)) != -1)
{
- udf_write_aext(inode, bloc, &extoffset, neloc, nelen, bh, 1);
+ udf_write_aext(inode, &epos, neloc, nelen, 1);
neloc = oeloc;
nelen = (etype << 30) | oelen;
}
- udf_add_aext(inode, &bloc, &extoffset, neloc, nelen, &bh, 1);
- udf_release_data(bh);
+ udf_add_aext(inode, &epos, neloc, nelen, 1);
+ brelse(epos.bh);
return (nelen >> 30);
}
-int8_t udf_delete_aext(struct inode *inode, kernel_lb_addr nbloc, int nextoffset,
- kernel_lb_addr eloc, uint32_t elen, struct buffer_head *nbh)
+int8_t udf_delete_aext(struct inode *inode, struct extent_position epos,
+ kernel_lb_addr eloc, uint32_t elen)
{
- struct buffer_head *obh;
- kernel_lb_addr obloc;
- int oextoffset, adsize;
+ struct extent_position oepos;
+ int adsize;
int8_t etype;
struct allocExtDesc *aed;
- if (nbh)
+ if (epos.bh)
{
- atomic_inc(&nbh->b_count);
- atomic_inc(&nbh->b_count);
+ get_bh(epos.bh);
+ get_bh(epos.bh);
}
if (UDF_I_ALLOCTYPE(inode) == ICBTAG_FLAG_AD_SHORT)
@@ -1878,80 +2011,77 @@ int8_t udf_delete_aext(struct inode *inode, kernel_lb_addr nbloc, int nextoffset
else
adsize = 0;
- obh = nbh;
- obloc = nbloc;
- oextoffset = nextoffset;
-
- if (udf_next_aext(inode, &nbloc, &nextoffset, &eloc, &elen, &nbh, 1) == -1)
+ oepos = epos;
+ if (udf_next_aext(inode, &epos, &eloc, &elen, 1) == -1)
return -1;
- while ((etype = udf_next_aext(inode, &nbloc, &nextoffset, &eloc, &elen, &nbh, 1)) != -1)
+ while ((etype = udf_next_aext(inode, &epos, &eloc, &elen, 1)) != -1)
{
- udf_write_aext(inode, obloc, &oextoffset, eloc, (etype << 30) | elen, obh, 1);
- if (obh != nbh)
+ udf_write_aext(inode, &oepos, eloc, (etype << 30) | elen, 1);
+ if (oepos.bh != epos.bh)
{
- obloc = nbloc;
- udf_release_data(obh);
- atomic_inc(&nbh->b_count);
- obh = nbh;
- oextoffset = nextoffset - adsize;
+ oepos.block = epos.block;
+ brelse(oepos.bh);
+ get_bh(epos.bh);
+ oepos.bh = epos.bh;
+ oepos.offset = epos.offset - adsize;
}
}
memset(&eloc, 0x00, sizeof(kernel_lb_addr));
elen = 0;
- if (nbh != obh)
+ if (epos.bh != oepos.bh)
{
- udf_free_blocks(inode->i_sb, inode, nbloc, 0, 1);
- udf_write_aext(inode, obloc, &oextoffset, eloc, elen, obh, 1);
- udf_write_aext(inode, obloc, &oextoffset, eloc, elen, obh, 1);
- if (!obh)
+ udf_free_blocks(inode->i_sb, inode, epos.block, 0, 1);
+ udf_write_aext(inode, &oepos, eloc, elen, 1);
+ udf_write_aext(inode, &oepos, eloc, elen, 1);
+ if (!oepos.bh)
{
UDF_I_LENALLOC(inode) -= (adsize * 2);
mark_inode_dirty(inode);
}
else
{
- aed = (struct allocExtDesc *)(obh)->b_data;
+ aed = (struct allocExtDesc *)oepos.bh->b_data;
aed->lengthAllocDescs =
cpu_to_le32(le32_to_cpu(aed->lengthAllocDescs) - (2*adsize));
if (!UDF_QUERY_FLAG(inode->i_sb, UDF_FLAG_STRICT) || UDF_SB_UDFREV(inode->i_sb) >= 0x0201)
- udf_update_tag((obh)->b_data, oextoffset - (2*adsize));
+ udf_update_tag(oepos.bh->b_data, oepos.offset - (2*adsize));
else
- udf_update_tag((obh)->b_data, sizeof(struct allocExtDesc));
- mark_buffer_dirty_inode(obh, inode);
+ udf_update_tag(oepos.bh->b_data, sizeof(struct allocExtDesc));
+ mark_buffer_dirty_inode(oepos.bh, inode);
}
}
else
{
- udf_write_aext(inode, obloc, &oextoffset, eloc, elen, obh, 1);
- if (!obh)
+ udf_write_aext(inode, &oepos, eloc, elen, 1);
+ if (!oepos.bh)
{
UDF_I_LENALLOC(inode) -= adsize;
mark_inode_dirty(inode);
}
else
{
- aed = (struct allocExtDesc *)(obh)->b_data;
+ aed = (struct allocExtDesc *)oepos.bh->b_data;
aed->lengthAllocDescs =
cpu_to_le32(le32_to_cpu(aed->lengthAllocDescs) - adsize);
if (!UDF_QUERY_FLAG(inode->i_sb, UDF_FLAG_STRICT) || UDF_SB_UDFREV(inode->i_sb) >= 0x0201)
- udf_update_tag((obh)->b_data, oextoffset - adsize);
+ udf_update_tag(oepos.bh->b_data, epos.offset - adsize);
else
- udf_update_tag((obh)->b_data, sizeof(struct allocExtDesc));
- mark_buffer_dirty_inode(obh, inode);
+ udf_update_tag(oepos.bh->b_data, sizeof(struct allocExtDesc));
+ mark_buffer_dirty_inode(oepos.bh, inode);
}
}
- udf_release_data(nbh);
- udf_release_data(obh);
+ brelse(epos.bh);
+ brelse(oepos.bh);
return (elen >> 30);
}
-int8_t inode_bmap(struct inode *inode, int block, kernel_lb_addr *bloc, uint32_t *extoffset,
- kernel_lb_addr *eloc, uint32_t *elen, uint32_t *offset, struct buffer_head **bh)
+int8_t inode_bmap(struct inode *inode, sector_t block, struct extent_position *pos,
+ kernel_lb_addr *eloc, uint32_t *elen, sector_t *offset)
{
- uint64_t lbcount = 0, bcount = (uint64_t)block << inode->i_sb->s_blocksize_bits;
+ loff_t lbcount = 0, bcount = (loff_t)block << inode->i_sb->s_blocksize_bits;
int8_t etype;
if (block < 0)
@@ -1960,42 +2090,44 @@ int8_t inode_bmap(struct inode *inode, int block, kernel_lb_addr *bloc, uint32_t
return -1;
}
- *extoffset = 0;
+ pos->offset = 0;
+ pos->block = UDF_I_LOCATION(inode);
+ pos->bh = NULL;
*elen = 0;
- *bloc = UDF_I_LOCATION(inode);
do
{
- if ((etype = udf_next_aext(inode, bloc, extoffset, eloc, elen, bh, 1)) == -1)
+ if ((etype = udf_next_aext(inode, pos, eloc, elen, 1)) == -1)
{
- *offset = bcount - lbcount;
+ *offset = (bcount - lbcount) >> inode->i_sb->s_blocksize_bits;
UDF_I_LENEXTENTS(inode) = lbcount;
return -1;
}
lbcount += *elen;
} while (lbcount <= bcount);
- *offset = bcount + *elen - lbcount;
+ *offset = (bcount + *elen - lbcount) >> inode->i_sb->s_blocksize_bits;
return etype;
}
-long udf_block_map(struct inode *inode, long block)
+long udf_block_map(struct inode *inode, sector_t block)
{
- kernel_lb_addr eloc, bloc;
- uint32_t offset, extoffset, elen;
- struct buffer_head *bh = NULL;
+ kernel_lb_addr eloc;
+ uint32_t elen;
+ sector_t offset;
+ struct extent_position epos = { NULL, 0, { 0, 0}};
int ret;
lock_kernel();
- if (inode_bmap(inode, block, &bloc, &extoffset, &eloc, &elen, &offset, &bh) == (EXT_RECORDED_ALLOCATED >> 30))
- ret = udf_get_lb_pblock(inode->i_sb, eloc, offset >> inode->i_sb->s_blocksize_bits);
+ if (inode_bmap(inode, block, &epos, &eloc, &elen, &offset) == (EXT_RECORDED_ALLOCATED >> 30))
+ ret = udf_get_lb_pblock(inode->i_sb, eloc, offset);
else
ret = 0;
unlock_kernel();
- udf_release_data(bh);
+ brelse(epos.bh);
if (UDF_QUERY_FLAG(inode->i_sb, UDF_FLAG_VARCONV))
return udf_fixed_to_variable(ret);
diff --git a/fs/udf/misc.c b/fs/udf/misc.c
index cc8ca3254db..a2b2a98ce78 100644
--- a/fs/udf/misc.c
+++ b/fs/udf/misc.c
@@ -274,12 +274,6 @@ udf_read_ptagged(struct super_block *sb, kernel_lb_addr loc, uint32_t offset, ui
loc.logicalBlockNum + offset, ident);
}
-void udf_release_data(struct buffer_head *bh)
-{
- if (bh)
- brelse(bh);
-}
-
void udf_update_tag(char *data, int length)
{
tag *tptr = (tag *)data;
diff --git a/fs/udf/namei.c b/fs/udf/namei.c
index fe361cd19a9..51fe307dc0e 100644
--- a/fs/udf/namei.c
+++ b/fs/udf/namei.c
@@ -30,6 +30,7 @@
#include <linux/quotaops.h>
#include <linux/smp_lock.h>
#include <linux/buffer_head.h>
+#include <linux/sched.h>
static inline int udf_match(int len1, const char *name1, int len2, const char *name2)
{
@@ -155,9 +156,10 @@ udf_find_entry(struct inode *dir, struct dentry *dentry,
uint8_t lfi;
uint16_t liu;
loff_t size;
- kernel_lb_addr bloc, eloc;
- uint32_t extoffset, elen, offset;
- struct buffer_head *bh = NULL;
+ kernel_lb_addr eloc;
+ uint32_t elen;
+ sector_t offset;
+ struct extent_position epos = { NULL, 0, { 0, 0}};
size = (udf_ext0_offset(dir) + dir->i_size) >> 2;
f_pos = (udf_ext0_offset(dir) >> 2);
@@ -166,42 +168,41 @@ udf_find_entry(struct inode *dir, struct dentry *dentry,
if (UDF_I_ALLOCTYPE(dir) == ICBTAG_FLAG_AD_IN_ICB)
fibh->sbh = fibh->ebh = NULL;
else if (inode_bmap(dir, f_pos >> (dir->i_sb->s_blocksize_bits - 2),
- &bloc, &extoffset, &eloc, &elen, &offset, &bh) == (EXT_RECORDED_ALLOCATED >> 30))
+ &epos, &eloc, &elen, &offset) == (EXT_RECORDED_ALLOCATED >> 30))
{
- offset >>= dir->i_sb->s_blocksize_bits;
block = udf_get_lb_pblock(dir->i_sb, eloc, offset);
if ((++offset << dir->i_sb->s_blocksize_bits) < elen)
{
if (UDF_I_ALLOCTYPE(dir) == ICBTAG_FLAG_AD_SHORT)
- extoffset -= sizeof(short_ad);
+ epos.offset -= sizeof(short_ad);
else if (UDF_I_ALLOCTYPE(dir) == ICBTAG_FLAG_AD_LONG)
- extoffset -= sizeof(long_ad);
+ epos.offset -= sizeof(long_ad);
}
else
offset = 0;
if (!(fibh->sbh = fibh->ebh = udf_tread(dir->i_sb, block)))
{
- udf_release_data(bh);
+ brelse(epos.bh);
return NULL;
}
}
else
{
- udf_release_data(bh);
+ brelse(epos.bh);
return NULL;
}
while ( (f_pos < size) )
{
- fi = udf_fileident_read(dir, &f_pos, fibh, cfi, &bloc, &extoffset, &eloc, &elen, &offset, &bh);
+ fi = udf_fileident_read(dir, &f_pos, fibh, cfi, &epos, &eloc, &elen, &offset);
if (!fi)
{
if (fibh->sbh != fibh->ebh)
- udf_release_data(fibh->ebh);
- udf_release_data(fibh->sbh);
- udf_release_data(bh);
+ brelse(fibh->ebh);
+ brelse(fibh->sbh);
+ brelse(epos.bh);
return NULL;
}
@@ -247,15 +248,15 @@ udf_find_entry(struct inode *dir, struct dentry *dentry,
{
if (udf_match(flen, fname, dentry->d_name.len, dentry->d_name.name))
{
- udf_release_data(bh);
+ brelse(epos.bh);
return fi;
}
}
}
if (fibh->sbh != fibh->ebh)
- udf_release_data(fibh->ebh);
- udf_release_data(fibh->sbh);
- udf_release_data(bh);
+ brelse(fibh->ebh);
+ brelse(fibh->sbh);
+ brelse(epos.bh);
return NULL;
}
@@ -321,8 +322,8 @@ udf_lookup(struct inode *dir, struct dentry *dentry, struct nameidata *nd)
if (udf_find_entry(dir, dentry, &fibh, &cfi))
{
if (fibh.sbh != fibh.ebh)
- udf_release_data(fibh.ebh);
- udf_release_data(fibh.sbh);
+ brelse(fibh.ebh);
+ brelse(fibh.sbh);
inode = udf_iget(dir->i_sb, lelb_to_cpu(cfi.icb.extLocation));
if ( !inode )
@@ -353,9 +354,10 @@ udf_add_entry(struct inode *dir, struct dentry *dentry,
uint8_t lfi;
uint16_t liu;
int block;
- kernel_lb_addr bloc, eloc;
- uint32_t extoffset, elen, offset;
- struct buffer_head *bh = NULL;
+ kernel_lb_addr eloc;
+ uint32_t elen;
+ sector_t offset;
+ struct extent_position epos = { NULL, 0, { 0, 0 }};
sb = dir->i_sb;
@@ -384,23 +386,22 @@ udf_add_entry(struct inode *dir, struct dentry *dentry,
if (UDF_I_ALLOCTYPE(dir) == ICBTAG_FLAG_AD_IN_ICB)
fibh->sbh = fibh->ebh = NULL;
else if (inode_bmap(dir, f_pos >> (dir->i_sb->s_blocksize_bits - 2),
- &bloc, &extoffset, &eloc, &elen, &offset, &bh) == (EXT_RECORDED_ALLOCATED >> 30))
+ &epos, &eloc, &elen, &offset) == (EXT_RECORDED_ALLOCATED >> 30))
{
- offset >>= dir->i_sb->s_blocksize_bits;
block = udf_get_lb_pblock(dir->i_sb, eloc, offset);
if ((++offset << dir->i_sb->s_blocksize_bits) < elen)
{
if (UDF_I_ALLOCTYPE(dir) == ICBTAG_FLAG_AD_SHORT)
- extoffset -= sizeof(short_ad);
+ epos.offset -= sizeof(short_ad);
else if (UDF_I_ALLOCTYPE(dir) == ICBTAG_FLAG_AD_LONG)
- extoffset -= sizeof(long_ad);
+ epos.offset -= sizeof(long_ad);
}
else
offset = 0;
if (!(fibh->sbh = fibh->ebh = udf_tread(dir->i_sb, block)))
{
- udf_release_data(bh);
+ brelse(epos.bh);
*err = -EIO;
return NULL;
}
@@ -418,14 +419,14 @@ udf_add_entry(struct inode *dir, struct dentry *dentry,
while ( (f_pos < size) )
{
- fi = udf_fileident_read(dir, &f_pos, fibh, cfi, &bloc, &extoffset, &eloc, &elen, &offset, &bh);
+ fi = udf_fileident_read(dir, &f_pos, fibh, cfi, &epos, &eloc, &elen, &offset);
if (!fi)
{
if (fibh->sbh != fibh->ebh)
- udf_release_data(fibh->ebh);
- udf_release_data(fibh->sbh);
- udf_release_data(bh);
+ brelse(fibh->ebh);
+ brelse(fibh->sbh);
+ brelse(epos.bh);
*err = -EIO;
return NULL;
}
@@ -455,7 +456,7 @@ udf_add_entry(struct inode *dir, struct dentry *dentry,
{
if (((sizeof(struct fileIdentDesc) + liu + lfi + 3) & ~3) == nfidlen)
{
- udf_release_data(bh);
+ brelse(epos.bh);
cfi->descTag.tagSerialNum = cpu_to_le16(1);
cfi->fileVersionNum = cpu_to_le16(1);
cfi->fileCharacteristics = 0;
@@ -478,9 +479,9 @@ udf_add_entry(struct inode *dir, struct dentry *dentry,
udf_match(flen, fname, dentry->d_name.len, dentry->d_name.name))
{
if (fibh->sbh != fibh->ebh)
- udf_release_data(fibh->ebh);
- udf_release_data(fibh->sbh);
- udf_release_data(bh);
+ brelse(fibh->ebh);
+ brelse(fibh->sbh);
+ brelse(epos.bh);
*err = -EEXIST;
return NULL;
}
@@ -492,25 +493,25 @@ add:
if (UDF_I_ALLOCTYPE(dir) == ICBTAG_FLAG_AD_IN_ICB &&
sb->s_blocksize - fibh->eoffset < nfidlen)
{
- udf_release_data(bh);
- bh = NULL;
+ brelse(epos.bh);
+ epos.bh = NULL;
fibh->soffset -= udf_ext0_offset(dir);
fibh->eoffset -= udf_ext0_offset(dir);
f_pos -= (udf_ext0_offset(dir) >> 2);
if (fibh->sbh != fibh->ebh)
- udf_release_data(fibh->ebh);
- udf_release_data(fibh->sbh);
+ brelse(fibh->ebh);
+ brelse(fibh->sbh);
if (!(fibh->sbh = fibh->ebh = udf_expand_dir_adinicb(dir, &block, err)))
return NULL;
- bloc = UDF_I_LOCATION(dir);
+ epos.block = UDF_I_LOCATION(dir);
eloc.logicalBlockNum = block;
eloc.partitionReferenceNum = UDF_I_LOCATION(dir).partitionReferenceNum;
elen = dir->i_sb->s_blocksize;
- extoffset = udf_file_entry_alloc_offset(dir);
+ epos.offset = udf_file_entry_alloc_offset(dir);
if (UDF_I_ALLOCTYPE(dir) == ICBTAG_FLAG_AD_SHORT)
- extoffset += sizeof(short_ad);
+ epos.offset += sizeof(short_ad);
else if (UDF_I_ALLOCTYPE(dir) == ICBTAG_FLAG_AD_LONG)
- extoffset += sizeof(long_ad);
+ epos.offset += sizeof(long_ad);
}
if (sb->s_blocksize - fibh->eoffset >= nfidlen)
@@ -519,7 +520,7 @@ add:
fibh->eoffset += nfidlen;
if (fibh->sbh != fibh->ebh)
{
- udf_release_data(fibh->sbh);
+ brelse(fibh->sbh);
fibh->sbh = fibh->ebh;
}
@@ -541,7 +542,7 @@ add:
fibh->eoffset += nfidlen - sb->s_blocksize;
if (fibh->sbh != fibh->ebh)
{
- udf_release_data(fibh->sbh);
+ brelse(fibh->sbh);
fibh->sbh = fibh->ebh;
}
@@ -550,14 +551,14 @@ add:
if (!(fibh->ebh = udf_bread(dir, f_pos >> (dir->i_sb->s_blocksize_bits - 2), 1, err)))
{
- udf_release_data(bh);
- udf_release_data(fibh->sbh);
+ brelse(epos.bh);
+ brelse(fibh->sbh);
return NULL;
}
if (!(fibh->soffset))
{
- if (udf_next_aext(dir, &bloc, &extoffset, &eloc, &elen, &bh, 1) ==
+ if (udf_next_aext(dir, &epos, &eloc, &elen, 1) ==
(EXT_RECORDED_ALLOCATED >> 30))
{
block = eloc.logicalBlockNum + ((elen - 1) >>
@@ -566,7 +567,7 @@ add:
else
block ++;
- udf_release_data(fibh->sbh);
+ brelse(fibh->sbh);
fibh->sbh = fibh->ebh;
fi = (struct fileIdentDesc *)(fibh->sbh->b_data);
}
@@ -587,7 +588,7 @@ add:
cfi->lengthOfImpUse = cpu_to_le16(0);
if (!udf_write_fi(dir, cfi, fi, fibh, NULL, name))
{
- udf_release_data(bh);
+ brelse(epos.bh);
dir->i_size += nfidlen;
if (UDF_I_ALLOCTYPE(dir) == ICBTAG_FLAG_AD_IN_ICB)
UDF_I_LENALLOC(dir) += nfidlen;
@@ -596,10 +597,10 @@ add:
}
else
{
- udf_release_data(bh);
+ brelse(epos.bh);
if (fibh->sbh != fibh->ebh)
- udf_release_data(fibh->ebh);
- udf_release_data(fibh->sbh);
+ brelse(fibh->ebh);
+ brelse(fibh->sbh);
*err = -EIO;
return NULL;
}
@@ -656,8 +657,8 @@ static int udf_create(struct inode *dir, struct dentry *dentry, int mode, struct
mark_inode_dirty(dir);
}
if (fibh.sbh != fibh.ebh)
- udf_release_data(fibh.ebh);
- udf_release_data(fibh.sbh);
+ brelse(fibh.ebh);
+ brelse(fibh.sbh);
unlock_kernel();
d_instantiate(dentry, inode);
return 0;
@@ -701,8 +702,8 @@ static int udf_mknod(struct inode * dir, struct dentry * dentry, int mode, dev_t
mark_inode_dirty(inode);
if (fibh.sbh != fibh.ebh)
- udf_release_data(fibh.ebh);
- udf_release_data(fibh.sbh);
+ brelse(fibh.ebh);
+ brelse(fibh.sbh);
d_instantiate(dentry, inode);
err = 0;
out:
@@ -743,7 +744,7 @@ static int udf_mkdir(struct inode * dir, struct dentry * dentry, int mode)
cpu_to_le32(UDF_I_UNIQUE(dir) & 0x00000000FFFFFFFFUL);
cfi.fileCharacteristics = FID_FILE_CHAR_DIRECTORY | FID_FILE_CHAR_PARENT;
udf_write_fi(inode, &cfi, fi, &fibh, NULL, NULL);
- udf_release_data(fibh.sbh);
+ brelse(fibh.sbh);
inode->i_mode = S_IFDIR | mode;
if (dir->i_mode & S_ISGID)
inode->i_mode |= S_ISGID;
@@ -766,8 +767,8 @@ static int udf_mkdir(struct inode * dir, struct dentry * dentry, int mode)
mark_inode_dirty(dir);
d_instantiate(dentry, inode);
if (fibh.sbh != fibh.ebh)
- udf_release_data(fibh.ebh);
- udf_release_data(fibh.sbh);
+ brelse(fibh.ebh);
+ brelse(fibh.sbh);
err = 0;
out:
unlock_kernel();
@@ -781,9 +782,10 @@ static int empty_dir(struct inode *dir)
loff_t f_pos;
loff_t size = (udf_ext0_offset(dir) + dir->i_size) >> 2;
int block;
- kernel_lb_addr bloc, eloc;
- uint32_t extoffset, elen, offset;
- struct buffer_head *bh = NULL;
+ kernel_lb_addr eloc;
+ uint32_t elen;
+ sector_t offset;
+ struct extent_position epos = { NULL, 0, { 0, 0}};
f_pos = (udf_ext0_offset(dir) >> 2);
@@ -792,59 +794,58 @@ static int empty_dir(struct inode *dir)
if (UDF_I_ALLOCTYPE(dir) == ICBTAG_FLAG_AD_IN_ICB)
fibh.sbh = fibh.ebh = NULL;
else if (inode_bmap(dir, f_pos >> (dir->i_sb->s_blocksize_bits - 2),
- &bloc, &extoffset, &eloc, &elen, &offset, &bh) == (EXT_RECORDED_ALLOCATED >> 30))
+ &epos, &eloc, &elen, &offset) == (EXT_RECORDED_ALLOCATED >> 30))
{
- offset >>= dir->i_sb->s_blocksize_bits;
block = udf_get_lb_pblock(dir->i_sb, eloc, offset);
if ((++offset << dir->i_sb->s_blocksize_bits) < elen)
{
if (UDF_I_ALLOCTYPE(dir) == ICBTAG_FLAG_AD_SHORT)
- extoffset -= sizeof(short_ad);
+ epos.offset -= sizeof(short_ad);
else if (UDF_I_ALLOCTYPE(dir) == ICBTAG_FLAG_AD_LONG)
- extoffset -= sizeof(long_ad);
+ epos.offset -= sizeof(long_ad);
}
else
offset = 0;
if (!(fibh.sbh = fibh.ebh = udf_tread(dir->i_sb, block)))
{
- udf_release_data(bh);
+ brelse(epos.bh);
return 0;
}
}
else
{
- udf_release_data(bh);
+ brelse(epos.bh);
return 0;
}
while ( (f_pos < size) )
{
- fi = udf_fileident_read(dir, &f_pos, &fibh, &cfi, &bloc, &extoffset, &eloc, &elen, &offset, &bh);
+ fi = udf_fileident_read(dir, &f_pos, &fibh, &cfi, &epos, &eloc, &elen, &offset);
if (!fi)
{
if (fibh.sbh != fibh.ebh)
- udf_release_data(fibh.ebh);
- udf_release_data(fibh.sbh);
- udf_release_data(bh);
+ brelse(fibh.ebh);
+ brelse(fibh.sbh);
+ brelse(epos.bh);
return 0;
}
if (cfi.lengthFileIdent && (cfi.fileCharacteristics & FID_FILE_CHAR_DELETED) == 0)
{
if (fibh.sbh != fibh.ebh)
- udf_release_data(fibh.ebh);
- udf_release_data(fibh.sbh);
- udf_release_data(bh);
+ brelse(fibh.ebh);
+ brelse(fibh.sbh);
+ brelse(epos.bh);
return 0;
}
}
if (fibh.sbh != fibh.ebh)
- udf_release_data(fibh.ebh);
- udf_release_data(fibh.sbh);
- udf_release_data(bh);
+ brelse(fibh.ebh);
+ brelse(fibh.sbh);
+ brelse(epos.bh);
return 1;
}
@@ -878,14 +879,14 @@ static int udf_rmdir(struct inode * dir, struct dentry * dentry)
inode->i_nlink);
clear_nlink(inode);
inode->i_size = 0;
- inode_dec_link_count(inode);
+ inode_dec_link_count(dir);
inode->i_ctime = dir->i_ctime = dir->i_mtime = current_fs_time(dir->i_sb);
mark_inode_dirty(dir);
end_rmdir:
if (fibh.sbh != fibh.ebh)
- udf_release_data(fibh.ebh);
- udf_release_data(fibh.sbh);
+ brelse(fibh.ebh);
+ brelse(fibh.sbh);
out:
unlock_kernel();
return retval;
@@ -928,8 +929,8 @@ static int udf_unlink(struct inode * dir, struct dentry * dentry)
end_unlink:
if (fibh.sbh != fibh.ebh)
- udf_release_data(fibh.ebh);
- udf_release_data(fibh.sbh);
+ brelse(fibh.ebh);
+ brelse(fibh.sbh);
out:
unlock_kernel();
return retval;
@@ -941,7 +942,7 @@ static int udf_symlink(struct inode * dir, struct dentry * dentry, const char *
struct pathComponent *pc;
char *compstart;
struct udf_fileident_bh fibh;
- struct buffer_head *bh = NULL;
+ struct extent_position epos = { NULL, 0, {0, 0}};
int eoffset, elen = 0;
struct fileIdentDesc *fi;
struct fileIdentDesc cfi;
@@ -961,33 +962,33 @@ static int udf_symlink(struct inode * dir, struct dentry * dentry, const char *
if (UDF_I_ALLOCTYPE(inode) != ICBTAG_FLAG_AD_IN_ICB)
{
- struct buffer_head *bh = NULL;
- kernel_lb_addr bloc, eloc;
- uint32_t elen, extoffset;
+ kernel_lb_addr eloc;
+ uint32_t elen;
block = udf_new_block(inode->i_sb, inode,
UDF_I_LOCATION(inode).partitionReferenceNum,
UDF_I_LOCATION(inode).logicalBlockNum, &err);
if (!block)
goto out_no_entry;
- bloc = UDF_I_LOCATION(inode);
+ epos.block = UDF_I_LOCATION(inode);
+ epos.offset = udf_file_entry_alloc_offset(inode);
+ epos.bh = NULL;
eloc.logicalBlockNum = block;
eloc.partitionReferenceNum = UDF_I_LOCATION(inode).partitionReferenceNum;
elen = inode->i_sb->s_blocksize;
UDF_I_LENEXTENTS(inode) = elen;
- extoffset = udf_file_entry_alloc_offset(inode);
- udf_add_aext(inode, &bloc, &extoffset, eloc, elen, &bh, 0);
- udf_release_data(bh);
+ udf_add_aext(inode, &epos, eloc, elen, 0);
+ brelse(epos.bh);
block = udf_get_pblock(inode->i_sb, block,
UDF_I_LOCATION(inode).partitionReferenceNum, 0);
- bh = udf_tread(inode->i_sb, block);
- lock_buffer(bh);
- memset(bh->b_data, 0x00, inode->i_sb->s_blocksize);
- set_buffer_uptodate(bh);
- unlock_buffer(bh);
- mark_buffer_dirty_inode(bh, inode);
- ea = bh->b_data + udf_ext0_offset(inode);
+ epos.bh = udf_tread(inode->i_sb, block);
+ lock_buffer(epos.bh);
+ memset(epos.bh->b_data, 0x00, inode->i_sb->s_blocksize);
+ set_buffer_uptodate(epos.bh);
+ unlock_buffer(epos.bh);
+ mark_buffer_dirty_inode(epos.bh, inode);
+ ea = epos.bh->b_data + udf_ext0_offset(inode);
}
else
ea = UDF_I_DATA(inode) + UDF_I_LENEATTR(inode);
@@ -1060,7 +1061,7 @@ static int udf_symlink(struct inode * dir, struct dentry * dentry, const char *
}
}
- udf_release_data(bh);
+ brelse(epos.bh);
inode->i_size = elen;
if (UDF_I_ALLOCTYPE(inode) == ICBTAG_FLAG_AD_IN_ICB)
UDF_I_LENALLOC(inode) = inode->i_size;
@@ -1089,8 +1090,8 @@ static int udf_symlink(struct inode * dir, struct dentry * dentry, const char *
mark_inode_dirty(dir);
}
if (fibh.sbh != fibh.ebh)
- udf_release_data(fibh.ebh);
- udf_release_data(fibh.sbh);
+ brelse(fibh.ebh);
+ brelse(fibh.sbh);
d_instantiate(dentry, inode);
err = 0;
@@ -1145,8 +1146,8 @@ static int udf_link(struct dentry * old_dentry, struct inode * dir,
mark_inode_dirty(dir);
}
if (fibh.sbh != fibh.ebh)
- udf_release_data(fibh.ebh);
- udf_release_data(fibh.sbh);
+ brelse(fibh.ebh);
+ brelse(fibh.sbh);
inc_nlink(inode);
inode->i_ctime = current_fs_time(inode->i_sb);
mark_inode_dirty(inode);
@@ -1174,8 +1175,8 @@ static int udf_rename (struct inode * old_dir, struct dentry * old_dentry,
if ((ofi = udf_find_entry(old_dir, old_dentry, &ofibh, &ocfi)))
{
if (ofibh.sbh != ofibh.ebh)
- udf_release_data(ofibh.ebh);
- udf_release_data(ofibh.sbh);
+ brelse(ofibh.ebh);
+ brelse(ofibh.sbh);
}
tloc = lelb_to_cpu(ocfi.icb.extLocation);
if (!ofi || udf_get_lb_pblock(old_dir->i_sb, tloc, 0)
@@ -1188,8 +1189,8 @@ static int udf_rename (struct inode * old_dir, struct dentry * old_dentry,
if (!new_inode)
{
if (nfibh.sbh != nfibh.ebh)
- udf_release_data(nfibh.ebh);
- udf_release_data(nfibh.sbh);
+ brelse(nfibh.ebh);
+ brelse(nfibh.sbh);
nfi = NULL;
}
}
@@ -1290,19 +1291,19 @@ static int udf_rename (struct inode * old_dir, struct dentry * old_dentry,
if (ofi)
{
if (ofibh.sbh != ofibh.ebh)
- udf_release_data(ofibh.ebh);
- udf_release_data(ofibh.sbh);
+ brelse(ofibh.ebh);
+ brelse(ofibh.sbh);
}
retval = 0;
end_rename:
- udf_release_data(dir_bh);
+ brelse(dir_bh);
if (nfi)
{
if (nfibh.sbh != nfibh.ebh)
- udf_release_data(nfibh.ebh);
- udf_release_data(nfibh.sbh);
+ brelse(nfibh.ebh);
+ brelse(nfibh.sbh);
}
unlock_kernel();
return retval;
diff --git a/fs/udf/partition.c b/fs/udf/partition.c
index dabf2b841db..467a26171cd 100644
--- a/fs/udf/partition.c
+++ b/fs/udf/partition.c
@@ -81,7 +81,7 @@ uint32_t udf_get_pblock_virt15(struct super_block *sb, uint32_t block, uint16_t
loc = le32_to_cpu(((__le32 *)bh->b_data)[index]);
- udf_release_data(bh);
+ brelse(bh);
if (UDF_I_LOCATION(UDF_SB_VAT(sb)).partitionReferenceNum == partition)
{
diff --git a/fs/udf/super.c b/fs/udf/super.c
index 023b304fdd9..6658afb41cc 100644
--- a/fs/udf/super.c
+++ b/fs/udf/super.c
@@ -134,10 +134,8 @@ static void init_once(void * foo, struct kmem_cache * cachep, unsigned long flag
{
struct udf_inode_info *ei = (struct udf_inode_info *) foo;
- if (flags & SLAB_CTOR_CONSTRUCTOR) {
- ei->i_ext.i_data = NULL;
- inode_init_once(&ei->vfs_inode);
- }
+ ei->i_ext.i_data = NULL;
+ inode_init_once(&ei->vfs_inode);
}
static int init_inodecache(void)
@@ -563,7 +561,7 @@ udf_vrs(struct super_block *sb, int silent)
if (vsd->stdIdent[0] == 0)
{
- udf_release_data(bh);
+ brelse(bh);
break;
}
else if (!strncmp(vsd->stdIdent, VSD_STD_ID_CD001, VSD_STD_ID_LEN))
@@ -596,7 +594,7 @@ udf_vrs(struct super_block *sb, int silent)
}
else if (!strncmp(vsd->stdIdent, VSD_STD_ID_TEA01, VSD_STD_ID_LEN))
{
- udf_release_data(bh);
+ brelse(bh);
break;
}
else if (!strncmp(vsd->stdIdent, VSD_STD_ID_NSR02, VSD_STD_ID_LEN))
@@ -607,7 +605,7 @@ udf_vrs(struct super_block *sb, int silent)
{
nsr03 = sector;
}
- udf_release_data(bh);
+ brelse(bh);
}
if (nsr03)
@@ -673,7 +671,7 @@ udf_find_anchor(struct super_block *sb)
{
ident = le16_to_cpu(((tag *)bh->b_data)->tagIdent);
location = le32_to_cpu(((tag *)bh->b_data)->tagLocation);
- udf_release_data(bh);
+ brelse(bh);
}
if (ident == TAG_IDENT_AVDP)
@@ -708,7 +706,7 @@ udf_find_anchor(struct super_block *sb)
{
ident = le16_to_cpu(((tag *)bh->b_data)->tagIdent);
location = le32_to_cpu(((tag *)bh->b_data)->tagLocation);
- udf_release_data(bh);
+ brelse(bh);
}
if (ident == TAG_IDENT_AVDP &&
@@ -727,7 +725,7 @@ udf_find_anchor(struct super_block *sb)
{
ident = le16_to_cpu(((tag *)bh->b_data)->tagIdent);
location = le32_to_cpu(((tag *)bh->b_data)->tagLocation);
- udf_release_data(bh);
+ brelse(bh);
}
if (ident == TAG_IDENT_AVDP &&
@@ -749,7 +747,7 @@ udf_find_anchor(struct super_block *sb)
{
ident = le16_to_cpu(((tag *)bh->b_data)->tagIdent);
location = le32_to_cpu(((tag *)bh->b_data)->tagLocation);
- udf_release_data(bh);
+ brelse(bh);
if (ident == TAG_IDENT_AVDP && location == 256)
UDF_SET_FLAG(sb, UDF_FLAG_VARCONV);
@@ -766,7 +764,7 @@ udf_find_anchor(struct super_block *sb)
}
else
{
- udf_release_data(bh);
+ brelse(bh);
if ((ident != TAG_IDENT_AVDP) && (i ||
(ident != TAG_IDENT_FE && ident != TAG_IDENT_EFE)))
{
@@ -795,7 +793,7 @@ udf_find_fileset(struct super_block *sb, kernel_lb_addr *fileset, kernel_lb_addr
return 1;
else if (ident != TAG_IDENT_FSD)
{
- udf_release_data(bh);
+ brelse(bh);
return 1;
}
@@ -834,7 +832,7 @@ udf_find_fileset(struct super_block *sb, kernel_lb_addr *fileset, kernel_lb_addr
newfileset.logicalBlockNum += 1 +
((le32_to_cpu(sp->numOfBytes) + sizeof(struct spaceBitmapDesc) - 1)
>> sb->s_blocksize_bits);
- udf_release_data(bh);
+ brelse(bh);
break;
}
case TAG_IDENT_FSD:
@@ -845,7 +843,7 @@ udf_find_fileset(struct super_block *sb, kernel_lb_addr *fileset, kernel_lb_addr
default:
{
newfileset.logicalBlockNum ++;
- udf_release_data(bh);
+ brelse(bh);
bh = NULL;
break;
}
@@ -865,7 +863,7 @@ udf_find_fileset(struct super_block *sb, kernel_lb_addr *fileset, kernel_lb_addr
UDF_SB_PARTITION(sb) = fileset->partitionReferenceNum;
udf_load_fileset(sb, bh, root);
- udf_release_data(bh);
+ brelse(bh);
return 0;
}
return 1;
@@ -1083,7 +1081,7 @@ udf_load_logicalvol(struct super_block *sb, struct buffer_head * bh, kernel_lb_a
if (ident != 0 ||
strncmp(st->sparingIdent.ident, UDF_ID_SPARING, strlen(UDF_ID_SPARING)))
{
- udf_release_data(UDF_SB_TYPESPAR(sb,i).s_spar_map[j]);
+ brelse(UDF_SB_TYPESPAR(sb,i).s_spar_map[j]);
UDF_SB_TYPESPAR(sb,i).s_spar_map[j] = NULL;
}
}
@@ -1137,12 +1135,12 @@ udf_load_logicalvolint(struct super_block *sb, kernel_extent_ad loc)
udf_load_logicalvolint(sb, leea_to_cpu(UDF_SB_LVID(sb)->nextIntegrityExt));
if (UDF_SB_LVIDBH(sb) != bh)
- udf_release_data(bh);
+ brelse(bh);
loc.extLength -= sb->s_blocksize;
loc.extLocation ++;
}
if (UDF_SB_LVIDBH(sb) != bh)
- udf_release_data(bh);
+ brelse(bh);
}
/*
@@ -1245,7 +1243,7 @@ udf_process_sequence(struct super_block *sb, long block, long lastblock, kernel_
done = 1;
break;
}
- udf_release_data(bh);
+ brelse(bh);
}
for (i=0; i<VDS_POS_LENGTH; i++)
{
@@ -1267,10 +1265,10 @@ udf_process_sequence(struct super_block *sb, long block, long lastblock, kernel_
gd = (struct generic_desc *)bh2->b_data;
if (ident == TAG_IDENT_PD)
udf_load_partdesc(sb, bh2);
- udf_release_data(bh2);
+ brelse(bh2);
}
}
- udf_release_data(bh);
+ brelse(bh);
}
}
@@ -1333,7 +1331,7 @@ udf_load_partition(struct super_block *sb, kernel_lb_addr *fileset)
reserve_e = reserve_e >> sb->s_blocksize_bits;
reserve_e += reserve_s;
- udf_release_data(bh);
+ brelse(bh);
/* Process the main & reserve sequences */
/* responsible for finding the PartitionDesc(s) */
@@ -1353,7 +1351,7 @@ udf_load_partition(struct super_block *sb, kernel_lb_addr *fileset)
for (i=0; i<UDF_SB_NUMPARTS(sb); i++)
{
- switch UDF_SB_PARTTYPE(sb, i)
+ switch (UDF_SB_PARTTYPE(sb, i))
{
case UDF_VIRTUAL_MAP15:
case UDF_VIRTUAL_MAP20:
@@ -1403,12 +1401,14 @@ udf_load_partition(struct super_block *sb, kernel_lb_addr *fileset)
pos = udf_block_map(UDF_SB_VAT(sb), 0);
bh = sb_bread(sb, pos);
+ if (!bh)
+ return 1;
UDF_SB_TYPEVIRT(sb,i).s_start_offset =
le16_to_cpu(((struct virtualAllocationTable20 *)bh->b_data + udf_ext0_offset(UDF_SB_VAT(sb)))->lengthHeader) +
udf_ext0_offset(UDF_SB_VAT(sb));
UDF_SB_TYPEVIRT(sb,i).s_num_entries = (UDF_SB_VAT(sb)->i_size -
UDF_SB_TYPEVIRT(sb,i).s_start_offset) >> 2;
- udf_release_data(bh);
+ brelse(bh);
}
UDF_SB_PARTROOT(sb,i) = udf_get_pblock(sb, 0, i, 0);
UDF_SB_PARTLEN(sb,i) = UDF_SB_PARTLEN(sb,ino.partitionReferenceNum);
@@ -1661,7 +1661,7 @@ static int udf_fill_super(struct super_block *sb, void *options, int silent)
iput(inode);
goto error_out;
}
- sb->s_maxbytes = 1<<30;
+ sb->s_maxbytes = MAX_LFS_FILESIZE;
return 0;
error_out:
@@ -1680,7 +1680,7 @@ error_out:
if (UDF_SB_PARTTYPE(sb, UDF_SB_PARTITION(sb)) == UDF_SPARABLE_MAP15)
{
for (i=0; i<4; i++)
- udf_release_data(UDF_SB_TYPESPAR(sb, UDF_SB_PARTITION(sb)).s_spar_map[i]);
+ brelse(UDF_SB_TYPESPAR(sb, UDF_SB_PARTITION(sb)).s_spar_map[i]);
}
}
#ifdef CONFIG_UDF_NLS
@@ -1689,7 +1689,7 @@ error_out:
#endif
if (!(sb->s_flags & MS_RDONLY))
udf_close_lvid(sb);
- udf_release_data(UDF_SB_LVIDBH(sb));
+ brelse(UDF_SB_LVIDBH(sb));
UDF_SB_FREE(sb);
kfree(sbi);
sb->s_fs_info = NULL;
@@ -1758,7 +1758,7 @@ udf_put_super(struct super_block *sb)
if (UDF_SB_PARTTYPE(sb, UDF_SB_PARTITION(sb)) == UDF_SPARABLE_MAP15)
{
for (i=0; i<4; i++)
- udf_release_data(UDF_SB_TYPESPAR(sb, UDF_SB_PARTITION(sb)).s_spar_map[i]);
+ brelse(UDF_SB_TYPESPAR(sb, UDF_SB_PARTITION(sb)).s_spar_map[i]);
}
}
#ifdef CONFIG_UDF_NLS
@@ -1767,7 +1767,7 @@ udf_put_super(struct super_block *sb)
#endif
if (!(sb->s_flags & MS_RDONLY))
udf_close_lvid(sb);
- udf_release_data(UDF_SB_LVIDBH(sb));
+ brelse(UDF_SB_LVIDBH(sb));
UDF_SB_FREE(sb);
kfree(sb->s_fs_info);
sb->s_fs_info = NULL;
@@ -1837,7 +1837,7 @@ udf_count_free_bitmap(struct super_block *sb, struct udf_bitmap *bitmap)
}
else if (ident != TAG_IDENT_SBD)
{
- udf_release_data(bh);
+ brelse(bh);
printk(KERN_ERR "udf: udf_count_free failed\n");
goto out;
}
@@ -1859,7 +1859,7 @@ udf_count_free_bitmap(struct super_block *sb, struct udf_bitmap *bitmap)
}
if ( bytes )
{
- udf_release_data(bh);
+ brelse(bh);
newblock = udf_get_lb_pblock(sb, loc, ++block);
bh = udf_tread(sb, newblock);
if (!bh)
@@ -1871,7 +1871,7 @@ udf_count_free_bitmap(struct super_block *sb, struct udf_bitmap *bitmap)
ptr = (uint8_t *)bh->b_data;
}
}
- udf_release_data(bh);
+ brelse(bh);
out:
unlock_kernel();
@@ -1883,21 +1883,20 @@ static unsigned int
udf_count_free_table(struct super_block *sb, struct inode * table)
{
unsigned int accum = 0;
- uint32_t extoffset, elen;
- kernel_lb_addr bloc, eloc;
+ uint32_t elen;
+ kernel_lb_addr eloc;
int8_t etype;
- struct buffer_head *bh = NULL;
+ struct extent_position epos;
lock_kernel();
- bloc = UDF_I_LOCATION(table);
- extoffset = sizeof(struct unallocSpaceEntry);
+ epos.block = UDF_I_LOCATION(table);
+ epos.offset = sizeof(struct unallocSpaceEntry);
+ epos.bh = NULL;
- while ((etype = udf_next_aext(table, &bloc, &extoffset, &eloc, &elen, &bh, 1)) != -1)
- {
+ while ((etype = udf_next_aext(table, &epos, &eloc, &elen, 1)) != -1)
accum += (elen >> table->i_sb->s_blocksize_bits);
- }
- udf_release_data(bh);
+ brelse(epos.bh);
unlock_kernel();
diff --git a/fs/udf/symlink.c b/fs/udf/symlink.c
index ba068a78656..12613b680cc 100644
--- a/fs/udf/symlink.c
+++ b/fs/udf/symlink.c
@@ -95,7 +95,7 @@ static int udf_symlink_filler(struct file *file, struct page *page)
}
udf_pc_to_char(inode->i_sb, symlink, inode->i_size, p);
- udf_release_data(bh);
+ brelse(bh);
unlock_kernel();
SetPageUptodate(page);
diff --git a/fs/udf/truncate.c b/fs/udf/truncate.c
index 0abd66ce36e..60d27764424 100644
--- a/fs/udf/truncate.c
+++ b/fs/udf/truncate.c
@@ -28,8 +28,8 @@
#include "udf_i.h"
#include "udf_sb.h"
-static void extent_trunc(struct inode * inode, kernel_lb_addr bloc, int extoffset,
- kernel_lb_addr eloc, int8_t etype, uint32_t elen, struct buffer_head *bh, uint32_t nelen)
+static void extent_trunc(struct inode * inode, struct extent_position *epos,
+ kernel_lb_addr eloc, int8_t etype, uint32_t elen, uint32_t nelen)
{
kernel_lb_addr neloc = { 0, 0 };
int last_block = (elen + inode->i_sb->s_blocksize - 1) >> inode->i_sb->s_blocksize_bits;
@@ -49,7 +49,7 @@ static void extent_trunc(struct inode * inode, kernel_lb_addr bloc, int extoffse
if (elen != nelen)
{
- udf_write_aext(inode, bloc, &extoffset, neloc, nelen, bh, 0);
+ udf_write_aext(inode, epos, neloc, nelen, 0);
if (last_block - first_block > 0)
{
if (etype == (EXT_RECORDED_ALLOCATED >> 30))
@@ -61,74 +61,125 @@ static void extent_trunc(struct inode * inode, kernel_lb_addr bloc, int extoffse
}
}
-void udf_discard_prealloc(struct inode * inode)
+/*
+ * Truncate the last extent to match i_size. This function assumes
+ * that preallocation extent is already truncated.
+ */
+void udf_truncate_tail_extent(struct inode *inode)
{
- kernel_lb_addr bloc, eloc;
- uint32_t extoffset = 0, elen, nelen;
+ struct extent_position epos = { NULL, 0, {0, 0}};
+ kernel_lb_addr eloc;
+ uint32_t elen, nelen;
uint64_t lbcount = 0;
int8_t etype = -1, netype;
- struct buffer_head *bh = NULL;
int adsize;
if (UDF_I_ALLOCTYPE(inode) == ICBTAG_FLAG_AD_IN_ICB ||
- inode->i_size == UDF_I_LENEXTENTS(inode))
- {
+ inode->i_size == UDF_I_LENEXTENTS(inode))
+ return;
+ /* Are we going to delete the file anyway? */
+ if (inode->i_nlink == 0)
return;
- }
if (UDF_I_ALLOCTYPE(inode) == ICBTAG_FLAG_AD_SHORT)
adsize = sizeof(short_ad);
else if (UDF_I_ALLOCTYPE(inode) == ICBTAG_FLAG_AD_LONG)
adsize = sizeof(long_ad);
else
- adsize = 0;
+ BUG();
- bloc = UDF_I_LOCATION(inode);
-
- while ((netype = udf_next_aext(inode, &bloc, &extoffset, &eloc, &elen, &bh, 1)) != -1)
+ /* Find the last extent in the file */
+ while ((netype = udf_next_aext(inode, &epos, &eloc, &elen, 1)) != -1)
{
etype = netype;
lbcount += elen;
- if (lbcount > inode->i_size && lbcount - inode->i_size < inode->i_sb->s_blocksize)
- {
+ if (lbcount > inode->i_size) {
+ if (lbcount - inode->i_size >= inode->i_sb->s_blocksize)
+ printk(KERN_WARNING
+ "udf_truncate_tail_extent(): Too long "
+ "extent after EOF in inode %u: i_size: "
+ "%Ld lbcount: %Ld extent %u+%u\n",
+ (unsigned)inode->i_ino,
+ (long long)inode->i_size,
+ (long long)lbcount,
+ (unsigned)eloc.logicalBlockNum,
+ (unsigned)elen);
nelen = elen - (lbcount - inode->i_size);
- extent_trunc(inode, bloc, extoffset-adsize, eloc, etype, elen, bh, nelen);
- lbcount = inode->i_size;
+ epos.offset -= adsize;
+ extent_trunc(inode, &epos, eloc, etype, elen, nelen);
+ epos.offset += adsize;
+ if (udf_next_aext(inode, &epos, &eloc, &elen, 1) != -1)
+ printk(KERN_ERR "udf_truncate_tail_extent(): "
+ "Extent after EOF in inode %u.\n",
+ (unsigned)inode->i_ino);
+ break;
}
}
- if (etype == (EXT_NOT_RECORDED_ALLOCATED >> 30))
- {
- extoffset -= adsize;
+ /* This inode entry is in-memory only and thus we don't have to mark
+ * the inode dirty */
+ UDF_I_LENEXTENTS(inode) = inode->i_size;
+ brelse(epos.bh);
+}
+
+void udf_discard_prealloc(struct inode *inode)
+{
+ struct extent_position epos = { NULL, 0, {0, 0}};
+ kernel_lb_addr eloc;
+ uint32_t elen;
+ uint64_t lbcount = 0;
+ int8_t etype = -1, netype;
+ int adsize;
+
+ if (UDF_I_ALLOCTYPE(inode) == ICBTAG_FLAG_AD_IN_ICB ||
+ inode->i_size == UDF_I_LENEXTENTS(inode))
+ return;
+
+ if (UDF_I_ALLOCTYPE(inode) == ICBTAG_FLAG_AD_SHORT)
+ adsize = sizeof(short_ad);
+ else if (UDF_I_ALLOCTYPE(inode) == ICBTAG_FLAG_AD_LONG)
+ adsize = sizeof(long_ad);
+ else
+ adsize = 0;
+
+ epos.block = UDF_I_LOCATION(inode);
+
+ /* Find the last extent in the file */
+ while ((netype = udf_next_aext(inode, &epos, &eloc, &elen, 1)) != -1) {
+ etype = netype;
+ lbcount += elen;
+ }
+ if (etype == (EXT_NOT_RECORDED_ALLOCATED >> 30)) {
+ epos.offset -= adsize;
lbcount -= elen;
- extent_trunc(inode, bloc, extoffset, eloc, etype, elen, bh, 0);
- if (!bh)
- {
- UDF_I_LENALLOC(inode) = extoffset - udf_file_entry_alloc_offset(inode);
+ extent_trunc(inode, &epos, eloc, etype, elen, 0);
+ if (!epos.bh) {
+ UDF_I_LENALLOC(inode) = epos.offset - udf_file_entry_alloc_offset(inode);
mark_inode_dirty(inode);
- }
- else
- {
- struct allocExtDesc *aed = (struct allocExtDesc *)(bh->b_data);
- aed->lengthAllocDescs = cpu_to_le32(extoffset - sizeof(struct allocExtDesc));
+ } else {
+ struct allocExtDesc *aed = (struct allocExtDesc *)(epos.bh->b_data);
+ aed->lengthAllocDescs = cpu_to_le32(epos.offset - sizeof(struct allocExtDesc));
if (!UDF_QUERY_FLAG(inode->i_sb, UDF_FLAG_STRICT) || UDF_SB_UDFREV(inode->i_sb) >= 0x0201)
- udf_update_tag(bh->b_data, extoffset);
+ udf_update_tag(epos.bh->b_data, epos.offset);
else
- udf_update_tag(bh->b_data, sizeof(struct allocExtDesc));
- mark_buffer_dirty_inode(bh, inode);
+ udf_update_tag(epos.bh->b_data, sizeof(struct allocExtDesc));
+ mark_buffer_dirty_inode(epos.bh, inode);
}
}
+ /* This inode entry is in-memory only and thus we don't have to mark
+ * the inode dirty */
UDF_I_LENEXTENTS(inode) = lbcount;
-
- udf_release_data(bh);
+ brelse(epos.bh);
}
void udf_truncate_extents(struct inode * inode)
{
- kernel_lb_addr bloc, eloc, neloc = { 0, 0 };
- uint32_t extoffset, elen, offset, nelen = 0, lelen = 0, lenalloc;
+ struct extent_position epos;
+ kernel_lb_addr eloc, neloc = { 0, 0 };
+ uint32_t elen, nelen = 0, indirect_ext_len = 0, lenalloc;
int8_t etype;
- int first_block = inode->i_size >> inode->i_sb->s_blocksize_bits;
- struct buffer_head *bh = NULL;
+ struct super_block *sb = inode->i_sb;
+ sector_t first_block = inode->i_size >> sb->s_blocksize_bits, offset;
+ loff_t byte_offset;
int adsize;
if (UDF_I_ALLOCTYPE(inode) == ICBTAG_FLAG_AD_SHORT)
@@ -136,158 +187,130 @@ void udf_truncate_extents(struct inode * inode)
else if (UDF_I_ALLOCTYPE(inode) == ICBTAG_FLAG_AD_LONG)
adsize = sizeof(long_ad);
else
- adsize = 0;
+ BUG();
- etype = inode_bmap(inode, first_block, &bloc, &extoffset, &eloc, &elen, &offset, &bh);
- offset += (inode->i_size & (inode->i_sb->s_blocksize - 1));
+ etype = inode_bmap(inode, first_block, &epos, &eloc, &elen, &offset);
+ byte_offset = (offset << sb->s_blocksize_bits) + (inode->i_size & (sb->s_blocksize-1));
if (etype != -1)
{
- extoffset -= adsize;
- extent_trunc(inode, bloc, extoffset, eloc, etype, elen, bh, offset);
- extoffset += adsize;
-
- if (offset)
- lenalloc = extoffset;
+ epos.offset -= adsize;
+ extent_trunc(inode, &epos, eloc, etype, elen, byte_offset);
+ epos.offset += adsize;
+ if (byte_offset)
+ lenalloc = epos.offset;
else
- lenalloc = extoffset - adsize;
+ lenalloc = epos.offset - adsize;
- if (!bh)
+ if (!epos.bh)
lenalloc -= udf_file_entry_alloc_offset(inode);
else
lenalloc -= sizeof(struct allocExtDesc);
- while ((etype = udf_current_aext(inode, &bloc, &extoffset, &eloc, &elen, &bh, 0)) != -1)
+ while ((etype = udf_current_aext(inode, &epos, &eloc, &elen, 0)) != -1)
{
if (etype == (EXT_NEXT_EXTENT_ALLOCDECS >> 30))
{
- udf_write_aext(inode, bloc, &extoffset, neloc, nelen, bh, 0);
- extoffset = 0;
- if (lelen)
+ udf_write_aext(inode, &epos, neloc, nelen, 0);
+ if (indirect_ext_len)
{
- if (!bh)
+ /* We managed to free all extents in the
+ * indirect extent - free it too */
+ if (!epos.bh)
BUG();
- else
- memset(bh->b_data, 0x00, sizeof(struct allocExtDesc));
- udf_free_blocks(inode->i_sb, inode, bloc, 0, lelen);
+ udf_free_blocks(sb, inode, epos.block, 0, indirect_ext_len);
}
else
{
- if (!bh)
+ if (!epos.bh)
{
UDF_I_LENALLOC(inode) = lenalloc;
mark_inode_dirty(inode);
}
else
{
- struct allocExtDesc *aed = (struct allocExtDesc *)(bh->b_data);
+ struct allocExtDesc *aed = (struct allocExtDesc *)(epos.bh->b_data);
aed->lengthAllocDescs = cpu_to_le32(lenalloc);
- if (!UDF_QUERY_FLAG(inode->i_sb, UDF_FLAG_STRICT) || UDF_SB_UDFREV(inode->i_sb) >= 0x0201)
- udf_update_tag(bh->b_data, lenalloc +
+ if (!UDF_QUERY_FLAG(sb, UDF_FLAG_STRICT) || UDF_SB_UDFREV(sb) >= 0x0201)
+ udf_update_tag(epos.bh->b_data, lenalloc +
sizeof(struct allocExtDesc));
else
- udf_update_tag(bh->b_data, sizeof(struct allocExtDesc));
- mark_buffer_dirty_inode(bh, inode);
+ udf_update_tag(epos.bh->b_data, sizeof(struct allocExtDesc));
+ mark_buffer_dirty_inode(epos.bh, inode);
}
}
-
- udf_release_data(bh);
- extoffset = sizeof(struct allocExtDesc);
- bloc = eloc;
- bh = udf_tread(inode->i_sb, udf_get_lb_pblock(inode->i_sb, bloc, 0));
+ brelse(epos.bh);
+ epos.offset = sizeof(struct allocExtDesc);
+ epos.block = eloc;
+ epos.bh = udf_tread(sb, udf_get_lb_pblock(sb, eloc, 0));
if (elen)
- lelen = (elen + inode->i_sb->s_blocksize - 1) >>
- inode->i_sb->s_blocksize_bits;
+ indirect_ext_len = (elen +
+ sb->s_blocksize - 1) >>
+ sb->s_blocksize_bits;
else
- lelen = 1;
+ indirect_ext_len = 1;
}
else
{
- extent_trunc(inode, bloc, extoffset, eloc, etype, elen, bh, 0);
- extoffset += adsize;
+ extent_trunc(inode, &epos, eloc, etype, elen, 0);
+ epos.offset += adsize;
}
}
- if (lelen)
+ if (indirect_ext_len)
{
- if (!bh)
+ if (!epos.bh)
BUG();
- else
- memset(bh->b_data, 0x00, sizeof(struct allocExtDesc));
- udf_free_blocks(inode->i_sb, inode, bloc, 0, lelen);
+ udf_free_blocks(sb, inode, epos.block, 0, indirect_ext_len);
}
else
{
- if (!bh)
+ if (!epos.bh)
{
UDF_I_LENALLOC(inode) = lenalloc;
mark_inode_dirty(inode);
}
else
{
- struct allocExtDesc *aed = (struct allocExtDesc *)(bh->b_data);
+ struct allocExtDesc *aed = (struct allocExtDesc *)(epos.bh->b_data);
aed->lengthAllocDescs = cpu_to_le32(lenalloc);
- if (!UDF_QUERY_FLAG(inode->i_sb, UDF_FLAG_STRICT) || UDF_SB_UDFREV(inode->i_sb) >= 0x0201)
- udf_update_tag(bh->b_data, lenalloc +
+ if (!UDF_QUERY_FLAG(sb, UDF_FLAG_STRICT) || UDF_SB_UDFREV(sb) >= 0x0201)
+ udf_update_tag(epos.bh->b_data, lenalloc +
sizeof(struct allocExtDesc));
else
- udf_update_tag(bh->b_data, sizeof(struct allocExtDesc));
- mark_buffer_dirty_inode(bh, inode);
+ udf_update_tag(epos.bh->b_data, sizeof(struct allocExtDesc));
+ mark_buffer_dirty_inode(epos.bh, inode);
}
}
}
else if (inode->i_size)
{
- if (offset)
+ if (byte_offset)
{
+ kernel_long_ad extent;
+
/*
* OK, there is not extent covering inode->i_size and
* no extent above inode->i_size => truncate is
- * extending the file by 'offset'.
+ * extending the file by 'offset' blocks.
*/
- if ((!bh && extoffset == udf_file_entry_alloc_offset(inode)) ||
- (bh && extoffset == sizeof(struct allocExtDesc))) {
- /* File has no extents at all! */
- memset(&eloc, 0x00, sizeof(kernel_lb_addr));
- elen = EXT_NOT_RECORDED_NOT_ALLOCATED | offset;
- udf_add_aext(inode, &bloc, &extoffset, eloc, elen, &bh, 1);
+ if ((!epos.bh && epos.offset == udf_file_entry_alloc_offset(inode)) ||
+ (epos.bh && epos.offset == sizeof(struct allocExtDesc))) {
+ /* File has no extents at all or has empty last
+ * indirect extent! Create a fake extent... */
+ extent.extLocation.logicalBlockNum = 0;
+ extent.extLocation.partitionReferenceNum = 0;
+ extent.extLength = EXT_NOT_RECORDED_NOT_ALLOCATED;
}
else {
- extoffset -= adsize;
- etype = udf_next_aext(inode, &bloc, &extoffset, &eloc, &elen, &bh, 1);
- if (etype == (EXT_NOT_RECORDED_NOT_ALLOCATED >> 30))
- {
- extoffset -= adsize;
- elen = EXT_NOT_RECORDED_NOT_ALLOCATED | (elen + offset);
- udf_write_aext(inode, bloc, &extoffset, eloc, elen, bh, 0);
- }
- else if (etype == (EXT_NOT_RECORDED_ALLOCATED >> 30))
- {
- kernel_lb_addr neloc = { 0, 0 };
- extoffset -= adsize;
- nelen = EXT_NOT_RECORDED_NOT_ALLOCATED |
- ((elen + offset + inode->i_sb->s_blocksize - 1) &
- ~(inode->i_sb->s_blocksize - 1));
- udf_write_aext(inode, bloc, &extoffset, neloc, nelen, bh, 1);
- udf_add_aext(inode, &bloc, &extoffset, eloc, (etype << 30) | elen, &bh, 1);
- }
- else
- {
- if (elen & (inode->i_sb->s_blocksize - 1))
- {
- extoffset -= adsize;
- elen = EXT_RECORDED_ALLOCATED |
- ((elen + inode->i_sb->s_blocksize - 1) &
- ~(inode->i_sb->s_blocksize - 1));
- udf_write_aext(inode, bloc, &extoffset, eloc, elen, bh, 1);
- }
- memset(&eloc, 0x00, sizeof(kernel_lb_addr));
- elen = EXT_NOT_RECORDED_NOT_ALLOCATED | offset;
- udf_add_aext(inode, &bloc, &extoffset, eloc, elen, &bh, 1);
- }
+ epos.offset -= adsize;
+ etype = udf_next_aext(inode, &epos,
+ &extent.extLocation, &extent.extLength, 0);
+ extent.extLength |= etype << 30;
}
+ udf_extend_file(inode, &epos, &extent, offset+((inode->i_size & (sb->s_blocksize-1)) != 0));
}
}
UDF_I_LENEXTENTS(inode) = inode->i_size;
- udf_release_data(bh);
+ brelse(epos.bh);
}
diff --git a/fs/udf/udf_sb.h b/fs/udf/udf_sb.h
index 110f8d62616..3b2e6c8cb15 100644
--- a/fs/udf/udf_sb.h
+++ b/fs/udf/udf_sb.h
@@ -93,7 +93,7 @@ static inline struct udf_sb_info *UDF_SB(struct super_block *sb)
for (i=0; i<nr_groups; i++)\
{\
if (UDF_SB_BITMAP(X,Y,Z,i))\
- udf_release_data(UDF_SB_BITMAP(X,Y,Z,i));\
+ brelse(UDF_SB_BITMAP(X,Y,Z,i));\
}\
if (size <= PAGE_SIZE)\
kfree(UDF_SB_PARTMAPS(X)[Y].Z.s_bitmap);\
diff --git a/fs/udf/udfdecl.h b/fs/udf/udfdecl.h
index ee1dece1f6f..f581f2f69c0 100644
--- a/fs/udf/udfdecl.h
+++ b/fs/udf/udfdecl.h
@@ -77,6 +77,13 @@ struct ustr
uint8_t u_len;
};
+struct extent_position {
+ struct buffer_head *bh;
+ uint32_t offset;
+ kernel_lb_addr block;
+};
+
+
/* super.c */
extern void udf_error(struct super_block *, const char *, const char *, ...);
extern void udf_warning(struct super_block *, const char *, const char *, ...);
@@ -98,13 +105,14 @@ extern void udf_read_inode(struct inode *);
extern void udf_delete_inode(struct inode *);
extern void udf_clear_inode(struct inode *);
extern int udf_write_inode(struct inode *, int);
-extern long udf_block_map(struct inode *, long);
-extern int8_t inode_bmap(struct inode *, int, kernel_lb_addr *, uint32_t *, kernel_lb_addr *, uint32_t *, uint32_t *, struct buffer_head **);
-extern int8_t udf_add_aext(struct inode *, kernel_lb_addr *, int *, kernel_lb_addr, uint32_t, struct buffer_head **, int);
-extern int8_t udf_write_aext(struct inode *, kernel_lb_addr, int *, kernel_lb_addr, uint32_t, struct buffer_head *, int);
-extern int8_t udf_delete_aext(struct inode *, kernel_lb_addr, int, kernel_lb_addr, uint32_t, struct buffer_head *);
-extern int8_t udf_next_aext(struct inode *, kernel_lb_addr *, int *, kernel_lb_addr *, uint32_t *, struct buffer_head **, int);
-extern int8_t udf_current_aext(struct inode *, kernel_lb_addr *, int *, kernel_lb_addr *, uint32_t *, struct buffer_head **, int);
+extern long udf_block_map(struct inode *, sector_t);
+extern int udf_extend_file(struct inode *, struct extent_position *, kernel_long_ad *, sector_t);
+extern int8_t inode_bmap(struct inode *, sector_t, struct extent_position *, kernel_lb_addr *, uint32_t *, sector_t *);
+extern int8_t udf_add_aext(struct inode *, struct extent_position *, kernel_lb_addr, uint32_t, int);
+extern int8_t udf_write_aext(struct inode *, struct extent_position *, kernel_lb_addr, uint32_t, int);
+extern int8_t udf_delete_aext(struct inode *, struct extent_position, kernel_lb_addr, uint32_t);
+extern int8_t udf_next_aext(struct inode *, struct extent_position *, kernel_lb_addr *, uint32_t *, int);
+extern int8_t udf_current_aext(struct inode *, struct extent_position *, kernel_lb_addr *, uint32_t *, int);
/* misc.c */
extern struct buffer_head *udf_tgetblk(struct super_block *, int);
@@ -113,7 +121,6 @@ extern struct genericFormat *udf_add_extendedattr(struct inode *, uint32_t, uint
extern struct genericFormat *udf_get_extendedattr(struct inode *, uint32_t, uint8_t);
extern struct buffer_head *udf_read_tagged(struct super_block *, uint32_t, uint32_t, uint16_t *);
extern struct buffer_head *udf_read_ptagged(struct super_block *, kernel_lb_addr, uint32_t, uint16_t *);
-extern void udf_release_data(struct buffer_head *);
extern void udf_update_tag(char *, int);
extern void udf_new_tag(char *, uint16_t, uint16_t, uint16_t, uint32_t, int);
@@ -139,6 +146,7 @@ extern void udf_free_inode(struct inode *);
extern struct inode * udf_new_inode (struct inode *, int, int *);
/* truncate.c */
+extern void udf_truncate_tail_extent(struct inode *);
extern void udf_discard_prealloc(struct inode *);
extern void udf_truncate_extents(struct inode *);
@@ -151,7 +159,7 @@ extern int udf_new_block(struct super_block *, struct inode *, uint16_t, uint32_
extern int udf_fsync_file(struct file *, struct dentry *, int);
/* directory.c */
-extern struct fileIdentDesc * udf_fileident_read(struct inode *, loff_t *, struct udf_fileident_bh *, struct fileIdentDesc *, kernel_lb_addr *, uint32_t *, kernel_lb_addr *, uint32_t *, uint32_t *, struct buffer_head **);
+extern struct fileIdentDesc * udf_fileident_read(struct inode *, loff_t *, struct udf_fileident_bh *, struct fileIdentDesc *, struct extent_position *, kernel_lb_addr *, uint32_t *, sector_t *);
extern struct fileIdentDesc * udf_get_fileident(void * buffer, int bufsize, int * offset);
extern long_ad * udf_get_filelongad(uint8_t *, int, int *, int);
extern short_ad * udf_get_fileshortad(uint8_t *, int, int *, int);
diff --git a/fs/ufs/dir.c b/fs/ufs/dir.c
index 4fb8b2e077e..154452172f4 100644
--- a/fs/ufs/dir.c
+++ b/fs/ufs/dir.c
@@ -19,7 +19,6 @@
#include <linux/time.h>
#include <linux/fs.h>
#include <linux/ufs_fs.h>
-#include <linux/smp_lock.h>
#include "swab.h"
#include "util.h"
diff --git a/fs/ufs/super.c b/fs/ufs/super.c
index be7c48c5f20..22ff6ed55ce 100644
--- a/fs/ufs/super.c
+++ b/fs/ufs/super.c
@@ -1237,8 +1237,7 @@ static void init_once(void * foo, struct kmem_cache * cachep, unsigned long flag
{
struct ufs_inode_info *ei = (struct ufs_inode_info *) foo;
- if (flags & SLAB_CTOR_CONSTRUCTOR)
- inode_init_once(&ei->vfs_inode);
+ inode_init_once(&ei->vfs_inode);
}
static int init_inodecache(void)
diff --git a/fs/utimes.c b/fs/utimes.c
index 99cf2cb11fe..480f7c8c29d 100644
--- a/fs/utimes.c
+++ b/fs/utimes.c
@@ -1,8 +1,10 @@
#include <linux/compiler.h>
+#include <linux/file.h>
#include <linux/fs.h>
#include <linux/linkage.h>
#include <linux/namei.h>
#include <linux/sched.h>
+#include <linux/stat.h>
#include <linux/utime.h>
#include <asm/uaccess.h>
#include <asm/unistd.h>
@@ -20,54 +22,18 @@
* must be owner or have write permission.
* Else, update from *times, must be owner or super user.
*/
-asmlinkage long sys_utime(char __user * filename, struct utimbuf __user * times)
+asmlinkage long sys_utime(char __user *filename, struct utimbuf __user *times)
{
- int error;
- struct nameidata nd;
- struct inode * inode;
- struct iattr newattrs;
+ struct timespec tv[2];
- error = user_path_walk(filename, &nd);
- if (error)
- goto out;
- inode = nd.dentry->d_inode;
-
- error = -EROFS;
- if (IS_RDONLY(inode))
- goto dput_and_out;
-
- /* Don't worry, the checks are done in inode_change_ok() */
- newattrs.ia_valid = ATTR_CTIME | ATTR_MTIME | ATTR_ATIME;
if (times) {
- error = -EPERM;
- if (IS_APPEND(inode) || IS_IMMUTABLE(inode))
- goto dput_and_out;
-
- error = get_user(newattrs.ia_atime.tv_sec, &times->actime);
- newattrs.ia_atime.tv_nsec = 0;
- if (!error)
- error = get_user(newattrs.ia_mtime.tv_sec, &times->modtime);
- newattrs.ia_mtime.tv_nsec = 0;
- if (error)
- goto dput_and_out;
-
- newattrs.ia_valid |= ATTR_ATIME_SET | ATTR_MTIME_SET;
- } else {
- error = -EACCES;
- if (IS_IMMUTABLE(inode))
- goto dput_and_out;
-
- if (current->fsuid != inode->i_uid &&
- (error = vfs_permission(&nd, MAY_WRITE)) != 0)
- goto dput_and_out;
+ if (get_user(tv[0].tv_sec, &times->actime) ||
+ get_user(tv[1].tv_sec, &times->modtime))
+ return -EFAULT;
+ tv[0].tv_nsec = 0;
+ tv[1].tv_nsec = 0;
}
- mutex_lock(&inode->i_mutex);
- error = notify_change(nd.dentry, &newattrs);
- mutex_unlock(&inode->i_mutex);
-dput_and_out:
- path_release(&nd);
-out:
- return error;
+ return do_utimes(AT_FDCWD, filename, times ? tv : NULL, 0);
}
#endif
@@ -76,18 +42,38 @@ out:
* must be owner or have write permission.
* Else, update from *times, must be owner or super user.
*/
-long do_utimes(int dfd, char __user *filename, struct timeval *times)
+long do_utimes(int dfd, char __user *filename, struct timespec *times, int flags)
{
int error;
struct nameidata nd;
- struct inode * inode;
+ struct dentry *dentry;
+ struct inode *inode;
struct iattr newattrs;
+ struct file *f = NULL;
- error = __user_walk_fd(dfd, filename, LOOKUP_FOLLOW, &nd);
-
- if (error)
+ error = -EINVAL;
+ if (flags & ~AT_SYMLINK_NOFOLLOW)
goto out;
- inode = nd.dentry->d_inode;
+
+ if (filename == NULL && dfd != AT_FDCWD) {
+ error = -EINVAL;
+ if (flags & AT_SYMLINK_NOFOLLOW)
+ goto out;
+
+ error = -EBADF;
+ f = fget(dfd);
+ if (!f)
+ goto out;
+ dentry = f->f_path.dentry;
+ } else {
+ error = __user_walk_fd(dfd, filename, (flags & AT_SYMLINK_NOFOLLOW) ? 0 : LOOKUP_FOLLOW, &nd);
+ if (error)
+ goto out;
+
+ dentry = nd.dentry;
+ }
+
+ inode = dentry->d_inode;
error = -EROFS;
if (IS_RDONLY(inode))
@@ -100,11 +86,21 @@ long do_utimes(int dfd, char __user *filename, struct timeval *times)
if (IS_APPEND(inode) || IS_IMMUTABLE(inode))
goto dput_and_out;
- newattrs.ia_atime.tv_sec = times[0].tv_sec;
- newattrs.ia_atime.tv_nsec = times[0].tv_usec * 1000;
- newattrs.ia_mtime.tv_sec = times[1].tv_sec;
- newattrs.ia_mtime.tv_nsec = times[1].tv_usec * 1000;
- newattrs.ia_valid |= ATTR_ATIME_SET | ATTR_MTIME_SET;
+ if (times[0].tv_nsec == UTIME_OMIT)
+ newattrs.ia_valid &= ~ATTR_ATIME;
+ else if (times[0].tv_nsec != UTIME_NOW) {
+ newattrs.ia_atime.tv_sec = times[0].tv_sec;
+ newattrs.ia_atime.tv_nsec = times[0].tv_nsec;
+ newattrs.ia_valid |= ATTR_ATIME_SET;
+ }
+
+ if (times[1].tv_nsec == UTIME_OMIT)
+ newattrs.ia_valid &= ~ATTR_MTIME;
+ else if (times[1].tv_nsec != UTIME_NOW) {
+ newattrs.ia_mtime.tv_sec = times[1].tv_sec;
+ newattrs.ia_mtime.tv_nsec = times[1].tv_nsec;
+ newattrs.ia_valid |= ATTR_MTIME_SET;
+ }
} else {
error = -EACCES;
if (IS_IMMUTABLE(inode))
@@ -115,21 +111,67 @@ long do_utimes(int dfd, char __user *filename, struct timeval *times)
goto dput_and_out;
}
mutex_lock(&inode->i_mutex);
- error = notify_change(nd.dentry, &newattrs);
+ error = notify_change(dentry, &newattrs);
mutex_unlock(&inode->i_mutex);
dput_and_out:
- path_release(&nd);
+ if (f)
+ fput(f);
+ else
+ path_release(&nd);
out:
return error;
}
+asmlinkage long sys_utimensat(int dfd, char __user *filename, struct timespec __user *utimes, int flags)
+{
+ struct timespec tstimes[2];
+
+ if (utimes) {
+ if (copy_from_user(&tstimes, utimes, sizeof(tstimes)))
+ return -EFAULT;
+ if ((tstimes[0].tv_nsec == UTIME_OMIT ||
+ tstimes[0].tv_nsec == UTIME_NOW) &&
+ tstimes[0].tv_sec != 0)
+ return -EINVAL;
+ if ((tstimes[1].tv_nsec == UTIME_OMIT ||
+ tstimes[1].tv_nsec == UTIME_NOW) &&
+ tstimes[1].tv_sec != 0)
+ return -EINVAL;
+
+ /* Nothing to do, we must not even check the path. */
+ if (tstimes[0].tv_nsec == UTIME_OMIT &&
+ tstimes[1].tv_nsec == UTIME_OMIT)
+ return 0;
+ }
+
+ return do_utimes(dfd, filename, utimes ? tstimes : NULL, flags);
+}
+
asmlinkage long sys_futimesat(int dfd, char __user *filename, struct timeval __user *utimes)
{
struct timeval times[2];
+ struct timespec tstimes[2];
+
+ if (utimes) {
+ if (copy_from_user(&times, utimes, sizeof(times)))
+ return -EFAULT;
+
+ /* This test is needed to catch all invalid values. If we
+ would test only in do_utimes we would miss those invalid
+ values truncated by the multiplication with 1000. Note
+ that we also catch UTIME_{NOW,OMIT} here which are only
+ valid for utimensat. */
+ if (times[0].tv_usec >= 1000000 || times[0].tv_usec < 0 ||
+ times[1].tv_usec >= 1000000 || times[1].tv_usec < 0)
+ return -EINVAL;
+
+ tstimes[0].tv_sec = times[0].tv_sec;
+ tstimes[0].tv_nsec = 1000 * times[0].tv_usec;
+ tstimes[1].tv_sec = times[1].tv_sec;
+ tstimes[1].tv_nsec = 1000 * times[1].tv_usec;
+ }
- if (utimes && copy_from_user(&times, utimes, sizeof(times)))
- return -EFAULT;
- return do_utimes(dfd, filename, utimes ? times : NULL);
+ return do_utimes(dfd, filename, utimes ? tstimes : NULL, 0);
}
asmlinkage long sys_utimes(char __user *filename, struct timeval __user *utimes)
diff --git a/fs/xattr.c b/fs/xattr.c
index 38646132ab0..4523aca7965 100644
--- a/fs/xattr.c
+++ b/fs/xattr.c
@@ -9,7 +9,6 @@
*/
#include <linux/fs.h>
#include <linux/slab.h>
-#include <linux/smp_lock.h>
#include <linux/file.h>
#include <linux/xattr.h>
#include <linux/namei.h>
@@ -351,6 +350,7 @@ sys_fgetxattr(int fd, char __user *name, void __user *value, size_t size)
f = fget(fd);
if (!f)
return error;
+ audit_inode(NULL, f->f_path.dentry->d_inode);
error = getxattr(f->f_path.dentry, name, value, size);
fput(f);
return error;
@@ -423,6 +423,7 @@ sys_flistxattr(int fd, char __user *list, size_t size)
f = fget(fd);
if (!f)
return error;
+ audit_inode(NULL, f->f_path.dentry->d_inode);
error = listxattr(f->f_path.dentry, list, size);
fput(f);
return error;
diff --git a/fs/xfs/linux-2.6/mrlock.h b/fs/xfs/linux-2.6/mrlock.h
index af168a1a98c..c110bb00266 100644
--- a/fs/xfs/linux-2.6/mrlock.h
+++ b/fs/xfs/linux-2.6/mrlock.h
@@ -43,6 +43,18 @@ static inline void mrupdate(mrlock_t *mrp)
mrp->mr_writer = 1;
}
+static inline void mraccess_nested(mrlock_t *mrp, int subclass)
+{
+ down_read_nested(&mrp->mr_lock, subclass);
+}
+
+static inline void mrupdate_nested(mrlock_t *mrp, int subclass)
+{
+ down_write_nested(&mrp->mr_lock, subclass);
+ mrp->mr_writer = 1;
+}
+
+
static inline int mrtryaccess(mrlock_t *mrp)
{
return down_read_trylock(&mrp->mr_lock);
diff --git a/fs/xfs/linux-2.6/xfs_aops.c b/fs/xfs/linux-2.6/xfs_aops.c
index 143ffc851c9..7361861e3aa 100644
--- a/fs/xfs/linux-2.6/xfs_aops.c
+++ b/fs/xfs/linux-2.6/xfs_aops.c
@@ -141,9 +141,46 @@ xfs_destroy_ioend(
}
/*
+ * Update on-disk file size now that data has been written to disk.
+ * The current in-memory file size is i_size. If a write is beyond
+ * eof io_new_size will be the intended file size until i_size is
+ * updated. If this write does not extend all the way to the valid
+ * file size then restrict this update to the end of the write.
+ */
+STATIC void
+xfs_setfilesize(
+ xfs_ioend_t *ioend)
+{
+ xfs_inode_t *ip;
+ xfs_fsize_t isize;
+ xfs_fsize_t bsize;
+
+ ip = xfs_vtoi(ioend->io_vnode);
+
+ ASSERT((ip->i_d.di_mode & S_IFMT) == S_IFREG);
+ ASSERT(ioend->io_type != IOMAP_READ);
+
+ if (unlikely(ioend->io_error))
+ return;
+
+ bsize = ioend->io_offset + ioend->io_size;
+
+ xfs_ilock(ip, XFS_ILOCK_EXCL);
+
+ isize = MAX(ip->i_size, ip->i_iocore.io_new_size);
+ isize = MIN(isize, bsize);
+
+ if (ip->i_d.di_size < isize) {
+ ip->i_d.di_size = isize;
+ ip->i_update_core = 1;
+ ip->i_update_size = 1;
+ }
+
+ xfs_iunlock(ip, XFS_ILOCK_EXCL);
+}
+
+/*
* Buffered IO write completion for delayed allocate extents.
- * TODO: Update ondisk isize now that we know the file data
- * has been flushed (i.e. the notorious "NULL file" problem).
*/
STATIC void
xfs_end_bio_delalloc(
@@ -152,6 +189,7 @@ xfs_end_bio_delalloc(
xfs_ioend_t *ioend =
container_of(work, xfs_ioend_t, io_work);
+ xfs_setfilesize(ioend);
xfs_destroy_ioend(ioend);
}
@@ -165,6 +203,7 @@ xfs_end_bio_written(
xfs_ioend_t *ioend =
container_of(work, xfs_ioend_t, io_work);
+ xfs_setfilesize(ioend);
xfs_destroy_ioend(ioend);
}
@@ -184,8 +223,23 @@ xfs_end_bio_unwritten(
xfs_off_t offset = ioend->io_offset;
size_t size = ioend->io_size;
- if (likely(!ioend->io_error))
+ if (likely(!ioend->io_error)) {
bhv_vop_bmap(vp, offset, size, BMAPI_UNWRITTEN, NULL, NULL);
+ xfs_setfilesize(ioend);
+ }
+ xfs_destroy_ioend(ioend);
+}
+
+/*
+ * IO read completion for regular, written extents.
+ */
+STATIC void
+xfs_end_bio_read(
+ struct work_struct *work)
+{
+ xfs_ioend_t *ioend =
+ container_of(work, xfs_ioend_t, io_work);
+
xfs_destroy_ioend(ioend);
}
@@ -224,6 +278,8 @@ xfs_alloc_ioend(
INIT_WORK(&ioend->io_work, xfs_end_bio_unwritten);
else if (type == IOMAP_DELAY)
INIT_WORK(&ioend->io_work, xfs_end_bio_delalloc);
+ else if (type == IOMAP_READ)
+ INIT_WORK(&ioend->io_work, xfs_end_bio_read);
else
INIT_WORK(&ioend->io_work, xfs_end_bio_written);
@@ -645,7 +701,7 @@ xfs_is_delayed_page(
else if (buffer_delay(bh))
acceptable = (type == IOMAP_DELAY);
else if (buffer_dirty(bh) && buffer_mapped(bh))
- acceptable = (type == 0);
+ acceptable = (type == IOMAP_NEW);
else
break;
} while ((bh = bh->b_this_page) != head);
@@ -754,7 +810,7 @@ xfs_convert_page(
page_dirty--;
count++;
} else {
- type = 0;
+ type = IOMAP_NEW;
if (buffer_mapped(bh) && all_bh && startio) {
lock_buffer(bh);
xfs_add_to_ioend(inode, bh, offset,
@@ -912,8 +968,8 @@ xfs_page_state_convert(
bh = head = page_buffers(page);
offset = page_offset(page);
- flags = -1;
- type = 0;
+ flags = BMAPI_READ;
+ type = IOMAP_NEW;
/* TODO: cleanup count and page_dirty */
@@ -943,14 +999,14 @@ xfs_page_state_convert(
*
* Third case, an unmapped buffer was found, and we are
* in a path where we need to write the whole page out.
- */
+ */
if (buffer_unwritten(bh) || buffer_delay(bh) ||
((buffer_uptodate(bh) || PageUptodate(page)) &&
!buffer_mapped(bh) && (unmapped || startio))) {
- /*
+ /*
* Make sure we don't use a read-only iomap
*/
- if (flags == BMAPI_READ)
+ if (flags == BMAPI_READ)
iomap_valid = 0;
if (buffer_unwritten(bh)) {
@@ -999,7 +1055,7 @@ xfs_page_state_convert(
* That means it must already have extents allocated
* underneath it. Map the extent by reading it.
*/
- if (!iomap_valid || type != 0) {
+ if (!iomap_valid || flags != BMAPI_READ) {
flags = BMAPI_READ;
size = xfs_probe_cluster(inode, page, bh,
head, 1);
@@ -1010,7 +1066,15 @@ xfs_page_state_convert(
iomap_valid = xfs_iomap_valid(&iomap, offset);
}
- type = 0;
+ /*
+ * We set the type to IOMAP_NEW in case we are doing a
+ * small write at EOF that is extending the file but
+ * without needing an allocation. We need to update the
+ * file size on I/O completion in this case so it is
+ * the same case as having just allocated a new extent
+ * that we are writing into for the first time.
+ */
+ type = IOMAP_NEW;
if (!test_and_set_bit(BH_Lock, &bh->b_state)) {
ASSERT(buffer_mapped(bh));
if (iomap_valid)
@@ -1356,12 +1420,21 @@ xfs_end_io_direct(
* completion handler in the future, in which case all this can
* go away.
*/
- if (private && size > 0) {
- ioend->io_offset = offset;
- ioend->io_size = size;
+ ioend->io_offset = offset;
+ ioend->io_size = size;
+ if (ioend->io_type == IOMAP_READ) {
+ xfs_finish_ioend(ioend);
+ } else if (private && size > 0) {
xfs_finish_ioend(ioend);
} else {
- xfs_destroy_ioend(ioend);
+ /*
+ * A direct I/O write ioend starts it's life in unwritten
+ * state in case they map an unwritten extent. This write
+ * didn't map an unwritten extent so switch it's completion
+ * handler.
+ */
+ INIT_WORK(&ioend->io_work, xfs_end_bio_written);
+ xfs_finish_ioend(ioend);
}
/*
@@ -1392,15 +1465,15 @@ xfs_vm_direct_IO(
if (error)
return -error;
- iocb->private = xfs_alloc_ioend(inode, IOMAP_UNWRITTEN);
-
if (rw == WRITE) {
+ iocb->private = xfs_alloc_ioend(inode, IOMAP_UNWRITTEN);
ret = blockdev_direct_IO_own_locking(rw, iocb, inode,
iomap.iomap_target->bt_bdev,
iov, offset, nr_segs,
xfs_get_blocks_direct,
xfs_end_io_direct);
} else {
+ iocb->private = xfs_alloc_ioend(inode, IOMAP_READ);
ret = blockdev_direct_IO_no_locking(rw, iocb, inode,
iomap.iomap_target->bt_bdev,
iov, offset, nr_segs,
diff --git a/fs/xfs/linux-2.6/xfs_buf.c b/fs/xfs/linux-2.6/xfs_buf.c
index 69e9e80735d..fe4f66a5af1 100644
--- a/fs/xfs/linux-2.6/xfs_buf.c
+++ b/fs/xfs/linux-2.6/xfs_buf.c
@@ -1426,7 +1426,7 @@ xfs_free_bufhash(
/*
* buftarg list for delwrite queue processing
*/
-LIST_HEAD(xfs_buftarg_list);
+static LIST_HEAD(xfs_buftarg_list);
static DEFINE_SPINLOCK(xfs_buftarg_lock);
STATIC void
@@ -1867,3 +1867,11 @@ xfs_buf_terminate(void)
ktrace_free(xfs_buf_trace_buf);
#endif
}
+
+#ifdef CONFIG_KDB_MODULES
+struct list_head *
+xfs_get_buftarg_list(void)
+{
+ return &xfs_buftarg_list;
+}
+#endif
diff --git a/fs/xfs/linux-2.6/xfs_buf.h b/fs/xfs/linux-2.6/xfs_buf.h
index 9e8ef8fef39..b6241f6201a 100644
--- a/fs/xfs/linux-2.6/xfs_buf.h
+++ b/fs/xfs/linux-2.6/xfs_buf.h
@@ -411,6 +411,9 @@ extern void xfs_free_buftarg(xfs_buftarg_t *, int);
extern void xfs_wait_buftarg(xfs_buftarg_t *);
extern int xfs_setsize_buftarg(xfs_buftarg_t *, unsigned int, unsigned int);
extern int xfs_flush_buftarg(xfs_buftarg_t *, int);
+#ifdef CONFIG_KDB_MODULES
+extern struct list_head *xfs_get_buftarg_list(void);
+#endif
#define xfs_getsize_buftarg(buftarg) block_size((buftarg)->bt_bdev)
#define xfs_readonly_buftarg(buftarg) bdev_read_only((buftarg)->bt_bdev)
diff --git a/fs/xfs/linux-2.6/xfs_fs_subr.c b/fs/xfs/linux-2.6/xfs_fs_subr.c
index dc0562828e7..2eb87cd082a 100644
--- a/fs/xfs/linux-2.6/xfs_fs_subr.c
+++ b/fs/xfs/linux-2.6/xfs_fs_subr.c
@@ -35,7 +35,7 @@ fs_tosspages(
truncate_inode_pages(ip->i_mapping, first);
}
-void
+int
fs_flushinval_pages(
bhv_desc_t *bdp,
xfs_off_t first,
@@ -44,13 +44,16 @@ fs_flushinval_pages(
{
bhv_vnode_t *vp = BHV_TO_VNODE(bdp);
struct inode *ip = vn_to_inode(vp);
+ int ret = 0;
if (VN_CACHED(vp)) {
if (VN_TRUNC(vp))
VUNTRUNCATE(vp);
- filemap_write_and_wait(ip->i_mapping);
- truncate_inode_pages(ip->i_mapping, first);
+ ret = filemap_write_and_wait(ip->i_mapping);
+ if (!ret)
+ truncate_inode_pages(ip->i_mapping, first);
}
+ return ret;
}
int
@@ -63,14 +66,18 @@ fs_flush_pages(
{
bhv_vnode_t *vp = BHV_TO_VNODE(bdp);
struct inode *ip = vn_to_inode(vp);
+ int ret = 0;
+ int ret2;
if (VN_DIRTY(vp)) {
if (VN_TRUNC(vp))
VUNTRUNCATE(vp);
- filemap_fdatawrite(ip->i_mapping);
+ ret = filemap_fdatawrite(ip->i_mapping);
if (flags & XFS_B_ASYNC)
- return 0;
- filemap_fdatawait(ip->i_mapping);
+ return ret;
+ ret2 = filemap_fdatawait(ip->i_mapping);
+ if (!ret)
+ ret = ret2;
}
- return 0;
+ return ret;
}
diff --git a/fs/xfs/linux-2.6/xfs_fs_subr.h b/fs/xfs/linux-2.6/xfs_fs_subr.h
index aee9ccdd18f..c1b53118a30 100644
--- a/fs/xfs/linux-2.6/xfs_fs_subr.h
+++ b/fs/xfs/linux-2.6/xfs_fs_subr.h
@@ -23,7 +23,7 @@ extern int fs_noerr(void);
extern int fs_nosys(void);
extern void fs_noval(void);
extern void fs_tosspages(bhv_desc_t *, xfs_off_t, xfs_off_t, int);
-extern void fs_flushinval_pages(bhv_desc_t *, xfs_off_t, xfs_off_t, int);
+extern int fs_flushinval_pages(bhv_desc_t *, xfs_off_t, xfs_off_t, int);
extern int fs_flush_pages(bhv_desc_t *, xfs_off_t, xfs_off_t, uint64_t, int);
#endif /* __XFS_FS_SUBR_H__ */
diff --git a/fs/xfs/linux-2.6/xfs_lrw.c b/fs/xfs/linux-2.6/xfs_lrw.c
index ff8d64eba9f..ed90403f0ee 100644
--- a/fs/xfs/linux-2.6/xfs_lrw.c
+++ b/fs/xfs/linux-2.6/xfs_lrw.c
@@ -159,7 +159,7 @@ xfs_iozero(
if (status)
goto unlock;
- memclear_highpage_flush(page, offset, bytes);
+ zero_user_page(page, offset, bytes, KM_USER0);
status = mapping->a_ops->commit_write(NULL, page, offset,
offset + bytes);
@@ -191,7 +191,7 @@ xfs_read(
struct file *file = iocb->ki_filp;
struct inode *inode = file->f_mapping->host;
size_t size = 0;
- ssize_t ret;
+ ssize_t ret = 0;
xfs_fsize_t n;
xfs_inode_t *ip;
xfs_mount_t *mp;
@@ -224,7 +224,7 @@ xfs_read(
mp->m_rtdev_targp : mp->m_ddev_targp;
if ((*offset & target->bt_smask) ||
(size & target->bt_smask)) {
- if (*offset == ip->i_d.di_size) {
+ if (*offset == ip->i_size) {
return (0);
}
return -XFS_ERROR(EINVAL);
@@ -263,9 +263,13 @@ xfs_read(
if (unlikely(ioflags & IO_ISDIRECT)) {
if (VN_CACHED(vp))
- bhv_vop_flushinval_pages(vp, ctooff(offtoct(*offset)),
+ ret = bhv_vop_flushinval_pages(vp, ctooff(offtoct(*offset)),
-1, FI_REMAPF_LOCKED);
mutex_unlock(&inode->i_mutex);
+ if (ret) {
+ xfs_iunlock(ip, XFS_IOLOCK_SHARED);
+ return ret;
+ }
}
xfs_rw_enter_trace(XFS_READ_ENTER, &ip->i_iocore,
@@ -383,9 +387,10 @@ xfs_splice_write(
{
xfs_inode_t *ip = XFS_BHVTOI(bdp);
xfs_mount_t *mp = ip->i_mount;
+ xfs_iocore_t *io = &ip->i_iocore;
ssize_t ret;
struct inode *inode = outfilp->f_mapping->host;
- xfs_fsize_t isize;
+ xfs_fsize_t isize, new_size;
XFS_STATS_INC(xs_write_calls);
if (XFS_FORCED_SHUTDOWN(ip->i_mount))
@@ -406,6 +411,14 @@ xfs_splice_write(
return -error;
}
}
+
+ new_size = *ppos + count;
+
+ xfs_ilock(ip, XFS_ILOCK_EXCL);
+ if (new_size > ip->i_size)
+ io->io_new_size = new_size;
+ xfs_iunlock(ip, XFS_ILOCK_EXCL);
+
xfs_rw_enter_trace(XFS_SPLICE_WRITE_ENTER, &ip->i_iocore,
pipe, count, *ppos, ioflags);
ret = generic_file_splice_write(pipe, outfilp, ppos, count, flags);
@@ -416,14 +429,18 @@ xfs_splice_write(
if (unlikely(ret < 0 && ret != -EFAULT && *ppos > isize))
*ppos = isize;
- if (*ppos > ip->i_d.di_size) {
+ if (*ppos > ip->i_size) {
xfs_ilock(ip, XFS_ILOCK_EXCL);
- if (*ppos > ip->i_d.di_size) {
- ip->i_d.di_size = *ppos;
- i_size_write(inode, *ppos);
- ip->i_update_core = 1;
- ip->i_update_size = 1;
- }
+ if (*ppos > ip->i_size)
+ ip->i_size = *ppos;
+ xfs_iunlock(ip, XFS_ILOCK_EXCL);
+ }
+
+ if (io->io_new_size) {
+ xfs_ilock(ip, XFS_ILOCK_EXCL);
+ io->io_new_size = 0;
+ if (ip->i_d.di_size > ip->i_size)
+ ip->i_d.di_size = ip->i_size;
xfs_iunlock(ip, XFS_ILOCK_EXCL);
}
xfs_iunlock(ip, XFS_IOLOCK_EXCL);
@@ -639,37 +656,21 @@ xfs_write(
xfs_fsize_t isize, new_size;
xfs_iocore_t *io;
bhv_vnode_t *vp;
- unsigned long seg;
int iolock;
int eventsent = 0;
bhv_vrwlock_t locktype;
size_t ocount = 0, count;
loff_t pos;
- int need_i_mutex = 1, need_flush = 0;
+ int need_i_mutex;
XFS_STATS_INC(xs_write_calls);
vp = BHV_TO_VNODE(bdp);
xip = XFS_BHVTOI(bdp);
- for (seg = 0; seg < segs; seg++) {
- const struct iovec *iv = &iovp[seg];
-
- /*
- * If any segment has a negative length, or the cumulative
- * length ever wraps negative then return -EINVAL.
- */
- ocount += iv->iov_len;
- if (unlikely((ssize_t)(ocount|iv->iov_len) < 0))
- return -EINVAL;
- if (access_ok(VERIFY_READ, iv->iov_base, iv->iov_len))
- continue;
- if (seg == 0)
- return -EFAULT;
- segs = seg;
- ocount -= iv->iov_len; /* This segment is no good */
- break;
- }
+ error = generic_segment_checks(iovp, &segs, &ocount, VERIFY_READ);
+ if (error)
+ return error;
count = ocount;
pos = *offset;
@@ -685,39 +686,20 @@ xfs_write(
if (XFS_FORCED_SHUTDOWN(mp))
return -EIO;
- if (ioflags & IO_ISDIRECT) {
- xfs_buftarg_t *target =
- (xip->i_d.di_flags & XFS_DIFLAG_REALTIME) ?
- mp->m_rtdev_targp : mp->m_ddev_targp;
-
- if ((pos & target->bt_smask) || (count & target->bt_smask))
- return XFS_ERROR(-EINVAL);
-
- if (!VN_CACHED(vp) && pos < i_size_read(inode))
- need_i_mutex = 0;
-
- if (VN_CACHED(vp))
- need_flush = 1;
- }
-
relock:
- if (need_i_mutex) {
+ if (ioflags & IO_ISDIRECT) {
+ iolock = XFS_IOLOCK_SHARED;
+ locktype = VRWLOCK_WRITE_DIRECT;
+ need_i_mutex = 0;
+ } else {
iolock = XFS_IOLOCK_EXCL;
locktype = VRWLOCK_WRITE;
-
+ need_i_mutex = 1;
mutex_lock(&inode->i_mutex);
- } else {
- iolock = XFS_IOLOCK_SHARED;
- locktype = VRWLOCK_WRITE_DIRECT;
}
xfs_ilock(xip, XFS_ILOCK_EXCL|iolock);
- isize = i_size_read(inode);
-
- if (file->f_flags & O_APPEND)
- *offset = isize;
-
start:
error = -generic_write_checks(file, &pos, &count,
S_ISBLK(inode->i_mode));
@@ -726,13 +708,8 @@ start:
goto out_unlock_mutex;
}
- new_size = pos + count;
- if (new_size > isize)
- io->io_new_size = new_size;
-
if ((DM_EVENT_ENABLED(vp->v_vfsp, xip, DM_EVENT_WRITE) &&
!(ioflags & IO_INVIS) && !eventsent)) {
- loff_t savedsize = pos;
int dmflags = FILP_DELAY_FLAG(file);
if (need_i_mutex)
@@ -743,8 +720,7 @@ start:
pos, count,
dmflags, &locktype);
if (error) {
- xfs_iunlock(xip, iolock);
- goto out_unlock_mutex;
+ goto out_unlock_internal;
}
xfs_ilock(xip, XFS_ILOCK_EXCL);
eventsent = 1;
@@ -756,12 +732,35 @@ start:
* event prevents another call to XFS_SEND_DATA, which is
* what allows the size to change in the first place.
*/
- if ((file->f_flags & O_APPEND) && savedsize != isize) {
- pos = isize = xip->i_d.di_size;
+ if ((file->f_flags & O_APPEND) && pos != xip->i_size)
+ goto start;
+ }
+
+ if (ioflags & IO_ISDIRECT) {
+ xfs_buftarg_t *target =
+ (xip->i_d.di_flags & XFS_DIFLAG_REALTIME) ?
+ mp->m_rtdev_targp : mp->m_ddev_targp;
+
+ if ((pos & target->bt_smask) || (count & target->bt_smask)) {
+ xfs_iunlock(xip, XFS_ILOCK_EXCL|iolock);
+ return XFS_ERROR(-EINVAL);
+ }
+
+ if (!need_i_mutex && (VN_CACHED(vp) || pos > xip->i_size)) {
+ xfs_iunlock(xip, XFS_ILOCK_EXCL|iolock);
+ iolock = XFS_IOLOCK_EXCL;
+ locktype = VRWLOCK_WRITE;
+ need_i_mutex = 1;
+ mutex_lock(&inode->i_mutex);
+ xfs_ilock(xip, XFS_ILOCK_EXCL|iolock);
goto start;
}
}
+ new_size = pos + count;
+ if (new_size > xip->i_size)
+ io->io_new_size = new_size;
+
if (likely(!(ioflags & IO_INVIS))) {
file_update_time(file);
xfs_ichgtime_fast(xip, inode,
@@ -777,11 +776,11 @@ start:
* to zero it out up to the new size.
*/
- if (pos > isize) {
- error = xfs_zero_eof(BHV_TO_VNODE(bdp), io, pos, isize);
+ if (pos > xip->i_size) {
+ error = xfs_zero_eof(BHV_TO_VNODE(bdp), io, pos, xip->i_size);
if (error) {
- xfs_iunlock(xip, XFS_ILOCK_EXCL|iolock);
- goto out_unlock_mutex;
+ xfs_iunlock(xip, XFS_ILOCK_EXCL);
+ goto out_unlock_internal;
}
}
xfs_iunlock(xip, XFS_ILOCK_EXCL);
@@ -801,8 +800,7 @@ start:
if (likely(!error))
error = -remove_suid(file->f_path.dentry);
if (unlikely(error)) {
- xfs_iunlock(xip, iolock);
- goto out_unlock_mutex;
+ goto out_unlock_internal;
}
}
@@ -811,11 +809,14 @@ retry:
current->backing_dev_info = mapping->backing_dev_info;
if ((ioflags & IO_ISDIRECT)) {
- if (need_flush) {
+ if (VN_CACHED(vp)) {
+ WARN_ON(need_i_mutex == 0);
xfs_inval_cached_trace(io, pos, -1,
ctooff(offtoct(pos)), -1);
- bhv_vop_flushinval_pages(vp, ctooff(offtoct(pos)),
+ error = bhv_vop_flushinval_pages(vp, ctooff(offtoct(pos)),
-1, FI_REMAPF_LOCKED);
+ if (error)
+ goto out_unlock_internal;
}
if (need_i_mutex) {
@@ -843,7 +844,6 @@ retry:
pos += ret;
count -= ret;
- need_i_mutex = 1;
ioflags &= ~IO_ISDIRECT;
xfs_iunlock(xip, iolock);
goto relock;
@@ -870,12 +870,12 @@ retry:
error = XFS_SEND_NAMESP(xip->i_mount, DM_EVENT_NOSPACE, vp,
DM_RIGHT_NULL, vp, DM_RIGHT_NULL, NULL, NULL,
0, 0, 0); /* Delay flag intentionally unused */
- if (error)
- goto out_nounlocks;
if (need_i_mutex)
mutex_lock(&inode->i_mutex);
xfs_rwlock(bdp, locktype);
- pos = xip->i_d.di_size;
+ if (error)
+ goto out_unlock_internal;
+ pos = xip->i_size;
ret = 0;
goto retry;
}
@@ -884,14 +884,10 @@ retry:
if (unlikely(ret < 0 && ret != -EFAULT && *offset > isize))
*offset = isize;
- if (*offset > xip->i_d.di_size) {
+ if (*offset > xip->i_size) {
xfs_ilock(xip, XFS_ILOCK_EXCL);
- if (*offset > xip->i_d.di_size) {
- xip->i_d.di_size = *offset;
- i_size_write(inode, *offset);
- xip->i_update_core = 1;
- xip->i_update_size = 1;
- }
+ if (*offset > xip->i_size)
+ xip->i_size = *offset;
xfs_iunlock(xip, XFS_ILOCK_EXCL);
}
@@ -913,16 +909,31 @@ retry:
error = sync_page_range(inode, mapping, pos, ret);
if (!error)
- error = ret;
- return error;
+ error = -ret;
+ if (need_i_mutex)
+ mutex_lock(&inode->i_mutex);
+ xfs_rwlock(bdp, locktype);
}
out_unlock_internal:
+ if (io->io_new_size) {
+ xfs_ilock(xip, XFS_ILOCK_EXCL);
+ io->io_new_size = 0;
+ /*
+ * If this was a direct or synchronous I/O that failed (such
+ * as ENOSPC) then part of the I/O may have been written to
+ * disk before the error occured. In this case the on-disk
+ * file size may have been adjusted beyond the in-memory file
+ * size and now needs to be truncated back.
+ */
+ if (xip->i_d.di_size > xip->i_size)
+ xip->i_d.di_size = xip->i_size;
+ xfs_iunlock(xip, XFS_ILOCK_EXCL);
+ }
xfs_rwunlock(bdp, locktype);
out_unlock_mutex:
if (need_i_mutex)
mutex_unlock(&inode->i_mutex);
- out_nounlocks:
return -error;
}
diff --git a/fs/xfs/linux-2.6/xfs_super.c b/fs/xfs/linux-2.6/xfs_super.c
index 14e2cbe5a8d..bf9a9d5909b 100644
--- a/fs/xfs/linux-2.6/xfs_super.c
+++ b/fs/xfs/linux-2.6/xfs_super.c
@@ -360,8 +360,7 @@ xfs_fs_inode_init_once(
kmem_zone_t *zonep,
unsigned long flags)
{
- if (flags & SLAB_CTOR_CONSTRUCTOR)
- inode_init_once(vn_to_inode((bhv_vnode_t *)vnode));
+ inode_init_once(vn_to_inode((bhv_vnode_t *)vnode));
}
STATIC int
diff --git a/fs/xfs/linux-2.6/xfs_vnode.h b/fs/xfs/linux-2.6/xfs_vnode.h
index b76118cf489..d1b2d01843d 100644
--- a/fs/xfs/linux-2.6/xfs_vnode.h
+++ b/fs/xfs/linux-2.6/xfs_vnode.h
@@ -194,7 +194,7 @@ typedef int (*vop_attr_list_t)(bhv_desc_t *, char *, int, int,
typedef void (*vop_link_removed_t)(bhv_desc_t *, bhv_vnode_t *, int);
typedef void (*vop_vnode_change_t)(bhv_desc_t *, bhv_vchange_t, __psint_t);
typedef void (*vop_ptossvp_t)(bhv_desc_t *, xfs_off_t, xfs_off_t, int);
-typedef void (*vop_pflushinvalvp_t)(bhv_desc_t *, xfs_off_t, xfs_off_t, int);
+typedef int (*vop_pflushinvalvp_t)(bhv_desc_t *, xfs_off_t, xfs_off_t, int);
typedef int (*vop_pflushvp_t)(bhv_desc_t *, xfs_off_t, xfs_off_t,
uint64_t, int);
typedef int (*vop_iflush_t)(bhv_desc_t *, int);
diff --git a/fs/xfs/quota/xfs_dquot.c b/fs/xfs/quota/xfs_dquot.c
index 4adaf13aac6..cfdd35ee9f7 100644
--- a/fs/xfs/quota/xfs_dquot.c
+++ b/fs/xfs/quota/xfs_dquot.c
@@ -753,8 +753,7 @@ xfs_qm_idtodq(
goto error0;
}
if (tp) {
- if ((error = xfs_trans_commit(tp, XFS_TRANS_RELEASE_LOG_RES,
- NULL)))
+ if ((error = xfs_trans_commit(tp, XFS_TRANS_RELEASE_LOG_RES)))
goto error1;
}
diff --git a/fs/xfs/quota/xfs_qm.c b/fs/xfs/quota/xfs_qm.c
index 1de2acdc7f7..3e4a8ad8a34 100644
--- a/fs/xfs/quota/xfs_qm.c
+++ b/fs/xfs/quota/xfs_qm.c
@@ -388,6 +388,17 @@ xfs_qm_mount_quotas(
return XFS_ERROR(error);
}
}
+ /*
+ * If one type of quotas is off, then it will lose its
+ * quotachecked status, since we won't be doing accounting for
+ * that type anymore.
+ */
+ if (!XFS_IS_UQUOTA_ON(mp)) {
+ mp->m_qflags &= ~XFS_UQUOTA_CHKD;
+ }
+ if (!(XFS_IS_GQUOTA_ON(mp) || XFS_IS_PQUOTA_ON(mp))) {
+ mp->m_qflags &= ~XFS_OQUOTA_CHKD;
+ }
write_changes:
/*
@@ -1453,8 +1464,7 @@ xfs_qm_qino_alloc(
XFS_SB_UNLOCK(mp, s);
xfs_mod_sb(tp, sbfields);
- if ((error = xfs_trans_commit(tp, XFS_TRANS_RELEASE_LOG_RES,
- NULL))) {
+ if ((error = xfs_trans_commit(tp, XFS_TRANS_RELEASE_LOG_RES))) {
xfs_fs_cmn_err(CE_ALERT, mp, "XFS qino_alloc failed!");
return error;
}
@@ -2405,7 +2415,7 @@ xfs_qm_write_sb_changes(
}
xfs_mod_sb(tp, flags);
- (void) xfs_trans_commit(tp, 0, NULL);
+ (void) xfs_trans_commit(tp, 0);
return 0;
}
diff --git a/fs/xfs/quota/xfs_qm_syscalls.c b/fs/xfs/quota/xfs_qm_syscalls.c
index 716f562aa8b..2df67fd913e 100644
--- a/fs/xfs/quota/xfs_qm_syscalls.c
+++ b/fs/xfs/quota/xfs_qm_syscalls.c
@@ -456,9 +456,7 @@ xfs_qm_scall_quotaon(
||
((flags & XFS_PQUOTA_ACCT) == 0 &&
(mp->m_sb.sb_qflags & XFS_PQUOTA_ACCT) == 0 &&
- (flags & XFS_OQUOTA_ENFD))
- ||
- ((flags & XFS_GQUOTA_ACCT) == 0 &&
+ (flags & XFS_GQUOTA_ACCT) == 0 &&
(mp->m_sb.sb_qflags & XFS_GQUOTA_ACCT) == 0 &&
(flags & XFS_OQUOTA_ENFD))) {
qdprintk("Can't enforce without acct, flags=%x sbflags=%x\n",
@@ -735,7 +733,7 @@ xfs_qm_scall_setqlim(
xfs_trans_log_dquot(tp, dqp);
xfs_dqtrace_entry(dqp, "Q_SETQLIM: COMMIT");
- xfs_trans_commit(tp, 0, NULL);
+ xfs_trans_commit(tp, 0);
xfs_qm_dqprint(dqp);
xfs_qm_dqrele(dqp);
mutex_unlock(&(XFS_QI_QOFFLOCK(mp)));
@@ -809,7 +807,7 @@ xfs_qm_log_quotaoff_end(
* We don't care about quotoff's performance.
*/
xfs_trans_set_sync(tp);
- error = xfs_trans_commit(tp, 0, NULL);
+ error = xfs_trans_commit(tp, 0);
return (error);
}
@@ -852,7 +850,7 @@ xfs_qm_log_quotaoff(
* We don't care about quotoff's performance.
*/
xfs_trans_set_sync(tp);
- error = xfs_trans_commit(tp, 0, NULL);
+ error = xfs_trans_commit(tp, 0);
error0:
if (error) {
@@ -911,14 +909,19 @@ xfs_qm_export_dquot(
* gets turned off. No need to confuse the user level code,
* so return zeroes in that case.
*/
- if (! XFS_IS_QUOTA_ENFORCED(mp)) {
+ if ((!XFS_IS_UQUOTA_ENFORCED(mp) && src->d_flags == XFS_DQ_USER) ||
+ (!XFS_IS_OQUOTA_ENFORCED(mp) &&
+ (src->d_flags & (XFS_DQ_PROJ | XFS_DQ_GROUP)))) {
dst->d_btimer = 0;
dst->d_itimer = 0;
dst->d_rtbtimer = 0;
}
#ifdef DEBUG
- if (XFS_IS_QUOTA_ENFORCED(mp) && dst->d_id != 0) {
+ if (((XFS_IS_UQUOTA_ENFORCED(mp) && dst->d_flags == XFS_USER_QUOTA) ||
+ (XFS_IS_OQUOTA_ENFORCED(mp) &&
+ (dst->d_flags & (XFS_PROJ_QUOTA | XFS_GROUP_QUOTA)))) &&
+ dst->d_id != 0) {
if (((int) dst->d_bcount >= (int) dst->d_blk_softlimit) &&
(dst->d_blk_softlimit > 0)) {
ASSERT(dst->d_btimer != 0);
diff --git a/fs/xfs/quota/xfs_trans_dquot.c b/fs/xfs/quota/xfs_trans_dquot.c
index d7491e7b1f3..7de6874bf1b 100644
--- a/fs/xfs/quota/xfs_trans_dquot.c
+++ b/fs/xfs/quota/xfs_trans_dquot.c
@@ -656,7 +656,9 @@ xfs_trans_dqresv(
if ((flags & XFS_QMOPT_FORCE_RES) == 0 &&
dqp->q_core.d_id &&
- XFS_IS_QUOTA_ENFORCED(dqp->q_mount)) {
+ ((XFS_IS_UQUOTA_ENFORCED(dqp->q_mount) && XFS_QM_ISUDQ(dqp)) ||
+ (XFS_IS_OQUOTA_ENFORCED(dqp->q_mount) &&
+ (XFS_QM_ISPDQ(dqp) || XFS_QM_ISGDQ(dqp))))) {
#ifdef QUOTADEBUG
cmn_err(CE_DEBUG, "BLK Res: nblks=%ld + resbcount=%Ld"
" > hardlimit=%Ld?", nblks, *resbcountp, hardlimit);
diff --git a/fs/xfs/support/debug.c b/fs/xfs/support/debug.c
index 08bbd3cb87a..f45a49ffd3a 100644
--- a/fs/xfs/support/debug.c
+++ b/fs/xfs/support/debug.c
@@ -81,20 +81,3 @@ assfail(char *expr, char *file, int line)
printk("Assertion failed: %s, file: %s, line: %d\n", expr, file, line);
BUG();
}
-
-#if ((defined(DEBUG) || defined(INDUCE_IO_ERRROR)) && !defined(NO_WANT_RANDOM))
-unsigned long random(void)
-{
- static unsigned long RandomValue = 1;
- /* cycles pseudo-randomly through all values between 1 and 2^31 - 2 */
- register long rv = RandomValue;
- register long lo;
- register long hi;
-
- hi = rv / 127773;
- lo = rv % 127773;
- rv = 16807 * lo - 2836 * hi;
- if (rv <= 0) rv += 2147483647;
- return RandomValue = rv;
-}
-#endif /* DEBUG || INDUCE_IO_ERRROR || !NO_WANT_RANDOM */
diff --git a/fs/xfs/support/debug.h b/fs/xfs/support/debug.h
index 2a70cc605ae..a27a7c8c052 100644
--- a/fs/xfs/support/debug.h
+++ b/fs/xfs/support/debug.h
@@ -50,7 +50,7 @@ extern void assfail(char *expr, char *f, int l);
#else /* DEBUG */
# define ASSERT(expr) ASSERT_ALWAYS(expr)
-extern unsigned long random(void);
+# include <linux/random.h>
#ifndef STATIC
# define STATIC noinline
diff --git a/fs/xfs/xfs_alloc.c b/fs/xfs/xfs_alloc.c
index e80dda3437d..8e9a40aa0cd 100644
--- a/fs/xfs/xfs_alloc.c
+++ b/fs/xfs/xfs_alloc.c
@@ -764,7 +764,7 @@ xfs_alloc_ag_vextent_near(
*/
int dofirst; /* set to do first algorithm */
- dofirst = random() & 1;
+ dofirst = random32() & 1;
#endif
/*
* Get a cursor for the by-size btree.
diff --git a/fs/xfs/xfs_attr.c b/fs/xfs/xfs_attr.c
index 9d358ffce4e..7ce44a7b88a 100644
--- a/fs/xfs/xfs_attr.c
+++ b/fs/xfs/xfs_attr.c
@@ -328,8 +328,7 @@ xfs_attr_set_int(xfs_inode_t *dp, const char *name, int namelen,
xfs_trans_set_sync(args.trans);
}
err2 = xfs_trans_commit(args.trans,
- XFS_TRANS_RELEASE_LOG_RES,
- NULL);
+ XFS_TRANS_RELEASE_LOG_RES);
xfs_iunlock(dp, XFS_ILOCK_EXCL);
/*
@@ -397,8 +396,7 @@ xfs_attr_set_int(xfs_inode_t *dp, const char *name, int namelen,
* Commit the last in the sequence of transactions.
*/
xfs_trans_log_inode(args.trans, dp, XFS_ILOG_CORE);
- error = xfs_trans_commit(args.trans, XFS_TRANS_RELEASE_LOG_RES,
- NULL);
+ error = xfs_trans_commit(args.trans, XFS_TRANS_RELEASE_LOG_RES);
xfs_iunlock(dp, XFS_ILOCK_EXCL);
/*
@@ -544,8 +542,7 @@ xfs_attr_remove_int(xfs_inode_t *dp, const char *name, int namelen, int flags)
* Commit the last in the sequence of transactions.
*/
xfs_trans_log_inode(args.trans, dp, XFS_ILOG_CORE);
- error = xfs_trans_commit(args.trans, XFS_TRANS_RELEASE_LOG_RES,
- NULL);
+ error = xfs_trans_commit(args.trans, XFS_TRANS_RELEASE_LOG_RES);
xfs_iunlock(dp, XFS_ILOCK_EXCL);
/*
@@ -859,8 +856,7 @@ xfs_attr_inactive(xfs_inode_t *dp)
* Commit the last in the sequence of transactions.
*/
xfs_trans_log_inode(trans, dp, XFS_ILOG_CORE);
- error = xfs_trans_commit(trans, XFS_TRANS_RELEASE_LOG_RES,
- NULL);
+ error = xfs_trans_commit(trans, XFS_TRANS_RELEASE_LOG_RES);
xfs_iunlock(dp, XFS_ILOCK_EXCL);
return(error);
diff --git a/fs/xfs/xfs_attr_leaf.c b/fs/xfs/xfs_attr_leaf.c
index 8eab73e8340..81f45dae1c5 100644
--- a/fs/xfs/xfs_attr_leaf.c
+++ b/fs/xfs/xfs_attr_leaf.c
@@ -3053,7 +3053,7 @@ xfs_attr_rolltrans(xfs_trans_t **transp, xfs_inode_t *dp)
* is in progress. The caller takes the responsibility to cancel
* the duplicate transaction that gets returned.
*/
- if ((error = xfs_trans_commit(trans, 0, NULL)))
+ if ((error = xfs_trans_commit(trans, 0)))
return (error);
trans = *transp;
diff --git a/fs/xfs/xfs_bmap.c b/fs/xfs/xfs_bmap.c
index 87795188ced..b1ea26e40aa 100644
--- a/fs/xfs/xfs_bmap.c
+++ b/fs/xfs/xfs_bmap.c
@@ -130,7 +130,6 @@ STATIC int /* error */
xfs_bmap_add_extent_hole_delay(
xfs_inode_t *ip, /* incore inode pointer */
xfs_extnum_t idx, /* extent number to update/insert */
- xfs_btree_cur_t *cur, /* if null, not a btree */
xfs_bmbt_irec_t *new, /* new data to add to file extents */
int *logflagsp,/* inode logging flags */
xfs_extdelta_t *delta, /* Change made to incore extents */
@@ -399,7 +398,6 @@ xfs_bmap_count_leaves(
STATIC int
xfs_bmap_disk_count_leaves(
- xfs_ifork_t *ifp,
xfs_extnum_t idx,
xfs_bmbt_block_t *block,
int numrecs,
@@ -580,7 +578,7 @@ xfs_bmap_add_extent(
if (cur)
ASSERT((cur->bc_private.b.flags &
XFS_BTCUR_BPRV_WASDEL) == 0);
- if ((error = xfs_bmap_add_extent_hole_delay(ip, idx, cur, new,
+ if ((error = xfs_bmap_add_extent_hole_delay(ip, idx, new,
&logflags, delta, rsvd)))
goto done;
}
@@ -1841,7 +1839,6 @@ STATIC int /* error */
xfs_bmap_add_extent_hole_delay(
xfs_inode_t *ip, /* incore inode pointer */
xfs_extnum_t idx, /* extent number to update/insert */
- xfs_btree_cur_t *cur, /* if null, not a btree */
xfs_bmbt_irec_t *new, /* new data to add to file extents */
int *logflagsp, /* inode logging flags */
xfs_extdelta_t *delta, /* Change made to incore extents */
@@ -4071,7 +4068,7 @@ xfs_bmap_add_attrfork(
}
if ((error = xfs_bmap_finish(&tp, &flist, &committed)))
goto error2;
- error = xfs_trans_commit(tp, XFS_TRANS_PERM_LOG_RES, NULL);
+ error = xfs_trans_commit(tp, XFS_TRANS_PERM_LOG_RES);
ASSERT(ip->i_df.if_ext_max ==
XFS_IFORK_DSIZE(ip) / (uint)sizeof(xfs_bmbt_rec_t));
return error;
@@ -4227,7 +4224,7 @@ xfs_bmap_finish(
logres = ntp->t_log_res;
logcount = ntp->t_log_count;
ntp = xfs_trans_dup(*tp);
- error = xfs_trans_commit(*tp, 0, NULL);
+ error = xfs_trans_commit(*tp, 0);
*tp = ntp;
*committed = 1;
/*
@@ -4447,8 +4444,11 @@ xfs_bmap_one_block(
xfs_bmbt_irec_t s; /* internal version of extent */
#ifndef DEBUG
- if (whichfork == XFS_DATA_FORK)
- return ip->i_d.di_size == ip->i_mount->m_sb.sb_blocksize;
+ if (whichfork == XFS_DATA_FORK) {
+ return ((ip->i_d.di_mode & S_IFMT) == S_IFREG) ?
+ (ip->i_size == ip->i_mount->m_sb.sb_blocksize) :
+ (ip->i_d.di_size == ip->i_mount->m_sb.sb_blocksize);
+ }
#endif /* !DEBUG */
if (XFS_IFORK_NEXTENTS(ip, whichfork) != 1)
return 0;
@@ -4460,7 +4460,7 @@ xfs_bmap_one_block(
xfs_bmbt_get_all(ep, &s);
rval = s.br_startoff == 0 && s.br_blockcount == 1;
if (rval && whichfork == XFS_DATA_FORK)
- ASSERT(ip->i_d.di_size == ip->i_mount->m_sb.sb_blocksize);
+ ASSERT(ip->i_size == ip->i_mount->m_sb.sb_blocksize);
return rval;
}
@@ -5820,7 +5820,7 @@ xfs_getbmap(
fixlen = XFS_MAXIOFFSET(mp);
} else {
prealloced = 0;
- fixlen = ip->i_d.di_size;
+ fixlen = ip->i_size;
}
} else {
prealloced = 0;
@@ -5844,7 +5844,8 @@ xfs_getbmap(
xfs_ilock(ip, XFS_IOLOCK_SHARED);
- if (whichfork == XFS_DATA_FORK && ip->i_delayed_blks) {
+ if (whichfork == XFS_DATA_FORK &&
+ (ip->i_delayed_blks || ip->i_size > ip->i_d.di_size)) {
/* xfs_fsize_t last_byte = xfs_file_last_byte(ip); */
error = bhv_vop_flush_pages(vp, (xfs_off_t)0, -1, 0, FI_REMAPF);
}
@@ -6425,8 +6426,8 @@ xfs_bmap_count_tree(
for (;;) {
nextbno = be64_to_cpu(block->bb_rightsib);
numrecs = be16_to_cpu(block->bb_numrecs);
- if (unlikely(xfs_bmap_disk_count_leaves(ifp,
- 0, block, numrecs, count) < 0)) {
+ if (unlikely(xfs_bmap_disk_count_leaves(0,
+ block, numrecs, count) < 0)) {
xfs_trans_brelse(tp, bp);
XFS_ERROR_REPORT("xfs_bmap_count_tree(2)",
XFS_ERRLEVEL_LOW, mp);
@@ -6472,7 +6473,6 @@ xfs_bmap_count_leaves(
*/
int
xfs_bmap_disk_count_leaves(
- xfs_ifork_t *ifp,
xfs_extnum_t idx,
xfs_bmbt_block_t *block,
int numrecs,
diff --git a/fs/xfs/xfs_dfrag.c b/fs/xfs/xfs_dfrag.c
index b847e6a7a3f..de35d18cc00 100644
--- a/fs/xfs/xfs_dfrag.c
+++ b/fs/xfs/xfs_dfrag.c
@@ -199,7 +199,9 @@ xfs_swap_extents(
if (VN_CACHED(tvp) != 0) {
xfs_inval_cached_trace(&tip->i_iocore, 0, -1, 0, -1);
- bhv_vop_flushinval_pages(tvp, 0, -1, FI_REMAPF_LOCKED);
+ error = bhv_vop_flushinval_pages(tvp, 0, -1, FI_REMAPF_LOCKED);
+ if (error)
+ goto error0;
}
/* Verify O_DIRECT for ftmp */
@@ -382,7 +384,7 @@ xfs_swap_extents(
xfs_trans_set_sync(tp);
}
- error = xfs_trans_commit(tp, XFS_TRANS_SWAPEXT, NULL);
+ error = xfs_trans_commit(tp, XFS_TRANS_SWAPEXT);
locked = 0;
error0:
diff --git a/fs/xfs/xfs_dir2_block.c b/fs/xfs/xfs_dir2_block.c
index 9d7438bba30..3accc1dcd6c 100644
--- a/fs/xfs/xfs_dir2_block.c
+++ b/fs/xfs/xfs_dir2_block.c
@@ -282,8 +282,7 @@ xfs_dir2_block_addname(
* This needs to happen before the next call to use_free.
*/
if (needscan) {
- xfs_dir2_data_freescan(mp, (xfs_dir2_data_t *)block,
- &needlog, NULL);
+ xfs_dir2_data_freescan(mp, (xfs_dir2_data_t *)block, &needlog);
needscan = 0;
}
}
@@ -333,7 +332,7 @@ xfs_dir2_block_addname(
*/
if (needscan) {
xfs_dir2_data_freescan(mp, (xfs_dir2_data_t *)block,
- &needlog, NULL);
+ &needlog);
needscan = 0;
}
/*
@@ -418,8 +417,7 @@ xfs_dir2_block_addname(
* Clean up the bestfree array and log the header, tail, and entry.
*/
if (needscan)
- xfs_dir2_data_freescan(mp, (xfs_dir2_data_t *)block, &needlog,
- NULL);
+ xfs_dir2_data_freescan(mp, (xfs_dir2_data_t *)block, &needlog);
if (needlog)
xfs_dir2_data_log_header(tp, bp);
xfs_dir2_block_log_tail(tp, bp);
@@ -798,8 +796,7 @@ xfs_dir2_block_removename(
* Fix up bestfree, log the header if necessary.
*/
if (needscan)
- xfs_dir2_data_freescan(mp, (xfs_dir2_data_t *)block, &needlog,
- NULL);
+ xfs_dir2_data_freescan(mp, (xfs_dir2_data_t *)block, &needlog);
if (needlog)
xfs_dir2_data_log_header(tp, bp);
xfs_dir2_data_check(dp, bp);
@@ -996,8 +993,7 @@ xfs_dir2_leaf_to_block(
* Scan the bestfree if we need it and log the data block header.
*/
if (needscan)
- xfs_dir2_data_freescan(mp, (xfs_dir2_data_t *)block, &needlog,
- NULL);
+ xfs_dir2_data_freescan(mp, (xfs_dir2_data_t *)block, &needlog);
if (needlog)
xfs_dir2_data_log_header(tp, dbp);
/*
diff --git a/fs/xfs/xfs_dir2_data.c b/fs/xfs/xfs_dir2_data.c
index f7c79921707..c211c37ef67 100644
--- a/fs/xfs/xfs_dir2_data.c
+++ b/fs/xfs/xfs_dir2_data.c
@@ -324,8 +324,7 @@ void
xfs_dir2_data_freescan(
xfs_mount_t *mp, /* filesystem mount point */
xfs_dir2_data_t *d, /* data block pointer */
- int *loghead, /* out: log data header */
- char *aendp) /* in: caller's endp */
+ int *loghead) /* out: log data header */
{
xfs_dir2_block_tail_t *btp; /* block tail */
xfs_dir2_data_entry_t *dep; /* active data entry */
@@ -346,9 +345,7 @@ xfs_dir2_data_freescan(
* Set up pointers.
*/
p = (char *)d->u;
- if (aendp)
- endp = aendp;
- else if (be32_to_cpu(d->hdr.magic) == XFS_DIR2_BLOCK_MAGIC) {
+ if (be32_to_cpu(d->hdr.magic) == XFS_DIR2_BLOCK_MAGIC) {
btp = XFS_DIR2_BLOCK_TAIL_P(mp, (xfs_dir2_block_t *)d);
endp = (char *)XFS_DIR2_BLOCK_LEAF_P(btp);
} else
diff --git a/fs/xfs/xfs_dir2_data.h b/fs/xfs/xfs_dir2_data.h
index a6ae2d21c40..c94c9099cfb 100644
--- a/fs/xfs/xfs_dir2_data.h
+++ b/fs/xfs/xfs_dir2_data.h
@@ -166,7 +166,7 @@ extern xfs_dir2_data_free_t *xfs_dir2_data_freefind(xfs_dir2_data_t *d,
extern xfs_dir2_data_free_t *xfs_dir2_data_freeinsert(xfs_dir2_data_t *d,
xfs_dir2_data_unused_t *dup, int *loghead);
extern void xfs_dir2_data_freescan(struct xfs_mount *mp, xfs_dir2_data_t *d,
- int *loghead, char *aendp);
+ int *loghead);
extern int xfs_dir2_data_init(struct xfs_da_args *args, xfs_dir2_db_t blkno,
struct xfs_dabuf **bpp);
extern void xfs_dir2_data_log_entry(struct xfs_trans *tp, struct xfs_dabuf *bp,
diff --git a/fs/xfs/xfs_dir2_leaf.c b/fs/xfs/xfs_dir2_leaf.c
index b1cf1fbf423..db14ea71459 100644
--- a/fs/xfs/xfs_dir2_leaf.c
+++ b/fs/xfs/xfs_dir2_leaf.c
@@ -133,8 +133,7 @@ xfs_dir2_block_to_leaf(
*/
block->hdr.magic = cpu_to_be32(XFS_DIR2_DATA_MAGIC);
if (needscan)
- xfs_dir2_data_freescan(mp, (xfs_dir2_data_t *)block, &needlog,
- NULL);
+ xfs_dir2_data_freescan(mp, (xfs_dir2_data_t *)block, &needlog);
/*
* Set up leaf tail and bests table.
*/
@@ -414,7 +413,7 @@ xfs_dir2_leaf_addname(
* Need to scan fix up the bestfree table.
*/
if (needscan)
- xfs_dir2_data_freescan(mp, data, &needlog, NULL);
+ xfs_dir2_data_freescan(mp, data, &needlog);
/*
* Need to log the data block's header.
*/
@@ -1496,7 +1495,7 @@ xfs_dir2_leaf_removename(
* log the data block header if necessary.
*/
if (needscan)
- xfs_dir2_data_freescan(mp, data, &needlog, NULL);
+ xfs_dir2_data_freescan(mp, data, &needlog);
if (needlog)
xfs_dir2_data_log_header(tp, dbp);
/*
diff --git a/fs/xfs/xfs_dir2_node.c b/fs/xfs/xfs_dir2_node.c
index 9ca71719b68..d083c381993 100644
--- a/fs/xfs/xfs_dir2_node.c
+++ b/fs/xfs/xfs_dir2_node.c
@@ -904,7 +904,7 @@ xfs_dir2_leafn_remove(
* Log the data block header if needed.
*/
if (needscan)
- xfs_dir2_data_freescan(mp, data, &needlog, NULL);
+ xfs_dir2_data_freescan(mp, data, &needlog);
if (needlog)
xfs_dir2_data_log_header(tp, dbp);
xfs_dir2_data_check(dp, dbp);
@@ -1705,7 +1705,7 @@ xfs_dir2_node_addname_int(
* Rescan the block for bestfree if needed.
*/
if (needscan)
- xfs_dir2_data_freescan(mp, data, &needlog, NULL);
+ xfs_dir2_data_freescan(mp, data, &needlog);
/*
* Log the data block header if needed.
*/
diff --git a/fs/xfs/xfs_error.c b/fs/xfs/xfs_error.c
index b1af54464f0..8c433163133 100644
--- a/fs/xfs/xfs_error.c
+++ b/fs/xfs/xfs_error.c
@@ -80,7 +80,7 @@ xfs_error_test(int error_tag, int *fsidp, char *expression,
int i;
int64_t fsid;
- if (random() % randfactor)
+ if (random32() % randfactor)
return 0;
memcpy(&fsid, fsidp, sizeof(xfs_fsid_t));
diff --git a/fs/xfs/xfs_fsops.c b/fs/xfs/xfs_fsops.c
index 32c37c1c47a..b599e6be9ec 100644
--- a/fs/xfs/xfs_fsops.c
+++ b/fs/xfs/xfs_fsops.c
@@ -346,7 +346,7 @@ xfs_growfs_data_private(
xfs_trans_mod_sb(tp, XFS_TRANS_SB_FDBLOCKS, nfree);
if (dpct)
xfs_trans_mod_sb(tp, XFS_TRANS_SB_IMAXPCT, dpct);
- error = xfs_trans_commit(tp, 0, NULL);
+ error = xfs_trans_commit(tp, 0);
if (error) {
return error;
}
@@ -605,7 +605,7 @@ xfs_fs_log_dummy(
xfs_trans_ihold(tp, ip);
xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
xfs_trans_set_sync(tp);
- xfs_trans_commit(tp, 0, NULL);
+ xfs_trans_commit(tp, 0);
xfs_iunlock(ip, XFS_ILOCK_EXCL);
}
diff --git a/fs/xfs/xfs_iget.c b/fs/xfs/xfs_iget.c
index c1c89dac19c..114433a22ba 100644
--- a/fs/xfs/xfs_iget.c
+++ b/fs/xfs/xfs_iget.c
@@ -879,17 +879,17 @@ xfs_ilock(xfs_inode_t *ip,
(XFS_IOLOCK_SHARED | XFS_IOLOCK_EXCL));
ASSERT((lock_flags & (XFS_ILOCK_SHARED | XFS_ILOCK_EXCL)) !=
(XFS_ILOCK_SHARED | XFS_ILOCK_EXCL));
- ASSERT((lock_flags & ~XFS_LOCK_MASK) == 0);
+ ASSERT((lock_flags & ~(XFS_LOCK_MASK | XFS_LOCK_DEP_MASK)) == 0);
if (lock_flags & XFS_IOLOCK_EXCL) {
- mrupdate(&ip->i_iolock);
+ mrupdate_nested(&ip->i_iolock, XFS_IOLOCK_DEP(lock_flags));
} else if (lock_flags & XFS_IOLOCK_SHARED) {
- mraccess(&ip->i_iolock);
+ mraccess_nested(&ip->i_iolock, XFS_IOLOCK_DEP(lock_flags));
}
if (lock_flags & XFS_ILOCK_EXCL) {
- mrupdate(&ip->i_lock);
+ mrupdate_nested(&ip->i_lock, XFS_ILOCK_DEP(lock_flags));
} else if (lock_flags & XFS_ILOCK_SHARED) {
- mraccess(&ip->i_lock);
+ mraccess_nested(&ip->i_lock, XFS_ILOCK_DEP(lock_flags));
}
xfs_ilock_trace(ip, 1, lock_flags, (inst_t *)__return_address);
}
@@ -923,7 +923,7 @@ xfs_ilock_nowait(xfs_inode_t *ip,
(XFS_IOLOCK_SHARED | XFS_IOLOCK_EXCL));
ASSERT((lock_flags & (XFS_ILOCK_SHARED | XFS_ILOCK_EXCL)) !=
(XFS_ILOCK_SHARED | XFS_ILOCK_EXCL));
- ASSERT((lock_flags & ~XFS_LOCK_MASK) == 0);
+ ASSERT((lock_flags & ~(XFS_LOCK_MASK | XFS_LOCK_DEP_MASK)) == 0);
iolocked = 0;
if (lock_flags & XFS_IOLOCK_EXCL) {
@@ -983,7 +983,8 @@ xfs_iunlock(xfs_inode_t *ip,
(XFS_IOLOCK_SHARED | XFS_IOLOCK_EXCL));
ASSERT((lock_flags & (XFS_ILOCK_SHARED | XFS_ILOCK_EXCL)) !=
(XFS_ILOCK_SHARED | XFS_ILOCK_EXCL));
- ASSERT((lock_flags & ~(XFS_LOCK_MASK | XFS_IUNLOCK_NONOTIFY)) == 0);
+ ASSERT((lock_flags & ~(XFS_LOCK_MASK | XFS_IUNLOCK_NONOTIFY |
+ XFS_LOCK_DEP_MASK)) == 0);
ASSERT(lock_flags != 0);
if (lock_flags & (XFS_IOLOCK_SHARED | XFS_IOLOCK_EXCL)) {
diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
index 3da9829c19d..3ca5d43b834 100644
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -442,6 +442,7 @@ xfs_iformat(
return XFS_ERROR(EFSCORRUPTED);
}
ip->i_d.di_size = 0;
+ ip->i_size = 0;
ip->i_df.if_u2.if_rdev = INT_GET(dip->di_u.di_dev, ARCH_CONVERT);
break;
@@ -980,6 +981,7 @@ xfs_iread(
}
ip->i_delayed_blks = 0;
+ ip->i_size = ip->i_d.di_size;
/*
* Mark the buffer containing the inode as something to keep
@@ -1170,6 +1172,7 @@ xfs_ialloc(
}
ip->i_d.di_size = 0;
+ ip->i_size = 0;
ip->i_d.di_nextents = 0;
ASSERT(ip->i_d.di_nblocks == 0);
xfs_ichgtime(ip, XFS_ICHGTIME_CHG|XFS_ICHGTIME_ACC|XFS_ICHGTIME_MOD);
@@ -1340,7 +1343,7 @@ xfs_file_last_byte(
} else {
last_block = 0;
}
- size_last_block = XFS_B_TO_FSB(mp, (xfs_ufsize_t)ip->i_d.di_size);
+ size_last_block = XFS_B_TO_FSB(mp, (xfs_ufsize_t)ip->i_size);
last_block = XFS_FILEOFF_MAX(last_block, size_last_block);
last_byte = XFS_FSB_TO_B(mp, last_block);
@@ -1421,7 +1424,7 @@ xfs_itrunc_trace(
* must be called again with all the same restrictions as the initial
* call.
*/
-void
+int
xfs_itruncate_start(
xfs_inode_t *ip,
uint flags,
@@ -1431,9 +1434,10 @@ xfs_itruncate_start(
xfs_off_t toss_start;
xfs_mount_t *mp;
bhv_vnode_t *vp;
+ int error = 0;
ASSERT(ismrlocked(&ip->i_iolock, MR_UPDATE) != 0);
- ASSERT((new_size == 0) || (new_size <= ip->i_d.di_size));
+ ASSERT((new_size == 0) || (new_size <= ip->i_size));
ASSERT((flags == XFS_ITRUNC_DEFINITE) ||
(flags == XFS_ITRUNC_MAYBE));
@@ -1468,7 +1472,7 @@ xfs_itruncate_start(
* file size, so there is no way that the data extended
* out there.
*/
- return;
+ return 0;
}
last_byte = xfs_file_last_byte(ip);
xfs_itrunc_trace(XFS_ITRUNC_START, ip, flags, new_size, toss_start,
@@ -1477,7 +1481,7 @@ xfs_itruncate_start(
if (flags & XFS_ITRUNC_DEFINITE) {
bhv_vop_toss_pages(vp, toss_start, -1, FI_REMAPF_LOCKED);
} else {
- bhv_vop_flushinval_pages(vp, toss_start, -1, FI_REMAPF_LOCKED);
+ error = bhv_vop_flushinval_pages(vp, toss_start, -1, FI_REMAPF_LOCKED);
}
}
@@ -1486,6 +1490,7 @@ xfs_itruncate_start(
ASSERT(VN_CACHED(vp) == 0);
}
#endif
+ return error;
}
/*
@@ -1556,7 +1561,7 @@ xfs_itruncate_finish(
ASSERT(ismrlocked(&ip->i_iolock, MR_UPDATE) != 0);
ASSERT(ismrlocked(&ip->i_lock, MR_UPDATE) != 0);
- ASSERT((new_size == 0) || (new_size <= ip->i_d.di_size));
+ ASSERT((new_size == 0) || (new_size <= ip->i_size));
ASSERT(*tp != NULL);
ASSERT((*tp)->t_flags & XFS_TRANS_PERM_LOG_RES);
ASSERT(ip->i_transp == *tp);
@@ -1630,8 +1635,20 @@ xfs_itruncate_finish(
*/
if (fork == XFS_DATA_FORK) {
if (ip->i_d.di_nextents > 0) {
- ip->i_d.di_size = new_size;
- xfs_trans_log_inode(ntp, ip, XFS_ILOG_CORE);
+ /*
+ * If we are not changing the file size then do
+ * not update the on-disk file size - we may be
+ * called from xfs_inactive_free_eofblocks(). 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).
+ */
+ if (ip->i_size != new_size) {
+ ip->i_d.di_size = new_size;
+ ip->i_size = new_size;
+ xfs_trans_log_inode(ntp, ip, XFS_ILOG_CORE);
+ }
}
} else if (sync) {
ASSERT(!(mp->m_flags & XFS_MOUNT_WSYNC));
@@ -1746,7 +1763,7 @@ xfs_itruncate_finish(
xfs_trans_log_inode(ntp, ip, XFS_ILOG_CORE);
}
ntp = xfs_trans_dup(ntp);
- (void) xfs_trans_commit(*tp, 0, NULL);
+ (void) xfs_trans_commit(*tp, 0);
*tp = ntp;
error = xfs_trans_reserve(ntp, 0, XFS_ITRUNCATE_LOG_RES(mp), 0,
XFS_TRANS_PERM_LOG_RES,
@@ -1767,7 +1784,19 @@ xfs_itruncate_finish(
*/
if (fork == XFS_DATA_FORK) {
xfs_isize_check(mp, ip, new_size);
- ip->i_d.di_size = new_size;
+ /*
+ * If we are not changing the file size then do
+ * not update the on-disk file size - we may be
+ * called from xfs_inactive_free_eofblocks(). 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).
+ */
+ if (ip->i_size != new_size) {
+ ip->i_d.di_size = new_size;
+ ip->i_size = new_size;
+ }
}
xfs_trans_log_inode(ntp, ip, XFS_ILOG_CORE);
ASSERT((new_size != 0) ||
@@ -1800,7 +1829,7 @@ xfs_igrow_start(
ASSERT(ismrlocked(&(ip->i_lock), MR_UPDATE) != 0);
ASSERT(ismrlocked(&(ip->i_iolock), MR_UPDATE) != 0);
- ASSERT(new_size > ip->i_d.di_size);
+ ASSERT(new_size > ip->i_size);
/*
* Zero any pages that may have been created by
@@ -1808,7 +1837,7 @@ xfs_igrow_start(
* and any blocks between the old and new file sizes.
*/
error = xfs_zero_eof(XFS_ITOV(ip), &ip->i_iocore, new_size,
- ip->i_d.di_size);
+ ip->i_size);
return error;
}
@@ -1832,13 +1861,14 @@ xfs_igrow_finish(
ASSERT(ismrlocked(&(ip->i_lock), MR_UPDATE) != 0);
ASSERT(ismrlocked(&(ip->i_iolock), MR_UPDATE) != 0);
ASSERT(ip->i_transp == tp);
- ASSERT(new_size > ip->i_d.di_size);
+ ASSERT(new_size > ip->i_size);
/*
* Update the file size. Update the inode change timestamp
* if change_flag set.
*/
ip->i_d.di_size = new_size;
+ ip->i_size = new_size;
if (change_flag)
xfs_ichgtime(ip, XFS_ICHGTIME_CHG);
xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
@@ -2321,7 +2351,7 @@ xfs_ifree(
ASSERT(ip->i_d.di_nlink == 0);
ASSERT(ip->i_d.di_nextents == 0);
ASSERT(ip->i_d.di_anextents == 0);
- ASSERT((ip->i_d.di_size == 0) ||
+ ASSERT((ip->i_d.di_size == 0 && ip->i_size == 0) ||
((ip->i_d.di_mode & S_IFMT) != S_IFREG));
ASSERT(ip->i_d.di_nblocks == 0);
diff --git a/fs/xfs/xfs_inode.h b/fs/xfs/xfs_inode.h
index bc823720d88..f75afecef8e 100644
--- a/fs/xfs/xfs_inode.h
+++ b/fs/xfs/xfs_inode.h
@@ -287,6 +287,7 @@ typedef struct xfs_inode {
struct xfs_inode *i_cnext; /* cluster hash link forward */
struct xfs_inode *i_cprev; /* cluster hash link backward */
+ xfs_fsize_t i_size; /* in-memory size */
/* Trace buffers per inode. */
#ifdef XFS_BMAP_TRACE
struct ktrace *i_xtrace; /* inode extent list trace */
@@ -305,6 +306,8 @@ typedef struct xfs_inode {
#endif
} xfs_inode_t;
+#define XFS_ISIZE(ip) (((ip)->i_d.di_mode & S_IFMT) == S_IFREG) ? \
+ (ip)->i_size : (ip)->i_d.di_size;
/*
* i_flags helper functions
@@ -379,26 +382,58 @@ xfs_iflags_test(xfs_inode_t *ip, unsigned short flags)
/*
* Flags for inode locking.
+ * Bit ranges: 1<<1 - 1<<16-1 -- iolock/ilock modes (bitfield)
+ * 1<<16 - 1<<32-1 -- lockdep annotation (integers)
*/
-#define XFS_IOLOCK_EXCL 0x001
-#define XFS_IOLOCK_SHARED 0x002
-#define XFS_ILOCK_EXCL 0x004
-#define XFS_ILOCK_SHARED 0x008
-#define XFS_IUNLOCK_NONOTIFY 0x010
-/* XFS_IOLOCK_NESTED 0x020 */
-#define XFS_EXTENT_TOKEN_RD 0x040
-#define XFS_SIZE_TOKEN_RD 0x080
+#define XFS_IOLOCK_EXCL (1<<0)
+#define XFS_IOLOCK_SHARED (1<<1)
+#define XFS_ILOCK_EXCL (1<<2)
+#define XFS_ILOCK_SHARED (1<<3)
+#define XFS_IUNLOCK_NONOTIFY (1<<4)
+/* #define XFS_IOLOCK_NESTED (1<<5) */
+#define XFS_EXTENT_TOKEN_RD (1<<6)
+#define XFS_SIZE_TOKEN_RD (1<<7)
#define XFS_EXTSIZE_RD (XFS_EXTENT_TOKEN_RD|XFS_SIZE_TOKEN_RD)
-#define XFS_WILLLEND 0x100 /* Always acquire tokens for lending */
+#define XFS_WILLLEND (1<<8) /* Always acquire tokens for lending */
#define XFS_EXTENT_TOKEN_WR (XFS_EXTENT_TOKEN_RD | XFS_WILLLEND)
#define XFS_SIZE_TOKEN_WR (XFS_SIZE_TOKEN_RD | XFS_WILLLEND)
#define XFS_EXTSIZE_WR (XFS_EXTSIZE_RD | XFS_WILLLEND)
-/* XFS_SIZE_TOKEN_WANT 0x200 */
+/* TODO:XFS_SIZE_TOKEN_WANT (1<<9) */
-#define XFS_LOCK_MASK \
- (XFS_IOLOCK_EXCL | XFS_IOLOCK_SHARED | XFS_ILOCK_EXCL | \
- XFS_ILOCK_SHARED | XFS_EXTENT_TOKEN_RD | XFS_SIZE_TOKEN_RD | \
- XFS_WILLLEND)
+#define XFS_LOCK_MASK (XFS_IOLOCK_EXCL | XFS_IOLOCK_SHARED \
+ | XFS_ILOCK_EXCL | XFS_ILOCK_SHARED \
+ | XFS_EXTENT_TOKEN_RD | XFS_SIZE_TOKEN_RD \
+ | XFS_WILLLEND)
+
+/*
+ * Flags for lockdep annotations.
+ *
+ * XFS_I[O]LOCK_PARENT - for operations that require locking two inodes
+ * (ie directory operations that require locking a directory inode and
+ * an entry inode). The first inode gets locked with this flag so it
+ * gets a lockdep subclass of 1 and the second lock will have a lockdep
+ * subclass of 0.
+ *
+ * XFS_I[O]LOCK_INUMORDER - for locking several inodes at the some time
+ * with xfs_lock_inodes(). This flag is used as the starting subclass
+ * and each subsequent lock acquired will increment the subclass by one.
+ * So the first lock acquired will have a lockdep subclass of 2, the
+ * second lock will have a lockdep subclass of 3, and so on.
+ */
+#define XFS_IOLOCK_SHIFT 16
+#define XFS_IOLOCK_PARENT (1 << XFS_IOLOCK_SHIFT)
+#define XFS_IOLOCK_INUMORDER (2 << XFS_IOLOCK_SHIFT)
+
+#define XFS_ILOCK_SHIFT 24
+#define XFS_ILOCK_PARENT (1 << XFS_ILOCK_SHIFT)
+#define XFS_ILOCK_INUMORDER (2 << XFS_ILOCK_SHIFT)
+
+#define XFS_IOLOCK_DEP_MASK 0x00ff0000
+#define XFS_ILOCK_DEP_MASK 0xff000000
+#define XFS_LOCK_DEP_MASK (XFS_IOLOCK_DEP_MASK | XFS_ILOCK_DEP_MASK)
+
+#define XFS_IOLOCK_DEP(flags) (((flags) & XFS_IOLOCK_DEP_MASK) >> XFS_IOLOCK_SHIFT)
+#define XFS_ILOCK_DEP(flags) (((flags) & XFS_ILOCK_DEP_MASK) >> XFS_ILOCK_SHIFT)
/*
* Flags for xfs_iflush()
@@ -481,7 +516,7 @@ uint xfs_ip2xflags(struct xfs_inode *);
uint xfs_dic2xflags(struct xfs_dinode_core *);
int xfs_ifree(struct xfs_trans *, xfs_inode_t *,
struct xfs_bmap_free *);
-void xfs_itruncate_start(xfs_inode_t *, uint, xfs_fsize_t);
+int xfs_itruncate_start(xfs_inode_t *, uint, xfs_fsize_t);
int xfs_itruncate_finish(struct xfs_trans **, xfs_inode_t *,
xfs_fsize_t, int, int);
int xfs_iunlink(struct xfs_trans *, xfs_inode_t *);
diff --git a/fs/xfs/xfs_iocore.c b/fs/xfs/xfs_iocore.c
index 06d710c9ce4..81548ec72ba 100644
--- a/fs/xfs/xfs_iocore.c
+++ b/fs/xfs/xfs_iocore.c
@@ -52,7 +52,7 @@ STATIC xfs_fsize_t
xfs_size_fn(
xfs_inode_t *ip)
{
- return (ip->i_d.di_size);
+ return XFS_ISIZE(ip);
}
STATIC int
diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c
index cc6a7b5a991..3f2b9f2a7b9 100644
--- a/fs/xfs/xfs_iomap.c
+++ b/fs/xfs/xfs_iomap.c
@@ -458,7 +458,7 @@ xfs_iomap_write_direct(
extsz = ip->i_d.di_extsize;
}
- isize = ip->i_d.di_size;
+ isize = ip->i_size;
if (io->io_new_size > isize)
isize = io->io_new_size;
@@ -524,7 +524,7 @@ xfs_iomap_write_direct(
xfs_trans_ihold(tp, ip);
bmapi_flag = XFS_BMAPI_WRITE;
- if ((flags & BMAPI_DIRECT) && (offset < ip->i_d.di_size || extsz))
+ if ((flags & BMAPI_DIRECT) && (offset < ip->i_size || extsz))
bmapi_flag |= XFS_BMAPI_PREALLOC;
/*
@@ -543,7 +543,7 @@ xfs_iomap_write_direct(
error = xfs_bmap_finish(&tp, &free_list, &committed);
if (error)
goto error0;
- error = xfs_trans_commit(tp, XFS_TRANS_RELEASE_LOG_RES, NULL);
+ error = xfs_trans_commit(tp, XFS_TRANS_RELEASE_LOG_RES);
if (error)
goto error_out;
@@ -676,7 +676,7 @@ xfs_iomap_write_delay(
offset_fsb = XFS_B_TO_FSBT(mp, offset);
retry:
- isize = ip->i_d.di_size;
+ isize = ip->i_size;
if (io->io_new_size > isize)
isize = io->io_new_size;
@@ -817,7 +817,7 @@ xfs_iomap_write_allocate(
* we dropped the ilock in the interim.
*/
- end_fsb = XFS_B_TO_FSB(mp, ip->i_d.di_size);
+ end_fsb = XFS_B_TO_FSB(mp, ip->i_size);
xfs_bmap_last_offset(NULL, ip, &last_block,
XFS_DATA_FORK);
last_block = XFS_FILEOFF_MAX(last_block, end_fsb);
@@ -840,8 +840,7 @@ xfs_iomap_write_allocate(
if (error)
goto trans_cancel;
- error = xfs_trans_commit(tp,
- XFS_TRANS_RELEASE_LOG_RES, NULL);
+ error = xfs_trans_commit(tp, XFS_TRANS_RELEASE_LOG_RES);
if (error)
goto error0;
@@ -948,7 +947,7 @@ xfs_iomap_write_unwritten(
if (error)
goto error_on_bmapi_transaction;
- error = xfs_trans_commit(tp, XFS_TRANS_RELEASE_LOG_RES, NULL);
+ error = xfs_trans_commit(tp, XFS_TRANS_RELEASE_LOG_RES);
xfs_iunlock(ip, XFS_ILOCK_EXCL);
if (error)
return XFS_ERROR(error);
diff --git a/fs/xfs/xfs_iomap.h b/fs/xfs/xfs_iomap.h
index 3ce204a524b..df441ee936b 100644
--- a/fs/xfs/xfs_iomap.h
+++ b/fs/xfs/xfs_iomap.h
@@ -22,6 +22,7 @@
typedef enum { /* iomap_flags values */
+ IOMAP_READ = 0, /* mapping for a read */
IOMAP_EOF = 0x01, /* mapping contains EOF */
IOMAP_HOLE = 0x02, /* mapping covers a hole */
IOMAP_DELAY = 0x04, /* mapping covers delalloc region */
diff --git a/fs/xfs/xfs_itable.c b/fs/xfs/xfs_itable.c
index 7775ddc0b3c..e725ddd3de5 100644
--- a/fs/xfs/xfs_itable.c
+++ b/fs/xfs/xfs_itable.c
@@ -809,7 +809,7 @@ xfs_inumbers(
xfs_buf_relse(agbp);
agbp = NULL;
/*
- * Move up the the last inode in the current
+ * Move up the last inode in the current
* chunk. The lookup_ge will always get
* us the first inode in the next chunk.
*/
diff --git a/fs/xfs/xfs_log_recover.c b/fs/xfs/xfs_log_recover.c
index ca74d3f5910..080fabf61c9 100644
--- a/fs/xfs/xfs_log_recover.c
+++ b/fs/xfs/xfs_log_recover.c
@@ -1509,7 +1509,6 @@ xlog_recover_insert_item_frontq(
STATIC int
xlog_recover_reorder_trans(
- xlog_t *log,
xlog_recover_t *trans)
{
xlog_recover_item_t *first_item, *itemq, *itemq_next;
@@ -1867,7 +1866,6 @@ xlog_recover_do_inode_buffer(
/*ARGSUSED*/
STATIC void
xlog_recover_do_reg_buffer(
- xfs_mount_t *mp,
xlog_recover_item_t *item,
xfs_buf_t *bp,
xfs_buf_log_format_t *buf_f)
@@ -2083,7 +2081,7 @@ xlog_recover_do_dquot_buffer(
if (log->l_quotaoffs_flag & type)
return;
- xlog_recover_do_reg_buffer(mp, item, bp, buf_f);
+ xlog_recover_do_reg_buffer(item, bp, buf_f);
}
/*
@@ -2184,7 +2182,7 @@ xlog_recover_do_buffer_trans(
(XFS_BLI_UDQUOT_BUF|XFS_BLI_PDQUOT_BUF|XFS_BLI_GDQUOT_BUF)) {
xlog_recover_do_dquot_buffer(mp, log, item, bp, buf_f);
} else {
- xlog_recover_do_reg_buffer(mp, item, bp, buf_f);
+ xlog_recover_do_reg_buffer(item, bp, buf_f);
}
if (error)
return XFS_ERROR(error);
@@ -2765,7 +2763,7 @@ xlog_recover_do_trans(
int error = 0;
xlog_recover_item_t *item, *first_item;
- if ((error = xlog_recover_reorder_trans(log, trans)))
+ if ((error = xlog_recover_reorder_trans(trans)))
return error;
first_item = item = trans->r_itemq;
do {
@@ -3016,7 +3014,7 @@ xlog_recover_process_efi(
}
efip->efi_flags |= XFS_EFI_RECOVERED;
- xfs_trans_commit(tp, 0, NULL);
+ xfs_trans_commit(tp, 0);
}
/*
@@ -3143,7 +3141,7 @@ xlog_recover_clear_agi_bucket(
xfs_trans_log_buf(tp, agibp, offset,
(offset + sizeof(xfs_agino_t) - 1));
- (void) xfs_trans_commit(tp, 0, NULL);
+ (void) xfs_trans_commit(tp, 0);
}
/*
@@ -3886,8 +3884,7 @@ xlog_recover(
* under the vfs layer, so we can get away with it unless
* the device itself is read-only, in which case we fail.
*/
- if ((error = xfs_dev_is_read_only(log->l_mp,
- "recovery required"))) {
+ if ((error = xfs_dev_is_read_only(log->l_mp, "recovery"))) {
return error;
}
diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c
index 3bed0cf0d8a..a96bde6df96 100644
--- a/fs/xfs/xfs_mount.c
+++ b/fs/xfs/xfs_mount.c
@@ -1653,7 +1653,7 @@ xfs_mount_log_sbunit(
return;
}
xfs_mod_sb(tp, fields);
- xfs_trans_commit(tp, 0, NULL);
+ xfs_trans_commit(tp, 0);
}
@@ -1734,11 +1734,13 @@ xfs_icsb_cpu_notify(
per_cpu_ptr(mp->m_sb_cnts, (unsigned long)hcpu);
switch (action) {
case CPU_UP_PREPARE:
+ case CPU_UP_PREPARE_FROZEN:
/* Easy Case - initialize the area and locks, and
* then rebalance when online does everything else for us. */
memset(cntp, 0, sizeof(xfs_icsb_cnts_t));
break;
case CPU_ONLINE:
+ case CPU_ONLINE_FROZEN:
xfs_icsb_lock(mp);
xfs_icsb_balance_counter(mp, XFS_SBS_ICOUNT, 0, 0);
xfs_icsb_balance_counter(mp, XFS_SBS_IFREE, 0, 0);
@@ -1746,6 +1748,7 @@ xfs_icsb_cpu_notify(
xfs_icsb_unlock(mp);
break;
case CPU_DEAD:
+ case CPU_DEAD_FROZEN:
/* Disable all the counters, then fold the dead cpu's
* count into the total on the global superblock and
* re-enable the counters. */
diff --git a/fs/xfs/xfs_qmops.c b/fs/xfs/xfs_qmops.c
index 320d63ff9ca..0d594ed7efe 100644
--- a/fs/xfs/xfs_qmops.c
+++ b/fs/xfs/xfs_qmops.c
@@ -78,7 +78,7 @@ xfs_mount_reset_sbqflags(xfs_mount_t *mp)
return error;
}
xfs_mod_sb(tp, XFS_SB_QFLAGS);
- error = xfs_trans_commit(tp, 0, NULL);
+ error = xfs_trans_commit(tp, 0);
return error;
}
diff --git a/fs/xfs/xfs_quota.h b/fs/xfs/xfs_quota.h
index 9dcb32aa4e2..6f14df976f7 100644
--- a/fs/xfs/xfs_quota.h
+++ b/fs/xfs/xfs_quota.h
@@ -154,10 +154,11 @@ typedef struct xfs_qoff_logformat {
#define XFS_ALL_QUOTA_CHKD (XFS_UQUOTA_CHKD | XFS_OQUOTA_CHKD)
#define XFS_IS_QUOTA_RUNNING(mp) ((mp)->m_qflags & XFS_ALL_QUOTA_ACCT)
-#define XFS_IS_QUOTA_ENFORCED(mp) ((mp)->m_qflags & XFS_ALL_QUOTA_ENFD)
#define XFS_IS_UQUOTA_RUNNING(mp) ((mp)->m_qflags & XFS_UQUOTA_ACCT)
#define XFS_IS_PQUOTA_RUNNING(mp) ((mp)->m_qflags & XFS_PQUOTA_ACCT)
#define XFS_IS_GQUOTA_RUNNING(mp) ((mp)->m_qflags & XFS_GQUOTA_ACCT)
+#define XFS_IS_UQUOTA_ENFORCED(mp) ((mp)->m_qflags & XFS_UQUOTA_ENFD)
+#define XFS_IS_OQUOTA_ENFORCED(mp) ((mp)->m_qflags & XFS_OQUOTA_ENFD)
/*
* Incore only flags for quotaoff - these bits get cleared when quota(s)
diff --git a/fs/xfs/xfs_rename.c b/fs/xfs/xfs_rename.c
index 4c6573d784c..7679d7a7022 100644
--- a/fs/xfs/xfs_rename.c
+++ b/fs/xfs/xfs_rename.c
@@ -584,7 +584,7 @@ xfs_rename(
* trans_commit will unlock src_ip, target_ip & decrement
* the vnode references.
*/
- error = xfs_trans_commit(tp, XFS_TRANS_RELEASE_LOG_RES, NULL);
+ error = xfs_trans_commit(tp, XFS_TRANS_RELEASE_LOG_RES);
if (target_ip != NULL) {
xfs_refcache_purge_ip(target_ip);
IRELE(target_ip);
diff --git a/fs/xfs/xfs_rtalloc.c b/fs/xfs/xfs_rtalloc.c
index 6fff19dc3cf..b3a5f07bd07 100644
--- a/fs/xfs/xfs_rtalloc.c
+++ b/fs/xfs/xfs_rtalloc.c
@@ -150,7 +150,7 @@ xfs_growfs_rt_alloc(
error = xfs_bmap_finish(&tp, &flist, &committed);
if (error)
goto error_exit;
- xfs_trans_commit(tp, XFS_TRANS_RELEASE_LOG_RES, NULL);
+ xfs_trans_commit(tp, XFS_TRANS_RELEASE_LOG_RES);
/*
* Now we need to clear the allocated blocks.
* Do this one block per transaction, to keep it simple.
@@ -187,7 +187,7 @@ xfs_growfs_rt_alloc(
/*
* Commit the transaction.
*/
- xfs_trans_commit(tp, 0, NULL);
+ xfs_trans_commit(tp, 0);
}
/*
* Go on to the next extent, if any.
@@ -2042,7 +2042,7 @@ xfs_growfs_rt(
/*
* Commit the transaction.
*/
- xfs_trans_commit(tp, 0, NULL);
+ xfs_trans_commit(tp, 0);
}
if (error)
diff --git a/fs/xfs/xfs_rw.c b/fs/xfs/xfs_rw.c
index 1ea7c0ca6ae..905d1c008be 100644
--- a/fs/xfs/xfs_rw.c
+++ b/fs/xfs/xfs_rw.c
@@ -83,7 +83,7 @@ xfs_write_clear_setuid(
}
xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
xfs_trans_set_sync(tp);
- error = xfs_trans_commit(tp, 0, NULL);
+ error = xfs_trans_commit(tp, 0);
xfs_iunlock(ip, XFS_ILOCK_EXCL);
return 0;
}
@@ -164,7 +164,7 @@ xfs_write_sync_logforce(
xfs_trans_ihold(tp, ip);
xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
xfs_trans_set_sync(tp);
- error = xfs_trans_commit(tp, 0, NULL);
+ error = xfs_trans_commit(tp, 0);
xfs_iunlock(ip, XFS_ILOCK_EXCL);
}
}
diff --git a/fs/xfs/xfs_trans.c b/fs/xfs/xfs_trans.c
index 301ff9445b6..cc2d60951e2 100644
--- a/fs/xfs/xfs_trans.c
+++ b/fs/xfs/xfs_trans.c
@@ -753,7 +753,6 @@ int
_xfs_trans_commit(
xfs_trans_t *tp,
uint flags,
- xfs_lsn_t *commit_lsn_p,
int *log_flushed)
{
xfs_log_iovec_t *log_vector;
@@ -812,8 +811,6 @@ shut_us_down:
xfs_trans_free_busy(tp);
xfs_trans_free(tp);
XFS_STATS_INC(xs_trans_empty);
- if (commit_lsn_p)
- *commit_lsn_p = commit_lsn;
return (shutdown);
}
ASSERT(tp->t_ticket != NULL);
@@ -864,9 +861,6 @@ shut_us_down:
kmem_free(log_vector, nvec * sizeof(xfs_log_iovec_t));
}
- if (commit_lsn_p)
- *commit_lsn_p = commit_lsn;
-
/*
* If we got a log write error. Unpin the logitems that we
* had pinned, clean up, free trans structure, and return error.
diff --git a/fs/xfs/xfs_trans.h b/fs/xfs/xfs_trans.h
index f1d7ab23672..7dfcc450366 100644
--- a/fs/xfs/xfs_trans.h
+++ b/fs/xfs/xfs_trans.h
@@ -988,10 +988,8 @@ void xfs_trans_log_efd_extent(xfs_trans_t *,
xfs_extlen_t);
int _xfs_trans_commit(xfs_trans_t *,
uint flags,
- xfs_lsn_t *,
int *);
-#define xfs_trans_commit(tp, flags, lsn) \
- _xfs_trans_commit(tp, flags, lsn, NULL)
+#define xfs_trans_commit(tp, flags) _xfs_trans_commit(tp, flags, NULL)
void xfs_trans_cancel(xfs_trans_t *, int);
void xfs_trans_ail_init(struct xfs_mount *);
xfs_lsn_t xfs_trans_push_ail(struct xfs_mount *, xfs_lsn_t);
diff --git a/fs/xfs/xfs_utils.c b/fs/xfs/xfs_utils.c
index 9014d7e4448..20ffec308e1 100644
--- a/fs/xfs/xfs_utils.c
+++ b/fs/xfs/xfs_utils.c
@@ -222,7 +222,7 @@ xfs_dir_ialloc(
}
ntp = xfs_trans_dup(tp);
- code = xfs_trans_commit(tp, 0, NULL);
+ code = xfs_trans_commit(tp, 0);
tp = ntp;
if (committed != NULL) {
*committed = 1;
@@ -420,7 +420,11 @@ xfs_truncate_file(
* in a transaction.
*/
xfs_ilock(ip, XFS_IOLOCK_EXCL);
- xfs_itruncate_start(ip, XFS_ITRUNC_DEFINITE, (xfs_fsize_t)0);
+ error = xfs_itruncate_start(ip, XFS_ITRUNC_DEFINITE, (xfs_fsize_t)0);
+ if (error) {
+ xfs_iunlock(ip, XFS_IOLOCK_EXCL);
+ return error;
+ }
tp = xfs_trans_alloc(mp, XFS_TRANS_TRUNCATE_FILE);
if ((error = xfs_trans_reserve(tp, 0, XFS_ITRUNCATE_LOG_RES(mp), 0,
@@ -460,8 +464,7 @@ xfs_truncate_file(
XFS_TRANS_ABORT);
} else {
xfs_ichgtime(ip, XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG);
- error = xfs_trans_commit(tp, XFS_TRANS_RELEASE_LOG_RES,
- NULL);
+ error = xfs_trans_commit(tp, XFS_TRANS_RELEASE_LOG_RES);
}
xfs_iunlock(ip, XFS_ILOCK_EXCL | XFS_IOLOCK_EXCL);
diff --git a/fs/xfs/xfs_vfsops.c b/fs/xfs/xfs_vfsops.c
index 29f72f61378..65c561201cb 100644
--- a/fs/xfs/xfs_vfsops.c
+++ b/fs/xfs/xfs_vfsops.c
@@ -696,7 +696,7 @@ xfs_unmount_flush(
bhv_vnode_t *rvp = XFS_ITOV(rip);
int error;
- xfs_ilock(rip, XFS_ILOCK_EXCL);
+ xfs_ilock(rip, XFS_ILOCK_EXCL | XFS_ILOCK_PARENT);
xfs_iflock(rip);
/*
@@ -1147,7 +1147,7 @@ xfs_sync_inodes(
if (XFS_FORCED_SHUTDOWN(mp)) {
bhv_vop_toss_pages(vp, 0, -1, FI_REMAPF);
} else {
- bhv_vop_flushinval_pages(vp, 0, -1, FI_REMAPF);
+ error = bhv_vop_flushinval_pages(vp, 0, -1, FI_REMAPF);
}
xfs_ilock(ip, XFS_ILOCK_SHARED);
@@ -1539,7 +1539,7 @@ xfs_syncsub(
xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL);
xfs_trans_ihold(tp, ip);
xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
- error = xfs_trans_commit(tp, 0, NULL);
+ error = xfs_trans_commit(tp, 0);
xfs_iunlock(ip, XFS_ILOCK_EXCL);
xfs_log_force(mp, (xfs_lsn_t)0, log_flags);
}
diff --git a/fs/xfs/xfs_vnodeops.c b/fs/xfs/xfs_vnodeops.c
index 52c41714ec5..de17aed578f 100644
--- a/fs/xfs/xfs_vnodeops.c
+++ b/fs/xfs/xfs_vnodeops.c
@@ -133,7 +133,7 @@ xfs_getattr(
if (!(flags & ATTR_LAZY))
xfs_ilock(ip, XFS_ILOCK_SHARED);
- vap->va_size = ip->i_d.di_size;
+ vap->va_size = XFS_ISIZE(ip);
if (vap->va_mask == XFS_AT_SIZE)
goto all_done;
@@ -496,7 +496,7 @@ xfs_setattr(
if (mask & XFS_AT_SIZE) {
/* Short circuit the truncate case for zero length files */
if ((vap->va_size == 0) &&
- (ip->i_d.di_size == 0) && (ip->i_d.di_nextents == 0)) {
+ (ip->i_size == 0) && (ip->i_d.di_nextents == 0)) {
xfs_iunlock(ip, XFS_ILOCK_EXCL);
lock_flags &= ~XFS_ILOCK_EXCL;
if (mask & XFS_AT_CTIME)
@@ -614,7 +614,7 @@ xfs_setattr(
*/
if (mask & XFS_AT_SIZE) {
code = 0;
- if ((vap->va_size > ip->i_d.di_size) &&
+ if ((vap->va_size > ip->i_size) &&
(flags & ATTR_NOSIZETOK) == 0) {
code = xfs_igrow_start(ip, vap->va_size, credp);
}
@@ -654,10 +654,10 @@ xfs_setattr(
* Truncate file. Must have write permission and not be a directory.
*/
if (mask & XFS_AT_SIZE) {
- if (vap->va_size > ip->i_d.di_size) {
+ if (vap->va_size > ip->i_size) {
xfs_igrow_finish(tp, ip, vap->va_size,
!(flags & ATTR_DMI));
- } else if ((vap->va_size <= ip->i_d.di_size) ||
+ } else if ((vap->va_size <= ip->i_size) ||
((vap->va_size == 0) && ip->i_d.di_nextents)) {
/*
* signal a sync transaction unless
@@ -873,7 +873,7 @@ xfs_setattr(
if (mp->m_flags & XFS_MOUNT_WSYNC)
xfs_trans_set_sync(tp);
- code = xfs_trans_commit(tp, commit_flags, NULL);
+ code = xfs_trans_commit(tp, commit_flags);
}
/*
@@ -1176,7 +1176,7 @@ xfs_fsync(
xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
if (flag & FSYNC_WAIT)
xfs_trans_set_sync(tp);
- error = _xfs_trans_commit(tp, 0, NULL, &log_flushed);
+ error = _xfs_trans_commit(tp, 0, &log_flushed);
xfs_iunlock(ip, XFS_ILOCK_EXCL);
}
@@ -1221,7 +1221,7 @@ xfs_inactive_free_eofblocks(
* 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)ip->i_d.di_size));
+ end_fsb = XFS_B_TO_FSB(mp, ((xfs_ufsize_t)ip->i_size));
last_fsb = XFS_B_TO_FSB(mp, (xfs_ufsize_t)XFS_MAXIOFFSET(mp));
map_len = last_fsb - end_fsb;
if (map_len <= 0)
@@ -1257,8 +1257,12 @@ xfs_inactive_free_eofblocks(
* do that within a transaction.
*/
xfs_ilock(ip, XFS_IOLOCK_EXCL);
- xfs_itruncate_start(ip, XFS_ITRUNC_DEFINITE,
- ip->i_d.di_size);
+ error = xfs_itruncate_start(ip, XFS_ITRUNC_DEFINITE,
+ ip->i_size);
+ if (error) {
+ xfs_iunlock(ip, XFS_IOLOCK_EXCL);
+ return error;
+ }
error = xfs_trans_reserve(tp, 0,
XFS_ITRUNCATE_LOG_RES(mp),
@@ -1278,7 +1282,7 @@ xfs_inactive_free_eofblocks(
xfs_trans_ihold(tp, ip);
error = xfs_itruncate_finish(&tp, ip,
- ip->i_d.di_size,
+ ip->i_size,
XFS_DATA_FORK,
0);
/*
@@ -1291,8 +1295,7 @@ xfs_inactive_free_eofblocks(
XFS_TRANS_ABORT));
} else {
error = xfs_trans_commit(tp,
- XFS_TRANS_RELEASE_LOG_RES,
- NULL);
+ XFS_TRANS_RELEASE_LOG_RES);
}
xfs_iunlock(ip, XFS_IOLOCK_EXCL | XFS_ILOCK_EXCL);
}
@@ -1406,7 +1409,7 @@ xfs_inactive_symlink_rmt(
* we need to unlock the inode since the new transaction doesn't
* have the inode attached.
*/
- error = xfs_trans_commit(tp, 0, NULL);
+ error = xfs_trans_commit(tp, 0);
tp = ntp;
if (error) {
ASSERT(XFS_FORCED_SHUTDOWN(mp));
@@ -1503,7 +1506,7 @@ xfs_inactive_attrs(
tp = *tpp;
mp = ip->i_mount;
ASSERT(ip->i_d.di_forkoff != 0);
- xfs_trans_commit(tp, XFS_TRANS_RELEASE_LOG_RES, NULL);
+ xfs_trans_commit(tp, XFS_TRANS_RELEASE_LOG_RES);
xfs_iunlock(ip, XFS_ILOCK_EXCL);
error = xfs_attr_inactive(ip);
@@ -1565,7 +1568,7 @@ xfs_release(
if (ip->i_d.di_nlink != 0) {
if ((((ip->i_d.di_mode & S_IFMT) == S_IFREG) &&
- ((ip->i_d.di_size > 0) || (VN_CACHED(vp) > 0 ||
+ ((ip->i_size > 0) || (VN_CACHED(vp) > 0 ||
ip->i_delayed_blks > 0)) &&
(ip->i_df.if_flags & XFS_IFEXTENTS)) &&
(!(ip->i_d.di_flags &
@@ -1626,8 +1629,8 @@ xfs_inactive(
* only one with a reference to the inode.
*/
truncate = ((ip->i_d.di_nlink == 0) &&
- ((ip->i_d.di_size != 0) || (ip->i_d.di_nextents > 0) ||
- (ip->i_delayed_blks > 0)) &&
+ ((ip->i_d.di_size != 0) || (ip->i_size != 0) ||
+ (ip->i_d.di_nextents > 0) || (ip->i_delayed_blks > 0)) &&
((ip->i_d.di_mode & S_IFMT) == S_IFREG));
mp = ip->i_mount;
@@ -1645,7 +1648,7 @@ xfs_inactive(
if (ip->i_d.di_nlink != 0) {
if ((((ip->i_d.di_mode & S_IFMT) == S_IFREG) &&
- ((ip->i_d.di_size > 0) || (VN_CACHED(vp) > 0 ||
+ ((ip->i_size > 0) || (VN_CACHED(vp) > 0 ||
ip->i_delayed_blks > 0)) &&
(ip->i_df.if_flags & XFS_IFEXTENTS) &&
(!(ip->i_d.di_flags &
@@ -1675,7 +1678,11 @@ xfs_inactive(
*/
xfs_ilock(ip, XFS_IOLOCK_EXCL);
- xfs_itruncate_start(ip, XFS_ITRUNC_DEFINITE, 0);
+ error = xfs_itruncate_start(ip, XFS_ITRUNC_DEFINITE, 0);
+ if (error) {
+ xfs_iunlock(ip, XFS_IOLOCK_EXCL);
+ return VN_INACTIVE_CACHE;
+ }
error = xfs_trans_reserve(tp, 0,
XFS_ITRUNCATE_LOG_RES(mp),
@@ -1790,7 +1797,7 @@ xfs_inactive(
* nothing we can do except to try to keep going.
*/
(void) xfs_bmap_finish(&tp, &free_list, &committed);
- (void) xfs_trans_commit(tp, XFS_TRANS_RELEASE_LOG_RES, NULL);
+ (void) xfs_trans_commit(tp, XFS_TRANS_RELEASE_LOG_RES);
}
/*
* Release the dquots held by inode, if any.
@@ -1940,7 +1947,7 @@ xfs_create(
goto error_return;
}
- xfs_ilock(dp, XFS_ILOCK_EXCL);
+ xfs_ilock(dp, XFS_ILOCK_EXCL | XFS_ILOCK_PARENT);
XFS_BMAP_INIT(&free_list, &first_block);
@@ -2026,7 +2033,7 @@ xfs_create(
goto abort_rele;
}
- error = xfs_trans_commit(tp, XFS_TRANS_RELEASE_LOG_RES, NULL);
+ error = xfs_trans_commit(tp, XFS_TRANS_RELEASE_LOG_RES);
if (error) {
IRELE(ip);
tp = NULL;
@@ -2121,7 +2128,6 @@ int xfs_rm_attempts;
STATIC int
xfs_lock_dir_and_entry(
xfs_inode_t *dp,
- bhv_vname_t *dentry,
xfs_inode_t *ip) /* inode of entry 'name' */
{
int attempts;
@@ -2135,7 +2141,7 @@ xfs_lock_dir_and_entry(
attempts = 0;
again:
- xfs_ilock(dp, XFS_ILOCK_EXCL);
+ xfs_ilock(dp, XFS_ILOCK_EXCL | XFS_ILOCK_PARENT);
e_inum = ip->i_ino;
@@ -2204,6 +2210,21 @@ int xfs_lock_delays;
#endif
/*
+ * Bump the subclass so xfs_lock_inodes() acquires each lock with
+ * a different value
+ */
+static inline int
+xfs_lock_inumorder(int lock_mode, int subclass)
+{
+ if (lock_mode & (XFS_IOLOCK_SHARED|XFS_IOLOCK_EXCL))
+ lock_mode |= (subclass + XFS_IOLOCK_INUMORDER) << XFS_IOLOCK_SHIFT;
+ if (lock_mode & (XFS_ILOCK_SHARED|XFS_ILOCK_EXCL))
+ lock_mode |= (subclass + XFS_ILOCK_INUMORDER) << XFS_ILOCK_SHIFT;
+
+ return lock_mode;
+}
+
+/*
* The following routine will lock n inodes in exclusive mode.
* We assume the caller calls us with the inodes in i_ino order.
*
@@ -2270,7 +2291,7 @@ again:
* that is in the AIL.
*/
ASSERT(i != 0);
- if (!xfs_ilock_nowait(ips[i], lock_mode)) {
+ if (!xfs_ilock_nowait(ips[i], xfs_lock_inumorder(lock_mode, i))) {
attempts++;
/*
@@ -2305,7 +2326,7 @@ again:
goto again;
}
} else {
- xfs_ilock(ips[i], lock_mode);
+ xfs_ilock(ips[i], xfs_lock_inumorder(lock_mode, i));
}
}
@@ -2440,7 +2461,7 @@ xfs_remove(
return error;
}
- error = xfs_lock_dir_and_entry(dp, dentry, ip);
+ error = xfs_lock_dir_and_entry(dp, ip);
if (error) {
REMOVE_DEBUG_TRACE(__LINE__);
xfs_trans_cancel(tp, cancel_flags);
@@ -2511,7 +2532,7 @@ xfs_remove(
goto error_rele;
}
- error = xfs_trans_commit(tp, XFS_TRANS_RELEASE_LOG_RES, NULL);
+ error = xfs_trans_commit(tp, XFS_TRANS_RELEASE_LOG_RES);
if (error) {
IRELE(ip);
goto std_return;
@@ -2719,7 +2740,7 @@ xfs_link(
goto abort_return;
}
- error = xfs_trans_commit(tp, XFS_TRANS_RELEASE_LOG_RES, NULL);
+ error = xfs_trans_commit(tp, XFS_TRANS_RELEASE_LOG_RES);
if (error)
goto std_return;
@@ -2839,7 +2860,7 @@ xfs_mkdir(
goto error_return;
}
- xfs_ilock(dp, XFS_ILOCK_EXCL);
+ xfs_ilock(dp, XFS_ILOCK_EXCL | XFS_ILOCK_PARENT);
/*
* Check for directory link count overflow.
@@ -2936,7 +2957,7 @@ xfs_mkdir(
goto error2;
}
- error = xfs_trans_commit(tp, XFS_TRANS_RELEASE_LOG_RES, NULL);
+ error = xfs_trans_commit(tp, XFS_TRANS_RELEASE_LOG_RES);
XFS_QM_DQRELE(mp, udqp);
XFS_QM_DQRELE(mp, gdqp);
if (error) {
@@ -3096,7 +3117,7 @@ xfs_rmdir(
* that the directory entry for the child directory inode has
* not changed while we were obtaining a log reservation.
*/
- error = xfs_lock_dir_and_entry(dp, dentry, cdp);
+ error = xfs_lock_dir_and_entry(dp, cdp);
if (error) {
xfs_trans_cancel(tp, cancel_flags);
IRELE(cdp);
@@ -3190,7 +3211,7 @@ xfs_rmdir(
goto std_return;
}
- error = xfs_trans_commit(tp, XFS_TRANS_RELEASE_LOG_RES, NULL);
+ error = xfs_trans_commit(tp, XFS_TRANS_RELEASE_LOG_RES);
if (error) {
IRELE(cdp);
goto std_return;
@@ -3393,7 +3414,7 @@ xfs_symlink(
goto error_return;
}
- xfs_ilock(dp, XFS_ILOCK_EXCL);
+ xfs_ilock(dp, XFS_ILOCK_EXCL | XFS_ILOCK_PARENT);
/*
* Check whether the directory allows new symlinks or not.
@@ -3535,7 +3556,7 @@ xfs_symlink(
if (error) {
goto error2;
}
- error = xfs_trans_commit(tp, XFS_TRANS_RELEASE_LOG_RES, NULL);
+ error = xfs_trans_commit(tp, XFS_TRANS_RELEASE_LOG_RES);
XFS_QM_DQRELE(mp, udqp);
XFS_QM_DQRELE(mp, gdqp);
@@ -3790,7 +3811,7 @@ xfs_set_dmattrs (
xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
IHOLD(ip);
- error = xfs_trans_commit(tp, 0, NULL);
+ error = xfs_trans_commit(tp, 0);
return error;
}
@@ -4049,14 +4070,14 @@ xfs_alloc_file_space(
allocatesize_fsb = XFS_B_TO_FSB(mp, count);
/* Generate a DMAPI event if needed. */
- if (alloc_type != 0 && offset < ip->i_d.di_size &&
+ if (alloc_type != 0 && offset < ip->i_size &&
(attr_flags&ATTR_DMI) == 0 &&
DM_EVENT_ENABLED(XFS_MTOVFS(mp), ip, DM_EVENT_WRITE)) {
xfs_off_t end_dmi_offset;
end_dmi_offset = offset+len;
- if (end_dmi_offset > ip->i_d.di_size)
- end_dmi_offset = ip->i_d.di_size;
+ if (end_dmi_offset > ip->i_size)
+ end_dmi_offset = ip->i_size;
error = XFS_SEND_DATA(mp, DM_EVENT_WRITE, XFS_ITOV(ip),
offset, end_dmi_offset - offset,
0, NULL);
@@ -4148,7 +4169,7 @@ retry:
goto error0;
}
- error = xfs_trans_commit(tp, XFS_TRANS_RELEASE_LOG_RES, NULL);
+ error = xfs_trans_commit(tp, XFS_TRANS_RELEASE_LOG_RES);
xfs_iunlock(ip, XFS_ILOCK_EXCL);
if (error) {
break;
@@ -4283,7 +4304,6 @@ xfs_free_file_space(
int error;
xfs_fsblock_t firstfsb;
xfs_bmap_free_t free_list;
- xfs_off_t ilen;
xfs_bmbt_irec_t imap;
xfs_off_t ioffset;
xfs_extlen_t mod=0;
@@ -4312,11 +4332,11 @@ xfs_free_file_space(
end_dmi_offset = offset + len;
endoffset_fsb = XFS_B_TO_FSBT(mp, end_dmi_offset);
- if (offset < ip->i_d.di_size &&
+ if (offset < ip->i_size &&
(attr_flags & ATTR_DMI) == 0 &&
DM_EVENT_ENABLED(XFS_MTOVFS(mp), ip, DM_EVENT_WRITE)) {
- if (end_dmi_offset > ip->i_d.di_size)
- end_dmi_offset = ip->i_d.di_size;
+ if (end_dmi_offset > ip->i_size)
+ end_dmi_offset = ip->i_size;
error = XFS_SEND_DATA(mp, DM_EVENT_WRITE, vp,
offset, end_dmi_offset - offset,
AT_DELAY_FLAG(attr_flags), NULL);
@@ -4332,16 +4352,15 @@ xfs_free_file_space(
}
rounding = max_t(uint, 1 << mp->m_sb.sb_blocklog, NBPP);
- ilen = len + (offset & (rounding - 1));
ioffset = offset & ~(rounding - 1);
- if (ilen & (rounding - 1))
- ilen = (ilen + rounding) & ~(rounding - 1);
if (VN_CACHED(vp) != 0) {
xfs_inval_cached_trace(&ip->i_iocore, ioffset, -1,
ctooff(offtoct(ioffset)), -1);
- bhv_vop_flushinval_pages(vp, ctooff(offtoct(ioffset)),
+ error = bhv_vop_flushinval_pages(vp, ctooff(offtoct(ioffset)),
-1, FI_REMAPF_LOCKED);
+ if (error)
+ goto out_unlock_iolock;
}
/*
@@ -4455,7 +4474,7 @@ xfs_free_file_space(
goto error0;
}
- error = xfs_trans_commit(tp, XFS_TRANS_RELEASE_LOG_RES, NULL);
+ error = xfs_trans_commit(tp, XFS_TRANS_RELEASE_LOG_RES);
xfs_iunlock(ip, XFS_ILOCK_EXCL);
}
@@ -4533,7 +4552,7 @@ xfs_change_file_space(
bf->l_start += offset;
break;
case 2: /*SEEK_END*/
- bf->l_start += ip->i_d.di_size;
+ bf->l_start += ip->i_size;
break;
default:
return XFS_ERROR(EINVAL);
@@ -4550,7 +4569,7 @@ xfs_change_file_space(
bf->l_whence = 0;
startoffset = bf->l_start;
- fsize = ip->i_d.di_size;
+ fsize = ip->i_size;
/*
* XFS_IOC_RESVSP and XFS_IOC_UNRESVSP will reserve or unreserve
@@ -4649,7 +4668,7 @@ xfs_change_file_space(
xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
xfs_trans_set_sync(tp);
- error = xfs_trans_commit(tp, 0, NULL);
+ error = xfs_trans_commit(tp, 0);
xfs_iunlock(ip, XFS_ILOCK_EXCL);