summaryrefslogtreecommitdiff
path: root/fs
diff options
context:
space:
mode:
Diffstat (limited to 'fs')
-rw-r--r--fs/9p/Kconfig1
-rw-r--r--fs/9p/acl.c11
-rw-r--r--fs/9p/acl.h27
-rw-r--r--fs/9p/cache.c141
-rw-r--r--fs/9p/cache.h97
-rw-r--r--fs/9p/fid.c3
-rw-r--r--fs/9p/v9fs.c22
-rw-r--r--fs/9p/v9fs.h17
-rw-r--r--fs/9p/v9fs_vfs.h11
-rw-r--r--fs/9p/vfs_addr.c203
-rw-r--r--fs/9p/vfs_dentry.c4
-rw-r--r--fs/9p/vfs_dir.c6
-rw-r--r--fs/9p/vfs_file.c20
-rw-r--r--fs/9p/vfs_inode.c29
-rw-r--r--fs/9p/vfs_inode_dotl.c11
-rw-r--r--fs/9p/vfs_super.c14
-rw-r--r--fs/9p/xattr.c10
-rw-r--r--fs/9p/xattr.h29
-rw-r--r--fs/afs/file.c14
-rw-r--r--fs/afs/inode.c6
-rw-r--r--fs/afs/internal.h3
-rw-r--r--fs/afs/yfsclient.c32
-rw-r--r--fs/binfmt_elf.c37
-rw-r--r--fs/binfmt_elf_fdpic.c2
-rw-r--r--fs/cifs/cifsfs.c1
-rw-r--r--fs/cifs/cifsglob.h3
-rw-r--r--fs/cifs/connect.c26
-rw-r--r--fs/cifs/fs_context.c16
-rw-r--r--fs/cifs/fs_context.h2
-rw-r--r--fs/cifs/misc.c2
-rw-r--r--fs/cifs/smb2maperror.c16
-rw-r--r--fs/cifs/smb2misc.c47
-rw-r--r--fs/cifs/smb2ops.c73
-rw-r--r--fs/cifs/smb2pdu.c187
-rw-r--r--fs/cifs/smb2pdu.h919
-rw-r--r--fs/cifs/smb2proto.h2
-rw-r--r--fs/cifs/smb2transport.c36
-rw-r--r--fs/cifs/trace.h71
-rw-r--r--fs/coda/cnode.c13
-rw-r--r--fs/coda/coda_linux.c39
-rw-r--r--fs/coda/coda_linux.h6
-rw-r--r--fs/coda/dir.c20
-rw-r--r--fs/coda/file.c12
-rw-r--r--fs/coda/psdev.c14
-rw-r--r--fs/coda/upcall.c3
-rw-r--r--fs/coredump.c88
-rw-r--r--fs/d_path.c8
-rw-r--r--fs/exec.c16
-rw-r--r--fs/ext4/super.c8
-rw-r--r--fs/fuse/dax.c5
-rw-r--r--fs/fuse/dev.c24
-rw-r--r--fs/fuse/dir.c128
-rw-r--r--fs/fuse/file.c106
-rw-r--r--fs/fuse/fuse_i.h17
-rw-r--r--fs/fuse/inode.c45
-rw-r--r--fs/fuse/ioctl.c4
-rw-r--r--fs/fuse/readdir.c6
-rw-r--r--fs/fuse/virtio_fs.c2
-rw-r--r--fs/fuse/xattr.c10
-rw-r--r--fs/gfs2/file.c11
-rw-r--r--fs/gfs2/glock.c163
-rw-r--r--fs/gfs2/glock.h14
-rw-r--r--fs/gfs2/glops.c29
-rw-r--r--fs/gfs2/incore.h6
-rw-r--r--fs/gfs2/inode.c12
-rw-r--r--fs/gfs2/rgrp.c70
-rw-r--r--fs/gfs2/rgrp.h2
-rw-r--r--fs/gfs2/super.c4
-rw-r--r--fs/gfs2/trace_gfs2.h9
-rw-r--r--fs/gfs2/util.c2
-rw-r--r--fs/hfs/inode.c6
-rw-r--r--fs/hfsplus/inode.c12
-rw-r--r--fs/hugetlbfs/inode.c23
-rw-r--r--fs/inode.c46
-rw-r--r--fs/internal.h1
-rw-r--r--fs/io-wq.c16
-rw-r--r--fs/io_uring.c11
-rw-r--r--fs/isofs/inode.c2
-rw-r--r--fs/jfs/jfs_mount.c51
-rw-r--r--fs/kernfs/symlink.c3
-rw-r--r--fs/lockd/clntproc.c3
-rw-r--r--fs/lockd/svc.c6
-rw-r--r--fs/lockd/svc4proc.c2
-rw-r--r--fs/lockd/svcproc.c2
-rw-r--r--fs/lockd/xdr.c152
-rw-r--r--fs/lockd/xdr4.c153
-rw-r--r--fs/nfs/callback_proc.c3
-rw-r--r--fs/nfs/callback_xdr.c4
-rw-r--r--fs/nfs/client.c39
-rw-r--r--fs/nfs/delegation.c10
-rw-r--r--fs/nfs/dir.c119
-rw-r--r--fs/nfs/direct.c2
-rw-r--r--fs/nfs/export.c44
-rw-r--r--fs/nfs/filelayout/filelayout.c2
-rw-r--r--fs/nfs/flexfilelayout/flexfilelayout.c2
-rw-r--r--fs/nfs/flexfilelayout/flexfilelayoutdev.c4
-rw-r--r--fs/nfs/getroot.c21
-rw-r--r--fs/nfs/inode.c130
-rw-r--r--fs/nfs/internal.h12
-rw-r--r--fs/nfs/namespace.c3
-rw-r--r--fs/nfs/nfs3proc.c10
-rw-r--r--fs/nfs/nfs3xdr.c2
-rw-r--r--fs/nfs/nfs42proc.c9
-rw-r--r--fs/nfs/nfs4_fs.h4
-rw-r--r--fs/nfs/nfs4client.c65
-rw-r--r--fs/nfs/nfs4file.c14
-rw-r--r--fs/nfs/nfs4idmap.c2
-rw-r--r--fs/nfs/nfs4proc.c289
-rw-r--r--fs/nfs/nfs4session.c12
-rw-r--r--fs/nfs/nfs4session.h1
-rw-r--r--fs/nfs/nfs4state.c5
-rw-r--r--fs/nfs/nfs4trace.h920
-rw-r--r--fs/nfs/nfs4xdr.c81
-rw-r--r--fs/nfs/nfstrace.h467
-rw-r--r--fs/nfs/pagelist.c13
-rw-r--r--fs/nfs/pnfs.h6
-rw-r--r--fs/nfs/pnfs_nfs.c6
-rw-r--r--fs/nfs/proc.c16
-rw-r--r--fs/nfs/read.c11
-rw-r--r--fs/nfs/super.c7
-rw-r--r--fs/nfs/write.c73
-rw-r--r--fs/nfsd/filecache.c3
-rw-r--r--fs/nfsd/flexfilelayout.c2
-rw-r--r--fs/nfsd/lockd.c2
-rw-r--r--fs/nfsd/nfs2acl.c44
-rw-r--r--fs/nfsd/nfs3acl.c48
-rw-r--r--fs/nfsd/nfs3proc.c3
-rw-r--r--fs/nfsd/nfs3xdr.c387
-rw-r--r--fs/nfsd/nfs4callback.c2
-rw-r--r--fs/nfsd/nfs4proc.c11
-rw-r--r--fs/nfsd/nfs4state.c6
-rw-r--r--fs/nfsd/nfs4xdr.c52
-rw-r--r--fs/nfsd/nfscache.c17
-rw-r--r--fs/nfsd/nfsctl.c6
-rw-r--r--fs/nfsd/nfsd.h6
-rw-r--r--fs/nfsd/nfsfh.c173
-rw-r--r--fs/nfsd/nfsfh.h55
-rw-r--r--fs/nfsd/nfsproc.c3
-rw-r--r--fs/nfsd/nfssvc.c28
-rw-r--r--fs/nfsd/nfsxdr.c187
-rw-r--r--fs/nfsd/trace.h1
-rw-r--r--fs/nfsd/vfs.c7
-rw-r--r--fs/nfsd/xdr.h37
-rw-r--r--fs/nfsd/xdr3.h63
-rw-r--r--fs/nfsd/xdr4.h7
-rw-r--r--fs/nilfs2/alloc.c2
-rw-r--r--fs/nilfs2/alloc.h2
-rw-r--r--fs/nilfs2/bmap.c2
-rw-r--r--fs/nilfs2/bmap.h2
-rw-r--r--fs/nilfs2/btnode.c2
-rw-r--r--fs/nilfs2/btnode.h2
-rw-r--r--fs/nilfs2/btree.c2
-rw-r--r--fs/nilfs2/btree.h2
-rw-r--r--fs/nilfs2/cpfile.c2
-rw-r--r--fs/nilfs2/cpfile.h2
-rw-r--r--fs/nilfs2/dat.c2
-rw-r--r--fs/nilfs2/dat.h2
-rw-r--r--fs/nilfs2/dir.c2
-rw-r--r--fs/nilfs2/direct.c2
-rw-r--r--fs/nilfs2/direct.h2
-rw-r--r--fs/nilfs2/file.c2
-rw-r--r--fs/nilfs2/gcinode.c2
-rw-r--r--fs/nilfs2/ifile.c2
-rw-r--r--fs/nilfs2/ifile.h2
-rw-r--r--fs/nilfs2/inode.c2
-rw-r--r--fs/nilfs2/ioctl.c2
-rw-r--r--fs/nilfs2/mdt.c2
-rw-r--r--fs/nilfs2/mdt.h2
-rw-r--r--fs/nilfs2/namei.c2
-rw-r--r--fs/nilfs2/nilfs.h2
-rw-r--r--fs/nilfs2/page.c2
-rw-r--r--fs/nilfs2/page.h2
-rw-r--r--fs/nilfs2/recovery.c2
-rw-r--r--fs/nilfs2/segbuf.c2
-rw-r--r--fs/nilfs2/segbuf.h2
-rw-r--r--fs/nilfs2/segment.c2
-rw-r--r--fs/nilfs2/segment.h2
-rw-r--r--fs/nilfs2/sufile.c2
-rw-r--r--fs/nilfs2/sufile.h2
-rw-r--r--fs/nilfs2/super.c2
-rw-r--r--fs/nilfs2/sysfs.c78
-rw-r--r--fs/nilfs2/sysfs.h2
-rw-r--r--fs/nilfs2/the_nilfs.c2
-rw-r--r--fs/nilfs2/the_nilfs.h2
-rw-r--r--fs/notify/fanotify/fanotify.c117
-rw-r--r--fs/notify/fanotify/fanotify.h54
-rw-r--r--fs/notify/fanotify/fanotify_user.c157
-rw-r--r--fs/notify/fsnotify.c10
-rw-r--r--fs/notify/group.c2
-rw-r--r--fs/notify/inotify/inotify_fsnotify.c5
-rw-r--r--fs/notify/inotify/inotify_user.c6
-rw-r--r--fs/notify/notification.c14
-rw-r--r--fs/ocfs2/alloc.c21
-rw-r--r--fs/ocfs2/dlm/dlmrecovery.c1
-rw-r--r--fs/ocfs2/file.c8
-rw-r--r--fs/ocfs2/inode.c4
-rw-r--r--fs/ocfs2/journal.c31
-rw-r--r--fs/ocfs2/journal.h3
-rw-r--r--fs/ocfs2/super.c40
-rw-r--r--fs/open.c16
-rw-r--r--fs/orangefs/dcache.c4
-rw-r--r--fs/orangefs/super.c4
-rw-r--r--fs/overlayfs/copy_up.c23
-rw-r--r--fs/overlayfs/dir.c3
-rw-r--r--fs/overlayfs/file.c16
-rw-r--r--fs/overlayfs/inode.c5
-rw-r--r--fs/overlayfs/overlayfs.h1
-rw-r--r--fs/overlayfs/super.c12
-rw-r--r--fs/posix_acl.c3
-rw-r--r--fs/proc/array.c6
-rw-r--r--fs/proc/base.c21
-rw-r--r--fs/proc/task_mmu.c28
-rw-r--r--fs/proc/vmcore.c105
-rw-r--r--fs/quota/quota_tree.c15
-rw-r--r--fs/ramfs/inode.c11
-rw-r--r--fs/reiserfs/super.c6
-rw-r--r--fs/seq_file.c16
-rw-r--r--fs/smbfs_common/smb2pdu.h989
-rw-r--r--fs/super.c3
-rw-r--r--fs/sysfs/dir.c3
-rw-r--r--fs/sysfs/file.c140
-rw-r--r--fs/sysfs/group.c15
-rw-r--r--fs/sysfs/sysfs.h8
-rw-r--r--fs/sysv/super.c6
-rw-r--r--fs/xfs/kmem.h4
-rw-r--r--fs/xfs/libxfs/xfs_ag.c2
-rw-r--r--fs/xfs/libxfs/xfs_ag.h36
-rw-r--r--fs/xfs/libxfs/xfs_ag_resv.c3
-rw-r--r--fs/xfs/libxfs/xfs_alloc.c120
-rw-r--r--fs/xfs/libxfs/xfs_alloc.h38
-rw-r--r--fs/xfs/libxfs/xfs_alloc_btree.c63
-rw-r--r--fs/xfs/libxfs/xfs_alloc_btree.h5
-rw-r--r--fs/xfs/libxfs/xfs_attr_leaf.c2
-rw-r--r--fs/xfs/libxfs/xfs_bmap.c101
-rw-r--r--fs/xfs/libxfs/xfs_bmap.h35
-rw-r--r--fs/xfs/libxfs/xfs_bmap_btree.c62
-rw-r--r--fs/xfs/libxfs/xfs_bmap_btree.h5
-rw-r--r--fs/xfs/libxfs/xfs_btree.c333
-rw-r--r--fs/xfs/libxfs/xfs_btree.h99
-rw-r--r--fs/xfs/libxfs/xfs_btree_staging.c8
-rw-r--r--fs/xfs/libxfs/xfs_da_btree.c6
-rw-r--r--fs/xfs/libxfs/xfs_da_btree.h3
-rw-r--r--fs/xfs/libxfs/xfs_defer.c241
-rw-r--r--fs/xfs/libxfs/xfs_defer.h41
-rw-r--r--fs/xfs/libxfs/xfs_dquot_buf.c4
-rw-r--r--fs/xfs/libxfs/xfs_format.h12
-rw-r--r--fs/xfs/libxfs/xfs_fs.h2
-rw-r--r--fs/xfs/libxfs/xfs_ialloc.c5
-rw-r--r--fs/xfs/libxfs/xfs_ialloc_btree.c90
-rw-r--r--fs/xfs/libxfs/xfs_ialloc_btree.h5
-rw-r--r--fs/xfs/libxfs/xfs_inode_buf.c6
-rw-r--r--fs/xfs/libxfs/xfs_inode_fork.c24
-rw-r--r--fs/xfs/libxfs/xfs_inode_fork.h2
-rw-r--r--fs/xfs/libxfs/xfs_refcount.c46
-rw-r--r--fs/xfs/libxfs/xfs_refcount.h7
-rw-r--r--fs/xfs/libxfs/xfs_refcount_btree.c65
-rw-r--r--fs/xfs/libxfs/xfs_refcount_btree.h5
-rw-r--r--fs/xfs/libxfs/xfs_rmap.c21
-rw-r--r--fs/xfs/libxfs/xfs_rmap.h7
-rw-r--r--fs/xfs/libxfs/xfs_rmap_btree.c116
-rw-r--r--fs/xfs/libxfs/xfs_rmap_btree.h5
-rw-r--r--fs/xfs/libxfs/xfs_sb.c4
-rw-r--r--fs/xfs/libxfs/xfs_trans_resv.c18
-rw-r--r--fs/xfs/libxfs/xfs_trans_space.h9
-rw-r--r--fs/xfs/scrub/agheader.c13
-rw-r--r--fs/xfs/scrub/agheader_repair.c8
-rw-r--r--fs/xfs/scrub/bitmap.c22
-rw-r--r--fs/xfs/scrub/bmap.c2
-rw-r--r--fs/xfs/scrub/btree.c121
-rw-r--r--fs/xfs/scrub/btree.h17
-rw-r--r--fs/xfs/scrub/dabtree.c62
-rw-r--r--fs/xfs/scrub/repair.h3
-rw-r--r--fs/xfs/scrub/scrub.c64
-rw-r--r--fs/xfs/scrub/trace.c11
-rw-r--r--fs/xfs/scrub/trace.h10
-rw-r--r--fs/xfs/xfs_aops.c15
-rw-r--r--fs/xfs/xfs_attr_inactive.c2
-rw-r--r--fs/xfs/xfs_bmap_item.c18
-rw-r--r--fs/xfs/xfs_bmap_item.h6
-rw-r--r--fs/xfs/xfs_buf.c14
-rw-r--r--fs/xfs/xfs_buf_item.c8
-rw-r--r--fs/xfs/xfs_buf_item.h2
-rw-r--r--fs/xfs/xfs_buf_item_recover.c2
-rw-r--r--fs/xfs/xfs_dquot.c28
-rw-r--r--fs/xfs/xfs_extfree_item.c33
-rw-r--r--fs/xfs/xfs_extfree_item.h6
-rw-r--r--fs/xfs/xfs_icache.c10
-rw-r--r--fs/xfs/xfs_icreate_item.c6
-rw-r--r--fs/xfs/xfs_icreate_item.h2
-rw-r--r--fs/xfs/xfs_inode.c12
-rw-r--r--fs/xfs/xfs_inode.h2
-rw-r--r--fs/xfs/xfs_inode_item.c6
-rw-r--r--fs/xfs/xfs_inode_item.h2
-rw-r--r--fs/xfs/xfs_log.c6
-rw-r--r--fs/xfs/xfs_log_priv.h2
-rw-r--r--fs/xfs/xfs_log_recover.c12
-rw-r--r--fs/xfs/xfs_mount.c14
-rw-r--r--fs/xfs/xfs_mount.h5
-rw-r--r--fs/xfs/xfs_mru_cache.c2
-rw-r--r--fs/xfs/xfs_qm.c2
-rw-r--r--fs/xfs/xfs_qm.h2
-rw-r--r--fs/xfs/xfs_refcount_item.c18
-rw-r--r--fs/xfs/xfs_refcount_item.h6
-rw-r--r--fs/xfs/xfs_reflink.c2
-rw-r--r--fs/xfs/xfs_rmap_item.c18
-rw-r--r--fs/xfs/xfs_rmap_item.h6
-rw-r--r--fs/xfs/xfs_super.c233
-rw-r--r--fs/xfs/xfs_sysfs.c24
-rw-r--r--fs/xfs/xfs_trace.h2
-rw-r--r--fs/xfs/xfs_trans.c16
-rw-r--r--fs/xfs/xfs_trans.h8
-rw-r--r--fs/xfs/xfs_trans_dquot.c4
312 files changed, 6333 insertions, 5396 deletions
diff --git a/fs/9p/Kconfig b/fs/9p/Kconfig
index 09fd4a185fd2..d7bc93447c85 100644
--- a/fs/9p/Kconfig
+++ b/fs/9p/Kconfig
@@ -2,6 +2,7 @@
config 9P_FS
tristate "Plan 9 Resource Sharing Support (9P2000)"
depends on INET && NET_9P
+ select NETFS_SUPPORT
help
If you say Y here, you will get experimental support for
Plan 9 resource sharing via the 9P2000 protocol.
diff --git a/fs/9p/acl.c b/fs/9p/acl.c
index c381499f5416..4dac4a0dc5f4 100644
--- a/fs/9p/acl.c
+++ b/fs/9p/acl.c
@@ -1,15 +1,7 @@
+// SPDX-License-Identifier: LGPL-2.1
/*
* Copyright IBM Corporation, 2010
* Author Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of version 2.1 of the GNU Lesser General Public License
- * as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it would be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
- *
*/
#include <linux/module.h>
@@ -123,6 +115,7 @@ static int v9fs_set_acl(struct p9_fid *fid, int type, struct posix_acl *acl)
char *name;
size_t size;
void *buffer;
+
if (!acl)
return 0;
diff --git a/fs/9p/acl.h b/fs/9p/acl.h
index d43c8949e807..ce5175d463dd 100644
--- a/fs/9p/acl.h
+++ b/fs/9p/acl.h
@@ -1,28 +1,21 @@
+/* SPDX-License-Identifier: LGPL-2.1 */
/*
* Copyright IBM Corporation, 2010
* Author Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of version 2.1 of the GNU Lesser General Public License
- * as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it would be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
- *
*/
#ifndef FS_9P_ACL_H
#define FS_9P_ACL_H
#ifdef CONFIG_9P_FS_POSIX_ACL
-extern int v9fs_get_acl(struct inode *, struct p9_fid *);
-extern struct posix_acl *v9fs_iop_get_acl(struct inode *inode, int type, bool rcu);
-extern int v9fs_acl_chmod(struct inode *, struct p9_fid *);
-extern int v9fs_set_create_acl(struct inode *, struct p9_fid *,
- struct posix_acl *, struct posix_acl *);
-extern int v9fs_acl_mode(struct inode *dir, umode_t *modep,
- struct posix_acl **dpacl, struct posix_acl **pacl);
-extern void v9fs_put_acl(struct posix_acl *dacl, struct posix_acl *acl);
+int v9fs_get_acl(struct inode *inode, struct p9_fid *fid);
+struct posix_acl *v9fs_iop_get_acl(struct inode *inode, int type,
+ bool rcu);
+int v9fs_acl_chmod(struct inode *inode, struct p9_fid *fid);
+int v9fs_set_create_acl(struct inode *inode, struct p9_fid *fid,
+ struct posix_acl *dacl, struct posix_acl *acl);
+int v9fs_acl_mode(struct inode *dir, umode_t *modep,
+ struct posix_acl **dpacl, struct posix_acl **pacl);
+void v9fs_put_acl(struct posix_acl *dacl, struct posix_acl *acl);
#else
#define v9fs_iop_get_acl NULL
static inline int v9fs_get_acl(struct inode *inode, struct p9_fid *fid)
diff --git a/fs/9p/cache.c b/fs/9p/cache.c
index 1769a44f4819..f2ba131cede1 100644
--- a/fs/9p/cache.c
+++ b/fs/9p/cache.c
@@ -19,8 +19,8 @@
#define CACHETAG_LEN 11
struct fscache_netfs v9fs_cache_netfs = {
- .name = "9p",
- .version = 0,
+ .name = "9p",
+ .version = 0,
};
/*
@@ -199,140 +199,3 @@ void v9fs_cache_inode_reset_cookie(struct inode *inode)
mutex_unlock(&v9inode->fscache_lock);
}
-
-int __v9fs_fscache_release_page(struct page *page, gfp_t gfp)
-{
- struct inode *inode = page->mapping->host;
- struct v9fs_inode *v9inode = V9FS_I(inode);
-
- BUG_ON(!v9inode->fscache);
-
- return fscache_maybe_release_page(v9inode->fscache, page, gfp);
-}
-
-void __v9fs_fscache_invalidate_page(struct page *page)
-{
- struct inode *inode = page->mapping->host;
- struct v9fs_inode *v9inode = V9FS_I(inode);
-
- BUG_ON(!v9inode->fscache);
-
- if (PageFsCache(page)) {
- fscache_wait_on_page_write(v9inode->fscache, page);
- BUG_ON(!PageLocked(page));
- fscache_uncache_page(v9inode->fscache, page);
- }
-}
-
-static void v9fs_vfs_readpage_complete(struct page *page, void *data,
- int error)
-{
- if (!error)
- SetPageUptodate(page);
-
- unlock_page(page);
-}
-
-/*
- * __v9fs_readpage_from_fscache - read a page from cache
- *
- * Returns 0 if the pages are in cache and a BIO is submitted,
- * 1 if the pages are not in cache and -error otherwise.
- */
-
-int __v9fs_readpage_from_fscache(struct inode *inode, struct page *page)
-{
- int ret;
- const struct v9fs_inode *v9inode = V9FS_I(inode);
-
- p9_debug(P9_DEBUG_FSC, "inode %p page %p\n", inode, page);
- if (!v9inode->fscache)
- return -ENOBUFS;
-
- ret = fscache_read_or_alloc_page(v9inode->fscache,
- page,
- v9fs_vfs_readpage_complete,
- NULL,
- GFP_KERNEL);
- switch (ret) {
- case -ENOBUFS:
- case -ENODATA:
- p9_debug(P9_DEBUG_FSC, "page/inode not in cache %d\n", ret);
- return 1;
- case 0:
- p9_debug(P9_DEBUG_FSC, "BIO submitted\n");
- return ret;
- default:
- p9_debug(P9_DEBUG_FSC, "ret %d\n", ret);
- return ret;
- }
-}
-
-/*
- * __v9fs_readpages_from_fscache - read multiple pages from cache
- *
- * Returns 0 if the pages are in cache and a BIO is submitted,
- * 1 if the pages are not in cache and -error otherwise.
- */
-
-int __v9fs_readpages_from_fscache(struct inode *inode,
- struct address_space *mapping,
- struct list_head *pages,
- unsigned *nr_pages)
-{
- int ret;
- const struct v9fs_inode *v9inode = V9FS_I(inode);
-
- p9_debug(P9_DEBUG_FSC, "inode %p pages %u\n", inode, *nr_pages);
- if (!v9inode->fscache)
- return -ENOBUFS;
-
- ret = fscache_read_or_alloc_pages(v9inode->fscache,
- mapping, pages, nr_pages,
- v9fs_vfs_readpage_complete,
- NULL,
- mapping_gfp_mask(mapping));
- switch (ret) {
- case -ENOBUFS:
- case -ENODATA:
- p9_debug(P9_DEBUG_FSC, "pages/inodes not in cache %d\n", ret);
- return 1;
- case 0:
- BUG_ON(!list_empty(pages));
- BUG_ON(*nr_pages != 0);
- p9_debug(P9_DEBUG_FSC, "BIO submitted\n");
- return ret;
- default:
- p9_debug(P9_DEBUG_FSC, "ret %d\n", ret);
- return ret;
- }
-}
-
-/*
- * __v9fs_readpage_to_fscache - write a page to the cache
- *
- */
-
-void __v9fs_readpage_to_fscache(struct inode *inode, struct page *page)
-{
- int ret;
- const struct v9fs_inode *v9inode = V9FS_I(inode);
-
- p9_debug(P9_DEBUG_FSC, "inode %p page %p\n", inode, page);
- ret = fscache_write_page(v9inode->fscache, page,
- i_size_read(&v9inode->vfs_inode), GFP_KERNEL);
- p9_debug(P9_DEBUG_FSC, "ret = %d\n", ret);
- if (ret != 0)
- v9fs_uncache_page(inode, page);
-}
-
-/*
- * wait for a page to complete writing to the cache
- */
-void __v9fs_fscache_wait_on_page_write(struct inode *inode, struct page *page)
-{
- const struct v9fs_inode *v9inode = V9FS_I(inode);
- p9_debug(P9_DEBUG_FSC, "inode %p page %p\n", inode, page);
- if (PageFsCache(page))
- fscache_wait_on_page_write(v9inode->fscache, page);
-}
diff --git a/fs/9p/cache.h b/fs/9p/cache.h
index 00f107af443e..7480b4b49fea 100644
--- a/fs/9p/cache.h
+++ b/fs/9p/cache.h
@@ -7,9 +7,10 @@
#ifndef _9P_CACHE_H
#define _9P_CACHE_H
-#ifdef CONFIG_9P_FSCACHE
+#define FSCACHE_USE_NEW_IO_API
#include <linux/fscache.h>
-#include <linux/spinlock.h>
+
+#ifdef CONFIG_9P_FSCACHE
extern struct fscache_netfs v9fs_cache_netfs;
extern const struct fscache_cookie_def v9fs_cache_session_index_def;
@@ -27,64 +28,6 @@ extern void v9fs_cache_inode_reset_cookie(struct inode *inode);
extern int __v9fs_cache_register(void);
extern void __v9fs_cache_unregister(void);
-extern int __v9fs_fscache_release_page(struct page *page, gfp_t gfp);
-extern void __v9fs_fscache_invalidate_page(struct page *page);
-extern int __v9fs_readpage_from_fscache(struct inode *inode,
- struct page *page);
-extern int __v9fs_readpages_from_fscache(struct inode *inode,
- struct address_space *mapping,
- struct list_head *pages,
- unsigned *nr_pages);
-extern void __v9fs_readpage_to_fscache(struct inode *inode, struct page *page);
-extern void __v9fs_fscache_wait_on_page_write(struct inode *inode,
- struct page *page);
-
-static inline int v9fs_fscache_release_page(struct page *page,
- gfp_t gfp)
-{
- return __v9fs_fscache_release_page(page, gfp);
-}
-
-static inline void v9fs_fscache_invalidate_page(struct page *page)
-{
- __v9fs_fscache_invalidate_page(page);
-}
-
-static inline int v9fs_readpage_from_fscache(struct inode *inode,
- struct page *page)
-{
- return __v9fs_readpage_from_fscache(inode, page);
-}
-
-static inline int v9fs_readpages_from_fscache(struct inode *inode,
- struct address_space *mapping,
- struct list_head *pages,
- unsigned *nr_pages)
-{
- return __v9fs_readpages_from_fscache(inode, mapping, pages,
- nr_pages);
-}
-
-static inline void v9fs_readpage_to_fscache(struct inode *inode,
- struct page *page)
-{
- if (PageFsCache(page))
- __v9fs_readpage_to_fscache(inode, page);
-}
-
-static inline void v9fs_uncache_page(struct inode *inode, struct page *page)
-{
- struct v9fs_inode *v9inode = V9FS_I(inode);
- fscache_uncache_page(v9inode->fscache, page);
- BUG_ON(PageFsCache(page));
-}
-
-static inline void v9fs_fscache_wait_on_page_write(struct inode *inode,
- struct page *page)
-{
- return __v9fs_fscache_wait_on_page_write(inode, page);
-}
-
#else /* CONFIG_9P_FSCACHE */
static inline void v9fs_cache_inode_get_cookie(struct inode *inode)
@@ -99,39 +42,5 @@ static inline void v9fs_cache_inode_set_cookie(struct inode *inode, struct file
{
}
-static inline int v9fs_fscache_release_page(struct page *page,
- gfp_t gfp) {
- return 1;
-}
-
-static inline void v9fs_fscache_invalidate_page(struct page *page) {}
-
-static inline int v9fs_readpage_from_fscache(struct inode *inode,
- struct page *page)
-{
- return -ENOBUFS;
-}
-
-static inline int v9fs_readpages_from_fscache(struct inode *inode,
- struct address_space *mapping,
- struct list_head *pages,
- unsigned *nr_pages)
-{
- return -ENOBUFS;
-}
-
-static inline void v9fs_readpage_to_fscache(struct inode *inode,
- struct page *page)
-{}
-
-static inline void v9fs_uncache_page(struct inode *inode, struct page *page)
-{}
-
-static inline void v9fs_fscache_wait_on_page_write(struct inode *inode,
- struct page *page)
-{
- return;
-}
-
#endif /* CONFIG_9P_FSCACHE */
#endif /* _9P_CACHE_H */
diff --git a/fs/9p/fid.c b/fs/9p/fid.c
index b8863dd0de5c..6aab046c98e2 100644
--- a/fs/9p/fid.c
+++ b/fs/9p/fid.c
@@ -103,6 +103,7 @@ static struct p9_fid *v9fs_fid_find(struct dentry *dentry, kuid_t uid, int any)
/* we'll recheck under lock if there's anything to look in */
if (!ret && dentry->d_fsdata) {
struct hlist_head *h = (struct hlist_head *)&dentry->d_fsdata;
+
spin_lock(&dentry->d_lock);
hlist_for_each_entry(fid, h, dlist) {
if (any || uid_eq(fid->uid, uid)) {
@@ -185,7 +186,7 @@ static struct p9_fid *v9fs_fid_lookup_with_uid(struct dentry *dentry,
return ERR_PTR(-EPERM);
if (v9fs_proto_dotu(v9ses) || v9fs_proto_dotl(v9ses))
- uname = NULL;
+ uname = NULL;
else
uname = v9ses->uname;
diff --git a/fs/9p/v9fs.c b/fs/9p/v9fs.c
index 2e0fa7c932db..e32dd5f7721b 100644
--- a/fs/9p/v9fs.c
+++ b/fs/9p/v9fs.c
@@ -1,7 +1,5 @@
// SPDX-License-Identifier: GPL-2.0-only
/*
- * linux/fs/9p/v9fs.c
- *
* This file contains functions assisting in mapping VFS to 9P2000
*
* Copyright (C) 2004-2008 by Eric Van Hensbergen <ericvh@gmail.com>
@@ -166,7 +164,7 @@ static int v9fs_parse_options(struct v9fs_session_info *v9ses, char *opts)
substring_t args[MAX_OPT_ARGS];
char *p;
int option = 0;
- char *s, *e;
+ char *s;
int ret = 0;
/* setup defaults */
@@ -190,8 +188,10 @@ static int v9fs_parse_options(struct v9fs_session_info *v9ses, char *opts)
while ((p = strsep(&options, ",")) != NULL) {
int token, r;
+
if (!*p)
continue;
+
token = match_token(p, tokens, args);
switch (token) {
case Opt_debug:
@@ -321,12 +321,13 @@ static int v9fs_parse_options(struct v9fs_session_info *v9ses, char *opts)
v9ses->flags |= V9FS_ACCESS_CLIENT;
} else {
uid_t uid;
+
v9ses->flags |= V9FS_ACCESS_SINGLE;
- uid = simple_strtoul(s, &e, 10);
- if (*e != '\0') {
- ret = -EINVAL;
- pr_info("Unknown access argument %s\n",
- s);
+ r = kstrtouint(s, 10, &uid);
+ if (r) {
+ ret = r;
+ pr_info("Unknown access argument %s: %d\n",
+ s, r);
kfree(s);
continue;
}
@@ -520,7 +521,8 @@ void v9fs_session_close(struct v9fs_session_info *v9ses)
* mark transport as disconnected and cancel all pending requests.
*/
-void v9fs_session_cancel(struct v9fs_session_info *v9ses) {
+void v9fs_session_cancel(struct v9fs_session_info *v9ses)
+{
p9_debug(P9_DEBUG_ERROR, "cancel session %p\n", v9ses);
p9_client_disconnect(v9ses->clnt);
}
@@ -659,6 +661,7 @@ static void v9fs_destroy_inode_cache(void)
static int v9fs_cache_register(void)
{
int ret;
+
ret = v9fs_init_inode_cache();
if (ret < 0)
return ret;
@@ -686,6 +689,7 @@ static void v9fs_cache_unregister(void)
static int __init init_v9fs(void)
{
int err;
+
pr_info("Installing v9fs 9p2000 file system support\n");
/* TODO: Setup list of registered trasnport modules */
diff --git a/fs/9p/v9fs.h b/fs/9p/v9fs.h
index 4ca56c5dd637..1647a8e63671 100644
--- a/fs/9p/v9fs.h
+++ b/fs/9p/v9fs.h
@@ -124,15 +124,24 @@ static inline struct v9fs_inode *V9FS_I(const struct inode *inode)
return container_of(inode, struct v9fs_inode, vfs_inode);
}
+static inline struct fscache_cookie *v9fs_inode_cookie(struct v9fs_inode *v9inode)
+{
+#ifdef CONFIG_9P_FSCACHE
+ return v9inode->fscache;
+#else
+ return NULL;
+#endif
+}
+
extern int v9fs_show_options(struct seq_file *m, struct dentry *root);
-struct p9_fid *v9fs_session_init(struct v9fs_session_info *, const char *,
- char *);
+struct p9_fid *v9fs_session_init(struct v9fs_session_info *v9ses,
+ const char *dev_name, char *data);
extern void v9fs_session_close(struct v9fs_session_info *v9ses);
extern void v9fs_session_cancel(struct v9fs_session_info *v9ses);
extern void v9fs_session_begin_cancel(struct v9fs_session_info *v9ses);
extern struct dentry *v9fs_vfs_lookup(struct inode *dir, struct dentry *dentry,
- unsigned int flags);
+ unsigned int flags);
extern int v9fs_vfs_unlink(struct inode *i, struct dentry *d);
extern int v9fs_vfs_rmdir(struct inode *i, struct dentry *d);
extern int v9fs_vfs_rename(struct user_namespace *mnt_userns,
@@ -158,7 +167,7 @@ extern struct inode *v9fs_inode_from_fid_dotl(struct v9fs_session_info *v9ses,
static inline struct v9fs_session_info *v9fs_inode2v9ses(struct inode *inode)
{
- return (inode->i_sb->s_fs_info);
+ return inode->i_sb->s_fs_info;
}
static inline struct v9fs_session_info *v9fs_dentry2v9ses(struct dentry *dentry)
diff --git a/fs/9p/v9fs_vfs.h b/fs/9p/v9fs_vfs.h
index d44ade76966a..bc417da7e9c1 100644
--- a/fs/9p/v9fs_vfs.h
+++ b/fs/9p/v9fs_vfs.h
@@ -44,9 +44,10 @@ extern struct kmem_cache *v9fs_inode_cache;
struct inode *v9fs_alloc_inode(struct super_block *sb);
void v9fs_free_inode(struct inode *inode);
-struct inode *v9fs_get_inode(struct super_block *sb, umode_t mode, dev_t);
+struct inode *v9fs_get_inode(struct super_block *sb, umode_t mode,
+ dev_t rdev);
int v9fs_init_inode(struct v9fs_session_info *v9ses,
- struct inode *inode, umode_t mode, dev_t);
+ struct inode *inode, umode_t mode, dev_t rdev);
void v9fs_evict_inode(struct inode *inode);
ino_t v9fs_qid2ino(struct p9_qid *qid);
void v9fs_stat2inode(struct p9_wstat *stat, struct inode *inode,
@@ -59,8 +60,8 @@ void v9fs_inode2stat(struct inode *inode, struct p9_wstat *stat);
int v9fs_uflags2omode(int uflags, int extended);
void v9fs_blank_wstat(struct p9_wstat *wstat);
-int v9fs_vfs_setattr_dotl(struct user_namespace *, struct dentry *,
- struct iattr *);
+int v9fs_vfs_setattr_dotl(struct user_namespace *mnt_userns,
+ struct dentry *dentry, struct iattr *iattr);
int v9fs_file_fsync_dotl(struct file *filp, loff_t start, loff_t end,
int datasync);
int v9fs_refresh_inode(struct p9_fid *fid, struct inode *inode);
@@ -68,9 +69,9 @@ int v9fs_refresh_inode_dotl(struct p9_fid *fid, struct inode *inode);
static inline void v9fs_invalidate_inode_attr(struct inode *inode)
{
struct v9fs_inode *v9inode;
+
v9inode = V9FS_I(inode);
v9inode->cache_validity |= V9FS_INO_INVALID_ATTR;
- return;
}
int v9fs_open_to_dotl_flags(int flags);
diff --git a/fs/9p/vfs_addr.c b/fs/9p/vfs_addr.c
index 1c4f1b39cc95..adafdf86f42f 100644
--- a/fs/9p/vfs_addr.c
+++ b/fs/9p/vfs_addr.c
@@ -1,7 +1,5 @@
// SPDX-License-Identifier: GPL-2.0-only
/*
- * linux/fs/9p/vfs_addr.c
- *
* This file contians vfs address (mmap) ops for 9P2000.
*
* Copyright (C) 2005 by Eric Van Hensbergen <ericvh@gmail.com>
@@ -19,7 +17,7 @@
#include <linux/idr.h>
#include <linux/sched.h>
#include <linux/uio.h>
-#include <linux/bvec.h>
+#include <linux/netfs.h>
#include <net/9p/9p.h>
#include <net/9p/client.h>
@@ -29,88 +27,97 @@
#include "fid.h"
/**
- * v9fs_fid_readpage - read an entire page in from 9P
- * @data: Opaque pointer to the fid being read
- * @page: structure to page
- *
+ * v9fs_req_issue_op - Issue a read from 9P
+ * @subreq: The read to make
*/
-static int v9fs_fid_readpage(void *data, struct page *page)
+static void v9fs_req_issue_op(struct netfs_read_subrequest *subreq)
{
- struct p9_fid *fid = data;
- struct inode *inode = page->mapping->host;
- struct bio_vec bvec = {.bv_page = page, .bv_len = PAGE_SIZE};
+ struct netfs_read_request *rreq = subreq->rreq;
+ struct p9_fid *fid = rreq->netfs_priv;
struct iov_iter to;
- int retval, err;
+ loff_t pos = subreq->start + subreq->transferred;
+ size_t len = subreq->len - subreq->transferred;
+ int total, err;
- p9_debug(P9_DEBUG_VFS, "\n");
+ iov_iter_xarray(&to, READ, &rreq->mapping->i_pages, pos, len);
- BUG_ON(!PageLocked(page));
+ total = p9_client_read(fid, pos, &to, &err);
+ netfs_subreq_terminated(subreq, err ?: total, false);
+}
- retval = v9fs_readpage_from_fscache(inode, page);
- if (retval == 0)
- return retval;
+/**
+ * v9fs_init_rreq - Initialise a read request
+ * @rreq: The read request
+ * @file: The file being read from
+ */
+static void v9fs_init_rreq(struct netfs_read_request *rreq, struct file *file)
+{
+ struct p9_fid *fid = file->private_data;
- iov_iter_bvec(&to, READ, &bvec, 1, PAGE_SIZE);
+ refcount_inc(&fid->count);
+ rreq->netfs_priv = fid;
+}
- retval = p9_client_read(fid, page_offset(page), &to, &err);
- if (err) {
- v9fs_uncache_page(inode, page);
- retval = err;
- goto done;
- }
+/**
+ * v9fs_req_cleanup - Cleanup request initialized by v9fs_init_rreq
+ * @mapping: unused mapping of request to cleanup
+ * @priv: private data to cleanup, a fid, guaranted non-null.
+ */
+static void v9fs_req_cleanup(struct address_space *mapping, void *priv)
+{
+ struct p9_fid *fid = priv;
- zero_user(page, retval, PAGE_SIZE - retval);
- flush_dcache_page(page);
- SetPageUptodate(page);
+ p9_client_clunk(fid);
+}
- v9fs_readpage_to_fscache(inode, page);
- retval = 0;
+/**
+ * v9fs_is_cache_enabled - Determine if caching is enabled for an inode
+ * @inode: The inode to check
+ */
+static bool v9fs_is_cache_enabled(struct inode *inode)
+{
+ struct fscache_cookie *cookie = v9fs_inode_cookie(V9FS_I(inode));
-done:
- unlock_page(page);
- return retval;
+ return fscache_cookie_enabled(cookie) && !hlist_empty(&cookie->backing_objects);
}
/**
+ * v9fs_begin_cache_operation - Begin a cache operation for a read
+ * @rreq: The read request
+ */
+static int v9fs_begin_cache_operation(struct netfs_read_request *rreq)
+{
+ struct fscache_cookie *cookie = v9fs_inode_cookie(V9FS_I(rreq->inode));
+
+ return fscache_begin_read_operation(rreq, cookie);
+}
+
+static const struct netfs_read_request_ops v9fs_req_ops = {
+ .init_rreq = v9fs_init_rreq,
+ .is_cache_enabled = v9fs_is_cache_enabled,
+ .begin_cache_operation = v9fs_begin_cache_operation,
+ .issue_op = v9fs_req_issue_op,
+ .cleanup = v9fs_req_cleanup,
+};
+
+/**
* v9fs_vfs_readpage - read an entire page in from 9P
- *
- * @filp: file being read
+ * @file: file being read
* @page: structure to page
*
*/
-
-static int v9fs_vfs_readpage(struct file *filp, struct page *page)
+static int v9fs_vfs_readpage(struct file *file, struct page *page)
{
- return v9fs_fid_readpage(filp->private_data, page);
+ return netfs_readpage(file, page, &v9fs_req_ops, NULL);
}
/**
- * v9fs_vfs_readpages - read a set of pages from 9P
- *
- * @filp: file being read
- * @mapping: the address space
- * @pages: list of pages to read
- * @nr_pages: count of pages to read
- *
+ * v9fs_vfs_readahead - read a set of pages from 9P
+ * @ractl: The readahead parameters
*/
-
-static int v9fs_vfs_readpages(struct file *filp, struct address_space *mapping,
- struct list_head *pages, unsigned nr_pages)
+static void v9fs_vfs_readahead(struct readahead_control *ractl)
{
- int ret = 0;
- struct inode *inode;
-
- inode = mapping->host;
- p9_debug(P9_DEBUG_VFS, "inode: %p file: %p\n", inode, filp);
-
- ret = v9fs_readpages_from_fscache(inode, mapping, pages, &nr_pages);
- if (ret == 0)
- return ret;
-
- ret = read_cache_pages(mapping, pages, v9fs_fid_readpage,
- filp->private_data);
- p9_debug(P9_DEBUG_VFS, " = %d\n", ret);
- return ret;
+ netfs_readahead(ractl, &v9fs_req_ops, NULL);
}
/**
@@ -125,7 +132,14 @@ static int v9fs_release_page(struct page *page, gfp_t gfp)
{
if (PagePrivate(page))
return 0;
- return v9fs_fscache_release_page(page, gfp);
+#ifdef CONFIG_9P_FSCACHE
+ if (PageFsCache(page)) {
+ if (!(gfp & __GFP_DIRECT_RECLAIM) || !(gfp & __GFP_FS))
+ return 0;
+ wait_on_page_fscache(page);
+ }
+#endif
+ return 1;
}
/**
@@ -138,21 +152,16 @@ static int v9fs_release_page(struct page *page, gfp_t gfp)
static void v9fs_invalidate_page(struct page *page, unsigned int offset,
unsigned int length)
{
- /*
- * If called with zero offset, we should release
- * the private state assocated with the page
- */
- if (offset == 0 && length == PAGE_SIZE)
- v9fs_fscache_invalidate_page(page);
+ wait_on_page_fscache(page);
}
static int v9fs_vfs_writepage_locked(struct page *page)
{
struct inode *inode = page->mapping->host;
struct v9fs_inode *v9inode = V9FS_I(inode);
+ loff_t start = page_offset(page);
loff_t size = i_size_read(inode);
struct iov_iter from;
- struct bio_vec bvec;
int err, len;
if (page->index == size >> PAGE_SHIFT)
@@ -160,17 +169,14 @@ static int v9fs_vfs_writepage_locked(struct page *page)
else
len = PAGE_SIZE;
- bvec.bv_page = page;
- bvec.bv_offset = 0;
- bvec.bv_len = len;
- iov_iter_bvec(&from, WRITE, &bvec, 1, len);
+ iov_iter_xarray(&from, WRITE, &page->mapping->i_pages, start, len);
/* We should have writeback_fid always set */
BUG_ON(!v9inode->writeback_fid);
set_page_writeback(page);
- p9_client_write(v9inode->writeback_fid, page_offset(page), &from, &err);
+ p9_client_write(v9inode->writeback_fid, start, &from, &err);
end_page_writeback(page);
return err;
@@ -208,14 +214,13 @@ static int v9fs_vfs_writepage(struct page *page, struct writeback_control *wbc)
static int v9fs_launder_page(struct page *page)
{
int retval;
- struct inode *inode = page->mapping->host;
- v9fs_fscache_wait_on_page_write(inode, page);
if (clear_page_dirty_for_io(page)) {
retval = v9fs_vfs_writepage_locked(page);
if (retval)
return retval;
}
+ wait_on_page_fscache(page);
return 0;
}
@@ -242,11 +247,13 @@ v9fs_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
loff_t pos = iocb->ki_pos;
ssize_t n;
int err = 0;
+
if (iov_iter_rw(iter) == WRITE) {
n = p9_client_write(file->private_data, pos, iter, &err);
if (n) {
struct inode *inode = file_inode(file);
loff_t i_size = i_size_read(inode);
+
if (pos + n > i_size)
inode_add_bytes(inode, pos + n - i_size);
}
@@ -257,43 +264,32 @@ v9fs_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
}
static int v9fs_write_begin(struct file *filp, struct address_space *mapping,
- loff_t pos, unsigned len, unsigned flags,
+ loff_t pos, unsigned int len, unsigned int flags,
struct page **pagep, void **fsdata)
{
- int retval = 0;
+ int retval;
struct page *page;
- struct v9fs_inode *v9inode;
- pgoff_t index = pos >> PAGE_SHIFT;
- struct inode *inode = mapping->host;
-
+ struct v9fs_inode *v9inode = V9FS_I(mapping->host);
p9_debug(P9_DEBUG_VFS, "filp %p, mapping %p\n", filp, mapping);
- v9inode = V9FS_I(inode);
-start:
- page = grab_cache_page_write_begin(mapping, index, flags);
- if (!page) {
- retval = -ENOMEM;
- goto out;
- }
BUG_ON(!v9inode->writeback_fid);
- if (PageUptodate(page))
- goto out;
- if (len == PAGE_SIZE)
- goto out;
+ /* Prefetch area to be written into the cache if we're caching this
+ * file. We need to do this before we get a lock on the page in case
+ * there's more than one writer competing for the same cache block.
+ */
+ retval = netfs_write_begin(filp, mapping, pos, len, flags, &page, fsdata,
+ &v9fs_req_ops, NULL);
+ if (retval < 0)
+ return retval;
- retval = v9fs_fid_readpage(v9inode->writeback_fid, page);
- put_page(page);
- if (!retval)
- goto start;
-out:
- *pagep = page;
+ *pagep = find_subpage(page, pos / PAGE_SIZE);
return retval;
}
static int v9fs_write_end(struct file *filp, struct address_space *mapping,
- loff_t pos, unsigned len, unsigned copied,
+ loff_t pos, unsigned int len, unsigned int copied,
struct page *page, void *fsdata)
{
loff_t last_pos = pos + copied;
@@ -305,10 +301,11 @@ static int v9fs_write_end(struct file *filp, struct address_space *mapping,
if (unlikely(copied < len)) {
copied = 0;
goto out;
- } else if (len == PAGE_SIZE) {
- SetPageUptodate(page);
}
+
+ SetPageUptodate(page);
}
+
/*
* No need to use i_size_read() here, the i_size
* cannot change under us because we hold the i_mutex.
@@ -328,7 +325,7 @@ out:
const struct address_space_operations v9fs_addr_operations = {
.readpage = v9fs_vfs_readpage,
- .readpages = v9fs_vfs_readpages,
+ .readahead = v9fs_vfs_readahead,
.set_page_dirty = __set_page_dirty_nobuffers,
.writepage = v9fs_vfs_writepage,
.write_begin = v9fs_write_begin,
diff --git a/fs/9p/vfs_dentry.c b/fs/9p/vfs_dentry.c
index 4b4292123b3d..1c609e99d280 100644
--- a/fs/9p/vfs_dentry.c
+++ b/fs/9p/vfs_dentry.c
@@ -1,7 +1,5 @@
// SPDX-License-Identifier: GPL-2.0-only
/*
- * linux/fs/9p/vfs_dentry.c
- *
* This file contians vfs dentry ops for the 9P2000 protocol.
*
* Copyright (C) 2004 by Eric Van Hensbergen <ericvh@gmail.com>
@@ -52,6 +50,7 @@ static int v9fs_cached_dentry_delete(const struct dentry *dentry)
static void v9fs_dentry_release(struct dentry *dentry)
{
struct hlist_node *p, *n;
+
p9_debug(P9_DEBUG_VFS, " dentry: %pd (%p)\n",
dentry, dentry);
hlist_for_each_safe(p, n, (struct hlist_head *)&dentry->d_fsdata)
@@ -76,6 +75,7 @@ static int v9fs_lookup_revalidate(struct dentry *dentry, unsigned int flags)
if (v9inode->cache_validity & V9FS_INO_INVALID_ATTR) {
int retval;
struct v9fs_session_info *v9ses;
+
fid = v9fs_fid_lookup(dentry);
if (IS_ERR(fid))
return PTR_ERR(fid);
diff --git a/fs/9p/vfs_dir.c b/fs/9p/vfs_dir.c
index b6a5a0be444d..8c854d8cb0cd 100644
--- a/fs/9p/vfs_dir.c
+++ b/fs/9p/vfs_dir.c
@@ -1,7 +1,5 @@
// SPDX-License-Identifier: GPL-2.0-only
/*
- * linux/fs/9p/vfs_dir.c
- *
* This file contains vfs directory ops for the 9P2000 protocol.
*
* Copyright (C) 2004 by Eric Van Hensbergen <ericvh@gmail.com>
@@ -71,6 +69,7 @@ static inline int dt_type(struct p9_wstat *mistat)
static struct p9_rdir *v9fs_alloc_rdir_buf(struct file *filp, int buflen)
{
struct p9_fid *fid = filp->private_data;
+
if (!fid->rdir)
fid->rdir = kzalloc(sizeof(struct p9_rdir) + buflen, GFP_KERNEL);
return fid->rdir;
@@ -108,6 +107,7 @@ static int v9fs_dir_readdir(struct file *file, struct dir_context *ctx)
if (rdir->tail == rdir->head) {
struct iov_iter to;
int n;
+
iov_iter_kvec(&to, READ, &kvec, 1, buflen);
n = p9_client_read(file->private_data, ctx->pos, &to,
&err);
@@ -233,5 +233,5 @@ const struct file_operations v9fs_dir_operations_dotl = {
.iterate_shared = v9fs_dir_readdir_dotl,
.open = v9fs_file_open,
.release = v9fs_dir_release,
- .fsync = v9fs_file_fsync_dotl,
+ .fsync = v9fs_file_fsync_dotl,
};
diff --git a/fs/9p/vfs_file.c b/fs/9p/vfs_file.c
index 246235ebdb70..4244d48398ef 100644
--- a/fs/9p/vfs_file.c
+++ b/fs/9p/vfs_file.c
@@ -1,7 +1,5 @@
// SPDX-License-Identifier: GPL-2.0-only
/*
- * linux/fs/9p/vfs_file.c
- *
* This file contians vfs file ops for 9P2000.
*
* Copyright (C) 2004 by Eric Van Hensbergen <ericvh@gmail.com>
@@ -408,6 +406,7 @@ v9fs_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
struct inode *inode = file_inode(file);
loff_t i_size;
unsigned long pg_start, pg_end;
+
pg_start = origin >> PAGE_SHIFT;
pg_end = (origin + retval - 1) >> PAGE_SHIFT;
if (inode->i_mapping && inode->i_mapping->nrpages)
@@ -537,14 +536,23 @@ v9fs_vm_page_mkwrite(struct vm_fault *vmf)
p9_debug(P9_DEBUG_VFS, "page %p fid %lx\n",
page, (unsigned long)filp->private_data);
+ v9inode = V9FS_I(inode);
+
+ /* Wait for the page to be written to the cache before we allow it to
+ * be modified. We then assume the entire page will need writing back.
+ */
+#ifdef CONFIG_9P_FSCACHE
+ if (PageFsCache(page) &&
+ wait_on_page_fscache_killable(page) < 0)
+ return VM_FAULT_RETRY;
+#endif
+
/* Update file times before taking page lock */
file_update_time(filp);
- v9inode = V9FS_I(inode);
- /* make sure the cache has finished storing the page */
- v9fs_fscache_wait_on_page_write(inode, page);
BUG_ON(!v9inode->writeback_fid);
- lock_page(page);
+ if (lock_page_killable(page) < 0)
+ return VM_FAULT_RETRY;
if (page->mapping != inode->i_mapping)
goto out_unlock;
wait_for_stable_page(page);
diff --git a/fs/9p/vfs_inode.c b/fs/9p/vfs_inode.c
index 08f48b70a741..328c338ff304 100644
--- a/fs/9p/vfs_inode.c
+++ b/fs/9p/vfs_inode.c
@@ -1,7 +1,5 @@
// SPDX-License-Identifier: GPL-2.0-only
/*
- * linux/fs/9p/vfs_inode.c
- *
* This file contains vfs inode ops for the 9P2000 protocol.
*
* Copyright (C) 2004 by Eric Van Hensbergen <ericvh@gmail.com>
@@ -49,6 +47,7 @@ static const struct inode_operations v9fs_symlink_inode_operations;
static u32 unixmode2p9mode(struct v9fs_session_info *v9ses, umode_t mode)
{
int res;
+
res = mode & 0777;
if (S_ISDIR(mode))
res |= P9_DMDIR;
@@ -110,7 +109,7 @@ static int p9mode2perm(struct v9fs_session_info *v9ses,
static umode_t p9mode2unixmode(struct v9fs_session_info *v9ses,
struct p9_wstat *stat, dev_t *rdev)
{
- int res;
+ int res, r;
u32 mode = stat->mode;
*rdev = 0;
@@ -128,11 +127,16 @@ static umode_t p9mode2unixmode(struct v9fs_session_info *v9ses,
res |= S_IFIFO;
else if ((mode & P9_DMDEVICE) && (v9fs_proto_dotu(v9ses))
&& (v9ses->nodev == 0)) {
- char type = 0, ext[32];
+ char type = 0;
int major = -1, minor = -1;
- strlcpy(ext, stat->extension, sizeof(ext));
- sscanf(ext, "%c %i %i", &type, &major, &minor);
+ r = sscanf(stat->extension, "%c %i %i", &type, &major, &minor);
+ if (r != 3) {
+ p9_debug(P9_DEBUG_ERROR,
+ "invalid device string, umode will be bogus: %s\n",
+ stat->extension);
+ return res;
+ }
switch (type) {
case 'c':
res |= S_IFCHR;
@@ -223,6 +227,7 @@ v9fs_blank_wstat(struct p9_wstat *wstat)
struct inode *v9fs_alloc_inode(struct super_block *sb)
{
struct v9fs_inode *v9inode;
+
v9inode = kmem_cache_alloc(v9fs_inode_cache, GFP_KERNEL);
if (!v9inode)
return NULL;
@@ -251,7 +256,7 @@ int v9fs_init_inode(struct v9fs_session_info *v9ses,
{
int err = 0;
- inode_init_owner(&init_user_ns,inode, NULL, mode);
+ inode_init_owner(&init_user_ns, inode, NULL, mode);
inode->i_blocks = 0;
inode->i_rdev = rdev;
inode->i_atime = inode->i_mtime = inode->i_ctime = current_time(inode);
@@ -440,7 +445,7 @@ static struct inode *v9fs_qid_iget(struct super_block *sb,
unsigned long i_ino;
struct inode *inode;
struct v9fs_session_info *v9ses = sb->s_fs_info;
- int (*test)(struct inode *, void *);
+ int (*test)(struct inode *inode, void *data);
if (new)
test = v9fs_test_new_inode;
@@ -499,8 +504,10 @@ v9fs_inode_from_fid(struct v9fs_session_info *v9ses, struct p9_fid *fid,
static int v9fs_at_to_dotl_flags(int flags)
{
int rflags = 0;
+
if (flags & AT_REMOVEDIR)
rflags |= P9_DOTL_AT_REMOVEDIR;
+
return rflags;
}
@@ -797,7 +804,7 @@ struct dentry *v9fs_vfs_lookup(struct inode *dir, struct dentry *dentry,
static int
v9fs_vfs_atomic_open(struct inode *dir, struct dentry *dentry,
- struct file *file, unsigned flags, umode_t mode)
+ struct file *file, unsigned int flags, umode_t mode)
{
int err;
u32 perm;
@@ -1084,7 +1091,7 @@ static int v9fs_vfs_setattr(struct user_namespace *mnt_userns,
fid = v9fs_fid_lookup(dentry);
use_dentry = 1;
}
- if(IS_ERR(fid))
+ if (IS_ERR(fid))
return PTR_ERR(fid);
v9fs_blank_wstat(&wstat);
@@ -1364,7 +1371,7 @@ v9fs_vfs_mknod(struct user_namespace *mnt_userns, struct inode *dir,
char name[2 + U32_MAX_DIGITS + 1 + U32_MAX_DIGITS + 1];
u32 perm;
- p9_debug(P9_DEBUG_VFS, " %lu,%pd mode: %hx MAJOR: %u MINOR: %u\n",
+ p9_debug(P9_DEBUG_VFS, " %lu,%pd mode: %x MAJOR: %u MINOR: %u\n",
dir->i_ino, dentry, mode,
MAJOR(rdev), MINOR(rdev));
diff --git a/fs/9p/vfs_inode_dotl.c b/fs/9p/vfs_inode_dotl.c
index 01b9e1281a29..7dee89ba32e7 100644
--- a/fs/9p/vfs_inode_dotl.c
+++ b/fs/9p/vfs_inode_dotl.c
@@ -1,7 +1,5 @@
// SPDX-License-Identifier: GPL-2.0-only
/*
- * linux/fs/9p/vfs_inode_dotl.c
- *
* This file contains vfs inode ops for the 9P2000.L protocol.
*
* Copyright (C) 2004 by Eric Van Hensbergen <ericvh@gmail.com>
@@ -107,7 +105,7 @@ static struct inode *v9fs_qid_iget_dotl(struct super_block *sb,
unsigned long i_ino;
struct inode *inode;
struct v9fs_session_info *v9ses = sb->s_fs_info;
- int (*test)(struct inode *, void *);
+ int (*test)(struct inode *inode, void *data);
if (new)
test = v9fs_test_new_inode_dotl;
@@ -230,7 +228,7 @@ v9fs_vfs_create_dotl(struct user_namespace *mnt_userns, struct inode *dir,
static int
v9fs_vfs_atomic_open_dotl(struct inode *dir, struct dentry *dentry,
- struct file *file, unsigned flags, umode_t omode)
+ struct file *file, unsigned int flags, umode_t omode)
{
int err = 0;
kgid_t gid;
@@ -261,7 +259,7 @@ v9fs_vfs_atomic_open_dotl(struct inode *dir, struct dentry *dentry,
v9ses = v9fs_inode2v9ses(dir);
name = dentry->d_name.name;
- p9_debug(P9_DEBUG_VFS, "name:%s flags:0x%x mode:0x%hx\n",
+ p9_debug(P9_DEBUG_VFS, "name:%s flags:0x%x mode:0x%x\n",
name, flags, omode);
dfid = v9fs_parent_fid(dentry);
@@ -807,6 +805,7 @@ v9fs_vfs_link_dotl(struct dentry *old_dentry, struct inode *dir,
if (v9ses->cache == CACHE_LOOSE || v9ses->cache == CACHE_FSCACHE) {
/* Get the latest stat info from server. */
struct p9_fid *fid;
+
fid = v9fs_fid_lookup(old_dentry);
if (IS_ERR(fid))
return PTR_ERR(fid);
@@ -843,7 +842,7 @@ v9fs_vfs_mknod_dotl(struct user_namespace *mnt_userns, struct inode *dir,
struct p9_qid qid;
struct posix_acl *dacl = NULL, *pacl = NULL;
- p9_debug(P9_DEBUG_VFS, " %lu,%pd mode: %hx MAJOR: %u MINOR: %u\n",
+ p9_debug(P9_DEBUG_VFS, " %lu,%pd mode: %x MAJOR: %u MINOR: %u\n",
dir->i_ino, dentry, omode,
MAJOR(rdev), MINOR(rdev));
diff --git a/fs/9p/vfs_super.c b/fs/9p/vfs_super.c
index 5fce6e30bc5a..b739e02f5ef7 100644
--- a/fs/9p/vfs_super.c
+++ b/fs/9p/vfs_super.c
@@ -1,9 +1,5 @@
// SPDX-License-Identifier: GPL-2.0-only
/*
- * linux/fs/9p/vfs_super.c
- *
- * This file contians superblock ops for 9P2000. It is intended that
- * you mount this file system on directories.
*
* Copyright (C) 2004 by Eric Van Hensbergen <ericvh@gmail.com>
* Copyright (C) 2002 by Ron Minnich <rminnich@lanl.gov>
@@ -83,6 +79,9 @@ v9fs_fill_super(struct super_block *sb, struct v9fs_session_info *v9ses,
if (!v9ses->cache) {
sb->s_bdi->ra_pages = 0;
sb->s_bdi->io_pages = 0;
+ } else {
+ sb->s_bdi->ra_pages = v9ses->maxdata >> PAGE_SHIFT;
+ sb->s_bdi->io_pages = v9ses->maxdata >> PAGE_SHIFT;
}
sb->s_flags |= SB_ACTIVE | SB_DIRSYNC;
@@ -113,7 +112,7 @@ static struct dentry *v9fs_mount(struct file_system_type *fs_type, int flags,
struct inode *inode = NULL;
struct dentry *root = NULL;
struct v9fs_session_info *v9ses = NULL;
- umode_t mode = S_IRWXUGO | S_ISVTX;
+ umode_t mode = 0777 | S_ISVTX;
struct p9_fid *fid;
int retval = 0;
@@ -157,6 +156,7 @@ static struct dentry *v9fs_mount(struct file_system_type *fs_type, int flags,
sb->s_root = root;
if (v9fs_proto_dotl(v9ses)) {
struct p9_stat_dotl *st = NULL;
+
st = p9_client_getattr_dotl(fid, P9_STATS_BASIC);
if (IS_ERR(st)) {
retval = PTR_ERR(st);
@@ -167,6 +167,7 @@ static struct dentry *v9fs_mount(struct file_system_type *fs_type, int flags,
kfree(st);
} else {
struct p9_wstat *st = NULL;
+
st = p9_client_stat(fid);
if (IS_ERR(st)) {
retval = PTR_ERR(st);
@@ -275,12 +276,13 @@ done:
static int v9fs_drop_inode(struct inode *inode)
{
struct v9fs_session_info *v9ses;
+
v9ses = v9fs_inode2v9ses(inode);
if (v9ses->cache == CACHE_LOOSE || v9ses->cache == CACHE_FSCACHE)
return generic_drop_inode(inode);
/*
* in case of non cached mode always drop the
- * the inode because we want the inode attribute
+ * inode because we want the inode attribute
* to always match that on the server.
*/
return 1;
diff --git a/fs/9p/xattr.c b/fs/9p/xattr.c
index ee331845e2c7..a824441b95a2 100644
--- a/fs/9p/xattr.c
+++ b/fs/9p/xattr.c
@@ -1,15 +1,7 @@
+// SPDX-License-Identifier: LGPL-2.1
/*
* Copyright IBM Corporation, 2010
* Author Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of version 2.1 of the GNU Lesser General Public License
- * as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it would be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
- *
*/
#include <linux/module.h>
diff --git a/fs/9p/xattr.h b/fs/9p/xattr.h
index c63c3bea5de5..3e11fc3331eb 100644
--- a/fs/9p/xattr.h
+++ b/fs/9p/xattr.h
@@ -1,15 +1,7 @@
+/* SPDX-License-Identifier: LGPL-2.1 */
/*
* Copyright IBM Corporation, 2010
* Author Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of version 2.1 of the GNU Lesser General Public License
- * as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it would be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
- *
*/
#ifndef FS_9P_XATTR_H
#define FS_9P_XATTR_H
@@ -22,13 +14,14 @@ extern const struct xattr_handler *v9fs_xattr_handlers[];
extern const struct xattr_handler v9fs_xattr_acl_access_handler;
extern const struct xattr_handler v9fs_xattr_acl_default_handler;
-extern ssize_t v9fs_fid_xattr_get(struct p9_fid *, const char *,
- void *, size_t);
-extern ssize_t v9fs_xattr_get(struct dentry *, const char *,
- void *, size_t);
-extern int v9fs_fid_xattr_set(struct p9_fid *, const char *,
- const void *, size_t, int);
-extern int v9fs_xattr_set(struct dentry *, const char *,
- const void *, size_t, int);
-extern ssize_t v9fs_listxattr(struct dentry *, char *, size_t);
+ssize_t v9fs_fid_xattr_get(struct p9_fid *fid, const char *name,
+ void *buffer, size_t buffer_size);
+ssize_t v9fs_xattr_get(struct dentry *dentry, const char *name,
+ void *buffer, size_t buffer_size);
+int v9fs_fid_xattr_set(struct p9_fid *fid, const char *name,
+ const void *value, size_t value_len, int flags);
+int v9fs_xattr_set(struct dentry *dentry, const char *name,
+ const void *value, size_t value_len, int flags);
+ssize_t v9fs_listxattr(struct dentry *dentry, char *buffer,
+ size_t buffer_size);
#endif /* FS_9P_XATTR_H */
diff --git a/fs/afs/file.c b/fs/afs/file.c
index e6c447ae91f3..eb11d047c0ae 100644
--- a/fs/afs/file.c
+++ b/fs/afs/file.c
@@ -19,6 +19,7 @@
static int afs_file_mmap(struct file *file, struct vm_area_struct *vma);
static int afs_readpage(struct file *file, struct page *page);
+static int afs_symlink_readpage(struct file *file, struct page *page);
static void afs_invalidatepage(struct page *page, unsigned int offset,
unsigned int length);
static int afs_releasepage(struct page *page, gfp_t gfp_flags);
@@ -49,7 +50,7 @@ const struct inode_operations afs_file_inode_operations = {
.permission = afs_permission,
};
-const struct address_space_operations afs_fs_aops = {
+const struct address_space_operations afs_file_aops = {
.readpage = afs_readpage,
.readahead = afs_readahead,
.set_page_dirty = afs_set_page_dirty,
@@ -62,6 +63,12 @@ const struct address_space_operations afs_fs_aops = {
.writepages = afs_writepages,
};
+const struct address_space_operations afs_symlink_aops = {
+ .readpage = afs_symlink_readpage,
+ .releasepage = afs_releasepage,
+ .invalidatepage = afs_invalidatepage,
+};
+
static const struct vm_operations_struct afs_vm_ops = {
.open = afs_vm_open,
.close = afs_vm_close,
@@ -313,7 +320,7 @@ static void afs_req_issue_op(struct netfs_read_subrequest *subreq)
afs_put_read(fsreq);
}
-static int afs_symlink_readpage(struct page *page)
+static int afs_symlink_readpage(struct file *file, struct page *page)
{
struct afs_vnode *vnode = AFS_FS_I(page->mapping->host);
struct afs_read *fsreq;
@@ -378,9 +385,6 @@ const struct netfs_read_request_ops afs_req_ops = {
static int afs_readpage(struct file *file, struct page *page)
{
- if (!file)
- return afs_symlink_readpage(page);
-
return netfs_readpage(file, page, &afs_req_ops, NULL);
}
diff --git a/fs/afs/inode.c b/fs/afs/inode.c
index 8fcffea2daf5..16906eb592d9 100644
--- a/fs/afs/inode.c
+++ b/fs/afs/inode.c
@@ -95,7 +95,7 @@ static int afs_inode_init_from_status(struct afs_operation *op,
inode->i_mode = S_IFREG | (status->mode & S_IALLUGO);
inode->i_op = &afs_file_inode_operations;
inode->i_fop = &afs_file_operations;
- inode->i_mapping->a_ops = &afs_fs_aops;
+ inode->i_mapping->a_ops = &afs_file_aops;
break;
case AFS_FTYPE_DIR:
inode->i_mode = S_IFDIR | (status->mode & S_IALLUGO);
@@ -113,11 +113,11 @@ static int afs_inode_init_from_status(struct afs_operation *op,
inode->i_mode = S_IFDIR | 0555;
inode->i_op = &afs_mntpt_inode_operations;
inode->i_fop = &afs_mntpt_file_operations;
- inode->i_mapping->a_ops = &afs_fs_aops;
+ inode->i_mapping->a_ops = &afs_symlink_aops;
} else {
inode->i_mode = S_IFLNK | status->mode;
inode->i_op = &afs_symlink_inode_operations;
- inode->i_mapping->a_ops = &afs_fs_aops;
+ inode->i_mapping->a_ops = &afs_symlink_aops;
}
inode_nohighmem(inode);
break;
diff --git a/fs/afs/internal.h b/fs/afs/internal.h
index 0ad97a8fc0d4..9357c53faa69 100644
--- a/fs/afs/internal.h
+++ b/fs/afs/internal.h
@@ -1055,7 +1055,8 @@ extern void afs_dynroot_depopulate(struct super_block *);
/*
* file.c
*/
-extern const struct address_space_operations afs_fs_aops;
+extern const struct address_space_operations afs_file_aops;
+extern const struct address_space_operations afs_symlink_aops;
extern const struct inode_operations afs_file_inode_operations;
extern const struct file_operations afs_file_operations;
extern const struct netfs_read_request_ops afs_req_ops;
diff --git a/fs/afs/yfsclient.c b/fs/afs/yfsclient.c
index 2b35cba8ad62..fdc7d675b4b0 100644
--- a/fs/afs/yfsclient.c
+++ b/fs/afs/yfsclient.c
@@ -83,25 +83,18 @@ static s64 linux_to_yfs_time(const struct timespec64 *t)
return (u64)t->tv_sec * 10000000 + t->tv_nsec/100;
}
-static __be32 *xdr_encode_YFSStoreStatus_mode(__be32 *bp, mode_t mode)
-{
- struct yfs_xdr_YFSStoreStatus *x = (void *)bp;
-
- x->mask = htonl(AFS_SET_MODE);
- x->mode = htonl(mode & S_IALLUGO);
- x->mtime_client = u64_to_xdr(0);
- x->owner = u64_to_xdr(0);
- x->group = u64_to_xdr(0);
- return bp + xdr_size(x);
-}
-
-static __be32 *xdr_encode_YFSStoreStatus_mtime(__be32 *bp, const struct timespec64 *t)
+static __be32 *xdr_encode_YFSStoreStatus(__be32 *bp, mode_t *mode,
+ const struct timespec64 *t)
{
struct yfs_xdr_YFSStoreStatus *x = (void *)bp;
+ mode_t masked_mode = mode ? *mode & S_IALLUGO : 0;
s64 mtime = linux_to_yfs_time(t);
+ u32 mask = AFS_SET_MTIME;
- x->mask = htonl(AFS_SET_MTIME);
- x->mode = htonl(0);
+ mask |= mode ? AFS_SET_MODE : 0;
+
+ x->mask = htonl(mask);
+ x->mode = htonl(masked_mode);
x->mtime_client = u64_to_xdr(mtime);
x->owner = u64_to_xdr(0);
x->group = u64_to_xdr(0);
@@ -576,7 +569,7 @@ void yfs_fs_create_file(struct afs_operation *op)
bp = xdr_encode_u32(bp, 0); /* RPC flags */
bp = xdr_encode_YFSFid(bp, &dvp->fid);
bp = xdr_encode_name(bp, name);
- bp = xdr_encode_YFSStoreStatus_mode(bp, op->create.mode);
+ bp = xdr_encode_YFSStoreStatus(bp, &op->create.mode, &op->mtime);
bp = xdr_encode_u32(bp, yfs_LockNone); /* ViceLockType */
yfs_check_req(call, bp);
@@ -625,7 +618,7 @@ void yfs_fs_make_dir(struct afs_operation *op)
bp = xdr_encode_u32(bp, 0); /* RPC flags */
bp = xdr_encode_YFSFid(bp, &dvp->fid);
bp = xdr_encode_name(bp, name);
- bp = xdr_encode_YFSStoreStatus_mode(bp, op->create.mode);
+ bp = xdr_encode_YFSStoreStatus(bp, &op->create.mode, &op->mtime);
yfs_check_req(call, bp);
trace_afs_make_fs_call1(call, &dvp->fid, name);
@@ -946,6 +939,7 @@ void yfs_fs_symlink(struct afs_operation *op)
struct afs_vnode_param *dvp = &op->file[0];
struct afs_call *call;
size_t contents_sz;
+ mode_t mode = 0777;
__be32 *bp;
_enter("");
@@ -972,7 +966,7 @@ void yfs_fs_symlink(struct afs_operation *op)
bp = xdr_encode_YFSFid(bp, &dvp->fid);
bp = xdr_encode_name(bp, name);
bp = xdr_encode_string(bp, op->create.symlink, contents_sz);
- bp = xdr_encode_YFSStoreStatus_mode(bp, S_IRWXUGO);
+ bp = xdr_encode_YFSStoreStatus(bp, &mode, &op->mtime);
yfs_check_req(call, bp);
trace_afs_make_fs_call1(call, &dvp->fid, name);
@@ -1103,7 +1097,7 @@ void yfs_fs_store_data(struct afs_operation *op)
bp = xdr_encode_u32(bp, YFSSTOREDATA64);
bp = xdr_encode_u32(bp, 0); /* RPC flags */
bp = xdr_encode_YFSFid(bp, &vp->fid);
- bp = xdr_encode_YFSStoreStatus_mtime(bp, &op->mtime);
+ bp = xdr_encode_YFSStoreStatus(bp, NULL, &op->mtime);
bp = xdr_encode_u64(bp, op->store.pos);
bp = xdr_encode_u64(bp, op->store.size);
bp = xdr_encode_u64(bp, op->store.i_size);
diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c
index a813b70f594e..f8c7f26f1fbb 100644
--- a/fs/binfmt_elf.c
+++ b/fs/binfmt_elf.c
@@ -156,7 +156,7 @@ static int padzero(unsigned long elf_bss)
#define STACK_ADD(sp, items) ((elf_addr_t __user *)(sp) - (items))
#define STACK_ROUND(sp, items) \
(((unsigned long) (sp - items)) &~ 15UL)
-#define STACK_ALLOC(sp, len) ({ sp -= len ; sp; })
+#define STACK_ALLOC(sp, len) (sp -= len)
#endif
#ifndef ELF_BASE_PLATFORM
@@ -1074,20 +1074,26 @@ out_free_interp:
vaddr = elf_ppnt->p_vaddr;
/*
- * If we are loading ET_EXEC or we have already performed
- * the ET_DYN load_addr calculations, proceed normally.
+ * The first time through the loop, load_addr_set is false:
+ * layout will be calculated. Once set, use MAP_FIXED since
+ * we know we've already safely mapped the entire region with
+ * MAP_FIXED_NOREPLACE in the once-per-binary logic following.
*/
- if (elf_ex->e_type == ET_EXEC || load_addr_set) {
+ if (load_addr_set) {
elf_flags |= MAP_FIXED;
+ } else if (elf_ex->e_type == ET_EXEC) {
+ /*
+ * This logic is run once for the first LOAD Program
+ * Header for ET_EXEC binaries. No special handling
+ * is needed.
+ */
+ elf_flags |= MAP_FIXED_NOREPLACE;
} else if (elf_ex->e_type == ET_DYN) {
/*
* This logic is run once for the first LOAD Program
* Header for ET_DYN binaries to calculate the
* randomization (load_bias) for all the LOAD
- * Program Headers, and to calculate the entire
- * size of the ELF mapping (total_size). (Note that
- * load_addr_set is set to true later once the
- * initial mapping is performed.)
+ * Program Headers.
*
* There are effectively two types of ET_DYN
* binaries: programs (i.e. PIE: ET_DYN with INTERP)
@@ -1108,7 +1114,7 @@ out_free_interp:
* Therefore, programs are loaded offset from
* ELF_ET_DYN_BASE and loaders are loaded into the
* independently randomized mmap region (0 load_bias
- * without MAP_FIXED).
+ * without MAP_FIXED nor MAP_FIXED_NOREPLACE).
*/
if (interpreter) {
load_bias = ELF_ET_DYN_BASE;
@@ -1117,7 +1123,7 @@ out_free_interp:
alignment = maximum_alignment(elf_phdata, elf_ex->e_phnum);
if (alignment)
load_bias &= ~(alignment - 1);
- elf_flags |= MAP_FIXED;
+ elf_flags |= MAP_FIXED_NOREPLACE;
} else
load_bias = 0;
@@ -1129,7 +1135,14 @@ out_free_interp:
* is then page aligned.
*/
load_bias = ELF_PAGESTART(load_bias - vaddr);
+ }
+ /*
+ * Calculate the entire size of the ELF mapping (total_size).
+ * (Note that load_addr_set is set to true later once the
+ * initial mapping is performed.)
+ */
+ if (!load_addr_set) {
total_size = total_mapping_size(elf_phdata,
elf_ex->e_phnum);
if (!total_size) {
@@ -1834,7 +1847,7 @@ static int fill_note_info(struct elfhdr *elf, int phdrs,
/*
* Allocate a structure for each thread.
*/
- for (ct = &dump_task->mm->core_state->dumper; ct; ct = ct->next) {
+ for (ct = &dump_task->signal->core_state->dumper; ct; ct = ct->next) {
t = kzalloc(offsetof(struct elf_thread_core_info,
notes[info->thread_notes]),
GFP_KERNEL);
@@ -2024,7 +2037,7 @@ static int fill_note_info(struct elfhdr *elf, int phdrs,
if (!elf_note_info_init(info))
return 0;
- for (ct = current->mm->core_state->dumper.next;
+ for (ct = current->signal->core_state->dumper.next;
ct; ct = ct->next) {
ets = kzalloc(sizeof(*ets), GFP_KERNEL);
if (!ets)
diff --git a/fs/binfmt_elf_fdpic.c b/fs/binfmt_elf_fdpic.c
index 6d8fd6030cbb..c6f588dc4a9d 100644
--- a/fs/binfmt_elf_fdpic.c
+++ b/fs/binfmt_elf_fdpic.c
@@ -1494,7 +1494,7 @@ static int elf_fdpic_core_dump(struct coredump_params *cprm)
if (dump_vma_snapshot(cprm, &vma_count, &vma_meta, &vma_data_size))
goto end_coredump;
- for (ct = current->mm->core_state->dumper.next;
+ for (ct = current->signal->core_state->dumper.next;
ct; ct = ct->next) {
tmp = elf_dump_thread_status(cprm->siginfo->si_signo,
ct->task, &thread_status_size);
diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c
index 9fa930dfd78d..dca42aa87d30 100644
--- a/fs/cifs/cifsfs.c
+++ b/fs/cifs/cifsfs.c
@@ -38,7 +38,6 @@
#include <linux/key-type.h>
#include "cifs_spnego.h"
#include "fscache.h"
-#include "smb2pdu.h"
#ifdef CONFIG_CIFS_DFS_UPCALL
#include "dfs_cache.h"
#endif
diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h
index e916470468ea..abff31dcd005 100644
--- a/fs/cifs/cifsglob.h
+++ b/fs/cifs/cifsglob.h
@@ -20,6 +20,7 @@
#include <crypto/internal/hash.h>
#include <linux/scatterlist.h>
#include <uapi/linux/cifs/cifs_mount.h>
+#include "../smbfs_common/smb2pdu.h"
#include "smb2pdu.h"
#define CIFS_MAGIC_NUMBER 0xFF534D42 /* the first four bytes of SMB PDUs */
@@ -776,7 +777,7 @@ revert_current_mid(struct TCP_Server_Info *server, const unsigned int val)
static inline void
revert_current_mid_from_hdr(struct TCP_Server_Info *server,
- const struct smb2_sync_hdr *shdr)
+ const struct smb2_hdr *shdr)
{
unsigned int num = le16_to_cpu(shdr->CreditCharge);
diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c
index c3b94c1e4591..0abbff4e4135 100644
--- a/fs/cifs/connect.c
+++ b/fs/cifs/connect.c
@@ -677,7 +677,7 @@ dequeue_mid(struct mid_q_entry *mid, bool malformed)
static unsigned int
smb2_get_credits_from_hdr(char *buffer, struct TCP_Server_Info *server)
{
- struct smb2_sync_hdr *shdr = (struct smb2_sync_hdr *)buffer;
+ struct smb2_hdr *shdr = (struct smb2_hdr *)buffer;
/*
* SMB1 does not use credits.
@@ -794,7 +794,6 @@ static void clean_demultiplex_info(struct TCP_Server_Info *server)
*/
}
- kfree(server->hostname);
kfree(server);
length = atomic_dec_return(&tcpSesAllocCount);
@@ -878,7 +877,7 @@ cifs_handle_standard(struct TCP_Server_Info *server, struct mid_q_entry *mid)
static void
smb2_add_credits_from_hdr(char *buffer, struct TCP_Server_Info *server)
{
- struct smb2_sync_hdr *shdr = (struct smb2_sync_hdr *)buffer;
+ struct smb2_hdr *shdr = (struct smb2_hdr *)buffer;
int scredits, in_flight;
/*
@@ -1235,6 +1234,9 @@ static int match_server(struct TCP_Server_Info *server, struct smb3_fs_context *
if (!net_eq(cifs_net_ns(server), current->nsproxy->net_ns))
return 0;
+ if (strcasecmp(server->hostname, ctx->server_hostname))
+ return 0;
+
if (!match_address(server, addr,
(struct sockaddr *)&ctx->srcaddr))
return 0;
@@ -1336,6 +1338,7 @@ cifs_put_tcp_session(struct TCP_Server_Info *server, int from_reconnect)
kfree(server->session_key.response);
server->session_key.response = NULL;
server->session_key.len = 0;
+ kfree(server->hostname);
task = xchg(&server->tsk, NULL);
if (task)
@@ -1361,14 +1364,15 @@ cifs_get_tcp_session(struct smb3_fs_context *ctx)
goto out_err;
}
+ tcp_ses->hostname = kstrdup(ctx->server_hostname, GFP_KERNEL);
+ if (!tcp_ses->hostname) {
+ rc = -ENOMEM;
+ goto out_err;
+ }
+
tcp_ses->ops = ctx->ops;
tcp_ses->vals = ctx->vals;
cifs_set_net_ns(tcp_ses, get_net(current->nsproxy->net_ns));
- tcp_ses->hostname = extract_hostname(ctx->UNC);
- if (IS_ERR(tcp_ses->hostname)) {
- rc = PTR_ERR(tcp_ses->hostname);
- goto out_err_crypto_release;
- }
tcp_ses->conn_id = atomic_inc_return(&tcpSesNextId);
tcp_ses->noblockcnt = ctx->rootfs;
@@ -1497,8 +1501,7 @@ out_err_crypto_release:
out_err:
if (tcp_ses) {
- if (!IS_ERR(tcp_ses->hostname))
- kfree(tcp_ses->hostname);
+ kfree(tcp_ses->hostname);
if (tcp_ses->ssocket)
sock_release(tcp_ses->ssocket);
kfree(tcp_ses);
@@ -2646,11 +2649,12 @@ generic_ip_connect(struct TCP_Server_Info *server)
rc = 0;
if (rc < 0) {
cifs_dbg(FYI, "Error %d connecting to server\n", rc);
+ trace_smb3_connect_err(server->hostname, server->conn_id, &server->dstaddr, rc);
sock_release(socket);
server->ssocket = NULL;
return rc;
}
-
+ trace_smb3_connect_done(server->hostname, server->conn_id, &server->dstaddr);
if (sport == htons(RFC1001_PORT))
rc = ip_rfc1001_connect(server);
diff --git a/fs/cifs/fs_context.c b/fs/cifs/fs_context.c
index 3109def8e199..38d96a480745 100644
--- a/fs/cifs/fs_context.c
+++ b/fs/cifs/fs_context.c
@@ -116,6 +116,7 @@ const struct fs_parameter_spec smb3_fs_parameters[] = {
fsparam_flag("nosharesock", Opt_nosharesock),
fsparam_flag_no("persistenthandles", Opt_persistent),
fsparam_flag_no("resilienthandles", Opt_resilient),
+ fsparam_flag_no("tcpnodelay", Opt_tcp_nodelay),
fsparam_flag("domainauto", Opt_domainauto),
fsparam_flag("rdma", Opt_rdma),
fsparam_flag("modesid", Opt_modesid),
@@ -318,6 +319,7 @@ smb3_fs_context_dup(struct smb3_fs_context *new_ctx, struct smb3_fs_context *ctx
DUP_CTX_STR(mount_options);
DUP_CTX_STR(username);
DUP_CTX_STR(password);
+ DUP_CTX_STR(server_hostname);
DUP_CTX_STR(UNC);
DUP_CTX_STR(source);
DUP_CTX_STR(domainname);
@@ -456,6 +458,11 @@ smb3_parse_devname(const char *devname, struct smb3_fs_context *ctx)
if (!pos)
return -EINVAL;
+ /* record the server hostname */
+ ctx->server_hostname = kstrndup(devname + 2, pos - devname - 2, GFP_KERNEL);
+ if (!ctx->server_hostname)
+ return -ENOMEM;
+
/* skip past delimiter */
++pos;
@@ -1383,6 +1390,13 @@ static int smb3_fs_context_parse_param(struct fs_context *fc,
}
}
break;
+ case Opt_tcp_nodelay:
+ /* tcp nodelay should not usually be needed since we CORK/UNCORK the socket */
+ if (result.negated)
+ ctx->sockopt_tcp_nodelay = false;
+ else
+ ctx->sockopt_tcp_nodelay = true;
+ break;
case Opt_domainauto:
ctx->domainauto = true;
break;
@@ -1496,6 +1510,8 @@ smb3_cleanup_fs_context_contents(struct smb3_fs_context *ctx)
ctx->username = NULL;
kfree_sensitive(ctx->password);
ctx->password = NULL;
+ kfree(ctx->server_hostname);
+ ctx->server_hostname = NULL;
kfree(ctx->UNC);
ctx->UNC = NULL;
kfree(ctx->source);
diff --git a/fs/cifs/fs_context.h b/fs/cifs/fs_context.h
index a42ba71d7a81..b2d22cf9cb18 100644
--- a/fs/cifs/fs_context.h
+++ b/fs/cifs/fs_context.h
@@ -98,6 +98,7 @@ enum cifs_param {
Opt_nosharesock,
Opt_persistent,
Opt_resilient,
+ Opt_tcp_nodelay,
Opt_domainauto,
Opt_rdma,
Opt_modesid,
@@ -166,6 +167,7 @@ struct smb3_fs_context {
char *password;
char *domainname;
char *source;
+ char *server_hostname;
char *UNC;
char *nodename;
char *iocharset; /* local code page for mapping to and from Unicode */
diff --git a/fs/cifs/misc.c b/fs/cifs/misc.c
index bb1185fff8cc..ba2c3e897b29 100644
--- a/fs/cifs/misc.c
+++ b/fs/cifs/misc.c
@@ -152,7 +152,7 @@ cifs_buf_get(void)
* SMB2 header is bigger than CIFS one - no problems to clean some
* more bytes for CIFS.
*/
- size_t buf_size = sizeof(struct smb2_sync_hdr);
+ size_t buf_size = sizeof(struct smb2_hdr);
/*
* We could use negotiated size instead of max_msgsize -
diff --git a/fs/cifs/smb2maperror.c b/fs/cifs/smb2maperror.c
index 181514b8770d..194799ddd382 100644
--- a/fs/cifs/smb2maperror.c
+++ b/fs/cifs/smb2maperror.c
@@ -2439,14 +2439,16 @@ smb2_print_status(__le32 status)
int
map_smb2_to_linux_error(char *buf, bool log_err)
{
- struct smb2_sync_hdr *shdr = (struct smb2_sync_hdr *)buf;
+ struct smb2_hdr *shdr = (struct smb2_hdr *)buf;
unsigned int i;
int rc = -EIO;
__le32 smb2err = shdr->Status;
if (smb2err == 0) {
- trace_smb3_cmd_done(shdr->TreeId, shdr->SessionId,
- le16_to_cpu(shdr->Command), le64_to_cpu(shdr->MessageId));
+ trace_smb3_cmd_done(le32_to_cpu(shdr->Id.SyncId.TreeId),
+ le64_to_cpu(shdr->SessionId),
+ le16_to_cpu(shdr->Command),
+ le64_to_cpu(shdr->MessageId));
return 0;
}
@@ -2470,8 +2472,10 @@ map_smb2_to_linux_error(char *buf, bool log_err)
cifs_dbg(FYI, "Mapping SMB2 status code 0x%08x to POSIX err %d\n",
__le32_to_cpu(smb2err), rc);
- trace_smb3_cmd_err(shdr->TreeId, shdr->SessionId,
- le16_to_cpu(shdr->Command),
- le64_to_cpu(shdr->MessageId), le32_to_cpu(smb2err), rc);
+ trace_smb3_cmd_err(le32_to_cpu(shdr->Id.SyncId.TreeId),
+ le64_to_cpu(shdr->SessionId),
+ le16_to_cpu(shdr->Command),
+ le64_to_cpu(shdr->MessageId),
+ le32_to_cpu(smb2err), rc);
return rc;
}
diff --git a/fs/cifs/smb2misc.c b/fs/cifs/smb2misc.c
index 29b5554f6263..cdcdef32759e 100644
--- a/fs/cifs/smb2misc.c
+++ b/fs/cifs/smb2misc.c
@@ -8,7 +8,6 @@
*
*/
#include <linux/ctype.h>
-#include "smb2pdu.h"
#include "cifsglob.h"
#include "cifsproto.h"
#include "smb2proto.h"
@@ -19,7 +18,7 @@
#include "nterr.h"
static int
-check_smb2_hdr(struct smb2_sync_hdr *shdr, __u64 mid)
+check_smb2_hdr(struct smb2_hdr *shdr, __u64 mid)
{
__u64 wire_mid = le64_to_cpu(shdr->MessageId);
@@ -81,9 +80,9 @@ static const __le16 smb2_rsp_struct_sizes[NUMBER_OF_SMB2_COMMANDS] = {
/* SMB2_OPLOCK_BREAK */ cpu_to_le16(24)
};
-#define SMB311_NEGPROT_BASE_SIZE (sizeof(struct smb2_sync_hdr) + sizeof(struct smb2_negotiate_rsp))
+#define SMB311_NEGPROT_BASE_SIZE (sizeof(struct smb2_hdr) + sizeof(struct smb2_negotiate_rsp))
-static __u32 get_neg_ctxt_len(struct smb2_sync_hdr *hdr, __u32 len,
+static __u32 get_neg_ctxt_len(struct smb2_hdr *hdr, __u32 len,
__u32 non_ctxlen)
{
__u16 neg_count;
@@ -135,13 +134,13 @@ static __u32 get_neg_ctxt_len(struct smb2_sync_hdr *hdr, __u32 len,
int
smb2_check_message(char *buf, unsigned int len, struct TCP_Server_Info *srvr)
{
- struct smb2_sync_hdr *shdr = (struct smb2_sync_hdr *)buf;
- struct smb2_sync_pdu *pdu = (struct smb2_sync_pdu *)shdr;
+ struct smb2_hdr *shdr = (struct smb2_hdr *)buf;
+ struct smb2_pdu *pdu = (struct smb2_pdu *)shdr;
__u64 mid;
__u32 clc_len; /* calculated length */
int command;
- int pdu_size = sizeof(struct smb2_sync_pdu);
- int hdr_size = sizeof(struct smb2_sync_hdr);
+ int pdu_size = sizeof(struct smb2_pdu);
+ int hdr_size = sizeof(struct smb2_hdr);
/*
* Add function to do table lookup of StructureSize by command
@@ -155,7 +154,7 @@ smb2_check_message(char *buf, unsigned int len, struct TCP_Server_Info *srvr)
/* decrypt frame now that it is completely read in */
spin_lock(&cifs_tcp_ses_lock);
list_for_each_entry(ses, &srvr->smb_ses_list, smb_ses_list) {
- if (ses->Suid == thdr->SessionId)
+ if (ses->Suid == le64_to_cpu(thdr->SessionId))
break;
}
spin_unlock(&cifs_tcp_ses_lock);
@@ -296,7 +295,7 @@ static const bool has_smb2_data_area[NUMBER_OF_SMB2_COMMANDS] = {
* area and the offset to it (from the beginning of the smb are also returned.
*/
char *
-smb2_get_data_area_len(int *off, int *len, struct smb2_sync_hdr *shdr)
+smb2_get_data_area_len(int *off, int *len, struct smb2_hdr *shdr)
{
*off = 0;
*len = 0;
@@ -401,8 +400,8 @@ smb2_get_data_area_len(int *off, int *len, struct smb2_sync_hdr *shdr)
unsigned int
smb2_calc_size(void *buf, struct TCP_Server_Info *srvr)
{
- struct smb2_sync_pdu *pdu = (struct smb2_sync_pdu *)buf;
- struct smb2_sync_hdr *shdr = &pdu->sync_hdr;
+ struct smb2_pdu *pdu = (struct smb2_pdu *)buf;
+ struct smb2_hdr *shdr = &pdu->hdr;
int offset; /* the offset from the beginning of SMB to data area */
int data_length; /* the length of the variable length data area */
/* Structure Size has already been checked to make sure it is 64 */
@@ -669,7 +668,7 @@ smb2_is_valid_oplock_break(char *buffer, struct TCP_Server_Info *server)
cifs_dbg(FYI, "Checking for oplock break\n");
- if (rsp->sync_hdr.Command != SMB2_OPLOCK_BREAK)
+ if (rsp->hdr.Command != SMB2_OPLOCK_BREAK)
return false;
if (rsp->StructureSize !=
@@ -816,25 +815,25 @@ smb2_handle_cancelled_close(struct cifs_tcon *tcon, __u64 persistent_fid,
int
smb2_handle_cancelled_mid(struct mid_q_entry *mid, struct TCP_Server_Info *server)
{
- struct smb2_sync_hdr *sync_hdr = mid->resp_buf;
+ struct smb2_hdr *hdr = mid->resp_buf;
struct smb2_create_rsp *rsp = mid->resp_buf;
struct cifs_tcon *tcon;
int rc;
- if ((mid->optype & CIFS_CP_CREATE_CLOSE_OP) || sync_hdr->Command != SMB2_CREATE ||
- sync_hdr->Status != STATUS_SUCCESS)
+ if ((mid->optype & CIFS_CP_CREATE_CLOSE_OP) || hdr->Command != SMB2_CREATE ||
+ hdr->Status != STATUS_SUCCESS)
return 0;
- tcon = smb2_find_smb_tcon(server, sync_hdr->SessionId,
- sync_hdr->TreeId);
+ tcon = smb2_find_smb_tcon(server, le64_to_cpu(hdr->SessionId),
+ le32_to_cpu(hdr->Id.SyncId.TreeId));
if (!tcon)
return -ENOENT;
rc = __smb2_handle_cancelled_cmd(tcon,
- le16_to_cpu(sync_hdr->Command),
- le64_to_cpu(sync_hdr->MessageId),
- rsp->PersistentFileId,
- rsp->VolatileFileId);
+ le16_to_cpu(hdr->Command),
+ le64_to_cpu(hdr->MessageId),
+ le64_to_cpu(rsp->PersistentFileId),
+ le64_to_cpu(rsp->VolatileFileId));
if (rc)
cifs_put_tcon(tcon);
@@ -856,10 +855,10 @@ smb311_update_preauth_hash(struct cifs_ses *ses, struct kvec *iov, int nvec)
{
int i, rc;
struct sdesc *d;
- struct smb2_sync_hdr *hdr;
+ struct smb2_hdr *hdr;
struct TCP_Server_Info *server = cifs_ses_server(ses);
- hdr = (struct smb2_sync_hdr *)iov[0].iov_base;
+ hdr = (struct smb2_hdr *)iov[0].iov_base;
/* neg prot are always taken */
if (hdr->Command == SMB2_NEGOTIATE)
goto ok;
diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c
index bda606dc72b1..7acf71defea7 100644
--- a/fs/cifs/smb2ops.c
+++ b/fs/cifs/smb2ops.c
@@ -325,7 +325,7 @@ static struct mid_q_entry *
__smb2_find_mid(struct TCP_Server_Info *server, char *buf, bool dequeue)
{
struct mid_q_entry *mid;
- struct smb2_sync_hdr *shdr = (struct smb2_sync_hdr *)buf;
+ struct smb2_hdr *shdr = (struct smb2_hdr *)buf;
__u64 wire_mid = le64_to_cpu(shdr->MessageId);
if (shdr->ProtocolId == SMB2_TRANSFORM_PROTO_NUM) {
@@ -367,11 +367,11 @@ static void
smb2_dump_detail(void *buf, struct TCP_Server_Info *server)
{
#ifdef CONFIG_CIFS_DEBUG2
- struct smb2_sync_hdr *shdr = (struct smb2_sync_hdr *)buf;
+ struct smb2_hdr *shdr = (struct smb2_hdr *)buf;
cifs_server_dbg(VFS, "Cmd: %d Err: 0x%x Flags: 0x%x Mid: %llu Pid: %d\n",
shdr->Command, shdr->Status, shdr->Flags, shdr->MessageId,
- shdr->ProcessId);
+ shdr->Id.SyncId.ProcessId);
cifs_server_dbg(VFS, "smb buf %p len %u\n", buf,
server->ops->calc_smb_size(buf, server));
#endif
@@ -885,10 +885,10 @@ int open_cached_dir(unsigned int xid, struct cifs_tcon *tcon,
atomic_inc(&tcon->num_remote_opens);
o_rsp = (struct smb2_create_rsp *)rsp_iov[0].iov_base;
- oparms.fid->persistent_fid = o_rsp->PersistentFileId;
- oparms.fid->volatile_fid = o_rsp->VolatileFileId;
+ oparms.fid->persistent_fid = le64_to_cpu(o_rsp->PersistentFileId);
+ oparms.fid->volatile_fid = le64_to_cpu(o_rsp->VolatileFileId);
#ifdef CONFIG_CIFS_DEBUG2
- oparms.fid->mid = le64_to_cpu(o_rsp->sync_hdr.MessageId);
+ oparms.fid->mid = le64_to_cpu(o_rsp->hdr.MessageId);
#endif /* CIFS_DEBUG2 */
tcon->crfid.tcon = tcon;
@@ -2391,12 +2391,12 @@ again:
/* If the open failed there is nothing to do */
op_rsp = (struct smb2_create_rsp *)rsp_iov[0].iov_base;
- if (op_rsp == NULL || op_rsp->sync_hdr.Status != STATUS_SUCCESS) {
+ if (op_rsp == NULL || op_rsp->hdr.Status != STATUS_SUCCESS) {
cifs_dbg(FYI, "query_dir_first: open failed rc=%d\n", rc);
goto qdf_free;
}
- fid->persistent_fid = op_rsp->PersistentFileId;
- fid->volatile_fid = op_rsp->VolatileFileId;
+ fid->persistent_fid = le64_to_cpu(op_rsp->PersistentFileId);
+ fid->volatile_fid = le64_to_cpu(op_rsp->VolatileFileId);
/* Anything else than ENODATA means a genuine error */
if (rc && rc != -ENODATA) {
@@ -2410,7 +2410,7 @@ again:
atomic_inc(&tcon->num_remote_opens);
qd_rsp = (struct smb2_query_directory_rsp *)rsp_iov[1].iov_base;
- if (qd_rsp->sync_hdr.Status == STATUS_NO_MORE_FILES) {
+ if (qd_rsp->hdr.Status == STATUS_NO_MORE_FILES) {
trace_smb3_query_dir_done(xid, fid->persistent_fid,
tcon->tid, tcon->ses->Suid, 0, 0);
srch_inf->endOfSearch = true;
@@ -2462,7 +2462,7 @@ smb2_close_dir(const unsigned int xid, struct cifs_tcon *tcon,
static bool
smb2_is_status_pending(char *buf, struct TCP_Server_Info *server)
{
- struct smb2_sync_hdr *shdr = (struct smb2_sync_hdr *)buf;
+ struct smb2_hdr *shdr = (struct smb2_hdr *)buf;
int scredits, in_flight;
if (shdr->Status != STATUS_PENDING)
@@ -2489,13 +2489,14 @@ smb2_is_status_pending(char *buf, struct TCP_Server_Info *server)
static bool
smb2_is_session_expired(char *buf)
{
- struct smb2_sync_hdr *shdr = (struct smb2_sync_hdr *)buf;
+ struct smb2_hdr *shdr = (struct smb2_hdr *)buf;
if (shdr->Status != STATUS_NETWORK_SESSION_EXPIRED &&
shdr->Status != STATUS_USER_SESSION_DELETED)
return false;
- trace_smb3_ses_expired(shdr->TreeId, shdr->SessionId,
+ trace_smb3_ses_expired(le32_to_cpu(shdr->Id.SyncId.TreeId),
+ le64_to_cpu(shdr->SessionId),
le16_to_cpu(shdr->Command),
le64_to_cpu(shdr->MessageId));
cifs_dbg(FYI, "Session expired or deleted\n");
@@ -2506,7 +2507,7 @@ smb2_is_session_expired(char *buf)
static bool
smb2_is_status_io_timeout(char *buf)
{
- struct smb2_sync_hdr *shdr = (struct smb2_sync_hdr *)buf;
+ struct smb2_hdr *shdr = (struct smb2_hdr *)buf;
if (shdr->Status == STATUS_IO_TIMEOUT)
return true;
@@ -2517,7 +2518,7 @@ smb2_is_status_io_timeout(char *buf)
static void
smb2_is_network_name_deleted(char *buf, struct TCP_Server_Info *server)
{
- struct smb2_sync_hdr *shdr = (struct smb2_sync_hdr *)buf;
+ struct smb2_hdr *shdr = (struct smb2_hdr *)buf;
struct list_head *tmp, *tmp1;
struct cifs_ses *ses;
struct cifs_tcon *tcon;
@@ -2530,7 +2531,7 @@ smb2_is_network_name_deleted(char *buf, struct TCP_Server_Info *server)
ses = list_entry(tmp, struct cifs_ses, smb_ses_list);
list_for_each(tmp1, &ses->tcon_list) {
tcon = list_entry(tmp1, struct cifs_tcon, tcon_list);
- if (tcon->tid == shdr->TreeId) {
+ if (tcon->tid == le32_to_cpu(shdr->Id.SyncId.TreeId)) {
tcon->need_reconnect = true;
spin_unlock(&cifs_tcp_ses_lock);
pr_warn_once("Server share %s deleted.\n",
@@ -2558,9 +2559,9 @@ smb2_oplock_response(struct cifs_tcon *tcon, struct cifs_fid *fid,
void
smb2_set_related(struct smb_rqst *rqst)
{
- struct smb2_sync_hdr *shdr;
+ struct smb2_hdr *shdr;
- shdr = (struct smb2_sync_hdr *)(rqst->rq_iov[0].iov_base);
+ shdr = (struct smb2_hdr *)(rqst->rq_iov[0].iov_base);
if (shdr == NULL) {
cifs_dbg(FYI, "shdr NULL in smb2_set_related\n");
return;
@@ -2573,13 +2574,13 @@ char smb2_padding[7] = {0, 0, 0, 0, 0, 0, 0};
void
smb2_set_next_command(struct cifs_tcon *tcon, struct smb_rqst *rqst)
{
- struct smb2_sync_hdr *shdr;
+ struct smb2_hdr *shdr;
struct cifs_ses *ses = tcon->ses;
struct TCP_Server_Info *server = ses->server;
unsigned long len = smb_rqst_len(server, rqst);
int i, num_padding;
- shdr = (struct smb2_sync_hdr *)(rqst->rq_iov[0].iov_base);
+ shdr = (struct smb2_hdr *)(rqst->rq_iov[0].iov_base);
if (shdr == NULL) {
cifs_dbg(FYI, "shdr NULL in smb2_set_next_command\n");
return;
@@ -3124,7 +3125,7 @@ smb2_query_symlink(const unsigned int xid, struct cifs_tcon *tcon,
resp_buftype, rsp_iov);
create_rsp = rsp_iov[0].iov_base;
- if (create_rsp && create_rsp->sync_hdr.Status)
+ if (create_rsp && create_rsp->hdr.Status)
err_iov = rsp_iov[0];
ioctl_rsp = rsp_iov[1].iov_base;
@@ -4369,8 +4370,8 @@ static void
fill_transform_hdr(struct smb2_transform_hdr *tr_hdr, unsigned int orig_len,
struct smb_rqst *old_rq, __le16 cipher_type)
{
- struct smb2_sync_hdr *shdr =
- (struct smb2_sync_hdr *)old_rq->rq_iov[0].iov_base;
+ struct smb2_hdr *shdr =
+ (struct smb2_hdr *)old_rq->rq_iov[0].iov_base;
memset(tr_hdr, 0, sizeof(struct smb2_transform_hdr));
tr_hdr->ProtocolId = SMB2_TRANSFORM_PROTO_NUM;
@@ -4496,7 +4497,7 @@ crypt_message(struct TCP_Server_Info *server, int num_rqst,
struct crypto_aead *tfm;
unsigned int crypt_len = le32_to_cpu(tr_hdr->OriginalMessageSize);
- rc = smb2_get_enc_key(server, tr_hdr->SessionId, enc, key);
+ rc = smb2_get_enc_key(server, le64_to_cpu(tr_hdr->SessionId), enc, key);
if (rc) {
cifs_server_dbg(VFS, "%s: Could not get %scryption key\n", __func__,
enc ? "en" : "de");
@@ -4788,7 +4789,7 @@ handle_read_data(struct TCP_Server_Info *server, struct mid_q_entry *mid,
unsigned int cur_page_idx;
unsigned int pad_len;
struct cifs_readdata *rdata = mid->callback_data;
- struct smb2_sync_hdr *shdr = (struct smb2_sync_hdr *)buf;
+ struct smb2_hdr *shdr = (struct smb2_hdr *)buf;
struct bio_vec *bvec = NULL;
struct iov_iter iter;
struct kvec iov;
@@ -5117,7 +5118,7 @@ receive_encrypted_standard(struct TCP_Server_Info *server,
{
int ret, length;
char *buf = server->smallbuf;
- struct smb2_sync_hdr *shdr;
+ struct smb2_hdr *shdr;
unsigned int pdu_length = server->pdu_size;
unsigned int buf_size;
struct mid_q_entry *mid_entry;
@@ -5147,7 +5148,7 @@ receive_encrypted_standard(struct TCP_Server_Info *server,
next_is_large = server->large_buf;
one_more:
- shdr = (struct smb2_sync_hdr *)buf;
+ shdr = (struct smb2_hdr *)buf;
if (shdr->NextCommand) {
if (next_is_large)
next_buffer = (char *)cifs_buf_get();
@@ -5213,7 +5214,7 @@ smb3_receive_transform(struct TCP_Server_Info *server,
unsigned int orig_len = le32_to_cpu(tr_hdr->OriginalMessageSize);
if (pdu_length < sizeof(struct smb2_transform_hdr) +
- sizeof(struct smb2_sync_hdr)) {
+ sizeof(struct smb2_hdr)) {
cifs_server_dbg(VFS, "Transform message is too small (%u)\n",
pdu_length);
cifs_reconnect(server);
@@ -5246,7 +5247,7 @@ smb3_handle_read_data(struct TCP_Server_Info *server, struct mid_q_entry *mid)
static int
smb2_next_header(char *buf)
{
- struct smb2_sync_hdr *hdr = (struct smb2_sync_hdr *)buf;
+ struct smb2_hdr *hdr = (struct smb2_hdr *)buf;
struct smb2_transform_hdr *t_hdr = (struct smb2_transform_hdr *)buf;
if (hdr->ProtocolId == SMB2_TRANSFORM_PROTO_NUM)
@@ -5788,7 +5789,7 @@ struct smb_version_values smb20_values = {
.exclusive_lock_type = SMB2_LOCKFLAG_EXCLUSIVE_LOCK,
.shared_lock_type = SMB2_LOCKFLAG_SHARED_LOCK,
.unlock_lock_type = SMB2_LOCKFLAG_UNLOCK,
- .header_size = sizeof(struct smb2_sync_hdr),
+ .header_size = sizeof(struct smb2_hdr),
.header_preamble_size = 0,
.max_header_size = MAX_SMB2_HDR_SIZE,
.read_rsp_size = sizeof(struct smb2_read_rsp) - 1,
@@ -5809,7 +5810,7 @@ struct smb_version_values smb21_values = {
.exclusive_lock_type = SMB2_LOCKFLAG_EXCLUSIVE_LOCK,
.shared_lock_type = SMB2_LOCKFLAG_SHARED_LOCK,
.unlock_lock_type = SMB2_LOCKFLAG_UNLOCK,
- .header_size = sizeof(struct smb2_sync_hdr),
+ .header_size = sizeof(struct smb2_hdr),
.header_preamble_size = 0,
.max_header_size = MAX_SMB2_HDR_SIZE,
.read_rsp_size = sizeof(struct smb2_read_rsp) - 1,
@@ -5830,7 +5831,7 @@ struct smb_version_values smb3any_values = {
.exclusive_lock_type = SMB2_LOCKFLAG_EXCLUSIVE_LOCK,
.shared_lock_type = SMB2_LOCKFLAG_SHARED_LOCK,
.unlock_lock_type = SMB2_LOCKFLAG_UNLOCK,
- .header_size = sizeof(struct smb2_sync_hdr),
+ .header_size = sizeof(struct smb2_hdr),
.header_preamble_size = 0,
.max_header_size = MAX_SMB2_HDR_SIZE,
.read_rsp_size = sizeof(struct smb2_read_rsp) - 1,
@@ -5851,7 +5852,7 @@ struct smb_version_values smbdefault_values = {
.exclusive_lock_type = SMB2_LOCKFLAG_EXCLUSIVE_LOCK,
.shared_lock_type = SMB2_LOCKFLAG_SHARED_LOCK,
.unlock_lock_type = SMB2_LOCKFLAG_UNLOCK,
- .header_size = sizeof(struct smb2_sync_hdr),
+ .header_size = sizeof(struct smb2_hdr),
.header_preamble_size = 0,
.max_header_size = MAX_SMB2_HDR_SIZE,
.read_rsp_size = sizeof(struct smb2_read_rsp) - 1,
@@ -5872,7 +5873,7 @@ struct smb_version_values smb30_values = {
.exclusive_lock_type = SMB2_LOCKFLAG_EXCLUSIVE_LOCK,
.shared_lock_type = SMB2_LOCKFLAG_SHARED_LOCK,
.unlock_lock_type = SMB2_LOCKFLAG_UNLOCK,
- .header_size = sizeof(struct smb2_sync_hdr),
+ .header_size = sizeof(struct smb2_hdr),
.header_preamble_size = 0,
.max_header_size = MAX_SMB2_HDR_SIZE,
.read_rsp_size = sizeof(struct smb2_read_rsp) - 1,
@@ -5893,7 +5894,7 @@ struct smb_version_values smb302_values = {
.exclusive_lock_type = SMB2_LOCKFLAG_EXCLUSIVE_LOCK,
.shared_lock_type = SMB2_LOCKFLAG_SHARED_LOCK,
.unlock_lock_type = SMB2_LOCKFLAG_UNLOCK,
- .header_size = sizeof(struct smb2_sync_hdr),
+ .header_size = sizeof(struct smb2_hdr),
.header_preamble_size = 0,
.max_header_size = MAX_SMB2_HDR_SIZE,
.read_rsp_size = sizeof(struct smb2_read_rsp) - 1,
@@ -5914,7 +5915,7 @@ struct smb_version_values smb311_values = {
.exclusive_lock_type = SMB2_LOCKFLAG_EXCLUSIVE_LOCK,
.shared_lock_type = SMB2_LOCKFLAG_SHARED_LOCK,
.unlock_lock_type = SMB2_LOCKFLAG_UNLOCK,
- .header_size = sizeof(struct smb2_sync_hdr),
+ .header_size = sizeof(struct smb2_hdr),
.header_preamble_size = 0,
.max_header_size = MAX_SMB2_HDR_SIZE,
.read_rsp_size = sizeof(struct smb2_read_rsp) - 1,
diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c
index 7829c590eeac..d2ecb2ea37c0 100644
--- a/fs/cifs/smb2pdu.c
+++ b/fs/cifs/smb2pdu.c
@@ -23,7 +23,6 @@
#include <linux/uuid.h>
#include <linux/pagemap.h>
#include <linux/xattr.h>
-#include "smb2pdu.h"
#include "cifsglob.h"
#include "cifsacl.h"
#include "cifsproto.h"
@@ -84,7 +83,7 @@ int smb3_encryption_required(const struct cifs_tcon *tcon)
}
static void
-smb2_hdr_assemble(struct smb2_sync_hdr *shdr, __le16 smb2_cmd,
+smb2_hdr_assemble(struct smb2_hdr *shdr, __le16 smb2_cmd,
const struct cifs_tcon *tcon,
struct TCP_Server_Info *server)
{
@@ -104,7 +103,7 @@ smb2_hdr_assemble(struct smb2_sync_hdr *shdr, __le16 smb2_cmd,
} else {
shdr->CreditRequest = cpu_to_le16(2);
}
- shdr->ProcessId = cpu_to_le32((__u16)current->tgid);
+ shdr->Id.SyncId.ProcessId = cpu_to_le32((__u16)current->tgid);
if (!tcon)
goto out;
@@ -115,10 +114,10 @@ smb2_hdr_assemble(struct smb2_sync_hdr *shdr, __le16 smb2_cmd,
shdr->CreditCharge = cpu_to_le16(1);
/* else CreditCharge MBZ */
- shdr->TreeId = tcon->tid;
+ shdr->Id.SyncId.TreeId = cpu_to_le32(tcon->tid);
/* Uid is not converted */
if (tcon->ses)
- shdr->SessionId = tcon->ses->Suid;
+ shdr->SessionId = cpu_to_le64(tcon->ses->Suid);
/*
* If we would set SMB2_FLAGS_DFS_OPERATIONS on open we also would have
@@ -331,7 +330,7 @@ fill_small_buf(__le16 smb2_command, struct cifs_tcon *tcon,
void *buf,
unsigned int *total_len)
{
- struct smb2_sync_pdu *spdu = (struct smb2_sync_pdu *)buf;
+ struct smb2_pdu *spdu = (struct smb2_pdu *)buf;
/* lookup word count ie StructureSize from table */
__u16 parmsize = smb2_req_struct_sizes[le16_to_cpu(smb2_command)];
@@ -341,10 +340,10 @@ fill_small_buf(__le16 smb2_command, struct cifs_tcon *tcon,
*/
memset(buf, 0, 256);
- smb2_hdr_assemble(&spdu->sync_hdr, smb2_command, tcon, server);
+ smb2_hdr_assemble(&spdu->hdr, smb2_command, tcon, server);
spdu->StructureSize2 = cpu_to_le16(parmsize);
- *total_len = parmsize + sizeof(struct smb2_sync_hdr);
+ *total_len = parmsize + sizeof(struct smb2_hdr);
}
/*
@@ -367,7 +366,7 @@ static int __smb2_plain_req_init(__le16 smb2_command, struct cifs_tcon *tcon,
}
fill_small_buf(smb2_command, tcon, server,
- (struct smb2_sync_hdr *)(*request_buf),
+ (struct smb2_hdr *)(*request_buf),
total_len);
if (tcon != NULL) {
@@ -414,8 +413,8 @@ build_preauth_ctxt(struct smb2_preauth_neg_context *pneg_ctxt)
pneg_ctxt->ContextType = SMB2_PREAUTH_INTEGRITY_CAPABILITIES;
pneg_ctxt->DataLength = cpu_to_le16(38);
pneg_ctxt->HashAlgorithmCount = cpu_to_le16(1);
- pneg_ctxt->SaltLength = cpu_to_le16(SMB311_LINUX_CLIENT_SALT_SIZE);
- get_random_bytes(pneg_ctxt->Salt, SMB311_LINUX_CLIENT_SALT_SIZE);
+ pneg_ctxt->SaltLength = cpu_to_le16(SMB311_SALT_SIZE);
+ get_random_bytes(pneg_ctxt->Salt, SMB311_SALT_SIZE);
pneg_ctxt->HashAlgorithms = SMB2_PREAUTH_INTEGRITY_SHA512;
}
@@ -857,7 +856,7 @@ SMB2_negotiate(const unsigned int xid, struct cifs_ses *ses)
if (rc)
return rc;
- req->sync_hdr.SessionId = 0;
+ req->hdr.SessionId = 0;
memset(server->preauth_sha_hash, 0, SMB2_PREAUTH_HASH_SIZE);
memset(ses->preauth_sha_hash, 0, SMB2_PREAUTH_HASH_SIZE);
@@ -1018,7 +1017,7 @@ SMB2_negotiate(const unsigned int xid, struct cifs_ses *ses)
server->cipher_type = SMB2_ENCRYPTION_AES128_CCM;
security_blob = smb2_get_data_area_len(&blob_offset, &blob_length,
- (struct smb2_sync_hdr *)rsp);
+ (struct smb2_hdr *)rsp);
/*
* See MS-SMB2 section 2.2.4: if no blob, client picks default which
* for us will be
@@ -1250,23 +1249,23 @@ SMB2_sess_alloc_buffer(struct SMB2_sess_data *sess_data)
return rc;
if (sess_data->ses->binding) {
- req->sync_hdr.SessionId = sess_data->ses->Suid;
- req->sync_hdr.Flags |= SMB2_FLAGS_SIGNED;
+ req->hdr.SessionId = cpu_to_le64(sess_data->ses->Suid);
+ req->hdr.Flags |= SMB2_FLAGS_SIGNED;
req->PreviousSessionId = 0;
req->Flags = SMB2_SESSION_REQ_FLAG_BINDING;
} else {
/* First session, not a reauthenticate */
- req->sync_hdr.SessionId = 0;
+ req->hdr.SessionId = 0;
/*
* if reconnect, we need to send previous sess id
* otherwise it is 0
*/
- req->PreviousSessionId = sess_data->previous_session;
+ req->PreviousSessionId = cpu_to_le64(sess_data->previous_session);
req->Flags = 0; /* MBZ */
}
/* enough to enable echos and oplocks and one max size write */
- req->sync_hdr.CreditRequest = cpu_to_le16(130);
+ req->hdr.CreditRequest = cpu_to_le16(130);
/* only one of SMB2 signing flags may be set in SMB2 request */
if (server->sign)
@@ -1425,7 +1424,7 @@ SMB2_auth_kerberos(struct SMB2_sess_data *sess_data)
rsp = (struct smb2_sess_setup_rsp *)sess_data->iov[0].iov_base;
/* keep session id and flags if binding */
if (!ses->binding) {
- ses->Suid = rsp->sync_hdr.SessionId;
+ ses->Suid = le64_to_cpu(rsp->hdr.SessionId);
ses->session_flags = le16_to_cpu(rsp->SessionFlags);
}
@@ -1501,7 +1500,7 @@ SMB2_sess_auth_rawntlmssp_negotiate(struct SMB2_sess_data *sess_data)
/* If true, rc here is expected and not an error */
if (sess_data->buf0_type != CIFS_NO_BUFFER &&
- rsp->sync_hdr.Status == STATUS_MORE_PROCESSING_REQUIRED)
+ rsp->hdr.Status == STATUS_MORE_PROCESSING_REQUIRED)
rc = 0;
if (rc)
@@ -1523,7 +1522,7 @@ SMB2_sess_auth_rawntlmssp_negotiate(struct SMB2_sess_data *sess_data)
/* keep existing ses id and flags if binding */
if (!ses->binding) {
- ses->Suid = rsp->sync_hdr.SessionId;
+ ses->Suid = le64_to_cpu(rsp->hdr.SessionId);
ses->session_flags = le16_to_cpu(rsp->SessionFlags);
}
@@ -1558,7 +1557,7 @@ SMB2_sess_auth_rawntlmssp_authenticate(struct SMB2_sess_data *sess_data)
goto out;
req = (struct smb2_sess_setup_req *) sess_data->iov[0].iov_base;
- req->sync_hdr.SessionId = ses->Suid;
+ req->hdr.SessionId = cpu_to_le64(ses->Suid);
rc = build_ntlmssp_auth_blob(&ntlmssp_blob, &blob_length, ses,
sess_data->nls_cp);
@@ -1584,7 +1583,7 @@ SMB2_sess_auth_rawntlmssp_authenticate(struct SMB2_sess_data *sess_data)
/* keep existing ses id and flags if binding */
if (!ses->binding) {
- ses->Suid = rsp->sync_hdr.SessionId;
+ ses->Suid = le64_to_cpu(rsp->hdr.SessionId);
ses->session_flags = le16_to_cpu(rsp->SessionFlags);
}
@@ -1715,12 +1714,12 @@ SMB2_logoff(const unsigned int xid, struct cifs_ses *ses)
return rc;
/* since no tcon, smb2_init can not do this, so do here */
- req->sync_hdr.SessionId = ses->Suid;
+ req->hdr.SessionId = cpu_to_le64(ses->Suid);
if (ses->session_flags & SMB2_SESSION_FLAG_ENCRYPT_DATA)
flags |= CIFS_TRANSFORM_REQ;
else if (server->sign)
- req->sync_hdr.Flags |= SMB2_FLAGS_SIGNED;
+ req->hdr.Flags |= SMB2_FLAGS_SIGNED;
flags |= CIFS_NO_RSP_BUF;
@@ -1828,14 +1827,14 @@ SMB2_tcon(const unsigned int xid, struct cifs_ses *ses, const char *tree,
!(ses->session_flags &
(SMB2_SESSION_FLAG_IS_GUEST|SMB2_SESSION_FLAG_IS_NULL)) &&
((ses->user_name != NULL) || (ses->sectype == Kerberos)))
- req->sync_hdr.Flags |= SMB2_FLAGS_SIGNED;
+ req->hdr.Flags |= SMB2_FLAGS_SIGNED;
memset(&rqst, 0, sizeof(struct smb_rqst));
rqst.rq_iov = iov;
rqst.rq_nvec = 2;
/* Need 64 for max size write so ask for more in case not there yet */
- req->sync_hdr.CreditRequest = cpu_to_le16(64);
+ req->hdr.CreditRequest = cpu_to_le16(64);
rc = cifs_send_recv(xid, ses, server,
&rqst, &resp_buftype, flags, &rsp_iov);
@@ -1871,7 +1870,7 @@ SMB2_tcon(const unsigned int xid, struct cifs_ses *ses, const char *tree,
tcon->maximal_access = le32_to_cpu(rsp->MaximalAccess);
tcon->tidStatus = CifsGood;
tcon->need_reconnect = false;
- tcon->tid = rsp->sync_hdr.TreeId;
+ tcon->tid = le32_to_cpu(rsp->hdr.Id.SyncId.TreeId);
strlcpy(tcon->treeName, tree, sizeof(tcon->treeName));
if ((rsp->Capabilities & SMB2_SHARE_CAP_DFS) &&
@@ -1892,9 +1891,8 @@ tcon_exit:
return rc;
tcon_error_exit:
- if (rsp && rsp->sync_hdr.Status == STATUS_BAD_NETWORK_NAME) {
+ if (rsp && rsp->hdr.Status == STATUS_BAD_NETWORK_NAME)
cifs_tcon_dbg(VFS, "BAD_NETWORK_NAME: %s\n", tree);
- }
goto tcon_exit;
}
@@ -2608,7 +2606,7 @@ int smb311_posix_mkdir(const unsigned int xid, struct inode *inode,
if (tcon->share_flags & SHI1005_FLAGS_DFS) {
int name_len;
- req->sync_hdr.Flags |= SMB2_FLAGS_DFS_OPERATIONS;
+ req->hdr.Flags |= SMB2_FLAGS_DFS_OPERATIONS;
rc = alloc_path_with_tree_prefix(&copy_path, &copy_size,
&name_len,
tcon->treeName, utf16_path);
@@ -2672,11 +2670,13 @@ int smb311_posix_mkdir(const unsigned int xid, struct inode *inode,
}
rsp = (struct smb2_create_rsp *)rsp_iov.iov_base;
- trace_smb3_posix_mkdir_done(xid, rsp->PersistentFileId, tcon->tid,
+ trace_smb3_posix_mkdir_done(xid, le64_to_cpu(rsp->PersistentFileId),
+ tcon->tid,
ses->Suid, CREATE_NOT_FILE,
FILE_WRITE_ATTRIBUTES);
- SMB2_close(xid, tcon, rsp->PersistentFileId, rsp->VolatileFileId);
+ SMB2_close(xid, tcon, le64_to_cpu(rsp->PersistentFileId),
+ le64_to_cpu(rsp->VolatileFileId));
/* Eventually save off posix specific response info and timestaps */
@@ -2740,7 +2740,7 @@ SMB2_open_init(struct cifs_tcon *tcon, struct TCP_Server_Info *server,
if (tcon->share_flags & SHI1005_FLAGS_DFS) {
int name_len;
- req->sync_hdr.Flags |= SMB2_FLAGS_DFS_OPERATIONS;
+ req->hdr.Flags |= SMB2_FLAGS_DFS_OPERATIONS;
rc = alloc_path_with_tree_prefix(&copy_path, &copy_size,
&name_len,
tcon->treeName, path);
@@ -2943,16 +2943,17 @@ SMB2_open(const unsigned int xid, struct cifs_open_parms *oparms, __le16 *path,
}
goto creat_exit;
} else
- trace_smb3_open_done(xid, rsp->PersistentFileId, tcon->tid,
+ trace_smb3_open_done(xid, le64_to_cpu(rsp->PersistentFileId),
+ tcon->tid,
ses->Suid, oparms->create_options,
oparms->desired_access);
atomic_inc(&tcon->num_remote_opens);
- oparms->fid->persistent_fid = rsp->PersistentFileId;
- oparms->fid->volatile_fid = rsp->VolatileFileId;
+ oparms->fid->persistent_fid = le64_to_cpu(rsp->PersistentFileId);
+ oparms->fid->volatile_fid = le64_to_cpu(rsp->VolatileFileId);
oparms->fid->access = oparms->desired_access;
#ifdef CONFIG_CIFS_DEBUG2
- oparms->fid->mid = le64_to_cpu(rsp->sync_hdr.MessageId);
+ oparms->fid->mid = le64_to_cpu(rsp->hdr.MessageId);
#endif /* CIFS_DEBUG2 */
if (buf) {
@@ -3052,7 +3053,7 @@ SMB2_ioctl_init(struct cifs_tcon *tcon, struct TCP_Server_Info *server,
* response size smaller.
*/
req->MaxOutputResponse = cpu_to_le32(max_response_size);
- req->sync_hdr.CreditCharge =
+ req->hdr.CreditCharge =
cpu_to_le16(DIV_ROUND_UP(max(indatalen, max_response_size),
SMB2_MAX_BUFFER_SIZE));
if (is_fsctl)
@@ -3062,7 +3063,7 @@ SMB2_ioctl_init(struct cifs_tcon *tcon, struct TCP_Server_Info *server,
/* validate negotiate request must be signed - see MS-SMB2 3.2.5.5 */
if (opcode == FSCTL_VALIDATE_NEGOTIATE_INFO)
- req->sync_hdr.Flags |= SMB2_FLAGS_SIGNED;
+ req->hdr.Flags |= SMB2_FLAGS_SIGNED;
return 0;
}
@@ -3236,8 +3237,8 @@ SMB2_close_init(struct cifs_tcon *tcon, struct TCP_Server_Info *server,
if (rc)
return rc;
- req->PersistentFileId = persistent_fid;
- req->VolatileFileId = volatile_fid;
+ req->PersistentFileId = cpu_to_le64(persistent_fid);
+ req->VolatileFileId = cpu_to_le64(volatile_fid);
if (query_attrs)
req->Flags = SMB2_CLOSE_FLAG_POSTQUERY_ATTRIB;
else
@@ -3600,8 +3601,8 @@ SMB2_notify_init(const unsigned int xid, struct smb_rqst *rqst,
if (rc)
return rc;
- req->PersistentFileId = persistent_fid;
- req->VolatileFileId = volatile_fid;
+ req->PersistentFileId = cpu_to_le64(persistent_fid);
+ req->VolatileFileId = cpu_to_le64(volatile_fid);
/* See note 354 of MS-SMB2, 64K max */
req->OutputBufferLength =
cpu_to_le32(SMB2_MAX_BUFFER_SIZE - MAX_SMB2_HDR_SIZE);
@@ -3687,7 +3688,7 @@ smb2_echo_callback(struct mid_q_entry *mid)
if (mid->mid_state == MID_RESPONSE_RECEIVED
|| mid->mid_state == MID_RESPONSE_MALFORMED) {
- credits.value = le16_to_cpu(rsp->sync_hdr.CreditRequest);
+ credits.value = le16_to_cpu(rsp->hdr.CreditRequest);
credits.instance = server->reconnect_instance;
}
@@ -3787,7 +3788,7 @@ SMB2_echo(struct TCP_Server_Info *server)
if (rc)
return rc;
- req->sync_hdr.CreditRequest = cpu_to_le16(1);
+ req->hdr.CreditRequest = cpu_to_le16(1);
iov[0].iov_len = total_len;
iov[0].iov_base = (char *)req;
@@ -3823,8 +3824,8 @@ SMB2_flush_init(const unsigned int xid, struct smb_rqst *rqst,
if (rc)
return rc;
- req->PersistentFileId = persistent_fid;
- req->VolatileFileId = volatile_fid;
+ req->PersistentFileId = cpu_to_le64(persistent_fid);
+ req->VolatileFileId = cpu_to_le64(volatile_fid);
iov[0].iov_base = (char *)req;
iov[0].iov_len = total_len;
@@ -3890,8 +3891,8 @@ smb2_new_read_req(void **buf, unsigned int *total_len,
unsigned int remaining_bytes, int request_type)
{
int rc = -EACCES;
- struct smb2_read_plain_req *req = NULL;
- struct smb2_sync_hdr *shdr;
+ struct smb2_read_req *req = NULL;
+ struct smb2_hdr *shdr;
struct TCP_Server_Info *server = io_parms->server;
rc = smb2_plain_req_init(SMB2_READ, io_parms->tcon, server,
@@ -3902,11 +3903,11 @@ smb2_new_read_req(void **buf, unsigned int *total_len,
if (server == NULL)
return -ECONNABORTED;
- shdr = &req->sync_hdr;
- shdr->ProcessId = cpu_to_le32(io_parms->pid);
+ shdr = &req->hdr;
+ shdr->Id.SyncId.ProcessId = cpu_to_le32(io_parms->pid);
- req->PersistentFileId = io_parms->persistent_fid;
- req->VolatileFileId = io_parms->volatile_fid;
+ req->PersistentFileId = cpu_to_le64(io_parms->persistent_fid);
+ req->VolatileFileId = cpu_to_le64(io_parms->volatile_fid);
req->ReadChannelInfoOffset = 0; /* reserved */
req->ReadChannelInfoLength = 0; /* reserved */
req->Channel = 0; /* reserved */
@@ -3940,7 +3941,7 @@ smb2_new_read_req(void **buf, unsigned int *total_len,
if (need_invalidate)
req->Channel = SMB2_CHANNEL_RDMA_V1;
req->ReadChannelInfoOffset =
- cpu_to_le16(offsetof(struct smb2_read_plain_req, Buffer));
+ cpu_to_le16(offsetof(struct smb2_read_req, Buffer));
req->ReadChannelInfoLength =
cpu_to_le16(sizeof(struct smbd_buffer_descriptor_v1));
v1 = (struct smbd_buffer_descriptor_v1 *) &req->Buffer[0];
@@ -3964,10 +3965,10 @@ smb2_new_read_req(void **buf, unsigned int *total_len,
* Related requests use info from previous read request
* in chain.
*/
- shdr->SessionId = 0xFFFFFFFFFFFFFFFF;
- shdr->TreeId = 0xFFFFFFFF;
- req->PersistentFileId = 0xFFFFFFFFFFFFFFFF;
- req->VolatileFileId = 0xFFFFFFFFFFFFFFFF;
+ shdr->SessionId = cpu_to_le64(0xFFFFFFFFFFFFFFFF);
+ shdr->Id.SyncId.TreeId = cpu_to_le32(0xFFFFFFFF);
+ req->PersistentFileId = cpu_to_le64(0xFFFFFFFFFFFFFFFF);
+ req->VolatileFileId = cpu_to_le64(0xFFFFFFFFFFFFFFFF);
}
}
if (remaining_bytes > io_parms->length)
@@ -3985,8 +3986,8 @@ smb2_readv_callback(struct mid_q_entry *mid)
struct cifs_readdata *rdata = mid->callback_data;
struct cifs_tcon *tcon = tlink_tcon(rdata->cfile->tlink);
struct TCP_Server_Info *server = rdata->server;
- struct smb2_sync_hdr *shdr =
- (struct smb2_sync_hdr *)rdata->iov[0].iov_base;
+ struct smb2_hdr *shdr =
+ (struct smb2_hdr *)rdata->iov[0].iov_base;
struct cifs_credits credits = { .value = 0, .instance = 0 };
struct smb_rqst rqst = { .rq_iov = &rdata->iov[1],
.rq_nvec = 1,
@@ -4072,7 +4073,7 @@ smb2_async_readv(struct cifs_readdata *rdata)
{
int rc, flags = 0;
char *buf;
- struct smb2_sync_hdr *shdr;
+ struct smb2_hdr *shdr;
struct cifs_io_parms io_parms;
struct smb_rqst rqst = { .rq_iov = rdata->iov,
.rq_nvec = 1 };
@@ -4105,7 +4106,7 @@ smb2_async_readv(struct cifs_readdata *rdata)
rdata->iov[0].iov_base = buf;
rdata->iov[0].iov_len = total_len;
- shdr = (struct smb2_sync_hdr *)buf;
+ shdr = (struct smb2_hdr *)buf;
if (rdata->credits.value > 0) {
shdr->CreditCharge = cpu_to_le16(DIV_ROUND_UP(rdata->bytes,
@@ -4144,7 +4145,7 @@ SMB2_read(const unsigned int xid, struct cifs_io_parms *io_parms,
{
struct smb_rqst rqst;
int resp_buftype, rc;
- struct smb2_read_plain_req *req = NULL;
+ struct smb2_read_req *req = NULL;
struct smb2_read_rsp *rsp = NULL;
struct kvec iov[1];
struct kvec rsp_iov;
@@ -4178,19 +4179,22 @@ SMB2_read(const unsigned int xid, struct cifs_io_parms *io_parms,
if (rc != -ENODATA) {
cifs_stats_fail_inc(io_parms->tcon, SMB2_READ_HE);
cifs_dbg(VFS, "Send error in read = %d\n", rc);
- trace_smb3_read_err(xid, req->PersistentFileId,
+ trace_smb3_read_err(xid,
+ le64_to_cpu(req->PersistentFileId),
io_parms->tcon->tid, ses->Suid,
io_parms->offset, io_parms->length,
rc);
} else
- trace_smb3_read_done(xid, req->PersistentFileId,
- io_parms->tcon->tid, ses->Suid,
- io_parms->offset, 0);
+ trace_smb3_read_done(xid,
+ le64_to_cpu(req->PersistentFileId),
+ io_parms->tcon->tid, ses->Suid,
+ io_parms->offset, 0);
free_rsp_buf(resp_buftype, rsp_iov.iov_base);
cifs_small_buf_release(req);
return rc == -ENODATA ? 0 : rc;
} else
- trace_smb3_read_done(xid, req->PersistentFileId,
+ trace_smb3_read_done(xid,
+ le64_to_cpu(req->PersistentFileId),
io_parms->tcon->tid, ses->Suid,
io_parms->offset, io_parms->length);
@@ -4238,7 +4242,7 @@ smb2_writev_callback(struct mid_q_entry *mid)
switch (mid->mid_state) {
case MID_RESPONSE_RECEIVED:
- credits.value = le16_to_cpu(rsp->sync_hdr.CreditRequest);
+ credits.value = le16_to_cpu(rsp->hdr.CreditRequest);
credits.instance = server->reconnect_instance;
wdata->result = smb2_check_receive(mid, server, 0);
if (wdata->result != 0)
@@ -4264,7 +4268,7 @@ smb2_writev_callback(struct mid_q_entry *mid)
wdata->result = -EAGAIN;
break;
case MID_RESPONSE_MALFORMED:
- credits.value = le16_to_cpu(rsp->sync_hdr.CreditRequest);
+ credits.value = le16_to_cpu(rsp->hdr.CreditRequest);
credits.instance = server->reconnect_instance;
fallthrough;
default:
@@ -4311,7 +4315,7 @@ smb2_async_writev(struct cifs_writedata *wdata,
{
int rc = -EACCES, flags = 0;
struct smb2_write_req *req = NULL;
- struct smb2_sync_hdr *shdr;
+ struct smb2_hdr *shdr;
struct cifs_tcon *tcon = tlink_tcon(wdata->cfile->tlink);
struct TCP_Server_Info *server = wdata->server;
struct kvec iov[1];
@@ -4329,11 +4333,11 @@ smb2_async_writev(struct cifs_writedata *wdata,
if (smb3_encryption_required(tcon))
flags |= CIFS_TRANSFORM_REQ;
- shdr = (struct smb2_sync_hdr *)req;
- shdr->ProcessId = cpu_to_le32(wdata->cfile->pid);
+ shdr = (struct smb2_hdr *)req;
+ shdr->Id.SyncId.ProcessId = cpu_to_le32(wdata->cfile->pid);
- req->PersistentFileId = wdata->cfile->fid.persistent_fid;
- req->VolatileFileId = wdata->cfile->fid.volatile_fid;
+ req->PersistentFileId = cpu_to_le64(wdata->cfile->fid.persistent_fid);
+ req->VolatileFileId = cpu_to_le64(wdata->cfile->fid.volatile_fid);
req->WriteChannelInfoOffset = 0;
req->WriteChannelInfoLength = 0;
req->Channel = 0;
@@ -4430,7 +4434,8 @@ smb2_async_writev(struct cifs_writedata *wdata,
wdata, flags, &wdata->credits);
if (rc) {
- trace_smb3_write_err(0 /* no xid */, req->PersistentFileId,
+ trace_smb3_write_err(0 /* no xid */,
+ le64_to_cpu(req->PersistentFileId),
tcon->tid, tcon->ses->Suid, wdata->offset,
wdata->bytes, rc);
kref_put(&wdata->refcount, release);
@@ -4481,10 +4486,10 @@ SMB2_write(const unsigned int xid, struct cifs_io_parms *io_parms,
if (smb3_encryption_required(io_parms->tcon))
flags |= CIFS_TRANSFORM_REQ;
- req->sync_hdr.ProcessId = cpu_to_le32(io_parms->pid);
+ req->hdr.Id.SyncId.ProcessId = cpu_to_le32(io_parms->pid);
- req->PersistentFileId = io_parms->persistent_fid;
- req->VolatileFileId = io_parms->volatile_fid;
+ req->PersistentFileId = cpu_to_le64(io_parms->persistent_fid);
+ req->VolatileFileId = cpu_to_le64(io_parms->volatile_fid);
req->WriteChannelInfoOffset = 0;
req->WriteChannelInfoLength = 0;
req->Channel = 0;
@@ -4512,7 +4517,8 @@ SMB2_write(const unsigned int xid, struct cifs_io_parms *io_parms,
rsp = (struct smb2_write_rsp *)rsp_iov.iov_base;
if (rc) {
- trace_smb3_write_err(xid, req->PersistentFileId,
+ trace_smb3_write_err(xid,
+ le64_to_cpu(req->PersistentFileId),
io_parms->tcon->tid,
io_parms->tcon->ses->Suid,
io_parms->offset, io_parms->length, rc);
@@ -4520,10 +4526,11 @@ SMB2_write(const unsigned int xid, struct cifs_io_parms *io_parms,
cifs_dbg(VFS, "Send error in write = %d\n", rc);
} else {
*nbytes = le32_to_cpu(rsp->DataLength);
- trace_smb3_write_done(xid, req->PersistentFileId,
- io_parms->tcon->tid,
- io_parms->tcon->ses->Suid,
- io_parms->offset, *nbytes);
+ trace_smb3_write_done(xid,
+ le64_to_cpu(req->PersistentFileId),
+ io_parms->tcon->tid,
+ io_parms->tcon->ses->Suid,
+ io_parms->offset, *nbytes);
}
cifs_small_buf_release(req);
@@ -4866,7 +4873,7 @@ SMB2_query_directory(const unsigned int xid, struct cifs_tcon *tcon,
if (rc) {
if (rc == -ENODATA &&
- rsp->sync_hdr.Status == STATUS_NO_MORE_FILES) {
+ rsp->hdr.Status == STATUS_NO_MORE_FILES) {
trace_smb3_query_dir_done(xid, persistent_fid,
tcon->tid, tcon->ses->Suid, index, 0);
srch_inf->endOfSearch = true;
@@ -4914,7 +4921,7 @@ SMB2_set_info_init(struct cifs_tcon *tcon, struct TCP_Server_Info *server,
if (rc)
return rc;
- req->sync_hdr.ProcessId = cpu_to_le32(pid);
+ req->hdr.Id.SyncId.ProcessId = cpu_to_le32(pid);
req->InfoType = info_type;
req->FileInfoClass = info_class;
req->PersistentFileId = persistent_fid;
@@ -5074,7 +5081,7 @@ SMB2_oplock_break(const unsigned int xid, struct cifs_tcon *tcon,
req->VolatileFid = volatile_fid;
req->PersistentFid = persistent_fid;
req->OplockLevel = oplock_level;
- req->sync_hdr.CreditRequest = cpu_to_le16(1);
+ req->hdr.CreditRequest = cpu_to_le16(1);
flags |= CIFS_NO_RSP_BUF;
@@ -5376,7 +5383,7 @@ smb2_lockv(const unsigned int xid, struct cifs_tcon *tcon,
if (smb3_encryption_required(tcon))
flags |= CIFS_TRANSFORM_REQ;
- req->sync_hdr.ProcessId = cpu_to_le32(pid);
+ req->hdr.Id.SyncId.ProcessId = cpu_to_le32(pid);
req->LockCount = cpu_to_le16(num_lock);
req->PersistentFileId = persist_fid;
@@ -5452,7 +5459,7 @@ SMB2_lease_break(const unsigned int xid, struct cifs_tcon *tcon,
if (smb3_encryption_required(tcon))
flags |= CIFS_TRANSFORM_REQ;
- req->sync_hdr.CreditRequest = cpu_to_le16(1);
+ req->hdr.CreditRequest = cpu_to_le16(1);
req->StructureSize = cpu_to_le16(36);
total_len += 12;
diff --git a/fs/cifs/smb2pdu.h b/fs/cifs/smb2pdu.h
index f32c99c9ba13..33cfd0a1adf1 100644
--- a/fs/cifs/smb2pdu.h
+++ b/fs/cifs/smb2pdu.h
@@ -14,156 +14,12 @@
#include <net/sock.h>
#include "cifsacl.h"
-/*
- * Note that, due to trying to use names similar to the protocol specifications,
- * there are many mixed case field names in the structures below. Although
- * this does not match typical Linux kernel style, it is necessary to be
- * able to match against the protocol specfication.
- *
- * SMB2 commands
- * Some commands have minimal (wct=0,bcc=0), or uninteresting, responses
- * (ie no useful data other than the SMB error code itself) and are marked such.
- * Knowing this helps avoid response buffer allocations and copy in some cases.
- */
-
-/* List of commands in host endian */
-#define SMB2_NEGOTIATE_HE 0x0000
-#define SMB2_SESSION_SETUP_HE 0x0001
-#define SMB2_LOGOFF_HE 0x0002 /* trivial request/resp */
-#define SMB2_TREE_CONNECT_HE 0x0003
-#define SMB2_TREE_DISCONNECT_HE 0x0004 /* trivial req/resp */
-#define SMB2_CREATE_HE 0x0005
-#define SMB2_CLOSE_HE 0x0006
-#define SMB2_FLUSH_HE 0x0007 /* trivial resp */
-#define SMB2_READ_HE 0x0008
-#define SMB2_WRITE_HE 0x0009
-#define SMB2_LOCK_HE 0x000A
-#define SMB2_IOCTL_HE 0x000B
-#define SMB2_CANCEL_HE 0x000C
-#define SMB2_ECHO_HE 0x000D
-#define SMB2_QUERY_DIRECTORY_HE 0x000E
-#define SMB2_CHANGE_NOTIFY_HE 0x000F
-#define SMB2_QUERY_INFO_HE 0x0010
-#define SMB2_SET_INFO_HE 0x0011
-#define SMB2_OPLOCK_BREAK_HE 0x0012
-
-/* The same list in little endian */
-#define SMB2_NEGOTIATE cpu_to_le16(SMB2_NEGOTIATE_HE)
-#define SMB2_SESSION_SETUP cpu_to_le16(SMB2_SESSION_SETUP_HE)
-#define SMB2_LOGOFF cpu_to_le16(SMB2_LOGOFF_HE)
-#define SMB2_TREE_CONNECT cpu_to_le16(SMB2_TREE_CONNECT_HE)
-#define SMB2_TREE_DISCONNECT cpu_to_le16(SMB2_TREE_DISCONNECT_HE)
-#define SMB2_CREATE cpu_to_le16(SMB2_CREATE_HE)
-#define SMB2_CLOSE cpu_to_le16(SMB2_CLOSE_HE)
-#define SMB2_FLUSH cpu_to_le16(SMB2_FLUSH_HE)
-#define SMB2_READ cpu_to_le16(SMB2_READ_HE)
-#define SMB2_WRITE cpu_to_le16(SMB2_WRITE_HE)
-#define SMB2_LOCK cpu_to_le16(SMB2_LOCK_HE)
-#define SMB2_IOCTL cpu_to_le16(SMB2_IOCTL_HE)
-#define SMB2_CANCEL cpu_to_le16(SMB2_CANCEL_HE)
-#define SMB2_ECHO cpu_to_le16(SMB2_ECHO_HE)
-#define SMB2_QUERY_DIRECTORY cpu_to_le16(SMB2_QUERY_DIRECTORY_HE)
-#define SMB2_CHANGE_NOTIFY cpu_to_le16(SMB2_CHANGE_NOTIFY_HE)
-#define SMB2_QUERY_INFO cpu_to_le16(SMB2_QUERY_INFO_HE)
-#define SMB2_SET_INFO cpu_to_le16(SMB2_SET_INFO_HE)
-#define SMB2_OPLOCK_BREAK cpu_to_le16(SMB2_OPLOCK_BREAK_HE)
-
-#define SMB2_INTERNAL_CMD cpu_to_le16(0xFFFF)
-
-#define NUMBER_OF_SMB2_COMMANDS 0x0013
-
/* 52 transform hdr + 64 hdr + 88 create rsp */
#define SMB2_TRANSFORM_HEADER_SIZE 52
#define MAX_SMB2_HDR_SIZE 204
-#define SMB2_PROTO_NUMBER cpu_to_le32(0x424d53fe)
-#define SMB2_TRANSFORM_PROTO_NUM cpu_to_le32(0x424d53fd)
-#define SMB2_COMPRESSION_TRANSFORM_ID cpu_to_le32(0x424d53fc)
-
-/*
- * SMB2 Header Definition
- *
- * "MBZ" : Must be Zero
- * "BB" : BugBug, Something to check/review/analyze later
- * "PDU" : "Protocol Data Unit" (ie a network "frame")
- *
- */
-
-#define SMB2_HEADER_STRUCTURE_SIZE cpu_to_le16(64)
-
-struct smb2_sync_hdr {
- __le32 ProtocolId; /* 0xFE 'S' 'M' 'B' */
- __le16 StructureSize; /* 64 */
- __le16 CreditCharge; /* MBZ */
- __le32 Status; /* Error from server */
- __le16 Command;
- __le16 CreditRequest; /* CreditResponse */
- __le32 Flags;
- __le32 NextCommand;
- __le64 MessageId;
- __le32 ProcessId;
- __u32 TreeId; /* opaque - so do not make little endian */
- __u64 SessionId; /* opaque - so do not make little endian */
- __u8 Signature[16];
-} __packed;
-
/* The total header size for SMB2 read and write */
-#define SMB2_READWRITE_PDU_HEADER_SIZE (48 + sizeof(struct smb2_sync_hdr))
-
-struct smb2_sync_pdu {
- struct smb2_sync_hdr sync_hdr;
- __le16 StructureSize2; /* size of wct area (varies, request specific) */
-} __packed;
-
-#define SMB3_AES_CCM_NONCE 11
-#define SMB3_AES_GCM_NONCE 12
-
-/* Transform flags (for 3.0 dialect this flag indicates CCM */
-#define TRANSFORM_FLAG_ENCRYPTED 0x0001
-struct smb2_transform_hdr {
- __le32 ProtocolId; /* 0xFD 'S' 'M' 'B' */
- __u8 Signature[16];
- __u8 Nonce[16];
- __le32 OriginalMessageSize;
- __u16 Reserved1;
- __le16 Flags; /* EncryptionAlgorithm for 3.0, enc enabled for 3.1.1 */
- __u64 SessionId;
-} __packed;
-
-/* See MS-SMB2 2.2.42 */
-struct smb2_compression_transform_hdr_unchained {
- __le32 ProtocolId; /* 0xFC 'S' 'M' 'B' */
- __le32 OriginalCompressedSegmentSize;
- __le16 CompressionAlgorithm;
- __le16 Flags;
- __le16 Length; /* if chained it is length, else offset */
-} __packed;
-
-/* See MS-SMB2 2.2.42.1 */
-#define SMB2_COMPRESSION_FLAG_NONE 0x0000
-#define SMB2_COMPRESSION_FLAG_CHAINED 0x0001
-
-struct compression_payload_header {
- __le16 CompressionAlgorithm;
- __le16 Flags;
- __le32 Length; /* length of compressed playload including field below if present */
- /* __le32 OriginalPayloadSize; */ /* optional, present when LZNT1, LZ77, LZ77+Huffman */
-} __packed;
-
-/* See MS-SMB2 2.2.42.2 */
-struct smb2_compression_transform_hdr_chained {
- __le32 ProtocolId; /* 0xFC 'S' 'M' 'B' */
- __le32 OriginalCompressedSegmentSize;
- /* struct compression_payload_header[] */
-} __packed;
-
-/* See MS-SMB2 2.2.42.2.2 */
-struct compression_pattern_payload_v1 {
- __le16 Pattern;
- __le16 Reserved1;
- __le16 Reserved2;
- __le32 Repetitions;
-} __packed;
+#define SMB2_READWRITE_PDU_HEADER_SIZE (48 + sizeof(struct smb2_hdr))
/* See MS-SMB2 2.2.43 */
struct smb2_rdma_transform {
@@ -190,17 +46,6 @@ struct smb2_rdma_crypto_transform {
} __packed;
/*
- * SMB2 flag definitions
- */
-#define SMB2_FLAGS_SERVER_TO_REDIR cpu_to_le32(0x00000001)
-#define SMB2_FLAGS_ASYNC_COMMAND cpu_to_le32(0x00000002)
-#define SMB2_FLAGS_RELATED_OPERATIONS cpu_to_le32(0x00000004)
-#define SMB2_FLAGS_SIGNED cpu_to_le32(0x00000008)
-#define SMB2_FLAGS_PRIORITY_MASK cpu_to_le32(0x00000070) /* SMB3.1.1 */
-#define SMB2_FLAGS_DFS_OPERATIONS cpu_to_le32(0x10000000)
-#define SMB2_FLAGS_REPLAY_OPERATION cpu_to_le32(0x20000000) /* SMB3 & up */
-
-/*
* Definitions for SMB2 Protocol Data Units (network frames)
*
* See MS-SMB2.PDF specification for protocol details.
@@ -214,7 +59,7 @@ struct smb2_rdma_crypto_transform {
#define SMB2_ERROR_STRUCTURE_SIZE2 cpu_to_le16(9)
struct smb2_err_rsp {
- struct smb2_sync_hdr sync_hdr;
+ struct smb2_hdr hdr;
__le16 StructureSize;
__le16 Reserved; /* MBZ */
__le32 ByteCount; /* even if zero, at least one byte follows */
@@ -270,530 +115,6 @@ struct share_redirect_error_context_rsp {
/* __u8 ResourceName[] */ /* Name of share as counted Unicode string */
} __packed;
-#define SMB2_CLIENT_GUID_SIZE 16
-
-struct smb2_negotiate_req {
- struct smb2_sync_hdr sync_hdr;
- __le16 StructureSize; /* Must be 36 */
- __le16 DialectCount;
- __le16 SecurityMode;
- __le16 Reserved; /* MBZ */
- __le32 Capabilities;
- __u8 ClientGUID[SMB2_CLIENT_GUID_SIZE];
- /* In SMB3.02 and earlier next three were MBZ le64 ClientStartTime */
- __le32 NegotiateContextOffset; /* SMB3.1.1 only. MBZ earlier */
- __le16 NegotiateContextCount; /* SMB3.1.1 only. MBZ earlier */
- __le16 Reserved2;
- __le16 Dialects[4]; /* BB expand this if autonegotiate > 4 dialects */
-} __packed;
-
-/* Dialects */
-#define SMB10_PROT_ID 0x0000 /* local only, not sent on wire w/CIFS negprot */
-#define SMB20_PROT_ID 0x0202
-#define SMB21_PROT_ID 0x0210
-#define SMB30_PROT_ID 0x0300
-#define SMB302_PROT_ID 0x0302
-#define SMB311_PROT_ID 0x0311
-#define BAD_PROT_ID 0xFFFF
-
-/* SecurityMode flags */
-#define SMB2_NEGOTIATE_SIGNING_ENABLED 0x0001
-#define SMB2_NEGOTIATE_SIGNING_REQUIRED 0x0002
-#define SMB2_SEC_MODE_FLAGS_ALL 0x0003
-
-/* Capabilities flags */
-#define SMB2_GLOBAL_CAP_DFS 0x00000001
-#define SMB2_GLOBAL_CAP_LEASING 0x00000002 /* Resp only New to SMB2.1 */
-#define SMB2_GLOBAL_CAP_LARGE_MTU 0X00000004 /* Resp only New to SMB2.1 */
-#define SMB2_GLOBAL_CAP_MULTI_CHANNEL 0x00000008 /* New to SMB3 */
-#define SMB2_GLOBAL_CAP_PERSISTENT_HANDLES 0x00000010 /* New to SMB3 */
-#define SMB2_GLOBAL_CAP_DIRECTORY_LEASING 0x00000020 /* New to SMB3 */
-#define SMB2_GLOBAL_CAP_ENCRYPTION 0x00000040 /* New to SMB3 */
-/* Internal types */
-#define SMB2_NT_FIND 0x00100000
-#define SMB2_LARGE_FILES 0x00200000
-
-
-/* Negotiate Contexts - ContextTypes. See MS-SMB2 section 2.2.3.1 for details */
-#define SMB2_PREAUTH_INTEGRITY_CAPABILITIES cpu_to_le16(1)
-#define SMB2_ENCRYPTION_CAPABILITIES cpu_to_le16(2)
-#define SMB2_COMPRESSION_CAPABILITIES cpu_to_le16(3)
-#define SMB2_NETNAME_NEGOTIATE_CONTEXT_ID cpu_to_le16(5)
-#define SMB2_TRANSPORT_CAPABILITIES cpu_to_le16(6)
-#define SMB2_RDMA_TRANSFORM_CAPABILITIES cpu_to_le16(7)
-#define SMB2_SIGNING_CAPABILITIES cpu_to_le16(8)
-#define SMB2_POSIX_EXTENSIONS_AVAILABLE cpu_to_le16(0x100)
-
-struct smb2_neg_context {
- __le16 ContextType;
- __le16 DataLength;
- __le32 Reserved;
- /* Followed by array of data. NOTE: some servers require padding to 8 byte boundary */
-} __packed;
-
-#define SMB311_LINUX_CLIENT_SALT_SIZE 32
-/* Hash Algorithm Types */
-#define SMB2_PREAUTH_INTEGRITY_SHA512 cpu_to_le16(0x0001)
-#define SMB2_PREAUTH_HASH_SIZE 64
-
-/*
- * SaltLength that the server send can be zero, so the only three required
- * fields (all __le16) end up six bytes total, so the minimum context data len
- * in the response is six bytes which accounts for
- *
- * HashAlgorithmCount, SaltLength, and 1 HashAlgorithm.
- */
-#define MIN_PREAUTH_CTXT_DATA_LEN 6
-
-struct smb2_preauth_neg_context {
- __le16 ContextType; /* 1 */
- __le16 DataLength;
- __le32 Reserved;
- __le16 HashAlgorithmCount; /* 1 */
- __le16 SaltLength;
- __le16 HashAlgorithms; /* HashAlgorithms[0] since only one defined */
- __u8 Salt[SMB311_LINUX_CLIENT_SALT_SIZE];
-} __packed;
-
-/* Encryption Algorithms Ciphers */
-#define SMB2_ENCRYPTION_AES128_CCM cpu_to_le16(0x0001)
-#define SMB2_ENCRYPTION_AES128_GCM cpu_to_le16(0x0002)
-/* we currently do not request AES256_CCM since presumably GCM faster */
-#define SMB2_ENCRYPTION_AES256_CCM cpu_to_le16(0x0003)
-#define SMB2_ENCRYPTION_AES256_GCM cpu_to_le16(0x0004)
-
-/* Min encrypt context data is one cipher so 2 bytes + 2 byte count field */
-#define MIN_ENCRYPT_CTXT_DATA_LEN 4
-struct smb2_encryption_neg_context {
- __le16 ContextType; /* 2 */
- __le16 DataLength;
- __le32 Reserved;
- /* CipherCount usally 2, but can be 3 when AES256-GCM enabled */
- __le16 CipherCount; /* AES128-GCM and AES128-CCM by default */
- __le16 Ciphers[3];
-} __packed;
-
-/* See MS-SMB2 2.2.3.1.3 */
-#define SMB3_COMPRESS_NONE cpu_to_le16(0x0000)
-#define SMB3_COMPRESS_LZNT1 cpu_to_le16(0x0001)
-#define SMB3_COMPRESS_LZ77 cpu_to_le16(0x0002)
-#define SMB3_COMPRESS_LZ77_HUFF cpu_to_le16(0x0003)
-/* Pattern scanning algorithm See MS-SMB2 3.1.4.4.1 */
-#define SMB3_COMPRESS_PATTERN cpu_to_le16(0x0004) /* Pattern_V1 */
-
-/* Compression Flags */
-#define SMB2_COMPRESSION_CAPABILITIES_FLAG_NONE cpu_to_le32(0x00000000)
-#define SMB2_COMPRESSION_CAPABILITIES_FLAG_CHAINED cpu_to_le32(0x00000001)
-
-struct smb2_compression_capabilities_context {
- __le16 ContextType; /* 3 */
- __le16 DataLength;
- __u32 Reserved;
- __le16 CompressionAlgorithmCount;
- __u16 Padding;
- __u32 Flags;
- __le16 CompressionAlgorithms[3];
- __u16 Pad; /* Some servers require pad to DataLen multiple of 8 */
- /* Check if pad needed */
-} __packed;
-
-/*
- * For smb2_netname_negotiate_context_id See MS-SMB2 2.2.3.1.4.
- * Its struct simply contains NetName, an array of Unicode characters
- */
-struct smb2_netname_neg_context {
- __le16 ContextType; /* 5 */
- __le16 DataLength;
- __le32 Reserved;
- __le16 NetName[]; /* hostname of target converted to UCS-2 */
-} __packed;
-
-/*
- * For smb2_transport_capabilities context see MS-SMB2 2.2.3.1.5
- * and 2.2.4.1.5
- */
-
-/* Flags */
-#define SMB2_ACCEPT_TRANSFORM_LEVEL_SECURITY 0x00000001
-
-struct smb2_transport_capabilities_context {
- __le16 ContextType; /* 6 */
- __le16 DataLength;
- __u32 Reserved;
- __le32 Flags;
- __u32 Pad;
-} __packed;
-
-/*
- * For rdma transform capabilities context see MS-SMB2 2.2.3.1.6
- * and 2.2.4.1.6
- */
-
-/* RDMA Transform IDs */
-#define SMB2_RDMA_TRANSFORM_NONE 0x0000
-#define SMB2_RDMA_TRANSFORM_ENCRYPTION 0x0001
-#define SMB2_RDMA_TRANSFORM_SIGNING 0x0002
-
-struct smb2_rdma_transform_capabilities_context {
- __le16 ContextType; /* 7 */
- __le16 DataLength;
- __u32 Reserved;
- __le16 TransformCount;
- __u16 Reserved1;
- __u32 Reserved2;
- __le16 RDMATransformIds[];
-} __packed;
-
-/*
- * For signing capabilities context see MS-SMB2 2.2.3.1.7
- * and 2.2.4.1.7
- */
-
-/* Signing algorithms */
-#define SIGNING_ALG_HMAC_SHA256 0
-#define SIGNING_ALG_AES_CMAC 1
-#define SIGNING_ALG_AES_GMAC 2
-
-struct smb2_signing_capabilities {
- __le16 ContextType; /* 8 */
- __le16 DataLength;
- __u32 Reserved;
- __le16 SigningAlgorithmCount;
- __le16 SigningAlgorithms[];
- /* Followed by padding to 8 byte boundary (required by some servers) */
-} __packed;
-
-#define POSIX_CTXT_DATA_LEN 16
-struct smb2_posix_neg_context {
- __le16 ContextType; /* 0x100 */
- __le16 DataLength;
- __le32 Reserved;
- __u8 Name[16]; /* POSIX ctxt GUID 93AD25509CB411E7B42383DE968BCD7C */
-} __packed;
-
-struct smb2_negotiate_rsp {
- struct smb2_sync_hdr sync_hdr;
- __le16 StructureSize; /* Must be 65 */
- __le16 SecurityMode;
- __le16 DialectRevision;
- __le16 NegotiateContextCount; /* Prior to SMB3.1.1 was Reserved & MBZ */
- __u8 ServerGUID[16];
- __le32 Capabilities;
- __le32 MaxTransactSize;
- __le32 MaxReadSize;
- __le32 MaxWriteSize;
- __le64 SystemTime; /* MBZ */
- __le64 ServerStartTime;
- __le16 SecurityBufferOffset;
- __le16 SecurityBufferLength;
- __le32 NegotiateContextOffset; /* Pre:SMB3.1.1 was reserved/ignored */
- __u8 Buffer[1]; /* variable length GSS security buffer */
-} __packed;
-
-/* Flags */
-#define SMB2_SESSION_REQ_FLAG_BINDING 0x01
-#define SMB2_SESSION_REQ_FLAG_ENCRYPT_DATA 0x04
-
-struct smb2_sess_setup_req {
- struct smb2_sync_hdr sync_hdr;
- __le16 StructureSize; /* Must be 25 */
- __u8 Flags;
- __u8 SecurityMode;
- __le32 Capabilities;
- __le32 Channel;
- __le16 SecurityBufferOffset;
- __le16 SecurityBufferLength;
- __u64 PreviousSessionId;
- __u8 Buffer[1]; /* variable length GSS security buffer */
-} __packed;
-
-/* Currently defined SessionFlags */
-#define SMB2_SESSION_FLAG_IS_GUEST 0x0001
-#define SMB2_SESSION_FLAG_IS_NULL 0x0002
-#define SMB2_SESSION_FLAG_ENCRYPT_DATA 0x0004
-struct smb2_sess_setup_rsp {
- struct smb2_sync_hdr sync_hdr;
- __le16 StructureSize; /* Must be 9 */
- __le16 SessionFlags;
- __le16 SecurityBufferOffset;
- __le16 SecurityBufferLength;
- __u8 Buffer[1]; /* variable length GSS security buffer */
-} __packed;
-
-struct smb2_logoff_req {
- struct smb2_sync_hdr sync_hdr;
- __le16 StructureSize; /* Must be 4 */
- __le16 Reserved;
-} __packed;
-
-struct smb2_logoff_rsp {
- struct smb2_sync_hdr sync_hdr;
- __le16 StructureSize; /* Must be 4 */
- __le16 Reserved;
-} __packed;
-
-/* Flags/Reserved for SMB3.1.1 */
-#define SMB2_TREE_CONNECT_FLAG_CLUSTER_RECONNECT cpu_to_le16(0x0001)
-#define SMB2_TREE_CONNECT_FLAG_REDIRECT_TO_OWNER cpu_to_le16(0x0002)
-#define SMB2_TREE_CONNECT_FLAG_EXTENSION_PRESENT cpu_to_le16(0x0004)
-
-struct smb2_tree_connect_req {
- struct smb2_sync_hdr sync_hdr;
- __le16 StructureSize; /* Must be 9 */
- __le16 Flags; /* Reserved MBZ for dialects prior to SMB3.1.1 */
- __le16 PathOffset;
- __le16 PathLength;
- __u8 Buffer[1]; /* variable length */
-} __packed;
-
-/* See MS-SMB2 section 2.2.9.2 */
-/* Context Types */
-#define SMB2_RESERVED_TREE_CONNECT_CONTEXT_ID 0x0000
-#define SMB2_REMOTED_IDENTITY_TREE_CONNECT_CONTEXT_ID cpu_to_le16(0x0001)
-
-struct tree_connect_contexts {
- __le16 ContextType;
- __le16 DataLength;
- __le32 Reserved;
- __u8 Data[];
-} __packed;
-
-/* Remoted identity tree connect context structures - see MS-SMB2 2.2.9.2.1 */
-struct smb3_blob_data {
- __le16 BlobSize;
- __u8 BlobData[];
-} __packed;
-
-/* Valid values for Attr */
-#define SE_GROUP_MANDATORY 0x00000001
-#define SE_GROUP_ENABLED_BY_DEFAULT 0x00000002
-#define SE_GROUP_ENABLED 0x00000004
-#define SE_GROUP_OWNER 0x00000008
-#define SE_GROUP_USE_FOR_DENY_ONLY 0x00000010
-#define SE_GROUP_INTEGRITY 0x00000020
-#define SE_GROUP_INTEGRITY_ENABLED 0x00000040
-#define SE_GROUP_RESOURCE 0x20000000
-#define SE_GROUP_LOGON_ID 0xC0000000
-
-/* struct sid_attr_data is SidData array in BlobData format then le32 Attr */
-
-struct sid_array_data {
- __le16 SidAttrCount;
- /* SidAttrList - array of sid_attr_data structs */
-} __packed;
-
-struct luid_attr_data {
-
-} __packed;
-
-/*
- * struct privilege_data is the same as BLOB_DATA - see MS-SMB2 2.2.9.2.1.5
- * but with size of LUID_ATTR_DATA struct and BlobData set to LUID_ATTR DATA
- */
-
-struct privilege_array_data {
- __le16 PrivilegeCount;
- /* array of privilege_data structs */
-} __packed;
-
-struct remoted_identity_tcon_context {
- __le16 TicketType; /* must be 0x0001 */
- __le16 TicketSize; /* total size of this struct */
- __le16 User; /* offset to SID_ATTR_DATA struct with user info */
- __le16 UserName; /* offset to null terminated Unicode username string */
- __le16 Domain; /* offset to null terminated Unicode domain name */
- __le16 Groups; /* offset to SID_ARRAY_DATA struct with group info */
- __le16 RestrictedGroups; /* similar to above */
- __le16 Privileges; /* offset to PRIVILEGE_ARRAY_DATA struct */
- __le16 PrimaryGroup; /* offset to SID_ARRAY_DATA struct */
- __le16 Owner; /* offset to BLOB_DATA struct */
- __le16 DefaultDacl; /* offset to BLOB_DATA struct */
- __le16 DeviceGroups; /* offset to SID_ARRAY_DATA struct */
- __le16 UserClaims; /* offset to BLOB_DATA struct */
- __le16 DeviceClaims; /* offset to BLOB_DATA struct */
- __u8 TicketInfo[]; /* variable length buf - remoted identity data */
-} __packed;
-
-struct smb2_tree_connect_req_extension {
- __le32 TreeConnectContextOffset;
- __le16 TreeConnectContextCount;
- __u8 Reserved[10];
- __u8 PathName[]; /* variable sized array */
- /* followed by array of TreeConnectContexts */
-} __packed;
-
-struct smb2_tree_connect_rsp {
- struct smb2_sync_hdr sync_hdr;
- __le16 StructureSize; /* Must be 16 */
- __u8 ShareType; /* see below */
- __u8 Reserved;
- __le32 ShareFlags; /* see below */
- __le32 Capabilities; /* see below */
- __le32 MaximalAccess;
-} __packed;
-
-/* Possible ShareType values */
-#define SMB2_SHARE_TYPE_DISK 0x01
-#define SMB2_SHARE_TYPE_PIPE 0x02
-#define SMB2_SHARE_TYPE_PRINT 0x03
-
-/*
- * Possible ShareFlags - exactly one and only one of the first 4 caching flags
- * must be set (any of the remaining, SHI1005, flags may be set individually
- * or in combination.
- */
-#define SMB2_SHAREFLAG_MANUAL_CACHING 0x00000000
-#define SMB2_SHAREFLAG_AUTO_CACHING 0x00000010
-#define SMB2_SHAREFLAG_VDO_CACHING 0x00000020
-#define SMB2_SHAREFLAG_NO_CACHING 0x00000030
-#define SHI1005_FLAGS_DFS 0x00000001
-#define SHI1005_FLAGS_DFS_ROOT 0x00000002
-#define SHI1005_FLAGS_RESTRICT_EXCLUSIVE_OPENS 0x00000100
-#define SHI1005_FLAGS_FORCE_SHARED_DELETE 0x00000200
-#define SHI1005_FLAGS_ALLOW_NAMESPACE_CACHING 0x00000400
-#define SHI1005_FLAGS_ACCESS_BASED_DIRECTORY_ENUM 0x00000800
-#define SHI1005_FLAGS_FORCE_LEVELII_OPLOCK 0x00001000
-#define SHI1005_FLAGS_ENABLE_HASH_V1 0x00002000
-#define SHI1005_FLAGS_ENABLE_HASH_V2 0x00004000
-#define SHI1005_FLAGS_ENCRYPT_DATA 0x00008000
-#define SMB2_SHAREFLAG_IDENTITY_REMOTING 0x00040000 /* 3.1.1 */
-#define SMB2_SHAREFLAG_COMPRESS_DATA 0x00100000 /* 3.1.1 */
-#define SHI1005_FLAGS_ALL 0x0014FF33
-
-/* Possible share capabilities */
-#define SMB2_SHARE_CAP_DFS cpu_to_le32(0x00000008) /* all dialects */
-#define SMB2_SHARE_CAP_CONTINUOUS_AVAILABILITY cpu_to_le32(0x00000010) /* 3.0 */
-#define SMB2_SHARE_CAP_SCALEOUT cpu_to_le32(0x00000020) /* 3.0 */
-#define SMB2_SHARE_CAP_CLUSTER cpu_to_le32(0x00000040) /* 3.0 */
-#define SMB2_SHARE_CAP_ASYMMETRIC cpu_to_le32(0x00000080) /* 3.02 */
-#define SMB2_SHARE_CAP_REDIRECT_TO_OWNER cpu_to_le32(0x00000100) /* 3.1.1 */
-
-struct smb2_tree_disconnect_req {
- struct smb2_sync_hdr sync_hdr;
- __le16 StructureSize; /* Must be 4 */
- __le16 Reserved;
-} __packed;
-
-struct smb2_tree_disconnect_rsp {
- struct smb2_sync_hdr sync_hdr;
- __le16 StructureSize; /* Must be 4 */
- __le16 Reserved;
-} __packed;
-
-/* File Attrubutes */
-#define FILE_ATTRIBUTE_READONLY 0x00000001
-#define FILE_ATTRIBUTE_HIDDEN 0x00000002
-#define FILE_ATTRIBUTE_SYSTEM 0x00000004
-#define FILE_ATTRIBUTE_DIRECTORY 0x00000010
-#define FILE_ATTRIBUTE_ARCHIVE 0x00000020
-#define FILE_ATTRIBUTE_NORMAL 0x00000080
-#define FILE_ATTRIBUTE_TEMPORARY 0x00000100
-#define FILE_ATTRIBUTE_SPARSE_FILE 0x00000200
-#define FILE_ATTRIBUTE_REPARSE_POINT 0x00000400
-#define FILE_ATTRIBUTE_COMPRESSED 0x00000800
-#define FILE_ATTRIBUTE_OFFLINE 0x00001000
-#define FILE_ATTRIBUTE_NOT_CONTENT_INDEXED 0x00002000
-#define FILE_ATTRIBUTE_ENCRYPTED 0x00004000
-#define FILE_ATTRIBUTE_INTEGRITY_STREAM 0x00008000
-#define FILE_ATTRIBUTE_NO_SCRUB_DATA 0x00020000
-
-/* Oplock levels */
-#define SMB2_OPLOCK_LEVEL_NONE 0x00
-#define SMB2_OPLOCK_LEVEL_II 0x01
-#define SMB2_OPLOCK_LEVEL_EXCLUSIVE 0x08
-#define SMB2_OPLOCK_LEVEL_BATCH 0x09
-#define SMB2_OPLOCK_LEVEL_LEASE 0xFF
-/* Non-spec internal type */
-#define SMB2_OPLOCK_LEVEL_NOCHANGE 0x99
-
-/* Desired Access Flags */
-#define FILE_READ_DATA_LE cpu_to_le32(0x00000001)
-#define FILE_WRITE_DATA_LE cpu_to_le32(0x00000002)
-#define FILE_APPEND_DATA_LE cpu_to_le32(0x00000004)
-#define FILE_READ_EA_LE cpu_to_le32(0x00000008)
-#define FILE_WRITE_EA_LE cpu_to_le32(0x00000010)
-#define FILE_EXECUTE_LE cpu_to_le32(0x00000020)
-#define FILE_READ_ATTRIBUTES_LE cpu_to_le32(0x00000080)
-#define FILE_WRITE_ATTRIBUTES_LE cpu_to_le32(0x00000100)
-#define FILE_DELETE_LE cpu_to_le32(0x00010000)
-#define FILE_READ_CONTROL_LE cpu_to_le32(0x00020000)
-#define FILE_WRITE_DAC_LE cpu_to_le32(0x00040000)
-#define FILE_WRITE_OWNER_LE cpu_to_le32(0x00080000)
-#define FILE_SYNCHRONIZE_LE cpu_to_le32(0x00100000)
-#define FILE_ACCESS_SYSTEM_SECURITY_LE cpu_to_le32(0x01000000)
-#define FILE_MAXIMAL_ACCESS_LE cpu_to_le32(0x02000000)
-#define FILE_GENERIC_ALL_LE cpu_to_le32(0x10000000)
-#define FILE_GENERIC_EXECUTE_LE cpu_to_le32(0x20000000)
-#define FILE_GENERIC_WRITE_LE cpu_to_le32(0x40000000)
-#define FILE_GENERIC_READ_LE cpu_to_le32(0x80000000)
-
-/* ShareAccess Flags */
-#define FILE_SHARE_READ_LE cpu_to_le32(0x00000001)
-#define FILE_SHARE_WRITE_LE cpu_to_le32(0x00000002)
-#define FILE_SHARE_DELETE_LE cpu_to_le32(0x00000004)
-#define FILE_SHARE_ALL_LE cpu_to_le32(0x00000007)
-
-/* CreateDisposition Flags */
-#define FILE_SUPERSEDE_LE cpu_to_le32(0x00000000)
-#define FILE_OPEN_LE cpu_to_le32(0x00000001)
-#define FILE_CREATE_LE cpu_to_le32(0x00000002)
-#define FILE_OPEN_IF_LE cpu_to_le32(0x00000003)
-#define FILE_OVERWRITE_LE cpu_to_le32(0x00000004)
-#define FILE_OVERWRITE_IF_LE cpu_to_le32(0x00000005)
-
-/* CreateOptions Flags */
-#define FILE_DIRECTORY_FILE_LE cpu_to_le32(0x00000001)
-/* same as #define CREATE_NOT_FILE_LE cpu_to_le32(0x00000001) */
-#define FILE_WRITE_THROUGH_LE cpu_to_le32(0x00000002)
-#define FILE_SEQUENTIAL_ONLY_LE cpu_to_le32(0x00000004)
-#define FILE_NO_INTERMEDIATE_BUFFERRING_LE cpu_to_le32(0x00000008)
-#define FILE_SYNCHRONOUS_IO_ALERT_LE cpu_to_le32(0x00000010)
-#define FILE_SYNCHRONOUS_IO_NON_ALERT_LE cpu_to_le32(0x00000020)
-#define FILE_NON_DIRECTORY_FILE_LE cpu_to_le32(0x00000040)
-#define FILE_COMPLETE_IF_OPLOCKED_LE cpu_to_le32(0x00000100)
-#define FILE_NO_EA_KNOWLEDGE_LE cpu_to_le32(0x00000200)
-#define FILE_RANDOM_ACCESS_LE cpu_to_le32(0x00000800)
-#define FILE_DELETE_ON_CLOSE_LE cpu_to_le32(0x00001000)
-#define FILE_OPEN_BY_FILE_ID_LE cpu_to_le32(0x00002000)
-#define FILE_OPEN_FOR_BACKUP_INTENT_LE cpu_to_le32(0x00004000)
-#define FILE_NO_COMPRESSION_LE cpu_to_le32(0x00008000)
-#define FILE_RESERVE_OPFILTER_LE cpu_to_le32(0x00100000)
-#define FILE_OPEN_REPARSE_POINT_LE cpu_to_le32(0x00200000)
-#define FILE_OPEN_NO_RECALL_LE cpu_to_le32(0x00400000)
-#define FILE_OPEN_FOR_FREE_SPACE_QUERY_LE cpu_to_le32(0x00800000)
-
-#define FILE_READ_RIGHTS_LE (FILE_READ_DATA_LE | FILE_READ_EA_LE \
- | FILE_READ_ATTRIBUTES_LE)
-#define FILE_WRITE_RIGHTS_LE (FILE_WRITE_DATA_LE | FILE_APPEND_DATA_LE \
- | FILE_WRITE_EA_LE | FILE_WRITE_ATTRIBUTES_LE)
-#define FILE_EXEC_RIGHTS_LE (FILE_EXECUTE_LE)
-
-/* Impersonation Levels. See MS-WPO section 9.7 and MSDN-IMPERS */
-#define IL_ANONYMOUS cpu_to_le32(0x00000000)
-#define IL_IDENTIFICATION cpu_to_le32(0x00000001)
-#define IL_IMPERSONATION cpu_to_le32(0x00000002)
-#define IL_DELEGATE cpu_to_le32(0x00000003)
-
-/* Create Context Values */
-#define SMB2_CREATE_EA_BUFFER "ExtA" /* extended attributes */
-#define SMB2_CREATE_SD_BUFFER "SecD" /* security descriptor */
-#define SMB2_CREATE_DURABLE_HANDLE_REQUEST "DHnQ"
-#define SMB2_CREATE_DURABLE_HANDLE_RECONNECT "DHnC"
-#define SMB2_CREATE_ALLOCATION_SIZE "AISi"
-#define SMB2_CREATE_QUERY_MAXIMAL_ACCESS_REQUEST "MxAc"
-#define SMB2_CREATE_TIMEWARP_REQUEST "TWrp"
-#define SMB2_CREATE_QUERY_ON_DISK_ID "QFid"
-#define SMB2_CREATE_REQUEST_LEASE "RqLs"
-#define SMB2_CREATE_DURABLE_HANDLE_REQUEST_V2 "DH2Q"
-#define SMB2_CREATE_DURABLE_HANDLE_RECONNECT_V2 "DH2C"
-#define SMB2_CREATE_APP_INSTANCE_ID 0x45BCA66AEFA7F74A9008FA462E144D74
-#define SMB2_CREATE_APP_INSTANCE_VERSION 0xB982D0B73B56074FA07B524A8116A010
-#define SVHDX_OPEN_DEVICE_CONTEX 0x9CCBCF9E04C1E643980E158DA1F6EC83
-#define SMB2_CREATE_TAG_POSIX 0x93AD25509CB411E7B42383DE968BCD7C
-
-/* Flag (SMB3 open response) values */
-#define SMB2_CREATE_FLAG_REPARSEPOINT 0x01
-
/*
* Maximum number of iovs we need for an open/create request.
* [0] : struct smb2_create_req
@@ -807,26 +128,6 @@ struct smb2_tree_disconnect_rsp {
*/
#define SMB2_CREATE_IOV_SIZE 8
-struct smb2_create_req {
- struct smb2_sync_hdr sync_hdr;
- __le16 StructureSize; /* Must be 57 */
- __u8 SecurityFlags;
- __u8 RequestedOplockLevel;
- __le32 ImpersonationLevel;
- __le64 SmbCreateFlags;
- __le64 Reserved;
- __le32 DesiredAccess;
- __le32 FileAttributes;
- __le32 ShareAccess;
- __le32 CreateDisposition;
- __le32 CreateOptions;
- __le16 NameOffset;
- __le16 NameLength;
- __le32 CreateContextsOffset;
- __le32 CreateContextsLength;
- __u8 Buffer[];
-} __packed;
-
/*
* Maximum size of a SMB2_CREATE response is 64 (smb2 header) +
* 88 (fixed part of create response) + 520 (path) + 208 (contexts) +
@@ -834,37 +135,6 @@ struct smb2_create_req {
*/
#define MAX_SMB2_CREATE_RESPONSE_SIZE 880
-struct smb2_create_rsp {
- struct smb2_sync_hdr sync_hdr;
- __le16 StructureSize; /* Must be 89 */
- __u8 OplockLevel;
- __u8 Flag; /* 0x01 if reparse point */
- __le32 CreateAction;
- __le64 CreationTime;
- __le64 LastAccessTime;
- __le64 LastWriteTime;
- __le64 ChangeTime;
- __le64 AllocationSize;
- __le64 EndofFile;
- __le32 FileAttributes;
- __le32 Reserved2;
- __u64 PersistentFileId; /* opaque endianness */
- __u64 VolatileFileId; /* opaque endianness */
- __le32 CreateContextsOffset;
- __le32 CreateContextsLength;
- __u8 Buffer[1];
-} __packed;
-
-struct create_context {
- __le32 Next;
- __le16 NameOffset;
- __le16 NameLength;
- __le16 Reserved;
- __le16 DataOffset;
- __le32 DataLength;
- __u8 Buffer[];
-} __packed;
-
#define SMB2_LEASE_READ_CACHING_HE 0x01
#define SMB2_LEASE_HANDLE_CACHING_HE 0x02
#define SMB2_LEASE_WRITE_CACHING_HE 0x04
@@ -1210,7 +480,7 @@ struct duplicate_extents_to_file {
#define SMB2_IOCTL_IOV_SIZE 2
struct smb2_ioctl_req {
- struct smb2_sync_hdr sync_hdr;
+ struct smb2_hdr hdr;
__le16 StructureSize; /* Must be 57 */
__u16 Reserved;
__le32 CtlCode;
@@ -1228,7 +498,7 @@ struct smb2_ioctl_req {
} __packed;
struct smb2_ioctl_rsp {
- struct smb2_sync_hdr sync_hdr;
+ struct smb2_hdr hdr;
__le16 StructureSize; /* Must be 57 */
__u16 Reserved;
__le32 CtlCode;
@@ -1243,161 +513,6 @@ struct smb2_ioctl_rsp {
/* char * buffer[] */
} __packed;
-/* Currently defined values for close flags */
-#define SMB2_CLOSE_FLAG_POSTQUERY_ATTRIB cpu_to_le16(0x0001)
-struct smb2_close_req {
- struct smb2_sync_hdr sync_hdr;
- __le16 StructureSize; /* Must be 24 */
- __le16 Flags;
- __le32 Reserved;
- __u64 PersistentFileId; /* opaque endianness */
- __u64 VolatileFileId; /* opaque endianness */
-} __packed;
-
-/*
- * Maximum size of a SMB2_CLOSE response is 64 (smb2 header) + 60 (data)
- */
-#define MAX_SMB2_CLOSE_RESPONSE_SIZE 124
-
-struct smb2_close_rsp {
- struct smb2_sync_hdr sync_hdr;
- __le16 StructureSize; /* 60 */
- __le16 Flags;
- __le32 Reserved;
- __le64 CreationTime;
- __le64 LastAccessTime;
- __le64 LastWriteTime;
- __le64 ChangeTime;
- __le64 AllocationSize; /* Beginning of FILE_STANDARD_INFO equivalent */
- __le64 EndOfFile;
- __le32 Attributes;
-} __packed;
-
-struct smb2_flush_req {
- struct smb2_sync_hdr sync_hdr;
- __le16 StructureSize; /* Must be 24 */
- __le16 Reserved1;
- __le32 Reserved2;
- __u64 PersistentFileId; /* opaque endianness */
- __u64 VolatileFileId; /* opaque endianness */
-} __packed;
-
-struct smb2_flush_rsp {
- struct smb2_sync_hdr sync_hdr;
- __le16 StructureSize;
- __le16 Reserved;
-} __packed;
-
-/* For read request Flags field below, following flag is defined for SMB3.02 */
-#define SMB2_READFLAG_READ_UNBUFFERED 0x01
-#define SMB2_READFLAG_REQUEST_COMPRESSED 0x02 /* See MS-SMB2 2.2.19 */
-
-/* Channel field for read and write: exactly one of following flags can be set*/
-#define SMB2_CHANNEL_NONE cpu_to_le32(0x00000000)
-#define SMB2_CHANNEL_RDMA_V1 cpu_to_le32(0x00000001) /* SMB3 or later */
-#define SMB2_CHANNEL_RDMA_V1_INVALIDATE cpu_to_le32(0x00000002) /* >= SMB3.02 */
-#define SMB2_CHANNEL_RDMA_TRANSFORM cpu_to_le32(0x00000003) /* >= SMB3.02, only used on write */
-
-/* SMB2 read request without RFC1001 length at the beginning */
-struct smb2_read_plain_req {
- struct smb2_sync_hdr sync_hdr;
- __le16 StructureSize; /* Must be 49 */
- __u8 Padding; /* offset from start of SMB2 header to place read */
- __u8 Flags; /* MBZ unless SMB3.02 or later */
- __le32 Length;
- __le64 Offset;
- __u64 PersistentFileId; /* opaque endianness */
- __u64 VolatileFileId; /* opaque endianness */
- __le32 MinimumCount;
- __le32 Channel; /* MBZ except for SMB3 or later */
- __le32 RemainingBytes;
- __le16 ReadChannelInfoOffset;
- __le16 ReadChannelInfoLength;
- __u8 Buffer[1];
-} __packed;
-
-/* Read flags */
-#define SMB2_READFLAG_RESPONSE_NONE 0x00000000
-#define SMB2_READFLAG_RESPONSE_RDMA_TRANSFORM 0x00000001
-
-struct smb2_read_rsp {
- struct smb2_sync_hdr sync_hdr;
- __le16 StructureSize; /* Must be 17 */
- __u8 DataOffset;
- __u8 Reserved;
- __le32 DataLength;
- __le32 DataRemaining;
- __u32 Flags;
- __u8 Buffer[1];
-} __packed;
-
-/* For write request Flags field below the following flags are defined: */
-#define SMB2_WRITEFLAG_WRITE_THROUGH 0x00000001 /* SMB2.1 or later */
-#define SMB2_WRITEFLAG_WRITE_UNBUFFERED 0x00000002 /* SMB3.02 or later */
-
-struct smb2_write_req {
- struct smb2_sync_hdr sync_hdr;
- __le16 StructureSize; /* Must be 49 */
- __le16 DataOffset; /* offset from start of SMB2 header to write data */
- __le32 Length;
- __le64 Offset;
- __u64 PersistentFileId; /* opaque endianness */
- __u64 VolatileFileId; /* opaque endianness */
- __le32 Channel; /* MBZ unless SMB3.02 or later */
- __le32 RemainingBytes;
- __le16 WriteChannelInfoOffset;
- __le16 WriteChannelInfoLength;
- __le32 Flags;
- __u8 Buffer[1];
-} __packed;
-
-struct smb2_write_rsp {
- struct smb2_sync_hdr sync_hdr;
- __le16 StructureSize; /* Must be 17 */
- __u8 DataOffset;
- __u8 Reserved;
- __le32 DataLength;
- __le32 DataRemaining;
- __u32 Reserved2;
- __u8 Buffer[1];
-} __packed;
-
-/* notify flags */
-#define SMB2_WATCH_TREE 0x0001
-
-/* notify completion filter flags. See MS-FSCC 2.6 and MS-SMB2 2.2.35 */
-#define FILE_NOTIFY_CHANGE_FILE_NAME 0x00000001
-#define FILE_NOTIFY_CHANGE_DIR_NAME 0x00000002
-#define FILE_NOTIFY_CHANGE_ATTRIBUTES 0x00000004
-#define FILE_NOTIFY_CHANGE_SIZE 0x00000008
-#define FILE_NOTIFY_CHANGE_LAST_WRITE 0x00000010
-#define FILE_NOTIFY_CHANGE_LAST_ACCESS 0x00000020
-#define FILE_NOTIFY_CHANGE_CREATION 0x00000040
-#define FILE_NOTIFY_CHANGE_EA 0x00000080
-#define FILE_NOTIFY_CHANGE_SECURITY 0x00000100
-#define FILE_NOTIFY_CHANGE_STREAM_NAME 0x00000200
-#define FILE_NOTIFY_CHANGE_STREAM_SIZE 0x00000400
-#define FILE_NOTIFY_CHANGE_STREAM_WRITE 0x00000800
-
-struct smb2_change_notify_req {
- struct smb2_sync_hdr sync_hdr;
- __le16 StructureSize;
- __le16 Flags;
- __le32 OutputBufferLength;
- __u64 PersistentFileId; /* opaque endianness */
- __u64 VolatileFileId; /* opaque endianness */
- __le32 CompletionFilter;
- __u32 Reserved;
-} __packed;
-
-struct smb2_change_notify_rsp {
- struct smb2_sync_hdr sync_hdr;
- __le16 StructureSize; /* Must be 9 */
- __le16 OutputBufferOffset;
- __le32 OutputBufferLength;
- __u8 Buffer[1]; /* array of file notify structs */
-} __packed;
-
#define SMB2_LOCKFLAG_SHARED_LOCK 0x0001
#define SMB2_LOCKFLAG_EXCLUSIVE_LOCK 0x0002
#define SMB2_LOCKFLAG_UNLOCK 0x0004
@@ -1411,7 +526,7 @@ struct smb2_lock_element {
} __packed;
struct smb2_lock_req {
- struct smb2_sync_hdr sync_hdr;
+ struct smb2_hdr hdr;
__le16 StructureSize; /* Must be 48 */
__le16 LockCount;
/*
@@ -1426,19 +541,19 @@ struct smb2_lock_req {
} __packed;
struct smb2_lock_rsp {
- struct smb2_sync_hdr sync_hdr;
+ struct smb2_hdr hdr;
__le16 StructureSize; /* Must be 4 */
__le16 Reserved;
} __packed;
struct smb2_echo_req {
- struct smb2_sync_hdr sync_hdr;
+ struct smb2_hdr hdr;
__le16 StructureSize; /* Must be 4 */
__u16 Reserved;
} __packed;
struct smb2_echo_rsp {
- struct smb2_sync_hdr sync_hdr;
+ struct smb2_hdr hdr;
__le16 StructureSize; /* Must be 4 */
__u16 Reserved;
} __packed;
@@ -1468,7 +583,7 @@ struct smb2_echo_rsp {
*/
struct smb2_query_directory_req {
- struct smb2_sync_hdr sync_hdr;
+ struct smb2_hdr hdr;
__le16 StructureSize; /* Must be 33 */
__u8 FileInformationClass;
__u8 Flags;
@@ -1482,7 +597,7 @@ struct smb2_query_directory_req {
} __packed;
struct smb2_query_directory_rsp {
- struct smb2_sync_hdr sync_hdr;
+ struct smb2_hdr hdr;
__le16 StructureSize; /* Must be 9 */
__le16 OutputBufferOffset;
__le32 OutputBufferLength;
@@ -1515,7 +630,7 @@ struct smb2_query_directory_rsp {
#define SL_INDEX_SPECIFIED 0x00000004
struct smb2_query_info_req {
- struct smb2_sync_hdr sync_hdr;
+ struct smb2_hdr hdr;
__le16 StructureSize; /* Must be 41 */
__u8 InfoType;
__u8 FileInfoClass;
@@ -1531,7 +646,7 @@ struct smb2_query_info_req {
} __packed;
struct smb2_query_info_rsp {
- struct smb2_sync_hdr sync_hdr;
+ struct smb2_hdr hdr;
__le16 StructureSize; /* Must be 9 */
__le16 OutputBufferOffset;
__le32 OutputBufferLength;
@@ -1548,7 +663,7 @@ struct smb2_query_info_rsp {
#define SMB2_SET_INFO_IOV_SIZE 3
struct smb2_set_info_req {
- struct smb2_sync_hdr sync_hdr;
+ struct smb2_hdr hdr;
__le16 StructureSize; /* Must be 33 */
__u8 InfoType;
__u8 FileInfoClass;
@@ -1562,12 +677,12 @@ struct smb2_set_info_req {
} __packed;
struct smb2_set_info_rsp {
- struct smb2_sync_hdr sync_hdr;
+ struct smb2_hdr hdr;
__le16 StructureSize; /* Must be 2 */
} __packed;
struct smb2_oplock_break {
- struct smb2_sync_hdr sync_hdr;
+ struct smb2_hdr hdr;
__le16 StructureSize; /* Must be 24 */
__u8 OplockLevel;
__u8 Reserved;
@@ -1579,7 +694,7 @@ struct smb2_oplock_break {
#define SMB2_NOTIFY_BREAK_LEASE_FLAG_ACK_REQUIRED cpu_to_le32(0x01)
struct smb2_lease_break {
- struct smb2_sync_hdr sync_hdr;
+ struct smb2_hdr hdr;
__le16 StructureSize; /* Must be 44 */
__le16 Epoch;
__le32 Flags;
@@ -1592,7 +707,7 @@ struct smb2_lease_break {
} __packed;
struct smb2_lease_ack {
- struct smb2_sync_hdr sync_hdr;
+ struct smb2_hdr hdr;
__le16 StructureSize; /* Must be 36 */
__le16 Reserved;
__le32 Flags;
diff --git a/fs/cifs/smb2proto.h b/fs/cifs/smb2proto.h
index 547945443fa7..096fada16ebd 100644
--- a/fs/cifs/smb2proto.h
+++ b/fs/cifs/smb2proto.h
@@ -25,7 +25,7 @@ extern int smb2_check_message(char *buf, unsigned int length,
struct TCP_Server_Info *server);
extern unsigned int smb2_calc_size(void *buf, struct TCP_Server_Info *server);
extern char *smb2_get_data_area_len(int *off, int *len,
- struct smb2_sync_hdr *shdr);
+ struct smb2_hdr *shdr);
extern __le16 *cifs_convert_path_to_utf16(const char *from,
struct cifs_sb_info *cifs_sb);
diff --git a/fs/cifs/smb2transport.c b/fs/cifs/smb2transport.c
index f59b956f9d25..2bf047b390a9 100644
--- a/fs/cifs/smb2transport.c
+++ b/fs/cifs/smb2transport.c
@@ -19,7 +19,6 @@
#include <linux/mempool.h>
#include <linux/highmem.h>
#include <crypto/aead.h>
-#include "smb2pdu.h"
#include "cifsglob.h"
#include "cifsproto.h"
#include "smb2proto.h"
@@ -213,14 +212,14 @@ smb2_calc_signature(struct smb_rqst *rqst, struct TCP_Server_Info *server,
unsigned char smb2_signature[SMB2_HMACSHA256_SIZE];
unsigned char *sigptr = smb2_signature;
struct kvec *iov = rqst->rq_iov;
- struct smb2_sync_hdr *shdr = (struct smb2_sync_hdr *)iov[0].iov_base;
+ struct smb2_hdr *shdr = (struct smb2_hdr *)iov[0].iov_base;
struct cifs_ses *ses;
struct shash_desc *shash;
struct crypto_shash *hash;
struct sdesc *sdesc = NULL;
struct smb_rqst drqst;
- ses = smb2_find_smb_ses(server, shdr->SessionId);
+ ses = smb2_find_smb_ses(server, le64_to_cpu(shdr->SessionId));
if (!ses) {
cifs_server_dbg(VFS, "%s: Could not find session\n", __func__);
return 0;
@@ -534,14 +533,14 @@ smb3_calc_signature(struct smb_rqst *rqst, struct TCP_Server_Info *server,
unsigned char smb3_signature[SMB2_CMACAES_SIZE];
unsigned char *sigptr = smb3_signature;
struct kvec *iov = rqst->rq_iov;
- struct smb2_sync_hdr *shdr = (struct smb2_sync_hdr *)iov[0].iov_base;
+ struct smb2_hdr *shdr = (struct smb2_hdr *)iov[0].iov_base;
struct shash_desc *shash;
struct crypto_shash *hash;
struct sdesc *sdesc = NULL;
struct smb_rqst drqst;
u8 key[SMB3_SIGN_KEY_SIZE];
- rc = smb2_get_sign_key(shdr->SessionId, server, key);
+ rc = smb2_get_sign_key(le64_to_cpu(shdr->SessionId), server, key);
if (rc)
return 0;
@@ -611,12 +610,12 @@ static int
smb2_sign_rqst(struct smb_rqst *rqst, struct TCP_Server_Info *server)
{
int rc = 0;
- struct smb2_sync_hdr *shdr;
+ struct smb2_hdr *shdr;
struct smb2_sess_setup_req *ssr;
bool is_binding;
bool is_signed;
- shdr = (struct smb2_sync_hdr *)rqst->rq_iov[0].iov_base;
+ shdr = (struct smb2_hdr *)rqst->rq_iov[0].iov_base;
ssr = (struct smb2_sess_setup_req *)shdr;
is_binding = shdr->Command == SMB2_SESSION_SETUP &&
@@ -642,8 +641,8 @@ smb2_verify_signature(struct smb_rqst *rqst, struct TCP_Server_Info *server)
{
unsigned int rc;
char server_response_sig[SMB2_SIGNATURE_SIZE];
- struct smb2_sync_hdr *shdr =
- (struct smb2_sync_hdr *)rqst->rq_iov[0].iov_base;
+ struct smb2_hdr *shdr =
+ (struct smb2_hdr *)rqst->rq_iov[0].iov_base;
if ((shdr->Command == SMB2_NEGOTIATE) ||
(shdr->Command == SMB2_SESSION_SETUP) ||
@@ -689,7 +688,7 @@ smb2_verify_signature(struct smb_rqst *rqst, struct TCP_Server_Info *server)
*/
static inline void
smb2_seq_num_into_buf(struct TCP_Server_Info *server,
- struct smb2_sync_hdr *shdr)
+ struct smb2_hdr *shdr)
{
unsigned int i, num = le16_to_cpu(shdr->CreditCharge);
@@ -700,7 +699,7 @@ smb2_seq_num_into_buf(struct TCP_Server_Info *server,
}
static struct mid_q_entry *
-smb2_mid_entry_alloc(const struct smb2_sync_hdr *shdr,
+smb2_mid_entry_alloc(const struct smb2_hdr *shdr,
struct TCP_Server_Info *server)
{
struct mid_q_entry *temp;
@@ -732,14 +731,15 @@ smb2_mid_entry_alloc(const struct smb2_sync_hdr *shdr,
atomic_inc(&midCount);
temp->mid_state = MID_REQUEST_ALLOCATED;
- trace_smb3_cmd_enter(shdr->TreeId, shdr->SessionId,
- le16_to_cpu(shdr->Command), temp->mid);
+ trace_smb3_cmd_enter(le32_to_cpu(shdr->Id.SyncId.TreeId),
+ le64_to_cpu(shdr->SessionId),
+ le16_to_cpu(shdr->Command), temp->mid);
return temp;
}
static int
smb2_get_mid_entry(struct cifs_ses *ses, struct TCP_Server_Info *server,
- struct smb2_sync_hdr *shdr, struct mid_q_entry **mid)
+ struct smb2_hdr *shdr, struct mid_q_entry **mid)
{
if (server->tcpStatus == CifsExiting)
return -ENOENT;
@@ -807,8 +807,8 @@ smb2_setup_request(struct cifs_ses *ses, struct TCP_Server_Info *server,
struct smb_rqst *rqst)
{
int rc;
- struct smb2_sync_hdr *shdr =
- (struct smb2_sync_hdr *)rqst->rq_iov[0].iov_base;
+ struct smb2_hdr *shdr =
+ (struct smb2_hdr *)rqst->rq_iov[0].iov_base;
struct mid_q_entry *mid;
smb2_seq_num_into_buf(server, shdr);
@@ -833,8 +833,8 @@ struct mid_q_entry *
smb2_setup_async_request(struct TCP_Server_Info *server, struct smb_rqst *rqst)
{
int rc;
- struct smb2_sync_hdr *shdr =
- (struct smb2_sync_hdr *)rqst->rq_iov[0].iov_base;
+ struct smb2_hdr *shdr =
+ (struct smb2_hdr *)rqst->rq_iov[0].iov_base;
struct mid_q_entry *mid;
if (server->tcpStatus == CifsNeedNegotiate &&
diff --git a/fs/cifs/trace.h b/fs/cifs/trace.h
index dafcb6ab050d..6cecf302dcfd 100644
--- a/fs/cifs/trace.h
+++ b/fs/cifs/trace.h
@@ -11,6 +11,8 @@
#define _CIFS_TRACE_H
#include <linux/tracepoint.h>
+#include <linux/net.h>
+#include <linux/inet.h>
/*
* Please use this 3-part article as a reference for writing new tracepoints:
@@ -854,6 +856,75 @@ DEFINE_EVENT(smb3_lease_err_class, smb3_##name, \
DEFINE_SMB3_LEASE_ERR_EVENT(lease_err);
+DECLARE_EVENT_CLASS(smb3_connect_class,
+ TP_PROTO(char *hostname,
+ __u64 conn_id,
+ const struct __kernel_sockaddr_storage *dst_addr),
+ TP_ARGS(hostname, conn_id, dst_addr),
+ TP_STRUCT__entry(
+ __string(hostname, hostname)
+ __field(__u64, conn_id)
+ __array(__u8, dst_addr, sizeof(struct sockaddr_storage))
+ ),
+ TP_fast_assign(
+ struct sockaddr_storage *pss = NULL;
+
+ __entry->conn_id = conn_id;
+ pss = (struct sockaddr_storage *)__entry->dst_addr;
+ *pss = *dst_addr;
+ __assign_str(hostname, hostname);
+ ),
+ TP_printk("conn_id=0x%llx server=%s addr=%pISpsfc",
+ __entry->conn_id,
+ __get_str(hostname),
+ __entry->dst_addr)
+)
+
+#define DEFINE_SMB3_CONNECT_EVENT(name) \
+DEFINE_EVENT(smb3_connect_class, smb3_##name, \
+ TP_PROTO(char *hostname, \
+ __u64 conn_id, \
+ const struct __kernel_sockaddr_storage *addr), \
+ TP_ARGS(hostname, conn_id, addr))
+
+DEFINE_SMB3_CONNECT_EVENT(connect_done);
+
+DECLARE_EVENT_CLASS(smb3_connect_err_class,
+ TP_PROTO(char *hostname, __u64 conn_id,
+ const struct __kernel_sockaddr_storage *dst_addr, int rc),
+ TP_ARGS(hostname, conn_id, dst_addr, rc),
+ TP_STRUCT__entry(
+ __string(hostname, hostname)
+ __field(__u64, conn_id)
+ __array(__u8, dst_addr, sizeof(struct sockaddr_storage))
+ __field(int, rc)
+ ),
+ TP_fast_assign(
+ struct sockaddr_storage *pss = NULL;
+
+ __entry->conn_id = conn_id;
+ __entry->rc = rc;
+ pss = (struct sockaddr_storage *)__entry->dst_addr;
+ *pss = *dst_addr;
+ __assign_str(hostname, hostname);
+ ),
+ TP_printk("rc=%d conn_id=0x%llx server=%s addr=%pISpsfc",
+ __entry->rc,
+ __entry->conn_id,
+ __get_str(hostname),
+ __entry->dst_addr)
+)
+
+#define DEFINE_SMB3_CONNECT_ERR_EVENT(name) \
+DEFINE_EVENT(smb3_connect_err_class, smb3_##name, \
+ TP_PROTO(char *hostname, \
+ __u64 conn_id, \
+ const struct __kernel_sockaddr_storage *addr, \
+ int rc), \
+ TP_ARGS(hostname, conn_id, addr, rc))
+
+DEFINE_SMB3_CONNECT_ERR_EVENT(connect_err);
+
DECLARE_EVENT_CLASS(smb3_reconnect_class,
TP_PROTO(__u64 currmid,
__u64 conn_id,
diff --git a/fs/coda/cnode.c b/fs/coda/cnode.c
index 06855f6c7902..62a3d2565c26 100644
--- a/fs/coda/cnode.c
+++ b/fs/coda/cnode.c
@@ -63,9 +63,10 @@ struct inode * coda_iget(struct super_block * sb, struct CodaFid * fid,
struct inode *inode;
struct coda_inode_info *cii;
unsigned long hash = coda_f2i(fid);
+ umode_t inode_type = coda_inode_type(attr);
+retry:
inode = iget5_locked(sb, hash, coda_test_inode, coda_set_inode, fid);
-
if (!inode)
return ERR_PTR(-ENOMEM);
@@ -75,11 +76,15 @@ struct inode * coda_iget(struct super_block * sb, struct CodaFid * fid,
inode->i_ino = hash;
/* inode is locked and unique, no need to grab cii->c_lock */
cii->c_mapcount = 0;
+ coda_fill_inode(inode, attr);
unlock_new_inode(inode);
+ } else if ((inode->i_mode & S_IFMT) != inode_type) {
+ /* Inode has changed type, mark bad and grab a new one */
+ remove_inode_hash(inode);
+ coda_flag_inode(inode, C_PURGE);
+ iput(inode);
+ goto retry;
}
-
- /* always replace the attributes, type might have changed */
- coda_fill_inode(inode, attr);
return inode;
}
diff --git a/fs/coda/coda_linux.c b/fs/coda/coda_linux.c
index 2e1a5a192074..903ca8fa4b9b 100644
--- a/fs/coda/coda_linux.c
+++ b/fs/coda/coda_linux.c
@@ -87,28 +87,27 @@ static struct coda_timespec timespec64_to_coda(struct timespec64 ts64)
}
/* utility functions below */
+umode_t coda_inode_type(struct coda_vattr *attr)
+{
+ switch (attr->va_type) {
+ case C_VREG:
+ return S_IFREG;
+ case C_VDIR:
+ return S_IFDIR;
+ case C_VLNK:
+ return S_IFLNK;
+ case C_VNON:
+ default:
+ return 0;
+ }
+}
+
void coda_vattr_to_iattr(struct inode *inode, struct coda_vattr *attr)
{
- int inode_type;
- /* inode's i_flags, i_ino are set by iget
- XXX: is this all we need ??
- */
- switch (attr->va_type) {
- case C_VNON:
- inode_type = 0;
- break;
- case C_VREG:
- inode_type = S_IFREG;
- break;
- case C_VDIR:
- inode_type = S_IFDIR;
- break;
- case C_VLNK:
- inode_type = S_IFLNK;
- break;
- default:
- inode_type = 0;
- }
+ /* inode's i_flags, i_ino are set by iget
+ * XXX: is this all we need ??
+ */
+ umode_t inode_type = coda_inode_type(attr);
inode->i_mode |= inode_type;
if (attr->va_mode != (u_short) -1)
diff --git a/fs/coda/coda_linux.h b/fs/coda/coda_linux.h
index e7b27754ce78..9be281bbcc06 100644
--- a/fs/coda/coda_linux.h
+++ b/fs/coda/coda_linux.h
@@ -53,10 +53,11 @@ int coda_getattr(struct user_namespace *, const struct path *, struct kstat *,
u32, unsigned int);
int coda_setattr(struct user_namespace *, struct dentry *, struct iattr *);
-/* this file: heloers */
+/* this file: helpers */
char *coda_f2s(struct CodaFid *f);
int coda_iscontrol(const char *name, size_t length);
+umode_t coda_inode_type(struct coda_vattr *attr);
void coda_vattr_to_iattr(struct inode *, struct coda_vattr *);
void coda_iattr_to_vattr(struct iattr *, struct coda_vattr *);
unsigned short coda_flags_to_cflags(unsigned short);
@@ -83,6 +84,9 @@ static __inline__ void coda_flag_inode(struct inode *inode, int flag)
{
struct coda_inode_info *cii = ITOC(inode);
+ if (!inode)
+ return;
+
spin_lock(&cii->c_lock);
cii->c_flags |= flag;
spin_unlock(&cii->c_lock);
diff --git a/fs/coda/dir.c b/fs/coda/dir.c
index d69989c1bac3..328d7a684b63 100644
--- a/fs/coda/dir.c
+++ b/fs/coda/dir.c
@@ -317,13 +317,10 @@ static int coda_rename(struct user_namespace *mnt_userns, struct inode *old_dir,
coda_dir_drop_nlink(old_dir);
coda_dir_inc_nlink(new_dir);
}
- coda_dir_update_mtime(old_dir);
- coda_dir_update_mtime(new_dir);
coda_flag_inode(d_inode(new_dentry), C_VATTR);
- } else {
- coda_flag_inode(old_dir, C_VATTR);
- coda_flag_inode(new_dir, C_VATTR);
}
+ coda_dir_update_mtime(old_dir);
+ coda_dir_update_mtime(new_dir);
}
return error;
}
@@ -499,15 +496,20 @@ out:
*/
static int coda_dentry_delete(const struct dentry * dentry)
{
- int flags;
+ struct inode *inode;
+ struct coda_inode_info *cii;
if (d_really_is_negative(dentry))
return 0;
- flags = (ITOC(d_inode(dentry))->c_flags) & C_PURGE;
- if (is_bad_inode(d_inode(dentry)) || flags) {
+ inode = d_inode(dentry);
+ if (!inode || is_bad_inode(inode))
return 1;
- }
+
+ cii = ITOC(inode);
+ if (cii->c_flags & C_PURGE)
+ return 1;
+
return 0;
}
diff --git a/fs/coda/file.c b/fs/coda/file.c
index ef5ca22bfb3e..29dd87be2fb8 100644
--- a/fs/coda/file.c
+++ b/fs/coda/file.c
@@ -8,6 +8,7 @@
* to the Coda project. Contact Peter Braam <coda@cs.cmu.edu>.
*/
+#include <linux/refcount.h>
#include <linux/types.h>
#include <linux/kernel.h>
#include <linux/time.h>
@@ -28,7 +29,7 @@
#include "coda_int.h"
struct coda_vm_ops {
- atomic_t refcnt;
+ refcount_t refcnt;
struct file *coda_file;
const struct vm_operations_struct *host_vm_ops;
struct vm_operations_struct vm_ops;
@@ -98,7 +99,7 @@ coda_vm_open(struct vm_area_struct *vma)
struct coda_vm_ops *cvm_ops =
container_of(vma->vm_ops, struct coda_vm_ops, vm_ops);
- atomic_inc(&cvm_ops->refcnt);
+ refcount_inc(&cvm_ops->refcnt);
if (cvm_ops->host_vm_ops && cvm_ops->host_vm_ops->open)
cvm_ops->host_vm_ops->open(vma);
@@ -113,7 +114,7 @@ coda_vm_close(struct vm_area_struct *vma)
if (cvm_ops->host_vm_ops && cvm_ops->host_vm_ops->close)
cvm_ops->host_vm_ops->close(vma);
- if (atomic_dec_and_test(&cvm_ops->refcnt)) {
+ if (refcount_dec_and_test(&cvm_ops->refcnt)) {
vma->vm_ops = cvm_ops->host_vm_ops;
fput(cvm_ops->coda_file);
kfree(cvm_ops);
@@ -189,7 +190,7 @@ coda_file_mmap(struct file *coda_file, struct vm_area_struct *vma)
cvm_ops->vm_ops.open = coda_vm_open;
cvm_ops->vm_ops.close = coda_vm_close;
cvm_ops->coda_file = coda_file;
- atomic_set(&cvm_ops->refcnt, 1);
+ refcount_set(&cvm_ops->refcnt, 1);
vma->vm_ops = &cvm_ops->vm_ops;
}
@@ -238,11 +239,10 @@ int coda_release(struct inode *coda_inode, struct file *coda_file)
struct coda_file_info *cfi;
struct coda_inode_info *cii;
struct inode *host_inode;
- int err;
cfi = coda_ftoc(coda_file);
- err = venus_close(coda_inode->i_sb, coda_i2f(coda_inode),
+ venus_close(coda_inode->i_sb, coda_i2f(coda_inode),
coda_flags, coda_file->f_cred->fsuid);
host_inode = file_inode(cfi->cfi_container);
diff --git a/fs/coda/psdev.c b/fs/coda/psdev.c
index 240669f51eac..b39580ad4ce5 100644
--- a/fs/coda/psdev.c
+++ b/fs/coda/psdev.c
@@ -122,14 +122,10 @@ static ssize_t coda_psdev_write(struct file *file, const char __user *buf,
hdr.opcode, hdr.unique);
nbytes = size;
}
- dcbuf = kvmalloc(nbytes, GFP_KERNEL);
- if (!dcbuf) {
- retval = -ENOMEM;
- goto out;
- }
- if (copy_from_user(dcbuf, buf, nbytes)) {
- kvfree(dcbuf);
- retval = -EFAULT;
+
+ dcbuf = vmemdup_user(buf, nbytes);
+ if (IS_ERR(dcbuf)) {
+ retval = PTR_ERR(dcbuf);
goto out;
}
@@ -388,7 +384,7 @@ MODULE_AUTHOR("Jan Harkes, Peter J. Braam");
MODULE_DESCRIPTION("Coda Distributed File System VFS interface");
MODULE_ALIAS_CHARDEV_MAJOR(CODA_PSDEV_MAJOR);
MODULE_LICENSE("GPL");
-MODULE_VERSION("7.0");
+MODULE_VERSION("7.2");
static int __init init_coda(void)
{
diff --git a/fs/coda/upcall.c b/fs/coda/upcall.c
index eb3b1898da46..59f6cfd06f96 100644
--- a/fs/coda/upcall.c
+++ b/fs/coda/upcall.c
@@ -744,7 +744,8 @@ static int coda_upcall(struct venus_comm *vcp,
list_add_tail(&req->uc_chain, &vcp->vc_pending);
wake_up_interruptible(&vcp->vc_waitq);
- if (req->uc_flags & CODA_REQ_ASYNC) {
+ /* We can return early on asynchronous requests */
+ if (outSize == NULL) {
mutex_unlock(&vcp->vc_mutex);
return 0;
}
diff --git a/fs/coredump.c b/fs/coredump.c
index 3224dee44d30..a6b3c196cdef 100644
--- a/fs/coredump.c
+++ b/fs/coredump.c
@@ -359,7 +359,7 @@ static int zap_process(struct task_struct *start, int exit_code, int flags)
for_each_thread(start, t) {
task_clear_jobctl_pending(t, JOBCTL_PENDING_MASK);
- if (t != current && t->mm) {
+ if (t != current && !(t->flags & PF_POSTCOREDUMP)) {
sigaddset(&t->pending.signal, SIGKILL);
signal_wake_up(t, 1);
nr++;
@@ -369,99 +369,34 @@ static int zap_process(struct task_struct *start, int exit_code, int flags)
return nr;
}
-static int zap_threads(struct task_struct *tsk, struct mm_struct *mm,
+static int zap_threads(struct task_struct *tsk,
struct core_state *core_state, int exit_code)
{
- struct task_struct *g, *p;
- unsigned long flags;
int nr = -EAGAIN;
spin_lock_irq(&tsk->sighand->siglock);
if (!signal_group_exit(tsk->signal)) {
- mm->core_state = core_state;
+ tsk->signal->core_state = core_state;
tsk->signal->group_exit_task = tsk;
nr = zap_process(tsk, exit_code, 0);
clear_tsk_thread_flag(tsk, TIF_SIGPENDING);
+ tsk->flags |= PF_DUMPCORE;
+ atomic_set(&core_state->nr_threads, nr);
}
spin_unlock_irq(&tsk->sighand->siglock);
- if (unlikely(nr < 0))
- return nr;
-
- tsk->flags |= PF_DUMPCORE;
- if (atomic_read(&mm->mm_users) == nr + 1)
- goto done;
- /*
- * We should find and kill all tasks which use this mm, and we should
- * count them correctly into ->nr_threads. We don't take tasklist
- * lock, but this is safe wrt:
- *
- * fork:
- * None of sub-threads can fork after zap_process(leader). All
- * processes which were created before this point should be
- * visible to zap_threads() because copy_process() adds the new
- * process to the tail of init_task.tasks list, and lock/unlock
- * of ->siglock provides a memory barrier.
- *
- * do_exit:
- * The caller holds mm->mmap_lock. This means that the task which
- * uses this mm can't pass exit_mm(), so it can't exit or clear
- * its ->mm.
- *
- * de_thread:
- * It does list_replace_rcu(&leader->tasks, &current->tasks),
- * we must see either old or new leader, this does not matter.
- * However, it can change p->sighand, so lock_task_sighand(p)
- * must be used. Since p->mm != NULL and we hold ->mmap_lock
- * it can't fail.
- *
- * Note also that "g" can be the old leader with ->mm == NULL
- * and already unhashed and thus removed from ->thread_group.
- * This is OK, __unhash_process()->list_del_rcu() does not
- * clear the ->next pointer, we will find the new leader via
- * next_thread().
- */
- rcu_read_lock();
- for_each_process(g) {
- if (g == tsk->group_leader)
- continue;
- if (g->flags & PF_KTHREAD)
- continue;
-
- for_each_thread(g, p) {
- if (unlikely(!p->mm))
- continue;
- if (unlikely(p->mm == mm)) {
- lock_task_sighand(p, &flags);
- nr += zap_process(p, exit_code,
- SIGNAL_GROUP_EXIT);
- unlock_task_sighand(p, &flags);
- }
- break;
- }
- }
- rcu_read_unlock();
-done:
- atomic_set(&core_state->nr_threads, nr);
return nr;
}
static int coredump_wait(int exit_code, struct core_state *core_state)
{
struct task_struct *tsk = current;
- struct mm_struct *mm = tsk->mm;
int core_waiters = -EBUSY;
init_completion(&core_state->startup);
core_state->dumper.task = tsk;
core_state->dumper.next = NULL;
- if (mmap_write_lock_killable(mm))
- return -EINTR;
-
- if (!mm->core_state)
- core_waiters = zap_threads(tsk, mm, core_state, exit_code);
- mmap_write_unlock(mm);
-
+ core_waiters = zap_threads(tsk, core_state, exit_code);
if (core_waiters > 0) {
struct core_thread *ptr;
@@ -483,7 +418,7 @@ static int coredump_wait(int exit_code, struct core_state *core_state)
return core_waiters;
}
-static void coredump_finish(struct mm_struct *mm, bool core_dumped)
+static void coredump_finish(bool core_dumped)
{
struct core_thread *curr, *next;
struct task_struct *task;
@@ -493,22 +428,21 @@ static void coredump_finish(struct mm_struct *mm, bool core_dumped)
current->signal->group_exit_code |= 0x80;
current->signal->group_exit_task = NULL;
current->signal->flags = SIGNAL_GROUP_EXIT;
+ next = current->signal->core_state->dumper.next;
+ current->signal->core_state = NULL;
spin_unlock_irq(&current->sighand->siglock);
- next = mm->core_state->dumper.next;
while ((curr = next) != NULL) {
next = curr->next;
task = curr->task;
/*
- * see exit_mm(), curr->task must not see
+ * see coredump_task_exit(), curr->task must not see
* ->task == NULL before we read ->next.
*/
smp_mb();
curr->task = NULL;
wake_up_process(task);
}
-
- mm->core_state = NULL;
}
static bool dump_interrupted(void)
@@ -839,7 +773,7 @@ fail_dropcount:
fail_unlock:
kfree(argv);
kfree(cn.corename);
- coredump_finish(mm, core_dumped);
+ coredump_finish(core_dumped);
revert_creds(old_cred);
fail_creds:
put_cred(cred);
diff --git a/fs/d_path.c b/fs/d_path.c
index cd60c7535181..e4e0ebad1f15 100644
--- a/fs/d_path.c
+++ b/fs/d_path.c
@@ -77,9 +77,8 @@ static bool prepend(struct prepend_buffer *p, const char *str, int namelen)
/**
* prepend_name - prepend a pathname in front of current buffer pointer
- * @buffer: buffer pointer
- * @buflen: allocated length of the buffer
- * @name: name string and length qstr structure
+ * @p: prepend buffer which contains buffer pointer and allocated length
+ * @name: name string and length qstr structure
*
* With RCU path tracing, it may race with d_move(). Use READ_ONCE() to
* make sure that either the old or the new name pointer and length are
@@ -141,8 +140,7 @@ static int __prepend_path(const struct dentry *dentry, const struct mount *mnt,
* prepend_path - Prepend path string to a buffer
* @path: the dentry/vfsmount to report
* @root: root vfsmnt/dentry
- * @buffer: pointer to the end of the buffer
- * @buflen: pointer to buffer length
+ * @p: prepend buffer which contains buffer pointer and allocated length
*
* The function will first try to write out the pathname without taking any
* lock other than the RCU read lock to make sure that dentries won't go away.
diff --git a/fs/exec.c b/fs/exec.c
index a098c133d8d7..537d92c41105 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -987,16 +987,14 @@ static int exec_mmap(struct mm_struct *mm)
if (old_mm) {
/*
- * Make sure that if there is a core dump in progress
- * for the old mm, we get out and die instead of going
- * through with the exec. We must hold mmap_lock around
- * checking core_state and changing tsk->mm.
+ * If there is a pending fatal signal perhaps a signal
+ * whose default action is to create a coredump get
+ * out and die instead of going through with the exec.
*/
- mmap_read_lock(old_mm);
- if (unlikely(old_mm->core_state)) {
- mmap_read_unlock(old_mm);
+ ret = mmap_read_lock_killable(old_mm);
+ if (ret) {
up_write(&tsk->signal->exec_update_lock);
- return -EINTR;
+ return ret;
}
}
@@ -1852,7 +1850,7 @@ out:
* SIGSEGV.
*/
if (bprm->point_of_no_return && !fatal_signal_pending(current))
- force_sigsegv(SIGSEGV);
+ force_fatal_sig(SIGSEGV);
out_unmark:
current->fs->in_exec = 0;
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 79b6a0c47f6f..a320c54202d9 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -46,6 +46,7 @@
#include <linux/part_stat.h>
#include <linux/kthread.h>
#include <linux/freezer.h>
+#include <linux/fsnotify.h>
#include "ext4.h"
#include "ext4_extents.h" /* Needed for trace points definition */
@@ -759,6 +760,8 @@ void __ext4_error(struct super_block *sb, const char *function,
sb->s_id, function, line, current->comm, &vaf);
va_end(args);
}
+ fsnotify_sb_error(sb, NULL, error ? error : EFSCORRUPTED);
+
ext4_handle_error(sb, force_ro, error, 0, block, function, line);
}
@@ -789,6 +792,8 @@ void __ext4_error_inode(struct inode *inode, const char *function,
current->comm, &vaf);
va_end(args);
}
+ fsnotify_sb_error(inode->i_sb, inode, error ? error : EFSCORRUPTED);
+
ext4_handle_error(inode->i_sb, false, error, inode->i_ino, block,
function, line);
}
@@ -827,6 +832,8 @@ void __ext4_error_file(struct file *file, const char *function,
current->comm, path, &vaf);
va_end(args);
}
+ fsnotify_sb_error(inode->i_sb, inode, EFSCORRUPTED);
+
ext4_handle_error(inode->i_sb, false, EFSCORRUPTED, inode->i_ino, block,
function, line);
}
@@ -894,6 +901,7 @@ void __ext4_std_error(struct super_block *sb, const char *function,
printk(KERN_CRIT "EXT4-fs error (device %s) in %s:%d: %s\n",
sb->s_id, function, line, errstr);
}
+ fsnotify_sb_error(sb, NULL, errno ? errno : EFSCORRUPTED);
ext4_handle_error(sb, false, -errno, 0, 0, function, line);
}
diff --git a/fs/fuse/dax.c b/fs/fuse/dax.c
index 281d79f8b3d3..713818d74de6 100644
--- a/fs/fuse/dax.c
+++ b/fs/fuse/dax.c
@@ -732,11 +732,8 @@ static ssize_t fuse_dax_direct_write(struct kiocb *iocb, struct iov_iter *from)
ssize_t ret;
ret = fuse_direct_io(&io, from, &iocb->ki_pos, FUSE_DIO_WRITE);
- if (ret < 0)
- return ret;
- fuse_invalidate_attr(inode);
- fuse_write_update_size(inode, iocb->ki_pos);
+ fuse_write_update_attr(inode, iocb->ki_pos, ret);
return ret;
}
diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c
index dde341a6388a..79f7eda49e06 100644
--- a/fs/fuse/dev.c
+++ b/fs/fuse/dev.c
@@ -756,7 +756,7 @@ static int fuse_copy_do(struct fuse_copy_state *cs, void **val, unsigned *size)
{
unsigned ncpy = min(*size, cs->len);
if (val) {
- void *pgaddr = kmap_atomic(cs->pg);
+ void *pgaddr = kmap_local_page(cs->pg);
void *buf = pgaddr + cs->offset;
if (cs->write)
@@ -764,7 +764,7 @@ static int fuse_copy_do(struct fuse_copy_state *cs, void **val, unsigned *size)
else
memcpy(*val, buf, ncpy);
- kunmap_atomic(pgaddr);
+ kunmap_local(pgaddr);
*val += ncpy;
}
*size -= ncpy;
@@ -847,6 +847,12 @@ static int fuse_try_move_page(struct fuse_copy_state *cs, struct page **pagep)
replace_page_cache_page(oldpage, newpage);
+ /*
+ * Release while we have extra ref on stolen page. Otherwise
+ * anon_pipe_buf_release() might think the page can be reused.
+ */
+ pipe_buf_release(cs->pipe, buf);
+
get_page(newpage);
if (!(buf->flags & PIPE_BUF_FLAG_LRU))
@@ -949,10 +955,10 @@ static int fuse_copy_page(struct fuse_copy_state *cs, struct page **pagep,
}
}
if (page) {
- void *mapaddr = kmap_atomic(page);
+ void *mapaddr = kmap_local_page(page);
void *buf = mapaddr + offset;
offset += fuse_copy_do(cs, &buf, &count);
- kunmap_atomic(mapaddr);
+ kunmap_local(mapaddr);
} else
offset += fuse_copy_do(cs, NULL, &count);
}
@@ -1591,7 +1597,7 @@ static int fuse_notify_store(struct fuse_conn *fc, unsigned int size,
end = outarg.offset + outarg.size;
if (end > file_size) {
file_size = end;
- fuse_write_update_size(inode, file_size);
+ fuse_write_update_attr(inode, file_size, outarg.size);
}
num = outarg.size;
@@ -2031,8 +2037,12 @@ static ssize_t fuse_dev_splice_write(struct pipe_inode_info *pipe,
pipe_lock(pipe);
out_free:
- for (idx = 0; idx < nbuf; idx++)
- pipe_buf_release(pipe, &bufs[idx]);
+ for (idx = 0; idx < nbuf; idx++) {
+ struct pipe_buffer *buf = &bufs[idx];
+
+ if (buf->ops)
+ pipe_buf_release(pipe, buf);
+ }
pipe_unlock(pipe);
kvfree(bufs);
diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c
index d9b977c0f38d..0654bfedcbb0 100644
--- a/fs/fuse/dir.c
+++ b/fs/fuse/dir.c
@@ -116,7 +116,7 @@ u64 entry_attr_timeout(struct fuse_entry_out *o)
return time_to_jiffies(o->attr_valid, o->attr_valid_nsec);
}
-static void fuse_invalidate_attr_mask(struct inode *inode, u32 mask)
+void fuse_invalidate_attr_mask(struct inode *inode, u32 mask)
{
set_mask_bits(&get_fuse_inode(inode)->inval_mask, 0, mask);
}
@@ -738,14 +738,51 @@ static int fuse_symlink(struct user_namespace *mnt_userns, struct inode *dir,
return create_new_entry(fm, &args, dir, entry, S_IFLNK);
}
-void fuse_update_ctime(struct inode *inode)
+void fuse_flush_time_update(struct inode *inode)
+{
+ int err = sync_inode_metadata(inode, 1);
+
+ mapping_set_error(inode->i_mapping, err);
+}
+
+static void fuse_update_ctime_in_cache(struct inode *inode)
{
if (!IS_NOCMTIME(inode)) {
inode->i_ctime = current_time(inode);
mark_inode_dirty_sync(inode);
+ fuse_flush_time_update(inode);
}
}
+void fuse_update_ctime(struct inode *inode)
+{
+ fuse_invalidate_attr_mask(inode, STATX_CTIME);
+ fuse_update_ctime_in_cache(inode);
+}
+
+static void fuse_entry_unlinked(struct dentry *entry)
+{
+ struct inode *inode = d_inode(entry);
+ struct fuse_conn *fc = get_fuse_conn(inode);
+ struct fuse_inode *fi = get_fuse_inode(inode);
+
+ spin_lock(&fi->lock);
+ fi->attr_version = atomic64_inc_return(&fc->attr_version);
+ /*
+ * If i_nlink == 0 then unlink doesn't make sense, yet this can
+ * happen if userspace filesystem is careless. It would be
+ * difficult to enforce correct nlink usage so just ignore this
+ * condition here
+ */
+ if (S_ISDIR(inode->i_mode))
+ clear_nlink(inode);
+ else if (inode->i_nlink > 0)
+ drop_nlink(inode);
+ spin_unlock(&fi->lock);
+ fuse_invalidate_entry_cache(entry);
+ fuse_update_ctime(inode);
+}
+
static int fuse_unlink(struct inode *dir, struct dentry *entry)
{
int err;
@@ -762,24 +799,8 @@ static int fuse_unlink(struct inode *dir, struct dentry *entry)
args.in_args[0].value = entry->d_name.name;
err = fuse_simple_request(fm, &args);
if (!err) {
- struct inode *inode = d_inode(entry);
- struct fuse_inode *fi = get_fuse_inode(inode);
-
- spin_lock(&fi->lock);
- fi->attr_version = atomic64_inc_return(&fm->fc->attr_version);
- /*
- * If i_nlink == 0 then unlink doesn't make sense, yet this can
- * happen if userspace filesystem is careless. It would be
- * difficult to enforce correct nlink usage so just ignore this
- * condition here
- */
- if (inode->i_nlink > 0)
- drop_nlink(inode);
- spin_unlock(&fi->lock);
- fuse_invalidate_attr(inode);
fuse_dir_changed(dir);
- fuse_invalidate_entry_cache(entry);
- fuse_update_ctime(inode);
+ fuse_entry_unlinked(entry);
} else if (err == -EINTR)
fuse_invalidate_entry(entry);
return err;
@@ -801,9 +822,8 @@ static int fuse_rmdir(struct inode *dir, struct dentry *entry)
args.in_args[0].value = entry->d_name.name;
err = fuse_simple_request(fm, &args);
if (!err) {
- clear_nlink(d_inode(entry));
fuse_dir_changed(dir);
- fuse_invalidate_entry_cache(entry);
+ fuse_entry_unlinked(entry);
} else if (err == -EINTR)
fuse_invalidate_entry(entry);
return err;
@@ -833,24 +853,18 @@ static int fuse_rename_common(struct inode *olddir, struct dentry *oldent,
err = fuse_simple_request(fm, &args);
if (!err) {
/* ctime changes */
- fuse_invalidate_attr(d_inode(oldent));
fuse_update_ctime(d_inode(oldent));
- if (flags & RENAME_EXCHANGE) {
- fuse_invalidate_attr(d_inode(newent));
+ if (flags & RENAME_EXCHANGE)
fuse_update_ctime(d_inode(newent));
- }
fuse_dir_changed(olddir);
if (olddir != newdir)
fuse_dir_changed(newdir);
/* newent will end up negative */
- if (!(flags & RENAME_EXCHANGE) && d_really_is_positive(newent)) {
- fuse_invalidate_attr(d_inode(newent));
- fuse_invalidate_entry_cache(newent);
- fuse_update_ctime(d_inode(newent));
- }
+ if (!(flags & RENAME_EXCHANGE) && d_really_is_positive(newent))
+ fuse_entry_unlinked(newent);
} else if (err == -EINTR) {
/* If request was interrupted, DEITY only knows if the
rename actually took place. If the invalidation
@@ -916,25 +930,11 @@ static int fuse_link(struct dentry *entry, struct inode *newdir,
args.in_args[1].size = newent->d_name.len + 1;
args.in_args[1].value = newent->d_name.name;
err = create_new_entry(fm, &args, newdir, newent, inode->i_mode);
- /* Contrary to "normal" filesystems it can happen that link
- makes two "logical" inodes point to the same "physical"
- inode. We invalidate the attributes of the old one, so it
- will reflect changes in the backing inode (link count,
- etc.)
- */
- if (!err) {
- struct fuse_inode *fi = get_fuse_inode(inode);
-
- spin_lock(&fi->lock);
- fi->attr_version = atomic64_inc_return(&fm->fc->attr_version);
- if (likely(inode->i_nlink < UINT_MAX))
- inc_nlink(inode);
- spin_unlock(&fi->lock);
- fuse_invalidate_attr(inode);
- fuse_update_ctime(inode);
- } else if (err == -EINTR) {
+ if (!err)
+ fuse_update_ctime_in_cache(inode);
+ else if (err == -EINTR)
fuse_invalidate_attr(inode);
- }
+
return err;
}
@@ -944,15 +944,6 @@ static void fuse_fillattr(struct inode *inode, struct fuse_attr *attr,
unsigned int blkbits;
struct fuse_conn *fc = get_fuse_conn(inode);
- /* see the comment in fuse_change_attributes() */
- if (fc->writeback_cache && S_ISREG(inode->i_mode)) {
- attr->size = i_size_read(inode);
- attr->mtime = inode->i_mtime.tv_sec;
- attr->mtimensec = inode->i_mtime.tv_nsec;
- attr->ctime = inode->i_ctime.tv_sec;
- attr->ctimensec = inode->i_ctime.tv_nsec;
- }
-
stat->dev = inode->i_sb->s_dev;
stat->ino = attr->ino;
stat->mode = (inode->i_mode & S_IFMT) | (attr->mode & 07777);
@@ -1030,12 +1021,14 @@ static int fuse_update_get_attr(struct inode *inode, struct file *file,
struct fuse_inode *fi = get_fuse_inode(inode);
int err = 0;
bool sync;
+ u32 inval_mask = READ_ONCE(fi->inval_mask);
+ u32 cache_mask = fuse_get_cache_mask(inode);
if (flags & AT_STATX_FORCE_SYNC)
sync = true;
else if (flags & AT_STATX_DONT_SYNC)
sync = false;
- else if (request_mask & READ_ONCE(fi->inval_mask))
+ else if (request_mask & inval_mask & ~cache_mask)
sync = true;
else
sync = time_before64(fi->i_time, get_jiffies_64());
@@ -1052,11 +1045,9 @@ static int fuse_update_get_attr(struct inode *inode, struct file *file,
return err;
}
-int fuse_update_attributes(struct inode *inode, struct file *file)
+int fuse_update_attributes(struct inode *inode, struct file *file, u32 mask)
{
- /* Do *not* need to get atime for internal purposes */
- return fuse_update_get_attr(inode, file, NULL,
- STATX_BASIC_STATS & ~STATX_ATIME, 0);
+ return fuse_update_get_attr(inode, file, NULL, mask, 0);
}
int fuse_reverse_inval_entry(struct fuse_conn *fc, u64 parent_nodeid,
@@ -1071,7 +1062,7 @@ int fuse_reverse_inval_entry(struct fuse_conn *fc, u64 parent_nodeid,
if (!parent)
return -ENOENT;
- inode_lock(parent);
+ inode_lock_nested(parent, I_MUTEX_PARENT);
if (!S_ISDIR(parent->i_mode))
goto unlock;
@@ -1561,10 +1552,10 @@ int fuse_do_setattr(struct dentry *dentry, struct iattr *attr,
struct fuse_setattr_in inarg;
struct fuse_attr_out outarg;
bool is_truncate = false;
- bool is_wb = fc->writeback_cache;
+ bool is_wb = fc->writeback_cache && S_ISREG(inode->i_mode);
loff_t oldsize;
int err;
- bool trust_local_cmtime = is_wb && S_ISREG(inode->i_mode);
+ bool trust_local_cmtime = is_wb;
bool fault_blocked = false;
if (!fc->default_permissions)
@@ -1608,7 +1599,7 @@ int fuse_do_setattr(struct dentry *dentry, struct iattr *attr,
}
/* Flush dirty data/metadata before non-truncate SETATTR */
- if (is_wb && S_ISREG(inode->i_mode) &&
+ if (is_wb &&
attr->ia_valid &
(ATTR_MODE | ATTR_UID | ATTR_GID | ATTR_MTIME_SET |
ATTR_TIMES_SET)) {
@@ -1676,10 +1667,11 @@ int fuse_do_setattr(struct dentry *dentry, struct iattr *attr,
}
fuse_change_attributes_common(inode, &outarg.attr,
- attr_timeout(&outarg));
+ attr_timeout(&outarg),
+ fuse_get_cache_mask(inode));
oldsize = inode->i_size;
/* see the comment in fuse_change_attributes() */
- if (!is_wb || is_truncate || !S_ISREG(inode->i_mode))
+ if (!is_wb || is_truncate)
i_size_write(inode, outarg.attr.size);
if (is_truncate) {
diff --git a/fs/fuse/file.c b/fs/fuse/file.c
index 34b6d0650e66..9d6c5f6361f7 100644
--- a/fs/fuse/file.c
+++ b/fs/fuse/file.c
@@ -211,9 +211,8 @@ void fuse_finish_open(struct inode *inode, struct file *file)
i_size_write(inode, 0);
spin_unlock(&fi->lock);
truncate_pagecache(inode, 0);
- fuse_invalidate_attr(inode);
- if (fc->writeback_cache)
- file_update_time(file);
+ file_update_time(file);
+ fuse_invalidate_attr_mask(inode, FUSE_STATX_MODSIZE);
} else if (!(ff->open_flags & FOPEN_KEEP_CACHE)) {
invalidate_inode_pages2(inode->i_mapping);
}
@@ -339,12 +338,6 @@ static int fuse_open(struct inode *inode, struct file *file)
static int fuse_release(struct inode *inode, struct file *file)
{
- struct fuse_conn *fc = get_fuse_conn(inode);
-
- /* see fuse_vma_close() for !writeback_cache case */
- if (fc->writeback_cache)
- write_inode_now(inode, 1);
-
fuse_release_common(file, false);
/* return value is ignored by VFS */
@@ -483,6 +476,9 @@ static int fuse_flush(struct file *file, fl_owner_t id)
if (fuse_is_bad(inode))
return -EIO;
+ if (ff->open_flags & FOPEN_NOFLUSH && !fm->fc->writeback_cache)
+ return 0;
+
err = write_inode_now(inode, 1);
if (err)
return err;
@@ -521,7 +517,7 @@ inval_attr_out:
* enabled, i_blocks from cached attr may not be accurate.
*/
if (!err && fm->fc->writeback_cache)
- fuse_invalidate_attr(inode);
+ fuse_invalidate_attr_mask(inode, STATX_BLOCKS);
return err;
}
@@ -793,7 +789,7 @@ static void fuse_read_update_size(struct inode *inode, loff_t size,
struct fuse_inode *fi = get_fuse_inode(inode);
spin_lock(&fi->lock);
- if (attr_ver == fi->attr_version && size < inode->i_size &&
+ if (attr_ver >= fi->attr_version && size < inode->i_size &&
!test_bit(FUSE_I_SIZE_UNSTABLE, &fi->state)) {
fi->attr_version = atomic64_inc_return(&fc->attr_version);
i_size_write(inode, size);
@@ -1003,7 +999,7 @@ static ssize_t fuse_cache_read_iter(struct kiocb *iocb, struct iov_iter *to)
if (fc->auto_inval_data ||
(iocb->ki_pos + iov_iter_count(to) > i_size_read(inode))) {
int err;
- err = fuse_update_attributes(inode, iocb->ki_filp);
+ err = fuse_update_attributes(inode, iocb->ki_filp, STATX_SIZE);
if (err)
return err;
}
@@ -1072,7 +1068,7 @@ static ssize_t fuse_send_write(struct fuse_io_args *ia, loff_t pos,
return err ?: ia->write.out.size;
}
-bool fuse_write_update_size(struct inode *inode, loff_t pos)
+bool fuse_write_update_attr(struct inode *inode, loff_t pos, ssize_t written)
{
struct fuse_conn *fc = get_fuse_conn(inode);
struct fuse_inode *fi = get_fuse_inode(inode);
@@ -1080,12 +1076,14 @@ bool fuse_write_update_size(struct inode *inode, loff_t pos)
spin_lock(&fi->lock);
fi->attr_version = atomic64_inc_return(&fc->attr_version);
- if (pos > inode->i_size) {
+ if (written > 0 && pos > inode->i_size) {
i_size_write(inode, pos);
ret = true;
}
spin_unlock(&fi->lock);
+ fuse_invalidate_attr_mask(inode, FUSE_STATX_MODSIZE);
+
return ret;
}
@@ -1268,11 +1266,8 @@ static ssize_t fuse_perform_write(struct kiocb *iocb,
kfree(ap->pages);
} while (!err && iov_iter_count(ii));
- if (res > 0)
- fuse_write_update_size(inode, pos);
-
+ fuse_write_update_attr(inode, pos, res);
clear_bit(FUSE_I_SIZE_UNSTABLE, &fi->state);
- fuse_invalidate_attr(inode);
return res > 0 ? res : err;
}
@@ -1290,7 +1285,8 @@ static ssize_t fuse_cache_write_iter(struct kiocb *iocb, struct iov_iter *from)
if (fc->writeback_cache) {
/* Update size (EOF optimization) and mode (SUID clearing) */
- err = fuse_update_attributes(mapping->host, file);
+ err = fuse_update_attributes(mapping->host, file,
+ STATX_SIZE | STATX_MODE);
if (err)
return err;
@@ -1451,7 +1447,6 @@ ssize_t fuse_direct_io(struct fuse_io_priv *io, struct iov_iter *iter,
if (!ia)
return -ENOMEM;
- ia->io = io;
if (!cuse && fuse_range_is_writeback(inode, idx_from, idx_to)) {
if (!write)
inode_lock(inode);
@@ -1561,11 +1556,9 @@ static ssize_t fuse_direct_write_iter(struct kiocb *iocb, struct iov_iter *from)
} else {
res = fuse_direct_io(&io, from, &iocb->ki_pos,
FUSE_DIO_WRITE);
+ fuse_write_update_attr(inode, iocb->ki_pos, res);
}
}
- fuse_invalidate_attr(inode);
- if (res > 0)
- fuse_write_update_size(inode, iocb->ki_pos);
inode_unlock(inode);
return res;
@@ -1776,7 +1769,7 @@ static void fuse_writepage_end(struct fuse_mount *fm, struct fuse_args *args,
* is enabled, we trust local ctime/mtime.
*/
if (!fc->writeback_cache)
- fuse_invalidate_attr(inode);
+ fuse_invalidate_attr_mask(inode, FUSE_STATX_MODIFY);
spin_lock(&fi->lock);
rb_erase(&wpa->writepages_entry, &fi->writepages);
while (wpa->next) {
@@ -1822,14 +1815,13 @@ static void fuse_writepage_end(struct fuse_mount *fm, struct fuse_args *args,
static struct fuse_file *__fuse_write_file_get(struct fuse_inode *fi)
{
- struct fuse_file *ff = NULL;
+ struct fuse_file *ff;
spin_lock(&fi->lock);
- if (!list_empty(&fi->write_files)) {
- ff = list_entry(fi->write_files.next, struct fuse_file,
- write_entry);
+ ff = list_first_entry_or_null(&fi->write_files, struct fuse_file,
+ write_entry);
+ if (ff)
fuse_file_get(ff);
- }
spin_unlock(&fi->lock);
return ff;
@@ -1848,6 +1840,17 @@ int fuse_write_inode(struct inode *inode, struct writeback_control *wbc)
struct fuse_file *ff;
int err;
+ /*
+ * Inode is always written before the last reference is dropped and
+ * hence this should not be reached from reclaim.
+ *
+ * Writing back the inode from reclaim can deadlock if the request
+ * processing itself needs an allocation. Allocations triggering
+ * reclaim while serving a request can't be prevented, because it can
+ * involve any number of unrelated userspace processes.
+ */
+ WARN_ON(wbc->for_reclaim);
+
ff = __fuse_write_file_get(fi);
err = fuse_flush_times(inode, ff);
if (ff)
@@ -2306,15 +2309,18 @@ static int fuse_write_end(struct file *file, struct address_space *mapping,
if (!copied)
goto unlock;
+ pos += copied;
if (!PageUptodate(page)) {
/* Zero any unwritten bytes at the end of the page */
- size_t endoff = (pos + copied) & ~PAGE_MASK;
+ size_t endoff = pos & ~PAGE_MASK;
if (endoff)
zero_user_segment(page, endoff, PAGE_SIZE);
SetPageUptodate(page);
}
- fuse_write_update_size(inode, pos + copied);
+ if (pos > inode->i_size)
+ i_size_write(inode, pos);
+
set_page_dirty(page);
unlock:
@@ -2340,12 +2346,15 @@ static int fuse_launder_page(struct page *page)
}
/*
- * Write back dirty pages now, because there may not be any suitable
- * open files later
+ * Write back dirty data/metadata now (there may not be any suitable
+ * open files later for data)
*/
static void fuse_vma_close(struct vm_area_struct *vma)
{
- filemap_write_and_wait(vma->vm_file->f_mapping);
+ int err;
+
+ err = write_inode_now(vma->vm_file->f_mapping->host, 1);
+ mapping_set_error(vma->vm_file->f_mapping, err);
}
/*
@@ -2628,7 +2637,7 @@ static loff_t fuse_lseek(struct file *file, loff_t offset, int whence)
return vfs_setpos(file, outarg.offset, inode->i_sb->s_maxbytes);
fallback:
- err = fuse_update_attributes(inode, file);
+ err = fuse_update_attributes(inode, file, STATX_SIZE);
if (!err)
return generic_file_llseek(file, offset, whence);
else
@@ -2648,7 +2657,7 @@ static loff_t fuse_file_llseek(struct file *file, loff_t offset, int whence)
break;
case SEEK_END:
inode_lock(inode);
- retval = fuse_update_attributes(inode, file);
+ retval = fuse_update_attributes(inode, file, STATX_SIZE);
if (!retval)
retval = generic_file_llseek(file, offset, whence);
inode_unlock(inode);
@@ -2869,7 +2878,7 @@ fuse_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
if (iov_iter_rw(iter) == WRITE) {
ret = fuse_direct_io(io, iter, &pos, FUSE_DIO_WRITE);
- fuse_invalidate_attr(inode);
+ fuse_invalidate_attr_mask(inode, FUSE_STATX_MODSIZE);
} else {
ret = __fuse_direct_read(io, iter, &pos);
}
@@ -2891,9 +2900,8 @@ fuse_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
kref_put(&io->refcnt, fuse_io_release);
if (iov_iter_rw(iter) == WRITE) {
- if (ret > 0)
- fuse_write_update_size(inode, pos);
- else if (ret < 0 && offset + count > i_size)
+ fuse_write_update_attr(inode, pos, ret);
+ if (ret < 0 && offset + count > i_size)
fuse_do_truncate(file);
}
@@ -2981,16 +2989,14 @@ static long fuse_file_fallocate(struct file *file, int mode, loff_t offset,
/* we could have extended the file */
if (!(mode & FALLOC_FL_KEEP_SIZE)) {
- bool changed = fuse_write_update_size(inode, offset + length);
-
- if (changed && fm->fc->writeback_cache)
+ if (fuse_write_update_attr(inode, offset + length, length))
file_update_time(file);
}
if (mode & (FALLOC_FL_PUNCH_HOLE | FALLOC_FL_ZERO_RANGE))
truncate_pagecache_range(inode, offset, offset + length - 1);
- fuse_invalidate_attr(inode);
+ fuse_invalidate_attr_mask(inode, FUSE_STATX_MODSIZE);
out:
if (!(mode & FALLOC_FL_KEEP_SIZE))
@@ -3002,6 +3008,8 @@ out:
if (lock_inode)
inode_unlock(inode);
+ fuse_flush_time_update(inode);
+
return err;
}
@@ -3096,12 +3104,8 @@ static ssize_t __fuse_copy_file_range(struct file *file_in, loff_t pos_in,
ALIGN_DOWN(pos_out, PAGE_SIZE),
ALIGN(pos_out + outarg.size, PAGE_SIZE) - 1);
- if (fc->writeback_cache) {
- fuse_write_update_size(inode_out, pos_out + outarg.size);
- file_update_time(file_out);
- }
-
- fuse_invalidate_attr(inode_out);
+ file_update_time(file_out);
+ fuse_write_update_attr(inode_out, pos_out + outarg.size, outarg.size);
err = outarg.size;
out:
@@ -3111,6 +3115,8 @@ out:
inode_unlock(inode_out);
file_accessed(file_in);
+ fuse_flush_time_update(inode_out);
+
return err;
}
diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h
index f55f9f94b1a4..198637b41e19 100644
--- a/fs/fuse/fuse_i.h
+++ b/fs/fuse/fuse_i.h
@@ -1031,7 +1031,9 @@ void fuse_change_attributes(struct inode *inode, struct fuse_attr *attr,
u64 attr_valid, u64 attr_version);
void fuse_change_attributes_common(struct inode *inode, struct fuse_attr *attr,
- u64 attr_valid);
+ u64 attr_valid, u32 cache_mask);
+
+u32 fuse_get_cache_mask(struct inode *inode);
/**
* Initialize the client device
@@ -1065,7 +1067,15 @@ void fuse_wait_aborted(struct fuse_conn *fc);
/**
* Invalidate inode attributes
*/
+
+/* Attributes possibly changed on data modification */
+#define FUSE_STATX_MODIFY (STATX_MTIME | STATX_CTIME | STATX_BLOCKS)
+
+/* Attributes possibly changed on data and/or size modification */
+#define FUSE_STATX_MODSIZE (FUSE_STATX_MODIFY | STATX_SIZE)
+
void fuse_invalidate_attr(struct inode *inode);
+void fuse_invalidate_attr_mask(struct inode *inode, u32 mask);
void fuse_invalidate_entry_cache(struct dentry *entry);
@@ -1148,9 +1158,10 @@ int fuse_allow_current_process(struct fuse_conn *fc);
u64 fuse_lock_owner_id(struct fuse_conn *fc, fl_owner_t id);
+void fuse_flush_time_update(struct inode *inode);
void fuse_update_ctime(struct inode *inode);
-int fuse_update_attributes(struct inode *inode, struct file *file);
+int fuse_update_attributes(struct inode *inode, struct file *file, u32 mask);
void fuse_flush_writepages(struct inode *inode);
@@ -1208,7 +1219,7 @@ long fuse_ioctl_common(struct file *file, unsigned int cmd,
__poll_t fuse_file_poll(struct file *file, poll_table *wait);
int fuse_dev_release(struct inode *inode, struct file *file);
-bool fuse_write_update_size(struct inode *inode, loff_t pos);
+bool fuse_write_update_attr(struct inode *inode, loff_t pos, ssize_t written);
int fuse_flush_times(struct inode *inode, struct fuse_file *ff);
int fuse_write_inode(struct inode *inode, struct writeback_control *wbc);
diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c
index 12d49a1914e8..8b89e3ba7df3 100644
--- a/fs/fuse/inode.c
+++ b/fs/fuse/inode.c
@@ -118,6 +118,9 @@ static void fuse_evict_inode(struct inode *inode)
{
struct fuse_inode *fi = get_fuse_inode(inode);
+ /* Will write inode on close/munmap and in all other dirtiers */
+ WARN_ON(inode->i_state & I_DIRTY_INODE);
+
truncate_inode_pages_final(&inode->i_data);
clear_inode(inode);
if (inode->i_sb->s_flags & SB_ACTIVE) {
@@ -161,7 +164,7 @@ static ino_t fuse_squash_ino(u64 ino64)
}
void fuse_change_attributes_common(struct inode *inode, struct fuse_attr *attr,
- u64 attr_valid)
+ u64 attr_valid, u32 cache_mask)
{
struct fuse_conn *fc = get_fuse_conn(inode);
struct fuse_inode *fi = get_fuse_inode(inode);
@@ -181,9 +184,11 @@ void fuse_change_attributes_common(struct inode *inode, struct fuse_attr *attr,
inode->i_atime.tv_sec = attr->atime;
inode->i_atime.tv_nsec = attr->atimensec;
/* mtime from server may be stale due to local buffered write */
- if (!fc->writeback_cache || !S_ISREG(inode->i_mode)) {
+ if (!(cache_mask & STATX_MTIME)) {
inode->i_mtime.tv_sec = attr->mtime;
inode->i_mtime.tv_nsec = attr->mtimensec;
+ }
+ if (!(cache_mask & STATX_CTIME)) {
inode->i_ctime.tv_sec = attr->ctime;
inode->i_ctime.tv_nsec = attr->ctimensec;
}
@@ -215,16 +220,44 @@ void fuse_change_attributes_common(struct inode *inode, struct fuse_attr *attr,
inode->i_flags &= ~S_NOSEC;
}
+u32 fuse_get_cache_mask(struct inode *inode)
+{
+ struct fuse_conn *fc = get_fuse_conn(inode);
+
+ if (!fc->writeback_cache || !S_ISREG(inode->i_mode))
+ return 0;
+
+ return STATX_MTIME | STATX_CTIME | STATX_SIZE;
+}
+
void fuse_change_attributes(struct inode *inode, struct fuse_attr *attr,
u64 attr_valid, u64 attr_version)
{
struct fuse_conn *fc = get_fuse_conn(inode);
struct fuse_inode *fi = get_fuse_inode(inode);
- bool is_wb = fc->writeback_cache;
+ u32 cache_mask;
loff_t oldsize;
struct timespec64 old_mtime;
spin_lock(&fi->lock);
+ /*
+ * In case of writeback_cache enabled, writes update mtime, ctime and
+ * may update i_size. In these cases trust the cached value in the
+ * inode.
+ */
+ cache_mask = fuse_get_cache_mask(inode);
+ if (cache_mask & STATX_SIZE)
+ attr->size = i_size_read(inode);
+
+ if (cache_mask & STATX_MTIME) {
+ attr->mtime = inode->i_mtime.tv_sec;
+ attr->mtimensec = inode->i_mtime.tv_nsec;
+ }
+ if (cache_mask & STATX_CTIME) {
+ attr->ctime = inode->i_ctime.tv_sec;
+ attr->ctimensec = inode->i_ctime.tv_nsec;
+ }
+
if ((attr_version != 0 && fi->attr_version > attr_version) ||
test_bit(FUSE_I_SIZE_UNSTABLE, &fi->state)) {
spin_unlock(&fi->lock);
@@ -232,7 +265,7 @@ void fuse_change_attributes(struct inode *inode, struct fuse_attr *attr,
}
old_mtime = inode->i_mtime;
- fuse_change_attributes_common(inode, attr, attr_valid);
+ fuse_change_attributes_common(inode, attr, attr_valid, cache_mask);
oldsize = inode->i_size;
/*
@@ -240,11 +273,11 @@ void fuse_change_attributes(struct inode *inode, struct fuse_attr *attr,
* extend local i_size without keeping userspace server in sync. So,
* attr->size coming from server can be stale. We cannot trust it.
*/
- if (!is_wb || !S_ISREG(inode->i_mode))
+ if (!(cache_mask & STATX_SIZE))
i_size_write(inode, attr->size);
spin_unlock(&fi->lock);
- if (!is_wb && S_ISREG(inode->i_mode)) {
+ if (!cache_mask && S_ISREG(inode->i_mode)) {
bool inval = false;
if (oldsize != attr->size) {
diff --git a/fs/fuse/ioctl.c b/fs/fuse/ioctl.c
index 546ea3d58fb4..fbc09dab1f85 100644
--- a/fs/fuse/ioctl.c
+++ b/fs/fuse/ioctl.c
@@ -286,11 +286,11 @@ long fuse_do_ioctl(struct file *file, unsigned int cmd, unsigned long arg,
in_iovs + out_iovs > FUSE_IOCTL_MAX_IOV)
goto out;
- vaddr = kmap_atomic(ap.pages[0]);
+ vaddr = kmap_local_page(ap.pages[0]);
err = fuse_copy_ioctl_iovec(fm->fc, iov_page, vaddr,
transferred, in_iovs + out_iovs,
(flags & FUSE_IOCTL_COMPAT) != 0);
- kunmap_atomic(vaddr);
+ kunmap_local(vaddr);
if (err)
goto out;
diff --git a/fs/fuse/readdir.c b/fs/fuse/readdir.c
index bc267832310c..b4e565711045 100644
--- a/fs/fuse/readdir.c
+++ b/fs/fuse/readdir.c
@@ -76,11 +76,11 @@ static void fuse_add_dirent_to_cache(struct file *file,
WARN_ON(fi->rdc.pos != pos))
goto unlock;
- addr = kmap_atomic(page);
+ addr = kmap_local_page(page);
if (!offset)
clear_page(addr);
memcpy(addr + offset, dirent, reclen);
- kunmap_atomic(addr);
+ kunmap_local(addr);
fi->rdc.size = (index << PAGE_SHIFT) + offset + reclen;
fi->rdc.pos = dirent->off;
unlock:
@@ -454,7 +454,7 @@ static int fuse_readdir_cached(struct file *file, struct dir_context *ctx)
* cache; both cases require an up-to-date mtime value.
*/
if (!ctx->pos && fc->auto_inval_data) {
- int err = fuse_update_attributes(inode, file);
+ int err = fuse_update_attributes(inode, file, STATX_MTIME);
if (err)
return err;
diff --git a/fs/fuse/virtio_fs.c b/fs/fuse/virtio_fs.c
index 94fc874f5de7..4cfa4bc1f579 100644
--- a/fs/fuse/virtio_fs.c
+++ b/fs/fuse/virtio_fs.c
@@ -649,7 +649,7 @@ static void virtio_fs_vq_done(struct virtqueue *vq)
static void virtio_fs_init_vq(struct virtio_fs_vq *fsvq, char *name,
int vq_type)
{
- strncpy(fsvq->name, name, VQ_NAME_LEN);
+ strscpy(fsvq->name, name, VQ_NAME_LEN);
spin_lock_init(&fsvq->lock);
INIT_LIST_HEAD(&fsvq->queued_reqs);
INIT_LIST_HEAD(&fsvq->end_reqs);
diff --git a/fs/fuse/xattr.c b/fs/fuse/xattr.c
index 61dfaf7b7d20..0d3e7177fce0 100644
--- a/fs/fuse/xattr.c
+++ b/fs/fuse/xattr.c
@@ -42,10 +42,9 @@ int fuse_setxattr(struct inode *inode, const char *name, const void *value,
fm->fc->no_setxattr = 1;
err = -EOPNOTSUPP;
}
- if (!err) {
- fuse_invalidate_attr(inode);
+ if (!err)
fuse_update_ctime(inode);
- }
+
return err;
}
@@ -173,10 +172,9 @@ int fuse_removexattr(struct inode *inode, const char *name)
fm->fc->no_removexattr = 1;
err = -EOPNOTSUPP;
}
- if (!err) {
- fuse_invalidate_attr(inode);
+ if (!err)
fuse_update_ctime(inode);
- }
+
return err;
}
diff --git a/fs/gfs2/file.c b/fs/gfs2/file.c
index 8f4627a19359..adafaaf7d24d 100644
--- a/fs/gfs2/file.c
+++ b/fs/gfs2/file.c
@@ -213,11 +213,9 @@ void gfs2_set_inode_flags(struct inode *inode)
* @inode: The inode
* @reqflags: The flags to set
* @mask: Indicates which flags are valid
- * @fsflags: The FS_* inode flags passed in
*
*/
-static int do_gfs2_set_flags(struct inode *inode, u32 reqflags, u32 mask,
- const u32 fsflags)
+static int do_gfs2_set_flags(struct inode *inode, u32 reqflags, u32 mask)
{
struct gfs2_inode *ip = GFS2_I(inode);
struct gfs2_sbd *sdp = GFS2_SB(inode);
@@ -236,11 +234,6 @@ static int do_gfs2_set_flags(struct inode *inode, u32 reqflags, u32 mask,
if ((new_flags ^ flags) == 0)
goto out;
- error = -EPERM;
- if (IS_IMMUTABLE(inode) && (new_flags & GFS2_DIF_IMMUTABLE))
- goto out;
- if (IS_APPEND(inode) && (new_flags & GFS2_DIF_APPENDONLY))
- goto out;
if (!IS_IMMUTABLE(inode)) {
error = gfs2_permission(&init_user_ns, inode, MAY_WRITE);
if (error)
@@ -313,7 +306,7 @@ int gfs2_fileattr_set(struct user_namespace *mnt_userns,
mask &= ~(GFS2_DIF_TOPDIR | GFS2_DIF_INHERIT_JDATA);
}
- return do_gfs2_set_flags(inode, gfsflags, mask, fsflags);
+ return do_gfs2_set_flags(inode, gfsflags, mask);
}
static int gfs2_getlabel(struct file *filp, char __user *label)
diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c
index f686083d0250..19f38aee1b61 100644
--- a/fs/gfs2/glock.c
+++ b/fs/gfs2/glock.c
@@ -301,6 +301,9 @@ void gfs2_glock_queue_put(struct gfs2_glock *gl)
void gfs2_glock_put(struct gfs2_glock *gl)
{
+ /* last put could call sleepable dlm api */
+ might_sleep();
+
if (lockref_put_or_lock(&gl->gl_lockref))
return;
@@ -472,6 +475,51 @@ find_first_strong_holder(struct gfs2_glock *gl)
return NULL;
}
+/*
+ * gfs2_instantiate - Call the glops instantiate function
+ * @gl: The glock
+ *
+ * Returns: 0 if instantiate was successful, 2 if type specific operation is
+ * underway, or error.
+ */
+int gfs2_instantiate(struct gfs2_holder *gh)
+{
+ struct gfs2_glock *gl = gh->gh_gl;
+ const struct gfs2_glock_operations *glops = gl->gl_ops;
+ int ret;
+
+again:
+ if (!test_bit(GLF_INSTANTIATE_NEEDED, &gl->gl_flags))
+ return 0;
+
+ /*
+ * Since we unlock the lockref lock, we set a flag to indicate
+ * instantiate is in progress.
+ */
+ if (test_bit(GLF_INSTANTIATE_IN_PROG, &gl->gl_flags)) {
+ wait_on_bit(&gl->gl_flags, GLF_INSTANTIATE_IN_PROG,
+ TASK_UNINTERRUPTIBLE);
+ /*
+ * Here we just waited for a different instantiate to finish.
+ * But that may not have been successful, as when a process
+ * locks an inode glock _before_ it has an actual inode to
+ * instantiate into. So we check again. This process might
+ * have an inode to instantiate, so might be successful.
+ */
+ goto again;
+ }
+
+ set_bit(GLF_INSTANTIATE_IN_PROG, &gl->gl_flags);
+
+ ret = glops->go_instantiate(gh);
+ if (!ret)
+ clear_bit(GLF_INSTANTIATE_NEEDED, &gl->gl_flags);
+ clear_bit(GLF_INSTANTIATE_IN_PROG, &gl->gl_flags);
+ smp_mb__after_atomic();
+ wake_up_bit(&gl->gl_flags, GLF_INSTANTIATE_IN_PROG);
+ return ret;
+}
+
/**
* do_promote - promote as many requests as possible on the current queue
* @gl: The glock
@@ -484,56 +532,59 @@ static int do_promote(struct gfs2_glock *gl)
__releases(&gl->gl_lockref.lock)
__acquires(&gl->gl_lockref.lock)
{
- const struct gfs2_glock_operations *glops = gl->gl_ops;
struct gfs2_holder *gh, *tmp, *first_gh;
bool incompat_holders_demoted = false;
+ bool lock_released;
int ret;
restart:
first_gh = find_first_strong_holder(gl);
list_for_each_entry_safe(gh, tmp, &gl->gl_holders, gh_list) {
- if (!test_bit(HIF_WAIT, &gh->gh_iflags))
+ lock_released = false;
+ if (test_bit(HIF_HOLDER, &gh->gh_iflags))
continue;
- if (may_grant(gl, first_gh, gh)) {
- if (!incompat_holders_demoted) {
- demote_incompat_holders(gl, first_gh);
- incompat_holders_demoted = true;
- first_gh = gh;
- }
- if (gh->gh_list.prev == &gl->gl_holders &&
- glops->go_lock) {
- spin_unlock(&gl->gl_lockref.lock);
- /* FIXME: eliminate this eventually */
- ret = glops->go_lock(gh);
- spin_lock(&gl->gl_lockref.lock);
- if (ret) {
- if (ret == 1)
- return 2;
- gh->gh_error = ret;
- list_del_init(&gh->gh_list);
- trace_gfs2_glock_queue(gh, 0);
- gfs2_holder_wake(gh);
- goto restart;
- }
- set_bit(HIF_HOLDER, &gh->gh_iflags);
- trace_gfs2_promote(gh, 1);
+ if (!may_grant(gl, first_gh, gh)) {
+ /*
+ * If we get here, it means we may not grant this holder for
+ * some reason. If this holder is the head of the list, it
+ * means we have a blocked holder at the head, so return 1.
+ */
+ if (gh->gh_list.prev == &gl->gl_holders)
+ return 1;
+ do_error(gl, 0);
+ break;
+ }
+ if (!incompat_holders_demoted) {
+ demote_incompat_holders(gl, first_gh);
+ incompat_holders_demoted = true;
+ first_gh = gh;
+ }
+ if (test_bit(GLF_INSTANTIATE_NEEDED, &gl->gl_flags) &&
+ !(gh->gh_flags & GL_SKIP) && gl->gl_ops->go_instantiate) {
+ lock_released = true;
+ spin_unlock(&gl->gl_lockref.lock);
+ ret = gfs2_instantiate(gh);
+ spin_lock(&gl->gl_lockref.lock);
+ if (ret) {
+ if (ret == 1)
+ return 2;
+ gh->gh_error = ret;
+ list_del_init(&gh->gh_list);
+ trace_gfs2_glock_queue(gh, 0);
gfs2_holder_wake(gh);
goto restart;
}
- set_bit(HIF_HOLDER, &gh->gh_iflags);
- trace_gfs2_promote(gh, 0);
- gfs2_holder_wake(gh);
- continue;
}
+ set_bit(HIF_HOLDER, &gh->gh_iflags);
+ trace_gfs2_promote(gh);
+ gfs2_holder_wake(gh);
/*
- * If we get here, it means we may not grant this holder for
- * some reason. If this holder is the head of the list, it
- * means we have a blocked holder at the head, so return 1.
+ * If we released the gl_lockref.lock the holders list may have
+ * changed. For that reason, we start again at the start of
+ * the holders queue.
*/
- if (gh->gh_list.prev == &gl->gl_holders)
- return 1;
- do_error(gl, 0);
- break;
+ if (lock_released)
+ goto restart;
}
return 0;
}
@@ -909,7 +960,7 @@ static void gfs2_glock_poke(struct gfs2_glock *gl)
struct gfs2_holder gh;
int error;
- gfs2_holder_init(gl, LM_ST_SHARED, flags, &gh);
+ __gfs2_holder_init(gl, LM_ST_SHARED, flags, &gh, _RET_IP_);
error = gfs2_glock_nq(&gh);
if (!error)
gfs2_glock_dq(&gh);
@@ -1144,7 +1195,7 @@ int gfs2_glock_get(struct gfs2_sbd *sdp, u64 number,
atomic_inc(&sdp->sd_glock_disposal);
gl->gl_node.next = NULL;
- gl->gl_flags = 0;
+ gl->gl_flags = glops->go_instantiate ? BIT(GLF_INSTANTIATE_NEEDED) : 0;
gl->gl_name = name;
lockdep_set_subclass(&gl->gl_lockref.lock, glops->go_subclass);
gl->gl_lockref.count = 1;
@@ -1206,12 +1257,12 @@ out:
*
*/
-void gfs2_holder_init(struct gfs2_glock *gl, unsigned int state, u16 flags,
- struct gfs2_holder *gh)
+void __gfs2_holder_init(struct gfs2_glock *gl, unsigned int state, u16 flags,
+ struct gfs2_holder *gh, unsigned long ip)
{
INIT_LIST_HEAD(&gh->gh_list);
gh->gh_gl = gl;
- gh->gh_ip = _RET_IP_;
+ gh->gh_ip = ip;
gh->gh_owner_pid = get_pid(task_pid(current));
gh->gh_state = state;
gh->gh_flags = flags;
@@ -2053,10 +2104,10 @@ static void glock_hash_walk(glock_examiner examiner, const struct gfs2_sbd *sdp)
do {
rhashtable_walk_start(&iter);
- while ((gl = rhashtable_walk_next(&iter)) && !IS_ERR(gl))
- if (gl->gl_name.ln_sbd == sdp &&
- lockref_get_not_dead(&gl->gl_lockref))
+ while ((gl = rhashtable_walk_next(&iter)) && !IS_ERR(gl)) {
+ if (gl->gl_name.ln_sbd == sdp)
examiner(gl);
+ }
rhashtable_walk_stop(&iter);
} while (cond_resched(), gl == ERR_PTR(-EAGAIN));
@@ -2079,7 +2130,7 @@ bool gfs2_queue_delete_work(struct gfs2_glock *gl, unsigned long delay)
void gfs2_cancel_delete_work(struct gfs2_glock *gl)
{
- if (cancel_delayed_work_sync(&gl->gl_delete)) {
+ if (cancel_delayed_work(&gl->gl_delete)) {
clear_bit(GLF_PENDING_DELETE, &gl->gl_flags);
gfs2_glock_put(gl);
}
@@ -2098,7 +2149,6 @@ static void flush_delete_work(struct gfs2_glock *gl)
&gl->gl_delete, 0);
}
}
- gfs2_glock_queue_work(gl, 0);
}
void gfs2_flush_delete_work(struct gfs2_sbd *sdp)
@@ -2115,10 +2165,10 @@ void gfs2_flush_delete_work(struct gfs2_sbd *sdp)
static void thaw_glock(struct gfs2_glock *gl)
{
- if (!test_and_clear_bit(GLF_FROZEN, &gl->gl_flags)) {
- gfs2_glock_put(gl);
+ if (!test_and_clear_bit(GLF_FROZEN, &gl->gl_flags))
+ return;
+ if (!lockref_get_not_dead(&gl->gl_lockref))
return;
- }
set_bit(GLF_REPLY_PENDING, &gl->gl_flags);
gfs2_glock_queue_work(gl, 0);
}
@@ -2134,9 +2184,12 @@ static void clear_glock(struct gfs2_glock *gl)
gfs2_glock_remove_from_lru(gl);
spin_lock(&gl->gl_lockref.lock);
- if (gl->gl_state != LM_ST_UNLOCKED)
- handle_callback(gl, LM_ST_UNLOCKED, 0, false);
- __gfs2_glock_queue_work(gl, 0);
+ if (!__lockref_is_dead(&gl->gl_lockref)) {
+ gl->gl_lockref.count++;
+ if (gl->gl_state != LM_ST_UNLOCKED)
+ handle_callback(gl, LM_ST_UNLOCKED, 0, false);
+ __gfs2_glock_queue_work(gl, 0);
+ }
spin_unlock(&gl->gl_lockref.lock);
}
@@ -2238,6 +2291,8 @@ static const char *hflags2str(char *buf, u16 flags, unsigned long iflags)
*p++ = 'W';
if (test_bit(HIF_MAY_DEMOTE, &iflags))
*p++ = 'D';
+ if (flags & GL_SKIP)
+ *p++ = 's';
*p = 0;
return buf;
}
@@ -2306,6 +2361,10 @@ static const char *gflags2str(char *buf, const struct gfs2_glock *gl)
*p++ = 'P';
if (test_bit(GLF_FREEING, gflags))
*p++ = 'x';
+ if (test_bit(GLF_INSTANTIATE_NEEDED, gflags))
+ *p++ = 'n';
+ if (test_bit(GLF_INSTANTIATE_IN_PROG, gflags))
+ *p++ = 'N';
*p = 0;
return buf;
}
diff --git a/fs/gfs2/glock.h b/fs/gfs2/glock.h
index 9012487da4c6..4f8642301801 100644
--- a/fs/gfs2/glock.h
+++ b/fs/gfs2/glock.h
@@ -190,13 +190,21 @@ extern int gfs2_glock_get(struct gfs2_sbd *sdp, u64 number,
extern void gfs2_glock_hold(struct gfs2_glock *gl);
extern void gfs2_glock_put(struct gfs2_glock *gl);
extern void gfs2_glock_queue_put(struct gfs2_glock *gl);
-extern void gfs2_holder_init(struct gfs2_glock *gl, unsigned int state,
- u16 flags, struct gfs2_holder *gh);
+
+extern void __gfs2_holder_init(struct gfs2_glock *gl, unsigned int state,
+ u16 flags, struct gfs2_holder *gh,
+ unsigned long ip);
+static inline void gfs2_holder_init(struct gfs2_glock *gl, unsigned int state,
+ u16 flags, struct gfs2_holder *gh) {
+ __gfs2_holder_init(gl, state, flags, gh, _RET_IP_);
+}
+
extern void gfs2_holder_reinit(unsigned int state, u16 flags,
struct gfs2_holder *gh);
extern void gfs2_holder_uninit(struct gfs2_holder *gh);
extern int gfs2_glock_nq(struct gfs2_holder *gh);
extern int gfs2_glock_poll(struct gfs2_holder *gh);
+extern int gfs2_instantiate(struct gfs2_holder *gh);
extern int gfs2_glock_wait(struct gfs2_holder *gh);
extern int gfs2_glock_async_wait(unsigned int num_gh, struct gfs2_holder *ghs);
extern void gfs2_glock_dq(struct gfs2_holder *gh);
@@ -241,7 +249,7 @@ static inline int gfs2_glock_nq_init(struct gfs2_glock *gl,
{
int error;
- gfs2_holder_init(gl, state, flags, gh);
+ __gfs2_holder_init(gl, state, flags, gh, _RET_IP_);
error = gfs2_glock_nq(gh);
if (error)
diff --git a/fs/gfs2/glops.c b/fs/gfs2/glops.c
index 79c621c7863d..650ad77c4d0b 100644
--- a/fs/gfs2/glops.c
+++ b/fs/gfs2/glops.c
@@ -228,7 +228,7 @@ static void rgrp_go_inval(struct gfs2_glock *gl, int flags)
gfs2_rgrp_brelse(rgd);
WARN_ON_ONCE(!(flags & DIO_METADATA));
truncate_inode_pages_range(mapping, start, end);
- rgd->rd_flags &= ~GFS2_RDF_UPTODATE;
+ set_bit(GLF_INSTANTIATE_NEEDED, &gl->gl_flags);
}
static void gfs2_rgrp_go_dump(struct seq_file *seq, struct gfs2_glock *gl,
@@ -356,7 +356,7 @@ static void inode_go_inval(struct gfs2_glock *gl, int flags)
struct address_space *mapping = gfs2_glock2aspace(gl);
truncate_inode_pages(mapping, 0);
if (ip) {
- set_bit(GIF_INVALID, &ip->i_flags);
+ set_bit(GLF_INSTANTIATE_NEEDED, &gl->gl_flags);
forget_all_cached_acls(&ip->i_inode);
security_inode_invalidate_secctx(&ip->i_inode);
gfs2_dir_hash_inval(ip);
@@ -476,33 +476,29 @@ int gfs2_inode_refresh(struct gfs2_inode *ip)
error = gfs2_dinode_in(ip, dibh->b_data);
brelse(dibh);
- clear_bit(GIF_INVALID, &ip->i_flags);
-
return error;
}
/**
- * inode_go_lock - operation done after an inode lock is locked by a process
+ * inode_go_instantiate - read in an inode if necessary
* @gh: The glock holder
*
* Returns: errno
*/
-static int inode_go_lock(struct gfs2_holder *gh)
+static int inode_go_instantiate(struct gfs2_holder *gh)
{
struct gfs2_glock *gl = gh->gh_gl;
struct gfs2_sbd *sdp = gl->gl_name.ln_sbd;
struct gfs2_inode *ip = gl->gl_object;
int error = 0;
- if (!ip || (gh->gh_flags & GL_SKIP))
- return 0;
+ if (!ip) /* no inode to populate - read it in later */
+ goto out;
- if (test_bit(GIF_INVALID, &ip->i_flags)) {
- error = gfs2_inode_refresh(ip);
- if (error)
- return error;
- }
+ error = gfs2_inode_refresh(ip);
+ if (error)
+ goto out;
if (gh->gh_state != LM_ST_DEFERRED)
inode_dio_wait(&ip->i_inode);
@@ -515,9 +511,10 @@ static int inode_go_lock(struct gfs2_holder *gh)
list_add(&ip->i_trunc_list, &sdp->sd_trunc_list);
spin_unlock(&sdp->sd_trunc_lock);
wake_up(&sdp->sd_quota_wait);
- return 1;
+ error = 1;
}
+out:
return error;
}
@@ -740,7 +737,7 @@ const struct gfs2_glock_operations gfs2_inode_glops = {
.go_sync = inode_go_sync,
.go_inval = inode_go_inval,
.go_demote_ok = inode_go_demote_ok,
- .go_lock = inode_go_lock,
+ .go_instantiate = inode_go_instantiate,
.go_dump = inode_go_dump,
.go_type = LM_TYPE_INODE,
.go_flags = GLOF_ASPACE | GLOF_LRU | GLOF_LVB,
@@ -750,7 +747,7 @@ const struct gfs2_glock_operations gfs2_inode_glops = {
const struct gfs2_glock_operations gfs2_rgrp_glops = {
.go_sync = rgrp_go_sync,
.go_inval = rgrp_go_inval,
- .go_lock = gfs2_rgrp_go_lock,
+ .go_instantiate = gfs2_rgrp_go_instantiate,
.go_dump = gfs2_rgrp_go_dump,
.go_type = LM_TYPE_RGRP,
.go_flags = GLOF_LVB,
diff --git a/fs/gfs2/incore.h b/fs/gfs2/incore.h
index ca42d310fd4d..8c00fb389ae5 100644
--- a/fs/gfs2/incore.h
+++ b/fs/gfs2/incore.h
@@ -119,7 +119,6 @@ struct gfs2_rgrpd {
u32 rd_flags;
u32 rd_extfail_pt; /* extent failure point */
#define GFS2_RDF_CHECK 0x10000000 /* check for unlinked inodes */
-#define GFS2_RDF_UPTODATE 0x20000000 /* rg is up to date */
#define GFS2_RDF_ERROR 0x40000000 /* error in rg */
#define GFS2_RDF_PREFERRED 0x80000000 /* This rgrp is preferred */
#define GFS2_RDF_MASK 0xf0000000 /* mask for internal flags */
@@ -220,7 +219,7 @@ struct gfs2_glock_operations {
int (*go_xmote_bh)(struct gfs2_glock *gl);
void (*go_inval) (struct gfs2_glock *gl, int flags);
int (*go_demote_ok) (const struct gfs2_glock *gl);
- int (*go_lock) (struct gfs2_holder *gh);
+ int (*go_instantiate) (struct gfs2_holder *gh);
void (*go_dump)(struct seq_file *seq, struct gfs2_glock *gl,
const char *fs_id_buf);
void (*go_callback)(struct gfs2_glock *gl, bool remote);
@@ -316,6 +315,7 @@ struct gfs2_alloc_parms {
enum {
GLF_LOCK = 1,
+ GLF_INSTANTIATE_NEEDED = 2, /* needs instantiate */
GLF_DEMOTE = 3,
GLF_PENDING_DEMOTE = 4,
GLF_DEMOTE_IN_PROGRESS = 5,
@@ -325,6 +325,7 @@ enum {
GLF_REPLY_PENDING = 9,
GLF_INITIAL = 10,
GLF_FROZEN = 11,
+ GLF_INSTANTIATE_IN_PROG = 12, /* instantiate happening now */
GLF_LRU = 13,
GLF_OBJECT = 14, /* Used only for tracing */
GLF_BLOCKING = 15,
@@ -371,7 +372,6 @@ struct gfs2_glock {
};
enum {
- GIF_INVALID = 0,
GIF_QD_LOCKED = 1,
GIF_ALLOC_FAILED = 2,
GIF_SW_PAGED = 3,
diff --git a/fs/gfs2/inode.c b/fs/gfs2/inode.c
index 3130f85d2b3f..6424b903e885 100644
--- a/fs/gfs2/inode.c
+++ b/fs/gfs2/inode.c
@@ -182,7 +182,7 @@ struct inode *gfs2_inode_lookup(struct super_block *sb, unsigned int type,
}
glock_set_object(ip->i_gl, ip);
- set_bit(GIF_INVALID, &ip->i_flags);
+ set_bit(GLF_INSTANTIATE_NEEDED, &ip->i_gl->gl_flags);
error = gfs2_glock_nq_init(io_gl, LM_ST_SHARED, GL_EXACT, &ip->i_iopen_gh);
if (unlikely(error))
goto fail;
@@ -196,7 +196,7 @@ struct inode *gfs2_inode_lookup(struct super_block *sb, unsigned int type,
if (type == DT_UNKNOWN) {
/* Inode glock must be locked already */
- error = gfs2_inode_refresh(GFS2_I(inode));
+ error = gfs2_instantiate(&i_gh);
if (error)
goto fail;
} else {
@@ -225,6 +225,10 @@ struct inode *gfs2_inode_lookup(struct super_block *sb, unsigned int type,
return inode;
fail:
+ if (gfs2_holder_initialized(&ip->i_iopen_gh)) {
+ glock_clear_object(ip->i_iopen_gh.gh_gl, ip);
+ gfs2_glock_dq_uninit(&ip->i_iopen_gh);
+ }
if (io_gl)
gfs2_glock_put(io_gl);
if (gfs2_holder_initialized(&i_gh))
@@ -727,18 +731,17 @@ static int gfs2_create_inode(struct inode *dir, struct dentry *dentry,
if (error)
goto fail_free_inode;
flush_delayed_work(&ip->i_gl->gl_work);
- glock_set_object(ip->i_gl, ip);
error = gfs2_glock_get(sdp, ip->i_no_addr, &gfs2_iopen_glops, CREATE, &io_gl);
if (error)
goto fail_free_inode;
gfs2_cancel_delete_work(io_gl);
- glock_set_object(io_gl, ip);
error = gfs2_glock_nq_init(ip->i_gl, LM_ST_EXCLUSIVE, GL_SKIP, ghs + 1);
if (error)
goto fail_gunlock2;
+ glock_set_object(ip->i_gl, ip);
error = gfs2_trans_begin(sdp, blocks, 0);
if (error)
goto fail_gunlock2;
@@ -754,6 +757,7 @@ static int gfs2_create_inode(struct inode *dir, struct dentry *dentry,
if (error)
goto fail_gunlock2;
+ glock_set_object(io_gl, ip);
gfs2_set_iop(inode);
insert_inode_hash(inode);
diff --git a/fs/gfs2/rgrp.c b/fs/gfs2/rgrp.c
index c3b00ba92ed2..0fb3c01bc557 100644
--- a/fs/gfs2/rgrp.c
+++ b/fs/gfs2/rgrp.c
@@ -932,7 +932,7 @@ static int read_rindex_entry(struct gfs2_inode *ip)
goto fail;
rgd->rd_rgl = (struct gfs2_rgrp_lvb *)rgd->rd_gl->gl_lksb.sb_lvbptr;
- rgd->rd_flags &= ~(GFS2_RDF_UPTODATE | GFS2_RDF_PREFERRED);
+ rgd->rd_flags &= ~GFS2_RDF_PREFERRED;
if (rgd->rd_data > sdp->sd_max_rg_data)
sdp->sd_max_rg_data = rgd->rd_data;
spin_lock(&sdp->sd_rindex_spin);
@@ -1185,8 +1185,8 @@ static void rgrp_set_bitmap_flags(struct gfs2_rgrpd *rgd)
}
/**
- * gfs2_rgrp_bh_get - Read in a RG's header and bitmaps
- * @rgd: the struct gfs2_rgrpd describing the RG to read in
+ * gfs2_rgrp_go_instantiate - Read in a RG's header and bitmaps
+ * @gh: the glock holder representing the rgrpd to read in
*
* Read in all of a Resource Group's header and bitmap blocks.
* Caller must eventually call gfs2_rgrp_brelse() to free the bitmaps.
@@ -1194,10 +1194,11 @@ static void rgrp_set_bitmap_flags(struct gfs2_rgrpd *rgd)
* Returns: errno
*/
-static int gfs2_rgrp_bh_get(struct gfs2_rgrpd *rgd)
+int gfs2_rgrp_go_instantiate(struct gfs2_holder *gh)
{
+ struct gfs2_glock *gl = gh->gh_gl;
+ struct gfs2_rgrpd *rgd = gl->gl_object;
struct gfs2_sbd *sdp = rgd->rd_sbd;
- struct gfs2_glock *gl = rgd->rd_gl;
unsigned int length = rgd->rd_length;
struct gfs2_bitmap *bi;
unsigned int x, y;
@@ -1225,21 +1226,18 @@ static int gfs2_rgrp_bh_get(struct gfs2_rgrpd *rgd)
}
}
- if (!(rgd->rd_flags & GFS2_RDF_UPTODATE)) {
- gfs2_rgrp_in(rgd, (rgd->rd_bits[0].bi_bh)->b_data);
- rgrp_set_bitmap_flags(rgd);
- rgd->rd_flags |= (GFS2_RDF_UPTODATE | GFS2_RDF_CHECK);
- rgd->rd_free_clone = rgd->rd_free;
- BUG_ON(rgd->rd_reserved);
- /* max out the rgrp allocation failure point */
- rgd->rd_extfail_pt = rgd->rd_free;
- }
+ gfs2_rgrp_in(rgd, (rgd->rd_bits[0].bi_bh)->b_data);
+ rgrp_set_bitmap_flags(rgd);
+ rgd->rd_flags |= GFS2_RDF_CHECK;
+ rgd->rd_free_clone = rgd->rd_free;
+ GLOCK_BUG_ON(rgd->rd_gl, rgd->rd_reserved);
+ /* max out the rgrp allocation failure point */
+ rgd->rd_extfail_pt = rgd->rd_free;
if (cpu_to_be32(GFS2_MAGIC) != rgd->rd_rgl->rl_magic) {
rgd->rd_rgl->rl_unlinked = cpu_to_be32(count_unlinked(rgd));
gfs2_rgrp_ondisk2lvb(rgd->rd_rgl,
rgd->rd_bits[0].bi_bh->b_data);
- }
- else if (sdp->sd_args.ar_rgrplvb) {
+ } else if (sdp->sd_args.ar_rgrplvb) {
if (!gfs2_rgrp_lvb_valid(rgd)){
gfs2_consist_rgrpd(rgd);
error = -EIO;
@@ -1257,19 +1255,18 @@ fail:
bi->bi_bh = NULL;
gfs2_assert_warn(sdp, !bi->bi_clone);
}
-
return error;
}
-static int update_rgrp_lvb(struct gfs2_rgrpd *rgd)
+static int update_rgrp_lvb(struct gfs2_rgrpd *rgd, struct gfs2_holder *gh)
{
u32 rl_flags;
- if (rgd->rd_flags & GFS2_RDF_UPTODATE)
+ if (!test_bit(GLF_INSTANTIATE_NEEDED, &gh->gh_gl->gl_flags))
return 0;
if (cpu_to_be32(GFS2_MAGIC) != rgd->rd_rgl->rl_magic)
- return gfs2_rgrp_bh_get(rgd);
+ return gfs2_instantiate(gh);
rl_flags = be32_to_cpu(rgd->rd_rgl->rl_flags);
rl_flags &= ~GFS2_RDF_MASK;
@@ -1280,7 +1277,7 @@ static int update_rgrp_lvb(struct gfs2_rgrpd *rgd)
rgd->rd_free = be32_to_cpu(rgd->rd_rgl->rl_free);
rgrp_set_bitmap_flags(rgd);
rgd->rd_free_clone = rgd->rd_free;
- BUG_ON(rgd->rd_reserved);
+ GLOCK_BUG_ON(rgd->rd_gl, rgd->rd_reserved);
/* max out the rgrp allocation failure point */
rgd->rd_extfail_pt = rgd->rd_free;
rgd->rd_dinodes = be32_to_cpu(rgd->rd_rgl->rl_dinodes);
@@ -1288,16 +1285,6 @@ static int update_rgrp_lvb(struct gfs2_rgrpd *rgd)
return 0;
}
-int gfs2_rgrp_go_lock(struct gfs2_holder *gh)
-{
- struct gfs2_rgrpd *rgd = gh->gh_gl->gl_object;
- struct gfs2_sbd *sdp = rgd->rd_sbd;
-
- if (gh->gh_flags & GL_SKIP && sdp->sd_args.ar_rgrplvb)
- return 0;
- return gfs2_rgrp_bh_get(rgd);
-}
-
/**
* gfs2_rgrp_brelse - Release RG bitmaps read in with gfs2_rgrp_bh_get()
* @rgd: The resource group
@@ -1315,6 +1302,7 @@ void gfs2_rgrp_brelse(struct gfs2_rgrpd *rgd)
bi->bi_bh = NULL;
}
}
+ set_bit(GLF_INSTANTIATE_NEEDED, &rgd->rd_gl->gl_flags);
}
int gfs2_rgrp_send_discards(struct gfs2_sbd *sdp, u64 offset,
@@ -2113,7 +2101,8 @@ int gfs2_inplace_reserve(struct gfs2_inode *ip, struct gfs2_alloc_parms *ap)
gfs2_rgrp_congested(rs->rs_rgd, loops))
goto skip_rgrp;
if (sdp->sd_args.ar_rgrplvb) {
- error = update_rgrp_lvb(rs->rs_rgd);
+ error = update_rgrp_lvb(rs->rs_rgd,
+ &ip->i_rgd_gh);
if (unlikely(error)) {
rgrp_unlock_local(rs->rs_rgd);
gfs2_glock_dq_uninit(&ip->i_rgd_gh);
@@ -2128,8 +2117,11 @@ int gfs2_inplace_reserve(struct gfs2_inode *ip, struct gfs2_alloc_parms *ap)
(loops == 0 && target > rs->rs_rgd->rd_extfail_pt))
goto skip_rgrp;
- if (sdp->sd_args.ar_rgrplvb)
- gfs2_rgrp_bh_get(rs->rs_rgd);
+ if (sdp->sd_args.ar_rgrplvb) {
+ error = gfs2_instantiate(&ip->i_rgd_gh);
+ if (error)
+ goto skip_rgrp;
+ }
/* Get a reservation if we don't already have one */
if (!gfs2_rs_active(rs))
@@ -2215,7 +2207,7 @@ void gfs2_inplace_release(struct gfs2_inode *ip)
struct gfs2_rgrpd *rgd = rs->rs_rgd;
spin_lock(&rgd->rd_rsspin);
- BUG_ON(rgd->rd_reserved < rs->rs_reserved);
+ GLOCK_BUG_ON(rgd->rd_gl, rgd->rd_reserved < rs->rs_reserved);
rgd->rd_reserved -= rs->rs_reserved;
spin_unlock(&rgd->rd_rsspin);
rs->rs_reserved = 0;
@@ -2476,9 +2468,9 @@ int gfs2_alloc_blocks(struct gfs2_inode *ip, u64 *bn, unsigned int *nblocks,
spin_unlock(&rbm.rgd->rd_rsspin);
goto rgrp_error;
}
- BUG_ON(rbm.rgd->rd_reserved < *nblocks);
- BUG_ON(rbm.rgd->rd_free_clone < *nblocks);
- BUG_ON(rbm.rgd->rd_free < *nblocks);
+ GLOCK_BUG_ON(rbm.rgd->rd_gl, rbm.rgd->rd_reserved < *nblocks);
+ GLOCK_BUG_ON(rbm.rgd->rd_gl, rbm.rgd->rd_free_clone < *nblocks);
+ GLOCK_BUG_ON(rbm.rgd->rd_gl, rbm.rgd->rd_free < *nblocks);
rbm.rgd->rd_reserved -= *nblocks;
rbm.rgd->rd_free_clone -= *nblocks;
rbm.rgd->rd_free -= *nblocks;
@@ -2765,8 +2757,6 @@ void gfs2_rlist_free(struct gfs2_rgrp_list *rlist)
void rgrp_lock_local(struct gfs2_rgrpd *rgd)
{
- BUG_ON(!gfs2_glock_is_held_excl(rgd->rd_gl) &&
- !test_bit(SDF_NORECOVERY, &rgd->rd_sbd->sd_flags));
mutex_lock(&rgd->rd_mutex);
}
diff --git a/fs/gfs2/rgrp.h b/fs/gfs2/rgrp.h
index a6855fd796e0..3e2ca1fb4305 100644
--- a/fs/gfs2/rgrp.h
+++ b/fs/gfs2/rgrp.h
@@ -31,7 +31,7 @@ extern struct gfs2_rgrpd *gfs2_rgrpd_get_next(struct gfs2_rgrpd *rgd);
extern void gfs2_clear_rgrpd(struct gfs2_sbd *sdp);
extern int gfs2_rindex_update(struct gfs2_sbd *sdp);
extern void gfs2_free_clones(struct gfs2_rgrpd *rgd);
-extern int gfs2_rgrp_go_lock(struct gfs2_holder *gh);
+extern int gfs2_rgrp_go_instantiate(struct gfs2_holder *gh);
extern void gfs2_rgrp_brelse(struct gfs2_rgrpd *rgd);
extern struct gfs2_alloc *gfs2_alloc_get(struct gfs2_inode *ip);
diff --git a/fs/gfs2/super.c b/fs/gfs2/super.c
index 6e00d15ef0a8..5b121371508a 100644
--- a/fs/gfs2/super.c
+++ b/fs/gfs2/super.c
@@ -1244,8 +1244,8 @@ static enum dinode_demise evict_should_delete(struct inode *inode,
if (ret)
return SHOULD_NOT_DELETE_DINODE;
- if (test_bit(GIF_INVALID, &ip->i_flags)) {
- ret = gfs2_inode_refresh(ip);
+ if (test_bit(GLF_INSTANTIATE_NEEDED, &ip->i_gl->gl_flags)) {
+ ret = gfs2_instantiate(gh);
if (ret)
return SHOULD_NOT_DELETE_DINODE;
}
diff --git a/fs/gfs2/trace_gfs2.h b/fs/gfs2/trace_gfs2.h
index bd6c8e9e49db..a5deb9f86831 100644
--- a/fs/gfs2/trace_gfs2.h
+++ b/fs/gfs2/trace_gfs2.h
@@ -197,15 +197,14 @@ TRACE_EVENT(gfs2_demote_rq,
/* Promotion/grant of a glock */
TRACE_EVENT(gfs2_promote,
- TP_PROTO(const struct gfs2_holder *gh, int first),
+ TP_PROTO(const struct gfs2_holder *gh),
- TP_ARGS(gh, first),
+ TP_ARGS(gh),
TP_STRUCT__entry(
__field( dev_t, dev )
__field( u64, glnum )
__field( u32, gltype )
- __field( int, first )
__field( u8, state )
),
@@ -213,14 +212,12 @@ TRACE_EVENT(gfs2_promote,
__entry->dev = gh->gh_gl->gl_name.ln_sbd->sd_vfs->s_dev;
__entry->glnum = gh->gh_gl->gl_name.ln_number;
__entry->gltype = gh->gh_gl->gl_name.ln_type;
- __entry->first = first;
__entry->state = glock_trace_state(gh->gh_state);
),
- TP_printk("%u,%u glock %u:%llu promote %s %s",
+ TP_printk("%u,%u glock %u:%llu promote %s",
MAJOR(__entry->dev), MINOR(__entry->dev), __entry->gltype,
(unsigned long long)__entry->glnum,
- __entry->first ? "first": "other",
glock_trace_name(__entry->state))
);
diff --git a/fs/gfs2/util.c b/fs/gfs2/util.c
index cf345a86ef67..8241029a2a5d 100644
--- a/fs/gfs2/util.c
+++ b/fs/gfs2/util.c
@@ -454,6 +454,7 @@ void gfs2_consist_inode_i(struct gfs2_inode *ip,
(unsigned long long)ip->i_no_formal_ino,
(unsigned long long)ip->i_no_addr,
function, file, line);
+ gfs2_dump_glock(NULL, ip->i_gl, 1);
gfs2_withdraw(sdp);
}
@@ -475,6 +476,7 @@ void gfs2_consist_rgrpd_i(struct gfs2_rgrpd *rgd,
" function = %s, file = %s, line = %u\n",
(unsigned long long)rgd->rd_addr,
function, file, line);
+ gfs2_dump_glock(NULL, rgd->rd_gl, 1);
gfs2_withdraw(sdp);
}
diff --git a/fs/hfs/inode.c b/fs/hfs/inode.c
index 4a95a92546a0..2a5143246282 100644
--- a/fs/hfs/inode.c
+++ b/fs/hfs/inode.c
@@ -462,8 +462,7 @@ int hfs_write_inode(struct inode *inode, struct writeback_control *wbc)
goto out;
if (S_ISDIR(main_inode->i_mode)) {
- if (fd.entrylength < sizeof(struct hfs_cat_dir))
- /* panic? */;
+ WARN_ON(fd.entrylength < sizeof(struct hfs_cat_dir));
hfs_bnode_read(fd.bnode, &rec, fd.entryoffset,
sizeof(struct hfs_cat_dir));
if (rec.type != HFS_CDR_DIR ||
@@ -483,8 +482,7 @@ int hfs_write_inode(struct inode *inode, struct writeback_control *wbc)
hfs_bnode_write(fd.bnode, &rec, fd.entryoffset,
sizeof(struct hfs_cat_file));
} else {
- if (fd.entrylength < sizeof(struct hfs_cat_file))
- /* panic? */;
+ WARN_ON(fd.entrylength < sizeof(struct hfs_cat_file));
hfs_bnode_read(fd.bnode, &rec, fd.entryoffset,
sizeof(struct hfs_cat_file));
if (rec.type != HFS_CDR_FIL ||
diff --git a/fs/hfsplus/inode.c b/fs/hfsplus/inode.c
index 6fef67c2a9f0..d08a8d1d40a4 100644
--- a/fs/hfsplus/inode.c
+++ b/fs/hfsplus/inode.c
@@ -509,8 +509,7 @@ int hfsplus_cat_read_inode(struct inode *inode, struct hfs_find_data *fd)
if (type == HFSPLUS_FOLDER) {
struct hfsplus_cat_folder *folder = &entry.folder;
- if (fd->entrylength < sizeof(struct hfsplus_cat_folder))
- /* panic? */;
+ WARN_ON(fd->entrylength < sizeof(struct hfsplus_cat_folder));
hfs_bnode_read(fd->bnode, &entry, fd->entryoffset,
sizeof(struct hfsplus_cat_folder));
hfsplus_get_perms(inode, &folder->permissions, 1);
@@ -530,8 +529,7 @@ int hfsplus_cat_read_inode(struct inode *inode, struct hfs_find_data *fd)
} else if (type == HFSPLUS_FILE) {
struct hfsplus_cat_file *file = &entry.file;
- if (fd->entrylength < sizeof(struct hfsplus_cat_file))
- /* panic? */;
+ WARN_ON(fd->entrylength < sizeof(struct hfsplus_cat_file));
hfs_bnode_read(fd->bnode, &entry, fd->entryoffset,
sizeof(struct hfsplus_cat_file));
@@ -588,8 +586,7 @@ int hfsplus_cat_write_inode(struct inode *inode)
if (S_ISDIR(main_inode->i_mode)) {
struct hfsplus_cat_folder *folder = &entry.folder;
- if (fd.entrylength < sizeof(struct hfsplus_cat_folder))
- /* panic? */;
+ WARN_ON(fd.entrylength < sizeof(struct hfsplus_cat_folder));
hfs_bnode_read(fd.bnode, &entry, fd.entryoffset,
sizeof(struct hfsplus_cat_folder));
/* simple node checks? */
@@ -614,8 +611,7 @@ int hfsplus_cat_write_inode(struct inode *inode)
} else {
struct hfsplus_cat_file *file = &entry.file;
- if (fd.entrylength < sizeof(struct hfsplus_cat_file))
- /* panic? */;
+ WARN_ON(fd.entrylength < sizeof(struct hfsplus_cat_file));
hfs_bnode_read(fd.bnode, &entry, fd.entryoffset,
sizeof(struct hfsplus_cat_file));
hfsplus_inode_write_fork(inode, &file->data_fork);
diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c
index cdfb1ae78a3f..49d2e686be74 100644
--- a/fs/hugetlbfs/inode.c
+++ b/fs/hugetlbfs/inode.c
@@ -1446,8 +1446,8 @@ static int get_hstate_idx(int page_size_log)
* otherwise hugetlb_reserve_pages reserves one less hugepages than intended.
*/
struct file *hugetlb_file_setup(const char *name, size_t size,
- vm_flags_t acctflag, struct ucounts **ucounts,
- int creat_flags, int page_size_log)
+ vm_flags_t acctflag, int creat_flags,
+ int page_size_log)
{
struct inode *inode;
struct vfsmount *mnt;
@@ -1458,22 +1458,19 @@ struct file *hugetlb_file_setup(const char *name, size_t size,
if (hstate_idx < 0)
return ERR_PTR(-ENODEV);
- *ucounts = NULL;
mnt = hugetlbfs_vfsmount[hstate_idx];
if (!mnt)
return ERR_PTR(-ENOENT);
if (creat_flags == HUGETLB_SHMFS_INODE && !can_do_hugetlb_shm()) {
- *ucounts = current_ucounts();
- if (user_shm_lock(size, *ucounts)) {
- task_lock(current);
- pr_warn_once("%s (%d): Using mlock ulimits for SHM_HUGETLB is deprecated\n",
+ struct ucounts *ucounts = current_ucounts();
+
+ if (user_shm_lock(size, ucounts)) {
+ pr_warn_once("%s (%d): Using mlock ulimits for SHM_HUGETLB is obsolete\n",
current->comm, current->pid);
- task_unlock(current);
- } else {
- *ucounts = NULL;
- return ERR_PTR(-EPERM);
+ user_shm_unlock(size, ucounts);
}
+ return ERR_PTR(-EPERM);
}
file = ERR_PTR(-ENOSPC);
@@ -1498,10 +1495,6 @@ struct file *hugetlb_file_setup(const char *name, size_t size,
iput(inode);
out:
- if (*ucounts) {
- user_shm_unlock(size, *ucounts);
- *ucounts = NULL;
- }
return file;
}
diff --git a/fs/inode.c b/fs/inode.c
index 9abc88d7959c..3eba0940ffcf 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -428,11 +428,20 @@ void ihold(struct inode *inode)
}
EXPORT_SYMBOL(ihold);
-static void inode_lru_list_add(struct inode *inode)
+static void __inode_add_lru(struct inode *inode, bool rotate)
{
+ if (inode->i_state & (I_DIRTY_ALL | I_SYNC | I_FREEING | I_WILL_FREE))
+ return;
+ if (atomic_read(&inode->i_count))
+ return;
+ if (!(inode->i_sb->s_flags & SB_ACTIVE))
+ return;
+ if (!mapping_shrinkable(&inode->i_data))
+ return;
+
if (list_lru_add(&inode->i_sb->s_inode_lru, &inode->i_lru))
this_cpu_inc(nr_unused);
- else
+ else if (rotate)
inode->i_state |= I_REFERENCED;
}
@@ -443,16 +452,11 @@ static void inode_lru_list_add(struct inode *inode)
*/
void inode_add_lru(struct inode *inode)
{
- if (!(inode->i_state & (I_DIRTY_ALL | I_SYNC |
- I_FREEING | I_WILL_FREE)) &&
- !atomic_read(&inode->i_count) && inode->i_sb->s_flags & SB_ACTIVE)
- inode_lru_list_add(inode);
+ __inode_add_lru(inode, false);
}
-
static void inode_lru_list_del(struct inode *inode)
{
-
if (list_lru_del(&inode->i_sb->s_inode_lru, &inode->i_lru))
this_cpu_dec(nr_unused);
}
@@ -728,10 +732,6 @@ again:
/*
* Isolate the inode from the LRU in preparation for freeing it.
*
- * Any inodes which are pinned purely because of attached pagecache have their
- * pagecache removed. If the inode has metadata buffers attached to
- * mapping->private_list then try to remove them.
- *
* If the inode has the I_REFERENCED flag set, then it means that it has been
* used recently - the flag is set in iput_final(). When we encounter such an
* inode, clear the flag and move it to the back of the LRU so it gets another
@@ -747,31 +747,39 @@ static enum lru_status inode_lru_isolate(struct list_head *item,
struct inode *inode = container_of(item, struct inode, i_lru);
/*
- * we are inverting the lru lock/inode->i_lock here, so use a trylock.
- * If we fail to get the lock, just skip it.
+ * We are inverting the lru lock/inode->i_lock here, so use a
+ * trylock. If we fail to get the lock, just skip it.
*/
if (!spin_trylock(&inode->i_lock))
return LRU_SKIP;
/*
- * Referenced or dirty inodes are still in use. Give them another pass
- * through the LRU as we canot reclaim them now.
+ * Inodes can get referenced, redirtied, or repopulated while
+ * they're already on the LRU, and this can make them
+ * unreclaimable for a while. Remove them lazily here; iput,
+ * sync, or the last page cache deletion will requeue them.
*/
if (atomic_read(&inode->i_count) ||
- (inode->i_state & ~I_REFERENCED)) {
+ (inode->i_state & ~I_REFERENCED) ||
+ !mapping_shrinkable(&inode->i_data)) {
list_lru_isolate(lru, &inode->i_lru);
spin_unlock(&inode->i_lock);
this_cpu_dec(nr_unused);
return LRU_REMOVED;
}
- /* recently referenced inodes get one more pass */
+ /* Recently referenced inodes get one more pass */
if (inode->i_state & I_REFERENCED) {
inode->i_state &= ~I_REFERENCED;
spin_unlock(&inode->i_lock);
return LRU_ROTATE;
}
+ /*
+ * On highmem systems, mapping_shrinkable() permits dropping
+ * page cache in order to free up struct inodes: lowmem might
+ * be under pressure before the cache inside the highmem zone.
+ */
if (inode_has_buffers(inode) || !mapping_empty(&inode->i_data)) {
__iget(inode);
spin_unlock(&inode->i_lock);
@@ -1638,7 +1646,7 @@ static void iput_final(struct inode *inode)
if (!drop &&
!(inode->i_state & I_DONTCACHE) &&
(sb->s_flags & SB_ACTIVE)) {
- inode_add_lru(inode);
+ __inode_add_lru(inode, true);
spin_unlock(&inode->i_lock);
return;
}
diff --git a/fs/internal.h b/fs/internal.h
index cdd83d4899bb..7979ff8d168c 100644
--- a/fs/internal.h
+++ b/fs/internal.h
@@ -138,7 +138,6 @@ extern int vfs_open(const struct path *, struct file *);
* inode.c
*/
extern long prune_icache_sb(struct super_block *sb, struct shrink_control *sc);
-extern void inode_add_lru(struct inode *inode);
extern int dentry_needs_remove_privs(struct dentry *dentry);
/*
diff --git a/fs/io-wq.c b/fs/io-wq.c
index c51691262208..afd955d53db9 100644
--- a/fs/io-wq.c
+++ b/fs/io-wq.c
@@ -1308,7 +1308,9 @@ int io_wq_cpu_affinity(struct io_wq *wq, cpumask_var_t mask)
*/
int io_wq_max_workers(struct io_wq *wq, int *new_count)
{
- int i, node, prev = 0;
+ int prev[IO_WQ_ACCT_NR];
+ bool first_node = true;
+ int i, node;
BUILD_BUG_ON((int) IO_WQ_ACCT_BOUND != (int) IO_WQ_BOUND);
BUILD_BUG_ON((int) IO_WQ_ACCT_UNBOUND != (int) IO_WQ_UNBOUND);
@@ -1319,6 +1321,9 @@ int io_wq_max_workers(struct io_wq *wq, int *new_count)
new_count[i] = task_rlimit(current, RLIMIT_NPROC);
}
+ for (i = 0; i < IO_WQ_ACCT_NR; i++)
+ prev[i] = 0;
+
rcu_read_lock();
for_each_node(node) {
struct io_wqe *wqe = wq->wqes[node];
@@ -1327,14 +1332,19 @@ int io_wq_max_workers(struct io_wq *wq, int *new_count)
raw_spin_lock(&wqe->lock);
for (i = 0; i < IO_WQ_ACCT_NR; i++) {
acct = &wqe->acct[i];
- prev = max_t(int, acct->max_workers, prev);
+ if (first_node)
+ prev[i] = max_t(int, acct->max_workers, prev[i]);
if (new_count[i])
acct->max_workers = new_count[i];
- new_count[i] = prev;
}
raw_spin_unlock(&wqe->lock);
+ first_node = false;
}
rcu_read_unlock();
+
+ for (i = 0; i < IO_WQ_ACCT_NR; i++)
+ new_count[i] = prev[i];
+
return 0;
}
diff --git a/fs/io_uring.c b/fs/io_uring.c
index 3ecd4b51510e..b07196b4511c 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -6950,10 +6950,6 @@ static void io_queue_sqe_arm_apoll(struct io_kiocb *req)
switch (io_arm_poll_handler(req)) {
case IO_APOLL_READY:
- if (linked_timeout) {
- io_queue_linked_timeout(linked_timeout);
- linked_timeout = NULL;
- }
io_req_task_queue(req);
break;
case IO_APOLL_ABORTED:
@@ -10144,7 +10140,7 @@ static __cold void __io_uring_show_fdinfo(struct io_ring_ctx *ctx,
for (i = 0; i < sq_entries; i++) {
unsigned int entry = i + sq_head;
unsigned int sq_idx = READ_ONCE(ctx->sq_array[entry & sq_mask]);
- struct io_uring_sqe *sqe = &ctx->sq_sqes[sq_idx];
+ struct io_uring_sqe *sqe;
if (sq_idx > sq_mask)
continue;
@@ -10795,10 +10791,11 @@ static __cold int io_register_iowq_max_workers(struct io_ring_ctx *ctx,
BUILD_BUG_ON(sizeof(new_count) != sizeof(ctx->iowq_limits));
- memcpy(ctx->iowq_limits, new_count, sizeof(new_count));
+ for (i = 0; i < ARRAY_SIZE(new_count); i++)
+ if (new_count[i])
+ ctx->iowq_limits[i] = new_count[i];
ctx->iowq_limits_set = true;
- ret = -EINVAL;
if (tctx && tctx->io_wq) {
ret = io_wq_max_workers(tctx->io_wq, new_count);
if (ret)
diff --git a/fs/isofs/inode.c b/fs/isofs/inode.c
index 678e2c51b855..0c6eacfcbeef 100644
--- a/fs/isofs/inode.c
+++ b/fs/isofs/inode.c
@@ -1322,6 +1322,8 @@ static int isofs_read_inode(struct inode *inode, int relocated)
de = (struct iso_directory_record *) (bh->b_data + offset);
de_len = *(unsigned char *) de;
+ if (de_len < sizeof(struct iso_directory_record))
+ goto fail;
if (offset + de_len > bufsize) {
int frag1 = bufsize - offset;
diff --git a/fs/jfs/jfs_mount.c b/fs/jfs/jfs_mount.c
index 5d7d7170c03c..aa4ff7bcaff2 100644
--- a/fs/jfs/jfs_mount.c
+++ b/fs/jfs/jfs_mount.c
@@ -81,14 +81,14 @@ int jfs_mount(struct super_block *sb)
* (initialize mount inode from the superblock)
*/
if ((rc = chkSuper(sb))) {
- goto errout20;
+ goto out;
}
ipaimap = diReadSpecial(sb, AGGREGATE_I, 0);
if (ipaimap == NULL) {
jfs_err("jfs_mount: Failed to read AGGREGATE_I");
rc = -EIO;
- goto errout20;
+ goto out;
}
sbi->ipaimap = ipaimap;
@@ -99,7 +99,7 @@ int jfs_mount(struct super_block *sb)
*/
if ((rc = diMount(ipaimap))) {
jfs_err("jfs_mount: diMount(ipaimap) failed w/rc = %d", rc);
- goto errout21;
+ goto err_ipaimap;
}
/*
@@ -108,7 +108,7 @@ int jfs_mount(struct super_block *sb)
ipbmap = diReadSpecial(sb, BMAP_I, 0);
if (ipbmap == NULL) {
rc = -EIO;
- goto errout22;
+ goto err_umount_ipaimap;
}
jfs_info("jfs_mount: ipbmap:0x%p", ipbmap);
@@ -120,7 +120,7 @@ int jfs_mount(struct super_block *sb)
*/
if ((rc = dbMount(ipbmap))) {
jfs_err("jfs_mount: dbMount failed w/rc = %d", rc);
- goto errout22;
+ goto err_ipbmap;
}
/*
@@ -139,7 +139,7 @@ int jfs_mount(struct super_block *sb)
if (!ipaimap2) {
jfs_err("jfs_mount: Failed to read AGGREGATE_I");
rc = -EIO;
- goto errout35;
+ goto err_umount_ipbmap;
}
sbi->ipaimap2 = ipaimap2;
@@ -151,7 +151,7 @@ int jfs_mount(struct super_block *sb)
if ((rc = diMount(ipaimap2))) {
jfs_err("jfs_mount: diMount(ipaimap2) failed, rc = %d",
rc);
- goto errout35;
+ goto err_ipaimap2;
}
} else
/* Secondary aggregate inode table is not valid */
@@ -168,7 +168,7 @@ int jfs_mount(struct super_block *sb)
jfs_err("jfs_mount: Failed to read FILESYSTEM_I");
/* open fileset secondary inode allocation map */
rc = -EIO;
- goto errout40;
+ goto err_umount_ipaimap2;
}
jfs_info("jfs_mount: ipimap:0x%p", ipimap);
@@ -178,41 +178,34 @@ int jfs_mount(struct super_block *sb)
/* initialize fileset inode allocation map */
if ((rc = diMount(ipimap))) {
jfs_err("jfs_mount: diMount failed w/rc = %d", rc);
- goto errout41;
+ goto err_ipimap;
}
- goto out;
+ return rc;
/*
* unwind on error
*/
- errout41: /* close fileset inode allocation map inode */
+err_ipimap:
+ /* close fileset inode allocation map inode */
diFreeSpecial(ipimap);
-
- errout40: /* fileset closed */
-
+err_umount_ipaimap2:
/* close secondary aggregate inode allocation map */
- if (ipaimap2) {
+ if (ipaimap2)
diUnmount(ipaimap2, 1);
+err_ipaimap2:
+ /* close aggregate inodes */
+ if (ipaimap2)
diFreeSpecial(ipaimap2);
- }
-
- errout35:
-
- /* close aggregate block allocation map */
+err_umount_ipbmap: /* close aggregate block allocation map */
dbUnmount(ipbmap, 1);
+err_ipbmap: /* close aggregate inodes */
diFreeSpecial(ipbmap);
-
- errout22: /* close aggregate inode allocation map */
-
+err_umount_ipaimap: /* close aggregate inode allocation map */
diUnmount(ipaimap, 1);
-
- errout21: /* close aggregate inodes */
+err_ipaimap: /* close aggregate inodes */
diFreeSpecial(ipaimap);
- errout20: /* aggregate closed */
-
- out:
-
+out:
if (rc)
jfs_err("Mount JFS Failure: %d", rc);
diff --git a/fs/kernfs/symlink.c b/fs/kernfs/symlink.c
index c8f8e41b8411..19a6c71c6ff5 100644
--- a/fs/kernfs/symlink.c
+++ b/fs/kernfs/symlink.c
@@ -36,8 +36,7 @@ struct kernfs_node *kernfs_create_link(struct kernfs_node *parent,
gid = target->iattr->ia_gid;
}
- kn = kernfs_new_node(parent, name, S_IFLNK|S_IRWXUGO, uid, gid,
- KERNFS_LINK);
+ kn = kernfs_new_node(parent, name, S_IFLNK|0777, uid, gid, KERNFS_LINK);
if (!kn)
return ERR_PTR(-ENOMEM);
diff --git a/fs/lockd/clntproc.c b/fs/lockd/clntproc.c
index b11f2afa84f1..99fffc9cb958 100644
--- a/fs/lockd/clntproc.c
+++ b/fs/lockd/clntproc.c
@@ -794,9 +794,6 @@ static void nlmclnt_cancel_callback(struct rpc_task *task, void *data)
goto retry_cancel;
}
- dprintk("lockd: cancel status %u (task %u)\n",
- status, task->tk_pid);
-
switch (status) {
case NLM_LCK_GRANTED:
case NLM_LCK_DENIED_GRACE_PERIOD:
diff --git a/fs/lockd/svc.c b/fs/lockd/svc.c
index b632be3ad57b..b220e1b91726 100644
--- a/fs/lockd/svc.c
+++ b/fs/lockd/svc.c
@@ -780,11 +780,9 @@ module_exit(exit_nlm);
static int nlmsvc_dispatch(struct svc_rqst *rqstp, __be32 *statp)
{
const struct svc_procedure *procp = rqstp->rq_procinfo;
- struct kvec *argv = rqstp->rq_arg.head;
- struct kvec *resv = rqstp->rq_res.head;
svcxdr_init_decode(rqstp);
- if (!procp->pc_decode(rqstp, argv->iov_base))
+ if (!procp->pc_decode(rqstp, &rqstp->rq_arg_stream))
goto out_decode_err;
*statp = procp->pc_func(rqstp);
@@ -794,7 +792,7 @@ static int nlmsvc_dispatch(struct svc_rqst *rqstp, __be32 *statp)
return 1;
svcxdr_init_encode(rqstp);
- if (!procp->pc_encode(rqstp, resv->iov_base + resv->iov_len))
+ if (!procp->pc_encode(rqstp, &rqstp->rq_res_stream))
goto out_encode_err;
return 1;
diff --git a/fs/lockd/svc4proc.c b/fs/lockd/svc4proc.c
index e10ae2c41279..176b468a61c7 100644
--- a/fs/lockd/svc4proc.c
+++ b/fs/lockd/svc4proc.c
@@ -269,8 +269,6 @@ nlm4svc_proc_granted(struct svc_rqst *rqstp)
*/
static void nlm4svc_callback_exit(struct rpc_task *task, void *data)
{
- dprintk("lockd: %5u callback returned %d\n", task->tk_pid,
- -task->tk_status);
}
static void nlm4svc_callback_release(void *data)
diff --git a/fs/lockd/svcproc.c b/fs/lockd/svcproc.c
index 99696d3f6dd6..4dc1b40a489a 100644
--- a/fs/lockd/svcproc.c
+++ b/fs/lockd/svcproc.c
@@ -301,8 +301,6 @@ nlmsvc_proc_granted(struct svc_rqst *rqstp)
*/
static void nlmsvc_callback_exit(struct rpc_task *task, void *data)
{
- dprintk("lockd: %5u callback returned %d\n", task->tk_pid,
- -task->tk_status);
}
void nlmsvc_release_call(struct nlm_rqst *call)
diff --git a/fs/lockd/xdr.c b/fs/lockd/xdr.c
index 9235e60b1769..2fb5748dae0c 100644
--- a/fs/lockd/xdr.c
+++ b/fs/lockd/xdr.c
@@ -145,137 +145,131 @@ svcxdr_encode_testrply(struct xdr_stream *xdr, const struct nlm_res *resp)
* Decode Call arguments
*/
-int
-nlmsvc_decode_void(struct svc_rqst *rqstp, __be32 *p)
+bool
+nlmsvc_decode_void(struct svc_rqst *rqstp, struct xdr_stream *xdr)
{
- return 1;
+ return true;
}
-int
-nlmsvc_decode_testargs(struct svc_rqst *rqstp, __be32 *p)
+bool
+nlmsvc_decode_testargs(struct svc_rqst *rqstp, struct xdr_stream *xdr)
{
- struct xdr_stream *xdr = &rqstp->rq_arg_stream;
struct nlm_args *argp = rqstp->rq_argp;
u32 exclusive;
if (!svcxdr_decode_cookie(xdr, &argp->cookie))
- return 0;
+ return false;
if (xdr_stream_decode_bool(xdr, &exclusive) < 0)
- return 0;
+ return false;
if (!svcxdr_decode_lock(xdr, &argp->lock))
- return 0;
+ return false;
if (exclusive)
argp->lock.fl.fl_type = F_WRLCK;
- return 1;
+ return true;
}
-int
-nlmsvc_decode_lockargs(struct svc_rqst *rqstp, __be32 *p)
+bool
+nlmsvc_decode_lockargs(struct svc_rqst *rqstp, struct xdr_stream *xdr)
{
- struct xdr_stream *xdr = &rqstp->rq_arg_stream;
struct nlm_args *argp = rqstp->rq_argp;
u32 exclusive;
if (!svcxdr_decode_cookie(xdr, &argp->cookie))
- return 0;
+ return false;
if (xdr_stream_decode_bool(xdr, &argp->block) < 0)
- return 0;
+ return false;
if (xdr_stream_decode_bool(xdr, &exclusive) < 0)
- return 0;
+ return false;
if (!svcxdr_decode_lock(xdr, &argp->lock))
- return 0;
+ return false;
if (exclusive)
argp->lock.fl.fl_type = F_WRLCK;
if (xdr_stream_decode_bool(xdr, &argp->reclaim) < 0)
- return 0;
+ return false;
if (xdr_stream_decode_u32(xdr, &argp->state) < 0)
- return 0;
+ return false;
argp->monitor = 1; /* monitor client by default */
- return 1;
+ return true;
}
-int
-nlmsvc_decode_cancargs(struct svc_rqst *rqstp, __be32 *p)
+bool
+nlmsvc_decode_cancargs(struct svc_rqst *rqstp, struct xdr_stream *xdr)
{
- struct xdr_stream *xdr = &rqstp->rq_arg_stream;
struct nlm_args *argp = rqstp->rq_argp;
u32 exclusive;
if (!svcxdr_decode_cookie(xdr, &argp->cookie))
- return 0;
+ return false;
if (xdr_stream_decode_bool(xdr, &argp->block) < 0)
- return 0;
+ return false;
if (xdr_stream_decode_bool(xdr, &exclusive) < 0)
- return 0;
+ return false;
if (!svcxdr_decode_lock(xdr, &argp->lock))
- return 0;
+ return false;
if (exclusive)
argp->lock.fl.fl_type = F_WRLCK;
- return 1;
+ return true;
}
-int
-nlmsvc_decode_unlockargs(struct svc_rqst *rqstp, __be32 *p)
+bool
+nlmsvc_decode_unlockargs(struct svc_rqst *rqstp, struct xdr_stream *xdr)
{
- struct xdr_stream *xdr = &rqstp->rq_arg_stream;
struct nlm_args *argp = rqstp->rq_argp;
if (!svcxdr_decode_cookie(xdr, &argp->cookie))
- return 0;
+ return false;
if (!svcxdr_decode_lock(xdr, &argp->lock))
- return 0;
+ return false;
argp->lock.fl.fl_type = F_UNLCK;
- return 1;
+ return true;
}
-int
-nlmsvc_decode_res(struct svc_rqst *rqstp, __be32 *p)
+bool
+nlmsvc_decode_res(struct svc_rqst *rqstp, struct xdr_stream *xdr)
{
- struct xdr_stream *xdr = &rqstp->rq_arg_stream;
struct nlm_res *resp = rqstp->rq_argp;
if (!svcxdr_decode_cookie(xdr, &resp->cookie))
- return 0;
+ return false;
if (!svcxdr_decode_stats(xdr, &resp->status))
- return 0;
+ return false;
- return 1;
+ return true;
}
-int
-nlmsvc_decode_reboot(struct svc_rqst *rqstp, __be32 *p)
+bool
+nlmsvc_decode_reboot(struct svc_rqst *rqstp, struct xdr_stream *xdr)
{
- struct xdr_stream *xdr = &rqstp->rq_arg_stream;
struct nlm_reboot *argp = rqstp->rq_argp;
+ __be32 *p;
u32 len;
if (xdr_stream_decode_u32(xdr, &len) < 0)
- return 0;
+ return false;
if (len > SM_MAXSTRLEN)
- return 0;
+ return false;
p = xdr_inline_decode(xdr, len);
if (!p)
- return 0;
+ return false;
argp->len = len;
argp->mon = (char *)p;
if (xdr_stream_decode_u32(xdr, &argp->state) < 0)
- return 0;
+ return false;
p = xdr_inline_decode(xdr, SM_PRIV_SIZE);
if (!p)
- return 0;
+ return false;
memcpy(&argp->priv.data, p, sizeof(argp->priv.data));
- return 1;
+ return true;
}
-int
-nlmsvc_decode_shareargs(struct svc_rqst *rqstp, __be32 *p)
+bool
+nlmsvc_decode_shareargs(struct svc_rqst *rqstp, struct xdr_stream *xdr)
{
- struct xdr_stream *xdr = &rqstp->rq_arg_stream;
struct nlm_args *argp = rqstp->rq_argp;
struct nlm_lock *lock = &argp->lock;
@@ -284,35 +278,34 @@ nlmsvc_decode_shareargs(struct svc_rqst *rqstp, __be32 *p)
lock->svid = ~(u32)0;
if (!svcxdr_decode_cookie(xdr, &argp->cookie))
- return 0;
+ return false;
if (!svcxdr_decode_string(xdr, &lock->caller, &lock->len))
- return 0;
+ return false;
if (!svcxdr_decode_fhandle(xdr, &lock->fh))
- return 0;
+ return false;
if (!svcxdr_decode_owner(xdr, &lock->oh))
- return 0;
+ return false;
/* XXX: Range checks are missing in the original code */
if (xdr_stream_decode_u32(xdr, &argp->fsm_mode) < 0)
- return 0;
+ return false;
if (xdr_stream_decode_u32(xdr, &argp->fsm_access) < 0)
- return 0;
+ return false;
- return 1;
+ return true;
}
-int
-nlmsvc_decode_notify(struct svc_rqst *rqstp, __be32 *p)
+bool
+nlmsvc_decode_notify(struct svc_rqst *rqstp, struct xdr_stream *xdr)
{
- struct xdr_stream *xdr = &rqstp->rq_arg_stream;
struct nlm_args *argp = rqstp->rq_argp;
struct nlm_lock *lock = &argp->lock;
if (!svcxdr_decode_string(xdr, &lock->caller, &lock->len))
- return 0;
+ return false;
if (xdr_stream_decode_u32(xdr, &argp->state) < 0)
- return 0;
+ return false;
- return 1;
+ return true;
}
@@ -320,45 +313,42 @@ nlmsvc_decode_notify(struct svc_rqst *rqstp, __be32 *p)
* Encode Reply results
*/
-int
-nlmsvc_encode_void(struct svc_rqst *rqstp, __be32 *p)
+bool
+nlmsvc_encode_void(struct svc_rqst *rqstp, struct xdr_stream *xdr)
{
- return 1;
+ return true;
}
-int
-nlmsvc_encode_testres(struct svc_rqst *rqstp, __be32 *p)
+bool
+nlmsvc_encode_testres(struct svc_rqst *rqstp, struct xdr_stream *xdr)
{
- struct xdr_stream *xdr = &rqstp->rq_res_stream;
struct nlm_res *resp = rqstp->rq_resp;
return svcxdr_encode_cookie(xdr, &resp->cookie) &&
svcxdr_encode_testrply(xdr, resp);
}
-int
-nlmsvc_encode_res(struct svc_rqst *rqstp, __be32 *p)
+bool
+nlmsvc_encode_res(struct svc_rqst *rqstp, struct xdr_stream *xdr)
{
- struct xdr_stream *xdr = &rqstp->rq_res_stream;
struct nlm_res *resp = rqstp->rq_resp;
return svcxdr_encode_cookie(xdr, &resp->cookie) &&
svcxdr_encode_stats(xdr, resp->status);
}
-int
-nlmsvc_encode_shareres(struct svc_rqst *rqstp, __be32 *p)
+bool
+nlmsvc_encode_shareres(struct svc_rqst *rqstp, struct xdr_stream *xdr)
{
- struct xdr_stream *xdr = &rqstp->rq_res_stream;
struct nlm_res *resp = rqstp->rq_resp;
if (!svcxdr_encode_cookie(xdr, &resp->cookie))
- return 0;
+ return false;
if (!svcxdr_encode_stats(xdr, resp->status))
- return 0;
+ return false;
/* sequence */
if (xdr_stream_encode_u32(xdr, 0) < 0)
- return 0;
+ return false;
- return 1;
+ return true;
}
diff --git a/fs/lockd/xdr4.c b/fs/lockd/xdr4.c
index 98e957e4566c..856267c0864b 100644
--- a/fs/lockd/xdr4.c
+++ b/fs/lockd/xdr4.c
@@ -144,136 +144,131 @@ svcxdr_encode_testrply(struct xdr_stream *xdr, const struct nlm_res *resp)
* Decode Call arguments
*/
-int
-nlm4svc_decode_void(struct svc_rqst *rqstp, __be32 *p)
+bool
+nlm4svc_decode_void(struct svc_rqst *rqstp, struct xdr_stream *xdr)
{
- return 1;
+ return true;
}
-int
-nlm4svc_decode_testargs(struct svc_rqst *rqstp, __be32 *p)
+bool
+nlm4svc_decode_testargs(struct svc_rqst *rqstp, struct xdr_stream *xdr)
{
- struct xdr_stream *xdr = &rqstp->rq_arg_stream;
struct nlm_args *argp = rqstp->rq_argp;
u32 exclusive;
if (!svcxdr_decode_cookie(xdr, &argp->cookie))
- return 0;
+ return false;
if (xdr_stream_decode_bool(xdr, &exclusive) < 0)
- return 0;
+ return false;
if (!svcxdr_decode_lock(xdr, &argp->lock))
- return 0;
+ return false;
if (exclusive)
argp->lock.fl.fl_type = F_WRLCK;
- return 1;
+ return true;
}
-int
-nlm4svc_decode_lockargs(struct svc_rqst *rqstp, __be32 *p)
+bool
+nlm4svc_decode_lockargs(struct svc_rqst *rqstp, struct xdr_stream *xdr)
{
- struct xdr_stream *xdr = &rqstp->rq_arg_stream;
struct nlm_args *argp = rqstp->rq_argp;
u32 exclusive;
if (!svcxdr_decode_cookie(xdr, &argp->cookie))
- return 0;
+ return false;
if (xdr_stream_decode_bool(xdr, &argp->block) < 0)
- return 0;
+ return false;
if (xdr_stream_decode_bool(xdr, &exclusive) < 0)
- return 0;
+ return false;
if (!svcxdr_decode_lock(xdr, &argp->lock))
- return 0;
+ return false;
if (exclusive)
argp->lock.fl.fl_type = F_WRLCK;
if (xdr_stream_decode_bool(xdr, &argp->reclaim) < 0)
- return 0;
+ return false;
if (xdr_stream_decode_u32(xdr, &argp->state) < 0)
- return 0;
+ return false;
argp->monitor = 1; /* monitor client by default */
- return 1;
+ return true;
}
-int
-nlm4svc_decode_cancargs(struct svc_rqst *rqstp, __be32 *p)
+bool
+nlm4svc_decode_cancargs(struct svc_rqst *rqstp, struct xdr_stream *xdr)
{
- struct xdr_stream *xdr = &rqstp->rq_arg_stream;
struct nlm_args *argp = rqstp->rq_argp;
u32 exclusive;
if (!svcxdr_decode_cookie(xdr, &argp->cookie))
- return 0;
+ return false;
if (xdr_stream_decode_bool(xdr, &argp->block) < 0)
- return 0;
+ return false;
if (xdr_stream_decode_bool(xdr, &exclusive) < 0)
- return 0;
+ return false;
if (!svcxdr_decode_lock(xdr, &argp->lock))
- return 0;
+ return false;
if (exclusive)
argp->lock.fl.fl_type = F_WRLCK;
- return 1;
+
+ return true;
}
-int
-nlm4svc_decode_unlockargs(struct svc_rqst *rqstp, __be32 *p)
+bool
+nlm4svc_decode_unlockargs(struct svc_rqst *rqstp, struct xdr_stream *xdr)
{
- struct xdr_stream *xdr = &rqstp->rq_arg_stream;
struct nlm_args *argp = rqstp->rq_argp;
if (!svcxdr_decode_cookie(xdr, &argp->cookie))
- return 0;
+ return false;
if (!svcxdr_decode_lock(xdr, &argp->lock))
- return 0;
+ return false;
argp->lock.fl.fl_type = F_UNLCK;
- return 1;
+ return true;
}
-int
-nlm4svc_decode_res(struct svc_rqst *rqstp, __be32 *p)
+bool
+nlm4svc_decode_res(struct svc_rqst *rqstp, struct xdr_stream *xdr)
{
- struct xdr_stream *xdr = &rqstp->rq_arg_stream;
struct nlm_res *resp = rqstp->rq_argp;
if (!svcxdr_decode_cookie(xdr, &resp->cookie))
- return 0;
+ return false;
if (!svcxdr_decode_stats(xdr, &resp->status))
- return 0;
+ return false;
- return 1;
+ return true;
}
-int
-nlm4svc_decode_reboot(struct svc_rqst *rqstp, __be32 *p)
+bool
+nlm4svc_decode_reboot(struct svc_rqst *rqstp, struct xdr_stream *xdr)
{
- struct xdr_stream *xdr = &rqstp->rq_arg_stream;
struct nlm_reboot *argp = rqstp->rq_argp;
+ __be32 *p;
u32 len;
if (xdr_stream_decode_u32(xdr, &len) < 0)
- return 0;
+ return false;
if (len > SM_MAXSTRLEN)
- return 0;
+ return false;
p = xdr_inline_decode(xdr, len);
if (!p)
- return 0;
+ return false;
argp->len = len;
argp->mon = (char *)p;
if (xdr_stream_decode_u32(xdr, &argp->state) < 0)
- return 0;
+ return false;
p = xdr_inline_decode(xdr, SM_PRIV_SIZE);
if (!p)
- return 0;
+ return false;
memcpy(&argp->priv.data, p, sizeof(argp->priv.data));
- return 1;
+ return true;
}
-int
-nlm4svc_decode_shareargs(struct svc_rqst *rqstp, __be32 *p)
+bool
+nlm4svc_decode_shareargs(struct svc_rqst *rqstp, struct xdr_stream *xdr)
{
- struct xdr_stream *xdr = &rqstp->rq_arg_stream;
struct nlm_args *argp = rqstp->rq_argp;
struct nlm_lock *lock = &argp->lock;
@@ -282,35 +277,34 @@ nlm4svc_decode_shareargs(struct svc_rqst *rqstp, __be32 *p)
lock->svid = ~(u32)0;
if (!svcxdr_decode_cookie(xdr, &argp->cookie))
- return 0;
+ return false;
if (!svcxdr_decode_string(xdr, &lock->caller, &lock->len))
- return 0;
+ return false;
if (!svcxdr_decode_fhandle(xdr, &lock->fh))
- return 0;
+ return false;
if (!svcxdr_decode_owner(xdr, &lock->oh))
- return 0;
+ return false;
/* XXX: Range checks are missing in the original code */
if (xdr_stream_decode_u32(xdr, &argp->fsm_mode) < 0)
- return 0;
+ return false;
if (xdr_stream_decode_u32(xdr, &argp->fsm_access) < 0)
- return 0;
+ return false;
- return 1;
+ return true;
}
-int
-nlm4svc_decode_notify(struct svc_rqst *rqstp, __be32 *p)
+bool
+nlm4svc_decode_notify(struct svc_rqst *rqstp, struct xdr_stream *xdr)
{
- struct xdr_stream *xdr = &rqstp->rq_arg_stream;
struct nlm_args *argp = rqstp->rq_argp;
struct nlm_lock *lock = &argp->lock;
if (!svcxdr_decode_string(xdr, &lock->caller, &lock->len))
- return 0;
+ return false;
if (xdr_stream_decode_u32(xdr, &argp->state) < 0)
- return 0;
+ return false;
- return 1;
+ return true;
}
@@ -318,45 +312,42 @@ nlm4svc_decode_notify(struct svc_rqst *rqstp, __be32 *p)
* Encode Reply results
*/
-int
-nlm4svc_encode_void(struct svc_rqst *rqstp, __be32 *p)
+bool
+nlm4svc_encode_void(struct svc_rqst *rqstp, struct xdr_stream *xdr)
{
- return 1;
+ return true;
}
-int
-nlm4svc_encode_testres(struct svc_rqst *rqstp, __be32 *p)
+bool
+nlm4svc_encode_testres(struct svc_rqst *rqstp, struct xdr_stream *xdr)
{
- struct xdr_stream *xdr = &rqstp->rq_res_stream;
struct nlm_res *resp = rqstp->rq_resp;
return svcxdr_encode_cookie(xdr, &resp->cookie) &&
svcxdr_encode_testrply(xdr, resp);
}
-int
-nlm4svc_encode_res(struct svc_rqst *rqstp, __be32 *p)
+bool
+nlm4svc_encode_res(struct svc_rqst *rqstp, struct xdr_stream *xdr)
{
- struct xdr_stream *xdr = &rqstp->rq_res_stream;
struct nlm_res *resp = rqstp->rq_resp;
return svcxdr_encode_cookie(xdr, &resp->cookie) &&
svcxdr_encode_stats(xdr, resp->status);
}
-int
-nlm4svc_encode_shareres(struct svc_rqst *rqstp, __be32 *p)
+bool
+nlm4svc_encode_shareres(struct svc_rqst *rqstp, struct xdr_stream *xdr)
{
- struct xdr_stream *xdr = &rqstp->rq_res_stream;
struct nlm_res *resp = rqstp->rq_resp;
if (!svcxdr_encode_cookie(xdr, &resp->cookie))
- return 0;
+ return false;
if (!svcxdr_encode_stats(xdr, resp->status))
- return 0;
+ return false;
/* sequence */
if (xdr_stream_encode_u32(xdr, 0) < 0)
- return 0;
+ return false;
- return 1;
+ return true;
}
diff --git a/fs/nfs/callback_proc.c b/fs/nfs/callback_proc.c
index ed9d580826f5..09c5b1cb3e07 100644
--- a/fs/nfs/callback_proc.c
+++ b/fs/nfs/callback_proc.c
@@ -739,6 +739,9 @@ out:
kfree(copy);
spin_unlock(&cps->clp->cl_lock);
+ trace_nfs4_cb_offload(&args->coa_fh, &args->coa_stateid,
+ args->wr_count, args->error,
+ args->wr_writeverf.committed);
return 0;
}
#endif /* CONFIG_NFS_V4_2 */
diff --git a/fs/nfs/callback_xdr.c b/fs/nfs/callback_xdr.c
index 4c48d85f6517..a67c41ec545f 100644
--- a/fs/nfs/callback_xdr.c
+++ b/fs/nfs/callback_xdr.c
@@ -67,9 +67,9 @@ static __be32 nfs4_callback_null(struct svc_rqst *rqstp)
* svc_process_common() looks for an XDR encoder to know when
* not to drop a Reply.
*/
-static int nfs4_encode_void(struct svc_rqst *rqstp, __be32 *p)
+static bool nfs4_encode_void(struct svc_rqst *rqstp, struct xdr_stream *xdr)
{
- return xdr_ressize_check(rqstp, p);
+ return true;
}
static __be32 decode_string(struct xdr_stream *xdr, unsigned int *len,
diff --git a/fs/nfs/client.c b/fs/nfs/client.c
index 23e165d5ec9c..1e4dc1ab9312 100644
--- a/fs/nfs/client.c
+++ b/fs/nfs/client.c
@@ -828,7 +828,7 @@ static void nfs_server_set_fsinfo(struct nfs_server *server,
/*
* Probe filesystem information, including the FSID on v2/v3
*/
-int nfs_probe_fsinfo(struct nfs_server *server, struct nfs_fh *mntfh, struct nfs_fattr *fattr)
+static int nfs_probe_fsinfo(struct nfs_server *server, struct nfs_fh *mntfh, struct nfs_fattr *fattr)
{
struct nfs_fsinfo fsinfo;
struct nfs_client *clp = server->nfs_client;
@@ -862,7 +862,30 @@ int nfs_probe_fsinfo(struct nfs_server *server, struct nfs_fh *mntfh, struct nfs
return 0;
}
-EXPORT_SYMBOL_GPL(nfs_probe_fsinfo);
+
+/*
+ * Grab the destination's particulars, including lease expiry time.
+ *
+ * Returns zero if probe succeeded and retrieved FSID matches the FSID
+ * we have cached.
+ */
+int nfs_probe_server(struct nfs_server *server, struct nfs_fh *mntfh)
+{
+ struct nfs_fattr *fattr;
+ int error;
+
+ fattr = nfs_alloc_fattr();
+ if (fattr == NULL)
+ return -ENOMEM;
+
+ /* Sanity: the probe won't work if the destination server
+ * does not recognize the migrated FH. */
+ error = nfs_probe_fsinfo(server, mntfh, fattr);
+
+ nfs_free_fattr(fattr);
+ return error;
+}
+EXPORT_SYMBOL_GPL(nfs_probe_server);
/*
* Copy useful information when duplicating a server record
@@ -1025,7 +1048,7 @@ struct nfs_server *nfs_create_server(struct fs_context *fc)
if (!(fattr->valid & NFS_ATTR_FATTR)) {
error = ctx->nfs_mod->rpc_ops->getattr(server, ctx->mntfh,
- fattr, NULL, NULL);
+ fattr, NULL);
if (error < 0) {
dprintk("nfs_create_server: getattr error = %d\n", -error);
goto error;
@@ -1058,7 +1081,6 @@ struct nfs_server *nfs_clone_server(struct nfs_server *source,
rpc_authflavor_t flavor)
{
struct nfs_server *server;
- struct nfs_fattr *fattr_fsinfo;
int error;
server = nfs_alloc_server();
@@ -1067,11 +1089,6 @@ struct nfs_server *nfs_clone_server(struct nfs_server *source,
server->cred = get_cred(source->cred);
- error = -ENOMEM;
- fattr_fsinfo = nfs_alloc_fattr();
- if (fattr_fsinfo == NULL)
- goto out_free_server;
-
/* Copy data from the source */
server->nfs_client = source->nfs_client;
server->destroy = source->destroy;
@@ -1087,7 +1104,7 @@ struct nfs_server *nfs_clone_server(struct nfs_server *source,
goto out_free_server;
/* probe the filesystem info for this server filesystem */
- error = nfs_probe_fsinfo(server, fh, fattr_fsinfo);
+ error = nfs_probe_server(server, fh);
if (error < 0)
goto out_free_server;
@@ -1101,11 +1118,9 @@ struct nfs_server *nfs_clone_server(struct nfs_server *source,
nfs_server_insert_lists(server);
server->mount_time = jiffies;
- nfs_free_fattr(fattr_fsinfo);
return server;
out_free_server:
- nfs_free_fattr(fattr_fsinfo);
nfs_free_server(server);
return ERR_PTR(error);
}
diff --git a/fs/nfs/delegation.c b/fs/nfs/delegation.c
index 11118398f495..7c9eb679dbdb 100644
--- a/fs/nfs/delegation.c
+++ b/fs/nfs/delegation.c
@@ -755,11 +755,13 @@ int nfs4_inode_return_delegation(struct inode *inode)
struct nfs_delegation *delegation;
delegation = nfs_start_delegation_return(nfsi);
- /* Synchronous recall of any application leases */
- break_lease(inode, O_WRONLY | O_RDWR);
- nfs_wb_all(inode);
- if (delegation != NULL)
+ if (delegation != NULL) {
+ /* Synchronous recall of any application leases */
+ break_lease(inode, O_WRONLY | O_RDWR);
+ if (S_ISREG(inode->i_mode))
+ nfs_wb_all(inode);
return nfs_end_delegation_return(inode, delegation, 1);
+ }
return 0;
}
diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index 1a6d2867fba4..731d31015b6a 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -78,6 +78,7 @@ static struct nfs_open_dir_context *alloc_nfs_open_dir_context(struct inode *dir
ctx->attr_gencount = nfsi->attr_gencount;
ctx->dir_cookie = 0;
ctx->dup_cookie = 0;
+ ctx->page_index = 0;
spin_lock(&dir->i_lock);
if (list_empty(&nfsi->open_files) &&
(nfsi->cache_validity & NFS_INO_DATA_INVAL_DEFER))
@@ -85,6 +86,7 @@ static struct nfs_open_dir_context *alloc_nfs_open_dir_context(struct inode *dir
NFS_INO_INVALID_DATA |
NFS_INO_REVAL_FORCED);
list_add(&ctx->list, &nfsi->open_files);
+ clear_bit(NFS_INO_FORCE_READDIR, &nfsi->flags);
spin_unlock(&dir->i_lock);
return ctx;
}
@@ -411,7 +413,8 @@ out_eof:
static bool
nfs_readdir_inode_mapping_valid(struct nfs_inode *nfsi)
{
- if (nfsi->cache_validity & (NFS_INO_INVALID_ATTR|NFS_INO_INVALID_DATA))
+ if (nfsi->cache_validity & (NFS_INO_INVALID_CHANGE |
+ NFS_INO_INVALID_DATA))
return false;
smp_rmb();
return !test_bit(NFS_INO_INVALIDATING, &nfsi->flags);
@@ -626,8 +629,7 @@ void nfs_force_use_readdirplus(struct inode *dir)
if (nfs_server_capable(dir, NFS_CAP_READDIRPLUS) &&
!list_empty(&nfsi->open_files)) {
set_bit(NFS_INO_ADVISE_RDPLUS, &nfsi->flags);
- invalidate_mapping_pages(dir->i_mapping,
- nfsi->page_index + 1, -1);
+ set_bit(NFS_INO_FORCE_READDIR, &nfsi->flags);
}
}
@@ -680,7 +682,7 @@ again:
nfs_set_verifier(dentry, dir_verifier);
status = nfs_refresh_inode(d_inode(dentry), entry->fattr);
if (!status)
- nfs_setsecurity(d_inode(dentry), entry->fattr, entry->label);
+ nfs_setsecurity(d_inode(dentry), entry->fattr);
goto out;
} else {
d_invalidate(dentry);
@@ -694,7 +696,7 @@ again:
goto out;
}
- inode = nfs_fhget(dentry->d_sb, entry->fh, entry->fattr, entry->label);
+ inode = nfs_fhget(dentry->d_sb, entry->fh, entry->fattr);
alias = d_splice_alias(inode, dentry);
d_lookup_done(dentry);
if (alias) {
@@ -730,8 +732,8 @@ static int nfs_readdir_page_filler(struct nfs_readdir_descriptor *desc,
xdr_set_scratch_page(&stream, scratch);
do {
- if (entry->label)
- entry->label->len = NFS4_MAXLABELLEN;
+ if (entry->fattr->label)
+ entry->fattr->label->len = NFS4_MAXLABELLEN;
status = xdr_decode(desc, entry, &stream);
if (status != 0)
@@ -836,21 +838,15 @@ static int nfs_readdir_xdr_to_array(struct nfs_readdir_descriptor *desc,
return -ENOMEM;
entry->cookie = nfs_readdir_page_last_cookie(page);
entry->fh = nfs_alloc_fhandle();
- entry->fattr = nfs_alloc_fattr();
+ entry->fattr = nfs_alloc_fattr_with_label(NFS_SERVER(inode));
entry->server = NFS_SERVER(inode);
if (entry->fh == NULL || entry->fattr == NULL)
goto out;
- entry->label = nfs4_label_alloc(NFS_SERVER(inode), GFP_NOWAIT);
- if (IS_ERR(entry->label)) {
- status = PTR_ERR(entry->label);
- goto out;
- }
-
array_size = (dtsize + PAGE_SIZE - 1) >> PAGE_SHIFT;
pages = nfs_readdir_alloc_pages(array_size);
if (!pages)
- goto out_release_label;
+ goto out;
do {
unsigned int pglen;
@@ -873,8 +869,6 @@ static int nfs_readdir_xdr_to_array(struct nfs_readdir_descriptor *desc,
} while (!status && nfs_readdir_page_needs_filling(page));
nfs_readdir_free_pages(pages, array_size);
-out_release_label:
- nfs4_label_free(entry->label);
out:
nfs_free_fattr(entry->fattr);
nfs_free_fhandle(entry->fh);
@@ -937,10 +931,8 @@ static int find_and_lock_cache_page(struct nfs_readdir_descriptor *desc)
sizeof(nfsi->cookieverf));
}
res = nfs_readdir_search_array(desc);
- if (res == 0) {
- nfsi->page_index = desc->page_index;
+ if (res == 0)
return 0;
- }
nfs_readdir_page_unlock_and_put_cached(desc);
return res;
}
@@ -1079,6 +1071,7 @@ static int nfs_readdir(struct file *file, struct dir_context *ctx)
struct nfs_inode *nfsi = NFS_I(inode);
struct nfs_open_dir_context *dir_ctx = file->private_data;
struct nfs_readdir_descriptor *desc;
+ pgoff_t page_index;
int res;
dfprintk(FILE, "NFS: readdir(%pD2) starting at cookie %llu\n",
@@ -1109,10 +1102,15 @@ static int nfs_readdir(struct file *file, struct dir_context *ctx)
desc->dir_cookie = dir_ctx->dir_cookie;
desc->dup_cookie = dir_ctx->dup_cookie;
desc->duped = dir_ctx->duped;
+ page_index = dir_ctx->page_index;
desc->attr_gencount = dir_ctx->attr_gencount;
memcpy(desc->verf, dir_ctx->verf, sizeof(desc->verf));
spin_unlock(&file->f_lock);
+ if (test_and_clear_bit(NFS_INO_FORCE_READDIR, &nfsi->flags) &&
+ list_is_singular(&nfsi->open_files))
+ invalidate_mapping_pages(inode->i_mapping, page_index + 1, -1);
+
do {
res = readdir_search_pagecache(desc);
@@ -1149,6 +1147,7 @@ static int nfs_readdir(struct file *file, struct dir_context *ctx)
dir_ctx->dup_cookie = desc->dup_cookie;
dir_ctx->duped = desc->duped;
dir_ctx->attr_gencount = desc->attr_gencount;
+ dir_ctx->page_index = desc->page_index;
memcpy(dir_ctx->verf, desc->verf, sizeof(dir_ctx->verf));
spin_unlock(&file->f_lock);
@@ -1269,13 +1268,12 @@ static bool nfs_verifier_is_delegated(struct dentry *dentry)
static void nfs_set_verifier_locked(struct dentry *dentry, unsigned long verf)
{
struct inode *inode = d_inode(dentry);
+ struct inode *dir = d_inode(dentry->d_parent);
- if (!nfs_verifier_is_delegated(dentry) &&
- !nfs_verify_change_attribute(d_inode(dentry->d_parent), verf))
- goto out;
+ if (!nfs_verify_change_attribute(dir, verf))
+ return;
if (inode && NFS_PROTO(inode)->have_delegation(inode, FMODE_READ))
nfs_set_verifier_delegated(&verf);
-out:
dentry->d_time = verf;
}
@@ -1413,7 +1411,7 @@ out_force:
static void nfs_mark_dir_for_revalidate(struct inode *inode)
{
spin_lock(&inode->i_lock);
- nfs_set_cache_invalid(inode, NFS_INO_REVAL_PAGECACHE);
+ nfs_set_cache_invalid(inode, NFS_INO_INVALID_CHANGE);
spin_unlock(&inode->i_lock);
}
@@ -1495,19 +1493,17 @@ nfs_lookup_revalidate_dentry(struct inode *dir, struct dentry *dentry,
{
struct nfs_fh *fhandle;
struct nfs_fattr *fattr;
- struct nfs4_label *label;
unsigned long dir_verifier;
int ret;
ret = -ENOMEM;
fhandle = nfs_alloc_fhandle();
- fattr = nfs_alloc_fattr();
- label = nfs4_label_alloc(NFS_SERVER(inode), GFP_KERNEL);
- if (fhandle == NULL || fattr == NULL || IS_ERR(label))
+ fattr = nfs_alloc_fattr_with_label(NFS_SERVER(inode));
+ if (fhandle == NULL || fattr == NULL)
goto out;
dir_verifier = nfs_save_change_attribute(dir);
- ret = NFS_PROTO(dir)->lookup(dir, dentry, fhandle, fattr, label);
+ ret = NFS_PROTO(dir)->lookup(dir, dentry, fhandle, fattr);
if (ret < 0) {
switch (ret) {
case -ESTALE:
@@ -1526,7 +1522,7 @@ nfs_lookup_revalidate_dentry(struct inode *dir, struct dentry *dentry,
if (nfs_refresh_inode(inode, fattr) < 0)
goto out;
- nfs_setsecurity(inode, fattr, label);
+ nfs_setsecurity(inode, fattr);
nfs_set_verifier(dentry, dir_verifier);
/* set a readdirplus hint that we had a cache miss */
@@ -1535,7 +1531,6 @@ nfs_lookup_revalidate_dentry(struct inode *dir, struct dentry *dentry,
out:
nfs_free_fattr(fattr);
nfs_free_fhandle(fhandle);
- nfs4_label_free(label);
/*
* If the lookup failed despite the dentry change attribute being
@@ -1721,10 +1716,6 @@ static void nfs_drop_nlink(struct inode *inode)
*/
static void nfs_dentry_iput(struct dentry *dentry, struct inode *inode)
{
- if (S_ISDIR(inode->i_mode))
- /* drop any readdir cache as it could easily be old */
- nfs_set_cache_invalid(inode, NFS_INO_INVALID_DATA);
-
if (dentry->d_flags & DCACHE_NFSFS_RENAMED) {
nfs_complete_unlink(dentry, inode);
nfs_drop_nlink(inode);
@@ -1759,7 +1750,6 @@ struct dentry *nfs_lookup(struct inode *dir, struct dentry * dentry, unsigned in
struct inode *inode = NULL;
struct nfs_fh *fhandle = NULL;
struct nfs_fattr *fattr = NULL;
- struct nfs4_label *label = NULL;
unsigned long dir_verifier;
int error;
@@ -1778,27 +1768,23 @@ struct dentry *nfs_lookup(struct inode *dir, struct dentry * dentry, unsigned in
res = ERR_PTR(-ENOMEM);
fhandle = nfs_alloc_fhandle();
- fattr = nfs_alloc_fattr();
+ fattr = nfs_alloc_fattr_with_label(NFS_SERVER(dir));
if (fhandle == NULL || fattr == NULL)
goto out;
- label = nfs4_label_alloc(NFS_SERVER(dir), GFP_NOWAIT);
- if (IS_ERR(label))
- goto out;
-
dir_verifier = nfs_save_change_attribute(dir);
trace_nfs_lookup_enter(dir, dentry, flags);
- error = NFS_PROTO(dir)->lookup(dir, dentry, fhandle, fattr, label);
+ error = NFS_PROTO(dir)->lookup(dir, dentry, fhandle, fattr);
if (error == -ENOENT)
goto no_entry;
if (error < 0) {
res = ERR_PTR(error);
- goto out_label;
+ goto out;
}
- inode = nfs_fhget(dentry->d_sb, fhandle, fattr, label);
+ inode = nfs_fhget(dentry->d_sb, fhandle, fattr);
res = ERR_CAST(inode);
if (IS_ERR(res))
- goto out_label;
+ goto out;
/* Notify readdir to use READDIRPLUS */
nfs_force_use_readdirplus(dir);
@@ -1807,14 +1793,12 @@ no_entry:
res = d_splice_alias(inode, dentry);
if (res != NULL) {
if (IS_ERR(res))
- goto out_label;
+ goto out;
dentry = res;
}
nfs_set_verifier(dentry, dir_verifier);
-out_label:
- trace_nfs_lookup_exit(dir, dentry, flags, error);
- nfs4_label_free(label);
out:
+ trace_nfs_lookup_exit(dir, dentry, flags, PTR_ERR_OR_ZERO(res));
nfs_free_fattr(fattr);
nfs_free_fhandle(fhandle);
return res;
@@ -2051,8 +2035,7 @@ static int nfs4_lookup_revalidate(struct dentry *dentry, unsigned int flags)
struct dentry *
nfs_add_or_obtain(struct dentry *dentry, struct nfs_fh *fhandle,
- struct nfs_fattr *fattr,
- struct nfs4_label *label)
+ struct nfs_fattr *fattr)
{
struct dentry *parent = dget_parent(dentry);
struct inode *dir = d_inode(parent);
@@ -2063,7 +2046,7 @@ nfs_add_or_obtain(struct dentry *dentry, struct nfs_fh *fhandle,
d_drop(dentry);
if (fhandle->size == 0) {
- error = NFS_PROTO(dir)->lookup(dir, dentry, fhandle, fattr, NULL);
+ error = NFS_PROTO(dir)->lookup(dir, dentry, fhandle, fattr);
if (error)
goto out_error;
}
@@ -2071,11 +2054,11 @@ nfs_add_or_obtain(struct dentry *dentry, struct nfs_fh *fhandle,
if (!(fattr->valid & NFS_ATTR_FATTR)) {
struct nfs_server *server = NFS_SB(dentry->d_sb);
error = server->nfs_client->rpc_ops->getattr(server, fhandle,
- fattr, NULL, NULL);
+ fattr, NULL);
if (error < 0)
goto out_error;
}
- inode = nfs_fhget(dentry->d_sb, fhandle, fattr, label);
+ inode = nfs_fhget(dentry->d_sb, fhandle, fattr);
d = d_splice_alias(inode, dentry);
out:
dput(parent);
@@ -2090,12 +2073,11 @@ EXPORT_SYMBOL_GPL(nfs_add_or_obtain);
* Code common to create, mkdir, and mknod.
*/
int nfs_instantiate(struct dentry *dentry, struct nfs_fh *fhandle,
- struct nfs_fattr *fattr,
- struct nfs4_label *label)
+ struct nfs_fattr *fattr)
{
struct dentry *d;
- d = nfs_add_or_obtain(dentry, fhandle, fattr, label);
+ d = nfs_add_or_obtain(dentry, fhandle, fattr);
if (IS_ERR(d))
return PTR_ERR(d);
@@ -2197,6 +2179,18 @@ static void nfs_dentry_handle_enoent(struct dentry *dentry)
d_delete(dentry);
}
+static void nfs_dentry_remove_handle_error(struct inode *dir,
+ struct dentry *dentry, int error)
+{
+ switch (error) {
+ case -ENOENT:
+ d_delete(dentry);
+ fallthrough;
+ case 0:
+ nfs_set_verifier(dentry, nfs_save_change_attribute(dir));
+ }
+}
+
int nfs_rmdir(struct inode *dir, struct dentry *dentry)
{
int error;
@@ -2219,6 +2213,7 @@ int nfs_rmdir(struct inode *dir, struct dentry *dentry)
up_write(&NFS_I(d_inode(dentry))->rmdir_sem);
} else
error = NFS_PROTO(dir)->rmdir(dir, &dentry->d_name);
+ nfs_dentry_remove_handle_error(dir, dentry, error);
trace_nfs_rmdir_exit(dir, dentry, error);
return error;
@@ -2288,9 +2283,8 @@ int nfs_unlink(struct inode *dir, struct dentry *dentry)
}
spin_unlock(&dentry->d_lock);
error = nfs_safe_remove(dentry);
- if (!error || error == -ENOENT) {
- nfs_set_verifier(dentry, nfs_save_change_attribute(dir));
- } else if (need_rehash)
+ nfs_dentry_remove_handle_error(dir, dentry, error);
+ if (need_rehash)
d_rehash(dentry);
out:
trace_nfs_unlink_exit(dir, dentry, error);
@@ -2352,6 +2346,8 @@ int nfs_symlink(struct user_namespace *mnt_userns, struct inode *dir,
return error;
}
+ nfs_set_verifier(dentry, nfs_save_change_attribute(dir));
+
/*
* No big deal if we can't add this page to the page cache here.
* READLINK will get the missing page from the server if needed.
@@ -2385,6 +2381,7 @@ nfs_link(struct dentry *old_dentry, struct inode *dir, struct dentry *dentry)
d_drop(dentry);
error = NFS_PROTO(dir)->link(inode, dir, &dentry->d_name);
if (error == 0) {
+ nfs_set_verifier(dentry, nfs_save_change_attribute(dir));
ihold(inode);
d_add(dentry, inode);
}
diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c
index 7a5f287c5391..9cff8709c80a 100644
--- a/fs/nfs/direct.c
+++ b/fs/nfs/direct.c
@@ -620,7 +620,7 @@ static void nfs_direct_commit_complete(struct nfs_commit_data *data)
nfs_unlock_and_release_request(req);
}
- if (atomic_dec_and_test(&cinfo.mds->rpcs_out))
+ if (nfs_commit_end(cinfo.mds))
nfs_direct_write_complete(dreq);
}
diff --git a/fs/nfs/export.c b/fs/nfs/export.c
index d772c20bbfd1..171c424cb6d5 100644
--- a/fs/nfs/export.c
+++ b/fs/nfs/export.c
@@ -64,7 +64,6 @@ static struct dentry *
nfs_fh_to_dentry(struct super_block *sb, struct fid *fid,
int fh_len, int fh_type)
{
- struct nfs4_label *label = NULL;
struct nfs_fattr *fattr = NULL;
struct nfs_fh *server_fh = nfs_exp_embedfh(fid->raw);
size_t fh_size = offsetof(struct nfs_fh, data) + server_fh->size;
@@ -79,7 +78,7 @@ nfs_fh_to_dentry(struct super_block *sb, struct fid *fid,
if (fh_len < len || fh_type != len)
return NULL;
- fattr = nfs_alloc_fattr();
+ fattr = nfs_alloc_fattr_with_label(NFS_SB(sb));
if (fattr == NULL) {
dentry = ERR_PTR(-ENOMEM);
goto out;
@@ -95,28 +94,19 @@ nfs_fh_to_dentry(struct super_block *sb, struct fid *fid,
if (inode)
goto out_found;
- label = nfs4_label_alloc(NFS_SB(sb), GFP_KERNEL);
- if (IS_ERR(label)) {
- dentry = ERR_CAST(label);
- goto out_free_fattr;
- }
-
rpc_ops = NFS_SB(sb)->nfs_client->rpc_ops;
- ret = rpc_ops->getattr(NFS_SB(sb), server_fh, fattr, label, NULL);
+ ret = rpc_ops->getattr(NFS_SB(sb), server_fh, fattr, NULL);
if (ret) {
dprintk("%s: getattr failed %d\n", __func__, ret);
trace_nfs_fh_to_dentry(sb, server_fh, fattr->fileid, ret);
dentry = ERR_PTR(ret);
- goto out_free_label;
+ goto out_free_fattr;
}
- inode = nfs_fhget(sb, server_fh, fattr, label);
+ inode = nfs_fhget(sb, server_fh, fattr);
out_found:
dentry = d_obtain_alias(inode);
-
-out_free_label:
- nfs4_label_free(label);
out_free_fattr:
nfs_free_fattr(fattr);
out:
@@ -131,7 +121,6 @@ nfs_get_parent(struct dentry *dentry)
struct super_block *sb = inode->i_sb;
struct nfs_server *server = NFS_SB(sb);
struct nfs_fattr *fattr = NULL;
- struct nfs4_label *label = NULL;
struct dentry *parent;
struct nfs_rpc_ops const *ops = server->nfs_client->rpc_ops;
struct nfs_fh fh;
@@ -139,31 +128,20 @@ nfs_get_parent(struct dentry *dentry)
if (!ops->lookupp)
return ERR_PTR(-EACCES);
- fattr = nfs_alloc_fattr();
- if (fattr == NULL) {
- parent = ERR_PTR(-ENOMEM);
- goto out;
- }
+ fattr = nfs_alloc_fattr_with_label(server);
+ if (fattr == NULL)
+ return ERR_PTR(-ENOMEM);
- label = nfs4_label_alloc(server, GFP_KERNEL);
- if (IS_ERR(label)) {
- parent = ERR_CAST(label);
- goto out_free_fattr;
- }
-
- ret = ops->lookupp(inode, &fh, fattr, label);
+ ret = ops->lookupp(inode, &fh, fattr);
if (ret) {
parent = ERR_PTR(ret);
- goto out_free_label;
+ goto out;
}
- pinode = nfs_fhget(sb, &fh, fattr, label);
+ pinode = nfs_fhget(sb, &fh, fattr);
parent = d_obtain_alias(pinode);
-out_free_label:
- nfs4_label_free(label);
-out_free_fattr:
- nfs_free_fattr(fattr);
out:
+ nfs_free_fattr(fattr);
return parent;
}
diff --git a/fs/nfs/filelayout/filelayout.c b/fs/nfs/filelayout/filelayout.c
index d2103852475f..9c96e3e5ed35 100644
--- a/fs/nfs/filelayout/filelayout.c
+++ b/fs/nfs/filelayout/filelayout.c
@@ -293,8 +293,6 @@ static void filelayout_read_call_done(struct rpc_task *task, void *data)
{
struct nfs_pgio_header *hdr = data;
- dprintk("--> %s task->tk_status %d\n", __func__, task->tk_status);
-
if (test_bit(NFS_IOHDR_REDO, &hdr->flags) &&
task->tk_status == 0) {
nfs41_sequence_done(task, &hdr->res.seq_res);
diff --git a/fs/nfs/flexfilelayout/flexfilelayout.c b/fs/nfs/flexfilelayout/flexfilelayout.c
index d383de00d486..a553d59afa8b 100644
--- a/fs/nfs/flexfilelayout/flexfilelayout.c
+++ b/fs/nfs/flexfilelayout/flexfilelayout.c
@@ -1414,8 +1414,6 @@ static void ff_layout_read_call_done(struct rpc_task *task, void *data)
{
struct nfs_pgio_header *hdr = data;
- dprintk("--> %s task->tk_status %d\n", __func__, task->tk_status);
-
if (test_bit(NFS_IOHDR_REDO, &hdr->flags) &&
task->tk_status == 0) {
nfs4_sequence_done(task, &hdr->res.seq_res);
diff --git a/fs/nfs/flexfilelayout/flexfilelayoutdev.c b/fs/nfs/flexfilelayout/flexfilelayoutdev.c
index c9b61b818ec1..bfa7202ca7be 100644
--- a/fs/nfs/flexfilelayout/flexfilelayoutdev.c
+++ b/fs/nfs/flexfilelayout/flexfilelayoutdev.c
@@ -378,10 +378,10 @@ nfs4_ff_layout_prepare_ds(struct pnfs_layout_segment *lseg,
goto noconnect;
ds = mirror->mirror_ds->ds;
+ if (READ_ONCE(ds->ds_clp))
+ goto out;
/* matching smp_wmb() in _nfs4_pnfs_v3/4_ds_connect */
smp_rmb();
- if (ds->ds_clp)
- goto out;
/* FIXME: For now we assume the server sent only one version of NFS
* to use for the DS.
diff --git a/fs/nfs/getroot.c b/fs/nfs/getroot.c
index 59355c106ece..11ff2b2e060f 100644
--- a/fs/nfs/getroot.c
+++ b/fs/nfs/getroot.c
@@ -80,31 +80,28 @@ int nfs_get_root(struct super_block *s, struct fs_context *fc)
goto out;
/* get the actual root for this mount */
- fsinfo.fattr = nfs_alloc_fattr();
+ fsinfo.fattr = nfs_alloc_fattr_with_label(server);
if (fsinfo.fattr == NULL)
goto out_name;
- fsinfo.fattr->label = nfs4_label_alloc(server, GFP_KERNEL);
- if (IS_ERR(fsinfo.fattr->label))
- goto out_fattr;
error = server->nfs_client->rpc_ops->getroot(server, ctx->mntfh, &fsinfo);
if (error < 0) {
dprintk("nfs_get_root: getattr error = %d\n", -error);
nfs_errorf(fc, "NFS: Couldn't getattr on root");
- goto out_label;
+ goto out_fattr;
}
- inode = nfs_fhget(s, ctx->mntfh, fsinfo.fattr, NULL);
+ inode = nfs_fhget(s, ctx->mntfh, fsinfo.fattr);
if (IS_ERR(inode)) {
dprintk("nfs_get_root: get root inode failed\n");
error = PTR_ERR(inode);
nfs_errorf(fc, "NFS: Couldn't get root inode");
- goto out_label;
+ goto out_fattr;
}
error = nfs_superblock_set_dummy_root(s, inode);
if (error != 0)
- goto out_label;
+ goto out_fattr;
/* root dentries normally start off anonymous and get spliced in later
* if the dentry tree reaches them; however if the dentry already
@@ -115,7 +112,7 @@ int nfs_get_root(struct super_block *s, struct fs_context *fc)
dprintk("nfs_get_root: get root dentry failed\n");
error = PTR_ERR(root);
nfs_errorf(fc, "NFS: Couldn't get root dentry");
- goto out_label;
+ goto out_fattr;
}
security_d_instantiate(root, inode);
@@ -151,11 +148,9 @@ int nfs_get_root(struct super_block *s, struct fs_context *fc)
!(kflags_out & SECURITY_LSM_NATIVE_LABELS))
server->caps &= ~NFS_CAP_SECURITY_LABEL;
- nfs_setsecurity(inode, fsinfo.fattr, fsinfo.fattr->label);
+ nfs_setsecurity(inode, fsinfo.fattr);
error = 0;
-out_label:
- nfs4_label_free(fsinfo.fattr->label);
out_fattr:
nfs_free_fattr(fsinfo.fattr);
out_name:
@@ -165,5 +160,5 @@ out:
error_splat_root:
dput(fc->root);
fc->root = NULL;
- goto out_label;
+ goto out_fattr;
}
diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c
index 853213b3a209..dd53704c3f40 100644
--- a/fs/nfs/inode.c
+++ b/fs/nfs/inode.c
@@ -210,10 +210,15 @@ void nfs_set_cache_invalid(struct inode *inode, unsigned long flags)
flags &= ~NFS_INO_INVALID_XATTR;
if (flags & NFS_INO_INVALID_DATA)
nfs_fscache_invalidate(inode);
- if (inode->i_mapping->nrpages == 0)
- flags &= ~(NFS_INO_INVALID_DATA|NFS_INO_DATA_INVAL_DEFER);
flags &= ~(NFS_INO_REVAL_PAGECACHE | NFS_INO_REVAL_FORCED);
+
nfsi->cache_validity |= flags;
+
+ if (inode->i_mapping->nrpages == 0)
+ nfsi->cache_validity &= ~(NFS_INO_INVALID_DATA |
+ NFS_INO_DATA_INVAL_DEFER);
+ else if (nfsi->cache_validity & NFS_INO_INVALID_DATA)
+ nfsi->cache_validity &= ~NFS_INO_DATA_INVAL_DEFER;
}
EXPORT_SYMBOL_GPL(nfs_set_cache_invalid);
@@ -350,37 +355,32 @@ static void nfs_clear_label_invalid(struct inode *inode)
spin_unlock(&inode->i_lock);
}
-void nfs_setsecurity(struct inode *inode, struct nfs_fattr *fattr,
- struct nfs4_label *label)
+void nfs_setsecurity(struct inode *inode, struct nfs_fattr *fattr)
{
int error;
- if (label == NULL)
+ if (fattr->label == NULL)
return;
if ((fattr->valid & NFS_ATTR_FATTR_V4_SECURITY_LABEL) && inode->i_security) {
- error = security_inode_notifysecctx(inode, label->label,
- label->len);
+ error = security_inode_notifysecctx(inode, fattr->label->label,
+ fattr->label->len);
if (error)
printk(KERN_ERR "%s() %s %d "
"security_inode_notifysecctx() %d\n",
__func__,
- (char *)label->label,
- label->len, error);
+ (char *)fattr->label->label,
+ fattr->label->len, error);
nfs_clear_label_invalid(inode);
}
}
struct nfs4_label *nfs4_label_alloc(struct nfs_server *server, gfp_t flags)
{
- struct nfs4_label *label = NULL;
- int minor_version = server->nfs_client->cl_minorversion;
-
- if (minor_version < 2)
- return label;
+ struct nfs4_label *label;
if (!(server->caps & NFS_CAP_SECURITY_LABEL))
- return label;
+ return NULL;
label = kzalloc(sizeof(struct nfs4_label), flags);
if (label == NULL)
@@ -397,8 +397,7 @@ struct nfs4_label *nfs4_label_alloc(struct nfs_server *server, gfp_t flags)
}
EXPORT_SYMBOL_GPL(nfs4_label_alloc);
#else
-void nfs_setsecurity(struct inode *inode, struct nfs_fattr *fattr,
- struct nfs4_label *label)
+void nfs_setsecurity(struct inode *inode, struct nfs_fattr *fattr)
{
}
#endif
@@ -426,12 +425,28 @@ nfs_ilookup(struct super_block *sb, struct nfs_fattr *fattr, struct nfs_fh *fh)
return inode;
}
+static void nfs_inode_init_regular(struct nfs_inode *nfsi)
+{
+ atomic_long_set(&nfsi->nrequests, 0);
+ INIT_LIST_HEAD(&nfsi->commit_info.list);
+ atomic_long_set(&nfsi->commit_info.ncommit, 0);
+ atomic_set(&nfsi->commit_info.rpcs_out, 0);
+ mutex_init(&nfsi->commit_mutex);
+}
+
+static void nfs_inode_init_dir(struct nfs_inode *nfsi)
+{
+ nfsi->cache_change_attribute = 0;
+ memset(nfsi->cookieverf, 0, sizeof(nfsi->cookieverf));
+ init_rwsem(&nfsi->rmdir_sem);
+}
+
/*
* This is our front-end to iget that looks up inodes by file handle
* instead of inode number.
*/
struct inode *
-nfs_fhget(struct super_block *sb, struct nfs_fh *fh, struct nfs_fattr *fattr, struct nfs4_label *label)
+nfs_fhget(struct super_block *sb, struct nfs_fh *fh, struct nfs_fattr *fattr)
{
struct nfs_find_desc desc = {
.fh = fh,
@@ -480,10 +495,12 @@ nfs_fhget(struct super_block *sb, struct nfs_fh *fh, struct nfs_fattr *fattr, st
if (S_ISREG(inode->i_mode)) {
inode->i_fop = NFS_SB(sb)->nfs_client->rpc_ops->file_ops;
inode->i_data.a_ops = &nfs_file_aops;
+ nfs_inode_init_regular(nfsi);
} else if (S_ISDIR(inode->i_mode)) {
inode->i_op = NFS_SB(sb)->nfs_client->rpc_ops->dir_inode_ops;
inode->i_fop = &nfs_dir_operations;
inode->i_data.a_ops = &nfs_dir_aops;
+ nfs_inode_init_dir(nfsi);
/* Deal with crossing mountpoints */
if (fattr->valid & NFS_ATTR_FATTR_MOUNTPOINT ||
fattr->valid & NFS_ATTR_FATTR_V4_REFERRAL) {
@@ -509,7 +526,6 @@ nfs_fhget(struct super_block *sb, struct nfs_fh *fh, struct nfs_fattr *fattr, st
inode->i_uid = make_kuid(&init_user_ns, -2);
inode->i_gid = make_kgid(&init_user_ns, -2);
inode->i_blocks = 0;
- memset(nfsi->cookieverf, 0, sizeof(nfsi->cookieverf));
nfsi->write_io = 0;
nfsi->read_io = 0;
@@ -563,7 +579,7 @@ nfs_fhget(struct super_block *sb, struct nfs_fh *fh, struct nfs_fattr *fattr, st
fattr->size != 0)
nfs_set_cache_invalid(inode, NFS_INO_INVALID_BLOCKS);
- nfs_setsecurity(inode, fattr, label);
+ nfs_setsecurity(inode, fattr);
nfsi->attrtimeo = NFS_MINATTRTIMEO(inode);
nfsi->attrtimeo_timestamp = now;
@@ -632,7 +648,7 @@ nfs_setattr(struct user_namespace *mnt_userns, struct dentry *dentry,
if (S_ISREG(inode->i_mode))
nfs_sync_inode(inode);
- fattr = nfs_alloc_fattr();
+ fattr = nfs_alloc_fattr_with_label(NFS_SERVER(inode));
if (fattr == NULL) {
error = -ENOMEM;
goto out;
@@ -666,6 +682,7 @@ static int nfs_vmtruncate(struct inode * inode, loff_t offset)
if (err)
goto out;
+ trace_nfs_size_truncate(inode, offset);
i_size_write(inode, offset);
/* Optimisation */
if (offset == 0)
@@ -1024,7 +1041,7 @@ struct nfs_open_context *alloc_nfs_open_context(struct dentry *dentry,
ctx->cred = get_cred(filp->f_cred);
else
ctx->cred = get_current_cred();
- ctx->ll_cred = NULL;
+ rcu_assign_pointer(ctx->ll_cred, NULL);
ctx->state = NULL;
ctx->mode = f_mode;
ctx->flags = 0;
@@ -1063,7 +1080,7 @@ static void __put_nfs_open_context(struct nfs_open_context *ctx, int is_sync)
put_cred(ctx->cred);
dput(ctx->dentry);
nfs_sb_deactive(sb);
- put_rpccred(ctx->ll_cred);
+ put_rpccred(rcu_dereference_protected(ctx->ll_cred, 1));
kfree(ctx->mdsthreshold);
kfree_rcu(ctx, rcu_head);
}
@@ -1175,7 +1192,6 @@ int
__nfs_revalidate_inode(struct nfs_server *server, struct inode *inode)
{
int status = -ESTALE;
- struct nfs4_label *label = NULL;
struct nfs_fattr *fattr = NULL;
struct nfs_inode *nfsi = NFS_I(inode);
@@ -1197,20 +1213,13 @@ __nfs_revalidate_inode(struct nfs_server *server, struct inode *inode)
}
status = -ENOMEM;
- fattr = nfs_alloc_fattr();
+ fattr = nfs_alloc_fattr_with_label(NFS_SERVER(inode));
if (fattr == NULL)
goto out;
nfs_inc_stats(inode, NFSIOS_INODEREVALIDATE);
- label = nfs4_label_alloc(NFS_SERVER(inode), GFP_KERNEL);
- if (IS_ERR(label)) {
- status = PTR_ERR(label);
- goto out;
- }
-
- status = NFS_PROTO(inode)->getattr(server, NFS_FH(inode), fattr,
- label, inode);
+ status = NFS_PROTO(inode)->getattr(server, NFS_FH(inode), fattr, inode);
if (status != 0) {
dfprintk(PAGECACHE, "nfs_revalidate_inode: (%s/%Lu) getattr failed, error=%d\n",
inode->i_sb->s_id,
@@ -1227,7 +1236,7 @@ __nfs_revalidate_inode(struct nfs_server *server, struct inode *inode)
else
nfs_zap_caches(inode);
}
- goto err_out;
+ goto out;
}
status = nfs_refresh_inode(inode, fattr);
@@ -1235,20 +1244,18 @@ __nfs_revalidate_inode(struct nfs_server *server, struct inode *inode)
dfprintk(PAGECACHE, "nfs_revalidate_inode: (%s/%Lu) refresh failed, error=%d\n",
inode->i_sb->s_id,
(unsigned long long)NFS_FILEID(inode), status);
- goto err_out;
+ goto out;
}
if (nfsi->cache_validity & NFS_INO_INVALID_ACL)
nfs_zap_acl_cache(inode);
- nfs_setsecurity(inode, fattr, label);
+ nfs_setsecurity(inode, fattr);
dfprintk(PAGECACHE, "NFS: (%s/%Lu) revalidation complete\n",
inode->i_sb->s_id,
(unsigned long long)NFS_FILEID(inode));
-err_out:
- nfs4_label_free(label);
out:
nfs_free_fattr(fattr);
trace_nfs_revalidate_inode_exit(inode, status);
@@ -1446,13 +1453,12 @@ static void nfs_wcc_update_inode(struct inode *inode, struct nfs_fattr *fattr)
&& (fattr->valid & NFS_ATTR_FATTR_MTIME)
&& timespec64_equal(&ts, &fattr->pre_mtime)) {
inode->i_mtime = fattr->mtime;
- if (S_ISDIR(inode->i_mode))
- nfs_set_cache_invalid(inode, NFS_INO_INVALID_DATA);
}
if ((fattr->valid & NFS_ATTR_FATTR_PRESIZE)
&& (fattr->valid & NFS_ATTR_FATTR_SIZE)
&& i_size_read(inode) == nfs_size_to_loff_t(fattr->pre_size)
&& !nfs_have_writebacks(inode)) {
+ trace_nfs_size_wcc(inode, fattr->size);
i_size_write(inode, nfs_size_to_loff_t(fattr->size));
}
}
@@ -1580,12 +1586,31 @@ struct nfs_fattr *nfs_alloc_fattr(void)
struct nfs_fattr *fattr;
fattr = kmalloc(sizeof(*fattr), GFP_NOFS);
- if (fattr != NULL)
+ if (fattr != NULL) {
nfs_fattr_init(fattr);
+ fattr->label = NULL;
+ }
return fattr;
}
EXPORT_SYMBOL_GPL(nfs_alloc_fattr);
+struct nfs_fattr *nfs_alloc_fattr_with_label(struct nfs_server *server)
+{
+ struct nfs_fattr *fattr = nfs_alloc_fattr();
+
+ if (!fattr)
+ return NULL;
+
+ fattr->label = nfs4_label_alloc(server, GFP_NOFS);
+ if (IS_ERR(fattr->label)) {
+ kfree(fattr);
+ return NULL;
+ }
+
+ return fattr;
+}
+EXPORT_SYMBOL_GPL(nfs_alloc_fattr_with_label);
+
struct nfs_fh *nfs_alloc_fhandle(void)
{
struct nfs_fh *fh;
@@ -1777,8 +1802,10 @@ static int nfs_inode_finish_partial_attr_update(const struct nfs_fattr *fattr,
NFS_INO_INVALID_BLOCKS | NFS_INO_INVALID_OTHER |
NFS_INO_INVALID_NLINK;
unsigned long cache_validity = NFS_I(inode)->cache_validity;
+ enum nfs4_change_attr_type ctype = NFS_SERVER(inode)->change_attr_type;
- if (!(cache_validity & NFS_INO_INVALID_CHANGE) &&
+ if (ctype != NFS4_CHANGE_TYPE_IS_UNDEFINED &&
+ !(cache_validity & NFS_INO_INVALID_CHANGE) &&
(cache_validity & check_valid) != 0 &&
(fattr->valid & NFS_ATTR_FATTR_CHANGE) != 0 &&
nfs_inode_attrs_cmp_monotonic(fattr, inode) == 0)
@@ -2095,16 +2122,11 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
/* Do we perhaps have any outstanding writes, or has
* the file grown beyond our last write? */
if (!nfs_have_writebacks(inode) || new_isize > cur_isize) {
+ trace_nfs_size_update(inode, new_isize);
i_size_write(inode, new_isize);
if (!have_writers)
invalid |= NFS_INO_INVALID_DATA;
}
- dprintk("NFS: isize change on server for file %s/%ld "
- "(%Ld to %Ld)\n",
- inode->i_sb->s_id,
- inode->i_ino,
- (long long)cur_isize,
- (long long)new_isize);
}
if (new_isize == 0 &&
!(fattr->valid & (NFS_ATTR_FATTR_SPACE_USED |
@@ -2155,11 +2177,8 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
save_cache_validity & NFS_INO_INVALID_OTHER;
if (fattr->valid & NFS_ATTR_FATTR_NLINK) {
- if (inode->i_nlink != fattr->nlink) {
- if (S_ISDIR(inode->i_mode))
- invalid |= NFS_INO_INVALID_DATA;
+ if (inode->i_nlink != fattr->nlink)
set_nlink(inode, fattr->nlink);
- }
} else if (fattr_supported & NFS_ATTR_FATTR_NLINK)
nfsi->cache_validity |=
save_cache_validity & NFS_INO_INVALID_NLINK;
@@ -2260,14 +2279,7 @@ static void init_once(void *foo)
INIT_LIST_HEAD(&nfsi->open_files);
INIT_LIST_HEAD(&nfsi->access_cache_entry_lru);
INIT_LIST_HEAD(&nfsi->access_cache_inode_lru);
- INIT_LIST_HEAD(&nfsi->commit_info.list);
- atomic_long_set(&nfsi->nrequests, 0);
- atomic_long_set(&nfsi->commit_info.ncommit, 0);
- atomic_set(&nfsi->commit_info.rpcs_out, 0);
- init_rwsem(&nfsi->rmdir_sem);
- mutex_init(&nfsi->commit_mutex);
nfs4_init_once(nfsi);
- nfsi->cache_change_attribute = 0;
}
static int __init nfs_init_inodecache(void)
diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h
index 66fc936834f2..12f6acb483bb 100644
--- a/fs/nfs/internal.h
+++ b/fs/nfs/internal.h
@@ -193,7 +193,7 @@ extern void nfs_clients_exit(struct net *net);
extern struct nfs_client *nfs_alloc_client(const struct nfs_client_initdata *);
int nfs_create_rpc_client(struct nfs_client *, const struct nfs_client_initdata *, rpc_authflavor_t);
struct nfs_client *nfs_get_client(const struct nfs_client_initdata *);
-int nfs_probe_fsinfo(struct nfs_server *server, struct nfs_fh *, struct nfs_fattr *);
+int nfs_probe_server(struct nfs_server *, struct nfs_fh *);
void nfs_server_insert_lists(struct nfs_server *);
void nfs_server_remove_lists(struct nfs_server *);
void nfs_init_timeout_values(struct rpc_timeout *to, int proto, int timeo, int retrans);
@@ -209,6 +209,7 @@ extern struct nfs_client *
nfs4_find_client_sessionid(struct net *, const struct sockaddr *,
struct nfs4_sessionid *, u32);
extern struct nfs_server *nfs_create_server(struct fs_context *);
+extern void nfs4_server_set_init_caps(struct nfs_server *);
extern struct nfs_server *nfs4_create_server(struct fs_context *);
extern struct nfs_server *nfs4_create_referral_server(struct fs_context *);
extern int nfs4_update_server(struct nfs_server *server, const char *hostname,
@@ -341,14 +342,6 @@ nfs4_label_copy(struct nfs4_label *dst, struct nfs4_label *src)
return dst;
}
-static inline void nfs4_label_free(struct nfs4_label *label)
-{
- if (label) {
- kfree(label->label);
- kfree(label);
- }
- return;
-}
static inline void nfs_zap_label_cache_locked(struct nfs_inode *nfsi)
{
@@ -357,7 +350,6 @@ static inline void nfs_zap_label_cache_locked(struct nfs_inode *nfsi)
}
#else
static inline struct nfs4_label *nfs4_label_alloc(struct nfs_server *server, gfp_t flags) { return NULL; }
-static inline void nfs4_label_free(void *label) {}
static inline void nfs_zap_label_cache_locked(struct nfs_inode *nfsi)
{
}
diff --git a/fs/nfs/namespace.c b/fs/nfs/namespace.c
index bc0c698f3350..3295af4110f1 100644
--- a/fs/nfs/namespace.c
+++ b/fs/nfs/namespace.c
@@ -308,8 +308,7 @@ int nfs_submount(struct fs_context *fc, struct nfs_server *server)
/* Look it up again to get its attributes */
err = server->nfs_client->rpc_ops->lookup(d_inode(parent), dentry,
- ctx->mntfh, ctx->clone_data.fattr,
- NULL);
+ ctx->mntfh, ctx->clone_data.fattr);
dput(parent);
if (err != 0)
return err;
diff --git a/fs/nfs/nfs3proc.c b/fs/nfs/nfs3proc.c
index f7524310ddf4..7100514d306b 100644
--- a/fs/nfs/nfs3proc.c
+++ b/fs/nfs/nfs3proc.c
@@ -100,8 +100,7 @@ nfs3_proc_get_root(struct nfs_server *server, struct nfs_fh *fhandle,
*/
static int
nfs3_proc_getattr(struct nfs_server *server, struct nfs_fh *fhandle,
- struct nfs_fattr *fattr, struct nfs4_label *label,
- struct inode *inode)
+ struct nfs_fattr *fattr, struct inode *inode)
{
struct rpc_message msg = {
.rpc_proc = &nfs3_procedures[NFS3PROC_GETATTR],
@@ -193,8 +192,7 @@ __nfs3_proc_lookup(struct inode *dir, const char *name, size_t len,
static int
nfs3_proc_lookup(struct inode *dir, struct dentry *dentry,
- struct nfs_fh *fhandle, struct nfs_fattr *fattr,
- struct nfs4_label *label)
+ struct nfs_fh *fhandle, struct nfs_fattr *fattr)
{
unsigned short task_flags = 0;
@@ -209,7 +207,7 @@ nfs3_proc_lookup(struct inode *dir, struct dentry *dentry,
}
static int nfs3_proc_lookupp(struct inode *inode, struct nfs_fh *fhandle,
- struct nfs_fattr *fattr, struct nfs4_label *label)
+ struct nfs_fattr *fattr)
{
const char dotdot[] = "..";
const size_t len = strlen(dotdot);
@@ -323,7 +321,7 @@ nfs3_do_create(struct inode *dir, struct dentry *dentry, struct nfs3_createdata
if (status != 0)
return ERR_PTR(status);
- return nfs_add_or_obtain(dentry, data->res.fh, data->res.fattr, NULL);
+ return nfs_add_or_obtain(dentry, data->res.fh, data->res.fattr);
}
static void nfs3_free_createdata(struct nfs3_createdata *data)
diff --git a/fs/nfs/nfs3xdr.c b/fs/nfs/nfs3xdr.c
index e6eca1d7481b..9274c9c5efea 100644
--- a/fs/nfs/nfs3xdr.c
+++ b/fs/nfs/nfs3xdr.c
@@ -2227,7 +2227,7 @@ static int decode_fsinfo3resok(struct xdr_stream *xdr,
/* ignore properties */
result->lease_time = 0;
- result->change_attr_type = NFS4_CHANGE_TYPE_IS_TIME_METADATA;
+ result->change_attr_type = NFS4_CHANGE_TYPE_IS_UNDEFINED;
return 0;
}
diff --git a/fs/nfs/nfs42proc.c b/fs/nfs/nfs42proc.c
index a24349512ffe..08355b66e7cb 100644
--- a/fs/nfs/nfs42proc.c
+++ b/fs/nfs/nfs42proc.c
@@ -83,6 +83,10 @@ static int _nfs42_proc_fallocate(struct rpc_message *msg, struct file *filep,
status = nfs_post_op_update_inode_force_wcc(inode,
res.falloc_fattr);
+ if (msg->rpc_proc == &nfs4_procedures[NFSPROC4_CLNT_ALLOCATE])
+ trace_nfs4_fallocate(inode, &args, status);
+ else
+ trace_nfs4_deallocate(inode, &args, status);
kfree(res.falloc_fattr);
return status;
}
@@ -363,6 +367,7 @@ static ssize_t _nfs42_proc_copy(struct file *src,
status = nfs4_call_sync(dst_server->client, dst_server, &msg,
&args->seq_args, &res->seq_res, 0);
+ trace_nfs4_copy(src_inode, dst_inode, args, res, nss, status);
if (status == -ENOTSUPP)
dst_server->caps &= ~NFS_CAP_COPY;
if (status)
@@ -504,6 +509,7 @@ static void nfs42_offload_cancel_done(struct rpc_task *task, void *calldata)
{
struct nfs42_offloadcancel_data *data = calldata;
+ trace_nfs4_offload_cancel(&data->args, task->tk_status);
nfs41_sequence_done(task, &data->res.osr_seq_res);
if (task->tk_status &&
nfs4_async_handle_error(task, data->seq_server, NULL,
@@ -598,6 +604,7 @@ static int _nfs42_proc_copy_notify(struct file *src, struct file *dst,
status = nfs4_call_sync(src_server->client, src_server, &msg,
&args->cna_seq_args, &res->cnr_seq_res, 0);
+ trace_nfs4_copy_notify(file_inode(src), args, res, status);
if (status == -ENOTSUPP)
src_server->caps &= ~NFS_CAP_COPY_NOTIFY;
@@ -678,6 +685,7 @@ static loff_t _nfs42_proc_llseek(struct file *filep,
status = nfs4_call_sync(server->client, server, &msg,
&args.seq_args, &res.seq_res, 0);
+ trace_nfs4_llseek(inode, &args, &res, status);
if (status == -ENOTSUPP)
server->caps &= ~NFS_CAP_SEEK;
if (status)
@@ -1071,6 +1079,7 @@ static int _nfs42_proc_clone(struct rpc_message *msg, struct file *src_f,
status = nfs4_call_sync(server->client, server, msg,
&args.seq_args, &res.seq_res, 0);
+ trace_nfs4_clone(src_inode, dst_inode, &args, status);
if (status == 0) {
nfs42_copy_dest_done(dst_inode, dst_offset, count);
status = nfs_post_op_update_inode(dst_inode, res.dst_fattr);
diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h
index ba78df4b13d9..ed5eaca6801e 100644
--- a/fs/nfs/nfs4_fs.h
+++ b/fs/nfs/nfs4_fs.h
@@ -234,7 +234,6 @@ struct nfs4_opendata {
struct nfs4_string group_name;
struct nfs4_label *a_label;
struct nfs_fattr f_attr;
- struct nfs4_label *f_label;
struct dentry *dir;
struct dentry *dentry;
struct nfs4_state_owner *owner;
@@ -317,8 +316,7 @@ extern int nfs4_set_rw_stateid(nfs4_stateid *stateid,
const struct nfs_lock_context *l_ctx,
fmode_t fmode);
extern int nfs4_proc_getattr(struct nfs_server *server, struct nfs_fh *fhandle,
- struct nfs_fattr *fattr, struct nfs4_label *label,
- struct inode *inode);
+ struct nfs_fattr *fattr, struct inode *inode);
extern int update_open_stateid(struct nfs4_state *state,
const nfs4_stateid *open_stateid,
const nfs4_stateid *deleg_stateid,
diff --git a/fs/nfs/nfs4client.c b/fs/nfs/nfs4client.c
index af57332503be..d8b5a250ca05 100644
--- a/fs/nfs/nfs4client.c
+++ b/fs/nfs/nfs4client.c
@@ -1059,31 +1059,15 @@ static void nfs4_session_limit_xasize(struct nfs_server *server)
#endif
}
-static int nfs4_server_common_setup(struct nfs_server *server,
- struct nfs_fh *mntfh, bool auth_probe)
+void nfs4_server_set_init_caps(struct nfs_server *server)
{
- struct nfs_fattr *fattr;
- int error;
-
- /* data servers support only a subset of NFSv4.1 */
- if (is_ds_only_client(server->nfs_client))
- return -EPROTONOSUPPORT;
-
- fattr = nfs_alloc_fattr();
- if (fattr == NULL)
- return -ENOMEM;
-
- /* We must ensure the session is initialised first */
- error = nfs4_init_session(server->nfs_client);
- if (error < 0)
- goto out;
-
/* Set the basic capabilities */
server->caps |= server->nfs_client->cl_mvops->init_caps;
if (server->flags & NFS_MOUNT_NORDIRPLUS)
server->caps &= ~NFS_CAP_READDIRPLUS;
if (server->nfs_client->cl_proto == XPRT_TRANSPORT_RDMA)
server->caps &= ~NFS_CAP_READ_PLUS;
+
/*
* Don't use NFS uid/gid mapping if we're using AUTH_SYS or lower
* authentication.
@@ -1091,7 +1075,23 @@ static int nfs4_server_common_setup(struct nfs_server *server,
if (nfs4_disable_idmapping &&
server->client->cl_auth->au_flavor == RPC_AUTH_UNIX)
server->caps |= NFS_CAP_UIDGID_NOMAP;
+}
+static int nfs4_server_common_setup(struct nfs_server *server,
+ struct nfs_fh *mntfh, bool auth_probe)
+{
+ int error;
+
+ /* data servers support only a subset of NFSv4.1 */
+ if (is_ds_only_client(server->nfs_client))
+ return -EPROTONOSUPPORT;
+
+ /* We must ensure the session is initialised first */
+ error = nfs4_init_session(server->nfs_client);
+ if (error < 0)
+ goto out;
+
+ nfs4_server_set_init_caps(server);
/* Probe the root fh to retrieve its FSID and filehandle */
error = nfs4_get_rootfh(server, mntfh, auth_probe);
@@ -1103,7 +1103,7 @@ static int nfs4_server_common_setup(struct nfs_server *server,
(unsigned long long) server->fsid.minor);
nfs_display_fhandle(mntfh, "Pseudo-fs root FH");
- error = nfs_probe_fsinfo(server, mntfh, fattr);
+ error = nfs_probe_server(server, mntfh);
if (error < 0)
goto out;
@@ -1117,7 +1117,6 @@ static int nfs4_server_common_setup(struct nfs_server *server,
server->mount_time = jiffies;
server->destroy = nfs4_destroy_server;
out:
- nfs_free_fattr(fattr);
return error;
}
@@ -1288,30 +1287,6 @@ error:
return ERR_PTR(error);
}
-/*
- * Grab the destination's particulars, including lease expiry time.
- *
- * Returns zero if probe succeeded and retrieved FSID matches the FSID
- * we have cached.
- */
-static int nfs_probe_destination(struct nfs_server *server)
-{
- struct inode *inode = d_inode(server->super->s_root);
- struct nfs_fattr *fattr;
- int error;
-
- fattr = nfs_alloc_fattr();
- if (fattr == NULL)
- return -ENOMEM;
-
- /* Sanity: the probe won't work if the destination server
- * does not recognize the migrated FH. */
- error = nfs_probe_fsinfo(server, NFS_FH(inode), fattr);
-
- nfs_free_fattr(fattr);
- return error;
-}
-
/**
* nfs4_update_server - Move an nfs_server to a different nfs_client
*
@@ -1372,5 +1347,5 @@ int nfs4_update_server(struct nfs_server *server, const char *hostname,
server->nfs_client->cl_hostname = kstrdup(hostname, GFP_KERNEL);
nfs_server_insert_lists(server);
- return nfs_probe_destination(server);
+ return nfs_probe_server(server, NFS_FH(d_inode(server->super->s_root)));
}
diff --git a/fs/nfs/nfs4file.c b/fs/nfs/nfs4file.c
index c91565227ea2..e79ae4cbc395 100644
--- a/fs/nfs/nfs4file.c
+++ b/fs/nfs/nfs4file.c
@@ -317,7 +317,7 @@ static int read_name_gen = 1;
static struct file *__nfs42_ssc_open(struct vfsmount *ss_mnt,
struct nfs_fh *src_fh, nfs4_stateid *stateid)
{
- struct nfs_fattr fattr;
+ struct nfs_fattr *fattr = nfs_alloc_fattr();
struct file *filep, *res;
struct nfs_server *server;
struct inode *r_ino = NULL;
@@ -328,9 +328,10 @@ static struct file *__nfs42_ssc_open(struct vfsmount *ss_mnt,
server = NFS_SERVER(ss_mnt->mnt_root->d_inode);
- nfs_fattr_init(&fattr);
+ if (!fattr)
+ return ERR_PTR(-ENOMEM);
- status = nfs4_proc_getattr(server, src_fh, &fattr, NULL, NULL);
+ status = nfs4_proc_getattr(server, src_fh, fattr, NULL);
if (status < 0) {
res = ERR_PTR(status);
goto out;
@@ -343,20 +344,18 @@ static struct file *__nfs42_ssc_open(struct vfsmount *ss_mnt,
goto out;
snprintf(read_name, len, SSC_READ_NAME_BODY, read_name_gen++);
- r_ino = nfs_fhget(ss_mnt->mnt_root->d_inode->i_sb, src_fh, &fattr,
- NULL);
+ r_ino = nfs_fhget(ss_mnt->mnt_root->d_inode->i_sb, src_fh, fattr);
if (IS_ERR(r_ino)) {
res = ERR_CAST(r_ino);
goto out_free_name;
}
- filep = alloc_file_pseudo(r_ino, ss_mnt, read_name, FMODE_READ,
+ filep = alloc_file_pseudo(r_ino, ss_mnt, read_name, O_RDONLY,
r_ino->i_fop);
if (IS_ERR(filep)) {
res = ERR_CAST(filep);
goto out_free_name;
}
- filep->f_mode |= FMODE_READ;
ctx = alloc_nfs_open_context(filep->f_path.dentry, filep->f_mode,
filep);
@@ -388,6 +387,7 @@ static struct file *__nfs42_ssc_open(struct vfsmount *ss_mnt,
out_free_name:
kfree(read_name);
out:
+ nfs_free_fattr(fattr);
return res;
out_stateowner:
nfs4_put_state_owner(sp);
diff --git a/fs/nfs/nfs4idmap.c b/fs/nfs/nfs4idmap.c
index 8d8aba305ecc..f331866dd418 100644
--- a/fs/nfs/nfs4idmap.c
+++ b/fs/nfs/nfs4idmap.c
@@ -487,7 +487,7 @@ nfs_idmap_new(struct nfs_client *clp)
err_destroy_pipe:
rpc_destroy_pipe_data(idmap->idmap_pipe);
err:
- get_user_ns(idmap->user_ns);
+ put_user_ns(idmap->user_ns);
kfree(idmap);
return error;
}
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 459860aa8fd7..ee3bc79f6ca3 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -93,11 +93,11 @@ struct nfs4_opendata;
static int _nfs4_recover_proc_open(struct nfs4_opendata *data);
static int nfs4_do_fsinfo(struct nfs_server *, struct nfs_fh *, struct nfs_fsinfo *);
static void nfs_fixup_referral_attributes(struct nfs_fattr *fattr);
-static int _nfs4_proc_getattr(struct nfs_server *server, struct nfs_fh *fhandle, struct nfs_fattr *fattr, struct nfs4_label *label, struct inode *inode);
+static int _nfs4_proc_getattr(struct nfs_server *server, struct nfs_fh *fhandle,
+ struct nfs_fattr *fattr, struct inode *inode);
static int nfs4_do_setattr(struct inode *inode, const struct cred *cred,
struct nfs_fattr *fattr, struct iattr *sattr,
- struct nfs_open_context *ctx, struct nfs4_label *ilabel,
- struct nfs4_label *olabel);
+ struct nfs_open_context *ctx, struct nfs4_label *ilabel);
#ifdef CONFIG_NFS_V4_1
static struct rpc_task *_nfs41_proc_sequence(struct nfs_client *clp,
const struct cred *cred,
@@ -1330,7 +1330,6 @@ nfs4_map_atomic_open_claim(struct nfs_server *server,
static void nfs4_init_opendata_res(struct nfs4_opendata *p)
{
p->o_res.f_attr = &p->f_attr;
- p->o_res.f_label = p->f_label;
p->o_res.seqid = p->o_arg.seqid;
p->c_res.seqid = p->c_arg.seqid;
p->o_res.server = p->o_arg.server;
@@ -1356,8 +1355,8 @@ static struct nfs4_opendata *nfs4_opendata_alloc(struct dentry *dentry,
if (p == NULL)
goto err;
- p->f_label = nfs4_label_alloc(server, gfp_mask);
- if (IS_ERR(p->f_label))
+ p->f_attr.label = nfs4_label_alloc(server, gfp_mask);
+ if (IS_ERR(p->f_attr.label))
goto err_free_p;
p->a_label = nfs4_label_alloc(server, gfp_mask);
@@ -1389,27 +1388,22 @@ static struct nfs4_opendata *nfs4_opendata_alloc(struct dentry *dentry,
sizeof(p->o_arg.u.verifier.data));
}
}
- /* don't put an ACCESS op in OPEN compound if O_EXCL, because ACCESS
- * will return permission denied for all bits until close */
- if (!(flags & O_EXCL)) {
- /* ask server to check for all possible rights as results
- * are cached */
- switch (p->o_arg.claim) {
- default:
- break;
- case NFS4_OPEN_CLAIM_NULL:
- case NFS4_OPEN_CLAIM_FH:
- p->o_arg.access = NFS4_ACCESS_READ |
- NFS4_ACCESS_MODIFY |
- NFS4_ACCESS_EXTEND |
- NFS4_ACCESS_EXECUTE;
+ /* ask server to check for all possible rights as results
+ * are cached */
+ switch (p->o_arg.claim) {
+ default:
+ break;
+ case NFS4_OPEN_CLAIM_NULL:
+ case NFS4_OPEN_CLAIM_FH:
+ p->o_arg.access = NFS4_ACCESS_READ | NFS4_ACCESS_MODIFY |
+ NFS4_ACCESS_EXTEND | NFS4_ACCESS_DELETE |
+ NFS4_ACCESS_EXECUTE;
#ifdef CONFIG_NFS_V4_2
- if (server->caps & NFS_CAP_XATTR)
- p->o_arg.access |= NFS4_ACCESS_XAREAD |
- NFS4_ACCESS_XAWRITE |
- NFS4_ACCESS_XALIST;
+ if (!(server->caps & NFS_CAP_XATTR))
+ break;
+ p->o_arg.access |= NFS4_ACCESS_XAREAD | NFS4_ACCESS_XAWRITE |
+ NFS4_ACCESS_XALIST;
#endif
- }
}
p->o_arg.clientid = server->nfs_client->cl_clientid;
p->o_arg.id.create_time = ktime_to_ns(sp->so_seqid.create_time);
@@ -1440,7 +1434,7 @@ static struct nfs4_opendata *nfs4_opendata_alloc(struct dentry *dentry,
err_free_label:
nfs4_label_free(p->a_label);
err_free_f:
- nfs4_label_free(p->f_label);
+ nfs4_label_free(p->f_attr.label);
err_free_p:
kfree(p);
err:
@@ -1462,7 +1456,7 @@ static void nfs4_opendata_free(struct kref *kref)
nfs4_put_state_owner(p->owner);
nfs4_label_free(p->a_label);
- nfs4_label_free(p->f_label);
+ nfs4_label_free(p->f_attr.label);
dput(p->dir);
dput(p->dentry);
@@ -1610,15 +1604,16 @@ static bool nfs_stateid_is_sequential(struct nfs4_state *state,
{
if (test_bit(NFS_OPEN_STATE, &state->flags)) {
/* The common case - we're updating to a new sequence number */
- if (nfs4_stateid_match_other(stateid, &state->open_stateid) &&
- nfs4_stateid_is_next(&state->open_stateid, stateid)) {
- return true;
+ if (nfs4_stateid_match_other(stateid, &state->open_stateid)) {
+ if (nfs4_stateid_is_next(&state->open_stateid, stateid))
+ return true;
+ return false;
}
- } else {
- /* This is the first OPEN in this generation */
- if (stateid->seqid == cpu_to_be32(1))
- return true;
+ /* The server returned a new stateid */
}
+ /* This is the first OPEN in this generation */
+ if (stateid->seqid == cpu_to_be32(1))
+ return true;
return false;
}
@@ -2014,7 +2009,7 @@ nfs4_opendata_get_inode(struct nfs4_opendata *data)
if (!(data->f_attr.valid & NFS_ATTR_FATTR))
return ERR_PTR(-EAGAIN);
inode = nfs_fhget(data->dir->d_sb, &data->o_res.fh,
- &data->f_attr, data->f_label);
+ &data->f_attr);
break;
default:
inode = d_inode(data->dentry);
@@ -2473,11 +2468,15 @@ static void nfs4_open_prepare(struct rpc_task *task, void *calldata)
/* Set the create mode (note dependency on the session type) */
data->o_arg.createmode = NFS4_CREATE_UNCHECKED;
if (data->o_arg.open_flags & O_EXCL) {
- data->o_arg.createmode = NFS4_CREATE_EXCLUSIVE;
- if (nfs4_has_persistent_session(clp))
+ data->o_arg.createmode = NFS4_CREATE_EXCLUSIVE4_1;
+ if (clp->cl_mvops->minor_version == 0) {
+ data->o_arg.createmode = NFS4_CREATE_EXCLUSIVE;
+ /* don't put an ACCESS op in OPEN compound if O_EXCL,
+ * because ACCESS will return permission denied for
+ * all bits until close */
+ data->o_res.access_request = data->o_arg.access = 0;
+ } else if (nfs4_has_persistent_session(clp))
data->o_arg.createmode = NFS4_CREATE_GUARDED;
- else if (clp->cl_mvops->minor_version > 0)
- data->o_arg.createmode = NFS4_CREATE_EXCLUSIVE4_1;
}
return;
unlock_no_action:
@@ -2709,8 +2708,7 @@ static int _nfs4_proc_open(struct nfs4_opendata *data,
}
if (!(o_res->f_attr->valid & NFS_ATTR_FATTR)) {
nfs4_sequence_free_slot(&o_res->seq_res);
- nfs4_proc_getattr(server, &o_res->fh, o_res->f_attr,
- o_res->f_label, NULL);
+ nfs4_proc_getattr(server, &o_res->fh, o_res->f_attr, NULL);
}
return 0;
}
@@ -3126,7 +3124,6 @@ static int _nfs4_do_open(struct inode *dir,
enum open_claim_type4 claim = NFS4_OPEN_CLAIM_NULL;
struct iattr *sattr = c->sattr;
struct nfs4_label *label = c->label;
- struct nfs4_label *olabel = NULL;
int status;
/* Protect against reboot recovery conflicts */
@@ -3149,19 +3146,11 @@ static int _nfs4_do_open(struct inode *dir,
if (opendata == NULL)
goto err_put_state_owner;
- if (label) {
- olabel = nfs4_label_alloc(server, GFP_KERNEL);
- if (IS_ERR(olabel)) {
- status = PTR_ERR(olabel);
- goto err_opendata_put;
- }
- }
-
if (server->attr_bitmask[2] & FATTR4_WORD2_MDSTHRESHOLD) {
if (!opendata->f_attr.mdsthreshold) {
opendata->f_attr.mdsthreshold = pnfs_mdsthreshold_alloc();
if (!opendata->f_attr.mdsthreshold)
- goto err_free_label;
+ goto err_opendata_put;
}
opendata->o_arg.open_bitmap = &nfs4_pnfs_open_bitmap[0];
}
@@ -3170,7 +3159,7 @@ static int _nfs4_do_open(struct inode *dir,
status = _nfs4_open_and_get_state(opendata, flags, ctx);
if (status != 0)
- goto err_free_label;
+ goto err_opendata_put;
state = ctx->state;
if ((opendata->o_arg.open_flags & (O_CREAT|O_EXCL)) == (O_CREAT|O_EXCL) &&
@@ -3187,11 +3176,11 @@ static int _nfs4_do_open(struct inode *dir,
nfs_fattr_init(opendata->o_res.f_attr);
status = nfs4_do_setattr(state->inode, cred,
opendata->o_res.f_attr, sattr,
- ctx, label, olabel);
+ ctx, label);
if (status == 0) {
nfs_setattr_update_inode(state->inode, sattr,
opendata->o_res.f_attr);
- nfs_setsecurity(state->inode, opendata->o_res.f_attr, olabel);
+ nfs_setsecurity(state->inode, opendata->o_res.f_attr);
}
sattr->ia_valid = ia_old;
}
@@ -3204,13 +3193,9 @@ static int _nfs4_do_open(struct inode *dir,
opendata->f_attr.mdsthreshold = NULL;
}
- nfs4_label_free(olabel);
-
nfs4_opendata_put(opendata);
nfs4_put_state_owner(sp);
return 0;
-err_free_label:
- nfs4_label_free(olabel);
err_opendata_put:
nfs4_opendata_put(opendata);
err_put_state_owner:
@@ -3355,8 +3340,7 @@ zero_stateid:
static int nfs4_do_setattr(struct inode *inode, const struct cred *cred,
struct nfs_fattr *fattr, struct iattr *sattr,
- struct nfs_open_context *ctx, struct nfs4_label *ilabel,
- struct nfs4_label *olabel)
+ struct nfs_open_context *ctx, struct nfs4_label *ilabel)
{
struct nfs_server *server = NFS_SERVER(inode);
__u32 bitmask[NFS4_BITMASK_SZ];
@@ -3370,7 +3354,6 @@ static int nfs4_do_setattr(struct inode *inode, const struct cred *cred,
};
struct nfs_setattrres res = {
.fattr = fattr,
- .label = olabel,
.server = server,
};
struct nfs4_exception exception = {
@@ -3387,7 +3370,7 @@ static int nfs4_do_setattr(struct inode *inode, const struct cred *cred,
adjust_flags |= NFS_INO_INVALID_OTHER;
do {
- nfs4_bitmap_copy_adjust(bitmask, nfs4_bitmask(server, olabel),
+ nfs4_bitmap_copy_adjust(bitmask, nfs4_bitmask(server, fattr->label),
inode, adjust_flags);
err = _nfs4_do_setattr(inode, &arg, &res, cred, ctx);
@@ -3562,7 +3545,6 @@ static void nfs4_close_done(struct rpc_task *task, void *data)
.stateid = &calldata->arg.stateid,
};
- dprintk("%s: begin!\n", __func__);
if (!nfs4_sequence_done(task, &calldata->res.seq_res))
return;
trace_nfs4_close(state, &calldata->arg, &calldata->res, task->tk_status);
@@ -3617,7 +3599,7 @@ out_release:
task->tk_status = 0;
nfs_release_seqid(calldata->arg.seqid);
nfs_refresh_inode(calldata->inode, &calldata->fattr);
- dprintk("%s: done, ret = %d!\n", __func__, task->tk_status);
+ dprintk("%s: ret = %d\n", __func__, task->tk_status);
return;
out_restart:
task->tk_status = 0;
@@ -3635,7 +3617,6 @@ static void nfs4_close_prepare(struct rpc_task *task, void *data)
bool is_rdonly, is_wronly, is_rdwr;
int call_close = 0;
- dprintk("%s: begin!\n", __func__);
if (nfs_wait_on_sequence(calldata->arg.seqid, task) != 0)
goto out_wait;
@@ -3709,7 +3690,6 @@ static void nfs4_close_prepare(struct rpc_task *task, void *data)
&calldata->res.seq_res,
task) != 0)
nfs_release_seqid(calldata->arg.seqid);
- dprintk("%s: done!\n", __func__);
return;
out_no_action:
task->tk_action = NULL;
@@ -3942,6 +3922,8 @@ int nfs4_server_capabilities(struct nfs_server *server, struct nfs_fh *fhandle)
.interruptible = true,
};
int err;
+
+ nfs4_server_set_init_caps(server);
do {
err = nfs4_handle_exception(server,
_nfs4_server_capabilities(server, fhandle),
@@ -4105,7 +4087,6 @@ static int nfs4_proc_get_root(struct nfs_server *server, struct nfs_fh *mntfh,
{
int error;
struct nfs_fattr *fattr = info->fattr;
- struct nfs4_label *label = fattr->label;
error = nfs4_server_capabilities(server, mntfh);
if (error < 0) {
@@ -4113,7 +4094,7 @@ static int nfs4_proc_get_root(struct nfs_server *server, struct nfs_fh *mntfh,
return error;
}
- error = nfs4_proc_getattr(server, mntfh, fattr, label, NULL);
+ error = nfs4_proc_getattr(server, mntfh, fattr, NULL);
if (error < 0) {
dprintk("nfs4_get_root: getattr error = %d\n", -error);
goto out;
@@ -4176,8 +4157,7 @@ out:
}
static int _nfs4_proc_getattr(struct nfs_server *server, struct nfs_fh *fhandle,
- struct nfs_fattr *fattr, struct nfs4_label *label,
- struct inode *inode)
+ struct nfs_fattr *fattr, struct inode *inode)
{
__u32 bitmask[NFS4_BITMASK_SZ];
struct nfs4_getattr_arg args = {
@@ -4186,7 +4166,6 @@ static int _nfs4_proc_getattr(struct nfs_server *server, struct nfs_fh *fhandle,
};
struct nfs4_getattr_res res = {
.fattr = fattr,
- .label = label,
.server = server,
};
struct rpc_message msg = {
@@ -4203,7 +4182,7 @@ static int _nfs4_proc_getattr(struct nfs_server *server, struct nfs_fh *fhandle,
if (inode && (server->flags & NFS_MOUNT_SOFTREVAL))
task_flags |= RPC_TASK_TIMEOUT;
- nfs4_bitmap_copy_adjust(bitmask, nfs4_bitmask(server, label), inode, 0);
+ nfs4_bitmap_copy_adjust(bitmask, nfs4_bitmask(server, fattr->label), inode, 0);
nfs_fattr_init(fattr);
nfs4_init_sequence(&args.seq_args, &res.seq_res, 0, 0);
return nfs4_do_call_sync(server->client, server, &msg,
@@ -4211,15 +4190,14 @@ static int _nfs4_proc_getattr(struct nfs_server *server, struct nfs_fh *fhandle,
}
int nfs4_proc_getattr(struct nfs_server *server, struct nfs_fh *fhandle,
- struct nfs_fattr *fattr, struct nfs4_label *label,
- struct inode *inode)
+ struct nfs_fattr *fattr, struct inode *inode)
{
struct nfs4_exception exception = {
.interruptible = true,
};
int err;
do {
- err = _nfs4_proc_getattr(server, fhandle, fattr, label, inode);
+ err = _nfs4_proc_getattr(server, fhandle, fattr, inode);
trace_nfs4_getattr(server, fhandle, fattr, err);
err = nfs4_handle_exception(server, err,
&exception);
@@ -4251,7 +4229,6 @@ nfs4_proc_setattr(struct dentry *dentry, struct nfs_fattr *fattr,
struct inode *inode = d_inode(dentry);
const struct cred *cred = NULL;
struct nfs_open_context *ctx = NULL;
- struct nfs4_label *label = NULL;
int status;
if (pnfs_ld_layoutret_on_setattr(inode) &&
@@ -4277,26 +4254,21 @@ nfs4_proc_setattr(struct dentry *dentry, struct nfs_fattr *fattr,
cred = ctx->cred;
}
- label = nfs4_label_alloc(NFS_SERVER(inode), GFP_KERNEL);
- if (IS_ERR(label))
- return PTR_ERR(label);
-
/* Return any delegations if we're going to change ACLs */
if ((sattr->ia_valid & (ATTR_MODE|ATTR_UID|ATTR_GID)) != 0)
nfs4_inode_make_writeable(inode);
- status = nfs4_do_setattr(inode, cred, fattr, sattr, ctx, NULL, label);
+ status = nfs4_do_setattr(inode, cred, fattr, sattr, ctx, NULL);
if (status == 0) {
nfs_setattr_update_inode(inode, sattr, fattr);
- nfs_setsecurity(inode, fattr, label);
+ nfs_setsecurity(inode, fattr);
}
- nfs4_label_free(label);
return status;
}
static int _nfs4_proc_lookup(struct rpc_clnt *clnt, struct inode *dir,
struct dentry *dentry, struct nfs_fh *fhandle,
- struct nfs_fattr *fattr, struct nfs4_label *label)
+ struct nfs_fattr *fattr)
{
struct nfs_server *server = NFS_SERVER(dir);
int status;
@@ -4308,7 +4280,6 @@ static int _nfs4_proc_lookup(struct rpc_clnt *clnt, struct inode *dir,
struct nfs4_lookup_res res = {
.server = server,
.fattr = fattr,
- .label = label,
.fh = fhandle,
};
struct rpc_message msg = {
@@ -4325,7 +4296,7 @@ static int _nfs4_proc_lookup(struct rpc_clnt *clnt, struct inode *dir,
if (nfs_lookup_is_soft_revalidate(dentry))
task_flags |= RPC_TASK_TIMEOUT;
- args.bitmask = nfs4_bitmask(server, label);
+ args.bitmask = nfs4_bitmask(server, fattr->label);
nfs_fattr_init(fattr);
@@ -4347,7 +4318,7 @@ static void nfs_fixup_secinfo_attributes(struct nfs_fattr *fattr)
static int nfs4_proc_lookup_common(struct rpc_clnt **clnt, struct inode *dir,
struct dentry *dentry, struct nfs_fh *fhandle,
- struct nfs_fattr *fattr, struct nfs4_label *label)
+ struct nfs_fattr *fattr)
{
struct nfs4_exception exception = {
.interruptible = true,
@@ -4356,7 +4327,7 @@ static int nfs4_proc_lookup_common(struct rpc_clnt **clnt, struct inode *dir,
const struct qstr *name = &dentry->d_name;
int err;
do {
- err = _nfs4_proc_lookup(client, dir, dentry, fhandle, fattr, label);
+ err = _nfs4_proc_lookup(client, dir, dentry, fhandle, fattr);
trace_nfs4_lookup(dir, name, err);
switch (err) {
case -NFS4ERR_BADNAME:
@@ -4392,13 +4363,12 @@ out:
}
static int nfs4_proc_lookup(struct inode *dir, struct dentry *dentry,
- struct nfs_fh *fhandle, struct nfs_fattr *fattr,
- struct nfs4_label *label)
+ struct nfs_fh *fhandle, struct nfs_fattr *fattr)
{
int status;
struct rpc_clnt *client = NFS_CLIENT(dir);
- status = nfs4_proc_lookup_common(&client, dir, dentry, fhandle, fattr, label);
+ status = nfs4_proc_lookup_common(&client, dir, dentry, fhandle, fattr);
if (client != NFS_CLIENT(dir)) {
rpc_shutdown_client(client);
nfs_fixup_secinfo_attributes(fattr);
@@ -4413,15 +4383,14 @@ nfs4_proc_lookup_mountpoint(struct inode *dir, struct dentry *dentry,
struct rpc_clnt *client = NFS_CLIENT(dir);
int status;
- status = nfs4_proc_lookup_common(&client, dir, dentry, fhandle, fattr, NULL);
+ status = nfs4_proc_lookup_common(&client, dir, dentry, fhandle, fattr);
if (status < 0)
return ERR_PTR(status);
return (client == NFS_CLIENT(dir)) ? rpc_clone_client(client) : client;
}
static int _nfs4_proc_lookupp(struct inode *inode,
- struct nfs_fh *fhandle, struct nfs_fattr *fattr,
- struct nfs4_label *label)
+ struct nfs_fh *fhandle, struct nfs_fattr *fattr)
{
struct rpc_clnt *clnt = NFS_CLIENT(inode);
struct nfs_server *server = NFS_SERVER(inode);
@@ -4433,7 +4402,6 @@ static int _nfs4_proc_lookupp(struct inode *inode,
struct nfs4_lookupp_res res = {
.server = server,
.fattr = fattr,
- .label = label,
.fh = fhandle,
};
struct rpc_message msg = {
@@ -4446,7 +4414,7 @@ static int _nfs4_proc_lookupp(struct inode *inode,
if (NFS_SERVER(inode)->flags & NFS_MOUNT_SOFTREVAL)
task_flags |= RPC_TASK_TIMEOUT;
- args.bitmask = nfs4_bitmask(server, label);
+ args.bitmask = nfs4_bitmask(server, fattr->label);
nfs_fattr_init(fattr);
@@ -4458,14 +4426,14 @@ static int _nfs4_proc_lookupp(struct inode *inode,
}
static int nfs4_proc_lookupp(struct inode *inode, struct nfs_fh *fhandle,
- struct nfs_fattr *fattr, struct nfs4_label *label)
+ struct nfs_fattr *fattr)
{
struct nfs4_exception exception = {
.interruptible = true,
};
int err;
do {
- err = _nfs4_proc_lookupp(inode, fhandle, fattr, label);
+ err = _nfs4_proc_lookupp(inode, fhandle, fattr);
trace_nfs4_lookupp(inode, err);
err = nfs4_handle_exception(NFS_SERVER(inode), err,
&exception);
@@ -4792,7 +4760,6 @@ static int _nfs4_proc_link(struct inode *inode, struct inode *dir, const struct
};
struct nfs4_link_res res = {
.server = server,
- .label = NULL,
};
struct rpc_message msg = {
.rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_LINK],
@@ -4801,18 +4768,12 @@ static int _nfs4_proc_link(struct inode *inode, struct inode *dir, const struct
};
int status = -ENOMEM;
- res.fattr = nfs_alloc_fattr();
+ res.fattr = nfs_alloc_fattr_with_label(server);
if (res.fattr == NULL)
goto out;
- res.label = nfs4_label_alloc(server, GFP_KERNEL);
- if (IS_ERR(res.label)) {
- status = PTR_ERR(res.label);
- goto out;
- }
-
nfs4_inode_make_writeable(inode);
- nfs4_bitmap_copy_adjust(bitmask, nfs4_bitmask(server, res.label), inode,
+ nfs4_bitmap_copy_adjust(bitmask, nfs4_bitmask(server, res.fattr->label), inode,
NFS_INO_INVALID_CHANGE);
status = nfs4_call_sync(server->client, server, &msg, &arg.seq_args, &res.seq_res, 1);
if (!status) {
@@ -4821,12 +4782,9 @@ static int _nfs4_proc_link(struct inode *inode, struct inode *dir, const struct
nfs4_inc_nlink(inode);
status = nfs_post_op_update_inode(inode, res.fattr);
if (!status)
- nfs_setsecurity(inode, res.fattr, res.label);
+ nfs_setsecurity(inode, res.fattr);
}
-
- nfs4_label_free(res.label);
-
out:
nfs_free_fattr(res.fattr);
return status;
@@ -4852,7 +4810,6 @@ struct nfs4_createdata {
struct nfs4_create_res res;
struct nfs_fh fh;
struct nfs_fattr fattr;
- struct nfs4_label *label;
};
static struct nfs4_createdata *nfs4_alloc_createdata(struct inode *dir,
@@ -4864,8 +4821,8 @@ static struct nfs4_createdata *nfs4_alloc_createdata(struct inode *dir,
if (data != NULL) {
struct nfs_server *server = NFS_SERVER(dir);
- data->label = nfs4_label_alloc(server, GFP_KERNEL);
- if (IS_ERR(data->label))
+ data->fattr.label = nfs4_label_alloc(server, GFP_KERNEL);
+ if (IS_ERR(data->fattr.label))
goto out_free;
data->msg.rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_CREATE];
@@ -4876,12 +4833,11 @@ static struct nfs4_createdata *nfs4_alloc_createdata(struct inode *dir,
data->arg.name = name;
data->arg.attrs = sattr;
data->arg.ftype = ftype;
- data->arg.bitmask = nfs4_bitmask(server, data->label);
+ data->arg.bitmask = nfs4_bitmask(server, data->fattr.label);
data->arg.umask = current_umask();
data->res.server = server;
data->res.fh = &data->fh;
data->res.fattr = &data->fattr;
- data->res.label = data->label;
nfs_fattr_init(data->res.fattr);
}
return data;
@@ -4903,14 +4859,14 @@ static int nfs4_do_create(struct inode *dir, struct dentry *dentry, struct nfs4_
data->res.fattr->time_start,
NFS_INO_INVALID_DATA);
spin_unlock(&dir->i_lock);
- status = nfs_instantiate(dentry, data->res.fh, data->res.fattr, data->res.label);
+ status = nfs_instantiate(dentry, data->res.fh, data->res.fattr);
}
return status;
}
static void nfs4_free_createdata(struct nfs4_createdata *data)
{
- nfs4_label_free(data->label);
+ nfs4_label_free(data->fattr.label);
kfree(data);
}
@@ -5348,8 +5304,6 @@ static bool nfs4_read_plus_not_supported(struct rpc_task *task,
static int nfs4_read_done(struct rpc_task *task, struct nfs_pgio_header *hdr)
{
- dprintk("--> %s\n", __func__);
-
if (!nfs4_sequence_done(task, &hdr->res.seq_res))
return -EAGAIN;
if (nfs4_read_stateid_changed(task, &hdr->args))
@@ -6005,17 +5959,18 @@ static int _nfs4_get_security_label(struct inode *inode, void *buf,
size_t buflen)
{
struct nfs_server *server = NFS_SERVER(inode);
- struct nfs_fattr fattr;
struct nfs4_label label = {0, 0, buflen, buf};
u32 bitmask[3] = { 0, 0, FATTR4_WORD2_SECURITY_LABEL };
+ struct nfs_fattr fattr = {
+ .label = &label,
+ };
struct nfs4_getattr_arg arg = {
.fh = NFS_FH(inode),
.bitmask = bitmask,
};
struct nfs4_getattr_res res = {
.fattr = &fattr,
- .label = &label,
.server = server,
};
struct rpc_message msg = {
@@ -6057,8 +6012,7 @@ static int nfs4_get_security_label(struct inode *inode, void *buf,
static int _nfs4_do_set_security_label(struct inode *inode,
struct nfs4_label *ilabel,
- struct nfs_fattr *fattr,
- struct nfs4_label *olabel)
+ struct nfs_fattr *fattr)
{
struct iattr sattr = {0};
@@ -6073,7 +6027,6 @@ static int _nfs4_do_set_security_label(struct inode *inode,
};
struct nfs_setattrres res = {
.fattr = fattr,
- .label = olabel,
.server = server,
};
struct rpc_message msg = {
@@ -6094,15 +6047,13 @@ static int _nfs4_do_set_security_label(struct inode *inode,
static int nfs4_do_set_security_label(struct inode *inode,
struct nfs4_label *ilabel,
- struct nfs_fattr *fattr,
- struct nfs4_label *olabel)
+ struct nfs_fattr *fattr)
{
struct nfs4_exception exception = { };
int err;
do {
- err = _nfs4_do_set_security_label(inode, ilabel,
- fattr, olabel);
+ err = _nfs4_do_set_security_label(inode, ilabel, fattr);
trace_nfs4_set_security_label(inode, err);
err = nfs4_handle_exception(NFS_SERVER(inode), err,
&exception);
@@ -6113,32 +6064,21 @@ static int nfs4_do_set_security_label(struct inode *inode,
static int
nfs4_set_security_label(struct inode *inode, const void *buf, size_t buflen)
{
- struct nfs4_label ilabel, *olabel = NULL;
- struct nfs_fattr fattr;
+ struct nfs4_label ilabel = {0, 0, buflen, (char *)buf };
+ struct nfs_fattr *fattr;
int status;
if (!nfs_server_capable(inode, NFS_CAP_SECURITY_LABEL))
return -EOPNOTSUPP;
- nfs_fattr_init(&fattr);
-
- ilabel.pi = 0;
- ilabel.lfs = 0;
- ilabel.label = (char *)buf;
- ilabel.len = buflen;
-
- olabel = nfs4_label_alloc(NFS_SERVER(inode), GFP_KERNEL);
- if (IS_ERR(olabel)) {
- status = -PTR_ERR(olabel);
- goto out;
- }
+ fattr = nfs_alloc_fattr_with_label(NFS_SERVER(inode));
+ if (fattr == NULL)
+ return -ENOMEM;
- status = nfs4_do_set_security_label(inode, &ilabel, &fattr, olabel);
+ status = nfs4_do_set_security_label(inode, &ilabel, fattr);
if (status == 0)
- nfs_setsecurity(inode, &fattr, olabel);
+ nfs_setsecurity(inode, fattr);
- nfs4_label_free(olabel);
-out:
return status;
}
#endif /* CONFIG_NFS_V4_SECURITY_LABEL */
@@ -7004,7 +6944,6 @@ static void nfs4_lock_prepare(struct rpc_task *task, void *calldata)
struct nfs4_lockdata *data = calldata;
struct nfs4_state *state = data->lsp->ls_state;
- dprintk("%s: begin!\n", __func__);
if (nfs_wait_on_sequence(data->arg.lock_seqid, task) != 0)
goto out_wait;
/* Do we need to do an open_to_lock_owner? */
@@ -7038,7 +6977,7 @@ out_release_lock_seqid:
nfs_release_seqid(data->arg.lock_seqid);
out_wait:
nfs4_sequence_done(task, &data->res.seq_res);
- dprintk("%s: done!, ret = %d\n", __func__, data->rpc_status);
+ dprintk("%s: ret = %d\n", __func__, data->rpc_status);
}
static void nfs4_lock_done(struct rpc_task *task, void *calldata)
@@ -7046,8 +6985,6 @@ static void nfs4_lock_done(struct rpc_task *task, void *calldata)
struct nfs4_lockdata *data = calldata;
struct nfs4_lock_state *lsp = data->lsp;
- dprintk("%s: begin!\n", __func__);
-
if (!nfs4_sequence_done(task, &data->res.seq_res))
return;
@@ -7081,7 +7018,7 @@ static void nfs4_lock_done(struct rpc_task *task, void *calldata)
goto out_restart;
}
out_done:
- dprintk("%s: done, ret = %d!\n", __func__, data->rpc_status);
+ dprintk("%s: ret = %d!\n", __func__, data->rpc_status);
return;
out_restart:
if (!data->cancelled)
@@ -7093,7 +7030,6 @@ static void nfs4_lock_release(void *calldata)
{
struct nfs4_lockdata *data = calldata;
- dprintk("%s: begin!\n", __func__);
nfs_free_seqid(data->arg.open_seqid);
if (data->cancelled && data->rpc_status == 0) {
struct rpc_task *task;
@@ -7107,7 +7043,6 @@ static void nfs4_lock_release(void *calldata)
nfs4_put_lock_state(data->lsp);
put_nfs_open_context(data->ctx);
kfree(data);
- dprintk("%s: done!\n", __func__);
}
static const struct rpc_call_ops nfs4_lock_ops = {
@@ -7154,7 +7089,6 @@ static int _nfs4_do_setlk(struct nfs4_state *state, int cmd, struct file_lock *f
if (client->cl_minorversion)
task_setup_data.flags |= RPC_TASK_MOVEABLE;
- dprintk("%s: begin!\n", __func__);
data = nfs4_alloc_lockdata(fl, nfs_file_open_context(fl->fl_file),
fl->fl_u.nfs4_fl.owner,
recovery_type == NFS_LOCK_NEW ? GFP_KERNEL : GFP_NOFS);
@@ -7185,7 +7119,7 @@ static int _nfs4_do_setlk(struct nfs4_state *state, int cmd, struct file_lock *f
data->cancelled = true;
trace_nfs4_set_lock(fl, state, &data->res.stateid, cmd, ret);
rpc_put_task(task);
- dprintk("%s: done, ret = %d!\n", __func__, ret);
+ dprintk("%s: ret = %d\n", __func__, ret);
return ret;
}
@@ -8856,14 +8790,12 @@ static void nfs4_get_lease_time_prepare(struct rpc_task *task,
struct nfs4_get_lease_time_data *data =
(struct nfs4_get_lease_time_data *)calldata;
- dprintk("--> %s\n", __func__);
/* just setup sequence, do not trigger session recovery
since we're invoked within one */
nfs4_setup_sequence(data->clp,
&data->args->la_seq_args,
&data->res->lr_seq_res,
task);
- dprintk("<-- %s\n", __func__);
}
/*
@@ -8875,13 +8807,11 @@ static void nfs4_get_lease_time_done(struct rpc_task *task, void *calldata)
struct nfs4_get_lease_time_data *data =
(struct nfs4_get_lease_time_data *)calldata;
- dprintk("--> %s\n", __func__);
if (!nfs4_sequence_done(task, &data->res->lr_seq_res))
return;
switch (task->tk_status) {
case -NFS4ERR_DELAY:
case -NFS4ERR_GRACE:
- dprintk("%s Retry: tk_status %d\n", __func__, task->tk_status);
rpc_delay(task, NFS4_POLL_RETRY_MIN);
task->tk_status = 0;
fallthrough;
@@ -8889,7 +8819,6 @@ static void nfs4_get_lease_time_done(struct rpc_task *task, void *calldata)
rpc_restart_call_prepare(task);
return;
}
- dprintk("<-- %s\n", __func__);
}
static const struct rpc_call_ops nfs4_get_lease_time_ops = {
@@ -9121,7 +9050,6 @@ int nfs4_proc_create_session(struct nfs_client *clp, const struct cred *cred)
dprintk("%s client>seqid %d sessionid %u:%u:%u:%u\n", __func__,
clp->cl_seqid, ptr[0], ptr[1], ptr[2], ptr[3]);
out:
- dprintk("<-- %s\n", __func__);
return status;
}
@@ -9139,8 +9067,6 @@ int nfs4_proc_destroy_session(struct nfs4_session *session,
};
int status = 0;
- dprintk("--> nfs4_proc_destroy_session\n");
-
/* session is still being setup */
if (!test_and_clear_bit(NFS4_SESSION_ESTABLISHED, &session->session_state))
return 0;
@@ -9152,8 +9078,6 @@ int nfs4_proc_destroy_session(struct nfs4_session *session,
if (status)
dprintk("NFS: Got error %d from the server on DESTROY_SESSION. "
"Session has been destroyed regardless...\n", status);
-
- dprintk("<-- nfs4_proc_destroy_session\n");
return status;
}
@@ -9201,7 +9125,7 @@ static void nfs41_sequence_call_done(struct rpc_task *task, void *data)
if (task->tk_status < 0) {
dprintk("%s ERROR %d\n", __func__, task->tk_status);
if (refcount_read(&clp->cl_count) == 1)
- goto out;
+ return;
if (nfs41_sequence_handle_errors(task, clp) == -EAGAIN) {
rpc_restart_call_prepare(task);
@@ -9209,8 +9133,6 @@ static void nfs41_sequence_call_done(struct rpc_task *task, void *data)
}
}
dprintk("%s rpc_cred %p\n", __func__, task->tk_msg.rpc_cred);
-out:
- dprintk("<-- %s\n", __func__);
}
static void nfs41_sequence_prepare(struct rpc_task *task, void *data)
@@ -9357,7 +9279,6 @@ static void nfs4_reclaim_complete_done(struct rpc_task *task, void *data)
struct nfs_client *clp = calldata->clp;
struct nfs4_sequence_res *res = &calldata->res.seq_res;
- dprintk("--> %s\n", __func__);
if (!nfs41_sequence_done(task, res))
return;
@@ -9366,7 +9287,6 @@ static void nfs4_reclaim_complete_done(struct rpc_task *task, void *data)
rpc_restart_call_prepare(task);
return;
}
- dprintk("<-- %s\n", __func__);
}
static void nfs4_free_reclaim_complete_data(void *data)
@@ -9401,7 +9321,6 @@ static int nfs41_proc_reclaim_complete(struct nfs_client *clp,
};
int status = -ENOMEM;
- dprintk("--> %s\n", __func__);
calldata = kzalloc(sizeof(*calldata), GFP_NOFS);
if (calldata == NULL)
goto out;
@@ -9424,19 +9343,15 @@ nfs4_layoutget_prepare(struct rpc_task *task, void *calldata)
struct nfs4_layoutget *lgp = calldata;
struct nfs_server *server = NFS_SERVER(lgp->args.inode);
- dprintk("--> %s\n", __func__);
nfs4_setup_sequence(server->nfs_client, &lgp->args.seq_args,
&lgp->res.seq_res, task);
- dprintk("<-- %s\n", __func__);
}
static void nfs4_layoutget_done(struct rpc_task *task, void *calldata)
{
struct nfs4_layoutget *lgp = calldata;
- dprintk("--> %s\n", __func__);
nfs41_sequence_process(task, &lgp->res.seq_res);
- dprintk("<-- %s\n", __func__);
}
static int
@@ -9525,7 +9440,6 @@ nfs4_layoutget_handle_exception(struct rpc_task *task,
status = err;
}
out:
- dprintk("<-- %s\n", __func__);
return status;
}
@@ -9539,10 +9453,8 @@ static void nfs4_layoutget_release(void *calldata)
{
struct nfs4_layoutget *lgp = calldata;
- dprintk("--> %s\n", __func__);
nfs4_sequence_free_slot(&lgp->res.seq_res);
pnfs_layoutget_free(lgp);
- dprintk("<-- %s\n", __func__);
}
static const struct rpc_call_ops nfs4_layoutget_call_ops = {
@@ -9578,8 +9490,6 @@ nfs4_proc_layoutget(struct nfs4_layoutget *lgp, long *timeout)
};
int status = 0;
- dprintk("--> %s\n", __func__);
-
nfs4_init_sequence(&lgp->args.seq_args, &lgp->res.seq_res, 0, 0);
task = rpc_run_task(&task_setup_data);
@@ -9615,7 +9525,6 @@ nfs4_layoutreturn_prepare(struct rpc_task *task, void *calldata)
{
struct nfs4_layoutreturn *lrp = calldata;
- dprintk("--> %s\n", __func__);
nfs4_setup_sequence(lrp->clp,
&lrp->args.seq_args,
&lrp->res.seq_res,
@@ -9629,8 +9538,6 @@ static void nfs4_layoutreturn_done(struct rpc_task *task, void *calldata)
struct nfs4_layoutreturn *lrp = calldata;
struct nfs_server *server;
- dprintk("--> %s\n", __func__);
-
if (!nfs41_sequence_process(task, &lrp->res.seq_res))
return;
@@ -9661,7 +9568,6 @@ static void nfs4_layoutreturn_done(struct rpc_task *task, void *calldata)
break;
goto out_restart;
}
- dprintk("<-- %s\n", __func__);
return;
out_restart:
task->tk_status = 0;
@@ -9674,7 +9580,6 @@ static void nfs4_layoutreturn_release(void *calldata)
struct nfs4_layoutreturn *lrp = calldata;
struct pnfs_layout_hdr *lo = lrp->args.layout;
- dprintk("--> %s\n", __func__);
pnfs_layoutreturn_free_lsegs(lo, &lrp->args.stateid, &lrp->args.range,
lrp->res.lrs_present ? &lrp->res.stateid : NULL);
nfs4_sequence_free_slot(&lrp->res.seq_res);
@@ -9684,7 +9589,6 @@ static void nfs4_layoutreturn_release(void *calldata)
nfs_iput_and_deactive(lrp->inode);
put_cred(lrp->cred);
kfree(calldata);
- dprintk("<-- %s\n", __func__);
}
static const struct rpc_call_ops nfs4_layoutreturn_call_ops = {
@@ -9715,7 +9619,6 @@ int nfs4_proc_layoutreturn(struct nfs4_layoutreturn *lrp, bool sync)
NFS_SP4_MACH_CRED_PNFS_CLEANUP,
&task_setup_data.rpc_client, &msg);
- dprintk("--> %s\n", __func__);
lrp->inode = nfs_igrab_and_active(lrp->args.inode);
if (!sync) {
if (!lrp->inode) {
@@ -9762,7 +9665,6 @@ _nfs4_proc_getdeviceinfo(struct nfs_server *server,
};
int status;
- dprintk("--> %s\n", __func__);
status = nfs4_call_sync(server->client, server, &msg, &args.seq_args, &res.seq_res, 0);
if (res.notification & ~args.notify_types)
dprintk("%s: unsupported notification\n", __func__);
@@ -9934,7 +9836,6 @@ _nfs41_proc_secinfo_no_name(struct nfs_server *server, struct nfs_fh *fhandle,
msg.rpc_cred = cred;
}
- dprintk("--> %s\n", __func__);
nfs4_init_sequence(&args.seq_args, &res.seq_res, 0, 0);
status = nfs4_call_sync_custom(&task_setup);
dprintk("<-- %s status=%d\n", __func__, status);
@@ -10158,6 +10059,10 @@ static void nfs41_free_stateid_done(struct rpc_task *task, void *calldata)
static void nfs41_free_stateid_release(void *calldata)
{
+ struct nfs_free_stateid_data *data = calldata;
+ struct nfs_client *clp = data->server->nfs_client;
+
+ nfs_put_client(clp);
kfree(calldata);
}
@@ -10194,6 +10099,10 @@ static int nfs41_free_stateid(struct nfs_server *server,
};
struct nfs_free_stateid_data *data;
struct rpc_task *task;
+ struct nfs_client *clp = server->nfs_client;
+
+ if (!refcount_inc_not_zero(&clp->cl_count))
+ return -EIO;
nfs4_state_protect(server->nfs_client, NFS_SP4_MACH_CRED_STATEID,
&task_setup.rpc_client, &msg);
diff --git a/fs/nfs/nfs4session.c b/fs/nfs/nfs4session.c
index 4145a0138907..5db460476bf2 100644
--- a/fs/nfs/nfs4session.c
+++ b/fs/nfs/nfs4session.c
@@ -511,12 +511,16 @@ void nfs41_update_target_slotid(struct nfs4_slot_table *tbl,
struct nfs4_slot *slot,
struct nfs4_sequence_res *res)
{
+ u32 target_highest_slotid = min(res->sr_target_highest_slotid,
+ NFS4_MAX_SLOTID);
+ u32 highest_slotid = min(res->sr_highest_slotid, NFS4_MAX_SLOTID);
+
spin_lock(&tbl->slot_tbl_lock);
- if (!nfs41_is_outlier_target_slotid(tbl, res->sr_target_highest_slotid))
- nfs41_set_target_slotid_locked(tbl, res->sr_target_highest_slotid);
+ if (!nfs41_is_outlier_target_slotid(tbl, target_highest_slotid))
+ nfs41_set_target_slotid_locked(tbl, target_highest_slotid);
if (tbl->generation == slot->generation)
- nfs41_set_server_slotid_locked(tbl, res->sr_highest_slotid);
- nfs41_set_max_slotid_locked(tbl, res->sr_target_highest_slotid);
+ nfs41_set_server_slotid_locked(tbl, highest_slotid);
+ nfs41_set_max_slotid_locked(tbl, target_highest_slotid);
spin_unlock(&tbl->slot_tbl_lock);
}
diff --git a/fs/nfs/nfs4session.h b/fs/nfs/nfs4session.h
index 3de425f59b3a..351616c61df5 100644
--- a/fs/nfs/nfs4session.h
+++ b/fs/nfs/nfs4session.h
@@ -12,6 +12,7 @@
#define NFS4_DEF_SLOT_TABLE_SIZE (64U)
#define NFS4_DEF_CB_SLOT_TABLE_SIZE (16U)
#define NFS4_MAX_SLOT_TABLE (1024U)
+#define NFS4_MAX_SLOTID (NFS4_MAX_SLOT_TABLE - 1U)
#define NFS4_NO_SLOT ((u32)-1)
#if IS_ENABLED(CONFIG_NFS_V4)
diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c
index f22818a80c2c..ecc4594299d6 100644
--- a/fs/nfs/nfs4state.c
+++ b/fs/nfs/nfs4state.c
@@ -1194,10 +1194,7 @@ static int nfs4_run_state_manager(void *);
static void nfs4_clear_state_manager_bit(struct nfs_client *clp)
{
- smp_mb__before_atomic();
- clear_bit(NFS4CLNT_MANAGER_RUNNING, &clp->cl_state);
- smp_mb__after_atomic();
- wake_up_bit(&clp->cl_state, NFS4CLNT_MANAGER_RUNNING);
+ clear_and_wake_up_bit(NFS4CLNT_MANAGER_RUNNING, &clp->cl_state);
rpc_wake_up(&clp->cl_rpcwaitq);
}
diff --git a/fs/nfs/nfs4trace.h b/fs/nfs/nfs4trace.h
index 7a2567aa2b86..6ee6ad3674a2 100644
--- a/fs/nfs/nfs4trace.h
+++ b/fs/nfs/nfs4trace.h
@@ -9,322 +9,10 @@
#define _TRACE_NFS4_H
#include <linux/tracepoint.h>
+#include <trace/events/sunrpc_base.h>
-TRACE_DEFINE_ENUM(EPERM);
-TRACE_DEFINE_ENUM(ENOENT);
-TRACE_DEFINE_ENUM(EIO);
-TRACE_DEFINE_ENUM(ENXIO);
-TRACE_DEFINE_ENUM(EACCES);
-TRACE_DEFINE_ENUM(EEXIST);
-TRACE_DEFINE_ENUM(EXDEV);
-TRACE_DEFINE_ENUM(ENOTDIR);
-TRACE_DEFINE_ENUM(EISDIR);
-TRACE_DEFINE_ENUM(EFBIG);
-TRACE_DEFINE_ENUM(ENOSPC);
-TRACE_DEFINE_ENUM(EROFS);
-TRACE_DEFINE_ENUM(EMLINK);
-TRACE_DEFINE_ENUM(ENAMETOOLONG);
-TRACE_DEFINE_ENUM(ENOTEMPTY);
-TRACE_DEFINE_ENUM(EDQUOT);
-TRACE_DEFINE_ENUM(ESTALE);
-TRACE_DEFINE_ENUM(EBADHANDLE);
-TRACE_DEFINE_ENUM(EBADCOOKIE);
-TRACE_DEFINE_ENUM(ENOTSUPP);
-TRACE_DEFINE_ENUM(ETOOSMALL);
-TRACE_DEFINE_ENUM(EREMOTEIO);
-TRACE_DEFINE_ENUM(EBADTYPE);
-TRACE_DEFINE_ENUM(EAGAIN);
-TRACE_DEFINE_ENUM(ELOOP);
-TRACE_DEFINE_ENUM(EOPNOTSUPP);
-TRACE_DEFINE_ENUM(EDEADLK);
-TRACE_DEFINE_ENUM(ENOMEM);
-TRACE_DEFINE_ENUM(EKEYEXPIRED);
-TRACE_DEFINE_ENUM(ETIMEDOUT);
-TRACE_DEFINE_ENUM(ERESTARTSYS);
-TRACE_DEFINE_ENUM(ECONNREFUSED);
-TRACE_DEFINE_ENUM(ECONNRESET);
-TRACE_DEFINE_ENUM(ENETUNREACH);
-TRACE_DEFINE_ENUM(EHOSTUNREACH);
-TRACE_DEFINE_ENUM(EHOSTDOWN);
-TRACE_DEFINE_ENUM(EPIPE);
-TRACE_DEFINE_ENUM(EPFNOSUPPORT);
-TRACE_DEFINE_ENUM(EPROTONOSUPPORT);
-
-TRACE_DEFINE_ENUM(NFS4_OK);
-TRACE_DEFINE_ENUM(NFS4ERR_ACCESS);
-TRACE_DEFINE_ENUM(NFS4ERR_ATTRNOTSUPP);
-TRACE_DEFINE_ENUM(NFS4ERR_ADMIN_REVOKED);
-TRACE_DEFINE_ENUM(NFS4ERR_BACK_CHAN_BUSY);
-TRACE_DEFINE_ENUM(NFS4ERR_BADCHAR);
-TRACE_DEFINE_ENUM(NFS4ERR_BADHANDLE);
-TRACE_DEFINE_ENUM(NFS4ERR_BADIOMODE);
-TRACE_DEFINE_ENUM(NFS4ERR_BADLAYOUT);
-TRACE_DEFINE_ENUM(NFS4ERR_BADLABEL);
-TRACE_DEFINE_ENUM(NFS4ERR_BADNAME);
-TRACE_DEFINE_ENUM(NFS4ERR_BADOWNER);
-TRACE_DEFINE_ENUM(NFS4ERR_BADSESSION);
-TRACE_DEFINE_ENUM(NFS4ERR_BADSLOT);
-TRACE_DEFINE_ENUM(NFS4ERR_BADTYPE);
-TRACE_DEFINE_ENUM(NFS4ERR_BADXDR);
-TRACE_DEFINE_ENUM(NFS4ERR_BAD_COOKIE);
-TRACE_DEFINE_ENUM(NFS4ERR_BAD_HIGH_SLOT);
-TRACE_DEFINE_ENUM(NFS4ERR_BAD_RANGE);
-TRACE_DEFINE_ENUM(NFS4ERR_BAD_SEQID);
-TRACE_DEFINE_ENUM(NFS4ERR_BAD_SESSION_DIGEST);
-TRACE_DEFINE_ENUM(NFS4ERR_BAD_STATEID);
-TRACE_DEFINE_ENUM(NFS4ERR_CB_PATH_DOWN);
-TRACE_DEFINE_ENUM(NFS4ERR_CLID_INUSE);
-TRACE_DEFINE_ENUM(NFS4ERR_CLIENTID_BUSY);
-TRACE_DEFINE_ENUM(NFS4ERR_COMPLETE_ALREADY);
-TRACE_DEFINE_ENUM(NFS4ERR_CONN_NOT_BOUND_TO_SESSION);
-TRACE_DEFINE_ENUM(NFS4ERR_DEADLOCK);
-TRACE_DEFINE_ENUM(NFS4ERR_DEADSESSION);
-TRACE_DEFINE_ENUM(NFS4ERR_DELAY);
-TRACE_DEFINE_ENUM(NFS4ERR_DELEG_ALREADY_WANTED);
-TRACE_DEFINE_ENUM(NFS4ERR_DELEG_REVOKED);
-TRACE_DEFINE_ENUM(NFS4ERR_DENIED);
-TRACE_DEFINE_ENUM(NFS4ERR_DIRDELEG_UNAVAIL);
-TRACE_DEFINE_ENUM(NFS4ERR_DQUOT);
-TRACE_DEFINE_ENUM(NFS4ERR_ENCR_ALG_UNSUPP);
-TRACE_DEFINE_ENUM(NFS4ERR_EXIST);
-TRACE_DEFINE_ENUM(NFS4ERR_EXPIRED);
-TRACE_DEFINE_ENUM(NFS4ERR_FBIG);
-TRACE_DEFINE_ENUM(NFS4ERR_FHEXPIRED);
-TRACE_DEFINE_ENUM(NFS4ERR_FILE_OPEN);
-TRACE_DEFINE_ENUM(NFS4ERR_GRACE);
-TRACE_DEFINE_ENUM(NFS4ERR_HASH_ALG_UNSUPP);
-TRACE_DEFINE_ENUM(NFS4ERR_INVAL);
-TRACE_DEFINE_ENUM(NFS4ERR_IO);
-TRACE_DEFINE_ENUM(NFS4ERR_ISDIR);
-TRACE_DEFINE_ENUM(NFS4ERR_LAYOUTTRYLATER);
-TRACE_DEFINE_ENUM(NFS4ERR_LAYOUTUNAVAILABLE);
-TRACE_DEFINE_ENUM(NFS4ERR_LEASE_MOVED);
-TRACE_DEFINE_ENUM(NFS4ERR_LOCKED);
-TRACE_DEFINE_ENUM(NFS4ERR_LOCKS_HELD);
-TRACE_DEFINE_ENUM(NFS4ERR_LOCK_RANGE);
-TRACE_DEFINE_ENUM(NFS4ERR_MINOR_VERS_MISMATCH);
-TRACE_DEFINE_ENUM(NFS4ERR_MLINK);
-TRACE_DEFINE_ENUM(NFS4ERR_MOVED);
-TRACE_DEFINE_ENUM(NFS4ERR_NAMETOOLONG);
-TRACE_DEFINE_ENUM(NFS4ERR_NOENT);
-TRACE_DEFINE_ENUM(NFS4ERR_NOFILEHANDLE);
-TRACE_DEFINE_ENUM(NFS4ERR_NOMATCHING_LAYOUT);
-TRACE_DEFINE_ENUM(NFS4ERR_NOSPC);
-TRACE_DEFINE_ENUM(NFS4ERR_NOTDIR);
-TRACE_DEFINE_ENUM(NFS4ERR_NOTEMPTY);
-TRACE_DEFINE_ENUM(NFS4ERR_NOTSUPP);
-TRACE_DEFINE_ENUM(NFS4ERR_NOT_ONLY_OP);
-TRACE_DEFINE_ENUM(NFS4ERR_NOT_SAME);
-TRACE_DEFINE_ENUM(NFS4ERR_NO_GRACE);
-TRACE_DEFINE_ENUM(NFS4ERR_NXIO);
-TRACE_DEFINE_ENUM(NFS4ERR_OLD_STATEID);
-TRACE_DEFINE_ENUM(NFS4ERR_OPENMODE);
-TRACE_DEFINE_ENUM(NFS4ERR_OP_ILLEGAL);
-TRACE_DEFINE_ENUM(NFS4ERR_OP_NOT_IN_SESSION);
-TRACE_DEFINE_ENUM(NFS4ERR_PERM);
-TRACE_DEFINE_ENUM(NFS4ERR_PNFS_IO_HOLE);
-TRACE_DEFINE_ENUM(NFS4ERR_PNFS_NO_LAYOUT);
-TRACE_DEFINE_ENUM(NFS4ERR_RECALLCONFLICT);
-TRACE_DEFINE_ENUM(NFS4ERR_RECLAIM_BAD);
-TRACE_DEFINE_ENUM(NFS4ERR_RECLAIM_CONFLICT);
-TRACE_DEFINE_ENUM(NFS4ERR_REJECT_DELEG);
-TRACE_DEFINE_ENUM(NFS4ERR_REP_TOO_BIG);
-TRACE_DEFINE_ENUM(NFS4ERR_REP_TOO_BIG_TO_CACHE);
-TRACE_DEFINE_ENUM(NFS4ERR_REQ_TOO_BIG);
-TRACE_DEFINE_ENUM(NFS4ERR_RESOURCE);
-TRACE_DEFINE_ENUM(NFS4ERR_RESTOREFH);
-TRACE_DEFINE_ENUM(NFS4ERR_RETRY_UNCACHED_REP);
-TRACE_DEFINE_ENUM(NFS4ERR_RETURNCONFLICT);
-TRACE_DEFINE_ENUM(NFS4ERR_ROFS);
-TRACE_DEFINE_ENUM(NFS4ERR_SAME);
-TRACE_DEFINE_ENUM(NFS4ERR_SHARE_DENIED);
-TRACE_DEFINE_ENUM(NFS4ERR_SEQUENCE_POS);
-TRACE_DEFINE_ENUM(NFS4ERR_SEQ_FALSE_RETRY);
-TRACE_DEFINE_ENUM(NFS4ERR_SEQ_MISORDERED);
-TRACE_DEFINE_ENUM(NFS4ERR_SERVERFAULT);
-TRACE_DEFINE_ENUM(NFS4ERR_STALE);
-TRACE_DEFINE_ENUM(NFS4ERR_STALE_CLIENTID);
-TRACE_DEFINE_ENUM(NFS4ERR_STALE_STATEID);
-TRACE_DEFINE_ENUM(NFS4ERR_SYMLINK);
-TRACE_DEFINE_ENUM(NFS4ERR_TOOSMALL);
-TRACE_DEFINE_ENUM(NFS4ERR_TOO_MANY_OPS);
-TRACE_DEFINE_ENUM(NFS4ERR_UNKNOWN_LAYOUTTYPE);
-TRACE_DEFINE_ENUM(NFS4ERR_UNSAFE_COMPOUND);
-TRACE_DEFINE_ENUM(NFS4ERR_WRONGSEC);
-TRACE_DEFINE_ENUM(NFS4ERR_WRONG_CRED);
-TRACE_DEFINE_ENUM(NFS4ERR_WRONG_TYPE);
-TRACE_DEFINE_ENUM(NFS4ERR_XDEV);
-
-TRACE_DEFINE_ENUM(NFS4ERR_RESET_TO_MDS);
-TRACE_DEFINE_ENUM(NFS4ERR_RESET_TO_PNFS);
-
-#define show_nfsv4_errors(error) \
- __print_symbolic(error, \
- { NFS4_OK, "OK" }, \
- /* Mapped by nfs4_stat_to_errno() */ \
- { EPERM, "EPERM" }, \
- { ENOENT, "ENOENT" }, \
- { EIO, "EIO" }, \
- { ENXIO, "ENXIO" }, \
- { EACCES, "EACCES" }, \
- { EEXIST, "EEXIST" }, \
- { EXDEV, "EXDEV" }, \
- { ENOTDIR, "ENOTDIR" }, \
- { EISDIR, "EISDIR" }, \
- { EFBIG, "EFBIG" }, \
- { ENOSPC, "ENOSPC" }, \
- { EROFS, "EROFS" }, \
- { EMLINK, "EMLINK" }, \
- { ENAMETOOLONG, "ENAMETOOLONG" }, \
- { ENOTEMPTY, "ENOTEMPTY" }, \
- { EDQUOT, "EDQUOT" }, \
- { ESTALE, "ESTALE" }, \
- { EBADHANDLE, "EBADHANDLE" }, \
- { EBADCOOKIE, "EBADCOOKIE" }, \
- { ENOTSUPP, "ENOTSUPP" }, \
- { ETOOSMALL, "ETOOSMALL" }, \
- { EREMOTEIO, "EREMOTEIO" }, \
- { EBADTYPE, "EBADTYPE" }, \
- { EAGAIN, "EAGAIN" }, \
- { ELOOP, "ELOOP" }, \
- { EOPNOTSUPP, "EOPNOTSUPP" }, \
- { EDEADLK, "EDEADLK" }, \
- /* RPC errors */ \
- { ENOMEM, "ENOMEM" }, \
- { EKEYEXPIRED, "EKEYEXPIRED" }, \
- { ETIMEDOUT, "ETIMEDOUT" }, \
- { ERESTARTSYS, "ERESTARTSYS" }, \
- { ECONNREFUSED, "ECONNREFUSED" }, \
- { ECONNRESET, "ECONNRESET" }, \
- { ENETUNREACH, "ENETUNREACH" }, \
- { EHOSTUNREACH, "EHOSTUNREACH" }, \
- { EHOSTDOWN, "EHOSTDOWN" }, \
- { EPIPE, "EPIPE" }, \
- { EPFNOSUPPORT, "EPFNOSUPPORT" }, \
- { EPROTONOSUPPORT, "EPROTONOSUPPORT" }, \
- /* NFSv4 native errors */ \
- { NFS4ERR_ACCESS, "ACCESS" }, \
- { NFS4ERR_ATTRNOTSUPP, "ATTRNOTSUPP" }, \
- { NFS4ERR_ADMIN_REVOKED, "ADMIN_REVOKED" }, \
- { NFS4ERR_BACK_CHAN_BUSY, "BACK_CHAN_BUSY" }, \
- { NFS4ERR_BADCHAR, "BADCHAR" }, \
- { NFS4ERR_BADHANDLE, "BADHANDLE" }, \
- { NFS4ERR_BADIOMODE, "BADIOMODE" }, \
- { NFS4ERR_BADLAYOUT, "BADLAYOUT" }, \
- { NFS4ERR_BADLABEL, "BADLABEL" }, \
- { NFS4ERR_BADNAME, "BADNAME" }, \
- { NFS4ERR_BADOWNER, "BADOWNER" }, \
- { NFS4ERR_BADSESSION, "BADSESSION" }, \
- { NFS4ERR_BADSLOT, "BADSLOT" }, \
- { NFS4ERR_BADTYPE, "BADTYPE" }, \
- { NFS4ERR_BADXDR, "BADXDR" }, \
- { NFS4ERR_BAD_COOKIE, "BAD_COOKIE" }, \
- { NFS4ERR_BAD_HIGH_SLOT, "BAD_HIGH_SLOT" }, \
- { NFS4ERR_BAD_RANGE, "BAD_RANGE" }, \
- { NFS4ERR_BAD_SEQID, "BAD_SEQID" }, \
- { NFS4ERR_BAD_SESSION_DIGEST, "BAD_SESSION_DIGEST" }, \
- { NFS4ERR_BAD_STATEID, "BAD_STATEID" }, \
- { NFS4ERR_CB_PATH_DOWN, "CB_PATH_DOWN" }, \
- { NFS4ERR_CLID_INUSE, "CLID_INUSE" }, \
- { NFS4ERR_CLIENTID_BUSY, "CLIENTID_BUSY" }, \
- { NFS4ERR_COMPLETE_ALREADY, "COMPLETE_ALREADY" }, \
- { NFS4ERR_CONN_NOT_BOUND_TO_SESSION, \
- "CONN_NOT_BOUND_TO_SESSION" }, \
- { NFS4ERR_DEADLOCK, "DEADLOCK" }, \
- { NFS4ERR_DEADSESSION, "DEAD_SESSION" }, \
- { NFS4ERR_DELAY, "DELAY" }, \
- { NFS4ERR_DELEG_ALREADY_WANTED, \
- "DELEG_ALREADY_WANTED" }, \
- { NFS4ERR_DELEG_REVOKED, "DELEG_REVOKED" }, \
- { NFS4ERR_DENIED, "DENIED" }, \
- { NFS4ERR_DIRDELEG_UNAVAIL, "DIRDELEG_UNAVAIL" }, \
- { NFS4ERR_DQUOT, "DQUOT" }, \
- { NFS4ERR_ENCR_ALG_UNSUPP, "ENCR_ALG_UNSUPP" }, \
- { NFS4ERR_EXIST, "EXIST" }, \
- { NFS4ERR_EXPIRED, "EXPIRED" }, \
- { NFS4ERR_FBIG, "FBIG" }, \
- { NFS4ERR_FHEXPIRED, "FHEXPIRED" }, \
- { NFS4ERR_FILE_OPEN, "FILE_OPEN" }, \
- { NFS4ERR_GRACE, "GRACE" }, \
- { NFS4ERR_HASH_ALG_UNSUPP, "HASH_ALG_UNSUPP" }, \
- { NFS4ERR_INVAL, "INVAL" }, \
- { NFS4ERR_IO, "IO" }, \
- { NFS4ERR_ISDIR, "ISDIR" }, \
- { NFS4ERR_LAYOUTTRYLATER, "LAYOUTTRYLATER" }, \
- { NFS4ERR_LAYOUTUNAVAILABLE, "LAYOUTUNAVAILABLE" }, \
- { NFS4ERR_LEASE_MOVED, "LEASE_MOVED" }, \
- { NFS4ERR_LOCKED, "LOCKED" }, \
- { NFS4ERR_LOCKS_HELD, "LOCKS_HELD" }, \
- { NFS4ERR_LOCK_RANGE, "LOCK_RANGE" }, \
- { NFS4ERR_MINOR_VERS_MISMATCH, "MINOR_VERS_MISMATCH" }, \
- { NFS4ERR_MLINK, "MLINK" }, \
- { NFS4ERR_MOVED, "MOVED" }, \
- { NFS4ERR_NAMETOOLONG, "NAMETOOLONG" }, \
- { NFS4ERR_NOENT, "NOENT" }, \
- { NFS4ERR_NOFILEHANDLE, "NOFILEHANDLE" }, \
- { NFS4ERR_NOMATCHING_LAYOUT, "NOMATCHING_LAYOUT" }, \
- { NFS4ERR_NOSPC, "NOSPC" }, \
- { NFS4ERR_NOTDIR, "NOTDIR" }, \
- { NFS4ERR_NOTEMPTY, "NOTEMPTY" }, \
- { NFS4ERR_NOTSUPP, "NOTSUPP" }, \
- { NFS4ERR_NOT_ONLY_OP, "NOT_ONLY_OP" }, \
- { NFS4ERR_NOT_SAME, "NOT_SAME" }, \
- { NFS4ERR_NO_GRACE, "NO_GRACE" }, \
- { NFS4ERR_NXIO, "NXIO" }, \
- { NFS4ERR_OLD_STATEID, "OLD_STATEID" }, \
- { NFS4ERR_OPENMODE, "OPENMODE" }, \
- { NFS4ERR_OP_ILLEGAL, "OP_ILLEGAL" }, \
- { NFS4ERR_OP_NOT_IN_SESSION, "OP_NOT_IN_SESSION" }, \
- { NFS4ERR_PERM, "PERM" }, \
- { NFS4ERR_PNFS_IO_HOLE, "PNFS_IO_HOLE" }, \
- { NFS4ERR_PNFS_NO_LAYOUT, "PNFS_NO_LAYOUT" }, \
- { NFS4ERR_RECALLCONFLICT, "RECALLCONFLICT" }, \
- { NFS4ERR_RECLAIM_BAD, "RECLAIM_BAD" }, \
- { NFS4ERR_RECLAIM_CONFLICT, "RECLAIM_CONFLICT" }, \
- { NFS4ERR_REJECT_DELEG, "REJECT_DELEG" }, \
- { NFS4ERR_REP_TOO_BIG, "REP_TOO_BIG" }, \
- { NFS4ERR_REP_TOO_BIG_TO_CACHE, \
- "REP_TOO_BIG_TO_CACHE" }, \
- { NFS4ERR_REQ_TOO_BIG, "REQ_TOO_BIG" }, \
- { NFS4ERR_RESOURCE, "RESOURCE" }, \
- { NFS4ERR_RESTOREFH, "RESTOREFH" }, \
- { NFS4ERR_RETRY_UNCACHED_REP, "RETRY_UNCACHED_REP" }, \
- { NFS4ERR_RETURNCONFLICT, "RETURNCONFLICT" }, \
- { NFS4ERR_ROFS, "ROFS" }, \
- { NFS4ERR_SAME, "SAME" }, \
- { NFS4ERR_SHARE_DENIED, "SHARE_DENIED" }, \
- { NFS4ERR_SEQUENCE_POS, "SEQUENCE_POS" }, \
- { NFS4ERR_SEQ_FALSE_RETRY, "SEQ_FALSE_RETRY" }, \
- { NFS4ERR_SEQ_MISORDERED, "SEQ_MISORDERED" }, \
- { NFS4ERR_SERVERFAULT, "SERVERFAULT" }, \
- { NFS4ERR_STALE, "STALE" }, \
- { NFS4ERR_STALE_CLIENTID, "STALE_CLIENTID" }, \
- { NFS4ERR_STALE_STATEID, "STALE_STATEID" }, \
- { NFS4ERR_SYMLINK, "SYMLINK" }, \
- { NFS4ERR_TOOSMALL, "TOOSMALL" }, \
- { NFS4ERR_TOO_MANY_OPS, "TOO_MANY_OPS" }, \
- { NFS4ERR_UNKNOWN_LAYOUTTYPE, "UNKNOWN_LAYOUTTYPE" }, \
- { NFS4ERR_UNSAFE_COMPOUND, "UNSAFE_COMPOUND" }, \
- { NFS4ERR_WRONGSEC, "WRONGSEC" }, \
- { NFS4ERR_WRONG_CRED, "WRONG_CRED" }, \
- { NFS4ERR_WRONG_TYPE, "WRONG_TYPE" }, \
- { NFS4ERR_XDEV, "XDEV" }, \
- /* ***** Internal to Linux NFS client ***** */ \
- { NFS4ERR_RESET_TO_MDS, "RESET_TO_MDS" }, \
- { NFS4ERR_RESET_TO_PNFS, "RESET_TO_PNFS" })
-
-#define show_open_flags(flags) \
- __print_flags(flags, "|", \
- { O_CREAT, "O_CREAT" }, \
- { O_EXCL, "O_EXCL" }, \
- { O_TRUNC, "O_TRUNC" }, \
- { O_DIRECT, "O_DIRECT" })
-
-#define show_fmode_flags(mode) \
- __print_flags(mode, "|", \
- { ((__force unsigned long)FMODE_READ), "READ" }, \
- { ((__force unsigned long)FMODE_WRITE), "WRITE" }, \
- { ((__force unsigned long)FMODE_EXEC), "EXEC" })
+#include <trace/events/fs.h>
+#include <trace/events/nfs.h>
#define show_nfs_fattr_flags(valid) \
__print_flags((unsigned long)valid, "|", \
@@ -365,7 +53,7 @@ DECLARE_EVENT_CLASS(nfs4_clientid_event,
TP_printk(
"error=%ld (%s) dstaddr=%s",
-__entry->error,
- show_nfsv4_errors(__entry->error),
+ show_nfs4_status(__entry->error),
__get_str(dstaddr)
)
);
@@ -389,29 +77,6 @@ DEFINE_NFS4_CLIENTID_EVENT(nfs4_bind_conn_to_session);
DEFINE_NFS4_CLIENTID_EVENT(nfs4_sequence);
DEFINE_NFS4_CLIENTID_EVENT(nfs4_reclaim_complete);
-#define show_nfs4_sequence_status_flags(status) \
- __print_flags((unsigned long)status, "|", \
- { SEQ4_STATUS_CB_PATH_DOWN, "CB_PATH_DOWN" }, \
- { SEQ4_STATUS_CB_GSS_CONTEXTS_EXPIRING, \
- "CB_GSS_CONTEXTS_EXPIRING" }, \
- { SEQ4_STATUS_CB_GSS_CONTEXTS_EXPIRED, \
- "CB_GSS_CONTEXTS_EXPIRED" }, \
- { SEQ4_STATUS_EXPIRED_ALL_STATE_REVOKED, \
- "EXPIRED_ALL_STATE_REVOKED" }, \
- { SEQ4_STATUS_EXPIRED_SOME_STATE_REVOKED, \
- "EXPIRED_SOME_STATE_REVOKED" }, \
- { SEQ4_STATUS_ADMIN_STATE_REVOKED, \
- "ADMIN_STATE_REVOKED" }, \
- { SEQ4_STATUS_RECALLABLE_STATE_REVOKED, \
- "RECALLABLE_STATE_REVOKED" }, \
- { SEQ4_STATUS_LEASE_MOVED, "LEASE_MOVED" }, \
- { SEQ4_STATUS_RESTART_RECLAIM_NEEDED, \
- "RESTART_RECLAIM_NEEDED" }, \
- { SEQ4_STATUS_CB_PATH_DOWN_SESSION, \
- "CB_PATH_DOWN_SESSION" }, \
- { SEQ4_STATUS_BACKCHANNEL_FAULT, \
- "BACKCHANNEL_FAULT" })
-
TRACE_EVENT(nfs4_sequence_done,
TP_PROTO(
const struct nfs4_session *session,
@@ -425,7 +90,7 @@ TRACE_EVENT(nfs4_sequence_done,
__field(unsigned int, seq_nr)
__field(unsigned int, highest_slotid)
__field(unsigned int, target_highest_slotid)
- __field(unsigned int, status_flags)
+ __field(unsigned long, status_flags)
__field(unsigned long, error)
),
@@ -444,16 +109,16 @@ TRACE_EVENT(nfs4_sequence_done,
TP_printk(
"error=%ld (%s) session=0x%08x slot_nr=%u seq_nr=%u "
"highest_slotid=%u target_highest_slotid=%u "
- "status_flags=%u (%s)",
+ "status_flags=0x%lx (%s)",
-__entry->error,
- show_nfsv4_errors(__entry->error),
+ show_nfs4_status(__entry->error),
__entry->session,
__entry->slot_nr,
__entry->seq_nr,
__entry->highest_slotid,
__entry->target_highest_slotid,
__entry->status_flags,
- show_nfs4_sequence_status_flags(__entry->status_flags)
+ show_nfs4_seq4_status(__entry->status_flags)
)
);
@@ -490,7 +155,7 @@ TRACE_EVENT(nfs4_cb_sequence,
"error=%ld (%s) session=0x%08x slot_nr=%u seq_nr=%u "
"highest_slotid=%u",
-__entry->error,
- show_nfsv4_errors(__entry->error),
+ show_nfs4_status(__entry->error),
__entry->session,
__entry->slot_nr,
__entry->seq_nr,
@@ -527,7 +192,7 @@ TRACE_EVENT(nfs4_cb_seqid_err,
"error=%ld (%s) session=0x%08x slot_nr=%u seq_nr=%u "
"highest_slotid=%u",
-__entry->error,
- show_nfsv4_errors(__entry->error),
+ show_nfs4_status(__entry->error),
__entry->session,
__entry->slot_nr,
__entry->seq_nr,
@@ -535,6 +200,49 @@ TRACE_EVENT(nfs4_cb_seqid_err,
)
);
+TRACE_EVENT(nfs4_cb_offload,
+ TP_PROTO(
+ const struct nfs_fh *cb_fh,
+ const nfs4_stateid *cb_stateid,
+ uint64_t cb_count,
+ int cb_error,
+ int cb_how_stable
+ ),
+
+ TP_ARGS(cb_fh, cb_stateid, cb_count, cb_error,
+ cb_how_stable),
+
+ TP_STRUCT__entry(
+ __field(unsigned long, error)
+ __field(u32, fhandle)
+ __field(loff_t, cb_count)
+ __field(int, cb_how)
+ __field(int, cb_stateid_seq)
+ __field(u32, cb_stateid_hash)
+ ),
+
+ TP_fast_assign(
+ __entry->error = cb_error < 0 ? -cb_error : 0;
+ __entry->fhandle = nfs_fhandle_hash(cb_fh);
+ __entry->cb_stateid_seq =
+ be32_to_cpu(cb_stateid->seqid);
+ __entry->cb_stateid_hash =
+ nfs_stateid_hash(cb_stateid);
+ __entry->cb_count = cb_count;
+ __entry->cb_how = cb_how_stable;
+ ),
+
+ TP_printk(
+ "error=%ld (%s) fhandle=0x%08x cb_stateid=%d:0x%08x "
+ "cb_count=%llu cb_how=%s",
+ -__entry->error,
+ show_nfs4_status(__entry->error),
+ __entry->fhandle,
+ __entry->cb_stateid_seq, __entry->cb_stateid_hash,
+ __entry->cb_count,
+ show_nfs_stable_how(__entry->cb_how)
+ )
+);
#endif /* CONFIG_NFS_V4_1 */
TRACE_EVENT(nfs4_setup_sequence,
@@ -661,7 +369,7 @@ TRACE_EVENT(nfs4_state_mgr_failed,
"hostname=%s clp state=%s error=%ld (%s) section=%s",
__get_str(hostname),
show_nfs4_clp_state(__entry->state), -__entry->error,
- show_nfsv4_errors(__entry->error), __get_str(section)
+ show_nfs4_status(__entry->error), __get_str(section)
)
)
@@ -694,8 +402,8 @@ TRACE_EVENT(nfs4_xdr_bad_operation,
__entry->expected = expected;
),
- TP_printk(
- "task:%u@%d xid=0x%08x operation=%u, expected=%u",
+ TP_printk(SUNRPC_TRACE_TASK_SPECIFIER
+ " xid=0x%08x operation=%u, expected=%u",
__entry->task_id, __entry->client_id, __entry->xid,
__entry->op, __entry->expected
)
@@ -729,10 +437,10 @@ DECLARE_EVENT_CLASS(nfs4_xdr_event,
__entry->error = error;
),
- TP_printk(
- "task:%u@%d xid=0x%08x error=%ld (%s) operation=%u",
+ TP_printk(SUNRPC_TRACE_TASK_SPECIFIER
+ " xid=0x%08x error=%ld (%s) operation=%u",
__entry->task_id, __entry->client_id, __entry->xid,
- -__entry->error, show_nfsv4_errors(__entry->error),
+ -__entry->error, show_nfs4_status(__entry->error),
__entry->op
)
);
@@ -793,8 +501,8 @@ DECLARE_EVENT_CLASS(nfs4_open_event,
TP_STRUCT__entry(
__field(unsigned long, error)
- __field(unsigned int, flags)
- __field(unsigned int, fmode)
+ __field(unsigned long, flags)
+ __field(unsigned long, fmode)
__field(dev_t, dev)
__field(u32, fhandle)
__field(u64, fileid)
@@ -812,7 +520,7 @@ DECLARE_EVENT_CLASS(nfs4_open_event,
__entry->error = -error;
__entry->flags = flags;
- __entry->fmode = (__force unsigned int)ctx->mode;
+ __entry->fmode = (__force unsigned long)ctx->mode;
__entry->dev = ctx->dentry->d_sb->s_dev;
if (!IS_ERR_OR_NULL(state)) {
inode = state->inode;
@@ -842,15 +550,15 @@ DECLARE_EVENT_CLASS(nfs4_open_event,
),
TP_printk(
- "error=%ld (%s) flags=%d (%s) fmode=%s "
+ "error=%ld (%s) flags=%lu (%s) fmode=%s "
"fileid=%02x:%02x:%llu fhandle=0x%08x "
"name=%02x:%02x:%llu/%s stateid=%d:0x%08x "
"openstateid=%d:0x%08x",
-__entry->error,
- show_nfsv4_errors(__entry->error),
+ show_nfs4_status(__entry->error),
__entry->flags,
- show_open_flags(__entry->flags),
- show_fmode_flags(__entry->fmode),
+ show_fs_fcntl_open_flags(__entry->flags),
+ show_fs_fmode_flags(__entry->fmode),
MAJOR(__entry->dev), MINOR(__entry->dev),
(unsigned long long)__entry->fileid,
__entry->fhandle,
@@ -904,7 +612,7 @@ TRACE_EVENT(nfs4_cached_open,
TP_printk(
"fmode=%s fileid=%02x:%02x:%llu "
"fhandle=0x%08x stateid=%d:0x%08x",
- __entry->fmode ? show_fmode_flags(__entry->fmode) :
+ __entry->fmode ? show_fs_fmode_flags(__entry->fmode) :
"closed",
MAJOR(__entry->dev), MINOR(__entry->dev),
(unsigned long long)__entry->fileid,
@@ -951,8 +659,8 @@ TRACE_EVENT(nfs4_close,
"error=%ld (%s) fmode=%s fileid=%02x:%02x:%llu "
"fhandle=0x%08x openstateid=%d:0x%08x",
-__entry->error,
- show_nfsv4_errors(__entry->error),
- __entry->fmode ? show_fmode_flags(__entry->fmode) :
+ show_nfs4_status(__entry->error),
+ __entry->fmode ? show_fs_fmode_flags(__entry->fmode) :
"closed",
MAJOR(__entry->dev), MINOR(__entry->dev),
(unsigned long long)__entry->fileid,
@@ -961,24 +669,6 @@ TRACE_EVENT(nfs4_close,
)
);
-TRACE_DEFINE_ENUM(F_GETLK);
-TRACE_DEFINE_ENUM(F_SETLK);
-TRACE_DEFINE_ENUM(F_SETLKW);
-TRACE_DEFINE_ENUM(F_RDLCK);
-TRACE_DEFINE_ENUM(F_WRLCK);
-TRACE_DEFINE_ENUM(F_UNLCK);
-
-#define show_lock_cmd(type) \
- __print_symbolic((int)type, \
- { F_GETLK, "GETLK" }, \
- { F_SETLK, "SETLK" }, \
- { F_SETLKW, "SETLKW" })
-#define show_lock_type(type) \
- __print_symbolic((int)type, \
- { F_RDLCK, "RDLCK" }, \
- { F_WRLCK, "WRLCK" }, \
- { F_UNLCK, "UNLCK" })
-
DECLARE_EVENT_CLASS(nfs4_lock_event,
TP_PROTO(
const struct file_lock *request,
@@ -991,8 +681,8 @@ DECLARE_EVENT_CLASS(nfs4_lock_event,
TP_STRUCT__entry(
__field(unsigned long, error)
- __field(int, cmd)
- __field(char, type)
+ __field(unsigned long, cmd)
+ __field(unsigned long, type)
__field(loff_t, start)
__field(loff_t, end)
__field(dev_t, dev)
@@ -1024,9 +714,9 @@ DECLARE_EVENT_CLASS(nfs4_lock_event,
"fileid=%02x:%02x:%llu fhandle=0x%08x "
"stateid=%d:0x%08x",
-__entry->error,
- show_nfsv4_errors(__entry->error),
- show_lock_cmd(__entry->cmd),
- show_lock_type(__entry->type),
+ show_nfs4_status(__entry->error),
+ show_fs_fcntl_cmd(__entry->cmd),
+ show_fs_fcntl_lock_type(__entry->type),
(long long)__entry->start,
(long long)__entry->end,
MAJOR(__entry->dev), MINOR(__entry->dev),
@@ -1061,8 +751,8 @@ TRACE_EVENT(nfs4_set_lock,
TP_STRUCT__entry(
__field(unsigned long, error)
- __field(int, cmd)
- __field(char, type)
+ __field(unsigned long, cmd)
+ __field(unsigned long, type)
__field(loff_t, start)
__field(loff_t, end)
__field(dev_t, dev)
@@ -1100,9 +790,9 @@ TRACE_EVENT(nfs4_set_lock,
"fileid=%02x:%02x:%llu fhandle=0x%08x "
"stateid=%d:0x%08x lockstateid=%d:0x%08x",
-__entry->error,
- show_nfsv4_errors(__entry->error),
- show_lock_cmd(__entry->cmd),
- show_lock_type(__entry->type),
+ show_nfs4_status(__entry->error),
+ show_fs_fcntl_cmd(__entry->cmd),
+ show_fs_fcntl_lock_type(__entry->type),
(long long)__entry->start,
(long long)__entry->end,
MAJOR(__entry->dev), MINOR(__entry->dev),
@@ -1219,7 +909,7 @@ DECLARE_EVENT_CLASS(nfs4_set_delegation_event,
TP_printk(
"fmode=%s fileid=%02x:%02x:%llu fhandle=0x%08x",
- show_fmode_flags(__entry->fmode),
+ show_fs_fmode_flags(__entry->fmode),
MAJOR(__entry->dev), MINOR(__entry->dev),
(unsigned long long)__entry->fileid,
__entry->fhandle
@@ -1266,7 +956,7 @@ TRACE_EVENT(nfs4_delegreturn_exit,
"error=%ld (%s) dev=%02x:%02x fhandle=0x%08x "
"stateid=%d:0x%08x",
-__entry->error,
- show_nfsv4_errors(__entry->error),
+ show_nfs4_status(__entry->error),
MAJOR(__entry->dev), MINOR(__entry->dev),
__entry->fhandle,
__entry->stateid_seq, __entry->stateid_hash
@@ -1309,7 +999,7 @@ DECLARE_EVENT_CLASS(nfs4_test_stateid_event,
"error=%ld (%s) fileid=%02x:%02x:%llu fhandle=0x%08x "
"stateid=%d:0x%08x",
-__entry->error,
- show_nfsv4_errors(__entry->error),
+ show_nfs4_status(__entry->error),
MAJOR(__entry->dev), MINOR(__entry->dev),
(unsigned long long)__entry->fileid,
__entry->fhandle,
@@ -1356,7 +1046,7 @@ DECLARE_EVENT_CLASS(nfs4_lookup_event,
TP_printk(
"error=%ld (%s) name=%02x:%02x:%llu/%s",
-__entry->error,
- show_nfsv4_errors(__entry->error),
+ show_nfs4_status(__entry->error),
MAJOR(__entry->dev), MINOR(__entry->dev),
(unsigned long long)__entry->dir,
__get_str(name)
@@ -1403,7 +1093,7 @@ TRACE_EVENT(nfs4_lookupp,
TP_printk(
"error=%ld (%s) inode=%02x:%02x:%llu",
-__entry->error,
- show_nfsv4_errors(__entry->error),
+ show_nfs4_status(__entry->error),
MAJOR(__entry->dev), MINOR(__entry->dev),
(unsigned long long)__entry->ino
)
@@ -1442,7 +1132,7 @@ TRACE_EVENT(nfs4_rename,
"error=%ld (%s) oldname=%02x:%02x:%llu/%s "
"newname=%02x:%02x:%llu/%s",
-__entry->error,
- show_nfsv4_errors(__entry->error),
+ show_nfs4_status(__entry->error),
MAJOR(__entry->dev), MINOR(__entry->dev),
(unsigned long long)__entry->olddir,
__get_str(oldname),
@@ -1477,7 +1167,7 @@ DECLARE_EVENT_CLASS(nfs4_inode_event,
TP_printk(
"error=%ld (%s) fileid=%02x:%02x:%llu fhandle=0x%08x",
-__entry->error,
- show_nfsv4_errors(__entry->error),
+ show_nfs4_status(__entry->error),
MAJOR(__entry->dev), MINOR(__entry->dev),
(unsigned long long)__entry->fileid,
__entry->fhandle
@@ -1535,7 +1225,7 @@ DECLARE_EVENT_CLASS(nfs4_inode_stateid_event,
"error=%ld (%s) fileid=%02x:%02x:%llu fhandle=0x%08x "
"stateid=%d:0x%08x",
-__entry->error,
- show_nfsv4_errors(__entry->error),
+ show_nfs4_status(__entry->error),
MAJOR(__entry->dev), MINOR(__entry->dev),
(unsigned long long)__entry->fileid,
__entry->fhandle,
@@ -1588,7 +1278,7 @@ DECLARE_EVENT_CLASS(nfs4_getattr_event,
"error=%ld (%s) fileid=%02x:%02x:%llu fhandle=0x%08x "
"valid=%s",
-__entry->error,
- show_nfsv4_errors(__entry->error),
+ show_nfs4_status(__entry->error),
MAJOR(__entry->dev), MINOR(__entry->dev),
(unsigned long long)__entry->fileid,
__entry->fhandle,
@@ -1644,7 +1334,7 @@ DECLARE_EVENT_CLASS(nfs4_inode_callback_event,
"error=%ld (%s) fileid=%02x:%02x:%llu fhandle=0x%08x "
"dstaddr=%s",
-__entry->error,
- show_nfsv4_errors(__entry->error),
+ show_nfs4_status(__entry->error),
MAJOR(__entry->dev), MINOR(__entry->dev),
(unsigned long long)__entry->fileid,
__entry->fhandle,
@@ -1705,7 +1395,7 @@ DECLARE_EVENT_CLASS(nfs4_inode_stateid_callback_event,
"error=%ld (%s) fileid=%02x:%02x:%llu fhandle=0x%08x "
"stateid=%d:0x%08x dstaddr=%s",
-__entry->error,
- show_nfsv4_errors(__entry->error),
+ show_nfs4_status(__entry->error),
MAJOR(__entry->dev), MINOR(__entry->dev),
(unsigned long long)__entry->fileid,
__entry->fhandle,
@@ -1754,7 +1444,7 @@ DECLARE_EVENT_CLASS(nfs4_idmap_event,
TP_printk(
"error=%ld (%s) id=%u name=%s",
- -__entry->error, show_nfsv4_errors(__entry->error),
+ -__entry->error, show_nfs4_status(__entry->error),
__entry->id,
__get_str(name)
)
@@ -1832,7 +1522,7 @@ DECLARE_EVENT_CLASS(nfs4_read_event,
"offset=%lld count=%u res=%u stateid=%d:0x%08x "
"layoutstateid=%d:0x%08x",
-__entry->error,
- show_nfsv4_errors(__entry->error),
+ show_nfs4_status(__entry->error),
MAJOR(__entry->dev), MINOR(__entry->dev),
(unsigned long long)__entry->fileid,
__entry->fhandle,
@@ -1906,7 +1596,7 @@ DECLARE_EVENT_CLASS(nfs4_write_event,
"offset=%lld count=%u res=%u stateid=%d:0x%08x "
"layoutstateid=%d:0x%08x",
-__entry->error,
- show_nfsv4_errors(__entry->error),
+ show_nfs4_status(__entry->error),
MAJOR(__entry->dev), MINOR(__entry->dev),
(unsigned long long)__entry->fileid,
__entry->fhandle,
@@ -1970,7 +1660,7 @@ DECLARE_EVENT_CLASS(nfs4_commit_event,
"error=%ld (%s) fileid=%02x:%02x:%llu fhandle=0x%08x "
"offset=%lld count=%u layoutstateid=%d:0x%08x",
-__entry->error,
- show_nfsv4_errors(__entry->error),
+ show_nfs4_status(__entry->error),
MAJOR(__entry->dev), MINOR(__entry->dev),
(unsigned long long)__entry->fileid,
__entry->fhandle,
@@ -1990,16 +1680,6 @@ DEFINE_NFS4_COMMIT_EVENT(nfs4_commit);
#ifdef CONFIG_NFS_V4_1
DEFINE_NFS4_COMMIT_EVENT(nfs4_pnfs_commit_ds);
-TRACE_DEFINE_ENUM(IOMODE_READ);
-TRACE_DEFINE_ENUM(IOMODE_RW);
-TRACE_DEFINE_ENUM(IOMODE_ANY);
-
-#define show_pnfs_iomode(iomode) \
- __print_symbolic(iomode, \
- { IOMODE_READ, "READ" }, \
- { IOMODE_RW, "RW" }, \
- { IOMODE_ANY, "ANY" })
-
TRACE_EVENT(nfs4_layoutget,
TP_PROTO(
const struct nfs_open_context *ctx,
@@ -2055,11 +1735,11 @@ TRACE_EVENT(nfs4_layoutget,
"iomode=%s offset=%llu count=%llu stateid=%d:0x%08x "
"layoutstateid=%d:0x%08x",
-__entry->error,
- show_nfsv4_errors(__entry->error),
+ show_nfs4_status(__entry->error),
MAJOR(__entry->dev), MINOR(__entry->dev),
(unsigned long long)__entry->fileid,
__entry->fhandle,
- show_pnfs_iomode(__entry->iomode),
+ show_pnfs_layout_iomode(__entry->iomode),
(unsigned long long)__entry->offset,
(unsigned long long)__entry->count,
__entry->stateid_seq, __entry->stateid_hash,
@@ -2153,7 +1833,7 @@ TRACE_EVENT(pnfs_update_layout,
MAJOR(__entry->dev), MINOR(__entry->dev),
(unsigned long long)__entry->fileid,
__entry->fhandle,
- show_pnfs_iomode(__entry->iomode),
+ show_pnfs_layout_iomode(__entry->iomode),
(unsigned long long)__entry->pos,
(unsigned long long)__entry->count,
__entry->layoutstateid_seq, __entry->layoutstateid_hash,
@@ -2207,7 +1887,7 @@ DECLARE_EVENT_CLASS(pnfs_layout_event,
MAJOR(__entry->dev), MINOR(__entry->dev),
(unsigned long long)__entry->fileid,
__entry->fhandle,
- show_pnfs_iomode(__entry->iomode),
+ show_pnfs_layout_iomode(__entry->iomode),
(unsigned long long)__entry->pos,
(unsigned long long)__entry->count,
__entry->layoutstateid_seq, __entry->layoutstateid_hash,
@@ -2352,7 +2032,7 @@ DECLARE_EVENT_CLASS(nfs4_flexfiles_io_event,
"error=%ld (%s) fileid=%02x:%02x:%llu fhandle=0x%08x "
"offset=%llu count=%u stateid=%d:0x%08x dstaddr=%s",
-__entry->error,
- show_nfsv4_errors(__entry->error),
+ show_nfs4_status(__entry->error),
MAJOR(__entry->dev), MINOR(__entry->dev),
(unsigned long long)__entry->fileid,
__entry->fhandle,
@@ -2408,7 +2088,7 @@ TRACE_EVENT(ff_layout_commit_error,
"error=%ld (%s) fileid=%02x:%02x:%llu fhandle=0x%08x "
"offset=%llu count=%u dstaddr=%s",
-__entry->error,
- show_nfsv4_errors(__entry->error),
+ show_nfs4_status(__entry->error),
MAJOR(__entry->dev), MINOR(__entry->dev),
(unsigned long long)__entry->fileid,
__entry->fhandle,
@@ -2417,6 +2097,406 @@ TRACE_EVENT(ff_layout_commit_error,
)
);
+TRACE_DEFINE_ENUM(NFS4_CONTENT_DATA);
+TRACE_DEFINE_ENUM(NFS4_CONTENT_HOLE);
+
+#define show_llseek_mode(what) \
+ __print_symbolic(what, \
+ { NFS4_CONTENT_DATA, "DATA" }, \
+ { NFS4_CONTENT_HOLE, "HOLE" })
+
+#ifdef CONFIG_NFS_V4_2
+TRACE_EVENT(nfs4_llseek,
+ TP_PROTO(
+ const struct inode *inode,
+ const struct nfs42_seek_args *args,
+ const struct nfs42_seek_res *res,
+ int error
+ ),
+
+ TP_ARGS(inode, args, res, error),
+
+ TP_STRUCT__entry(
+ __field(unsigned long, error)
+ __field(u32, fhandle)
+ __field(u32, fileid)
+ __field(dev_t, dev)
+ __field(int, stateid_seq)
+ __field(u32, stateid_hash)
+ __field(loff_t, offset_s)
+ __field(u32, what)
+ __field(loff_t, offset_r)
+ __field(u32, eof)
+ ),
+
+ TP_fast_assign(
+ const struct nfs_inode *nfsi = NFS_I(inode);
+ const struct nfs_fh *fh = args->sa_fh;
+
+ __entry->fileid = nfsi->fileid;
+ __entry->dev = inode->i_sb->s_dev;
+ __entry->fhandle = nfs_fhandle_hash(fh);
+ __entry->offset_s = args->sa_offset;
+ __entry->stateid_seq =
+ be32_to_cpu(args->sa_stateid.seqid);
+ __entry->stateid_hash =
+ nfs_stateid_hash(&args->sa_stateid);
+ __entry->what = args->sa_what;
+ if (error) {
+ __entry->error = -error;
+ __entry->offset_r = 0;
+ __entry->eof = 0;
+ } else {
+ __entry->error = 0;
+ __entry->offset_r = res->sr_offset;
+ __entry->eof = res->sr_eof;
+ }
+ ),
+
+ TP_printk(
+ "error=%ld (%s) fileid=%02x:%02x:%llu fhandle=0x%08x "
+ "stateid=%d:0x%08x offset_s=%llu what=%s "
+ "offset_r=%llu eof=%u",
+ -__entry->error,
+ show_nfs4_status(__entry->error),
+ MAJOR(__entry->dev), MINOR(__entry->dev),
+ (unsigned long long)__entry->fileid,
+ __entry->fhandle,
+ __entry->stateid_seq, __entry->stateid_hash,
+ __entry->offset_s,
+ show_llseek_mode(__entry->what),
+ __entry->offset_r,
+ __entry->eof
+ )
+);
+
+DECLARE_EVENT_CLASS(nfs4_sparse_event,
+ TP_PROTO(
+ const struct inode *inode,
+ const struct nfs42_falloc_args *args,
+ int error
+ ),
+
+ TP_ARGS(inode, args, error),
+
+ TP_STRUCT__entry(
+ __field(unsigned long, error)
+ __field(loff_t, offset)
+ __field(loff_t, len)
+ __field(dev_t, dev)
+ __field(u32, fhandle)
+ __field(u64, fileid)
+ __field(int, stateid_seq)
+ __field(u32, stateid_hash)
+ ),
+
+ TP_fast_assign(
+ __entry->error = error < 0 ? -error : 0;
+ __entry->offset = args->falloc_offset;
+ __entry->len = args->falloc_length;
+ __entry->dev = inode->i_sb->s_dev;
+ __entry->fileid = NFS_FILEID(inode);
+ __entry->fhandle = nfs_fhandle_hash(NFS_FH(inode));
+ __entry->stateid_seq =
+ be32_to_cpu(args->falloc_stateid.seqid);
+ __entry->stateid_hash =
+ nfs_stateid_hash(&args->falloc_stateid);
+ ),
+
+ TP_printk(
+ "error=%ld (%s) fileid=%02x:%02x:%llu fhandle=0x%08x "
+ "stateid=%d:0x%08x offset=%llu len=%llu",
+ -__entry->error,
+ show_nfs4_status(__entry->error),
+ MAJOR(__entry->dev), MINOR(__entry->dev),
+ (unsigned long long)__entry->fileid,
+ __entry->fhandle,
+ __entry->stateid_seq, __entry->stateid_hash,
+ (long long)__entry->offset,
+ (long long)__entry->len
+ )
+);
+#define DEFINE_NFS4_SPARSE_EVENT(name) \
+ DEFINE_EVENT(nfs4_sparse_event, name, \
+ TP_PROTO( \
+ const struct inode *inode, \
+ const struct nfs42_falloc_args *args, \
+ int error \
+ ), \
+ TP_ARGS(inode, args, error))
+DEFINE_NFS4_SPARSE_EVENT(nfs4_fallocate);
+DEFINE_NFS4_SPARSE_EVENT(nfs4_deallocate);
+
+TRACE_EVENT(nfs4_copy,
+ TP_PROTO(
+ const struct inode *src_inode,
+ const struct inode *dst_inode,
+ const struct nfs42_copy_args *args,
+ const struct nfs42_copy_res *res,
+ const struct nl4_server *nss,
+ int error
+ ),
+
+ TP_ARGS(src_inode, dst_inode, args, res, nss, error),
+
+ TP_STRUCT__entry(
+ __field(unsigned long, error)
+ __field(u32, src_fhandle)
+ __field(u32, src_fileid)
+ __field(u32, dst_fhandle)
+ __field(u32, dst_fileid)
+ __field(dev_t, src_dev)
+ __field(dev_t, dst_dev)
+ __field(int, src_stateid_seq)
+ __field(u32, src_stateid_hash)
+ __field(int, dst_stateid_seq)
+ __field(u32, dst_stateid_hash)
+ __field(loff_t, src_offset)
+ __field(loff_t, dst_offset)
+ __field(bool, sync)
+ __field(loff_t, len)
+ __field(int, res_stateid_seq)
+ __field(u32, res_stateid_hash)
+ __field(loff_t, res_count)
+ __field(bool, res_sync)
+ __field(bool, res_cons)
+ __field(bool, intra)
+ ),
+
+ TP_fast_assign(
+ const struct nfs_inode *src_nfsi = NFS_I(src_inode);
+ const struct nfs_inode *dst_nfsi = NFS_I(dst_inode);
+
+ __entry->src_fileid = src_nfsi->fileid;
+ __entry->src_dev = src_inode->i_sb->s_dev;
+ __entry->src_fhandle = nfs_fhandle_hash(args->src_fh);
+ __entry->src_offset = args->src_pos;
+ __entry->dst_fileid = dst_nfsi->fileid;
+ __entry->dst_dev = dst_inode->i_sb->s_dev;
+ __entry->dst_fhandle = nfs_fhandle_hash(args->dst_fh);
+ __entry->dst_offset = args->dst_pos;
+ __entry->len = args->count;
+ __entry->sync = args->sync;
+ __entry->src_stateid_seq =
+ be32_to_cpu(args->src_stateid.seqid);
+ __entry->src_stateid_hash =
+ nfs_stateid_hash(&args->src_stateid);
+ __entry->dst_stateid_seq =
+ be32_to_cpu(args->dst_stateid.seqid);
+ __entry->dst_stateid_hash =
+ nfs_stateid_hash(&args->dst_stateid);
+ __entry->intra = nss ? 0 : 1;
+ if (error) {
+ __entry->error = -error;
+ __entry->res_stateid_seq = 0;
+ __entry->res_stateid_hash = 0;
+ __entry->res_count = 0;
+ __entry->res_sync = 0;
+ __entry->res_cons = 0;
+ } else {
+ __entry->error = 0;
+ __entry->res_stateid_seq =
+ be32_to_cpu(res->write_res.stateid.seqid);
+ __entry->res_stateid_hash =
+ nfs_stateid_hash(&res->write_res.stateid);
+ __entry->res_count = res->write_res.count;
+ __entry->res_sync = res->synchronous;
+ __entry->res_cons = res->consecutive;
+ }
+ ),
+
+ TP_printk(
+ "error=%ld (%s) intra=%d src_fileid=%02x:%02x:%llu "
+ "src_fhandle=0x%08x dst_fileid=%02x:%02x:%llu "
+ "dst_fhandle=0x%08x src_stateid=%d:0x%08x "
+ "dst_stateid=%d:0x%08x src_offset=%llu dst_offset=%llu "
+ "len=%llu sync=%d cb_stateid=%d:0x%08x res_sync=%d "
+ "res_cons=%d res_count=%llu",
+ -__entry->error,
+ show_nfs4_status(__entry->error),
+ __entry->intra,
+ MAJOR(__entry->src_dev), MINOR(__entry->src_dev),
+ (unsigned long long)__entry->src_fileid,
+ __entry->src_fhandle,
+ MAJOR(__entry->dst_dev), MINOR(__entry->dst_dev),
+ (unsigned long long)__entry->dst_fileid,
+ __entry->dst_fhandle,
+ __entry->src_stateid_seq, __entry->src_stateid_hash,
+ __entry->dst_stateid_seq, __entry->dst_stateid_hash,
+ __entry->src_offset,
+ __entry->dst_offset,
+ __entry->len,
+ __entry->sync,
+ __entry->res_stateid_seq, __entry->res_stateid_hash,
+ __entry->res_sync,
+ __entry->res_cons,
+ __entry->res_count
+ )
+);
+
+TRACE_EVENT(nfs4_clone,
+ TP_PROTO(
+ const struct inode *src_inode,
+ const struct inode *dst_inode,
+ const struct nfs42_clone_args *args,
+ int error
+ ),
+
+ TP_ARGS(src_inode, dst_inode, args, error),
+
+ TP_STRUCT__entry(
+ __field(unsigned long, error)
+ __field(u32, src_fhandle)
+ __field(u32, src_fileid)
+ __field(u32, dst_fhandle)
+ __field(u32, dst_fileid)
+ __field(dev_t, src_dev)
+ __field(dev_t, dst_dev)
+ __field(loff_t, src_offset)
+ __field(loff_t, dst_offset)
+ __field(int, src_stateid_seq)
+ __field(u32, src_stateid_hash)
+ __field(int, dst_stateid_seq)
+ __field(u32, dst_stateid_hash)
+ __field(loff_t, len)
+ ),
+
+ TP_fast_assign(
+ const struct nfs_inode *src_nfsi = NFS_I(src_inode);
+ const struct nfs_inode *dst_nfsi = NFS_I(dst_inode);
+
+ __entry->src_fileid = src_nfsi->fileid;
+ __entry->src_dev = src_inode->i_sb->s_dev;
+ __entry->src_fhandle = nfs_fhandle_hash(args->src_fh);
+ __entry->src_offset = args->src_offset;
+ __entry->dst_fileid = dst_nfsi->fileid;
+ __entry->dst_dev = dst_inode->i_sb->s_dev;
+ __entry->dst_fhandle = nfs_fhandle_hash(args->dst_fh);
+ __entry->dst_offset = args->dst_offset;
+ __entry->len = args->count;
+ __entry->error = error < 0 ? -error : 0;
+ __entry->src_stateid_seq =
+ be32_to_cpu(args->src_stateid.seqid);
+ __entry->src_stateid_hash =
+ nfs_stateid_hash(&args->src_stateid);
+ __entry->dst_stateid_seq =
+ be32_to_cpu(args->dst_stateid.seqid);
+ __entry->dst_stateid_hash =
+ nfs_stateid_hash(&args->dst_stateid);
+ ),
+
+ TP_printk(
+ "error=%ld (%s) src_fileid=%02x:%02x:%llu "
+ "src_fhandle=0x%08x dst_fileid=%02x:%02x:%llu "
+ "dst_fhandle=0x%08x src_stateid=%d:0x%08x "
+ "dst_stateid=%d:0x%08x src_offset=%llu "
+ "dst_offset=%llu len=%llu",
+ -__entry->error,
+ show_nfs4_status(__entry->error),
+ MAJOR(__entry->src_dev), MINOR(__entry->src_dev),
+ (unsigned long long)__entry->src_fileid,
+ __entry->src_fhandle,
+ MAJOR(__entry->dst_dev), MINOR(__entry->dst_dev),
+ (unsigned long long)__entry->dst_fileid,
+ __entry->dst_fhandle,
+ __entry->src_stateid_seq, __entry->src_stateid_hash,
+ __entry->dst_stateid_seq, __entry->dst_stateid_hash,
+ __entry->src_offset,
+ __entry->dst_offset,
+ __entry->len
+ )
+);
+
+TRACE_EVENT(nfs4_copy_notify,
+ TP_PROTO(
+ const struct inode *inode,
+ const struct nfs42_copy_notify_args *args,
+ const struct nfs42_copy_notify_res *res,
+ int error
+ ),
+
+ TP_ARGS(inode, args, res, error),
+
+ TP_STRUCT__entry(
+ __field(unsigned long, error)
+ __field(u32, fhandle)
+ __field(u32, fileid)
+ __field(dev_t, dev)
+ __field(int, stateid_seq)
+ __field(u32, stateid_hash)
+ __field(int, res_stateid_seq)
+ __field(u32, res_stateid_hash)
+ ),
+
+ TP_fast_assign(
+ const struct nfs_inode *nfsi = NFS_I(inode);
+
+ __entry->fileid = nfsi->fileid;
+ __entry->dev = inode->i_sb->s_dev;
+ __entry->fhandle = nfs_fhandle_hash(args->cna_src_fh);
+ __entry->stateid_seq =
+ be32_to_cpu(args->cna_src_stateid.seqid);
+ __entry->stateid_hash =
+ nfs_stateid_hash(&args->cna_src_stateid);
+ if (error) {
+ __entry->error = -error;
+ __entry->res_stateid_seq = 0;
+ __entry->res_stateid_hash = 0;
+ } else {
+ __entry->error = 0;
+ __entry->res_stateid_seq =
+ be32_to_cpu(res->cnr_stateid.seqid);
+ __entry->res_stateid_hash =
+ nfs_stateid_hash(&res->cnr_stateid);
+ }
+ ),
+
+ TP_printk(
+ "error=%ld (%s) fileid=%02x:%02x:%llu fhandle=0x%08x "
+ "stateid=%d:0x%08x res_stateid=%d:0x%08x",
+ -__entry->error,
+ show_nfs4_status(__entry->error),
+ MAJOR(__entry->dev), MINOR(__entry->dev),
+ (unsigned long long)__entry->fileid,
+ __entry->fhandle,
+ __entry->stateid_seq, __entry->stateid_hash,
+ __entry->res_stateid_seq, __entry->res_stateid_hash
+ )
+);
+
+TRACE_EVENT(nfs4_offload_cancel,
+ TP_PROTO(
+ const struct nfs42_offload_status_args *args,
+ int error
+ ),
+
+ TP_ARGS(args, error),
+
+ TP_STRUCT__entry(
+ __field(unsigned long, error)
+ __field(u32, fhandle)
+ __field(int, stateid_seq)
+ __field(u32, stateid_hash)
+ ),
+
+ TP_fast_assign(
+ __entry->fhandle = nfs_fhandle_hash(args->osa_src_fh);
+ __entry->error = error < 0 ? -error : 0;
+ __entry->stateid_seq =
+ be32_to_cpu(args->osa_stateid.seqid);
+ __entry->stateid_hash =
+ nfs_stateid_hash(&args->osa_stateid);
+ ),
+
+ TP_printk(
+ "error=%ld (%s) fhandle=0x%08x stateid=%d:0x%08x",
+ -__entry->error,
+ show_nfs4_status(__entry->error),
+ __entry->fhandle,
+ __entry->stateid_seq, __entry->stateid_hash
+ )
+);
+#endif /* CONFIG_NFS_V4_2 */
#endif /* CONFIG_NFS_V4_1 */
diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c
index a8cff19c6f00..69862bf6db00 100644
--- a/fs/nfs/nfs4xdr.c
+++ b/fs/nfs/nfs4xdr.c
@@ -3168,20 +3168,23 @@ static int decode_opaque_inline(struct xdr_stream *xdr, unsigned int *len, char
static int decode_compound_hdr(struct xdr_stream *xdr, struct compound_hdr *hdr)
{
- __be32 *p;
+ ssize_t ret;
+ void *ptr;
+ u32 tmp;
- p = xdr_inline_decode(xdr, 8);
- if (unlikely(!p))
+ if (xdr_stream_decode_u32(xdr, &tmp) < 0)
return -EIO;
- hdr->status = be32_to_cpup(p++);
- hdr->taglen = be32_to_cpup(p);
+ hdr->status = tmp;
- p = xdr_inline_decode(xdr, hdr->taglen + 4);
- if (unlikely(!p))
+ ret = xdr_stream_decode_opaque_inline(xdr, &ptr, NFS4_OPAQUE_LIMIT);
+ if (ret < 0)
+ return -EIO;
+ hdr->taglen = ret;
+ hdr->tag = ptr;
+
+ if (xdr_stream_decode_u32(xdr, &tmp) < 0)
return -EIO;
- hdr->tag = (char *)p;
- p += XDR_QUADLEN(hdr->taglen);
- hdr->nops = be32_to_cpup(p);
+ hdr->nops = tmp;
if (unlikely(hdr->nops < 1))
return nfs4_stat_to_errno(hdr->status);
return 0;
@@ -4582,8 +4585,7 @@ static int decode_attr_mdsthreshold(struct xdr_stream *xdr,
static int decode_getfattr_attrs(struct xdr_stream *xdr, uint32_t *bitmap,
struct nfs_fattr *fattr, struct nfs_fh *fh,
- struct nfs4_fs_locations *fs_loc, struct nfs4_label *label,
- const struct nfs_server *server)
+ struct nfs4_fs_locations *fs_loc, const struct nfs_server *server)
{
int status;
umode_t fmode = 0;
@@ -4698,8 +4700,8 @@ static int decode_getfattr_attrs(struct xdr_stream *xdr, uint32_t *bitmap,
if (status < 0)
goto xdr_error;
- if (label) {
- status = decode_attr_security_label(xdr, bitmap, label);
+ if (fattr->label) {
+ status = decode_attr_security_label(xdr, bitmap, fattr->label);
if (status < 0)
goto xdr_error;
fattr->valid |= status;
@@ -4712,7 +4714,7 @@ xdr_error:
static int decode_getfattr_generic(struct xdr_stream *xdr, struct nfs_fattr *fattr,
struct nfs_fh *fh, struct nfs4_fs_locations *fs_loc,
- struct nfs4_label *label, const struct nfs_server *server)
+ const struct nfs_server *server)
{
unsigned int savep;
uint32_t attrlen,
@@ -4731,8 +4733,7 @@ static int decode_getfattr_generic(struct xdr_stream *xdr, struct nfs_fattr *fat
if (status < 0)
goto xdr_error;
- status = decode_getfattr_attrs(xdr, bitmap, fattr, fh, fs_loc,
- label, server);
+ status = decode_getfattr_attrs(xdr, bitmap, fattr, fh, fs_loc, server);
if (status < 0)
goto xdr_error;
@@ -4742,16 +4743,10 @@ xdr_error:
return status;
}
-static int decode_getfattr_label(struct xdr_stream *xdr, struct nfs_fattr *fattr,
- struct nfs4_label *label, const struct nfs_server *server)
-{
- return decode_getfattr_generic(xdr, fattr, NULL, NULL, label, server);
-}
-
static int decode_getfattr(struct xdr_stream *xdr, struct nfs_fattr *fattr,
const struct nfs_server *server)
{
- return decode_getfattr_generic(xdr, fattr, NULL, NULL, NULL, server);
+ return decode_getfattr_generic(xdr, fattr, NULL, NULL, server);
}
/*
@@ -5572,20 +5567,9 @@ static int decode_secinfo_no_name(struct xdr_stream *xdr, struct nfs4_secinfo_re
static int decode_op_map(struct xdr_stream *xdr, struct nfs4_op_map *op_map)
{
- __be32 *p;
- uint32_t bitmap_words;
- unsigned int i;
-
- p = xdr_inline_decode(xdr, 4);
- if (!p)
- return -EIO;
- bitmap_words = be32_to_cpup(p++);
- if (bitmap_words > NFS4_OP_MAP_NUM_WORDS)
+ if (xdr_stream_decode_uint32_array(xdr, op_map->u.words,
+ ARRAY_SIZE(op_map->u.words)) < 0)
return -EIO;
- p = xdr_inline_decode(xdr, 4 * bitmap_words);
- for (i = 0; i < bitmap_words; i++)
- op_map->u.words[i] = be32_to_cpup(p++);
-
return 0;
}
@@ -6179,7 +6163,7 @@ static int nfs4_xdr_dec_lookup(struct rpc_rqst *rqstp, struct xdr_stream *xdr,
status = decode_getfh(xdr, res->fh);
if (status)
goto out;
- status = decode_getfattr_label(xdr, res->fattr, res->label, res->server);
+ status = decode_getfattr(xdr, res->fattr, res->server);
out:
return status;
}
@@ -6209,7 +6193,7 @@ static int nfs4_xdr_dec_lookupp(struct rpc_rqst *rqstp, struct xdr_stream *xdr,
status = decode_getfh(xdr, res->fh);
if (status)
goto out;
- status = decode_getfattr_label(xdr, res->fattr, res->label, res->server);
+ status = decode_getfattr(xdr, res->fattr, res->server);
out:
return status;
}
@@ -6236,8 +6220,7 @@ static int nfs4_xdr_dec_lookup_root(struct rpc_rqst *rqstp,
goto out;
status = decode_getfh(xdr, res->fh);
if (status == 0)
- status = decode_getfattr_label(xdr, res->fattr,
- res->label, res->server);
+ status = decode_getfattr(xdr, res->fattr, res->server);
out:
return status;
}
@@ -6331,7 +6314,7 @@ static int nfs4_xdr_dec_link(struct rpc_rqst *rqstp, struct xdr_stream *xdr,
status = decode_restorefh(xdr);
if (status)
goto out;
- decode_getfattr_label(xdr, res->fattr, res->label, res->server);
+ decode_getfattr(xdr, res->fattr, res->server);
out:
return status;
}
@@ -6361,7 +6344,7 @@ static int nfs4_xdr_dec_create(struct rpc_rqst *rqstp, struct xdr_stream *xdr,
status = decode_getfh(xdr, res->fh);
if (status)
goto out;
- decode_getfattr_label(xdr, res->fattr, res->label, res->server);
+ decode_getfattr(xdr, res->fattr, res->server);
out:
return status;
}
@@ -6394,7 +6377,7 @@ static int nfs4_xdr_dec_getattr(struct rpc_rqst *rqstp, struct xdr_stream *xdr,
status = decode_putfh(xdr);
if (status)
goto out;
- status = decode_getfattr_label(xdr, res->fattr, res->label, res->server);
+ status = decode_getfattr(xdr, res->fattr, res->server);
out:
return status;
}
@@ -6532,7 +6515,7 @@ static int nfs4_xdr_dec_open(struct rpc_rqst *rqstp, struct xdr_stream *xdr,
goto out;
if (res->access_request)
decode_access(xdr, &res->access_supported, &res->access_result);
- decode_getfattr_label(xdr, res->f_attr, res->f_label, res->server);
+ decode_getfattr(xdr, res->f_attr, res->server);
if (res->lg_res)
decode_layoutget(xdr, rqstp, res->lg_res);
out:
@@ -6616,7 +6599,7 @@ static int nfs4_xdr_dec_setattr(struct rpc_rqst *rqstp,
status = decode_setattr(xdr);
if (status)
goto out;
- decode_getfattr_label(xdr, res->fattr, res->label, res->server);
+ decode_getfattr(xdr, res->fattr, res->server);
out:
return status;
}
@@ -7031,7 +7014,7 @@ static int nfs4_xdr_dec_fs_locations(struct rpc_rqst *req,
status = decode_getfattr_generic(xdr,
&res->fs_locations->fattr,
NULL, res->fs_locations,
- NULL, res->fs_locations->server);
+ res->fs_locations->server);
if (status)
goto out;
if (res->renew)
@@ -7044,7 +7027,7 @@ static int nfs4_xdr_dec_fs_locations(struct rpc_rqst *req,
status = decode_getfattr_generic(xdr,
&res->fs_locations->fattr,
NULL, res->fs_locations,
- NULL, res->fs_locations->server);
+ res->fs_locations->server);
}
out:
return status;
@@ -7475,7 +7458,7 @@ int nfs4_decode_dirent(struct xdr_stream *xdr, struct nfs_entry *entry,
return -EAGAIN;
if (decode_getfattr_attrs(xdr, bitmap, entry->fattr, entry->fh,
- NULL, entry->label, entry->server) < 0)
+ NULL, entry->server) < 0)
return -EAGAIN;
if (entry->fattr->valid & NFS_ATTR_FATTR_MOUNTED_ON_FILEID)
entry->ino = entry->fattr->mounted_on_fileid;
diff --git a/fs/nfs/nfstrace.h b/fs/nfs/nfstrace.h
index 8a224871be74..21dac847f1e4 100644
--- a/fs/nfs/nfstrace.h
+++ b/fs/nfs/nfstrace.h
@@ -11,45 +11,9 @@
#include <linux/tracepoint.h>
#include <linux/iversion.h>
-TRACE_DEFINE_ENUM(DT_UNKNOWN);
-TRACE_DEFINE_ENUM(DT_FIFO);
-TRACE_DEFINE_ENUM(DT_CHR);
-TRACE_DEFINE_ENUM(DT_DIR);
-TRACE_DEFINE_ENUM(DT_BLK);
-TRACE_DEFINE_ENUM(DT_REG);
-TRACE_DEFINE_ENUM(DT_LNK);
-TRACE_DEFINE_ENUM(DT_SOCK);
-TRACE_DEFINE_ENUM(DT_WHT);
-
-#define nfs_show_file_type(ftype) \
- __print_symbolic(ftype, \
- { DT_UNKNOWN, "UNKNOWN" }, \
- { DT_FIFO, "FIFO" }, \
- { DT_CHR, "CHR" }, \
- { DT_DIR, "DIR" }, \
- { DT_BLK, "BLK" }, \
- { DT_REG, "REG" }, \
- { DT_LNK, "LNK" }, \
- { DT_SOCK, "SOCK" }, \
- { DT_WHT, "WHT" })
-
-TRACE_DEFINE_ENUM(NFS_INO_INVALID_DATA);
-TRACE_DEFINE_ENUM(NFS_INO_INVALID_ATIME);
-TRACE_DEFINE_ENUM(NFS_INO_INVALID_ACCESS);
-TRACE_DEFINE_ENUM(NFS_INO_INVALID_ACL);
-TRACE_DEFINE_ENUM(NFS_INO_REVAL_PAGECACHE);
-TRACE_DEFINE_ENUM(NFS_INO_REVAL_FORCED);
-TRACE_DEFINE_ENUM(NFS_INO_INVALID_LABEL);
-TRACE_DEFINE_ENUM(NFS_INO_INVALID_CHANGE);
-TRACE_DEFINE_ENUM(NFS_INO_INVALID_CTIME);
-TRACE_DEFINE_ENUM(NFS_INO_INVALID_MTIME);
-TRACE_DEFINE_ENUM(NFS_INO_INVALID_SIZE);
-TRACE_DEFINE_ENUM(NFS_INO_INVALID_OTHER);
-TRACE_DEFINE_ENUM(NFS_INO_DATA_INVAL_DEFER);
-TRACE_DEFINE_ENUM(NFS_INO_INVALID_BLOCKS);
-TRACE_DEFINE_ENUM(NFS_INO_INVALID_XATTR);
-TRACE_DEFINE_ENUM(NFS_INO_INVALID_NLINK);
-TRACE_DEFINE_ENUM(NFS_INO_INVALID_MODE);
+#include <trace/events/fs.h>
+#include <trace/events/nfs.h>
+#include <trace/events/sunrpc_base.h>
#define nfs_show_cache_validity(v) \
__print_flags(v, "|", \
@@ -71,17 +35,6 @@ TRACE_DEFINE_ENUM(NFS_INO_INVALID_MODE);
{ NFS_INO_INVALID_NLINK, "INVALID_NLINK" }, \
{ NFS_INO_INVALID_MODE, "INVALID_MODE" })
-TRACE_DEFINE_ENUM(NFS_INO_ADVISE_RDPLUS);
-TRACE_DEFINE_ENUM(NFS_INO_STALE);
-TRACE_DEFINE_ENUM(NFS_INO_ACL_LRU_SET);
-TRACE_DEFINE_ENUM(NFS_INO_INVALIDATING);
-TRACE_DEFINE_ENUM(NFS_INO_FSCACHE);
-TRACE_DEFINE_ENUM(NFS_INO_FSCACHE_LOCK);
-TRACE_DEFINE_ENUM(NFS_INO_LAYOUTCOMMIT);
-TRACE_DEFINE_ENUM(NFS_INO_LAYOUTCOMMITTING);
-TRACE_DEFINE_ENUM(NFS_INO_LAYOUTSTATS);
-TRACE_DEFINE_ENUM(NFS_INO_ODIRECT);
-
#define nfs_show_nfsi_flags(v) \
__print_flags(v, "|", \
{ BIT(NFS_INO_ADVISE_RDPLUS), "ADVISE_RDPLUS" }, \
@@ -163,12 +116,12 @@ DECLARE_EVENT_CLASS(nfs_inode_event_done,
"error=%ld (%s) fileid=%02x:%02x:%llu fhandle=0x%08x "
"type=%u (%s) version=%llu size=%lld "
"cache_validity=0x%lx (%s) nfs_flags=0x%lx (%s)",
- -__entry->error, nfs_show_status(__entry->error),
+ -__entry->error, show_nfs_status(__entry->error),
MAJOR(__entry->dev), MINOR(__entry->dev),
(unsigned long long)__entry->fileid,
__entry->fhandle,
__entry->type,
- nfs_show_file_type(__entry->type),
+ show_fs_dirent_type(__entry->type),
(unsigned long long)__entry->version,
(long long)__entry->size,
__entry->cache_validity,
@@ -254,12 +207,12 @@ TRACE_EVENT(nfs_access_exit,
"type=%u (%s) version=%llu size=%lld "
"cache_validity=0x%lx (%s) nfs_flags=0x%lx (%s) "
"mask=0x%x permitted=0x%x",
- -__entry->error, nfs_show_status(__entry->error),
+ -__entry->error, show_nfs_status(__entry->error),
MAJOR(__entry->dev), MINOR(__entry->dev),
(unsigned long long)__entry->fileid,
__entry->fhandle,
__entry->type,
- nfs_show_file_type(__entry->type),
+ show_fs_dirent_type(__entry->type),
(unsigned long long)__entry->version,
(long long)__entry->size,
__entry->cache_validity,
@@ -270,33 +223,55 @@ TRACE_EVENT(nfs_access_exit,
)
);
-TRACE_DEFINE_ENUM(LOOKUP_FOLLOW);
-TRACE_DEFINE_ENUM(LOOKUP_DIRECTORY);
-TRACE_DEFINE_ENUM(LOOKUP_AUTOMOUNT);
-TRACE_DEFINE_ENUM(LOOKUP_PARENT);
-TRACE_DEFINE_ENUM(LOOKUP_REVAL);
-TRACE_DEFINE_ENUM(LOOKUP_RCU);
-TRACE_DEFINE_ENUM(LOOKUP_OPEN);
-TRACE_DEFINE_ENUM(LOOKUP_CREATE);
-TRACE_DEFINE_ENUM(LOOKUP_EXCL);
-TRACE_DEFINE_ENUM(LOOKUP_RENAME_TARGET);
-TRACE_DEFINE_ENUM(LOOKUP_EMPTY);
-TRACE_DEFINE_ENUM(LOOKUP_DOWN);
-
-#define show_lookup_flags(flags) \
- __print_flags(flags, "|", \
- { LOOKUP_FOLLOW, "FOLLOW" }, \
- { LOOKUP_DIRECTORY, "DIRECTORY" }, \
- { LOOKUP_AUTOMOUNT, "AUTOMOUNT" }, \
- { LOOKUP_PARENT, "PARENT" }, \
- { LOOKUP_REVAL, "REVAL" }, \
- { LOOKUP_RCU, "RCU" }, \
- { LOOKUP_OPEN, "OPEN" }, \
- { LOOKUP_CREATE, "CREATE" }, \
- { LOOKUP_EXCL, "EXCL" }, \
- { LOOKUP_RENAME_TARGET, "RENAME_TARGET" }, \
- { LOOKUP_EMPTY, "EMPTY" }, \
- { LOOKUP_DOWN, "DOWN" })
+DECLARE_EVENT_CLASS(nfs_update_size_class,
+ TP_PROTO(
+ const struct inode *inode,
+ loff_t new_size
+ ),
+
+ TP_ARGS(inode, new_size),
+
+ TP_STRUCT__entry(
+ __field(dev_t, dev)
+ __field(u32, fhandle)
+ __field(u64, fileid)
+ __field(u64, version)
+ __field(loff_t, cur_size)
+ __field(loff_t, new_size)
+ ),
+
+ TP_fast_assign(
+ const struct nfs_inode *nfsi = NFS_I(inode);
+
+ __entry->dev = inode->i_sb->s_dev;
+ __entry->fhandle = nfs_fhandle_hash(&nfsi->fh);
+ __entry->fileid = nfsi->fileid;
+ __entry->version = inode_peek_iversion_raw(inode);
+ __entry->cur_size = i_size_read(inode);
+ __entry->new_size = new_size;
+ ),
+
+ TP_printk(
+ "fileid=%02x:%02x:%llu fhandle=0x%08x version=%llu cursize=%lld newsize=%lld",
+ MAJOR(__entry->dev), MINOR(__entry->dev),
+ (unsigned long long)__entry->fileid,
+ __entry->fhandle, __entry->version,
+ __entry->cur_size, __entry->new_size
+ )
+);
+
+#define DEFINE_NFS_UPDATE_SIZE_EVENT(name) \
+ DEFINE_EVENT(nfs_update_size_class, nfs_size_##name, \
+ TP_PROTO( \
+ const struct inode *inode, \
+ loff_t new_size \
+ ), \
+ TP_ARGS(inode, new_size))
+
+DEFINE_NFS_UPDATE_SIZE_EVENT(truncate);
+DEFINE_NFS_UPDATE_SIZE_EVENT(wcc);
+DEFINE_NFS_UPDATE_SIZE_EVENT(update);
+DEFINE_NFS_UPDATE_SIZE_EVENT(grow);
DECLARE_EVENT_CLASS(nfs_lookup_event,
TP_PROTO(
@@ -324,7 +299,7 @@ DECLARE_EVENT_CLASS(nfs_lookup_event,
TP_printk(
"flags=0x%lx (%s) name=%02x:%02x:%llu/%s",
__entry->flags,
- show_lookup_flags(__entry->flags),
+ show_fs_lookup_flags(__entry->flags),
MAJOR(__entry->dev), MINOR(__entry->dev),
(unsigned long long)__entry->dir,
__get_str(name)
@@ -368,9 +343,9 @@ DECLARE_EVENT_CLASS(nfs_lookup_event_done,
TP_printk(
"error=%ld (%s) flags=0x%lx (%s) name=%02x:%02x:%llu/%s",
- -__entry->error, nfs_show_status(__entry->error),
+ -__entry->error, show_nfs_status(__entry->error),
__entry->flags,
- show_lookup_flags(__entry->flags),
+ show_fs_lookup_flags(__entry->flags),
MAJOR(__entry->dev), MINOR(__entry->dev),
(unsigned long long)__entry->dir,
__get_str(name)
@@ -392,46 +367,6 @@ DEFINE_NFS_LOOKUP_EVENT_DONE(nfs_lookup_exit);
DEFINE_NFS_LOOKUP_EVENT(nfs_lookup_revalidate_enter);
DEFINE_NFS_LOOKUP_EVENT_DONE(nfs_lookup_revalidate_exit);
-TRACE_DEFINE_ENUM(O_WRONLY);
-TRACE_DEFINE_ENUM(O_RDWR);
-TRACE_DEFINE_ENUM(O_CREAT);
-TRACE_DEFINE_ENUM(O_EXCL);
-TRACE_DEFINE_ENUM(O_NOCTTY);
-TRACE_DEFINE_ENUM(O_TRUNC);
-TRACE_DEFINE_ENUM(O_APPEND);
-TRACE_DEFINE_ENUM(O_NONBLOCK);
-TRACE_DEFINE_ENUM(O_DSYNC);
-TRACE_DEFINE_ENUM(O_DIRECT);
-TRACE_DEFINE_ENUM(O_LARGEFILE);
-TRACE_DEFINE_ENUM(O_DIRECTORY);
-TRACE_DEFINE_ENUM(O_NOFOLLOW);
-TRACE_DEFINE_ENUM(O_NOATIME);
-TRACE_DEFINE_ENUM(O_CLOEXEC);
-
-#define show_open_flags(flags) \
- __print_flags(flags, "|", \
- { O_WRONLY, "O_WRONLY" }, \
- { O_RDWR, "O_RDWR" }, \
- { O_CREAT, "O_CREAT" }, \
- { O_EXCL, "O_EXCL" }, \
- { O_NOCTTY, "O_NOCTTY" }, \
- { O_TRUNC, "O_TRUNC" }, \
- { O_APPEND, "O_APPEND" }, \
- { O_NONBLOCK, "O_NONBLOCK" }, \
- { O_DSYNC, "O_DSYNC" }, \
- { O_DIRECT, "O_DIRECT" }, \
- { O_LARGEFILE, "O_LARGEFILE" }, \
- { O_DIRECTORY, "O_DIRECTORY" }, \
- { O_NOFOLLOW, "O_NOFOLLOW" }, \
- { O_NOATIME, "O_NOATIME" }, \
- { O_CLOEXEC, "O_CLOEXEC" })
-
-#define show_fmode_flags(mode) \
- __print_flags(mode, "|", \
- { ((__force unsigned long)FMODE_READ), "READ" }, \
- { ((__force unsigned long)FMODE_WRITE), "WRITE" }, \
- { ((__force unsigned long)FMODE_EXEC), "EXEC" })
-
TRACE_EVENT(nfs_atomic_open_enter,
TP_PROTO(
const struct inode *dir,
@@ -443,7 +378,7 @@ TRACE_EVENT(nfs_atomic_open_enter,
TP_STRUCT__entry(
__field(unsigned long, flags)
- __field(unsigned int, fmode)
+ __field(unsigned long, fmode)
__field(dev_t, dev)
__field(u64, dir)
__string(name, ctx->dentry->d_name.name)
@@ -453,15 +388,15 @@ TRACE_EVENT(nfs_atomic_open_enter,
__entry->dev = dir->i_sb->s_dev;
__entry->dir = NFS_FILEID(dir);
__entry->flags = flags;
- __entry->fmode = (__force unsigned int)ctx->mode;
+ __entry->fmode = (__force unsigned long)ctx->mode;
__assign_str(name, ctx->dentry->d_name.name);
),
TP_printk(
"flags=0x%lx (%s) fmode=%s name=%02x:%02x:%llu/%s",
__entry->flags,
- show_open_flags(__entry->flags),
- show_fmode_flags(__entry->fmode),
+ show_fs_fcntl_open_flags(__entry->flags),
+ show_fs_fmode_flags(__entry->fmode),
MAJOR(__entry->dev), MINOR(__entry->dev),
(unsigned long long)__entry->dir,
__get_str(name)
@@ -481,7 +416,7 @@ TRACE_EVENT(nfs_atomic_open_exit,
TP_STRUCT__entry(
__field(unsigned long, error)
__field(unsigned long, flags)
- __field(unsigned int, fmode)
+ __field(unsigned long, fmode)
__field(dev_t, dev)
__field(u64, dir)
__string(name, ctx->dentry->d_name.name)
@@ -492,17 +427,17 @@ TRACE_EVENT(nfs_atomic_open_exit,
__entry->dev = dir->i_sb->s_dev;
__entry->dir = NFS_FILEID(dir);
__entry->flags = flags;
- __entry->fmode = (__force unsigned int)ctx->mode;
+ __entry->fmode = (__force unsigned long)ctx->mode;
__assign_str(name, ctx->dentry->d_name.name);
),
TP_printk(
"error=%ld (%s) flags=0x%lx (%s) fmode=%s "
"name=%02x:%02x:%llu/%s",
- -__entry->error, nfs_show_status(__entry->error),
+ -__entry->error, show_nfs_status(__entry->error),
__entry->flags,
- show_open_flags(__entry->flags),
- show_fmode_flags(__entry->fmode),
+ show_fs_fcntl_open_flags(__entry->flags),
+ show_fs_fmode_flags(__entry->fmode),
MAJOR(__entry->dev), MINOR(__entry->dev),
(unsigned long long)__entry->dir,
__get_str(name)
@@ -535,7 +470,7 @@ TRACE_EVENT(nfs_create_enter,
TP_printk(
"flags=0x%lx (%s) name=%02x:%02x:%llu/%s",
__entry->flags,
- show_open_flags(__entry->flags),
+ show_fs_fcntl_open_flags(__entry->flags),
MAJOR(__entry->dev), MINOR(__entry->dev),
(unsigned long long)__entry->dir,
__get_str(name)
@@ -570,9 +505,9 @@ TRACE_EVENT(nfs_create_exit,
TP_printk(
"error=%ld (%s) flags=0x%lx (%s) name=%02x:%02x:%llu/%s",
- -__entry->error, nfs_show_status(__entry->error),
+ -__entry->error, show_nfs_status(__entry->error),
__entry->flags,
- show_open_flags(__entry->flags),
+ show_fs_fcntl_open_flags(__entry->flags),
MAJOR(__entry->dev), MINOR(__entry->dev),
(unsigned long long)__entry->dir,
__get_str(name)
@@ -640,7 +575,7 @@ DECLARE_EVENT_CLASS(nfs_directory_event_done,
TP_printk(
"error=%ld (%s) name=%02x:%02x:%llu/%s",
- -__entry->error, nfs_show_status(__entry->error),
+ -__entry->error, show_nfs_status(__entry->error),
MAJOR(__entry->dev), MINOR(__entry->dev),
(unsigned long long)__entry->dir,
__get_str(name)
@@ -730,7 +665,7 @@ TRACE_EVENT(nfs_link_exit,
TP_printk(
"error=%ld (%s) fileid=%02x:%02x:%llu name=%02x:%02x:%llu/%s",
- -__entry->error, nfs_show_status(__entry->error),
+ -__entry->error, show_nfs_status(__entry->error),
MAJOR(__entry->dev), MINOR(__entry->dev),
__entry->fileid,
MAJOR(__entry->dev), MINOR(__entry->dev),
@@ -817,7 +752,7 @@ DECLARE_EVENT_CLASS(nfs_rename_event_done,
TP_printk(
"error=%ld (%s) old_name=%02x:%02x:%llu/%s "
"new_name=%02x:%02x:%llu/%s",
- -__entry->error, nfs_show_status(__entry->error),
+ -__entry->error, show_nfs_status(__entry->error),
MAJOR(__entry->dev), MINOR(__entry->dev),
(unsigned long long)__entry->old_dir,
__get_str(old_name),
@@ -871,13 +806,163 @@ TRACE_EVENT(nfs_sillyrename_unlink,
TP_printk(
"error=%ld (%s) name=%02x:%02x:%llu/%s",
- -__entry->error, nfs_show_status(__entry->error),
+ -__entry->error, show_nfs_status(__entry->error),
MAJOR(__entry->dev), MINOR(__entry->dev),
(unsigned long long)__entry->dir,
__get_str(name)
)
);
+TRACE_EVENT(nfs_aop_readpage,
+ TP_PROTO(
+ const struct inode *inode,
+ struct page *page
+ ),
+
+ TP_ARGS(inode, page),
+
+ TP_STRUCT__entry(
+ __field(dev_t, dev)
+ __field(u32, fhandle)
+ __field(u64, fileid)
+ __field(u64, version)
+ __field(loff_t, offset)
+ ),
+
+ TP_fast_assign(
+ const struct nfs_inode *nfsi = NFS_I(inode);
+
+ __entry->dev = inode->i_sb->s_dev;
+ __entry->fileid = nfsi->fileid;
+ __entry->fhandle = nfs_fhandle_hash(&nfsi->fh);
+ __entry->version = inode_peek_iversion_raw(inode);
+ __entry->offset = page_index(page) << PAGE_SHIFT;
+ ),
+
+ TP_printk(
+ "fileid=%02x:%02x:%llu fhandle=0x%08x version=%llu offset=%lld",
+ MAJOR(__entry->dev), MINOR(__entry->dev),
+ (unsigned long long)__entry->fileid,
+ __entry->fhandle, __entry->version,
+ __entry->offset
+ )
+);
+
+TRACE_EVENT(nfs_aop_readpage_done,
+ TP_PROTO(
+ const struct inode *inode,
+ struct page *page,
+ int ret
+ ),
+
+ TP_ARGS(inode, page, ret),
+
+ TP_STRUCT__entry(
+ __field(dev_t, dev)
+ __field(u32, fhandle)
+ __field(int, ret)
+ __field(u64, fileid)
+ __field(u64, version)
+ __field(loff_t, offset)
+ ),
+
+ TP_fast_assign(
+ const struct nfs_inode *nfsi = NFS_I(inode);
+
+ __entry->dev = inode->i_sb->s_dev;
+ __entry->fileid = nfsi->fileid;
+ __entry->fhandle = nfs_fhandle_hash(&nfsi->fh);
+ __entry->version = inode_peek_iversion_raw(inode);
+ __entry->offset = page_index(page) << PAGE_SHIFT;
+ __entry->ret = ret;
+ ),
+
+ TP_printk(
+ "fileid=%02x:%02x:%llu fhandle=0x%08x version=%llu offset=%lld ret=%d",
+ MAJOR(__entry->dev), MINOR(__entry->dev),
+ (unsigned long long)__entry->fileid,
+ __entry->fhandle, __entry->version,
+ __entry->offset, __entry->ret
+ )
+);
+
+TRACE_EVENT(nfs_aop_readahead,
+ TP_PROTO(
+ const struct inode *inode,
+ struct page *page,
+ unsigned int nr_pages
+ ),
+
+ TP_ARGS(inode, page, nr_pages),
+
+ TP_STRUCT__entry(
+ __field(dev_t, dev)
+ __field(u32, fhandle)
+ __field(u64, fileid)
+ __field(u64, version)
+ __field(loff_t, offset)
+ __field(unsigned int, nr_pages)
+ ),
+
+ TP_fast_assign(
+ const struct nfs_inode *nfsi = NFS_I(inode);
+
+ __entry->dev = inode->i_sb->s_dev;
+ __entry->fileid = nfsi->fileid;
+ __entry->fhandle = nfs_fhandle_hash(&nfsi->fh);
+ __entry->version = inode_peek_iversion_raw(inode);
+ __entry->offset = page_index(page) << PAGE_SHIFT;
+ __entry->nr_pages = nr_pages;
+ ),
+
+ TP_printk(
+ "fileid=%02x:%02x:%llu fhandle=0x%08x version=%llu offset=%lld nr_pages=%u",
+ MAJOR(__entry->dev), MINOR(__entry->dev),
+ (unsigned long long)__entry->fileid,
+ __entry->fhandle, __entry->version,
+ __entry->offset, __entry->nr_pages
+ )
+);
+
+TRACE_EVENT(nfs_aop_readahead_done,
+ TP_PROTO(
+ const struct inode *inode,
+ unsigned int nr_pages,
+ int ret
+ ),
+
+ TP_ARGS(inode, nr_pages, ret),
+
+ TP_STRUCT__entry(
+ __field(dev_t, dev)
+ __field(u32, fhandle)
+ __field(int, ret)
+ __field(u64, fileid)
+ __field(u64, version)
+ __field(loff_t, offset)
+ __field(unsigned int, nr_pages)
+ ),
+
+ TP_fast_assign(
+ const struct nfs_inode *nfsi = NFS_I(inode);
+
+ __entry->dev = inode->i_sb->s_dev;
+ __entry->fileid = nfsi->fileid;
+ __entry->fhandle = nfs_fhandle_hash(&nfsi->fh);
+ __entry->version = inode_peek_iversion_raw(inode);
+ __entry->nr_pages = nr_pages;
+ __entry->ret = ret;
+ ),
+
+ TP_printk(
+ "fileid=%02x:%02x:%llu fhandle=0x%08x version=%llu nr_pages=%u ret=%d",
+ MAJOR(__entry->dev), MINOR(__entry->dev),
+ (unsigned long long)__entry->fileid,
+ __entry->fhandle, __entry->version,
+ __entry->nr_pages, __entry->ret
+ )
+);
+
TRACE_EVENT(nfs_initiate_read,
TP_PROTO(
const struct nfs_pgio_header *hdr
@@ -1054,16 +1139,6 @@ TRACE_EVENT(nfs_pgio_error,
)
);
-TRACE_DEFINE_ENUM(NFS_UNSTABLE);
-TRACE_DEFINE_ENUM(NFS_DATA_SYNC);
-TRACE_DEFINE_ENUM(NFS_FILE_SYNC);
-
-#define nfs_show_stable(stable) \
- __print_symbolic(stable, \
- { NFS_UNSTABLE, "UNSTABLE" }, \
- { NFS_DATA_SYNC, "DATA_SYNC" }, \
- { NFS_FILE_SYNC, "FILE_SYNC" })
-
TRACE_EVENT(nfs_initiate_write,
TP_PROTO(
const struct nfs_pgio_header *hdr
@@ -1077,7 +1152,7 @@ TRACE_EVENT(nfs_initiate_write,
__field(u64, fileid)
__field(loff_t, offset)
__field(u32, count)
- __field(enum nfs3_stable_how, stable)
+ __field(unsigned long, stable)
),
TP_fast_assign(
@@ -1101,7 +1176,7 @@ TRACE_EVENT(nfs_initiate_write,
(unsigned long long)__entry->fileid,
__entry->fhandle,
(long long)__entry->offset, __entry->count,
- nfs_show_stable(__entry->stable)
+ show_nfs_stable_how(__entry->stable)
)
);
@@ -1121,7 +1196,7 @@ TRACE_EVENT(nfs_writeback_done,
__field(u32, arg_count)
__field(u32, res_count)
__field(int, status)
- __field(enum nfs3_stable_how, stable)
+ __field(unsigned long, stable)
__array(char, verifier, NFS4_VERIFIER_SIZE)
),
@@ -1154,8 +1229,8 @@ TRACE_EVENT(nfs_writeback_done,
__entry->fhandle,
(long long)__entry->offset, __entry->arg_count,
__entry->res_count, __entry->status,
- nfs_show_stable(__entry->stable),
- __print_hex_str(__entry->verifier, NFS4_VERIFIER_SIZE)
+ show_nfs_stable_how(__entry->stable),
+ show_nfs4_verifier(__entry->verifier)
)
);
@@ -1256,7 +1331,7 @@ TRACE_EVENT(nfs_commit_done,
__field(u64, fileid)
__field(loff_t, offset)
__field(int, status)
- __field(enum nfs3_stable_how, stable)
+ __field(unsigned long, stable)
__array(char, verifier, NFS4_VERIFIER_SIZE)
),
@@ -1285,8 +1360,8 @@ TRACE_EVENT(nfs_commit_done,
(unsigned long long)__entry->fileid,
__entry->fhandle,
(long long)__entry->offset, __entry->status,
- nfs_show_stable(__entry->stable),
- __print_hex_str(__entry->verifier, NFS4_VERIFIER_SIZE)
+ show_nfs_stable_how(__entry->stable),
+ show_nfs4_verifier(__entry->verifier)
)
);
@@ -1323,76 +1398,6 @@ TRACE_EVENT(nfs_fh_to_dentry,
)
);
-TRACE_DEFINE_ENUM(NFS_OK);
-TRACE_DEFINE_ENUM(NFSERR_PERM);
-TRACE_DEFINE_ENUM(NFSERR_NOENT);
-TRACE_DEFINE_ENUM(NFSERR_IO);
-TRACE_DEFINE_ENUM(NFSERR_NXIO);
-TRACE_DEFINE_ENUM(ECHILD);
-TRACE_DEFINE_ENUM(NFSERR_EAGAIN);
-TRACE_DEFINE_ENUM(NFSERR_ACCES);
-TRACE_DEFINE_ENUM(NFSERR_EXIST);
-TRACE_DEFINE_ENUM(NFSERR_XDEV);
-TRACE_DEFINE_ENUM(NFSERR_NODEV);
-TRACE_DEFINE_ENUM(NFSERR_NOTDIR);
-TRACE_DEFINE_ENUM(NFSERR_ISDIR);
-TRACE_DEFINE_ENUM(NFSERR_INVAL);
-TRACE_DEFINE_ENUM(NFSERR_FBIG);
-TRACE_DEFINE_ENUM(NFSERR_NOSPC);
-TRACE_DEFINE_ENUM(NFSERR_ROFS);
-TRACE_DEFINE_ENUM(NFSERR_MLINK);
-TRACE_DEFINE_ENUM(NFSERR_OPNOTSUPP);
-TRACE_DEFINE_ENUM(NFSERR_NAMETOOLONG);
-TRACE_DEFINE_ENUM(NFSERR_NOTEMPTY);
-TRACE_DEFINE_ENUM(NFSERR_DQUOT);
-TRACE_DEFINE_ENUM(NFSERR_STALE);
-TRACE_DEFINE_ENUM(NFSERR_REMOTE);
-TRACE_DEFINE_ENUM(NFSERR_WFLUSH);
-TRACE_DEFINE_ENUM(NFSERR_BADHANDLE);
-TRACE_DEFINE_ENUM(NFSERR_NOT_SYNC);
-TRACE_DEFINE_ENUM(NFSERR_BAD_COOKIE);
-TRACE_DEFINE_ENUM(NFSERR_NOTSUPP);
-TRACE_DEFINE_ENUM(NFSERR_TOOSMALL);
-TRACE_DEFINE_ENUM(NFSERR_SERVERFAULT);
-TRACE_DEFINE_ENUM(NFSERR_BADTYPE);
-TRACE_DEFINE_ENUM(NFSERR_JUKEBOX);
-
-#define nfs_show_status(x) \
- __print_symbolic(x, \
- { NFS_OK, "OK" }, \
- { NFSERR_PERM, "PERM" }, \
- { NFSERR_NOENT, "NOENT" }, \
- { NFSERR_IO, "IO" }, \
- { NFSERR_NXIO, "NXIO" }, \
- { ECHILD, "CHILD" }, \
- { NFSERR_EAGAIN, "AGAIN" }, \
- { NFSERR_ACCES, "ACCES" }, \
- { NFSERR_EXIST, "EXIST" }, \
- { NFSERR_XDEV, "XDEV" }, \
- { NFSERR_NODEV, "NODEV" }, \
- { NFSERR_NOTDIR, "NOTDIR" }, \
- { NFSERR_ISDIR, "ISDIR" }, \
- { NFSERR_INVAL, "INVAL" }, \
- { NFSERR_FBIG, "FBIG" }, \
- { NFSERR_NOSPC, "NOSPC" }, \
- { NFSERR_ROFS, "ROFS" }, \
- { NFSERR_MLINK, "MLINK" }, \
- { NFSERR_OPNOTSUPP, "OPNOTSUPP" }, \
- { NFSERR_NAMETOOLONG, "NAMETOOLONG" }, \
- { NFSERR_NOTEMPTY, "NOTEMPTY" }, \
- { NFSERR_DQUOT, "DQUOT" }, \
- { NFSERR_STALE, "STALE" }, \
- { NFSERR_REMOTE, "REMOTE" }, \
- { NFSERR_WFLUSH, "WFLUSH" }, \
- { NFSERR_BADHANDLE, "BADHANDLE" }, \
- { NFSERR_NOT_SYNC, "NOTSYNC" }, \
- { NFSERR_BAD_COOKIE, "BADCOOKIE" }, \
- { NFSERR_NOTSUPP, "NOTSUPP" }, \
- { NFSERR_TOOSMALL, "TOOSMALL" }, \
- { NFSERR_SERVERFAULT, "REMOTEIO" }, \
- { NFSERR_BADTYPE, "BADTYPE" }, \
- { NFSERR_JUKEBOX, "JUKEBOX" })
-
DECLARE_EVENT_CLASS(nfs_xdr_event,
TP_PROTO(
const struct xdr_stream *xdr,
@@ -1427,12 +1432,12 @@ DECLARE_EVENT_CLASS(nfs_xdr_event,
__assign_str(procedure, task->tk_msg.rpc_proc->p_name);
),
- TP_printk(
- "task:%u@%d xid=0x%08x %sv%d %s error=%ld (%s)",
+ TP_printk(SUNRPC_TRACE_TASK_SPECIFIER
+ " xid=0x%08x %sv%d %s error=%ld (%s)",
__entry->task_id, __entry->client_id, __entry->xid,
__get_str(program), __entry->version,
__get_str(procedure), -__entry->error,
- nfs_show_status(__entry->error)
+ show_nfs_status(__entry->error)
)
);
#define DEFINE_NFS_XDR_EVENT(name) \
diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c
index cc232d1f16f2..ad7f83dc9a2d 100644
--- a/fs/nfs/pagelist.c
+++ b/fs/nfs/pagelist.c
@@ -271,8 +271,7 @@ nfs_page_set_headlock(struct nfs_page *req)
void
nfs_page_clear_headlock(struct nfs_page *req)
{
- smp_mb__before_atomic();
- clear_bit(PG_HEADLOCK, &req->wb_flags);
+ clear_bit_unlock(PG_HEADLOCK, &req->wb_flags);
smp_mb__after_atomic();
if (!test_bit(PG_CONTENDED1, &req->wb_flags))
return;
@@ -525,12 +524,7 @@ nfs_create_subreq(struct nfs_page *req,
*/
void nfs_unlock_request(struct nfs_page *req)
{
- if (!NFS_WBACK_BUSY(req)) {
- printk(KERN_ERR "NFS: Invalid unlock attempted\n");
- BUG();
- }
- smp_mb__before_atomic();
- clear_bit(PG_BUSY, &req->wb_flags);
+ clear_bit_unlock(PG_BUSY, &req->wb_flags);
smp_mb__after_atomic();
if (!test_bit(PG_CONTENDED2, &req->wb_flags))
return;
@@ -870,9 +864,6 @@ static void nfs_pgio_result(struct rpc_task *task, void *calldata)
struct nfs_pgio_header *hdr = calldata;
struct inode *inode = hdr->inode;
- dprintk("NFS: %s: %5u, (status %d)\n", __func__,
- task->tk_pid, task->tk_status);
-
if (hdr->rw_ops->rw_done(task, hdr, inode) != 0)
return;
if (task->tk_status < 0)
diff --git a/fs/nfs/pnfs.h b/fs/nfs/pnfs.h
index d810ae674f4e..f4d7548d67b2 100644
--- a/fs/nfs/pnfs.h
+++ b/fs/nfs/pnfs.h
@@ -82,10 +82,6 @@ enum pnfs_try_status {
PNFS_TRY_AGAIN = 2,
};
-/* error codes for internal use */
-#define NFS4ERR_RESET_TO_MDS 12001
-#define NFS4ERR_RESET_TO_PNFS 12002
-
#ifdef CONFIG_NFS_V4_1
#define LAYOUT_NFSV4_1_MODULE_PREFIX "nfs-layouttype4"
@@ -517,7 +513,7 @@ pnfs_mark_request_commit(struct nfs_page *req, struct pnfs_layout_segment *lseg,
{
struct pnfs_ds_commit_info *fl_cinfo = cinfo->ds;
- if (!lseg || !fl_cinfo->ops->mark_request_commit)
+ if (!lseg || !fl_cinfo->ops || !fl_cinfo->ops->mark_request_commit)
return false;
fl_cinfo->ops->mark_request_commit(req, lseg, cinfo, ds_commit_idx);
return true;
diff --git a/fs/nfs/pnfs_nfs.c b/fs/nfs/pnfs_nfs.c
index cf19914fec81..316f68f96e57 100644
--- a/fs/nfs/pnfs_nfs.c
+++ b/fs/nfs/pnfs_nfs.c
@@ -468,7 +468,6 @@ pnfs_bucket_alloc_ds_commits(struct list_head *list,
goto out_error;
data->ds_commit_index = i;
list_add_tail(&data->list, list);
- atomic_inc(&cinfo->mds->rpcs_out);
nreq++;
}
mutex_unlock(&NFS_I(cinfo->inode)->commit_mutex);
@@ -520,7 +519,6 @@ pnfs_generic_commit_pagelist(struct inode *inode, struct list_head *mds_pages,
data->ds_commit_index = -1;
list_splice_init(mds_pages, &data->pages);
list_add_tail(&data->list, &list);
- atomic_inc(&cinfo->mds->rpcs_out);
nreq++;
}
@@ -895,7 +893,7 @@ static int _nfs4_pnfs_v3_ds_connect(struct nfs_server *mds_srv,
}
smp_wmb();
- ds->ds_clp = clp;
+ WRITE_ONCE(ds->ds_clp, clp);
dprintk("%s [new] addr: %s\n", __func__, ds->ds_remotestr);
out:
return status;
@@ -973,7 +971,7 @@ static int _nfs4_pnfs_v4_ds_connect(struct nfs_server *mds_srv,
}
smp_wmb();
- ds->ds_clp = clp;
+ WRITE_ONCE(ds->ds_clp, clp);
dprintk("%s [new] addr: %s\n", __func__, ds->ds_remotestr);
out:
return status;
diff --git a/fs/nfs/proc.c b/fs/nfs/proc.c
index ea19dbf12301..73dcaa99fa9b 100644
--- a/fs/nfs/proc.c
+++ b/fs/nfs/proc.c
@@ -91,7 +91,7 @@ nfs_proc_get_root(struct nfs_server *server, struct nfs_fh *fhandle,
info->dtpref = fsinfo.tsize;
info->maxfilesize = 0x7FFFFFFF;
info->lease_time = 0;
- info->change_attr_type = NFS4_CHANGE_TYPE_IS_TIME_METADATA;
+ info->change_attr_type = NFS4_CHANGE_TYPE_IS_UNDEFINED;
return 0;
}
@@ -100,8 +100,7 @@ nfs_proc_get_root(struct nfs_server *server, struct nfs_fh *fhandle,
*/
static int
nfs_proc_getattr(struct nfs_server *server, struct nfs_fh *fhandle,
- struct nfs_fattr *fattr, struct nfs4_label *label,
- struct inode *inode)
+ struct nfs_fattr *fattr, struct inode *inode)
{
struct rpc_message msg = {
.rpc_proc = &nfs_procedures[NFSPROC_GETATTR],
@@ -154,8 +153,7 @@ nfs_proc_setattr(struct dentry *dentry, struct nfs_fattr *fattr,
static int
nfs_proc_lookup(struct inode *dir, struct dentry *dentry,
- struct nfs_fh *fhandle, struct nfs_fattr *fattr,
- struct nfs4_label *label)
+ struct nfs_fh *fhandle, struct nfs_fattr *fattr)
{
struct nfs_diropargs arg = {
.fh = NFS_FH(dir),
@@ -257,7 +255,7 @@ nfs_proc_create(struct inode *dir, struct dentry *dentry, struct iattr *sattr,
status = rpc_call_sync(NFS_CLIENT(dir), &msg, 0);
nfs_mark_for_revalidate(dir);
if (status == 0)
- status = nfs_instantiate(dentry, data->res.fh, data->res.fattr, NULL);
+ status = nfs_instantiate(dentry, data->res.fh, data->res.fattr);
nfs_free_createdata(data);
out:
dprintk("NFS reply create: %d\n", status);
@@ -304,7 +302,7 @@ nfs_proc_mknod(struct inode *dir, struct dentry *dentry, struct iattr *sattr,
status = rpc_call_sync(NFS_CLIENT(dir), &msg, 0);
}
if (status == 0)
- status = nfs_instantiate(dentry, data->res.fh, data->res.fattr, NULL);
+ status = nfs_instantiate(dentry, data->res.fh, data->res.fattr);
nfs_free_createdata(data);
out:
dprintk("NFS reply mknod: %d\n", status);
@@ -436,7 +434,7 @@ nfs_proc_symlink(struct inode *dir, struct dentry *dentry, struct page *page,
* should fill in the data with a LOOKUP call on the wire.
*/
if (status == 0)
- status = nfs_instantiate(dentry, fh, fattr, NULL);
+ status = nfs_instantiate(dentry, fh, fattr);
out_free:
nfs_free_fattr(fattr);
@@ -465,7 +463,7 @@ nfs_proc_mkdir(struct inode *dir, struct dentry *dentry, struct iattr *sattr)
status = rpc_call_sync(NFS_CLIENT(dir), &msg, 0);
nfs_mark_for_revalidate(dir);
if (status == 0)
- status = nfs_instantiate(dentry, data->res.fh, data->res.fattr, NULL);
+ status = nfs_instantiate(dentry, data->res.fh, data->res.fattr);
nfs_free_createdata(data);
out:
dprintk("NFS reply mkdir: %d\n", status);
diff --git a/fs/nfs/read.c b/fs/nfs/read.c
index 08d6cc57cbc3..d11af2a9299c 100644
--- a/fs/nfs/read.c
+++ b/fs/nfs/read.c
@@ -337,8 +337,7 @@ int nfs_readpage(struct file *file, struct page *page)
struct inode *inode = page_file_mapping(page)->host;
int ret;
- dprintk("NFS: nfs_readpage (%p %ld@%lu)\n",
- page, PAGE_SIZE, page_index(page));
+ trace_nfs_aop_readpage(inode, page);
nfs_inc_stats(inode, NFSIOS_VFSREADPAGE);
/*
@@ -390,9 +389,11 @@ out_wait:
}
out:
put_nfs_open_context(desc.ctx);
+ trace_nfs_aop_readpage_done(inode, page, ret);
return ret;
out_unlock:
unlock_page(page);
+ trace_nfs_aop_readpage_done(inode, page, ret);
return ret;
}
@@ -403,10 +404,7 @@ int nfs_readpages(struct file *file, struct address_space *mapping,
struct inode *inode = mapping->host;
int ret;
- dprintk("NFS: nfs_readpages (%s/%Lu %d)\n",
- inode->i_sb->s_id,
- (unsigned long long)NFS_FILEID(inode),
- nr_pages);
+ trace_nfs_aop_readahead(inode, lru_to_page(pages), nr_pages);
nfs_inc_stats(inode, NFSIOS_VFSREADPAGES);
ret = -ESTALE;
@@ -439,6 +437,7 @@ int nfs_readpages(struct file *file, struct address_space *mapping,
read_complete:
put_nfs_open_context(desc.ctx);
out:
+ trace_nfs_aop_readahead_done(inode, nr_pages, ret);
return ret;
}
diff --git a/fs/nfs/super.c b/fs/nfs/super.c
index e65c83494c05..3aced401735c 100644
--- a/fs/nfs/super.c
+++ b/fs/nfs/super.c
@@ -1004,6 +1004,7 @@ int nfs_reconfigure(struct fs_context *fc)
struct nfs_fs_context *ctx = nfs_fc2context(fc);
struct super_block *sb = fc->root->d_sb;
struct nfs_server *nfss = sb->s_fs_info;
+ int ret;
sync_filesystem(sb);
@@ -1028,7 +1029,11 @@ int nfs_reconfigure(struct fs_context *fc)
}
/* compare new mount options with old ones */
- return nfs_compare_remount_data(nfss, ctx);
+ ret = nfs_compare_remount_data(nfss, ctx);
+ if (ret)
+ return ret;
+
+ return nfs_probe_server(nfss, NFS_FH(d_inode(fc->root)));
}
EXPORT_SYMBOL_GPL(nfs_reconfigure);
diff --git a/fs/nfs/write.c b/fs/nfs/write.c
index eae9bf114041..9b7619ce17a7 100644
--- a/fs/nfs/write.c
+++ b/fs/nfs/write.c
@@ -288,6 +288,7 @@ static void nfs_grow_file(struct page *page, unsigned int offset, unsigned int c
end = page_file_offset(page) + ((loff_t)offset+count);
if (i_size >= end)
goto out;
+ trace_nfs_size_grow(inode, end);
i_size_write(inode, end);
NFS_I(inode)->cache_validity &= ~NFS_INO_INVALID_SIZE;
nfs_inc_stats(inode, NFSIOS_EXTENDWRITE);
@@ -1038,25 +1039,11 @@ nfs_scan_commit_list(struct list_head *src, struct list_head *dst,
struct nfs_page *req, *tmp;
int ret = 0;
-restart:
list_for_each_entry_safe(req, tmp, src, wb_list) {
kref_get(&req->wb_kref);
if (!nfs_lock_request(req)) {
- int status;
-
- /* Prevent deadlock with nfs_lock_and_join_requests */
- if (!list_empty(dst)) {
- nfs_release_request(req);
- continue;
- }
- /* Ensure we make progress to prevent livelock */
- mutex_unlock(&NFS_I(cinfo->inode)->commit_mutex);
- status = nfs_wait_on_request(req);
nfs_release_request(req);
- mutex_lock(&NFS_I(cinfo->inode)->commit_mutex);
- if (status < 0)
- break;
- goto restart;
+ continue;
}
nfs_request_remove_commit_list(req, cinfo);
clear_bit(PG_COMMIT_TO_DS, &req->wb_flags);
@@ -1246,7 +1233,7 @@ nfs_key_timeout_notify(struct file *filp, struct inode *inode)
struct nfs_open_context *ctx = nfs_file_open_context(filp);
if (nfs_ctx_key_to_expire(ctx, inode) &&
- !ctx->ll_cred)
+ !rcu_access_pointer(ctx->ll_cred))
/* Already expired! */
return -EACCES;
return 0;
@@ -1258,23 +1245,38 @@ nfs_key_timeout_notify(struct file *filp, struct inode *inode)
bool nfs_ctx_key_to_expire(struct nfs_open_context *ctx, struct inode *inode)
{
struct rpc_auth *auth = NFS_SERVER(inode)->client->cl_auth;
- struct rpc_cred *cred = ctx->ll_cred;
+ struct rpc_cred *cred, *new, *old = NULL;
struct auth_cred acred = {
.cred = ctx->cred,
};
+ bool ret = false;
- if (cred && !cred->cr_ops->crmatch(&acred, cred, 0)) {
- put_rpccred(cred);
- ctx->ll_cred = NULL;
- cred = NULL;
- }
- if (!cred)
- cred = auth->au_ops->lookup_cred(auth, &acred, 0);
- if (!cred || IS_ERR(cred))
+ rcu_read_lock();
+ cred = rcu_dereference(ctx->ll_cred);
+ if (cred && !(cred->cr_ops->crkey_timeout &&
+ cred->cr_ops->crkey_timeout(cred)))
+ goto out;
+ rcu_read_unlock();
+
+ new = auth->au_ops->lookup_cred(auth, &acred, 0);
+ if (new == cred) {
+ put_rpccred(new);
return true;
- ctx->ll_cred = cred;
- return !!(cred->cr_ops->crkey_timeout &&
- cred->cr_ops->crkey_timeout(cred));
+ }
+ if (IS_ERR_OR_NULL(new)) {
+ new = NULL;
+ ret = true;
+ } else if (new->cr_ops->crkey_timeout &&
+ new->cr_ops->crkey_timeout(new))
+ ret = true;
+
+ rcu_read_lock();
+ old = rcu_dereference_protected(xchg(&ctx->ll_cred,
+ RCU_INITIALIZER(new)), 1);
+out:
+ rcu_read_unlock();
+ put_rpccred(old);
+ return ret;
}
/*
@@ -1382,8 +1384,6 @@ int nfs_updatepage(struct file *file, struct page *page,
status = nfs_writepage_setup(ctx, page, offset, count);
if (status < 0)
nfs_set_pageerror(mapping);
- else
- __set_page_dirty_nobuffers(page);
out:
dprintk("NFS: nfs_updatepage returns %d (isize %lld)\n",
status, (long long)i_size_read(inode));
@@ -1671,10 +1671,13 @@ static void nfs_commit_begin(struct nfs_mds_commit_info *cinfo)
atomic_inc(&cinfo->rpcs_out);
}
-static void nfs_commit_end(struct nfs_mds_commit_info *cinfo)
+bool nfs_commit_end(struct nfs_mds_commit_info *cinfo)
{
- if (atomic_dec_and_test(&cinfo->rpcs_out))
+ if (atomic_dec_and_test(&cinfo->rpcs_out)) {
wake_up_var(&cinfo->rpcs_out);
+ return true;
+ }
+ return false;
}
void nfs_commitdata_release(struct nfs_commit_data *data)
@@ -1774,6 +1777,7 @@ void nfs_init_commit(struct nfs_commit_data *data,
data->res.fattr = &data->fattr;
data->res.verf = &data->verf;
nfs_fattr_init(&data->fattr);
+ nfs_commit_begin(cinfo->mds);
}
EXPORT_SYMBOL_GPL(nfs_init_commit);
@@ -1820,7 +1824,6 @@ nfs_commit_list(struct inode *inode, struct list_head *head, int how,
/* Set up the argument struct */
nfs_init_commit(data, head, NULL, cinfo);
- atomic_inc(&cinfo->mds->rpcs_out);
if (NFS_SERVER(inode)->nfs_client->cl_minorversion)
task_flags = RPC_TASK_MOVEABLE;
return nfs_initiate_commit(NFS_CLIENT(inode), data, NFS_PROTO(inode),
@@ -1835,9 +1838,6 @@ static void nfs_commit_done(struct rpc_task *task, void *calldata)
{
struct nfs_commit_data *data = calldata;
- dprintk("NFS: %5u nfs_commit_done (status %d)\n",
- task->tk_pid, task->tk_status);
-
/* Call the NFS version-specific code */
NFS_PROTO(data->inode)->commit_done(task, data);
trace_nfs_commit_done(task, data);
@@ -1936,6 +1936,7 @@ static int __nfs_commit_inode(struct inode *inode, int how,
int may_wait = how & FLUSH_SYNC;
int ret, nscan;
+ how &= ~FLUSH_SYNC;
nfs_init_cinfo_from_inode(&cinfo, inode);
nfs_commit_begin(cinfo.mds);
for (;;) {
diff --git a/fs/nfsd/filecache.c b/fs/nfsd/filecache.c
index be3c1aad50ea..fdf89fcf1a0c 100644
--- a/fs/nfsd/filecache.c
+++ b/fs/nfsd/filecache.c
@@ -602,6 +602,9 @@ nfsd_file_fsnotify_handle_event(struct fsnotify_mark *mark, u32 mask,
struct inode *inode, struct inode *dir,
const struct qstr *name, u32 cookie)
{
+ if (WARN_ON_ONCE(!inode))
+ return 0;
+
trace_nfsd_file_fsnotify_handle_event(inode, mask);
/* Should be no marks on non-regular files */
diff --git a/fs/nfsd/flexfilelayout.c b/fs/nfsd/flexfilelayout.c
index db7ef07ae50c..2e2f1d5e9f62 100644
--- a/fs/nfsd/flexfilelayout.c
+++ b/fs/nfsd/flexfilelayout.c
@@ -61,7 +61,7 @@ nfsd4_ff_proc_layoutget(struct inode *inode, const struct svc_fh *fhp,
goto out_error;
fl->fh.size = fhp->fh_handle.fh_size;
- memcpy(fl->fh.data, &fhp->fh_handle.fh_base, fl->fh.size);
+ memcpy(fl->fh.data, &fhp->fh_handle.fh_raw, fl->fh.size);
/* Give whole file layout segments */
seg->offset = 0;
diff --git a/fs/nfsd/lockd.c b/fs/nfsd/lockd.c
index 606fa155c28a..46a7f9b813e5 100644
--- a/fs/nfsd/lockd.c
+++ b/fs/nfsd/lockd.c
@@ -35,7 +35,7 @@ nlm_fopen(struct svc_rqst *rqstp, struct nfs_fh *f, struct file **filp,
/* must initialize before using! but maxsize doesn't matter */
fh_init(&fh,0);
fh.fh_handle.fh_size = f->size;
- memcpy((char*)&fh.fh_handle.fh_base, f->data, f->size);
+ memcpy(&fh.fh_handle.fh_raw, f->data, f->size);
fh.fh_export = NULL;
access = (mode == O_WRONLY) ? NFSD_MAY_WRITE : NFSD_MAY_READ;
diff --git a/fs/nfsd/nfs2acl.c b/fs/nfsd/nfs2acl.c
index 4b43929c1f25..367551bddfc6 100644
--- a/fs/nfsd/nfs2acl.c
+++ b/fs/nfsd/nfs2acl.c
@@ -188,51 +188,51 @@ out:
* XDR decode functions
*/
-static int nfsaclsvc_decode_getaclargs(struct svc_rqst *rqstp, __be32 *p)
+static bool
+nfsaclsvc_decode_getaclargs(struct svc_rqst *rqstp, struct xdr_stream *xdr)
{
- struct xdr_stream *xdr = &rqstp->rq_arg_stream;
struct nfsd3_getaclargs *argp = rqstp->rq_argp;
if (!svcxdr_decode_fhandle(xdr, &argp->fh))
- return 0;
+ return false;
if (xdr_stream_decode_u32(xdr, &argp->mask) < 0)
- return 0;
+ return false;
- return 1;
+ return true;
}
-static int nfsaclsvc_decode_setaclargs(struct svc_rqst *rqstp, __be32 *p)
+static bool
+nfsaclsvc_decode_setaclargs(struct svc_rqst *rqstp, struct xdr_stream *xdr)
{
- struct xdr_stream *xdr = &rqstp->rq_arg_stream;
struct nfsd3_setaclargs *argp = rqstp->rq_argp;
if (!svcxdr_decode_fhandle(xdr, &argp->fh))
- return 0;
+ return false;
if (xdr_stream_decode_u32(xdr, &argp->mask) < 0)
- return 0;
+ return false;
if (argp->mask & ~NFS_ACL_MASK)
- return 0;
+ return false;
if (!nfs_stream_decode_acl(xdr, NULL, (argp->mask & NFS_ACL) ?
&argp->acl_access : NULL))
- return 0;
+ return false;
if (!nfs_stream_decode_acl(xdr, NULL, (argp->mask & NFS_DFACL) ?
&argp->acl_default : NULL))
- return 0;
+ return false;
- return 1;
+ return true;
}
-static int nfsaclsvc_decode_accessargs(struct svc_rqst *rqstp, __be32 *p)
+static bool
+nfsaclsvc_decode_accessargs(struct svc_rqst *rqstp, struct xdr_stream *xdr)
{
- struct xdr_stream *xdr = &rqstp->rq_arg_stream;
struct nfsd3_accessargs *args = rqstp->rq_argp;
if (!svcxdr_decode_fhandle(xdr, &args->fh))
- return 0;
+ return false;
if (xdr_stream_decode_u32(xdr, &args->access) < 0)
- return 0;
+ return false;
- return 1;
+ return true;
}
/*
@@ -240,9 +240,9 @@ static int nfsaclsvc_decode_accessargs(struct svc_rqst *rqstp, __be32 *p)
*/
/* GETACL */
-static int nfsaclsvc_encode_getaclres(struct svc_rqst *rqstp, __be32 *p)
+static bool
+nfsaclsvc_encode_getaclres(struct svc_rqst *rqstp, struct xdr_stream *xdr)
{
- struct xdr_stream *xdr = &rqstp->rq_res_stream;
struct nfsd3_getaclres *resp = rqstp->rq_resp;
struct dentry *dentry = resp->fh.fh_dentry;
struct inode *inode;
@@ -280,9 +280,9 @@ static int nfsaclsvc_encode_getaclres(struct svc_rqst *rqstp, __be32 *p)
}
/* ACCESS */
-static int nfsaclsvc_encode_accessres(struct svc_rqst *rqstp, __be32 *p)
+static bool
+nfsaclsvc_encode_accessres(struct svc_rqst *rqstp, struct xdr_stream *xdr)
{
- struct xdr_stream *xdr = &rqstp->rq_res_stream;
struct nfsd3_accessres *resp = rqstp->rq_resp;
if (!svcxdr_encode_stat(xdr, resp->status))
diff --git a/fs/nfsd/nfs3acl.c b/fs/nfsd/nfs3acl.c
index 5dfe7644a517..35b2ebda14da 100644
--- a/fs/nfsd/nfs3acl.c
+++ b/fs/nfsd/nfs3acl.c
@@ -127,38 +127,38 @@ out:
* XDR decode functions
*/
-static int nfs3svc_decode_getaclargs(struct svc_rqst *rqstp, __be32 *p)
+static bool
+nfs3svc_decode_getaclargs(struct svc_rqst *rqstp, struct xdr_stream *xdr)
{
- struct xdr_stream *xdr = &rqstp->rq_arg_stream;
struct nfsd3_getaclargs *args = rqstp->rq_argp;
if (!svcxdr_decode_nfs_fh3(xdr, &args->fh))
- return 0;
+ return false;
if (xdr_stream_decode_u32(xdr, &args->mask) < 0)
- return 0;
+ return false;
- return 1;
+ return true;
}
-static int nfs3svc_decode_setaclargs(struct svc_rqst *rqstp, __be32 *p)
+static bool
+nfs3svc_decode_setaclargs(struct svc_rqst *rqstp, struct xdr_stream *xdr)
{
- struct xdr_stream *xdr = &rqstp->rq_arg_stream;
struct nfsd3_setaclargs *argp = rqstp->rq_argp;
if (!svcxdr_decode_nfs_fh3(xdr, &argp->fh))
- return 0;
+ return false;
if (xdr_stream_decode_u32(xdr, &argp->mask) < 0)
- return 0;
+ return false;
if (argp->mask & ~NFS_ACL_MASK)
- return 0;
+ return false;
if (!nfs_stream_decode_acl(xdr, NULL, (argp->mask & NFS_ACL) ?
&argp->acl_access : NULL))
- return 0;
+ return false;
if (!nfs_stream_decode_acl(xdr, NULL, (argp->mask & NFS_DFACL) ?
&argp->acl_default : NULL))
- return 0;
+ return false;
- return 1;
+ return true;
}
/*
@@ -166,9 +166,9 @@ static int nfs3svc_decode_setaclargs(struct svc_rqst *rqstp, __be32 *p)
*/
/* GETACL */
-static int nfs3svc_encode_getaclres(struct svc_rqst *rqstp, __be32 *p)
+static bool
+nfs3svc_encode_getaclres(struct svc_rqst *rqstp, struct xdr_stream *xdr)
{
- struct xdr_stream *xdr = &rqstp->rq_res_stream;
struct nfsd3_getaclres *resp = rqstp->rq_resp;
struct dentry *dentry = resp->fh.fh_dentry;
struct kvec *head = rqstp->rq_res.head;
@@ -178,14 +178,14 @@ static int nfs3svc_encode_getaclres(struct svc_rqst *rqstp, __be32 *p)
int w;
if (!svcxdr_encode_nfsstat3(xdr, resp->status))
- return 0;
+ return false;
switch (resp->status) {
case nfs_ok:
inode = d_inode(dentry);
if (!svcxdr_encode_post_op_attr(rqstp, xdr, &resp->fh))
- return 0;
+ return false;
if (xdr_stream_encode_u32(xdr, resp->mask) < 0)
- return 0;
+ return false;
base = (char *)xdr->p - (char *)head->iov_base;
@@ -194,7 +194,7 @@ static int nfs3svc_encode_getaclres(struct svc_rqst *rqstp, __be32 *p)
(resp->mask & NFS_DFACL) ? resp->acl_default : NULL);
while (w > 0) {
if (!*(rqstp->rq_next_page++))
- return 0;
+ return false;
w -= PAGE_SIZE;
}
@@ -207,20 +207,20 @@ static int nfs3svc_encode_getaclres(struct svc_rqst *rqstp, __be32 *p)
resp->mask & NFS_DFACL,
NFS_ACL_DEFAULT);
if (n <= 0)
- return 0;
+ return false;
break;
default:
if (!svcxdr_encode_post_op_attr(rqstp, xdr, &resp->fh))
- return 0;
+ return false;
}
- return 1;
+ return true;
}
/* SETACL */
-static int nfs3svc_encode_setaclres(struct svc_rqst *rqstp, __be32 *p)
+static bool
+nfs3svc_encode_setaclres(struct svc_rqst *rqstp, struct xdr_stream *xdr)
{
- struct xdr_stream *xdr = &rqstp->rq_res_stream;
struct nfsd3_attrstat *resp = rqstp->rq_resp;
return svcxdr_encode_nfsstat3(xdr, resp->status) &&
diff --git a/fs/nfsd/nfs3proc.c b/fs/nfsd/nfs3proc.c
index 17715a6c7a40..4418517f6f12 100644
--- a/fs/nfsd/nfs3proc.c
+++ b/fs/nfsd/nfs3proc.c
@@ -201,8 +201,7 @@ nfsd3_proc_write(struct svc_rqst *rqstp)
fh_copy(&resp->fh, &argp->fh);
resp->committed = argp->stable;
- nvecs = svc_fill_write_vector(rqstp, rqstp->rq_arg.pages,
- &argp->first, cnt);
+ nvecs = svc_fill_write_vector(rqstp, &argp->payload);
if (!nvecs) {
resp->status = nfserr_io;
goto out;
diff --git a/fs/nfsd/nfs3xdr.c b/fs/nfsd/nfs3xdr.c
index 0a5ebc52e6a9..c3ac1b6aa3aa 100644
--- a/fs/nfsd/nfs3xdr.c
+++ b/fs/nfsd/nfs3xdr.c
@@ -92,7 +92,7 @@ svcxdr_decode_nfs_fh3(struct xdr_stream *xdr, struct svc_fh *fhp)
return false;
fh_init(fhp, NFS3_FHSIZE);
fhp->fh_handle.fh_size = size;
- memcpy(&fhp->fh_handle.fh_base, p, size);
+ memcpy(&fhp->fh_handle.fh_raw, p, size);
return true;
}
@@ -131,7 +131,7 @@ svcxdr_encode_nfs_fh3(struct xdr_stream *xdr, const struct svc_fh *fhp)
*p++ = cpu_to_be32(size);
if (size)
p[XDR_QUADLEN(size) - 1] = 0;
- memcpy(p, &fhp->fh_handle.fh_base, size);
+ memcpy(p, &fhp->fh_handle.fh_raw, size);
return true;
}
@@ -556,19 +556,17 @@ void fill_post_wcc(struct svc_fh *fhp)
* XDR decode functions
*/
-int
-nfs3svc_decode_fhandleargs(struct svc_rqst *rqstp, __be32 *p)
+bool
+nfs3svc_decode_fhandleargs(struct svc_rqst *rqstp, struct xdr_stream *xdr)
{
- struct xdr_stream *xdr = &rqstp->rq_arg_stream;
struct nfsd_fhandle *args = rqstp->rq_argp;
return svcxdr_decode_nfs_fh3(xdr, &args->fh);
}
-int
-nfs3svc_decode_sattrargs(struct svc_rqst *rqstp, __be32 *p)
+bool
+nfs3svc_decode_sattrargs(struct svc_rqst *rqstp, struct xdr_stream *xdr)
{
- struct xdr_stream *xdr = &rqstp->rq_arg_stream;
struct nfsd3_sattrargs *args = rqstp->rq_argp;
return svcxdr_decode_nfs_fh3(xdr, &args->fh) &&
@@ -576,96 +574,83 @@ nfs3svc_decode_sattrargs(struct svc_rqst *rqstp, __be32 *p)
svcxdr_decode_sattrguard3(xdr, args);
}
-int
-nfs3svc_decode_diropargs(struct svc_rqst *rqstp, __be32 *p)
+bool
+nfs3svc_decode_diropargs(struct svc_rqst *rqstp, struct xdr_stream *xdr)
{
- struct xdr_stream *xdr = &rqstp->rq_arg_stream;
struct nfsd3_diropargs *args = rqstp->rq_argp;
return svcxdr_decode_diropargs3(xdr, &args->fh, &args->name, &args->len);
}
-int
-nfs3svc_decode_accessargs(struct svc_rqst *rqstp, __be32 *p)
+bool
+nfs3svc_decode_accessargs(struct svc_rqst *rqstp, struct xdr_stream *xdr)
{
- struct xdr_stream *xdr = &rqstp->rq_arg_stream;
struct nfsd3_accessargs *args = rqstp->rq_argp;
if (!svcxdr_decode_nfs_fh3(xdr, &args->fh))
- return 0;
+ return false;
if (xdr_stream_decode_u32(xdr, &args->access) < 0)
- return 0;
+ return false;
- return 1;
+ return true;
}
-int
-nfs3svc_decode_readargs(struct svc_rqst *rqstp, __be32 *p)
+bool
+nfs3svc_decode_readargs(struct svc_rqst *rqstp, struct xdr_stream *xdr)
{
- struct xdr_stream *xdr = &rqstp->rq_arg_stream;
struct nfsd3_readargs *args = rqstp->rq_argp;
if (!svcxdr_decode_nfs_fh3(xdr, &args->fh))
- return 0;
+ return false;
if (xdr_stream_decode_u64(xdr, &args->offset) < 0)
- return 0;
+ return false;
if (xdr_stream_decode_u32(xdr, &args->count) < 0)
- return 0;
+ return false;
- return 1;
+ return true;
}
-int
-nfs3svc_decode_writeargs(struct svc_rqst *rqstp, __be32 *p)
+bool
+nfs3svc_decode_writeargs(struct svc_rqst *rqstp, struct xdr_stream *xdr)
{
- struct xdr_stream *xdr = &rqstp->rq_arg_stream;
struct nfsd3_writeargs *args = rqstp->rq_argp;
u32 max_blocksize = svc_max_payload(rqstp);
- struct kvec *head = rqstp->rq_arg.head;
- struct kvec *tail = rqstp->rq_arg.tail;
- size_t remaining;
if (!svcxdr_decode_nfs_fh3(xdr, &args->fh))
- return 0;
+ return false;
if (xdr_stream_decode_u64(xdr, &args->offset) < 0)
- return 0;
+ return false;
if (xdr_stream_decode_u32(xdr, &args->count) < 0)
- return 0;
+ return false;
if (xdr_stream_decode_u32(xdr, &args->stable) < 0)
- return 0;
+ return false;
/* opaque data */
if (xdr_stream_decode_u32(xdr, &args->len) < 0)
- return 0;
+ return false;
/* request sanity */
if (args->count != args->len)
- return 0;
- remaining = head->iov_len + rqstp->rq_arg.page_len + tail->iov_len;
- remaining -= xdr_stream_pos(xdr);
- if (remaining < xdr_align_size(args->len))
- return 0;
+ return false;
if (args->count > max_blocksize) {
args->count = max_blocksize;
args->len = max_blocksize;
}
+ if (!xdr_stream_subsegment(xdr, &args->payload, args->count))
+ return false;
- args->first.iov_base = xdr->p;
- args->first.iov_len = head->iov_len - xdr_stream_pos(xdr);
-
- return 1;
+ return true;
}
-int
-nfs3svc_decode_createargs(struct svc_rqst *rqstp, __be32 *p)
+bool
+nfs3svc_decode_createargs(struct svc_rqst *rqstp, struct xdr_stream *xdr)
{
- struct xdr_stream *xdr = &rqstp->rq_arg_stream;
struct nfsd3_createargs *args = rqstp->rq_argp;
if (!svcxdr_decode_diropargs3(xdr, &args->fh, &args->name, &args->len))
- return 0;
+ return false;
if (xdr_stream_decode_u32(xdr, &args->createmode) < 0)
- return 0;
+ return false;
switch (args->createmode) {
case NFS3_CREATE_UNCHECKED:
case NFS3_CREATE_GUARDED:
@@ -673,18 +658,17 @@ nfs3svc_decode_createargs(struct svc_rqst *rqstp, __be32 *p)
case NFS3_CREATE_EXCLUSIVE:
args->verf = xdr_inline_decode(xdr, NFS3_CREATEVERFSIZE);
if (!args->verf)
- return 0;
+ return false;
break;
default:
- return 0;
+ return false;
}
- return 1;
+ return true;
}
-int
-nfs3svc_decode_mkdirargs(struct svc_rqst *rqstp, __be32 *p)
+bool
+nfs3svc_decode_mkdirargs(struct svc_rqst *rqstp, struct xdr_stream *xdr)
{
- struct xdr_stream *xdr = &rqstp->rq_arg_stream;
struct nfsd3_createargs *args = rqstp->rq_argp;
return svcxdr_decode_diropargs3(xdr, &args->fh,
@@ -692,44 +676,42 @@ nfs3svc_decode_mkdirargs(struct svc_rqst *rqstp, __be32 *p)
svcxdr_decode_sattr3(rqstp, xdr, &args->attrs);
}
-int
-nfs3svc_decode_symlinkargs(struct svc_rqst *rqstp, __be32 *p)
+bool
+nfs3svc_decode_symlinkargs(struct svc_rqst *rqstp, struct xdr_stream *xdr)
{
- struct xdr_stream *xdr = &rqstp->rq_arg_stream;
struct nfsd3_symlinkargs *args = rqstp->rq_argp;
struct kvec *head = rqstp->rq_arg.head;
struct kvec *tail = rqstp->rq_arg.tail;
size_t remaining;
if (!svcxdr_decode_diropargs3(xdr, &args->ffh, &args->fname, &args->flen))
- return 0;
+ return false;
if (!svcxdr_decode_sattr3(rqstp, xdr, &args->attrs))
- return 0;
+ return false;
if (xdr_stream_decode_u32(xdr, &args->tlen) < 0)
- return 0;
+ return false;
/* request sanity */
remaining = head->iov_len + rqstp->rq_arg.page_len + tail->iov_len;
remaining -= xdr_stream_pos(xdr);
if (remaining < xdr_align_size(args->tlen))
- return 0;
+ return false;
args->first.iov_base = xdr->p;
args->first.iov_len = head->iov_len - xdr_stream_pos(xdr);
- return 1;
+ return true;
}
-int
-nfs3svc_decode_mknodargs(struct svc_rqst *rqstp, __be32 *p)
+bool
+nfs3svc_decode_mknodargs(struct svc_rqst *rqstp, struct xdr_stream *xdr)
{
- struct xdr_stream *xdr = &rqstp->rq_arg_stream;
struct nfsd3_mknodargs *args = rqstp->rq_argp;
if (!svcxdr_decode_diropargs3(xdr, &args->fh, &args->name, &args->len))
- return 0;
+ return false;
if (xdr_stream_decode_u32(xdr, &args->ftype) < 0)
- return 0;
+ return false;
switch (args->ftype) {
case NF3CHR:
case NF3BLK:
@@ -743,16 +725,15 @@ nfs3svc_decode_mknodargs(struct svc_rqst *rqstp, __be32 *p)
/* Valid XDR but illegal file types */
break;
default:
- return 0;
+ return false;
}
- return 1;
+ return true;
}
-int
-nfs3svc_decode_renameargs(struct svc_rqst *rqstp, __be32 *p)
+bool
+nfs3svc_decode_renameargs(struct svc_rqst *rqstp, struct xdr_stream *xdr)
{
- struct xdr_stream *xdr = &rqstp->rq_arg_stream;
struct nfsd3_renameargs *args = rqstp->rq_argp;
return svcxdr_decode_diropargs3(xdr, &args->ffh,
@@ -761,10 +742,9 @@ nfs3svc_decode_renameargs(struct svc_rqst *rqstp, __be32 *p)
&args->tname, &args->tlen);
}
-int
-nfs3svc_decode_linkargs(struct svc_rqst *rqstp, __be32 *p)
+bool
+nfs3svc_decode_linkargs(struct svc_rqst *rqstp, struct xdr_stream *xdr)
{
- struct xdr_stream *xdr = &rqstp->rq_arg_stream;
struct nfsd3_linkargs *args = rqstp->rq_argp;
return svcxdr_decode_nfs_fh3(xdr, &args->ffh) &&
@@ -772,62 +752,59 @@ nfs3svc_decode_linkargs(struct svc_rqst *rqstp, __be32 *p)
&args->tname, &args->tlen);
}
-int
-nfs3svc_decode_readdirargs(struct svc_rqst *rqstp, __be32 *p)
+bool
+nfs3svc_decode_readdirargs(struct svc_rqst *rqstp, struct xdr_stream *xdr)
{
- struct xdr_stream *xdr = &rqstp->rq_arg_stream;
struct nfsd3_readdirargs *args = rqstp->rq_argp;
if (!svcxdr_decode_nfs_fh3(xdr, &args->fh))
- return 0;
+ return false;
if (xdr_stream_decode_u64(xdr, &args->cookie) < 0)
- return 0;
+ return false;
args->verf = xdr_inline_decode(xdr, NFS3_COOKIEVERFSIZE);
if (!args->verf)
- return 0;
+ return false;
if (xdr_stream_decode_u32(xdr, &args->count) < 0)
- return 0;
+ return false;
- return 1;
+ return true;
}
-int
-nfs3svc_decode_readdirplusargs(struct svc_rqst *rqstp, __be32 *p)
+bool
+nfs3svc_decode_readdirplusargs(struct svc_rqst *rqstp, struct xdr_stream *xdr)
{
- struct xdr_stream *xdr = &rqstp->rq_arg_stream;
struct nfsd3_readdirargs *args = rqstp->rq_argp;
u32 dircount;
if (!svcxdr_decode_nfs_fh3(xdr, &args->fh))
- return 0;
+ return false;
if (xdr_stream_decode_u64(xdr, &args->cookie) < 0)
- return 0;
+ return false;
args->verf = xdr_inline_decode(xdr, NFS3_COOKIEVERFSIZE);
if (!args->verf)
- return 0;
+ return false;
/* dircount is ignored */
if (xdr_stream_decode_u32(xdr, &dircount) < 0)
- return 0;
+ return false;
if (xdr_stream_decode_u32(xdr, &args->count) < 0)
- return 0;
+ return false;
- return 1;
+ return true;
}
-int
-nfs3svc_decode_commitargs(struct svc_rqst *rqstp, __be32 *p)
+bool
+nfs3svc_decode_commitargs(struct svc_rqst *rqstp, struct xdr_stream *xdr)
{
- struct xdr_stream *xdr = &rqstp->rq_arg_stream;
struct nfsd3_commitargs *args = rqstp->rq_argp;
if (!svcxdr_decode_nfs_fh3(xdr, &args->fh))
- return 0;
+ return false;
if (xdr_stream_decode_u64(xdr, &args->offset) < 0)
- return 0;
+ return false;
if (xdr_stream_decode_u32(xdr, &args->count) < 0)
- return 0;
+ return false;
- return 1;
+ return true;
}
/*
@@ -835,30 +812,28 @@ nfs3svc_decode_commitargs(struct svc_rqst *rqstp, __be32 *p)
*/
/* GETATTR */
-int
-nfs3svc_encode_getattrres(struct svc_rqst *rqstp, __be32 *p)
+bool
+nfs3svc_encode_getattrres(struct svc_rqst *rqstp, struct xdr_stream *xdr)
{
- struct xdr_stream *xdr = &rqstp->rq_res_stream;
struct nfsd3_attrstat *resp = rqstp->rq_resp;
if (!svcxdr_encode_nfsstat3(xdr, resp->status))
- return 0;
+ return false;
switch (resp->status) {
case nfs_ok:
lease_get_mtime(d_inode(resp->fh.fh_dentry), &resp->stat.mtime);
if (!svcxdr_encode_fattr3(rqstp, xdr, &resp->fh, &resp->stat))
- return 0;
+ return false;
break;
}
- return 1;
+ return true;
}
/* SETATTR, REMOVE, RMDIR */
-int
-nfs3svc_encode_wccstat(struct svc_rqst *rqstp, __be32 *p)
+bool
+nfs3svc_encode_wccstat(struct svc_rqst *rqstp, struct xdr_stream *xdr)
{
- struct xdr_stream *xdr = &rqstp->rq_res_stream;
struct nfsd3_attrstat *resp = rqstp->rq_resp;
return svcxdr_encode_nfsstat3(xdr, resp->status) &&
@@ -866,174 +841,168 @@ nfs3svc_encode_wccstat(struct svc_rqst *rqstp, __be32 *p)
}
/* LOOKUP */
-int nfs3svc_encode_lookupres(struct svc_rqst *rqstp, __be32 *p)
+bool
+nfs3svc_encode_lookupres(struct svc_rqst *rqstp, struct xdr_stream *xdr)
{
- struct xdr_stream *xdr = &rqstp->rq_res_stream;
struct nfsd3_diropres *resp = rqstp->rq_resp;
if (!svcxdr_encode_nfsstat3(xdr, resp->status))
- return 0;
+ return false;
switch (resp->status) {
case nfs_ok:
if (!svcxdr_encode_nfs_fh3(xdr, &resp->fh))
- return 0;
+ return false;
if (!svcxdr_encode_post_op_attr(rqstp, xdr, &resp->fh))
- return 0;
+ return false;
if (!svcxdr_encode_post_op_attr(rqstp, xdr, &resp->dirfh))
- return 0;
+ return false;
break;
default:
if (!svcxdr_encode_post_op_attr(rqstp, xdr, &resp->dirfh))
- return 0;
+ return false;
}
- return 1;
+ return true;
}
/* ACCESS */
-int
-nfs3svc_encode_accessres(struct svc_rqst *rqstp, __be32 *p)
+bool
+nfs3svc_encode_accessres(struct svc_rqst *rqstp, struct xdr_stream *xdr)
{
- struct xdr_stream *xdr = &rqstp->rq_res_stream;
struct nfsd3_accessres *resp = rqstp->rq_resp;
if (!svcxdr_encode_nfsstat3(xdr, resp->status))
- return 0;
+ return false;
switch (resp->status) {
case nfs_ok:
if (!svcxdr_encode_post_op_attr(rqstp, xdr, &resp->fh))
- return 0;
+ return false;
if (xdr_stream_encode_u32(xdr, resp->access) < 0)
- return 0;
+ return false;
break;
default:
if (!svcxdr_encode_post_op_attr(rqstp, xdr, &resp->fh))
- return 0;
+ return false;
}
- return 1;
+ return true;
}
/* READLINK */
-int
-nfs3svc_encode_readlinkres(struct svc_rqst *rqstp, __be32 *p)
+bool
+nfs3svc_encode_readlinkres(struct svc_rqst *rqstp, struct xdr_stream *xdr)
{
- struct xdr_stream *xdr = &rqstp->rq_res_stream;
struct nfsd3_readlinkres *resp = rqstp->rq_resp;
struct kvec *head = rqstp->rq_res.head;
if (!svcxdr_encode_nfsstat3(xdr, resp->status))
- return 0;
+ return false;
switch (resp->status) {
case nfs_ok:
if (!svcxdr_encode_post_op_attr(rqstp, xdr, &resp->fh))
- return 0;
+ return false;
if (xdr_stream_encode_u32(xdr, resp->len) < 0)
- return 0;
+ return false;
xdr_write_pages(xdr, resp->pages, 0, resp->len);
if (svc_encode_result_payload(rqstp, head->iov_len, resp->len) < 0)
- return 0;
+ return false;
break;
default:
if (!svcxdr_encode_post_op_attr(rqstp, xdr, &resp->fh))
- return 0;
+ return false;
}
- return 1;
+ return true;
}
/* READ */
-int
-nfs3svc_encode_readres(struct svc_rqst *rqstp, __be32 *p)
+bool
+nfs3svc_encode_readres(struct svc_rqst *rqstp, struct xdr_stream *xdr)
{
- struct xdr_stream *xdr = &rqstp->rq_res_stream;
struct nfsd3_readres *resp = rqstp->rq_resp;
struct kvec *head = rqstp->rq_res.head;
if (!svcxdr_encode_nfsstat3(xdr, resp->status))
- return 0;
+ return false;
switch (resp->status) {
case nfs_ok:
if (!svcxdr_encode_post_op_attr(rqstp, xdr, &resp->fh))
- return 0;
+ return false;
if (xdr_stream_encode_u32(xdr, resp->count) < 0)
- return 0;
+ return false;
if (xdr_stream_encode_bool(xdr, resp->eof) < 0)
- return 0;
+ return false;
if (xdr_stream_encode_u32(xdr, resp->count) < 0)
- return 0;
+ return false;
xdr_write_pages(xdr, resp->pages, rqstp->rq_res.page_base,
resp->count);
if (svc_encode_result_payload(rqstp, head->iov_len, resp->count) < 0)
- return 0;
+ return false;
break;
default:
if (!svcxdr_encode_post_op_attr(rqstp, xdr, &resp->fh))
- return 0;
+ return false;
}
- return 1;
+ return true;
}
/* WRITE */
-int
-nfs3svc_encode_writeres(struct svc_rqst *rqstp, __be32 *p)
+bool
+nfs3svc_encode_writeres(struct svc_rqst *rqstp, struct xdr_stream *xdr)
{
- struct xdr_stream *xdr = &rqstp->rq_res_stream;
struct nfsd3_writeres *resp = rqstp->rq_resp;
if (!svcxdr_encode_nfsstat3(xdr, resp->status))
- return 0;
+ return false;
switch (resp->status) {
case nfs_ok:
if (!svcxdr_encode_wcc_data(rqstp, xdr, &resp->fh))
- return 0;
+ return false;
if (xdr_stream_encode_u32(xdr, resp->count) < 0)
- return 0;
+ return false;
if (xdr_stream_encode_u32(xdr, resp->committed) < 0)
- return 0;
+ return false;
if (!svcxdr_encode_writeverf3(xdr, resp->verf))
- return 0;
+ return false;
break;
default:
if (!svcxdr_encode_wcc_data(rqstp, xdr, &resp->fh))
- return 0;
+ return false;
}
- return 1;
+ return true;
}
/* CREATE, MKDIR, SYMLINK, MKNOD */
-int
-nfs3svc_encode_createres(struct svc_rqst *rqstp, __be32 *p)
+bool
+nfs3svc_encode_createres(struct svc_rqst *rqstp, struct xdr_stream *xdr)
{
- struct xdr_stream *xdr = &rqstp->rq_res_stream;
struct nfsd3_diropres *resp = rqstp->rq_resp;
if (!svcxdr_encode_nfsstat3(xdr, resp->status))
- return 0;
+ return false;
switch (resp->status) {
case nfs_ok:
if (!svcxdr_encode_post_op_fh3(xdr, &resp->fh))
- return 0;
+ return false;
if (!svcxdr_encode_post_op_attr(rqstp, xdr, &resp->fh))
- return 0;
+ return false;
if (!svcxdr_encode_wcc_data(rqstp, xdr, &resp->dirfh))
- return 0;
+ return false;
break;
default:
if (!svcxdr_encode_wcc_data(rqstp, xdr, &resp->dirfh))
- return 0;
+ return false;
}
- return 1;
+ return true;
}
/* RENAME */
-int
-nfs3svc_encode_renameres(struct svc_rqst *rqstp, __be32 *p)
+bool
+nfs3svc_encode_renameres(struct svc_rqst *rqstp, struct xdr_stream *xdr)
{
- struct xdr_stream *xdr = &rqstp->rq_res_stream;
struct nfsd3_renameres *resp = rqstp->rq_resp;
return svcxdr_encode_nfsstat3(xdr, resp->status) &&
@@ -1042,10 +1011,9 @@ nfs3svc_encode_renameres(struct svc_rqst *rqstp, __be32 *p)
}
/* LINK */
-int
-nfs3svc_encode_linkres(struct svc_rqst *rqstp, __be32 *p)
+bool
+nfs3svc_encode_linkres(struct svc_rqst *rqstp, struct xdr_stream *xdr)
{
- struct xdr_stream *xdr = &rqstp->rq_res_stream;
struct nfsd3_linkres *resp = rqstp->rq_resp;
return svcxdr_encode_nfsstat3(xdr, resp->status) &&
@@ -1054,34 +1022,33 @@ nfs3svc_encode_linkres(struct svc_rqst *rqstp, __be32 *p)
}
/* READDIR */
-int
-nfs3svc_encode_readdirres(struct svc_rqst *rqstp, __be32 *p)
+bool
+nfs3svc_encode_readdirres(struct svc_rqst *rqstp, struct xdr_stream *xdr)
{
- struct xdr_stream *xdr = &rqstp->rq_res_stream;
struct nfsd3_readdirres *resp = rqstp->rq_resp;
struct xdr_buf *dirlist = &resp->dirlist;
if (!svcxdr_encode_nfsstat3(xdr, resp->status))
- return 0;
+ return false;
switch (resp->status) {
case nfs_ok:
if (!svcxdr_encode_post_op_attr(rqstp, xdr, &resp->fh))
- return 0;
+ return false;
if (!svcxdr_encode_cookieverf3(xdr, resp->verf))
- return 0;
+ return false;
xdr_write_pages(xdr, dirlist->pages, 0, dirlist->len);
/* no more entries */
if (xdr_stream_encode_item_absent(xdr) < 0)
- return 0;
+ return false;
if (xdr_stream_encode_bool(xdr, resp->common.err == nfserr_eof) < 0)
- return 0;
+ return false;
break;
default:
if (!svcxdr_encode_post_op_attr(rqstp, xdr, &resp->fh))
- return 0;
+ return false;
}
- return 1;
+ return true;
}
static __be32
@@ -1308,27 +1275,26 @@ svcxdr_encode_fsstat3resok(struct xdr_stream *xdr,
}
/* FSSTAT */
-int
-nfs3svc_encode_fsstatres(struct svc_rqst *rqstp, __be32 *p)
+bool
+nfs3svc_encode_fsstatres(struct svc_rqst *rqstp, struct xdr_stream *xdr)
{
- struct xdr_stream *xdr = &rqstp->rq_res_stream;
struct nfsd3_fsstatres *resp = rqstp->rq_resp;
if (!svcxdr_encode_nfsstat3(xdr, resp->status))
- return 0;
+ return false;
switch (resp->status) {
case nfs_ok:
if (!svcxdr_encode_post_op_attr(rqstp, xdr, &nfs3svc_null_fh))
- return 0;
+ return false;
if (!svcxdr_encode_fsstat3resok(xdr, resp))
- return 0;
+ return false;
break;
default:
if (!svcxdr_encode_post_op_attr(rqstp, xdr, &nfs3svc_null_fh))
- return 0;
+ return false;
}
- return 1;
+ return true;
}
static bool
@@ -1355,27 +1321,26 @@ svcxdr_encode_fsinfo3resok(struct xdr_stream *xdr,
}
/* FSINFO */
-int
-nfs3svc_encode_fsinfores(struct svc_rqst *rqstp, __be32 *p)
+bool
+nfs3svc_encode_fsinfores(struct svc_rqst *rqstp, struct xdr_stream *xdr)
{
- struct xdr_stream *xdr = &rqstp->rq_res_stream;
struct nfsd3_fsinfores *resp = rqstp->rq_resp;
if (!svcxdr_encode_nfsstat3(xdr, resp->status))
- return 0;
+ return false;
switch (resp->status) {
case nfs_ok:
if (!svcxdr_encode_post_op_attr(rqstp, xdr, &nfs3svc_null_fh))
- return 0;
+ return false;
if (!svcxdr_encode_fsinfo3resok(xdr, resp))
- return 0;
+ return false;
break;
default:
if (!svcxdr_encode_post_op_attr(rqstp, xdr, &nfs3svc_null_fh))
- return 0;
+ return false;
}
- return 1;
+ return true;
}
static bool
@@ -1398,51 +1363,49 @@ svcxdr_encode_pathconf3resok(struct xdr_stream *xdr,
}
/* PATHCONF */
-int
-nfs3svc_encode_pathconfres(struct svc_rqst *rqstp, __be32 *p)
+bool
+nfs3svc_encode_pathconfres(struct svc_rqst *rqstp, struct xdr_stream *xdr)
{
- struct xdr_stream *xdr = &rqstp->rq_res_stream;
struct nfsd3_pathconfres *resp = rqstp->rq_resp;
if (!svcxdr_encode_nfsstat3(xdr, resp->status))
- return 0;
+ return false;
switch (resp->status) {
case nfs_ok:
if (!svcxdr_encode_post_op_attr(rqstp, xdr, &nfs3svc_null_fh))
- return 0;
+ return false;
if (!svcxdr_encode_pathconf3resok(xdr, resp))
- return 0;
+ return false;
break;
default:
if (!svcxdr_encode_post_op_attr(rqstp, xdr, &nfs3svc_null_fh))
- return 0;
+ return false;
}
- return 1;
+ return true;
}
/* COMMIT */
-int
-nfs3svc_encode_commitres(struct svc_rqst *rqstp, __be32 *p)
+bool
+nfs3svc_encode_commitres(struct svc_rqst *rqstp, struct xdr_stream *xdr)
{
- struct xdr_stream *xdr = &rqstp->rq_res_stream;
struct nfsd3_commitres *resp = rqstp->rq_resp;
if (!svcxdr_encode_nfsstat3(xdr, resp->status))
- return 0;
+ return false;
switch (resp->status) {
case nfs_ok:
if (!svcxdr_encode_wcc_data(rqstp, xdr, &resp->fh))
- return 0;
+ return false;
if (!svcxdr_encode_writeverf3(xdr, resp->verf))
- return 0;
+ return false;
break;
default:
if (!svcxdr_encode_wcc_data(rqstp, xdr, &resp->fh))
- return 0;
+ return false;
}
- return 1;
+ return true;
}
/*
diff --git a/fs/nfsd/nfs4callback.c b/fs/nfsd/nfs4callback.c
index 0f8b10f363e7..11f8715d92d6 100644
--- a/fs/nfsd/nfs4callback.c
+++ b/fs/nfsd/nfs4callback.c
@@ -121,7 +121,7 @@ static void encode_nfs_fh4(struct xdr_stream *xdr, const struct knfsd_fh *fh)
BUG_ON(length > NFS4_FHSIZE);
p = xdr_reserve_space(xdr, 4 + length);
- xdr_encode_opaque(p, &fh->fh_base, length);
+ xdr_encode_opaque(p, &fh->fh_raw, length);
}
/*
diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c
index 486c5dba4b65..a36261f89bdf 100644
--- a/fs/nfsd/nfs4proc.c
+++ b/fs/nfsd/nfs4proc.c
@@ -519,7 +519,7 @@ nfsd4_putfh(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
fh_put(&cstate->current_fh);
cstate->current_fh.fh_handle.fh_size = putfh->pf_fhlen;
- memcpy(&cstate->current_fh.fh_handle.fh_base, putfh->pf_fhval,
+ memcpy(&cstate->current_fh.fh_handle.fh_raw, putfh->pf_fhval,
putfh->pf_fhlen);
ret = fh_verify(rqstp, &cstate->current_fh, 0, NFSD_MAY_BYPASS_GSS);
#ifdef CONFIG_NFSD_V4_2_INTER_SSC
@@ -1033,8 +1033,7 @@ nfsd4_write(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
write->wr_how_written = write->wr_stable_how;
- nvecs = svc_fill_write_vector(rqstp, write->wr_payload.pages,
- write->wr_payload.head, write->wr_buflen);
+ nvecs = svc_fill_write_vector(rqstp, &write->wr_payload);
WARN_ON_ONCE(nvecs > ARRAY_SIZE(rqstp->rq_vec));
status = nfsd_vfs_write(rqstp, &cstate->current_fh, nf,
@@ -1178,7 +1177,7 @@ extern void nfs_sb_deactive(struct super_block *sb);
static __be32 nfsd4_ssc_setup_dul(struct nfsd_net *nn, char *ipaddr,
struct nfsd4_ssc_umount_item **retwork, struct vfsmount **ss_mnt)
{
- struct nfsd4_ssc_umount_item *ni = 0;
+ struct nfsd4_ssc_umount_item *ni = NULL;
struct nfsd4_ssc_umount_item *work = NULL;
struct nfsd4_ssc_umount_item *tmp;
DEFINE_WAIT(wait);
@@ -1383,7 +1382,7 @@ nfsd4_setup_inter_ssc(struct svc_rqst *rqstp,
s_fh = &cstate->save_fh;
copy->c_fh.size = s_fh->fh_handle.fh_size;
- memcpy(copy->c_fh.data, &s_fh->fh_handle.fh_base, copy->c_fh.size);
+ memcpy(copy->c_fh.data, &s_fh->fh_handle.fh_raw, copy->c_fh.size);
copy->stateid.seqid = cpu_to_be32(s_stid->si_generation);
memcpy(copy->stateid.other, (void *)&s_stid->si_opaque,
sizeof(stateid_opaque_t));
@@ -2462,11 +2461,11 @@ nfsd4_proc_compound(struct svc_rqst *rqstp)
__be32 status;
resp->xdr = &rqstp->rq_res_stream;
+ resp->statusp = resp->xdr->p;
/* reserve space for: NFS status code */
xdr_reserve_space(resp->xdr, XDR_UNIT);
- resp->tagp = resp->xdr->p;
/* reserve space for: taglen, tag, and opcnt */
xdr_reserve_space(resp->xdr, XDR_UNIT * 2 + args->taglen);
resp->taglen = args->taglen;
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 3f4027a5de88..bfad94c70b84 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -1010,7 +1010,7 @@ static int delegation_blocked(struct knfsd_fh *fh)
}
spin_unlock(&blocked_delegations_lock);
}
- hash = jhash(&fh->fh_base, fh->fh_size, 0);
+ hash = jhash(&fh->fh_raw, fh->fh_size, 0);
if (test_bit(hash&255, bd->set[0]) &&
test_bit((hash>>8)&255, bd->set[0]) &&
test_bit((hash>>16)&255, bd->set[0]))
@@ -1029,7 +1029,7 @@ static void block_delegations(struct knfsd_fh *fh)
u32 hash;
struct bloom_pair *bd = &blocked_delegations;
- hash = jhash(&fh->fh_base, fh->fh_size, 0);
+ hash = jhash(&fh->fh_raw, fh->fh_size, 0);
spin_lock(&blocked_delegations_lock);
__set_bit(hash&255, bd->set[bd->new]);
@@ -5541,7 +5541,7 @@ static void nfsd4_ssc_shutdown_umount(struct nfsd_net *nn)
static void nfsd4_ssc_expire_umount(struct nfsd_net *nn)
{
bool do_wakeup = false;
- struct nfsd4_ssc_umount_item *ni = 0;
+ struct nfsd4_ssc_umount_item *ni = NULL;
struct nfsd4_ssc_umount_item *tmp;
spin_lock(&nn->nfsd_ssc_lock);
diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c
index cf030ebe2827..b2a1d969a172 100644
--- a/fs/nfsd/nfs4xdr.c
+++ b/fs/nfsd/nfs4xdr.c
@@ -2322,7 +2322,7 @@ nfsd4_opnum_in_range(struct nfsd4_compoundargs *argp, struct nfsd4_op *op)
return true;
}
-static int
+static bool
nfsd4_decode_compound(struct nfsd4_compoundargs *argp)
{
struct nfsd4_op *op;
@@ -2335,25 +2335,25 @@ nfsd4_decode_compound(struct nfsd4_compoundargs *argp)
int i;
if (xdr_stream_decode_u32(argp->xdr, &argp->taglen) < 0)
- return 0;
+ return false;
max_reply += XDR_UNIT;
argp->tag = NULL;
if (unlikely(argp->taglen)) {
if (argp->taglen > NFSD4_MAX_TAGLEN)
- return 0;
+ return false;
p = xdr_inline_decode(argp->xdr, argp->taglen);
if (!p)
- return 0;
+ return false;
argp->tag = svcxdr_savemem(argp, p, argp->taglen);
if (!argp->tag)
- return 0;
+ return false;
max_reply += xdr_align_size(argp->taglen);
}
if (xdr_stream_decode_u32(argp->xdr, &argp->minorversion) < 0)
- return 0;
+ return false;
if (xdr_stream_decode_u32(argp->xdr, &argp->opcnt) < 0)
- return 0;
+ return false;
/*
* NFS4ERR_RESOURCE is a more helpful error than GARBAGE_ARGS
@@ -2361,14 +2361,14 @@ nfsd4_decode_compound(struct nfsd4_compoundargs *argp)
* nfsd4_proc can handle this is an NFS-level error.
*/
if (argp->opcnt > NFSD_MAX_OPS_PER_COMPOUND)
- return 1;
+ return true;
if (argp->opcnt > ARRAY_SIZE(argp->iops)) {
argp->ops = kzalloc(argp->opcnt * sizeof(*argp->ops), GFP_KERNEL);
if (!argp->ops) {
argp->ops = argp->iops;
dprintk("nfsd: couldn't allocate room for COMPOUND\n");
- return 0;
+ return false;
}
}
@@ -2380,7 +2380,7 @@ nfsd4_decode_compound(struct nfsd4_compoundargs *argp)
op->replay = NULL;
if (xdr_stream_decode_u32(argp->xdr, &op->opnum) < 0)
- return 0;
+ return false;
if (nfsd4_opnum_in_range(argp, op)) {
op->status = nfsd4_dec_ops[op->opnum](argp, &op->u);
if (op->status != nfs_ok)
@@ -2427,7 +2427,7 @@ nfsd4_decode_compound(struct nfsd4_compoundargs *argp)
if (readcount > 1 || max_reply > PAGE_SIZE - auth_slack)
clear_bit(RQ_SPLICE_OK, &argp->rqstp->rq_flags);
- return 1;
+ return true;
}
static __be32 *encode_change(__be32 *p, struct kstat *stat, struct inode *inode,
@@ -3110,7 +3110,7 @@ out_acl:
p = xdr_reserve_space(xdr, fhp->fh_handle.fh_size + 4);
if (!p)
goto out_resource;
- p = xdr_encode_opaque(p, &fhp->fh_handle.fh_base,
+ p = xdr_encode_opaque(p, &fhp->fh_handle.fh_raw,
fhp->fh_handle.fh_size);
}
if (bmval0 & FATTR4_WORD0_FILEID) {
@@ -3670,7 +3670,7 @@ nfsd4_encode_getfh(struct nfsd4_compoundres *resp, __be32 nfserr, struct svc_fh
p = xdr_reserve_space(xdr, len + 4);
if (!p)
return nfserr_resource;
- p = xdr_encode_opaque(p, &fhp->fh_handle.fh_base, len);
+ p = xdr_encode_opaque(p, &fhp->fh_handle.fh_raw, len);
return 0;
}
@@ -5414,40 +5414,46 @@ void nfsd4_release_compoundargs(struct svc_rqst *rqstp)
}
}
-int
-nfs4svc_decode_compoundargs(struct svc_rqst *rqstp, __be32 *p)
+bool
+nfs4svc_decode_compoundargs(struct svc_rqst *rqstp, struct xdr_stream *xdr)
{
struct nfsd4_compoundargs *args = rqstp->rq_argp;
/* svcxdr_tmp_alloc */
args->to_free = NULL;
- args->xdr = &rqstp->rq_arg_stream;
+ args->xdr = xdr;
args->ops = args->iops;
args->rqstp = rqstp;
return nfsd4_decode_compound(args);
}
-int
-nfs4svc_encode_compoundres(struct svc_rqst *rqstp, __be32 *p)
+bool
+nfs4svc_encode_compoundres(struct svc_rqst *rqstp, struct xdr_stream *xdr)
{
struct nfsd4_compoundres *resp = rqstp->rq_resp;
- struct xdr_buf *buf = resp->xdr->buf;
+ struct xdr_buf *buf = xdr->buf;
+ __be32 *p;
WARN_ON_ONCE(buf->len != buf->head[0].iov_len + buf->page_len +
buf->tail[0].iov_len);
- *p = resp->cstate.status;
+ /*
+ * Send buffer space for the following items is reserved
+ * at the top of nfsd4_proc_compound().
+ */
+ p = resp->statusp;
+
+ *p++ = resp->cstate.status;
- rqstp->rq_next_page = resp->xdr->page_ptr + 1;
+ rqstp->rq_next_page = xdr->page_ptr + 1;
- p = resp->tagp;
*p++ = htonl(resp->taglen);
memcpy(p, resp->tag, resp->taglen);
p += XDR_QUADLEN(resp->taglen);
*p++ = htonl(resp->opcnt);
nfsd4_sequence_done(resp);
- return 1;
+ return true;
}
diff --git a/fs/nfsd/nfscache.c b/fs/nfsd/nfscache.c
index 96cdf77925f3..6e0b6f3148dc 100644
--- a/fs/nfsd/nfscache.c
+++ b/fs/nfsd/nfscache.c
@@ -241,8 +241,8 @@ lru_put_end(struct nfsd_drc_bucket *b, struct svc_cacherep *rp)
list_move_tail(&rp->c_lru, &b->lru_head);
}
-static long
-prune_bucket(struct nfsd_drc_bucket *b, struct nfsd_net *nn)
+static long prune_bucket(struct nfsd_drc_bucket *b, struct nfsd_net *nn,
+ unsigned int max)
{
struct svc_cacherep *rp, *tmp;
long freed = 0;
@@ -258,11 +258,17 @@ prune_bucket(struct nfsd_drc_bucket *b, struct nfsd_net *nn)
time_before(jiffies, rp->c_timestamp + RC_EXPIRE))
break;
nfsd_reply_cache_free_locked(b, rp, nn);
- freed++;
+ if (max && freed++ > max)
+ break;
}
return freed;
}
+static long nfsd_prune_bucket(struct nfsd_drc_bucket *b, struct nfsd_net *nn)
+{
+ return prune_bucket(b, nn, 3);
+}
+
/*
* Walk the LRU list and prune off entries that are older than RC_EXPIRE.
* Also prune the oldest ones when the total exceeds the max number of entries.
@@ -279,7 +285,7 @@ prune_cache_entries(struct nfsd_net *nn)
if (list_empty(&b->lru_head))
continue;
spin_lock(&b->cache_lock);
- freed += prune_bucket(b, nn);
+ freed += prune_bucket(b, nn, 0);
spin_unlock(&b->cache_lock);
}
return freed;
@@ -453,8 +459,7 @@ int nfsd_cache_lookup(struct svc_rqst *rqstp)
atomic_inc(&nn->num_drc_entries);
nfsd_stats_drc_mem_usage_add(nn, sizeof(*rp));
- /* go ahead and prune the cache */
- prune_bucket(b, nn);
+ nfsd_prune_bucket(b, nn);
out_unlock:
spin_unlock(&b->cache_lock);
diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c
index 070e5dd03e26..af8531c3854a 100644
--- a/fs/nfsd/nfsctl.c
+++ b/fs/nfsd/nfsctl.c
@@ -395,12 +395,12 @@ static ssize_t write_filehandle(struct file *file, char *buf, size_t size)
auth_domain_put(dom);
if (len)
return len;
-
+
mesg = buf;
len = SIMPLE_TRANSACTION_LIMIT;
- qword_addhex(&mesg, &len, (char*)&fh.fh_base, fh.fh_size);
+ qword_addhex(&mesg, &len, fh.fh_raw, fh.fh_size);
mesg[-1] = '\n';
- return mesg - buf;
+ return mesg - buf;
}
/*
diff --git a/fs/nfsd/nfsd.h b/fs/nfsd/nfsd.h
index 9664303afdaf..498e5a489826 100644
--- a/fs/nfsd/nfsd.h
+++ b/fs/nfsd/nfsd.h
@@ -78,8 +78,10 @@ extern const struct seq_operations nfs_exports_op;
*/
struct nfsd_voidargs { };
struct nfsd_voidres { };
-int nfssvc_decode_voidarg(struct svc_rqst *rqstp, __be32 *p);
-int nfssvc_encode_voidres(struct svc_rqst *rqstp, __be32 *p);
+bool nfssvc_decode_voidarg(struct svc_rqst *rqstp,
+ struct xdr_stream *xdr);
+bool nfssvc_encode_voidres(struct svc_rqst *rqstp,
+ struct xdr_stream *xdr);
/*
* Function prototypes.
diff --git a/fs/nfsd/nfsfh.c b/fs/nfsd/nfsfh.c
index c475d2271f9c..f3779fa72c89 100644
--- a/fs/nfsd/nfsfh.c
+++ b/fs/nfsd/nfsfh.c
@@ -154,11 +154,12 @@ static inline __be32 check_pseudo_root(struct svc_rqst *rqstp,
static __be32 nfsd_set_fh_dentry(struct svc_rqst *rqstp, struct svc_fh *fhp)
{
struct knfsd_fh *fh = &fhp->fh_handle;
- struct fid *fid = NULL, sfid;
+ struct fid *fid = NULL;
struct svc_export *exp;
struct dentry *dentry;
int fileid_type;
int data_left = fh->fh_size/4;
+ int len;
__be32 error;
error = nfserr_stale;
@@ -167,48 +168,35 @@ static __be32 nfsd_set_fh_dentry(struct svc_rqst *rqstp, struct svc_fh *fhp)
if (rqstp->rq_vers == 4 && fh->fh_size == 0)
return nfserr_nofilehandle;
- if (fh->fh_version == 1) {
- int len;
-
- if (--data_left < 0)
- return error;
- if (fh->fh_auth_type != 0)
- return error;
- len = key_len(fh->fh_fsid_type) / 4;
- if (len == 0)
- return error;
- if (fh->fh_fsid_type == FSID_MAJOR_MINOR) {
- /* deprecated, convert to type 3 */
- len = key_len(FSID_ENCODE_DEV)/4;
- fh->fh_fsid_type = FSID_ENCODE_DEV;
- /*
- * struct knfsd_fh uses host-endian fields, which are
- * sometimes used to hold net-endian values. This
- * confuses sparse, so we must use __force here to
- * keep it from complaining.
- */
- fh->fh_fsid[0] = new_encode_dev(MKDEV(ntohl((__force __be32)fh->fh_fsid[0]),
- ntohl((__force __be32)fh->fh_fsid[1])));
- fh->fh_fsid[1] = fh->fh_fsid[2];
- }
- data_left -= len;
- if (data_left < 0)
- return error;
- exp = rqst_exp_find(rqstp, fh->fh_fsid_type, fh->fh_fsid);
- fid = (struct fid *)(fh->fh_fsid + len);
- } else {
- __u32 tfh[2];
- dev_t xdev;
- ino_t xino;
-
- if (fh->fh_size != NFS_FHSIZE)
- return error;
- /* assume old filehandle format */
- xdev = old_decode_dev(fh->ofh_xdev);
- xino = u32_to_ino_t(fh->ofh_xino);
- mk_fsid(FSID_DEV, tfh, xdev, xino, 0, NULL);
- exp = rqst_exp_find(rqstp, FSID_DEV, tfh);
+ if (fh->fh_version != 1)
+ return error;
+
+ if (--data_left < 0)
+ return error;
+ if (fh->fh_auth_type != 0)
+ return error;
+ len = key_len(fh->fh_fsid_type) / 4;
+ if (len == 0)
+ return error;
+ if (fh->fh_fsid_type == FSID_MAJOR_MINOR) {
+ /* deprecated, convert to type 3 */
+ len = key_len(FSID_ENCODE_DEV)/4;
+ fh->fh_fsid_type = FSID_ENCODE_DEV;
+ /*
+ * struct knfsd_fh uses host-endian fields, which are
+ * sometimes used to hold net-endian values. This
+ * confuses sparse, so we must use __force here to
+ * keep it from complaining.
+ */
+ fh->fh_fsid[0] = new_encode_dev(MKDEV(ntohl((__force __be32)fh->fh_fsid[0]),
+ ntohl((__force __be32)fh->fh_fsid[1])));
+ fh->fh_fsid[1] = fh->fh_fsid[2];
}
+ data_left -= len;
+ if (data_left < 0)
+ return error;
+ exp = rqst_exp_find(rqstp, fh->fh_fsid_type, fh->fh_fsid);
+ fid = (struct fid *)(fh->fh_fsid + len);
error = nfserr_stale;
if (IS_ERR(exp)) {
@@ -253,18 +241,7 @@ static __be32 nfsd_set_fh_dentry(struct svc_rqst *rqstp, struct svc_fh *fhp)
if (rqstp->rq_vers > 2)
error = nfserr_badhandle;
- if (fh->fh_version != 1) {
- sfid.i32.ino = fh->ofh_ino;
- sfid.i32.gen = fh->ofh_generation;
- sfid.i32.parent_ino = fh->ofh_dirino;
- fid = &sfid;
- data_left = 3;
- if (fh->ofh_dirino == 0)
- fileid_type = FILEID_INO32_GEN;
- else
- fileid_type = FILEID_INO32_GEN_PARENT;
- } else
- fileid_type = fh->fh_fileid_type;
+ fileid_type = fh->fh_fileid_type;
if (fileid_type == FILEID_ROOT)
dentry = dget(exp->ex_path.dentry);
@@ -452,20 +429,6 @@ static void _fh_update(struct svc_fh *fhp, struct svc_export *exp,
}
}
-/*
- * for composing old style file handles
- */
-static inline void _fh_update_old(struct dentry *dentry,
- struct svc_export *exp,
- struct knfsd_fh *fh)
-{
- fh->ofh_ino = ino_t_to_u32(d_inode(dentry)->i_ino);
- fh->ofh_generation = d_inode(dentry)->i_generation;
- if (d_is_dir(dentry) ||
- (exp->ex_flags & NFSEXP_NOSUBTREECHECK))
- fh->ofh_dirino = 0;
-}
-
static bool is_root_export(struct svc_export *exp)
{
return exp->ex_path.dentry == exp->ex_path.dentry->d_sb->s_root;
@@ -562,9 +525,6 @@ fh_compose(struct svc_fh *fhp, struct svc_export *exp, struct dentry *dentry,
/* ref_fh is a reference file handle.
* if it is non-null and for the same filesystem, then we should compose
* a filehandle which is of the same version, where possible.
- * Currently, that means that if ref_fh->fh_handle.fh_version == 0xca
- * Then create a 32byte filehandle using nfs_fhbase_old
- *
*/
struct inode * inode = d_inode(dentry);
@@ -600,35 +560,21 @@ fh_compose(struct svc_fh *fhp, struct svc_export *exp, struct dentry *dentry,
fhp->fh_dentry = dget(dentry); /* our internal copy */
fhp->fh_export = exp_get(exp);
- if (fhp->fh_handle.fh_version == 0xca) {
- /* old style filehandle please */
- memset(&fhp->fh_handle.fh_base, 0, NFS_FHSIZE);
- fhp->fh_handle.fh_size = NFS_FHSIZE;
- fhp->fh_handle.ofh_dcookie = 0xfeebbaca;
- fhp->fh_handle.ofh_dev = old_encode_dev(ex_dev);
- fhp->fh_handle.ofh_xdev = fhp->fh_handle.ofh_dev;
- fhp->fh_handle.ofh_xino =
- ino_t_to_u32(d_inode(exp->ex_path.dentry)->i_ino);
- fhp->fh_handle.ofh_dirino = ino_t_to_u32(parent_ino(dentry));
- if (inode)
- _fh_update_old(dentry, exp, &fhp->fh_handle);
- } else {
- fhp->fh_handle.fh_size =
- key_len(fhp->fh_handle.fh_fsid_type) + 4;
- fhp->fh_handle.fh_auth_type = 0;
-
- mk_fsid(fhp->fh_handle.fh_fsid_type,
- fhp->fh_handle.fh_fsid,
- ex_dev,
- d_inode(exp->ex_path.dentry)->i_ino,
- exp->ex_fsid, exp->ex_uuid);
-
- if (inode)
- _fh_update(fhp, exp, dentry);
- if (fhp->fh_handle.fh_fileid_type == FILEID_INVALID) {
- fh_put(fhp);
- return nfserr_opnotsupp;
- }
+ fhp->fh_handle.fh_size =
+ key_len(fhp->fh_handle.fh_fsid_type) + 4;
+ fhp->fh_handle.fh_auth_type = 0;
+
+ mk_fsid(fhp->fh_handle.fh_fsid_type,
+ fhp->fh_handle.fh_fsid,
+ ex_dev,
+ d_inode(exp->ex_path.dentry)->i_ino,
+ exp->ex_fsid, exp->ex_uuid);
+
+ if (inode)
+ _fh_update(fhp, exp, dentry);
+ if (fhp->fh_handle.fh_fileid_type == FILEID_INVALID) {
+ fh_put(fhp);
+ return nfserr_opnotsupp;
}
return 0;
@@ -649,16 +595,12 @@ fh_update(struct svc_fh *fhp)
dentry = fhp->fh_dentry;
if (d_really_is_negative(dentry))
goto out_negative;
- if (fhp->fh_handle.fh_version != 1) {
- _fh_update_old(dentry, fhp->fh_export, &fhp->fh_handle);
- } else {
- if (fhp->fh_handle.fh_fileid_type != FILEID_ROOT)
- return 0;
+ if (fhp->fh_handle.fh_fileid_type != FILEID_ROOT)
+ return 0;
- _fh_update(fhp, fhp->fh_export, dentry);
- if (fhp->fh_handle.fh_fileid_type == FILEID_INVALID)
- return nfserr_opnotsupp;
- }
+ _fh_update(fhp, fhp->fh_export, dentry);
+ if (fhp->fh_handle.fh_fileid_type == FILEID_INVALID)
+ return nfserr_opnotsupp;
return 0;
out_bad:
printk(KERN_ERR "fh_update: fh not verified!\n");
@@ -698,16 +640,11 @@ fh_put(struct svc_fh *fhp)
char * SVCFH_fmt(struct svc_fh *fhp)
{
struct knfsd_fh *fh = &fhp->fh_handle;
+ static char buf[2+1+1+64*3+1];
- static char buf[80];
- sprintf(buf, "%d: %08x %08x %08x %08x %08x %08x",
- fh->fh_size,
- fh->fh_base.fh_pad[0],
- fh->fh_base.fh_pad[1],
- fh->fh_base.fh_pad[2],
- fh->fh_base.fh_pad[3],
- fh->fh_base.fh_pad[4],
- fh->fh_base.fh_pad[5]);
+ if (fh->fh_size < 0 || fh->fh_size> 64)
+ return "bad-fh";
+ sprintf(buf, "%d: %*ph", fh->fh_size, fh->fh_size, fh->fh_raw);
return buf;
}
diff --git a/fs/nfsd/nfsfh.h b/fs/nfsd/nfsfh.h
index 6106697adc04..d11e4b6870d6 100644
--- a/fs/nfsd/nfsfh.h
+++ b/fs/nfsd/nfsfh.h
@@ -10,9 +10,56 @@
#include <linux/crc32.h>
#include <linux/sunrpc/svc.h>
-#include <uapi/linux/nfsd/nfsfh.h>
#include <linux/iversion.h>
#include <linux/exportfs.h>
+#include <linux/nfs4.h>
+
+/*
+ * The file handle starts with a sequence of four-byte words.
+ * The first word contains a version number (1) and three descriptor bytes
+ * that tell how the remaining 3 variable length fields should be handled.
+ * These three bytes are auth_type, fsid_type and fileid_type.
+ *
+ * All four-byte values are in host-byte-order.
+ *
+ * The auth_type field is deprecated and must be set to 0.
+ *
+ * The fsid_type identifies how the filesystem (or export point) is
+ * encoded.
+ * Current values:
+ * 0 - 4 byte device id (ms-2-bytes major, ls-2-bytes minor), 4byte inode number
+ * NOTE: we cannot use the kdev_t device id value, because kdev_t.h
+ * says we mustn't. We must break it up and reassemble.
+ * 1 - 4 byte user specified identifier
+ * 2 - 4 byte major, 4 byte minor, 4 byte inode number - DEPRECATED
+ * 3 - 4 byte device id, encoded for user-space, 4 byte inode number
+ * 4 - 4 byte inode number and 4 byte uuid
+ * 5 - 8 byte uuid
+ * 6 - 16 byte uuid
+ * 7 - 8 byte inode number and 16 byte uuid
+ *
+ * The fileid_type identifies how the file within the filesystem is encoded.
+ * The values for this field are filesystem specific, exccept that
+ * filesystems must not use the values '0' or '0xff'. 'See enum fid_type'
+ * in include/linux/exportfs.h for currently registered values.
+ */
+
+struct knfsd_fh {
+ unsigned int fh_size; /*
+ * Points to the current size while
+ * building a new file handle.
+ */
+ union {
+ char fh_raw[NFS4_FHSIZE];
+ struct {
+ u8 fh_version; /* == 1 */
+ u8 fh_auth_type; /* deprecated */
+ u8 fh_fsid_type;
+ u8 fh_fileid_type;
+ u32 fh_fsid[]; /* flexible-array member */
+ };
+ };
+};
static inline __u32 ino_t_to_u32(ino_t ino)
{
@@ -188,7 +235,7 @@ static inline void
fh_copy_shallow(struct knfsd_fh *dst, struct knfsd_fh *src)
{
dst->fh_size = src->fh_size;
- memcpy(&dst->fh_base, &src->fh_base, src->fh_size);
+ memcpy(&dst->fh_raw, &src->fh_raw, src->fh_size);
}
static __inline__ struct svc_fh *
@@ -203,7 +250,7 @@ static inline bool fh_match(struct knfsd_fh *fh1, struct knfsd_fh *fh2)
{
if (fh1->fh_size != fh2->fh_size)
return false;
- if (memcmp(fh1->fh_base.fh_pad, fh2->fh_base.fh_pad, fh1->fh_size) != 0)
+ if (memcmp(fh1->fh_raw, fh2->fh_raw, fh1->fh_size) != 0)
return false;
return true;
}
@@ -227,7 +274,7 @@ static inline bool fh_fsid_match(struct knfsd_fh *fh1, struct knfsd_fh *fh2)
*/
static inline u32 knfsd_fh_hash(const struct knfsd_fh *fh)
{
- return ~crc32_le(0xFFFFFFFF, (unsigned char *)&fh->fh_base, fh->fh_size);
+ return ~crc32_le(0xFFFFFFFF, fh->fh_raw, fh->fh_size);
}
#else
static inline u32 knfsd_fh_hash(const struct knfsd_fh *fh)
diff --git a/fs/nfsd/nfsproc.c b/fs/nfsd/nfsproc.c
index 90fcd6178823..eea5b59b6a6c 100644
--- a/fs/nfsd/nfsproc.c
+++ b/fs/nfsd/nfsproc.c
@@ -234,8 +234,7 @@ nfsd_proc_write(struct svc_rqst *rqstp)
SVCFH_fmt(&argp->fh),
argp->len, argp->offset);
- nvecs = svc_fill_write_vector(rqstp, rqstp->rq_arg.pages,
- &argp->first, cnt);
+ nvecs = svc_fill_write_vector(rqstp, &argp->payload);
if (!nvecs) {
resp->status = nfserr_io;
goto out;
diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c
index ccb59e91011b..80431921e5d7 100644
--- a/fs/nfsd/nfssvc.c
+++ b/fs/nfsd/nfssvc.c
@@ -1004,9 +1004,6 @@ out:
int nfsd_dispatch(struct svc_rqst *rqstp, __be32 *statp)
{
const struct svc_procedure *proc = rqstp->rq_procinfo;
- struct kvec *argv = &rqstp->rq_arg.head[0];
- struct kvec *resv = &rqstp->rq_res.head[0];
- __be32 *p;
/*
* Give the xdr decoder a chance to change this if it wants
@@ -1015,7 +1012,7 @@ int nfsd_dispatch(struct svc_rqst *rqstp, __be32 *statp)
rqstp->rq_cachetype = proc->pc_cachetype;
svcxdr_init_decode(rqstp);
- if (!proc->pc_decode(rqstp, argv->iov_base))
+ if (!proc->pc_decode(rqstp, &rqstp->rq_arg_stream))
goto out_decode_err;
switch (nfsd_cache_lookup(rqstp)) {
@@ -1031,14 +1028,13 @@ int nfsd_dispatch(struct svc_rqst *rqstp, __be32 *statp)
* Need to grab the location to store the status, as
* NFSv4 does some encoding while processing
*/
- p = resv->iov_base + resv->iov_len;
svcxdr_init_encode(rqstp);
*statp = proc->pc_func(rqstp);
if (*statp == rpc_drop_reply || test_bit(RQ_DROPME, &rqstp->rq_flags))
goto out_update_drop;
- if (!proc->pc_encode(rqstp, p))
+ if (!proc->pc_encode(rqstp, &rqstp->rq_res_stream))
goto out_encode_err;
nfsd_cache_update(rqstp, rqstp->rq_cachetype, statp + 1);
@@ -1065,29 +1061,29 @@ out_encode_err:
/**
* nfssvc_decode_voidarg - Decode void arguments
* @rqstp: Server RPC transaction context
- * @p: buffer containing arguments to decode
+ * @xdr: XDR stream positioned at arguments to decode
*
* Return values:
- * %0: Arguments were not valid
- * %1: Decoding was successful
+ * %false: Arguments were not valid
+ * %true: Decoding was successful
*/
-int nfssvc_decode_voidarg(struct svc_rqst *rqstp, __be32 *p)
+bool nfssvc_decode_voidarg(struct svc_rqst *rqstp, struct xdr_stream *xdr)
{
- return 1;
+ return true;
}
/**
* nfssvc_encode_voidres - Encode void results
* @rqstp: Server RPC transaction context
- * @p: buffer in which to encode results
+ * @xdr: XDR stream into which to encode results
*
* Return values:
- * %0: Local error while encoding
- * %1: Encoding was successful
+ * %false: Local error while encoding
+ * %true: Encoding was successful
*/
-int nfssvc_encode_voidres(struct svc_rqst *rqstp, __be32 *p)
+bool nfssvc_encode_voidres(struct svc_rqst *rqstp, struct xdr_stream *xdr)
{
- return 1;
+ return true;
}
int nfsd_pool_stats_open(struct inode *inode, struct file *file)
diff --git a/fs/nfsd/nfsxdr.c b/fs/nfsd/nfsxdr.c
index a06c05fe3b42..aba8520b4b8b 100644
--- a/fs/nfsd/nfsxdr.c
+++ b/fs/nfsd/nfsxdr.c
@@ -64,7 +64,7 @@ svcxdr_decode_fhandle(struct xdr_stream *xdr, struct svc_fh *fhp)
if (!p)
return false;
fh_init(fhp, NFS_FHSIZE);
- memcpy(&fhp->fh_handle.fh_base, p, NFS_FHSIZE);
+ memcpy(&fhp->fh_handle.fh_raw, p, NFS_FHSIZE);
fhp->fh_handle.fh_size = NFS_FHSIZE;
return true;
@@ -78,7 +78,7 @@ svcxdr_encode_fhandle(struct xdr_stream *xdr, const struct svc_fh *fhp)
p = xdr_reserve_space(xdr, NFS_FHSIZE);
if (!p)
return false;
- memcpy(p, &fhp->fh_handle.fh_base, NFS_FHSIZE);
+ memcpy(p, &fhp->fh_handle.fh_raw, NFS_FHSIZE);
return true;
}
@@ -272,94 +272,81 @@ svcxdr_encode_fattr(struct svc_rqst *rqstp, struct xdr_stream *xdr,
* XDR decode functions
*/
-int
-nfssvc_decode_fhandleargs(struct svc_rqst *rqstp, __be32 *p)
+bool
+nfssvc_decode_fhandleargs(struct svc_rqst *rqstp, struct xdr_stream *xdr)
{
- struct xdr_stream *xdr = &rqstp->rq_arg_stream;
struct nfsd_fhandle *args = rqstp->rq_argp;
return svcxdr_decode_fhandle(xdr, &args->fh);
}
-int
-nfssvc_decode_sattrargs(struct svc_rqst *rqstp, __be32 *p)
+bool
+nfssvc_decode_sattrargs(struct svc_rqst *rqstp, struct xdr_stream *xdr)
{
- struct xdr_stream *xdr = &rqstp->rq_arg_stream;
struct nfsd_sattrargs *args = rqstp->rq_argp;
return svcxdr_decode_fhandle(xdr, &args->fh) &&
svcxdr_decode_sattr(rqstp, xdr, &args->attrs);
}
-int
-nfssvc_decode_diropargs(struct svc_rqst *rqstp, __be32 *p)
+bool
+nfssvc_decode_diropargs(struct svc_rqst *rqstp, struct xdr_stream *xdr)
{
- struct xdr_stream *xdr = &rqstp->rq_arg_stream;
struct nfsd_diropargs *args = rqstp->rq_argp;
return svcxdr_decode_diropargs(xdr, &args->fh, &args->name, &args->len);
}
-int
-nfssvc_decode_readargs(struct svc_rqst *rqstp, __be32 *p)
+bool
+nfssvc_decode_readargs(struct svc_rqst *rqstp, struct xdr_stream *xdr)
{
- struct xdr_stream *xdr = &rqstp->rq_arg_stream;
struct nfsd_readargs *args = rqstp->rq_argp;
u32 totalcount;
if (!svcxdr_decode_fhandle(xdr, &args->fh))
- return 0;
+ return false;
if (xdr_stream_decode_u32(xdr, &args->offset) < 0)
- return 0;
+ return false;
if (xdr_stream_decode_u32(xdr, &args->count) < 0)
- return 0;
+ return false;
/* totalcount is ignored */
if (xdr_stream_decode_u32(xdr, &totalcount) < 0)
- return 0;
+ return false;
- return 1;
+ return true;
}
-int
-nfssvc_decode_writeargs(struct svc_rqst *rqstp, __be32 *p)
+bool
+nfssvc_decode_writeargs(struct svc_rqst *rqstp, struct xdr_stream *xdr)
{
- struct xdr_stream *xdr = &rqstp->rq_arg_stream;
struct nfsd_writeargs *args = rqstp->rq_argp;
- struct kvec *head = rqstp->rq_arg.head;
- struct kvec *tail = rqstp->rq_arg.tail;
u32 beginoffset, totalcount;
- size_t remaining;
if (!svcxdr_decode_fhandle(xdr, &args->fh))
- return 0;
+ return false;
/* beginoffset is ignored */
if (xdr_stream_decode_u32(xdr, &beginoffset) < 0)
- return 0;
+ return false;
if (xdr_stream_decode_u32(xdr, &args->offset) < 0)
- return 0;
+ return false;
/* totalcount is ignored */
if (xdr_stream_decode_u32(xdr, &totalcount) < 0)
- return 0;
+ return false;
/* opaque data */
if (xdr_stream_decode_u32(xdr, &args->len) < 0)
- return 0;
+ return false;
if (args->len > NFSSVC_MAXBLKSIZE_V2)
- return 0;
- remaining = head->iov_len + rqstp->rq_arg.page_len + tail->iov_len;
- remaining -= xdr_stream_pos(xdr);
- if (remaining < xdr_align_size(args->len))
- return 0;
- args->first.iov_base = xdr->p;
- args->first.iov_len = head->iov_len - xdr_stream_pos(xdr);
+ return false;
+ if (!xdr_stream_subsegment(xdr, &args->payload, args->len))
+ return false;
- return 1;
+ return true;
}
-int
-nfssvc_decode_createargs(struct svc_rqst *rqstp, __be32 *p)
+bool
+nfssvc_decode_createargs(struct svc_rqst *rqstp, struct xdr_stream *xdr)
{
- struct xdr_stream *xdr = &rqstp->rq_arg_stream;
struct nfsd_createargs *args = rqstp->rq_argp;
return svcxdr_decode_diropargs(xdr, &args->fh,
@@ -367,10 +354,9 @@ nfssvc_decode_createargs(struct svc_rqst *rqstp, __be32 *p)
svcxdr_decode_sattr(rqstp, xdr, &args->attrs);
}
-int
-nfssvc_decode_renameargs(struct svc_rqst *rqstp, __be32 *p)
+bool
+nfssvc_decode_renameargs(struct svc_rqst *rqstp, struct xdr_stream *xdr)
{
- struct xdr_stream *xdr = &rqstp->rq_arg_stream;
struct nfsd_renameargs *args = rqstp->rq_argp;
return svcxdr_decode_diropargs(xdr, &args->ffh,
@@ -379,10 +365,9 @@ nfssvc_decode_renameargs(struct svc_rqst *rqstp, __be32 *p)
&args->tname, &args->tlen);
}
-int
-nfssvc_decode_linkargs(struct svc_rqst *rqstp, __be32 *p)
+bool
+nfssvc_decode_linkargs(struct svc_rqst *rqstp, struct xdr_stream *xdr)
{
- struct xdr_stream *xdr = &rqstp->rq_arg_stream;
struct nfsd_linkargs *args = rqstp->rq_argp;
return svcxdr_decode_fhandle(xdr, &args->ffh) &&
@@ -390,178 +375,170 @@ nfssvc_decode_linkargs(struct svc_rqst *rqstp, __be32 *p)
&args->tname, &args->tlen);
}
-int
-nfssvc_decode_symlinkargs(struct svc_rqst *rqstp, __be32 *p)
+bool
+nfssvc_decode_symlinkargs(struct svc_rqst *rqstp, struct xdr_stream *xdr)
{
- struct xdr_stream *xdr = &rqstp->rq_arg_stream;
struct nfsd_symlinkargs *args = rqstp->rq_argp;
struct kvec *head = rqstp->rq_arg.head;
if (!svcxdr_decode_diropargs(xdr, &args->ffh, &args->fname, &args->flen))
- return 0;
+ return false;
if (xdr_stream_decode_u32(xdr, &args->tlen) < 0)
- return 0;
+ return false;
if (args->tlen == 0)
- return 0;
+ return false;
args->first.iov_len = head->iov_len - xdr_stream_pos(xdr);
args->first.iov_base = xdr_inline_decode(xdr, args->tlen);
if (!args->first.iov_base)
- return 0;
+ return false;
return svcxdr_decode_sattr(rqstp, xdr, &args->attrs);
}
-int
-nfssvc_decode_readdirargs(struct svc_rqst *rqstp, __be32 *p)
+bool
+nfssvc_decode_readdirargs(struct svc_rqst *rqstp, struct xdr_stream *xdr)
{
- struct xdr_stream *xdr = &rqstp->rq_arg_stream;
struct nfsd_readdirargs *args = rqstp->rq_argp;
if (!svcxdr_decode_fhandle(xdr, &args->fh))
- return 0;
+ return false;
if (xdr_stream_decode_u32(xdr, &args->cookie) < 0)
- return 0;
+ return false;
if (xdr_stream_decode_u32(xdr, &args->count) < 0)
- return 0;
+ return false;
- return 1;
+ return true;
}
/*
* XDR encode functions
*/
-int
-nfssvc_encode_statres(struct svc_rqst *rqstp, __be32 *p)
+bool
+nfssvc_encode_statres(struct svc_rqst *rqstp, struct xdr_stream *xdr)
{
- struct xdr_stream *xdr = &rqstp->rq_res_stream;
struct nfsd_stat *resp = rqstp->rq_resp;
return svcxdr_encode_stat(xdr, resp->status);
}
-int
-nfssvc_encode_attrstatres(struct svc_rqst *rqstp, __be32 *p)
+bool
+nfssvc_encode_attrstatres(struct svc_rqst *rqstp, struct xdr_stream *xdr)
{
- struct xdr_stream *xdr = &rqstp->rq_res_stream;
struct nfsd_attrstat *resp = rqstp->rq_resp;
if (!svcxdr_encode_stat(xdr, resp->status))
- return 0;
+ return false;
switch (resp->status) {
case nfs_ok:
if (!svcxdr_encode_fattr(rqstp, xdr, &resp->fh, &resp->stat))
- return 0;
+ return false;
break;
}
- return 1;
+ return true;
}
-int
-nfssvc_encode_diropres(struct svc_rqst *rqstp, __be32 *p)
+bool
+nfssvc_encode_diropres(struct svc_rqst *rqstp, struct xdr_stream *xdr)
{
- struct xdr_stream *xdr = &rqstp->rq_res_stream;
struct nfsd_diropres *resp = rqstp->rq_resp;
if (!svcxdr_encode_stat(xdr, resp->status))
- return 0;
+ return false;
switch (resp->status) {
case nfs_ok:
if (!svcxdr_encode_fhandle(xdr, &resp->fh))
- return 0;
+ return false;
if (!svcxdr_encode_fattr(rqstp, xdr, &resp->fh, &resp->stat))
- return 0;
+ return false;
break;
}
- return 1;
+ return true;
}
-int
-nfssvc_encode_readlinkres(struct svc_rqst *rqstp, __be32 *p)
+bool
+nfssvc_encode_readlinkres(struct svc_rqst *rqstp, struct xdr_stream *xdr)
{
- struct xdr_stream *xdr = &rqstp->rq_res_stream;
struct nfsd_readlinkres *resp = rqstp->rq_resp;
struct kvec *head = rqstp->rq_res.head;
if (!svcxdr_encode_stat(xdr, resp->status))
- return 0;
+ return false;
switch (resp->status) {
case nfs_ok:
if (xdr_stream_encode_u32(xdr, resp->len) < 0)
- return 0;
+ return false;
xdr_write_pages(xdr, &resp->page, 0, resp->len);
if (svc_encode_result_payload(rqstp, head->iov_len, resp->len) < 0)
- return 0;
+ return false;
break;
}
- return 1;
+ return true;
}
-int
-nfssvc_encode_readres(struct svc_rqst *rqstp, __be32 *p)
+bool
+nfssvc_encode_readres(struct svc_rqst *rqstp, struct xdr_stream *xdr)
{
- struct xdr_stream *xdr = &rqstp->rq_res_stream;
struct nfsd_readres *resp = rqstp->rq_resp;
struct kvec *head = rqstp->rq_res.head;
if (!svcxdr_encode_stat(xdr, resp->status))
- return 0;
+ return false;
switch (resp->status) {
case nfs_ok:
if (!svcxdr_encode_fattr(rqstp, xdr, &resp->fh, &resp->stat))
- return 0;
+ return false;
if (xdr_stream_encode_u32(xdr, resp->count) < 0)
- return 0;
+ return false;
xdr_write_pages(xdr, resp->pages, rqstp->rq_res.page_base,
resp->count);
if (svc_encode_result_payload(rqstp, head->iov_len, resp->count) < 0)
- return 0;
+ return false;
break;
}
- return 1;
+ return true;
}
-int
-nfssvc_encode_readdirres(struct svc_rqst *rqstp, __be32 *p)
+bool
+nfssvc_encode_readdirres(struct svc_rqst *rqstp, struct xdr_stream *xdr)
{
- struct xdr_stream *xdr = &rqstp->rq_res_stream;
struct nfsd_readdirres *resp = rqstp->rq_resp;
struct xdr_buf *dirlist = &resp->dirlist;
if (!svcxdr_encode_stat(xdr, resp->status))
- return 0;
+ return false;
switch (resp->status) {
case nfs_ok:
xdr_write_pages(xdr, dirlist->pages, 0, dirlist->len);
/* no more entries */
if (xdr_stream_encode_item_absent(xdr) < 0)
- return 0;
+ return false;
if (xdr_stream_encode_bool(xdr, resp->common.err == nfserr_eof) < 0)
- return 0;
+ return false;
break;
}
- return 1;
+ return true;
}
-int
-nfssvc_encode_statfsres(struct svc_rqst *rqstp, __be32 *p)
+bool
+nfssvc_encode_statfsres(struct svc_rqst *rqstp, struct xdr_stream *xdr)
{
- struct xdr_stream *xdr = &rqstp->rq_res_stream;
struct nfsd_statfsres *resp = rqstp->rq_resp;
struct kstatfs *stat = &resp->stats;
+ __be32 *p;
if (!svcxdr_encode_stat(xdr, resp->status))
- return 0;
+ return false;
switch (resp->status) {
case nfs_ok:
p = xdr_reserve_space(xdr, XDR_UNIT * 5);
if (!p)
- return 0;
+ return false;
*p++ = cpu_to_be32(NFSSVC_MAXBLKSIZE_V2);
*p++ = cpu_to_be32(stat->f_bsize);
*p++ = cpu_to_be32(stat->f_blocks);
@@ -570,7 +547,7 @@ nfssvc_encode_statfsres(struct svc_rqst *rqstp, __be32 *p)
break;
}
- return 1;
+ return true;
}
/**
diff --git a/fs/nfsd/trace.h b/fs/nfsd/trace.h
index 538520957a81..f1e0d3c51bc2 100644
--- a/fs/nfsd/trace.h
+++ b/fs/nfsd/trace.h
@@ -9,6 +9,7 @@
#define _NFSD_TRACE_H
#include <linux/tracepoint.h>
+
#include "export.h"
#include "nfsfh.h"
diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c
index 738d564ca4ce..c99857689e2c 100644
--- a/fs/nfsd/vfs.c
+++ b/fs/nfsd/vfs.c
@@ -244,6 +244,7 @@ out_nfserr:
* returned. Otherwise the covered directory is returned.
* NOTE: this mountpoint crossing is not supported properly by all
* clients and is explicitly disallowed for NFSv3
+ * NeilBrown <neilb@cse.unsw.edu.au>
*/
__be32
nfsd_lookup(struct svc_rqst *rqstp, struct svc_fh *fhp, const char *name,
@@ -729,9 +730,6 @@ __nfsd_open(struct svc_rqst *rqstp, struct svc_fh *fhp, umode_t type,
path.dentry = fhp->fh_dentry;
inode = d_inode(path.dentry);
- /* Disallow write access to files with the append-only bit set
- * or any access when mandatory locking enabled
- */
err = nfserr_perm;
if (IS_APPEND(inode) && (may_flags & NFSD_MAY_WRITE))
goto out;
@@ -1410,7 +1408,8 @@ do_nfsd_create(struct svc_rqst *rqstp, struct svc_fh *fhp,
if (nfsd_create_is_exclusive(createmode)) {
/* solaris7 gets confused (bugid 4218508) if these have
- * the high bit set, so just clear the high bits. If this is
+ * the high bit set, as do xfs filesystems without the
+ * "bigtime" feature. So just clear the high bits. If this is
* ever changed to use different attrs for storing the
* verifier, then do_open_lookup() will also need to be fixed
* accordingly.
diff --git a/fs/nfsd/xdr.h b/fs/nfsd/xdr.h
index f45b4bc93f52..528fb299430e 100644
--- a/fs/nfsd/xdr.h
+++ b/fs/nfsd/xdr.h
@@ -33,7 +33,7 @@ struct nfsd_writeargs {
svc_fh fh;
__u32 offset;
int len;
- struct kvec first;
+ struct xdr_buf payload;
};
struct nfsd_createargs {
@@ -141,23 +141,24 @@ union nfsd_xdrstore {
#define NFS2_SVC_XDRSIZE sizeof(union nfsd_xdrstore)
-int nfssvc_decode_fhandleargs(struct svc_rqst *, __be32 *);
-int nfssvc_decode_sattrargs(struct svc_rqst *, __be32 *);
-int nfssvc_decode_diropargs(struct svc_rqst *, __be32 *);
-int nfssvc_decode_readargs(struct svc_rqst *, __be32 *);
-int nfssvc_decode_writeargs(struct svc_rqst *, __be32 *);
-int nfssvc_decode_createargs(struct svc_rqst *, __be32 *);
-int nfssvc_decode_renameargs(struct svc_rqst *, __be32 *);
-int nfssvc_decode_linkargs(struct svc_rqst *, __be32 *);
-int nfssvc_decode_symlinkargs(struct svc_rqst *, __be32 *);
-int nfssvc_decode_readdirargs(struct svc_rqst *, __be32 *);
-int nfssvc_encode_statres(struct svc_rqst *, __be32 *);
-int nfssvc_encode_attrstatres(struct svc_rqst *, __be32 *);
-int nfssvc_encode_diropres(struct svc_rqst *, __be32 *);
-int nfssvc_encode_readlinkres(struct svc_rqst *, __be32 *);
-int nfssvc_encode_readres(struct svc_rqst *, __be32 *);
-int nfssvc_encode_statfsres(struct svc_rqst *, __be32 *);
-int nfssvc_encode_readdirres(struct svc_rqst *, __be32 *);
+bool nfssvc_decode_fhandleargs(struct svc_rqst *rqstp, struct xdr_stream *xdr);
+bool nfssvc_decode_sattrargs(struct svc_rqst *rqstp, struct xdr_stream *xdr);
+bool nfssvc_decode_diropargs(struct svc_rqst *rqstp, struct xdr_stream *xdr);
+bool nfssvc_decode_readargs(struct svc_rqst *rqstp, struct xdr_stream *xdr);
+bool nfssvc_decode_writeargs(struct svc_rqst *rqstp, struct xdr_stream *xdr);
+bool nfssvc_decode_createargs(struct svc_rqst *rqstp, struct xdr_stream *xdr);
+bool nfssvc_decode_renameargs(struct svc_rqst *rqstp, struct xdr_stream *xdr);
+bool nfssvc_decode_linkargs(struct svc_rqst *rqstp, struct xdr_stream *xdr);
+bool nfssvc_decode_symlinkargs(struct svc_rqst *rqstp, struct xdr_stream *xdr);
+bool nfssvc_decode_readdirargs(struct svc_rqst *rqstp, struct xdr_stream *xdr);
+
+bool nfssvc_encode_statres(struct svc_rqst *rqstp, struct xdr_stream *xdr);
+bool nfssvc_encode_attrstatres(struct svc_rqst *rqstp, struct xdr_stream *xdr);
+bool nfssvc_encode_diropres(struct svc_rqst *rqstp, struct xdr_stream *xdr);
+bool nfssvc_encode_readlinkres(struct svc_rqst *rqstp, struct xdr_stream *xdr);
+bool nfssvc_encode_readres(struct svc_rqst *rqstp, struct xdr_stream *xdr);
+bool nfssvc_encode_statfsres(struct svc_rqst *rqstp, struct xdr_stream *xdr);
+bool nfssvc_encode_readdirres(struct svc_rqst *rqstp, struct xdr_stream *xdr);
void nfssvc_encode_nfscookie(struct nfsd_readdirres *resp, u32 offset);
int nfssvc_encode_entry(void *data, const char *name, int namlen,
diff --git a/fs/nfsd/xdr3.h b/fs/nfsd/xdr3.h
index 933008382bbe..03fe4e21306c 100644
--- a/fs/nfsd/xdr3.h
+++ b/fs/nfsd/xdr3.h
@@ -40,7 +40,7 @@ struct nfsd3_writeargs {
__u32 count;
int stable;
__u32 len;
- struct kvec first;
+ struct xdr_buf payload;
};
struct nfsd3_createargs {
@@ -265,36 +265,37 @@ union nfsd3_xdrstore {
#define NFS3_SVC_XDRSIZE sizeof(union nfsd3_xdrstore)
-int nfs3svc_decode_fhandleargs(struct svc_rqst *, __be32 *);
-int nfs3svc_decode_sattrargs(struct svc_rqst *, __be32 *);
-int nfs3svc_decode_diropargs(struct svc_rqst *, __be32 *);
-int nfs3svc_decode_accessargs(struct svc_rqst *, __be32 *);
-int nfs3svc_decode_readargs(struct svc_rqst *, __be32 *);
-int nfs3svc_decode_writeargs(struct svc_rqst *, __be32 *);
-int nfs3svc_decode_createargs(struct svc_rqst *, __be32 *);
-int nfs3svc_decode_mkdirargs(struct svc_rqst *, __be32 *);
-int nfs3svc_decode_mknodargs(struct svc_rqst *, __be32 *);
-int nfs3svc_decode_renameargs(struct svc_rqst *, __be32 *);
-int nfs3svc_decode_linkargs(struct svc_rqst *, __be32 *);
-int nfs3svc_decode_symlinkargs(struct svc_rqst *, __be32 *);
-int nfs3svc_decode_readdirargs(struct svc_rqst *, __be32 *);
-int nfs3svc_decode_readdirplusargs(struct svc_rqst *, __be32 *);
-int nfs3svc_decode_commitargs(struct svc_rqst *, __be32 *);
-int nfs3svc_encode_getattrres(struct svc_rqst *, __be32 *);
-int nfs3svc_encode_wccstat(struct svc_rqst *, __be32 *);
-int nfs3svc_encode_lookupres(struct svc_rqst *, __be32 *);
-int nfs3svc_encode_accessres(struct svc_rqst *, __be32 *);
-int nfs3svc_encode_readlinkres(struct svc_rqst *, __be32 *);
-int nfs3svc_encode_readres(struct svc_rqst *, __be32 *);
-int nfs3svc_encode_writeres(struct svc_rqst *, __be32 *);
-int nfs3svc_encode_createres(struct svc_rqst *, __be32 *);
-int nfs3svc_encode_renameres(struct svc_rqst *, __be32 *);
-int nfs3svc_encode_linkres(struct svc_rqst *, __be32 *);
-int nfs3svc_encode_readdirres(struct svc_rqst *, __be32 *);
-int nfs3svc_encode_fsstatres(struct svc_rqst *, __be32 *);
-int nfs3svc_encode_fsinfores(struct svc_rqst *, __be32 *);
-int nfs3svc_encode_pathconfres(struct svc_rqst *, __be32 *);
-int nfs3svc_encode_commitres(struct svc_rqst *, __be32 *);
+bool nfs3svc_decode_fhandleargs(struct svc_rqst *rqstp, struct xdr_stream *xdr);
+bool nfs3svc_decode_sattrargs(struct svc_rqst *rqstp, struct xdr_stream *xdr);
+bool nfs3svc_decode_diropargs(struct svc_rqst *rqstp, struct xdr_stream *xdr);
+bool nfs3svc_decode_accessargs(struct svc_rqst *rqstp, struct xdr_stream *xdr);
+bool nfs3svc_decode_readargs(struct svc_rqst *rqstp, struct xdr_stream *xdr);
+bool nfs3svc_decode_writeargs(struct svc_rqst *rqstp, struct xdr_stream *xdr);
+bool nfs3svc_decode_createargs(struct svc_rqst *rqstp, struct xdr_stream *xdr);
+bool nfs3svc_decode_mkdirargs(struct svc_rqst *rqstp, struct xdr_stream *xdr);
+bool nfs3svc_decode_mknodargs(struct svc_rqst *rqstp, struct xdr_stream *xdr);
+bool nfs3svc_decode_renameargs(struct svc_rqst *rqstp, struct xdr_stream *xdr);
+bool nfs3svc_decode_linkargs(struct svc_rqst *rqstp, struct xdr_stream *xdr);
+bool nfs3svc_decode_symlinkargs(struct svc_rqst *rqstp, struct xdr_stream *xdr);
+bool nfs3svc_decode_readdirargs(struct svc_rqst *rqstp, struct xdr_stream *xdr);
+bool nfs3svc_decode_readdirplusargs(struct svc_rqst *rqstp, struct xdr_stream *xdr);
+bool nfs3svc_decode_commitargs(struct svc_rqst *rqstp, struct xdr_stream *xdr);
+
+bool nfs3svc_encode_getattrres(struct svc_rqst *rqstp, struct xdr_stream *xdr);
+bool nfs3svc_encode_wccstat(struct svc_rqst *rqstp, struct xdr_stream *xdr);
+bool nfs3svc_encode_lookupres(struct svc_rqst *rqstp, struct xdr_stream *xdr);
+bool nfs3svc_encode_accessres(struct svc_rqst *rqstp, struct xdr_stream *xdr);
+bool nfs3svc_encode_readlinkres(struct svc_rqst *rqstp, struct xdr_stream *xdr);
+bool nfs3svc_encode_readres(struct svc_rqst *rqstp, struct xdr_stream *xdr);
+bool nfs3svc_encode_writeres(struct svc_rqst *rqstp, struct xdr_stream *xdr);
+bool nfs3svc_encode_createres(struct svc_rqst *rqstp, struct xdr_stream *xdr);
+bool nfs3svc_encode_renameres(struct svc_rqst *rqstp, struct xdr_stream *xdr);
+bool nfs3svc_encode_linkres(struct svc_rqst *rqstp, struct xdr_stream *xdr);
+bool nfs3svc_encode_readdirres(struct svc_rqst *rqstp, struct xdr_stream *xdr);
+bool nfs3svc_encode_fsstatres(struct svc_rqst *rqstp, struct xdr_stream *xdr);
+bool nfs3svc_encode_fsinfores(struct svc_rqst *rqstp, struct xdr_stream *xdr);
+bool nfs3svc_encode_pathconfres(struct svc_rqst *rqstp, struct xdr_stream *xdr);
+bool nfs3svc_encode_commitres(struct svc_rqst *rqstp, struct xdr_stream *xdr);
void nfs3svc_release_fhandle(struct svc_rqst *);
void nfs3svc_release_fhandle2(struct svc_rqst *);
diff --git a/fs/nfsd/xdr4.h b/fs/nfsd/xdr4.h
index 3e4052e3bd50..846ab6df9d48 100644
--- a/fs/nfsd/xdr4.h
+++ b/fs/nfsd/xdr4.h
@@ -702,10 +702,11 @@ struct nfsd4_compoundres {
struct xdr_stream *xdr;
struct svc_rqst * rqstp;
+ __be32 *statusp;
u32 taglen;
char * tag;
u32 opcnt;
- __be32 * tagp; /* tag, opcount encode location */
+
struct nfsd4_compound_state cstate;
};
@@ -756,8 +757,8 @@ set_change_info(struct nfsd4_change_info *cinfo, struct svc_fh *fhp)
bool nfsd4_mach_creds_match(struct nfs4_client *cl, struct svc_rqst *rqstp);
-int nfs4svc_decode_compoundargs(struct svc_rqst *, __be32 *);
-int nfs4svc_encode_compoundres(struct svc_rqst *, __be32 *);
+bool nfs4svc_decode_compoundargs(struct svc_rqst *rqstp, struct xdr_stream *xdr);
+bool nfs4svc_encode_compoundres(struct svc_rqst *rqstp, struct xdr_stream *xdr);
__be32 nfsd4_check_resp_size(struct nfsd4_compoundres *, u32);
void nfsd4_encode_operation(struct nfsd4_compoundres *, struct nfsd4_op *);
void nfsd4_encode_replay(struct xdr_stream *xdr, struct nfsd4_op *op);
diff --git a/fs/nilfs2/alloc.c b/fs/nilfs2/alloc.c
index adf3bb0a8048..6ce8617b562d 100644
--- a/fs/nilfs2/alloc.c
+++ b/fs/nilfs2/alloc.c
@@ -1,6 +1,6 @@
// SPDX-License-Identifier: GPL-2.0+
/*
- * alloc.c - NILFS dat/inode allocator
+ * NILFS dat/inode allocator
*
* Copyright (C) 2006-2008 Nippon Telegraph and Telephone Corporation.
*
diff --git a/fs/nilfs2/alloc.h b/fs/nilfs2/alloc.h
index 0303c3968cee..b667e869ac07 100644
--- a/fs/nilfs2/alloc.h
+++ b/fs/nilfs2/alloc.h
@@ -1,6 +1,6 @@
/* SPDX-License-Identifier: GPL-2.0+ */
/*
- * alloc.h - persistent object (dat entry/disk inode) allocator/deallocator
+ * Persistent object (dat entry/disk inode) allocator/deallocator
*
* Copyright (C) 2006-2008 Nippon Telegraph and Telephone Corporation.
*
diff --git a/fs/nilfs2/bmap.c b/fs/nilfs2/bmap.c
index 5900879d5693..798a2c1b38c6 100644
--- a/fs/nilfs2/bmap.c
+++ b/fs/nilfs2/bmap.c
@@ -1,6 +1,6 @@
// SPDX-License-Identifier: GPL-2.0+
/*
- * bmap.c - NILFS block mapping.
+ * NILFS block mapping.
*
* Copyright (C) 2006-2008 Nippon Telegraph and Telephone Corporation.
*
diff --git a/fs/nilfs2/bmap.h b/fs/nilfs2/bmap.h
index 2c63858e81c9..608168a5cb88 100644
--- a/fs/nilfs2/bmap.h
+++ b/fs/nilfs2/bmap.h
@@ -1,6 +1,6 @@
/* SPDX-License-Identifier: GPL-2.0+ */
/*
- * bmap.h - NILFS block mapping.
+ * NILFS block mapping.
*
* Copyright (C) 2006-2008 Nippon Telegraph and Telephone Corporation.
*
diff --git a/fs/nilfs2/btnode.c b/fs/nilfs2/btnode.c
index 4391fd3abd8f..66bdaa2cf496 100644
--- a/fs/nilfs2/btnode.c
+++ b/fs/nilfs2/btnode.c
@@ -1,6 +1,6 @@
// SPDX-License-Identifier: GPL-2.0+
/*
- * btnode.c - NILFS B-tree node cache
+ * NILFS B-tree node cache
*
* Copyright (C) 2005-2008 Nippon Telegraph and Telephone Corporation.
*
diff --git a/fs/nilfs2/btnode.h b/fs/nilfs2/btnode.h
index 0f88dbc9bcb3..11663650add7 100644
--- a/fs/nilfs2/btnode.h
+++ b/fs/nilfs2/btnode.h
@@ -1,6 +1,6 @@
/* SPDX-License-Identifier: GPL-2.0+ */
/*
- * btnode.h - NILFS B-tree node cache
+ * NILFS B-tree node cache
*
* Copyright (C) 2005-2008 Nippon Telegraph and Telephone Corporation.
*
diff --git a/fs/nilfs2/btree.c b/fs/nilfs2/btree.c
index ab9ec073330f..3594eabe1419 100644
--- a/fs/nilfs2/btree.c
+++ b/fs/nilfs2/btree.c
@@ -1,6 +1,6 @@
// SPDX-License-Identifier: GPL-2.0+
/*
- * btree.c - NILFS B-tree.
+ * NILFS B-tree.
*
* Copyright (C) 2005-2008 Nippon Telegraph and Telephone Corporation.
*
diff --git a/fs/nilfs2/btree.h b/fs/nilfs2/btree.h
index d1421b646ce4..92868e1a48ca 100644
--- a/fs/nilfs2/btree.h
+++ b/fs/nilfs2/btree.h
@@ -1,6 +1,6 @@
/* SPDX-License-Identifier: GPL-2.0+ */
/*
- * btree.h - NILFS B-tree.
+ * NILFS B-tree.
*
* Copyright (C) 2005-2008 Nippon Telegraph and Telephone Corporation.
*
diff --git a/fs/nilfs2/cpfile.c b/fs/nilfs2/cpfile.c
index ce144776b4ef..9ebefb3acb0e 100644
--- a/fs/nilfs2/cpfile.c
+++ b/fs/nilfs2/cpfile.c
@@ -1,6 +1,6 @@
// SPDX-License-Identifier: GPL-2.0+
/*
- * cpfile.c - NILFS checkpoint file.
+ * NILFS checkpoint file.
*
* Copyright (C) 2006-2008 Nippon Telegraph and Telephone Corporation.
*
diff --git a/fs/nilfs2/cpfile.h b/fs/nilfs2/cpfile.h
index 6336222df24a..edabb2dc5756 100644
--- a/fs/nilfs2/cpfile.h
+++ b/fs/nilfs2/cpfile.h
@@ -1,6 +1,6 @@
/* SPDX-License-Identifier: GPL-2.0+ */
/*
- * cpfile.h - NILFS checkpoint file.
+ * NILFS checkpoint file.
*
* Copyright (C) 2006-2008 Nippon Telegraph and Telephone Corporation.
*
diff --git a/fs/nilfs2/dat.c b/fs/nilfs2/dat.c
index 8bccdf1158fc..dc51d3b7a7bf 100644
--- a/fs/nilfs2/dat.c
+++ b/fs/nilfs2/dat.c
@@ -1,6 +1,6 @@
// SPDX-License-Identifier: GPL-2.0+
/*
- * dat.c - NILFS disk address translation.
+ * NILFS disk address translation.
*
* Copyright (C) 2006-2008 Nippon Telegraph and Telephone Corporation.
*
diff --git a/fs/nilfs2/dat.h b/fs/nilfs2/dat.h
index b17ee34580ae..468c82d26183 100644
--- a/fs/nilfs2/dat.h
+++ b/fs/nilfs2/dat.h
@@ -1,6 +1,6 @@
/* SPDX-License-Identifier: GPL-2.0+ */
/*
- * dat.h - NILFS disk address translation.
+ * NILFS disk address translation.
*
* Copyright (C) 2006-2008 Nippon Telegraph and Telephone Corporation.
*
diff --git a/fs/nilfs2/dir.c b/fs/nilfs2/dir.c
index 81394e22d0a0..f8f4c2ff52f4 100644
--- a/fs/nilfs2/dir.c
+++ b/fs/nilfs2/dir.c
@@ -1,6 +1,6 @@
// SPDX-License-Identifier: GPL-2.0+
/*
- * dir.c - NILFS directory entry operations
+ * NILFS directory entry operations
*
* Copyright (C) 2005-2008 Nippon Telegraph and Telephone Corporation.
*
diff --git a/fs/nilfs2/direct.c b/fs/nilfs2/direct.c
index f353101955e3..a35f2795b242 100644
--- a/fs/nilfs2/direct.c
+++ b/fs/nilfs2/direct.c
@@ -1,6 +1,6 @@
// SPDX-License-Identifier: GPL-2.0+
/*
- * direct.c - NILFS direct block pointer.
+ * NILFS direct block pointer.
*
* Copyright (C) 2006-2008 Nippon Telegraph and Telephone Corporation.
*
diff --git a/fs/nilfs2/direct.h b/fs/nilfs2/direct.h
index ec9a23c77994..b7ca896269af 100644
--- a/fs/nilfs2/direct.h
+++ b/fs/nilfs2/direct.h
@@ -1,6 +1,6 @@
/* SPDX-License-Identifier: GPL-2.0+ */
/*
- * direct.h - NILFS direct block pointer.
+ * NILFS direct block pointer.
*
* Copyright (C) 2006-2008 Nippon Telegraph and Telephone Corporation.
*
diff --git a/fs/nilfs2/file.c b/fs/nilfs2/file.c
index 7cf765258fda..a265d391ffe9 100644
--- a/fs/nilfs2/file.c
+++ b/fs/nilfs2/file.c
@@ -1,6 +1,6 @@
// SPDX-License-Identifier: GPL-2.0+
/*
- * file.c - NILFS regular file handling primitives including fsync().
+ * NILFS regular file handling primitives including fsync().
*
* Copyright (C) 2005-2008 Nippon Telegraph and Telephone Corporation.
*
diff --git a/fs/nilfs2/gcinode.c b/fs/nilfs2/gcinode.c
index 448320496856..a8f5315f01e3 100644
--- a/fs/nilfs2/gcinode.c
+++ b/fs/nilfs2/gcinode.c
@@ -1,6 +1,6 @@
// SPDX-License-Identifier: GPL-2.0+
/*
- * gcinode.c - dummy inodes to buffer blocks for garbage collection
+ * Dummy inodes to buffer blocks for garbage collection
*
* Copyright (C) 2005-2008 Nippon Telegraph and Telephone Corporation.
*
diff --git a/fs/nilfs2/ifile.c b/fs/nilfs2/ifile.c
index 02727ed3a7c6..a8a4bc8490b4 100644
--- a/fs/nilfs2/ifile.c
+++ b/fs/nilfs2/ifile.c
@@ -1,6 +1,6 @@
// SPDX-License-Identifier: GPL-2.0+
/*
- * ifile.c - NILFS inode file
+ * NILFS inode file
*
* Copyright (C) 2006-2008 Nippon Telegraph and Telephone Corporation.
*
diff --git a/fs/nilfs2/ifile.h b/fs/nilfs2/ifile.h
index a1e1e5711a05..35c5273f4821 100644
--- a/fs/nilfs2/ifile.h
+++ b/fs/nilfs2/ifile.h
@@ -1,6 +1,6 @@
/* SPDX-License-Identifier: GPL-2.0+ */
/*
- * ifile.h - NILFS inode file
+ * NILFS inode file
*
* Copyright (C) 2006-2008 Nippon Telegraph and Telephone Corporation.
*
diff --git a/fs/nilfs2/inode.c b/fs/nilfs2/inode.c
index 2e8eb263cf0f..e3d807d5b83a 100644
--- a/fs/nilfs2/inode.c
+++ b/fs/nilfs2/inode.c
@@ -1,6 +1,6 @@
// SPDX-License-Identifier: GPL-2.0+
/*
- * inode.c - NILFS inode operations.
+ * NILFS inode operations.
*
* Copyright (C) 2005-2008 Nippon Telegraph and Telephone Corporation.
*
diff --git a/fs/nilfs2/ioctl.c b/fs/nilfs2/ioctl.c
index 1d0583cfd970..fec194a666f4 100644
--- a/fs/nilfs2/ioctl.c
+++ b/fs/nilfs2/ioctl.c
@@ -1,6 +1,6 @@
// SPDX-License-Identifier: GPL-2.0+
/*
- * ioctl.c - NILFS ioctl operations.
+ * NILFS ioctl operations.
*
* Copyright (C) 2007, 2008 Nippon Telegraph and Telephone Corporation.
*
diff --git a/fs/nilfs2/mdt.c b/fs/nilfs2/mdt.c
index 97769fe4d588..4b3d33cf0041 100644
--- a/fs/nilfs2/mdt.c
+++ b/fs/nilfs2/mdt.c
@@ -1,6 +1,6 @@
// SPDX-License-Identifier: GPL-2.0+
/*
- * mdt.c - meta data file for NILFS
+ * Meta data file for NILFS
*
* Copyright (C) 2005-2008 Nippon Telegraph and Telephone Corporation.
*
diff --git a/fs/nilfs2/mdt.h b/fs/nilfs2/mdt.h
index e77aea4bb921..8f86080a436d 100644
--- a/fs/nilfs2/mdt.h
+++ b/fs/nilfs2/mdt.h
@@ -1,6 +1,6 @@
/* SPDX-License-Identifier: GPL-2.0+ */
/*
- * mdt.h - NILFS meta data file prototype and definitions
+ * NILFS meta data file prototype and definitions
*
* Copyright (C) 2005-2008 Nippon Telegraph and Telephone Corporation.
*
diff --git a/fs/nilfs2/namei.c b/fs/nilfs2/namei.c
index 91eebeb0c48b..23899e0ae850 100644
--- a/fs/nilfs2/namei.c
+++ b/fs/nilfs2/namei.c
@@ -1,6 +1,6 @@
// SPDX-License-Identifier: GPL-2.0+
/*
- * namei.c - NILFS pathname lookup operations.
+ * NILFS pathname lookup operations.
*
* Copyright (C) 2005-2008 Nippon Telegraph and Telephone Corporation.
*
diff --git a/fs/nilfs2/nilfs.h b/fs/nilfs2/nilfs.h
index 60b21b6eeac0..a7b81755c350 100644
--- a/fs/nilfs2/nilfs.h
+++ b/fs/nilfs2/nilfs.h
@@ -1,6 +1,6 @@
/* SPDX-License-Identifier: GPL-2.0+ */
/*
- * nilfs.h - NILFS local header file.
+ * NILFS local header file.
*
* Copyright (C) 2005-2008 Nippon Telegraph and Telephone Corporation.
*
diff --git a/fs/nilfs2/page.c b/fs/nilfs2/page.c
index 171fb5cd427f..bc3e2cd4117f 100644
--- a/fs/nilfs2/page.c
+++ b/fs/nilfs2/page.c
@@ -1,6 +1,6 @@
// SPDX-License-Identifier: GPL-2.0+
/*
- * page.c - buffer/page management specific to NILFS
+ * Buffer/page management specific to NILFS
*
* Copyright (C) 2005-2008 Nippon Telegraph and Telephone Corporation.
*
diff --git a/fs/nilfs2/page.h b/fs/nilfs2/page.h
index 62b9bb469e92..569263b23c0c 100644
--- a/fs/nilfs2/page.h
+++ b/fs/nilfs2/page.h
@@ -1,6 +1,6 @@
/* SPDX-License-Identifier: GPL-2.0+ */
/*
- * page.h - buffer/page management specific to NILFS
+ * Buffer/page management specific to NILFS
*
* Copyright (C) 2005-2008 Nippon Telegraph and Telephone Corporation.
*
diff --git a/fs/nilfs2/recovery.c b/fs/nilfs2/recovery.c
index 2217f904a7cf..9e2ed76c0f25 100644
--- a/fs/nilfs2/recovery.c
+++ b/fs/nilfs2/recovery.c
@@ -1,6 +1,6 @@
// SPDX-License-Identifier: GPL-2.0+
/*
- * recovery.c - NILFS recovery logic
+ * NILFS recovery logic
*
* Copyright (C) 2005-2008 Nippon Telegraph and Telephone Corporation.
*
diff --git a/fs/nilfs2/segbuf.c b/fs/nilfs2/segbuf.c
index 56872e93823d..43287b0d3e9b 100644
--- a/fs/nilfs2/segbuf.c
+++ b/fs/nilfs2/segbuf.c
@@ -1,6 +1,6 @@
// SPDX-License-Identifier: GPL-2.0+
/*
- * segbuf.c - NILFS segment buffer
+ * NILFS segment buffer
*
* Copyright (C) 2005-2008 Nippon Telegraph and Telephone Corporation.
*
diff --git a/fs/nilfs2/segbuf.h b/fs/nilfs2/segbuf.h
index 9bea1bd59041..e20091ededba 100644
--- a/fs/nilfs2/segbuf.h
+++ b/fs/nilfs2/segbuf.h
@@ -1,6 +1,6 @@
/* SPDX-License-Identifier: GPL-2.0+ */
/*
- * segbuf.h - NILFS Segment buffer prototypes and definitions
+ * NILFS Segment buffer prototypes and definitions
*
* Copyright (C) 2005-2008 Nippon Telegraph and Telephone Corporation.
*
diff --git a/fs/nilfs2/segment.c b/fs/nilfs2/segment.c
index 686c8ee7b29c..85a853334771 100644
--- a/fs/nilfs2/segment.c
+++ b/fs/nilfs2/segment.c
@@ -1,6 +1,6 @@
// SPDX-License-Identifier: GPL-2.0+
/*
- * segment.c - NILFS segment constructor.
+ * NILFS segment constructor.
*
* Copyright (C) 2005-2008 Nippon Telegraph and Telephone Corporation.
*
diff --git a/fs/nilfs2/segment.h b/fs/nilfs2/segment.h
index f5cf5308f3fc..1060f72ebf5a 100644
--- a/fs/nilfs2/segment.h
+++ b/fs/nilfs2/segment.h
@@ -1,6 +1,6 @@
/* SPDX-License-Identifier: GPL-2.0+ */
/*
- * segment.h - NILFS Segment constructor prototypes and definitions
+ * NILFS Segment constructor prototypes and definitions
*
* Copyright (C) 2005-2008 Nippon Telegraph and Telephone Corporation.
*
diff --git a/fs/nilfs2/sufile.c b/fs/nilfs2/sufile.c
index 63722475e17e..e385cca2004a 100644
--- a/fs/nilfs2/sufile.c
+++ b/fs/nilfs2/sufile.c
@@ -1,6 +1,6 @@
// SPDX-License-Identifier: GPL-2.0+
/*
- * sufile.c - NILFS segment usage file.
+ * NILFS segment usage file.
*
* Copyright (C) 2006-2008 Nippon Telegraph and Telephone Corporation.
*
diff --git a/fs/nilfs2/sufile.h b/fs/nilfs2/sufile.h
index c4e2c7a7add1..8e8a1a5a0402 100644
--- a/fs/nilfs2/sufile.h
+++ b/fs/nilfs2/sufile.h
@@ -1,6 +1,6 @@
/* SPDX-License-Identifier: GPL-2.0+ */
/*
- * sufile.h - NILFS segment usage file.
+ * NILFS segment usage file.
*
* Copyright (C) 2006-2008 Nippon Telegraph and Telephone Corporation.
*
diff --git a/fs/nilfs2/super.c b/fs/nilfs2/super.c
index 3134c0e42fd4..63e5fa74016c 100644
--- a/fs/nilfs2/super.c
+++ b/fs/nilfs2/super.c
@@ -1,6 +1,6 @@
// SPDX-License-Identifier: GPL-2.0+
/*
- * super.c - NILFS module and super block management.
+ * NILFS module and super block management.
*
* Copyright (C) 2005-2008 Nippon Telegraph and Telephone Corporation.
*
diff --git a/fs/nilfs2/sysfs.c b/fs/nilfs2/sysfs.c
index 62f8a7ac19c8..81f35c5b5a40 100644
--- a/fs/nilfs2/sysfs.c
+++ b/fs/nilfs2/sysfs.c
@@ -1,6 +1,6 @@
// SPDX-License-Identifier: GPL-2.0+
/*
- * sysfs.c - sysfs support implementation.
+ * Sysfs support implementation.
*
* Copyright (C) 2005-2014 Nippon Telegraph and Telephone Corporation.
* Copyright (C) 2014 HGST, Inc., a Western Digital Company.
@@ -95,7 +95,7 @@ static ssize_t
nilfs_snapshot_inodes_count_show(struct nilfs_snapshot_attr *attr,
struct nilfs_root *root, char *buf)
{
- return snprintf(buf, PAGE_SIZE, "%llu\n",
+ return sysfs_emit(buf, "%llu\n",
(unsigned long long)atomic64_read(&root->inodes_count));
}
@@ -103,7 +103,7 @@ static ssize_t
nilfs_snapshot_blocks_count_show(struct nilfs_snapshot_attr *attr,
struct nilfs_root *root, char *buf)
{
- return snprintf(buf, PAGE_SIZE, "%llu\n",
+ return sysfs_emit(buf, "%llu\n",
(unsigned long long)atomic64_read(&root->blocks_count));
}
@@ -116,7 +116,7 @@ static ssize_t
nilfs_snapshot_README_show(struct nilfs_snapshot_attr *attr,
struct nilfs_root *root, char *buf)
{
- return snprintf(buf, PAGE_SIZE, snapshot_readme_str);
+ return sysfs_emit(buf, snapshot_readme_str);
}
NILFS_SNAPSHOT_RO_ATTR(inodes_count);
@@ -217,7 +217,7 @@ static ssize_t
nilfs_mounted_snapshots_README_show(struct nilfs_mounted_snapshots_attr *attr,
struct the_nilfs *nilfs, char *buf)
{
- return snprintf(buf, PAGE_SIZE, mounted_snapshots_readme_str);
+ return sysfs_emit(buf, mounted_snapshots_readme_str);
}
NILFS_MOUNTED_SNAPSHOTS_RO_ATTR(README);
@@ -255,7 +255,7 @@ nilfs_checkpoints_checkpoints_number_show(struct nilfs_checkpoints_attr *attr,
ncheckpoints = cpstat.cs_ncps;
- return snprintf(buf, PAGE_SIZE, "%llu\n", ncheckpoints);
+ return sysfs_emit(buf, "%llu\n", ncheckpoints);
}
static ssize_t
@@ -278,7 +278,7 @@ nilfs_checkpoints_snapshots_number_show(struct nilfs_checkpoints_attr *attr,
nsnapshots = cpstat.cs_nsss;
- return snprintf(buf, PAGE_SIZE, "%llu\n", nsnapshots);
+ return sysfs_emit(buf, "%llu\n", nsnapshots);
}
static ssize_t
@@ -292,7 +292,7 @@ nilfs_checkpoints_last_seg_checkpoint_show(struct nilfs_checkpoints_attr *attr,
last_cno = nilfs->ns_last_cno;
spin_unlock(&nilfs->ns_last_segment_lock);
- return snprintf(buf, PAGE_SIZE, "%llu\n", last_cno);
+ return sysfs_emit(buf, "%llu\n", last_cno);
}
static ssize_t
@@ -306,7 +306,7 @@ nilfs_checkpoints_next_checkpoint_show(struct nilfs_checkpoints_attr *attr,
cno = nilfs->ns_cno;
up_read(&nilfs->ns_segctor_sem);
- return snprintf(buf, PAGE_SIZE, "%llu\n", cno);
+ return sysfs_emit(buf, "%llu\n", cno);
}
static const char checkpoints_readme_str[] =
@@ -322,7 +322,7 @@ static ssize_t
nilfs_checkpoints_README_show(struct nilfs_checkpoints_attr *attr,
struct the_nilfs *nilfs, char *buf)
{
- return snprintf(buf, PAGE_SIZE, checkpoints_readme_str);
+ return sysfs_emit(buf, checkpoints_readme_str);
}
NILFS_CHECKPOINTS_RO_ATTR(checkpoints_number);
@@ -353,7 +353,7 @@ nilfs_segments_segments_number_show(struct nilfs_segments_attr *attr,
struct the_nilfs *nilfs,
char *buf)
{
- return snprintf(buf, PAGE_SIZE, "%lu\n", nilfs->ns_nsegments);
+ return sysfs_emit(buf, "%lu\n", nilfs->ns_nsegments);
}
static ssize_t
@@ -361,7 +361,7 @@ nilfs_segments_blocks_per_segment_show(struct nilfs_segments_attr *attr,
struct the_nilfs *nilfs,
char *buf)
{
- return snprintf(buf, PAGE_SIZE, "%lu\n", nilfs->ns_blocks_per_segment);
+ return sysfs_emit(buf, "%lu\n", nilfs->ns_blocks_per_segment);
}
static ssize_t
@@ -375,7 +375,7 @@ nilfs_segments_clean_segments_show(struct nilfs_segments_attr *attr,
ncleansegs = nilfs_sufile_get_ncleansegs(nilfs->ns_sufile);
up_read(&NILFS_MDT(nilfs->ns_dat)->mi_sem);
- return snprintf(buf, PAGE_SIZE, "%lu\n", ncleansegs);
+ return sysfs_emit(buf, "%lu\n", ncleansegs);
}
static ssize_t
@@ -395,7 +395,7 @@ nilfs_segments_dirty_segments_show(struct nilfs_segments_attr *attr,
return err;
}
- return snprintf(buf, PAGE_SIZE, "%llu\n", sustat.ss_ndirtysegs);
+ return sysfs_emit(buf, "%llu\n", sustat.ss_ndirtysegs);
}
static const char segments_readme_str[] =
@@ -411,7 +411,7 @@ nilfs_segments_README_show(struct nilfs_segments_attr *attr,
struct the_nilfs *nilfs,
char *buf)
{
- return snprintf(buf, PAGE_SIZE, segments_readme_str);
+ return sysfs_emit(buf, segments_readme_str);
}
NILFS_SEGMENTS_RO_ATTR(segments_number);
@@ -448,7 +448,7 @@ nilfs_segctor_last_pseg_block_show(struct nilfs_segctor_attr *attr,
last_pseg = nilfs->ns_last_pseg;
spin_unlock(&nilfs->ns_last_segment_lock);
- return snprintf(buf, PAGE_SIZE, "%llu\n",
+ return sysfs_emit(buf, "%llu\n",
(unsigned long long)last_pseg);
}
@@ -463,7 +463,7 @@ nilfs_segctor_last_seg_sequence_show(struct nilfs_segctor_attr *attr,
last_seq = nilfs->ns_last_seq;
spin_unlock(&nilfs->ns_last_segment_lock);
- return snprintf(buf, PAGE_SIZE, "%llu\n", last_seq);
+ return sysfs_emit(buf, "%llu\n", last_seq);
}
static ssize_t
@@ -477,7 +477,7 @@ nilfs_segctor_last_seg_checkpoint_show(struct nilfs_segctor_attr *attr,
last_cno = nilfs->ns_last_cno;
spin_unlock(&nilfs->ns_last_segment_lock);
- return snprintf(buf, PAGE_SIZE, "%llu\n", last_cno);
+ return sysfs_emit(buf, "%llu\n", last_cno);
}
static ssize_t
@@ -491,7 +491,7 @@ nilfs_segctor_current_seg_sequence_show(struct nilfs_segctor_attr *attr,
seg_seq = nilfs->ns_seg_seq;
up_read(&nilfs->ns_segctor_sem);
- return snprintf(buf, PAGE_SIZE, "%llu\n", seg_seq);
+ return sysfs_emit(buf, "%llu\n", seg_seq);
}
static ssize_t
@@ -505,7 +505,7 @@ nilfs_segctor_current_last_full_seg_show(struct nilfs_segctor_attr *attr,
segnum = nilfs->ns_segnum;
up_read(&nilfs->ns_segctor_sem);
- return snprintf(buf, PAGE_SIZE, "%llu\n", segnum);
+ return sysfs_emit(buf, "%llu\n", segnum);
}
static ssize_t
@@ -519,7 +519,7 @@ nilfs_segctor_next_full_seg_show(struct nilfs_segctor_attr *attr,
nextnum = nilfs->ns_nextnum;
up_read(&nilfs->ns_segctor_sem);
- return snprintf(buf, PAGE_SIZE, "%llu\n", nextnum);
+ return sysfs_emit(buf, "%llu\n", nextnum);
}
static ssize_t
@@ -533,7 +533,7 @@ nilfs_segctor_next_pseg_offset_show(struct nilfs_segctor_attr *attr,
pseg_offset = nilfs->ns_pseg_offset;
up_read(&nilfs->ns_segctor_sem);
- return snprintf(buf, PAGE_SIZE, "%lu\n", pseg_offset);
+ return sysfs_emit(buf, "%lu\n", pseg_offset);
}
static ssize_t
@@ -547,7 +547,7 @@ nilfs_segctor_next_checkpoint_show(struct nilfs_segctor_attr *attr,
cno = nilfs->ns_cno;
up_read(&nilfs->ns_segctor_sem);
- return snprintf(buf, PAGE_SIZE, "%llu\n", cno);
+ return sysfs_emit(buf, "%llu\n", cno);
}
static ssize_t
@@ -575,7 +575,7 @@ nilfs_segctor_last_seg_write_time_secs_show(struct nilfs_segctor_attr *attr,
ctime = nilfs->ns_ctime;
up_read(&nilfs->ns_segctor_sem);
- return snprintf(buf, PAGE_SIZE, "%llu\n", ctime);
+ return sysfs_emit(buf, "%llu\n", ctime);
}
static ssize_t
@@ -603,7 +603,7 @@ nilfs_segctor_last_nongc_write_time_secs_show(struct nilfs_segctor_attr *attr,
nongc_ctime = nilfs->ns_nongc_ctime;
up_read(&nilfs->ns_segctor_sem);
- return snprintf(buf, PAGE_SIZE, "%llu\n", nongc_ctime);
+ return sysfs_emit(buf, "%llu\n", nongc_ctime);
}
static ssize_t
@@ -617,7 +617,7 @@ nilfs_segctor_dirty_data_blocks_count_show(struct nilfs_segctor_attr *attr,
ndirtyblks = atomic_read(&nilfs->ns_ndirtyblks);
up_read(&nilfs->ns_segctor_sem);
- return snprintf(buf, PAGE_SIZE, "%u\n", ndirtyblks);
+ return sysfs_emit(buf, "%u\n", ndirtyblks);
}
static const char segctor_readme_str[] =
@@ -654,7 +654,7 @@ static ssize_t
nilfs_segctor_README_show(struct nilfs_segctor_attr *attr,
struct the_nilfs *nilfs, char *buf)
{
- return snprintf(buf, PAGE_SIZE, segctor_readme_str);
+ return sysfs_emit(buf, segctor_readme_str);
}
NILFS_SEGCTOR_RO_ATTR(last_pseg_block);
@@ -723,7 +723,7 @@ nilfs_superblock_sb_write_time_secs_show(struct nilfs_superblock_attr *attr,
sbwtime = nilfs->ns_sbwtime;
up_read(&nilfs->ns_sem);
- return snprintf(buf, PAGE_SIZE, "%llu\n", sbwtime);
+ return sysfs_emit(buf, "%llu\n", sbwtime);
}
static ssize_t
@@ -737,7 +737,7 @@ nilfs_superblock_sb_write_count_show(struct nilfs_superblock_attr *attr,
sbwcount = nilfs->ns_sbwcount;
up_read(&nilfs->ns_sem);
- return snprintf(buf, PAGE_SIZE, "%u\n", sbwcount);
+ return sysfs_emit(buf, "%u\n", sbwcount);
}
static ssize_t
@@ -751,7 +751,7 @@ nilfs_superblock_sb_update_frequency_show(struct nilfs_superblock_attr *attr,
sb_update_freq = nilfs->ns_sb_update_freq;
up_read(&nilfs->ns_sem);
- return snprintf(buf, PAGE_SIZE, "%u\n", sb_update_freq);
+ return sysfs_emit(buf, "%u\n", sb_update_freq);
}
static ssize_t
@@ -799,7 +799,7 @@ static ssize_t
nilfs_superblock_README_show(struct nilfs_superblock_attr *attr,
struct the_nilfs *nilfs, char *buf)
{
- return snprintf(buf, PAGE_SIZE, sb_readme_str);
+ return sysfs_emit(buf, sb_readme_str);
}
NILFS_SUPERBLOCK_RO_ATTR(sb_write_time);
@@ -834,7 +834,7 @@ ssize_t nilfs_dev_revision_show(struct nilfs_dev_attr *attr,
u32 major = le32_to_cpu(sbp[0]->s_rev_level);
u16 minor = le16_to_cpu(sbp[0]->s_minor_rev_level);
- return snprintf(buf, PAGE_SIZE, "%d.%d\n", major, minor);
+ return sysfs_emit(buf, "%d.%d\n", major, minor);
}
static
@@ -842,7 +842,7 @@ ssize_t nilfs_dev_blocksize_show(struct nilfs_dev_attr *attr,
struct the_nilfs *nilfs,
char *buf)
{
- return snprintf(buf, PAGE_SIZE, "%u\n", nilfs->ns_blocksize);
+ return sysfs_emit(buf, "%u\n", nilfs->ns_blocksize);
}
static
@@ -853,7 +853,7 @@ ssize_t nilfs_dev_device_size_show(struct nilfs_dev_attr *attr,
struct nilfs_super_block **sbp = nilfs->ns_sbp;
u64 dev_size = le64_to_cpu(sbp[0]->s_dev_size);
- return snprintf(buf, PAGE_SIZE, "%llu\n", dev_size);
+ return sysfs_emit(buf, "%llu\n", dev_size);
}
static
@@ -864,7 +864,7 @@ ssize_t nilfs_dev_free_blocks_show(struct nilfs_dev_attr *attr,
sector_t free_blocks = 0;
nilfs_count_free_blocks(nilfs, &free_blocks);
- return snprintf(buf, PAGE_SIZE, "%llu\n",
+ return sysfs_emit(buf, "%llu\n",
(unsigned long long)free_blocks);
}
@@ -875,7 +875,7 @@ ssize_t nilfs_dev_uuid_show(struct nilfs_dev_attr *attr,
{
struct nilfs_super_block **sbp = nilfs->ns_sbp;
- return snprintf(buf, PAGE_SIZE, "%pUb\n", sbp[0]->s_uuid);
+ return sysfs_emit(buf, "%pUb\n", sbp[0]->s_uuid);
}
static
@@ -903,7 +903,7 @@ static ssize_t nilfs_dev_README_show(struct nilfs_dev_attr *attr,
struct the_nilfs *nilfs,
char *buf)
{
- return snprintf(buf, PAGE_SIZE, dev_readme_str);
+ return sysfs_emit(buf, dev_readme_str);
}
NILFS_DEV_RO_ATTR(revision);
@@ -1047,7 +1047,7 @@ void nilfs_sysfs_delete_device_group(struct the_nilfs *nilfs)
static ssize_t nilfs_feature_revision_show(struct kobject *kobj,
struct attribute *attr, char *buf)
{
- return snprintf(buf, PAGE_SIZE, "%d.%d\n",
+ return sysfs_emit(buf, "%d.%d\n",
NILFS_CURRENT_REV, NILFS_MINOR_REV);
}
@@ -1060,7 +1060,7 @@ static ssize_t nilfs_feature_README_show(struct kobject *kobj,
struct attribute *attr,
char *buf)
{
- return snprintf(buf, PAGE_SIZE, features_readme_str);
+ return sysfs_emit(buf, features_readme_str);
}
NILFS_FEATURE_RO_ATTR(revision);
diff --git a/fs/nilfs2/sysfs.h b/fs/nilfs2/sysfs.h
index d001eb862dae..78a87a016928 100644
--- a/fs/nilfs2/sysfs.h
+++ b/fs/nilfs2/sysfs.h
@@ -1,6 +1,6 @@
/* SPDX-License-Identifier: GPL-2.0+ */
/*
- * sysfs.h - sysfs support declarations.
+ * Sysfs support declarations.
*
* Copyright (C) 2005-2014 Nippon Telegraph and Telephone Corporation.
* Copyright (C) 2014 HGST, Inc., a Western Digital Company.
diff --git a/fs/nilfs2/the_nilfs.c b/fs/nilfs2/the_nilfs.c
index 1bfcb5d3ea48..dd48a8f74d57 100644
--- a/fs/nilfs2/the_nilfs.c
+++ b/fs/nilfs2/the_nilfs.c
@@ -1,6 +1,6 @@
// SPDX-License-Identifier: GPL-2.0+
/*
- * the_nilfs.c - the_nilfs shared structure.
+ * the_nilfs shared structure.
*
* Copyright (C) 2005-2008 Nippon Telegraph and Telephone Corporation.
*
diff --git a/fs/nilfs2/the_nilfs.h b/fs/nilfs2/the_nilfs.h
index 987c8ab02aee..47c7dfbb7ea5 100644
--- a/fs/nilfs2/the_nilfs.h
+++ b/fs/nilfs2/the_nilfs.h
@@ -1,6 +1,6 @@
/* SPDX-License-Identifier: GPL-2.0+ */
/*
- * the_nilfs.h - the_nilfs shared structure.
+ * the_nilfs shared structure.
*
* Copyright (C) 2005-2008 Nippon Telegraph and Telephone Corporation.
*
diff --git a/fs/notify/fanotify/fanotify.c b/fs/notify/fanotify/fanotify.c
index 057abd2cf887..b6091775aa6e 100644
--- a/fs/notify/fanotify/fanotify.c
+++ b/fs/notify/fanotify/fanotify.c
@@ -111,6 +111,16 @@ static bool fanotify_name_event_equal(struct fanotify_name_event *fne1,
return fanotify_info_equal(info1, info2);
}
+static bool fanotify_error_event_equal(struct fanotify_error_event *fee1,
+ struct fanotify_error_event *fee2)
+{
+ /* Error events against the same file system are always merged. */
+ if (!fanotify_fsid_equal(&fee1->fsid, &fee2->fsid))
+ return false;
+
+ return true;
+}
+
static bool fanotify_should_merge(struct fanotify_event *old,
struct fanotify_event *new)
{
@@ -141,6 +151,9 @@ static bool fanotify_should_merge(struct fanotify_event *old,
case FANOTIFY_EVENT_TYPE_FID_NAME:
return fanotify_name_event_equal(FANOTIFY_NE(old),
FANOTIFY_NE(new));
+ case FANOTIFY_EVENT_TYPE_FS_ERROR:
+ return fanotify_error_event_equal(FANOTIFY_EE(old),
+ FANOTIFY_EE(new));
default:
WARN_ON_ONCE(1);
}
@@ -176,6 +189,10 @@ static int fanotify_merge(struct fsnotify_group *group,
break;
if (fanotify_should_merge(old, new)) {
old->mask |= new->mask;
+
+ if (fanotify_is_error_event(old->mask))
+ FANOTIFY_EE(old)->err_count++;
+
return 1;
}
}
@@ -343,13 +360,23 @@ static u32 fanotify_group_event_mask(struct fsnotify_group *group,
static int fanotify_encode_fh_len(struct inode *inode)
{
int dwords = 0;
+ int fh_len;
if (!inode)
return 0;
exportfs_encode_inode_fh(inode, NULL, &dwords, NULL);
+ fh_len = dwords << 2;
+
+ /*
+ * struct fanotify_error_event might be preallocated and is
+ * limited to MAX_HANDLE_SZ. This should never happen, but
+ * safeguard by forcing an invalid file handle.
+ */
+ if (WARN_ON_ONCE(fh_len > MAX_HANDLE_SZ))
+ return 0;
- return dwords << 2;
+ return fh_len;
}
/*
@@ -370,8 +397,14 @@ static int fanotify_encode_fh(struct fanotify_fh *fh, struct inode *inode,
fh->type = FILEID_ROOT;
fh->len = 0;
fh->flags = 0;
+
+ /*
+ * Invalid FHs are used by FAN_FS_ERROR for errors not
+ * linked to any inode. The f_handle won't be reported
+ * back to userspace.
+ */
if (!inode)
- return 0;
+ goto out;
/*
* !gpf means preallocated variable size fh, but fh_len could
@@ -403,8 +436,13 @@ static int fanotify_encode_fh(struct fanotify_fh *fh, struct inode *inode,
fh->type = type;
fh->len = fh_len;
- /* Mix fh into event merge key */
- *hash ^= fanotify_hash_fh(fh);
+out:
+ /*
+ * Mix fh into event merge key. Hash might be NULL in case of
+ * unhashed FID events (i.e. FAN_FS_ERROR).
+ */
+ if (hash)
+ *hash ^= fanotify_hash_fh(fh);
return FANOTIFY_FH_HDR_LEN + fh_len;
@@ -452,7 +490,7 @@ static struct inode *fanotify_dfid_inode(u32 event_mask, const void *data,
if (event_mask & ALL_FSNOTIFY_DIRENT_EVENTS)
return dir;
- if (S_ISDIR(inode->i_mode))
+ if (inode && S_ISDIR(inode->i_mode))
return inode;
return dir;
@@ -563,6 +601,44 @@ static struct fanotify_event *fanotify_alloc_name_event(struct inode *id,
return &fne->fae;
}
+static struct fanotify_event *fanotify_alloc_error_event(
+ struct fsnotify_group *group,
+ __kernel_fsid_t *fsid,
+ const void *data, int data_type,
+ unsigned int *hash)
+{
+ struct fs_error_report *report =
+ fsnotify_data_error_report(data, data_type);
+ struct inode *inode;
+ struct fanotify_error_event *fee;
+ int fh_len;
+
+ if (WARN_ON_ONCE(!report))
+ return NULL;
+
+ fee = mempool_alloc(&group->fanotify_data.error_events_pool, GFP_NOFS);
+ if (!fee)
+ return NULL;
+
+ fee->fae.type = FANOTIFY_EVENT_TYPE_FS_ERROR;
+ fee->error = report->error;
+ fee->err_count = 1;
+ fee->fsid = *fsid;
+
+ inode = report->inode;
+ fh_len = fanotify_encode_fh_len(inode);
+
+ /* Bad fh_len. Fallback to using an invalid fh. Should never happen. */
+ if (!fh_len && inode)
+ inode = NULL;
+
+ fanotify_encode_fh(&fee->object_fh, inode, fh_len, NULL, 0);
+
+ *hash ^= fanotify_hash_fsid(fsid);
+
+ return &fee->fae;
+}
+
static struct fanotify_event *fanotify_alloc_event(struct fsnotify_group *group,
u32 mask, const void *data,
int data_type, struct inode *dir,
@@ -630,6 +706,9 @@ static struct fanotify_event *fanotify_alloc_event(struct fsnotify_group *group,
if (fanotify_is_perm_event(mask)) {
event = fanotify_alloc_perm_event(path, gfp);
+ } else if (fanotify_is_error_event(mask)) {
+ event = fanotify_alloc_error_event(group, fsid, data,
+ data_type, &hash);
} else if (name_event && (file_name || child)) {
event = fanotify_alloc_name_event(id, fsid, file_name, child,
&hash, gfp);
@@ -702,6 +781,9 @@ static void fanotify_insert_event(struct fsnotify_group *group,
assert_spin_locked(&group->notification_lock);
+ if (!fanotify_is_hashed_event(event->mask))
+ return;
+
pr_debug("%s: group=%p event=%p bucket=%u\n", __func__,
group, event, bucket);
@@ -738,8 +820,9 @@ static int fanotify_handle_event(struct fsnotify_group *group, u32 mask,
BUILD_BUG_ON(FAN_ONDIR != FS_ISDIR);
BUILD_BUG_ON(FAN_OPEN_EXEC != FS_OPEN_EXEC);
BUILD_BUG_ON(FAN_OPEN_EXEC_PERM != FS_OPEN_EXEC_PERM);
+ BUILD_BUG_ON(FAN_FS_ERROR != FS_ERROR);
- BUILD_BUG_ON(HWEIGHT32(ALL_FANOTIFY_EVENT_BITS) != 19);
+ BUILD_BUG_ON(HWEIGHT32(ALL_FANOTIFY_EVENT_BITS) != 20);
mask = fanotify_group_event_mask(group, iter_info, mask, data,
data_type, dir);
@@ -778,9 +861,8 @@ static int fanotify_handle_event(struct fsnotify_group *group, u32 mask,
}
fsn_event = &event->fse;
- ret = fsnotify_add_event(group, fsn_event, fanotify_merge,
- fanotify_is_hashed_event(mask) ?
- fanotify_insert_event : NULL);
+ ret = fsnotify_insert_event(group, fsn_event, fanotify_merge,
+ fanotify_insert_event);
if (ret) {
/* Permission events shouldn't be merged */
BUG_ON(ret == 1 && mask & FANOTIFY_PERM_EVENTS);
@@ -805,6 +887,9 @@ static void fanotify_free_group_priv(struct fsnotify_group *group)
if (group->fanotify_data.ucounts)
dec_ucount(group->fanotify_data.ucounts,
UCOUNT_FANOTIFY_GROUPS);
+
+ if (mempool_initialized(&group->fanotify_data.error_events_pool))
+ mempool_exit(&group->fanotify_data.error_events_pool);
}
static void fanotify_free_path_event(struct fanotify_event *event)
@@ -833,7 +918,16 @@ static void fanotify_free_name_event(struct fanotify_event *event)
kfree(FANOTIFY_NE(event));
}
-static void fanotify_free_event(struct fsnotify_event *fsn_event)
+static void fanotify_free_error_event(struct fsnotify_group *group,
+ struct fanotify_event *event)
+{
+ struct fanotify_error_event *fee = FANOTIFY_EE(event);
+
+ mempool_free(fee, &group->fanotify_data.error_events_pool);
+}
+
+static void fanotify_free_event(struct fsnotify_group *group,
+ struct fsnotify_event *fsn_event)
{
struct fanotify_event *event;
@@ -855,6 +949,9 @@ static void fanotify_free_event(struct fsnotify_event *fsn_event)
case FANOTIFY_EVENT_TYPE_OVERFLOW:
kfree(event);
break;
+ case FANOTIFY_EVENT_TYPE_FS_ERROR:
+ fanotify_free_error_event(group, event);
+ break;
default:
WARN_ON_ONCE(1);
}
diff --git a/fs/notify/fanotify/fanotify.h b/fs/notify/fanotify/fanotify.h
index 4a5e555dc3d2..d25f500bf7e7 100644
--- a/fs/notify/fanotify/fanotify.h
+++ b/fs/notify/fanotify/fanotify.h
@@ -141,6 +141,7 @@ enum fanotify_event_type {
FANOTIFY_EVENT_TYPE_PATH,
FANOTIFY_EVENT_TYPE_PATH_PERM,
FANOTIFY_EVENT_TYPE_OVERFLOW, /* struct fanotify_event */
+ FANOTIFY_EVENT_TYPE_FS_ERROR, /* struct fanotify_error_event */
__FANOTIFY_EVENT_TYPE_NUM
};
@@ -170,12 +171,18 @@ static inline void fanotify_init_event(struct fanotify_event *event,
event->pid = NULL;
}
+#define FANOTIFY_INLINE_FH(name, size) \
+struct { \
+ struct fanotify_fh (name); \
+ /* Space for object_fh.buf[] - access with fanotify_fh_buf() */ \
+ unsigned char _inline_fh_buf[(size)]; \
+}
+
struct fanotify_fid_event {
struct fanotify_event fae;
__kernel_fsid_t fsid;
- struct fanotify_fh object_fh;
- /* Reserve space in object_fh.buf[] - access with fanotify_fh_buf() */
- unsigned char _inline_fh_buf[FANOTIFY_INLINE_FH_LEN];
+
+ FANOTIFY_INLINE_FH(object_fh, FANOTIFY_INLINE_FH_LEN);
};
static inline struct fanotify_fid_event *
@@ -196,12 +203,30 @@ FANOTIFY_NE(struct fanotify_event *event)
return container_of(event, struct fanotify_name_event, fae);
}
+struct fanotify_error_event {
+ struct fanotify_event fae;
+ s32 error; /* Error reported by the Filesystem. */
+ u32 err_count; /* Suppressed errors count */
+
+ __kernel_fsid_t fsid; /* FSID this error refers to. */
+
+ FANOTIFY_INLINE_FH(object_fh, MAX_HANDLE_SZ);
+};
+
+static inline struct fanotify_error_event *
+FANOTIFY_EE(struct fanotify_event *event)
+{
+ return container_of(event, struct fanotify_error_event, fae);
+}
+
static inline __kernel_fsid_t *fanotify_event_fsid(struct fanotify_event *event)
{
if (event->type == FANOTIFY_EVENT_TYPE_FID)
return &FANOTIFY_FE(event)->fsid;
else if (event->type == FANOTIFY_EVENT_TYPE_FID_NAME)
return &FANOTIFY_NE(event)->fsid;
+ else if (event->type == FANOTIFY_EVENT_TYPE_FS_ERROR)
+ return &FANOTIFY_EE(event)->fsid;
else
return NULL;
}
@@ -213,6 +238,8 @@ static inline struct fanotify_fh *fanotify_event_object_fh(
return &FANOTIFY_FE(event)->object_fh;
else if (event->type == FANOTIFY_EVENT_TYPE_FID_NAME)
return fanotify_info_file_fh(&FANOTIFY_NE(event)->info);
+ else if (event->type == FANOTIFY_EVENT_TYPE_FS_ERROR)
+ return &FANOTIFY_EE(event)->object_fh;
else
return NULL;
}
@@ -244,6 +271,19 @@ static inline int fanotify_event_dir_fh_len(struct fanotify_event *event)
return info ? fanotify_info_dir_fh_len(info) : 0;
}
+static inline bool fanotify_event_has_object_fh(struct fanotify_event *event)
+{
+ /* For error events, even zeroed fh are reported. */
+ if (event->type == FANOTIFY_EVENT_TYPE_FS_ERROR)
+ return true;
+ return fanotify_event_object_fh_len(event) > 0;
+}
+
+static inline bool fanotify_event_has_dir_fh(struct fanotify_event *event)
+{
+ return fanotify_event_dir_fh_len(event) > 0;
+}
+
struct fanotify_path_event {
struct fanotify_event fae;
struct path path;
@@ -287,6 +327,11 @@ static inline struct fanotify_event *FANOTIFY_E(struct fsnotify_event *fse)
return container_of(fse, struct fanotify_event, fse);
}
+static inline bool fanotify_is_error_event(u32 mask)
+{
+ return mask & FAN_FS_ERROR;
+}
+
static inline bool fanotify_event_has_path(struct fanotify_event *event)
{
return event->type == FANOTIFY_EVENT_TYPE_PATH ||
@@ -315,7 +360,8 @@ static inline struct path *fanotify_event_path(struct fanotify_event *event)
*/
static inline bool fanotify_is_hashed_event(u32 mask)
{
- return !fanotify_is_perm_event(mask) && !(mask & FS_Q_OVERFLOW);
+ return !(fanotify_is_perm_event(mask) ||
+ fsnotify_is_overflow_event(mask));
}
static inline unsigned int fanotify_event_hash_bucket(
diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c
index 6facdf476255..559bc1e9926d 100644
--- a/fs/notify/fanotify/fanotify_user.c
+++ b/fs/notify/fanotify/fanotify_user.c
@@ -30,6 +30,7 @@
#define FANOTIFY_DEFAULT_MAX_EVENTS 16384
#define FANOTIFY_OLD_DEFAULT_MAX_MARKS 8192
#define FANOTIFY_DEFAULT_MAX_GROUPS 128
+#define FANOTIFY_DEFAULT_FEE_POOL_SIZE 32
/*
* Legacy fanotify marks limits (8192) is per group and we introduced a tunable
@@ -114,6 +115,8 @@ struct kmem_cache *fanotify_perm_event_cachep __read_mostly;
(sizeof(struct fanotify_event_info_fid) + sizeof(struct file_handle))
#define FANOTIFY_PIDFD_INFO_HDR_LEN \
sizeof(struct fanotify_event_info_pidfd)
+#define FANOTIFY_ERROR_INFO_LEN \
+ (sizeof(struct fanotify_event_info_error))
static int fanotify_fid_info_len(int fh_len, int name_len)
{
@@ -126,17 +129,26 @@ static int fanotify_fid_info_len(int fh_len, int name_len)
FANOTIFY_EVENT_ALIGN);
}
-static int fanotify_event_info_len(unsigned int info_mode,
- struct fanotify_event *event)
+static size_t fanotify_event_len(unsigned int info_mode,
+ struct fanotify_event *event)
{
- struct fanotify_info *info = fanotify_event_info(event);
- int dir_fh_len = fanotify_event_dir_fh_len(event);
- int fh_len = fanotify_event_object_fh_len(event);
- int info_len = 0;
+ size_t event_len = FAN_EVENT_METADATA_LEN;
+ struct fanotify_info *info;
+ int dir_fh_len;
+ int fh_len;
int dot_len = 0;
- if (dir_fh_len) {
- info_len += fanotify_fid_info_len(dir_fh_len, info->name_len);
+ if (!info_mode)
+ return event_len;
+
+ if (fanotify_is_error_event(event->mask))
+ event_len += FANOTIFY_ERROR_INFO_LEN;
+
+ info = fanotify_event_info(event);
+
+ if (fanotify_event_has_dir_fh(event)) {
+ dir_fh_len = fanotify_event_dir_fh_len(event);
+ event_len += fanotify_fid_info_len(dir_fh_len, info->name_len);
} else if ((info_mode & FAN_REPORT_NAME) &&
(event->mask & FAN_ONDIR)) {
/*
@@ -147,12 +159,14 @@ static int fanotify_event_info_len(unsigned int info_mode,
}
if (info_mode & FAN_REPORT_PIDFD)
- info_len += FANOTIFY_PIDFD_INFO_HDR_LEN;
+ event_len += FANOTIFY_PIDFD_INFO_HDR_LEN;
- if (fh_len)
- info_len += fanotify_fid_info_len(fh_len, dot_len);
+ if (fanotify_event_has_object_fh(event)) {
+ fh_len = fanotify_event_object_fh_len(event);
+ event_len += fanotify_fid_info_len(fh_len, dot_len);
+ }
- return info_len;
+ return event_len;
}
/*
@@ -181,7 +195,7 @@ static void fanotify_unhash_event(struct fsnotify_group *group,
static struct fanotify_event *get_one_event(struct fsnotify_group *group,
size_t count)
{
- size_t event_size = FAN_EVENT_METADATA_LEN;
+ size_t event_size;
struct fanotify_event *event = NULL;
struct fsnotify_event *fsn_event;
unsigned int info_mode = FAN_GROUP_FLAG(group, FANOTIFY_INFO_MODES);
@@ -194,8 +208,7 @@ static struct fanotify_event *get_one_event(struct fsnotify_group *group,
goto out;
event = FANOTIFY_E(fsn_event);
- if (info_mode)
- event_size += fanotify_event_info_len(info_mode, event);
+ event_size = fanotify_event_len(info_mode, event);
if (event_size > count) {
event = ERR_PTR(-EINVAL);
@@ -316,6 +329,28 @@ static int process_access_response(struct fsnotify_group *group,
return -ENOENT;
}
+static size_t copy_error_info_to_user(struct fanotify_event *event,
+ char __user *buf, int count)
+{
+ struct fanotify_event_info_error info;
+ struct fanotify_error_event *fee = FANOTIFY_EE(event);
+
+ info.hdr.info_type = FAN_EVENT_INFO_TYPE_ERROR;
+ info.hdr.pad = 0;
+ info.hdr.len = FANOTIFY_ERROR_INFO_LEN;
+
+ if (WARN_ON(count < info.hdr.len))
+ return -EFAULT;
+
+ info.error = fee->error;
+ info.error_count = fee->err_count;
+
+ if (copy_to_user(buf, &info, sizeof(info)))
+ return -EFAULT;
+
+ return info.hdr.len;
+}
+
static int copy_fid_info_to_user(__kernel_fsid_t *fsid, struct fanotify_fh *fh,
int info_type, const char *name,
size_t name_len,
@@ -331,9 +366,6 @@ static int copy_fid_info_to_user(__kernel_fsid_t *fsid, struct fanotify_fh *fh,
pr_debug("%s: fh_len=%zu name_len=%zu, info_len=%zu, count=%zu\n",
__func__, fh_len, name_len, info_len, count);
- if (!fh_len)
- return 0;
-
if (WARN_ON_ONCE(len < sizeof(info) || len > count))
return -EFAULT;
@@ -368,6 +400,11 @@ static int copy_fid_info_to_user(__kernel_fsid_t *fsid, struct fanotify_fh *fh,
handle.handle_type = fh->type;
handle.handle_bytes = fh_len;
+
+ /* Mangle handle_type for bad file_handle */
+ if (!fh_len)
+ handle.handle_type = FILEID_INVALID;
+
if (copy_to_user(buf, &handle, sizeof(handle)))
return -EFAULT;
@@ -444,7 +481,7 @@ static int copy_info_records_to_user(struct fanotify_event *event,
/*
* Event info records order is as follows: dir fid + name, child fid.
*/
- if (fanotify_event_dir_fh_len(event)) {
+ if (fanotify_event_has_dir_fh(event)) {
info_type = info->name_len ? FAN_EVENT_INFO_TYPE_DFID_NAME :
FAN_EVENT_INFO_TYPE_DFID;
ret = copy_fid_info_to_user(fanotify_event_fsid(event),
@@ -460,7 +497,7 @@ static int copy_info_records_to_user(struct fanotify_event *event,
total_bytes += ret;
}
- if (fanotify_event_object_fh_len(event)) {
+ if (fanotify_event_has_object_fh(event)) {
const char *dot = NULL;
int dot_len = 0;
@@ -520,6 +557,15 @@ static int copy_info_records_to_user(struct fanotify_event *event,
total_bytes += ret;
}
+ if (fanotify_is_error_event(event->mask)) {
+ ret = copy_error_info_to_user(event, buf, count);
+ if (ret < 0)
+ return ret;
+ buf += ret;
+ count -= ret;
+ total_bytes += ret;
+ }
+
return total_bytes;
}
@@ -537,8 +583,7 @@ static ssize_t copy_event_to_user(struct fsnotify_group *group,
pr_debug("%s: group=%p event=%p\n", __func__, group, event);
- metadata.event_len = FAN_EVENT_METADATA_LEN +
- fanotify_event_info_len(info_mode, event);
+ metadata.event_len = fanotify_event_len(info_mode, event);
metadata.metadata_len = FAN_EVENT_METADATA_LEN;
metadata.vers = FANOTIFY_METADATA_VERSION;
metadata.reserved = 0;
@@ -1049,6 +1094,15 @@ out_dec_ucounts:
return ERR_PTR(ret);
}
+static int fanotify_group_init_error_pool(struct fsnotify_group *group)
+{
+ if (mempool_initialized(&group->fanotify_data.error_events_pool))
+ return 0;
+
+ return mempool_init_kmalloc_pool(&group->fanotify_data.error_events_pool,
+ FANOTIFY_DEFAULT_FEE_POOL_SIZE,
+ sizeof(struct fanotify_error_event));
+}
static int fanotify_add_mark(struct fsnotify_group *group,
fsnotify_connp_t *connp, unsigned int type,
@@ -1057,6 +1111,7 @@ static int fanotify_add_mark(struct fsnotify_group *group,
{
struct fsnotify_mark *fsn_mark;
__u32 added;
+ int ret = 0;
mutex_lock(&group->mark_mutex);
fsn_mark = fsnotify_find_mark(connp, group);
@@ -1067,13 +1122,26 @@ static int fanotify_add_mark(struct fsnotify_group *group,
return PTR_ERR(fsn_mark);
}
}
+
+ /*
+ * Error events are pre-allocated per group, only if strictly
+ * needed (i.e. FAN_FS_ERROR was requested).
+ */
+ if (!(flags & FAN_MARK_IGNORED_MASK) && (mask & FAN_FS_ERROR)) {
+ ret = fanotify_group_init_error_pool(group);
+ if (ret)
+ goto out;
+ }
+
added = fanotify_mark_add_to_mask(fsn_mark, mask, flags);
if (added & ~fsnotify_conn_mask(fsn_mark->connector))
fsnotify_recalc_mask(fsn_mark->connector);
+
+out:
mutex_unlock(&group->mark_mutex);
fsnotify_put_mark(fsn_mark);
- return 0;
+ return ret;
}
static int fanotify_add_vfsmount_mark(struct fsnotify_group *group,
@@ -1295,16 +1363,15 @@ out_destroy_group:
return fd;
}
-/* Check if filesystem can encode a unique fid */
-static int fanotify_test_fid(struct path *path, __kernel_fsid_t *fsid)
+static int fanotify_test_fsid(struct dentry *dentry, __kernel_fsid_t *fsid)
{
__kernel_fsid_t root_fsid;
int err;
/*
- * Make sure path is not in filesystem with zero fsid (e.g. tmpfs).
+ * Make sure dentry is not of a filesystem with zero fsid (e.g. fuse).
*/
- err = vfs_get_fsid(path->dentry, fsid);
+ err = vfs_get_fsid(dentry, fsid);
if (err)
return err;
@@ -1312,10 +1379,10 @@ static int fanotify_test_fid(struct path *path, __kernel_fsid_t *fsid)
return -ENODEV;
/*
- * Make sure path is not inside a filesystem subvolume (e.g. btrfs)
+ * Make sure dentry is not of a filesystem subvolume (e.g. btrfs)
* which uses a different fsid than sb root.
*/
- err = vfs_get_fsid(path->dentry->d_sb->s_root, &root_fsid);
+ err = vfs_get_fsid(dentry->d_sb->s_root, &root_fsid);
if (err)
return err;
@@ -1323,6 +1390,12 @@ static int fanotify_test_fid(struct path *path, __kernel_fsid_t *fsid)
root_fsid.val[1] != fsid->val[1])
return -EXDEV;
+ return 0;
+}
+
+/* Check if filesystem can encode a unique fid */
+static int fanotify_test_fid(struct dentry *dentry)
+{
/*
* We need to make sure that the file system supports at least
* encoding a file handle so user can use name_to_handle_at() to
@@ -1330,8 +1403,8 @@ static int fanotify_test_fid(struct path *path, __kernel_fsid_t *fsid)
* objects. However, name_to_handle_at() requires that the
* filesystem also supports decoding file handles.
*/
- if (!path->dentry->d_sb->s_export_op ||
- !path->dentry->d_sb->s_export_op->fh_to_dentry)
+ if (!dentry->d_sb->s_export_op ||
+ !dentry->d_sb->s_export_op->fh_to_dentry)
return -EOPNOTSUPP;
return 0;
@@ -1447,15 +1520,19 @@ static int do_fanotify_mark(int fanotify_fd, unsigned int flags, __u64 mask,
group->priority == FS_PRIO_0)
goto fput_and_out;
+ if (mask & FAN_FS_ERROR &&
+ mark_type != FAN_MARK_FILESYSTEM)
+ goto fput_and_out;
+
/*
- * Events with data type inode do not carry enough information to report
- * event->fd, so we do not allow setting a mask for inode events unless
- * group supports reporting fid.
- * inode events are not supported on a mount mark, because they do not
- * carry enough information (i.e. path) to be filtered by mount point.
+ * Events that do not carry enough information to report
+ * event->fd require a group that supports reporting fid. Those
+ * events are not supported on a mount mark, because they do not
+ * carry enough information (i.e. path) to be filtered by mount
+ * point.
*/
fid_mode = FAN_GROUP_FLAG(group, FANOTIFY_FID_BITS);
- if (mask & FANOTIFY_INODE_EVENTS &&
+ if (mask & ~(FANOTIFY_FD_EVENTS|FANOTIFY_EVENT_FLAGS) &&
(!fid_mode || mark_type == FAN_MARK_MOUNT))
goto fput_and_out;
@@ -1482,7 +1559,11 @@ static int do_fanotify_mark(int fanotify_fd, unsigned int flags, __u64 mask,
}
if (fid_mode) {
- ret = fanotify_test_fid(&path, &__fsid);
+ ret = fanotify_test_fsid(path.dentry, &__fsid);
+ if (ret)
+ goto path_put_and_out;
+
+ ret = fanotify_test_fid(path.dentry);
if (ret)
goto path_put_and_out;
diff --git a/fs/notify/fsnotify.c b/fs/notify/fsnotify.c
index 963e6ce75b96..4034ca566f95 100644
--- a/fs/notify/fsnotify.c
+++ b/fs/notify/fsnotify.c
@@ -252,6 +252,9 @@ static int fsnotify_handle_inode_event(struct fsnotify_group *group,
if (WARN_ON_ONCE(!ops->handle_inode_event))
return 0;
+ if (WARN_ON_ONCE(!inode && !dir))
+ return 0;
+
if ((inode_mark->mask & FS_EXCL_UNLINK) &&
path && d_unlinked(path->dentry))
return 0;
@@ -455,16 +458,16 @@ static void fsnotify_iter_next(struct fsnotify_iter_info *iter_info)
* @file_name is relative to
* @file_name: optional file name associated with event
* @inode: optional inode associated with event -
- * either @dir or @inode must be non-NULL.
- * if both are non-NULL event may be reported to both.
+ * If @dir and @inode are both non-NULL, event may be
+ * reported to both.
* @cookie: inotify rename cookie
*/
int fsnotify(__u32 mask, const void *data, int data_type, struct inode *dir,
const struct qstr *file_name, struct inode *inode, u32 cookie)
{
const struct path *path = fsnotify_data_path(data, data_type);
+ struct super_block *sb = fsnotify_data_sb(data, data_type);
struct fsnotify_iter_info iter_info = {};
- struct super_block *sb;
struct mount *mnt = NULL;
struct inode *parent = NULL;
int ret = 0;
@@ -483,7 +486,6 @@ int fsnotify(__u32 mask, const void *data, int data_type, struct inode *dir,
*/
parent = dir;
}
- sb = inode->i_sb;
/*
* Optimization: srcu_read_lock() has a memory barrier which can
diff --git a/fs/notify/group.c b/fs/notify/group.c
index fb89c351295d..6a297efc4788 100644
--- a/fs/notify/group.c
+++ b/fs/notify/group.c
@@ -88,7 +88,7 @@ void fsnotify_destroy_group(struct fsnotify_group *group)
* that deliberately ignores overflow events.
*/
if (group->overflow_event)
- group->ops->free_event(group->overflow_event);
+ group->ops->free_event(group, group->overflow_event);
fsnotify_put_group(group);
}
diff --git a/fs/notify/inotify/inotify_fsnotify.c b/fs/notify/inotify/inotify_fsnotify.c
index d1a64daa0171..d92d7b0adc9a 100644
--- a/fs/notify/inotify/inotify_fsnotify.c
+++ b/fs/notify/inotify/inotify_fsnotify.c
@@ -116,7 +116,7 @@ int inotify_handle_inode_event(struct fsnotify_mark *inode_mark, u32 mask,
if (len)
strcpy(event->name, name->name);
- ret = fsnotify_add_event(group, fsn_event, inotify_merge, NULL);
+ ret = fsnotify_add_event(group, fsn_event, inotify_merge);
if (ret) {
/* Our event wasn't used in the end. Free it. */
fsnotify_destroy_event(group, fsn_event);
@@ -177,7 +177,8 @@ static void inotify_free_group_priv(struct fsnotify_group *group)
dec_inotify_instances(group->inotify_data.ucounts);
}
-static void inotify_free_event(struct fsnotify_event *fsn_event)
+static void inotify_free_event(struct fsnotify_group *group,
+ struct fsnotify_event *fsn_event)
{
kfree(INOTIFY_E(fsn_event));
}
diff --git a/fs/notify/inotify/inotify_user.c b/fs/notify/inotify/inotify_user.c
index 62051247f6d2..29fca3284bb5 100644
--- a/fs/notify/inotify/inotify_user.c
+++ b/fs/notify/inotify/inotify_user.c
@@ -94,10 +94,10 @@ static inline __u32 inotify_arg_to_mask(struct inode *inode, u32 arg)
__u32 mask;
/*
- * Everything should accept their own ignored and should receive events
- * when the inode is unmounted. All directories care about children.
+ * Everything should receive events when the inode is unmounted.
+ * All directories care about children.
*/
- mask = (FS_IN_IGNORED | FS_UNMOUNT);
+ mask = (FS_UNMOUNT);
if (S_ISDIR(inode->i_mode))
mask |= FS_EVENT_ON_CHILD;
diff --git a/fs/notify/notification.c b/fs/notify/notification.c
index 32f45543b9c6..9022ae650cf8 100644
--- a/fs/notify/notification.c
+++ b/fs/notify/notification.c
@@ -64,7 +64,7 @@ void fsnotify_destroy_event(struct fsnotify_group *group,
WARN_ON(!list_empty(&event->list));
spin_unlock(&group->notification_lock);
}
- group->ops->free_event(event);
+ group->ops->free_event(group, event);
}
/*
@@ -78,12 +78,12 @@ void fsnotify_destroy_event(struct fsnotify_group *group,
* 2 if the event was not queued - either the queue of events has overflown
* or the group is shutting down.
*/
-int fsnotify_add_event(struct fsnotify_group *group,
- struct fsnotify_event *event,
- int (*merge)(struct fsnotify_group *,
- struct fsnotify_event *),
- void (*insert)(struct fsnotify_group *,
- struct fsnotify_event *))
+int fsnotify_insert_event(struct fsnotify_group *group,
+ struct fsnotify_event *event,
+ int (*merge)(struct fsnotify_group *,
+ struct fsnotify_event *),
+ void (*insert)(struct fsnotify_group *,
+ struct fsnotify_event *))
{
int ret = 0;
struct list_head *list = &group->notification_list;
diff --git a/fs/ocfs2/alloc.c b/fs/ocfs2/alloc.c
index 5d9ae17bd443..bb247bc349e4 100644
--- a/fs/ocfs2/alloc.c
+++ b/fs/ocfs2/alloc.c
@@ -5940,6 +5940,7 @@ static int ocfs2_replay_truncate_records(struct ocfs2_super *osb,
status = ocfs2_journal_access_di(handle, INODE_CACHE(tl_inode), tl_bh,
OCFS2_JOURNAL_ACCESS_WRITE);
if (status < 0) {
+ ocfs2_commit_trans(osb, handle);
mlog_errno(status);
goto bail;
}
@@ -5964,6 +5965,7 @@ static int ocfs2_replay_truncate_records(struct ocfs2_super *osb,
data_alloc_bh, start_blk,
num_clusters);
if (status < 0) {
+ ocfs2_commit_trans(osb, handle);
mlog_errno(status);
goto bail;
}
@@ -6921,13 +6923,12 @@ static int ocfs2_grab_eof_pages(struct inode *inode, loff_t start, loff_t end,
}
/*
- * Zero the area past i_size but still within an allocated
- * cluster. This avoids exposing nonzero data on subsequent file
- * extends.
+ * Zero partial cluster for a hole punch or truncate. This avoids exposing
+ * nonzero data on subsequent file extends.
*
* We need to call this before i_size is updated on the inode because
* otherwise block_write_full_page() will skip writeout of pages past
- * i_size. The new_i_size parameter is passed for this reason.
+ * i_size.
*/
int ocfs2_zero_range_for_truncate(struct inode *inode, handle_t *handle,
u64 range_start, u64 range_end)
@@ -6945,6 +6946,15 @@ int ocfs2_zero_range_for_truncate(struct inode *inode, handle_t *handle,
if (!ocfs2_sparse_alloc(OCFS2_SB(sb)))
return 0;
+ /*
+ * Avoid zeroing pages fully beyond current i_size. It is pointless as
+ * underlying blocks of those pages should be already zeroed out and
+ * page writeback will skip them anyway.
+ */
+ range_end = min_t(u64, range_end, i_size_read(inode));
+ if (range_start >= range_end)
+ return 0;
+
pages = kcalloc(ocfs2_pages_per_cluster(sb),
sizeof(struct page *), GFP_NOFS);
if (pages == NULL) {
@@ -6953,9 +6963,6 @@ int ocfs2_zero_range_for_truncate(struct inode *inode, handle_t *handle,
goto out;
}
- if (range_start == range_end)
- goto out;
-
ret = ocfs2_extent_map_get_blocks(inode,
range_start >> sb->s_blocksize_bits,
&phys, NULL, &ext_flags);
diff --git a/fs/ocfs2/dlm/dlmrecovery.c b/fs/ocfs2/dlm/dlmrecovery.c
index 0e7aad1b11cc..5cd5f7511dac 100644
--- a/fs/ocfs2/dlm/dlmrecovery.c
+++ b/fs/ocfs2/dlm/dlmrecovery.c
@@ -2698,7 +2698,6 @@ static int dlm_send_begin_reco_message(struct dlm_ctxt *dlm, u8 dead_node)
continue;
}
retry:
- ret = -EINVAL;
mlog(0, "attempting to send begin reco msg to %d\n",
nodenum);
ret = o2net_send_message(DLM_BEGIN_RECO_MSG, dlm->key,
diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c
index 54d7843c0211..fc5f780fa235 100644
--- a/fs/ocfs2/file.c
+++ b/fs/ocfs2/file.c
@@ -476,10 +476,11 @@ int ocfs2_truncate_file(struct inode *inode,
* greater than page size, so we have to truncate them
* anyway.
*/
- unmap_mapping_range(inode->i_mapping, new_i_size + PAGE_SIZE - 1, 0, 1);
- truncate_inode_pages(inode->i_mapping, new_i_size);
if (OCFS2_I(inode)->ip_dyn_features & OCFS2_INLINE_DATA_FL) {
+ unmap_mapping_range(inode->i_mapping,
+ new_i_size + PAGE_SIZE - 1, 0, 1);
+ truncate_inode_pages(inode->i_mapping, new_i_size);
status = ocfs2_truncate_inline(inode, di_bh, new_i_size,
i_size_read(inode), 1);
if (status)
@@ -498,6 +499,9 @@ int ocfs2_truncate_file(struct inode *inode,
goto bail_unlock_sem;
}
+ unmap_mapping_range(inode->i_mapping, new_i_size + PAGE_SIZE - 1, 0, 1);
+ truncate_inode_pages(inode->i_mapping, new_i_size);
+
status = ocfs2_commit_truncate(osb, inode, di_bh);
if (status < 0) {
mlog_errno(status);
diff --git a/fs/ocfs2/inode.c b/fs/ocfs2/inode.c
index bc8f32fab964..6c2411c2afcf 100644
--- a/fs/ocfs2/inode.c
+++ b/fs/ocfs2/inode.c
@@ -125,7 +125,6 @@ struct inode *ocfs2_iget(struct ocfs2_super *osb, u64 blkno, unsigned flags,
struct inode *inode = NULL;
struct super_block *sb = osb->sb;
struct ocfs2_find_inode_args args;
- journal_t *journal = OCFS2_SB(sb)->journal->j_journal;
trace_ocfs2_iget_begin((unsigned long long)blkno, flags,
sysfile_type);
@@ -172,10 +171,11 @@ struct inode *ocfs2_iget(struct ocfs2_super *osb, u64 blkno, unsigned flags,
* part of the transaction - the inode could have been reclaimed and
* now it is reread from disk.
*/
- if (journal) {
+ if (osb->journal) {
transaction_t *transaction;
tid_t tid;
struct ocfs2_inode_info *oi = OCFS2_I(inode);
+ journal_t *journal = osb->journal->j_journal;
read_lock(&journal->j_state_lock);
if (journal->j_running_transaction)
diff --git a/fs/ocfs2/journal.c b/fs/ocfs2/journal.c
index 4f15750aac5d..dbf9b9e97d74 100644
--- a/fs/ocfs2/journal.c
+++ b/fs/ocfs2/journal.c
@@ -810,19 +810,34 @@ void ocfs2_set_journal_params(struct ocfs2_super *osb)
write_unlock(&journal->j_state_lock);
}
-int ocfs2_journal_init(struct ocfs2_journal *journal, int *dirty)
+int ocfs2_journal_init(struct ocfs2_super *osb, int *dirty)
{
int status = -1;
struct inode *inode = NULL; /* the journal inode */
journal_t *j_journal = NULL;
+ struct ocfs2_journal *journal = NULL;
struct ocfs2_dinode *di = NULL;
struct buffer_head *bh = NULL;
- struct ocfs2_super *osb;
int inode_lock = 0;
- BUG_ON(!journal);
+ /* initialize our journal structure */
+ journal = kzalloc(sizeof(struct ocfs2_journal), GFP_KERNEL);
+ if (!journal) {
+ mlog(ML_ERROR, "unable to alloc journal\n");
+ status = -ENOMEM;
+ goto done;
+ }
+ osb->journal = journal;
+ journal->j_osb = osb;
- osb = journal->j_osb;
+ atomic_set(&journal->j_num_trans, 0);
+ init_rwsem(&journal->j_trans_barrier);
+ init_waitqueue_head(&journal->j_checkpointed);
+ spin_lock_init(&journal->j_lock);
+ journal->j_trans_id = 1UL;
+ INIT_LIST_HEAD(&journal->j_la_cleanups);
+ INIT_WORK(&journal->j_recovery_work, ocfs2_complete_recovery);
+ journal->j_state = OCFS2_JOURNAL_FREE;
/* already have the inode for our journal */
inode = ocfs2_get_system_file_inode(osb, JOURNAL_SYSTEM_INODE,
@@ -1028,9 +1043,10 @@ void ocfs2_journal_shutdown(struct ocfs2_super *osb)
journal->j_state = OCFS2_JOURNAL_FREE;
-// up_write(&journal->j_trans_barrier);
done:
iput(inode);
+ kfree(journal);
+ osb->journal = NULL;
}
static void ocfs2_clear_journal_error(struct super_block *sb,
@@ -1497,10 +1513,7 @@ bail:
if (quota_enabled)
kfree(rm_quota);
- /* no one is callint kthread_stop() for us so the kthread() api
- * requires that we call do_exit(). And it isn't exported, but
- * complete_and_exit() seems to be a minimal wrapper around it. */
- complete_and_exit(NULL, status);
+ return status;
}
void ocfs2_recovery_thread(struct ocfs2_super *osb, int node_num)
diff --git a/fs/ocfs2/journal.h b/fs/ocfs2/journal.h
index d158acb8b38a..8dcb2f2cadbc 100644
--- a/fs/ocfs2/journal.h
+++ b/fs/ocfs2/journal.h
@@ -167,8 +167,7 @@ int ocfs2_compute_replay_slots(struct ocfs2_super *osb);
* ocfs2_start_checkpoint - Kick the commit thread to do a checkpoint.
*/
void ocfs2_set_journal_params(struct ocfs2_super *osb);
-int ocfs2_journal_init(struct ocfs2_journal *journal,
- int *dirty);
+int ocfs2_journal_init(struct ocfs2_super *osb, int *dirty);
void ocfs2_journal_shutdown(struct ocfs2_super *osb);
int ocfs2_journal_wipe(struct ocfs2_journal *journal,
int full);
diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c
index 5c914ce9b3ac..1286b88b6fa1 100644
--- a/fs/ocfs2/super.c
+++ b/fs/ocfs2/super.c
@@ -1894,8 +1894,6 @@ static void ocfs2_dismount_volume(struct super_block *sb, int mnt_err)
/* This will disable recovery and flush any recovery work. */
ocfs2_recovery_exit(osb);
- ocfs2_journal_shutdown(osb);
-
ocfs2_sync_blockdev(sb);
ocfs2_purge_refcount_trees(osb);
@@ -1918,6 +1916,8 @@ static void ocfs2_dismount_volume(struct super_block *sb, int mnt_err)
ocfs2_release_system_inodes(osb);
+ ocfs2_journal_shutdown(osb);
+
/*
* If we're dismounting due to mount error, mount.ocfs2 will clean
* up heartbeat. If we're a local mount, there is no heartbeat.
@@ -2016,7 +2016,6 @@ static int ocfs2_initialize_super(struct super_block *sb,
int i, cbits, bbits;
struct ocfs2_dinode *di = (struct ocfs2_dinode *)bh->b_data;
struct inode *inode = NULL;
- struct ocfs2_journal *journal;
struct ocfs2_super *osb;
u64 total_blocks;
@@ -2197,33 +2196,6 @@ static int ocfs2_initialize_super(struct super_block *sb,
get_random_bytes(&osb->s_next_generation, sizeof(u32));
- /* FIXME
- * This should be done in ocfs2_journal_init(), but unknown
- * ordering issues will cause the filesystem to crash.
- * If anyone wants to figure out what part of the code
- * refers to osb->journal before ocfs2_journal_init() is run,
- * be my guest.
- */
- /* initialize our journal structure */
-
- journal = kzalloc(sizeof(struct ocfs2_journal), GFP_KERNEL);
- if (!journal) {
- mlog(ML_ERROR, "unable to alloc journal\n");
- status = -ENOMEM;
- goto bail;
- }
- osb->journal = journal;
- journal->j_osb = osb;
-
- atomic_set(&journal->j_num_trans, 0);
- init_rwsem(&journal->j_trans_barrier);
- init_waitqueue_head(&journal->j_checkpointed);
- spin_lock_init(&journal->j_lock);
- journal->j_trans_id = (unsigned long) 1;
- INIT_LIST_HEAD(&journal->j_la_cleanups);
- INIT_WORK(&journal->j_recovery_work, ocfs2_complete_recovery);
- journal->j_state = OCFS2_JOURNAL_FREE;
-
INIT_WORK(&osb->dquot_drop_work, ocfs2_drop_dquot_refs);
init_llist_head(&osb->dquot_drop_list);
@@ -2404,7 +2376,7 @@ static int ocfs2_check_volume(struct ocfs2_super *osb)
* ourselves. */
/* Init our journal object. */
- status = ocfs2_journal_init(osb->journal, &dirty);
+ status = ocfs2_journal_init(osb, &dirty);
if (status < 0) {
mlog(ML_ERROR, "Could not initialize journal!\n");
goto finally;
@@ -2513,12 +2485,6 @@ static void ocfs2_delete_osb(struct ocfs2_super *osb)
kfree(osb->osb_orphan_wipes);
kfree(osb->slot_recovery_generations);
- /* FIXME
- * This belongs in journal shutdown, but because we have to
- * allocate osb->journal at the start of ocfs2_initialize_osb(),
- * we free it here.
- */
- kfree(osb->journal);
kfree(osb->local_alloc_copy);
kfree(osb->uuid_str);
kfree(osb->vol_label);
diff --git a/fs/open.c b/fs/open.c
index a7f6cab81267..f732fb94600c 100644
--- a/fs/open.c
+++ b/fs/open.c
@@ -856,8 +856,20 @@ static int do_dentry_open(struct file *f,
* of THPs into the page cache will fail.
*/
smp_mb();
- if (filemap_nr_thps(inode->i_mapping))
- truncate_pagecache(inode, 0);
+ if (filemap_nr_thps(inode->i_mapping)) {
+ struct address_space *mapping = inode->i_mapping;
+
+ filemap_invalidate_lock(inode->i_mapping);
+ /*
+ * unmap_mapping_range just need to be called once
+ * here, because the private pages is not need to be
+ * unmapped mapping (e.g. data segment of dynamic
+ * shared libraries here).
+ */
+ unmap_mapping_range(mapping, 0, 0, 0);
+ truncate_inode_pages(mapping, 0);
+ filemap_invalidate_unlock(inode->i_mapping);
+ }
}
return 0;
diff --git a/fs/orangefs/dcache.c b/fs/orangefs/dcache.c
index fe484cf93e5c..8bbe9486e3a6 100644
--- a/fs/orangefs/dcache.c
+++ b/fs/orangefs/dcache.c
@@ -26,8 +26,10 @@ static int orangefs_revalidate_lookup(struct dentry *dentry)
gossip_debug(GOSSIP_DCACHE_DEBUG, "%s: attempting lookup.\n", __func__);
new_op = op_alloc(ORANGEFS_VFS_OP_LOOKUP);
- if (!new_op)
+ if (!new_op) {
+ ret = -ENOMEM;
goto out_put_parent;
+ }
new_op->upcall.req.lookup.sym_follow = ORANGEFS_LOOKUP_LINK_NO_FOLLOW;
new_op->upcall.req.lookup.parent_refn = parent->refn;
diff --git a/fs/orangefs/super.c b/fs/orangefs/super.c
index 8bb0a53a658b..d90d8addbfc2 100644
--- a/fs/orangefs/super.c
+++ b/fs/orangefs/super.c
@@ -476,7 +476,7 @@ struct dentry *orangefs_mount(struct file_system_type *fst,
const char *devname,
void *data)
{
- int ret = -EINVAL;
+ int ret;
struct super_block *sb = ERR_PTR(-EINVAL);
struct orangefs_kernel_op_s *new_op;
struct dentry *d = ERR_PTR(-EINVAL);
@@ -527,7 +527,7 @@ struct dentry *orangefs_mount(struct file_system_type *fst,
sb->s_fs_info = kzalloc(sizeof(struct orangefs_sb_info_s), GFP_KERNEL);
if (!ORANGEFS_SB(sb)) {
d = ERR_PTR(-ENOMEM);
- goto free_op;
+ goto free_sb_and_op;
}
ret = orangefs_fill_sb(sb,
diff --git a/fs/overlayfs/copy_up.c b/fs/overlayfs/copy_up.c
index 4e7d5bfa2949..b193d08a3dc3 100644
--- a/fs/overlayfs/copy_up.c
+++ b/fs/overlayfs/copy_up.c
@@ -140,12 +140,14 @@ static int ovl_copy_fileattr(struct inode *inode, struct path *old,
int err;
err = ovl_real_fileattr_get(old, &oldfa);
- if (err)
- return err;
-
- err = ovl_real_fileattr_get(new, &newfa);
- if (err)
+ if (err) {
+ /* Ntfs-3g returns -EINVAL for "no fileattr support" */
+ if (err == -ENOTTY || err == -EINVAL)
+ return 0;
+ pr_warn("failed to retrieve lower fileattr (%pd2, err=%i)\n",
+ old, err);
return err;
+ }
/*
* We cannot set immutable and append-only flags on upper inode,
@@ -159,6 +161,17 @@ static int ovl_copy_fileattr(struct inode *inode, struct path *old,
return err;
}
+ /* Don't bother copying flags if none are set */
+ if (!(oldfa.flags & OVL_COPY_FS_FLAGS_MASK))
+ return 0;
+
+ err = ovl_real_fileattr_get(new, &newfa);
+ if (err) {
+ pr_warn("failed to retrieve upper fileattr (%pd2, err=%i)\n",
+ new, err);
+ return err;
+ }
+
BUILD_BUG_ON(OVL_COPY_FS_FLAGS_MASK & ~FS_COMMON_FL);
newfa.flags &= ~OVL_COPY_FS_FLAGS_MASK;
newfa.flags |= (oldfa.flags & OVL_COPY_FS_FLAGS_MASK);
diff --git a/fs/overlayfs/dir.c b/fs/overlayfs/dir.c
index 93c7c267de93..f18490813170 100644
--- a/fs/overlayfs/dir.c
+++ b/fs/overlayfs/dir.c
@@ -137,8 +137,7 @@ kill_whiteout:
goto out;
}
-static int ovl_mkdir_real(struct inode *dir, struct dentry **newdentry,
- umode_t mode)
+int ovl_mkdir_real(struct inode *dir, struct dentry **newdentry, umode_t mode)
{
int err;
struct dentry *d, *dentry = *newdentry;
diff --git a/fs/overlayfs/file.c b/fs/overlayfs/file.c
index ac461a499882..fa125feed0ff 100644
--- a/fs/overlayfs/file.c
+++ b/fs/overlayfs/file.c
@@ -17,6 +17,7 @@
struct ovl_aio_req {
struct kiocb iocb;
+ refcount_t ref;
struct kiocb *orig_iocb;
struct fd fd;
};
@@ -252,6 +253,14 @@ static rwf_t ovl_iocb_to_rwf(int ifl)
return flags;
}
+static inline void ovl_aio_put(struct ovl_aio_req *aio_req)
+{
+ if (refcount_dec_and_test(&aio_req->ref)) {
+ fdput(aio_req->fd);
+ kmem_cache_free(ovl_aio_request_cachep, aio_req);
+ }
+}
+
static void ovl_aio_cleanup_handler(struct ovl_aio_req *aio_req)
{
struct kiocb *iocb = &aio_req->iocb;
@@ -268,8 +277,7 @@ static void ovl_aio_cleanup_handler(struct ovl_aio_req *aio_req)
}
orig_iocb->ki_pos = iocb->ki_pos;
- fdput(aio_req->fd);
- kmem_cache_free(ovl_aio_request_cachep, aio_req);
+ ovl_aio_put(aio_req);
}
static void ovl_aio_rw_complete(struct kiocb *iocb, long res)
@@ -319,7 +327,9 @@ static ssize_t ovl_read_iter(struct kiocb *iocb, struct iov_iter *iter)
aio_req->orig_iocb = iocb;
kiocb_clone(&aio_req->iocb, iocb, real.file);
aio_req->iocb.ki_complete = ovl_aio_rw_complete;
+ refcount_set(&aio_req->ref, 2);
ret = vfs_iocb_iter_read(real.file, &aio_req->iocb, iter);
+ ovl_aio_put(aio_req);
if (ret != -EIOCBQUEUED)
ovl_aio_cleanup_handler(aio_req);
}
@@ -390,7 +400,9 @@ static ssize_t ovl_write_iter(struct kiocb *iocb, struct iov_iter *iter)
kiocb_clone(&aio_req->iocb, iocb, real.file);
aio_req->iocb.ki_flags = ifl;
aio_req->iocb.ki_complete = ovl_aio_rw_complete;
+ refcount_set(&aio_req->ref, 2);
ret = vfs_iocb_iter_write(real.file, &aio_req->iocb, iter);
+ ovl_aio_put(aio_req);
if (ret != -EIOCBQUEUED)
ovl_aio_cleanup_handler(aio_req);
}
diff --git a/fs/overlayfs/inode.c b/fs/overlayfs/inode.c
index 832b17589733..1f36158c7dbe 100644
--- a/fs/overlayfs/inode.c
+++ b/fs/overlayfs/inode.c
@@ -610,7 +610,10 @@ int ovl_real_fileattr_get(struct path *realpath, struct fileattr *fa)
if (err)
return err;
- return vfs_fileattr_get(realpath->dentry, fa);
+ err = vfs_fileattr_get(realpath->dentry, fa);
+ if (err == -ENOIOCTLCMD)
+ err = -ENOTTY;
+ return err;
}
int ovl_fileattr_get(struct dentry *dentry, struct fileattr *fa)
diff --git a/fs/overlayfs/overlayfs.h b/fs/overlayfs/overlayfs.h
index 3894f3347955..2cd5741c873b 100644
--- a/fs/overlayfs/overlayfs.h
+++ b/fs/overlayfs/overlayfs.h
@@ -570,6 +570,7 @@ struct ovl_cattr {
#define OVL_CATTR(m) (&(struct ovl_cattr) { .mode = (m) })
+int ovl_mkdir_real(struct inode *dir, struct dentry **newdentry, umode_t mode);
struct dentry *ovl_create_real(struct inode *dir, struct dentry *newdentry,
struct ovl_cattr *attr);
int ovl_cleanup(struct inode *dir, struct dentry *dentry);
diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c
index 178daa5e82c9..265181c110ae 100644
--- a/fs/overlayfs/super.c
+++ b/fs/overlayfs/super.c
@@ -787,10 +787,14 @@ retry:
goto retry;
}
- work = ovl_create_real(dir, work, OVL_CATTR(attr.ia_mode));
- err = PTR_ERR(work);
- if (IS_ERR(work))
- goto out_err;
+ err = ovl_mkdir_real(dir, &work, attr.ia_mode);
+ if (err)
+ goto out_dput;
+
+ /* Weird filesystem returning with hashed negative (kernfs)? */
+ err = -EINVAL;
+ if (d_really_is_negative(work))
+ goto out_dput;
/*
* Try to remove POSIX ACL xattrs from workdir. We are good if:
diff --git a/fs/posix_acl.c b/fs/posix_acl.c
index f5c25f580dd9..9323a854a60a 100644
--- a/fs/posix_acl.c
+++ b/fs/posix_acl.c
@@ -134,8 +134,7 @@ struct posix_acl *get_acl(struct inode *inode, int type)
* to just call ->get_acl to fetch the ACL ourself. (This is going to
* be an unlikely race.)
*/
- if (cmpxchg(p, ACL_NOT_CACHED, sentinel) != ACL_NOT_CACHED)
- /* fall through */ ;
+ cmpxchg(p, ACL_NOT_CACHED, sentinel);
/*
* Normally, the ACL returned by ->get_acl will be cached.
diff --git a/fs/proc/array.c b/fs/proc/array.c
index 77cf4187adec..ff869a66b34e 100644
--- a/fs/proc/array.c
+++ b/fs/proc/array.c
@@ -408,9 +408,9 @@ static void task_cpus_allowed(struct seq_file *m, struct task_struct *task)
cpumask_pr_args(&task->cpus_mask));
}
-static inline void task_core_dumping(struct seq_file *m, struct mm_struct *mm)
+static inline void task_core_dumping(struct seq_file *m, struct task_struct *task)
{
- seq_put_decimal_ull(m, "CoreDumping:\t", !!mm->core_state);
+ seq_put_decimal_ull(m, "CoreDumping:\t", !!task->signal->core_state);
seq_putc(m, '\n');
}
@@ -436,7 +436,7 @@ int proc_pid_status(struct seq_file *m, struct pid_namespace *ns,
if (mm) {
task_mem(m, mm);
- task_core_dumping(m, mm);
+ task_core_dumping(m, task);
task_thp_status(m, mm);
mmput(mm);
}
diff --git a/fs/proc/base.c b/fs/proc/base.c
index 1f394095eb88..13eda8de2998 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -1982,19 +1982,21 @@ static int pid_revalidate(struct dentry *dentry, unsigned int flags)
{
struct inode *inode;
struct task_struct *task;
+ int ret = 0;
- if (flags & LOOKUP_RCU)
- return -ECHILD;
-
- inode = d_inode(dentry);
- task = get_proc_task(inode);
+ rcu_read_lock();
+ inode = d_inode_rcu(dentry);
+ if (!inode)
+ goto out;
+ task = pid_task(proc_pid(inode), PIDTYPE_PID);
if (task) {
pid_update_inode(task, inode);
- put_task_struct(task);
- return 1;
+ ret = 1;
}
- return 0;
+out:
+ rcu_read_unlock();
+ return ret;
}
static inline bool proc_inode_is_dead(struct inode *inode)
@@ -3802,7 +3804,10 @@ static int proc_task_readdir(struct file *file, struct dir_context *ctx)
task = next_tid(task), ctx->pos++) {
char name[10 + 1];
unsigned int len;
+
tid = task_pid_nr_ns(task, ns);
+ if (!tid)
+ continue; /* The task has just exited. */
len = snprintf(name, sizeof(name), "%u", tid);
if (!proc_fill_cache(file, ctx, name, len,
proc_task_instantiate, task, NULL)) {
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index cf25be3e0321..ad667dbc96f5 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -397,7 +397,6 @@ struct mem_size_stats {
u64 pss_shmem;
u64 pss_locked;
u64 swap_pss;
- bool check_shmem_swap;
};
static void smaps_page_accumulate(struct mem_size_stats *mss,
@@ -478,9 +477,11 @@ static int smaps_pte_hole(unsigned long addr, unsigned long end,
__always_unused int depth, struct mm_walk *walk)
{
struct mem_size_stats *mss = walk->private;
+ struct vm_area_struct *vma = walk->vma;
- mss->swap += shmem_partial_swap_usage(
- walk->vma->vm_file->f_mapping, addr, end);
+ mss->swap += shmem_partial_swap_usage(walk->vma->vm_file->f_mapping,
+ linear_page_index(vma, addr),
+ linear_page_index(vma, end));
return 0;
}
@@ -488,6 +489,16 @@ static int smaps_pte_hole(unsigned long addr, unsigned long end,
#define smaps_pte_hole NULL
#endif /* CONFIG_SHMEM */
+static void smaps_pte_hole_lookup(unsigned long addr, struct mm_walk *walk)
+{
+#ifdef CONFIG_SHMEM
+ if (walk->ops->pte_hole) {
+ /* depth is not used */
+ smaps_pte_hole(addr, addr + PAGE_SIZE, 0, walk);
+ }
+#endif
+}
+
static void smaps_pte_entry(pte_t *pte, unsigned long addr,
struct mm_walk *walk)
{
@@ -516,12 +527,8 @@ static void smaps_pte_entry(pte_t *pte, unsigned long addr,
}
} else if (is_pfn_swap_entry(swpent))
page = pfn_swap_entry_to_page(swpent);
- } else if (unlikely(IS_ENABLED(CONFIG_SHMEM) && mss->check_shmem_swap
- && pte_none(*pte))) {
- page = xa_load(&vma->vm_file->f_mapping->i_pages,
- linear_page_index(vma, addr));
- if (xa_is_value(page))
- mss->swap += PAGE_SIZE;
+ } else {
+ smaps_pte_hole_lookup(addr, walk);
return;
}
@@ -735,8 +742,6 @@ static void smap_gather_stats(struct vm_area_struct *vma,
return;
#ifdef CONFIG_SHMEM
- /* In case of smaps_rollup, reset the value from previous vma */
- mss->check_shmem_swap = false;
if (vma->vm_file && shmem_mapping(vma->vm_file->f_mapping)) {
/*
* For shared or readonly shmem mappings we know that all
@@ -754,7 +759,6 @@ static void smap_gather_stats(struct vm_area_struct *vma,
!(vma->vm_flags & VM_WRITE))) {
mss->swap += shmem_swapped;
} else {
- mss->check_shmem_swap = true;
ops = &smaps_shmem_walk_ops;
}
}
diff --git a/fs/proc/vmcore.c b/fs/proc/vmcore.c
index cdbbf819d2d6..30a3b66f475a 100644
--- a/fs/proc/vmcore.c
+++ b/fs/proc/vmcore.c
@@ -62,46 +62,75 @@ core_param(novmcoredd, vmcoredd_disabled, bool, 0);
/* Device Dump Size */
static size_t vmcoredd_orig_sz;
-/*
- * Returns > 0 for RAM pages, 0 for non-RAM pages, < 0 on error
- * The called function has to take care of module refcounting.
- */
-static int (*oldmem_pfn_is_ram)(unsigned long pfn);
-
-int register_oldmem_pfn_is_ram(int (*fn)(unsigned long pfn))
+static DECLARE_RWSEM(vmcore_cb_rwsem);
+/* List of registered vmcore callbacks. */
+static LIST_HEAD(vmcore_cb_list);
+/* Whether we had a surprise unregistration of a callback. */
+static bool vmcore_cb_unstable;
+/* Whether the vmcore has been opened once. */
+static bool vmcore_opened;
+
+void register_vmcore_cb(struct vmcore_cb *cb)
{
- if (oldmem_pfn_is_ram)
- return -EBUSY;
- oldmem_pfn_is_ram = fn;
- return 0;
+ down_write(&vmcore_cb_rwsem);
+ INIT_LIST_HEAD(&cb->next);
+ list_add_tail(&cb->next, &vmcore_cb_list);
+ /*
+ * Registering a vmcore callback after the vmcore was opened is
+ * very unusual (e.g., manual driver loading).
+ */
+ if (vmcore_opened)
+ pr_warn_once("Unexpected vmcore callback registration\n");
+ up_write(&vmcore_cb_rwsem);
}
-EXPORT_SYMBOL_GPL(register_oldmem_pfn_is_ram);
+EXPORT_SYMBOL_GPL(register_vmcore_cb);
-void unregister_oldmem_pfn_is_ram(void)
+void unregister_vmcore_cb(struct vmcore_cb *cb)
{
- oldmem_pfn_is_ram = NULL;
- wmb();
+ down_write(&vmcore_cb_rwsem);
+ list_del(&cb->next);
+ /*
+ * Unregistering a vmcore callback after the vmcore was opened is
+ * very unusual (e.g., forced driver removal), but we cannot stop
+ * unregistering.
+ */
+ if (vmcore_opened) {
+ pr_warn_once("Unexpected vmcore callback unregistration\n");
+ vmcore_cb_unstable = true;
+ }
+ up_write(&vmcore_cb_rwsem);
}
-EXPORT_SYMBOL_GPL(unregister_oldmem_pfn_is_ram);
+EXPORT_SYMBOL_GPL(unregister_vmcore_cb);
-static int pfn_is_ram(unsigned long pfn)
+static bool pfn_is_ram(unsigned long pfn)
{
- int (*fn)(unsigned long pfn);
- /* pfn is ram unless fn() checks pagetype */
- int ret = 1;
+ struct vmcore_cb *cb;
+ bool ret = true;
- /*
- * Ask hypervisor if the pfn is really ram.
- * A ballooned page contains no data and reading from such a page
- * will cause high load in the hypervisor.
- */
- fn = oldmem_pfn_is_ram;
- if (fn)
- ret = fn(pfn);
+ lockdep_assert_held_read(&vmcore_cb_rwsem);
+ if (unlikely(vmcore_cb_unstable))
+ return false;
+
+ list_for_each_entry(cb, &vmcore_cb_list, next) {
+ if (unlikely(!cb->pfn_is_ram))
+ continue;
+ ret = cb->pfn_is_ram(cb, pfn);
+ if (!ret)
+ break;
+ }
return ret;
}
+static int open_vmcore(struct inode *inode, struct file *file)
+{
+ down_read(&vmcore_cb_rwsem);
+ vmcore_opened = true;
+ up_read(&vmcore_cb_rwsem);
+
+ return 0;
+}
+
/* Reads a page from the oldmem device from given offset. */
ssize_t read_from_oldmem(char *buf, size_t count,
u64 *ppos, int userbuf,
@@ -117,6 +146,7 @@ ssize_t read_from_oldmem(char *buf, size_t count,
offset = (unsigned long)(*ppos % PAGE_SIZE);
pfn = (unsigned long)(*ppos / PAGE_SIZE);
+ down_read(&vmcore_cb_rwsem);
do {
if (count > (PAGE_SIZE - offset))
nr_bytes = PAGE_SIZE - offset;
@@ -124,7 +154,7 @@ ssize_t read_from_oldmem(char *buf, size_t count,
nr_bytes = count;
/* If pfn is not ram, return zeros for sparse dump files */
- if (pfn_is_ram(pfn) == 0)
+ if (!pfn_is_ram(pfn))
memset(buf, 0, nr_bytes);
else {
if (encrypted)
@@ -136,8 +166,10 @@ ssize_t read_from_oldmem(char *buf, size_t count,
tmp = copy_oldmem_page(pfn, buf, nr_bytes,
offset, userbuf);
- if (tmp < 0)
+ if (tmp < 0) {
+ up_read(&vmcore_cb_rwsem);
return tmp;
+ }
}
*ppos += nr_bytes;
count -= nr_bytes;
@@ -147,6 +179,7 @@ ssize_t read_from_oldmem(char *buf, size_t count,
offset = 0;
} while (count);
+ up_read(&vmcore_cb_rwsem);
return read;
}
@@ -537,14 +570,19 @@ static int vmcore_remap_oldmem_pfn(struct vm_area_struct *vma,
unsigned long from, unsigned long pfn,
unsigned long size, pgprot_t prot)
{
+ int ret;
+
/*
* Check if oldmem_pfn_is_ram was registered to avoid
* looping over all pages without a reason.
*/
- if (oldmem_pfn_is_ram)
- return remap_oldmem_pfn_checked(vma, from, pfn, size, prot);
+ down_read(&vmcore_cb_rwsem);
+ if (!list_empty(&vmcore_cb_list) || vmcore_cb_unstable)
+ ret = remap_oldmem_pfn_checked(vma, from, pfn, size, prot);
else
- return remap_oldmem_pfn_range(vma, from, pfn, size, prot);
+ ret = remap_oldmem_pfn_range(vma, from, pfn, size, prot);
+ up_read(&vmcore_cb_rwsem);
+ return ret;
}
static int mmap_vmcore(struct file *file, struct vm_area_struct *vma)
@@ -668,6 +706,7 @@ static int mmap_vmcore(struct file *file, struct vm_area_struct *vma)
#endif
static const struct proc_ops vmcore_proc_ops = {
+ .proc_open = open_vmcore,
.proc_read = read_vmcore,
.proc_lseek = default_llseek,
.proc_mmap = mmap_vmcore,
diff --git a/fs/quota/quota_tree.c b/fs/quota/quota_tree.c
index d3e995e1046f..5f2405994280 100644
--- a/fs/quota/quota_tree.c
+++ b/fs/quota/quota_tree.c
@@ -414,6 +414,7 @@ static int free_dqentry(struct qtree_mem_dqinfo *info, struct dquot *dquot,
quota_error(dquot->dq_sb, "Quota structure has offset to "
"other block (%u) than it should (%u)", blk,
(uint)(dquot->dq_off >> info->dqi_blocksize_bits));
+ ret = -EIO;
goto out_buf;
}
ret = read_blk(info, blk, buf);
@@ -479,6 +480,13 @@ static int remove_tree(struct qtree_mem_dqinfo *info, struct dquot *dquot,
goto out_buf;
}
newblk = le32_to_cpu(ref[get_index(info, dquot->dq_id, depth)]);
+ if (newblk < QT_TREEOFF || newblk >= info->dqi_blocks) {
+ quota_error(dquot->dq_sb, "Getting block too big (%u >= %u)",
+ newblk, info->dqi_blocks);
+ ret = -EUCLEAN;
+ goto out_buf;
+ }
+
if (depth == info->dqi_qtree_depth - 1) {
ret = free_dqentry(info, dquot, newblk);
newblk = 0;
@@ -578,6 +586,13 @@ static loff_t find_tree_dqentry(struct qtree_mem_dqinfo *info,
blk = le32_to_cpu(ref[get_index(info, dquot->dq_id, depth)]);
if (!blk) /* No reference? */
goto out_buf;
+ if (blk < QT_TREEOFF || blk >= info->dqi_blocks) {
+ quota_error(dquot->dq_sb, "Getting block too big (%u >= %u)",
+ blk, info->dqi_blocks);
+ ret = -EUCLEAN;
+ goto out_buf;
+ }
+
if (depth < info->dqi_qtree_depth - 1)
ret = find_tree_dqentry(info, dquot, blk, depth+1);
else
diff --git a/fs/ramfs/inode.c b/fs/ramfs/inode.c
index e2302342a67f..bc66d0173e33 100644
--- a/fs/ramfs/inode.c
+++ b/fs/ramfs/inode.c
@@ -204,17 +204,20 @@ static int ramfs_parse_param(struct fs_context *fc, struct fs_parameter *param)
int opt;
opt = fs_parse(fc, ramfs_fs_parameters, param, &result);
- if (opt < 0) {
+ if (opt == -ENOPARAM) {
+ opt = vfs_parse_fs_param_source(fc, param);
+ if (opt != -ENOPARAM)
+ return opt;
/*
* We might like to report bad mount options here;
* but traditionally ramfs has ignored all mount options,
* and as it is used as a !CONFIG_SHMEM simple substitute
* for tmpfs, better continue to ignore other mount options.
*/
- if (opt == -ENOPARAM)
- opt = 0;
- return opt;
+ return 0;
}
+ if (opt < 0)
+ return opt;
switch (opt) {
case Opt_mode:
diff --git a/fs/reiserfs/super.c b/fs/reiserfs/super.c
index 076f9ab94306..82e09901462e 100644
--- a/fs/reiserfs/super.c
+++ b/fs/reiserfs/super.c
@@ -1435,7 +1435,6 @@ static int reiserfs_remount(struct super_block *s, int *mount_flags, char *arg)
unsigned long safe_mask = 0;
unsigned int commit_max_age = (unsigned int)-1;
struct reiserfs_journal *journal = SB_JOURNAL(s);
- char *new_opts;
int err;
char *qf_names[REISERFS_MAXQUOTAS];
unsigned int qfmt = 0;
@@ -1443,10 +1442,6 @@ static int reiserfs_remount(struct super_block *s, int *mount_flags, char *arg)
int i;
#endif
- new_opts = kstrdup(arg, GFP_KERNEL);
- if (arg && !new_opts)
- return -ENOMEM;
-
sync_filesystem(s);
reiserfs_write_lock(s);
@@ -1597,7 +1592,6 @@ out_ok_unlocked:
out_err_unlock:
reiserfs_write_unlock(s);
out_err:
- kfree(new_opts);
return err;
}
diff --git a/fs/seq_file.c b/fs/seq_file.c
index 4a2cda04d3e2..f8e1f4ee87ff 100644
--- a/fs/seq_file.c
+++ b/fs/seq_file.c
@@ -383,22 +383,6 @@ void seq_escape_mem(struct seq_file *m, const char *src, size_t len,
}
EXPORT_SYMBOL(seq_escape_mem);
-/**
- * seq_escape - print string into buffer, escaping some characters
- * @m: target buffer
- * @s: string
- * @esc: set of characters that need escaping
- *
- * Puts string into buffer, replacing each occurrence of character from
- * @esc with usual octal escape.
- * Use seq_has_overflowed() to check for errors.
- */
-void seq_escape(struct seq_file *m, const char *s, const char *esc)
-{
- seq_escape_str(m, s, ESCAPE_OCTAL, esc);
-}
-EXPORT_SYMBOL(seq_escape);
-
void seq_vprintf(struct seq_file *m, const char *f, va_list args)
{
int len;
diff --git a/fs/smbfs_common/smb2pdu.h b/fs/smbfs_common/smb2pdu.h
new file mode 100644
index 000000000000..7ccadcbe684b
--- /dev/null
+++ b/fs/smbfs_common/smb2pdu.h
@@ -0,0 +1,989 @@
+/* SPDX-License-Identifier: LGPL-2.1 */
+#ifndef _COMMON_SMB2PDU_H
+#define _COMMON_SMB2PDU_H
+
+/*
+ * Note that, due to trying to use names similar to the protocol specifications,
+ * there are many mixed case field names in the structures below. Although
+ * this does not match typical Linux kernel style, it is necessary to be
+ * able to match against the protocol specfication.
+ *
+ * SMB2 commands
+ * Some commands have minimal (wct=0,bcc=0), or uninteresting, responses
+ * (ie no useful data other than the SMB error code itself) and are marked such.
+ * Knowing this helps avoid response buffer allocations and copy in some cases.
+ */
+
+/* List of commands in host endian */
+#define SMB2_NEGOTIATE_HE 0x0000
+#define SMB2_SESSION_SETUP_HE 0x0001
+#define SMB2_LOGOFF_HE 0x0002 /* trivial request/resp */
+#define SMB2_TREE_CONNECT_HE 0x0003
+#define SMB2_TREE_DISCONNECT_HE 0x0004 /* trivial req/resp */
+#define SMB2_CREATE_HE 0x0005
+#define SMB2_CLOSE_HE 0x0006
+#define SMB2_FLUSH_HE 0x0007 /* trivial resp */
+#define SMB2_READ_HE 0x0008
+#define SMB2_WRITE_HE 0x0009
+#define SMB2_LOCK_HE 0x000A
+#define SMB2_IOCTL_HE 0x000B
+#define SMB2_CANCEL_HE 0x000C
+#define SMB2_ECHO_HE 0x000D
+#define SMB2_QUERY_DIRECTORY_HE 0x000E
+#define SMB2_CHANGE_NOTIFY_HE 0x000F
+#define SMB2_QUERY_INFO_HE 0x0010
+#define SMB2_SET_INFO_HE 0x0011
+#define SMB2_OPLOCK_BREAK_HE 0x0012
+
+/* The same list in little endian */
+#define SMB2_NEGOTIATE cpu_to_le16(SMB2_NEGOTIATE_HE)
+#define SMB2_SESSION_SETUP cpu_to_le16(SMB2_SESSION_SETUP_HE)
+#define SMB2_LOGOFF cpu_to_le16(SMB2_LOGOFF_HE)
+#define SMB2_TREE_CONNECT cpu_to_le16(SMB2_TREE_CONNECT_HE)
+#define SMB2_TREE_DISCONNECT cpu_to_le16(SMB2_TREE_DISCONNECT_HE)
+#define SMB2_CREATE cpu_to_le16(SMB2_CREATE_HE)
+#define SMB2_CLOSE cpu_to_le16(SMB2_CLOSE_HE)
+#define SMB2_FLUSH cpu_to_le16(SMB2_FLUSH_HE)
+#define SMB2_READ cpu_to_le16(SMB2_READ_HE)
+#define SMB2_WRITE cpu_to_le16(SMB2_WRITE_HE)
+#define SMB2_LOCK cpu_to_le16(SMB2_LOCK_HE)
+#define SMB2_IOCTL cpu_to_le16(SMB2_IOCTL_HE)
+#define SMB2_CANCEL cpu_to_le16(SMB2_CANCEL_HE)
+#define SMB2_ECHO cpu_to_le16(SMB2_ECHO_HE)
+#define SMB2_QUERY_DIRECTORY cpu_to_le16(SMB2_QUERY_DIRECTORY_HE)
+#define SMB2_CHANGE_NOTIFY cpu_to_le16(SMB2_CHANGE_NOTIFY_HE)
+#define SMB2_QUERY_INFO cpu_to_le16(SMB2_QUERY_INFO_HE)
+#define SMB2_SET_INFO cpu_to_le16(SMB2_SET_INFO_HE)
+#define SMB2_OPLOCK_BREAK cpu_to_le16(SMB2_OPLOCK_BREAK_HE)
+
+#define SMB2_INTERNAL_CMD cpu_to_le16(0xFFFF)
+
+#define NUMBER_OF_SMB2_COMMANDS 0x0013
+
+/*
+ * SMB2 Header Definition
+ *
+ * "MBZ" : Must be Zero
+ * "BB" : BugBug, Something to check/review/analyze later
+ * "PDU" : "Protocol Data Unit" (ie a network "frame")
+ *
+ */
+
+#define __SMB2_HEADER_STRUCTURE_SIZE 64
+#define SMB2_HEADER_STRUCTURE_SIZE \
+ cpu_to_le16(__SMB2_HEADER_STRUCTURE_SIZE)
+
+#define SMB2_PROTO_NUMBER cpu_to_le32(0x424d53fe)
+#define SMB2_TRANSFORM_PROTO_NUM cpu_to_le32(0x424d53fd)
+#define SMB2_COMPRESSION_TRANSFORM_ID cpu_to_le32(0x424d53fc)
+
+/*
+ * SMB2 flag definitions
+ */
+#define SMB2_FLAGS_SERVER_TO_REDIR cpu_to_le32(0x00000001)
+#define SMB2_FLAGS_ASYNC_COMMAND cpu_to_le32(0x00000002)
+#define SMB2_FLAGS_RELATED_OPERATIONS cpu_to_le32(0x00000004)
+#define SMB2_FLAGS_SIGNED cpu_to_le32(0x00000008)
+#define SMB2_FLAGS_PRIORITY_MASK cpu_to_le32(0x00000070) /* SMB3.1.1 */
+#define SMB2_FLAGS_DFS_OPERATIONS cpu_to_le32(0x10000000)
+#define SMB2_FLAGS_REPLAY_OPERATION cpu_to_le32(0x20000000) /* SMB3 & up */
+
+/* See MS-SMB2 section 2.2.1 */
+struct smb2_hdr {
+ __le32 ProtocolId; /* 0xFE 'S' 'M' 'B' */
+ __le16 StructureSize; /* 64 */
+ __le16 CreditCharge; /* MBZ */
+ __le32 Status; /* Error from server */
+ __le16 Command;
+ __le16 CreditRequest; /* CreditResponse */
+ __le32 Flags;
+ __le32 NextCommand;
+ __le64 MessageId;
+ union {
+ struct {
+ __le32 ProcessId;
+ __le32 TreeId;
+ } __packed SyncId;
+ __le64 AsyncId;
+ } __packed Id;
+ __le64 SessionId;
+ __u8 Signature[16];
+} __packed;
+
+struct smb2_pdu {
+ struct smb2_hdr hdr;
+ __le16 StructureSize2; /* size of wct area (varies, request specific) */
+} __packed;
+
+#define SMB3_AES_CCM_NONCE 11
+#define SMB3_AES_GCM_NONCE 12
+
+/* Transform flags (for 3.0 dialect this flag indicates CCM */
+#define TRANSFORM_FLAG_ENCRYPTED 0x0001
+struct smb2_transform_hdr {
+ __le32 ProtocolId; /* 0xFD 'S' 'M' 'B' */
+ __u8 Signature[16];
+ __u8 Nonce[16];
+ __le32 OriginalMessageSize;
+ __u16 Reserved1;
+ __le16 Flags; /* EncryptionAlgorithm for 3.0, enc enabled for 3.1.1 */
+ __le64 SessionId;
+} __packed;
+
+
+/* See MS-SMB2 2.2.42 */
+struct smb2_compression_transform_hdr_unchained {
+ __le32 ProtocolId; /* 0xFC 'S' 'M' 'B' */
+ __le32 OriginalCompressedSegmentSize;
+ __le16 CompressionAlgorithm;
+ __le16 Flags;
+ __le16 Length; /* if chained it is length, else offset */
+} __packed;
+
+/* See MS-SMB2 2.2.42.1 */
+#define SMB2_COMPRESSION_FLAG_NONE 0x0000
+#define SMB2_COMPRESSION_FLAG_CHAINED 0x0001
+
+struct compression_payload_header {
+ __le16 CompressionAlgorithm;
+ __le16 Flags;
+ __le32 Length; /* length of compressed playload including field below if present */
+ /* __le32 OriginalPayloadSize; */ /* optional, present when LZNT1, LZ77, LZ77+Huffman */
+} __packed;
+
+/* See MS-SMB2 2.2.42.2 */
+struct smb2_compression_transform_hdr_chained {
+ __le32 ProtocolId; /* 0xFC 'S' 'M' 'B' */
+ __le32 OriginalCompressedSegmentSize;
+ /* struct compression_payload_header[] */
+} __packed;
+
+/* See MS-SMB2 2.2.42.2.2 */
+struct compression_pattern_payload_v1 {
+ __le16 Pattern;
+ __le16 Reserved1;
+ __le16 Reserved2;
+ __le32 Repetitions;
+} __packed;
+
+/* See MS-SMB2 section 2.2.9.2 */
+/* Context Types */
+#define SMB2_RESERVED_TREE_CONNECT_CONTEXT_ID 0x0000
+#define SMB2_REMOTED_IDENTITY_TREE_CONNECT_CONTEXT_ID cpu_to_le16(0x0001)
+
+struct tree_connect_contexts {
+ __le16 ContextType;
+ __le16 DataLength;
+ __le32 Reserved;
+ __u8 Data[];
+} __packed;
+
+/* Remoted identity tree connect context structures - see MS-SMB2 2.2.9.2.1 */
+struct smb3_blob_data {
+ __le16 BlobSize;
+ __u8 BlobData[];
+} __packed;
+
+/* Valid values for Attr */
+#define SE_GROUP_MANDATORY 0x00000001
+#define SE_GROUP_ENABLED_BY_DEFAULT 0x00000002
+#define SE_GROUP_ENABLED 0x00000004
+#define SE_GROUP_OWNER 0x00000008
+#define SE_GROUP_USE_FOR_DENY_ONLY 0x00000010
+#define SE_GROUP_INTEGRITY 0x00000020
+#define SE_GROUP_INTEGRITY_ENABLED 0x00000040
+#define SE_GROUP_RESOURCE 0x20000000
+#define SE_GROUP_LOGON_ID 0xC0000000
+
+/* struct sid_attr_data is SidData array in BlobData format then le32 Attr */
+
+struct sid_array_data {
+ __le16 SidAttrCount;
+ /* SidAttrList - array of sid_attr_data structs */
+} __packed;
+
+struct luid_attr_data {
+
+} __packed;
+
+/*
+ * struct privilege_data is the same as BLOB_DATA - see MS-SMB2 2.2.9.2.1.5
+ * but with size of LUID_ATTR_DATA struct and BlobData set to LUID_ATTR DATA
+ */
+
+struct privilege_array_data {
+ __le16 PrivilegeCount;
+ /* array of privilege_data structs */
+} __packed;
+
+struct remoted_identity_tcon_context {
+ __le16 TicketType; /* must be 0x0001 */
+ __le16 TicketSize; /* total size of this struct */
+ __le16 User; /* offset to SID_ATTR_DATA struct with user info */
+ __le16 UserName; /* offset to null terminated Unicode username string */
+ __le16 Domain; /* offset to null terminated Unicode domain name */
+ __le16 Groups; /* offset to SID_ARRAY_DATA struct with group info */
+ __le16 RestrictedGroups; /* similar to above */
+ __le16 Privileges; /* offset to PRIVILEGE_ARRAY_DATA struct */
+ __le16 PrimaryGroup; /* offset to SID_ARRAY_DATA struct */
+ __le16 Owner; /* offset to BLOB_DATA struct */
+ __le16 DefaultDacl; /* offset to BLOB_DATA struct */
+ __le16 DeviceGroups; /* offset to SID_ARRAY_DATA struct */
+ __le16 UserClaims; /* offset to BLOB_DATA struct */
+ __le16 DeviceClaims; /* offset to BLOB_DATA struct */
+ __u8 TicketInfo[]; /* variable length buf - remoted identity data */
+} __packed;
+
+struct smb2_tree_connect_req_extension {
+ __le32 TreeConnectContextOffset;
+ __le16 TreeConnectContextCount;
+ __u8 Reserved[10];
+ __u8 PathName[]; /* variable sized array */
+ /* followed by array of TreeConnectContexts */
+} __packed;
+
+/* Flags/Reserved for SMB3.1.1 */
+#define SMB2_TREE_CONNECT_FLAG_CLUSTER_RECONNECT cpu_to_le16(0x0001)
+#define SMB2_TREE_CONNECT_FLAG_REDIRECT_TO_OWNER cpu_to_le16(0x0002)
+#define SMB2_TREE_CONNECT_FLAG_EXTENSION_PRESENT cpu_to_le16(0x0004)
+
+struct smb2_tree_connect_req {
+ struct smb2_hdr hdr;
+ __le16 StructureSize; /* Must be 9 */
+ __le16 Flags; /* Flags in SMB3.1.1 */
+ __le16 PathOffset;
+ __le16 PathLength;
+ __u8 Buffer[1]; /* variable length */
+} __packed;
+
+/* Possible ShareType values */
+#define SMB2_SHARE_TYPE_DISK 0x01
+#define SMB2_SHARE_TYPE_PIPE 0x02
+#define SMB2_SHARE_TYPE_PRINT 0x03
+
+/*
+ * Possible ShareFlags - exactly one and only one of the first 4 caching flags
+ * must be set (any of the remaining, SHI1005, flags may be set individually
+ * or in combination.
+ */
+#define SMB2_SHAREFLAG_MANUAL_CACHING 0x00000000
+#define SMB2_SHAREFLAG_AUTO_CACHING 0x00000010
+#define SMB2_SHAREFLAG_VDO_CACHING 0x00000020
+#define SMB2_SHAREFLAG_NO_CACHING 0x00000030
+#define SHI1005_FLAGS_DFS 0x00000001
+#define SHI1005_FLAGS_DFS_ROOT 0x00000002
+#define SHI1005_FLAGS_RESTRICT_EXCLUSIVE_OPENS 0x00000100
+#define SHI1005_FLAGS_FORCE_SHARED_DELETE 0x00000200
+#define SHI1005_FLAGS_ALLOW_NAMESPACE_CACHING 0x00000400
+#define SHI1005_FLAGS_ACCESS_BASED_DIRECTORY_ENUM 0x00000800
+#define SHI1005_FLAGS_FORCE_LEVELII_OPLOCK 0x00001000
+#define SHI1005_FLAGS_ENABLE_HASH_V1 0x00002000
+#define SHI1005_FLAGS_ENABLE_HASH_V2 0x00004000
+#define SHI1005_FLAGS_ENCRYPT_DATA 0x00008000
+#define SMB2_SHAREFLAG_IDENTITY_REMOTING 0x00040000 /* 3.1.1 */
+#define SMB2_SHAREFLAG_COMPRESS_DATA 0x00100000 /* 3.1.1 */
+#define SHI1005_FLAGS_ALL 0x0014FF33
+
+/* Possible share capabilities */
+#define SMB2_SHARE_CAP_DFS cpu_to_le32(0x00000008) /* all dialects */
+#define SMB2_SHARE_CAP_CONTINUOUS_AVAILABILITY cpu_to_le32(0x00000010) /* 3.0 */
+#define SMB2_SHARE_CAP_SCALEOUT cpu_to_le32(0x00000020) /* 3.0 */
+#define SMB2_SHARE_CAP_CLUSTER cpu_to_le32(0x00000040) /* 3.0 */
+#define SMB2_SHARE_CAP_ASYMMETRIC cpu_to_le32(0x00000080) /* 3.02 */
+#define SMB2_SHARE_CAP_REDIRECT_TO_OWNER cpu_to_le32(0x00000100) /* 3.1.1 */
+
+struct smb2_tree_connect_rsp {
+ struct smb2_hdr hdr;
+ __le16 StructureSize; /* Must be 16 */
+ __u8 ShareType; /* see below */
+ __u8 Reserved;
+ __le32 ShareFlags; /* see below */
+ __le32 Capabilities; /* see below */
+ __le32 MaximalAccess;
+} __packed;
+
+struct smb2_tree_disconnect_req {
+ struct smb2_hdr hdr;
+ __le16 StructureSize; /* Must be 4 */
+ __le16 Reserved;
+} __packed;
+
+struct smb2_tree_disconnect_rsp {
+ struct smb2_hdr hdr;
+ __le16 StructureSize; /* Must be 4 */
+ __le16 Reserved;
+} __packed;
+
+
+/*
+ * SMB2_NEGOTIATE_PROTOCOL See MS-SMB2 section 2.2.3
+ */
+/* SecurityMode flags */
+#define SMB2_NEGOTIATE_SIGNING_ENABLED 0x0001
+#define SMB2_NEGOTIATE_SIGNING_ENABLED_LE cpu_to_le16(0x0001)
+#define SMB2_NEGOTIATE_SIGNING_REQUIRED 0x0002
+#define SMB2_NEGOTIATE_SIGNING_REQUIRED_LE cpu_to_le16(0x0002)
+#define SMB2_SEC_MODE_FLAGS_ALL 0x0003
+
+/* Capabilities flags */
+#define SMB2_GLOBAL_CAP_DFS 0x00000001
+#define SMB2_GLOBAL_CAP_LEASING 0x00000002 /* Resp only New to SMB2.1 */
+#define SMB2_GLOBAL_CAP_LARGE_MTU 0X00000004 /* Resp only New to SMB2.1 */
+#define SMB2_GLOBAL_CAP_MULTI_CHANNEL 0x00000008 /* New to SMB3 */
+#define SMB2_GLOBAL_CAP_PERSISTENT_HANDLES 0x00000010 /* New to SMB3 */
+#define SMB2_GLOBAL_CAP_DIRECTORY_LEASING 0x00000020 /* New to SMB3 */
+#define SMB2_GLOBAL_CAP_ENCRYPTION 0x00000040 /* New to SMB3 */
+/* Internal types */
+#define SMB2_NT_FIND 0x00100000
+#define SMB2_LARGE_FILES 0x00200000
+
+#define SMB2_CLIENT_GUID_SIZE 16
+#define SMB2_CREATE_GUID_SIZE 16
+
+/* Dialects */
+#define SMB10_PROT_ID 0x0000 /* local only, not sent on wire w/CIFS negprot */
+#define SMB20_PROT_ID 0x0202
+#define SMB21_PROT_ID 0x0210
+#define SMB2X_PROT_ID 0x02FF
+#define SMB30_PROT_ID 0x0300
+#define SMB302_PROT_ID 0x0302
+#define SMB311_PROT_ID 0x0311
+#define BAD_PROT_ID 0xFFFF
+
+#define SMB311_SALT_SIZE 32
+/* Hash Algorithm Types */
+#define SMB2_PREAUTH_INTEGRITY_SHA512 cpu_to_le16(0x0001)
+#define SMB2_PREAUTH_HASH_SIZE 64
+
+/* Negotiate Contexts - ContextTypes. See MS-SMB2 section 2.2.3.1 for details */
+#define SMB2_PREAUTH_INTEGRITY_CAPABILITIES cpu_to_le16(1)
+#define SMB2_ENCRYPTION_CAPABILITIES cpu_to_le16(2)
+#define SMB2_COMPRESSION_CAPABILITIES cpu_to_le16(3)
+#define SMB2_NETNAME_NEGOTIATE_CONTEXT_ID cpu_to_le16(5)
+#define SMB2_TRANSPORT_CAPABILITIES cpu_to_le16(6)
+#define SMB2_RDMA_TRANSFORM_CAPABILITIES cpu_to_le16(7)
+#define SMB2_SIGNING_CAPABILITIES cpu_to_le16(8)
+#define SMB2_POSIX_EXTENSIONS_AVAILABLE cpu_to_le16(0x100)
+
+struct smb2_neg_context {
+ __le16 ContextType;
+ __le16 DataLength;
+ __le32 Reserved;
+ /* Followed by array of data. NOTE: some servers require padding to 8 byte boundary */
+} __packed;
+
+/*
+ * SaltLength that the server send can be zero, so the only three required
+ * fields (all __le16) end up six bytes total, so the minimum context data len
+ * in the response is six bytes which accounts for
+ *
+ * HashAlgorithmCount, SaltLength, and 1 HashAlgorithm.
+ */
+#define MIN_PREAUTH_CTXT_DATA_LEN 6
+
+struct smb2_preauth_neg_context {
+ __le16 ContextType; /* 1 */
+ __le16 DataLength;
+ __le32 Reserved;
+ __le16 HashAlgorithmCount; /* 1 */
+ __le16 SaltLength;
+ __le16 HashAlgorithms; /* HashAlgorithms[0] since only one defined */
+ __u8 Salt[SMB311_SALT_SIZE];
+} __packed;
+
+/* Encryption Algorithms Ciphers */
+#define SMB2_ENCRYPTION_AES128_CCM cpu_to_le16(0x0001)
+#define SMB2_ENCRYPTION_AES128_GCM cpu_to_le16(0x0002)
+#define SMB2_ENCRYPTION_AES256_CCM cpu_to_le16(0x0003)
+#define SMB2_ENCRYPTION_AES256_GCM cpu_to_le16(0x0004)
+
+/* Min encrypt context data is one cipher so 2 bytes + 2 byte count field */
+#define MIN_ENCRYPT_CTXT_DATA_LEN 4
+struct smb2_encryption_neg_context {
+ __le16 ContextType; /* 2 */
+ __le16 DataLength;
+ __le32 Reserved;
+ /* CipherCount usally 2, but can be 3 when AES256-GCM enabled */
+ __le16 CipherCount; /* AES128-GCM and AES128-CCM by default */
+ __le16 Ciphers[];
+} __packed;
+
+/* See MS-SMB2 2.2.3.1.3 */
+#define SMB3_COMPRESS_NONE cpu_to_le16(0x0000)
+#define SMB3_COMPRESS_LZNT1 cpu_to_le16(0x0001)
+#define SMB3_COMPRESS_LZ77 cpu_to_le16(0x0002)
+#define SMB3_COMPRESS_LZ77_HUFF cpu_to_le16(0x0003)
+/* Pattern scanning algorithm See MS-SMB2 3.1.4.4.1 */
+#define SMB3_COMPRESS_PATTERN cpu_to_le16(0x0004) /* Pattern_V1 */
+
+/* Compression Flags */
+#define SMB2_COMPRESSION_CAPABILITIES_FLAG_NONE cpu_to_le32(0x00000000)
+#define SMB2_COMPRESSION_CAPABILITIES_FLAG_CHAINED cpu_to_le32(0x00000001)
+
+struct smb2_compression_capabilities_context {
+ __le16 ContextType; /* 3 */
+ __le16 DataLength;
+ __le32 Reserved;
+ __le16 CompressionAlgorithmCount;
+ __le16 Padding;
+ __le32 Flags;
+ __le16 CompressionAlgorithms[3];
+ __u16 Pad; /* Some servers require pad to DataLen multiple of 8 */
+ /* Check if pad needed */
+} __packed;
+
+/*
+ * For smb2_netname_negotiate_context_id See MS-SMB2 2.2.3.1.4.
+ * Its struct simply contains NetName, an array of Unicode characters
+ */
+struct smb2_netname_neg_context {
+ __le16 ContextType; /* 5 */
+ __le16 DataLength;
+ __le32 Reserved;
+ __le16 NetName[]; /* hostname of target converted to UCS-2 */
+} __packed;
+
+/*
+ * For smb2_transport_capabilities context see MS-SMB2 2.2.3.1.5
+ * and 2.2.4.1.5
+ */
+
+/* Flags */
+#define SMB2_ACCEPT_TRANSFORM_LEVEL_SECURITY 0x00000001
+
+struct smb2_transport_capabilities_context {
+ __le16 ContextType; /* 6 */
+ __le16 DataLength;
+ __u32 Reserved;
+ __le32 Flags;
+ __u32 Pad;
+} __packed;
+
+/*
+ * For rdma transform capabilities context see MS-SMB2 2.2.3.1.6
+ * and 2.2.4.1.6
+ */
+
+/* RDMA Transform IDs */
+#define SMB2_RDMA_TRANSFORM_NONE 0x0000
+#define SMB2_RDMA_TRANSFORM_ENCRYPTION 0x0001
+#define SMB2_RDMA_TRANSFORM_SIGNING 0x0002
+
+struct smb2_rdma_transform_capabilities_context {
+ __le16 ContextType; /* 7 */
+ __le16 DataLength;
+ __u32 Reserved;
+ __le16 TransformCount;
+ __u16 Reserved1;
+ __u32 Reserved2;
+ __le16 RDMATransformIds[];
+} __packed;
+
+/*
+ * For signing capabilities context see MS-SMB2 2.2.3.1.7
+ * and 2.2.4.1.7
+ */
+
+/* Signing algorithms */
+#define SIGNING_ALG_HMAC_SHA256 0
+#define SIGNING_ALG_HMAC_SHA256_LE cpu_to_le16(0)
+#define SIGNING_ALG_AES_CMAC 1
+#define SIGNING_ALG_AES_CMAC_LE cpu_to_le16(1)
+#define SIGNING_ALG_AES_GMAC 2
+#define SIGNING_ALG_AES_GMAC_LE cpu_to_le16(2)
+
+struct smb2_signing_capabilities {
+ __le16 ContextType; /* 8 */
+ __le16 DataLength;
+ __le32 Reserved;
+ __le16 SigningAlgorithmCount;
+ __le16 SigningAlgorithms[];
+ /* Followed by padding to 8 byte boundary (required by some servers) */
+} __packed;
+
+#define POSIX_CTXT_DATA_LEN 16
+struct smb2_posix_neg_context {
+ __le16 ContextType; /* 0x100 */
+ __le16 DataLength;
+ __le32 Reserved;
+ __u8 Name[16]; /* POSIX ctxt GUID 93AD25509CB411E7B42383DE968BCD7C */
+} __packed;
+
+struct smb2_negotiate_req {
+ struct smb2_hdr hdr;
+ __le16 StructureSize; /* Must be 36 */
+ __le16 DialectCount;
+ __le16 SecurityMode;
+ __le16 Reserved; /* MBZ */
+ __le32 Capabilities;
+ __u8 ClientGUID[SMB2_CLIENT_GUID_SIZE];
+ /* In SMB3.02 and earlier next three were MBZ le64 ClientStartTime */
+ __le32 NegotiateContextOffset; /* SMB3.1.1 only. MBZ earlier */
+ __le16 NegotiateContextCount; /* SMB3.1.1 only. MBZ earlier */
+ __le16 Reserved2;
+ __le16 Dialects[];
+} __packed;
+
+struct smb2_negotiate_rsp {
+ struct smb2_hdr hdr;
+ __le16 StructureSize; /* Must be 65 */
+ __le16 SecurityMode;
+ __le16 DialectRevision;
+ __le16 NegotiateContextCount; /* Prior to SMB3.1.1 was Reserved & MBZ */
+ __u8 ServerGUID[16];
+ __le32 Capabilities;
+ __le32 MaxTransactSize;
+ __le32 MaxReadSize;
+ __le32 MaxWriteSize;
+ __le64 SystemTime; /* MBZ */
+ __le64 ServerStartTime;
+ __le16 SecurityBufferOffset;
+ __le16 SecurityBufferLength;
+ __le32 NegotiateContextOffset; /* Pre:SMB3.1.1 was reserved/ignored */
+ __u8 Buffer[1]; /* variable length GSS security buffer */
+} __packed;
+
+
+/*
+ * SMB2_SESSION_SETUP See MS-SMB2 section 2.2.5
+ */
+/* Flags */
+#define SMB2_SESSION_REQ_FLAG_BINDING 0x01
+#define SMB2_SESSION_REQ_FLAG_ENCRYPT_DATA 0x04
+
+struct smb2_sess_setup_req {
+ struct smb2_hdr hdr;
+ __le16 StructureSize; /* Must be 25 */
+ __u8 Flags;
+ __u8 SecurityMode;
+ __le32 Capabilities;
+ __le32 Channel;
+ __le16 SecurityBufferOffset;
+ __le16 SecurityBufferLength;
+ __le64 PreviousSessionId;
+ __u8 Buffer[1]; /* variable length GSS security buffer */
+} __packed;
+
+/* Currently defined SessionFlags */
+#define SMB2_SESSION_FLAG_IS_GUEST 0x0001
+#define SMB2_SESSION_FLAG_IS_GUEST_LE cpu_to_le16(0x0001)
+#define SMB2_SESSION_FLAG_IS_NULL 0x0002
+#define SMB2_SESSION_FLAG_IS_NULL_LE cpu_to_le16(0x0002)
+#define SMB2_SESSION_FLAG_ENCRYPT_DATA 0x0004
+#define SMB2_SESSION_FLAG_ENCRYPT_DATA_LE cpu_to_le16(0x0004)
+
+struct smb2_sess_setup_rsp {
+ struct smb2_hdr hdr;
+ __le16 StructureSize; /* Must be 9 */
+ __le16 SessionFlags;
+ __le16 SecurityBufferOffset;
+ __le16 SecurityBufferLength;
+ __u8 Buffer[1]; /* variable length GSS security buffer */
+} __packed;
+
+
+/*
+ * SMB2_LOGOFF See MS-SMB2 section 2.2.7
+ */
+struct smb2_logoff_req {
+ struct smb2_hdr hdr;
+ __le16 StructureSize; /* Must be 4 */
+ __le16 Reserved;
+} __packed;
+
+struct smb2_logoff_rsp {
+ struct smb2_hdr hdr;
+ __le16 StructureSize; /* Must be 4 */
+ __le16 Reserved;
+} __packed;
+
+
+/*
+ * SMB2_CLOSE See MS-SMB2 section 2.2.15
+ */
+/* Currently defined values for close flags */
+#define SMB2_CLOSE_FLAG_POSTQUERY_ATTRIB cpu_to_le16(0x0001)
+struct smb2_close_req {
+ struct smb2_hdr hdr;
+ __le16 StructureSize; /* Must be 24 */
+ __le16 Flags;
+ __le32 Reserved;
+ __le64 PersistentFileId; /* opaque endianness */
+ __le64 VolatileFileId; /* opaque endianness */
+} __packed;
+
+/*
+ * Maximum size of a SMB2_CLOSE response is 64 (smb2 header) + 60 (data)
+ */
+#define MAX_SMB2_CLOSE_RESPONSE_SIZE 124
+
+struct smb2_close_rsp {
+ struct smb2_hdr hdr;
+ __le16 StructureSize; /* 60 */
+ __le16 Flags;
+ __le32 Reserved;
+ __le64 CreationTime;
+ __le64 LastAccessTime;
+ __le64 LastWriteTime;
+ __le64 ChangeTime;
+ __le64 AllocationSize; /* Beginning of FILE_STANDARD_INFO equivalent */
+ __le64 EndOfFile;
+ __le32 Attributes;
+} __packed;
+
+
+/*
+ * SMB2_READ See MS-SMB2 section 2.2.19
+ */
+/* For read request Flags field below, following flag is defined for SMB3.02 */
+#define SMB2_READFLAG_READ_UNBUFFERED 0x01
+#define SMB2_READFLAG_REQUEST_COMPRESSED 0x02 /* See MS-SMB2 2.2.19 */
+
+/* Channel field for read and write: exactly one of following flags can be set*/
+#define SMB2_CHANNEL_NONE cpu_to_le32(0x00000000)
+#define SMB2_CHANNEL_RDMA_V1 cpu_to_le32(0x00000001)
+#define SMB2_CHANNEL_RDMA_V1_INVALIDATE cpu_to_le32(0x00000002)
+#define SMB2_CHANNEL_RDMA_TRANSFORM cpu_to_le32(0x00000003)
+
+/* SMB2 read request without RFC1001 length at the beginning */
+struct smb2_read_req {
+ struct smb2_hdr hdr;
+ __le16 StructureSize; /* Must be 49 */
+ __u8 Padding; /* offset from start of SMB2 header to place read */
+ __u8 Flags; /* MBZ unless SMB3.02 or later */
+ __le32 Length;
+ __le64 Offset;
+ __le64 PersistentFileId;
+ __le64 VolatileFileId;
+ __le32 MinimumCount;
+ __le32 Channel; /* MBZ except for SMB3 or later */
+ __le32 RemainingBytes;
+ __le16 ReadChannelInfoOffset;
+ __le16 ReadChannelInfoLength;
+ __u8 Buffer[1];
+} __packed;
+
+/* Read flags */
+#define SMB2_READFLAG_RESPONSE_NONE cpu_to_le32(0x00000000)
+#define SMB2_READFLAG_RESPONSE_RDMA_TRANSFORM cpu_to_le32(0x00000001)
+
+struct smb2_read_rsp {
+ struct smb2_hdr hdr;
+ __le16 StructureSize; /* Must be 17 */
+ __u8 DataOffset;
+ __u8 Reserved;
+ __le32 DataLength;
+ __le32 DataRemaining;
+ __le32 Flags;
+ __u8 Buffer[1];
+} __packed;
+
+
+/*
+ * SMB2_WRITE See MS-SMB2 section 2.2.21
+ */
+/* For write request Flags field below the following flags are defined: */
+#define SMB2_WRITEFLAG_WRITE_THROUGH 0x00000001 /* SMB2.1 or later */
+#define SMB2_WRITEFLAG_WRITE_UNBUFFERED 0x00000002 /* SMB3.02 or later */
+
+struct smb2_write_req {
+ struct smb2_hdr hdr;
+ __le16 StructureSize; /* Must be 49 */
+ __le16 DataOffset; /* offset from start of SMB2 header to write data */
+ __le32 Length;
+ __le64 Offset;
+ __le64 PersistentFileId; /* opaque endianness */
+ __le64 VolatileFileId; /* opaque endianness */
+ __le32 Channel; /* MBZ unless SMB3.02 or later */
+ __le32 RemainingBytes;
+ __le16 WriteChannelInfoOffset;
+ __le16 WriteChannelInfoLength;
+ __le32 Flags;
+ __u8 Buffer[1];
+} __packed;
+
+struct smb2_write_rsp {
+ struct smb2_hdr hdr;
+ __le16 StructureSize; /* Must be 17 */
+ __u8 DataOffset;
+ __u8 Reserved;
+ __le32 DataLength;
+ __le32 DataRemaining;
+ __u32 Reserved2;
+ __u8 Buffer[1];
+} __packed;
+
+
+/*
+ * SMB2_FLUSH See MS-SMB2 section 2.2.17
+ */
+struct smb2_flush_req {
+ struct smb2_hdr hdr;
+ __le16 StructureSize; /* Must be 24 */
+ __le16 Reserved1;
+ __le32 Reserved2;
+ __le64 PersistentFileId;
+ __le64 VolatileFileId;
+} __packed;
+
+struct smb2_flush_rsp {
+ struct smb2_hdr hdr;
+ __le16 StructureSize;
+ __le16 Reserved;
+} __packed;
+
+
+/*
+ * SMB2_NOTIFY See MS-SMB2 section 2.2.35
+ */
+/* notify flags */
+#define SMB2_WATCH_TREE 0x0001
+
+/* notify completion filter flags. See MS-FSCC 2.6 and MS-SMB2 2.2.35 */
+#define FILE_NOTIFY_CHANGE_FILE_NAME 0x00000001
+#define FILE_NOTIFY_CHANGE_DIR_NAME 0x00000002
+#define FILE_NOTIFY_CHANGE_ATTRIBUTES 0x00000004
+#define FILE_NOTIFY_CHANGE_SIZE 0x00000008
+#define FILE_NOTIFY_CHANGE_LAST_WRITE 0x00000010
+#define FILE_NOTIFY_CHANGE_LAST_ACCESS 0x00000020
+#define FILE_NOTIFY_CHANGE_CREATION 0x00000040
+#define FILE_NOTIFY_CHANGE_EA 0x00000080
+#define FILE_NOTIFY_CHANGE_SECURITY 0x00000100
+#define FILE_NOTIFY_CHANGE_STREAM_NAME 0x00000200
+#define FILE_NOTIFY_CHANGE_STREAM_SIZE 0x00000400
+#define FILE_NOTIFY_CHANGE_STREAM_WRITE 0x00000800
+
+/* SMB2 Notify Action Flags */
+#define FILE_ACTION_ADDED 0x00000001
+#define FILE_ACTION_REMOVED 0x00000002
+#define FILE_ACTION_MODIFIED 0x00000003
+#define FILE_ACTION_RENAMED_OLD_NAME 0x00000004
+#define FILE_ACTION_RENAMED_NEW_NAME 0x00000005
+#define FILE_ACTION_ADDED_STREAM 0x00000006
+#define FILE_ACTION_REMOVED_STREAM 0x00000007
+#define FILE_ACTION_MODIFIED_STREAM 0x00000008
+#define FILE_ACTION_REMOVED_BY_DELETE 0x00000009
+
+struct smb2_change_notify_req {
+ struct smb2_hdr hdr;
+ __le16 StructureSize;
+ __le16 Flags;
+ __le32 OutputBufferLength;
+ __le64 PersistentFileId; /* opaque endianness */
+ __le64 VolatileFileId; /* opaque endianness */
+ __le32 CompletionFilter;
+ __u32 Reserved;
+} __packed;
+
+struct smb2_change_notify_rsp {
+ struct smb2_hdr hdr;
+ __le16 StructureSize; /* Must be 9 */
+ __le16 OutputBufferOffset;
+ __le32 OutputBufferLength;
+ __u8 Buffer[1]; /* array of file notify structs */
+} __packed;
+
+
+/*
+ * SMB2_CREATE See MS-SMB2 section 2.2.13
+ */
+/* Oplock levels */
+#define SMB2_OPLOCK_LEVEL_NONE 0x00
+#define SMB2_OPLOCK_LEVEL_II 0x01
+#define SMB2_OPLOCK_LEVEL_EXCLUSIVE 0x08
+#define SMB2_OPLOCK_LEVEL_BATCH 0x09
+#define SMB2_OPLOCK_LEVEL_LEASE 0xFF
+/* Non-spec internal type */
+#define SMB2_OPLOCK_LEVEL_NOCHANGE 0x99
+
+/* Impersonation Levels. See MS-WPO section 9.7 and MSDN-IMPERS */
+#define IL_ANONYMOUS cpu_to_le32(0x00000000)
+#define IL_IDENTIFICATION cpu_to_le32(0x00000001)
+#define IL_IMPERSONATION cpu_to_le32(0x00000002)
+#define IL_DELEGATE cpu_to_le32(0x00000003)
+
+/* File Attrubutes */
+#define FILE_ATTRIBUTE_READONLY 0x00000001
+#define FILE_ATTRIBUTE_HIDDEN 0x00000002
+#define FILE_ATTRIBUTE_SYSTEM 0x00000004
+#define FILE_ATTRIBUTE_DIRECTORY 0x00000010
+#define FILE_ATTRIBUTE_ARCHIVE 0x00000020
+#define FILE_ATTRIBUTE_NORMAL 0x00000080
+#define FILE_ATTRIBUTE_TEMPORARY 0x00000100
+#define FILE_ATTRIBUTE_SPARSE_FILE 0x00000200
+#define FILE_ATTRIBUTE_REPARSE_POINT 0x00000400
+#define FILE_ATTRIBUTE_COMPRESSED 0x00000800
+#define FILE_ATTRIBUTE_OFFLINE 0x00001000
+#define FILE_ATTRIBUTE_NOT_CONTENT_INDEXED 0x00002000
+#define FILE_ATTRIBUTE_ENCRYPTED 0x00004000
+#define FILE_ATTRIBUTE_INTEGRITY_STREAM 0x00008000
+#define FILE_ATTRIBUTE_NO_SCRUB_DATA 0x00020000
+#define FILE_ATTRIBUTE__MASK 0x00007FB7
+
+#define FILE_ATTRIBUTE_READONLY_LE cpu_to_le32(0x00000001)
+#define FILE_ATTRIBUTE_HIDDEN_LE cpu_to_le32(0x00000002)
+#define FILE_ATTRIBUTE_SYSTEM_LE cpu_to_le32(0x00000004)
+#define FILE_ATTRIBUTE_DIRECTORY_LE cpu_to_le32(0x00000010)
+#define FILE_ATTRIBUTE_ARCHIVE_LE cpu_to_le32(0x00000020)
+#define FILE_ATTRIBUTE_NORMAL_LE cpu_to_le32(0x00000080)
+#define FILE_ATTRIBUTE_TEMPORARY_LE cpu_to_le32(0x00000100)
+#define FILE_ATTRIBUTE_SPARSE_FILE_LE cpu_to_le32(0x00000200)
+#define FILE_ATTRIBUTE_REPARSE_POINT_LE cpu_to_le32(0x00000400)
+#define FILE_ATTRIBUTE_COMPRESSED_LE cpu_to_le32(0x00000800)
+#define FILE_ATTRIBUTE_OFFLINE_LE cpu_to_le32(0x00001000)
+#define FILE_ATTRIBUTE_NOT_CONTENT_INDEXED_LE cpu_to_le32(0x00002000)
+#define FILE_ATTRIBUTE_ENCRYPTED_LE cpu_to_le32(0x00004000)
+#define FILE_ATTRIBUTE_INTEGRITY_STREAM_LE cpu_to_le32(0x00008000)
+#define FILE_ATTRIBUTE_NO_SCRUB_DATA_LE cpu_to_le32(0x00020000)
+#define FILE_ATTRIBUTE_MASK_LE cpu_to_le32(0x00007FB7)
+
+/* Desired Access Flags */
+#define FILE_READ_DATA_LE cpu_to_le32(0x00000001)
+#define FILE_LIST_DIRECTORY_LE cpu_to_le32(0x00000001)
+#define FILE_WRITE_DATA_LE cpu_to_le32(0x00000002)
+#define FILE_APPEND_DATA_LE cpu_to_le32(0x00000004)
+#define FILE_ADD_SUBDIRECTORY_LE cpu_to_le32(0x00000004)
+#define FILE_READ_EA_LE cpu_to_le32(0x00000008)
+#define FILE_WRITE_EA_LE cpu_to_le32(0x00000010)
+#define FILE_EXECUTE_LE cpu_to_le32(0x00000020)
+#define FILE_DELETE_CHILD_LE cpu_to_le32(0x00000040)
+#define FILE_READ_ATTRIBUTES_LE cpu_to_le32(0x00000080)
+#define FILE_WRITE_ATTRIBUTES_LE cpu_to_le32(0x00000100)
+#define FILE_DELETE_LE cpu_to_le32(0x00010000)
+#define FILE_READ_CONTROL_LE cpu_to_le32(0x00020000)
+#define FILE_WRITE_DAC_LE cpu_to_le32(0x00040000)
+#define FILE_WRITE_OWNER_LE cpu_to_le32(0x00080000)
+#define FILE_SYNCHRONIZE_LE cpu_to_le32(0x00100000)
+#define FILE_ACCESS_SYSTEM_SECURITY_LE cpu_to_le32(0x01000000)
+#define FILE_MAXIMAL_ACCESS_LE cpu_to_le32(0x02000000)
+#define FILE_GENERIC_ALL_LE cpu_to_le32(0x10000000)
+#define FILE_GENERIC_EXECUTE_LE cpu_to_le32(0x20000000)
+#define FILE_GENERIC_WRITE_LE cpu_to_le32(0x40000000)
+#define FILE_GENERIC_READ_LE cpu_to_le32(0x80000000)
+#define DESIRED_ACCESS_MASK cpu_to_le32(0xF21F01FF)
+
+
+#define FILE_READ_DESIRED_ACCESS_LE (FILE_READ_DATA_LE | \
+ FILE_READ_EA_LE | \
+ FILE_GENERIC_READ_LE)
+#define FILE_WRITE_DESIRE_ACCESS_LE (FILE_WRITE_DATA_LE | \
+ FILE_APPEND_DATA_LE | \
+ FILE_WRITE_EA_LE | \
+ FILE_WRITE_ATTRIBUTES_LE | \
+ FILE_GENERIC_WRITE_LE)
+
+/* ShareAccess Flags */
+#define FILE_SHARE_READ_LE cpu_to_le32(0x00000001)
+#define FILE_SHARE_WRITE_LE cpu_to_le32(0x00000002)
+#define FILE_SHARE_DELETE_LE cpu_to_le32(0x00000004)
+#define FILE_SHARE_ALL_LE cpu_to_le32(0x00000007)
+
+/* CreateDisposition Flags */
+#define FILE_SUPERSEDE_LE cpu_to_le32(0x00000000)
+#define FILE_OPEN_LE cpu_to_le32(0x00000001)
+#define FILE_CREATE_LE cpu_to_le32(0x00000002)
+#define FILE_OPEN_IF_LE cpu_to_le32(0x00000003)
+#define FILE_OVERWRITE_LE cpu_to_le32(0x00000004)
+#define FILE_OVERWRITE_IF_LE cpu_to_le32(0x00000005)
+#define FILE_CREATE_MASK_LE cpu_to_le32(0x00000007)
+
+#define FILE_READ_RIGHTS (FILE_READ_DATA | FILE_READ_EA \
+ | FILE_READ_ATTRIBUTES)
+#define FILE_WRITE_RIGHTS (FILE_WRITE_DATA | FILE_APPEND_DATA \
+ | FILE_WRITE_EA | FILE_WRITE_ATTRIBUTES)
+#define FILE_EXEC_RIGHTS (FILE_EXECUTE)
+
+/* CreateOptions Flags */
+#define FILE_DIRECTORY_FILE_LE cpu_to_le32(0x00000001)
+/* same as #define CREATE_NOT_FILE_LE cpu_to_le32(0x00000001) */
+#define FILE_WRITE_THROUGH_LE cpu_to_le32(0x00000002)
+#define FILE_SEQUENTIAL_ONLY_LE cpu_to_le32(0x00000004)
+#define FILE_NO_INTERMEDIATE_BUFFERING_LE cpu_to_le32(0x00000008)
+#define FILE_NON_DIRECTORY_FILE_LE cpu_to_le32(0x00000040)
+#define FILE_COMPLETE_IF_OPLOCKED_LE cpu_to_le32(0x00000100)
+#define FILE_NO_EA_KNOWLEDGE_LE cpu_to_le32(0x00000200)
+#define FILE_RANDOM_ACCESS_LE cpu_to_le32(0x00000800)
+#define FILE_DELETE_ON_CLOSE_LE cpu_to_le32(0x00001000)
+#define FILE_OPEN_BY_FILE_ID_LE cpu_to_le32(0x00002000)
+#define FILE_OPEN_FOR_BACKUP_INTENT_LE cpu_to_le32(0x00004000)
+#define FILE_NO_COMPRESSION_LE cpu_to_le32(0x00008000)
+#define FILE_OPEN_REPARSE_POINT_LE cpu_to_le32(0x00200000)
+#define FILE_OPEN_NO_RECALL_LE cpu_to_le32(0x00400000)
+#define CREATE_OPTIONS_MASK_LE cpu_to_le32(0x00FFFFFF)
+
+#define FILE_READ_RIGHTS_LE (FILE_READ_DATA_LE | FILE_READ_EA_LE \
+ | FILE_READ_ATTRIBUTES_LE)
+#define FILE_WRITE_RIGHTS_LE (FILE_WRITE_DATA_LE | FILE_APPEND_DATA_LE \
+ | FILE_WRITE_EA_LE | FILE_WRITE_ATTRIBUTES_LE)
+#define FILE_EXEC_RIGHTS_LE (FILE_EXECUTE_LE)
+
+/* Create Context Values */
+#define SMB2_CREATE_EA_BUFFER "ExtA" /* extended attributes */
+#define SMB2_CREATE_SD_BUFFER "SecD" /* security descriptor */
+#define SMB2_CREATE_DURABLE_HANDLE_REQUEST "DHnQ"
+#define SMB2_CREATE_DURABLE_HANDLE_RECONNECT "DHnC"
+#define SMB2_CREATE_ALLOCATION_SIZE "AISi"
+#define SMB2_CREATE_QUERY_MAXIMAL_ACCESS_REQUEST "MxAc"
+#define SMB2_CREATE_TIMEWARP_REQUEST "TWrp"
+#define SMB2_CREATE_QUERY_ON_DISK_ID "QFid"
+#define SMB2_CREATE_REQUEST_LEASE "RqLs"
+#define SMB2_CREATE_DURABLE_HANDLE_REQUEST_V2 "DH2Q"
+#define SMB2_CREATE_DURABLE_HANDLE_RECONNECT_V2 "DH2C"
+#define SMB2_CREATE_TAG_POSIX "\x93\xAD\x25\x50\x9C\xB4\x11\xE7\xB4\x23\x83\xDE\x96\x8B\xCD\x7C"
+
+/* Flag (SMB3 open response) values */
+#define SMB2_CREATE_FLAG_REPARSEPOINT 0x01
+
+struct create_context {
+ __le32 Next;
+ __le16 NameOffset;
+ __le16 NameLength;
+ __le16 Reserved;
+ __le16 DataOffset;
+ __le32 DataLength;
+ __u8 Buffer[];
+} __packed;
+
+struct smb2_create_req {
+ struct smb2_hdr hdr;
+ __le16 StructureSize; /* Must be 57 */
+ __u8 SecurityFlags;
+ __u8 RequestedOplockLevel;
+ __le32 ImpersonationLevel;
+ __le64 SmbCreateFlags;
+ __le64 Reserved;
+ __le32 DesiredAccess;
+ __le32 FileAttributes;
+ __le32 ShareAccess;
+ __le32 CreateDisposition;
+ __le32 CreateOptions;
+ __le16 NameOffset;
+ __le16 NameLength;
+ __le32 CreateContextsOffset;
+ __le32 CreateContextsLength;
+ __u8 Buffer[];
+} __packed;
+
+struct smb2_create_rsp {
+ struct smb2_hdr hdr;
+ __le16 StructureSize; /* Must be 89 */
+ __u8 OplockLevel;
+ __u8 Flags; /* 0x01 if reparse point */
+ __le32 CreateAction;
+ __le64 CreationTime;
+ __le64 LastAccessTime;
+ __le64 LastWriteTime;
+ __le64 ChangeTime;
+ __le64 AllocationSize;
+ __le64 EndofFile;
+ __le32 FileAttributes;
+ __le32 Reserved2;
+ __le64 PersistentFileId;
+ __le64 VolatileFileId;
+ __le32 CreateContextsOffset;
+ __le32 CreateContextsLength;
+ __u8 Buffer[1];
+} __packed;
+
+
+#endif /* _COMMON_SMB2PDU_H */
diff --git a/fs/super.c b/fs/super.c
index bcef3a6f4c4b..3bfc0f8fbd5b 100644
--- a/fs/super.c
+++ b/fs/super.c
@@ -476,6 +476,8 @@ void generic_shutdown_super(struct super_block *sb)
spin_unlock(&sb_lock);
up_write(&sb->s_umount);
if (sb->s_bdi != &noop_backing_dev_info) {
+ if (sb->s_iflags & SB_I_PERSB_BDI)
+ bdi_unregister(sb->s_bdi);
bdi_put(sb->s_bdi);
sb->s_bdi = &noop_backing_dev_info;
}
@@ -1562,6 +1564,7 @@ int super_setup_bdi_name(struct super_block *sb, char *fmt, ...)
}
WARN_ON(sb->s_bdi != &noop_backing_dev_info);
sb->s_bdi = bdi;
+ sb->s_iflags |= SB_I_PERSB_BDI;
return 0;
}
diff --git a/fs/sysfs/dir.c b/fs/sysfs/dir.c
index 59dffd5ca517..b6b6796e1616 100644
--- a/fs/sysfs/dir.c
+++ b/fs/sysfs/dir.c
@@ -56,8 +56,7 @@ int sysfs_create_dir_ns(struct kobject *kobj, const void *ns)
kobject_get_ownership(kobj, &uid, &gid);
- kn = kernfs_create_dir_ns(parent, kobject_name(kobj),
- S_IRWXU | S_IRUGO | S_IXUGO, uid, gid,
+ kn = kernfs_create_dir_ns(parent, kobject_name(kobj), 0755, uid, gid,
kobj, ns);
if (IS_ERR(kn)) {
if (PTR_ERR(kn) == -EEXIST)
diff --git a/fs/sysfs/file.c b/fs/sysfs/file.c
index d019d6ac6ad0..42dcf96881b6 100644
--- a/fs/sysfs/file.c
+++ b/fs/sysfs/file.c
@@ -45,6 +45,9 @@ static int sysfs_kf_seq_show(struct seq_file *sf, void *v)
ssize_t count;
char *buf;
+ if (WARN_ON_ONCE(!ops->show))
+ return -EINVAL;
+
/* acquire buffer and ensure that it's >= PAGE_SIZE and clear */
count = seq_get_buf(sf, &buf);
if (count < PAGE_SIZE) {
@@ -53,15 +56,9 @@ static int sysfs_kf_seq_show(struct seq_file *sf, void *v)
}
memset(buf, 0, PAGE_SIZE);
- /*
- * Invoke show(). Control may reach here via seq file lseek even
- * if @ops->show() isn't implemented.
- */
- if (ops->show) {
- count = ops->show(kobj, of->kn->priv, buf);
- if (count < 0)
- return count;
- }
+ count = ops->show(kobj, of->kn->priv, buf);
+ if (count < 0)
+ return count;
/*
* The code works fine with PAGE_SIZE return but it's likely to
@@ -255,59 +252,74 @@ static const struct kernfs_ops sysfs_bin_kfops_mmap = {
};
int sysfs_add_file_mode_ns(struct kernfs_node *parent,
- const struct attribute *attr, bool is_bin,
- umode_t mode, kuid_t uid, kgid_t gid, const void *ns)
+ const struct attribute *attr, umode_t mode, kuid_t uid,
+ kgid_t gid, const void *ns)
{
+ struct kobject *kobj = parent->priv;
+ const struct sysfs_ops *sysfs_ops = kobj->ktype->sysfs_ops;
struct lock_class_key *key = NULL;
- const struct kernfs_ops *ops;
+ const struct kernfs_ops *ops = NULL;
struct kernfs_node *kn;
- loff_t size;
-
- if (!is_bin) {
- struct kobject *kobj = parent->priv;
- const struct sysfs_ops *sysfs_ops = kobj->ktype->sysfs_ops;
-
- /* every kobject with an attribute needs a ktype assigned */
- if (WARN(!sysfs_ops, KERN_ERR
- "missing sysfs attribute operations for kobject: %s\n",
- kobject_name(kobj)))
- return -EINVAL;
-
- if (sysfs_ops->show && sysfs_ops->store) {
- if (mode & SYSFS_PREALLOC)
- ops = &sysfs_prealloc_kfops_rw;
- else
- ops = &sysfs_file_kfops_rw;
- } else if (sysfs_ops->show) {
- if (mode & SYSFS_PREALLOC)
- ops = &sysfs_prealloc_kfops_ro;
- else
- ops = &sysfs_file_kfops_ro;
- } else if (sysfs_ops->store) {
- if (mode & SYSFS_PREALLOC)
- ops = &sysfs_prealloc_kfops_wo;
- else
- ops = &sysfs_file_kfops_wo;
- } else
- ops = &sysfs_file_kfops_empty;
-
- size = PAGE_SIZE;
+
+ /* every kobject with an attribute needs a ktype assigned */
+ if (WARN(!sysfs_ops, KERN_ERR
+ "missing sysfs attribute operations for kobject: %s\n",
+ kobject_name(kobj)))
+ return -EINVAL;
+
+ if (mode & SYSFS_PREALLOC) {
+ if (sysfs_ops->show && sysfs_ops->store)
+ ops = &sysfs_prealloc_kfops_rw;
+ else if (sysfs_ops->show)
+ ops = &sysfs_prealloc_kfops_ro;
+ else if (sysfs_ops->store)
+ ops = &sysfs_prealloc_kfops_wo;
} else {
- struct bin_attribute *battr = (void *)attr;
-
- if (battr->mmap)
- ops = &sysfs_bin_kfops_mmap;
- else if (battr->read && battr->write)
- ops = &sysfs_bin_kfops_rw;
- else if (battr->read)
- ops = &sysfs_bin_kfops_ro;
- else if (battr->write)
- ops = &sysfs_bin_kfops_wo;
- else
- ops = &sysfs_file_kfops_empty;
-
- size = battr->size;
+ if (sysfs_ops->show && sysfs_ops->store)
+ ops = &sysfs_file_kfops_rw;
+ else if (sysfs_ops->show)
+ ops = &sysfs_file_kfops_ro;
+ else if (sysfs_ops->store)
+ ops = &sysfs_file_kfops_wo;
+ }
+
+ if (!ops)
+ ops = &sysfs_file_kfops_empty;
+
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+ if (!attr->ignore_lockdep)
+ key = attr->key ?: (struct lock_class_key *)&attr->skey;
+#endif
+
+ kn = __kernfs_create_file(parent, attr->name, mode & 0777, uid, gid,
+ PAGE_SIZE, ops, (void *)attr, ns, key);
+ if (IS_ERR(kn)) {
+ if (PTR_ERR(kn) == -EEXIST)
+ sysfs_warn_dup(parent, attr->name);
+ return PTR_ERR(kn);
}
+ return 0;
+}
+
+int sysfs_add_bin_file_mode_ns(struct kernfs_node *parent,
+ const struct bin_attribute *battr, umode_t mode,
+ kuid_t uid, kgid_t gid, const void *ns)
+{
+ const struct attribute *attr = &battr->attr;
+ struct lock_class_key *key = NULL;
+ const struct kernfs_ops *ops;
+ struct kernfs_node *kn;
+
+ if (battr->mmap)
+ ops = &sysfs_bin_kfops_mmap;
+ else if (battr->read && battr->write)
+ ops = &sysfs_bin_kfops_rw;
+ else if (battr->read)
+ ops = &sysfs_bin_kfops_ro;
+ else if (battr->write)
+ ops = &sysfs_bin_kfops_wo;
+ else
+ ops = &sysfs_file_kfops_empty;
#ifdef CONFIG_DEBUG_LOCK_ALLOC
if (!attr->ignore_lockdep)
@@ -315,7 +327,7 @@ int sysfs_add_file_mode_ns(struct kernfs_node *parent,
#endif
kn = __kernfs_create_file(parent, attr->name, mode & 0777, uid, gid,
- size, ops, (void *)attr, ns, key);
+ battr->size, ops, (void *)attr, ns, key);
if (IS_ERR(kn)) {
if (PTR_ERR(kn) == -EEXIST)
sysfs_warn_dup(parent, attr->name);
@@ -340,9 +352,7 @@ int sysfs_create_file_ns(struct kobject *kobj, const struct attribute *attr,
return -EINVAL;
kobject_get_ownership(kobj, &uid, &gid);
- return sysfs_add_file_mode_ns(kobj->sd, attr, false, attr->mode,
- uid, gid, ns);
-
+ return sysfs_add_file_mode_ns(kobj->sd, attr, attr->mode, uid, gid, ns);
}
EXPORT_SYMBOL_GPL(sysfs_create_file_ns);
@@ -385,8 +395,8 @@ int sysfs_add_file_to_group(struct kobject *kobj,
return -ENOENT;
kobject_get_ownership(kobj, &uid, &gid);
- error = sysfs_add_file_mode_ns(parent, attr, false,
- attr->mode, uid, gid, NULL);
+ error = sysfs_add_file_mode_ns(parent, attr, attr->mode, uid, gid,
+ NULL);
kernfs_put(parent);
return error;
@@ -555,8 +565,8 @@ int sysfs_create_bin_file(struct kobject *kobj,
return -EINVAL;
kobject_get_ownership(kobj, &uid, &gid);
- return sysfs_add_file_mode_ns(kobj->sd, &attr->attr, true,
- attr->attr.mode, uid, gid, NULL);
+ return sysfs_add_bin_file_mode_ns(kobj->sd, attr, attr->attr.mode, uid,
+ gid, NULL);
}
EXPORT_SYMBOL_GPL(sysfs_create_bin_file);
diff --git a/fs/sysfs/group.c b/fs/sysfs/group.c
index f29d62004527..eeb0e3099421 100644
--- a/fs/sysfs/group.c
+++ b/fs/sysfs/group.c
@@ -61,8 +61,8 @@ static int create_files(struct kernfs_node *parent, struct kobject *kobj,
(*attr)->name, mode);
mode &= SYSFS_PREALLOC | 0664;
- error = sysfs_add_file_mode_ns(parent, *attr, false,
- mode, uid, gid, NULL);
+ error = sysfs_add_file_mode_ns(parent, *attr, mode, uid,
+ gid, NULL);
if (unlikely(error))
break;
}
@@ -90,10 +90,9 @@ static int create_files(struct kernfs_node *parent, struct kobject *kobj,
(*bin_attr)->attr.name, mode);
mode &= SYSFS_PREALLOC | 0664;
- error = sysfs_add_file_mode_ns(parent,
- &(*bin_attr)->attr, true,
- mode,
- uid, gid, NULL);
+ error = sysfs_add_bin_file_mode_ns(parent, *bin_attr,
+ mode, uid, gid,
+ NULL);
if (error)
break;
}
@@ -340,8 +339,8 @@ int sysfs_merge_group(struct kobject *kobj,
kobject_get_ownership(kobj, &uid, &gid);
for ((i = 0, attr = grp->attrs); *attr && !error; (++i, ++attr))
- error = sysfs_add_file_mode_ns(parent, *attr, false,
- (*attr)->mode, uid, gid, NULL);
+ error = sysfs_add_file_mode_ns(parent, *attr, (*attr)->mode,
+ uid, gid, NULL);
if (error) {
while (--i >= 0)
kernfs_remove_by_name(parent, (*--attr)->name);
diff --git a/fs/sysfs/sysfs.h b/fs/sysfs/sysfs.h
index 0050cc0c0236..3f28c9af5756 100644
--- a/fs/sysfs/sysfs.h
+++ b/fs/sysfs/sysfs.h
@@ -28,9 +28,11 @@ void sysfs_warn_dup(struct kernfs_node *parent, const char *name);
* file.c
*/
int sysfs_add_file_mode_ns(struct kernfs_node *parent,
- const struct attribute *attr, bool is_bin,
- umode_t amode, kuid_t uid, kgid_t gid,
- const void *ns);
+ const struct attribute *attr, umode_t amode, kuid_t uid,
+ kgid_t gid, const void *ns);
+int sysfs_add_bin_file_mode_ns(struct kernfs_node *parent,
+ const struct bin_attribute *battr, umode_t mode,
+ kuid_t uid, kgid_t gid, const void *ns);
/*
* symlink.c
diff --git a/fs/sysv/super.c b/fs/sysv/super.c
index cc8e2ed155c8..d1def0771a40 100644
--- a/fs/sysv/super.c
+++ b/fs/sysv/super.c
@@ -474,10 +474,8 @@ static int v7_fill_super(struct super_block *sb, void *data, int silent)
struct sysv_sb_info *sbi;
struct buffer_head *bh;
- if (440 != sizeof (struct v7_super_block))
- panic("V7 FS: bad super-block size");
- if (64 != sizeof (struct sysv_inode))
- panic("sysv fs: bad i-node size");
+ BUILD_BUG_ON(sizeof(struct v7_super_block) != 440);
+ BUILD_BUG_ON(sizeof(struct sysv_inode) != 64);
sbi = kzalloc(sizeof(struct sysv_sb_info), GFP_KERNEL);
if (!sbi)
diff --git a/fs/xfs/kmem.h b/fs/xfs/kmem.h
index 54da6d717a06..b987dc2c6851 100644
--- a/fs/xfs/kmem.h
+++ b/fs/xfs/kmem.h
@@ -72,10 +72,6 @@ kmem_zalloc(size_t size, xfs_km_flags_t flags)
/*
* Zone interfaces
*/
-
-#define kmem_zone kmem_cache
-#define kmem_zone_t struct kmem_cache
-
static inline struct page *
kmem_to_page(void *addr)
{
diff --git a/fs/xfs/libxfs/xfs_ag.c b/fs/xfs/libxfs/xfs_ag.c
index 005abfd9fd34..d7d875cef07a 100644
--- a/fs/xfs/libxfs/xfs_ag.c
+++ b/fs/xfs/libxfs/xfs_ag.c
@@ -850,7 +850,7 @@ xfs_ag_shrink_space(
if (err2 != -ENOSPC)
goto resv_err;
- __xfs_bmap_add_free(*tpp, args.fsbno, delta, NULL, true);
+ __xfs_free_extent_later(*tpp, args.fsbno, delta, NULL, true);
/*
* Roll the transaction before trying to re-init the per-ag
diff --git a/fs/xfs/libxfs/xfs_ag.h b/fs/xfs/libxfs/xfs_ag.h
index 4c6f9045baca..3f597cad2c33 100644
--- a/fs/xfs/libxfs/xfs_ag.h
+++ b/fs/xfs/libxfs/xfs_ag.h
@@ -116,23 +116,29 @@ void xfs_perag_put(struct xfs_perag *pag);
/*
* Perag iteration APIs
- *
- * XXX: for_each_perag_range() usage really needs an iterator to clean up when
- * we terminate at end_agno because we may have taken a reference to the perag
- * beyond end_agno. Right now callers have to be careful to catch and clean that
- * up themselves. This is not necessary for the callers of for_each_perag() and
- * for_each_perag_from() because they terminate at sb_agcount where there are
- * no perag structures in tree beyond end_agno.
*/
-#define for_each_perag_range(mp, next_agno, end_agno, pag) \
- for ((pag) = xfs_perag_get((mp), (next_agno)); \
- (pag) != NULL && (next_agno) <= (end_agno); \
- (next_agno) = (pag)->pag_agno + 1, \
- xfs_perag_put(pag), \
- (pag) = xfs_perag_get((mp), (next_agno)))
+static inline struct xfs_perag *
+xfs_perag_next(
+ struct xfs_perag *pag,
+ xfs_agnumber_t *agno,
+ xfs_agnumber_t end_agno)
+{
+ struct xfs_mount *mp = pag->pag_mount;
+
+ *agno = pag->pag_agno + 1;
+ xfs_perag_put(pag);
+ if (*agno > end_agno)
+ return NULL;
+ return xfs_perag_get(mp, *agno);
+}
+
+#define for_each_perag_range(mp, agno, end_agno, pag) \
+ for ((pag) = xfs_perag_get((mp), (agno)); \
+ (pag) != NULL; \
+ (pag) = xfs_perag_next((pag), &(agno), (end_agno)))
-#define for_each_perag_from(mp, next_agno, pag) \
- for_each_perag_range((mp), (next_agno), (mp)->m_sb.sb_agcount, (pag))
+#define for_each_perag_from(mp, agno, pag) \
+ for_each_perag_range((mp), (agno), (mp)->m_sb.sb_agcount - 1, (pag))
#define for_each_perag(mp, agno, pag) \
diff --git a/fs/xfs/libxfs/xfs_ag_resv.c b/fs/xfs/libxfs/xfs_ag_resv.c
index 2aa2b3484c28..fe94058d4e9e 100644
--- a/fs/xfs/libxfs/xfs_ag_resv.c
+++ b/fs/xfs/libxfs/xfs_ag_resv.c
@@ -91,7 +91,8 @@ xfs_ag_resv_critical(
trace_xfs_ag_resv_critical(pag, type, avail);
/* Critically low if less than 10% or max btree height remains. */
- return XFS_TEST_ERROR(avail < orig / 10 || avail < XFS_BTREE_MAXLEVELS,
+ return XFS_TEST_ERROR(avail < orig / 10 ||
+ avail < pag->pag_mount->m_agbtree_maxlevels,
pag->pag_mount, XFS_ERRTAG_AG_RESV_CRITICAL);
}
diff --git a/fs/xfs/libxfs/xfs_alloc.c b/fs/xfs/libxfs/xfs_alloc.c
index 95157f5a5a6c..353e53b892e6 100644
--- a/fs/xfs/libxfs/xfs_alloc.c
+++ b/fs/xfs/libxfs/xfs_alloc.c
@@ -27,7 +27,7 @@
#include "xfs_ag_resv.h"
#include "xfs_bmap.h"
-extern kmem_zone_t *xfs_bmap_free_item_zone;
+struct kmem_cache *xfs_extfree_item_cache;
struct workqueue_struct *xfs_alloc_wq;
@@ -426,8 +426,8 @@ xfs_alloc_fix_len(
*/
STATIC int /* error code */
xfs_alloc_fixup_trees(
- xfs_btree_cur_t *cnt_cur, /* cursor for by-size btree */
- xfs_btree_cur_t *bno_cur, /* cursor for by-block btree */
+ struct xfs_btree_cur *cnt_cur, /* cursor for by-size btree */
+ struct xfs_btree_cur *bno_cur, /* cursor for by-block btree */
xfs_agblock_t fbno, /* starting block of free extent */
xfs_extlen_t flen, /* length of free extent */
xfs_agblock_t rbno, /* starting block of returned extent */
@@ -488,8 +488,8 @@ xfs_alloc_fixup_trees(
struct xfs_btree_block *bnoblock;
struct xfs_btree_block *cntblock;
- bnoblock = XFS_BUF_TO_BLOCK(bno_cur->bc_bufs[0]);
- cntblock = XFS_BUF_TO_BLOCK(cnt_cur->bc_bufs[0]);
+ bnoblock = XFS_BUF_TO_BLOCK(bno_cur->bc_levels[0].bp);
+ cntblock = XFS_BUF_TO_BLOCK(cnt_cur->bc_levels[0].bp);
if (XFS_IS_CORRUPT(mp,
bnoblock->bb_numrecs !=
@@ -1200,8 +1200,8 @@ xfs_alloc_ag_vextent_exact(
xfs_alloc_arg_t *args) /* allocation argument structure */
{
struct xfs_agf __maybe_unused *agf = args->agbp->b_addr;
- xfs_btree_cur_t *bno_cur;/* by block-number btree cursor */
- xfs_btree_cur_t *cnt_cur;/* by count btree cursor */
+ struct xfs_btree_cur *bno_cur;/* by block-number btree cursor */
+ struct xfs_btree_cur *cnt_cur;/* by count btree cursor */
int error;
xfs_agblock_t fbno; /* start block of found extent */
xfs_extlen_t flen; /* length of found extent */
@@ -1512,7 +1512,7 @@ xfs_alloc_ag_vextent_lastblock(
* than minlen.
*/
if (*len || args->alignment > 1) {
- acur->cnt->bc_ptrs[0] = 1;
+ acur->cnt->bc_levels[0].ptr = 1;
do {
error = xfs_alloc_get_rec(acur->cnt, bno, len, &i);
if (error)
@@ -1658,8 +1658,8 @@ xfs_alloc_ag_vextent_size(
xfs_alloc_arg_t *args) /* allocation argument structure */
{
struct xfs_agf *agf = args->agbp->b_addr;
- xfs_btree_cur_t *bno_cur; /* cursor for bno btree */
- xfs_btree_cur_t *cnt_cur; /* cursor for cnt btree */
+ struct xfs_btree_cur *bno_cur; /* cursor for bno btree */
+ struct xfs_btree_cur *cnt_cur; /* cursor for cnt btree */
int error; /* error result */
xfs_agblock_t fbno; /* start of found freespace */
xfs_extlen_t flen; /* length of found freespace */
@@ -2190,14 +2190,15 @@ xfs_free_ag_extent(
*/
/*
- * Compute and fill in value of m_ag_maxlevels.
+ * Compute and fill in value of m_alloc_maxlevels.
*/
void
xfs_alloc_compute_maxlevels(
xfs_mount_t *mp) /* file system mount structure */
{
- mp->m_ag_maxlevels = xfs_btree_compute_maxlevels(mp->m_alloc_mnr,
+ mp->m_alloc_maxlevels = xfs_btree_compute_maxlevels(mp->m_alloc_mnr,
(mp->m_sb.sb_agblocks + 1) / 2);
+ ASSERT(mp->m_alloc_maxlevels <= xfs_allocbt_maxlevels_ondisk());
}
/*
@@ -2255,14 +2256,14 @@ xfs_alloc_min_freelist(
const uint8_t *levels = pag ? pag->pagf_levels : fake_levels;
unsigned int min_free;
- ASSERT(mp->m_ag_maxlevels > 0);
+ ASSERT(mp->m_alloc_maxlevels > 0);
/* space needed by-bno freespace btree */
min_free = min_t(unsigned int, levels[XFS_BTNUM_BNOi] + 1,
- mp->m_ag_maxlevels);
+ mp->m_alloc_maxlevels);
/* space needed by-size freespace btree */
min_free += min_t(unsigned int, levels[XFS_BTNUM_CNTi] + 1,
- mp->m_ag_maxlevels);
+ mp->m_alloc_maxlevels);
/* space needed reverse mapping used space btree */
if (xfs_has_rmapbt(mp))
min_free += min_t(unsigned int, levels[XFS_BTNUM_RMAPi] + 1,
@@ -2439,7 +2440,7 @@ xfs_agfl_reset(
/*
* Defer an AGFL block free. This is effectively equivalent to
- * xfs_bmap_add_free() with some special handling particular to AGFL blocks.
+ * xfs_free_extent_later() with some special handling particular to AGFL blocks.
*
* Deferring AGFL frees helps prevent log reservation overruns due to too many
* allocation operations in a transaction. AGFL frees are prone to this problem
@@ -2458,21 +2459,74 @@ xfs_defer_agfl_block(
struct xfs_mount *mp = tp->t_mountp;
struct xfs_extent_free_item *new; /* new element */
- ASSERT(xfs_bmap_free_item_zone != NULL);
+ ASSERT(xfs_extfree_item_cache != NULL);
ASSERT(oinfo != NULL);
- new = kmem_cache_alloc(xfs_bmap_free_item_zone,
+ new = kmem_cache_zalloc(xfs_extfree_item_cache,
GFP_KERNEL | __GFP_NOFAIL);
new->xefi_startblock = XFS_AGB_TO_FSB(mp, agno, agbno);
new->xefi_blockcount = 1;
- new->xefi_oinfo = *oinfo;
- new->xefi_skip_discard = false;
+ new->xefi_owner = oinfo->oi_owner;
trace_xfs_agfl_free_defer(mp, agno, 0, agbno, 1);
xfs_defer_add(tp, XFS_DEFER_OPS_TYPE_AGFL_FREE, &new->xefi_list);
}
+/*
+ * Add the extent to the list of extents to be free at transaction end.
+ * The list is maintained sorted (by block number).
+ */
+void
+__xfs_free_extent_later(
+ struct xfs_trans *tp,
+ xfs_fsblock_t bno,
+ xfs_filblks_t len,
+ const struct xfs_owner_info *oinfo,
+ bool skip_discard)
+{
+ struct xfs_extent_free_item *new; /* new element */
+#ifdef DEBUG
+ struct xfs_mount *mp = tp->t_mountp;
+ xfs_agnumber_t agno;
+ xfs_agblock_t agbno;
+
+ ASSERT(bno != NULLFSBLOCK);
+ ASSERT(len > 0);
+ ASSERT(len <= MAXEXTLEN);
+ ASSERT(!isnullstartblock(bno));
+ agno = XFS_FSB_TO_AGNO(mp, bno);
+ agbno = XFS_FSB_TO_AGBNO(mp, bno);
+ ASSERT(agno < mp->m_sb.sb_agcount);
+ ASSERT(agbno < mp->m_sb.sb_agblocks);
+ ASSERT(len < mp->m_sb.sb_agblocks);
+ ASSERT(agbno + len <= mp->m_sb.sb_agblocks);
+#endif
+ ASSERT(xfs_extfree_item_cache != NULL);
+
+ new = kmem_cache_zalloc(xfs_extfree_item_cache,
+ GFP_KERNEL | __GFP_NOFAIL);
+ new->xefi_startblock = bno;
+ new->xefi_blockcount = (xfs_extlen_t)len;
+ if (skip_discard)
+ new->xefi_flags |= XFS_EFI_SKIP_DISCARD;
+ if (oinfo) {
+ ASSERT(oinfo->oi_offset == 0);
+
+ if (oinfo->oi_flags & XFS_OWNER_INFO_ATTR_FORK)
+ new->xefi_flags |= XFS_EFI_ATTR_FORK;
+ if (oinfo->oi_flags & XFS_OWNER_INFO_BMBT_BLOCK)
+ new->xefi_flags |= XFS_EFI_BMBT_BLOCK;
+ new->xefi_owner = oinfo->oi_owner;
+ } else {
+ new->xefi_owner = XFS_RMAP_OWN_NULL;
+ }
+ trace_xfs_bmap_free_defer(tp->t_mountp,
+ XFS_FSB_TO_AGNO(tp->t_mountp, bno), 0,
+ XFS_FSB_TO_AGBNO(tp->t_mountp, bno), len);
+ xfs_defer_add(tp, XFS_DEFER_OPS_TYPE_FREE, &new->xefi_list);
+}
+
#ifdef DEBUG
/*
* Check if an AGF has a free extent record whose length is equal to
@@ -2903,13 +2957,16 @@ xfs_agf_verify(
if (be32_to_cpu(agf->agf_levels[XFS_BTNUM_BNO]) < 1 ||
be32_to_cpu(agf->agf_levels[XFS_BTNUM_CNT]) < 1 ||
- be32_to_cpu(agf->agf_levels[XFS_BTNUM_BNO]) > mp->m_ag_maxlevels ||
- be32_to_cpu(agf->agf_levels[XFS_BTNUM_CNT]) > mp->m_ag_maxlevels)
+ be32_to_cpu(agf->agf_levels[XFS_BTNUM_BNO]) >
+ mp->m_alloc_maxlevels ||
+ be32_to_cpu(agf->agf_levels[XFS_BTNUM_CNT]) >
+ mp->m_alloc_maxlevels)
return __this_address;
if (xfs_has_rmapbt(mp) &&
(be32_to_cpu(agf->agf_levels[XFS_BTNUM_RMAP]) < 1 ||
- be32_to_cpu(agf->agf_levels[XFS_BTNUM_RMAP]) > mp->m_rmap_maxlevels))
+ be32_to_cpu(agf->agf_levels[XFS_BTNUM_RMAP]) >
+ mp->m_rmap_maxlevels))
return __this_address;
if (xfs_has_rmapbt(mp) &&
@@ -3495,3 +3552,20 @@ xfs_agfl_walk(
return 0;
}
+
+int __init
+xfs_extfree_intent_init_cache(void)
+{
+ xfs_extfree_item_cache = kmem_cache_create("xfs_extfree_intent",
+ sizeof(struct xfs_extent_free_item),
+ 0, 0, NULL);
+
+ return xfs_extfree_item_cache != NULL ? 0 : -ENOMEM;
+}
+
+void
+xfs_extfree_intent_destroy_cache(void)
+{
+ kmem_cache_destroy(xfs_extfree_item_cache);
+ xfs_extfree_item_cache = NULL;
+}
diff --git a/fs/xfs/libxfs/xfs_alloc.h b/fs/xfs/libxfs/xfs_alloc.h
index df4aefaf0046..1c14a0b1abea 100644
--- a/fs/xfs/libxfs/xfs_alloc.h
+++ b/fs/xfs/libxfs/xfs_alloc.h
@@ -98,7 +98,7 @@ unsigned int xfs_alloc_min_freelist(struct xfs_mount *mp,
struct xfs_perag *pag);
/*
- * Compute and fill in value of m_ag_maxlevels.
+ * Compute and fill in value of m_alloc_maxlevels.
*/
void
xfs_alloc_compute_maxlevels(
@@ -248,4 +248,40 @@ xfs_buf_to_agfl_bno(
return bp->b_addr;
}
+void __xfs_free_extent_later(struct xfs_trans *tp, xfs_fsblock_t bno,
+ xfs_filblks_t len, const struct xfs_owner_info *oinfo,
+ bool skip_discard);
+
+/*
+ * List of extents to be free "later".
+ * The list is kept sorted on xbf_startblock.
+ */
+struct xfs_extent_free_item {
+ struct list_head xefi_list;
+ uint64_t xefi_owner;
+ xfs_fsblock_t xefi_startblock;/* starting fs block number */
+ xfs_extlen_t xefi_blockcount;/* number of blocks in extent */
+ unsigned int xefi_flags;
+};
+
+#define XFS_EFI_SKIP_DISCARD (1U << 0) /* don't issue discard */
+#define XFS_EFI_ATTR_FORK (1U << 1) /* freeing attr fork block */
+#define XFS_EFI_BMBT_BLOCK (1U << 2) /* freeing bmap btree block */
+
+static inline void
+xfs_free_extent_later(
+ struct xfs_trans *tp,
+ xfs_fsblock_t bno,
+ xfs_filblks_t len,
+ const struct xfs_owner_info *oinfo)
+{
+ __xfs_free_extent_later(tp, bno, len, oinfo, false);
+}
+
+
+extern struct kmem_cache *xfs_extfree_item_cache;
+
+int __init xfs_extfree_intent_init_cache(void);
+void xfs_extfree_intent_destroy_cache(void);
+
#endif /* __XFS_ALLOC_H__ */
diff --git a/fs/xfs/libxfs/xfs_alloc_btree.c b/fs/xfs/libxfs/xfs_alloc_btree.c
index 6746fd735550..8c9f73cc0bee 100644
--- a/fs/xfs/libxfs/xfs_alloc_btree.c
+++ b/fs/xfs/libxfs/xfs_alloc_btree.c
@@ -20,6 +20,7 @@
#include "xfs_trans.h"
#include "xfs_ag.h"
+static struct kmem_cache *xfs_allocbt_cur_cache;
STATIC struct xfs_btree_cur *
xfs_allocbt_dup_cursor(
@@ -316,7 +317,7 @@ xfs_allocbt_verify(
if (pag && pag->pagf_init) {
if (level >= pag->pagf_levels[btnum])
return __this_address;
- } else if (level >= mp->m_ag_maxlevels)
+ } else if (level >= mp->m_alloc_maxlevels)
return __this_address;
return xfs_btree_sblock_verify(bp, mp->m_alloc_mxr[level != 0]);
@@ -477,12 +478,8 @@ xfs_allocbt_init_common(
ASSERT(btnum == XFS_BTNUM_BNO || btnum == XFS_BTNUM_CNT);
- cur = kmem_cache_zalloc(xfs_btree_cur_zone, GFP_NOFS | __GFP_NOFAIL);
-
- cur->bc_tp = tp;
- cur->bc_mp = mp;
- cur->bc_btnum = btnum;
- cur->bc_blocklog = mp->m_sb.sb_blocklog;
+ cur = xfs_btree_alloc_cursor(mp, tp, btnum, mp->m_alloc_maxlevels,
+ xfs_allocbt_cur_cache);
cur->bc_ag.abt.active = false;
if (btnum == XFS_BTNUM_CNT) {
@@ -571,6 +568,17 @@ xfs_allocbt_commit_staged_btree(
}
}
+/* Calculate number of records in an alloc btree block. */
+static inline unsigned int
+xfs_allocbt_block_maxrecs(
+ unsigned int blocklen,
+ bool leaf)
+{
+ if (leaf)
+ return blocklen / sizeof(xfs_alloc_rec_t);
+ return blocklen / (sizeof(xfs_alloc_key_t) + sizeof(xfs_alloc_ptr_t));
+}
+
/*
* Calculate number of records in an alloc btree block.
*/
@@ -581,10 +589,26 @@ xfs_allocbt_maxrecs(
int leaf)
{
blocklen -= XFS_ALLOC_BLOCK_LEN(mp);
+ return xfs_allocbt_block_maxrecs(blocklen, leaf);
+}
- if (leaf)
- return blocklen / sizeof(xfs_alloc_rec_t);
- return blocklen / (sizeof(xfs_alloc_key_t) + sizeof(xfs_alloc_ptr_t));
+/* Free space btrees are at their largest when every other block is free. */
+#define XFS_MAX_FREESP_RECORDS ((XFS_MAX_AG_BLOCKS + 1) / 2)
+
+/* Compute the max possible height for free space btrees. */
+unsigned int
+xfs_allocbt_maxlevels_ondisk(void)
+{
+ unsigned int minrecs[2];
+ unsigned int blocklen;
+
+ blocklen = min(XFS_MIN_BLOCKSIZE - XFS_BTREE_SBLOCK_LEN,
+ XFS_MIN_CRC_BLOCKSIZE - XFS_BTREE_SBLOCK_CRC_LEN);
+
+ minrecs[0] = xfs_allocbt_block_maxrecs(blocklen, true) / 2;
+ minrecs[1] = xfs_allocbt_block_maxrecs(blocklen, false) / 2;
+
+ return xfs_btree_compute_maxlevels(minrecs, XFS_MAX_FREESP_RECORDS);
}
/* Calculate the freespace btree size for some records. */
@@ -595,3 +619,22 @@ xfs_allocbt_calc_size(
{
return xfs_btree_calc_size(mp->m_alloc_mnr, len);
}
+
+int __init
+xfs_allocbt_init_cur_cache(void)
+{
+ xfs_allocbt_cur_cache = kmem_cache_create("xfs_bnobt_cur",
+ xfs_btree_cur_sizeof(xfs_allocbt_maxlevels_ondisk()),
+ 0, 0, NULL);
+
+ if (!xfs_allocbt_cur_cache)
+ return -ENOMEM;
+ return 0;
+}
+
+void
+xfs_allocbt_destroy_cur_cache(void)
+{
+ kmem_cache_destroy(xfs_allocbt_cur_cache);
+ xfs_allocbt_cur_cache = NULL;
+}
diff --git a/fs/xfs/libxfs/xfs_alloc_btree.h b/fs/xfs/libxfs/xfs_alloc_btree.h
index 2f6b816aaf9f..45df893ef6bb 100644
--- a/fs/xfs/libxfs/xfs_alloc_btree.h
+++ b/fs/xfs/libxfs/xfs_alloc_btree.h
@@ -60,4 +60,9 @@ extern xfs_extlen_t xfs_allocbt_calc_size(struct xfs_mount *mp,
void xfs_allocbt_commit_staged_btree(struct xfs_btree_cur *cur,
struct xfs_trans *tp, struct xfs_buf *agbp);
+unsigned int xfs_allocbt_maxlevels_ondisk(void);
+
+int __init xfs_allocbt_init_cur_cache(void);
+void xfs_allocbt_destroy_cur_cache(void);
+
#endif /* __XFS_ALLOC_BTREE_H__ */
diff --git a/fs/xfs/libxfs/xfs_attr_leaf.c b/fs/xfs/libxfs/xfs_attr_leaf.c
index e1d11e314228..014daa8c542d 100644
--- a/fs/xfs/libxfs/xfs_attr_leaf.c
+++ b/fs/xfs/libxfs/xfs_attr_leaf.c
@@ -770,7 +770,7 @@ xfs_attr_fork_remove(
ASSERT(ip->i_afp->if_nextents == 0);
xfs_idestroy_fork(ip->i_afp);
- kmem_cache_free(xfs_ifork_zone, ip->i_afp);
+ kmem_cache_free(xfs_ifork_cache, ip->i_afp);
ip->i_afp = NULL;
ip->i_forkoff = 0;
xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c
index b48230f1a361..4dccd4d90622 100644
--- a/fs/xfs/libxfs/xfs_bmap.c
+++ b/fs/xfs/libxfs/xfs_bmap.c
@@ -37,8 +37,7 @@
#include "xfs_icache.h"
#include "xfs_iomap.h"
-
-kmem_zone_t *xfs_bmap_free_item_zone;
+struct kmem_cache *xfs_bmap_intent_cache;
/*
* Miscellaneous helper functions
@@ -93,6 +92,7 @@ xfs_bmap_compute_maxlevels(
maxblocks = (maxblocks + minnoderecs - 1) / minnoderecs;
}
mp->m_bm_maxlevels[whichfork] = level;
+ ASSERT(mp->m_bm_maxlevels[whichfork] <= xfs_bmbt_maxlevels_ondisk());
}
unsigned int
@@ -239,11 +239,11 @@ xfs_bmap_get_bp(
if (!cur)
return NULL;
- for (i = 0; i < XFS_BTREE_MAXLEVELS; i++) {
- if (!cur->bc_bufs[i])
+ for (i = 0; i < cur->bc_maxlevels; i++) {
+ if (!cur->bc_levels[i].bp)
break;
- if (xfs_buf_daddr(cur->bc_bufs[i]) == bno)
- return cur->bc_bufs[i];
+ if (xfs_buf_daddr(cur->bc_levels[i].bp) == bno)
+ return cur->bc_levels[i].bp;
}
/* Chase down all the log items to see if the bp is there */
@@ -316,7 +316,7 @@ xfs_check_block(
*/
STATIC void
xfs_bmap_check_leaf_extents(
- xfs_btree_cur_t *cur, /* btree cursor or null */
+ struct xfs_btree_cur *cur, /* btree cursor or null */
xfs_inode_t *ip, /* incore inode pointer */
int whichfork) /* data or attr fork */
{
@@ -522,56 +522,6 @@ xfs_bmap_validate_ret(
#endif /* DEBUG */
/*
- * bmap free list manipulation functions
- */
-
-/*
- * Add the extent to the list of extents to be free at transaction end.
- * The list is maintained sorted (by block number).
- */
-void
-__xfs_bmap_add_free(
- struct xfs_trans *tp,
- xfs_fsblock_t bno,
- xfs_filblks_t len,
- const struct xfs_owner_info *oinfo,
- bool skip_discard)
-{
- struct xfs_extent_free_item *new; /* new element */
-#ifdef DEBUG
- struct xfs_mount *mp = tp->t_mountp;
- xfs_agnumber_t agno;
- xfs_agblock_t agbno;
-
- ASSERT(bno != NULLFSBLOCK);
- ASSERT(len > 0);
- ASSERT(len <= MAXEXTLEN);
- ASSERT(!isnullstartblock(bno));
- agno = XFS_FSB_TO_AGNO(mp, bno);
- agbno = XFS_FSB_TO_AGBNO(mp, bno);
- ASSERT(agno < mp->m_sb.sb_agcount);
- ASSERT(agbno < mp->m_sb.sb_agblocks);
- ASSERT(len < mp->m_sb.sb_agblocks);
- ASSERT(agbno + len <= mp->m_sb.sb_agblocks);
-#endif
- ASSERT(xfs_bmap_free_item_zone != NULL);
-
- new = kmem_cache_alloc(xfs_bmap_free_item_zone,
- GFP_KERNEL | __GFP_NOFAIL);
- new->xefi_startblock = bno;
- new->xefi_blockcount = (xfs_extlen_t)len;
- if (oinfo)
- new->xefi_oinfo = *oinfo;
- else
- new->xefi_oinfo = XFS_RMAP_OINFO_SKIP_UPDATE;
- new->xefi_skip_discard = skip_discard;
- trace_xfs_bmap_free_defer(tp->t_mountp,
- XFS_FSB_TO_AGNO(tp->t_mountp, bno), 0,
- XFS_FSB_TO_AGBNO(tp->t_mountp, bno), len);
- xfs_defer_add(tp, XFS_DEFER_OPS_TYPE_FREE, &new->xefi_list);
-}
-
-/*
* Inode fork format manipulation functions
*/
@@ -625,12 +575,12 @@ xfs_bmap_btree_to_extents(
if ((error = xfs_btree_check_block(cur, cblock, 0, cbp)))
return error;
xfs_rmap_ino_bmbt_owner(&oinfo, ip->i_ino, whichfork);
- xfs_bmap_add_free(cur->bc_tp, cbno, 1, &oinfo);
+ xfs_free_extent_later(cur->bc_tp, cbno, 1, &oinfo);
ip->i_nblocks--;
xfs_trans_mod_dquot_byino(tp, ip, XFS_TRANS_DQ_BCOUNT, -1L);
xfs_trans_binval(tp, cbp);
- if (cur->bc_bufs[0] == cbp)
- cur->bc_bufs[0] = NULL;
+ if (cur->bc_levels[0].bp == cbp)
+ cur->bc_levels[0].bp = NULL;
xfs_iroot_realloc(ip, -1, whichfork);
ASSERT(ifp->if_broot == NULL);
ifp->if_format = XFS_DINODE_FMT_EXTENTS;
@@ -925,7 +875,7 @@ xfs_bmap_add_attrfork_btree(
int *flags) /* inode logging flags */
{
struct xfs_btree_block *block = ip->i_df.if_broot;
- xfs_btree_cur_t *cur; /* btree cursor */
+ struct xfs_btree_cur *cur; /* btree cursor */
int error; /* error return value */
xfs_mount_t *mp; /* file system mount struct */
int stat; /* newroot status */
@@ -968,7 +918,7 @@ xfs_bmap_add_attrfork_extents(
struct xfs_inode *ip, /* incore inode pointer */
int *flags) /* inode logging flags */
{
- xfs_btree_cur_t *cur; /* bmap btree cursor */
+ struct xfs_btree_cur *cur; /* bmap btree cursor */
int error; /* error return value */
if (ip->i_df.if_nextents * sizeof(struct xfs_bmbt_rec) <=
@@ -1988,11 +1938,11 @@ xfs_bmap_add_extent_unwritten_real(
xfs_inode_t *ip, /* incore inode pointer */
int whichfork,
struct xfs_iext_cursor *icur,
- xfs_btree_cur_t **curp, /* if *curp is null, not a btree */
+ struct xfs_btree_cur **curp, /* if *curp is null, not a btree */
xfs_bmbt_irec_t *new, /* new data to add to file extents */
int *logflagsp) /* inode logging flags */
{
- xfs_btree_cur_t *cur; /* btree cursor */
+ struct xfs_btree_cur *cur; /* btree cursor */
int error; /* error return value */
int i; /* temp state */
struct xfs_ifork *ifp; /* inode fork pointer */
@@ -5045,7 +4995,7 @@ xfs_bmap_del_extent_real(
xfs_inode_t *ip, /* incore inode pointer */
xfs_trans_t *tp, /* current transaction pointer */
struct xfs_iext_cursor *icur,
- xfs_btree_cur_t *cur, /* if null, not a btree */
+ struct xfs_btree_cur *cur, /* if null, not a btree */
xfs_bmbt_irec_t *del, /* data to remove from extents */
int *logflagsp, /* inode logging flags */
int whichfork, /* data or attr fork */
@@ -5296,7 +5246,7 @@ xfs_bmap_del_extent_real(
if (xfs_is_reflink_inode(ip) && whichfork == XFS_DATA_FORK) {
xfs_refcount_decrease_extent(tp, del);
} else {
- __xfs_bmap_add_free(tp, del->br_startblock,
+ __xfs_free_extent_later(tp, del->br_startblock,
del->br_blockcount, NULL,
(bflags & XFS_BMAPI_NODISCARD) ||
del->br_state == XFS_EXT_UNWRITTEN);
@@ -6189,7 +6139,7 @@ __xfs_bmap_add(
bmap->br_blockcount,
bmap->br_state);
- bi = kmem_alloc(sizeof(struct xfs_bmap_intent), KM_NOFS);
+ bi = kmem_cache_alloc(xfs_bmap_intent_cache, GFP_NOFS | __GFP_NOFAIL);
INIT_LIST_HEAD(&bi->bi_list);
bi->bi_type = type;
bi->bi_owner = ip;
@@ -6300,3 +6250,20 @@ xfs_bmap_validate_extent(
return __this_address;
return NULL;
}
+
+int __init
+xfs_bmap_intent_init_cache(void)
+{
+ xfs_bmap_intent_cache = kmem_cache_create("xfs_bmap_intent",
+ sizeof(struct xfs_bmap_intent),
+ 0, 0, NULL);
+
+ return xfs_bmap_intent_cache != NULL ? 0 : -ENOMEM;
+}
+
+void
+xfs_bmap_intent_destroy_cache(void)
+{
+ kmem_cache_destroy(xfs_bmap_intent_cache);
+ xfs_bmap_intent_cache = NULL;
+}
diff --git a/fs/xfs/libxfs/xfs_bmap.h b/fs/xfs/libxfs/xfs_bmap.h
index 67641f669918..03d9aaf87413 100644
--- a/fs/xfs/libxfs/xfs_bmap.h
+++ b/fs/xfs/libxfs/xfs_bmap.h
@@ -13,8 +13,6 @@ struct xfs_inode;
struct xfs_mount;
struct xfs_trans;
-extern kmem_zone_t *xfs_bmap_free_item_zone;
-
/*
* Argument structure for xfs_bmap_alloc.
*/
@@ -44,19 +42,6 @@ struct xfs_bmalloca {
int flags;
};
-/*
- * List of extents to be free "later".
- * The list is kept sorted on xbf_startblock.
- */
-struct xfs_extent_free_item
-{
- xfs_fsblock_t xefi_startblock;/* starting fs block number */
- xfs_extlen_t xefi_blockcount;/* number of blocks in extent */
- bool xefi_skip_discard;
- struct list_head xefi_list;
- struct xfs_owner_info xefi_oinfo; /* extent owner */
-};
-
#define XFS_BMAP_MAX_NMAP 4
/*
@@ -189,9 +174,6 @@ unsigned int xfs_bmap_compute_attr_offset(struct xfs_mount *mp);
int xfs_bmap_add_attrfork(struct xfs_inode *ip, int size, int rsvd);
void xfs_bmap_local_to_extents_empty(struct xfs_trans *tp,
struct xfs_inode *ip, int whichfork);
-void __xfs_bmap_add_free(struct xfs_trans *tp, xfs_fsblock_t bno,
- xfs_filblks_t len, const struct xfs_owner_info *oinfo,
- bool skip_discard);
void xfs_bmap_compute_maxlevels(struct xfs_mount *mp, int whichfork);
int xfs_bmap_first_unused(struct xfs_trans *tp, struct xfs_inode *ip,
xfs_extlen_t len, xfs_fileoff_t *unused, int whichfork);
@@ -239,16 +221,6 @@ int xfs_bmap_add_extent_unwritten_real(struct xfs_trans *tp,
struct xfs_iext_cursor *icur, struct xfs_btree_cur **curp,
struct xfs_bmbt_irec *new, int *logflagsp);
-static inline void
-xfs_bmap_add_free(
- struct xfs_trans *tp,
- xfs_fsblock_t bno,
- xfs_filblks_t len,
- const struct xfs_owner_info *oinfo)
-{
- __xfs_bmap_add_free(tp, bno, len, oinfo, false);
-}
-
enum xfs_bmap_intent_type {
XFS_BMAP_MAP = 1,
XFS_BMAP_UNMAP,
@@ -257,8 +229,8 @@ enum xfs_bmap_intent_type {
struct xfs_bmap_intent {
struct list_head bi_list;
enum xfs_bmap_intent_type bi_type;
- struct xfs_inode *bi_owner;
int bi_whichfork;
+ struct xfs_inode *bi_owner;
struct xfs_bmbt_irec bi_bmap;
};
@@ -290,4 +262,9 @@ int xfs_bmapi_remap(struct xfs_trans *tp, struct xfs_inode *ip,
xfs_fileoff_t bno, xfs_filblks_t len, xfs_fsblock_t startblock,
int flags);
+extern struct kmem_cache *xfs_bmap_intent_cache;
+
+int __init xfs_bmap_intent_init_cache(void);
+void xfs_bmap_intent_destroy_cache(void);
+
#endif /* __XFS_BMAP_H__ */
diff --git a/fs/xfs/libxfs/xfs_bmap_btree.c b/fs/xfs/libxfs/xfs_bmap_btree.c
index 72444b8b38a6..453309fc85f2 100644
--- a/fs/xfs/libxfs/xfs_bmap_btree.c
+++ b/fs/xfs/libxfs/xfs_bmap_btree.c
@@ -22,6 +22,8 @@
#include "xfs_trace.h"
#include "xfs_rmap.h"
+static struct kmem_cache *xfs_bmbt_cur_cache;
+
/*
* Convert on-disk form of btree root to in-memory form.
*/
@@ -286,7 +288,7 @@ xfs_bmbt_free_block(
struct xfs_owner_info oinfo;
xfs_rmap_ino_bmbt_owner(&oinfo, ip->i_ino, cur->bc_ino.whichfork);
- xfs_bmap_add_free(cur->bc_tp, fsbno, 1, &oinfo);
+ xfs_free_extent_later(cur->bc_tp, fsbno, 1, &oinfo);
ip->i_nblocks--;
xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
@@ -552,13 +554,9 @@ xfs_bmbt_init_cursor(
struct xfs_btree_cur *cur;
ASSERT(whichfork != XFS_COW_FORK);
- cur = kmem_cache_zalloc(xfs_btree_cur_zone, GFP_NOFS | __GFP_NOFAIL);
-
- cur->bc_tp = tp;
- cur->bc_mp = mp;
+ cur = xfs_btree_alloc_cursor(mp, tp, XFS_BTNUM_BMAP,
+ mp->m_bm_maxlevels[whichfork], xfs_bmbt_cur_cache);
cur->bc_nlevels = be16_to_cpu(ifp->if_broot->bb_level) + 1;
- cur->bc_btnum = XFS_BTNUM_BMAP;
- cur->bc_blocklog = mp->m_sb.sb_blocklog;
cur->bc_statoff = XFS_STATS_CALC_INDEX(xs_bmbt_2);
cur->bc_ops = &xfs_bmbt_ops;
@@ -575,6 +573,17 @@ xfs_bmbt_init_cursor(
return cur;
}
+/* Calculate number of records in a block mapping btree block. */
+static inline unsigned int
+xfs_bmbt_block_maxrecs(
+ unsigned int blocklen,
+ bool leaf)
+{
+ if (leaf)
+ return blocklen / sizeof(xfs_bmbt_rec_t);
+ return blocklen / (sizeof(xfs_bmbt_key_t) + sizeof(xfs_bmbt_ptr_t));
+}
+
/*
* Calculate number of records in a bmap btree block.
*/
@@ -585,10 +594,24 @@ xfs_bmbt_maxrecs(
int leaf)
{
blocklen -= XFS_BMBT_BLOCK_LEN(mp);
+ return xfs_bmbt_block_maxrecs(blocklen, leaf);
+}
- if (leaf)
- return blocklen / sizeof(xfs_bmbt_rec_t);
- return blocklen / (sizeof(xfs_bmbt_key_t) + sizeof(xfs_bmbt_ptr_t));
+/* Compute the max possible height for block mapping btrees. */
+unsigned int
+xfs_bmbt_maxlevels_ondisk(void)
+{
+ unsigned int minrecs[2];
+ unsigned int blocklen;
+
+ blocklen = min(XFS_MIN_BLOCKSIZE - XFS_BTREE_SBLOCK_LEN,
+ XFS_MIN_CRC_BLOCKSIZE - XFS_BTREE_SBLOCK_CRC_LEN);
+
+ minrecs[0] = xfs_bmbt_block_maxrecs(blocklen, true) / 2;
+ minrecs[1] = xfs_bmbt_block_maxrecs(blocklen, false) / 2;
+
+ /* One extra level for the inode root. */
+ return xfs_btree_compute_maxlevels(minrecs, MAXEXTNUM) + 1;
}
/*
@@ -654,3 +677,22 @@ xfs_bmbt_calc_size(
{
return xfs_btree_calc_size(mp->m_bmap_dmnr, len);
}
+
+int __init
+xfs_bmbt_init_cur_cache(void)
+{
+ xfs_bmbt_cur_cache = kmem_cache_create("xfs_bmbt_cur",
+ xfs_btree_cur_sizeof(xfs_bmbt_maxlevels_ondisk()),
+ 0, 0, NULL);
+
+ if (!xfs_bmbt_cur_cache)
+ return -ENOMEM;
+ return 0;
+}
+
+void
+xfs_bmbt_destroy_cur_cache(void)
+{
+ kmem_cache_destroy(xfs_bmbt_cur_cache);
+ xfs_bmbt_cur_cache = NULL;
+}
diff --git a/fs/xfs/libxfs/xfs_bmap_btree.h b/fs/xfs/libxfs/xfs_bmap_btree.h
index 729e3bc569be..3e7a40a83835 100644
--- a/fs/xfs/libxfs/xfs_bmap_btree.h
+++ b/fs/xfs/libxfs/xfs_bmap_btree.h
@@ -110,4 +110,9 @@ extern struct xfs_btree_cur *xfs_bmbt_init_cursor(struct xfs_mount *,
extern unsigned long long xfs_bmbt_calc_size(struct xfs_mount *mp,
unsigned long long len);
+unsigned int xfs_bmbt_maxlevels_ondisk(void);
+
+int __init xfs_bmbt_init_cur_cache(void);
+void xfs_bmbt_destroy_cur_cache(void);
+
#endif /* __XFS_BMAP_BTREE_H__ */
diff --git a/fs/xfs/libxfs/xfs_btree.c b/fs/xfs/libxfs/xfs_btree.c
index 298395481713..b4e19aacb9de 100644
--- a/fs/xfs/libxfs/xfs_btree.c
+++ b/fs/xfs/libxfs/xfs_btree.c
@@ -22,11 +22,11 @@
#include "xfs_log.h"
#include "xfs_btree_staging.h"
#include "xfs_ag.h"
-
-/*
- * Cursor allocation zone.
- */
-kmem_zone_t *xfs_btree_cur_zone;
+#include "xfs_alloc_btree.h"
+#include "xfs_ialloc_btree.h"
+#include "xfs_bmap_btree.h"
+#include "xfs_rmap_btree.h"
+#include "xfs_refcount_btree.h"
/*
* Btree magic numbers.
@@ -367,8 +367,8 @@ xfs_btree_del_cursor(
* way we won't have initialized all the entries down to 0.
*/
for (i = 0; i < cur->bc_nlevels; i++) {
- if (cur->bc_bufs[i])
- xfs_trans_brelse(cur->bc_tp, cur->bc_bufs[i]);
+ if (cur->bc_levels[i].bp)
+ xfs_trans_brelse(cur->bc_tp, cur->bc_levels[i].bp);
else if (!error)
break;
}
@@ -379,7 +379,7 @@ xfs_btree_del_cursor(
kmem_free(cur->bc_ops);
if (!(cur->bc_flags & XFS_BTREE_LONG_PTRS) && cur->bc_ag.pag)
xfs_perag_put(cur->bc_ag.pag);
- kmem_cache_free(xfs_btree_cur_zone, cur);
+ kmem_cache_free(cur->bc_cache, cur);
}
/*
@@ -388,14 +388,14 @@ xfs_btree_del_cursor(
*/
int /* error */
xfs_btree_dup_cursor(
- xfs_btree_cur_t *cur, /* input cursor */
- xfs_btree_cur_t **ncur) /* output cursor */
+ struct xfs_btree_cur *cur, /* input cursor */
+ struct xfs_btree_cur **ncur) /* output cursor */
{
struct xfs_buf *bp; /* btree block's buffer pointer */
int error; /* error return value */
int i; /* level number of btree block */
xfs_mount_t *mp; /* mount structure for filesystem */
- xfs_btree_cur_t *new; /* new cursor value */
+ struct xfs_btree_cur *new; /* new cursor value */
xfs_trans_t *tp; /* transaction pointer, can be NULL */
tp = cur->bc_tp;
@@ -415,9 +415,9 @@ xfs_btree_dup_cursor(
* For each level current, re-get the buffer and copy the ptr value.
*/
for (i = 0; i < new->bc_nlevels; i++) {
- new->bc_ptrs[i] = cur->bc_ptrs[i];
- new->bc_ra[i] = cur->bc_ra[i];
- bp = cur->bc_bufs[i];
+ new->bc_levels[i].ptr = cur->bc_levels[i].ptr;
+ new->bc_levels[i].ra = cur->bc_levels[i].ra;
+ bp = cur->bc_levels[i].bp;
if (bp) {
error = xfs_trans_read_buf(mp, tp, mp->m_ddev_targp,
xfs_buf_daddr(bp), mp->m_bsize,
@@ -429,7 +429,7 @@ xfs_btree_dup_cursor(
return error;
}
}
- new->bc_bufs[i] = bp;
+ new->bc_levels[i].bp = bp;
}
*ncur = new;
return 0;
@@ -681,7 +681,7 @@ xfs_btree_get_block(
return xfs_btree_get_iroot(cur);
}
- *bpp = cur->bc_bufs[level];
+ *bpp = cur->bc_levels[level].bp;
return XFS_BUF_TO_BLOCK(*bpp);
}
@@ -691,7 +691,7 @@ xfs_btree_get_block(
*/
STATIC int /* success=1, failure=0 */
xfs_btree_firstrec(
- xfs_btree_cur_t *cur, /* btree cursor */
+ struct xfs_btree_cur *cur, /* btree cursor */
int level) /* level to change */
{
struct xfs_btree_block *block; /* generic btree block pointer */
@@ -711,7 +711,7 @@ xfs_btree_firstrec(
/*
* Set the ptr value to 1, that's the first record/key.
*/
- cur->bc_ptrs[level] = 1;
+ cur->bc_levels[level].ptr = 1;
return 1;
}
@@ -721,7 +721,7 @@ xfs_btree_firstrec(
*/
STATIC int /* success=1, failure=0 */
xfs_btree_lastrec(
- xfs_btree_cur_t *cur, /* btree cursor */
+ struct xfs_btree_cur *cur, /* btree cursor */
int level) /* level to change */
{
struct xfs_btree_block *block; /* generic btree block pointer */
@@ -741,7 +741,7 @@ xfs_btree_lastrec(
/*
* Set the ptr value to numrecs, that's the last record/key.
*/
- cur->bc_ptrs[level] = be16_to_cpu(block->bb_numrecs);
+ cur->bc_levels[level].ptr = be16_to_cpu(block->bb_numrecs);
return 1;
}
@@ -922,11 +922,11 @@ xfs_btree_readahead(
(lev == cur->bc_nlevels - 1))
return 0;
- if ((cur->bc_ra[lev] | lr) == cur->bc_ra[lev])
+ if ((cur->bc_levels[lev].ra | lr) == cur->bc_levels[lev].ra)
return 0;
- cur->bc_ra[lev] |= lr;
- block = XFS_BUF_TO_BLOCK(cur->bc_bufs[lev]);
+ cur->bc_levels[lev].ra |= lr;
+ block = XFS_BUF_TO_BLOCK(cur->bc_levels[lev].bp);
if (cur->bc_flags & XFS_BTREE_LONG_PTRS)
return xfs_btree_readahead_lblock(cur, lr, block);
@@ -985,28 +985,28 @@ xfs_btree_readahead_ptr(
*/
STATIC void
xfs_btree_setbuf(
- xfs_btree_cur_t *cur, /* btree cursor */
+ struct xfs_btree_cur *cur, /* btree cursor */
int lev, /* level in btree */
struct xfs_buf *bp) /* new buffer to set */
{
struct xfs_btree_block *b; /* btree block */
- if (cur->bc_bufs[lev])
- xfs_trans_brelse(cur->bc_tp, cur->bc_bufs[lev]);
- cur->bc_bufs[lev] = bp;
- cur->bc_ra[lev] = 0;
+ if (cur->bc_levels[lev].bp)
+ xfs_trans_brelse(cur->bc_tp, cur->bc_levels[lev].bp);
+ cur->bc_levels[lev].bp = bp;
+ cur->bc_levels[lev].ra = 0;
b = XFS_BUF_TO_BLOCK(bp);
if (cur->bc_flags & XFS_BTREE_LONG_PTRS) {
if (b->bb_u.l.bb_leftsib == cpu_to_be64(NULLFSBLOCK))
- cur->bc_ra[lev] |= XFS_BTCUR_LEFTRA;
+ cur->bc_levels[lev].ra |= XFS_BTCUR_LEFTRA;
if (b->bb_u.l.bb_rightsib == cpu_to_be64(NULLFSBLOCK))
- cur->bc_ra[lev] |= XFS_BTCUR_RIGHTRA;
+ cur->bc_levels[lev].ra |= XFS_BTCUR_RIGHTRA;
} else {
if (b->bb_u.s.bb_leftsib == cpu_to_be32(NULLAGBLOCK))
- cur->bc_ra[lev] |= XFS_BTCUR_LEFTRA;
+ cur->bc_levels[lev].ra |= XFS_BTCUR_LEFTRA;
if (b->bb_u.s.bb_rightsib == cpu_to_be32(NULLAGBLOCK))
- cur->bc_ra[lev] |= XFS_BTCUR_RIGHTRA;
+ cur->bc_levels[lev].ra |= XFS_BTCUR_RIGHTRA;
}
}
@@ -1548,7 +1548,7 @@ xfs_btree_increment(
#endif
/* We're done if we remain in the block after the increment. */
- if (++cur->bc_ptrs[level] <= xfs_btree_get_numrecs(block))
+ if (++cur->bc_levels[level].ptr <= xfs_btree_get_numrecs(block))
goto out1;
/* Fail if we just went off the right edge of the tree. */
@@ -1571,7 +1571,7 @@ xfs_btree_increment(
goto error0;
#endif
- if (++cur->bc_ptrs[lev] <= xfs_btree_get_numrecs(block))
+ if (++cur->bc_levels[lev].ptr <= xfs_btree_get_numrecs(block))
break;
/* Read-ahead the right block for the next loop. */
@@ -1598,14 +1598,14 @@ xfs_btree_increment(
for (block = xfs_btree_get_block(cur, lev, &bp); lev > level; ) {
union xfs_btree_ptr *ptrp;
- ptrp = xfs_btree_ptr_addr(cur, cur->bc_ptrs[lev], block);
+ ptrp = xfs_btree_ptr_addr(cur, cur->bc_levels[lev].ptr, block);
--lev;
error = xfs_btree_read_buf_block(cur, ptrp, 0, &block, &bp);
if (error)
goto error0;
xfs_btree_setbuf(cur, lev, bp);
- cur->bc_ptrs[lev] = 1;
+ cur->bc_levels[lev].ptr = 1;
}
out1:
*stat = 1;
@@ -1641,7 +1641,7 @@ xfs_btree_decrement(
xfs_btree_readahead(cur, level, XFS_BTCUR_LEFTRA);
/* We're done if we remain in the block after the decrement. */
- if (--cur->bc_ptrs[level] > 0)
+ if (--cur->bc_levels[level].ptr > 0)
goto out1;
/* Get a pointer to the btree block. */
@@ -1665,7 +1665,7 @@ xfs_btree_decrement(
* Stop when we don't go off the left edge of a block.
*/
for (lev = level + 1; lev < cur->bc_nlevels; lev++) {
- if (--cur->bc_ptrs[lev] > 0)
+ if (--cur->bc_levels[lev].ptr > 0)
break;
/* Read-ahead the left block for the next loop. */
xfs_btree_readahead(cur, lev, XFS_BTCUR_LEFTRA);
@@ -1691,13 +1691,13 @@ xfs_btree_decrement(
for (block = xfs_btree_get_block(cur, lev, &bp); lev > level; ) {
union xfs_btree_ptr *ptrp;
- ptrp = xfs_btree_ptr_addr(cur, cur->bc_ptrs[lev], block);
+ ptrp = xfs_btree_ptr_addr(cur, cur->bc_levels[lev].ptr, block);
--lev;
error = xfs_btree_read_buf_block(cur, ptrp, 0, &block, &bp);
if (error)
goto error0;
xfs_btree_setbuf(cur, lev, bp);
- cur->bc_ptrs[lev] = xfs_btree_get_numrecs(block);
+ cur->bc_levels[lev].ptr = xfs_btree_get_numrecs(block);
}
out1:
*stat = 1;
@@ -1735,7 +1735,7 @@ xfs_btree_lookup_get_block(
*
* Otherwise throw it away and get a new one.
*/
- bp = cur->bc_bufs[level];
+ bp = cur->bc_levels[level].bp;
error = xfs_btree_ptr_to_daddr(cur, pp, &daddr);
if (error)
return error;
@@ -1864,7 +1864,7 @@ xfs_btree_lookup(
return -EFSCORRUPTED;
}
- cur->bc_ptrs[0] = dir != XFS_LOOKUP_LE;
+ cur->bc_levels[0].ptr = dir != XFS_LOOKUP_LE;
*stat = 0;
return 0;
}
@@ -1916,7 +1916,7 @@ xfs_btree_lookup(
if (error)
goto error0;
- cur->bc_ptrs[level] = keyno;
+ cur->bc_levels[level].ptr = keyno;
}
}
@@ -1933,7 +1933,7 @@ xfs_btree_lookup(
!xfs_btree_ptr_is_null(cur, &ptr)) {
int i;
- cur->bc_ptrs[0] = keyno;
+ cur->bc_levels[0].ptr = keyno;
error = xfs_btree_increment(cur, 0, &i);
if (error)
goto error0;
@@ -1944,7 +1944,7 @@ xfs_btree_lookup(
}
} else if (dir == XFS_LOOKUP_LE && diff > 0)
keyno--;
- cur->bc_ptrs[0] = keyno;
+ cur->bc_levels[0].ptr = keyno;
/* Return if we succeeded or not. */
if (keyno == 0 || keyno > xfs_btree_get_numrecs(block))
@@ -2104,7 +2104,7 @@ __xfs_btree_updkeys(
if (error)
return error;
#endif
- ptr = cur->bc_ptrs[level];
+ ptr = cur->bc_levels[level].ptr;
nlkey = xfs_btree_key_addr(cur, ptr, block);
nhkey = xfs_btree_high_key_addr(cur, ptr, block);
if (!force_all &&
@@ -2171,7 +2171,7 @@ xfs_btree_update_keys(
if (error)
return error;
#endif
- ptr = cur->bc_ptrs[level];
+ ptr = cur->bc_levels[level].ptr;
kp = xfs_btree_key_addr(cur, ptr, block);
xfs_btree_copy_keys(cur, kp, &key, 1);
xfs_btree_log_keys(cur, bp, ptr, ptr);
@@ -2205,7 +2205,7 @@ xfs_btree_update(
goto error0;
#endif
/* Get the address of the rec to be updated. */
- ptr = cur->bc_ptrs[0];
+ ptr = cur->bc_levels[0].ptr;
rp = xfs_btree_rec_addr(cur, ptr, block);
/* Fill in the new contents and log them. */
@@ -2280,7 +2280,7 @@ xfs_btree_lshift(
* If the cursor entry is the one that would be moved, don't
* do it... it's too complicated.
*/
- if (cur->bc_ptrs[level] <= 1)
+ if (cur->bc_levels[level].ptr <= 1)
goto out0;
/* Set up the left neighbor as "left". */
@@ -2414,7 +2414,7 @@ xfs_btree_lshift(
goto error0;
/* Slide the cursor value left one. */
- cur->bc_ptrs[level]--;
+ cur->bc_levels[level].ptr--;
*stat = 1;
return 0;
@@ -2476,7 +2476,7 @@ xfs_btree_rshift(
* do it... it's too complicated.
*/
lrecs = xfs_btree_get_numrecs(left);
- if (cur->bc_ptrs[level] >= lrecs)
+ if (cur->bc_levels[level].ptr >= lrecs)
goto out0;
/* Set up the right neighbor as "right". */
@@ -2664,7 +2664,7 @@ __xfs_btree_split(
*/
lrecs = xfs_btree_get_numrecs(left);
rrecs = lrecs / 2;
- if ((lrecs & 1) && cur->bc_ptrs[level] <= rrecs + 1)
+ if ((lrecs & 1) && cur->bc_levels[level].ptr <= rrecs + 1)
rrecs++;
src_index = (lrecs - rrecs + 1);
@@ -2760,9 +2760,9 @@ __xfs_btree_split(
* If it's just pointing past the last entry in left, then we'll
* insert there, so don't change anything in that case.
*/
- if (cur->bc_ptrs[level] > lrecs + 1) {
+ if (cur->bc_levels[level].ptr > lrecs + 1) {
xfs_btree_setbuf(cur, level, rbp);
- cur->bc_ptrs[level] -= lrecs;
+ cur->bc_levels[level].ptr -= lrecs;
}
/*
* If there are more levels, we'll need another cursor which refers
@@ -2772,7 +2772,7 @@ __xfs_btree_split(
error = xfs_btree_dup_cursor(cur, curp);
if (error)
goto error0;
- (*curp)->bc_ptrs[level + 1]++;
+ (*curp)->bc_levels[level + 1].ptr++;
}
*ptrp = rptr;
*stat = 1;
@@ -2933,7 +2933,8 @@ xfs_btree_new_iroot(
be16_add_cpu(&block->bb_level, 1);
xfs_btree_set_numrecs(block, 1);
cur->bc_nlevels++;
- cur->bc_ptrs[level + 1] = 1;
+ ASSERT(cur->bc_nlevels <= cur->bc_maxlevels);
+ cur->bc_levels[level + 1].ptr = 1;
kp = xfs_btree_key_addr(cur, 1, block);
ckp = xfs_btree_key_addr(cur, 1, cblock);
@@ -3094,8 +3095,9 @@ xfs_btree_new_root(
/* Fix up the cursor. */
xfs_btree_setbuf(cur, cur->bc_nlevels, nbp);
- cur->bc_ptrs[cur->bc_nlevels] = nptr;
+ cur->bc_levels[cur->bc_nlevels].ptr = nptr;
cur->bc_nlevels++;
+ ASSERT(cur->bc_nlevels <= cur->bc_maxlevels);
*stat = 1;
return 0;
error0:
@@ -3152,7 +3154,7 @@ xfs_btree_make_block_unfull(
return error;
if (*stat) {
- *oindex = *index = cur->bc_ptrs[level];
+ *oindex = *index = cur->bc_levels[level].ptr;
return 0;
}
@@ -3167,7 +3169,7 @@ xfs_btree_make_block_unfull(
return error;
- *index = cur->bc_ptrs[level];
+ *index = cur->bc_levels[level].ptr;
return 0;
}
@@ -3214,7 +3216,7 @@ xfs_btree_insrec(
}
/* If we're off the left edge, return failure. */
- ptr = cur->bc_ptrs[level];
+ ptr = cur->bc_levels[level].ptr;
if (ptr == 0) {
*stat = 0;
return 0;
@@ -3557,7 +3559,7 @@ xfs_btree_kill_iroot(
if (error)
return error;
- cur->bc_bufs[level - 1] = NULL;
+ cur->bc_levels[level - 1].bp = NULL;
be16_add_cpu(&block->bb_level, -1);
xfs_trans_log_inode(cur->bc_tp, ip,
XFS_ILOG_CORE | xfs_ilog_fbroot(cur->bc_ino.whichfork));
@@ -3590,8 +3592,8 @@ xfs_btree_kill_root(
if (error)
return error;
- cur->bc_bufs[level] = NULL;
- cur->bc_ra[level] = 0;
+ cur->bc_levels[level].bp = NULL;
+ cur->bc_levels[level].ra = 0;
cur->bc_nlevels--;
return 0;
@@ -3650,7 +3652,7 @@ xfs_btree_delrec(
tcur = NULL;
/* Get the index of the entry being deleted, check for nothing there. */
- ptr = cur->bc_ptrs[level];
+ ptr = cur->bc_levels[level].ptr;
if (ptr == 0) {
*stat = 0;
return 0;
@@ -3960,7 +3962,7 @@ xfs_btree_delrec(
xfs_btree_del_cursor(tcur, XFS_BTREE_NOERROR);
tcur = NULL;
if (level == 0)
- cur->bc_ptrs[0]++;
+ cur->bc_levels[0].ptr++;
*stat = 1;
return 0;
@@ -4097,9 +4099,9 @@ xfs_btree_delrec(
* cursor to the left block, and fix up the index.
*/
if (bp != lbp) {
- cur->bc_bufs[level] = lbp;
- cur->bc_ptrs[level] += lrecs;
- cur->bc_ra[level] = 0;
+ cur->bc_levels[level].bp = lbp;
+ cur->bc_levels[level].ptr += lrecs;
+ cur->bc_levels[level].ra = 0;
}
/*
* If we joined with the right neighbor and there's a level above
@@ -4119,16 +4121,16 @@ xfs_btree_delrec(
* We can't use decrement because it would change the next level up.
*/
if (level > 0)
- cur->bc_ptrs[level]--;
+ cur->bc_levels[level].ptr--;
/*
* We combined blocks, so we have to update the parent keys if the
- * btree supports overlapped intervals. However, bc_ptrs[level + 1]
- * points to the old block so that the caller knows which record to
- * delete. Therefore, the caller must be savvy enough to call updkeys
- * for us if we return stat == 2. The other exit points from this
- * function don't require deletions further up the tree, so they can
- * call updkeys directly.
+ * btree supports overlapped intervals. However,
+ * bc_levels[level + 1].ptr points to the old block so that the caller
+ * knows which record to delete. Therefore, the caller must be savvy
+ * enough to call updkeys for us if we return stat == 2. The other
+ * exit points from this function don't require deletions further up
+ * the tree, so they can call updkeys directly.
*/
/* Return value means the next level up has something to do. */
@@ -4182,7 +4184,7 @@ xfs_btree_delete(
if (i == 0) {
for (level = 1; level < cur->bc_nlevels; level++) {
- if (cur->bc_ptrs[level] == 0) {
+ if (cur->bc_levels[level].ptr == 0) {
error = xfs_btree_decrement(cur, level, &i);
if (error)
goto error0;
@@ -4213,7 +4215,7 @@ xfs_btree_get_rec(
int error; /* error return value */
#endif
- ptr = cur->bc_ptrs[0];
+ ptr = cur->bc_levels[0].ptr;
block = xfs_btree_get_block(cur, 0, &bp);
#ifdef DEBUG
@@ -4512,21 +4514,76 @@ xfs_btree_sblock_verify(
}
/*
- * Calculate the number of btree levels needed to store a given number of
- * records in a short-format btree.
+ * For the given limits on leaf and keyptr records per block, calculate the
+ * height of the tree needed to index the number of leaf records.
*/
-uint
+unsigned int
xfs_btree_compute_maxlevels(
- uint *limits,
- unsigned long len)
+ const unsigned int *limits,
+ unsigned long long records)
+{
+ unsigned long long level_blocks = howmany_64(records, limits[0]);
+ unsigned int height = 1;
+
+ while (level_blocks > 1) {
+ level_blocks = howmany_64(level_blocks, limits[1]);
+ height++;
+ }
+
+ return height;
+}
+
+/*
+ * For the given limits on leaf and keyptr records per block, calculate the
+ * number of blocks needed to index the given number of leaf records.
+ */
+unsigned long long
+xfs_btree_calc_size(
+ const unsigned int *limits,
+ unsigned long long records)
+{
+ unsigned long long level_blocks = howmany_64(records, limits[0]);
+ unsigned long long blocks = level_blocks;
+
+ while (level_blocks > 1) {
+ level_blocks = howmany_64(level_blocks, limits[1]);
+ blocks += level_blocks;
+ }
+
+ return blocks;
+}
+
+/*
+ * Given a number of available blocks for the btree to consume with records and
+ * pointers, calculate the height of the tree needed to index all the records
+ * that space can hold based on the number of pointers each interior node
+ * holds.
+ *
+ * We start by assuming a single level tree consumes a single block, then track
+ * the number of blocks each node level consumes until we no longer have space
+ * to store the next node level. At this point, we are indexing all the leaf
+ * blocks in the space, and there's no more free space to split the tree any
+ * further. That's our maximum btree height.
+ */
+unsigned int
+xfs_btree_space_to_height(
+ const unsigned int *limits,
+ unsigned long long leaf_blocks)
{
- uint level;
- unsigned long maxblocks;
+ unsigned long long node_blocks = limits[1];
+ unsigned long long blocks_left = leaf_blocks - 1;
+ unsigned int height = 1;
+
+ if (leaf_blocks < 1)
+ return 0;
+
+ while (node_blocks < blocks_left) {
+ blocks_left -= node_blocks;
+ node_blocks *= limits[1];
+ height++;
+ }
- maxblocks = (len + limits[0] - 1) / limits[0];
- for (level = 1; maxblocks > 1; level++)
- maxblocks = (maxblocks + limits[1] - 1) / limits[1];
- return level;
+ return height;
}
/*
@@ -4661,23 +4718,25 @@ xfs_btree_overlapped_query_range(
if (error)
goto out;
#endif
- cur->bc_ptrs[level] = 1;
+ cur->bc_levels[level].ptr = 1;
while (level < cur->bc_nlevels) {
block = xfs_btree_get_block(cur, level, &bp);
/* End of node, pop back towards the root. */
- if (cur->bc_ptrs[level] > be16_to_cpu(block->bb_numrecs)) {
+ if (cur->bc_levels[level].ptr >
+ be16_to_cpu(block->bb_numrecs)) {
pop_up:
if (level < cur->bc_nlevels - 1)
- cur->bc_ptrs[level + 1]++;
+ cur->bc_levels[level + 1].ptr++;
level++;
continue;
}
if (level == 0) {
/* Handle a leaf node. */
- recp = xfs_btree_rec_addr(cur, cur->bc_ptrs[0], block);
+ recp = xfs_btree_rec_addr(cur, cur->bc_levels[0].ptr,
+ block);
cur->bc_ops->init_high_key_from_rec(&rec_hkey, recp);
ldiff = cur->bc_ops->diff_two_keys(cur, &rec_hkey,
@@ -4700,14 +4759,15 @@ pop_up:
/* Record is larger than high key; pop. */
goto pop_up;
}
- cur->bc_ptrs[level]++;
+ cur->bc_levels[level].ptr++;
continue;
}
/* Handle an internal node. */
- lkp = xfs_btree_key_addr(cur, cur->bc_ptrs[level], block);
- hkp = xfs_btree_high_key_addr(cur, cur->bc_ptrs[level], block);
- pp = xfs_btree_ptr_addr(cur, cur->bc_ptrs[level], block);
+ lkp = xfs_btree_key_addr(cur, cur->bc_levels[level].ptr, block);
+ hkp = xfs_btree_high_key_addr(cur, cur->bc_levels[level].ptr,
+ block);
+ pp = xfs_btree_ptr_addr(cur, cur->bc_levels[level].ptr, block);
ldiff = cur->bc_ops->diff_two_keys(cur, hkp, low_key);
hdiff = cur->bc_ops->diff_two_keys(cur, high_key, lkp);
@@ -4730,13 +4790,13 @@ pop_up:
if (error)
goto out;
#endif
- cur->bc_ptrs[level] = 1;
+ cur->bc_levels[level].ptr = 1;
continue;
} else if (hdiff < 0) {
/* The low key is larger than the upper range; pop. */
goto pop_up;
}
- cur->bc_ptrs[level]++;
+ cur->bc_levels[level].ptr++;
}
out:
@@ -4747,13 +4807,14 @@ out:
* with a zero-results range query, so release the buffers if we
* failed to return any results.
*/
- if (cur->bc_bufs[0] == NULL) {
+ if (cur->bc_levels[0].bp == NULL) {
for (i = 0; i < cur->bc_nlevels; i++) {
- if (cur->bc_bufs[i]) {
- xfs_trans_brelse(cur->bc_tp, cur->bc_bufs[i]);
- cur->bc_bufs[i] = NULL;
- cur->bc_ptrs[i] = 0;
- cur->bc_ra[i] = 0;
+ if (cur->bc_levels[i].bp) {
+ xfs_trans_brelse(cur->bc_tp,
+ cur->bc_levels[i].bp);
+ cur->bc_levels[i].bp = NULL;
+ cur->bc_levels[i].ptr = 0;
+ cur->bc_levels[i].ra = 0;
}
}
}
@@ -4816,29 +4877,6 @@ xfs_btree_query_all(
return xfs_btree_simple_query_range(cur, &low_key, &high_key, fn, priv);
}
-/*
- * Calculate the number of blocks needed to store a given number of records
- * in a short-format (per-AG metadata) btree.
- */
-unsigned long long
-xfs_btree_calc_size(
- uint *limits,
- unsigned long long len)
-{
- int level;
- int maxrecs;
- unsigned long long rval;
-
- maxrecs = limits[0];
- for (level = 0, rval = 0; len > 1; level++) {
- len += maxrecs - 1;
- do_div(len, maxrecs);
- maxrecs = limits[1];
- rval += len;
- }
- return rval;
-}
-
static int
xfs_btree_count_blocks_helper(
struct xfs_btree_cur *cur,
@@ -4915,7 +4953,7 @@ xfs_btree_has_more_records(
block = xfs_btree_get_block(cur, 0, &bp);
/* There are still records in this block. */
- if (cur->bc_ptrs[0] < xfs_btree_get_numrecs(block))
+ if (cur->bc_levels[0].ptr < xfs_btree_get_numrecs(block))
return true;
/* There are more record blocks. */
@@ -4924,3 +4962,42 @@ xfs_btree_has_more_records(
else
return block->bb_u.s.bb_rightsib != cpu_to_be32(NULLAGBLOCK);
}
+
+/* Set up all the btree cursor caches. */
+int __init
+xfs_btree_init_cur_caches(void)
+{
+ int error;
+
+ error = xfs_allocbt_init_cur_cache();
+ if (error)
+ return error;
+ error = xfs_inobt_init_cur_cache();
+ if (error)
+ goto err;
+ error = xfs_bmbt_init_cur_cache();
+ if (error)
+ goto err;
+ error = xfs_rmapbt_init_cur_cache();
+ if (error)
+ goto err;
+ error = xfs_refcountbt_init_cur_cache();
+ if (error)
+ goto err;
+
+ return 0;
+err:
+ xfs_btree_destroy_cur_caches();
+ return error;
+}
+
+/* Destroy all the btree cursor caches, if they've been allocated. */
+void
+xfs_btree_destroy_cur_caches(void)
+{
+ xfs_allocbt_destroy_cur_cache();
+ xfs_inobt_destroy_cur_cache();
+ xfs_bmbt_destroy_cur_cache();
+ xfs_rmapbt_destroy_cur_cache();
+ xfs_refcountbt_destroy_cur_cache();
+}
diff --git a/fs/xfs/libxfs/xfs_btree.h b/fs/xfs/libxfs/xfs_btree.h
index 4eaf8517f850..22d9f411fde6 100644
--- a/fs/xfs/libxfs/xfs_btree.h
+++ b/fs/xfs/libxfs/xfs_btree.h
@@ -13,8 +13,6 @@ struct xfs_trans;
struct xfs_ifork;
struct xfs_perag;
-extern kmem_zone_t *xfs_btree_cur_zone;
-
/*
* Generic key, ptr and record wrapper structures.
*
@@ -92,8 +90,6 @@ uint32_t xfs_btree_magic(int crc, xfs_btnum_t btnum);
#define XFS_BTREE_STATS_ADD(cur, stat, val) \
XFS_STATS_ADD_OFF((cur)->bc_mp, (cur)->bc_statoff + __XBTS_ ## stat, val)
-#define XFS_BTREE_MAXLEVELS 9 /* max of all btrees */
-
struct xfs_btree_ops {
/* size of the key and record structures */
size_t key_len;
@@ -181,18 +177,18 @@ union xfs_btree_irec {
/* Per-AG btree information. */
struct xfs_btree_cur_ag {
- struct xfs_perag *pag;
+ struct xfs_perag *pag;
union {
struct xfs_buf *agbp;
struct xbtree_afakeroot *afake; /* for staging cursor */
};
union {
struct {
- unsigned long nr_ops; /* # record updates */
- int shape_changes; /* # of extent splits */
+ unsigned int nr_ops; /* # record updates */
+ unsigned int shape_changes; /* # of extent splits */
} refc;
struct {
- bool active; /* allocation cursor state */
+ bool active; /* allocation cursor state */
} abt;
};
};
@@ -212,26 +208,35 @@ struct xfs_btree_cur_ino {
#define XFS_BTCUR_BMBT_INVALID_OWNER (1 << 1)
};
+struct xfs_btree_level {
+ /* buffer pointer */
+ struct xfs_buf *bp;
+
+ /* key/record number */
+ uint16_t ptr;
+
+ /* readahead info */
+#define XFS_BTCUR_LEFTRA (1 << 0) /* left sibling has been read-ahead */
+#define XFS_BTCUR_RIGHTRA (1 << 1) /* right sibling has been read-ahead */
+ uint16_t ra;
+};
+
/*
* Btree cursor structure.
* This collects all information needed by the btree code in one place.
*/
-typedef struct xfs_btree_cur
+struct xfs_btree_cur
{
struct xfs_trans *bc_tp; /* transaction we're in, if any */
struct xfs_mount *bc_mp; /* file system mount struct */
const struct xfs_btree_ops *bc_ops;
- uint bc_flags; /* btree features - below */
+ struct kmem_cache *bc_cache; /* cursor cache */
+ unsigned int bc_flags; /* btree features - below */
+ xfs_btnum_t bc_btnum; /* identifies which btree type */
union xfs_btree_irec bc_rec; /* current insert/search record value */
- struct xfs_buf *bc_bufs[XFS_BTREE_MAXLEVELS]; /* buf ptr per level */
- int bc_ptrs[XFS_BTREE_MAXLEVELS]; /* key/record # */
- uint8_t bc_ra[XFS_BTREE_MAXLEVELS]; /* readahead bits */
-#define XFS_BTCUR_LEFTRA 1 /* left sibling has been read-ahead */
-#define XFS_BTCUR_RIGHTRA 2 /* right sibling has been read-ahead */
- uint8_t bc_nlevels; /* number of levels in the tree */
- uint8_t bc_blocklog; /* log2(blocksize) of btree blocks */
- xfs_btnum_t bc_btnum; /* identifies which btree type */
- int bc_statoff; /* offset of btre stats array */
+ uint8_t bc_nlevels; /* number of levels in the tree */
+ uint8_t bc_maxlevels; /* maximum levels for this btree type */
+ int bc_statoff; /* offset of btree stats array */
/*
* Short btree pointers need an agno to be able to turn the pointers
@@ -243,7 +248,21 @@ typedef struct xfs_btree_cur
struct xfs_btree_cur_ag bc_ag;
struct xfs_btree_cur_ino bc_ino;
};
-} xfs_btree_cur_t;
+
+ /* Must be at the end of the struct! */
+ struct xfs_btree_level bc_levels[];
+};
+
+/*
+ * Compute the size of a btree cursor that can handle a btree of a given
+ * height. The bc_levels array handles node and leaf blocks, so its size
+ * is exactly nlevels.
+ */
+static inline size_t
+xfs_btree_cur_sizeof(unsigned int nlevels)
+{
+ return struct_size((struct xfs_btree_cur *)NULL, bc_levels, nlevels);
+}
/* cursor flags */
#define XFS_BTREE_LONG_PTRS (1<<0) /* pointers are 64bits long */
@@ -258,7 +277,6 @@ typedef struct xfs_btree_cur
*/
#define XFS_BTREE_STAGING (1<<5)
-
#define XFS_BTREE_NOERROR 0
#define XFS_BTREE_ERROR 1
@@ -309,7 +327,7 @@ xfs_btree_check_sptr(
*/
void
xfs_btree_del_cursor(
- xfs_btree_cur_t *cur, /* btree cursor */
+ struct xfs_btree_cur *cur, /* btree cursor */
int error); /* del because of error */
/*
@@ -318,8 +336,8 @@ xfs_btree_del_cursor(
*/
int /* error */
xfs_btree_dup_cursor(
- xfs_btree_cur_t *cur, /* input cursor */
- xfs_btree_cur_t **ncur);/* output cursor */
+ struct xfs_btree_cur *cur, /* input cursor */
+ struct xfs_btree_cur **ncur);/* output cursor */
/*
* Compute first and last byte offsets for the fields given.
@@ -460,8 +478,12 @@ xfs_failaddr_t xfs_btree_lblock_v5hdr_verify(struct xfs_buf *bp,
xfs_failaddr_t xfs_btree_lblock_verify(struct xfs_buf *bp,
unsigned int max_recs);
-uint xfs_btree_compute_maxlevels(uint *limits, unsigned long len);
-unsigned long long xfs_btree_calc_size(uint *limits, unsigned long long len);
+unsigned int xfs_btree_compute_maxlevels(const unsigned int *limits,
+ unsigned long long records);
+unsigned long long xfs_btree_calc_size(const unsigned int *limits,
+ unsigned long long records);
+unsigned int xfs_btree_space_to_height(const unsigned int *limits,
+ unsigned long long blocks);
/*
* Return codes for the query range iterator function are 0 to continue
@@ -527,7 +549,7 @@ struct xfs_ifork *xfs_btree_ifork_ptr(struct xfs_btree_cur *cur);
/* Does this cursor point to the last block in the given level? */
static inline bool
xfs_btree_islastblock(
- xfs_btree_cur_t *cur,
+ struct xfs_btree_cur *cur,
int level)
{
struct xfs_btree_block *block;
@@ -558,4 +580,27 @@ void xfs_btree_copy_keys(struct xfs_btree_cur *cur,
union xfs_btree_key *dst_key,
const union xfs_btree_key *src_key, int numkeys);
+static inline struct xfs_btree_cur *
+xfs_btree_alloc_cursor(
+ struct xfs_mount *mp,
+ struct xfs_trans *tp,
+ xfs_btnum_t btnum,
+ uint8_t maxlevels,
+ struct kmem_cache *cache)
+{
+ struct xfs_btree_cur *cur;
+
+ cur = kmem_cache_zalloc(cache, GFP_NOFS | __GFP_NOFAIL);
+ cur->bc_tp = tp;
+ cur->bc_mp = mp;
+ cur->bc_btnum = btnum;
+ cur->bc_maxlevels = maxlevels;
+ cur->bc_cache = cache;
+
+ return cur;
+}
+
+int __init xfs_btree_init_cur_caches(void);
+void xfs_btree_destroy_cur_caches(void);
+
#endif /* __XFS_BTREE_H__ */
diff --git a/fs/xfs/libxfs/xfs_btree_staging.c b/fs/xfs/libxfs/xfs_btree_staging.c
index ac9e80152b5c..dd75e208b543 100644
--- a/fs/xfs/libxfs/xfs_btree_staging.c
+++ b/fs/xfs/libxfs/xfs_btree_staging.c
@@ -657,12 +657,12 @@ xfs_btree_bload_compute_geometry(
* checking levels 0 and 1 here, so set bc_nlevels such that the btree
* code doesn't interpret either as the root level.
*/
- cur->bc_nlevels = XFS_BTREE_MAXLEVELS - 1;
+ cur->bc_nlevels = cur->bc_maxlevels - 1;
xfs_btree_bload_ensure_slack(cur, &bbl->leaf_slack, 0);
xfs_btree_bload_ensure_slack(cur, &bbl->node_slack, 1);
bbl->nr_records = nr_this_level = nr_records;
- for (cur->bc_nlevels = 1; cur->bc_nlevels < XFS_BTREE_MAXLEVELS;) {
+ for (cur->bc_nlevels = 1; cur->bc_nlevels <= cur->bc_maxlevels;) {
uint64_t level_blocks;
uint64_t dontcare64;
unsigned int level = cur->bc_nlevels - 1;
@@ -703,6 +703,7 @@ xfs_btree_bload_compute_geometry(
* block-based btree level.
*/
cur->bc_nlevels++;
+ ASSERT(cur->bc_nlevels <= cur->bc_maxlevels);
xfs_btree_bload_level_geometry(cur, bbl, level,
nr_this_level, &avg_per_block,
&level_blocks, &dontcare64);
@@ -718,13 +719,14 @@ xfs_btree_bload_compute_geometry(
/* Otherwise, we need another level of btree. */
cur->bc_nlevels++;
+ ASSERT(cur->bc_nlevels <= cur->bc_maxlevels);
}
nr_blocks += level_blocks;
nr_this_level = level_blocks;
}
- if (cur->bc_nlevels == XFS_BTREE_MAXLEVELS)
+ if (cur->bc_nlevels > cur->bc_maxlevels)
return -EOVERFLOW;
bbl->btree_height = cur->bc_nlevels;
diff --git a/fs/xfs/libxfs/xfs_da_btree.c b/fs/xfs/libxfs/xfs_da_btree.c
index c062e2c85178..dd7a2dbce1d1 100644
--- a/fs/xfs/libxfs/xfs_da_btree.c
+++ b/fs/xfs/libxfs/xfs_da_btree.c
@@ -72,7 +72,7 @@ STATIC int xfs_da3_blk_unlink(xfs_da_state_t *state,
xfs_da_state_blk_t *save_blk);
-kmem_zone_t *xfs_da_state_zone; /* anchor for state struct zone */
+struct kmem_cache *xfs_da_state_cache; /* anchor for dir/attr state */
/*
* Allocate a dir-state structure.
@@ -84,7 +84,7 @@ xfs_da_state_alloc(
{
struct xfs_da_state *state;
- state = kmem_cache_zalloc(xfs_da_state_zone, GFP_NOFS | __GFP_NOFAIL);
+ state = kmem_cache_zalloc(xfs_da_state_cache, GFP_NOFS | __GFP_NOFAIL);
state->args = args;
state->mp = args->dp->i_mount;
return state;
@@ -113,7 +113,7 @@ xfs_da_state_free(xfs_da_state_t *state)
#ifdef DEBUG
memset((char *)state, 0, sizeof(*state));
#endif /* DEBUG */
- kmem_cache_free(xfs_da_state_zone, state);
+ kmem_cache_free(xfs_da_state_cache, state);
}
static inline int xfs_dabuf_nfsb(struct xfs_mount *mp, int whichfork)
diff --git a/fs/xfs/libxfs/xfs_da_btree.h b/fs/xfs/libxfs/xfs_da_btree.h
index ad5dd324631a..0faf7d9ac241 100644
--- a/fs/xfs/libxfs/xfs_da_btree.h
+++ b/fs/xfs/libxfs/xfs_da_btree.h
@@ -9,7 +9,6 @@
struct xfs_inode;
struct xfs_trans;
-struct zone;
/*
* Directory/attribute geometry information. There will be one of these for each
@@ -227,6 +226,6 @@ void xfs_da3_node_hdr_from_disk(struct xfs_mount *mp,
void xfs_da3_node_hdr_to_disk(struct xfs_mount *mp,
struct xfs_da_intnode *to, struct xfs_da3_icnode_hdr *from);
-extern struct kmem_zone *xfs_da_state_zone;
+extern struct kmem_cache *xfs_da_state_cache;
#endif /* __XFS_DA_BTREE_H__ */
diff --git a/fs/xfs/libxfs/xfs_defer.c b/fs/xfs/libxfs/xfs_defer.c
index eff4a127188e..0805ade2d300 100644
--- a/fs/xfs/libxfs/xfs_defer.c
+++ b/fs/xfs/libxfs/xfs_defer.c
@@ -18,6 +18,12 @@
#include "xfs_trace.h"
#include "xfs_icache.h"
#include "xfs_log.h"
+#include "xfs_rmap.h"
+#include "xfs_refcount.h"
+#include "xfs_bmap.h"
+#include "xfs_alloc.h"
+
+static struct kmem_cache *xfs_defer_pending_cache;
/*
* Deferred Operations in XFS
@@ -232,23 +238,20 @@ xfs_defer_trans_abort(
}
}
-/* Roll a transaction so we can do some deferred op processing. */
-STATIC int
-xfs_defer_trans_roll(
- struct xfs_trans **tpp)
+/*
+ * Capture resources that the caller said not to release ("held") when the
+ * transaction commits. Caller is responsible for zero-initializing @dres.
+ */
+static int
+xfs_defer_save_resources(
+ struct xfs_defer_resources *dres,
+ struct xfs_trans *tp)
{
- struct xfs_trans *tp = *tpp;
struct xfs_buf_log_item *bli;
struct xfs_inode_log_item *ili;
struct xfs_log_item *lip;
- struct xfs_buf *bplist[XFS_DEFER_OPS_NR_BUFS];
- struct xfs_inode *iplist[XFS_DEFER_OPS_NR_INODES];
- unsigned int ordered = 0; /* bitmap */
- int bpcount = 0, ipcount = 0;
- int i;
- int error;
- BUILD_BUG_ON(NBBY * sizeof(ordered) < XFS_DEFER_OPS_NR_BUFS);
+ BUILD_BUG_ON(NBBY * sizeof(dres->dr_ordered) < XFS_DEFER_OPS_NR_BUFS);
list_for_each_entry(lip, &tp->t_items, li_trans) {
switch (lip->li_type) {
@@ -256,28 +259,29 @@ xfs_defer_trans_roll(
bli = container_of(lip, struct xfs_buf_log_item,
bli_item);
if (bli->bli_flags & XFS_BLI_HOLD) {
- if (bpcount >= XFS_DEFER_OPS_NR_BUFS) {
+ if (dres->dr_bufs >= XFS_DEFER_OPS_NR_BUFS) {
ASSERT(0);
return -EFSCORRUPTED;
}
if (bli->bli_flags & XFS_BLI_ORDERED)
- ordered |= (1U << bpcount);
+ dres->dr_ordered |=
+ (1U << dres->dr_bufs);
else
xfs_trans_dirty_buf(tp, bli->bli_buf);
- bplist[bpcount++] = bli->bli_buf;
+ dres->dr_bp[dres->dr_bufs++] = bli->bli_buf;
}
break;
case XFS_LI_INODE:
ili = container_of(lip, struct xfs_inode_log_item,
ili_item);
if (ili->ili_lock_flags == 0) {
- if (ipcount >= XFS_DEFER_OPS_NR_INODES) {
+ if (dres->dr_inos >= XFS_DEFER_OPS_NR_INODES) {
ASSERT(0);
return -EFSCORRUPTED;
}
xfs_trans_log_inode(tp, ili->ili_inode,
XFS_ILOG_CORE);
- iplist[ipcount++] = ili->ili_inode;
+ dres->dr_ip[dres->dr_inos++] = ili->ili_inode;
}
break;
default:
@@ -285,7 +289,43 @@ xfs_defer_trans_roll(
}
}
- trace_xfs_defer_trans_roll(tp, _RET_IP_);
+ return 0;
+}
+
+/* Attach the held resources to the transaction. */
+static void
+xfs_defer_restore_resources(
+ struct xfs_trans *tp,
+ struct xfs_defer_resources *dres)
+{
+ unsigned short i;
+
+ /* Rejoin the joined inodes. */
+ for (i = 0; i < dres->dr_inos; i++)
+ xfs_trans_ijoin(tp, dres->dr_ip[i], 0);
+
+ /* Rejoin the buffers and dirty them so the log moves forward. */
+ for (i = 0; i < dres->dr_bufs; i++) {
+ xfs_trans_bjoin(tp, dres->dr_bp[i]);
+ if (dres->dr_ordered & (1U << i))
+ xfs_trans_ordered_buf(tp, dres->dr_bp[i]);
+ xfs_trans_bhold(tp, dres->dr_bp[i]);
+ }
+}
+
+/* Roll a transaction so we can do some deferred op processing. */
+STATIC int
+xfs_defer_trans_roll(
+ struct xfs_trans **tpp)
+{
+ struct xfs_defer_resources dres = { };
+ int error;
+
+ error = xfs_defer_save_resources(&dres, *tpp);
+ if (error)
+ return error;
+
+ trace_xfs_defer_trans_roll(*tpp, _RET_IP_);
/*
* Roll the transaction. Rolling always given a new transaction (even
@@ -295,22 +335,11 @@ xfs_defer_trans_roll(
* happened.
*/
error = xfs_trans_roll(tpp);
- tp = *tpp;
- /* Rejoin the joined inodes. */
- for (i = 0; i < ipcount; i++)
- xfs_trans_ijoin(tp, iplist[i], 0);
-
- /* Rejoin the buffers and dirty them so the log moves forward. */
- for (i = 0; i < bpcount; i++) {
- xfs_trans_bjoin(tp, bplist[i]);
- if (ordered & (1U << i))
- xfs_trans_ordered_buf(tp, bplist[i]);
- xfs_trans_bhold(tp, bplist[i]);
- }
+ xfs_defer_restore_resources(*tpp, &dres);
if (error)
- trace_xfs_defer_trans_roll_error(tp, error);
+ trace_xfs_defer_trans_roll_error(*tpp, error);
return error;
}
@@ -342,7 +371,7 @@ xfs_defer_cancel_list(
ops->cancel_item(pwi);
}
ASSERT(dfp->dfp_count == 0);
- kmem_free(dfp);
+ kmem_cache_free(xfs_defer_pending_cache, dfp);
}
}
@@ -439,7 +468,7 @@ xfs_defer_finish_one(
/* Done with the dfp, free it. */
list_del(&dfp->dfp_list);
- kmem_free(dfp);
+ kmem_cache_free(xfs_defer_pending_cache, dfp);
out:
if (ops->finish_cleanup)
ops->finish_cleanup(tp, state, error);
@@ -573,8 +602,8 @@ xfs_defer_add(
dfp = NULL;
}
if (!dfp) {
- dfp = kmem_alloc(sizeof(struct xfs_defer_pending),
- KM_NOFS);
+ dfp = kmem_cache_zalloc(xfs_defer_pending_cache,
+ GFP_NOFS | __GFP_NOFAIL);
dfp->dfp_type = type;
dfp->dfp_intent = NULL;
dfp->dfp_done = NULL;
@@ -627,10 +656,11 @@ xfs_defer_move(
*/
static struct xfs_defer_capture *
xfs_defer_ops_capture(
- struct xfs_trans *tp,
- struct xfs_inode *capture_ip)
+ struct xfs_trans *tp)
{
struct xfs_defer_capture *dfc;
+ unsigned short i;
+ int error;
if (list_empty(&tp->t_dfops))
return NULL;
@@ -654,27 +684,48 @@ xfs_defer_ops_capture(
/* Preserve the log reservation size. */
dfc->dfc_logres = tp->t_log_res;
+ error = xfs_defer_save_resources(&dfc->dfc_held, tp);
+ if (error) {
+ /*
+ * Resource capture should never fail, but if it does, we
+ * still have to shut down the log and release things
+ * properly.
+ */
+ xfs_force_shutdown(tp->t_mountp, SHUTDOWN_CORRUPT_INCORE);
+ }
+
/*
- * Grab an extra reference to this inode and attach it to the capture
- * structure.
+ * Grab extra references to the inodes and buffers because callers are
+ * expected to release their held references after we commit the
+ * transaction.
*/
- if (capture_ip) {
- ihold(VFS_I(capture_ip));
- dfc->dfc_capture_ip = capture_ip;
+ for (i = 0; i < dfc->dfc_held.dr_inos; i++) {
+ ASSERT(xfs_isilocked(dfc->dfc_held.dr_ip[i], XFS_ILOCK_EXCL));
+ ihold(VFS_I(dfc->dfc_held.dr_ip[i]));
}
+ for (i = 0; i < dfc->dfc_held.dr_bufs; i++)
+ xfs_buf_hold(dfc->dfc_held.dr_bp[i]);
+
return dfc;
}
/* Release all resources that we used to capture deferred ops. */
void
-xfs_defer_ops_release(
+xfs_defer_ops_capture_free(
struct xfs_mount *mp,
struct xfs_defer_capture *dfc)
{
+ unsigned short i;
+
xfs_defer_cancel_list(mp, &dfc->dfc_dfops);
- if (dfc->dfc_capture_ip)
- xfs_irele(dfc->dfc_capture_ip);
+
+ for (i = 0; i < dfc->dfc_held.dr_bufs; i++)
+ xfs_buf_relse(dfc->dfc_held.dr_bp[i]);
+
+ for (i = 0; i < dfc->dfc_held.dr_inos; i++)
+ xfs_irele(dfc->dfc_held.dr_ip[i]);
+
kmem_free(dfc);
}
@@ -689,24 +740,21 @@ xfs_defer_ops_release(
int
xfs_defer_ops_capture_and_commit(
struct xfs_trans *tp,
- struct xfs_inode *capture_ip,
struct list_head *capture_list)
{
struct xfs_mount *mp = tp->t_mountp;
struct xfs_defer_capture *dfc;
int error;
- ASSERT(!capture_ip || xfs_isilocked(capture_ip, XFS_ILOCK_EXCL));
-
/* If we don't capture anything, commit transaction and exit. */
- dfc = xfs_defer_ops_capture(tp, capture_ip);
+ dfc = xfs_defer_ops_capture(tp);
if (!dfc)
return xfs_trans_commit(tp);
/* Commit the transaction and add the capture structure to the list. */
error = xfs_trans_commit(tp);
if (error) {
- xfs_defer_ops_release(mp, dfc);
+ xfs_defer_ops_capture_free(mp, dfc);
return error;
}
@@ -724,17 +772,19 @@ void
xfs_defer_ops_continue(
struct xfs_defer_capture *dfc,
struct xfs_trans *tp,
- struct xfs_inode **captured_ipp)
+ struct xfs_defer_resources *dres)
{
ASSERT(tp->t_flags & XFS_TRANS_PERM_LOG_RES);
ASSERT(!(tp->t_flags & XFS_TRANS_DIRTY));
/* Lock and join the captured inode to the new transaction. */
- if (dfc->dfc_capture_ip) {
- xfs_ilock(dfc->dfc_capture_ip, XFS_ILOCK_EXCL);
- xfs_trans_ijoin(tp, dfc->dfc_capture_ip, 0);
- }
- *captured_ipp = dfc->dfc_capture_ip;
+ if (dfc->dfc_held.dr_inos == 2)
+ xfs_lock_two_inodes(dfc->dfc_held.dr_ip[0], XFS_ILOCK_EXCL,
+ dfc->dfc_held.dr_ip[1], XFS_ILOCK_EXCL);
+ else if (dfc->dfc_held.dr_inos == 1)
+ xfs_ilock(dfc->dfc_held.dr_ip[0], XFS_ILOCK_EXCL);
+ xfs_defer_restore_resources(tp, &dfc->dfc_held);
+ memcpy(dres, &dfc->dfc_held, sizeof(struct xfs_defer_resources));
/* Move captured dfops chain and state to the transaction. */
list_splice_init(&dfc->dfc_dfops, &tp->t_dfops);
@@ -742,3 +792,82 @@ xfs_defer_ops_continue(
kmem_free(dfc);
}
+
+/* Release the resources captured and continued during recovery. */
+void
+xfs_defer_resources_rele(
+ struct xfs_defer_resources *dres)
+{
+ unsigned short i;
+
+ for (i = 0; i < dres->dr_inos; i++) {
+ xfs_iunlock(dres->dr_ip[i], XFS_ILOCK_EXCL);
+ xfs_irele(dres->dr_ip[i]);
+ dres->dr_ip[i] = NULL;
+ }
+
+ for (i = 0; i < dres->dr_bufs; i++) {
+ xfs_buf_relse(dres->dr_bp[i]);
+ dres->dr_bp[i] = NULL;
+ }
+
+ dres->dr_inos = 0;
+ dres->dr_bufs = 0;
+ dres->dr_ordered = 0;
+}
+
+static inline int __init
+xfs_defer_init_cache(void)
+{
+ xfs_defer_pending_cache = kmem_cache_create("xfs_defer_pending",
+ sizeof(struct xfs_defer_pending),
+ 0, 0, NULL);
+
+ return xfs_defer_pending_cache != NULL ? 0 : -ENOMEM;
+}
+
+static inline void
+xfs_defer_destroy_cache(void)
+{
+ kmem_cache_destroy(xfs_defer_pending_cache);
+ xfs_defer_pending_cache = NULL;
+}
+
+/* Set up caches for deferred work items. */
+int __init
+xfs_defer_init_item_caches(void)
+{
+ int error;
+
+ error = xfs_defer_init_cache();
+ if (error)
+ return error;
+ error = xfs_rmap_intent_init_cache();
+ if (error)
+ goto err;
+ error = xfs_refcount_intent_init_cache();
+ if (error)
+ goto err;
+ error = xfs_bmap_intent_init_cache();
+ if (error)
+ goto err;
+ error = xfs_extfree_intent_init_cache();
+ if (error)
+ goto err;
+
+ return 0;
+err:
+ xfs_defer_destroy_item_caches();
+ return error;
+}
+
+/* Destroy all the deferred work item caches, if they've been allocated. */
+void
+xfs_defer_destroy_item_caches(void)
+{
+ xfs_extfree_intent_destroy_cache();
+ xfs_bmap_intent_destroy_cache();
+ xfs_refcount_intent_destroy_cache();
+ xfs_rmap_intent_destroy_cache();
+ xfs_defer_destroy_cache();
+}
diff --git a/fs/xfs/libxfs/xfs_defer.h b/fs/xfs/libxfs/xfs_defer.h
index 05472f71fffe..7bb8a31ad65b 100644
--- a/fs/xfs/libxfs/xfs_defer.h
+++ b/fs/xfs/libxfs/xfs_defer.h
@@ -65,6 +65,30 @@ extern const struct xfs_defer_op_type xfs_extent_free_defer_type;
extern const struct xfs_defer_op_type xfs_agfl_free_defer_type;
/*
+ * Deferred operation item relogging limits.
+ */
+#define XFS_DEFER_OPS_NR_INODES 2 /* join up to two inodes */
+#define XFS_DEFER_OPS_NR_BUFS 2 /* join up to two buffers */
+
+/* Resources that must be held across a transaction roll. */
+struct xfs_defer_resources {
+ /* held buffers */
+ struct xfs_buf *dr_bp[XFS_DEFER_OPS_NR_BUFS];
+
+ /* inodes with no unlock flags */
+ struct xfs_inode *dr_ip[XFS_DEFER_OPS_NR_INODES];
+
+ /* number of held buffers */
+ unsigned short dr_bufs;
+
+ /* bitmap of ordered buffers */
+ unsigned short dr_ordered;
+
+ /* number of held inodes */
+ unsigned short dr_inos;
+};
+
+/*
* This structure enables a dfops user to detach the chain of deferred
* operations from a transaction so that they can be continued later.
*/
@@ -83,11 +107,7 @@ struct xfs_defer_capture {
/* Log reservation saved from the transaction. */
unsigned int dfc_logres;
- /*
- * An inode reference that must be maintained to complete the deferred
- * work.
- */
- struct xfs_inode *dfc_capture_ip;
+ struct xfs_defer_resources dfc_held;
};
/*
@@ -95,9 +115,14 @@ struct xfs_defer_capture {
* This doesn't normally happen except log recovery.
*/
int xfs_defer_ops_capture_and_commit(struct xfs_trans *tp,
- struct xfs_inode *capture_ip, struct list_head *capture_list);
+ struct list_head *capture_list);
void xfs_defer_ops_continue(struct xfs_defer_capture *d, struct xfs_trans *tp,
- struct xfs_inode **captured_ipp);
-void xfs_defer_ops_release(struct xfs_mount *mp, struct xfs_defer_capture *d);
+ struct xfs_defer_resources *dres);
+void xfs_defer_ops_capture_free(struct xfs_mount *mp,
+ struct xfs_defer_capture *d);
+void xfs_defer_resources_rele(struct xfs_defer_resources *dres);
+
+int __init xfs_defer_init_item_caches(void);
+void xfs_defer_destroy_item_caches(void);
#endif /* __XFS_DEFER_H__ */
diff --git a/fs/xfs/libxfs/xfs_dquot_buf.c b/fs/xfs/libxfs/xfs_dquot_buf.c
index deeb74becabc..15a362e2f5ea 100644
--- a/fs/xfs/libxfs/xfs_dquot_buf.c
+++ b/fs/xfs/libxfs/xfs_dquot_buf.c
@@ -22,7 +22,7 @@ xfs_calc_dquots_per_chunk(
unsigned int nbblks) /* basic block units */
{
ASSERT(nbblks > 0);
- return BBTOB(nbblks) / sizeof(xfs_dqblk_t);
+ return BBTOB(nbblks) / sizeof(struct xfs_dqblk);
}
/*
@@ -127,7 +127,7 @@ xfs_dqblk_repair(
* Typically, a repair is only requested by quotacheck.
*/
ASSERT(id != -1);
- memset(dqb, 0, sizeof(xfs_dqblk_t));
+ memset(dqb, 0, sizeof(struct xfs_dqblk));
dqb->dd_diskdq.d_magic = cpu_to_be16(XFS_DQUOT_MAGIC);
dqb->dd_diskdq.d_version = XFS_DQUOT_VERSION;
diff --git a/fs/xfs/libxfs/xfs_format.h b/fs/xfs/libxfs/xfs_format.h
index 2d7057b7984b..d665c04e69dd 100644
--- a/fs/xfs/libxfs/xfs_format.h
+++ b/fs/xfs/libxfs/xfs_format.h
@@ -184,7 +184,7 @@ typedef struct xfs_sb {
* Superblock - on disk version. Must match the in core version above.
* Must be padded to 64 bit alignment.
*/
-typedef struct xfs_dsb {
+struct xfs_dsb {
__be32 sb_magicnum; /* magic number == XFS_SB_MAGIC */
__be32 sb_blocksize; /* logical block size, bytes */
__be64 sb_dblocks; /* number of data blocks */
@@ -263,7 +263,7 @@ typedef struct xfs_dsb {
uuid_t sb_meta_uuid; /* metadata file system unique id */
/* must be padded to 64 bit alignment */
-} xfs_dsb_t;
+};
/*
* Misc. Flags - warning - these will be cleared by xfs_repair unless
@@ -780,7 +780,7 @@ static inline time64_t xfs_bigtime_to_unix(uint64_t ondisk_seconds)
* padding field for v3 inodes.
*/
#define XFS_DINODE_MAGIC 0x494e /* 'IN' */
-typedef struct xfs_dinode {
+struct xfs_dinode {
__be16 di_magic; /* inode magic # = XFS_DINODE_MAGIC */
__be16 di_mode; /* mode and type of file */
__u8 di_version; /* inode version */
@@ -825,7 +825,7 @@ typedef struct xfs_dinode {
uuid_t di_uuid; /* UUID of the filesystem */
/* structure must be padded to 64 bit alignment */
-} xfs_dinode_t;
+};
#define XFS_DINODE_CRC_OFF offsetof(struct xfs_dinode, di_crc)
@@ -1215,7 +1215,7 @@ struct xfs_disk_dquot {
* This is what goes on disk. This is separated from the xfs_disk_dquot because
* carrying the unnecessary padding would be a waste of memory.
*/
-typedef struct xfs_dqblk {
+struct xfs_dqblk {
struct xfs_disk_dquot dd_diskdq; /* portion living incore as well */
char dd_fill[4];/* filling for posterity */
@@ -1225,7 +1225,7 @@ typedef struct xfs_dqblk {
__be32 dd_crc; /* checksum */
__be64 dd_lsn; /* last modification in log */
uuid_t dd_uuid; /* location information */
-} xfs_dqblk_t;
+};
#define XFS_DQUOT_CRC_OFF offsetof(struct xfs_dqblk, dd_crc)
diff --git a/fs/xfs/libxfs/xfs_fs.h b/fs/xfs/libxfs/xfs_fs.h
index bde2b4c64dbe..c43877c8a279 100644
--- a/fs/xfs/libxfs/xfs_fs.h
+++ b/fs/xfs/libxfs/xfs_fs.h
@@ -268,6 +268,8 @@ typedef struct xfs_fsop_resblks {
*/
#define XFS_MIN_AG_BYTES (1ULL << 24) /* 16 MB */
#define XFS_MAX_AG_BYTES (1ULL << 40) /* 1 TB */
+#define XFS_MAX_AG_BLOCKS (XFS_MAX_AG_BYTES / XFS_MIN_BLOCKSIZE)
+#define XFS_MAX_CRC_AG_BLOCKS (XFS_MAX_AG_BYTES / XFS_MIN_CRC_BLOCKSIZE)
/* keep the maximum size under 2^31 by a small amount */
#define XFS_MAX_LOG_BYTES \
diff --git a/fs/xfs/libxfs/xfs_ialloc.c b/fs/xfs/libxfs/xfs_ialloc.c
index 994ad783d407..b418fe0c0679 100644
--- a/fs/xfs/libxfs/xfs_ialloc.c
+++ b/fs/xfs/libxfs/xfs_ialloc.c
@@ -1827,7 +1827,7 @@ xfs_difree_inode_chunk(
if (!xfs_inobt_issparse(rec->ir_holemask)) {
/* not sparse, calculate extent info directly */
- xfs_bmap_add_free(tp, XFS_AGB_TO_FSB(mp, agno, sagbno),
+ xfs_free_extent_later(tp, XFS_AGB_TO_FSB(mp, agno, sagbno),
M_IGEO(mp)->ialloc_blks,
&XFS_RMAP_OINFO_INODES);
return;
@@ -1872,7 +1872,7 @@ xfs_difree_inode_chunk(
ASSERT(agbno % mp->m_sb.sb_spino_align == 0);
ASSERT(contigblk % mp->m_sb.sb_spino_align == 0);
- xfs_bmap_add_free(tp, XFS_AGB_TO_FSB(mp, agno, agbno),
+ xfs_free_extent_later(tp, XFS_AGB_TO_FSB(mp, agno, agbno),
contigblk, &XFS_RMAP_OINFO_INODES);
/* reset range to current bit and carry on... */
@@ -2793,6 +2793,7 @@ xfs_ialloc_setup_geometry(
inodes = (1LL << XFS_INO_AGINO_BITS(mp)) >> XFS_INODES_PER_CHUNK_LOG;
igeo->inobt_maxlevels = xfs_btree_compute_maxlevels(igeo->inobt_mnr,
inodes);
+ ASSERT(igeo->inobt_maxlevels <= xfs_iallocbt_maxlevels_ondisk());
/*
* Set the maximum inode count for this filesystem, being careful not
diff --git a/fs/xfs/libxfs/xfs_ialloc_btree.c b/fs/xfs/libxfs/xfs_ialloc_btree.c
index 27190840c5d8..b2ad2fdc40f5 100644
--- a/fs/xfs/libxfs/xfs_ialloc_btree.c
+++ b/fs/xfs/libxfs/xfs_ialloc_btree.c
@@ -22,6 +22,8 @@
#include "xfs_rmap.h"
#include "xfs_ag.h"
+static struct kmem_cache *xfs_inobt_cur_cache;
+
STATIC int
xfs_inobt_get_minrecs(
struct xfs_btree_cur *cur,
@@ -432,10 +434,8 @@ xfs_inobt_init_common(
{
struct xfs_btree_cur *cur;
- cur = kmem_cache_zalloc(xfs_btree_cur_zone, GFP_NOFS | __GFP_NOFAIL);
- cur->bc_tp = tp;
- cur->bc_mp = mp;
- cur->bc_btnum = btnum;
+ cur = xfs_btree_alloc_cursor(mp, tp, btnum,
+ M_IGEO(mp)->inobt_maxlevels, xfs_inobt_cur_cache);
if (btnum == XFS_BTNUM_INO) {
cur->bc_statoff = XFS_STATS_CALC_INDEX(xs_ibt_2);
cur->bc_ops = &xfs_inobt_ops;
@@ -444,8 +444,6 @@ xfs_inobt_init_common(
cur->bc_ops = &xfs_finobt_ops;
}
- cur->bc_blocklog = mp->m_sb.sb_blocklog;
-
if (xfs_has_crc(mp))
cur->bc_flags |= XFS_BTREE_CRC_BLOCKS;
@@ -530,6 +528,17 @@ xfs_inobt_commit_staged_btree(
}
}
+/* Calculate number of records in an inode btree block. */
+static inline unsigned int
+xfs_inobt_block_maxrecs(
+ unsigned int blocklen,
+ bool leaf)
+{
+ if (leaf)
+ return blocklen / sizeof(xfs_inobt_rec_t);
+ return blocklen / (sizeof(xfs_inobt_key_t) + sizeof(xfs_inobt_ptr_t));
+}
+
/*
* Calculate number of records in an inobt btree block.
*/
@@ -540,10 +549,54 @@ xfs_inobt_maxrecs(
int leaf)
{
blocklen -= XFS_INOBT_BLOCK_LEN(mp);
+ return xfs_inobt_block_maxrecs(blocklen, leaf);
+}
- if (leaf)
- return blocklen / sizeof(xfs_inobt_rec_t);
- return blocklen / (sizeof(xfs_inobt_key_t) + sizeof(xfs_inobt_ptr_t));
+/*
+ * Maximum number of inode btree records per AG. Pretend that we can fill an
+ * entire AG completely full of inodes except for the AG headers.
+ */
+#define XFS_MAX_INODE_RECORDS \
+ ((XFS_MAX_AG_BYTES - (4 * BBSIZE)) / XFS_DINODE_MIN_SIZE) / \
+ XFS_INODES_PER_CHUNK
+
+/* Compute the max possible height for the inode btree. */
+static inline unsigned int
+xfs_inobt_maxlevels_ondisk(void)
+{
+ unsigned int minrecs[2];
+ unsigned int blocklen;
+
+ blocklen = min(XFS_MIN_BLOCKSIZE - XFS_BTREE_SBLOCK_LEN,
+ XFS_MIN_CRC_BLOCKSIZE - XFS_BTREE_SBLOCK_CRC_LEN);
+
+ minrecs[0] = xfs_inobt_block_maxrecs(blocklen, true) / 2;
+ minrecs[1] = xfs_inobt_block_maxrecs(blocklen, false) / 2;
+
+ return xfs_btree_compute_maxlevels(minrecs, XFS_MAX_INODE_RECORDS);
+}
+
+/* Compute the max possible height for the free inode btree. */
+static inline unsigned int
+xfs_finobt_maxlevels_ondisk(void)
+{
+ unsigned int minrecs[2];
+ unsigned int blocklen;
+
+ blocklen = XFS_MIN_CRC_BLOCKSIZE - XFS_BTREE_SBLOCK_CRC_LEN;
+
+ minrecs[0] = xfs_inobt_block_maxrecs(blocklen, true) / 2;
+ minrecs[1] = xfs_inobt_block_maxrecs(blocklen, false) / 2;
+
+ return xfs_btree_compute_maxlevels(minrecs, XFS_MAX_INODE_RECORDS);
+}
+
+/* Compute the max possible height for either inode btree. */
+unsigned int
+xfs_iallocbt_maxlevels_ondisk(void)
+{
+ return max(xfs_inobt_maxlevels_ondisk(),
+ xfs_finobt_maxlevels_ondisk());
}
/*
@@ -761,3 +814,22 @@ xfs_iallocbt_calc_size(
{
return xfs_btree_calc_size(M_IGEO(mp)->inobt_mnr, len);
}
+
+int __init
+xfs_inobt_init_cur_cache(void)
+{
+ xfs_inobt_cur_cache = kmem_cache_create("xfs_inobt_cur",
+ xfs_btree_cur_sizeof(xfs_inobt_maxlevels_ondisk()),
+ 0, 0, NULL);
+
+ if (!xfs_inobt_cur_cache)
+ return -ENOMEM;
+ return 0;
+}
+
+void
+xfs_inobt_destroy_cur_cache(void)
+{
+ kmem_cache_destroy(xfs_inobt_cur_cache);
+ xfs_inobt_cur_cache = NULL;
+}
diff --git a/fs/xfs/libxfs/xfs_ialloc_btree.h b/fs/xfs/libxfs/xfs_ialloc_btree.h
index 8a322d402e61..26451cb76b98 100644
--- a/fs/xfs/libxfs/xfs_ialloc_btree.h
+++ b/fs/xfs/libxfs/xfs_ialloc_btree.h
@@ -75,4 +75,9 @@ int xfs_inobt_cur(struct xfs_mount *mp, struct xfs_trans *tp,
void xfs_inobt_commit_staged_btree(struct xfs_btree_cur *cur,
struct xfs_trans *tp, struct xfs_buf *agbp);
+unsigned int xfs_iallocbt_maxlevels_ondisk(void);
+
+int __init xfs_inobt_init_cur_cache(void);
+void xfs_inobt_destroy_cur_cache(void);
+
#endif /* __XFS_IALLOC_BTREE_H__ */
diff --git a/fs/xfs/libxfs/xfs_inode_buf.c b/fs/xfs/libxfs/xfs_inode_buf.c
index 3932b4ebf903..cae9708c8587 100644
--- a/fs/xfs/libxfs/xfs_inode_buf.c
+++ b/fs/xfs/libxfs/xfs_inode_buf.c
@@ -51,9 +51,9 @@ xfs_inode_buf_verify(
agno = xfs_daddr_to_agno(mp, xfs_buf_daddr(bp));
ni = XFS_BB_TO_FSB(mp, bp->b_length) * mp->m_sb.sb_inopblock;
for (i = 0; i < ni; i++) {
- int di_ok;
- xfs_dinode_t *dip;
- xfs_agino_t unlinked_ino;
+ struct xfs_dinode *dip;
+ xfs_agino_t unlinked_ino;
+ int di_ok;
dip = xfs_buf_offset(bp, (i << mp->m_sb.sb_inodelog));
unlinked_ino = be32_to_cpu(dip->di_next_unlinked);
diff --git a/fs/xfs/libxfs/xfs_inode_fork.c b/fs/xfs/libxfs/xfs_inode_fork.c
index 1d174909f9bd..9149f4f796fc 100644
--- a/fs/xfs/libxfs/xfs_inode_fork.c
+++ b/fs/xfs/libxfs/xfs_inode_fork.c
@@ -26,7 +26,7 @@
#include "xfs_types.h"
#include "xfs_errortag.h"
-kmem_zone_t *xfs_ifork_zone;
+struct kmem_cache *xfs_ifork_cache;
void
xfs_init_local_fork(
@@ -67,10 +67,10 @@ xfs_init_local_fork(
*/
STATIC int
xfs_iformat_local(
- xfs_inode_t *ip,
- xfs_dinode_t *dip,
- int whichfork,
- int size)
+ struct xfs_inode *ip,
+ struct xfs_dinode *dip,
+ int whichfork,
+ int size)
{
/*
* If the size is unreasonable, then something
@@ -162,8 +162,8 @@ xfs_iformat_extents(
*/
STATIC int
xfs_iformat_btree(
- xfs_inode_t *ip,
- xfs_dinode_t *dip,
+ struct xfs_inode *ip,
+ struct xfs_dinode *dip,
int whichfork)
{
struct xfs_mount *mp = ip->i_mount;
@@ -284,7 +284,7 @@ xfs_ifork_alloc(
{
struct xfs_ifork *ifp;
- ifp = kmem_cache_zalloc(xfs_ifork_zone, GFP_NOFS | __GFP_NOFAIL);
+ ifp = kmem_cache_zalloc(xfs_ifork_cache, GFP_NOFS | __GFP_NOFAIL);
ifp->if_format = format;
ifp->if_nextents = nextents;
return ifp;
@@ -325,7 +325,7 @@ xfs_iformat_attr_fork(
}
if (error) {
- kmem_cache_free(xfs_ifork_zone, ip->i_afp);
+ kmem_cache_free(xfs_ifork_cache, ip->i_afp);
ip->i_afp = NULL;
}
return error;
@@ -580,8 +580,8 @@ xfs_iextents_copy(
*/
void
xfs_iflush_fork(
- xfs_inode_t *ip,
- xfs_dinode_t *dip,
+ struct xfs_inode *ip,
+ struct xfs_dinode *dip,
struct xfs_inode_log_item *iip,
int whichfork)
{
@@ -676,7 +676,7 @@ xfs_ifork_init_cow(
if (ip->i_cowfp)
return;
- ip->i_cowfp = kmem_cache_zalloc(xfs_ifork_zone,
+ ip->i_cowfp = kmem_cache_zalloc(xfs_ifork_cache,
GFP_NOFS | __GFP_NOFAIL);
ip->i_cowfp->if_format = XFS_DINODE_FMT_EXTENTS;
}
diff --git a/fs/xfs/libxfs/xfs_inode_fork.h b/fs/xfs/libxfs/xfs_inode_fork.h
index a6f7897b6887..3d64a3acb0ed 100644
--- a/fs/xfs/libxfs/xfs_inode_fork.h
+++ b/fs/xfs/libxfs/xfs_inode_fork.h
@@ -221,7 +221,7 @@ static inline bool xfs_iext_peek_prev_extent(struct xfs_ifork *ifp,
xfs_iext_get_extent((ifp), (ext), (got)); \
xfs_iext_next((ifp), (ext)))
-extern struct kmem_zone *xfs_ifork_zone;
+extern struct kmem_cache *xfs_ifork_cache;
extern void xfs_ifork_init_cow(struct xfs_inode *ip);
diff --git a/fs/xfs/libxfs/xfs_refcount.c b/fs/xfs/libxfs/xfs_refcount.c
index e5d767a7fc5d..327ba25e9e17 100644
--- a/fs/xfs/libxfs/xfs_refcount.c
+++ b/fs/xfs/libxfs/xfs_refcount.c
@@ -24,6 +24,8 @@
#include "xfs_rmap.h"
#include "xfs_ag.h"
+struct kmem_cache *xfs_refcount_intent_cache;
+
/* Allowable refcount adjustment amounts. */
enum xfs_refc_adjust_op {
XFS_REFCOUNT_ADJUST_INCREASE = 1,
@@ -916,8 +918,7 @@ xfs_refcount_adjust_extents(
struct xfs_btree_cur *cur,
xfs_agblock_t *agbno,
xfs_extlen_t *aglen,
- enum xfs_refc_adjust_op adj,
- struct xfs_owner_info *oinfo)
+ enum xfs_refc_adjust_op adj)
{
struct xfs_refcount_irec ext, tmp;
int error;
@@ -974,8 +975,8 @@ xfs_refcount_adjust_extents(
fsbno = XFS_AGB_TO_FSB(cur->bc_mp,
cur->bc_ag.pag->pag_agno,
tmp.rc_startblock);
- xfs_bmap_add_free(cur->bc_tp, fsbno,
- tmp.rc_blockcount, oinfo);
+ xfs_free_extent_later(cur->bc_tp, fsbno,
+ tmp.rc_blockcount, NULL);
}
(*agbno) += tmp.rc_blockcount;
@@ -1019,8 +1020,8 @@ xfs_refcount_adjust_extents(
fsbno = XFS_AGB_TO_FSB(cur->bc_mp,
cur->bc_ag.pag->pag_agno,
ext.rc_startblock);
- xfs_bmap_add_free(cur->bc_tp, fsbno, ext.rc_blockcount,
- oinfo);
+ xfs_free_extent_later(cur->bc_tp, fsbno,
+ ext.rc_blockcount, NULL);
}
skip:
@@ -1048,8 +1049,7 @@ xfs_refcount_adjust(
xfs_extlen_t aglen,
xfs_agblock_t *new_agbno,
xfs_extlen_t *new_aglen,
- enum xfs_refc_adjust_op adj,
- struct xfs_owner_info *oinfo)
+ enum xfs_refc_adjust_op adj)
{
bool shape_changed;
int shape_changes = 0;
@@ -1092,8 +1092,7 @@ xfs_refcount_adjust(
cur->bc_ag.refc.shape_changes++;
/* Now that we've taken care of the ends, adjust the middle extents */
- error = xfs_refcount_adjust_extents(cur, new_agbno, new_aglen,
- adj, oinfo);
+ error = xfs_refcount_adjust_extents(cur, new_agbno, new_aglen, adj);
if (error)
goto out_error;
@@ -1188,12 +1187,12 @@ xfs_refcount_finish_one(
switch (type) {
case XFS_REFCOUNT_INCREASE:
error = xfs_refcount_adjust(rcur, bno, blockcount, &new_agbno,
- new_len, XFS_REFCOUNT_ADJUST_INCREASE, NULL);
+ new_len, XFS_REFCOUNT_ADJUST_INCREASE);
*new_fsb = XFS_AGB_TO_FSB(mp, pag->pag_agno, new_agbno);
break;
case XFS_REFCOUNT_DECREASE:
error = xfs_refcount_adjust(rcur, bno, blockcount, &new_agbno,
- new_len, XFS_REFCOUNT_ADJUST_DECREASE, NULL);
+ new_len, XFS_REFCOUNT_ADJUST_DECREASE);
*new_fsb = XFS_AGB_TO_FSB(mp, pag->pag_agno, new_agbno);
break;
case XFS_REFCOUNT_ALLOC_COW:
@@ -1235,8 +1234,8 @@ __xfs_refcount_add(
type, XFS_FSB_TO_AGBNO(tp->t_mountp, startblock),
blockcount);
- ri = kmem_alloc(sizeof(struct xfs_refcount_intent),
- KM_NOFS);
+ ri = kmem_cache_alloc(xfs_refcount_intent_cache,
+ GFP_NOFS | __GFP_NOFAIL);
INIT_LIST_HEAD(&ri->ri_list);
ri->ri_type = type;
ri->ri_startblock = startblock;
@@ -1742,7 +1741,7 @@ xfs_refcount_recover_cow_leftovers(
rr->rr_rrec.rc_blockcount);
/* Free the block. */
- xfs_bmap_add_free(tp, fsb, rr->rr_rrec.rc_blockcount, NULL);
+ xfs_free_extent_later(tp, fsb, rr->rr_rrec.rc_blockcount, NULL);
error = xfs_trans_commit(tp);
if (error)
@@ -1782,3 +1781,20 @@ xfs_refcount_has_record(
return xfs_btree_has_record(cur, &low, &high, exists);
}
+
+int __init
+xfs_refcount_intent_init_cache(void)
+{
+ xfs_refcount_intent_cache = kmem_cache_create("xfs_refc_intent",
+ sizeof(struct xfs_refcount_intent),
+ 0, 0, NULL);
+
+ return xfs_refcount_intent_cache != NULL ? 0 : -ENOMEM;
+}
+
+void
+xfs_refcount_intent_destroy_cache(void)
+{
+ kmem_cache_destroy(xfs_refcount_intent_cache);
+ xfs_refcount_intent_cache = NULL;
+}
diff --git a/fs/xfs/libxfs/xfs_refcount.h b/fs/xfs/libxfs/xfs_refcount.h
index 02cb3aa405be..9eb01edbd89d 100644
--- a/fs/xfs/libxfs/xfs_refcount.h
+++ b/fs/xfs/libxfs/xfs_refcount.h
@@ -32,8 +32,8 @@ enum xfs_refcount_intent_type {
struct xfs_refcount_intent {
struct list_head ri_list;
enum xfs_refcount_intent_type ri_type;
- xfs_fsblock_t ri_startblock;
xfs_extlen_t ri_blockcount;
+ xfs_fsblock_t ri_startblock;
};
void xfs_refcount_increase_extent(struct xfs_trans *tp,
@@ -83,4 +83,9 @@ extern void xfs_refcount_btrec_to_irec(const union xfs_btree_rec *rec,
extern int xfs_refcount_insert(struct xfs_btree_cur *cur,
struct xfs_refcount_irec *irec, int *stat);
+extern struct kmem_cache *xfs_refcount_intent_cache;
+
+int __init xfs_refcount_intent_init_cache(void);
+void xfs_refcount_intent_destroy_cache(void);
+
#endif /* __XFS_REFCOUNT_H__ */
diff --git a/fs/xfs/libxfs/xfs_refcount_btree.c b/fs/xfs/libxfs/xfs_refcount_btree.c
index 1ef9b99962ab..d14c1720b0fb 100644
--- a/fs/xfs/libxfs/xfs_refcount_btree.c
+++ b/fs/xfs/libxfs/xfs_refcount_btree.c
@@ -21,6 +21,8 @@
#include "xfs_rmap.h"
#include "xfs_ag.h"
+static struct kmem_cache *xfs_refcountbt_cur_cache;
+
static struct xfs_btree_cur *
xfs_refcountbt_dup_cursor(
struct xfs_btree_cur *cur)
@@ -322,11 +324,8 @@ xfs_refcountbt_init_common(
ASSERT(pag->pag_agno < mp->m_sb.sb_agcount);
- cur = kmem_cache_zalloc(xfs_btree_cur_zone, GFP_NOFS | __GFP_NOFAIL);
- cur->bc_tp = tp;
- cur->bc_mp = mp;
- cur->bc_btnum = XFS_BTNUM_REFC;
- cur->bc_blocklog = mp->m_sb.sb_blocklog;
+ cur = xfs_btree_alloc_cursor(mp, tp, XFS_BTNUM_REFC,
+ mp->m_refc_maxlevels, xfs_refcountbt_cur_cache);
cur->bc_statoff = XFS_STATS_CALC_INDEX(xs_refcbt_2);
cur->bc_flags |= XFS_BTREE_CRC_BLOCKS;
@@ -396,6 +395,18 @@ xfs_refcountbt_commit_staged_btree(
xfs_btree_commit_afakeroot(cur, tp, agbp, &xfs_refcountbt_ops);
}
+/* Calculate number of records in a refcount btree block. */
+static inline unsigned int
+xfs_refcountbt_block_maxrecs(
+ unsigned int blocklen,
+ bool leaf)
+{
+ if (leaf)
+ return blocklen / sizeof(struct xfs_refcount_rec);
+ return blocklen / (sizeof(struct xfs_refcount_key) +
+ sizeof(xfs_refcount_ptr_t));
+}
+
/*
* Calculate the number of records in a refcount btree block.
*/
@@ -405,11 +416,22 @@ xfs_refcountbt_maxrecs(
bool leaf)
{
blocklen -= XFS_REFCOUNT_BLOCK_LEN;
+ return xfs_refcountbt_block_maxrecs(blocklen, leaf);
+}
- if (leaf)
- return blocklen / sizeof(struct xfs_refcount_rec);
- return blocklen / (sizeof(struct xfs_refcount_key) +
- sizeof(xfs_refcount_ptr_t));
+/* Compute the max possible height of the maximally sized refcount btree. */
+unsigned int
+xfs_refcountbt_maxlevels_ondisk(void)
+{
+ unsigned int minrecs[2];
+ unsigned int blocklen;
+
+ blocklen = XFS_MIN_CRC_BLOCKSIZE - XFS_BTREE_SBLOCK_CRC_LEN;
+
+ minrecs[0] = xfs_refcountbt_block_maxrecs(blocklen, true) / 2;
+ minrecs[1] = xfs_refcountbt_block_maxrecs(blocklen, false) / 2;
+
+ return xfs_btree_compute_maxlevels(minrecs, XFS_MAX_CRC_AG_BLOCKS);
}
/* Compute the maximum height of a refcount btree. */
@@ -417,8 +439,14 @@ void
xfs_refcountbt_compute_maxlevels(
struct xfs_mount *mp)
{
+ if (!xfs_has_reflink(mp)) {
+ mp->m_refc_maxlevels = 0;
+ return;
+ }
+
mp->m_refc_maxlevels = xfs_btree_compute_maxlevels(
mp->m_refc_mnr, mp->m_sb.sb_agblocks);
+ ASSERT(mp->m_refc_maxlevels <= xfs_refcountbt_maxlevels_ondisk());
}
/* Calculate the refcount btree size for some records. */
@@ -488,3 +516,22 @@ xfs_refcountbt_calc_reserves(
return error;
}
+
+int __init
+xfs_refcountbt_init_cur_cache(void)
+{
+ xfs_refcountbt_cur_cache = kmem_cache_create("xfs_refcbt_cur",
+ xfs_btree_cur_sizeof(xfs_refcountbt_maxlevels_ondisk()),
+ 0, 0, NULL);
+
+ if (!xfs_refcountbt_cur_cache)
+ return -ENOMEM;
+ return 0;
+}
+
+void
+xfs_refcountbt_destroy_cur_cache(void)
+{
+ kmem_cache_destroy(xfs_refcountbt_cur_cache);
+ xfs_refcountbt_cur_cache = NULL;
+}
diff --git a/fs/xfs/libxfs/xfs_refcount_btree.h b/fs/xfs/libxfs/xfs_refcount_btree.h
index bd9ed9e1e41f..d66b37259bed 100644
--- a/fs/xfs/libxfs/xfs_refcount_btree.h
+++ b/fs/xfs/libxfs/xfs_refcount_btree.h
@@ -65,4 +65,9 @@ extern int xfs_refcountbt_calc_reserves(struct xfs_mount *mp,
void xfs_refcountbt_commit_staged_btree(struct xfs_btree_cur *cur,
struct xfs_trans *tp, struct xfs_buf *agbp);
+unsigned int xfs_refcountbt_maxlevels_ondisk(void);
+
+int __init xfs_refcountbt_init_cur_cache(void);
+void xfs_refcountbt_destroy_cur_cache(void);
+
#endif /* __XFS_REFCOUNT_BTREE_H__ */
diff --git a/fs/xfs/libxfs/xfs_rmap.c b/fs/xfs/libxfs/xfs_rmap.c
index f45929b1b94a..cd322174dbff 100644
--- a/fs/xfs/libxfs/xfs_rmap.c
+++ b/fs/xfs/libxfs/xfs_rmap.c
@@ -24,6 +24,8 @@
#include "xfs_inode.h"
#include "xfs_ag.h"
+struct kmem_cache *xfs_rmap_intent_cache;
+
/*
* Lookup the first record less than or equal to [bno, len, owner, offset]
* in the btree given by cur.
@@ -2485,7 +2487,7 @@ __xfs_rmap_add(
bmap->br_blockcount,
bmap->br_state);
- ri = kmem_alloc(sizeof(struct xfs_rmap_intent), KM_NOFS);
+ ri = kmem_cache_alloc(xfs_rmap_intent_cache, GFP_NOFS | __GFP_NOFAIL);
INIT_LIST_HEAD(&ri->ri_list);
ri->ri_type = type;
ri->ri_owner = owner;
@@ -2779,3 +2781,20 @@ const struct xfs_owner_info XFS_RMAP_OINFO_REFC = {
const struct xfs_owner_info XFS_RMAP_OINFO_COW = {
.oi_owner = XFS_RMAP_OWN_COW,
};
+
+int __init
+xfs_rmap_intent_init_cache(void)
+{
+ xfs_rmap_intent_cache = kmem_cache_create("xfs_rmap_intent",
+ sizeof(struct xfs_rmap_intent),
+ 0, 0, NULL);
+
+ return xfs_rmap_intent_cache != NULL ? 0 : -ENOMEM;
+}
+
+void
+xfs_rmap_intent_destroy_cache(void)
+{
+ kmem_cache_destroy(xfs_rmap_intent_cache);
+ xfs_rmap_intent_cache = NULL;
+}
diff --git a/fs/xfs/libxfs/xfs_rmap.h b/fs/xfs/libxfs/xfs_rmap.h
index fd67904ed446..b718ebeda372 100644
--- a/fs/xfs/libxfs/xfs_rmap.h
+++ b/fs/xfs/libxfs/xfs_rmap.h
@@ -159,8 +159,8 @@ enum xfs_rmap_intent_type {
struct xfs_rmap_intent {
struct list_head ri_list;
enum xfs_rmap_intent_type ri_type;
- uint64_t ri_owner;
int ri_whichfork;
+ uint64_t ri_owner;
struct xfs_bmbt_irec ri_bmap;
};
@@ -215,4 +215,9 @@ extern const struct xfs_owner_info XFS_RMAP_OINFO_INODES;
extern const struct xfs_owner_info XFS_RMAP_OINFO_REFC;
extern const struct xfs_owner_info XFS_RMAP_OINFO_COW;
+extern struct kmem_cache *xfs_rmap_intent_cache;
+
+int __init xfs_rmap_intent_init_cache(void);
+void xfs_rmap_intent_destroy_cache(void);
+
#endif /* __XFS_RMAP_H__ */
diff --git a/fs/xfs/libxfs/xfs_rmap_btree.c b/fs/xfs/libxfs/xfs_rmap_btree.c
index b7dbbfb3aeed..69e104d0277f 100644
--- a/fs/xfs/libxfs/xfs_rmap_btree.c
+++ b/fs/xfs/libxfs/xfs_rmap_btree.c
@@ -22,6 +22,8 @@
#include "xfs_ag.h"
#include "xfs_ag_resv.h"
+static struct kmem_cache *xfs_rmapbt_cur_cache;
+
/*
* Reverse map btree.
*
@@ -451,13 +453,10 @@ xfs_rmapbt_init_common(
{
struct xfs_btree_cur *cur;
- cur = kmem_cache_zalloc(xfs_btree_cur_zone, GFP_NOFS | __GFP_NOFAIL);
- cur->bc_tp = tp;
- cur->bc_mp = mp;
/* Overlapping btree; 2 keys per pointer. */
- cur->bc_btnum = XFS_BTNUM_RMAP;
+ cur = xfs_btree_alloc_cursor(mp, tp, XFS_BTNUM_RMAP,
+ mp->m_rmap_maxlevels, xfs_rmapbt_cur_cache);
cur->bc_flags = XFS_BTREE_CRC_BLOCKS | XFS_BTREE_OVERLAPPING;
- cur->bc_blocklog = mp->m_sb.sb_blocklog;
cur->bc_statoff = XFS_STATS_CALC_INDEX(xs_rmap_2);
cur->bc_ops = &xfs_rmapbt_ops;
@@ -522,6 +521,18 @@ xfs_rmapbt_commit_staged_btree(
xfs_btree_commit_afakeroot(cur, tp, agbp, &xfs_rmapbt_ops);
}
+/* Calculate number of records in a reverse mapping btree block. */
+static inline unsigned int
+xfs_rmapbt_block_maxrecs(
+ unsigned int blocklen,
+ bool leaf)
+{
+ if (leaf)
+ return blocklen / sizeof(struct xfs_rmap_rec);
+ return blocklen /
+ (2 * sizeof(struct xfs_rmap_key) + sizeof(xfs_rmap_ptr_t));
+}
+
/*
* Calculate number of records in an rmap btree block.
*/
@@ -531,11 +542,33 @@ xfs_rmapbt_maxrecs(
int leaf)
{
blocklen -= XFS_RMAP_BLOCK_LEN;
+ return xfs_rmapbt_block_maxrecs(blocklen, leaf);
+}
- if (leaf)
- return blocklen / sizeof(struct xfs_rmap_rec);
- return blocklen /
- (2 * sizeof(struct xfs_rmap_key) + sizeof(xfs_rmap_ptr_t));
+/* Compute the max possible height for reverse mapping btrees. */
+unsigned int
+xfs_rmapbt_maxlevels_ondisk(void)
+{
+ unsigned int minrecs[2];
+ unsigned int blocklen;
+
+ blocklen = XFS_MIN_CRC_BLOCKSIZE - XFS_BTREE_SBLOCK_CRC_LEN;
+
+ minrecs[0] = xfs_rmapbt_block_maxrecs(blocklen, true) / 2;
+ minrecs[1] = xfs_rmapbt_block_maxrecs(blocklen, false) / 2;
+
+ /*
+ * Compute the asymptotic maxlevels for an rmapbt on any reflink fs.
+ *
+ * On a reflink filesystem, each AG block can have up to 2^32 (per the
+ * refcount record format) owners, which means that theoretically we
+ * could face up to 2^64 rmap records. However, we're likely to run
+ * out of blocks in the AG long before that happens, which means that
+ * we must compute the max height based on what the btree will look
+ * like if it consumes almost all the blocks in the AG due to maximal
+ * sharing factor.
+ */
+ return xfs_btree_space_to_height(minrecs, XFS_MAX_CRC_AG_BLOCKS);
}
/* Compute the maximum height of an rmap btree. */
@@ -543,26 +576,36 @@ void
xfs_rmapbt_compute_maxlevels(
struct xfs_mount *mp)
{
- /*
- * On a non-reflink filesystem, the maximum number of rmap
- * records is the number of blocks in the AG, hence the max
- * rmapbt height is log_$maxrecs($agblocks). However, with
- * reflink each AG block can have up to 2^32 (per the refcount
- * record format) owners, which means that theoretically we
- * could face up to 2^64 rmap records.
- *
- * That effectively means that the max rmapbt height must be
- * XFS_BTREE_MAXLEVELS. "Fortunately" we'll run out of AG
- * blocks to feed the rmapbt long before the rmapbt reaches
- * maximum height. The reflink code uses ag_resv_critical to
- * disallow reflinking when less than 10% of the per-AG metadata
- * block reservation since the fallback is a regular file copy.
- */
- if (xfs_has_reflink(mp))
- mp->m_rmap_maxlevels = XFS_BTREE_MAXLEVELS;
- else
+ if (!xfs_has_rmapbt(mp)) {
+ mp->m_rmap_maxlevels = 0;
+ return;
+ }
+
+ if (xfs_has_reflink(mp)) {
+ /*
+ * Compute the asymptotic maxlevels for an rmap btree on a
+ * filesystem that supports reflink.
+ *
+ * On a reflink filesystem, each AG block can have up to 2^32
+ * (per the refcount record format) owners, which means that
+ * theoretically we could face up to 2^64 rmap records.
+ * However, we're likely to run out of blocks in the AG long
+ * before that happens, which means that we must compute the
+ * max height based on what the btree will look like if it
+ * consumes almost all the blocks in the AG due to maximal
+ * sharing factor.
+ */
+ mp->m_rmap_maxlevels = xfs_btree_space_to_height(mp->m_rmap_mnr,
+ mp->m_sb.sb_agblocks);
+ } else {
+ /*
+ * If there's no block sharing, compute the maximum rmapbt
+ * height assuming one rmap record per AG block.
+ */
mp->m_rmap_maxlevels = xfs_btree_compute_maxlevels(
mp->m_rmap_mnr, mp->m_sb.sb_agblocks);
+ }
+ ASSERT(mp->m_rmap_maxlevels <= xfs_rmapbt_maxlevels_ondisk());
}
/* Calculate the refcount btree size for some records. */
@@ -633,3 +676,22 @@ xfs_rmapbt_calc_reserves(
return error;
}
+
+int __init
+xfs_rmapbt_init_cur_cache(void)
+{
+ xfs_rmapbt_cur_cache = kmem_cache_create("xfs_rmapbt_cur",
+ xfs_btree_cur_sizeof(xfs_rmapbt_maxlevels_ondisk()),
+ 0, 0, NULL);
+
+ if (!xfs_rmapbt_cur_cache)
+ return -ENOMEM;
+ return 0;
+}
+
+void
+xfs_rmapbt_destroy_cur_cache(void)
+{
+ kmem_cache_destroy(xfs_rmapbt_cur_cache);
+ xfs_rmapbt_cur_cache = NULL;
+}
diff --git a/fs/xfs/libxfs/xfs_rmap_btree.h b/fs/xfs/libxfs/xfs_rmap_btree.h
index f2eee6572af4..3244715dd111 100644
--- a/fs/xfs/libxfs/xfs_rmap_btree.h
+++ b/fs/xfs/libxfs/xfs_rmap_btree.h
@@ -59,4 +59,9 @@ extern xfs_extlen_t xfs_rmapbt_max_size(struct xfs_mount *mp,
extern int xfs_rmapbt_calc_reserves(struct xfs_mount *mp, struct xfs_trans *tp,
struct xfs_perag *pag, xfs_extlen_t *ask, xfs_extlen_t *used);
+unsigned int xfs_rmapbt_maxlevels_ondisk(void);
+
+int __init xfs_rmapbt_init_cur_cache(void);
+void xfs_rmapbt_destroy_cur_cache(void);
+
#endif /* __XFS_RMAP_BTREE_H__ */
diff --git a/fs/xfs/libxfs/xfs_sb.c b/fs/xfs/libxfs/xfs_sb.c
index e58349be78bd..f4e84aa1d50a 100644
--- a/fs/xfs/libxfs/xfs_sb.c
+++ b/fs/xfs/libxfs/xfs_sb.c
@@ -495,7 +495,7 @@ xfs_sb_quota_from_disk(struct xfs_sb *sbp)
static void
__xfs_sb_from_disk(
struct xfs_sb *to,
- xfs_dsb_t *from,
+ struct xfs_dsb *from,
bool convert_xquota)
{
to->sb_magicnum = be32_to_cpu(from->sb_magicnum);
@@ -571,7 +571,7 @@ __xfs_sb_from_disk(
void
xfs_sb_from_disk(
struct xfs_sb *to,
- xfs_dsb_t *from)
+ struct xfs_dsb *from)
{
__xfs_sb_from_disk(to, from, true);
}
diff --git a/fs/xfs/libxfs/xfs_trans_resv.c b/fs/xfs/libxfs/xfs_trans_resv.c
index 5e300daa2559..6f83d9b306ee 100644
--- a/fs/xfs/libxfs/xfs_trans_resv.c
+++ b/fs/xfs/libxfs/xfs_trans_resv.c
@@ -70,7 +70,7 @@ xfs_allocfree_log_count(
{
uint blocks;
- blocks = num_ops * 2 * (2 * mp->m_ag_maxlevels - 1);
+ blocks = num_ops * 2 * (2 * mp->m_alloc_maxlevels - 1);
if (xfs_has_rmapbt(mp))
blocks += num_ops * (2 * mp->m_rmap_maxlevels - 1);
if (xfs_has_reflink(mp))
@@ -814,6 +814,19 @@ xfs_trans_resv_calc(
struct xfs_mount *mp,
struct xfs_trans_resv *resp)
{
+ unsigned int rmap_maxlevels = mp->m_rmap_maxlevels;
+
+ /*
+ * In the early days of rmap+reflink, we always set the rmap maxlevels
+ * to 9 even if the AG was small enough that it would never grow to
+ * that height. Transaction reservation sizes influence the minimum
+ * log size calculation, which influences the size of the log that mkfs
+ * creates. Use the old value here to ensure that newly formatted
+ * small filesystems will mount on older kernels.
+ */
+ if (xfs_has_rmapbt(mp) && xfs_has_reflink(mp))
+ mp->m_rmap_maxlevels = XFS_OLD_REFLINK_RMAP_MAXLEVELS;
+
/*
* The following transactions are logged in physical format and
* require a permanent reservation on space.
@@ -916,4 +929,7 @@ xfs_trans_resv_calc(
resp->tr_clearagi.tr_logres = xfs_calc_clear_agi_bucket_reservation(mp);
resp->tr_growrtzero.tr_logres = xfs_calc_growrtzero_reservation(mp);
resp->tr_growrtfree.tr_logres = xfs_calc_growrtfree_reservation(mp);
+
+ /* Put everything back the way it was. This goes at the end. */
+ mp->m_rmap_maxlevels = rmap_maxlevels;
}
diff --git a/fs/xfs/libxfs/xfs_trans_space.h b/fs/xfs/libxfs/xfs_trans_space.h
index 50332be34388..87b31c69a773 100644
--- a/fs/xfs/libxfs/xfs_trans_space.h
+++ b/fs/xfs/libxfs/xfs_trans_space.h
@@ -17,6 +17,13 @@
/* Adding one rmap could split every level up to the top of the tree. */
#define XFS_RMAPADD_SPACE_RES(mp) ((mp)->m_rmap_maxlevels)
+/*
+ * Note that we historically set m_rmap_maxlevels to 9 when reflink is enabled,
+ * so we must preserve this behavior to avoid changing the transaction space
+ * reservations and minimum log size calculations for existing filesystems.
+ */
+#define XFS_OLD_REFLINK_RMAP_MAXLEVELS 9
+
/* Blocks we might need to add "b" rmaps to a tree. */
#define XFS_NRMAPADD_SPACE_RES(mp, b)\
(((b + XFS_MAX_CONTIG_RMAPS_PER_BLOCK(mp) - 1) / \
@@ -74,7 +81,7 @@
#define XFS_DIOSTRAT_SPACE_RES(mp, v) \
(XFS_EXTENTADD_SPACE_RES(mp, XFS_DATA_FORK) + (v))
#define XFS_GROWFS_SPACE_RES(mp) \
- (2 * (mp)->m_ag_maxlevels)
+ (2 * (mp)->m_alloc_maxlevels)
#define XFS_GROWFSRT_SPACE_RES(mp,b) \
((b) + XFS_EXTENTADD_SPACE_RES(mp, XFS_DATA_FORK))
#define XFS_LINK_SPACE_RES(mp,nl) \
diff --git a/fs/xfs/scrub/agheader.c b/fs/xfs/scrub/agheader.c
index ae3c9f6e2c69..bed798792226 100644
--- a/fs/xfs/scrub/agheader.c
+++ b/fs/xfs/scrub/agheader.c
@@ -555,11 +555,11 @@ xchk_agf(
xchk_block_set_corrupt(sc, sc->sa.agf_bp);
level = be32_to_cpu(agf->agf_levels[XFS_BTNUM_BNO]);
- if (level <= 0 || level > XFS_BTREE_MAXLEVELS)
+ if (level <= 0 || level > mp->m_alloc_maxlevels)
xchk_block_set_corrupt(sc, sc->sa.agf_bp);
level = be32_to_cpu(agf->agf_levels[XFS_BTNUM_CNT]);
- if (level <= 0 || level > XFS_BTREE_MAXLEVELS)
+ if (level <= 0 || level > mp->m_alloc_maxlevels)
xchk_block_set_corrupt(sc, sc->sa.agf_bp);
if (xfs_has_rmapbt(mp)) {
@@ -568,7 +568,7 @@ xchk_agf(
xchk_block_set_corrupt(sc, sc->sa.agf_bp);
level = be32_to_cpu(agf->agf_levels[XFS_BTNUM_RMAP]);
- if (level <= 0 || level > XFS_BTREE_MAXLEVELS)
+ if (level <= 0 || level > mp->m_rmap_maxlevels)
xchk_block_set_corrupt(sc, sc->sa.agf_bp);
}
@@ -578,7 +578,7 @@ xchk_agf(
xchk_block_set_corrupt(sc, sc->sa.agf_bp);
level = be32_to_cpu(agf->agf_refcount_level);
- if (level <= 0 || level > XFS_BTREE_MAXLEVELS)
+ if (level <= 0 || level > mp->m_refc_maxlevels)
xchk_block_set_corrupt(sc, sc->sa.agf_bp);
}
@@ -850,6 +850,7 @@ xchk_agi(
struct xfs_mount *mp = sc->mp;
struct xfs_agi *agi;
struct xfs_perag *pag;
+ struct xfs_ino_geometry *igeo = M_IGEO(sc->mp);
xfs_agnumber_t agno = sc->sm->sm_agno;
xfs_agblock_t agbno;
xfs_agblock_t eoag;
@@ -880,7 +881,7 @@ xchk_agi(
xchk_block_set_corrupt(sc, sc->sa.agi_bp);
level = be32_to_cpu(agi->agi_level);
- if (level <= 0 || level > XFS_BTREE_MAXLEVELS)
+ if (level <= 0 || level > igeo->inobt_maxlevels)
xchk_block_set_corrupt(sc, sc->sa.agi_bp);
if (xfs_has_finobt(mp)) {
@@ -889,7 +890,7 @@ xchk_agi(
xchk_block_set_corrupt(sc, sc->sa.agi_bp);
level = be32_to_cpu(agi->agi_free_level);
- if (level <= 0 || level > XFS_BTREE_MAXLEVELS)
+ if (level <= 0 || level > igeo->inobt_maxlevels)
xchk_block_set_corrupt(sc, sc->sa.agi_bp);
}
diff --git a/fs/xfs/scrub/agheader_repair.c b/fs/xfs/scrub/agheader_repair.c
index 0f8deee66f15..d7bfed52f4cd 100644
--- a/fs/xfs/scrub/agheader_repair.c
+++ b/fs/xfs/scrub/agheader_repair.c
@@ -122,7 +122,7 @@ xrep_check_btree_root(
xfs_agnumber_t agno = sc->sm->sm_agno;
return xfs_verify_agbno(mp, agno, fab->root) &&
- fab->height <= XFS_BTREE_MAXLEVELS;
+ fab->height <= fab->maxlevels;
}
/*
@@ -339,18 +339,22 @@ xrep_agf(
[XREP_AGF_BNOBT] = {
.rmap_owner = XFS_RMAP_OWN_AG,
.buf_ops = &xfs_bnobt_buf_ops,
+ .maxlevels = sc->mp->m_alloc_maxlevels,
},
[XREP_AGF_CNTBT] = {
.rmap_owner = XFS_RMAP_OWN_AG,
.buf_ops = &xfs_cntbt_buf_ops,
+ .maxlevels = sc->mp->m_alloc_maxlevels,
},
[XREP_AGF_RMAPBT] = {
.rmap_owner = XFS_RMAP_OWN_AG,
.buf_ops = &xfs_rmapbt_buf_ops,
+ .maxlevels = sc->mp->m_rmap_maxlevels,
},
[XREP_AGF_REFCOUNTBT] = {
.rmap_owner = XFS_RMAP_OWN_REFC,
.buf_ops = &xfs_refcountbt_buf_ops,
+ .maxlevels = sc->mp->m_refc_maxlevels,
},
[XREP_AGF_END] = {
.buf_ops = NULL,
@@ -881,10 +885,12 @@ xrep_agi(
[XREP_AGI_INOBT] = {
.rmap_owner = XFS_RMAP_OWN_INOBT,
.buf_ops = &xfs_inobt_buf_ops,
+ .maxlevels = M_IGEO(sc->mp)->inobt_maxlevels,
},
[XREP_AGI_FINOBT] = {
.rmap_owner = XFS_RMAP_OWN_INOBT,
.buf_ops = &xfs_finobt_buf_ops,
+ .maxlevels = M_IGEO(sc->mp)->inobt_maxlevels,
},
[XREP_AGI_END] = {
.buf_ops = NULL
diff --git a/fs/xfs/scrub/bitmap.c b/fs/xfs/scrub/bitmap.c
index d6d24c866bc4..b89bf9de9b1c 100644
--- a/fs/xfs/scrub/bitmap.c
+++ b/fs/xfs/scrub/bitmap.c
@@ -222,21 +222,21 @@ out:
* 1 2 3
*
* Pretend for this example that each leaf block has 100 btree records. For
- * the first btree record, we'll observe that bc_ptrs[0] == 1, so we record
- * that we saw block 1. Then we observe that bc_ptrs[1] == 1, so we record
- * block 4. The list is [1, 4].
+ * the first btree record, we'll observe that bc_levels[0].ptr == 1, so we
+ * record that we saw block 1. Then we observe that bc_levels[1].ptr == 1, so
+ * we record block 4. The list is [1, 4].
*
- * For the second btree record, we see that bc_ptrs[0] == 2, so we exit the
- * loop. The list remains [1, 4].
+ * For the second btree record, we see that bc_levels[0].ptr == 2, so we exit
+ * the loop. The list remains [1, 4].
*
* For the 101st btree record, we've moved onto leaf block 2. Now
- * bc_ptrs[0] == 1 again, so we record that we saw block 2. We see that
- * bc_ptrs[1] == 2, so we exit the loop. The list is now [1, 4, 2].
+ * bc_levels[0].ptr == 1 again, so we record that we saw block 2. We see that
+ * bc_levels[1].ptr == 2, so we exit the loop. The list is now [1, 4, 2].
*
- * For the 102nd record, bc_ptrs[0] == 2, so we continue.
+ * For the 102nd record, bc_levels[0].ptr == 2, so we continue.
*
- * For the 201st record, we've moved on to leaf block 3. bc_ptrs[0] == 1, so
- * we add 3 to the list. Now it is [1, 4, 2, 3].
+ * For the 201st record, we've moved on to leaf block 3.
+ * bc_levels[0].ptr == 1, so we add 3 to the list. Now it is [1, 4, 2, 3].
*
* For the 300th record we just exit, with the list being [1, 4, 2, 3].
*/
@@ -256,7 +256,7 @@ xbitmap_set_btcur_path(
int i;
int error;
- for (i = 0; i < cur->bc_nlevels && cur->bc_ptrs[i] == 1; i++) {
+ for (i = 0; i < cur->bc_nlevels && cur->bc_levels[i].ptr == 1; i++) {
xfs_btree_get_block(cur, i, &bp);
if (!bp)
continue;
diff --git a/fs/xfs/scrub/bmap.c b/fs/xfs/scrub/bmap.c
index 017da9ceaee9..a4cbbc346f60 100644
--- a/fs/xfs/scrub/bmap.c
+++ b/fs/xfs/scrub/bmap.c
@@ -402,7 +402,7 @@ xchk_bmapbt_rec(
* the root since the verifiers don't do that.
*/
if (xfs_has_crc(bs->cur->bc_mp) &&
- bs->cur->bc_ptrs[0] == 1) {
+ bs->cur->bc_levels[0].ptr == 1) {
for (i = 0; i < bs->cur->bc_nlevels - 1; i++) {
block = xfs_btree_get_block(bs->cur, i, &bp);
owner = be64_to_cpu(block->bb_u.l.bb_owner);
diff --git a/fs/xfs/scrub/btree.c b/fs/xfs/scrub/btree.c
index eccb855dc904..39dd46f038fe 100644
--- a/fs/xfs/scrub/btree.c
+++ b/fs/xfs/scrub/btree.c
@@ -136,14 +136,14 @@ xchk_btree_rec(
struct xfs_buf *bp;
block = xfs_btree_get_block(cur, 0, &bp);
- rec = xfs_btree_rec_addr(cur, cur->bc_ptrs[0], block);
+ rec = xfs_btree_rec_addr(cur, cur->bc_levels[0].ptr, block);
trace_xchk_btree_rec(bs->sc, cur, 0);
/* If this isn't the first record, are they in order? */
- if (!bs->firstrec && !cur->bc_ops->recs_inorder(cur, &bs->lastrec, rec))
+ if (cur->bc_levels[0].ptr > 1 &&
+ !cur->bc_ops->recs_inorder(cur, &bs->lastrec, rec))
xchk_btree_set_corrupt(bs->sc, cur, 0);
- bs->firstrec = false;
memcpy(&bs->lastrec, rec, cur->bc_ops->rec_len);
if (cur->bc_nlevels == 1)
@@ -152,7 +152,7 @@ xchk_btree_rec(
/* Is this at least as large as the parent low key? */
cur->bc_ops->init_key_from_rec(&key, rec);
keyblock = xfs_btree_get_block(cur, 1, &bp);
- keyp = xfs_btree_key_addr(cur, cur->bc_ptrs[1], keyblock);
+ keyp = xfs_btree_key_addr(cur, cur->bc_levels[1].ptr, keyblock);
if (cur->bc_ops->diff_two_keys(cur, &key, keyp) < 0)
xchk_btree_set_corrupt(bs->sc, cur, 1);
@@ -161,7 +161,7 @@ xchk_btree_rec(
/* Is this no larger than the parent high key? */
cur->bc_ops->init_high_key_from_rec(&hkey, rec);
- keyp = xfs_btree_high_key_addr(cur, cur->bc_ptrs[1], keyblock);
+ keyp = xfs_btree_high_key_addr(cur, cur->bc_levels[1].ptr, keyblock);
if (cur->bc_ops->diff_two_keys(cur, keyp, &hkey) < 0)
xchk_btree_set_corrupt(bs->sc, cur, 1);
}
@@ -183,23 +183,22 @@ xchk_btree_key(
struct xfs_buf *bp;
block = xfs_btree_get_block(cur, level, &bp);
- key = xfs_btree_key_addr(cur, cur->bc_ptrs[level], block);
+ key = xfs_btree_key_addr(cur, cur->bc_levels[level].ptr, block);
trace_xchk_btree_key(bs->sc, cur, level);
/* If this isn't the first key, are they in order? */
- if (!bs->firstkey[level] &&
- !cur->bc_ops->keys_inorder(cur, &bs->lastkey[level], key))
+ if (cur->bc_levels[level].ptr > 1 &&
+ !cur->bc_ops->keys_inorder(cur, &bs->lastkey[level - 1], key))
xchk_btree_set_corrupt(bs->sc, cur, level);
- bs->firstkey[level] = false;
- memcpy(&bs->lastkey[level], key, cur->bc_ops->key_len);
+ memcpy(&bs->lastkey[level - 1], key, cur->bc_ops->key_len);
if (level + 1 >= cur->bc_nlevels)
return;
/* Is this at least as large as the parent low key? */
keyblock = xfs_btree_get_block(cur, level + 1, &bp);
- keyp = xfs_btree_key_addr(cur, cur->bc_ptrs[level + 1], keyblock);
+ keyp = xfs_btree_key_addr(cur, cur->bc_levels[level + 1].ptr, keyblock);
if (cur->bc_ops->diff_two_keys(cur, key, keyp) < 0)
xchk_btree_set_corrupt(bs->sc, cur, level);
@@ -207,8 +206,9 @@ xchk_btree_key(
return;
/* Is this no larger than the parent high key? */
- key = xfs_btree_high_key_addr(cur, cur->bc_ptrs[level], block);
- keyp = xfs_btree_high_key_addr(cur, cur->bc_ptrs[level + 1], keyblock);
+ key = xfs_btree_high_key_addr(cur, cur->bc_levels[level].ptr, block);
+ keyp = xfs_btree_high_key_addr(cur, cur->bc_levels[level + 1].ptr,
+ keyblock);
if (cur->bc_ops->diff_two_keys(cur, keyp, key) < 0)
xchk_btree_set_corrupt(bs->sc, cur, level);
}
@@ -291,7 +291,7 @@ xchk_btree_block_check_sibling(
/* Compare upper level pointer to sibling pointer. */
pblock = xfs_btree_get_block(ncur, level + 1, &pbp);
- pp = xfs_btree_ptr_addr(ncur, ncur->bc_ptrs[level + 1], pblock);
+ pp = xfs_btree_ptr_addr(ncur, ncur->bc_levels[level + 1].ptr, pblock);
if (!xchk_btree_ptr_ok(bs, level + 1, pp))
goto out;
if (pbp)
@@ -596,7 +596,7 @@ xchk_btree_block_keys(
/* Obtain the parent's copy of the keys for this block. */
parent_block = xfs_btree_get_block(cur, level + 1, &bp);
- parent_keys = xfs_btree_key_addr(cur, cur->bc_ptrs[level + 1],
+ parent_keys = xfs_btree_key_addr(cur, cur->bc_levels[level + 1].ptr,
parent_block);
if (cur->bc_ops->diff_two_keys(cur, &block_keys, parent_keys) != 0)
@@ -607,7 +607,7 @@ xchk_btree_block_keys(
/* Get high keys */
high_bk = xfs_btree_high_key_from_key(cur, &block_keys);
- high_pk = xfs_btree_high_key_addr(cur, cur->bc_ptrs[level + 1],
+ high_pk = xfs_btree_high_key_addr(cur, cur->bc_levels[level + 1].ptr,
parent_block);
if (cur->bc_ops->diff_two_keys(cur, high_bk, high_pk) != 0)
@@ -627,35 +627,39 @@ xchk_btree(
const struct xfs_owner_info *oinfo,
void *private)
{
- struct xchk_btree bs = {
- .cur = cur,
- .scrub_rec = scrub_fn,
- .oinfo = oinfo,
- .firstrec = true,
- .private = private,
- .sc = sc,
- };
union xfs_btree_ptr ptr;
+ struct xchk_btree *bs;
union xfs_btree_ptr *pp;
union xfs_btree_rec *recp;
struct xfs_btree_block *block;
- int level;
struct xfs_buf *bp;
struct check_owner *co;
struct check_owner *n;
- int i;
+ size_t cur_sz;
+ int level;
int error = 0;
- /* Initialize scrub state */
- for (i = 0; i < XFS_BTREE_MAXLEVELS; i++)
- bs.firstkey[i] = true;
- INIT_LIST_HEAD(&bs.to_check);
-
- /* Don't try to check a tree with a height we can't handle. */
- if (cur->bc_nlevels > XFS_BTREE_MAXLEVELS) {
+ /*
+ * Allocate the btree scrub context from the heap, because this
+ * structure can get rather large. Don't let a caller feed us a
+ * totally absurd size.
+ */
+ cur_sz = xchk_btree_sizeof(cur->bc_nlevels);
+ if (cur_sz > PAGE_SIZE) {
xchk_btree_set_corrupt(sc, cur, 0);
- goto out;
+ return 0;
}
+ bs = kmem_zalloc(cur_sz, KM_NOFS | KM_MAYFAIL);
+ if (!bs)
+ return -ENOMEM;
+ bs->cur = cur;
+ bs->scrub_rec = scrub_fn;
+ bs->oinfo = oinfo;
+ bs->private = private;
+ bs->sc = sc;
+
+ /* Initialize scrub state */
+ INIT_LIST_HEAD(&bs->to_check);
/*
* Load the root of the btree. The helper function absorbs
@@ -663,79 +667,82 @@ xchk_btree(
*/
level = cur->bc_nlevels - 1;
cur->bc_ops->init_ptr_from_cur(cur, &ptr);
- if (!xchk_btree_ptr_ok(&bs, cur->bc_nlevels, &ptr))
+ if (!xchk_btree_ptr_ok(bs, cur->bc_nlevels, &ptr))
goto out;
- error = xchk_btree_get_block(&bs, level, &ptr, &block, &bp);
+ error = xchk_btree_get_block(bs, level, &ptr, &block, &bp);
if (error || !block)
goto out;
- cur->bc_ptrs[level] = 1;
+ cur->bc_levels[level].ptr = 1;
while (level < cur->bc_nlevels) {
block = xfs_btree_get_block(cur, level, &bp);
if (level == 0) {
/* End of leaf, pop back towards the root. */
- if (cur->bc_ptrs[level] >
+ if (cur->bc_levels[level].ptr >
be16_to_cpu(block->bb_numrecs)) {
- xchk_btree_block_keys(&bs, level, block);
+ xchk_btree_block_keys(bs, level, block);
if (level < cur->bc_nlevels - 1)
- cur->bc_ptrs[level + 1]++;
+ cur->bc_levels[level + 1].ptr++;
level++;
continue;
}
/* Records in order for scrub? */
- xchk_btree_rec(&bs);
+ xchk_btree_rec(bs);
/* Call out to the record checker. */
- recp = xfs_btree_rec_addr(cur, cur->bc_ptrs[0], block);
- error = bs.scrub_rec(&bs, recp);
+ recp = xfs_btree_rec_addr(cur, cur->bc_levels[0].ptr,
+ block);
+ error = bs->scrub_rec(bs, recp);
if (error)
break;
if (xchk_should_terminate(sc, &error) ||
(sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT))
break;
- cur->bc_ptrs[level]++;
+ cur->bc_levels[level].ptr++;
continue;
}
/* End of node, pop back towards the root. */
- if (cur->bc_ptrs[level] > be16_to_cpu(block->bb_numrecs)) {
- xchk_btree_block_keys(&bs, level, block);
+ if (cur->bc_levels[level].ptr >
+ be16_to_cpu(block->bb_numrecs)) {
+ xchk_btree_block_keys(bs, level, block);
if (level < cur->bc_nlevels - 1)
- cur->bc_ptrs[level + 1]++;
+ cur->bc_levels[level + 1].ptr++;
level++;
continue;
}
/* Keys in order for scrub? */
- xchk_btree_key(&bs, level);
+ xchk_btree_key(bs, level);
/* Drill another level deeper. */
- pp = xfs_btree_ptr_addr(cur, cur->bc_ptrs[level], block);
- if (!xchk_btree_ptr_ok(&bs, level, pp)) {
- cur->bc_ptrs[level]++;
+ pp = xfs_btree_ptr_addr(cur, cur->bc_levels[level].ptr, block);
+ if (!xchk_btree_ptr_ok(bs, level, pp)) {
+ cur->bc_levels[level].ptr++;
continue;
}
level--;
- error = xchk_btree_get_block(&bs, level, pp, &block, &bp);
+ error = xchk_btree_get_block(bs, level, pp, &block, &bp);
if (error || !block)
goto out;
- cur->bc_ptrs[level] = 1;
+ cur->bc_levels[level].ptr = 1;
}
out:
/* Process deferred owner checks on btree blocks. */
- list_for_each_entry_safe(co, n, &bs.to_check, list) {
- if (!error && bs.cur)
- error = xchk_btree_check_block_owner(&bs,
- co->level, co->daddr);
+ list_for_each_entry_safe(co, n, &bs->to_check, list) {
+ if (!error && bs->cur)
+ error = xchk_btree_check_block_owner(bs, co->level,
+ co->daddr);
list_del(&co->list);
kmem_free(co);
}
+ kmem_free(bs);
return error;
}
diff --git a/fs/xfs/scrub/btree.h b/fs/xfs/scrub/btree.h
index b7d2fc01fbf9..da61a53a0b61 100644
--- a/fs/xfs/scrub/btree.h
+++ b/fs/xfs/scrub/btree.h
@@ -39,11 +39,22 @@ struct xchk_btree {
/* internal scrub state */
union xfs_btree_rec lastrec;
- bool firstrec;
- union xfs_btree_key lastkey[XFS_BTREE_MAXLEVELS];
- bool firstkey[XFS_BTREE_MAXLEVELS];
struct list_head to_check;
+
+ /* this element must come last! */
+ union xfs_btree_key lastkey[];
};
+
+/*
+ * Calculate the size of a xchk_btree structure. There are nlevels-1 slots for
+ * keys because we track leaf records separately in lastrec.
+ */
+static inline size_t
+xchk_btree_sizeof(unsigned int nlevels)
+{
+ return struct_size((struct xchk_btree *)NULL, lastkey, nlevels - 1);
+}
+
int xchk_btree(struct xfs_scrub *sc, struct xfs_btree_cur *cur,
xchk_btree_rec_fn scrub_fn, const struct xfs_owner_info *oinfo,
void *private);
diff --git a/fs/xfs/scrub/dabtree.c b/fs/xfs/scrub/dabtree.c
index 8a52514bc1ff..b962cfbbd92b 100644
--- a/fs/xfs/scrub/dabtree.c
+++ b/fs/xfs/scrub/dabtree.c
@@ -473,7 +473,7 @@ xchk_da_btree(
xchk_da_btree_rec_fn scrub_fn,
void *private)
{
- struct xchk_da_btree ds = {};
+ struct xchk_da_btree *ds;
struct xfs_mount *mp = sc->mp;
struct xfs_da_state_blk *blks;
struct xfs_da_node_entry *key;
@@ -486,32 +486,35 @@ xchk_da_btree(
return 0;
/* Set up initial da state. */
- ds.dargs.dp = sc->ip;
- ds.dargs.whichfork = whichfork;
- ds.dargs.trans = sc->tp;
- ds.dargs.op_flags = XFS_DA_OP_OKNOENT;
- ds.state = xfs_da_state_alloc(&ds.dargs);
- ds.sc = sc;
- ds.private = private;
+ ds = kmem_zalloc(sizeof(struct xchk_da_btree), KM_NOFS | KM_MAYFAIL);
+ if (!ds)
+ return -ENOMEM;
+ ds->dargs.dp = sc->ip;
+ ds->dargs.whichfork = whichfork;
+ ds->dargs.trans = sc->tp;
+ ds->dargs.op_flags = XFS_DA_OP_OKNOENT;
+ ds->state = xfs_da_state_alloc(&ds->dargs);
+ ds->sc = sc;
+ ds->private = private;
if (whichfork == XFS_ATTR_FORK) {
- ds.dargs.geo = mp->m_attr_geo;
- ds.lowest = 0;
- ds.highest = 0;
+ ds->dargs.geo = mp->m_attr_geo;
+ ds->lowest = 0;
+ ds->highest = 0;
} else {
- ds.dargs.geo = mp->m_dir_geo;
- ds.lowest = ds.dargs.geo->leafblk;
- ds.highest = ds.dargs.geo->freeblk;
+ ds->dargs.geo = mp->m_dir_geo;
+ ds->lowest = ds->dargs.geo->leafblk;
+ ds->highest = ds->dargs.geo->freeblk;
}
- blkno = ds.lowest;
+ blkno = ds->lowest;
level = 0;
/* Find the root of the da tree, if present. */
- blks = ds.state->path.blk;
- error = xchk_da_btree_block(&ds, level, blkno);
+ blks = ds->state->path.blk;
+ error = xchk_da_btree_block(ds, level, blkno);
if (error)
goto out_state;
/*
- * We didn't find a block at ds.lowest, which means that there's
+ * We didn't find a block at ds->lowest, which means that there's
* no LEAF1/LEAFN tree (at least not where it's supposed to be),
* so jump out now.
*/
@@ -523,16 +526,16 @@ xchk_da_btree(
/* Handle leaf block. */
if (blks[level].magic != XFS_DA_NODE_MAGIC) {
/* End of leaf, pop back towards the root. */
- if (blks[level].index >= ds.maxrecs[level]) {
+ if (blks[level].index >= ds->maxrecs[level]) {
if (level > 0)
blks[level - 1].index++;
- ds.tree_level++;
+ ds->tree_level++;
level--;
continue;
}
/* Dispatch record scrubbing. */
- error = scrub_fn(&ds, level);
+ error = scrub_fn(ds, level);
if (error)
break;
if (xchk_should_terminate(sc, &error) ||
@@ -545,17 +548,17 @@ xchk_da_btree(
/* End of node, pop back towards the root. */
- if (blks[level].index >= ds.maxrecs[level]) {
+ if (blks[level].index >= ds->maxrecs[level]) {
if (level > 0)
blks[level - 1].index++;
- ds.tree_level++;
+ ds->tree_level++;
level--;
continue;
}
/* Hashes in order for scrub? */
- key = xchk_da_btree_node_entry(&ds, level);
- error = xchk_da_btree_hash(&ds, level, &key->hashval);
+ key = xchk_da_btree_node_entry(ds, level);
+ error = xchk_da_btree_hash(ds, level, &key->hashval);
if (error)
goto out;
@@ -564,11 +567,11 @@ xchk_da_btree(
level++;
if (level >= XFS_DA_NODE_MAXDEPTH) {
/* Too deep! */
- xchk_da_set_corrupt(&ds, level - 1);
+ xchk_da_set_corrupt(ds, level - 1);
break;
}
- ds.tree_level--;
- error = xchk_da_btree_block(&ds, level, blkno);
+ ds->tree_level--;
+ error = xchk_da_btree_block(ds, level, blkno);
if (error)
goto out;
if (blks[level].bp == NULL)
@@ -587,6 +590,7 @@ out:
}
out_state:
- xfs_da_state_free(ds.state);
+ xfs_da_state_free(ds->state);
+ kmem_free(ds);
return error;
}
diff --git a/fs/xfs/scrub/repair.h b/fs/xfs/scrub/repair.h
index 3bb152d52a07..840f74ec431c 100644
--- a/fs/xfs/scrub/repair.h
+++ b/fs/xfs/scrub/repair.h
@@ -44,6 +44,9 @@ struct xrep_find_ag_btree {
/* in: buffer ops */
const struct xfs_buf_ops *buf_ops;
+ /* in: maximum btree height */
+ unsigned int maxlevels;
+
/* out: the highest btree block found and the tree height */
xfs_agblock_t root;
unsigned int height;
diff --git a/fs/xfs/scrub/scrub.c b/fs/xfs/scrub/scrub.c
index 51e4c61916d2..8d528d35b725 100644
--- a/fs/xfs/scrub/scrub.c
+++ b/fs/xfs/scrub/scrub.c
@@ -461,15 +461,10 @@ xfs_scrub_metadata(
struct file *file,
struct xfs_scrub_metadata *sm)
{
- struct xfs_scrub sc = {
- .file = file,
- .sm = sm,
- };
+ struct xfs_scrub *sc;
struct xfs_mount *mp = XFS_I(file_inode(file))->i_mount;
int error = 0;
- sc.mp = mp;
-
BUILD_BUG_ON(sizeof(meta_scrub_ops) !=
(sizeof(struct xchk_meta_ops) * XFS_SCRUB_TYPE_NR));
@@ -489,59 +484,68 @@ xfs_scrub_metadata(
xchk_experimental_warning(mp);
- sc.ops = &meta_scrub_ops[sm->sm_type];
- sc.sick_mask = xchk_health_mask_for_scrub_type(sm->sm_type);
+ sc = kmem_zalloc(sizeof(struct xfs_scrub), KM_NOFS | KM_MAYFAIL);
+ if (!sc) {
+ error = -ENOMEM;
+ goto out;
+ }
+
+ sc->mp = mp;
+ sc->file = file;
+ sc->sm = sm;
+ sc->ops = &meta_scrub_ops[sm->sm_type];
+ sc->sick_mask = xchk_health_mask_for_scrub_type(sm->sm_type);
retry_op:
/*
* When repairs are allowed, prevent freezing or readonly remount while
* scrub is running with a real transaction.
*/
if (sm->sm_flags & XFS_SCRUB_IFLAG_REPAIR) {
- error = mnt_want_write_file(sc.file);
+ error = mnt_want_write_file(sc->file);
if (error)
- goto out;
+ goto out_sc;
}
/* Set up for the operation. */
- error = sc.ops->setup(&sc);
+ error = sc->ops->setup(sc);
if (error)
goto out_teardown;
/* Scrub for errors. */
- error = sc.ops->scrub(&sc);
- if (!(sc.flags & XCHK_TRY_HARDER) && error == -EDEADLOCK) {
+ error = sc->ops->scrub(sc);
+ if (!(sc->flags & XCHK_TRY_HARDER) && error == -EDEADLOCK) {
/*
* Scrubbers return -EDEADLOCK to mean 'try harder'.
* Tear down everything we hold, then set up again with
* preparation for worst-case scenarios.
*/
- error = xchk_teardown(&sc, 0);
+ error = xchk_teardown(sc, 0);
if (error)
- goto out;
- sc.flags |= XCHK_TRY_HARDER;
+ goto out_sc;
+ sc->flags |= XCHK_TRY_HARDER;
goto retry_op;
} else if (error || (sm->sm_flags & XFS_SCRUB_OFLAG_INCOMPLETE))
goto out_teardown;
- xchk_update_health(&sc);
+ xchk_update_health(sc);
- if ((sc.sm->sm_flags & XFS_SCRUB_IFLAG_REPAIR) &&
- !(sc.flags & XREP_ALREADY_FIXED)) {
+ if ((sc->sm->sm_flags & XFS_SCRUB_IFLAG_REPAIR) &&
+ !(sc->flags & XREP_ALREADY_FIXED)) {
bool needs_fix;
/* Let debug users force us into the repair routines. */
if (XFS_TEST_ERROR(false, mp, XFS_ERRTAG_FORCE_SCRUB_REPAIR))
- sc.sm->sm_flags |= XFS_SCRUB_OFLAG_CORRUPT;
+ sc->sm->sm_flags |= XFS_SCRUB_OFLAG_CORRUPT;
- needs_fix = (sc.sm->sm_flags & (XFS_SCRUB_OFLAG_CORRUPT |
- XFS_SCRUB_OFLAG_XCORRUPT |
- XFS_SCRUB_OFLAG_PREEN));
+ needs_fix = (sc->sm->sm_flags & (XFS_SCRUB_OFLAG_CORRUPT |
+ XFS_SCRUB_OFLAG_XCORRUPT |
+ XFS_SCRUB_OFLAG_PREEN));
/*
* If userspace asked for a repair but it wasn't necessary,
* report that back to userspace.
*/
if (!needs_fix) {
- sc.sm->sm_flags |= XFS_SCRUB_OFLAG_NO_REPAIR_NEEDED;
+ sc->sm->sm_flags |= XFS_SCRUB_OFLAG_NO_REPAIR_NEEDED;
goto out_nofix;
}
@@ -549,26 +553,28 @@ retry_op:
* If it's broken, userspace wants us to fix it, and we haven't
* already tried to fix it, then attempt a repair.
*/
- error = xrep_attempt(&sc);
+ error = xrep_attempt(sc);
if (error == -EAGAIN) {
/*
* Either the repair function succeeded or it couldn't
* get all the resources it needs; either way, we go
* back to the beginning and call the scrub function.
*/
- error = xchk_teardown(&sc, 0);
+ error = xchk_teardown(sc, 0);
if (error) {
xrep_failure(mp);
- goto out;
+ goto out_sc;
}
goto retry_op;
}
}
out_nofix:
- xchk_postmortem(&sc);
+ xchk_postmortem(sc);
out_teardown:
- error = xchk_teardown(&sc, error);
+ error = xchk_teardown(sc, error);
+out_sc:
+ kmem_free(sc);
out:
trace_xchk_done(XFS_I(file_inode(file)), sm, error);
if (error == -EFSCORRUPTED || error == -EFSBADCRC) {
diff --git a/fs/xfs/scrub/trace.c b/fs/xfs/scrub/trace.c
index c0ef53fe6611..b5f94676c37c 100644
--- a/fs/xfs/scrub/trace.c
+++ b/fs/xfs/scrub/trace.c
@@ -21,13 +21,14 @@ xchk_btree_cur_fsbno(
struct xfs_btree_cur *cur,
int level)
{
- if (level < cur->bc_nlevels && cur->bc_bufs[level])
+ if (level < cur->bc_nlevels && cur->bc_levels[level].bp)
return XFS_DADDR_TO_FSB(cur->bc_mp,
- xfs_buf_daddr(cur->bc_bufs[level]));
- if (level == cur->bc_nlevels - 1 && cur->bc_flags & XFS_BTREE_LONG_PTRS)
+ xfs_buf_daddr(cur->bc_levels[level].bp));
+
+ if (level == cur->bc_nlevels - 1 &&
+ (cur->bc_flags & XFS_BTREE_ROOT_IN_INODE))
return XFS_INO_TO_FSB(cur->bc_mp, cur->bc_ino.ip->i_ino);
- if (!(cur->bc_flags & XFS_BTREE_LONG_PTRS))
- return XFS_AGB_TO_FSB(cur->bc_mp, cur->bc_ag.pag->pag_agno, 0);
+
return NULLFSBLOCK;
}
diff --git a/fs/xfs/scrub/trace.h b/fs/xfs/scrub/trace.h
index a7bbb84f91a7..93ece6df02e3 100644
--- a/fs/xfs/scrub/trace.h
+++ b/fs/xfs/scrub/trace.h
@@ -348,7 +348,7 @@ TRACE_EVENT(xchk_btree_op_error,
__entry->level = level;
__entry->agno = XFS_FSB_TO_AGNO(cur->bc_mp, fsbno);
__entry->bno = XFS_FSB_TO_AGBNO(cur->bc_mp, fsbno);
- __entry->ptr = cur->bc_ptrs[level];
+ __entry->ptr = cur->bc_levels[level].ptr;
__entry->error = error;
__entry->ret_ip = ret_ip;
),
@@ -389,7 +389,7 @@ TRACE_EVENT(xchk_ifork_btree_op_error,
__entry->type = sc->sm->sm_type;
__entry->btnum = cur->bc_btnum;
__entry->level = level;
- __entry->ptr = cur->bc_ptrs[level];
+ __entry->ptr = cur->bc_levels[level].ptr;
__entry->agno = XFS_FSB_TO_AGNO(cur->bc_mp, fsbno);
__entry->bno = XFS_FSB_TO_AGBNO(cur->bc_mp, fsbno);
__entry->error = error;
@@ -431,7 +431,7 @@ TRACE_EVENT(xchk_btree_error,
__entry->level = level;
__entry->agno = XFS_FSB_TO_AGNO(cur->bc_mp, fsbno);
__entry->bno = XFS_FSB_TO_AGBNO(cur->bc_mp, fsbno);
- __entry->ptr = cur->bc_ptrs[level];
+ __entry->ptr = cur->bc_levels[level].ptr;
__entry->ret_ip = ret_ip;
),
TP_printk("dev %d:%d type %s btree %s level %d ptr %d agno 0x%x agbno 0x%x ret_ip %pS",
@@ -471,7 +471,7 @@ TRACE_EVENT(xchk_ifork_btree_error,
__entry->level = level;
__entry->agno = XFS_FSB_TO_AGNO(cur->bc_mp, fsbno);
__entry->bno = XFS_FSB_TO_AGBNO(cur->bc_mp, fsbno);
- __entry->ptr = cur->bc_ptrs[level];
+ __entry->ptr = cur->bc_levels[level].ptr;
__entry->ret_ip = ret_ip;
),
TP_printk("dev %d:%d ino 0x%llx fork %s type %s btree %s level %d ptr %d agno 0x%x agbno 0x%x ret_ip %pS",
@@ -511,7 +511,7 @@ DECLARE_EVENT_CLASS(xchk_sbtree_class,
__entry->bno = XFS_FSB_TO_AGBNO(cur->bc_mp, fsbno);
__entry->level = level;
__entry->nlevels = cur->bc_nlevels;
- __entry->ptr = cur->bc_ptrs[level];
+ __entry->ptr = cur->bc_levels[level].ptr;
),
TP_printk("dev %d:%d type %s btree %s agno 0x%x agbno 0x%x level %d nlevels %d ptr %d",
MAJOR(__entry->dev), MINOR(__entry->dev),
diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c
index 34fc6148032a..c8c15c3c3147 100644
--- a/fs/xfs/xfs_aops.c
+++ b/fs/xfs/xfs_aops.c
@@ -82,6 +82,7 @@ xfs_end_ioend(
struct iomap_ioend *ioend)
{
struct xfs_inode *ip = XFS_I(ioend->io_inode);
+ struct xfs_mount *mp = ip->i_mount;
xfs_off_t offset = ioend->io_offset;
size_t size = ioend->io_size;
unsigned int nofs_flag;
@@ -97,18 +98,26 @@ xfs_end_ioend(
/*
* Just clean up the in-memory structures if the fs has been shut down.
*/
- if (xfs_is_shutdown(ip->i_mount)) {
+ if (xfs_is_shutdown(mp)) {
error = -EIO;
goto done;
}
/*
- * Clean up any COW blocks on an I/O error.
+ * Clean up all COW blocks and underlying data fork delalloc blocks on
+ * I/O error. The delalloc punch is required because this ioend was
+ * mapped to blocks in the COW fork and the associated pages are no
+ * longer dirty. If we don't remove delalloc blocks here, they become
+ * stale and can corrupt free space accounting on unmount.
*/
error = blk_status_to_errno(ioend->io_bio->bi_status);
if (unlikely(error)) {
- if (ioend->io_flags & IOMAP_F_SHARED)
+ if (ioend->io_flags & IOMAP_F_SHARED) {
xfs_reflink_cancel_cow_range(ip, offset, size, true);
+ xfs_bmap_punch_delalloc_range(ip,
+ XFS_B_TO_FSBT(mp, offset),
+ XFS_B_TO_FSB(mp, size));
+ }
goto done;
}
diff --git a/fs/xfs/xfs_attr_inactive.c b/fs/xfs/xfs_attr_inactive.c
index 2b5da6218977..27265771f247 100644
--- a/fs/xfs/xfs_attr_inactive.c
+++ b/fs/xfs/xfs_attr_inactive.c
@@ -390,7 +390,7 @@ out_destroy_fork:
/* kill the in-core attr fork before we drop the inode lock */
if (dp->i_afp) {
xfs_idestroy_fork(dp->i_afp);
- kmem_cache_free(xfs_ifork_zone, dp->i_afp);
+ kmem_cache_free(xfs_ifork_cache, dp->i_afp);
dp->i_afp = NULL;
}
if (lock_mode)
diff --git a/fs/xfs/xfs_bmap_item.c b/fs/xfs/xfs_bmap_item.c
index 03159970133f..e1f4d7d5a011 100644
--- a/fs/xfs/xfs_bmap_item.c
+++ b/fs/xfs/xfs_bmap_item.c
@@ -25,8 +25,8 @@
#include "xfs_log_priv.h"
#include "xfs_log_recover.h"
-kmem_zone_t *xfs_bui_zone;
-kmem_zone_t *xfs_bud_zone;
+struct kmem_cache *xfs_bui_cache;
+struct kmem_cache *xfs_bud_cache;
static const struct xfs_item_ops xfs_bui_item_ops;
@@ -39,7 +39,7 @@ STATIC void
xfs_bui_item_free(
struct xfs_bui_log_item *buip)
{
- kmem_cache_free(xfs_bui_zone, buip);
+ kmem_cache_free(xfs_bui_cache, buip);
}
/*
@@ -138,7 +138,7 @@ xfs_bui_init(
{
struct xfs_bui_log_item *buip;
- buip = kmem_cache_zalloc(xfs_bui_zone, GFP_KERNEL | __GFP_NOFAIL);
+ buip = kmem_cache_zalloc(xfs_bui_cache, GFP_KERNEL | __GFP_NOFAIL);
xfs_log_item_init(mp, &buip->bui_item, XFS_LI_BUI, &xfs_bui_item_ops);
buip->bui_format.bui_nextents = XFS_BUI_MAX_FAST_EXTENTS;
@@ -198,7 +198,7 @@ xfs_bud_item_release(
struct xfs_bud_log_item *budp = BUD_ITEM(lip);
xfs_bui_release(budp->bud_buip);
- kmem_cache_free(xfs_bud_zone, budp);
+ kmem_cache_free(xfs_bud_cache, budp);
}
static const struct xfs_item_ops xfs_bud_item_ops = {
@@ -215,7 +215,7 @@ xfs_trans_get_bud(
{
struct xfs_bud_log_item *budp;
- budp = kmem_cache_zalloc(xfs_bud_zone, GFP_KERNEL | __GFP_NOFAIL);
+ budp = kmem_cache_zalloc(xfs_bud_cache, GFP_KERNEL | __GFP_NOFAIL);
xfs_log_item_init(tp->t_mountp, &budp->bud_item, XFS_LI_BUD,
&xfs_bud_item_ops);
budp->bud_buip = buip;
@@ -384,7 +384,7 @@ xfs_bmap_update_finish_item(
bmap->bi_bmap.br_blockcount = count;
return -EAGAIN;
}
- kmem_free(bmap);
+ kmem_cache_free(xfs_bmap_intent_cache, bmap);
return error;
}
@@ -404,7 +404,7 @@ xfs_bmap_update_cancel_item(
struct xfs_bmap_intent *bmap;
bmap = container_of(item, struct xfs_bmap_intent, bi_list);
- kmem_free(bmap);
+ kmem_cache_free(xfs_bmap_intent_cache, bmap);
}
const struct xfs_defer_op_type xfs_bmap_update_defer_type = {
@@ -532,7 +532,7 @@ xfs_bui_item_recover(
* Commit transaction, which frees the transaction and saves the inode
* for later replay activities.
*/
- error = xfs_defer_ops_capture_and_commit(tp, ip, capture_list);
+ error = xfs_defer_ops_capture_and_commit(tp, capture_list);
if (error)
goto err_unlock;
diff --git a/fs/xfs/xfs_bmap_item.h b/fs/xfs/xfs_bmap_item.h
index b9be62f8bd52..3fafd3881a0b 100644
--- a/fs/xfs/xfs_bmap_item.h
+++ b/fs/xfs/xfs_bmap_item.h
@@ -25,7 +25,7 @@
/* kernel only BUI/BUD definitions */
struct xfs_mount;
-struct kmem_zone;
+struct kmem_cache;
/*
* Max number of extents in fast allocation path.
@@ -65,7 +65,7 @@ struct xfs_bud_log_item {
struct xfs_bud_log_format bud_format;
};
-extern struct kmem_zone *xfs_bui_zone;
-extern struct kmem_zone *xfs_bud_zone;
+extern struct kmem_cache *xfs_bui_cache;
+extern struct kmem_cache *xfs_bud_cache;
#endif /* __XFS_BMAP_ITEM_H__ */
diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c
index 5fa6cd947dd4..631c5a61d89b 100644
--- a/fs/xfs/xfs_buf.c
+++ b/fs/xfs/xfs_buf.c
@@ -20,7 +20,7 @@
#include "xfs_error.h"
#include "xfs_ag.h"
-static kmem_zone_t *xfs_buf_zone;
+static struct kmem_cache *xfs_buf_cache;
/*
* Locking orders
@@ -220,7 +220,7 @@ _xfs_buf_alloc(
int i;
*bpp = NULL;
- bp = kmem_cache_zalloc(xfs_buf_zone, GFP_NOFS | __GFP_NOFAIL);
+ bp = kmem_cache_zalloc(xfs_buf_cache, GFP_NOFS | __GFP_NOFAIL);
/*
* We don't want certain flags to appear in b_flags unless they are
@@ -247,7 +247,7 @@ _xfs_buf_alloc(
*/
error = xfs_buf_get_maps(bp, nmaps);
if (error) {
- kmem_cache_free(xfs_buf_zone, bp);
+ kmem_cache_free(xfs_buf_cache, bp);
return error;
}
@@ -307,7 +307,7 @@ xfs_buf_free(
kmem_free(bp->b_addr);
xfs_buf_free_maps(bp);
- kmem_cache_free(xfs_buf_zone, bp);
+ kmem_cache_free(xfs_buf_cache, bp);
}
static int
@@ -2258,12 +2258,12 @@ xfs_buf_delwri_pushbuf(
int __init
xfs_buf_init(void)
{
- xfs_buf_zone = kmem_cache_create("xfs_buf", sizeof(struct xfs_buf), 0,
+ xfs_buf_cache = kmem_cache_create("xfs_buf", sizeof(struct xfs_buf), 0,
SLAB_HWCACHE_ALIGN |
SLAB_RECLAIM_ACCOUNT |
SLAB_MEM_SPREAD,
NULL);
- if (!xfs_buf_zone)
+ if (!xfs_buf_cache)
goto out;
return 0;
@@ -2275,7 +2275,7 @@ xfs_buf_init(void)
void
xfs_buf_terminate(void)
{
- kmem_cache_destroy(xfs_buf_zone);
+ kmem_cache_destroy(xfs_buf_cache);
}
void xfs_buf_set_ref(struct xfs_buf *bp, int lru_ref)
diff --git a/fs/xfs/xfs_buf_item.c b/fs/xfs/xfs_buf_item.c
index b1ab100c09e1..a7a8e4528881 100644
--- a/fs/xfs/xfs_buf_item.c
+++ b/fs/xfs/xfs_buf_item.c
@@ -23,7 +23,7 @@
#include "xfs_log.h"
-kmem_zone_t *xfs_buf_item_zone;
+struct kmem_cache *xfs_buf_item_cache;
static inline struct xfs_buf_log_item *BUF_ITEM(struct xfs_log_item *lip)
{
@@ -804,7 +804,7 @@ xfs_buf_item_init(
return 0;
}
- bip = kmem_cache_zalloc(xfs_buf_item_zone, GFP_KERNEL | __GFP_NOFAIL);
+ bip = kmem_cache_zalloc(xfs_buf_item_cache, GFP_KERNEL | __GFP_NOFAIL);
xfs_log_item_init(mp, &bip->bli_item, XFS_LI_BUF, &xfs_buf_item_ops);
bip->bli_buf = bp;
@@ -825,7 +825,7 @@ xfs_buf_item_init(
map_size = DIV_ROUND_UP(chunks, NBWORD);
if (map_size > XFS_BLF_DATAMAP_SIZE) {
- kmem_cache_free(xfs_buf_item_zone, bip);
+ kmem_cache_free(xfs_buf_item_cache, bip);
xfs_err(mp,
"buffer item dirty bitmap (%u uints) too small to reflect %u bytes!",
map_size,
@@ -1002,7 +1002,7 @@ xfs_buf_item_free(
{
xfs_buf_item_free_format(bip);
kmem_free(bip->bli_item.li_lv_shadow);
- kmem_cache_free(xfs_buf_item_zone, bip);
+ kmem_cache_free(xfs_buf_item_cache, bip);
}
/*
diff --git a/fs/xfs/xfs_buf_item.h b/fs/xfs/xfs_buf_item.h
index 50aa0f5ef959..e11e9ef2338f 100644
--- a/fs/xfs/xfs_buf_item.h
+++ b/fs/xfs/xfs_buf_item.h
@@ -71,6 +71,6 @@ static inline void xfs_buf_dquot_io_fail(struct xfs_buf *bp)
void xfs_buf_iodone(struct xfs_buf *);
bool xfs_buf_log_check_iovec(struct xfs_log_iovec *iovec);
-extern kmem_zone_t *xfs_buf_item_zone;
+extern struct kmem_cache *xfs_buf_item_cache;
#endif /* __XFS_BUF_ITEM_H__ */
diff --git a/fs/xfs/xfs_buf_item_recover.c b/fs/xfs/xfs_buf_item_recover.c
index a476c7ef5d53..70ca5751b13e 100644
--- a/fs/xfs/xfs_buf_item_recover.c
+++ b/fs/xfs/xfs_buf_item_recover.c
@@ -603,7 +603,7 @@ xlog_recover_do_inode_buffer(
inodes_per_buf = BBTOB(bp->b_length) >> mp->m_sb.sb_inodelog;
for (i = 0; i < inodes_per_buf; i++) {
next_unlinked_offset = (i * mp->m_sb.sb_inodesize) +
- offsetof(xfs_dinode_t, di_next_unlinked);
+ offsetof(struct xfs_dinode, di_next_unlinked);
while (next_unlinked_offset >=
(reg_buf_offset + reg_buf_bytes)) {
diff --git a/fs/xfs/xfs_dquot.c b/fs/xfs/xfs_dquot.c
index c15d61d47a06..e48ae227bb11 100644
--- a/fs/xfs/xfs_dquot.c
+++ b/fs/xfs/xfs_dquot.c
@@ -38,8 +38,8 @@
* otherwise by the lowest id first, see xfs_dqlock2.
*/
-struct kmem_zone *xfs_qm_dqtrxzone;
-static struct kmem_zone *xfs_qm_dqzone;
+struct kmem_cache *xfs_dqtrx_cache;
+static struct kmem_cache *xfs_dquot_cache;
static struct lock_class_key xfs_dquot_group_class;
static struct lock_class_key xfs_dquot_project_class;
@@ -57,7 +57,7 @@ xfs_qm_dqdestroy(
mutex_destroy(&dqp->q_qlock);
XFS_STATS_DEC(dqp->q_mount, xs_qm_dquot);
- kmem_cache_free(xfs_qm_dqzone, dqp);
+ kmem_cache_free(xfs_dquot_cache, dqp);
}
/*
@@ -458,7 +458,7 @@ xfs_dquot_alloc(
{
struct xfs_dquot *dqp;
- dqp = kmem_cache_zalloc(xfs_qm_dqzone, GFP_KERNEL | __GFP_NOFAIL);
+ dqp = kmem_cache_zalloc(xfs_dquot_cache, GFP_KERNEL | __GFP_NOFAIL);
dqp->q_type = type;
dqp->q_id = id;
@@ -471,7 +471,7 @@ xfs_dquot_alloc(
* Offset of dquot in the (fixed sized) dquot chunk.
*/
dqp->q_bufoffset = (id % mp->m_quotainfo->qi_dqperchunk) *
- sizeof(xfs_dqblk_t);
+ sizeof(struct xfs_dqblk);
/*
* Because we want to use a counting completion, complete
@@ -1363,22 +1363,22 @@ xfs_dqlock2(
int __init
xfs_qm_init(void)
{
- xfs_qm_dqzone = kmem_cache_create("xfs_dquot",
+ xfs_dquot_cache = kmem_cache_create("xfs_dquot",
sizeof(struct xfs_dquot),
0, 0, NULL);
- if (!xfs_qm_dqzone)
+ if (!xfs_dquot_cache)
goto out;
- xfs_qm_dqtrxzone = kmem_cache_create("xfs_dqtrx",
+ xfs_dqtrx_cache = kmem_cache_create("xfs_dqtrx",
sizeof(struct xfs_dquot_acct),
0, 0, NULL);
- if (!xfs_qm_dqtrxzone)
- goto out_free_dqzone;
+ if (!xfs_dqtrx_cache)
+ goto out_free_dquot_cache;
return 0;
-out_free_dqzone:
- kmem_cache_destroy(xfs_qm_dqzone);
+out_free_dquot_cache:
+ kmem_cache_destroy(xfs_dquot_cache);
out:
return -ENOMEM;
}
@@ -1386,8 +1386,8 @@ out:
void
xfs_qm_exit(void)
{
- kmem_cache_destroy(xfs_qm_dqtrxzone);
- kmem_cache_destroy(xfs_qm_dqzone);
+ kmem_cache_destroy(xfs_dqtrx_cache);
+ kmem_cache_destroy(xfs_dquot_cache);
}
/*
diff --git a/fs/xfs/xfs_extfree_item.c b/fs/xfs/xfs_extfree_item.c
index 3f8a0713573a..47ef9c9c5c17 100644
--- a/fs/xfs/xfs_extfree_item.c
+++ b/fs/xfs/xfs_extfree_item.c
@@ -25,8 +25,8 @@
#include "xfs_log_priv.h"
#include "xfs_log_recover.h"
-kmem_zone_t *xfs_efi_zone;
-kmem_zone_t *xfs_efd_zone;
+struct kmem_cache *xfs_efi_cache;
+struct kmem_cache *xfs_efd_cache;
static const struct xfs_item_ops xfs_efi_item_ops;
@@ -43,7 +43,7 @@ xfs_efi_item_free(
if (efip->efi_format.efi_nextents > XFS_EFI_MAX_FAST_EXTENTS)
kmem_free(efip);
else
- kmem_cache_free(xfs_efi_zone, efip);
+ kmem_cache_free(xfs_efi_cache, efip);
}
/*
@@ -161,7 +161,7 @@ xfs_efi_init(
((nextents - 1) * sizeof(xfs_extent_t)));
efip = kmem_zalloc(size, 0);
} else {
- efip = kmem_cache_zalloc(xfs_efi_zone,
+ efip = kmem_cache_zalloc(xfs_efi_cache,
GFP_KERNEL | __GFP_NOFAIL);
}
@@ -241,7 +241,7 @@ xfs_efd_item_free(struct xfs_efd_log_item *efdp)
if (efdp->efd_format.efd_nextents > XFS_EFD_MAX_FAST_EXTENTS)
kmem_free(efdp);
else
- kmem_cache_free(xfs_efd_zone, efdp);
+ kmem_cache_free(xfs_efd_cache, efdp);
}
/*
@@ -333,7 +333,7 @@ xfs_trans_get_efd(
(nextents - 1) * sizeof(struct xfs_extent),
0);
} else {
- efdp = kmem_cache_zalloc(xfs_efd_zone,
+ efdp = kmem_cache_zalloc(xfs_efd_cache,
GFP_KERNEL | __GFP_NOFAIL);
}
@@ -474,15 +474,21 @@ xfs_extent_free_finish_item(
struct list_head *item,
struct xfs_btree_cur **state)
{
+ struct xfs_owner_info oinfo = { };
struct xfs_extent_free_item *free;
int error;
free = container_of(item, struct xfs_extent_free_item, xefi_list);
+ oinfo.oi_owner = free->xefi_owner;
+ if (free->xefi_flags & XFS_EFI_ATTR_FORK)
+ oinfo.oi_flags |= XFS_OWNER_INFO_ATTR_FORK;
+ if (free->xefi_flags & XFS_EFI_BMBT_BLOCK)
+ oinfo.oi_flags |= XFS_OWNER_INFO_BMBT_BLOCK;
error = xfs_trans_free_extent(tp, EFD_ITEM(done),
free->xefi_startblock,
free->xefi_blockcount,
- &free->xefi_oinfo, free->xefi_skip_discard);
- kmem_free(free);
+ &oinfo, free->xefi_flags & XFS_EFI_SKIP_DISCARD);
+ kmem_cache_free(xfs_extfree_item_cache, free);
return error;
}
@@ -502,7 +508,7 @@ xfs_extent_free_cancel_item(
struct xfs_extent_free_item *free;
free = container_of(item, struct xfs_extent_free_item, xefi_list);
- kmem_free(free);
+ kmem_cache_free(xfs_extfree_item_cache, free);
}
const struct xfs_defer_op_type xfs_extent_free_defer_type = {
@@ -525,6 +531,7 @@ xfs_agfl_free_finish_item(
struct list_head *item,
struct xfs_btree_cur **state)
{
+ struct xfs_owner_info oinfo = { };
struct xfs_mount *mp = tp->t_mountp;
struct xfs_efd_log_item *efdp = EFD_ITEM(done);
struct xfs_extent_free_item *free;
@@ -539,13 +546,13 @@ xfs_agfl_free_finish_item(
ASSERT(free->xefi_blockcount == 1);
agno = XFS_FSB_TO_AGNO(mp, free->xefi_startblock);
agbno = XFS_FSB_TO_AGBNO(mp, free->xefi_startblock);
+ oinfo.oi_owner = free->xefi_owner;
trace_xfs_agfl_free_deferred(mp, agno, 0, agbno, free->xefi_blockcount);
error = xfs_alloc_read_agf(mp, tp, agno, 0, &agbp);
if (!error)
- error = xfs_free_agfl_block(tp, agno, agbno, agbp,
- &free->xefi_oinfo);
+ error = xfs_free_agfl_block(tp, agno, agbno, agbp, &oinfo);
/*
* Mark the transaction dirty, even on error. This ensures the
@@ -564,7 +571,7 @@ xfs_agfl_free_finish_item(
extp->ext_len = free->xefi_blockcount;
efdp->efd_next_extent++;
- kmem_free(free);
+ kmem_cache_free(xfs_extfree_item_cache, free);
return error;
}
@@ -637,7 +644,7 @@ xfs_efi_item_recover(
}
- return xfs_defer_ops_capture_and_commit(tp, NULL, capture_list);
+ return xfs_defer_ops_capture_and_commit(tp, capture_list);
abort_error:
xfs_trans_cancel(tp);
diff --git a/fs/xfs/xfs_extfree_item.h b/fs/xfs/xfs_extfree_item.h
index cd2860c875bf..186d0f2137f1 100644
--- a/fs/xfs/xfs_extfree_item.h
+++ b/fs/xfs/xfs_extfree_item.h
@@ -9,7 +9,7 @@
/* kernel only EFI/EFD definitions */
struct xfs_mount;
-struct kmem_zone;
+struct kmem_cache;
/*
* Max number of extents in fast allocation path.
@@ -69,7 +69,7 @@ struct xfs_efd_log_item {
*/
#define XFS_EFD_MAX_FAST_EXTENTS 16
-extern struct kmem_zone *xfs_efi_zone;
-extern struct kmem_zone *xfs_efd_zone;
+extern struct kmem_cache *xfs_efi_cache;
+extern struct kmem_cache *xfs_efd_cache;
#endif /* __XFS_EXTFREE_ITEM_H__ */
diff --git a/fs/xfs/xfs_icache.c b/fs/xfs/xfs_icache.c
index f2210d927481..e1472004170e 100644
--- a/fs/xfs/xfs_icache.c
+++ b/fs/xfs/xfs_icache.c
@@ -77,10 +77,10 @@ xfs_inode_alloc(
* XXX: If this didn't occur in transactions, we could drop GFP_NOFAIL
* and return NULL here on ENOMEM.
*/
- ip = kmem_cache_alloc(xfs_inode_zone, GFP_KERNEL | __GFP_NOFAIL);
+ ip = kmem_cache_alloc(xfs_inode_cache, GFP_KERNEL | __GFP_NOFAIL);
if (inode_init_always(mp->m_super, VFS_I(ip))) {
- kmem_cache_free(xfs_inode_zone, ip);
+ kmem_cache_free(xfs_inode_cache, ip);
return NULL;
}
@@ -130,11 +130,11 @@ xfs_inode_free_callback(
if (ip->i_afp) {
xfs_idestroy_fork(ip->i_afp);
- kmem_cache_free(xfs_ifork_zone, ip->i_afp);
+ kmem_cache_free(xfs_ifork_cache, ip->i_afp);
}
if (ip->i_cowfp) {
xfs_idestroy_fork(ip->i_cowfp);
- kmem_cache_free(xfs_ifork_zone, ip->i_cowfp);
+ kmem_cache_free(xfs_ifork_cache, ip->i_cowfp);
}
if (ip->i_itemp) {
ASSERT(!test_bit(XFS_LI_IN_AIL,
@@ -143,7 +143,7 @@ xfs_inode_free_callback(
ip->i_itemp = NULL;
}
- kmem_cache_free(xfs_inode_zone, ip);
+ kmem_cache_free(xfs_inode_cache, ip);
}
static void
diff --git a/fs/xfs/xfs_icreate_item.c b/fs/xfs/xfs_icreate_item.c
index 017904a34c02..508e184e3b8f 100644
--- a/fs/xfs/xfs_icreate_item.c
+++ b/fs/xfs/xfs_icreate_item.c
@@ -20,7 +20,7 @@
#include "xfs_ialloc.h"
#include "xfs_trace.h"
-kmem_zone_t *xfs_icreate_zone; /* inode create item zone */
+struct kmem_cache *xfs_icreate_cache; /* inode create item */
static inline struct xfs_icreate_item *ICR_ITEM(struct xfs_log_item *lip)
{
@@ -63,7 +63,7 @@ STATIC void
xfs_icreate_item_release(
struct xfs_log_item *lip)
{
- kmem_cache_free(xfs_icreate_zone, ICR_ITEM(lip));
+ kmem_cache_free(xfs_icreate_cache, ICR_ITEM(lip));
}
static const struct xfs_item_ops xfs_icreate_item_ops = {
@@ -97,7 +97,7 @@ xfs_icreate_log(
{
struct xfs_icreate_item *icp;
- icp = kmem_cache_zalloc(xfs_icreate_zone, GFP_KERNEL | __GFP_NOFAIL);
+ icp = kmem_cache_zalloc(xfs_icreate_cache, GFP_KERNEL | __GFP_NOFAIL);
xfs_log_item_init(tp->t_mountp, &icp->ic_item, XFS_LI_ICREATE,
&xfs_icreate_item_ops);
diff --git a/fs/xfs/xfs_icreate_item.h b/fs/xfs/xfs_icreate_item.h
index a50d0b01e15a..64992823108a 100644
--- a/fs/xfs/xfs_icreate_item.h
+++ b/fs/xfs/xfs_icreate_item.h
@@ -12,7 +12,7 @@ struct xfs_icreate_item {
struct xfs_icreate_log ic_format;
};
-extern kmem_zone_t *xfs_icreate_zone; /* inode create item zone */
+extern struct kmem_cache *xfs_icreate_cache; /* inode create item */
void xfs_icreate_log(struct xfs_trans *tp, xfs_agnumber_t agno,
xfs_agblock_t agbno, unsigned int count,
diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
index a4f6f034fb81..64b9bf334806 100644
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -36,7 +36,7 @@
#include "xfs_reflink.h"
#include "xfs_ag.h"
-kmem_zone_t *xfs_inode_zone;
+struct kmem_cache *xfs_inode_cache;
/*
* Used in xfs_itruncate_extents(). This is the maximum number of extents
@@ -564,8 +564,6 @@ xfs_lock_two_inodes(
struct xfs_inode *ip1,
uint ip1_mode)
{
- struct xfs_inode *temp;
- uint mode_temp;
int attempts = 0;
struct xfs_log_item *lp;
@@ -578,12 +576,8 @@ xfs_lock_two_inodes(
ASSERT(ip0->i_ino != ip1->i_ino);
if (ip0->i_ino > ip1->i_ino) {
- temp = ip0;
- ip0 = ip1;
- ip1 = temp;
- mode_temp = ip0_mode;
- ip0_mode = ip1_mode;
- ip1_mode = mode_temp;
+ swap(ip0, ip1);
+ swap(ip0_mode, ip1_mode);
}
again:
diff --git a/fs/xfs/xfs_inode.h b/fs/xfs/xfs_inode.h
index b21b177832d1..e635a3d64cba 100644
--- a/fs/xfs/xfs_inode.h
+++ b/fs/xfs/xfs_inode.h
@@ -504,7 +504,7 @@ static inline void xfs_setup_existing_inode(struct xfs_inode *ip)
void xfs_irele(struct xfs_inode *ip);
-extern struct kmem_zone *xfs_inode_zone;
+extern struct kmem_cache *xfs_inode_cache;
/* The default CoW extent size hint. */
#define XFS_DEFAULT_COWEXTSZ_HINT 32
diff --git a/fs/xfs/xfs_inode_item.c b/fs/xfs/xfs_inode_item.c
index 0659d19c211e..90d8e591baf8 100644
--- a/fs/xfs/xfs_inode_item.c
+++ b/fs/xfs/xfs_inode_item.c
@@ -21,7 +21,7 @@
#include <linux/iversion.h>
-kmem_zone_t *xfs_ili_zone; /* inode log item zone */
+struct kmem_cache *xfs_ili_cache; /* inode log item */
static inline struct xfs_inode_log_item *INODE_ITEM(struct xfs_log_item *lip)
{
@@ -672,7 +672,7 @@ xfs_inode_item_init(
struct xfs_inode_log_item *iip;
ASSERT(ip->i_itemp == NULL);
- iip = ip->i_itemp = kmem_cache_zalloc(xfs_ili_zone,
+ iip = ip->i_itemp = kmem_cache_zalloc(xfs_ili_cache,
GFP_KERNEL | __GFP_NOFAIL);
iip->ili_inode = ip;
@@ -694,7 +694,7 @@ xfs_inode_item_destroy(
ip->i_itemp = NULL;
kmem_free(iip->ili_item.li_lv_shadow);
- kmem_cache_free(xfs_ili_zone, iip);
+ kmem_cache_free(xfs_ili_cache, iip);
}
diff --git a/fs/xfs/xfs_inode_item.h b/fs/xfs/xfs_inode_item.h
index 403b45ab9aa2..1a302000d604 100644
--- a/fs/xfs/xfs_inode_item.h
+++ b/fs/xfs/xfs_inode_item.h
@@ -47,6 +47,6 @@ extern void xfs_iflush_abort(struct xfs_inode *);
extern int xfs_inode_item_format_convert(xfs_log_iovec_t *,
struct xfs_inode_log_format *);
-extern struct kmem_zone *xfs_ili_zone;
+extern struct kmem_cache *xfs_ili_cache;
#endif /* __XFS_INODE_ITEM_H__ */
diff --git a/fs/xfs/xfs_log.c b/fs/xfs/xfs_log.c
index f6cd2d4aa770..89fec9a18c34 100644
--- a/fs/xfs/xfs_log.c
+++ b/fs/xfs/xfs_log.c
@@ -21,7 +21,7 @@
#include "xfs_sb.h"
#include "xfs_health.h"
-kmem_zone_t *xfs_log_ticket_zone;
+struct kmem_cache *xfs_log_ticket_cache;
/* Local miscellaneous function prototypes */
STATIC struct xlog *
@@ -3487,7 +3487,7 @@ xfs_log_ticket_put(
{
ASSERT(atomic_read(&ticket->t_ref) > 0);
if (atomic_dec_and_test(&ticket->t_ref))
- kmem_cache_free(xfs_log_ticket_zone, ticket);
+ kmem_cache_free(xfs_log_ticket_cache, ticket);
}
xlog_ticket_t *
@@ -3611,7 +3611,7 @@ xlog_ticket_alloc(
struct xlog_ticket *tic;
int unit_res;
- tic = kmem_cache_zalloc(xfs_log_ticket_zone, GFP_NOFS | __GFP_NOFAIL);
+ tic = kmem_cache_zalloc(xfs_log_ticket_cache, GFP_NOFS | __GFP_NOFAIL);
unit_res = xlog_calc_unit_res(log, unit_bytes);
diff --git a/fs/xfs/xfs_log_priv.h b/fs/xfs/xfs_log_priv.h
index 844fbeec3545..23103d68423c 100644
--- a/fs/xfs/xfs_log_priv.h
+++ b/fs/xfs/xfs_log_priv.h
@@ -497,7 +497,7 @@ xlog_recover_cancel(struct xlog *);
extern __le32 xlog_cksum(struct xlog *log, struct xlog_rec_header *rhead,
char *dp, int size);
-extern kmem_zone_t *xfs_log_ticket_zone;
+extern struct kmem_cache *xfs_log_ticket_cache;
struct xlog_ticket *
xlog_ticket_alloc(
struct xlog *log,
diff --git a/fs/xfs/xfs_log_recover.c b/fs/xfs/xfs_log_recover.c
index 10562ecbd9ea..53366cc0bc9e 100644
--- a/fs/xfs/xfs_log_recover.c
+++ b/fs/xfs/xfs_log_recover.c
@@ -2466,11 +2466,11 @@ xlog_finish_defer_ops(
{
struct xfs_defer_capture *dfc, *next;
struct xfs_trans *tp;
- struct xfs_inode *ip;
int error = 0;
list_for_each_entry_safe(dfc, next, capture_list, dfc_list) {
struct xfs_trans_res resv;
+ struct xfs_defer_resources dres;
/*
* Create a new transaction reservation from the captured
@@ -2494,13 +2494,9 @@ xlog_finish_defer_ops(
* from recovering a single intent item.
*/
list_del_init(&dfc->dfc_list);
- xfs_defer_ops_continue(dfc, tp, &ip);
-
+ xfs_defer_ops_continue(dfc, tp, &dres);
error = xfs_trans_commit(tp);
- if (ip) {
- xfs_iunlock(ip, XFS_ILOCK_EXCL);
- xfs_irele(ip);
- }
+ xfs_defer_resources_rele(&dres);
if (error)
return error;
}
@@ -2520,7 +2516,7 @@ xlog_abort_defer_ops(
list_for_each_entry_safe(dfc, next, capture_list, dfc_list) {
list_del_init(&dfc->dfc_list);
- xfs_defer_ops_release(mp, dfc);
+ xfs_defer_ops_capture_free(mp, dfc);
}
}
/*
diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c
index 06dac09eddbd..359109b6f0d3 100644
--- a/fs/xfs/xfs_mount.c
+++ b/fs/xfs/xfs_mount.c
@@ -567,6 +567,18 @@ xfs_mount_setup_inode_geom(
xfs_ialloc_setup_geometry(mp);
}
+/* Compute maximum possible height for per-AG btree types for this fs. */
+static inline void
+xfs_agbtree_compute_maxlevels(
+ struct xfs_mount *mp)
+{
+ unsigned int levels;
+
+ levels = max(mp->m_alloc_maxlevels, M_IGEO(mp)->inobt_maxlevels);
+ levels = max(levels, mp->m_rmap_maxlevels);
+ mp->m_agbtree_maxlevels = max(levels, mp->m_refc_maxlevels);
+}
+
/*
* This function does the following on an initial mount of a file system:
* - reads the superblock from disk and init the mount struct
@@ -638,6 +650,8 @@ xfs_mountfs(
xfs_rmapbt_compute_maxlevels(mp);
xfs_refcountbt_compute_maxlevels(mp);
+ xfs_agbtree_compute_maxlevels(mp);
+
/*
* Check if sb_agblocks is aligned at stripe boundary. If sb_agblocks
* is NOT aligned turn off m_dalign since allocator alignment is within
diff --git a/fs/xfs/xfs_mount.h b/fs/xfs/xfs_mount.h
index e091f3b3fa15..00720a02e761 100644
--- a/fs/xfs/xfs_mount.h
+++ b/fs/xfs/xfs_mount.h
@@ -128,10 +128,11 @@ typedef struct xfs_mount {
uint m_rmap_mnr[2]; /* min rmap btree records */
uint m_refc_mxr[2]; /* max refc btree records */
uint m_refc_mnr[2]; /* min refc btree records */
- uint m_ag_maxlevels; /* XFS_AG_MAXLEVELS */
- uint m_bm_maxlevels[2]; /* XFS_BM_MAXLEVELS */
+ uint m_alloc_maxlevels; /* max alloc btree levels */
+ uint m_bm_maxlevels[2]; /* max bmap btree levels */
uint m_rmap_maxlevels; /* max rmap btree levels */
uint m_refc_maxlevels; /* max refcount btree level */
+ unsigned int m_agbtree_maxlevels; /* max level of all AG btrees */
xfs_extlen_t m_ag_prealloc_blocks; /* reserved ag blocks */
uint m_alloc_set_aside; /* space we can't use */
uint m_ag_max_usable; /* max space per AG */
diff --git a/fs/xfs/xfs_mru_cache.c b/fs/xfs/xfs_mru_cache.c
index 34c3b16f834f..f85e3b07ab44 100644
--- a/fs/xfs/xfs_mru_cache.c
+++ b/fs/xfs/xfs_mru_cache.c
@@ -219,7 +219,7 @@ _xfs_mru_cache_list_insert(
* When destroying or reaping, all the elements that were migrated to the reap
* list need to be deleted. For each element this involves removing it from the
* data store, removing it from the reap list, calling the client's free
- * function and deleting the element from the element zone.
+ * function and deleting the element from the element cache.
*
* We get called holding the mru->lock, which we drop and then reacquire.
* Sparse need special help with this to tell it we know what we are doing.
diff --git a/fs/xfs/xfs_qm.c b/fs/xfs/xfs_qm.c
index 5608066d6e53..32ac8d9c8940 100644
--- a/fs/xfs/xfs_qm.c
+++ b/fs/xfs/xfs_qm.c
@@ -850,7 +850,7 @@ xfs_qm_reset_dqcounts(
*/
#ifdef DEBUG
j = (int)XFS_FSB_TO_B(mp, XFS_DQUOT_CLUSTER_SIZE_FSB) /
- sizeof(xfs_dqblk_t);
+ sizeof(struct xfs_dqblk);
ASSERT(mp->m_quotainfo->qi_dqperchunk == j);
#endif
dqb = bp->b_addr;
diff --git a/fs/xfs/xfs_qm.h b/fs/xfs/xfs_qm.h
index 442a0f97a9d4..5bb12717ea28 100644
--- a/fs/xfs/xfs_qm.h
+++ b/fs/xfs/xfs_qm.h
@@ -11,7 +11,7 @@
struct xfs_inode;
-extern struct kmem_zone *xfs_qm_dqtrxzone;
+extern struct kmem_cache *xfs_dqtrx_cache;
/*
* Number of bmaps that we ask from bmapi when doing a quotacheck.
diff --git a/fs/xfs/xfs_refcount_item.c b/fs/xfs/xfs_refcount_item.c
index 46904b793bd4..d3da67772d57 100644
--- a/fs/xfs/xfs_refcount_item.c
+++ b/fs/xfs/xfs_refcount_item.c
@@ -21,8 +21,8 @@
#include "xfs_log_priv.h"
#include "xfs_log_recover.h"
-kmem_zone_t *xfs_cui_zone;
-kmem_zone_t *xfs_cud_zone;
+struct kmem_cache *xfs_cui_cache;
+struct kmem_cache *xfs_cud_cache;
static const struct xfs_item_ops xfs_cui_item_ops;
@@ -38,7 +38,7 @@ xfs_cui_item_free(
if (cuip->cui_format.cui_nextents > XFS_CUI_MAX_FAST_EXTENTS)
kmem_free(cuip);
else
- kmem_cache_free(xfs_cui_zone, cuip);
+ kmem_cache_free(xfs_cui_cache, cuip);
}
/*
@@ -143,7 +143,7 @@ xfs_cui_init(
cuip = kmem_zalloc(xfs_cui_log_item_sizeof(nextents),
0);
else
- cuip = kmem_cache_zalloc(xfs_cui_zone,
+ cuip = kmem_cache_zalloc(xfs_cui_cache,
GFP_KERNEL | __GFP_NOFAIL);
xfs_log_item_init(mp, &cuip->cui_item, XFS_LI_CUI, &xfs_cui_item_ops);
@@ -204,7 +204,7 @@ xfs_cud_item_release(
struct xfs_cud_log_item *cudp = CUD_ITEM(lip);
xfs_cui_release(cudp->cud_cuip);
- kmem_cache_free(xfs_cud_zone, cudp);
+ kmem_cache_free(xfs_cud_cache, cudp);
}
static const struct xfs_item_ops xfs_cud_item_ops = {
@@ -221,7 +221,7 @@ xfs_trans_get_cud(
{
struct xfs_cud_log_item *cudp;
- cudp = kmem_cache_zalloc(xfs_cud_zone, GFP_KERNEL | __GFP_NOFAIL);
+ cudp = kmem_cache_zalloc(xfs_cud_cache, GFP_KERNEL | __GFP_NOFAIL);
xfs_log_item_init(tp->t_mountp, &cudp->cud_item, XFS_LI_CUD,
&xfs_cud_item_ops);
cudp->cud_cuip = cuip;
@@ -384,7 +384,7 @@ xfs_refcount_update_finish_item(
refc->ri_blockcount = new_aglen;
return -EAGAIN;
}
- kmem_free(refc);
+ kmem_cache_free(xfs_refcount_intent_cache, refc);
return error;
}
@@ -404,7 +404,7 @@ xfs_refcount_update_cancel_item(
struct xfs_refcount_intent *refc;
refc = container_of(item, struct xfs_refcount_intent, ri_list);
- kmem_free(refc);
+ kmem_cache_free(xfs_refcount_intent_cache, refc);
}
const struct xfs_defer_op_type xfs_refcount_update_defer_type = {
@@ -557,7 +557,7 @@ xfs_cui_item_recover(
}
xfs_refcount_finish_one_cleanup(tp, rcur, error);
- return xfs_defer_ops_capture_and_commit(tp, NULL, capture_list);
+ return xfs_defer_ops_capture_and_commit(tp, capture_list);
abort_error:
xfs_refcount_finish_one_cleanup(tp, rcur, error);
diff --git a/fs/xfs/xfs_refcount_item.h b/fs/xfs/xfs_refcount_item.h
index f4f2e836540b..eb0ab13682d0 100644
--- a/fs/xfs/xfs_refcount_item.h
+++ b/fs/xfs/xfs_refcount_item.h
@@ -25,7 +25,7 @@
/* kernel only CUI/CUD definitions */
struct xfs_mount;
-struct kmem_zone;
+struct kmem_cache;
/*
* Max number of extents in fast allocation path.
@@ -68,7 +68,7 @@ struct xfs_cud_log_item {
struct xfs_cud_log_format cud_format;
};
-extern struct kmem_zone *xfs_cui_zone;
-extern struct kmem_zone *xfs_cud_zone;
+extern struct kmem_cache *xfs_cui_cache;
+extern struct kmem_cache *xfs_cud_cache;
#endif /* __XFS_REFCOUNT_ITEM_H__ */
diff --git a/fs/xfs/xfs_reflink.c b/fs/xfs/xfs_reflink.c
index 76355f293488..cb0edb1d68ef 100644
--- a/fs/xfs/xfs_reflink.c
+++ b/fs/xfs/xfs_reflink.c
@@ -484,7 +484,7 @@ xfs_reflink_cancel_cow_blocks(
xfs_refcount_free_cow_extent(*tpp, del.br_startblock,
del.br_blockcount);
- xfs_bmap_add_free(*tpp, del.br_startblock,
+ xfs_free_extent_later(*tpp, del.br_startblock,
del.br_blockcount, NULL);
/* Roll the transaction */
diff --git a/fs/xfs/xfs_rmap_item.c b/fs/xfs/xfs_rmap_item.c
index 5f0695980467..c3966b4c58ef 100644
--- a/fs/xfs/xfs_rmap_item.c
+++ b/fs/xfs/xfs_rmap_item.c
@@ -21,8 +21,8 @@
#include "xfs_log_priv.h"
#include "xfs_log_recover.h"
-kmem_zone_t *xfs_rui_zone;
-kmem_zone_t *xfs_rud_zone;
+struct kmem_cache *xfs_rui_cache;
+struct kmem_cache *xfs_rud_cache;
static const struct xfs_item_ops xfs_rui_item_ops;
@@ -38,7 +38,7 @@ xfs_rui_item_free(
if (ruip->rui_format.rui_nextents > XFS_RUI_MAX_FAST_EXTENTS)
kmem_free(ruip);
else
- kmem_cache_free(xfs_rui_zone, ruip);
+ kmem_cache_free(xfs_rui_cache, ruip);
}
/*
@@ -141,7 +141,7 @@ xfs_rui_init(
if (nextents > XFS_RUI_MAX_FAST_EXTENTS)
ruip = kmem_zalloc(xfs_rui_log_item_sizeof(nextents), 0);
else
- ruip = kmem_cache_zalloc(xfs_rui_zone,
+ ruip = kmem_cache_zalloc(xfs_rui_cache,
GFP_KERNEL | __GFP_NOFAIL);
xfs_log_item_init(mp, &ruip->rui_item, XFS_LI_RUI, &xfs_rui_item_ops);
@@ -227,7 +227,7 @@ xfs_rud_item_release(
struct xfs_rud_log_item *rudp = RUD_ITEM(lip);
xfs_rui_release(rudp->rud_ruip);
- kmem_cache_free(xfs_rud_zone, rudp);
+ kmem_cache_free(xfs_rud_cache, rudp);
}
static const struct xfs_item_ops xfs_rud_item_ops = {
@@ -244,7 +244,7 @@ xfs_trans_get_rud(
{
struct xfs_rud_log_item *rudp;
- rudp = kmem_cache_zalloc(xfs_rud_zone, GFP_KERNEL | __GFP_NOFAIL);
+ rudp = kmem_cache_zalloc(xfs_rud_cache, GFP_KERNEL | __GFP_NOFAIL);
xfs_log_item_init(tp->t_mountp, &rudp->rud_item, XFS_LI_RUD,
&xfs_rud_item_ops);
rudp->rud_ruip = ruip;
@@ -427,7 +427,7 @@ xfs_rmap_update_finish_item(
rmap->ri_bmap.br_startoff, rmap->ri_bmap.br_startblock,
rmap->ri_bmap.br_blockcount, rmap->ri_bmap.br_state,
state);
- kmem_free(rmap);
+ kmem_cache_free(xfs_rmap_intent_cache, rmap);
return error;
}
@@ -447,7 +447,7 @@ xfs_rmap_update_cancel_item(
struct xfs_rmap_intent *rmap;
rmap = container_of(item, struct xfs_rmap_intent, ri_list);
- kmem_free(rmap);
+ kmem_cache_free(xfs_rmap_intent_cache, rmap);
}
const struct xfs_defer_op_type xfs_rmap_update_defer_type = {
@@ -587,7 +587,7 @@ xfs_rui_item_recover(
}
xfs_rmap_finish_one_cleanup(tp, rcur, error);
- return xfs_defer_ops_capture_and_commit(tp, NULL, capture_list);
+ return xfs_defer_ops_capture_and_commit(tp, capture_list);
abort_error:
xfs_rmap_finish_one_cleanup(tp, rcur, error);
diff --git a/fs/xfs/xfs_rmap_item.h b/fs/xfs/xfs_rmap_item.h
index 31e6cdfff71f..802e5119eaca 100644
--- a/fs/xfs/xfs_rmap_item.h
+++ b/fs/xfs/xfs_rmap_item.h
@@ -28,7 +28,7 @@
/* kernel only RUI/RUD definitions */
struct xfs_mount;
-struct kmem_zone;
+struct kmem_cache;
/*
* Max number of extents in fast allocation path.
@@ -68,7 +68,7 @@ struct xfs_rud_log_item {
struct xfs_rud_log_format rud_format;
};
-extern struct kmem_zone *xfs_rui_zone;
-extern struct kmem_zone *xfs_rud_zone;
+extern struct kmem_cache *xfs_rui_cache;
+extern struct kmem_cache *xfs_rud_cache;
#endif /* __XFS_RMAP_ITEM_H__ */
diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c
index c4e0cd1c1c8c..e21459f9923a 100644
--- a/fs/xfs/xfs_super.c
+++ b/fs/xfs/xfs_super.c
@@ -37,6 +37,7 @@
#include "xfs_reflink.h"
#include "xfs_pwork.h"
#include "xfs_ag.h"
+#include "xfs_defer.h"
#include <linux/magic.h>
#include <linux/fs_context.h>
@@ -1951,196 +1952,194 @@ static struct file_system_type xfs_fs_type = {
MODULE_ALIAS_FS("xfs");
STATIC int __init
-xfs_init_zones(void)
+xfs_init_caches(void)
{
- xfs_log_ticket_zone = kmem_cache_create("xfs_log_ticket",
+ int error;
+
+ xfs_log_ticket_cache = kmem_cache_create("xfs_log_ticket",
sizeof(struct xlog_ticket),
0, 0, NULL);
- if (!xfs_log_ticket_zone)
+ if (!xfs_log_ticket_cache)
goto out;
- xfs_bmap_free_item_zone = kmem_cache_create("xfs_bmap_free_item",
- sizeof(struct xfs_extent_free_item),
- 0, 0, NULL);
- if (!xfs_bmap_free_item_zone)
- goto out_destroy_log_ticket_zone;
+ error = xfs_btree_init_cur_caches();
+ if (error)
+ goto out_destroy_log_ticket_cache;
- xfs_btree_cur_zone = kmem_cache_create("xfs_btree_cur",
- sizeof(struct xfs_btree_cur),
- 0, 0, NULL);
- if (!xfs_btree_cur_zone)
- goto out_destroy_bmap_free_item_zone;
+ error = xfs_defer_init_item_caches();
+ if (error)
+ goto out_destroy_btree_cur_cache;
- xfs_da_state_zone = kmem_cache_create("xfs_da_state",
+ xfs_da_state_cache = kmem_cache_create("xfs_da_state",
sizeof(struct xfs_da_state),
0, 0, NULL);
- if (!xfs_da_state_zone)
- goto out_destroy_btree_cur_zone;
+ if (!xfs_da_state_cache)
+ goto out_destroy_defer_item_cache;
- xfs_ifork_zone = kmem_cache_create("xfs_ifork",
+ xfs_ifork_cache = kmem_cache_create("xfs_ifork",
sizeof(struct xfs_ifork),
0, 0, NULL);
- if (!xfs_ifork_zone)
- goto out_destroy_da_state_zone;
+ if (!xfs_ifork_cache)
+ goto out_destroy_da_state_cache;
- xfs_trans_zone = kmem_cache_create("xfs_trans",
+ xfs_trans_cache = kmem_cache_create("xfs_trans",
sizeof(struct xfs_trans),
0, 0, NULL);
- if (!xfs_trans_zone)
- goto out_destroy_ifork_zone;
+ if (!xfs_trans_cache)
+ goto out_destroy_ifork_cache;
/*
- * The size of the zone allocated buf log item is the maximum
+ * The size of the cache-allocated buf log item is the maximum
* size possible under XFS. This wastes a little bit of memory,
* but it is much faster.
*/
- xfs_buf_item_zone = kmem_cache_create("xfs_buf_item",
+ xfs_buf_item_cache = kmem_cache_create("xfs_buf_item",
sizeof(struct xfs_buf_log_item),
0, 0, NULL);
- if (!xfs_buf_item_zone)
- goto out_destroy_trans_zone;
+ if (!xfs_buf_item_cache)
+ goto out_destroy_trans_cache;
- xfs_efd_zone = kmem_cache_create("xfs_efd_item",
+ xfs_efd_cache = kmem_cache_create("xfs_efd_item",
(sizeof(struct xfs_efd_log_item) +
(XFS_EFD_MAX_FAST_EXTENTS - 1) *
sizeof(struct xfs_extent)),
0, 0, NULL);
- if (!xfs_efd_zone)
- goto out_destroy_buf_item_zone;
+ if (!xfs_efd_cache)
+ goto out_destroy_buf_item_cache;
- xfs_efi_zone = kmem_cache_create("xfs_efi_item",
+ xfs_efi_cache = kmem_cache_create("xfs_efi_item",
(sizeof(struct xfs_efi_log_item) +
(XFS_EFI_MAX_FAST_EXTENTS - 1) *
sizeof(struct xfs_extent)),
0, 0, NULL);
- if (!xfs_efi_zone)
- goto out_destroy_efd_zone;
+ if (!xfs_efi_cache)
+ goto out_destroy_efd_cache;
- xfs_inode_zone = kmem_cache_create("xfs_inode",
+ xfs_inode_cache = kmem_cache_create("xfs_inode",
sizeof(struct xfs_inode), 0,
(SLAB_HWCACHE_ALIGN |
SLAB_RECLAIM_ACCOUNT |
SLAB_MEM_SPREAD | SLAB_ACCOUNT),
xfs_fs_inode_init_once);
- if (!xfs_inode_zone)
- goto out_destroy_efi_zone;
+ if (!xfs_inode_cache)
+ goto out_destroy_efi_cache;
- xfs_ili_zone = kmem_cache_create("xfs_ili",
+ xfs_ili_cache = kmem_cache_create("xfs_ili",
sizeof(struct xfs_inode_log_item), 0,
SLAB_RECLAIM_ACCOUNT | SLAB_MEM_SPREAD,
NULL);
- if (!xfs_ili_zone)
- goto out_destroy_inode_zone;
+ if (!xfs_ili_cache)
+ goto out_destroy_inode_cache;
- xfs_icreate_zone = kmem_cache_create("xfs_icr",
+ xfs_icreate_cache = kmem_cache_create("xfs_icr",
sizeof(struct xfs_icreate_item),
0, 0, NULL);
- if (!xfs_icreate_zone)
- goto out_destroy_ili_zone;
+ if (!xfs_icreate_cache)
+ goto out_destroy_ili_cache;
- xfs_rud_zone = kmem_cache_create("xfs_rud_item",
+ xfs_rud_cache = kmem_cache_create("xfs_rud_item",
sizeof(struct xfs_rud_log_item),
0, 0, NULL);
- if (!xfs_rud_zone)
- goto out_destroy_icreate_zone;
+ if (!xfs_rud_cache)
+ goto out_destroy_icreate_cache;
- xfs_rui_zone = kmem_cache_create("xfs_rui_item",
+ xfs_rui_cache = kmem_cache_create("xfs_rui_item",
xfs_rui_log_item_sizeof(XFS_RUI_MAX_FAST_EXTENTS),
0, 0, NULL);
- if (!xfs_rui_zone)
- goto out_destroy_rud_zone;
+ if (!xfs_rui_cache)
+ goto out_destroy_rud_cache;
- xfs_cud_zone = kmem_cache_create("xfs_cud_item",
+ xfs_cud_cache = kmem_cache_create("xfs_cud_item",
sizeof(struct xfs_cud_log_item),
0, 0, NULL);
- if (!xfs_cud_zone)
- goto out_destroy_rui_zone;
+ if (!xfs_cud_cache)
+ goto out_destroy_rui_cache;
- xfs_cui_zone = kmem_cache_create("xfs_cui_item",
+ xfs_cui_cache = kmem_cache_create("xfs_cui_item",
xfs_cui_log_item_sizeof(XFS_CUI_MAX_FAST_EXTENTS),
0, 0, NULL);
- if (!xfs_cui_zone)
- goto out_destroy_cud_zone;
+ if (!xfs_cui_cache)
+ goto out_destroy_cud_cache;
- xfs_bud_zone = kmem_cache_create("xfs_bud_item",
+ xfs_bud_cache = kmem_cache_create("xfs_bud_item",
sizeof(struct xfs_bud_log_item),
0, 0, NULL);
- if (!xfs_bud_zone)
- goto out_destroy_cui_zone;
+ if (!xfs_bud_cache)
+ goto out_destroy_cui_cache;
- xfs_bui_zone = kmem_cache_create("xfs_bui_item",
+ xfs_bui_cache = kmem_cache_create("xfs_bui_item",
xfs_bui_log_item_sizeof(XFS_BUI_MAX_FAST_EXTENTS),
0, 0, NULL);
- if (!xfs_bui_zone)
- goto out_destroy_bud_zone;
+ if (!xfs_bui_cache)
+ goto out_destroy_bud_cache;
return 0;
- out_destroy_bud_zone:
- kmem_cache_destroy(xfs_bud_zone);
- out_destroy_cui_zone:
- kmem_cache_destroy(xfs_cui_zone);
- out_destroy_cud_zone:
- kmem_cache_destroy(xfs_cud_zone);
- out_destroy_rui_zone:
- kmem_cache_destroy(xfs_rui_zone);
- out_destroy_rud_zone:
- kmem_cache_destroy(xfs_rud_zone);
- out_destroy_icreate_zone:
- kmem_cache_destroy(xfs_icreate_zone);
- out_destroy_ili_zone:
- kmem_cache_destroy(xfs_ili_zone);
- out_destroy_inode_zone:
- kmem_cache_destroy(xfs_inode_zone);
- out_destroy_efi_zone:
- kmem_cache_destroy(xfs_efi_zone);
- out_destroy_efd_zone:
- kmem_cache_destroy(xfs_efd_zone);
- out_destroy_buf_item_zone:
- kmem_cache_destroy(xfs_buf_item_zone);
- out_destroy_trans_zone:
- kmem_cache_destroy(xfs_trans_zone);
- out_destroy_ifork_zone:
- kmem_cache_destroy(xfs_ifork_zone);
- out_destroy_da_state_zone:
- kmem_cache_destroy(xfs_da_state_zone);
- out_destroy_btree_cur_zone:
- kmem_cache_destroy(xfs_btree_cur_zone);
- out_destroy_bmap_free_item_zone:
- kmem_cache_destroy(xfs_bmap_free_item_zone);
- out_destroy_log_ticket_zone:
- kmem_cache_destroy(xfs_log_ticket_zone);
+ out_destroy_bud_cache:
+ kmem_cache_destroy(xfs_bud_cache);
+ out_destroy_cui_cache:
+ kmem_cache_destroy(xfs_cui_cache);
+ out_destroy_cud_cache:
+ kmem_cache_destroy(xfs_cud_cache);
+ out_destroy_rui_cache:
+ kmem_cache_destroy(xfs_rui_cache);
+ out_destroy_rud_cache:
+ kmem_cache_destroy(xfs_rud_cache);
+ out_destroy_icreate_cache:
+ kmem_cache_destroy(xfs_icreate_cache);
+ out_destroy_ili_cache:
+ kmem_cache_destroy(xfs_ili_cache);
+ out_destroy_inode_cache:
+ kmem_cache_destroy(xfs_inode_cache);
+ out_destroy_efi_cache:
+ kmem_cache_destroy(xfs_efi_cache);
+ out_destroy_efd_cache:
+ kmem_cache_destroy(xfs_efd_cache);
+ out_destroy_buf_item_cache:
+ kmem_cache_destroy(xfs_buf_item_cache);
+ out_destroy_trans_cache:
+ kmem_cache_destroy(xfs_trans_cache);
+ out_destroy_ifork_cache:
+ kmem_cache_destroy(xfs_ifork_cache);
+ out_destroy_da_state_cache:
+ kmem_cache_destroy(xfs_da_state_cache);
+ out_destroy_defer_item_cache:
+ xfs_defer_destroy_item_caches();
+ out_destroy_btree_cur_cache:
+ xfs_btree_destroy_cur_caches();
+ out_destroy_log_ticket_cache:
+ kmem_cache_destroy(xfs_log_ticket_cache);
out:
return -ENOMEM;
}
STATIC void
-xfs_destroy_zones(void)
+xfs_destroy_caches(void)
{
/*
* Make sure all delayed rcu free are flushed before we
* destroy caches.
*/
rcu_barrier();
- kmem_cache_destroy(xfs_bui_zone);
- kmem_cache_destroy(xfs_bud_zone);
- kmem_cache_destroy(xfs_cui_zone);
- kmem_cache_destroy(xfs_cud_zone);
- kmem_cache_destroy(xfs_rui_zone);
- kmem_cache_destroy(xfs_rud_zone);
- kmem_cache_destroy(xfs_icreate_zone);
- kmem_cache_destroy(xfs_ili_zone);
- kmem_cache_destroy(xfs_inode_zone);
- kmem_cache_destroy(xfs_efi_zone);
- kmem_cache_destroy(xfs_efd_zone);
- kmem_cache_destroy(xfs_buf_item_zone);
- kmem_cache_destroy(xfs_trans_zone);
- kmem_cache_destroy(xfs_ifork_zone);
- kmem_cache_destroy(xfs_da_state_zone);
- kmem_cache_destroy(xfs_btree_cur_zone);
- kmem_cache_destroy(xfs_bmap_free_item_zone);
- kmem_cache_destroy(xfs_log_ticket_zone);
+ kmem_cache_destroy(xfs_bui_cache);
+ kmem_cache_destroy(xfs_bud_cache);
+ kmem_cache_destroy(xfs_cui_cache);
+ kmem_cache_destroy(xfs_cud_cache);
+ kmem_cache_destroy(xfs_rui_cache);
+ kmem_cache_destroy(xfs_rud_cache);
+ kmem_cache_destroy(xfs_icreate_cache);
+ kmem_cache_destroy(xfs_ili_cache);
+ kmem_cache_destroy(xfs_inode_cache);
+ kmem_cache_destroy(xfs_efi_cache);
+ kmem_cache_destroy(xfs_efd_cache);
+ kmem_cache_destroy(xfs_buf_item_cache);
+ kmem_cache_destroy(xfs_trans_cache);
+ kmem_cache_destroy(xfs_ifork_cache);
+ kmem_cache_destroy(xfs_da_state_cache);
+ xfs_defer_destroy_item_caches();
+ xfs_btree_destroy_cur_caches();
+ kmem_cache_destroy(xfs_log_ticket_cache);
}
STATIC int __init
@@ -2233,13 +2232,13 @@ init_xfs_fs(void)
if (error)
goto out;
- error = xfs_init_zones();
+ error = xfs_init_caches();
if (error)
goto out_destroy_hp;
error = xfs_init_workqueues();
if (error)
- goto out_destroy_zones;
+ goto out_destroy_caches;
error = xfs_mru_cache_init();
if (error)
@@ -2314,8 +2313,8 @@ init_xfs_fs(void)
xfs_mru_cache_uninit();
out_destroy_wq:
xfs_destroy_workqueues();
- out_destroy_zones:
- xfs_destroy_zones();
+ out_destroy_caches:
+ xfs_destroy_caches();
out_destroy_hp:
xfs_cpu_hotplug_destroy();
out:
@@ -2338,7 +2337,7 @@ exit_xfs_fs(void)
xfs_buf_terminate();
xfs_mru_cache_uninit();
xfs_destroy_workqueues();
- xfs_destroy_zones();
+ xfs_destroy_caches();
xfs_uuid_table_free();
xfs_cpu_hotplug_destroy();
}
diff --git a/fs/xfs/xfs_sysfs.c b/fs/xfs/xfs_sysfs.c
index 18dc5eca6c04..8608f804388f 100644
--- a/fs/xfs/xfs_sysfs.c
+++ b/fs/xfs/xfs_sysfs.c
@@ -105,7 +105,7 @@ bug_on_assert_show(
struct kobject *kobject,
char *buf)
{
- return snprintf(buf, PAGE_SIZE, "%d\n", xfs_globals.bug_on_assert ? 1 : 0);
+ return sysfs_emit(buf, "%d\n", xfs_globals.bug_on_assert);
}
XFS_SYSFS_ATTR_RW(bug_on_assert);
@@ -135,7 +135,7 @@ log_recovery_delay_show(
struct kobject *kobject,
char *buf)
{
- return snprintf(buf, PAGE_SIZE, "%d\n", xfs_globals.log_recovery_delay);
+ return sysfs_emit(buf, "%d\n", xfs_globals.log_recovery_delay);
}
XFS_SYSFS_ATTR_RW(log_recovery_delay);
@@ -165,7 +165,7 @@ mount_delay_show(
struct kobject *kobject,
char *buf)
{
- return snprintf(buf, PAGE_SIZE, "%d\n", xfs_globals.mount_delay);
+ return sysfs_emit(buf, "%d\n", xfs_globals.mount_delay);
}
XFS_SYSFS_ATTR_RW(mount_delay);
@@ -188,7 +188,7 @@ always_cow_show(
struct kobject *kobject,
char *buf)
{
- return snprintf(buf, PAGE_SIZE, "%d\n", xfs_globals.always_cow);
+ return sysfs_emit(buf, "%d\n", xfs_globals.always_cow);
}
XFS_SYSFS_ATTR_RW(always_cow);
@@ -224,7 +224,7 @@ pwork_threads_show(
struct kobject *kobject,
char *buf)
{
- return snprintf(buf, PAGE_SIZE, "%d\n", xfs_globals.pwork_threads);
+ return sysfs_emit(buf, "%d\n", xfs_globals.pwork_threads);
}
XFS_SYSFS_ATTR_RW(pwork_threads);
#endif /* DEBUG */
@@ -327,7 +327,7 @@ log_head_lsn_show(
block = log->l_curr_block;
spin_unlock(&log->l_icloglock);
- return snprintf(buf, PAGE_SIZE, "%d:%d\n", cycle, block);
+ return sysfs_emit(buf, "%d:%d\n", cycle, block);
}
XFS_SYSFS_ATTR_RO(log_head_lsn);
@@ -341,7 +341,7 @@ log_tail_lsn_show(
struct xlog *log = to_xlog(kobject);
xlog_crack_atomic_lsn(&log->l_tail_lsn, &cycle, &block);
- return snprintf(buf, PAGE_SIZE, "%d:%d\n", cycle, block);
+ return sysfs_emit(buf, "%d:%d\n", cycle, block);
}
XFS_SYSFS_ATTR_RO(log_tail_lsn);
@@ -356,7 +356,7 @@ reserve_grant_head_show(
struct xlog *log = to_xlog(kobject);
xlog_crack_grant_head(&log->l_reserve_head.grant, &cycle, &bytes);
- return snprintf(buf, PAGE_SIZE, "%d:%d\n", cycle, bytes);
+ return sysfs_emit(buf, "%d:%d\n", cycle, bytes);
}
XFS_SYSFS_ATTR_RO(reserve_grant_head);
@@ -370,7 +370,7 @@ write_grant_head_show(
struct xlog *log = to_xlog(kobject);
xlog_crack_grant_head(&log->l_write_head.grant, &cycle, &bytes);
- return snprintf(buf, PAGE_SIZE, "%d:%d\n", cycle, bytes);
+ return sysfs_emit(buf, "%d:%d\n", cycle, bytes);
}
XFS_SYSFS_ATTR_RO(write_grant_head);
@@ -425,7 +425,7 @@ max_retries_show(
else
retries = cfg->max_retries;
- return snprintf(buf, PAGE_SIZE, "%d\n", retries);
+ return sysfs_emit(buf, "%d\n", retries);
}
static ssize_t
@@ -466,7 +466,7 @@ retry_timeout_seconds_show(
else
timeout = jiffies_to_msecs(cfg->retry_timeout) / MSEC_PER_SEC;
- return snprintf(buf, PAGE_SIZE, "%d\n", timeout);
+ return sysfs_emit(buf, "%d\n", timeout);
}
static ssize_t
@@ -504,7 +504,7 @@ fail_at_unmount_show(
{
struct xfs_mount *mp = err_to_mp(kobject);
- return snprintf(buf, PAGE_SIZE, "%d\n", mp->m_fail_unmount);
+ return sysfs_emit(buf, "%d\n", mp->m_fail_unmount);
}
static ssize_t
diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h
index 1033a95fbf8e..4a8076ef8cb4 100644
--- a/fs/xfs/xfs_trace.h
+++ b/fs/xfs/xfs_trace.h
@@ -2476,7 +2476,7 @@ DECLARE_EVENT_CLASS(xfs_btree_cur_class,
__entry->btnum = cur->bc_btnum;
__entry->level = level;
__entry->nlevels = cur->bc_nlevels;
- __entry->ptr = cur->bc_ptrs[level];
+ __entry->ptr = cur->bc_levels[level].ptr;
__entry->daddr = bp ? xfs_buf_daddr(bp) : -1;
),
TP_printk("dev %d:%d btree %s level %d/%d ptr %d daddr 0x%llx",
diff --git a/fs/xfs/xfs_trans.c b/fs/xfs/xfs_trans.c
index 67dec11e34c7..234a9d9c2f43 100644
--- a/fs/xfs/xfs_trans.c
+++ b/fs/xfs/xfs_trans.c
@@ -25,7 +25,7 @@
#include "xfs_dquot.h"
#include "xfs_icache.h"
-kmem_zone_t *xfs_trans_zone;
+struct kmem_cache *xfs_trans_cache;
#if defined(CONFIG_TRACEPOINTS)
static void
@@ -76,7 +76,7 @@ xfs_trans_free(
if (!(tp->t_flags & XFS_TRANS_NO_WRITECOUNT))
sb_end_intwrite(tp->t_mountp->m_super);
xfs_trans_free_dqinfo(tp);
- kmem_cache_free(xfs_trans_zone, tp);
+ kmem_cache_free(xfs_trans_cache, tp);
}
/*
@@ -95,7 +95,7 @@ xfs_trans_dup(
trace_xfs_trans_dup(tp, _RET_IP_);
- ntp = kmem_cache_zalloc(xfs_trans_zone, GFP_KERNEL | __GFP_NOFAIL);
+ ntp = kmem_cache_zalloc(xfs_trans_cache, GFP_KERNEL | __GFP_NOFAIL);
/*
* Initialize the new transaction structure.
@@ -263,7 +263,7 @@ xfs_trans_alloc(
* by doing GFP_KERNEL allocations inside sb_start_intwrite().
*/
retry:
- tp = kmem_cache_zalloc(xfs_trans_zone, GFP_KERNEL | __GFP_NOFAIL);
+ tp = kmem_cache_zalloc(xfs_trans_cache, GFP_KERNEL | __GFP_NOFAIL);
if (!(flags & XFS_TRANS_NO_WRITECOUNT))
sb_start_intwrite(mp->m_super);
xfs_trans_set_context(tp);
@@ -477,7 +477,7 @@ STATIC void
xfs_trans_apply_sb_deltas(
xfs_trans_t *tp)
{
- xfs_dsb_t *sbp;
+ struct xfs_dsb *sbp;
struct xfs_buf *bp;
int whole = 0;
@@ -541,14 +541,14 @@ xfs_trans_apply_sb_deltas(
/*
* Log the whole thing, the fields are noncontiguous.
*/
- xfs_trans_log_buf(tp, bp, 0, sizeof(xfs_dsb_t) - 1);
+ xfs_trans_log_buf(tp, bp, 0, sizeof(struct xfs_dsb) - 1);
else
/*
* Since all the modifiable fields are contiguous, we
* can get away with this.
*/
- xfs_trans_log_buf(tp, bp, offsetof(xfs_dsb_t, sb_icount),
- offsetof(xfs_dsb_t, sb_frextents) +
+ xfs_trans_log_buf(tp, bp, offsetof(struct xfs_dsb, sb_icount),
+ offsetof(struct xfs_dsb, sb_frextents) +
sizeof(sbp->sb_frextents) - 1);
}
diff --git a/fs/xfs/xfs_trans.h b/fs/xfs/xfs_trans.h
index 50da47f23a07..a487b264a9eb 100644
--- a/fs/xfs/xfs_trans.h
+++ b/fs/xfs/xfs_trans.h
@@ -113,12 +113,6 @@ void xfs_log_item_init(struct xfs_mount *mp, struct xfs_log_item *item,
#define XFS_ITEM_FLUSHING 3
/*
- * Deferred operation item relogging limits.
- */
-#define XFS_DEFER_OPS_NR_INODES 2 /* join up to two inodes */
-#define XFS_DEFER_OPS_NR_BUFS 2 /* join up to two buffers */
-
-/*
* This is the structure maintained for every active transaction.
*/
typedef struct xfs_trans {
@@ -243,7 +237,7 @@ void xfs_trans_buf_set_type(struct xfs_trans *, struct xfs_buf *,
void xfs_trans_buf_copy_type(struct xfs_buf *dst_bp,
struct xfs_buf *src_bp);
-extern kmem_zone_t *xfs_trans_zone;
+extern struct kmem_cache *xfs_trans_cache;
static inline struct xfs_log_item *
xfs_trans_item_relog(
diff --git a/fs/xfs/xfs_trans_dquot.c b/fs/xfs/xfs_trans_dquot.c
index 3872ce671411..9ba7e6b9bed3 100644
--- a/fs/xfs/xfs_trans_dquot.c
+++ b/fs/xfs/xfs_trans_dquot.c
@@ -846,7 +846,7 @@ STATIC void
xfs_trans_alloc_dqinfo(
xfs_trans_t *tp)
{
- tp->t_dqinfo = kmem_cache_zalloc(xfs_qm_dqtrxzone,
+ tp->t_dqinfo = kmem_cache_zalloc(xfs_dqtrx_cache,
GFP_KERNEL | __GFP_NOFAIL);
}
@@ -856,6 +856,6 @@ xfs_trans_free_dqinfo(
{
if (!tp->t_dqinfo)
return;
- kmem_cache_free(xfs_qm_dqtrxzone, tp->t_dqinfo);
+ kmem_cache_free(xfs_dqtrx_cache, tp->t_dqinfo);
tp->t_dqinfo = NULL;
}