summaryrefslogtreecommitdiff
path: root/fs
diff options
context:
space:
mode:
Diffstat (limited to 'fs')
-rw-r--r--fs/Kconfig3
-rw-r--r--fs/Makefile1
-rw-r--r--fs/affs/affs.h16
-rw-r--r--fs/affs/super.c10
-rw-r--r--fs/afs/callback.c1
-rw-r--r--fs/afs/cmservice.c6
-rw-r--r--fs/afs/dir.c7
-rw-r--r--fs/afs/dir_edit.c12
-rw-r--r--fs/afs/file.c6
-rw-r--r--fs/afs/flock.c4
-rw-r--r--fs/afs/fsclient.c16
-rw-r--r--fs/afs/inode.c13
-rw-r--r--fs/afs/internal.h16
-rw-r--r--fs/afs/rxrpc.c13
-rw-r--r--fs/afs/server.c3
-rw-r--r--fs/afs/super.c1
-rw-r--r--fs/afs/vl_list.c4
-rw-r--r--fs/afs/vlclient.c6
-rw-r--r--fs/afs/xattr.c16
-rw-r--r--fs/afs/yfsclient.c15
-rw-r--r--fs/aio.c12
-rw-r--r--fs/autofs/autofs_i.h2
-rw-r--r--fs/autofs/expire.c11
-rw-r--r--fs/autofs/root.c39
-rw-r--r--fs/binfmt_elf.c68
-rw-r--r--fs/binfmt_elf_fdpic.c12
-rw-r--r--fs/block_dev.c69
-rw-r--r--fs/btrfs/Kconfig2
-rw-r--r--fs/btrfs/async-thread.c113
-rw-r--r--fs/btrfs/async-thread.h37
-rw-r--r--fs/btrfs/block-group.c588
-rw-r--r--fs/btrfs/block-group.h51
-rw-r--r--fs/btrfs/btrfs_inode.h3
-rw-r--r--fs/btrfs/compression.c269
-rw-r--r--fs/btrfs/compression.h46
-rw-r--r--fs/btrfs/ctree.c287
-rw-r--r--fs/btrfs/ctree.h56
-rw-r--r--fs/btrfs/delalloc-space.c28
-rw-r--r--fs/btrfs/delayed-inode.c18
-rw-r--r--fs/btrfs/dev-replace.c2
-rw-r--r--fs/btrfs/dev-replace.h2
-rw-r--r--fs/btrfs/disk-io.c371
-rw-r--r--fs/btrfs/disk-io.h4
-rw-r--r--fs/btrfs/export.c4
-rw-r--r--fs/btrfs/extent-io-tree.h248
-rw-r--r--fs/btrfs/extent-tree.c146
-rw-r--r--fs/btrfs/extent_io.c120
-rw-r--r--fs/btrfs/extent_io.h231
-rw-r--r--fs/btrfs/extent_map.c6
-rw-r--r--fs/btrfs/extent_map.h11
-rw-r--r--fs/btrfs/file-item.c1
-rw-r--r--fs/btrfs/file.c117
-rw-r--r--fs/btrfs/free-space-cache.c118
-rw-r--r--fs/btrfs/free-space-cache.h39
-rw-r--r--fs/btrfs/free-space-tree.c133
-rw-r--r--fs/btrfs/free-space-tree.h18
-rw-r--r--fs/btrfs/inode-map.c4
-rw-r--r--fs/btrfs/inode.c212
-rw-r--r--fs/btrfs/ioctl.c61
-rw-r--r--fs/btrfs/locking.c309
-rw-r--r--fs/btrfs/locking.h13
-rw-r--r--fs/btrfs/lzo.c53
-rw-r--r--fs/btrfs/misc.h11
-rw-r--r--fs/btrfs/ordered-data.c7
-rw-r--r--fs/btrfs/ordered-data.h2
-rw-r--r--fs/btrfs/print-tree.c6
-rw-r--r--fs/btrfs/props.c6
-rw-r--r--fs/btrfs/qgroup.c15
-rw-r--r--fs/btrfs/qgroup.h2
-rw-r--r--fs/btrfs/raid56.c101
-rw-r--r--fs/btrfs/reada.c19
-rw-r--r--fs/btrfs/relocation.c52
-rw-r--r--fs/btrfs/scrub.c100
-rw-r--r--fs/btrfs/send.c45
-rw-r--r--fs/btrfs/space-info.c29
-rw-r--r--fs/btrfs/space-info.h3
-rw-r--r--fs/btrfs/super.c28
-rw-r--r--fs/btrfs/sysfs.c47
-rw-r--r--fs/btrfs/sysfs.h2
-rw-r--r--fs/btrfs/tests/btrfs-tests.c11
-rw-r--r--fs/btrfs/tests/btrfs-tests.h4
-rw-r--r--fs/btrfs/tests/free-space-tests.c15
-rw-r--r--fs/btrfs/tests/free-space-tree-tests.c101
-rw-r--r--fs/btrfs/transaction.c98
-rw-r--r--fs/btrfs/transaction.h5
-rw-r--r--fs/btrfs/tree-checker.c219
-rw-r--r--fs/btrfs/tree-log.c136
-rw-r--r--fs/btrfs/volumes.c495
-rw-r--r--fs/btrfs/volumes.h24
-rw-r--r--fs/btrfs/zlib.c52
-rw-r--r--fs/btrfs/zstd.c47
-rw-r--r--fs/buffer.c54
-rw-r--r--fs/ceph/cache.c9
-rw-r--r--fs/ceph/cache.h5
-rw-r--r--fs/ceph/caps.c10
-rw-r--r--fs/ceph/dir.c16
-rw-r--r--fs/ceph/file.c46
-rw-r--r--fs/ceph/inode.c1
-rw-r--r--fs/ceph/mds_client.c40
-rw-r--r--fs/ceph/mdsmap.c11
-rw-r--r--fs/ceph/super.c643
-rw-r--r--fs/ceph/super.h13
-rw-r--r--fs/cifs/cifs_debug.c43
-rw-r--r--fs/cifs/cifs_spnego.c2
-rw-r--r--fs/cifs/cifsacl.c2
-rw-r--r--fs/cifs/cifsfs.c61
-rw-r--r--fs/cifs/cifsfs.h3
-rw-r--r--fs/cifs/cifsglob.h95
-rw-r--r--fs/cifs/cifsproto.h9
-rw-r--r--fs/cifs/connect.c209
-rw-r--r--fs/cifs/dfs_cache.c3
-rw-r--r--fs/cifs/dir.c6
-rw-r--r--fs/cifs/file.c186
-rw-r--r--fs/cifs/inode.c337
-rw-r--r--fs/cifs/misc.c17
-rw-r--r--fs/cifs/sess.c230
-rw-r--r--fs/cifs/smb1ops.c11
-rw-r--r--fs/cifs/smb2file.c2
-rw-r--r--fs/cifs/smb2misc.c175
-rw-r--r--fs/cifs/smb2ops.c144
-rw-r--r--fs/cifs/smb2pdu.c168
-rw-r--r--fs/cifs/smb2pdu.h3
-rw-r--r--fs/cifs/smb2proto.h6
-rw-r--r--fs/cifs/smb2transport.c165
-rw-r--r--fs/cifs/smbdirect.c36
-rw-r--r--fs/cifs/transport.c79
-rw-r--r--fs/compat_binfmt_elf.c4
-rw-r--r--fs/compat_ioctl.c926
-rw-r--r--fs/configfs/symlink.c2
-rw-r--r--fs/cramfs/inode.c4
-rw-r--r--fs/crypto/bio.c29
-rw-r--r--fs/crypto/crypto.c124
-rw-r--r--fs/crypto/fscrypt_private.h25
-rw-r--r--fs/crypto/keyring.c6
-rw-r--r--fs/crypto/keysetup.c158
-rw-r--r--fs/crypto/keysetup_v1.c4
-rw-r--r--fs/crypto/policy.c41
-rw-r--r--fs/dax.c5
-rw-r--r--fs/dcache.c8
-rw-r--r--fs/debugfs/file.c87
-rw-r--r--fs/debugfs/inode.c6
-rw-r--r--fs/direct-io.c22
-rw-r--r--fs/ecryptfs/file.c1
-rw-r--r--fs/ecryptfs/inode.c84
-rw-r--r--fs/erofs/Kconfig1
-rw-r--r--fs/erofs/decompressor.c2
-rw-r--r--fs/erofs/erofs_fs.h3
-rw-r--r--fs/erofs/internal.h7
-rw-r--r--fs/erofs/super.c39
-rw-r--r--fs/erofs/utils.c17
-rw-r--r--fs/erofs/zdata.c288
-rw-r--r--fs/erofs/zdata.h8
-rw-r--r--fs/erofs/zmap.c28
-rw-r--r--fs/eventpoll.c52
-rw-r--r--fs/exec.c5
-rw-r--r--fs/exportfs/expfs.c31
-rw-r--r--fs/ext2/balloc.c75
-rw-r--r--fs/ext2/ext2.h12
-rw-r--r--fs/ext2/inode.c7
-rw-r--r--fs/ext2/ioctl.c5
-rw-r--r--fs/ext2/super.c13
-rw-r--r--fs/ext4/Kconfig17
-rw-r--r--fs/ext4/Makefile1
-rw-r--r--fs/ext4/ext4.h24
-rw-r--r--fs/ext4/ext4_jbd2.c32
-rw-r--r--fs/ext4/ext4_jbd2.h106
-rw-r--r--fs/ext4/extents.c149
-rw-r--r--fs/ext4/file.c412
-rw-r--r--fs/ext4/fsync.c72
-rw-r--r--fs/ext4/ialloc.c7
-rw-r--r--fs/ext4/indirect.c125
-rw-r--r--fs/ext4/inode-test.c272
-rw-r--r--fs/ext4/inode.c931
-rw-r--r--fs/ext4/ioctl.c1
-rw-r--r--fs/ext4/migrate.c103
-rw-r--r--fs/ext4/namei.c50
-rw-r--r--fs/ext4/page-io.c167
-rw-r--r--fs/ext4/readpage.c6
-rw-r--r--fs/ext4/resize.c46
-rw-r--r--fs/ext4/super.c73
-rw-r--r--fs/ext4/xattr.c94
-rw-r--r--fs/f2fs/checkpoint.c2
-rw-r--r--fs/f2fs/data.c190
-rw-r--r--fs/f2fs/dir.c7
-rw-r--r--fs/f2fs/f2fs.h63
-rw-r--r--fs/f2fs/file.c53
-rw-r--r--fs/f2fs/gc.c46
-rw-r--r--fs/f2fs/inode.c8
-rw-r--r--fs/f2fs/namei.c15
-rw-r--r--fs/f2fs/node.c3
-rw-r--r--fs/f2fs/recovery.c2
-rw-r--r--fs/f2fs/segment.c67
-rw-r--r--fs/f2fs/segment.h2
-rw-r--r--fs/f2fs/super.c129
-rw-r--r--fs/f2fs/sysfs.c4
-rw-r--r--fs/f2fs/xattr.c14
-rw-r--r--fs/fat/file.c13
-rw-r--r--fs/fcntl.c2
-rw-r--r--fs/fs-writeback.c11
-rw-r--r--fs/fuse/Kconfig4
-rw-r--r--fs/fuse/Makefile3
-rw-r--r--fs/fuse/dev.c37
-rw-r--r--fs/fuse/dir.c41
-rw-r--r--fs/fuse/file.c20
-rw-r--r--fs/fuse/fuse_i.h6
-rw-r--r--fs/fuse/inode.c4
-rw-r--r--fs/fuse/readdir.c2
-rw-r--r--fs/fuse/virtio_fs.c365
-rw-r--r--fs/gfs2/aops.c6
-rw-r--r--fs/gfs2/bmap.c11
-rw-r--r--fs/gfs2/file.c86
-rw-r--r--fs/gfs2/glock.c16
-rw-r--r--fs/gfs2/glops.c4
-rw-r--r--fs/gfs2/inode.c16
-rw-r--r--fs/gfs2/log.c25
-rw-r--r--fs/gfs2/log.h2
-rw-r--r--fs/gfs2/lops.c34
-rw-r--r--fs/gfs2/lops.h3
-rw-r--r--fs/gfs2/meta_io.c6
-rw-r--r--fs/gfs2/ops_fstype.c26
-rw-r--r--fs/gfs2/quota.c4
-rw-r--r--fs/gfs2/recovery.c8
-rw-r--r--fs/gfs2/super.c33
-rw-r--r--fs/gfs2/sys.c2
-rw-r--r--fs/gfs2/trans.c2
-rw-r--r--fs/gfs2/util.c2
-rw-r--r--fs/gfs2/util.h9
-rw-r--r--fs/hpfs/dir.c1
-rw-r--r--fs/hpfs/file.c1
-rw-r--r--fs/hugetlbfs/inode.c63
-rw-r--r--fs/io-wq.c1094
-rw-r--r--fs/io-wq.h124
-rw-r--r--fs/io_uring.c3214
-rw-r--r--fs/ioctl.c80
-rw-r--r--fs/iomap/apply.c7
-rw-r--r--fs/iomap/buffered-io.c7
-rw-r--r--fs/iomap/direct-io.c54
-rw-r--r--fs/iomap/fiemap.c6
-rw-r--r--fs/iomap/trace.h103
-rw-r--r--fs/jbd2/checkpoint.c2
-rw-r--r--fs/jbd2/commit.c26
-rw-r--r--fs/jbd2/journal.c65
-rw-r--r--fs/jbd2/revoke.c6
-rw-r--r--fs/jbd2/transaction.c400
-rw-r--r--fs/jffs2/nodelist.c2
-rw-r--r--fs/kernfs/dir.c105
-rw-r--r--fs/kernfs/file.c4
-rw-r--r--fs/kernfs/inode.c4
-rw-r--r--fs/kernfs/kernfs-internal.h2
-rw-r--r--fs/kernfs/mount.c104
-rw-r--r--fs/libfs.c3
-rw-r--r--fs/lockd/host.c3
-rw-r--r--fs/namei.c64
-rw-r--r--fs/namespace.c15
-rw-r--r--fs/nfs/callback.h4
-rw-r--r--fs/nfs/callback_proc.c8
-rw-r--r--fs/nfs/callback_xdr.c6
-rw-r--r--fs/nfs/client.c11
-rw-r--r--fs/nfs/delegation.c170
-rw-r--r--fs/nfs/delegation.h4
-rw-r--r--fs/nfs/export.c1
-rw-r--r--fs/nfs/file.c2
-rw-r--r--fs/nfs/inode.c54
-rw-r--r--fs/nfs/internal.h2
-rw-r--r--fs/nfs/namespace.c3
-rw-r--r--fs/nfs/nfs2xdr.c21
-rw-r--r--fs/nfs/nfs3client.c5
-rw-r--r--fs/nfs/nfs3xdr.c14
-rw-r--r--fs/nfs/nfs42.h15
-rw-r--r--fs/nfs/nfs42proc.c201
-rw-r--r--fs/nfs/nfs42xdr.c190
-rw-r--r--fs/nfs/nfs4_fs.h21
-rw-r--r--fs/nfs/nfs4client.c13
-rw-r--r--fs/nfs/nfs4file.c141
-rw-r--r--fs/nfs/nfs4proc.c76
-rw-r--r--fs/nfs/nfs4state.c51
-rw-r--r--fs/nfs/nfs4super.c4
-rw-r--r--fs/nfs/nfs4trace.h175
-rw-r--r--fs/nfs/nfs4xdr.c24
-rw-r--r--fs/nfs/nfstrace.h33
-rw-r--r--fs/nfs/pnfs.c2
-rw-r--r--fs/nfs/super.c6
-rw-r--r--fs/nfs/sysfs.c3
-rw-r--r--fs/nfsd/Kconfig3
-rw-r--r--fs/nfsd/filecache.c2
-rw-r--r--fs/nfsd/nfs3xdr.c4
-rw-r--r--fs/nfsd/nfs4callback.c104
-rw-r--r--fs/nfsd/nfs4proc.c6
-rw-r--r--fs/nfsd/nfs4recover.c23
-rw-r--r--fs/nfsd/nfs4state.c19
-rw-r--r--fs/nfsd/nfs4xdr.c13
-rw-r--r--fs/nfsd/nfsd.h3
-rw-r--r--fs/nfsd/nfssvc.c3
-rw-r--r--fs/nfsd/state.h1
-rw-r--r--fs/nfsd/vfs.c20
-rw-r--r--fs/nfsd/vfs.h2
-rw-r--r--fs/nilfs2/ioctl.c1
-rw-r--r--fs/notify/fanotify/fanotify_user.c2
-rw-r--r--fs/notify/fdinfo.c2
-rw-r--r--fs/notify/fsnotify.c2
-rw-r--r--fs/notify/fsnotify.h2
-rw-r--r--fs/ocfs2/acl.c4
-rw-r--r--fs/ocfs2/alloc.c32
-rw-r--r--fs/ocfs2/aops.c1
-rw-r--r--fs/ocfs2/dlmglue.c2
-rw-r--r--fs/ocfs2/file.c136
-rw-r--r--fs/ocfs2/ioctl.c1
-rw-r--r--fs/ocfs2/journal.c11
-rw-r--r--fs/ocfs2/localalloc.c3
-rw-r--r--fs/ocfs2/quota_global.c2
-rw-r--r--fs/ocfs2/suballoc.c19
-rw-r--r--fs/ocfs2/super.c4
-rw-r--r--fs/ocfs2/xattr.c56
-rw-r--r--fs/orangefs/file.c39
-rw-r--r--fs/orangefs/inode.c8
-rw-r--r--fs/orangefs/orangefs-kernel.h3
-rw-r--r--fs/overlayfs/namei.c24
-rw-r--r--fs/pipe.c338
-rw-r--r--fs/proc/Kconfig8
-rw-r--r--fs/proc/array.c2
-rw-r--r--fs/proc/generic.c37
-rw-r--r--fs/proc/internal.h2
-rw-r--r--fs/proc/meminfo.c4
-rw-r--r--fs/proc/page.c28
-rw-r--r--fs/proc/stat.c56
-rw-r--r--fs/pstore/platform.c2
-rw-r--r--fs/quota/dquot.c297
-rw-r--r--fs/quota/quota.c7
-rw-r--r--fs/quota/quota_v1.c1
-rw-r--r--fs/readdir.c4
-rw-r--r--fs/reiserfs/file.c10
-rw-r--r--fs/reiserfs/inode.c12
-rw-r--r--fs/reiserfs/namei.c7
-rw-r--r--fs/reiserfs/reiserfs.h2
-rw-r--r--fs/reiserfs/super.c2
-rw-r--r--fs/reiserfs/xattr.c19
-rw-r--r--fs/reiserfs/xattr_acl.c4
-rw-r--r--fs/select.c10
-rw-r--r--fs/splice.c222
-rw-r--r--fs/timerfd.c14
-rw-r--r--fs/ubifs/debug.c12
-rw-r--r--fs/ubifs/journal.c4
-rw-r--r--fs/ubifs/orphan.c17
-rw-r--r--fs/ubifs/sb.c2
-rw-r--r--fs/ubifs/super.c4
-rw-r--r--fs/ubifs/tnc_commit.c34
-rw-r--r--fs/userfaultfd.c23
-rw-r--r--fs/utimes.c8
-rw-r--r--fs/xfs/libxfs/xfs_fs.h8
349 files changed, 14185 insertions, 9241 deletions
diff --git a/fs/Kconfig b/fs/Kconfig
index 2501e6f1f965..7b623e9fc1b0 100644
--- a/fs/Kconfig
+++ b/fs/Kconfig
@@ -322,4 +322,7 @@ source "fs/nls/Kconfig"
source "fs/dlm/Kconfig"
source "fs/unicode/Kconfig"
+config IO_WQ
+ bool
+
endmenu
diff --git a/fs/Makefile b/fs/Makefile
index 14231b4cf383..1148c555c4d3 100644
--- a/fs/Makefile
+++ b/fs/Makefile
@@ -32,6 +32,7 @@ obj-$(CONFIG_EVENTFD) += eventfd.o
obj-$(CONFIG_USERFAULTFD) += userfaultfd.o
obj-$(CONFIG_AIO) += aio.o
obj-$(CONFIG_IO_URING) += io_uring.o
+obj-$(CONFIG_IO_WQ) += io-wq.o
obj-$(CONFIG_FS_DAX) += dax.o
obj-$(CONFIG_FS_ENCRYPTION) += crypto/
obj-$(CONFIG_FS_VERITY) += verity/
diff --git a/fs/affs/affs.h b/fs/affs/affs.h
index a92eb6ae2ae2..a755bef7c4c7 100644
--- a/fs/affs/affs.h
+++ b/fs/affs/affs.h
@@ -43,8 +43,8 @@ struct affs_ext_key {
*/
struct affs_inode_info {
atomic_t i_opencnt;
- struct semaphore i_link_lock; /* Protects internal inode access. */
- struct semaphore i_ext_lock; /* Protects internal inode access. */
+ struct mutex i_link_lock; /* Protects internal inode access. */
+ struct mutex i_ext_lock; /* Protects internal inode access. */
#define i_hash_lock i_ext_lock
u32 i_blkcnt; /* block count */
u32 i_extcnt; /* extended block count */
@@ -293,30 +293,30 @@ affs_adjust_bitmapchecksum(struct buffer_head *bh, u32 val)
static inline void
affs_lock_link(struct inode *inode)
{
- down(&AFFS_I(inode)->i_link_lock);
+ mutex_lock(&AFFS_I(inode)->i_link_lock);
}
static inline void
affs_unlock_link(struct inode *inode)
{
- up(&AFFS_I(inode)->i_link_lock);
+ mutex_unlock(&AFFS_I(inode)->i_link_lock);
}
static inline void
affs_lock_dir(struct inode *inode)
{
- down(&AFFS_I(inode)->i_hash_lock);
+ mutex_lock_nested(&AFFS_I(inode)->i_hash_lock, SINGLE_DEPTH_NESTING);
}
static inline void
affs_unlock_dir(struct inode *inode)
{
- up(&AFFS_I(inode)->i_hash_lock);
+ mutex_unlock(&AFFS_I(inode)->i_hash_lock);
}
static inline void
affs_lock_ext(struct inode *inode)
{
- down(&AFFS_I(inode)->i_ext_lock);
+ mutex_lock(&AFFS_I(inode)->i_ext_lock);
}
static inline void
affs_unlock_ext(struct inode *inode)
{
- up(&AFFS_I(inode)->i_ext_lock);
+ mutex_unlock(&AFFS_I(inode)->i_ext_lock);
}
diff --git a/fs/affs/super.c b/fs/affs/super.c
index cc463ae47c12..47107c6712a6 100644
--- a/fs/affs/super.c
+++ b/fs/affs/super.c
@@ -121,8 +121,8 @@ static void init_once(void *foo)
{
struct affs_inode_info *ei = (struct affs_inode_info *) foo;
- sema_init(&ei->i_link_lock, 1);
- sema_init(&ei->i_ext_lock, 1);
+ mutex_init(&ei->i_link_lock);
+ mutex_init(&ei->i_ext_lock);
inode_init_once(&ei->vfs_inode);
}
@@ -561,14 +561,9 @@ affs_remount(struct super_block *sb, int *flags, char *data)
int root_block;
unsigned long mount_flags;
int res = 0;
- char *new_opts;
char volume[32];
char *prefix = NULL;
- new_opts = kstrdup(data, GFP_KERNEL);
- if (data && !new_opts)
- return -ENOMEM;
-
pr_debug("%s(flags=0x%x,opts=\"%s\")\n", __func__, *flags, data);
sync_filesystem(sb);
@@ -579,7 +574,6 @@ affs_remount(struct super_block *sb, int *flags, char *data)
&blocksize, &prefix, volume,
&mount_flags)) {
kfree(prefix);
- kfree(new_opts);
return -EINVAL;
}
diff --git a/fs/afs/callback.c b/fs/afs/callback.c
index 6cdd7047c809..2dca8df1a18d 100644
--- a/fs/afs/callback.c
+++ b/fs/afs/callback.c
@@ -312,7 +312,6 @@ void afs_break_callbacks(struct afs_server *server, size_t count,
_enter("%p,%zu,", server, count);
ASSERT(server != NULL);
- ASSERTCMP(count, <=, AFSCBMAX);
/* TODO: Sort the callback break list by volume ID */
diff --git a/fs/afs/cmservice.c b/fs/afs/cmservice.c
index b86195e4dc6c..ff3994a6be23 100644
--- a/fs/afs/cmservice.c
+++ b/fs/afs/cmservice.c
@@ -342,14 +342,14 @@ static int afs_deliver_cb_callback(struct afs_call *call)
if (call->count2 != call->count && call->count2 != 0)
return afs_protocol_error(call, -EBADMSG,
afs_eproto_cb_count);
- call->_iter = &call->iter;
- iov_iter_discard(&call->iter, READ, call->count2 * 3 * 4);
+ call->iter = &call->def_iter;
+ iov_iter_discard(&call->def_iter, READ, call->count2 * 3 * 4);
call->unmarshall++;
/* Fall through */
case 4:
_debug("extract discard %zu/%u",
- iov_iter_count(&call->iter), call->count2 * 3 * 4);
+ iov_iter_count(call->iter), call->count2 * 3 * 4);
ret = afs_extract_data(call, false);
if (ret < 0)
diff --git a/fs/afs/dir.c b/fs/afs/dir.c
index cc12772d0a4d..497f979018c2 100644
--- a/fs/afs/dir.c
+++ b/fs/afs/dir.c
@@ -803,7 +803,12 @@ success:
continue;
if (cookie->inodes[i]) {
- afs_vnode_commit_status(&fc, AFS_FS_I(cookie->inodes[i]),
+ struct afs_vnode *iv = AFS_FS_I(cookie->inodes[i]);
+
+ if (test_bit(AFS_VNODE_UNSET, &iv->flags))
+ continue;
+
+ afs_vnode_commit_status(&fc, iv,
scb->cb_break, NULL, scb);
continue;
}
diff --git a/fs/afs/dir_edit.c b/fs/afs/dir_edit.c
index d4fbe5f85f1b..b108528bf010 100644
--- a/fs/afs/dir_edit.c
+++ b/fs/afs/dir_edit.c
@@ -68,13 +68,11 @@ static int afs_find_contig_bits(union afs_xdr_dir_block *block, unsigned int nr_
static void afs_set_contig_bits(union afs_xdr_dir_block *block,
int bit, unsigned int nr_slots)
{
- u64 mask, before, after;
+ u64 mask;
mask = (1 << nr_slots) - 1;
mask <<= bit;
- before = *(u64 *)block->hdr.bitmap;
-
block->hdr.bitmap[0] |= (u8)(mask >> 0 * 8);
block->hdr.bitmap[1] |= (u8)(mask >> 1 * 8);
block->hdr.bitmap[2] |= (u8)(mask >> 2 * 8);
@@ -83,8 +81,6 @@ static void afs_set_contig_bits(union afs_xdr_dir_block *block,
block->hdr.bitmap[5] |= (u8)(mask >> 5 * 8);
block->hdr.bitmap[6] |= (u8)(mask >> 6 * 8);
block->hdr.bitmap[7] |= (u8)(mask >> 7 * 8);
-
- after = *(u64 *)block->hdr.bitmap;
}
/*
@@ -93,13 +89,11 @@ static void afs_set_contig_bits(union afs_xdr_dir_block *block,
static void afs_clear_contig_bits(union afs_xdr_dir_block *block,
int bit, unsigned int nr_slots)
{
- u64 mask, before, after;
+ u64 mask;
mask = (1 << nr_slots) - 1;
mask <<= bit;
- before = *(u64 *)block->hdr.bitmap;
-
block->hdr.bitmap[0] &= ~(u8)(mask >> 0 * 8);
block->hdr.bitmap[1] &= ~(u8)(mask >> 1 * 8);
block->hdr.bitmap[2] &= ~(u8)(mask >> 2 * 8);
@@ -108,8 +102,6 @@ static void afs_clear_contig_bits(union afs_xdr_dir_block *block,
block->hdr.bitmap[5] &= ~(u8)(mask >> 5 * 8);
block->hdr.bitmap[6] &= ~(u8)(mask >> 6 * 8);
block->hdr.bitmap[7] &= ~(u8)(mask >> 7 * 8);
-
- after = *(u64 *)block->hdr.bitmap;
}
/*
diff --git a/fs/afs/file.c b/fs/afs/file.c
index dd3c55c9101c..8415733f7bc1 100644
--- a/fs/afs/file.c
+++ b/fs/afs/file.c
@@ -223,7 +223,7 @@ static void afs_file_readpage_read_complete(struct page *page,
/*
* Fetch file data from the volume.
*/
-int afs_fetch_data(struct afs_vnode *vnode, struct key *key, struct afs_read *desc)
+int afs_fetch_data(struct afs_vnode *vnode, struct key *key, struct afs_read *req)
{
struct afs_fs_cursor fc;
struct afs_status_cb *scb;
@@ -246,7 +246,7 @@ int afs_fetch_data(struct afs_vnode *vnode, struct key *key, struct afs_read *de
while (afs_select_fileserver(&fc)) {
fc.cb_break = afs_calc_vnode_cb_break(vnode);
- afs_fs_fetch_data(&fc, scb, desc);
+ afs_fs_fetch_data(&fc, scb, req);
}
afs_check_for_remote_deletion(&fc, vnode);
@@ -257,7 +257,7 @@ int afs_fetch_data(struct afs_vnode *vnode, struct key *key, struct afs_read *de
if (ret == 0) {
afs_stat_v(vnode, n_fetches);
- atomic_long_add(desc->actual_len,
+ atomic_long_add(req->actual_len,
&afs_v2net(vnode)->n_fetch_bytes);
}
diff --git a/fs/afs/flock.c b/fs/afs/flock.c
index d5e5a6ddc847..0f2a94ba73cb 100644
--- a/fs/afs/flock.c
+++ b/fs/afs/flock.c
@@ -346,8 +346,8 @@ again:
if (ret < 0) {
trace_afs_flock_ev(vnode, NULL, afs_flock_extend_fail,
ret);
- pr_warning("AFS: Failed to extend lock on {%llx:%llx} error %d\n",
- vnode->fid.vid, vnode->fid.vnode, ret);
+ pr_warn("AFS: Failed to extend lock on {%llx:%llx} error %d\n",
+ vnode->fid.vid, vnode->fid.vnode, ret);
}
spin_lock(&vnode->lock);
diff --git a/fs/afs/fsclient.c b/fs/afs/fsclient.c
index 6f84231f11a5..1f9c5d8e6fe5 100644
--- a/fs/afs/fsclient.c
+++ b/fs/afs/fsclient.c
@@ -323,7 +323,7 @@ static int afs_deliver_fs_fetch_data(struct afs_call *call)
int ret;
_enter("{%u,%zu/%llu}",
- call->unmarshall, iov_iter_count(&call->iter), req->actual_len);
+ call->unmarshall, iov_iter_count(call->iter), req->actual_len);
switch (call->unmarshall) {
case 0:
@@ -363,14 +363,14 @@ static int afs_deliver_fs_fetch_data(struct afs_call *call)
call->bvec[0].bv_len = size;
call->bvec[0].bv_offset = req->offset;
call->bvec[0].bv_page = req->pages[req->index];
- iov_iter_bvec(&call->iter, READ, call->bvec, 1, size);
+ iov_iter_bvec(&call->def_iter, READ, call->bvec, 1, size);
ASSERTCMP(size, <=, PAGE_SIZE);
/* Fall through */
/* extract the returned data */
case 2:
_debug("extract data %zu/%llu",
- iov_iter_count(&call->iter), req->remain);
+ iov_iter_count(call->iter), req->remain);
ret = afs_extract_data(call, true);
if (ret < 0)
@@ -398,7 +398,7 @@ static int afs_deliver_fs_fetch_data(struct afs_call *call)
case 3:
_debug("extract discard %zu/%llu",
- iov_iter_count(&call->iter), req->actual_len - req->len);
+ iov_iter_count(call->iter), req->actual_len - req->len);
ret = afs_extract_data(call, true);
if (ret < 0)
@@ -490,7 +490,7 @@ static int afs_fs_fetch_data64(struct afs_fs_cursor *fc,
call->key = fc->key;
call->out_scb = scb;
call->out_volsync = NULL;
- call->read_request = req;
+ call->read_request = afs_get_read(req);
/* marshall the parameters */
bp = call->request;
@@ -503,7 +503,6 @@ static int afs_fs_fetch_data64(struct afs_fs_cursor *fc,
bp[6] = 0;
bp[7] = htonl(lower_32_bits(req->len));
- refcount_inc(&req->usage);
afs_use_fs_server(call, fc->cbi);
trace_afs_make_fs_call(call, &vnode->fid);
afs_set_fc_call(call, fc);
@@ -540,7 +539,7 @@ int afs_fs_fetch_data(struct afs_fs_cursor *fc,
call->key = fc->key;
call->out_scb = scb;
call->out_volsync = NULL;
- call->read_request = req;
+ call->read_request = afs_get_read(req);
/* marshall the parameters */
bp = call->request;
@@ -551,7 +550,6 @@ int afs_fs_fetch_data(struct afs_fs_cursor *fc,
bp[4] = htonl(lower_32_bits(req->pos));
bp[5] = htonl(lower_32_bits(req->len));
- refcount_inc(&req->usage);
afs_use_fs_server(call, fc->cbi);
trace_afs_make_fs_call(call, &vnode->fid);
afs_set_fc_call(call, fc);
@@ -1852,7 +1850,7 @@ static int afs_deliver_fs_get_capabilities(struct afs_call *call)
u32 count;
int ret;
- _enter("{%u,%zu}", call->unmarshall, iov_iter_count(&call->iter));
+ _enter("{%u,%zu}", call->unmarshall, iov_iter_count(call->iter));
switch (call->unmarshall) {
case 0:
diff --git a/fs/afs/inode.c b/fs/afs/inode.c
index 46d2d7cb461d..281470fe1183 100644
--- a/fs/afs/inode.c
+++ b/fs/afs/inode.c
@@ -34,8 +34,7 @@ static noinline void dump_vnode(struct afs_vnode *vnode, struct afs_vnode *paren
{
static unsigned long once_only;
- pr_warn("kAFS: AFS vnode with undefined type %u\n",
- vnode->status.type);
+ pr_warn("kAFS: AFS vnode with undefined type %u\n", vnode->status.type);
pr_warn("kAFS: A=%d m=%o s=%llx v=%llx\n",
vnode->status.abort_code,
vnode->status.mode,
@@ -175,11 +174,11 @@ static void afs_apply_status(struct afs_fs_cursor *fc,
BUG_ON(test_bit(AFS_VNODE_UNSET, &vnode->flags));
if (status->type != vnode->status.type) {
- pr_warning("Vnode %llx:%llx:%x changed type %u to %u\n",
- vnode->fid.vid,
- vnode->fid.vnode,
- vnode->fid.unique,
- status->type, vnode->status.type);
+ pr_warn("Vnode %llx:%llx:%x changed type %u to %u\n",
+ vnode->fid.vid,
+ vnode->fid.vnode,
+ vnode->fid.unique,
+ status->type, vnode->status.type);
afs_protocol_error(NULL, -EBADMSG, afs_eproto_bad_status);
return;
}
diff --git a/fs/afs/internal.h b/fs/afs/internal.h
index 759e0578012c..1d81fc4c3058 100644
--- a/fs/afs/internal.h
+++ b/fs/afs/internal.h
@@ -115,9 +115,9 @@ struct afs_call {
struct afs_vnode *lvnode; /* vnode being locked */
void *request; /* request data (first part) */
struct address_space *mapping; /* Pages being written from */
- struct iov_iter iter; /* Buffer iterator */
- struct iov_iter *_iter; /* Iterator currently in use */
- union { /* Convenience for ->iter */
+ struct iov_iter def_iter; /* Default buffer/data iterator */
+ struct iov_iter *iter; /* Iterator currently in use */
+ union { /* Convenience for ->def_iter */
struct kvec kvec[1];
struct bio_vec bvec[1];
};
@@ -934,6 +934,12 @@ extern int afs_fetch_data(struct afs_vnode *, struct key *, struct afs_read *);
extern int afs_page_filler(void *, struct page *);
extern void afs_put_read(struct afs_read *);
+static inline struct afs_read *afs_get_read(struct afs_read *req)
+{
+ refcount_inc(&req->usage);
+ return req;
+}
+
/*
* flock.c
*/
@@ -1136,7 +1142,7 @@ static inline void afs_extract_begin(struct afs_call *call, void *buf, size_t si
{
call->kvec[0].iov_base = buf;
call->kvec[0].iov_len = size;
- iov_iter_kvec(&call->iter, READ, call->kvec, 1, size);
+ iov_iter_kvec(&call->def_iter, READ, call->kvec, 1, size);
}
static inline void afs_extract_to_tmp(struct afs_call *call)
@@ -1151,7 +1157,7 @@ static inline void afs_extract_to_tmp64(struct afs_call *call)
static inline void afs_extract_discard(struct afs_call *call, size_t size)
{
- iov_iter_discard(&call->iter, READ, size);
+ iov_iter_discard(&call->def_iter, READ, size);
}
static inline void afs_extract_to_buf(struct afs_call *call, size_t size)
diff --git a/fs/afs/rxrpc.c b/fs/afs/rxrpc.c
index 0e5269374ac1..58d396592250 100644
--- a/fs/afs/rxrpc.c
+++ b/fs/afs/rxrpc.c
@@ -152,7 +152,7 @@ static struct afs_call *afs_alloc_call(struct afs_net *net,
INIT_WORK(&call->async_work, afs_process_async_call);
init_waitqueue_head(&call->waitq);
spin_lock_init(&call->state_lock);
- call->_iter = &call->iter;
+ call->iter = &call->def_iter;
o = atomic_inc_return(&net->nr_outstanding_calls);
trace_afs_call(call, afs_call_trace_alloc, 1, o,
@@ -513,12 +513,12 @@ static void afs_deliver_to_call(struct afs_call *call)
state == AFS_CALL_SV_AWAIT_ACK
) {
if (state == AFS_CALL_SV_AWAIT_ACK) {
- iov_iter_kvec(&call->iter, READ, NULL, 0, 0);
+ iov_iter_kvec(&call->def_iter, READ, NULL, 0, 0);
ret = rxrpc_kernel_recv_data(call->net->socket,
- call->rxcall, &call->iter,
+ call->rxcall, &call->def_iter,
false, &remote_abort,
&call->service_id);
- trace_afs_receive_data(call, &call->iter, false, ret);
+ trace_afs_receive_data(call, &call->def_iter, false, ret);
if (ret == -EINPROGRESS || ret == -EAGAIN)
return;
@@ -637,6 +637,7 @@ long afs_wait_for_call_to_complete(struct afs_call *call,
call->need_attention = false;
__set_current_state(TASK_RUNNING);
afs_deliver_to_call(call);
+ timeout = rtt2;
continue;
}
@@ -858,7 +859,7 @@ static int afs_deliver_cm_op_id(struct afs_call *call)
{
int ret;
- _enter("{%zu}", iov_iter_count(call->_iter));
+ _enter("{%zu}", iov_iter_count(call->iter));
/* the operation ID forms the first four bytes of the request data */
ret = afs_extract_data(call, true);
@@ -974,7 +975,7 @@ void afs_send_simple_reply(struct afs_call *call, const void *buf, size_t len)
int afs_extract_data(struct afs_call *call, bool want_more)
{
struct afs_net *net = call->net;
- struct iov_iter *iter = call->_iter;
+ struct iov_iter *iter = call->iter;
enum afs_call_state state;
u32 remote_abort = 0;
int ret;
diff --git a/fs/afs/server.c b/fs/afs/server.c
index 64d440aaabc0..1686bf188ccd 100644
--- a/fs/afs/server.c
+++ b/fs/afs/server.c
@@ -151,7 +151,7 @@ static struct afs_server *afs_install_server(struct afs_net *net,
const struct afs_addr_list *alist;
struct afs_server *server;
struct rb_node **pp, *p;
- int ret = -EEXIST, diff;
+ int diff;
_enter("%p", candidate);
@@ -196,7 +196,6 @@ static struct afs_server *afs_install_server(struct afs_net *net,
hlist_add_head_rcu(&server->addr6_link, &net->fs_addresses6);
write_sequnlock(&net->fs_addr_lock);
- ret = 0;
exists:
afs_get_server(server, afs_server_trace_get_install);
diff --git a/fs/afs/super.c b/fs/afs/super.c
index f18911e8d770..488641b1a418 100644
--- a/fs/afs/super.c
+++ b/fs/afs/super.c
@@ -435,6 +435,7 @@ static int afs_fill_super(struct super_block *sb, struct afs_fs_context *ctx)
/* fill in the superblock */
sb->s_blocksize = PAGE_SIZE;
sb->s_blocksize_bits = PAGE_SHIFT;
+ sb->s_maxbytes = MAX_LFS_FILESIZE;
sb->s_magic = AFS_FS_MAGIC;
sb->s_op = &afs_super_ops;
if (!as->dyn_root)
diff --git a/fs/afs/vl_list.c b/fs/afs/vl_list.c
index 21eb0c0be912..8fea54eba0c2 100644
--- a/fs/afs/vl_list.c
+++ b/fs/afs/vl_list.c
@@ -279,8 +279,8 @@ struct afs_vlserver_list *afs_extract_vlserver_list(struct afs_cell *cell,
struct afs_addr_list *old = addrs;
write_lock(&server->lock);
- rcu_swap_protected(server->addresses, old,
- lockdep_is_held(&server->lock));
+ old = rcu_replace_pointer(server->addresses, old,
+ lockdep_is_held(&server->lock));
write_unlock(&server->lock);
afs_put_addrlist(old);
}
diff --git a/fs/afs/vlclient.c b/fs/afs/vlclient.c
index cfb0ac4bd039..516e9a3bb5b4 100644
--- a/fs/afs/vlclient.c
+++ b/fs/afs/vlclient.c
@@ -185,7 +185,7 @@ static int afs_deliver_vl_get_addrs_u(struct afs_call *call)
int i, ret;
_enter("{%u,%zu/%u}",
- call->unmarshall, iov_iter_count(call->_iter), call->count);
+ call->unmarshall, iov_iter_count(call->iter), call->count);
switch (call->unmarshall) {
case 0:
@@ -316,7 +316,7 @@ static int afs_deliver_vl_get_capabilities(struct afs_call *call)
int ret;
_enter("{%u,%zu/%u}",
- call->unmarshall, iov_iter_count(call->_iter), call->count);
+ call->unmarshall, iov_iter_count(call->iter), call->count);
switch (call->unmarshall) {
case 0:
@@ -425,7 +425,7 @@ static int afs_deliver_yfsvl_get_endpoints(struct afs_call *call)
int ret;
_enter("{%u,%zu,%u}",
- call->unmarshall, iov_iter_count(call->_iter), call->count2);
+ call->unmarshall, iov_iter_count(call->iter), call->count2);
switch (call->unmarshall) {
case 0:
diff --git a/fs/afs/xattr.c b/fs/afs/xattr.c
index 5552d034090a..7af41fd5f3ee 100644
--- a/fs/afs/xattr.c
+++ b/fs/afs/xattr.c
@@ -228,11 +228,11 @@ static int afs_xattr_get_yfs(const struct xattr_handler *handler,
break;
case 1:
data = buf;
- dsize = snprintf(buf, sizeof(buf), "%u", yacl->inherit_flag);
+ dsize = scnprintf(buf, sizeof(buf), "%u", yacl->inherit_flag);
break;
case 2:
data = buf;
- dsize = snprintf(buf, sizeof(buf), "%u", yacl->num_cleaned);
+ dsize = scnprintf(buf, sizeof(buf), "%u", yacl->num_cleaned);
break;
case 3:
data = yacl->vol_acl->data;
@@ -370,13 +370,15 @@ static int afs_xattr_get_fid(const struct xattr_handler *handler,
/* The volume ID is 64-bit, the vnode ID is 96-bit and the
* uniquifier is 32-bit.
*/
- len = sprintf(text, "%llx:", vnode->fid.vid);
+ len = scnprintf(text, sizeof(text), "%llx:", vnode->fid.vid);
if (vnode->fid.vnode_hi)
- len += sprintf(text + len, "%x%016llx",
- vnode->fid.vnode_hi, vnode->fid.vnode);
+ len += scnprintf(text + len, sizeof(text) - len, "%x%016llx",
+ vnode->fid.vnode_hi, vnode->fid.vnode);
else
- len += sprintf(text + len, "%llx", vnode->fid.vnode);
- len += sprintf(text + len, ":%x", vnode->fid.unique);
+ len += scnprintf(text + len, sizeof(text) - len, "%llx",
+ vnode->fid.vnode);
+ len += scnprintf(text + len, sizeof(text) - len, ":%x",
+ vnode->fid.unique);
if (size == 0)
return len;
diff --git a/fs/afs/yfsclient.c b/fs/afs/yfsclient.c
index 3ee7abf4b2d0..a26126ac7bf1 100644
--- a/fs/afs/yfsclient.c
+++ b/fs/afs/yfsclient.c
@@ -152,8 +152,8 @@ static void yfs_check_req(struct afs_call *call, __be32 *bp)
pr_err("kAFS: %s: Request buffer overflow (%zu>%u)\n",
call->type->name, len, call->request_size);
else if (len < call->request_size)
- pr_warning("kAFS: %s: Request buffer underflow (%zu<%u)\n",
- call->type->name, len, call->request_size);
+ pr_warn("kAFS: %s: Request buffer underflow (%zu<%u)\n",
+ call->type->name, len, call->request_size);
}
/*
@@ -441,7 +441,7 @@ static int yfs_deliver_fs_fetch_data64(struct afs_call *call)
int ret;
_enter("{%u,%zu/%llu}",
- call->unmarshall, iov_iter_count(&call->iter), req->actual_len);
+ call->unmarshall, iov_iter_count(call->iter), req->actual_len);
switch (call->unmarshall) {
case 0:
@@ -476,14 +476,14 @@ static int yfs_deliver_fs_fetch_data64(struct afs_call *call)
call->bvec[0].bv_len = size;
call->bvec[0].bv_offset = req->offset;
call->bvec[0].bv_page = req->pages[req->index];
- iov_iter_bvec(&call->iter, READ, call->bvec, 1, size);
+ iov_iter_bvec(&call->def_iter, READ, call->bvec, 1, size);
ASSERTCMP(size, <=, PAGE_SIZE);
/* Fall through */
/* extract the returned data */
case 2:
_debug("extract data %zu/%llu",
- iov_iter_count(&call->iter), req->remain);
+ iov_iter_count(call->iter), req->remain);
ret = afs_extract_data(call, true);
if (ret < 0)
@@ -511,7 +511,7 @@ static int yfs_deliver_fs_fetch_data64(struct afs_call *call)
case 3:
_debug("extract discard %zu/%llu",
- iov_iter_count(&call->iter), req->actual_len - req->len);
+ iov_iter_count(call->iter), req->actual_len - req->len);
ret = afs_extract_data(call, true);
if (ret < 0)
@@ -605,7 +605,7 @@ int yfs_fs_fetch_data(struct afs_fs_cursor *fc, struct afs_status_cb *scb,
call->key = fc->key;
call->out_scb = scb;
call->out_volsync = NULL;
- call->read_request = req;
+ call->read_request = afs_get_read(req);
/* marshall the parameters */
bp = call->request;
@@ -616,7 +616,6 @@ int yfs_fs_fetch_data(struct afs_fs_cursor *fc, struct afs_status_cb *scb,
bp = xdr_encode_u64(bp, req->len);
yfs_check_req(call, bp);
- refcount_inc(&req->usage);
afs_use_fs_server(call, fc->cbi);
trace_afs_make_fs_call(call, &vnode->fid);
afs_set_fc_call(call, fc);
diff --git a/fs/aio.c b/fs/aio.c
index 01e0fb9ae45a..a9fbad2ce5e6 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -2056,7 +2056,7 @@ static long do_io_getevents(aio_context_t ctx_id,
* specifies an infinite timeout. Note that the timeout pointed to by
* timeout is relative. Will fail with -ENOSYS if not implemented.
*/
-#if !defined(CONFIG_64BIT_TIME) || defined(CONFIG_64BIT)
+#ifdef CONFIG_64BIT
SYSCALL_DEFINE5(io_getevents, aio_context_t, ctx_id,
long, min_nr,
@@ -2179,7 +2179,7 @@ SYSCALL_DEFINE5(io_getevents_time32, __u32, ctx_id,
#ifdef CONFIG_COMPAT
struct __compat_aio_sigset {
- compat_sigset_t __user *sigmask;
+ compat_uptr_t sigmask;
compat_size_t sigsetsize;
};
@@ -2193,7 +2193,7 @@ COMPAT_SYSCALL_DEFINE6(io_pgetevents,
struct old_timespec32 __user *, timeout,
const struct __compat_aio_sigset __user *, usig)
{
- struct __compat_aio_sigset ksig = { NULL, };
+ struct __compat_aio_sigset ksig = { 0, };
struct timespec64 t;
bool interrupted;
int ret;
@@ -2204,7 +2204,7 @@ COMPAT_SYSCALL_DEFINE6(io_pgetevents,
if (usig && copy_from_user(&ksig, usig, sizeof(ksig)))
return -EFAULT;
- ret = set_compat_user_sigmask(ksig.sigmask, ksig.sigsetsize);
+ ret = set_compat_user_sigmask(compat_ptr(ksig.sigmask), ksig.sigsetsize);
if (ret)
return ret;
@@ -2228,7 +2228,7 @@ COMPAT_SYSCALL_DEFINE6(io_pgetevents_time64,
struct __kernel_timespec __user *, timeout,
const struct __compat_aio_sigset __user *, usig)
{
- struct __compat_aio_sigset ksig = { NULL, };
+ struct __compat_aio_sigset ksig = { 0, };
struct timespec64 t;
bool interrupted;
int ret;
@@ -2239,7 +2239,7 @@ COMPAT_SYSCALL_DEFINE6(io_pgetevents_time64,
if (usig && copy_from_user(&ksig, usig, sizeof(ksig)))
return -EFAULT;
- ret = set_compat_user_sigmask(ksig.sigmask, ksig.sigsetsize);
+ ret = set_compat_user_sigmask(compat_ptr(ksig.sigmask), ksig.sigsetsize);
if (ret)
return ret;
diff --git a/fs/autofs/autofs_i.h b/fs/autofs/autofs_i.h
index 8bcec8dcabb6..054f97b07754 100644
--- a/fs/autofs/autofs_i.h
+++ b/fs/autofs/autofs_i.h
@@ -63,7 +63,7 @@ struct autofs_info {
struct autofs_sb_info *sbi;
unsigned long last_used;
- atomic_t count;
+ int count;
kuid_t uid;
kgid_t gid;
diff --git a/fs/autofs/expire.c b/fs/autofs/expire.c
index 2866fabf497f..a1c7701007e7 100644
--- a/fs/autofs/expire.c
+++ b/fs/autofs/expire.c
@@ -211,7 +211,7 @@ static int autofs_tree_busy(struct vfsmount *mnt,
}
} else {
struct autofs_info *ino = autofs_dentry_ino(p);
- unsigned int ino_count = atomic_read(&ino->count);
+ unsigned int ino_count = READ_ONCE(ino->count);
/* allow for dget above and top is already dgot */
if (p == top)
@@ -379,7 +379,7 @@ static struct dentry *should_expire(struct dentry *dentry,
/* Not a forced expire? */
if (!(how & AUTOFS_EXP_FORCED)) {
/* ref-walk currently on this dentry? */
- ino_count = atomic_read(&ino->count) + 1;
+ ino_count = READ_ONCE(ino->count) + 1;
if (d_count(dentry) > ino_count)
return NULL;
}
@@ -396,7 +396,7 @@ static struct dentry *should_expire(struct dentry *dentry,
/* Not a forced expire? */
if (!(how & AUTOFS_EXP_FORCED)) {
/* ref-walk currently on this dentry? */
- ino_count = atomic_read(&ino->count) + 1;
+ ino_count = READ_ONCE(ino->count) + 1;
if (d_count(dentry) > ino_count)
return NULL;
}
@@ -459,9 +459,10 @@ static struct dentry *autofs_expire_indirect(struct super_block *sb,
*/
how &= ~AUTOFS_EXP_LEAVES;
found = should_expire(expired, mnt, timeout, how);
- if (!found || found != expired)
- /* Something has changed, continue */
+ if (found != expired) { // something has changed, continue
+ dput(found);
goto next;
+ }
if (expired != dentry)
dput(dentry);
diff --git a/fs/autofs/root.c b/fs/autofs/root.c
index 29abafc0ce31..5aaa1732bf1e 100644
--- a/fs/autofs/root.c
+++ b/fs/autofs/root.c
@@ -569,10 +569,9 @@ static int autofs_dir_symlink(struct inode *dir,
d_add(dentry, inode);
dget(dentry);
- atomic_inc(&ino->count);
+ ino->count++;
p_ino = autofs_dentry_ino(dentry->d_parent);
- if (p_ino && !IS_ROOT(dentry))
- atomic_inc(&p_ino->count);
+ p_ino->count++;
dir->i_mtime = current_time(dir);
@@ -610,11 +609,9 @@ static int autofs_dir_unlink(struct inode *dir, struct dentry *dentry)
if (sbi->flags & AUTOFS_SBI_CATATONIC)
return -EACCES;
- if (atomic_dec_and_test(&ino->count)) {
- p_ino = autofs_dentry_ino(dentry->d_parent);
- if (p_ino && !IS_ROOT(dentry))
- atomic_dec(&p_ino->count);
- }
+ ino->count--;
+ p_ino = autofs_dentry_ino(dentry->d_parent);
+ p_ino->count--;
dput(ino->dentry);
d_inode(dentry)->i_size = 0;
@@ -660,7 +657,6 @@ static void autofs_set_leaf_automount_flags(struct dentry *dentry)
static void autofs_clear_leaf_automount_flags(struct dentry *dentry)
{
- struct list_head *d_child;
struct dentry *parent;
/* flags for dentrys in the root are handled elsewhere */
@@ -673,10 +669,7 @@ static void autofs_clear_leaf_automount_flags(struct dentry *dentry)
/* only consider parents below dentrys in the root */
if (IS_ROOT(parent->d_parent))
return;
- d_child = &dentry->d_child;
- /* Set parent managed if it's becoming empty */
- if (d_child->next == &parent->d_subdirs &&
- d_child->prev == &parent->d_subdirs)
+ if (autofs_dentry_ino(parent)->count == 2)
managed_dentry_set_managed(parent);
}
@@ -698,11 +691,10 @@ static int autofs_dir_rmdir(struct inode *dir, struct dentry *dentry)
if (sbi->flags & AUTOFS_SBI_CATATONIC)
return -EACCES;
- spin_lock(&sbi->lookup_lock);
- if (!simple_empty(dentry)) {
- spin_unlock(&sbi->lookup_lock);
+ if (ino->count != 1)
return -ENOTEMPTY;
- }
+
+ spin_lock(&sbi->lookup_lock);
__autofs_add_expiring(dentry);
d_drop(dentry);
spin_unlock(&sbi->lookup_lock);
@@ -710,11 +702,9 @@ static int autofs_dir_rmdir(struct inode *dir, struct dentry *dentry)
if (sbi->version < 5)
autofs_clear_leaf_automount_flags(dentry);
- if (atomic_dec_and_test(&ino->count)) {
- p_ino = autofs_dentry_ino(dentry->d_parent);
- if (p_ino && dentry->d_parent != dentry)
- atomic_dec(&p_ino->count);
- }
+ ino->count--;
+ p_ino = autofs_dentry_ino(dentry->d_parent);
+ p_ino->count--;
dput(ino->dentry);
d_inode(dentry)->i_size = 0;
clear_nlink(d_inode(dentry));
@@ -760,10 +750,9 @@ static int autofs_dir_mkdir(struct inode *dir,
autofs_set_leaf_automount_flags(dentry);
dget(dentry);
- atomic_inc(&ino->count);
+ ino->count++;
p_ino = autofs_dentry_ino(dentry->d_parent);
- if (p_ino && !IS_ROOT(dentry))
- atomic_inc(&p_ino->count);
+ p_ino->count++;
inc_nlink(dir);
dir->i_mtime = current_time(dir);
diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c
index c5642bcb6b46..ecd8d2698515 100644
--- a/fs/binfmt_elf.c
+++ b/fs/binfmt_elf.c
@@ -404,6 +404,17 @@ static unsigned long total_mapping_size(const struct elf_phdr *cmds, int nr)
ELF_PAGESTART(cmds[first_idx].p_vaddr);
}
+static int elf_read(struct file *file, void *buf, size_t len, loff_t pos)
+{
+ ssize_t rv;
+
+ rv = kernel_read(file, buf, len, &pos);
+ if (unlikely(rv != len)) {
+ return (rv < 0) ? rv : -EIO;
+ }
+ return 0;
+}
+
/**
* load_elf_phdrs() - load ELF program headers
* @elf_ex: ELF header of the binary whose program headers should be loaded
@@ -418,7 +429,6 @@ static struct elf_phdr *load_elf_phdrs(const struct elfhdr *elf_ex,
{
struct elf_phdr *elf_phdata = NULL;
int retval, err = -1;
- loff_t pos = elf_ex->e_phoff;
unsigned int size;
/*
@@ -439,9 +449,9 @@ static struct elf_phdr *load_elf_phdrs(const struct elfhdr *elf_ex,
goto out;
/* Read in the program headers */
- retval = kernel_read(elf_file, elf_phdata, size, &pos);
- if (retval != size) {
- err = (retval < 0) ? retval : -EIO;
+ retval = elf_read(elf_file, elf_phdata, size, elf_ex->e_phoff);
+ if (retval < 0) {
+ err = retval;
goto out;
}
@@ -544,7 +554,7 @@ static inline int make_prot(u32 p_flags)
an ELF header */
static unsigned long load_elf_interp(struct elfhdr *interp_elf_ex,
- struct file *interpreter, unsigned long *interp_map_addr,
+ struct file *interpreter,
unsigned long no_base, struct elf_phdr *interp_elf_phdata)
{
struct elf_phdr *eppnt;
@@ -590,8 +600,6 @@ static unsigned long load_elf_interp(struct elfhdr *interp_elf_ex,
map_addr = elf_map(interpreter, load_addr + vaddr,
eppnt, elf_prot, elf_type, total_size);
total_size = 0;
- if (!*interp_map_addr)
- *interp_map_addr = map_addr;
error = map_addr;
if (BAD_ADDR(map_addr))
goto out;
@@ -722,7 +730,6 @@ static int load_elf_binary(struct linux_binprm *bprm)
elf_ppnt = elf_phdata;
for (i = 0; i < loc->elf_ex.e_phnum; i++, elf_ppnt++) {
char *elf_interpreter;
- loff_t pos;
if (elf_ppnt->p_type != PT_INTERP)
continue;
@@ -740,14 +747,10 @@ static int load_elf_binary(struct linux_binprm *bprm)
if (!elf_interpreter)
goto out_free_ph;
- pos = elf_ppnt->p_offset;
- retval = kernel_read(bprm->file, elf_interpreter,
- elf_ppnt->p_filesz, &pos);
- if (retval != elf_ppnt->p_filesz) {
- if (retval >= 0)
- retval = -EIO;
+ retval = elf_read(bprm->file, elf_interpreter, elf_ppnt->p_filesz,
+ elf_ppnt->p_offset);
+ if (retval < 0)
goto out_free_interp;
- }
/* make sure path is NULL terminated */
retval = -ENOEXEC;
if (elf_interpreter[elf_ppnt->p_filesz - 1] != '\0')
@@ -766,14 +769,10 @@ static int load_elf_binary(struct linux_binprm *bprm)
would_dump(bprm, interpreter);
/* Get the exec headers */
- pos = 0;
- retval = kernel_read(interpreter, &loc->interp_elf_ex,
- sizeof(loc->interp_elf_ex), &pos);
- if (retval != sizeof(loc->interp_elf_ex)) {
- if (retval >= 0)
- retval = -EIO;
+ retval = elf_read(interpreter, &loc->interp_elf_ex,
+ sizeof(loc->interp_elf_ex), 0);
+ if (retval < 0)
goto out_free_dentry;
- }
break;
@@ -1054,11 +1053,8 @@ out_free_interp:
}
if (interpreter) {
- unsigned long interp_map_addr = 0;
-
elf_entry = load_elf_interp(&loc->interp_elf_ex,
interpreter,
- &interp_map_addr,
load_bias, interp_elf_phdata);
if (!IS_ERR((void *)elf_entry)) {
/*
@@ -1179,11 +1175,10 @@ static int load_elf_library(struct file *file)
unsigned long elf_bss, bss, len;
int retval, error, i, j;
struct elfhdr elf_ex;
- loff_t pos = 0;
error = -ENOEXEC;
- retval = kernel_read(file, &elf_ex, sizeof(elf_ex), &pos);
- if (retval != sizeof(elf_ex))
+ retval = elf_read(file, &elf_ex, sizeof(elf_ex), 0);
+ if (retval < 0)
goto out;
if (memcmp(elf_ex.e_ident, ELFMAG, SELFMAG) != 0)
@@ -1208,9 +1203,8 @@ static int load_elf_library(struct file *file)
eppnt = elf_phdata;
error = -ENOEXEC;
- pos = elf_ex.e_phoff;
- retval = kernel_read(file, eppnt, j, &pos);
- if (retval != j)
+ retval = elf_read(file, eppnt, j, elf_ex.e_phoff);
+ if (retval < 0)
goto out_free_ph;
for (j = 0, i = 0; i<elf_ex.e_phnum; i++)
@@ -1489,18 +1483,18 @@ static void fill_prstatus(struct elf_prstatus *prstatus,
* group-wide total, not its individual thread total.
*/
thread_group_cputime(p, &cputime);
- prstatus->pr_utime = ns_to_timeval(cputime.utime);
- prstatus->pr_stime = ns_to_timeval(cputime.stime);
+ prstatus->pr_utime = ns_to_kernel_old_timeval(cputime.utime);
+ prstatus->pr_stime = ns_to_kernel_old_timeval(cputime.stime);
} else {
u64 utime, stime;
task_cputime(p, &utime, &stime);
- prstatus->pr_utime = ns_to_timeval(utime);
- prstatus->pr_stime = ns_to_timeval(stime);
+ prstatus->pr_utime = ns_to_kernel_old_timeval(utime);
+ prstatus->pr_stime = ns_to_kernel_old_timeval(stime);
}
- prstatus->pr_cutime = ns_to_timeval(p->signal->cutime);
- prstatus->pr_cstime = ns_to_timeval(p->signal->cstime);
+ prstatus->pr_cutime = ns_to_kernel_old_timeval(p->signal->cutime);
+ prstatus->pr_cstime = ns_to_kernel_old_timeval(p->signal->cstime);
}
static int fill_psinfo(struct elf_prpsinfo *psinfo, struct task_struct *p,
diff --git a/fs/binfmt_elf_fdpic.c b/fs/binfmt_elf_fdpic.c
index d86ebd0dcc3d..240f66663543 100644
--- a/fs/binfmt_elf_fdpic.c
+++ b/fs/binfmt_elf_fdpic.c
@@ -1359,17 +1359,17 @@ static void fill_prstatus(struct elf_prstatus *prstatus,
* group-wide total, not its individual thread total.
*/
thread_group_cputime(p, &cputime);
- prstatus->pr_utime = ns_to_timeval(cputime.utime);
- prstatus->pr_stime = ns_to_timeval(cputime.stime);
+ prstatus->pr_utime = ns_to_kernel_old_timeval(cputime.utime);
+ prstatus->pr_stime = ns_to_kernel_old_timeval(cputime.stime);
} else {
u64 utime, stime;
task_cputime(p, &utime, &stime);
- prstatus->pr_utime = ns_to_timeval(utime);
- prstatus->pr_stime = ns_to_timeval(stime);
+ prstatus->pr_utime = ns_to_kernel_old_timeval(utime);
+ prstatus->pr_stime = ns_to_kernel_old_timeval(stime);
}
- prstatus->pr_cutime = ns_to_timeval(p->signal->cutime);
- prstatus->pr_cstime = ns_to_timeval(p->signal->cstime);
+ prstatus->pr_cutime = ns_to_kernel_old_timeval(p->signal->cutime);
+ prstatus->pr_cstime = ns_to_kernel_old_timeval(p->signal->cstime);
prstatus->pr_exec_fdpic_loadmap = p->mm->context.exec_fdpic_loadmap;
prstatus->pr_interp_fdpic_loadmap = p->mm->context.interp_fdpic_loadmap;
diff --git a/fs/block_dev.c b/fs/block_dev.c
index 9c073dbdc1b0..69bf2fb6f7cd 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -1403,11 +1403,7 @@ static void flush_disk(struct block_device *bdev, bool kill_dirty)
"resized disk %s\n",
bdev->bd_disk ? bdev->bd_disk->disk_name : "");
}
-
- if (!bdev->bd_disk)
- return;
- if (disk_part_scan_enabled(bdev->bd_disk))
- bdev->bd_invalidated = 1;
+ bdev->bd_invalidated = 1;
}
/**
@@ -1420,8 +1416,8 @@ static void flush_disk(struct block_device *bdev, bool kill_dirty)
* and adjusts it if it differs. When shrinking the bdev size, its all caches
* are freed.
*/
-void check_disk_size_change(struct gendisk *disk, struct block_device *bdev,
- bool verbose)
+static void check_disk_size_change(struct gendisk *disk,
+ struct block_device *bdev, bool verbose)
{
loff_t disk_size, bdev_size;
@@ -1437,6 +1433,7 @@ void check_disk_size_change(struct gendisk *disk, struct block_device *bdev,
if (bdev_size > disk_size)
flush_disk(bdev, false);
}
+ bdev->bd_invalidated = 0;
}
/**
@@ -1466,7 +1463,6 @@ int revalidate_disk(struct gendisk *disk)
mutex_lock(&bdev->bd_mutex);
check_disk_size_change(disk, bdev, ret == 0);
- bdev->bd_invalidated = 0;
mutex_unlock(&bdev->bd_mutex);
bdput(bdev);
}
@@ -1512,6 +1508,45 @@ EXPORT_SYMBOL(bd_set_size);
static void __blkdev_put(struct block_device *bdev, fmode_t mode, int for_part);
+int bdev_disk_changed(struct block_device *bdev, bool invalidate)
+{
+ struct gendisk *disk = bdev->bd_disk;
+ int ret;
+
+ lockdep_assert_held(&bdev->bd_mutex);
+
+rescan:
+ ret = blk_drop_partitions(disk, bdev);
+ if (ret)
+ return ret;
+
+ if (invalidate)
+ set_capacity(disk, 0);
+ else if (disk->fops->revalidate_disk)
+ disk->fops->revalidate_disk(disk);
+
+ check_disk_size_change(disk, bdev, !invalidate);
+
+ if (get_capacity(disk)) {
+ ret = blk_add_partitions(disk, bdev);
+ if (ret == -EAGAIN)
+ goto rescan;
+ } else if (invalidate) {
+ /*
+ * Tell userspace that the media / partition table may have
+ * changed.
+ */
+ kobject_uevent(&disk_to_dev(disk)->kobj, KOBJ_CHANGE);
+ }
+
+ return ret;
+}
+/*
+ * Only exported for for loop and dasd for historic reasons. Don't use in new
+ * code!
+ */
+EXPORT_SYMBOL_GPL(bdev_disk_changed);
+
/*
* bd_mutex locking:
*
@@ -1594,12 +1629,9 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part)
* The latter is necessary to prevent ghost
* partitions on a removed medium.
*/
- if (bdev->bd_invalidated) {
- if (!ret)
- rescan_partitions(disk, bdev);
- else if (ret == -ENOMEDIUM)
- invalidate_partitions(disk, bdev);
- }
+ if (bdev->bd_invalidated &&
+ (!ret || ret == -ENOMEDIUM))
+ bdev_disk_changed(bdev, ret == -ENOMEDIUM);
if (ret)
goto out_clear;
@@ -1632,12 +1664,9 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part)
if (bdev->bd_disk->fops->open)
ret = bdev->bd_disk->fops->open(bdev, mode);
/* the same as first opener case, read comment there */
- if (bdev->bd_invalidated) {
- if (!ret)
- rescan_partitions(bdev->bd_disk, bdev);
- else if (ret == -ENOMEDIUM)
- invalidate_partitions(bdev->bd_disk, bdev);
- }
+ if (bdev->bd_invalidated &&
+ (!ret || ret == -ENOMEDIUM))
+ bdev_disk_changed(bdev, ret == -ENOMEDIUM);
if (ret)
goto out_unlock_bdev;
}
diff --git a/fs/btrfs/Kconfig b/fs/btrfs/Kconfig
index 38651fae7f21..75b6d10c9845 100644
--- a/fs/btrfs/Kconfig
+++ b/fs/btrfs/Kconfig
@@ -5,6 +5,8 @@ config BTRFS_FS
select CRYPTO
select CRYPTO_CRC32C
select LIBCRC32C
+ select CRYPTO_XXHASH
+ select CRYPTO_SHA256
select ZLIB_INFLATE
select ZLIB_DEFLATE
select LZO_COMPRESS
diff --git a/fs/btrfs/async-thread.c b/fs/btrfs/async-thread.c
index 2e9e13ffbd08..1d32a07bb2d1 100644
--- a/fs/btrfs/async-thread.c
+++ b/fs/btrfs/async-thread.c
@@ -53,24 +53,12 @@ struct btrfs_workqueue {
struct __btrfs_workqueue *high;
};
-static void normal_work_helper(struct btrfs_work *work);
-
-#define BTRFS_WORK_HELPER(name) \
-noinline_for_stack void btrfs_##name(struct work_struct *arg) \
-{ \
- struct btrfs_work *work = container_of(arg, struct btrfs_work, \
- normal_work); \
- normal_work_helper(work); \
-}
-
-struct btrfs_fs_info *
-btrfs_workqueue_owner(const struct __btrfs_workqueue *wq)
+struct btrfs_fs_info * __pure btrfs_workqueue_owner(const struct __btrfs_workqueue *wq)
{
return wq->fs_info;
}
-struct btrfs_fs_info *
-btrfs_work_owner(const struct btrfs_work *work)
+struct btrfs_fs_info * __pure btrfs_work_owner(const struct btrfs_work *work)
{
return work->wq->fs_info;
}
@@ -89,29 +77,6 @@ bool btrfs_workqueue_normal_congested(const struct btrfs_workqueue *wq)
return atomic_read(&wq->normal->pending) > wq->normal->thresh * 2;
}
-BTRFS_WORK_HELPER(worker_helper);
-BTRFS_WORK_HELPER(delalloc_helper);
-BTRFS_WORK_HELPER(flush_delalloc_helper);
-BTRFS_WORK_HELPER(cache_helper);
-BTRFS_WORK_HELPER(submit_helper);
-BTRFS_WORK_HELPER(fixup_helper);
-BTRFS_WORK_HELPER(endio_helper);
-BTRFS_WORK_HELPER(endio_meta_helper);
-BTRFS_WORK_HELPER(endio_meta_write_helper);
-BTRFS_WORK_HELPER(endio_raid56_helper);
-BTRFS_WORK_HELPER(endio_repair_helper);
-BTRFS_WORK_HELPER(rmw_helper);
-BTRFS_WORK_HELPER(endio_write_helper);
-BTRFS_WORK_HELPER(freespace_write_helper);
-BTRFS_WORK_HELPER(delayed_meta_helper);
-BTRFS_WORK_HELPER(readahead_helper);
-BTRFS_WORK_HELPER(qgroup_rescan_helper);
-BTRFS_WORK_HELPER(extent_refs_helper);
-BTRFS_WORK_HELPER(scrub_helper);
-BTRFS_WORK_HELPER(scrubwrc_helper);
-BTRFS_WORK_HELPER(scrubnc_helper);
-BTRFS_WORK_HELPER(scrubparity_helper);
-
static struct __btrfs_workqueue *
__btrfs_alloc_workqueue(struct btrfs_fs_info *fs_info, const char *name,
unsigned int flags, int limit_active, int thresh)
@@ -252,16 +217,16 @@ out:
}
}
-static void run_ordered_work(struct __btrfs_workqueue *wq)
+static void run_ordered_work(struct __btrfs_workqueue *wq,
+ struct btrfs_work *self)
{
struct list_head *list = &wq->ordered_list;
struct btrfs_work *work;
spinlock_t *lock = &wq->list_lock;
unsigned long flags;
+ bool free_self = false;
while (1) {
- void *wtag;
-
spin_lock_irqsave(lock, flags);
if (list_empty(list))
break;
@@ -287,22 +252,53 @@ static void run_ordered_work(struct __btrfs_workqueue *wq)
list_del(&work->ordered_list);
spin_unlock_irqrestore(lock, flags);
- /*
- * We don't want to call the ordered free functions with the
- * lock held though. Save the work as tag for the trace event,
- * because the callback could free the structure.
- */
- wtag = work;
- work->ordered_free(work);
- trace_btrfs_all_work_done(wq->fs_info, wtag);
+ if (work == self) {
+ /*
+ * This is the work item that the worker is currently
+ * executing.
+ *
+ * The kernel workqueue code guarantees non-reentrancy
+ * of work items. I.e., if a work item with the same
+ * address and work function is queued twice, the second
+ * execution is blocked until the first one finishes. A
+ * work item may be freed and recycled with the same
+ * work function; the workqueue code assumes that the
+ * original work item cannot depend on the recycled work
+ * item in that case (see find_worker_executing_work()).
+ *
+ * Note that different types of Btrfs work can depend on
+ * each other, and one type of work on one Btrfs
+ * filesystem may even depend on the same type of work
+ * on another Btrfs filesystem via, e.g., a loop device.
+ * Therefore, we must not allow the current work item to
+ * be recycled until we are really done, otherwise we
+ * break the above assumption and can deadlock.
+ */
+ free_self = true;
+ } else {
+ /*
+ * We don't want to call the ordered free functions with
+ * the lock held.
+ */
+ work->ordered_free(work);
+ /* NB: work must not be dereferenced past this point. */
+ trace_btrfs_all_work_done(wq->fs_info, work);
+ }
}
spin_unlock_irqrestore(lock, flags);
+
+ if (free_self) {
+ self->ordered_free(self);
+ /* NB: self must not be dereferenced past this point. */
+ trace_btrfs_all_work_done(wq->fs_info, self);
+ }
}
-static void normal_work_helper(struct btrfs_work *work)
+static void btrfs_work_helper(struct work_struct *normal_work)
{
+ struct btrfs_work *work = container_of(normal_work, struct btrfs_work,
+ normal_work);
struct __btrfs_workqueue *wq;
- void *wtag;
int need_order = 0;
/*
@@ -316,29 +312,26 @@ static void normal_work_helper(struct btrfs_work *work)
if (work->ordered_func)
need_order = 1;
wq = work->wq;
- /* Safe for tracepoints in case work gets freed by the callback */
- wtag = work;
trace_btrfs_work_sched(work);
thresh_exec_hook(wq);
work->func(work);
if (need_order) {
set_bit(WORK_DONE_BIT, &work->flags);
- run_ordered_work(wq);
+ run_ordered_work(wq, work);
+ } else {
+ /* NB: work must not be dereferenced past this point. */
+ trace_btrfs_all_work_done(wq->fs_info, work);
}
- if (!need_order)
- trace_btrfs_all_work_done(wq->fs_info, wtag);
}
-void btrfs_init_work(struct btrfs_work *work, btrfs_work_func_t uniq_func,
- btrfs_func_t func,
- btrfs_func_t ordered_func,
- btrfs_func_t ordered_free)
+void btrfs_init_work(struct btrfs_work *work, btrfs_func_t func,
+ btrfs_func_t ordered_func, btrfs_func_t ordered_free)
{
work->func = func;
work->ordered_func = ordered_func;
work->ordered_free = ordered_free;
- INIT_WORK(&work->normal_work, uniq_func);
+ INIT_WORK(&work->normal_work, btrfs_work_helper);
INIT_LIST_HEAD(&work->ordered_list);
work->flags = 0;
}
diff --git a/fs/btrfs/async-thread.h b/fs/btrfs/async-thread.h
index 7861c9feba5f..a4434301d84d 100644
--- a/fs/btrfs/async-thread.h
+++ b/fs/btrfs/async-thread.h
@@ -29,49 +29,20 @@ struct btrfs_work {
unsigned long flags;
};
-#define BTRFS_WORK_HELPER_PROTO(name) \
-void btrfs_##name(struct work_struct *arg)
-
-BTRFS_WORK_HELPER_PROTO(worker_helper);
-BTRFS_WORK_HELPER_PROTO(delalloc_helper);
-BTRFS_WORK_HELPER_PROTO(flush_delalloc_helper);
-BTRFS_WORK_HELPER_PROTO(cache_helper);
-BTRFS_WORK_HELPER_PROTO(submit_helper);
-BTRFS_WORK_HELPER_PROTO(fixup_helper);
-BTRFS_WORK_HELPER_PROTO(endio_helper);
-BTRFS_WORK_HELPER_PROTO(endio_meta_helper);
-BTRFS_WORK_HELPER_PROTO(endio_meta_write_helper);
-BTRFS_WORK_HELPER_PROTO(endio_raid56_helper);
-BTRFS_WORK_HELPER_PROTO(endio_repair_helper);
-BTRFS_WORK_HELPER_PROTO(rmw_helper);
-BTRFS_WORK_HELPER_PROTO(endio_write_helper);
-BTRFS_WORK_HELPER_PROTO(freespace_write_helper);
-BTRFS_WORK_HELPER_PROTO(delayed_meta_helper);
-BTRFS_WORK_HELPER_PROTO(readahead_helper);
-BTRFS_WORK_HELPER_PROTO(qgroup_rescan_helper);
-BTRFS_WORK_HELPER_PROTO(extent_refs_helper);
-BTRFS_WORK_HELPER_PROTO(scrub_helper);
-BTRFS_WORK_HELPER_PROTO(scrubwrc_helper);
-BTRFS_WORK_HELPER_PROTO(scrubnc_helper);
-BTRFS_WORK_HELPER_PROTO(scrubparity_helper);
-
-
struct btrfs_workqueue *btrfs_alloc_workqueue(struct btrfs_fs_info *fs_info,
const char *name,
unsigned int flags,
int limit_active,
int thresh);
-void btrfs_init_work(struct btrfs_work *work, btrfs_work_func_t helper,
- btrfs_func_t func,
- btrfs_func_t ordered_func,
- btrfs_func_t ordered_free);
+void btrfs_init_work(struct btrfs_work *work, btrfs_func_t func,
+ btrfs_func_t ordered_func, btrfs_func_t ordered_free);
void btrfs_queue_work(struct btrfs_workqueue *wq,
struct btrfs_work *work);
void btrfs_destroy_workqueue(struct btrfs_workqueue *wq);
void btrfs_workqueue_set_max(struct btrfs_workqueue *wq, int max);
void btrfs_set_work_high_priority(struct btrfs_work *work);
-struct btrfs_fs_info *btrfs_work_owner(const struct btrfs_work *work);
-struct btrfs_fs_info *btrfs_workqueue_owner(const struct __btrfs_workqueue *wq);
+struct btrfs_fs_info * __pure btrfs_work_owner(const struct btrfs_work *work);
+struct btrfs_fs_info * __pure btrfs_workqueue_owner(const struct __btrfs_workqueue *wq);
bool btrfs_workqueue_normal_congested(const struct btrfs_workqueue *wq);
#endif
diff --git a/fs/btrfs/block-group.c b/fs/btrfs/block-group.c
index bf7e3f23bba7..6934a5b8708f 100644
--- a/fs/btrfs/block-group.c
+++ b/fs/btrfs/block-group.c
@@ -120,12 +120,12 @@ u64 btrfs_get_alloc_profile(struct btrfs_fs_info *fs_info, u64 orig_flags)
return get_alloc_profile(fs_info, orig_flags);
}
-void btrfs_get_block_group(struct btrfs_block_group_cache *cache)
+void btrfs_get_block_group(struct btrfs_block_group *cache)
{
atomic_inc(&cache->count);
}
-void btrfs_put_block_group(struct btrfs_block_group_cache *cache)
+void btrfs_put_block_group(struct btrfs_block_group *cache)
{
if (atomic_dec_and_test(&cache->count)) {
WARN_ON(cache->pinned > 0);
@@ -149,22 +149,21 @@ void btrfs_put_block_group(struct btrfs_block_group_cache *cache)
* This adds the block group to the fs_info rb tree for the block group cache
*/
static int btrfs_add_block_group_cache(struct btrfs_fs_info *info,
- struct btrfs_block_group_cache *block_group)
+ struct btrfs_block_group *block_group)
{
struct rb_node **p;
struct rb_node *parent = NULL;
- struct btrfs_block_group_cache *cache;
+ struct btrfs_block_group *cache;
spin_lock(&info->block_group_cache_lock);
p = &info->block_group_cache_tree.rb_node;
while (*p) {
parent = *p;
- cache = rb_entry(parent, struct btrfs_block_group_cache,
- cache_node);
- if (block_group->key.objectid < cache->key.objectid) {
+ cache = rb_entry(parent, struct btrfs_block_group, cache_node);
+ if (block_group->start < cache->start) {
p = &(*p)->rb_left;
- } else if (block_group->key.objectid > cache->key.objectid) {
+ } else if (block_group->start > cache->start) {
p = &(*p)->rb_right;
} else {
spin_unlock(&info->block_group_cache_lock);
@@ -176,8 +175,8 @@ static int btrfs_add_block_group_cache(struct btrfs_fs_info *info,
rb_insert_color(&block_group->cache_node,
&info->block_group_cache_tree);
- if (info->first_logical_byte > block_group->key.objectid)
- info->first_logical_byte = block_group->key.objectid;
+ if (info->first_logical_byte > block_group->start)
+ info->first_logical_byte = block_group->start;
spin_unlock(&info->block_group_cache_lock);
@@ -188,10 +187,10 @@ static int btrfs_add_block_group_cache(struct btrfs_fs_info *info,
* This will return the block group at or after bytenr if contains is 0, else
* it will return the block group that contains the bytenr
*/
-static struct btrfs_block_group_cache *block_group_cache_tree_search(
+static struct btrfs_block_group *block_group_cache_tree_search(
struct btrfs_fs_info *info, u64 bytenr, int contains)
{
- struct btrfs_block_group_cache *cache, *ret = NULL;
+ struct btrfs_block_group *cache, *ret = NULL;
struct rb_node *n;
u64 end, start;
@@ -199,13 +198,12 @@ static struct btrfs_block_group_cache *block_group_cache_tree_search(
n = info->block_group_cache_tree.rb_node;
while (n) {
- cache = rb_entry(n, struct btrfs_block_group_cache,
- cache_node);
- end = cache->key.objectid + cache->key.offset - 1;
- start = cache->key.objectid;
+ cache = rb_entry(n, struct btrfs_block_group, cache_node);
+ end = cache->start + cache->length - 1;
+ start = cache->start;
if (bytenr < start) {
- if (!contains && (!ret || start < ret->key.objectid))
+ if (!contains && (!ret || start < ret->start))
ret = cache;
n = n->rb_left;
} else if (bytenr > start) {
@@ -221,8 +219,8 @@ static struct btrfs_block_group_cache *block_group_cache_tree_search(
}
if (ret) {
btrfs_get_block_group(ret);
- if (bytenr == 0 && info->first_logical_byte > ret->key.objectid)
- info->first_logical_byte = ret->key.objectid;
+ if (bytenr == 0 && info->first_logical_byte > ret->start)
+ info->first_logical_byte = ret->start;
}
spin_unlock(&info->block_group_cache_lock);
@@ -232,7 +230,7 @@ static struct btrfs_block_group_cache *block_group_cache_tree_search(
/*
* Return the block group that starts at or after bytenr
*/
-struct btrfs_block_group_cache *btrfs_lookup_first_block_group(
+struct btrfs_block_group *btrfs_lookup_first_block_group(
struct btrfs_fs_info *info, u64 bytenr)
{
return block_group_cache_tree_search(info, bytenr, 0);
@@ -241,14 +239,14 @@ struct btrfs_block_group_cache *btrfs_lookup_first_block_group(
/*
* Return the block group that contains the given bytenr
*/
-struct btrfs_block_group_cache *btrfs_lookup_block_group(
+struct btrfs_block_group *btrfs_lookup_block_group(
struct btrfs_fs_info *info, u64 bytenr)
{
return block_group_cache_tree_search(info, bytenr, 1);
}
-struct btrfs_block_group_cache *btrfs_next_block_group(
- struct btrfs_block_group_cache *cache)
+struct btrfs_block_group *btrfs_next_block_group(
+ struct btrfs_block_group *cache)
{
struct btrfs_fs_info *fs_info = cache->fs_info;
struct rb_node *node;
@@ -257,7 +255,7 @@ struct btrfs_block_group_cache *btrfs_next_block_group(
/* If our block group was removed, we need a full search. */
if (RB_EMPTY_NODE(&cache->cache_node)) {
- const u64 next_bytenr = cache->key.objectid + cache->key.offset;
+ const u64 next_bytenr = cache->start + cache->length;
spin_unlock(&fs_info->block_group_cache_lock);
btrfs_put_block_group(cache);
@@ -266,8 +264,7 @@ struct btrfs_block_group_cache *btrfs_next_block_group(
node = rb_next(&cache->cache_node);
btrfs_put_block_group(cache);
if (node) {
- cache = rb_entry(node, struct btrfs_block_group_cache,
- cache_node);
+ cache = rb_entry(node, struct btrfs_block_group, cache_node);
btrfs_get_block_group(cache);
} else
cache = NULL;
@@ -277,7 +274,7 @@ struct btrfs_block_group_cache *btrfs_next_block_group(
bool btrfs_inc_nocow_writers(struct btrfs_fs_info *fs_info, u64 bytenr)
{
- struct btrfs_block_group_cache *bg;
+ struct btrfs_block_group *bg;
bool ret = true;
bg = btrfs_lookup_block_group(fs_info, bytenr);
@@ -300,7 +297,7 @@ bool btrfs_inc_nocow_writers(struct btrfs_fs_info *fs_info, u64 bytenr)
void btrfs_dec_nocow_writers(struct btrfs_fs_info *fs_info, u64 bytenr)
{
- struct btrfs_block_group_cache *bg;
+ struct btrfs_block_group *bg;
bg = btrfs_lookup_block_group(fs_info, bytenr);
ASSERT(bg);
@@ -314,7 +311,7 @@ void btrfs_dec_nocow_writers(struct btrfs_fs_info *fs_info, u64 bytenr)
btrfs_put_block_group(bg);
}
-void btrfs_wait_nocow_writers(struct btrfs_block_group_cache *bg)
+void btrfs_wait_nocow_writers(struct btrfs_block_group *bg)
{
wait_var_event(&bg->nocow_writers, !atomic_read(&bg->nocow_writers));
}
@@ -322,7 +319,7 @@ void btrfs_wait_nocow_writers(struct btrfs_block_group_cache *bg)
void btrfs_dec_block_group_reservations(struct btrfs_fs_info *fs_info,
const u64 start)
{
- struct btrfs_block_group_cache *bg;
+ struct btrfs_block_group *bg;
bg = btrfs_lookup_block_group(fs_info, start);
ASSERT(bg);
@@ -331,7 +328,7 @@ void btrfs_dec_block_group_reservations(struct btrfs_fs_info *fs_info,
btrfs_put_block_group(bg);
}
-void btrfs_wait_block_group_reservations(struct btrfs_block_group_cache *bg)
+void btrfs_wait_block_group_reservations(struct btrfs_block_group *bg)
{
struct btrfs_space_info *space_info = bg->space_info;
@@ -357,7 +354,7 @@ void btrfs_wait_block_group_reservations(struct btrfs_block_group_cache *bg)
}
struct btrfs_caching_control *btrfs_get_caching_control(
- struct btrfs_block_group_cache *cache)
+ struct btrfs_block_group *cache)
{
struct btrfs_caching_control *ctl;
@@ -392,7 +389,7 @@ void btrfs_put_caching_control(struct btrfs_caching_control *ctl)
* Callers of this must check if cache->cached == BTRFS_CACHE_ERROR before using
* any of the information in this block group.
*/
-void btrfs_wait_block_group_cache_progress(struct btrfs_block_group_cache *cache,
+void btrfs_wait_block_group_cache_progress(struct btrfs_block_group *cache,
u64 num_bytes)
{
struct btrfs_caching_control *caching_ctl;
@@ -401,13 +398,13 @@ void btrfs_wait_block_group_cache_progress(struct btrfs_block_group_cache *cache
if (!caching_ctl)
return;
- wait_event(caching_ctl->wait, btrfs_block_group_cache_done(cache) ||
+ wait_event(caching_ctl->wait, btrfs_block_group_done(cache) ||
(cache->free_space_ctl->free_space >= num_bytes));
btrfs_put_caching_control(caching_ctl);
}
-int btrfs_wait_block_group_cache_done(struct btrfs_block_group_cache *cache)
+int btrfs_wait_block_group_cache_done(struct btrfs_block_group *cache)
{
struct btrfs_caching_control *caching_ctl;
int ret = 0;
@@ -416,7 +413,7 @@ int btrfs_wait_block_group_cache_done(struct btrfs_block_group_cache *cache)
if (!caching_ctl)
return (cache->cached == BTRFS_CACHE_ERROR) ? -EIO : 0;
- wait_event(caching_ctl->wait, btrfs_block_group_cache_done(cache));
+ wait_event(caching_ctl->wait, btrfs_block_group_done(cache));
if (cache->cached == BTRFS_CACHE_ERROR)
ret = -EIO;
btrfs_put_caching_control(caching_ctl);
@@ -424,11 +421,11 @@ int btrfs_wait_block_group_cache_done(struct btrfs_block_group_cache *cache)
}
#ifdef CONFIG_BTRFS_DEBUG
-static void fragment_free_space(struct btrfs_block_group_cache *block_group)
+static void fragment_free_space(struct btrfs_block_group *block_group)
{
struct btrfs_fs_info *fs_info = block_group->fs_info;
- u64 start = block_group->key.objectid;
- u64 len = block_group->key.offset;
+ u64 start = block_group->start;
+ u64 len = block_group->length;
u64 chunk = block_group->flags & BTRFS_BLOCK_GROUP_METADATA ?
fs_info->nodesize : fs_info->sectorsize;
u64 step = chunk << 1;
@@ -450,8 +447,7 @@ static void fragment_free_space(struct btrfs_block_group_cache *block_group)
* used yet since their free space will be released as soon as the transaction
* commits.
*/
-u64 add_new_free_space(struct btrfs_block_group_cache *block_group,
- u64 start, u64 end)
+u64 add_new_free_space(struct btrfs_block_group *block_group, u64 start, u64 end)
{
struct btrfs_fs_info *info = block_group->fs_info;
u64 extent_start, extent_end, size, total_added = 0;
@@ -491,7 +487,7 @@ u64 add_new_free_space(struct btrfs_block_group_cache *block_group,
static int load_extent_tree_free(struct btrfs_caching_control *caching_ctl)
{
- struct btrfs_block_group_cache *block_group = caching_ctl->block_group;
+ struct btrfs_block_group *block_group = caching_ctl->block_group;
struct btrfs_fs_info *fs_info = block_group->fs_info;
struct btrfs_root *extent_root = fs_info->extent_root;
struct btrfs_path *path;
@@ -507,7 +503,7 @@ static int load_extent_tree_free(struct btrfs_caching_control *caching_ctl)
if (!path)
return -ENOMEM;
- last = max_t(u64, block_group->key.objectid, BTRFS_SUPER_INFO_OFFSET);
+ last = max_t(u64, block_group->start, BTRFS_SUPER_INFO_OFFSET);
#ifdef CONFIG_BTRFS_DEBUG
/*
@@ -587,13 +583,12 @@ next:
goto next;
}
- if (key.objectid < block_group->key.objectid) {
+ if (key.objectid < block_group->start) {
path->slots[0]++;
continue;
}
- if (key.objectid >= block_group->key.objectid +
- block_group->key.offset)
+ if (key.objectid >= block_group->start + block_group->length)
break;
if (key.type == BTRFS_EXTENT_ITEM_KEY ||
@@ -617,8 +612,7 @@ next:
ret = 0;
total_found += add_new_free_space(block_group, last,
- block_group->key.objectid +
- block_group->key.offset);
+ block_group->start + block_group->length);
caching_ctl->progress = (u64)-1;
out:
@@ -628,7 +622,7 @@ out:
static noinline void caching_thread(struct btrfs_work *work)
{
- struct btrfs_block_group_cache *block_group;
+ struct btrfs_block_group *block_group;
struct btrfs_fs_info *fs_info;
struct btrfs_caching_control *caching_ctl;
int ret;
@@ -656,8 +650,7 @@ static noinline void caching_thread(struct btrfs_work *work)
spin_lock(&block_group->space_info->lock);
spin_lock(&block_group->lock);
- bytes_used = block_group->key.offset -
- btrfs_block_group_used(&block_group->item);
+ bytes_used = block_group->length - block_group->used;
block_group->space_info->bytes_used += bytes_used >> 1;
spin_unlock(&block_group->lock);
spin_unlock(&block_group->space_info->lock);
@@ -677,8 +670,7 @@ static noinline void caching_thread(struct btrfs_work *work)
btrfs_put_block_group(block_group);
}
-int btrfs_cache_block_group(struct btrfs_block_group_cache *cache,
- int load_cache_only)
+int btrfs_cache_block_group(struct btrfs_block_group *cache, int load_cache_only)
{
DEFINE_WAIT(wait);
struct btrfs_fs_info *fs_info = cache->fs_info;
@@ -693,10 +685,9 @@ int btrfs_cache_block_group(struct btrfs_block_group_cache *cache,
mutex_init(&caching_ctl->mutex);
init_waitqueue_head(&caching_ctl->wait);
caching_ctl->block_group = cache;
- caching_ctl->progress = cache->key.objectid;
+ caching_ctl->progress = cache->start;
refcount_set(&caching_ctl->count, 1);
- btrfs_init_work(&caching_ctl->work, btrfs_cache_helper,
- caching_thread, NULL, NULL);
+ btrfs_init_work(&caching_ctl->work, caching_thread, NULL, NULL);
spin_lock(&cache->lock);
/*
@@ -763,8 +754,7 @@ int btrfs_cache_block_group(struct btrfs_block_group_cache *cache,
spin_lock(&cache->space_info->lock);
spin_lock(&cache->lock);
- bytes_used = cache->key.offset -
- btrfs_block_group_used(&cache->item);
+ bytes_used = cache->length - cache->used;
cache->space_info->bytes_used += bytes_used >> 1;
spin_unlock(&cache->lock);
spin_unlock(&cache->space_info->lock);
@@ -833,27 +823,36 @@ static void clear_avail_alloc_bits(struct btrfs_fs_info *fs_info, u64 flags)
*
* - RAID56 - in case there's neither RAID5 nor RAID6 profile block group
* in the whole filesystem
+ *
+ * - RAID1C34 - same as above for RAID1C3 and RAID1C4 block groups
*/
static void clear_incompat_bg_bits(struct btrfs_fs_info *fs_info, u64 flags)
{
- if (flags & BTRFS_BLOCK_GROUP_RAID56_MASK) {
+ bool found_raid56 = false;
+ bool found_raid1c34 = false;
+
+ if ((flags & BTRFS_BLOCK_GROUP_RAID56_MASK) ||
+ (flags & BTRFS_BLOCK_GROUP_RAID1C3) ||
+ (flags & BTRFS_BLOCK_GROUP_RAID1C4)) {
struct list_head *head = &fs_info->space_info;
struct btrfs_space_info *sinfo;
list_for_each_entry_rcu(sinfo, head, list) {
- bool found = false;
-
down_read(&sinfo->groups_sem);
if (!list_empty(&sinfo->block_groups[BTRFS_RAID_RAID5]))
- found = true;
+ found_raid56 = true;
if (!list_empty(&sinfo->block_groups[BTRFS_RAID_RAID6]))
- found = true;
+ found_raid56 = true;
+ if (!list_empty(&sinfo->block_groups[BTRFS_RAID_RAID1C3]))
+ found_raid1c34 = true;
+ if (!list_empty(&sinfo->block_groups[BTRFS_RAID_RAID1C4]))
+ found_raid1c34 = true;
up_read(&sinfo->groups_sem);
-
- if (found)
- return;
}
- btrfs_clear_fs_incompat(fs_info, RAID56);
+ if (found_raid56)
+ btrfs_clear_fs_incompat(fs_info, RAID56);
+ if (found_raid1c34)
+ btrfs_clear_fs_incompat(fs_info, RAID1C34);
}
}
@@ -863,7 +862,7 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans,
struct btrfs_fs_info *fs_info = trans->fs_info;
struct btrfs_root *root = fs_info->extent_root;
struct btrfs_path *path;
- struct btrfs_block_group_cache *block_group;
+ struct btrfs_block_group *block_group;
struct btrfs_free_cluster *cluster;
struct btrfs_root *tree_root = fs_info->tree_root;
struct btrfs_key key;
@@ -886,10 +885,9 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans,
* remove it.
*/
btrfs_free_excluded_extents(block_group);
- btrfs_free_ref_tree_range(fs_info, block_group->key.objectid,
- block_group->key.offset);
+ btrfs_free_ref_tree_range(fs_info, block_group->start,
+ block_group->length);
- memcpy(&key, &block_group->key, sizeof(key));
index = btrfs_bg_flags_to_raid_index(block_group->flags);
factor = btrfs_bg_type_to_factor(block_group->flags);
@@ -967,8 +965,8 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans,
}
key.objectid = BTRFS_FREE_SPACE_OBJECTID;
- key.offset = block_group->key.objectid;
key.type = 0;
+ key.offset = block_group->start;
ret = btrfs_search_slot(trans, tree_root, &key, path, -1, 1);
if (ret < 0)
@@ -987,7 +985,7 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans,
&fs_info->block_group_cache_tree);
RB_CLEAR_NODE(&block_group->cache_node);
- if (fs_info->first_logical_byte == block_group->key.objectid)
+ if (fs_info->first_logical_byte == block_group->start)
fs_info->first_logical_byte = (u64)-1;
spin_unlock(&fs_info->block_group_cache_lock);
@@ -1048,19 +1046,21 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans,
if (btrfs_test_opt(fs_info, ENOSPC_DEBUG)) {
WARN_ON(block_group->space_info->total_bytes
- < block_group->key.offset);
+ < block_group->length);
WARN_ON(block_group->space_info->bytes_readonly
- < block_group->key.offset);
+ < block_group->length);
WARN_ON(block_group->space_info->disk_total
- < block_group->key.offset * factor);
+ < block_group->length * factor);
}
- block_group->space_info->total_bytes -= block_group->key.offset;
- block_group->space_info->bytes_readonly -= block_group->key.offset;
- block_group->space_info->disk_total -= block_group->key.offset * factor;
+ block_group->space_info->total_bytes -= block_group->length;
+ block_group->space_info->bytes_readonly -= block_group->length;
+ block_group->space_info->disk_total -= block_group->length * factor;
spin_unlock(&block_group->space_info->lock);
- memcpy(&key, &block_group->key, sizeof(key));
+ key.objectid = block_group->start;
+ key.type = BTRFS_BLOCK_GROUP_ITEM_KEY;
+ key.offset = block_group->length;
mutex_lock(&fs_info->chunk_mutex);
spin_lock(&block_group->lock);
@@ -1180,7 +1180,7 @@ struct btrfs_trans_handle *btrfs_start_trans_remove_block_group(
* data in this block group. That check should be done by relocation routine,
* not this function.
*/
-static int inc_block_group_ro(struct btrfs_block_group_cache *cache, int force)
+static int inc_block_group_ro(struct btrfs_block_group *cache, int force)
{
struct btrfs_space_info *sinfo = cache->space_info;
u64 num_bytes;
@@ -1209,8 +1209,8 @@ static int inc_block_group_ro(struct btrfs_block_group_cache *cache, int force)
goto out;
}
- num_bytes = cache->key.offset - cache->reserved - cache->pinned -
- cache->bytes_super - btrfs_block_group_used(&cache->item);
+ num_bytes = cache->length - cache->reserved - cache->pinned -
+ cache->bytes_super - cache->used;
sinfo_used = btrfs_space_info_used(sinfo, true);
/*
@@ -1231,8 +1231,7 @@ out:
spin_unlock(&sinfo->lock);
if (ret == -ENOSPC && btrfs_test_opt(cache->fs_info, ENOSPC_DEBUG)) {
btrfs_info(cache->fs_info,
- "unable to make block group %llu ro",
- cache->key.objectid);
+ "unable to make block group %llu ro", cache->start);
btrfs_info(cache->fs_info,
"sinfo_used=%llu bg_num_bytes=%llu min_allocable=%llu",
sinfo_used, num_bytes, min_allocable_bytes);
@@ -1247,7 +1246,7 @@ out:
*/
void btrfs_delete_unused_bgs(struct btrfs_fs_info *fs_info)
{
- struct btrfs_block_group_cache *block_group;
+ struct btrfs_block_group *block_group;
struct btrfs_space_info *space_info;
struct btrfs_trans_handle *trans;
int ret = 0;
@@ -1261,7 +1260,7 @@ void btrfs_delete_unused_bgs(struct btrfs_fs_info *fs_info)
int trimming;
block_group = list_first_entry(&fs_info->unused_bgs,
- struct btrfs_block_group_cache,
+ struct btrfs_block_group,
bg_list);
list_del_init(&block_group->bg_list);
@@ -1279,8 +1278,7 @@ void btrfs_delete_unused_bgs(struct btrfs_fs_info *fs_info)
down_write(&space_info->groups_sem);
spin_lock(&block_group->lock);
if (block_group->reserved || block_group->pinned ||
- btrfs_block_group_used(&block_group->item) ||
- block_group->ro ||
+ block_group->used || block_group->ro ||
list_is_singular(&block_group->list)) {
/*
* We want to bail if we made new allocations or have
@@ -1308,7 +1306,7 @@ void btrfs_delete_unused_bgs(struct btrfs_fs_info *fs_info)
* properly if we fail to join the transaction.
*/
trans = btrfs_start_trans_remove_block_group(fs_info,
- block_group->key.objectid);
+ block_group->start);
if (IS_ERR(trans)) {
btrfs_dec_block_group_ro(block_group);
ret = PTR_ERR(trans);
@@ -1319,8 +1317,8 @@ void btrfs_delete_unused_bgs(struct btrfs_fs_info *fs_info)
* We could have pending pinned extents for this block group,
* just delete them, we don't care about them anymore.
*/
- start = block_group->key.objectid;
- end = start + block_group->key.offset - 1;
+ start = block_group->start;
+ end = start + block_group->length - 1;
/*
* Hold the unused_bg_unpin_mutex lock to avoid racing with
* btrfs_finish_extent_commit(). If we are at transaction N,
@@ -1375,7 +1373,7 @@ void btrfs_delete_unused_bgs(struct btrfs_fs_info *fs_info)
* Btrfs_remove_chunk will abort the transaction if things go
* horribly wrong.
*/
- ret = btrfs_remove_chunk(trans, block_group->key.objectid);
+ ret = btrfs_remove_chunk(trans, block_group->start);
if (ret) {
if (trimming)
@@ -1410,7 +1408,7 @@ next:
spin_unlock(&fs_info->unused_bgs_lock);
}
-void btrfs_mark_bg_unused(struct btrfs_block_group_cache *bg)
+void btrfs_mark_bg_unused(struct btrfs_block_group *bg)
{
struct btrfs_fs_info *fs_info = bg->fs_info;
@@ -1478,7 +1476,7 @@ static int find_first_block_group(struct btrfs_fs_info *fs_info,
read_extent_buffer(leaf, &bg,
btrfs_item_ptr_offset(leaf, slot),
sizeof(bg));
- flags = btrfs_block_group_flags(&bg) &
+ flags = btrfs_stack_block_group_flags(&bg) &
BTRFS_BLOCK_GROUP_TYPE_MASK;
if (flags != (em->map_lookup->type &
@@ -1518,7 +1516,7 @@ static void set_avail_alloc_bits(struct btrfs_fs_info *fs_info, u64 flags)
write_sequnlock(&fs_info->profiles_lock);
}
-static int exclude_super_stripes(struct btrfs_block_group_cache *cache)
+static int exclude_super_stripes(struct btrfs_block_group *cache)
{
struct btrfs_fs_info *fs_info = cache->fs_info;
u64 bytenr;
@@ -1526,10 +1524,10 @@ static int exclude_super_stripes(struct btrfs_block_group_cache *cache)
int stripe_len;
int i, nr, ret;
- if (cache->key.objectid < BTRFS_SUPER_INFO_OFFSET) {
- stripe_len = BTRFS_SUPER_INFO_OFFSET - cache->key.objectid;
+ if (cache->start < BTRFS_SUPER_INFO_OFFSET) {
+ stripe_len = BTRFS_SUPER_INFO_OFFSET - cache->start;
cache->bytes_super += stripe_len;
- ret = btrfs_add_excluded_extent(fs_info, cache->key.objectid,
+ ret = btrfs_add_excluded_extent(fs_info, cache->start,
stripe_len);
if (ret)
return ret;
@@ -1537,7 +1535,7 @@ static int exclude_super_stripes(struct btrfs_block_group_cache *cache)
for (i = 0; i < BTRFS_SUPER_MIRROR_MAX; i++) {
bytenr = btrfs_sb_offset(i);
- ret = btrfs_rmap_block(fs_info, cache->key.objectid,
+ ret = btrfs_rmap_block(fs_info, cache->start,
bytenr, &logical, &nr, &stripe_len);
if (ret)
return ret;
@@ -1545,21 +1543,19 @@ static int exclude_super_stripes(struct btrfs_block_group_cache *cache)
while (nr--) {
u64 start, len;
- if (logical[nr] > cache->key.objectid +
- cache->key.offset)
+ if (logical[nr] > cache->start + cache->length)
continue;
- if (logical[nr] + stripe_len <= cache->key.objectid)
+ if (logical[nr] + stripe_len <= cache->start)
continue;
start = logical[nr];
- if (start < cache->key.objectid) {
- start = cache->key.objectid;
+ if (start < cache->start) {
+ start = cache->start;
len = (logical[nr] + stripe_len) - start;
} else {
len = min_t(u64, stripe_len,
- cache->key.objectid +
- cache->key.offset - start);
+ cache->start + cache->length - start);
}
cache->bytes_super += len;
@@ -1575,7 +1571,7 @@ static int exclude_super_stripes(struct btrfs_block_group_cache *cache)
return 0;
}
-static void link_block_group(struct btrfs_block_group_cache *cache)
+static void link_block_group(struct btrfs_block_group *cache)
{
struct btrfs_space_info *space_info = cache->space_info;
int index = btrfs_bg_flags_to_raid_index(cache->flags);
@@ -1591,10 +1587,10 @@ static void link_block_group(struct btrfs_block_group_cache *cache)
btrfs_sysfs_add_block_group_type(cache);
}
-static struct btrfs_block_group_cache *btrfs_create_block_group_cache(
+static struct btrfs_block_group *btrfs_create_block_group_cache(
struct btrfs_fs_info *fs_info, u64 start, u64 size)
{
- struct btrfs_block_group_cache *cache;
+ struct btrfs_block_group *cache;
cache = kzalloc(sizeof(*cache), GFP_NOFS);
if (!cache)
@@ -1607,9 +1603,8 @@ static struct btrfs_block_group_cache *btrfs_create_block_group_cache(
return NULL;
}
- cache->key.objectid = start;
- cache->key.offset = size;
- cache->key.type = BTRFS_BLOCK_GROUP_ITEM_KEY;
+ cache->start = start;
+ cache->length = size;
cache->fs_info = fs_info;
cache->full_stripe_len = btrfs_full_stripe_len(fs_info, start);
@@ -1640,7 +1635,7 @@ static int check_chunk_block_group_mappings(struct btrfs_fs_info *fs_info)
{
struct extent_map_tree *map_tree = &fs_info->mapping_tree;
struct extent_map *em;
- struct btrfs_block_group_cache *bg;
+ struct btrfs_block_group *bg;
u64 start = 0;
int ret = 0;
@@ -1665,15 +1660,14 @@ static int check_chunk_block_group_mappings(struct btrfs_fs_info *fs_info)
free_extent_map(em);
break;
}
- if (bg->key.objectid != em->start ||
- bg->key.offset != em->len ||
+ if (bg->start != em->start || bg->length != em->len ||
(bg->flags & BTRFS_BLOCK_GROUP_TYPE_MASK) !=
(em->map_lookup->type & BTRFS_BLOCK_GROUP_TYPE_MASK)) {
btrfs_err(fs_info,
"chunk start=%llu len=%llu flags=0x%llx doesn't match block group start=%llu len=%llu flags=0x%llx",
em->start, em->len,
em->map_lookup->type & BTRFS_BLOCK_GROUP_TYPE_MASK,
- bg->key.objectid, bg->key.offset,
+ bg->start, bg->length,
bg->flags & BTRFS_BLOCK_GROUP_TYPE_MASK);
ret = -EUCLEAN;
free_extent_map(em);
@@ -1687,22 +1681,117 @@ static int check_chunk_block_group_mappings(struct btrfs_fs_info *fs_info)
return ret;
}
+static int read_one_block_group(struct btrfs_fs_info *info,
+ struct btrfs_path *path,
+ const struct btrfs_key *key,
+ int need_clear)
+{
+ struct extent_buffer *leaf = path->nodes[0];
+ struct btrfs_block_group *cache;
+ struct btrfs_space_info *space_info;
+ struct btrfs_block_group_item bgi;
+ const bool mixed = btrfs_fs_incompat(info, MIXED_GROUPS);
+ int slot = path->slots[0];
+ int ret;
+
+ ASSERT(key->type == BTRFS_BLOCK_GROUP_ITEM_KEY);
+
+ cache = btrfs_create_block_group_cache(info, key->objectid, key->offset);
+ if (!cache)
+ return -ENOMEM;
+
+ if (need_clear) {
+ /*
+ * When we mount with old space cache, we need to
+ * set BTRFS_DC_CLEAR and set dirty flag.
+ *
+ * a) Setting 'BTRFS_DC_CLEAR' makes sure that we
+ * truncate the old free space cache inode and
+ * setup a new one.
+ * b) Setting 'dirty flag' makes sure that we flush
+ * the new space cache info onto disk.
+ */
+ if (btrfs_test_opt(info, SPACE_CACHE))
+ cache->disk_cache_state = BTRFS_DC_CLEAR;
+ }
+ read_extent_buffer(leaf, &bgi, btrfs_item_ptr_offset(leaf, slot),
+ sizeof(bgi));
+ cache->used = btrfs_stack_block_group_used(&bgi);
+ cache->flags = btrfs_stack_block_group_flags(&bgi);
+ if (!mixed && ((cache->flags & BTRFS_BLOCK_GROUP_METADATA) &&
+ (cache->flags & BTRFS_BLOCK_GROUP_DATA))) {
+ btrfs_err(info,
+"bg %llu is a mixed block group but filesystem hasn't enabled mixed block groups",
+ cache->start);
+ ret = -EINVAL;
+ goto error;
+ }
+
+ /*
+ * We need to exclude the super stripes now so that the space info has
+ * super bytes accounted for, otherwise we'll think we have more space
+ * than we actually do.
+ */
+ ret = exclude_super_stripes(cache);
+ if (ret) {
+ /* We may have excluded something, so call this just in case. */
+ btrfs_free_excluded_extents(cache);
+ goto error;
+ }
+
+ /*
+ * Check for two cases, either we are full, and therefore don't need
+ * to bother with the caching work since we won't find any space, or we
+ * are empty, and we can just add all the space in and be done with it.
+ * This saves us _a_lot_ of time, particularly in the full case.
+ */
+ if (key->offset == cache->used) {
+ cache->last_byte_to_unpin = (u64)-1;
+ cache->cached = BTRFS_CACHE_FINISHED;
+ btrfs_free_excluded_extents(cache);
+ } else if (cache->used == 0) {
+ cache->last_byte_to_unpin = (u64)-1;
+ cache->cached = BTRFS_CACHE_FINISHED;
+ add_new_free_space(cache, key->objectid,
+ key->objectid + key->offset);
+ btrfs_free_excluded_extents(cache);
+ }
+
+ ret = btrfs_add_block_group_cache(info, cache);
+ if (ret) {
+ btrfs_remove_free_space_cache(cache);
+ goto error;
+ }
+ trace_btrfs_add_block_group(info, cache, 0);
+ btrfs_update_space_info(info, cache->flags, key->offset,
+ cache->used, cache->bytes_super, &space_info);
+
+ cache->space_info = space_info;
+
+ link_block_group(cache);
+
+ set_avail_alloc_bits(info, cache->flags);
+ if (btrfs_chunk_readonly(info, cache->start)) {
+ inc_block_group_ro(cache, 1);
+ } else if (cache->used == 0) {
+ ASSERT(list_empty(&cache->bg_list));
+ btrfs_mark_bg_unused(cache);
+ }
+ return 0;
+error:
+ btrfs_put_block_group(cache);
+ return ret;
+}
+
int btrfs_read_block_groups(struct btrfs_fs_info *info)
{
struct btrfs_path *path;
int ret;
- struct btrfs_block_group_cache *cache;
+ struct btrfs_block_group *cache;
struct btrfs_space_info *space_info;
struct btrfs_key key;
- struct btrfs_key found_key;
- struct extent_buffer *leaf;
int need_clear = 0;
u64 cache_gen;
- u64 feature;
- int mixed;
-
- feature = btrfs_super_incompat_flags(info->super_copy);
- mixed = !!(feature & BTRFS_FEATURE_INCOMPAT_MIXED_GROUPS);
key.objectid = 0;
key.offset = 0;
@@ -1726,107 +1815,13 @@ int btrfs_read_block_groups(struct btrfs_fs_info *info)
if (ret != 0)
goto error;
- leaf = path->nodes[0];
- btrfs_item_key_to_cpu(leaf, &found_key, path->slots[0]);
-
- cache = btrfs_create_block_group_cache(info, found_key.objectid,
- found_key.offset);
- if (!cache) {
- ret = -ENOMEM;
- goto error;
- }
-
- if (need_clear) {
- /*
- * When we mount with old space cache, we need to
- * set BTRFS_DC_CLEAR and set dirty flag.
- *
- * a) Setting 'BTRFS_DC_CLEAR' makes sure that we
- * truncate the old free space cache inode and
- * setup a new one.
- * b) Setting 'dirty flag' makes sure that we flush
- * the new space cache info onto disk.
- */
- if (btrfs_test_opt(info, SPACE_CACHE))
- cache->disk_cache_state = BTRFS_DC_CLEAR;
- }
-
- read_extent_buffer(leaf, &cache->item,
- btrfs_item_ptr_offset(leaf, path->slots[0]),
- sizeof(cache->item));
- cache->flags = btrfs_block_group_flags(&cache->item);
- if (!mixed &&
- ((cache->flags & BTRFS_BLOCK_GROUP_METADATA) &&
- (cache->flags & BTRFS_BLOCK_GROUP_DATA))) {
- btrfs_err(info,
-"bg %llu is a mixed block group but filesystem hasn't enabled mixed block groups",
- cache->key.objectid);
- ret = -EINVAL;
+ btrfs_item_key_to_cpu(path->nodes[0], &key, path->slots[0]);
+ ret = read_one_block_group(info, path, &key, need_clear);
+ if (ret < 0)
goto error;
- }
-
- key.objectid = found_key.objectid + found_key.offset;
+ key.objectid += key.offset;
+ key.offset = 0;
btrfs_release_path(path);
-
- /*
- * We need to exclude the super stripes now so that the space
- * info has super bytes accounted for, otherwise we'll think
- * we have more space than we actually do.
- */
- ret = exclude_super_stripes(cache);
- if (ret) {
- /*
- * We may have excluded something, so call this just in
- * case.
- */
- btrfs_free_excluded_extents(cache);
- btrfs_put_block_group(cache);
- goto error;
- }
-
- /*
- * Check for two cases, either we are full, and therefore
- * don't need to bother with the caching work since we won't
- * find any space, or we are empty, and we can just add all
- * the space in and be done with it. This saves us _a_lot_ of
- * time, particularly in the full case.
- */
- if (found_key.offset == btrfs_block_group_used(&cache->item)) {
- cache->last_byte_to_unpin = (u64)-1;
- cache->cached = BTRFS_CACHE_FINISHED;
- btrfs_free_excluded_extents(cache);
- } else if (btrfs_block_group_used(&cache->item) == 0) {
- cache->last_byte_to_unpin = (u64)-1;
- cache->cached = BTRFS_CACHE_FINISHED;
- add_new_free_space(cache, found_key.objectid,
- found_key.objectid +
- found_key.offset);
- btrfs_free_excluded_extents(cache);
- }
-
- ret = btrfs_add_block_group_cache(info, cache);
- if (ret) {
- btrfs_remove_free_space_cache(cache);
- btrfs_put_block_group(cache);
- goto error;
- }
-
- trace_btrfs_add_block_group(info, cache, 0);
- btrfs_update_space_info(info, cache->flags, found_key.offset,
- btrfs_block_group_used(&cache->item),
- cache->bytes_super, &space_info);
-
- cache->space_info = space_info;
-
- link_block_group(cache);
-
- set_avail_alloc_bits(info, cache->flags);
- if (btrfs_chunk_readonly(info, cache->key.objectid)) {
- inc_block_group_ro(cache, 1);
- } else if (btrfs_block_group_used(&cache->item) == 0) {
- ASSERT(list_empty(&cache->bg_list));
- btrfs_mark_bg_unused(cache);
- }
}
list_for_each_entry_rcu(space_info, &info->space_info, list) {
@@ -1860,7 +1855,7 @@ error:
void btrfs_create_pending_block_groups(struct btrfs_trans_handle *trans)
{
struct btrfs_fs_info *fs_info = trans->fs_info;
- struct btrfs_block_group_cache *block_group;
+ struct btrfs_block_group *block_group;
struct btrfs_root *extent_root = fs_info->extent_root;
struct btrfs_block_group_item item;
struct btrfs_key key;
@@ -1871,14 +1866,19 @@ void btrfs_create_pending_block_groups(struct btrfs_trans_handle *trans)
while (!list_empty(&trans->new_bgs)) {
block_group = list_first_entry(&trans->new_bgs,
- struct btrfs_block_group_cache,
+ struct btrfs_block_group,
bg_list);
if (ret)
goto next;
spin_lock(&block_group->lock);
- memcpy(&item, &block_group->item, sizeof(item));
- memcpy(&key, &block_group->key, sizeof(key));
+ btrfs_set_stack_block_group_used(&item, block_group->used);
+ btrfs_set_stack_block_group_chunk_objectid(&item,
+ BTRFS_FIRST_CHUNK_TREE_OBJECTID);
+ btrfs_set_stack_block_group_flags(&item, block_group->flags);
+ key.objectid = block_group->start;
+ key.type = BTRFS_BLOCK_GROUP_ITEM_KEY;
+ key.offset = block_group->length;
spin_unlock(&block_group->lock);
ret = btrfs_insert_item(trans, extent_root, &key, &item,
@@ -1901,7 +1901,7 @@ int btrfs_make_block_group(struct btrfs_trans_handle *trans, u64 bytes_used,
u64 type, u64 chunk_offset, u64 size)
{
struct btrfs_fs_info *fs_info = trans->fs_info;
- struct btrfs_block_group_cache *cache;
+ struct btrfs_block_group *cache;
int ret;
btrfs_set_log_full_commit(trans);
@@ -1910,11 +1910,7 @@ int btrfs_make_block_group(struct btrfs_trans_handle *trans, u64 bytes_used,
if (!cache)
return -ENOMEM;
- btrfs_set_block_group_used(&cache->item, bytes_used);
- btrfs_set_block_group_chunk_objectid(&cache->item,
- BTRFS_FIRST_CHUNK_TREE_OBJECTID);
- btrfs_set_block_group_flags(&cache->item, type);
-
+ cache->used = bytes_used;
cache->flags = type;
cache->last_byte_to_unpin = (u64)-1;
cache->cached = BTRFS_CACHE_FINISHED;
@@ -2021,8 +2017,17 @@ static u64 update_block_group_flags(struct btrfs_fs_info *fs_info, u64 flags)
return flags;
}
-int btrfs_inc_block_group_ro(struct btrfs_block_group_cache *cache)
-
+/*
+ * Mark one block group RO, can be called several times for the same block
+ * group.
+ *
+ * @cache: the destination block group
+ * @do_chunk_alloc: whether need to do chunk pre-allocation, this is to
+ * ensure we still have some free space after marking this
+ * block group RO.
+ */
+int btrfs_inc_block_group_ro(struct btrfs_block_group *cache,
+ bool do_chunk_alloc)
{
struct btrfs_fs_info *fs_info = cache->fs_info;
struct btrfs_trans_handle *trans;
@@ -2052,25 +2057,29 @@ again:
goto again;
}
- /*
- * if we are changing raid levels, try to allocate a corresponding
- * block group with the new raid level.
- */
- alloc_flags = update_block_group_flags(fs_info, cache->flags);
- if (alloc_flags != cache->flags) {
- ret = btrfs_chunk_alloc(trans, alloc_flags, CHUNK_ALLOC_FORCE);
+ if (do_chunk_alloc) {
/*
- * ENOSPC is allowed here, we may have enough space
- * already allocated at the new raid level to
- * carry on
+ * If we are changing raid levels, try to allocate a
+ * corresponding block group with the new raid level.
*/
- if (ret == -ENOSPC)
- ret = 0;
- if (ret < 0)
- goto out;
+ alloc_flags = update_block_group_flags(fs_info, cache->flags);
+ if (alloc_flags != cache->flags) {
+ ret = btrfs_chunk_alloc(trans, alloc_flags,
+ CHUNK_ALLOC_FORCE);
+ /*
+ * ENOSPC is allowed here, we may have enough space
+ * already allocated at the new raid level to carry on
+ */
+ if (ret == -ENOSPC)
+ ret = 0;
+ if (ret < 0)
+ goto out;
+ }
}
- ret = inc_block_group_ro(cache, 0);
+ ret = inc_block_group_ro(cache, !do_chunk_alloc);
+ if (!do_chunk_alloc)
+ goto unlock_out;
if (!ret)
goto out;
alloc_flags = btrfs_get_alloc_profile(fs_info, cache->space_info->flags);
@@ -2085,13 +2094,14 @@ out:
check_system_chunk(trans, alloc_flags);
mutex_unlock(&fs_info->chunk_mutex);
}
+unlock_out:
mutex_unlock(&fs_info->ro_block_group_mutex);
btrfs_end_transaction(trans);
return ret;
}
-void btrfs_dec_block_group_ro(struct btrfs_block_group_cache *cache)
+void btrfs_dec_block_group_ro(struct btrfs_block_group *cache)
{
struct btrfs_space_info *sinfo = cache->space_info;
u64 num_bytes;
@@ -2101,9 +2111,8 @@ void btrfs_dec_block_group_ro(struct btrfs_block_group_cache *cache)
spin_lock(&sinfo->lock);
spin_lock(&cache->lock);
if (!--cache->ro) {
- num_bytes = cache->key.offset - cache->reserved -
- cache->pinned - cache->bytes_super -
- btrfs_block_group_used(&cache->item);
+ num_bytes = cache->length - cache->reserved -
+ cache->pinned - cache->bytes_super - cache->used;
sinfo->bytes_readonly -= num_bytes;
list_del_init(&cache->ro_list);
}
@@ -2113,15 +2122,21 @@ void btrfs_dec_block_group_ro(struct btrfs_block_group_cache *cache)
static int write_one_cache_group(struct btrfs_trans_handle *trans,
struct btrfs_path *path,
- struct btrfs_block_group_cache *cache)
+ struct btrfs_block_group *cache)
{
struct btrfs_fs_info *fs_info = trans->fs_info;
int ret;
struct btrfs_root *extent_root = fs_info->extent_root;
unsigned long bi;
struct extent_buffer *leaf;
+ struct btrfs_block_group_item bgi;
+ struct btrfs_key key;
+
+ key.objectid = cache->start;
+ key.type = BTRFS_BLOCK_GROUP_ITEM_KEY;
+ key.offset = cache->length;
- ret = btrfs_search_slot(trans, extent_root, &cache->key, path, 0, 1);
+ ret = btrfs_search_slot(trans, extent_root, &key, path, 0, 1);
if (ret) {
if (ret > 0)
ret = -ENOENT;
@@ -2130,7 +2145,11 @@ static int write_one_cache_group(struct btrfs_trans_handle *trans,
leaf = path->nodes[0];
bi = btrfs_item_ptr_offset(leaf, path->slots[0]);
- write_extent_buffer(leaf, &cache->item, bi, sizeof(cache->item));
+ btrfs_set_stack_block_group_used(&bgi, cache->used);
+ btrfs_set_stack_block_group_chunk_objectid(&bgi,
+ BTRFS_FIRST_CHUNK_TREE_OBJECTID);
+ btrfs_set_stack_block_group_flags(&bgi, cache->flags);
+ write_extent_buffer(leaf, &bgi, bi, sizeof(bgi));
btrfs_mark_buffer_dirty(leaf);
fail:
btrfs_release_path(path);
@@ -2138,7 +2157,7 @@ fail:
}
-static int cache_save_setup(struct btrfs_block_group_cache *block_group,
+static int cache_save_setup(struct btrfs_block_group *block_group,
struct btrfs_trans_handle *trans,
struct btrfs_path *path)
{
@@ -2156,7 +2175,7 @@ static int cache_save_setup(struct btrfs_block_group_cache *block_group,
* If this block group is smaller than 100 megs don't bother caching the
* block group.
*/
- if (block_group->key.offset < (100 * SZ_1M)) {
+ if (block_group->length < (100 * SZ_1M)) {
spin_lock(&block_group->lock);
block_group->disk_cache_state = BTRFS_DC_WRITTEN;
spin_unlock(&block_group->lock);
@@ -2257,7 +2276,7 @@ again:
* taking up quite a bit since it's not folded into the other space
* cache.
*/
- num_pages = div_u64(block_group->key.offset, SZ_256M);
+ num_pages = div_u64(block_group->length, SZ_256M);
if (!num_pages)
num_pages = 1;
@@ -2302,7 +2321,7 @@ out:
int btrfs_setup_space_cache(struct btrfs_trans_handle *trans)
{
struct btrfs_fs_info *fs_info = trans->fs_info;
- struct btrfs_block_group_cache *cache, *tmp;
+ struct btrfs_block_group *cache, *tmp;
struct btrfs_transaction *cur_trans = trans->transaction;
struct btrfs_path *path;
@@ -2340,7 +2359,7 @@ int btrfs_setup_space_cache(struct btrfs_trans_handle *trans)
int btrfs_start_dirty_block_groups(struct btrfs_trans_handle *trans)
{
struct btrfs_fs_info *fs_info = trans->fs_info;
- struct btrfs_block_group_cache *cache;
+ struct btrfs_block_group *cache;
struct btrfs_transaction *cur_trans = trans->transaction;
int ret = 0;
int should_put;
@@ -2377,8 +2396,7 @@ again:
while (!list_empty(&dirty)) {
bool drop_reserve = true;
- cache = list_first_entry(&dirty,
- struct btrfs_block_group_cache,
+ cache = list_first_entry(&dirty, struct btrfs_block_group,
dirty_list);
/*
* This can happen if something re-dirties a block group that
@@ -2503,7 +2521,7 @@ again:
int btrfs_write_dirty_block_groups(struct btrfs_trans_handle *trans)
{
struct btrfs_fs_info *fs_info = trans->fs_info;
- struct btrfs_block_group_cache *cache;
+ struct btrfs_block_group *cache;
struct btrfs_transaction *cur_trans = trans->transaction;
int ret = 0;
int should_put;
@@ -2533,7 +2551,7 @@ int btrfs_write_dirty_block_groups(struct btrfs_trans_handle *trans)
spin_lock(&cur_trans->dirty_bgs_lock);
while (!list_empty(&cur_trans->dirty_bgs)) {
cache = list_first_entry(&cur_trans->dirty_bgs,
- struct btrfs_block_group_cache,
+ struct btrfs_block_group,
dirty_list);
/*
@@ -2615,7 +2633,7 @@ int btrfs_write_dirty_block_groups(struct btrfs_trans_handle *trans)
* to use it without any locking
*/
while (!list_empty(io)) {
- cache = list_first_entry(io, struct btrfs_block_group_cache,
+ cache = list_first_entry(io, struct btrfs_block_group,
io_list);
list_del_init(&cache->io_list);
btrfs_wait_cache_io(trans, cache, path);
@@ -2630,7 +2648,7 @@ int btrfs_update_block_group(struct btrfs_trans_handle *trans,
u64 bytenr, u64 num_bytes, int alloc)
{
struct btrfs_fs_info *info = trans->fs_info;
- struct btrfs_block_group_cache *cache = NULL;
+ struct btrfs_block_group *cache = NULL;
u64 total = num_bytes;
u64 old_val;
u64 byte_in_group;
@@ -2661,11 +2679,11 @@ int btrfs_update_block_group(struct btrfs_trans_handle *trans,
* is because we need the unpinning stage to actually add the
* space back to the block group, otherwise we will leak space.
*/
- if (!alloc && cache->cached == BTRFS_CACHE_NO)
+ if (!alloc && !btrfs_block_group_done(cache))
btrfs_cache_block_group(cache, 1);
- byte_in_group = bytenr - cache->key.objectid;
- WARN_ON(byte_in_group > cache->key.offset);
+ byte_in_group = bytenr - cache->start;
+ WARN_ON(byte_in_group > cache->length);
spin_lock(&cache->space_info->lock);
spin_lock(&cache->lock);
@@ -2674,11 +2692,11 @@ int btrfs_update_block_group(struct btrfs_trans_handle *trans,
cache->disk_cache_state < BTRFS_DC_CLEAR)
cache->disk_cache_state = BTRFS_DC_CLEAR;
- old_val = btrfs_block_group_used(&cache->item);
- num_bytes = min(total, cache->key.offset - byte_in_group);
+ old_val = cache->used;
+ num_bytes = min(total, cache->length - byte_in_group);
if (alloc) {
old_val += num_bytes;
- btrfs_set_block_group_used(&cache->item, old_val);
+ cache->used = old_val;
cache->reserved -= num_bytes;
cache->space_info->bytes_reserved -= num_bytes;
cache->space_info->bytes_used += num_bytes;
@@ -2687,7 +2705,7 @@ int btrfs_update_block_group(struct btrfs_trans_handle *trans,
spin_unlock(&cache->space_info->lock);
} else {
old_val -= num_bytes;
- btrfs_set_block_group_used(&cache->item, old_val);
+ cache->used = old_val;
cache->pinned += num_bytes;
btrfs_space_info_update_bytes_pinned(info,
cache->space_info, num_bytes);
@@ -2745,7 +2763,7 @@ int btrfs_update_block_group(struct btrfs_trans_handle *trans,
* reservation and the block group has become read only we cannot make the
* reservation and return -EAGAIN, otherwise this function always succeeds.
*/
-int btrfs_add_reserved_bytes(struct btrfs_block_group_cache *cache,
+int btrfs_add_reserved_bytes(struct btrfs_block_group *cache,
u64 ram_bytes, u64 num_bytes, int delalloc)
{
struct btrfs_space_info *space_info = cache->space_info;
@@ -2781,7 +2799,7 @@ int btrfs_add_reserved_bytes(struct btrfs_block_group_cache *cache,
* A and before transaction A commits you free that leaf, you call this with
* reserve set to 0 in order to clear the reservation.
*/
-void btrfs_free_reserved_bytes(struct btrfs_block_group_cache *cache,
+void btrfs_free_reserved_bytes(struct btrfs_block_group *cache,
u64 num_bytes, int delalloc)
{
struct btrfs_space_info *space_info = cache->space_info;
@@ -2987,9 +3005,7 @@ static u64 get_profile_num_devs(struct btrfs_fs_info *fs_info, u64 type)
}
/*
- * If @is_allocation is true, reserve space in the system space info necessary
- * for allocating a chunk, otherwise if it's false, reserve space necessary for
- * removing a chunk.
+ * Reserve space in the system space for allocating or removing a chunk
*/
void check_system_chunk(struct btrfs_trans_handle *trans, u64 type)
{
@@ -3046,7 +3062,7 @@ void check_system_chunk(struct btrfs_trans_handle *trans, u64 type)
void btrfs_put_block_group_cache(struct btrfs_fs_info *info)
{
- struct btrfs_block_group_cache *block_group;
+ struct btrfs_block_group *block_group;
u64 last = 0;
while (1) {
@@ -3074,7 +3090,7 @@ void btrfs_put_block_group_cache(struct btrfs_fs_info *info)
spin_unlock(&block_group->lock);
ASSERT(block_group->io_ctl.inode == NULL);
iput(inode);
- last = block_group->key.objectid + block_group->key.offset;
+ last = block_group->start + block_group->length;
btrfs_put_block_group(block_group);
}
}
@@ -3086,7 +3102,7 @@ void btrfs_put_block_group_cache(struct btrfs_fs_info *info)
*/
int btrfs_free_block_groups(struct btrfs_fs_info *info)
{
- struct btrfs_block_group_cache *block_group;
+ struct btrfs_block_group *block_group;
struct btrfs_space_info *space_info;
struct btrfs_caching_control *caching_ctl;
struct rb_node *n;
@@ -3103,7 +3119,7 @@ int btrfs_free_block_groups(struct btrfs_fs_info *info)
spin_lock(&info->unused_bgs_lock);
while (!list_empty(&info->unused_bgs)) {
block_group = list_first_entry(&info->unused_bgs,
- struct btrfs_block_group_cache,
+ struct btrfs_block_group,
bg_list);
list_del_init(&block_group->bg_list);
btrfs_put_block_group(block_group);
@@ -3112,7 +3128,7 @@ int btrfs_free_block_groups(struct btrfs_fs_info *info)
spin_lock(&info->block_group_cache_lock);
while ((n = rb_last(&info->block_group_cache_tree)) != NULL) {
- block_group = rb_entry(n, struct btrfs_block_group_cache,
+ block_group = rb_entry(n, struct btrfs_block_group,
cache_node);
rb_erase(&block_group->cache_node,
&info->block_group_cache_tree);
diff --git a/fs/btrfs/block-group.h b/fs/btrfs/block-group.h
index c391800388dd..9b409676c4b2 100644
--- a/fs/btrfs/block-group.h
+++ b/fs/btrfs/block-group.h
@@ -34,7 +34,7 @@ struct btrfs_caching_control {
struct mutex mutex;
wait_queue_head_t wait;
struct btrfs_work work;
- struct btrfs_block_group_cache *block_group;
+ struct btrfs_block_group *block_group;
u64 progress;
refcount_t count;
};
@@ -42,14 +42,15 @@ struct btrfs_caching_control {
/* Once caching_thread() finds this much free space, it will wake up waiters. */
#define CACHING_CTL_WAKE_UP SZ_2M
-struct btrfs_block_group_cache {
- struct btrfs_key key;
- struct btrfs_block_group_item item;
+struct btrfs_block_group {
struct btrfs_fs_info *fs_info;
struct inode *inode;
spinlock_t lock;
+ u64 start;
+ u64 length;
u64 pinned;
u64 reserved;
+ u64 used;
u64 delalloc_bytes;
u64 bytes_super;
u64 flags;
@@ -159,7 +160,7 @@ struct btrfs_block_group_cache {
#ifdef CONFIG_BTRFS_DEBUG
static inline int btrfs_should_fragment_free_space(
- struct btrfs_block_group_cache *block_group)
+ struct btrfs_block_group *block_group)
{
struct btrfs_fs_info *fs_info = block_group->fs_info;
@@ -170,29 +171,29 @@ static inline int btrfs_should_fragment_free_space(
}
#endif
-struct btrfs_block_group_cache *btrfs_lookup_first_block_group(
+struct btrfs_block_group *btrfs_lookup_first_block_group(
struct btrfs_fs_info *info, u64 bytenr);
-struct btrfs_block_group_cache *btrfs_lookup_block_group(
+struct btrfs_block_group *btrfs_lookup_block_group(
struct btrfs_fs_info *info, u64 bytenr);
-struct btrfs_block_group_cache *btrfs_next_block_group(
- struct btrfs_block_group_cache *cache);
-void btrfs_get_block_group(struct btrfs_block_group_cache *cache);
-void btrfs_put_block_group(struct btrfs_block_group_cache *cache);
+struct btrfs_block_group *btrfs_next_block_group(
+ struct btrfs_block_group *cache);
+void btrfs_get_block_group(struct btrfs_block_group *cache);
+void btrfs_put_block_group(struct btrfs_block_group *cache);
void btrfs_dec_block_group_reservations(struct btrfs_fs_info *fs_info,
const u64 start);
-void btrfs_wait_block_group_reservations(struct btrfs_block_group_cache *bg);
+void btrfs_wait_block_group_reservations(struct btrfs_block_group *bg);
bool btrfs_inc_nocow_writers(struct btrfs_fs_info *fs_info, u64 bytenr);
void btrfs_dec_nocow_writers(struct btrfs_fs_info *fs_info, u64 bytenr);
-void btrfs_wait_nocow_writers(struct btrfs_block_group_cache *bg);
-void btrfs_wait_block_group_cache_progress(struct btrfs_block_group_cache *cache,
+void btrfs_wait_nocow_writers(struct btrfs_block_group *bg);
+void btrfs_wait_block_group_cache_progress(struct btrfs_block_group *cache,
u64 num_bytes);
-int btrfs_wait_block_group_cache_done(struct btrfs_block_group_cache *cache);
-int btrfs_cache_block_group(struct btrfs_block_group_cache *cache,
+int btrfs_wait_block_group_cache_done(struct btrfs_block_group *cache);
+int btrfs_cache_block_group(struct btrfs_block_group *cache,
int load_cache_only);
void btrfs_put_caching_control(struct btrfs_caching_control *ctl);
struct btrfs_caching_control *btrfs_get_caching_control(
- struct btrfs_block_group_cache *cache);
-u64 add_new_free_space(struct btrfs_block_group_cache *block_group,
+ struct btrfs_block_group *cache);
+u64 add_new_free_space(struct btrfs_block_group *block_group,
u64 start, u64 end);
struct btrfs_trans_handle *btrfs_start_trans_remove_block_group(
struct btrfs_fs_info *fs_info,
@@ -200,21 +201,22 @@ struct btrfs_trans_handle *btrfs_start_trans_remove_block_group(
int btrfs_remove_block_group(struct btrfs_trans_handle *trans,
u64 group_start, struct extent_map *em);
void btrfs_delete_unused_bgs(struct btrfs_fs_info *fs_info);
-void btrfs_mark_bg_unused(struct btrfs_block_group_cache *bg);
+void btrfs_mark_bg_unused(struct btrfs_block_group *bg);
int btrfs_read_block_groups(struct btrfs_fs_info *info);
int btrfs_make_block_group(struct btrfs_trans_handle *trans, u64 bytes_used,
u64 type, u64 chunk_offset, u64 size);
void btrfs_create_pending_block_groups(struct btrfs_trans_handle *trans);
-int btrfs_inc_block_group_ro(struct btrfs_block_group_cache *cache);
-void btrfs_dec_block_group_ro(struct btrfs_block_group_cache *cache);
+int btrfs_inc_block_group_ro(struct btrfs_block_group *cache,
+ bool do_chunk_alloc);
+void btrfs_dec_block_group_ro(struct btrfs_block_group *cache);
int btrfs_start_dirty_block_groups(struct btrfs_trans_handle *trans);
int btrfs_write_dirty_block_groups(struct btrfs_trans_handle *trans);
int btrfs_setup_space_cache(struct btrfs_trans_handle *trans);
int btrfs_update_block_group(struct btrfs_trans_handle *trans,
u64 bytenr, u64 num_bytes, int alloc);
-int btrfs_add_reserved_bytes(struct btrfs_block_group_cache *cache,
+int btrfs_add_reserved_bytes(struct btrfs_block_group *cache,
u64 ram_bytes, u64 num_bytes, int delalloc);
-void btrfs_free_reserved_bytes(struct btrfs_block_group_cache *cache,
+void btrfs_free_reserved_bytes(struct btrfs_block_group *cache,
u64 num_bytes, int delalloc);
int btrfs_chunk_alloc(struct btrfs_trans_handle *trans, u64 flags,
enum btrfs_chunk_alloc_enum force);
@@ -239,8 +241,7 @@ static inline u64 btrfs_system_alloc_profile(struct btrfs_fs_info *fs_info)
return btrfs_get_alloc_profile(fs_info, BTRFS_BLOCK_GROUP_SYSTEM);
}
-static inline int btrfs_block_group_cache_done(
- struct btrfs_block_group_cache *cache)
+static inline int btrfs_block_group_done(struct btrfs_block_group *cache)
{
smp_mb();
return cache->cached == BTRFS_CACHE_FINISHED ||
diff --git a/fs/btrfs/btrfs_inode.h b/fs/btrfs/btrfs_inode.h
index f853835c409c..4e12a477d32e 100644
--- a/fs/btrfs/btrfs_inode.h
+++ b/fs/btrfs/btrfs_inode.h
@@ -63,9 +63,6 @@ struct btrfs_inode {
/* held while logging the inode in tree-log.c */
struct mutex log_mutex;
- /* held while doing delalloc reservations */
- struct mutex delalloc_mutex;
-
/* used to order data wrt metadata */
struct btrfs_ordered_inode_tree ordered_tree;
diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c
index b05b361e2062..ee834ef7beb4 100644
--- a/fs/btrfs/compression.c
+++ b/fs/btrfs/compression.c
@@ -29,6 +29,41 @@
#include "extent_io.h"
#include "extent_map.h"
+int zlib_compress_pages(struct list_head *ws, struct address_space *mapping,
+ u64 start, struct page **pages, unsigned long *out_pages,
+ unsigned long *total_in, unsigned long *total_out);
+int zlib_decompress_bio(struct list_head *ws, struct compressed_bio *cb);
+int zlib_decompress(struct list_head *ws, unsigned char *data_in,
+ struct page *dest_page, unsigned long start_byte, size_t srclen,
+ size_t destlen);
+struct list_head *zlib_alloc_workspace(unsigned int level);
+void zlib_free_workspace(struct list_head *ws);
+struct list_head *zlib_get_workspace(unsigned int level);
+
+int lzo_compress_pages(struct list_head *ws, struct address_space *mapping,
+ u64 start, struct page **pages, unsigned long *out_pages,
+ unsigned long *total_in, unsigned long *total_out);
+int lzo_decompress_bio(struct list_head *ws, struct compressed_bio *cb);
+int lzo_decompress(struct list_head *ws, unsigned char *data_in,
+ struct page *dest_page, unsigned long start_byte, size_t srclen,
+ size_t destlen);
+struct list_head *lzo_alloc_workspace(unsigned int level);
+void lzo_free_workspace(struct list_head *ws);
+
+int zstd_compress_pages(struct list_head *ws, struct address_space *mapping,
+ u64 start, struct page **pages, unsigned long *out_pages,
+ unsigned long *total_in, unsigned long *total_out);
+int zstd_decompress_bio(struct list_head *ws, struct compressed_bio *cb);
+int zstd_decompress(struct list_head *ws, unsigned char *data_in,
+ struct page *dest_page, unsigned long start_byte, size_t srclen,
+ size_t destlen);
+void zstd_init_workspace_manager(void);
+void zstd_cleanup_workspace_manager(void);
+struct list_head *zstd_alloc_workspace(unsigned int level);
+void zstd_free_workspace(struct list_head *ws);
+struct list_head *zstd_get_workspace(unsigned int level);
+void zstd_put_workspace(struct list_head *ws);
+
static const char* const btrfs_compress_types[] = { "", "zlib", "lzo", "zstd" };
const char* btrfs_compress_type2str(enum btrfs_compression_type type)
@@ -39,6 +74,8 @@ const char* btrfs_compress_type2str(enum btrfs_compression_type type)
case BTRFS_COMPRESS_ZSTD:
case BTRFS_COMPRESS_NONE:
return btrfs_compress_types[type];
+ default:
+ break;
}
return NULL;
@@ -60,6 +97,70 @@ bool btrfs_compress_is_valid_type(const char *str, size_t len)
return false;
}
+static int compression_compress_pages(int type, struct list_head *ws,
+ struct address_space *mapping, u64 start, struct page **pages,
+ unsigned long *out_pages, unsigned long *total_in,
+ unsigned long *total_out)
+{
+ switch (type) {
+ case BTRFS_COMPRESS_ZLIB:
+ return zlib_compress_pages(ws, mapping, start, pages,
+ out_pages, total_in, total_out);
+ case BTRFS_COMPRESS_LZO:
+ return lzo_compress_pages(ws, mapping, start, pages,
+ out_pages, total_in, total_out);
+ case BTRFS_COMPRESS_ZSTD:
+ return zstd_compress_pages(ws, mapping, start, pages,
+ out_pages, total_in, total_out);
+ case BTRFS_COMPRESS_NONE:
+ default:
+ /*
+ * This can't happen, the type is validated several times
+ * before we get here. As a sane fallback, return what the
+ * callers will understand as 'no compression happened'.
+ */
+ return -E2BIG;
+ }
+}
+
+static int compression_decompress_bio(int type, struct list_head *ws,
+ struct compressed_bio *cb)
+{
+ switch (type) {
+ case BTRFS_COMPRESS_ZLIB: return zlib_decompress_bio(ws, cb);
+ case BTRFS_COMPRESS_LZO: return lzo_decompress_bio(ws, cb);
+ case BTRFS_COMPRESS_ZSTD: return zstd_decompress_bio(ws, cb);
+ case BTRFS_COMPRESS_NONE:
+ default:
+ /*
+ * This can't happen, the type is validated several times
+ * before we get here.
+ */
+ BUG();
+ }
+}
+
+static int compression_decompress(int type, struct list_head *ws,
+ unsigned char *data_in, struct page *dest_page,
+ unsigned long start_byte, size_t srclen, size_t destlen)
+{
+ switch (type) {
+ case BTRFS_COMPRESS_ZLIB: return zlib_decompress(ws, data_in, dest_page,
+ start_byte, srclen, destlen);
+ case BTRFS_COMPRESS_LZO: return lzo_decompress(ws, data_in, dest_page,
+ start_byte, srclen, destlen);
+ case BTRFS_COMPRESS_ZSTD: return zstd_decompress(ws, data_in, dest_page,
+ start_byte, srclen, destlen);
+ case BTRFS_COMPRESS_NONE:
+ default:
+ /*
+ * This can't happen, the type is validated several times
+ * before we get here.
+ */
+ BUG();
+ }
+}
+
static int btrfs_decompress_bio(struct compressed_bio *cb);
static inline int compressed_bio_size(struct btrfs_fs_info *fs_info,
@@ -311,7 +412,8 @@ blk_status_t btrfs_submit_compressed_write(struct inode *inode, u64 start,
unsigned long compressed_len,
struct page **compressed_pages,
unsigned long nr_pages,
- unsigned int write_flags)
+ unsigned int write_flags,
+ struct cgroup_subsys_state *blkcg_css)
{
struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
struct bio *bio = NULL;
@@ -320,7 +422,6 @@ blk_status_t btrfs_submit_compressed_write(struct inode *inode, u64 start,
int pg_index = 0;
struct page *page;
u64 first_byte = disk_start;
- struct block_device *bdev;
blk_status_t ret;
int skip_sum = BTRFS_I(inode)->flags & BTRFS_INODE_NODATASUM;
@@ -339,13 +440,15 @@ blk_status_t btrfs_submit_compressed_write(struct inode *inode, u64 start,
cb->orig_bio = NULL;
cb->nr_pages = nr_pages;
- bdev = fs_info->fs_devices->latest_bdev;
-
bio = btrfs_bio_alloc(first_byte);
- bio_set_dev(bio, bdev);
bio->bi_opf = REQ_OP_WRITE | write_flags;
bio->bi_private = cb;
bio->bi_end_io = end_compressed_bio_write;
+
+ if (blkcg_css) {
+ bio->bi_opf |= REQ_CGROUP_PUNT;
+ bio_associate_blkg_from_css(bio, blkcg_css);
+ }
refcount_set(&cb->pending_bios, 1);
/* create and submit bios for the compressed pages */
@@ -378,14 +481,13 @@ blk_status_t btrfs_submit_compressed_write(struct inode *inode, u64 start,
BUG_ON(ret); /* -ENOMEM */
}
- ret = btrfs_map_bio(fs_info, bio, 0, 1);
+ ret = btrfs_map_bio(fs_info, bio, 0);
if (ret) {
bio->bi_status = ret;
bio_endio(bio);
}
bio = btrfs_bio_alloc(first_byte);
- bio_set_dev(bio, bdev);
bio->bi_opf = REQ_OP_WRITE | write_flags;
bio->bi_private = cb;
bio->bi_end_io = end_compressed_bio_write;
@@ -409,7 +511,7 @@ blk_status_t btrfs_submit_compressed_write(struct inode *inode, u64 start,
BUG_ON(ret); /* -ENOMEM */
}
- ret = btrfs_map_bio(fs_info, bio, 0, 1);
+ ret = btrfs_map_bio(fs_info, bio, 0);
if (ret) {
bio->bi_status = ret;
bio_endio(bio);
@@ -553,7 +655,6 @@ blk_status_t btrfs_submit_compressed_read(struct inode *inode, struct bio *bio,
unsigned long nr_pages;
unsigned long pg_index;
struct page *page;
- struct block_device *bdev;
struct bio *comp_bio;
u64 cur_disk_byte = (u64)bio->bi_iter.bi_sector << 9;
u64 em_len;
@@ -604,8 +705,6 @@ blk_status_t btrfs_submit_compressed_read(struct inode *inode, struct bio *bio,
if (!cb->compressed_pages)
goto fail1;
- bdev = fs_info->fs_devices->latest_bdev;
-
for (pg_index = 0; pg_index < nr_pages; pg_index++) {
cb->compressed_pages[pg_index] = alloc_page(GFP_NOFS |
__GFP_HIGHMEM);
@@ -624,7 +723,6 @@ blk_status_t btrfs_submit_compressed_read(struct inode *inode, struct bio *bio,
cb->len = bio->bi_iter.bi_size;
comp_bio = btrfs_bio_alloc(cur_disk_byte);
- bio_set_dev(comp_bio, bdev);
comp_bio->bi_opf = REQ_OP_READ;
comp_bio->bi_private = cb;
comp_bio->bi_end_io = end_compressed_bio_read;
@@ -668,14 +766,13 @@ blk_status_t btrfs_submit_compressed_read(struct inode *inode, struct bio *bio,
fs_info->sectorsize);
sums += csum_size * nr_sectors;
- ret = btrfs_map_bio(fs_info, comp_bio, mirror_num, 0);
+ ret = btrfs_map_bio(fs_info, comp_bio, mirror_num);
if (ret) {
comp_bio->bi_status = ret;
bio_endio(comp_bio);
}
comp_bio = btrfs_bio_alloc(cur_disk_byte);
- bio_set_dev(comp_bio, bdev);
comp_bio->bi_opf = REQ_OP_READ;
comp_bio->bi_private = cb;
comp_bio->bi_end_io = end_compressed_bio_read;
@@ -693,7 +790,7 @@ blk_status_t btrfs_submit_compressed_read(struct inode *inode, struct bio *bio,
BUG_ON(ret); /* -ENOMEM */
}
- ret = btrfs_map_bio(fs_info, comp_bio, mirror_num, 0);
+ ret = btrfs_map_bio(fs_info, comp_bio, mirror_num);
if (ret) {
comp_bio->bi_status = ret;
bio_endio(comp_bio);
@@ -764,26 +861,6 @@ struct heuristic_ws {
static struct workspace_manager heuristic_wsm;
-static void heuristic_init_workspace_manager(void)
-{
- btrfs_init_workspace_manager(&heuristic_wsm, &btrfs_heuristic_compress);
-}
-
-static void heuristic_cleanup_workspace_manager(void)
-{
- btrfs_cleanup_workspace_manager(&heuristic_wsm);
-}
-
-static struct list_head *heuristic_get_workspace(unsigned int level)
-{
- return btrfs_get_workspace(&heuristic_wsm, level);
-}
-
-static void heuristic_put_workspace(struct list_head *ws)
-{
- btrfs_put_workspace(&heuristic_wsm, ws);
-}
-
static void free_heuristic_ws(struct list_head *ws)
{
struct heuristic_ws *workspace;
@@ -824,12 +901,7 @@ fail:
}
const struct btrfs_compress_op btrfs_heuristic_compress = {
- .init_workspace_manager = heuristic_init_workspace_manager,
- .cleanup_workspace_manager = heuristic_cleanup_workspace_manager,
- .get_workspace = heuristic_get_workspace,
- .put_workspace = heuristic_put_workspace,
- .alloc_workspace = alloc_heuristic_ws,
- .free_workspace = free_heuristic_ws,
+ .workspace_manager = &heuristic_wsm,
};
static const struct btrfs_compress_op * const btrfs_compress_op[] = {
@@ -840,13 +912,44 @@ static const struct btrfs_compress_op * const btrfs_compress_op[] = {
&btrfs_zstd_compress,
};
-void btrfs_init_workspace_manager(struct workspace_manager *wsm,
- const struct btrfs_compress_op *ops)
+static struct list_head *alloc_workspace(int type, unsigned int level)
{
- struct list_head *workspace;
+ switch (type) {
+ case BTRFS_COMPRESS_NONE: return alloc_heuristic_ws(level);
+ case BTRFS_COMPRESS_ZLIB: return zlib_alloc_workspace(level);
+ case BTRFS_COMPRESS_LZO: return lzo_alloc_workspace(level);
+ case BTRFS_COMPRESS_ZSTD: return zstd_alloc_workspace(level);
+ default:
+ /*
+ * This can't happen, the type is validated several times
+ * before we get here.
+ */
+ BUG();
+ }
+}
- wsm->ops = ops;
+static void free_workspace(int type, struct list_head *ws)
+{
+ switch (type) {
+ case BTRFS_COMPRESS_NONE: return free_heuristic_ws(ws);
+ case BTRFS_COMPRESS_ZLIB: return zlib_free_workspace(ws);
+ case BTRFS_COMPRESS_LZO: return lzo_free_workspace(ws);
+ case BTRFS_COMPRESS_ZSTD: return zstd_free_workspace(ws);
+ default:
+ /*
+ * This can't happen, the type is validated several times
+ * before we get here.
+ */
+ BUG();
+ }
+}
+
+static void btrfs_init_workspace_manager(int type)
+{
+ struct workspace_manager *wsm;
+ struct list_head *workspace;
+ wsm = btrfs_compress_op[type]->workspace_manager;
INIT_LIST_HEAD(&wsm->idle_ws);
spin_lock_init(&wsm->ws_lock);
atomic_set(&wsm->total_ws, 0);
@@ -856,7 +959,7 @@ void btrfs_init_workspace_manager(struct workspace_manager *wsm,
* Preallocate one workspace for each compression type so we can
* guarantee forward progress in the worst case
*/
- workspace = wsm->ops->alloc_workspace(0);
+ workspace = alloc_workspace(type, 0);
if (IS_ERR(workspace)) {
pr_warn(
"BTRFS: cannot preallocate compression workspace, will try later\n");
@@ -867,14 +970,16 @@ void btrfs_init_workspace_manager(struct workspace_manager *wsm,
}
}
-void btrfs_cleanup_workspace_manager(struct workspace_manager *wsman)
+static void btrfs_cleanup_workspace_manager(int type)
{
+ struct workspace_manager *wsman;
struct list_head *ws;
+ wsman = btrfs_compress_op[type]->workspace_manager;
while (!list_empty(&wsman->idle_ws)) {
ws = wsman->idle_ws.next;
list_del(ws);
- wsman->ops->free_workspace(ws);
+ free_workspace(type, ws);
atomic_dec(&wsman->total_ws);
}
}
@@ -885,9 +990,9 @@ void btrfs_cleanup_workspace_manager(struct workspace_manager *wsman)
* Preallocation makes a forward progress guarantees and we do not return
* errors.
*/
-struct list_head *btrfs_get_workspace(struct workspace_manager *wsm,
- unsigned int level)
+struct list_head *btrfs_get_workspace(int type, unsigned int level)
{
+ struct workspace_manager *wsm;
struct list_head *workspace;
int cpus = num_online_cpus();
unsigned nofs_flag;
@@ -897,6 +1002,7 @@ struct list_head *btrfs_get_workspace(struct workspace_manager *wsm,
wait_queue_head_t *ws_wait;
int *free_ws;
+ wsm = btrfs_compress_op[type]->workspace_manager;
idle_ws = &wsm->idle_ws;
ws_lock = &wsm->ws_lock;
total_ws = &wsm->total_ws;
@@ -932,7 +1038,7 @@ again:
* context of btrfs_compress_bio/btrfs_compress_pages
*/
nofs_flag = memalloc_nofs_save();
- workspace = wsm->ops->alloc_workspace(level);
+ workspace = alloc_workspace(type, level);
memalloc_nofs_restore(nofs_flag);
if (IS_ERR(workspace)) {
@@ -965,21 +1071,34 @@ again:
static struct list_head *get_workspace(int type, int level)
{
- return btrfs_compress_op[type]->get_workspace(level);
+ switch (type) {
+ case BTRFS_COMPRESS_NONE: return btrfs_get_workspace(type, level);
+ case BTRFS_COMPRESS_ZLIB: return zlib_get_workspace(level);
+ case BTRFS_COMPRESS_LZO: return btrfs_get_workspace(type, level);
+ case BTRFS_COMPRESS_ZSTD: return zstd_get_workspace(level);
+ default:
+ /*
+ * This can't happen, the type is validated several times
+ * before we get here.
+ */
+ BUG();
+ }
}
/*
* put a workspace struct back on the list or free it if we have enough
* idle ones sitting around
*/
-void btrfs_put_workspace(struct workspace_manager *wsm, struct list_head *ws)
+void btrfs_put_workspace(int type, struct list_head *ws)
{
+ struct workspace_manager *wsm;
struct list_head *idle_ws;
spinlock_t *ws_lock;
atomic_t *total_ws;
wait_queue_head_t *ws_wait;
int *free_ws;
+ wsm = btrfs_compress_op[type]->workspace_manager;
idle_ws = &wsm->idle_ws;
ws_lock = &wsm->ws_lock;
total_ws = &wsm->total_ws;
@@ -995,7 +1114,7 @@ void btrfs_put_workspace(struct workspace_manager *wsm, struct list_head *ws)
}
spin_unlock(ws_lock);
- wsm->ops->free_workspace(ws);
+ free_workspace(type, ws);
atomic_dec(total_ws);
wake:
cond_wake_up(ws_wait);
@@ -1003,7 +1122,18 @@ wake:
static void put_workspace(int type, struct list_head *ws)
{
- return btrfs_compress_op[type]->put_workspace(ws);
+ switch (type) {
+ case BTRFS_COMPRESS_NONE: return btrfs_put_workspace(type, ws);
+ case BTRFS_COMPRESS_ZLIB: return btrfs_put_workspace(type, ws);
+ case BTRFS_COMPRESS_LZO: return btrfs_put_workspace(type, ws);
+ case BTRFS_COMPRESS_ZSTD: return zstd_put_workspace(ws);
+ default:
+ /*
+ * This can't happen, the type is validated several times
+ * before we get here.
+ */
+ BUG();
+ }
}
/*
@@ -1042,10 +1172,8 @@ int btrfs_compress_pages(unsigned int type_level, struct address_space *mapping,
level = btrfs_compress_set_level(type, level);
workspace = get_workspace(type, level);
- ret = btrfs_compress_op[type]->compress_pages(workspace, mapping,
- start, pages,
- out_pages,
- total_in, total_out);
+ ret = compression_compress_pages(type, workspace, mapping, start, pages,
+ out_pages, total_in, total_out);
put_workspace(type, workspace);
return ret;
}
@@ -1071,7 +1199,7 @@ static int btrfs_decompress_bio(struct compressed_bio *cb)
int type = cb->compress_type;
workspace = get_workspace(type, 0);
- ret = btrfs_compress_op[type]->decompress_bio(workspace, cb);
+ ret = compression_decompress_bio(type, workspace, cb);
put_workspace(type, workspace);
return ret;
@@ -1089,9 +1217,8 @@ int btrfs_decompress(int type, unsigned char *data_in, struct page *dest_page,
int ret;
workspace = get_workspace(type, 0);
- ret = btrfs_compress_op[type]->decompress(workspace, data_in,
- dest_page, start_byte,
- srclen, destlen);
+ ret = compression_decompress(type, workspace, data_in, dest_page,
+ start_byte, srclen, destlen);
put_workspace(type, workspace);
return ret;
@@ -1099,18 +1226,18 @@ int btrfs_decompress(int type, unsigned char *data_in, struct page *dest_page,
void __init btrfs_init_compress(void)
{
- int i;
-
- for (i = 0; i < BTRFS_NR_WORKSPACE_MANAGERS; i++)
- btrfs_compress_op[i]->init_workspace_manager();
+ btrfs_init_workspace_manager(BTRFS_COMPRESS_NONE);
+ btrfs_init_workspace_manager(BTRFS_COMPRESS_ZLIB);
+ btrfs_init_workspace_manager(BTRFS_COMPRESS_LZO);
+ zstd_init_workspace_manager();
}
void __cold btrfs_exit_compress(void)
{
- int i;
-
- for (i = 0; i < BTRFS_NR_WORKSPACE_MANAGERS; i++)
- btrfs_compress_op[i]->cleanup_workspace_manager();
+ btrfs_cleanup_workspace_manager(BTRFS_COMPRESS_NONE);
+ btrfs_cleanup_workspace_manager(BTRFS_COMPRESS_ZLIB);
+ btrfs_cleanup_workspace_manager(BTRFS_COMPRESS_LZO);
+ zstd_cleanup_workspace_manager();
}
/*
diff --git a/fs/btrfs/compression.h b/fs/btrfs/compression.h
index 4cb8be9ff88b..d253f7aa8ed5 100644
--- a/fs/btrfs/compression.h
+++ b/fs/btrfs/compression.h
@@ -93,7 +93,8 @@ blk_status_t btrfs_submit_compressed_write(struct inode *inode, u64 start,
unsigned long compressed_len,
struct page **compressed_pages,
unsigned long nr_pages,
- unsigned int write_flags);
+ unsigned int write_flags,
+ struct cgroup_subsys_state *blkcg_css);
blk_status_t btrfs_submit_compressed_read(struct inode *inode, struct bio *bio,
int mirror_num, unsigned long bio_flags);
@@ -104,11 +105,10 @@ enum btrfs_compression_type {
BTRFS_COMPRESS_ZLIB = 1,
BTRFS_COMPRESS_LZO = 2,
BTRFS_COMPRESS_ZSTD = 3,
- BTRFS_COMPRESS_TYPES = 3,
+ BTRFS_NR_COMPRESS_TYPES = 4,
};
struct workspace_manager {
- const struct btrfs_compress_op *ops;
struct list_head idle_ws;
spinlock_t ws_lock;
/* Number of free workspaces */
@@ -119,50 +119,18 @@ struct workspace_manager {
wait_queue_head_t ws_wait;
};
-void btrfs_init_workspace_manager(struct workspace_manager *wsm,
- const struct btrfs_compress_op *ops);
-struct list_head *btrfs_get_workspace(struct workspace_manager *wsm,
- unsigned int level);
-void btrfs_put_workspace(struct workspace_manager *wsm, struct list_head *ws);
-void btrfs_cleanup_workspace_manager(struct workspace_manager *wsm);
+struct list_head *btrfs_get_workspace(int type, unsigned int level);
+void btrfs_put_workspace(int type, struct list_head *ws);
struct btrfs_compress_op {
- void (*init_workspace_manager)(void);
-
- void (*cleanup_workspace_manager)(void);
-
- struct list_head *(*get_workspace)(unsigned int level);
-
- void (*put_workspace)(struct list_head *ws);
-
- struct list_head *(*alloc_workspace)(unsigned int level);
-
- void (*free_workspace)(struct list_head *workspace);
-
- int (*compress_pages)(struct list_head *workspace,
- struct address_space *mapping,
- u64 start,
- struct page **pages,
- unsigned long *out_pages,
- unsigned long *total_in,
- unsigned long *total_out);
-
- int (*decompress_bio)(struct list_head *workspace,
- struct compressed_bio *cb);
-
- int (*decompress)(struct list_head *workspace,
- unsigned char *data_in,
- struct page *dest_page,
- unsigned long start_byte,
- size_t srclen, size_t destlen);
-
+ struct workspace_manager *workspace_manager;
/* Maximum level supported by the compression algorithm */
unsigned int max_level;
unsigned int default_level;
};
/* The heuristic workspaces are managed via the 0th workspace manager */
-#define BTRFS_NR_WORKSPACE_MANAGERS (BTRFS_COMPRESS_TYPES + 1)
+#define BTRFS_NR_WORKSPACE_MANAGERS BTRFS_NR_COMPRESS_TYPES
extern const struct btrfs_compress_op btrfs_heuristic_compress;
extern const struct btrfs_compress_op btrfs_zlib_compress;
diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c
index e59cde204b2f..5b6e86aaf2e1 100644
--- a/fs/btrfs/ctree.c
+++ b/fs/btrfs/ctree.c
@@ -32,8 +32,13 @@ static void del_ptr(struct btrfs_root *root, struct btrfs_path *path,
static const struct btrfs_csums {
u16 size;
const char *name;
+ const char *driver;
} btrfs_csums[] = {
[BTRFS_CSUM_TYPE_CRC32] = { .size = 4, .name = "crc32c" },
+ [BTRFS_CSUM_TYPE_XXHASH] = { .size = 8, .name = "xxhash64" },
+ [BTRFS_CSUM_TYPE_SHA256] = { .size = 32, .name = "sha256" },
+ [BTRFS_CSUM_TYPE_BLAKE2] = { .size = 32, .name = "blake2b",
+ .driver = "blake2b-256" },
};
int btrfs_super_csum_size(const struct btrfs_super_block *s)
@@ -51,34 +56,25 @@ const char *btrfs_super_csum_name(u16 csum_type)
return btrfs_csums[csum_type].name;
}
-struct btrfs_path *btrfs_alloc_path(void)
+/*
+ * Return driver name if defined, otherwise the name that's also a valid driver
+ * name
+ */
+const char *btrfs_super_csum_driver(u16 csum_type)
{
- return kmem_cache_zalloc(btrfs_path_cachep, GFP_NOFS);
+ /* csum type is validated at mount time */
+ return btrfs_csums[csum_type].driver ?:
+ btrfs_csums[csum_type].name;
}
-/*
- * set all locked nodes in the path to blocking locks. This should
- * be done before scheduling
- */
-noinline void btrfs_set_path_blocking(struct btrfs_path *p)
+size_t __const btrfs_get_num_csums(void)
{
- int i;
- for (i = 0; i < BTRFS_MAX_LEVEL; i++) {
- if (!p->nodes[i] || !p->locks[i])
- continue;
- /*
- * If we currently have a spinning reader or writer lock this
- * will bump the count of blocking holders and drop the
- * spinlock.
- */
- if (p->locks[i] == BTRFS_READ_LOCK) {
- btrfs_set_lock_blocking_read(p->nodes[i]);
- p->locks[i] = BTRFS_READ_LOCK_BLOCKING;
- } else if (p->locks[i] == BTRFS_WRITE_LOCK) {
- btrfs_set_lock_blocking_write(p->nodes[i]);
- p->locks[i] = BTRFS_WRITE_LOCK_BLOCKING;
- }
- }
+ return ARRAY_SIZE(btrfs_csums);
+}
+
+struct btrfs_path *btrfs_alloc_path(void)
+{
+ return kmem_cache_zalloc(btrfs_path_cachep, GFP_NOFS);
}
/* this also releases the path */
@@ -1125,7 +1121,7 @@ static noinline int __btrfs_cow_block(struct btrfs_trans_handle *trans,
btrfs_header_backref_rev(buf) < BTRFS_MIXED_BACKREF_REV)
parent_start = buf->start;
- extent_buffer_get(cow);
+ atomic_inc(&cow->refs);
ret = tree_mod_log_insert_root(root->node, cow, 1);
BUG_ON(ret < 0);
rcu_assign_pointer(root->node, cow);
@@ -1563,7 +1559,7 @@ static int comp_keys(const struct btrfs_disk_key *disk,
/*
* same as comp_keys only with two btrfs_key's
*/
-int btrfs_comp_cpu_keys(const struct btrfs_key *k1, const struct btrfs_key *k2)
+int __pure btrfs_comp_cpu_keys(const struct btrfs_key *k1, const struct btrfs_key *k2)
{
if (k1->objectid > k2->objectid)
return 1;
@@ -2036,7 +2032,7 @@ static noinline int balance_level(struct btrfs_trans_handle *trans,
/* update the path */
if (left) {
if (btrfs_header_nritems(left) > orig_slot) {
- extent_buffer_get(left);
+ atomic_inc(&left->refs);
/* left was locked after cow */
path->nodes[level] = left;
path->slots[level + 1] -= 1;
@@ -2379,32 +2375,6 @@ static noinline void unlock_up(struct btrfs_path *path, int level,
}
/*
- * This releases any locks held in the path starting at level and
- * going all the way up to the root.
- *
- * btrfs_search_slot will keep the lock held on higher nodes in a few
- * corner cases, such as COW of the block at slot zero in the node. This
- * ignores those rules, and it should only be called when there are no
- * more updates to be done higher up in the tree.
- */
-noinline void btrfs_unlock_up_safe(struct btrfs_path *path, int level)
-{
- int i;
-
- if (path->keep_locks)
- return;
-
- for (i = level; i < BTRFS_MAX_LEVEL; i++) {
- if (!path->nodes[i])
- continue;
- if (!path->locks[i])
- continue;
- btrfs_tree_unlock_rw(path->nodes[i], path->locks[i]);
- path->locks[i] = 0;
- }
-}
-
-/*
* helper function for btrfs_search_slot. The goal is to find a block
* in cache without setting the path to blocking. If we find the block
* we return zero and the path is unchanged.
@@ -2652,7 +2622,7 @@ static struct extent_buffer *btrfs_search_slot_get_root(struct btrfs_root *root,
} else {
b = root->commit_root;
- extent_buffer_get(b);
+ atomic_inc(&b->refs);
}
level = btrfs_header_level(b);
/*
@@ -2785,12 +2755,10 @@ again:
}
while (b) {
+ int dec = 0;
+
level = btrfs_header_level(b);
- /*
- * setup the path here so we can release it under lock
- * contention with the cow code
- */
if (cow) {
bool last_level = (level == (BTRFS_MAX_LEVEL - 1));
@@ -2861,73 +2829,7 @@ cow_done:
if (ret < 0)
goto done;
- if (level != 0) {
- int dec = 0;
- if (ret && slot > 0) {
- dec = 1;
- slot -= 1;
- }
- p->slots[level] = slot;
- err = setup_nodes_for_search(trans, root, p, b, level,
- ins_len, &write_lock_level);
- if (err == -EAGAIN)
- goto again;
- if (err) {
- ret = err;
- goto done;
- }
- b = p->nodes[level];
- slot = p->slots[level];
-
- /*
- * slot 0 is special, if we change the key
- * we have to update the parent pointer
- * which means we must have a write lock
- * on the parent
- */
- if (slot == 0 && ins_len &&
- write_lock_level < level + 1) {
- write_lock_level = level + 1;
- btrfs_release_path(p);
- goto again;
- }
-
- unlock_up(p, level, lowest_unlock,
- min_write_lock_level, &write_lock_level);
-
- if (level == lowest_level) {
- if (dec)
- p->slots[level]++;
- goto done;
- }
-
- err = read_block_for_search(root, p, &b, level,
- slot, key);
- if (err == -EAGAIN)
- goto again;
- if (err) {
- ret = err;
- goto done;
- }
-
- if (!p->skip_locking) {
- level = btrfs_header_level(b);
- if (level <= write_lock_level) {
- if (!btrfs_try_tree_write_lock(b)) {
- btrfs_set_path_blocking(p);
- btrfs_tree_lock(b);
- }
- p->locks[level] = BTRFS_WRITE_LOCK;
- } else {
- if (!btrfs_tree_read_lock_atomic(b)) {
- btrfs_set_path_blocking(p);
- btrfs_tree_read_lock(b);
- }
- p->locks[level] = BTRFS_READ_LOCK;
- }
- p->nodes[level] = b;
- }
- } else {
+ if (level == 0) {
p->slots[level] = slot;
if (ins_len > 0 &&
btrfs_leaf_free_space(b) < ins_len) {
@@ -2952,6 +2854,67 @@ cow_done:
min_write_lock_level, NULL);
goto done;
}
+ if (ret && slot > 0) {
+ dec = 1;
+ slot--;
+ }
+ p->slots[level] = slot;
+ err = setup_nodes_for_search(trans, root, p, b, level, ins_len,
+ &write_lock_level);
+ if (err == -EAGAIN)
+ goto again;
+ if (err) {
+ ret = err;
+ goto done;
+ }
+ b = p->nodes[level];
+ slot = p->slots[level];
+
+ /*
+ * Slot 0 is special, if we change the key we have to update
+ * the parent pointer which means we must have a write lock on
+ * the parent
+ */
+ if (slot == 0 && ins_len && write_lock_level < level + 1) {
+ write_lock_level = level + 1;
+ btrfs_release_path(p);
+ goto again;
+ }
+
+ unlock_up(p, level, lowest_unlock, min_write_lock_level,
+ &write_lock_level);
+
+ if (level == lowest_level) {
+ if (dec)
+ p->slots[level]++;
+ goto done;
+ }
+
+ err = read_block_for_search(root, p, &b, level, slot, key);
+ if (err == -EAGAIN)
+ goto again;
+ if (err) {
+ ret = err;
+ goto done;
+ }
+
+ if (!p->skip_locking) {
+ level = btrfs_header_level(b);
+ if (level <= write_lock_level) {
+ if (!btrfs_try_tree_write_lock(b)) {
+ btrfs_set_path_blocking(p);
+ btrfs_tree_lock(b);
+ }
+ p->locks[level] = BTRFS_WRITE_LOCK;
+ } else {
+ if (!btrfs_tree_read_lock_atomic(b)) {
+ btrfs_set_path_blocking(p);
+ btrfs_tree_read_lock(b);
+ }
+ p->locks[level] = BTRFS_READ_LOCK;
+ }
+ p->nodes[level] = b;
+ }
}
ret = 1;
done:
@@ -3008,6 +2971,8 @@ again:
p->locks[level] = BTRFS_READ_LOCK;
while (b) {
+ int dec = 0;
+
level = btrfs_header_level(b);
p->nodes[level] = b;
@@ -3028,47 +2993,45 @@ again:
if (ret < 0)
goto done;
- if (level != 0) {
- int dec = 0;
- if (ret && slot > 0) {
- dec = 1;
- slot -= 1;
- }
+ if (level == 0) {
p->slots[level] = slot;
unlock_up(p, level, lowest_unlock, 0, NULL);
+ goto done;
+ }
- if (level == lowest_level) {
- if (dec)
- p->slots[level]++;
- goto done;
- }
+ if (ret && slot > 0) {
+ dec = 1;
+ slot--;
+ }
+ p->slots[level] = slot;
+ unlock_up(p, level, lowest_unlock, 0, NULL);
- err = read_block_for_search(root, p, &b, level,
- slot, key);
- if (err == -EAGAIN)
- goto again;
- if (err) {
- ret = err;
- goto done;
- }
+ if (level == lowest_level) {
+ if (dec)
+ p->slots[level]++;
+ goto done;
+ }
- level = btrfs_header_level(b);
- if (!btrfs_tree_read_lock_atomic(b)) {
- btrfs_set_path_blocking(p);
- btrfs_tree_read_lock(b);
- }
- b = tree_mod_log_rewind(fs_info, p, b, time_seq);
- if (!b) {
- ret = -ENOMEM;
- goto done;
- }
- p->locks[level] = BTRFS_READ_LOCK;
- p->nodes[level] = b;
- } else {
- p->slots[level] = slot;
- unlock_up(p, level, lowest_unlock, 0, NULL);
+ err = read_block_for_search(root, p, &b, level, slot, key);
+ if (err == -EAGAIN)
+ goto again;
+ if (err) {
+ ret = err;
+ goto done;
+ }
+
+ level = btrfs_header_level(b);
+ if (!btrfs_tree_read_lock_atomic(b)) {
+ btrfs_set_path_blocking(p);
+ btrfs_tree_read_lock(b);
+ }
+ b = tree_mod_log_rewind(fs_info, p, b, time_seq);
+ if (!b) {
+ ret = -ENOMEM;
goto done;
}
+ p->locks[level] = BTRFS_READ_LOCK;
+ p->nodes[level] = b;
}
ret = 1;
done:
@@ -3433,7 +3396,7 @@ static noinline int insert_new_root(struct btrfs_trans_handle *trans,
free_extent_buffer(old);
add_root_to_dirty_list(root);
- extent_buffer_get(c);
+ atomic_inc(&c->refs);
path->nodes[level] = c;
path->locks[level] = BTRFS_WRITE_LOCK_BLOCKING;
path->slots[level] = 0;
@@ -4966,7 +4929,7 @@ static noinline void btrfs_del_leaf(struct btrfs_trans_handle *trans,
root_sub_used(root, leaf->len);
- extent_buffer_get(leaf);
+ atomic_inc(&leaf->refs);
btrfs_free_tree_block(trans, root, leaf, 0, 1);
free_extent_buffer_stale(leaf);
}
@@ -5047,7 +5010,7 @@ int btrfs_del_items(struct btrfs_trans_handle *trans, struct btrfs_root *root,
* for possible call to del_ptr below
*/
slot = path->slots[1];
- extent_buffer_get(leaf);
+ atomic_inc(&leaf->refs);
btrfs_set_path_blocking(path);
wret = push_leaf_left(trans, root, path, 1, 1,
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 19d669d12ca1..b2e8fd8a8e59 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -28,6 +28,7 @@
#include <linux/dynamic_debug.h>
#include <linux/refcount.h>
#include <linux/crc32c.h>
+#include "extent-io-tree.h"
#include "extent_io.h"
#include "extent_map.h"
#include "async-thread.h"
@@ -38,7 +39,7 @@ struct btrfs_transaction;
struct btrfs_pending_snapshot;
struct btrfs_delayed_ref_root;
struct btrfs_space_info;
-struct btrfs_block_group_cache;
+struct btrfs_block_group;
extern struct kmem_cache *btrfs_trans_handle_cachep;
extern struct kmem_cache *btrfs_bit_radix_cachep;
extern struct kmem_cache *btrfs_path_cachep;
@@ -56,9 +57,9 @@ struct btrfs_ref;
* filesystem data as well that can be used to read data in order to repair
* read errors on other disks.
*
- * Current value is derived from RAID1 with 2 copies.
+ * Current value is derived from RAID1C4 with 4 copies.
*/
-#define BTRFS_MAX_MIRRORS (2 + 1)
+#define BTRFS_MAX_MIRRORS (4 + 1)
#define BTRFS_MAX_LEVEL 8
@@ -291,7 +292,8 @@ struct btrfs_super_block {
BTRFS_FEATURE_INCOMPAT_EXTENDED_IREF | \
BTRFS_FEATURE_INCOMPAT_SKINNY_METADATA | \
BTRFS_FEATURE_INCOMPAT_NO_HOLES | \
- BTRFS_FEATURE_INCOMPAT_METADATA_UUID)
+ BTRFS_FEATURE_INCOMPAT_METADATA_UUID | \
+ BTRFS_FEATURE_INCOMPAT_RAID1C34)
#define BTRFS_FEATURE_INCOMPAT_SAFE_SET \
(BTRFS_FEATURE_INCOMPAT_EXTENDED_IREF)
@@ -413,7 +415,7 @@ struct btrfs_free_cluster {
/* We did a full search and couldn't create a cluster */
bool fragmented;
- struct btrfs_block_group_cache *block_group;
+ struct btrfs_block_group *block_group;
/*
* when a cluster is allocated from a block group, we put the
* cluster onto a list in the block group so that it can
@@ -476,8 +478,8 @@ struct btrfs_swapfile_pin {
void *ptr;
struct inode *inode;
/*
- * If true, ptr points to a struct btrfs_block_group_cache. Otherwise,
- * ptr points to a struct btrfs_device.
+ * If true, ptr points to a struct btrfs_block_group. Otherwise, ptr
+ * points to a struct btrfs_device.
*/
bool is_block_group;
};
@@ -722,7 +724,6 @@ struct btrfs_fs_info {
struct btrfs_workqueue *endio_meta_write_workers;
struct btrfs_workqueue *endio_write_workers;
struct btrfs_workqueue *endio_freespace_worker;
- struct btrfs_workqueue *submit_workers;
struct btrfs_workqueue *caching_workers;
struct btrfs_workqueue *readahead_workers;
@@ -734,8 +735,6 @@ struct btrfs_fs_info {
struct btrfs_workqueue *fixup_workers;
struct btrfs_workqueue *delayed_workers;
- /* the extent workers do delayed refs on the extent allocation tree */
- struct btrfs_workqueue *extent_workers;
struct task_struct *transaction_kthread;
struct task_struct *cleaner_kthread;
u32 thread_pool_size;
@@ -1521,18 +1520,18 @@ static inline u64 btrfs_stripe_devid_nr(struct extent_buffer *eb,
}
/* struct btrfs_block_group_item */
-BTRFS_SETGET_STACK_FUNCS(block_group_used, struct btrfs_block_group_item,
+BTRFS_SETGET_STACK_FUNCS(stack_block_group_used, struct btrfs_block_group_item,
used, 64);
-BTRFS_SETGET_FUNCS(disk_block_group_used, struct btrfs_block_group_item,
+BTRFS_SETGET_FUNCS(block_group_used, struct btrfs_block_group_item,
used, 64);
-BTRFS_SETGET_STACK_FUNCS(block_group_chunk_objectid,
+BTRFS_SETGET_STACK_FUNCS(stack_block_group_chunk_objectid,
struct btrfs_block_group_item, chunk_objectid, 64);
-BTRFS_SETGET_FUNCS(disk_block_group_chunk_objectid,
+BTRFS_SETGET_FUNCS(block_group_chunk_objectid,
struct btrfs_block_group_item, chunk_objectid, 64);
-BTRFS_SETGET_FUNCS(disk_block_group_flags,
+BTRFS_SETGET_FUNCS(block_group_flags,
struct btrfs_block_group_item, flags, 64);
-BTRFS_SETGET_STACK_FUNCS(block_group_flags,
+BTRFS_SETGET_STACK_FUNCS(stack_block_group_flags,
struct btrfs_block_group_item, flags, 64);
/* struct btrfs_free_space_info */
@@ -2165,6 +2164,9 @@ BTRFS_SETGET_STACK_FUNCS(super_uuid_tree_generation, struct btrfs_super_block,
int btrfs_super_csum_size(const struct btrfs_super_block *s);
const char *btrfs_super_csum_name(u16 csum_type);
+const char *btrfs_super_csum_driver(u16 csum_type);
+size_t __const btrfs_get_num_csums(void);
+
/*
* The leaf data grows from end-to-front in the node.
@@ -2399,7 +2401,7 @@ static inline u64 btrfs_calc_metadata_size(struct btrfs_fs_info *fs_info,
int btrfs_add_excluded_extent(struct btrfs_fs_info *fs_info,
u64 start, u64 num_bytes);
-void btrfs_free_excluded_extents(struct btrfs_block_group_cache *cache);
+void btrfs_free_excluded_extents(struct btrfs_block_group *cache);
int btrfs_run_delayed_refs(struct btrfs_trans_handle *trans,
unsigned long count);
void btrfs_cleanup_ref_head_accounting(struct btrfs_fs_info *fs_info,
@@ -2455,8 +2457,8 @@ int btrfs_inc_extent_ref(struct btrfs_trans_handle *trans,
struct btrfs_ref *generic_ref);
int btrfs_extent_readonly(struct btrfs_fs_info *fs_info, u64 bytenr);
-void btrfs_get_block_group_trimming(struct btrfs_block_group_cache *cache);
-void btrfs_put_block_group_trimming(struct btrfs_block_group_cache *cache);
+void btrfs_get_block_group_trimming(struct btrfs_block_group *cache);
+void btrfs_put_block_group_trimming(struct btrfs_block_group *cache);
void btrfs_clear_space_info_full(struct btrfs_fs_info *info);
enum btrfs_reserve_flush_enum {
@@ -2489,8 +2491,7 @@ int btrfs_subvolume_reserve_metadata(struct btrfs_root *root,
int nitems, bool use_global_rsv);
void btrfs_subvolume_release_metadata(struct btrfs_fs_info *fs_info,
struct btrfs_block_rsv *rsv);
-void btrfs_delalloc_release_extents(struct btrfs_inode *inode, u64 num_bytes,
- bool qgroup_free);
+void btrfs_delalloc_release_extents(struct btrfs_inode *inode, u64 num_bytes);
int btrfs_delalloc_reserve_metadata(struct btrfs_inode *inode, u64 num_bytes);
u64 btrfs_account_ro_block_groups_free_space(struct btrfs_space_info *sinfo);
@@ -2510,7 +2511,7 @@ void btrfs_wait_for_snapshot_creation(struct btrfs_root *root);
/* ctree.c */
int btrfs_bin_search(struct extent_buffer *eb, const struct btrfs_key *key,
int level, int *slot);
-int btrfs_comp_cpu_keys(const struct btrfs_key *k1, const struct btrfs_key *k2);
+int __pure btrfs_comp_cpu_keys(const struct btrfs_key *k1, const struct btrfs_key *k2);
int btrfs_previous_item(struct btrfs_root *root,
struct btrfs_path *path, u64 min_objectid,
int type);
@@ -2570,8 +2571,6 @@ int btrfs_realloc_node(struct btrfs_trans_handle *trans,
void btrfs_release_path(struct btrfs_path *p);
struct btrfs_path *btrfs_alloc_path(void);
void btrfs_free_path(struct btrfs_path *p);
-void btrfs_set_path_blocking(struct btrfs_path *p);
-void btrfs_unlock_up_safe(struct btrfs_path *p, int level);
int btrfs_del_items(struct btrfs_trans_handle *trans, struct btrfs_root *root,
struct btrfs_path *path, int slot, int nr);
@@ -2873,10 +2872,9 @@ int btrfs_drop_inode(struct inode *inode);
int __init btrfs_init_cachep(void);
void __cold btrfs_destroy_cachep(void);
struct inode *btrfs_iget_path(struct super_block *s, struct btrfs_key *location,
- struct btrfs_root *root, int *new,
- struct btrfs_path *path);
+ struct btrfs_root *root, struct btrfs_path *path);
struct inode *btrfs_iget(struct super_block *s, struct btrfs_key *location,
- struct btrfs_root *root, int *was_new);
+ struct btrfs_root *root);
struct extent_map *btrfs_get_extent(struct btrfs_inode *inode,
struct page *page, size_t pg_offset,
u64 start, u64 end, int create);
@@ -2912,7 +2910,7 @@ long btrfs_ioctl(struct file *file, unsigned int cmd, unsigned long arg);
long btrfs_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg);
int btrfs_ioctl_get_supported_features(void __user *arg);
void btrfs_sync_inode_flags_to_i_flags(struct inode *inode);
-int btrfs_is_empty_uuid(u8 *uuid);
+int __pure btrfs_is_empty_uuid(u8 *uuid);
int btrfs_defrag_file(struct inode *inode, struct file *file,
struct btrfs_ioctl_defrag_range_args *range,
u64 newer_than, unsigned long max_pages);
@@ -3146,7 +3144,7 @@ __cold
void __btrfs_handle_fs_error(struct btrfs_fs_info *fs_info, const char *function,
unsigned int line, int errno, const char *fmt, ...);
-const char *btrfs_decode_error(int errno);
+const char * __attribute_const__ btrfs_decode_error(int errno);
__cold
void __btrfs_abort_transaction(struct btrfs_trans_handle *trans,
diff --git a/fs/btrfs/delalloc-space.c b/fs/btrfs/delalloc-space.c
index d949d7d2abed..4cdac4d834f5 100644
--- a/fs/btrfs/delalloc-space.c
+++ b/fs/btrfs/delalloc-space.c
@@ -307,7 +307,6 @@ int btrfs_delalloc_reserve_metadata(struct btrfs_inode *inode, u64 num_bytes)
unsigned nr_extents;
enum btrfs_reserve_flush_enum flush = BTRFS_RESERVE_FLUSH_ALL;
int ret = 0;
- bool delalloc_lock = true;
/*
* If we are a free space inode we need to not flush since we will be in
@@ -320,7 +319,6 @@ int btrfs_delalloc_reserve_metadata(struct btrfs_inode *inode, u64 num_bytes)
*/
if (btrfs_is_free_space_inode(inode)) {
flush = BTRFS_RESERVE_NO_FLUSH;
- delalloc_lock = false;
} else {
if (current->journal_info)
flush = BTRFS_RESERVE_FLUSH_LIMIT;
@@ -329,9 +327,6 @@ int btrfs_delalloc_reserve_metadata(struct btrfs_inode *inode, u64 num_bytes)
schedule_timeout(1);
}
- if (delalloc_lock)
- mutex_lock(&inode->delalloc_mutex);
-
num_bytes = ALIGN(num_bytes, fs_info->sectorsize);
/*
@@ -348,10 +343,12 @@ int btrfs_delalloc_reserve_metadata(struct btrfs_inode *inode, u64 num_bytes)
&qgroup_reserve);
ret = btrfs_qgroup_reserve_meta_prealloc(root, qgroup_reserve, true);
if (ret)
- goto out_fail;
+ return ret;
ret = btrfs_reserve_metadata_bytes(root, block_rsv, meta_reserve, flush);
- if (ret)
- goto out_qgroup;
+ if (ret) {
+ btrfs_qgroup_free_meta_prealloc(root, qgroup_reserve);
+ return ret;
+ }
/*
* Now we need to update our outstanding extents and csum bytes _first_
@@ -375,16 +372,7 @@ int btrfs_delalloc_reserve_metadata(struct btrfs_inode *inode, u64 num_bytes)
block_rsv->qgroup_rsv_reserved += qgroup_reserve;
spin_unlock(&block_rsv->lock);
- if (delalloc_lock)
- mutex_unlock(&inode->delalloc_mutex);
return 0;
-out_qgroup:
- btrfs_qgroup_free_meta_prealloc(root, qgroup_reserve);
-out_fail:
- btrfs_inode_rsv_release(inode, true);
- if (delalloc_lock)
- mutex_unlock(&inode->delalloc_mutex);
- return ret;
}
/**
@@ -418,7 +406,6 @@ void btrfs_delalloc_release_metadata(struct btrfs_inode *inode, u64 num_bytes,
* btrfs_delalloc_release_extents - release our outstanding_extents
* @inode: the inode to balance the reservation for.
* @num_bytes: the number of bytes we originally reserved with
- * @qgroup_free: do we need to free qgroup meta reservation or convert them.
*
* When we reserve space we increase outstanding_extents for the extents we may
* add. Once we've set the range as delalloc or created our ordered extents we
@@ -426,8 +413,7 @@ void btrfs_delalloc_release_metadata(struct btrfs_inode *inode, u64 num_bytes,
* temporarily tracked outstanding_extents. This _must_ be used in conjunction
* with btrfs_delalloc_reserve_metadata.
*/
-void btrfs_delalloc_release_extents(struct btrfs_inode *inode, u64 num_bytes,
- bool qgroup_free)
+void btrfs_delalloc_release_extents(struct btrfs_inode *inode, u64 num_bytes)
{
struct btrfs_fs_info *fs_info = inode->root->fs_info;
unsigned num_extents;
@@ -441,7 +427,7 @@ void btrfs_delalloc_release_extents(struct btrfs_inode *inode, u64 num_bytes,
if (btrfs_is_testing(fs_info))
return;
- btrfs_inode_rsv_release(inode, qgroup_free);
+ btrfs_inode_rsv_release(inode, true);
}
/**
diff --git a/fs/btrfs/delayed-inode.c b/fs/btrfs/delayed-inode.c
index 1f7f39b10bd0..d3e15e1d4a91 100644
--- a/fs/btrfs/delayed-inode.c
+++ b/fs/btrfs/delayed-inode.c
@@ -12,6 +12,7 @@
#include "transaction.h"
#include "ctree.h"
#include "qgroup.h"
+#include "locking.h"
#define BTRFS_DELAYED_WRITEBACK 512
#define BTRFS_DELAYED_BACKGROUND 128
@@ -1367,8 +1368,8 @@ static int btrfs_wq_run_delayed_node(struct btrfs_delayed_root *delayed_root,
return -ENOMEM;
async_work->delayed_root = delayed_root;
- btrfs_init_work(&async_work->work, btrfs_delayed_meta_helper,
- btrfs_async_run_delayed_root, NULL, NULL);
+ btrfs_init_work(&async_work->work, btrfs_async_run_delayed_root, NULL,
+ NULL);
async_work->nr = nr;
btrfs_queue_work(fs_info->delayed_workers, &async_work->work);
@@ -1949,12 +1950,19 @@ void btrfs_kill_all_delayed_nodes(struct btrfs_root *root)
}
inode_id = delayed_nodes[n - 1]->inode_id + 1;
-
- for (i = 0; i < n; i++)
- refcount_inc(&delayed_nodes[i]->refs);
+ for (i = 0; i < n; i++) {
+ /*
+ * Don't increase refs in case the node is dead and
+ * about to be removed from the tree in the loop below
+ */
+ if (!refcount_inc_not_zero(&delayed_nodes[i]->refs))
+ delayed_nodes[i] = NULL;
+ }
spin_unlock(&root->inode_lock);
for (i = 0; i < n; i++) {
+ if (!delayed_nodes[i])
+ continue;
__btrfs_kill_delayed_node(delayed_nodes[i]);
btrfs_release_delayed_node(delayed_nodes[i]);
}
diff --git a/fs/btrfs/dev-replace.c b/fs/btrfs/dev-replace.c
index 48890826b5e6..f639dde2a679 100644
--- a/fs/btrfs/dev-replace.c
+++ b/fs/btrfs/dev-replace.c
@@ -986,7 +986,7 @@ static int btrfs_dev_replace_kthread(void *data)
return 0;
}
-int btrfs_dev_replace_is_ongoing(struct btrfs_dev_replace *dev_replace)
+int __pure btrfs_dev_replace_is_ongoing(struct btrfs_dev_replace *dev_replace)
{
if (!dev_replace->is_valid)
return 0;
diff --git a/fs/btrfs/dev-replace.h b/fs/btrfs/dev-replace.h
index 78c5d8f1adda..60b70dacc299 100644
--- a/fs/btrfs/dev-replace.h
+++ b/fs/btrfs/dev-replace.h
@@ -17,6 +17,6 @@ void btrfs_dev_replace_status(struct btrfs_fs_info *fs_info,
int btrfs_dev_replace_cancel(struct btrfs_fs_info *fs_info);
void btrfs_dev_replace_suspend_for_unmount(struct btrfs_fs_info *fs_info);
int btrfs_resume_dev_replace_async(struct btrfs_fs_info *fs_info);
-int btrfs_dev_replace_is_ongoing(struct btrfs_dev_replace *dev_replace);
+int __pure btrfs_dev_replace_is_ongoing(struct btrfs_dev_replace *dev_replace);
#endif
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 044981cf6df9..e0edfdc9c82b 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -205,7 +205,6 @@ struct extent_map *btree_get_extent(struct btrfs_inode *inode,
struct page *page, size_t pg_offset, u64 start, u64 len,
int create)
{
- struct btrfs_fs_info *fs_info = inode->root->fs_info;
struct extent_map_tree *em_tree = &inode->extent_tree;
struct extent_map *em;
int ret;
@@ -213,7 +212,6 @@ struct extent_map *btree_get_extent(struct btrfs_inode *inode,
read_lock(&em_tree->lock);
em = lookup_extent_mapping(em_tree, start, len);
if (em) {
- em->bdev = fs_info->fs_devices->latest_bdev;
read_unlock(&em_tree->lock);
goto out;
}
@@ -228,7 +226,6 @@ struct extent_map *btree_get_extent(struct btrfs_inode *inode,
em->len = (u64)-1;
em->block_len = (u64)-1;
em->block_start = 0;
- em->bdev = fs_info->fs_devices->latest_bdev;
write_lock(&em_tree->lock);
ret = add_extent_mapping(em_tree, em, 0);
@@ -352,6 +349,9 @@ static bool btrfs_supported_super_csum(u16 csum_type)
{
switch (csum_type) {
case BTRFS_CSUM_TYPE_CRC32:
+ case BTRFS_CSUM_TYPE_XXHASH:
+ case BTRFS_CSUM_TYPE_SHA256:
+ case BTRFS_CSUM_TYPE_BLAKE2:
return true;
default:
return false;
@@ -545,9 +545,11 @@ static int csum_dirty_buffer(struct btrfs_fs_info *fs_info, struct page *page)
ret = btrfs_check_leaf_full(eb);
if (ret < 0) {
+ btrfs_print_tree(eb, 0);
btrfs_err(fs_info,
"block=%llu write time tree block corruption detected",
eb->start);
+ WARN_ON(IS_ENABLED(CONFIG_BTRFS_DEBUG));
return ret;
}
write_extent_buffer(eb, result, 0, csum_size);
@@ -608,7 +610,7 @@ static int btree_readpage_end_io_hook(struct btrfs_io_bio *io_bio,
/* the pending IO might have been the only thing that kept this buffer
* in memory. Make sure we have a ref for all this other checks
*/
- extent_buffer_get(eb);
+ atomic_inc(&eb->refs);
reads_done = atomic_dec_and_test(&eb->io_pages);
if (!reads_done)
@@ -706,43 +708,31 @@ static void end_workqueue_bio(struct bio *bio)
struct btrfs_end_io_wq *end_io_wq = bio->bi_private;
struct btrfs_fs_info *fs_info;
struct btrfs_workqueue *wq;
- btrfs_work_func_t func;
fs_info = end_io_wq->info;
end_io_wq->status = bio->bi_status;
if (bio_op(bio) == REQ_OP_WRITE) {
- if (end_io_wq->metadata == BTRFS_WQ_ENDIO_METADATA) {
+ if (end_io_wq->metadata == BTRFS_WQ_ENDIO_METADATA)
wq = fs_info->endio_meta_write_workers;
- func = btrfs_endio_meta_write_helper;
- } else if (end_io_wq->metadata == BTRFS_WQ_ENDIO_FREE_SPACE) {
+ else if (end_io_wq->metadata == BTRFS_WQ_ENDIO_FREE_SPACE)
wq = fs_info->endio_freespace_worker;
- func = btrfs_freespace_write_helper;
- } else if (end_io_wq->metadata == BTRFS_WQ_ENDIO_RAID56) {
+ else if (end_io_wq->metadata == BTRFS_WQ_ENDIO_RAID56)
wq = fs_info->endio_raid56_workers;
- func = btrfs_endio_raid56_helper;
- } else {
+ else
wq = fs_info->endio_write_workers;
- func = btrfs_endio_write_helper;
- }
} else {
- if (unlikely(end_io_wq->metadata ==
- BTRFS_WQ_ENDIO_DIO_REPAIR)) {
+ if (unlikely(end_io_wq->metadata == BTRFS_WQ_ENDIO_DIO_REPAIR))
wq = fs_info->endio_repair_workers;
- func = btrfs_endio_repair_helper;
- } else if (end_io_wq->metadata == BTRFS_WQ_ENDIO_RAID56) {
+ else if (end_io_wq->metadata == BTRFS_WQ_ENDIO_RAID56)
wq = fs_info->endio_raid56_workers;
- func = btrfs_endio_raid56_helper;
- } else if (end_io_wq->metadata) {
+ else if (end_io_wq->metadata)
wq = fs_info->endio_meta_workers;
- func = btrfs_endio_meta_helper;
- } else {
+ else
wq = fs_info->endio_workers;
- func = btrfs_endio_helper;
- }
}
- btrfs_init_work(&end_io_wq->work, func, end_workqueue_fn, NULL, NULL);
+ btrfs_init_work(&end_io_wq->work, end_workqueue_fn, NULL, NULL);
btrfs_queue_work(wq, &end_io_wq->work);
}
@@ -803,8 +793,13 @@ static void run_one_async_done(struct btrfs_work *work)
return;
}
- ret = btrfs_map_bio(btrfs_sb(inode->i_sb), async->bio,
- async->mirror_num, 1);
+ /*
+ * All of the bios that pass through here are from async helpers.
+ * Use REQ_CGROUP_PUNT to issue them from the owning cgroup's context.
+ * This changes nothing when cgroups aren't in use.
+ */
+ async->bio->bi_opf |= REQ_CGROUP_PUNT;
+ ret = btrfs_map_bio(btrfs_sb(inode->i_sb), async->bio, async->mirror_num);
if (ret) {
async->bio->bi_status = ret;
bio_endio(async->bio);
@@ -835,8 +830,8 @@ blk_status_t btrfs_wq_submit_bio(struct btrfs_fs_info *fs_info, struct bio *bio,
async->mirror_num = mirror_num;
async->submit_bio_start = submit_bio_start;
- btrfs_init_work(&async->work, btrfs_worker_helper, run_one_async_start,
- run_one_async_done, run_one_async_free);
+ btrfs_init_work(&async->work, run_one_async_start, run_one_async_done,
+ run_one_async_free);
async->bio_offset = bio_offset;
@@ -904,12 +899,12 @@ static blk_status_t btree_submit_bio_hook(struct inode *inode, struct bio *bio,
BTRFS_WQ_ENDIO_METADATA);
if (ret)
goto out_w_error;
- ret = btrfs_map_bio(fs_info, bio, mirror_num, 0);
+ ret = btrfs_map_bio(fs_info, bio, mirror_num);
} else if (!async) {
ret = btree_csum_one_bio(bio);
if (ret)
goto out_w_error;
- ret = btrfs_map_bio(fs_info, bio, mirror_num, 0);
+ ret = btrfs_map_bio(fs_info, bio, mirror_num);
} else {
/*
* kthread helpers are used to submit writes so that
@@ -1657,8 +1652,8 @@ static void end_workqueue_fn(struct btrfs_work *work)
bio->bi_status = end_io_wq->status;
bio->bi_private = end_io_wq->private;
bio->bi_end_io = end_io_wq->end_io;
- kmem_cache_free(btrfs_end_io_wq_cache, end_io_wq);
bio_endio(bio);
+ kmem_cache_free(btrfs_end_io_wq_cache, end_io_wq);
}
static int cleaner_kthread(void *arg)
@@ -1753,7 +1748,7 @@ static int transaction_kthread(void *arg)
}
now = ktime_get_seconds();
- if (cur->state < TRANS_STATE_BLOCKED &&
+ if (cur->state < TRANS_STATE_COMMIT_START &&
!test_bit(BTRFS_FS_NEED_ASYNC_COMMIT, &fs_info->flags) &&
(now < cur->start_time ||
now - cur->start_time < fs_info->commit_interval)) {
@@ -1792,18 +1787,18 @@ sleep:
}
/*
- * this will find the highest generation in the array of
- * root backups. The index of the highest array is returned,
- * or -1 if we can't find anything.
+ * This will find the highest generation in the array of root backups. The
+ * index of the highest array is returned, or -EINVAL if we can't find
+ * anything.
*
* We check to make sure the array is valid by comparing the
* generation of the latest root in the array with the generation
* in the super block. If they don't match we pitch it.
*/
-static int find_newest_super_backup(struct btrfs_fs_info *info, u64 newest_gen)
+static int find_newest_super_backup(struct btrfs_fs_info *info)
{
+ const u64 newest_gen = btrfs_super_generation(info->super_copy);
u64 cur;
- int newest_index = -1;
struct btrfs_root_backup *root_backup;
int i;
@@ -1811,37 +1806,10 @@ static int find_newest_super_backup(struct btrfs_fs_info *info, u64 newest_gen)
root_backup = info->super_copy->super_roots + i;
cur = btrfs_backup_tree_root_gen(root_backup);
if (cur == newest_gen)
- newest_index = i;
+ return i;
}
- /* check to see if we actually wrapped around */
- if (newest_index == BTRFS_NUM_BACKUP_ROOTS - 1) {
- root_backup = info->super_copy->super_roots;
- cur = btrfs_backup_tree_root_gen(root_backup);
- if (cur == newest_gen)
- newest_index = 0;
- }
- return newest_index;
-}
-
-
-/*
- * find the oldest backup so we know where to store new entries
- * in the backup array. This will set the backup_root_index
- * field in the fs_info struct
- */
-static void find_oldest_super_backup(struct btrfs_fs_info *info,
- u64 newest_gen)
-{
- int newest_index = -1;
-
- newest_index = find_newest_super_backup(info, newest_gen);
- /* if there was garbage in there, just move along */
- if (newest_index == -1) {
- info->backup_root_index = 0;
- } else {
- info->backup_root_index = (newest_index + 1) % BTRFS_NUM_BACKUP_ROOTS;
- }
+ return -EINVAL;
}
/*
@@ -1851,22 +1819,8 @@ static void find_oldest_super_backup(struct btrfs_fs_info *info,
*/
static void backup_super_roots(struct btrfs_fs_info *info)
{
- int next_backup;
+ const int next_backup = info->backup_root_index;
struct btrfs_root_backup *root_backup;
- int last_backup;
-
- next_backup = info->backup_root_index;
- last_backup = (next_backup + BTRFS_NUM_BACKUP_ROOTS - 1) %
- BTRFS_NUM_BACKUP_ROOTS;
-
- /*
- * just overwrite the last backup if we're at the same generation
- * this happens only at umount
- */
- root_backup = info->super_for_commit->super_roots + last_backup;
- if (btrfs_backup_tree_root_gen(root_backup) ==
- btrfs_header_generation(info->tree_root->node))
- next_backup = last_backup;
root_backup = info->super_for_commit->super_roots + next_backup;
@@ -1939,40 +1893,31 @@ static void backup_super_roots(struct btrfs_fs_info *info)
}
/*
- * this copies info out of the root backup array and back into
- * the in-memory super block. It is meant to help iterate through
- * the array, so you send it the number of backups you've already
- * tried and the last backup index you used.
+ * read_backup_root - Reads a backup root based on the passed priority. Prio 0
+ * is the newest, prio 1/2/3 are 2nd newest/3rd newest/4th (oldest) backup roots
*
- * this returns -1 when it has tried all the backups
+ * fs_info - filesystem whose backup roots need to be read
+ * priority - priority of backup root required
+ *
+ * Returns backup root index on success and -EINVAL otherwise.
*/
-static noinline int next_root_backup(struct btrfs_fs_info *info,
- struct btrfs_super_block *super,
- int *num_backups_tried, int *backup_index)
+static int read_backup_root(struct btrfs_fs_info *fs_info, u8 priority)
{
+ int backup_index = find_newest_super_backup(fs_info);
+ struct btrfs_super_block *super = fs_info->super_copy;
struct btrfs_root_backup *root_backup;
- int newest = *backup_index;
-
- if (*num_backups_tried == 0) {
- u64 gen = btrfs_super_generation(super);
- newest = find_newest_super_backup(info, gen);
- if (newest == -1)
- return -1;
+ if (priority < BTRFS_NUM_BACKUP_ROOTS && backup_index >= 0) {
+ if (priority == 0)
+ return backup_index;
- *backup_index = newest;
- *num_backups_tried = 1;
- } else if (*num_backups_tried == BTRFS_NUM_BACKUP_ROOTS) {
- /* we've tried all the backups, all done */
- return -1;
+ backup_index = backup_index + BTRFS_NUM_BACKUP_ROOTS - priority;
+ backup_index %= BTRFS_NUM_BACKUP_ROOTS;
} else {
- /* jump to the next oldest backup */
- newest = (*backup_index + BTRFS_NUM_BACKUP_ROOTS - 1) %
- BTRFS_NUM_BACKUP_ROOTS;
- *backup_index = newest;
- *num_backups_tried += 1;
+ return -EINVAL;
}
- root_backup = super->super_roots + newest;
+
+ root_backup = super->super_roots + backup_index;
btrfs_set_super_generation(super,
btrfs_backup_tree_root_gen(root_backup));
@@ -1982,12 +1927,13 @@ static noinline int next_root_backup(struct btrfs_fs_info *info,
btrfs_set_super_bytes_used(super, btrfs_backup_bytes_used(root_backup));
/*
- * fixme: the total bytes and num_devices need to match or we should
+ * Fixme: the total bytes and num_devices need to match or we should
* need a fsck
*/
btrfs_set_super_total_bytes(super, btrfs_backup_total_bytes(root_backup));
btrfs_set_super_num_devices(super, btrfs_backup_num_devices(root_backup));
- return 0;
+
+ return backup_index;
}
/* helper to cleanup workers */
@@ -2002,13 +1948,11 @@ static void btrfs_stop_all_workers(struct btrfs_fs_info *fs_info)
btrfs_destroy_workqueue(fs_info->rmw_workers);
btrfs_destroy_workqueue(fs_info->endio_write_workers);
btrfs_destroy_workqueue(fs_info->endio_freespace_worker);
- btrfs_destroy_workqueue(fs_info->submit_workers);
btrfs_destroy_workqueue(fs_info->delayed_workers);
btrfs_destroy_workqueue(fs_info->caching_workers);
btrfs_destroy_workqueue(fs_info->readahead_workers);
btrfs_destroy_workqueue(fs_info->flush_workers);
btrfs_destroy_workqueue(fs_info->qgroup_rescan_workers);
- btrfs_destroy_workqueue(fs_info->extent_workers);
/*
* Now that all other work queues are destroyed, we can safely destroy
* the queues used for metadata I/O, since tasks from those other work
@@ -2029,7 +1973,7 @@ static void free_root_extent_buffers(struct btrfs_root *root)
}
/* helper to cleanup tree roots */
-static void free_root_pointers(struct btrfs_fs_info *info, int chunk_root)
+static void free_root_pointers(struct btrfs_fs_info *info, bool free_chunk_root)
{
free_root_extent_buffers(info->tree_root);
@@ -2038,7 +1982,7 @@ static void free_root_pointers(struct btrfs_fs_info *info, int chunk_root)
free_root_extent_buffers(info->csum_root);
free_root_extent_buffers(info->quota_root);
free_root_extent_buffers(info->uuid_root);
- if (chunk_root)
+ if (free_chunk_root)
free_root_extent_buffers(info->chunk_root);
free_root_extent_buffers(info->free_space_root);
}
@@ -2168,16 +2112,6 @@ static int btrfs_init_workqueues(struct btrfs_fs_info *fs_info,
fs_info->caching_workers =
btrfs_alloc_workqueue(fs_info, "cache", flags, max_active, 0);
- /*
- * a higher idle thresh on the submit workers makes it much more
- * likely that bios will be send down in a sane order to the
- * devices
- */
- fs_info->submit_workers =
- btrfs_alloc_workqueue(fs_info, "submit", flags,
- min_t(u64, fs_devices->num_devices,
- max_active), 64);
-
fs_info->fixup_workers =
btrfs_alloc_workqueue(fs_info, "fixup", flags, 1, 0);
@@ -2214,13 +2148,9 @@ static int btrfs_init_workqueues(struct btrfs_fs_info *fs_info,
max_active, 2);
fs_info->qgroup_rescan_workers =
btrfs_alloc_workqueue(fs_info, "qgroup-rescan", flags, 1, 0);
- fs_info->extent_workers =
- btrfs_alloc_workqueue(fs_info, "extent-refs", flags,
- min_t(u64, fs_devices->num_devices,
- max_active), 8);
if (!(fs_info->workers && fs_info->delalloc_workers &&
- fs_info->submit_workers && fs_info->flush_workers &&
+ fs_info->flush_workers &&
fs_info->endio_workers && fs_info->endio_meta_workers &&
fs_info->endio_meta_write_workers &&
fs_info->endio_repair_workers &&
@@ -2228,7 +2158,6 @@ static int btrfs_init_workqueues(struct btrfs_fs_info *fs_info,
fs_info->endio_freespace_worker && fs_info->rmw_workers &&
fs_info->caching_workers && fs_info->readahead_workers &&
fs_info->fixup_workers && fs_info->delayed_workers &&
- fs_info->extent_workers &&
fs_info->qgroup_rescan_workers)) {
return -ENOMEM;
}
@@ -2239,13 +2168,13 @@ static int btrfs_init_workqueues(struct btrfs_fs_info *fs_info,
static int btrfs_init_csum_hash(struct btrfs_fs_info *fs_info, u16 csum_type)
{
struct crypto_shash *csum_shash;
- const char *csum_name = btrfs_super_csum_name(csum_type);
+ const char *csum_driver = btrfs_super_csum_driver(csum_type);
- csum_shash = crypto_alloc_shash(csum_name, 0, 0);
+ csum_shash = crypto_alloc_shash(csum_driver, 0, 0);
if (IS_ERR(csum_shash)) {
btrfs_err(fs_info, "error allocating %s hash for checksum",
- csum_name);
+ csum_driver);
return PTR_ERR(csum_shash);
}
@@ -2595,7 +2524,101 @@ out:
return ret;
}
-int open_ctree(struct super_block *sb,
+static int __cold init_tree_roots(struct btrfs_fs_info *fs_info)
+{
+ int backup_index = find_newest_super_backup(fs_info);
+ struct btrfs_super_block *sb = fs_info->super_copy;
+ struct btrfs_root *tree_root = fs_info->tree_root;
+ bool handle_error = false;
+ int ret = 0;
+ int i;
+
+ for (i = 0; i < BTRFS_NUM_BACKUP_ROOTS; i++) {
+ u64 generation;
+ int level;
+
+ if (handle_error) {
+ if (!IS_ERR(tree_root->node))
+ free_extent_buffer(tree_root->node);
+ tree_root->node = NULL;
+
+ if (!btrfs_test_opt(fs_info, USEBACKUPROOT))
+ break;
+
+ free_root_pointers(fs_info, 0);
+
+ /*
+ * Don't use the log in recovery mode, it won't be
+ * valid
+ */
+ btrfs_set_super_log_root(sb, 0);
+
+ /* We can't trust the free space cache either */
+ btrfs_set_opt(fs_info->mount_opt, CLEAR_CACHE);
+
+ ret = read_backup_root(fs_info, i);
+ backup_index = ret;
+ if (ret < 0)
+ return ret;
+ }
+ generation = btrfs_super_generation(sb);
+ level = btrfs_super_root_level(sb);
+ tree_root->node = read_tree_block(fs_info, btrfs_super_root(sb),
+ generation, level, NULL);
+ if (IS_ERR(tree_root->node) ||
+ !extent_buffer_uptodate(tree_root->node)) {
+ handle_error = true;
+
+ if (IS_ERR(tree_root->node))
+ ret = PTR_ERR(tree_root->node);
+ else if (!extent_buffer_uptodate(tree_root->node))
+ ret = -EUCLEAN;
+
+ btrfs_warn(fs_info, "failed to read tree root");
+ continue;
+ }
+
+ btrfs_set_root_node(&tree_root->root_item, tree_root->node);
+ tree_root->commit_root = btrfs_root_node(tree_root);
+ btrfs_set_root_refs(&tree_root->root_item, 1);
+
+ /*
+ * No need to hold btrfs_root::objectid_mutex since the fs
+ * hasn't been fully initialised and we are the only user
+ */
+ ret = btrfs_find_highest_objectid(tree_root,
+ &tree_root->highest_objectid);
+ if (ret < 0) {
+ handle_error = true;
+ continue;
+ }
+
+ ASSERT(tree_root->highest_objectid <= BTRFS_LAST_FREE_OBJECTID);
+
+ ret = btrfs_read_roots(fs_info);
+ if (ret < 0) {
+ handle_error = true;
+ continue;
+ }
+
+ /* All successful */
+ fs_info->generation = generation;
+ fs_info->last_trans_committed = generation;
+
+ /* Always begin writing backup roots after the one being used */
+ if (backup_index < 0) {
+ fs_info->backup_root_index = 0;
+ } else {
+ fs_info->backup_root_index = backup_index + 1;
+ fs_info->backup_root_index %= BTRFS_NUM_BACKUP_ROOTS;
+ }
+ break;
+ }
+
+ return ret;
+}
+
+int __cold open_ctree(struct super_block *sb,
struct btrfs_fs_devices *fs_devices,
char *options)
{
@@ -2613,8 +2636,6 @@ int open_ctree(struct super_block *sb,
struct btrfs_root *chunk_root;
int ret;
int err = -EINVAL;
- int num_backups_tried = 0;
- int backup_index = 0;
int clear_free_space_tree = 0;
int level;
@@ -2885,13 +2906,6 @@ int open_ctree(struct super_block *sb,
set_bit(BTRFS_FS_STATE_ERROR, &fs_info->fs_state);
/*
- * run through our array of backup supers and setup
- * our ring pointer to the oldest one
- */
- generation = btrfs_super_generation(disk_super);
- find_oldest_super_backup(fs_info, generation);
-
- /*
* In the long term, we'll store the compression type in the super
* block, and it'll be used for per file compression control.
*/
@@ -3037,44 +3051,9 @@ int open_ctree(struct super_block *sb,
goto fail_tree_roots;
}
-retry_root_backup:
- generation = btrfs_super_generation(disk_super);
- level = btrfs_super_root_level(disk_super);
-
- tree_root->node = read_tree_block(fs_info,
- btrfs_super_root(disk_super),
- generation, level, NULL);
- if (IS_ERR(tree_root->node) ||
- !extent_buffer_uptodate(tree_root->node)) {
- btrfs_warn(fs_info, "failed to read tree root");
- if (!IS_ERR(tree_root->node))
- free_extent_buffer(tree_root->node);
- tree_root->node = NULL;
- goto recovery_tree_root;
- }
-
- btrfs_set_root_node(&tree_root->root_item, tree_root->node);
- tree_root->commit_root = btrfs_root_node(tree_root);
- btrfs_set_root_refs(&tree_root->root_item, 1);
-
- mutex_lock(&tree_root->objectid_mutex);
- ret = btrfs_find_highest_objectid(tree_root,
- &tree_root->highest_objectid);
- if (ret) {
- mutex_unlock(&tree_root->objectid_mutex);
- goto recovery_tree_root;
- }
-
- ASSERT(tree_root->highest_objectid <= BTRFS_LAST_FREE_OBJECTID);
-
- mutex_unlock(&tree_root->objectid_mutex);
-
- ret = btrfs_read_roots(fs_info);
+ ret = init_tree_roots(fs_info);
if (ret)
- goto recovery_tree_root;
-
- fs_info->generation = generation;
- fs_info->last_trans_committed = generation;
+ goto fail_tree_roots;
ret = btrfs_verify_dev_extents(fs_info);
if (ret) {
@@ -3342,7 +3321,7 @@ fail_block_groups:
btrfs_put_block_group_cache(fs_info);
fail_tree_roots:
- free_root_pointers(fs_info, 1);
+ free_root_pointers(fs_info, true);
invalidate_inode_pages2(fs_info->btree_inode->i_mapping);
fail_sb_buffer:
@@ -3369,24 +3348,6 @@ fail:
btrfs_free_stripe_hash_table(fs_info);
btrfs_close_devices(fs_info->fs_devices);
return err;
-
-recovery_tree_root:
- if (!btrfs_test_opt(fs_info, USEBACKUPROOT))
- goto fail_tree_roots;
-
- free_root_pointers(fs_info, 0);
-
- /* don't use the log in recovery mode, it won't be valid */
- btrfs_set_super_log_root(disk_super, 0);
-
- /* we can't trust the free space cache either */
- btrfs_set_opt(fs_info->mount_opt, CLEAR_CACHE);
-
- ret = next_root_backup(fs_info, fs_info->super_copy,
- &num_backups_tried, &backup_index);
- if (ret == -1)
- goto fail_block_groups;
- goto retry_root_backup;
}
ALLOW_ERROR_INJECTION(open_ctree, ERRNO);
@@ -3980,7 +3941,7 @@ int btrfs_commit_super(struct btrfs_fs_info *fs_info)
return btrfs_commit_transaction(trans);
}
-void close_ctree(struct btrfs_fs_info *fs_info)
+void __cold close_ctree(struct btrfs_fs_info *fs_info)
{
int ret;
@@ -4068,7 +4029,7 @@ void close_ctree(struct btrfs_fs_info *fs_info)
btrfs_free_block_groups(fs_info);
clear_bit(BTRFS_FS_OPEN, &fs_info->flags);
- free_root_pointers(fs_info, 1);
+ free_root_pointers(fs_info, true);
iput(fs_info->btree_inode);
@@ -4445,7 +4406,7 @@ again:
return 0;
}
-static void btrfs_cleanup_bg_io(struct btrfs_block_group_cache *cache)
+static void btrfs_cleanup_bg_io(struct btrfs_block_group *cache)
{
struct inode *inode;
@@ -4462,12 +4423,12 @@ static void btrfs_cleanup_bg_io(struct btrfs_block_group_cache *cache)
void btrfs_cleanup_dirty_bgs(struct btrfs_transaction *cur_trans,
struct btrfs_fs_info *fs_info)
{
- struct btrfs_block_group_cache *cache;
+ struct btrfs_block_group *cache;
spin_lock(&cur_trans->dirty_bgs_lock);
while (!list_empty(&cur_trans->dirty_bgs)) {
cache = list_first_entry(&cur_trans->dirty_bgs,
- struct btrfs_block_group_cache,
+ struct btrfs_block_group,
dirty_list);
if (!list_empty(&cache->io_list)) {
@@ -4495,7 +4456,7 @@ void btrfs_cleanup_dirty_bgs(struct btrfs_transaction *cur_trans,
*/
while (!list_empty(&cur_trans->io_bgs)) {
cache = list_first_entry(&cur_trans->io_bgs,
- struct btrfs_block_group_cache,
+ struct btrfs_block_group,
io_list);
list_del_init(&cache->io_list);
diff --git a/fs/btrfs/disk-io.h b/fs/btrfs/disk-io.h
index a6958103d87e..76f123ebb292 100644
--- a/fs/btrfs/disk-io.h
+++ b/fs/btrfs/disk-io.h
@@ -49,10 +49,10 @@ struct extent_buffer *btrfs_find_create_tree_block(
struct btrfs_fs_info *fs_info,
u64 bytenr);
void btrfs_clean_tree_block(struct extent_buffer *buf);
-int open_ctree(struct super_block *sb,
+int __cold open_ctree(struct super_block *sb,
struct btrfs_fs_devices *fs_devices,
char *options);
-void close_ctree(struct btrfs_fs_info *fs_info);
+void __cold close_ctree(struct btrfs_fs_info *fs_info);
int write_all_supers(struct btrfs_fs_info *fs_info, int max_mirrors);
struct buffer_head *btrfs_read_dev_super(struct block_device *bdev);
int btrfs_read_dev_one_super(struct block_device *bdev, int copy_num,
diff --git a/fs/btrfs/export.c b/fs/btrfs/export.c
index ddf28ecf17f9..72e312cae69d 100644
--- a/fs/btrfs/export.c
+++ b/fs/btrfs/export.c
@@ -87,7 +87,7 @@ static struct dentry *btrfs_get_dentry(struct super_block *sb, u64 objectid,
key.type = BTRFS_INODE_ITEM_KEY;
key.offset = 0;
- inode = btrfs_iget(sb, &key, root, NULL);
+ inode = btrfs_iget(sb, &key, root);
if (IS_ERR(inode)) {
err = PTR_ERR(inode);
goto fail;
@@ -214,7 +214,7 @@ static struct dentry *btrfs_get_parent(struct dentry *child)
key.type = BTRFS_INODE_ITEM_KEY;
key.offset = 0;
- return d_obtain_alias(btrfs_iget(fs_info->sb, &key, root, NULL));
+ return d_obtain_alias(btrfs_iget(fs_info->sb, &key, root));
fail:
btrfs_free_path(path);
return ERR_PTR(ret);
diff --git a/fs/btrfs/extent-io-tree.h b/fs/btrfs/extent-io-tree.h
new file mode 100644
index 000000000000..a3febe746c79
--- /dev/null
+++ b/fs/btrfs/extent-io-tree.h
@@ -0,0 +1,248 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef BTRFS_EXTENT_IO_TREE_H
+#define BTRFS_EXTENT_IO_TREE_H
+
+struct extent_changeset;
+struct io_failure_record;
+
+/* Bits for the extent state */
+#define EXTENT_DIRTY (1U << 0)
+#define EXTENT_UPTODATE (1U << 1)
+#define EXTENT_LOCKED (1U << 2)
+#define EXTENT_NEW (1U << 3)
+#define EXTENT_DELALLOC (1U << 4)
+#define EXTENT_DEFRAG (1U << 5)
+#define EXTENT_BOUNDARY (1U << 6)
+#define EXTENT_NODATASUM (1U << 7)
+#define EXTENT_CLEAR_META_RESV (1U << 8)
+#define EXTENT_NEED_WAIT (1U << 9)
+#define EXTENT_DAMAGED (1U << 10)
+#define EXTENT_NORESERVE (1U << 11)
+#define EXTENT_QGROUP_RESERVED (1U << 12)
+#define EXTENT_CLEAR_DATA_RESV (1U << 13)
+#define EXTENT_DELALLOC_NEW (1U << 14)
+#define EXTENT_DO_ACCOUNTING (EXTENT_CLEAR_META_RESV | \
+ EXTENT_CLEAR_DATA_RESV)
+#define EXTENT_CTLBITS (EXTENT_DO_ACCOUNTING)
+
+/*
+ * Redefined bits above which are used only in the device allocation tree,
+ * shouldn't be using EXTENT_LOCKED / EXTENT_BOUNDARY / EXTENT_CLEAR_META_RESV
+ * / EXTENT_CLEAR_DATA_RESV because they have special meaning to the bit
+ * manipulation functions
+ */
+#define CHUNK_ALLOCATED EXTENT_DIRTY
+#define CHUNK_TRIMMED EXTENT_DEFRAG
+
+enum {
+ IO_TREE_FS_INFO_FREED_EXTENTS0,
+ IO_TREE_FS_INFO_FREED_EXTENTS1,
+ IO_TREE_INODE_IO,
+ IO_TREE_INODE_IO_FAILURE,
+ IO_TREE_RELOC_BLOCKS,
+ IO_TREE_TRANS_DIRTY_PAGES,
+ IO_TREE_ROOT_DIRTY_LOG_PAGES,
+ IO_TREE_SELFTEST,
+};
+
+struct extent_io_tree {
+ struct rb_root state;
+ struct btrfs_fs_info *fs_info;
+ void *private_data;
+ u64 dirty_bytes;
+ bool track_uptodate;
+
+ /* Who owns this io tree, should be one of IO_TREE_* */
+ u8 owner;
+
+ spinlock_t lock;
+ const struct extent_io_ops *ops;
+};
+
+struct extent_state {
+ u64 start;
+ u64 end; /* inclusive */
+ struct rb_node rb_node;
+
+ /* ADD NEW ELEMENTS AFTER THIS */
+ wait_queue_head_t wq;
+ refcount_t refs;
+ unsigned state;
+
+ struct io_failure_record *failrec;
+
+#ifdef CONFIG_BTRFS_DEBUG
+ struct list_head leak_list;
+#endif
+};
+
+int __init extent_state_cache_init(void);
+void __cold extent_state_cache_exit(void);
+
+void extent_io_tree_init(struct btrfs_fs_info *fs_info,
+ struct extent_io_tree *tree, unsigned int owner,
+ void *private_data);
+void extent_io_tree_release(struct extent_io_tree *tree);
+
+int lock_extent_bits(struct extent_io_tree *tree, u64 start, u64 end,
+ struct extent_state **cached);
+
+static inline int lock_extent(struct extent_io_tree *tree, u64 start, u64 end)
+{
+ return lock_extent_bits(tree, start, end, NULL);
+}
+
+int try_lock_extent(struct extent_io_tree *tree, u64 start, u64 end);
+
+int __init extent_io_init(void);
+void __cold extent_io_exit(void);
+
+u64 count_range_bits(struct extent_io_tree *tree,
+ u64 *start, u64 search_end,
+ u64 max_bytes, unsigned bits, int contig);
+
+void free_extent_state(struct extent_state *state);
+int test_range_bit(struct extent_io_tree *tree, u64 start, u64 end,
+ unsigned bits, int filled,
+ struct extent_state *cached_state);
+int clear_record_extent_bits(struct extent_io_tree *tree, u64 start, u64 end,
+ unsigned bits, struct extent_changeset *changeset);
+int clear_extent_bit(struct extent_io_tree *tree, u64 start, u64 end,
+ unsigned bits, int wake, int delete,
+ struct extent_state **cached);
+int __clear_extent_bit(struct extent_io_tree *tree, u64 start, u64 end,
+ unsigned bits, int wake, int delete,
+ struct extent_state **cached, gfp_t mask,
+ struct extent_changeset *changeset);
+
+static inline int unlock_extent(struct extent_io_tree *tree, u64 start, u64 end)
+{
+ return clear_extent_bit(tree, start, end, EXTENT_LOCKED, 1, 0, NULL);
+}
+
+static inline int unlock_extent_cached(struct extent_io_tree *tree, u64 start,
+ u64 end, struct extent_state **cached)
+{
+ return __clear_extent_bit(tree, start, end, EXTENT_LOCKED, 1, 0, cached,
+ GFP_NOFS, NULL);
+}
+
+static inline int unlock_extent_cached_atomic(struct extent_io_tree *tree,
+ u64 start, u64 end, struct extent_state **cached)
+{
+ return __clear_extent_bit(tree, start, end, EXTENT_LOCKED, 1, 0, cached,
+ GFP_ATOMIC, NULL);
+}
+
+static inline int clear_extent_bits(struct extent_io_tree *tree, u64 start,
+ u64 end, unsigned bits)
+{
+ int wake = 0;
+
+ if (bits & EXTENT_LOCKED)
+ wake = 1;
+
+ return clear_extent_bit(tree, start, end, bits, wake, 0, NULL);
+}
+
+int set_record_extent_bits(struct extent_io_tree *tree, u64 start, u64 end,
+ unsigned bits, struct extent_changeset *changeset);
+int set_extent_bit(struct extent_io_tree *tree, u64 start, u64 end,
+ unsigned bits, u64 *failed_start,
+ struct extent_state **cached_state, gfp_t mask);
+int set_extent_bits_nowait(struct extent_io_tree *tree, u64 start, u64 end,
+ unsigned bits);
+
+static inline int set_extent_bits(struct extent_io_tree *tree, u64 start,
+ u64 end, unsigned bits)
+{
+ return set_extent_bit(tree, start, end, bits, NULL, NULL, GFP_NOFS);
+}
+
+static inline int clear_extent_uptodate(struct extent_io_tree *tree, u64 start,
+ u64 end, struct extent_state **cached_state)
+{
+ return __clear_extent_bit(tree, start, end, EXTENT_UPTODATE, 0, 0,
+ cached_state, GFP_NOFS, NULL);
+}
+
+static inline int set_extent_dirty(struct extent_io_tree *tree, u64 start,
+ u64 end, gfp_t mask)
+{
+ return set_extent_bit(tree, start, end, EXTENT_DIRTY, NULL,
+ NULL, mask);
+}
+
+static inline int clear_extent_dirty(struct extent_io_tree *tree, u64 start,
+ u64 end, struct extent_state **cached)
+{
+ return clear_extent_bit(tree, start, end,
+ EXTENT_DIRTY | EXTENT_DELALLOC |
+ EXTENT_DO_ACCOUNTING, 0, 0, cached);
+}
+
+int convert_extent_bit(struct extent_io_tree *tree, u64 start, u64 end,
+ unsigned bits, unsigned clear_bits,
+ struct extent_state **cached_state);
+
+static inline int set_extent_delalloc(struct extent_io_tree *tree, u64 start,
+ u64 end, unsigned int extra_bits,
+ struct extent_state **cached_state)
+{
+ return set_extent_bit(tree, start, end,
+ EXTENT_DELALLOC | EXTENT_UPTODATE | extra_bits,
+ NULL, cached_state, GFP_NOFS);
+}
+
+static inline int set_extent_defrag(struct extent_io_tree *tree, u64 start,
+ u64 end, struct extent_state **cached_state)
+{
+ return set_extent_bit(tree, start, end,
+ EXTENT_DELALLOC | EXTENT_UPTODATE | EXTENT_DEFRAG,
+ NULL, cached_state, GFP_NOFS);
+}
+
+static inline int set_extent_new(struct extent_io_tree *tree, u64 start,
+ u64 end)
+{
+ return set_extent_bit(tree, start, end, EXTENT_NEW, NULL, NULL,
+ GFP_NOFS);
+}
+
+static inline int set_extent_uptodate(struct extent_io_tree *tree, u64 start,
+ u64 end, struct extent_state **cached_state, gfp_t mask)
+{
+ return set_extent_bit(tree, start, end, EXTENT_UPTODATE, NULL,
+ cached_state, mask);
+}
+
+int find_first_extent_bit(struct extent_io_tree *tree, u64 start,
+ u64 *start_ret, u64 *end_ret, unsigned bits,
+ struct extent_state **cached_state);
+void find_first_clear_extent_bit(struct extent_io_tree *tree, u64 start,
+ u64 *start_ret, u64 *end_ret, unsigned bits);
+int extent_invalidatepage(struct extent_io_tree *tree,
+ struct page *page, unsigned long offset);
+bool btrfs_find_delalloc_range(struct extent_io_tree *tree, u64 *start,
+ u64 *end, u64 max_bytes,
+ struct extent_state **cached_state);
+
+/* This should be reworked in the future and put elsewhere. */
+int get_state_failrec(struct extent_io_tree *tree, u64 start,
+ struct io_failure_record **failrec);
+int set_state_failrec(struct extent_io_tree *tree, u64 start,
+ struct io_failure_record *failrec);
+void btrfs_free_io_failure_record(struct btrfs_inode *inode, u64 start,
+ u64 end);
+int btrfs_get_io_failure_record(struct inode *inode, u64 start, u64 end,
+ struct io_failure_record **failrec_ret);
+int free_io_failure(struct extent_io_tree *failure_tree,
+ struct extent_io_tree *io_tree,
+ struct io_failure_record *rec);
+int clean_io_failure(struct btrfs_fs_info *fs_info,
+ struct extent_io_tree *failure_tree,
+ struct extent_io_tree *io_tree, u64 start,
+ struct page *page, u64 ino, unsigned int pg_offset);
+
+#endif /* BTRFS_EXTENT_IO_TREE_H */
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 49cb26fa7c63..153f71a5bba9 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -54,7 +54,7 @@ static int alloc_reserved_tree_block(struct btrfs_trans_handle *trans,
static int find_next_key(struct btrfs_path *path, int level,
struct btrfs_key *key);
-static int block_group_bits(struct btrfs_block_group_cache *cache, u64 bits)
+static int block_group_bits(struct btrfs_block_group *cache, u64 bits)
{
return (cache->flags & bits) == bits;
}
@@ -70,13 +70,13 @@ int btrfs_add_excluded_extent(struct btrfs_fs_info *fs_info,
return 0;
}
-void btrfs_free_excluded_extents(struct btrfs_block_group_cache *cache)
+void btrfs_free_excluded_extents(struct btrfs_block_group *cache)
{
struct btrfs_fs_info *fs_info = cache->fs_info;
u64 start, end;
- start = cache->key.objectid;
- end = start + cache->key.offset - 1;
+ start = cache->start;
+ end = start + cache->length - 1;
clear_extent_bits(&fs_info->freed_extents[0],
start, end, EXTENT_UPTODATE);
@@ -1306,8 +1306,10 @@ static int btrfs_issue_discard(struct block_device *bdev, u64 start, u64 len,
int btrfs_discard_extent(struct btrfs_fs_info *fs_info, u64 bytenr,
u64 num_bytes, u64 *actual_bytes)
{
- int ret;
+ int ret = 0;
u64 discarded_bytes = 0;
+ u64 end = bytenr + num_bytes;
+ u64 cur = bytenr;
struct btrfs_bio *bbio = NULL;
@@ -1316,15 +1318,23 @@ int btrfs_discard_extent(struct btrfs_fs_info *fs_info, u64 bytenr,
* associated to its stripes that don't go away while we are discarding.
*/
btrfs_bio_counter_inc_blocked(fs_info);
- /* Tell the block device(s) that the sectors can be discarded */
- ret = btrfs_map_block(fs_info, BTRFS_MAP_DISCARD, bytenr, &num_bytes,
- &bbio, 0);
- /* Error condition is -ENOMEM */
- if (!ret) {
- struct btrfs_bio_stripe *stripe = bbio->stripes;
+ while (cur < end) {
+ struct btrfs_bio_stripe *stripe;
int i;
+ num_bytes = end - cur;
+ /* Tell the block device(s) that the sectors can be discarded */
+ ret = btrfs_map_block(fs_info, BTRFS_MAP_DISCARD, cur,
+ &num_bytes, &bbio, 0);
+ /*
+ * Error can be -ENOMEM, -ENOENT (no such chunk mapping) or
+ * -EOPNOTSUPP. For any such error, @num_bytes is not updated,
+ * thus we can't continue anyway.
+ */
+ if (ret < 0)
+ goto out;
+ stripe = bbio->stripes;
for (i = 0; i < bbio->num_stripes; i++, stripe++) {
u64 bytes;
struct request_queue *req_q;
@@ -1341,10 +1351,19 @@ int btrfs_discard_extent(struct btrfs_fs_info *fs_info, u64 bytenr,
stripe->physical,
stripe->length,
&bytes);
- if (!ret)
+ if (!ret) {
discarded_bytes += bytes;
- else if (ret != -EOPNOTSUPP)
- break; /* Logic errors or -ENOMEM, or -EIO but I don't know how that could happen JDM */
+ } else if (ret != -EOPNOTSUPP) {
+ /*
+ * Logic errors or -ENOMEM, or -EIO, but
+ * unlikely to happen.
+ *
+ * And since there are two loops, explicitly
+ * go to out to avoid confusion.
+ */
+ btrfs_put_bbio(bbio);
+ goto out;
+ }
/*
* Just in case we get back EOPNOTSUPP for some reason,
@@ -1354,7 +1373,9 @@ int btrfs_discard_extent(struct btrfs_fs_info *fs_info, u64 bytenr,
ret = 0;
}
btrfs_put_bbio(bbio);
+ cur += num_bytes;
}
+out:
btrfs_bio_counter_dec(fs_info);
if (actual_bytes)
@@ -2516,7 +2537,7 @@ int btrfs_dec_ref(struct btrfs_trans_handle *trans, struct btrfs_root *root,
int btrfs_extent_readonly(struct btrfs_fs_info *fs_info, u64 bytenr)
{
- struct btrfs_block_group_cache *block_group;
+ struct btrfs_block_group *block_group;
int readonly = 0;
block_group = btrfs_lookup_block_group(fs_info, bytenr);
@@ -2546,7 +2567,7 @@ static u64 get_alloc_profile_by_root(struct btrfs_root *root, int data)
static u64 first_logical_byte(struct btrfs_fs_info *fs_info, u64 search_start)
{
- struct btrfs_block_group_cache *cache;
+ struct btrfs_block_group *cache;
u64 bytenr;
spin_lock(&fs_info->block_group_cache_lock);
@@ -2560,13 +2581,13 @@ static u64 first_logical_byte(struct btrfs_fs_info *fs_info, u64 search_start)
if (!cache)
return 0;
- bytenr = cache->key.objectid;
+ bytenr = cache->start;
btrfs_put_block_group(cache);
return bytenr;
}
-static int pin_down_extent(struct btrfs_block_group_cache *cache,
+static int pin_down_extent(struct btrfs_block_group *cache,
u64 bytenr, u64 num_bytes, int reserved)
{
struct btrfs_fs_info *fs_info = cache->fs_info;
@@ -2590,13 +2611,12 @@ static int pin_down_extent(struct btrfs_block_group_cache *cache,
return 0;
}
-/*
- * this function must be called within transaction
- */
int btrfs_pin_extent(struct btrfs_fs_info *fs_info,
u64 bytenr, u64 num_bytes, int reserved)
{
- struct btrfs_block_group_cache *cache;
+ struct btrfs_block_group *cache;
+
+ ASSERT(fs_info->running_transaction);
cache = btrfs_lookup_block_group(fs_info, bytenr);
BUG_ON(!cache); /* Logic error */
@@ -2613,7 +2633,7 @@ int btrfs_pin_extent(struct btrfs_fs_info *fs_info,
int btrfs_pin_extent_for_log_replay(struct btrfs_fs_info *fs_info,
u64 bytenr, u64 num_bytes)
{
- struct btrfs_block_group_cache *cache;
+ struct btrfs_block_group *cache;
int ret;
cache = btrfs_lookup_block_group(fs_info, bytenr);
@@ -2640,7 +2660,7 @@ static int __exclude_logged_extent(struct btrfs_fs_info *fs_info,
u64 start, u64 num_bytes)
{
int ret;
- struct btrfs_block_group_cache *block_group;
+ struct btrfs_block_group *block_group;
struct btrfs_caching_control *caching_ctl;
block_group = btrfs_lookup_block_group(fs_info, start);
@@ -2652,7 +2672,7 @@ static int __exclude_logged_extent(struct btrfs_fs_info *fs_info,
if (!caching_ctl) {
/* Logic error */
- BUG_ON(!btrfs_block_group_cache_done(block_group));
+ BUG_ON(!btrfs_block_group_done(block_group));
ret = btrfs_remove_free_space(block_group, start, num_bytes);
} else {
mutex_lock(&caching_ctl->mutex);
@@ -2717,7 +2737,7 @@ int btrfs_exclude_logged_extents(struct extent_buffer *eb)
}
static void
-btrfs_inc_block_group_reservations(struct btrfs_block_group_cache *bg)
+btrfs_inc_block_group_reservations(struct btrfs_block_group *bg)
{
atomic_inc(&bg->reservations);
}
@@ -2726,14 +2746,14 @@ void btrfs_prepare_extent_commit(struct btrfs_fs_info *fs_info)
{
struct btrfs_caching_control *next;
struct btrfs_caching_control *caching_ctl;
- struct btrfs_block_group_cache *cache;
+ struct btrfs_block_group *cache;
down_write(&fs_info->commit_root_sem);
list_for_each_entry_safe(caching_ctl, next,
&fs_info->caching_block_groups, list) {
cache = caching_ctl->block_group;
- if (btrfs_block_group_cache_done(cache)) {
+ if (btrfs_block_group_done(cache)) {
cache->last_byte_to_unpin = (u64)-1;
list_del_init(&caching_ctl->list);
btrfs_put_caching_control(caching_ctl);
@@ -2785,7 +2805,7 @@ static int unpin_extent_range(struct btrfs_fs_info *fs_info,
u64 start, u64 end,
const bool return_free_space)
{
- struct btrfs_block_group_cache *cache = NULL;
+ struct btrfs_block_group *cache = NULL;
struct btrfs_space_info *space_info;
struct btrfs_block_rsv *global_rsv = &fs_info->global_block_rsv;
struct btrfs_free_cluster *cluster = NULL;
@@ -2797,7 +2817,7 @@ static int unpin_extent_range(struct btrfs_fs_info *fs_info,
while (start <= end) {
readonly = false;
if (!cache ||
- start >= cache->key.objectid + cache->key.offset) {
+ start >= cache->start + cache->length) {
if (cache)
btrfs_put_block_group(cache);
total_unpinned = 0;
@@ -2810,7 +2830,7 @@ static int unpin_extent_range(struct btrfs_fs_info *fs_info,
empty_cluster <<= 1;
}
- len = cache->key.objectid + cache->key.offset - start;
+ len = cache->start + cache->length - start;
len = min(len, end + 1 - start);
if (start < cache->last_byte_to_unpin) {
@@ -2880,7 +2900,7 @@ static int unpin_extent_range(struct btrfs_fs_info *fs_info,
int btrfs_finish_extent_commit(struct btrfs_trans_handle *trans)
{
struct btrfs_fs_info *fs_info = trans->fs_info;
- struct btrfs_block_group_cache *block_group, *tmp;
+ struct btrfs_block_group *block_group, *tmp;
struct list_head *deleted_bgs;
struct extent_io_tree *unpin;
u64 start;
@@ -2926,8 +2946,8 @@ int btrfs_finish_extent_commit(struct btrfs_trans_handle *trans)
ret = -EROFS;
if (!trans->aborted)
ret = btrfs_discard_extent(fs_info,
- block_group->key.objectid,
- block_group->key.offset,
+ block_group->start,
+ block_group->length,
&trimmed);
list_del_init(&block_group->bg_list);
@@ -3262,7 +3282,7 @@ void btrfs_free_tree_block(struct btrfs_trans_handle *trans,
}
if (last_ref && btrfs_header_generation(buf) == trans->transid) {
- struct btrfs_block_group_cache *cache;
+ struct btrfs_block_group *cache;
if (root->root_key.objectid != BTRFS_TREE_LOG_OBJECTID) {
ret = check_ref_cleanup(trans, buf->start);
@@ -3349,15 +3369,14 @@ enum btrfs_loop_type {
};
static inline void
-btrfs_lock_block_group(struct btrfs_block_group_cache *cache,
+btrfs_lock_block_group(struct btrfs_block_group *cache,
int delalloc)
{
if (delalloc)
down_read(&cache->data_rwsem);
}
-static inline void
-btrfs_grab_block_group(struct btrfs_block_group_cache *cache,
+static inline void btrfs_grab_block_group(struct btrfs_block_group *cache,
int delalloc)
{
btrfs_get_block_group(cache);
@@ -3365,12 +3384,12 @@ btrfs_grab_block_group(struct btrfs_block_group_cache *cache,
down_read(&cache->data_rwsem);
}
-static struct btrfs_block_group_cache *
-btrfs_lock_cluster(struct btrfs_block_group_cache *block_group,
+static struct btrfs_block_group *btrfs_lock_cluster(
+ struct btrfs_block_group *block_group,
struct btrfs_free_cluster *cluster,
int delalloc)
{
- struct btrfs_block_group_cache *used_bg = NULL;
+ struct btrfs_block_group *used_bg = NULL;
spin_lock(&cluster->refill_lock);
while (1) {
@@ -3404,7 +3423,7 @@ btrfs_lock_cluster(struct btrfs_block_group_cache *block_group,
}
static inline void
-btrfs_release_block_group(struct btrfs_block_group_cache *cache,
+btrfs_release_block_group(struct btrfs_block_group *cache,
int delalloc)
{
if (delalloc)
@@ -3475,12 +3494,12 @@ struct find_free_extent_ctl {
* Return >0 to inform caller that we find nothing
* Return 0 means we have found a location and set ffe_ctl->found_offset.
*/
-static int find_free_extent_clustered(struct btrfs_block_group_cache *bg,
+static int find_free_extent_clustered(struct btrfs_block_group *bg,
struct btrfs_free_cluster *last_ptr,
struct find_free_extent_ctl *ffe_ctl,
- struct btrfs_block_group_cache **cluster_bg_ret)
+ struct btrfs_block_group **cluster_bg_ret)
{
- struct btrfs_block_group_cache *cluster_bg;
+ struct btrfs_block_group *cluster_bg;
u64 aligned_cluster;
u64 offset;
int ret;
@@ -3493,7 +3512,7 @@ static int find_free_extent_clustered(struct btrfs_block_group_cache *bg,
goto release_cluster;
offset = btrfs_alloc_from_cluster(cluster_bg, last_ptr,
- ffe_ctl->num_bytes, cluster_bg->key.objectid,
+ ffe_ctl->num_bytes, cluster_bg->start,
&ffe_ctl->max_extent_size);
if (offset) {
/* We have a block, we're done */
@@ -3579,7 +3598,7 @@ refill_cluster:
* Return 0 when we found an free extent and set ffe_ctrl->found_offset
* Return -EAGAIN to inform caller that we need to re-search this block group
*/
-static int find_free_extent_unclustered(struct btrfs_block_group_cache *bg,
+static int find_free_extent_unclustered(struct btrfs_block_group *bg,
struct btrfs_free_cluster *last_ptr,
struct find_free_extent_ctl *ffe_ctl)
{
@@ -3781,7 +3800,7 @@ static noinline int find_free_extent(struct btrfs_fs_info *fs_info,
{
int ret = 0;
struct btrfs_free_cluster *last_ptr = NULL;
- struct btrfs_block_group_cache *block_group = NULL;
+ struct btrfs_block_group *block_group = NULL;
struct find_free_extent_ctl ffe_ctl = {0};
struct btrfs_space_info *space_info;
bool use_cluster = true;
@@ -3904,7 +3923,7 @@ search:
continue;
btrfs_grab_block_group(block_group, delalloc);
- ffe_ctl.search_start = block_group->key.objectid;
+ ffe_ctl.search_start = block_group->start;
/*
* this can happen if we end up cycling through all the
@@ -3935,7 +3954,7 @@ search:
}
have_block_group:
- ffe_ctl.cached = btrfs_block_group_cache_done(block_group);
+ ffe_ctl.cached = btrfs_block_group_done(block_group);
if (unlikely(!ffe_ctl.cached)) {
ffe_ctl.have_caching_bg = true;
ret = btrfs_cache_block_group(block_group, 0);
@@ -3951,7 +3970,7 @@ have_block_group:
* lets look there
*/
if (last_ptr && use_cluster) {
- struct btrfs_block_group_cache *cluster_bg = NULL;
+ struct btrfs_block_group *cluster_bg = NULL;
ret = find_free_extent_clustered(block_group, last_ptr,
&ffe_ctl, &cluster_bg);
@@ -3984,7 +4003,7 @@ checks:
/* move on to the next group */
if (ffe_ctl.search_start + num_bytes >
- block_group->key.objectid + block_group->key.offset) {
+ block_group->start + block_group->length) {
btrfs_add_free_space(block_group, ffe_ctl.found_offset,
num_bytes);
goto loop;
@@ -4133,7 +4152,7 @@ static int __btrfs_free_reserved_extent(struct btrfs_fs_info *fs_info,
u64 start, u64 len,
int pin, int delalloc)
{
- struct btrfs_block_group_cache *cache;
+ struct btrfs_block_group *cache;
int ret = 0;
cache = btrfs_lookup_block_group(fs_info, start);
@@ -4366,7 +4385,7 @@ int btrfs_alloc_logged_file_extent(struct btrfs_trans_handle *trans,
{
struct btrfs_fs_info *fs_info = trans->fs_info;
int ret;
- struct btrfs_block_group_cache *block_group;
+ struct btrfs_block_group *block_group;
struct btrfs_space_info *space_info;
/*
@@ -5436,7 +5455,7 @@ int btrfs_drop_subtree(struct btrfs_trans_handle *trans,
btrfs_assert_tree_locked(parent);
parent_level = btrfs_header_level(parent);
- extent_buffer_get(parent);
+ atomic_inc(&parent->refs);
path->nodes[parent_level] = parent;
path->slots[parent_level] = btrfs_header_nritems(parent);
@@ -5480,7 +5499,7 @@ int btrfs_drop_subtree(struct btrfs_trans_handle *trans,
*/
u64 btrfs_account_ro_block_groups_free_space(struct btrfs_space_info *sinfo)
{
- struct btrfs_block_group_cache *block_group;
+ struct btrfs_block_group *block_group;
u64 free_bytes = 0;
int factor;
@@ -5498,9 +5517,8 @@ u64 btrfs_account_ro_block_groups_free_space(struct btrfs_space_info *sinfo)
}
factor = btrfs_bg_type_to_factor(block_group->flags);
- free_bytes += (block_group->key.offset -
- btrfs_block_group_used(&block_group->item)) *
- factor;
+ free_bytes += (block_group->length -
+ block_group->used) * factor;
spin_unlock(&block_group->lock);
}
@@ -5623,7 +5641,7 @@ static int btrfs_trim_free_extents(struct btrfs_device *device, u64 *trimmed)
*/
int btrfs_trim_fs(struct btrfs_fs_info *fs_info, struct fstrim_range *range)
{
- struct btrfs_block_group_cache *cache = NULL;
+ struct btrfs_block_group *cache = NULL;
struct btrfs_device *device;
struct list_head *devices;
u64 group_trimmed;
@@ -5647,16 +5665,16 @@ int btrfs_trim_fs(struct btrfs_fs_info *fs_info, struct fstrim_range *range)
cache = btrfs_lookup_first_block_group(fs_info, range->start);
for (; cache; cache = btrfs_next_block_group(cache)) {
- if (cache->key.objectid >= range_end) {
+ if (cache->start >= range_end) {
btrfs_put_block_group(cache);
break;
}
- start = max(range->start, cache->key.objectid);
- end = min(range_end, cache->key.objectid + cache->key.offset);
+ start = max(range->start, cache->start);
+ end = min(range_end, cache->start + cache->length);
if (end - start >= range->minlen) {
- if (!btrfs_block_group_cache_done(cache)) {
+ if (!btrfs_block_group_done(cache)) {
ret = btrfs_cache_block_group(cache, 0);
if (ret) {
bg_failed++;
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index cceaf05aada2..eb8bd0258360 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -14,6 +14,7 @@
#include <linux/prefetch.h>
#include <linux/cleancache.h>
#include "extent_io.h"
+#include "extent-io-tree.h"
#include "extent_map.h"
#include "ctree.h"
#include "btrfs_inode.h"
@@ -59,12 +60,23 @@ void btrfs_leak_debug_del(struct list_head *entry)
spin_unlock_irqrestore(&leak_lock, flags);
}
-static inline
-void btrfs_leak_debug_check(void)
+static inline void btrfs_extent_buffer_leak_debug_check(void)
{
- struct extent_state *state;
struct extent_buffer *eb;
+ while (!list_empty(&buffers)) {
+ eb = list_entry(buffers.next, struct extent_buffer, leak_list);
+ pr_err("BTRFS: buffer leak start %llu len %lu refs %d bflags %lu\n",
+ eb->start, eb->len, atomic_read(&eb->refs), eb->bflags);
+ list_del(&eb->leak_list);
+ kmem_cache_free(extent_buffer_cache, eb);
+ }
+}
+
+static inline void btrfs_extent_state_leak_debug_check(void)
+{
+ struct extent_state *state;
+
while (!list_empty(&states)) {
state = list_entry(states.next, struct extent_state, leak_list);
pr_err("BTRFS: state leak: start %llu end %llu state %u in tree %d refs %d\n",
@@ -74,14 +86,6 @@ void btrfs_leak_debug_check(void)
list_del(&state->leak_list);
kmem_cache_free(extent_state_cache, state);
}
-
- while (!list_empty(&buffers)) {
- eb = list_entry(buffers.next, struct extent_buffer, leak_list);
- pr_err("BTRFS: buffer leak start %llu len %lu refs %d bflags %lu\n",
- eb->start, eb->len, atomic_read(&eb->refs), eb->bflags);
- list_del(&eb->leak_list);
- kmem_cache_free(extent_buffer_cache, eb);
- }
}
#define btrfs_debug_check_extent_io_range(tree, start, end) \
@@ -105,7 +109,8 @@ static inline void __btrfs_debug_check_extent_io_range(const char *caller,
#else
#define btrfs_leak_debug_add(new, head) do {} while (0)
#define btrfs_leak_debug_del(entry) do {} while (0)
-#define btrfs_leak_debug_check() do {} while (0)
+#define btrfs_extent_buffer_leak_debug_check() do {} while (0)
+#define btrfs_extent_state_leak_debug_check() do {} while (0)
#define btrfs_debug_check_extent_io_range(c, s, e) do {} while (0)
#endif
@@ -196,19 +201,23 @@ static int __must_check flush_write_bio(struct extent_page_data *epd)
return ret;
}
-int __init extent_io_init(void)
+int __init extent_state_cache_init(void)
{
extent_state_cache = kmem_cache_create("btrfs_extent_state",
sizeof(struct extent_state), 0,
SLAB_MEM_SPREAD, NULL);
if (!extent_state_cache)
return -ENOMEM;
+ return 0;
+}
+int __init extent_io_init(void)
+{
extent_buffer_cache = kmem_cache_create("btrfs_extent_buffer",
sizeof(struct extent_buffer), 0,
SLAB_MEM_SPREAD, NULL);
if (!extent_buffer_cache)
- goto free_state_cache;
+ return -ENOMEM;
if (bioset_init(&btrfs_bioset, BIO_POOL_SIZE,
offsetof(struct btrfs_io_bio, bio),
@@ -226,23 +235,24 @@ free_bioset:
free_buffer_cache:
kmem_cache_destroy(extent_buffer_cache);
extent_buffer_cache = NULL;
+ return -ENOMEM;
+}
-free_state_cache:
+void __cold extent_state_cache_exit(void)
+{
+ btrfs_extent_state_leak_debug_check();
kmem_cache_destroy(extent_state_cache);
- extent_state_cache = NULL;
- return -ENOMEM;
}
void __cold extent_io_exit(void)
{
- btrfs_leak_debug_check();
+ btrfs_extent_buffer_leak_debug_check();
/*
* Make sure all delayed rcu free are flushed before we
* destroy caches.
*/
rcu_barrier();
- kmem_cache_destroy(extent_state_cache);
kmem_cache_destroy(extent_buffer_cache);
bioset_exit(&btrfs_bioset);
}
@@ -1676,9 +1686,9 @@ out:
*
* true is returned if we find something, false if nothing was in the tree
*/
-static noinline bool find_delalloc_range(struct extent_io_tree *tree,
- u64 *start, u64 *end, u64 max_bytes,
- struct extent_state **cached_state)
+bool btrfs_find_delalloc_range(struct extent_io_tree *tree, u64 *start,
+ u64 *end, u64 max_bytes,
+ struct extent_state **cached_state)
{
struct rb_node *node;
struct extent_state *state;
@@ -1796,8 +1806,8 @@ again:
/* step one, find a bunch of delalloc bytes starting at start */
delalloc_start = *start;
delalloc_end = 0;
- found = find_delalloc_range(tree, &delalloc_start, &delalloc_end,
- max_bytes, &cached_state);
+ found = btrfs_find_delalloc_range(tree, &delalloc_start, &delalloc_end,
+ max_bytes, &cached_state);
if (!found || delalloc_end <= *start) {
*start = delalloc_start;
*end = delalloc_end;
@@ -1899,7 +1909,7 @@ static int __process_pages_contig(struct address_space *mapping,
if (page_ops & PAGE_SET_PRIVATE2)
SetPagePrivate2(pages[i]);
- if (pages[i] == locked_page) {
+ if (locked_page && pages[i] == locked_page) {
put_page(pages[i]);
pages_locked++;
continue;
@@ -2014,8 +2024,8 @@ out:
* set the private field for a given byte offset in the tree. If there isn't
* an extent_state there already, this does nothing.
*/
-static noinline int set_state_failrec(struct extent_io_tree *tree, u64 start,
- struct io_failure_record *failrec)
+int set_state_failrec(struct extent_io_tree *tree, u64 start,
+ struct io_failure_record *failrec)
{
struct rb_node *node;
struct extent_state *state;
@@ -2042,8 +2052,8 @@ out:
return ret;
}
-static noinline int get_state_failrec(struct extent_io_tree *tree, u64 start,
- struct io_failure_record **failrec)
+int get_state_failrec(struct extent_io_tree *tree, u64 start,
+ struct io_failure_record **failrec)
{
struct rb_node *node;
struct extent_state *state;
@@ -2534,7 +2544,6 @@ struct bio *btrfs_create_repair_bio(struct inode *inode, struct bio *failed_bio,
bio = btrfs_io_bio_alloc(1);
bio->bi_end_io = endio_func;
bio->bi_iter.bi_sector = failrec->logical >> 9;
- bio_set_dev(bio, fs_info->fs_devices->latest_bdev);
bio->bi_iter.bi_size = 0;
bio->bi_private = data;
@@ -2920,7 +2929,6 @@ struct bio *btrfs_bio_clone_partial(struct bio *orig, int offset, int size)
* a contiguous page to the previous one
* @size: portion of page that we want to write
* @offset: starting offset in the page
- * @bdev: attach newly created bios to this bdev
* @bio_ret: must be valid pointer, newly allocated bio will be stored there
* @end_io_func: end_io callback for new bio
* @mirror_num: desired mirror to read/write
@@ -2931,7 +2939,6 @@ static int submit_extent_page(unsigned int opf, struct extent_io_tree *tree,
struct writeback_control *wbc,
struct page *page, u64 offset,
size_t size, unsigned long pg_offset,
- struct block_device *bdev,
struct bio **bio_ret,
bio_end_io_t end_io_func,
int mirror_num,
@@ -2977,13 +2984,16 @@ static int submit_extent_page(unsigned int opf, struct extent_io_tree *tree,
}
bio = btrfs_bio_alloc(offset);
- bio_set_dev(bio, bdev);
bio_add_page(bio, page, page_size, pg_offset);
bio->bi_end_io = end_io_func;
bio->bi_private = tree;
bio->bi_write_hint = page->mapping->host->i_write_hint;
bio->bi_opf = opf;
if (wbc) {
+ struct block_device *bdev;
+
+ bdev = BTRFS_I(page->mapping->host)->root->fs_info->fs_devices->latest_bdev;
+ bio_set_dev(bio, bdev);
wbc_init_bio(wbc, bio);
wbc_account_cgroup_owner(wbc, page, page_size);
}
@@ -3065,7 +3075,6 @@ static int __do_readpage(struct extent_io_tree *tree,
u64 block_start;
u64 cur_end;
struct extent_map *em;
- struct block_device *bdev;
int ret = 0;
int nr = 0;
size_t pg_offset = 0;
@@ -3142,7 +3151,6 @@ static int __do_readpage(struct extent_io_tree *tree,
offset = em->block_start + extent_offset;
disk_io_size = iosize;
}
- bdev = em->bdev;
block_start = em->block_start;
if (test_bit(EXTENT_FLAG_PREALLOC, &em->flags))
block_start = EXTENT_MAP_HOLE;
@@ -3232,7 +3240,7 @@ static int __do_readpage(struct extent_io_tree *tree,
ret = submit_extent_page(REQ_OP_READ | read_flags, tree, NULL,
page, offset, disk_io_size,
- pg_offset, bdev, bio,
+ pg_offset, bio,
end_bio_extent_readpage, mirror_num,
*bio_flags,
this_bio_flag,
@@ -3409,7 +3417,7 @@ static noinline_for_stack int __extent_writepage_io(struct inode *inode,
struct extent_page_data *epd,
loff_t i_size,
unsigned long nr_written,
- unsigned int write_flags, int *nr_ret)
+ int *nr_ret)
{
struct extent_io_tree *tree = epd->tree;
u64 start = page_offset(page);
@@ -3420,11 +3428,11 @@ static noinline_for_stack int __extent_writepage_io(struct inode *inode,
u64 block_start;
u64 iosize;
struct extent_map *em;
- struct block_device *bdev;
size_t pg_offset = 0;
size_t blocksize;
int ret = 0;
int nr = 0;
+ const unsigned int write_flags = wbc_to_write_flags(wbc);
bool compressed;
ret = btrfs_writepage_cow_fixup(page, start, page_end);
@@ -3478,7 +3486,6 @@ static noinline_for_stack int __extent_writepage_io(struct inode *inode,
iosize = min(em_end - cur, end - cur + 1);
iosize = ALIGN(iosize, blocksize);
offset = em->block_start + extent_offset;
- bdev = em->bdev;
block_start = em->block_start;
compressed = test_bit(EXTENT_FLAG_COMPRESSED, &em->flags);
free_extent_map(em);
@@ -3520,7 +3527,7 @@ static noinline_for_stack int __extent_writepage_io(struct inode *inode,
ret = submit_extent_page(REQ_OP_WRITE | write_flags, tree, wbc,
page, offset, iosize, pg_offset,
- bdev, &epd->bio,
+ &epd->bio,
end_bio_extent_writepage,
0, 0, 0, false);
if (ret) {
@@ -3558,11 +3565,8 @@ static int __extent_writepage(struct page *page, struct writeback_control *wbc,
size_t pg_offset = 0;
loff_t i_size = i_size_read(inode);
unsigned long end_index = i_size >> PAGE_SHIFT;
- unsigned int write_flags = 0;
unsigned long nr_written = 0;
- write_flags = wbc_to_write_flags(wbc);
-
trace___extent_writepage(page, inode, wbc);
WARN_ON(!PageLocked(page));
@@ -3600,7 +3604,7 @@ static int __extent_writepage(struct page *page, struct writeback_control *wbc,
}
ret = __extent_writepage_io(inode, page, wbc, epd,
- i_size, nr_written, write_flags, &nr);
+ i_size, nr_written, &nr);
if (ret == 1)
goto done_unlocked;
@@ -3849,7 +3853,6 @@ static noinline_for_stack int write_one_eb(struct extent_buffer *eb,
struct extent_page_data *epd)
{
struct btrfs_fs_info *fs_info = eb->fs_info;
- struct block_device *bdev = fs_info->fs_devices->latest_bdev;
struct extent_io_tree *tree = &BTRFS_I(fs_info->btree_inode)->io_tree;
u64 offset = eb->start;
u32 nritems;
@@ -3884,7 +3887,7 @@ static noinline_for_stack int write_one_eb(struct extent_buffer *eb,
clear_page_dirty_for_io(p);
set_page_writeback(p);
ret = submit_extent_page(REQ_OP_WRITE | write_flags, tree, wbc,
- p, offset, PAGE_SIZE, 0, bdev,
+ p, offset, PAGE_SIZE, 0,
&epd->bio,
end_bio_extent_buffer_writepage,
0, 0, 0, false);
@@ -4121,7 +4124,7 @@ retry:
for (i = 0; i < nr_pages; i++) {
struct page *page = pvec.pages[i];
- done_index = page->index;
+ done_index = page->index + 1;
/*
* At this point we hold neither the i_pages lock nor
* the page lock: the page may be truncated or
@@ -4156,16 +4159,6 @@ retry:
ret = __extent_writepage(page, wbc, epd);
if (ret < 0) {
- /*
- * done_index is set past this page,
- * so media errors will not choke
- * background writeout for the entire
- * file. This has consequences for
- * range_cyclic semantics (ie. it may
- * not be suitable for data integrity
- * writeout).
- */
- done_index = page->index + 1;
done = 1;
break;
}
@@ -4240,8 +4233,12 @@ int extent_write_locked_range(struct inode *inode, u64 start, u64 end,
.nr_to_write = nr_pages * 2,
.range_start = start,
.range_end = end + 1,
+ /* We're called from an async helper function */
+ .punt_to_cgroup = 1,
+ .no_cgroup_owner = 1,
};
+ wbc_attach_fdatawrite_inode(&wbc_writepages, inode);
while (start <= end) {
page = find_get_page(mapping, start >> PAGE_SHIFT);
if (clear_page_dirty_for_io(page))
@@ -4256,11 +4253,12 @@ int extent_write_locked_range(struct inode *inode, u64 start, u64 end,
}
ASSERT(ret <= 0);
- if (ret < 0) {
+ if (ret == 0)
+ ret = flush_write_bio(&epd);
+ else
end_write_bio(&epd, ret);
- return ret;
- }
- ret = flush_write_bio(&epd);
+
+ wbc_detach_inode(&wbc_writepages);
return ret;
}
diff --git a/fs/btrfs/extent_io.h b/fs/btrfs/extent_io.h
index cf3424d58fec..a8551a1f56e2 100644
--- a/fs/btrfs/extent_io.h
+++ b/fs/btrfs/extent_io.h
@@ -7,35 +7,6 @@
#include <linux/refcount.h>
#include "ulist.h"
-/* bits for the extent state */
-#define EXTENT_DIRTY (1U << 0)
-#define EXTENT_UPTODATE (1U << 1)
-#define EXTENT_LOCKED (1U << 2)
-#define EXTENT_NEW (1U << 3)
-#define EXTENT_DELALLOC (1U << 4)
-#define EXTENT_DEFRAG (1U << 5)
-#define EXTENT_BOUNDARY (1U << 6)
-#define EXTENT_NODATASUM (1U << 7)
-#define EXTENT_CLEAR_META_RESV (1U << 8)
-#define EXTENT_NEED_WAIT (1U << 9)
-#define EXTENT_DAMAGED (1U << 10)
-#define EXTENT_NORESERVE (1U << 11)
-#define EXTENT_QGROUP_RESERVED (1U << 12)
-#define EXTENT_CLEAR_DATA_RESV (1U << 13)
-#define EXTENT_DELALLOC_NEW (1U << 14)
-#define EXTENT_DO_ACCOUNTING (EXTENT_CLEAR_META_RESV | \
- EXTENT_CLEAR_DATA_RESV)
-#define EXTENT_CTLBITS (EXTENT_DO_ACCOUNTING)
-
-/*
- * Redefined bits above which are used only in the device allocation tree,
- * shouldn't be using EXTENT_LOCKED / EXTENT_BOUNDARY / EXTENT_CLEAR_META_RESV
- * / EXTENT_CLEAR_DATA_RESV because they have special meaning to the bit
- * manipulation functions
- */
-#define CHUNK_ALLOCATED EXTENT_DIRTY
-#define CHUNK_TRIMMED EXTENT_DEFRAG
-
/*
* flags for bio submission. The high bits indicate the compression
* type for this bio
@@ -89,12 +60,11 @@ enum {
#define BITMAP_LAST_BYTE_MASK(nbits) \
(BYTE_MASK >> (-(nbits) & (BITS_PER_BYTE - 1)))
-struct extent_state;
struct btrfs_root;
struct btrfs_inode;
struct btrfs_io_bio;
struct io_failure_record;
-
+struct extent_io_tree;
typedef blk_status_t (extent_submit_bio_start_t)(void *private_data,
struct bio *bio, u64 bio_offset);
@@ -111,47 +81,6 @@ struct extent_io_ops {
int mirror);
};
-enum {
- IO_TREE_FS_INFO_FREED_EXTENTS0,
- IO_TREE_FS_INFO_FREED_EXTENTS1,
- IO_TREE_INODE_IO,
- IO_TREE_INODE_IO_FAILURE,
- IO_TREE_RELOC_BLOCKS,
- IO_TREE_TRANS_DIRTY_PAGES,
- IO_TREE_ROOT_DIRTY_LOG_PAGES,
- IO_TREE_SELFTEST,
-};
-
-struct extent_io_tree {
- struct rb_root state;
- struct btrfs_fs_info *fs_info;
- void *private_data;
- u64 dirty_bytes;
- bool track_uptodate;
-
- /* Who owns this io tree, should be one of IO_TREE_* */
- u8 owner;
-
- spinlock_t lock;
- const struct extent_io_ops *ops;
-};
-
-struct extent_state {
- u64 start;
- u64 end; /* inclusive */
- struct rb_node rb_node;
-
- /* ADD NEW ELEMENTS AFTER THIS */
- wait_queue_head_t wq;
- refcount_t refs;
- unsigned state;
-
- struct io_failure_record *failrec;
-
-#ifdef CONFIG_BTRFS_DEBUG
- struct list_head leak_list;
-#endif
-};
#define INLINE_EXTENT_BUFFER_PAGES 16
#define MAX_INLINE_EXTENT_BUFFER_SIZE (INLINE_EXTENT_BUFFER_PAGES * PAGE_SIZE)
@@ -259,152 +188,11 @@ typedef struct extent_map *(get_extent_t)(struct btrfs_inode *inode,
u64 start, u64 len,
int create);
-void extent_io_tree_init(struct btrfs_fs_info *fs_info,
- struct extent_io_tree *tree, unsigned int owner,
- void *private_data);
-void extent_io_tree_release(struct extent_io_tree *tree);
int try_release_extent_mapping(struct page *page, gfp_t mask);
int try_release_extent_buffer(struct page *page);
-int lock_extent_bits(struct extent_io_tree *tree, u64 start, u64 end,
- struct extent_state **cached);
-static inline int lock_extent(struct extent_io_tree *tree, u64 start, u64 end)
-{
- return lock_extent_bits(tree, start, end, NULL);
-}
-
-int try_lock_extent(struct extent_io_tree *tree, u64 start, u64 end);
int extent_read_full_page(struct extent_io_tree *tree, struct page *page,
get_extent_t *get_extent, int mirror_num);
-int __init extent_io_init(void);
-void __cold extent_io_exit(void);
-
-u64 count_range_bits(struct extent_io_tree *tree,
- u64 *start, u64 search_end,
- u64 max_bytes, unsigned bits, int contig);
-
-void free_extent_state(struct extent_state *state);
-int test_range_bit(struct extent_io_tree *tree, u64 start, u64 end,
- unsigned bits, int filled,
- struct extent_state *cached_state);
-int clear_record_extent_bits(struct extent_io_tree *tree, u64 start, u64 end,
- unsigned bits, struct extent_changeset *changeset);
-int clear_extent_bit(struct extent_io_tree *tree, u64 start, u64 end,
- unsigned bits, int wake, int delete,
- struct extent_state **cached);
-int __clear_extent_bit(struct extent_io_tree *tree, u64 start, u64 end,
- unsigned bits, int wake, int delete,
- struct extent_state **cached, gfp_t mask,
- struct extent_changeset *changeset);
-
-static inline int unlock_extent(struct extent_io_tree *tree, u64 start, u64 end)
-{
- return clear_extent_bit(tree, start, end, EXTENT_LOCKED, 1, 0, NULL);
-}
-
-static inline int unlock_extent_cached(struct extent_io_tree *tree, u64 start,
- u64 end, struct extent_state **cached)
-{
- return __clear_extent_bit(tree, start, end, EXTENT_LOCKED, 1, 0, cached,
- GFP_NOFS, NULL);
-}
-
-static inline int unlock_extent_cached_atomic(struct extent_io_tree *tree,
- u64 start, u64 end, struct extent_state **cached)
-{
- return __clear_extent_bit(tree, start, end, EXTENT_LOCKED, 1, 0, cached,
- GFP_ATOMIC, NULL);
-}
-
-static inline int clear_extent_bits(struct extent_io_tree *tree, u64 start,
- u64 end, unsigned bits)
-{
- int wake = 0;
-
- if (bits & EXTENT_LOCKED)
- wake = 1;
-
- return clear_extent_bit(tree, start, end, bits, wake, 0, NULL);
-}
-
-int set_record_extent_bits(struct extent_io_tree *tree, u64 start, u64 end,
- unsigned bits, struct extent_changeset *changeset);
-int set_extent_bit(struct extent_io_tree *tree, u64 start, u64 end,
- unsigned bits, u64 *failed_start,
- struct extent_state **cached_state, gfp_t mask);
-int set_extent_bits_nowait(struct extent_io_tree *tree, u64 start, u64 end,
- unsigned bits);
-
-static inline int set_extent_bits(struct extent_io_tree *tree, u64 start,
- u64 end, unsigned bits)
-{
- return set_extent_bit(tree, start, end, bits, NULL, NULL, GFP_NOFS);
-}
-
-static inline int clear_extent_uptodate(struct extent_io_tree *tree, u64 start,
- u64 end, struct extent_state **cached_state)
-{
- return __clear_extent_bit(tree, start, end, EXTENT_UPTODATE, 0, 0,
- cached_state, GFP_NOFS, NULL);
-}
-
-static inline int set_extent_dirty(struct extent_io_tree *tree, u64 start,
- u64 end, gfp_t mask)
-{
- return set_extent_bit(tree, start, end, EXTENT_DIRTY, NULL,
- NULL, mask);
-}
-
-static inline int clear_extent_dirty(struct extent_io_tree *tree, u64 start,
- u64 end, struct extent_state **cached)
-{
- return clear_extent_bit(tree, start, end,
- EXTENT_DIRTY | EXTENT_DELALLOC |
- EXTENT_DO_ACCOUNTING, 0, 0, cached);
-}
-
-int convert_extent_bit(struct extent_io_tree *tree, u64 start, u64 end,
- unsigned bits, unsigned clear_bits,
- struct extent_state **cached_state);
-
-static inline int set_extent_delalloc(struct extent_io_tree *tree, u64 start,
- u64 end, unsigned int extra_bits,
- struct extent_state **cached_state)
-{
- return set_extent_bit(tree, start, end,
- EXTENT_DELALLOC | EXTENT_UPTODATE | extra_bits,
- NULL, cached_state, GFP_NOFS);
-}
-
-static inline int set_extent_defrag(struct extent_io_tree *tree, u64 start,
- u64 end, struct extent_state **cached_state)
-{
- return set_extent_bit(tree, start, end,
- EXTENT_DELALLOC | EXTENT_UPTODATE | EXTENT_DEFRAG,
- NULL, cached_state, GFP_NOFS);
-}
-
-static inline int set_extent_new(struct extent_io_tree *tree, u64 start,
- u64 end)
-{
- return set_extent_bit(tree, start, end, EXTENT_NEW, NULL, NULL,
- GFP_NOFS);
-}
-
-static inline int set_extent_uptodate(struct extent_io_tree *tree, u64 start,
- u64 end, struct extent_state **cached_state, gfp_t mask)
-{
- return set_extent_bit(tree, start, end, EXTENT_UPTODATE, NULL,
- cached_state, mask);
-}
-
-int find_first_extent_bit(struct extent_io_tree *tree, u64 start,
- u64 *start_ret, u64 *end_ret, unsigned bits,
- struct extent_state **cached_state);
-void find_first_clear_extent_bit(struct extent_io_tree *tree, u64 start,
- u64 *start_ret, u64 *end_ret, unsigned bits);
-int extent_invalidatepage(struct extent_io_tree *tree,
- struct page *page, unsigned long offset);
int extent_write_full_page(struct page *page, struct writeback_control *wbc);
int extent_write_locked_range(struct inode *inode, u64 start, u64 end,
int mode);
@@ -442,11 +230,6 @@ static inline int num_extent_pages(const struct extent_buffer *eb)
(eb->start >> PAGE_SHIFT);
}
-static inline void extent_buffer_get(struct extent_buffer *eb)
-{
- atomic_inc(&eb->refs);
-}
-
static inline int extent_buffer_uptodate(struct extent_buffer *eb)
{
return test_bit(EXTENT_BUFFER_UPTODATE, &eb->bflags);
@@ -508,10 +291,6 @@ struct btrfs_inode;
int repair_io_failure(struct btrfs_fs_info *fs_info, u64 ino, u64 start,
u64 length, u64 logical, struct page *page,
unsigned int pg_offset, int mirror_num);
-int clean_io_failure(struct btrfs_fs_info *fs_info,
- struct extent_io_tree *failure_tree,
- struct extent_io_tree *io_tree, u64 start,
- struct page *page, u64 ino, unsigned int pg_offset);
void end_extent_writepage(struct page *page, int err, u64 start, u64 end);
int btrfs_repair_eb_io_failure(struct extent_buffer *eb, int mirror_num);
@@ -535,19 +314,12 @@ struct io_failure_record {
};
-void btrfs_free_io_failure_record(struct btrfs_inode *inode, u64 start,
- u64 end);
-int btrfs_get_io_failure_record(struct inode *inode, u64 start, u64 end,
- struct io_failure_record **failrec_ret);
bool btrfs_check_repairable(struct inode *inode, unsigned failed_bio_pages,
struct io_failure_record *failrec, int fail_mirror);
struct bio *btrfs_create_repair_bio(struct inode *inode, struct bio *failed_bio,
struct io_failure_record *failrec,
struct page *page, int pg_offset, int icsum,
bio_end_io_t *endio_func, void *data);
-int free_io_failure(struct extent_io_tree *failure_tree,
- struct extent_io_tree *io_tree,
- struct io_failure_record *rec);
#ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS
bool find_lock_delalloc_range(struct inode *inode,
struct page *locked_page, u64 *start,
@@ -555,5 +327,4 @@ bool find_lock_delalloc_range(struct inode *inode,
#endif
struct extent_buffer *alloc_test_extent_buffer(struct btrfs_fs_info *fs_info,
u64 start);
-
#endif
diff --git a/fs/btrfs/extent_map.c b/fs/btrfs/extent_map.c
index 9d30acca55e1..6f417ff68980 100644
--- a/fs/btrfs/extent_map.c
+++ b/fs/btrfs/extent_map.c
@@ -214,9 +214,13 @@ static int mergable_maps(struct extent_map *prev, struct extent_map *next)
ASSERT(next->block_start != EXTENT_MAP_DELALLOC &&
prev->block_start != EXTENT_MAP_DELALLOC);
+ if (prev->map_lookup || next->map_lookup)
+ ASSERT(test_bit(EXTENT_FLAG_FS_MAPPING, &prev->flags) &&
+ test_bit(EXTENT_FLAG_FS_MAPPING, &next->flags));
+
if (extent_map_end(prev) == next->start &&
prev->flags == next->flags &&
- prev->bdev == next->bdev &&
+ prev->map_lookup == next->map_lookup &&
((next->block_start == EXTENT_MAP_HOLE &&
prev->block_start == EXTENT_MAP_HOLE) ||
(next->block_start == EXTENT_MAP_INLINE &&
diff --git a/fs/btrfs/extent_map.h b/fs/btrfs/extent_map.h
index 473f039fcd7c..8e217337dff9 100644
--- a/fs/btrfs/extent_map.h
+++ b/fs/btrfs/extent_map.h
@@ -42,15 +42,8 @@ struct extent_map {
u64 block_len;
u64 generation;
unsigned long flags;
- union {
- struct block_device *bdev;
-
- /*
- * used for chunk mappings
- * flags & EXTENT_FLAG_FS_MAPPING must be set
- */
- struct map_lookup *map_lookup;
- };
+ /* Used for chunk mappings, flag EXTENT_FLAG_FS_MAPPING must be set */
+ struct map_lookup *map_lookup;
refcount_t refs;
unsigned int compress_type;
struct list_head list;
diff --git a/fs/btrfs/file-item.c b/fs/btrfs/file-item.c
index 1a599f50837b..3270a40b0777 100644
--- a/fs/btrfs/file-item.c
+++ b/fs/btrfs/file-item.c
@@ -945,7 +945,6 @@ void btrfs_extent_item_to_extent_map(struct btrfs_inode *inode,
u8 type = btrfs_file_extent_type(leaf, fi);
int compress_type = btrfs_file_extent_compression(leaf, fi);
- em->bdev = fs_info->fs_devices->latest_bdev;
btrfs_item_key_to_cpu(leaf, &key, slot);
extent_start = key.offset;
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index 27e5b269e729..0cb43b682789 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -296,7 +296,7 @@ static int __btrfs_run_defrag_inode(struct btrfs_fs_info *fs_info,
key.objectid = defrag->ino;
key.type = BTRFS_INODE_ITEM_KEY;
key.offset = 0;
- inode = btrfs_iget(fs_info->sb, &key, inode_root, NULL);
+ inode = btrfs_iget(fs_info->sb, &key, inode_root);
if (IS_ERR(inode)) {
ret = PTR_ERR(inode);
goto cleanup;
@@ -667,7 +667,6 @@ void btrfs_drop_extent_cache(struct btrfs_inode *inode, u64 start, u64 end,
}
split->generation = gen;
- split->bdev = em->bdev;
split->flags = flags;
split->compress_type = em->compress_type;
replace_extent_mapping(em_tree, em, split, modified);
@@ -680,7 +679,6 @@ void btrfs_drop_extent_cache(struct btrfs_inode *inode, u64 start, u64 end,
split->start = start + len;
split->len = em->start + em->len - (start + len);
- split->bdev = em->bdev;
split->flags = flags;
split->compress_type = em->compress_type;
split->generation = gen;
@@ -1636,6 +1634,7 @@ static noinline ssize_t btrfs_buffered_write(struct kiocb *iocb,
break;
}
+ only_release_metadata = false;
sector_offset = pos & (fs_info->sectorsize - 1);
reserve_bytes = round_up(write_bytes + sector_offset,
fs_info->sectorsize);
@@ -1692,7 +1691,7 @@ again:
force_page_uptodate);
if (ret) {
btrfs_delalloc_release_extents(BTRFS_I(inode),
- reserve_bytes, true);
+ reserve_bytes);
break;
}
@@ -1704,7 +1703,7 @@ again:
if (extents_locked == -EAGAIN)
goto again;
btrfs_delalloc_release_extents(BTRFS_I(inode),
- reserve_bytes, true);
+ reserve_bytes);
ret = extents_locked;
break;
}
@@ -1772,8 +1771,7 @@ again:
else
free_extent_state(cached_state);
- btrfs_delalloc_release_extents(BTRFS_I(inode), reserve_bytes,
- true);
+ btrfs_delalloc_release_extents(BTRFS_I(inode), reserve_bytes);
if (ret) {
btrfs_drop_pages(pages, num_pages);
break;
@@ -1792,7 +1790,6 @@ again:
set_extent_bit(&BTRFS_I(inode)->io_tree, lockstart,
lockend, EXTENT_NORESERVE, NULL,
NULL, GFP_NOFS);
- only_release_metadata = false;
}
btrfs_drop_pages(pages, num_pages);
@@ -1904,9 +1901,10 @@ static ssize_t btrfs_file_write_iter(struct kiocb *iocb,
(iocb->ki_flags & IOCB_NOWAIT))
return -EOPNOTSUPP;
- if (!inode_trylock(inode)) {
- if (iocb->ki_flags & IOCB_NOWAIT)
+ if (iocb->ki_flags & IOCB_NOWAIT) {
+ if (!inode_trylock(inode))
return -EAGAIN;
+ } else {
inode_lock(inode);
}
@@ -2068,25 +2066,7 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
struct btrfs_trans_handle *trans;
struct btrfs_log_ctx ctx;
int ret = 0, err;
- u64 len;
-
- /*
- * If the inode needs a full sync, make sure we use a full range to
- * avoid log tree corruption, due to hole detection racing with ordered
- * extent completion for adjacent ranges, and assertion failures during
- * hole detection.
- */
- if (test_bit(BTRFS_INODE_NEEDS_FULL_SYNC,
- &BTRFS_I(inode)->runtime_flags)) {
- start = 0;
- end = LLONG_MAX;
- }
- /*
- * The range length can be represented by u64, we have to do the typecasts
- * to avoid signed overflow if it's [0, LLONG_MAX] eg. from fsync()
- */
- len = (u64)end - (u64)start + 1;
trace_btrfs_sync_file(file, datasync);
btrfs_init_log_ctx(&ctx, inode);
@@ -2113,6 +2093,19 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
atomic_inc(&root->log_batch);
/*
+ * If the inode needs a full sync, make sure we use a full range to
+ * avoid log tree corruption, due to hole detection racing with ordered
+ * extent completion for adjacent ranges, and assertion failures during
+ * hole detection. Do this while holding the inode lock, to avoid races
+ * with other tasks.
+ */
+ if (test_bit(BTRFS_INODE_NEEDS_FULL_SYNC,
+ &BTRFS_I(inode)->runtime_flags)) {
+ start = 0;
+ end = LLONG_MAX;
+ }
+
+ /*
* Before we acquired the inode's lock, someone may have dirtied more
* pages in the target range. We need to make sure that writeback for
* any such pages does not start while we are logging the inode, because
@@ -2139,8 +2132,11 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
/*
* We have to do this here to avoid the priority inversion of waiting on
* IO of a lower priority task while holding a transaction open.
+ *
+ * Also, the range length can be represented by u64, we have to do the
+ * typecasts to avoid signed overflow if it's [0, LLONG_MAX].
*/
- ret = btrfs_wait_ordered_range(inode, start, len);
+ ret = btrfs_wait_ordered_range(inode, start, (u64)end - (u64)start + 1);
if (ret) {
up_write(&BTRFS_I(inode)->dio_sem);
inode_unlock(inode);
@@ -2362,7 +2358,6 @@ out:
hole_em->block_start = EXTENT_MAP_HOLE;
hole_em->block_len = 0;
hole_em->orig_block_len = 0;
- hole_em->bdev = fs_info->fs_devices->latest_bdev;
hole_em->compress_type = BTRFS_COMPRESS_NONE;
hole_em->generation = trans->transid;
@@ -3353,29 +3348,30 @@ out:
return ret;
}
-static int find_desired_extent(struct inode *inode, loff_t *offset, int whence)
+static loff_t find_desired_extent(struct inode *inode, loff_t offset,
+ int whence)
{
struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
struct extent_map *em = NULL;
struct extent_state *cached_state = NULL;
+ loff_t i_size = inode->i_size;
u64 lockstart;
u64 lockend;
u64 start;
u64 len;
int ret = 0;
- if (inode->i_size == 0)
+ if (i_size == 0 || offset >= i_size)
return -ENXIO;
/*
- * *offset can be negative, in this case we start finding DATA/HOLE from
+ * offset can be negative, in this case we start finding DATA/HOLE from
* the very start of the file.
*/
- start = max_t(loff_t, 0, *offset);
+ start = max_t(loff_t, 0, offset);
lockstart = round_down(start, fs_info->sectorsize);
- lockend = round_up(i_size_read(inode),
- fs_info->sectorsize);
+ lockend = round_up(i_size, fs_info->sectorsize);
if (lockend <= lockstart)
lockend = lockstart + fs_info->sectorsize;
lockend--;
@@ -3384,7 +3380,7 @@ static int find_desired_extent(struct inode *inode, loff_t *offset, int whence)
lock_extent_bits(&BTRFS_I(inode)->io_tree, lockstart, lockend,
&cached_state);
- while (start < inode->i_size) {
+ while (start < i_size) {
em = btrfs_get_extent_fiemap(BTRFS_I(inode), start, len);
if (IS_ERR(em)) {
ret = PTR_ERR(em);
@@ -3407,46 +3403,39 @@ static int find_desired_extent(struct inode *inode, loff_t *offset, int whence)
cond_resched();
}
free_extent_map(em);
- if (!ret) {
- if (whence == SEEK_DATA && start >= inode->i_size)
- ret = -ENXIO;
- else
- *offset = min_t(loff_t, start, inode->i_size);
- }
unlock_extent_cached(&BTRFS_I(inode)->io_tree, lockstart, lockend,
&cached_state);
- return ret;
+ if (ret) {
+ offset = ret;
+ } else {
+ if (whence == SEEK_DATA && start >= i_size)
+ offset = -ENXIO;
+ else
+ offset = min_t(loff_t, start, i_size);
+ }
+
+ return offset;
}
static loff_t btrfs_file_llseek(struct file *file, loff_t offset, int whence)
{
struct inode *inode = file->f_mapping->host;
- int ret;
- inode_lock(inode);
switch (whence) {
- case SEEK_END:
- case SEEK_CUR:
- offset = generic_file_llseek(file, offset, whence);
- goto out;
+ default:
+ return generic_file_llseek(file, offset, whence);
case SEEK_DATA:
case SEEK_HOLE:
- if (offset >= i_size_read(inode)) {
- inode_unlock(inode);
- return -ENXIO;
- }
-
- ret = find_desired_extent(inode, &offset, whence);
- if (ret) {
- inode_unlock(inode);
- return ret;
- }
+ inode_lock_shared(inode);
+ offset = find_desired_extent(inode, offset, whence);
+ inode_unlock_shared(inode);
+ break;
}
- offset = vfs_setpos(file, offset, inode->i_sb->s_maxbytes);
-out:
- inode_unlock(inode);
- return offset;
+ if (offset < 0)
+ return offset;
+
+ return vfs_setpos(file, offset, inode->i_sb->s_maxbytes);
}
static int btrfs_file_open(struct inode *inode, struct file *filp)
diff --git a/fs/btrfs/free-space-cache.c b/fs/btrfs/free-space-cache.c
index d54dcd0ab230..3283da419200 100644
--- a/fs/btrfs/free-space-cache.c
+++ b/fs/btrfs/free-space-cache.c
@@ -78,7 +78,7 @@ static struct inode *__lookup_free_space_inode(struct btrfs_root *root,
* sure NOFS is set to keep us from deadlocking.
*/
nofs_flag = memalloc_nofs_save();
- inode = btrfs_iget_path(fs_info->sb, &location, root, NULL, path);
+ inode = btrfs_iget_path(fs_info->sb, &location, root, path);
btrfs_release_path(path);
memalloc_nofs_restore(nofs_flag);
if (IS_ERR(inode))
@@ -91,8 +91,7 @@ static struct inode *__lookup_free_space_inode(struct btrfs_root *root,
return inode;
}
-struct inode *lookup_free_space_inode(
- struct btrfs_block_group_cache *block_group,
+struct inode *lookup_free_space_inode(struct btrfs_block_group *block_group,
struct btrfs_path *path)
{
struct btrfs_fs_info *fs_info = block_group->fs_info;
@@ -107,7 +106,7 @@ struct inode *lookup_free_space_inode(
return inode;
inode = __lookup_free_space_inode(fs_info->tree_root, path,
- block_group->key.objectid);
+ block_group->start);
if (IS_ERR(inode))
return inode;
@@ -190,7 +189,7 @@ static int __create_free_space_inode(struct btrfs_root *root,
}
int create_free_space_inode(struct btrfs_trans_handle *trans,
- struct btrfs_block_group_cache *block_group,
+ struct btrfs_block_group *block_group,
struct btrfs_path *path)
{
int ret;
@@ -201,7 +200,7 @@ int create_free_space_inode(struct btrfs_trans_handle *trans,
return ret;
return __create_free_space_inode(trans->fs_info->tree_root, trans, path,
- ino, block_group->key.objectid);
+ ino, block_group->start);
}
int btrfs_check_trunc_cache_free_space(struct btrfs_fs_info *fs_info,
@@ -224,7 +223,7 @@ int btrfs_check_trunc_cache_free_space(struct btrfs_fs_info *fs_info,
}
int btrfs_truncate_free_space_cache(struct btrfs_trans_handle *trans,
- struct btrfs_block_group_cache *block_group,
+ struct btrfs_block_group *block_group,
struct inode *inode)
{
struct btrfs_root *root = BTRFS_I(inode)->root;
@@ -385,6 +384,12 @@ static int io_ctl_prepare_pages(struct btrfs_io_ctl *io_ctl, struct inode *inode
if (uptodate && !PageUptodate(page)) {
btrfs_readpage(NULL, page);
lock_page(page);
+ if (page->mapping != inode->i_mapping) {
+ btrfs_err(BTRFS_I(inode)->root->fs_info,
+ "free space cache page truncated");
+ io_ctl_drop_pages(io_ctl);
+ return -EIO;
+ }
if (!PageUptodate(page)) {
btrfs_err(BTRFS_I(inode)->root->fs_info,
"error reading free space cache");
@@ -814,7 +819,7 @@ free_cache:
goto out;
}
-int load_free_space_cache(struct btrfs_block_group_cache *block_group)
+int load_free_space_cache(struct btrfs_block_group *block_group)
{
struct btrfs_fs_info *fs_info = block_group->fs_info;
struct btrfs_free_space_ctl *ctl = block_group->free_space_ctl;
@@ -822,7 +827,7 @@ int load_free_space_cache(struct btrfs_block_group_cache *block_group)
struct btrfs_path *path;
int ret = 0;
bool matched;
- u64 used = btrfs_block_group_used(&block_group->item);
+ u64 used = block_group->used;
/*
* If this block group has been marked to be cleared for one reason or
@@ -876,13 +881,13 @@ int load_free_space_cache(struct btrfs_block_group_cache *block_group)
spin_unlock(&block_group->lock);
ret = __load_free_space_cache(fs_info->tree_root, inode, ctl,
- path, block_group->key.objectid);
+ path, block_group->start);
btrfs_free_path(path);
if (ret <= 0)
goto out;
spin_lock(&ctl->tree_lock);
- matched = (ctl->free_space == (block_group->key.offset - used -
+ matched = (ctl->free_space == (block_group->length - used -
block_group->bytes_super));
spin_unlock(&ctl->tree_lock);
@@ -890,7 +895,7 @@ int load_free_space_cache(struct btrfs_block_group_cache *block_group)
__btrfs_remove_free_space_cache(ctl);
btrfs_warn(fs_info,
"block group %llu has wrong amount of free space",
- block_group->key.objectid);
+ block_group->start);
ret = -1;
}
out:
@@ -903,7 +908,7 @@ out:
btrfs_warn(fs_info,
"failed to load free space cache for block group %llu, rebuilding it now",
- block_group->key.objectid);
+ block_group->start);
}
iput(inode);
@@ -913,7 +918,7 @@ out:
static noinline_for_stack
int write_cache_extent_entries(struct btrfs_io_ctl *io_ctl,
struct btrfs_free_space_ctl *ctl,
- struct btrfs_block_group_cache *block_group,
+ struct btrfs_block_group *block_group,
int *entries, int *bitmaps,
struct list_head *bitmap_list)
{
@@ -1041,7 +1046,7 @@ fail:
}
static noinline_for_stack int write_pinned_extent_entries(
- struct btrfs_block_group_cache *block_group,
+ struct btrfs_block_group *block_group,
struct btrfs_io_ctl *io_ctl,
int *entries)
{
@@ -1061,9 +1066,9 @@ static noinline_for_stack int write_pinned_extent_entries(
*/
unpin = block_group->fs_info->pinned_extents;
- start = block_group->key.objectid;
+ start = block_group->start;
- while (start < block_group->key.objectid + block_group->key.offset) {
+ while (start < block_group->start + block_group->length) {
ret = find_first_extent_bit(unpin, start,
&extent_start, &extent_end,
EXTENT_DIRTY, NULL);
@@ -1071,13 +1076,12 @@ static noinline_for_stack int write_pinned_extent_entries(
return 0;
/* This pinned extent is out of our range */
- if (extent_start >= block_group->key.objectid +
- block_group->key.offset)
+ if (extent_start >= block_group->start + block_group->length)
return 0;
extent_start = max(extent_start, start);
- extent_end = min(block_group->key.objectid +
- block_group->key.offset, extent_end + 1);
+ extent_end = min(block_group->start + block_group->length,
+ extent_end + 1);
len = extent_end - extent_start;
*entries += 1;
@@ -1141,7 +1145,7 @@ cleanup_write_cache_enospc(struct inode *inode,
static int __btrfs_wait_cache_io(struct btrfs_root *root,
struct btrfs_trans_handle *trans,
- struct btrfs_block_group_cache *block_group,
+ struct btrfs_block_group *block_group,
struct btrfs_io_ctl *io_ctl,
struct btrfs_path *path, u64 offset)
{
@@ -1168,7 +1172,7 @@ out:
#ifdef DEBUG
btrfs_err(root->fs_info,
"failed to write free space cache for block group %llu",
- block_group->key.objectid);
+ block_group->start);
#endif
}
}
@@ -1210,12 +1214,12 @@ static int btrfs_wait_cache_io_root(struct btrfs_root *root,
}
int btrfs_wait_cache_io(struct btrfs_trans_handle *trans,
- struct btrfs_block_group_cache *block_group,
+ struct btrfs_block_group *block_group,
struct btrfs_path *path)
{
return __btrfs_wait_cache_io(block_group->fs_info->tree_root, trans,
block_group, &block_group->io_ctl,
- path, block_group->key.objectid);
+ path, block_group->start);
}
/**
@@ -1231,7 +1235,7 @@ int btrfs_wait_cache_io(struct btrfs_trans_handle *trans,
*/
static int __btrfs_write_out_cache(struct btrfs_root *root, struct inode *inode,
struct btrfs_free_space_ctl *ctl,
- struct btrfs_block_group_cache *block_group,
+ struct btrfs_block_group *block_group,
struct btrfs_io_ctl *io_ctl,
struct btrfs_trans_handle *trans)
{
@@ -1369,7 +1373,7 @@ out_unlock:
}
int btrfs_write_out_cache(struct btrfs_trans_handle *trans,
- struct btrfs_block_group_cache *block_group,
+ struct btrfs_block_group *block_group,
struct btrfs_path *path)
{
struct btrfs_fs_info *fs_info = trans->fs_info;
@@ -1394,7 +1398,7 @@ int btrfs_write_out_cache(struct btrfs_trans_handle *trans,
#ifdef DEBUG
btrfs_err(fs_info,
"failed to write free space cache for block group %llu",
- block_group->key.objectid);
+ block_group->start);
#endif
spin_lock(&block_group->lock);
block_group->disk_cache_state = BTRFS_DC_ERROR;
@@ -1647,11 +1651,11 @@ static int link_free_space(struct btrfs_free_space_ctl *ctl,
static void recalculate_thresholds(struct btrfs_free_space_ctl *ctl)
{
- struct btrfs_block_group_cache *block_group = ctl->private;
+ struct btrfs_block_group *block_group = ctl->private;
u64 max_bytes;
u64 bitmap_bytes;
u64 extent_bytes;
- u64 size = block_group->key.offset;
+ u64 size = block_group->length;
u64 bytes_per_bg = BITS_PER_BITMAP * ctl->unit;
u64 max_bitmaps = div64_u64(size + bytes_per_bg - 1, bytes_per_bg);
@@ -1991,7 +1995,7 @@ static u64 add_bytes_to_bitmap(struct btrfs_free_space_ctl *ctl,
static bool use_bitmap(struct btrfs_free_space_ctl *ctl,
struct btrfs_free_space *info)
{
- struct btrfs_block_group_cache *block_group = ctl->private;
+ struct btrfs_block_group *block_group = ctl->private;
struct btrfs_fs_info *fs_info = block_group->fs_info;
bool forced = false;
@@ -2028,7 +2032,7 @@ static bool use_bitmap(struct btrfs_free_space_ctl *ctl,
* so allow those block groups to still be allowed to have a bitmap
* entry.
*/
- if (((BITS_PER_BITMAP * ctl->unit) >> 1) > block_group->key.offset)
+ if (((BITS_PER_BITMAP * ctl->unit) >> 1) > block_group->length)
return false;
return true;
@@ -2043,7 +2047,7 @@ static int insert_into_bitmap(struct btrfs_free_space_ctl *ctl,
struct btrfs_free_space *info)
{
struct btrfs_free_space *bitmap_info;
- struct btrfs_block_group_cache *block_group = NULL;
+ struct btrfs_block_group *block_group = NULL;
int added = 0;
u64 bytes, offset, bytes_added;
int ret;
@@ -2380,7 +2384,7 @@ out:
return ret;
}
-int btrfs_add_free_space(struct btrfs_block_group_cache *block_group,
+int btrfs_add_free_space(struct btrfs_block_group *block_group,
u64 bytenr, u64 size)
{
return __btrfs_add_free_space(block_group->fs_info,
@@ -2388,7 +2392,7 @@ int btrfs_add_free_space(struct btrfs_block_group_cache *block_group,
bytenr, size);
}
-int btrfs_remove_free_space(struct btrfs_block_group_cache *block_group,
+int btrfs_remove_free_space(struct btrfs_block_group *block_group,
u64 offset, u64 bytes)
{
struct btrfs_free_space_ctl *ctl = block_group->free_space_ctl;
@@ -2478,7 +2482,7 @@ out:
return ret;
}
-void btrfs_dump_free_space(struct btrfs_block_group_cache *block_group,
+void btrfs_dump_free_space(struct btrfs_block_group *block_group,
u64 bytes)
{
struct btrfs_fs_info *fs_info = block_group->fs_info;
@@ -2503,14 +2507,14 @@ void btrfs_dump_free_space(struct btrfs_block_group_cache *block_group,
"%d blocks of free space at or bigger than bytes is", count);
}
-void btrfs_init_free_space_ctl(struct btrfs_block_group_cache *block_group)
+void btrfs_init_free_space_ctl(struct btrfs_block_group *block_group)
{
struct btrfs_fs_info *fs_info = block_group->fs_info;
struct btrfs_free_space_ctl *ctl = block_group->free_space_ctl;
spin_lock_init(&ctl->tree_lock);
ctl->unit = fs_info->sectorsize;
- ctl->start = block_group->key.objectid;
+ ctl->start = block_group->start;
ctl->private = block_group;
ctl->op = &free_space_op;
INIT_LIST_HEAD(&ctl->trimming_ranges);
@@ -2532,7 +2536,7 @@ void btrfs_init_free_space_ctl(struct btrfs_block_group_cache *block_group)
*/
static int
__btrfs_return_cluster_to_free_space(
- struct btrfs_block_group_cache *block_group,
+ struct btrfs_block_group *block_group,
struct btrfs_free_cluster *cluster)
{
struct btrfs_free_space_ctl *ctl = block_group->free_space_ctl;
@@ -2598,7 +2602,7 @@ void __btrfs_remove_free_space_cache(struct btrfs_free_space_ctl *ctl)
spin_unlock(&ctl->tree_lock);
}
-void btrfs_remove_free_space_cache(struct btrfs_block_group_cache *block_group)
+void btrfs_remove_free_space_cache(struct btrfs_block_group *block_group)
{
struct btrfs_free_space_ctl *ctl = block_group->free_space_ctl;
struct btrfs_free_cluster *cluster;
@@ -2620,7 +2624,7 @@ void btrfs_remove_free_space_cache(struct btrfs_block_group_cache *block_group)
}
-u64 btrfs_find_space_for_alloc(struct btrfs_block_group_cache *block_group,
+u64 btrfs_find_space_for_alloc(struct btrfs_block_group *block_group,
u64 offset, u64 bytes, u64 empty_size,
u64 *max_extent_size)
{
@@ -2674,7 +2678,7 @@ out:
* cluster and remove the cluster from it.
*/
int btrfs_return_cluster_to_free_space(
- struct btrfs_block_group_cache *block_group,
+ struct btrfs_block_group *block_group,
struct btrfs_free_cluster *cluster)
{
struct btrfs_free_space_ctl *ctl;
@@ -2708,7 +2712,7 @@ int btrfs_return_cluster_to_free_space(
return ret;
}
-static u64 btrfs_alloc_from_bitmap(struct btrfs_block_group_cache *block_group,
+static u64 btrfs_alloc_from_bitmap(struct btrfs_block_group *block_group,
struct btrfs_free_cluster *cluster,
struct btrfs_free_space *entry,
u64 bytes, u64 min_start,
@@ -2741,7 +2745,7 @@ static u64 btrfs_alloc_from_bitmap(struct btrfs_block_group_cache *block_group,
* if it couldn't find anything suitably large, or a logical disk offset
* if things worked out
*/
-u64 btrfs_alloc_from_cluster(struct btrfs_block_group_cache *block_group,
+u64 btrfs_alloc_from_cluster(struct btrfs_block_group *block_group,
struct btrfs_free_cluster *cluster, u64 bytes,
u64 min_start, u64 *max_extent_size)
{
@@ -2827,7 +2831,7 @@ out:
return ret;
}
-static int btrfs_bitmap_cluster(struct btrfs_block_group_cache *block_group,
+static int btrfs_bitmap_cluster(struct btrfs_block_group *block_group,
struct btrfs_free_space *entry,
struct btrfs_free_cluster *cluster,
u64 offset, u64 bytes,
@@ -2909,7 +2913,7 @@ again:
* extent of cont1_bytes, and other clusters of at least min_bytes.
*/
static noinline int
-setup_cluster_no_bitmap(struct btrfs_block_group_cache *block_group,
+setup_cluster_no_bitmap(struct btrfs_block_group *block_group,
struct btrfs_free_cluster *cluster,
struct list_head *bitmaps, u64 offset, u64 bytes,
u64 cont1_bytes, u64 min_bytes)
@@ -3000,7 +3004,7 @@ setup_cluster_no_bitmap(struct btrfs_block_group_cache *block_group,
* that we have already failed to find extents that will work.
*/
static noinline int
-setup_cluster_bitmap(struct btrfs_block_group_cache *block_group,
+setup_cluster_bitmap(struct btrfs_block_group *block_group,
struct btrfs_free_cluster *cluster,
struct list_head *bitmaps, u64 offset, u64 bytes,
u64 cont1_bytes, u64 min_bytes)
@@ -3050,7 +3054,7 @@ setup_cluster_bitmap(struct btrfs_block_group_cache *block_group,
* returns zero and sets up cluster if things worked out, otherwise
* it returns -enospc
*/
-int btrfs_find_space_cluster(struct btrfs_block_group_cache *block_group,
+int btrfs_find_space_cluster(struct btrfs_block_group *block_group,
struct btrfs_free_cluster *cluster,
u64 offset, u64 bytes, u64 empty_size)
{
@@ -3141,7 +3145,7 @@ void btrfs_init_free_cluster(struct btrfs_free_cluster *cluster)
cluster->block_group = NULL;
}
-static int do_trimming(struct btrfs_block_group_cache *block_group,
+static int do_trimming(struct btrfs_block_group *block_group,
u64 *total_trimmed, u64 start, u64 bytes,
u64 reserved_start, u64 reserved_bytes,
struct btrfs_trim_range *trim_entry)
@@ -3186,7 +3190,7 @@ static int do_trimming(struct btrfs_block_group_cache *block_group,
return ret;
}
-static int trim_no_bitmap(struct btrfs_block_group_cache *block_group,
+static int trim_no_bitmap(struct btrfs_block_group *block_group,
u64 *total_trimmed, u64 start, u64 end, u64 minlen)
{
struct btrfs_free_space_ctl *ctl = block_group->free_space_ctl;
@@ -3271,7 +3275,7 @@ out:
return ret;
}
-static int trim_bitmaps(struct btrfs_block_group_cache *block_group,
+static int trim_bitmaps(struct btrfs_block_group *block_group,
u64 *total_trimmed, u64 start, u64 end, u64 minlen)
{
struct btrfs_free_space_ctl *ctl = block_group->free_space_ctl;
@@ -3352,12 +3356,12 @@ next:
return ret;
}
-void btrfs_get_block_group_trimming(struct btrfs_block_group_cache *cache)
+void btrfs_get_block_group_trimming(struct btrfs_block_group *cache)
{
atomic_inc(&cache->trimming);
}
-void btrfs_put_block_group_trimming(struct btrfs_block_group_cache *block_group)
+void btrfs_put_block_group_trimming(struct btrfs_block_group *block_group)
{
struct btrfs_fs_info *fs_info = block_group->fs_info;
struct extent_map_tree *em_tree;
@@ -3373,7 +3377,7 @@ void btrfs_put_block_group_trimming(struct btrfs_block_group_cache *block_group)
mutex_lock(&fs_info->chunk_mutex);
em_tree = &fs_info->mapping_tree;
write_lock(&em_tree->lock);
- em = lookup_extent_mapping(em_tree, block_group->key.objectid,
+ em = lookup_extent_mapping(em_tree, block_group->start,
1);
BUG_ON(!em); /* logic error, can't happen */
remove_extent_mapping(em_tree, em);
@@ -3392,7 +3396,7 @@ void btrfs_put_block_group_trimming(struct btrfs_block_group_cache *block_group)
}
}
-int btrfs_trim_block_group(struct btrfs_block_group_cache *block_group,
+int btrfs_trim_block_group(struct btrfs_block_group *block_group,
u64 *trimmed, u64 start, u64 end, u64 minlen)
{
int ret;
@@ -3590,7 +3594,7 @@ int btrfs_write_out_ino_cache(struct btrfs_root *root,
* how the free space cache loading stuff works, so you can get really weird
* configurations.
*/
-int test_add_free_space_entry(struct btrfs_block_group_cache *cache,
+int test_add_free_space_entry(struct btrfs_block_group *cache,
u64 offset, u64 bytes, bool bitmap)
{
struct btrfs_free_space_ctl *ctl = cache->free_space_ctl;
@@ -3658,7 +3662,7 @@ again:
* just used to check the absence of space, so if there is free space in the
* range at all we will return 1.
*/
-int test_check_exists(struct btrfs_block_group_cache *cache,
+int test_check_exists(struct btrfs_block_group *cache,
u64 offset, u64 bytes)
{
struct btrfs_free_space_ctl *ctl = cache->free_space_ctl;
diff --git a/fs/btrfs/free-space-cache.h b/fs/btrfs/free-space-cache.h
index 39c32c8fc24f..ba9a23241101 100644
--- a/fs/btrfs/free-space-cache.h
+++ b/fs/btrfs/free-space-cache.h
@@ -50,24 +50,23 @@ struct btrfs_io_ctl {
unsigned check_crcs:1;
};
-struct inode *lookup_free_space_inode(
- struct btrfs_block_group_cache *block_group,
+struct inode *lookup_free_space_inode(struct btrfs_block_group *block_group,
struct btrfs_path *path);
int create_free_space_inode(struct btrfs_trans_handle *trans,
- struct btrfs_block_group_cache *block_group,
+ struct btrfs_block_group *block_group,
struct btrfs_path *path);
int btrfs_check_trunc_cache_free_space(struct btrfs_fs_info *fs_info,
struct btrfs_block_rsv *rsv);
int btrfs_truncate_free_space_cache(struct btrfs_trans_handle *trans,
- struct btrfs_block_group_cache *block_group,
+ struct btrfs_block_group *block_group,
struct inode *inode);
-int load_free_space_cache(struct btrfs_block_group_cache *block_group);
+int load_free_space_cache(struct btrfs_block_group *block_group);
int btrfs_wait_cache_io(struct btrfs_trans_handle *trans,
- struct btrfs_block_group_cache *block_group,
+ struct btrfs_block_group *block_group,
struct btrfs_path *path);
int btrfs_write_out_cache(struct btrfs_trans_handle *trans,
- struct btrfs_block_group_cache *block_group,
+ struct btrfs_block_group *block_group,
struct btrfs_path *path);
struct inode *lookup_free_ino_inode(struct btrfs_root *root,
struct btrfs_path *path);
@@ -81,42 +80,40 @@ int btrfs_write_out_ino_cache(struct btrfs_root *root,
struct btrfs_path *path,
struct inode *inode);
-void btrfs_init_free_space_ctl(struct btrfs_block_group_cache *block_group);
+void btrfs_init_free_space_ctl(struct btrfs_block_group *block_group);
int __btrfs_add_free_space(struct btrfs_fs_info *fs_info,
struct btrfs_free_space_ctl *ctl,
u64 bytenr, u64 size);
-int btrfs_add_free_space(struct btrfs_block_group_cache *block_group,
+int btrfs_add_free_space(struct btrfs_block_group *block_group,
u64 bytenr, u64 size);
-int btrfs_remove_free_space(struct btrfs_block_group_cache *block_group,
+int btrfs_remove_free_space(struct btrfs_block_group *block_group,
u64 bytenr, u64 size);
void __btrfs_remove_free_space_cache(struct btrfs_free_space_ctl *ctl);
-void btrfs_remove_free_space_cache(struct btrfs_block_group_cache
- *block_group);
-u64 btrfs_find_space_for_alloc(struct btrfs_block_group_cache *block_group,
+void btrfs_remove_free_space_cache(struct btrfs_block_group *block_group);
+u64 btrfs_find_space_for_alloc(struct btrfs_block_group *block_group,
u64 offset, u64 bytes, u64 empty_size,
u64 *max_extent_size);
u64 btrfs_find_ino_for_alloc(struct btrfs_root *fs_root);
-void btrfs_dump_free_space(struct btrfs_block_group_cache *block_group,
+void btrfs_dump_free_space(struct btrfs_block_group *block_group,
u64 bytes);
-int btrfs_find_space_cluster(struct btrfs_block_group_cache *block_group,
+int btrfs_find_space_cluster(struct btrfs_block_group *block_group,
struct btrfs_free_cluster *cluster,
u64 offset, u64 bytes, u64 empty_size);
void btrfs_init_free_cluster(struct btrfs_free_cluster *cluster);
-u64 btrfs_alloc_from_cluster(struct btrfs_block_group_cache *block_group,
+u64 btrfs_alloc_from_cluster(struct btrfs_block_group *block_group,
struct btrfs_free_cluster *cluster, u64 bytes,
u64 min_start, u64 *max_extent_size);
int btrfs_return_cluster_to_free_space(
- struct btrfs_block_group_cache *block_group,
+ struct btrfs_block_group *block_group,
struct btrfs_free_cluster *cluster);
-int btrfs_trim_block_group(struct btrfs_block_group_cache *block_group,
+int btrfs_trim_block_group(struct btrfs_block_group *block_group,
u64 *trimmed, u64 start, u64 end, u64 minlen);
/* Support functions for running our sanity tests */
#ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS
-int test_add_free_space_entry(struct btrfs_block_group_cache *cache,
+int test_add_free_space_entry(struct btrfs_block_group *cache,
u64 offset, u64 bytes, bool bitmap);
-int test_check_exists(struct btrfs_block_group_cache *cache,
- u64 offset, u64 bytes);
+int test_check_exists(struct btrfs_block_group *cache, u64 offset, u64 bytes);
#endif
#endif
diff --git a/fs/btrfs/free-space-tree.c b/fs/btrfs/free-space-tree.c
index 48a03f5240f5..258cb3fae17a 100644
--- a/fs/btrfs/free-space-tree.c
+++ b/fs/btrfs/free-space-tree.c
@@ -13,10 +13,10 @@
#include "block-group.h"
static int __add_block_group_free_space(struct btrfs_trans_handle *trans,
- struct btrfs_block_group_cache *block_group,
+ struct btrfs_block_group *block_group,
struct btrfs_path *path);
-void set_free_space_tree_thresholds(struct btrfs_block_group_cache *cache)
+void set_free_space_tree_thresholds(struct btrfs_block_group *cache)
{
u32 bitmap_range;
size_t bitmap_size;
@@ -27,8 +27,7 @@ void set_free_space_tree_thresholds(struct btrfs_block_group_cache *cache)
* exceeds that required for using bitmaps.
*/
bitmap_range = cache->fs_info->sectorsize * BTRFS_FREE_SPACE_BITMAP_BITS;
- num_bitmaps = div_u64(cache->key.offset + bitmap_range - 1,
- bitmap_range);
+ num_bitmaps = div_u64(cache->length + bitmap_range - 1, bitmap_range);
bitmap_size = sizeof(struct btrfs_item) + BTRFS_FREE_SPACE_BITMAP_SIZE;
total_bitmap_size = num_bitmaps * bitmap_size;
cache->bitmap_high_thresh = div_u64(total_bitmap_size,
@@ -45,7 +44,7 @@ void set_free_space_tree_thresholds(struct btrfs_block_group_cache *cache)
}
static int add_new_free_space_info(struct btrfs_trans_handle *trans,
- struct btrfs_block_group_cache *block_group,
+ struct btrfs_block_group *block_group,
struct btrfs_path *path)
{
struct btrfs_root *root = trans->fs_info->free_space_root;
@@ -54,9 +53,9 @@ static int add_new_free_space_info(struct btrfs_trans_handle *trans,
struct extent_buffer *leaf;
int ret;
- key.objectid = block_group->key.objectid;
+ key.objectid = block_group->start;
key.type = BTRFS_FREE_SPACE_INFO_KEY;
- key.offset = block_group->key.offset;
+ key.offset = block_group->length;
ret = btrfs_insert_empty_item(trans, root, path, &key, sizeof(*info));
if (ret)
@@ -78,7 +77,7 @@ out:
EXPORT_FOR_TESTS
struct btrfs_free_space_info *search_free_space_info(
struct btrfs_trans_handle *trans,
- struct btrfs_block_group_cache *block_group,
+ struct btrfs_block_group *block_group,
struct btrfs_path *path, int cow)
{
struct btrfs_fs_info *fs_info = block_group->fs_info;
@@ -86,16 +85,16 @@ struct btrfs_free_space_info *search_free_space_info(
struct btrfs_key key;
int ret;
- key.objectid = block_group->key.objectid;
+ key.objectid = block_group->start;
key.type = BTRFS_FREE_SPACE_INFO_KEY;
- key.offset = block_group->key.offset;
+ key.offset = block_group->length;
ret = btrfs_search_slot(trans, root, &key, path, 0, cow);
if (ret < 0)
return ERR_PTR(ret);
if (ret != 0) {
btrfs_warn(fs_info, "missing free space info for %llu",
- block_group->key.objectid);
+ block_group->start);
ASSERT(0);
return ERR_PTR(-ENOENT);
}
@@ -180,7 +179,7 @@ static void le_bitmap_set(unsigned long *map, unsigned int start, int len)
EXPORT_FOR_TESTS
int convert_free_space_to_bitmaps(struct btrfs_trans_handle *trans,
- struct btrfs_block_group_cache *block_group,
+ struct btrfs_block_group *block_group,
struct btrfs_path *path)
{
struct btrfs_fs_info *fs_info = trans->fs_info;
@@ -197,7 +196,7 @@ int convert_free_space_to_bitmaps(struct btrfs_trans_handle *trans,
int done = 0, nr;
int ret;
- bitmap_size = free_space_bitmap_size(block_group->key.offset,
+ bitmap_size = free_space_bitmap_size(block_group->length,
fs_info->sectorsize);
bitmap = alloc_bitmap(bitmap_size);
if (!bitmap) {
@@ -205,8 +204,8 @@ int convert_free_space_to_bitmaps(struct btrfs_trans_handle *trans,
goto out;
}
- start = block_group->key.objectid;
- end = block_group->key.objectid + block_group->key.offset;
+ start = block_group->start;
+ end = block_group->start + block_group->length;
key.objectid = end - 1;
key.type = (u8)-1;
@@ -224,8 +223,8 @@ int convert_free_space_to_bitmaps(struct btrfs_trans_handle *trans,
btrfs_item_key_to_cpu(leaf, &found_key, path->slots[0] - 1);
if (found_key.type == BTRFS_FREE_SPACE_INFO_KEY) {
- ASSERT(found_key.objectid == block_group->key.objectid);
- ASSERT(found_key.offset == block_group->key.offset);
+ ASSERT(found_key.objectid == block_group->start);
+ ASSERT(found_key.offset == block_group->length);
done = 1;
break;
} else if (found_key.type == BTRFS_FREE_SPACE_EXTENT_KEY) {
@@ -271,7 +270,7 @@ int convert_free_space_to_bitmaps(struct btrfs_trans_handle *trans,
if (extent_count != expected_extent_count) {
btrfs_err(fs_info,
"incorrect extent count for %llu; counted %u, expected %u",
- block_group->key.objectid, extent_count,
+ block_group->start, extent_count,
expected_extent_count);
ASSERT(0);
ret = -EIO;
@@ -320,7 +319,7 @@ out:
EXPORT_FOR_TESTS
int convert_free_space_to_extents(struct btrfs_trans_handle *trans,
- struct btrfs_block_group_cache *block_group,
+ struct btrfs_block_group *block_group,
struct btrfs_path *path)
{
struct btrfs_fs_info *fs_info = trans->fs_info;
@@ -336,7 +335,7 @@ int convert_free_space_to_extents(struct btrfs_trans_handle *trans,
int done = 0, nr;
int ret;
- bitmap_size = free_space_bitmap_size(block_group->key.offset,
+ bitmap_size = free_space_bitmap_size(block_group->length,
fs_info->sectorsize);
bitmap = alloc_bitmap(bitmap_size);
if (!bitmap) {
@@ -344,8 +343,8 @@ int convert_free_space_to_extents(struct btrfs_trans_handle *trans,
goto out;
}
- start = block_group->key.objectid;
- end = block_group->key.objectid + block_group->key.offset;
+ start = block_group->start;
+ end = block_group->start + block_group->length;
key.objectid = end - 1;
key.type = (u8)-1;
@@ -363,8 +362,8 @@ int convert_free_space_to_extents(struct btrfs_trans_handle *trans,
btrfs_item_key_to_cpu(leaf, &found_key, path->slots[0] - 1);
if (found_key.type == BTRFS_FREE_SPACE_INFO_KEY) {
- ASSERT(found_key.objectid == block_group->key.objectid);
- ASSERT(found_key.offset == block_group->key.offset);
+ ASSERT(found_key.objectid == block_group->start);
+ ASSERT(found_key.offset == block_group->length);
done = 1;
break;
} else if (found_key.type == BTRFS_FREE_SPACE_BITMAP_KEY) {
@@ -413,7 +412,7 @@ int convert_free_space_to_extents(struct btrfs_trans_handle *trans,
btrfs_mark_buffer_dirty(leaf);
btrfs_release_path(path);
- nrbits = div_u64(block_group->key.offset, block_group->fs_info->sectorsize);
+ nrbits = div_u64(block_group->length, block_group->fs_info->sectorsize);
start_bit = find_next_bit_le(bitmap, nrbits, 0);
while (start_bit < nrbits) {
@@ -437,7 +436,7 @@ int convert_free_space_to_extents(struct btrfs_trans_handle *trans,
if (extent_count != expected_extent_count) {
btrfs_err(fs_info,
"incorrect extent count for %llu; counted %u, expected %u",
- block_group->key.objectid, extent_count,
+ block_group->start, extent_count,
expected_extent_count);
ASSERT(0);
ret = -EIO;
@@ -453,7 +452,7 @@ out:
}
static int update_free_space_extent_count(struct btrfs_trans_handle *trans,
- struct btrfs_block_group_cache *block_group,
+ struct btrfs_block_group *block_group,
struct btrfs_path *path,
int new_extents)
{
@@ -491,7 +490,7 @@ out:
}
EXPORT_FOR_TESTS
-int free_space_test_bit(struct btrfs_block_group_cache *block_group,
+int free_space_test_bit(struct btrfs_block_group *block_group,
struct btrfs_path *path, u64 offset)
{
struct extent_buffer *leaf;
@@ -513,7 +512,7 @@ int free_space_test_bit(struct btrfs_block_group_cache *block_group,
return !!extent_buffer_test_bit(leaf, ptr, i);
}
-static void free_space_set_bits(struct btrfs_block_group_cache *block_group,
+static void free_space_set_bits(struct btrfs_block_group *block_group,
struct btrfs_path *path, u64 *start, u64 *size,
int bit)
{
@@ -581,7 +580,7 @@ static int free_space_next_bitmap(struct btrfs_trans_handle *trans,
* the bitmap.
*/
static int modify_free_space_bitmap(struct btrfs_trans_handle *trans,
- struct btrfs_block_group_cache *block_group,
+ struct btrfs_block_group *block_group,
struct btrfs_path *path,
u64 start, u64 size, int remove)
{
@@ -597,7 +596,7 @@ static int modify_free_space_bitmap(struct btrfs_trans_handle *trans,
* Read the bit for the block immediately before the extent of space if
* that block is within the block group.
*/
- if (start > block_group->key.objectid) {
+ if (start > block_group->start) {
u64 prev_block = start - block_group->fs_info->sectorsize;
key.objectid = prev_block;
@@ -649,7 +648,7 @@ static int modify_free_space_bitmap(struct btrfs_trans_handle *trans,
* Read the bit for the block immediately after the extent of space if
* that block is within the block group.
*/
- if (end < block_group->key.objectid + block_group->key.offset) {
+ if (end < block_group->start + block_group->length) {
/* The next block may be in the next bitmap. */
btrfs_item_key_to_cpu(path->nodes[0], &key, path->slots[0]);
if (end >= key.objectid + key.offset) {
@@ -694,7 +693,7 @@ out:
}
static int remove_free_space_extent(struct btrfs_trans_handle *trans,
- struct btrfs_block_group_cache *block_group,
+ struct btrfs_block_group *block_group,
struct btrfs_path *path,
u64 start, u64 size)
{
@@ -781,7 +780,7 @@ out:
EXPORT_FOR_TESTS
int __remove_from_free_space_tree(struct btrfs_trans_handle *trans,
- struct btrfs_block_group_cache *block_group,
+ struct btrfs_block_group *block_group,
struct btrfs_path *path, u64 start, u64 size)
{
struct btrfs_free_space_info *info;
@@ -812,7 +811,7 @@ int __remove_from_free_space_tree(struct btrfs_trans_handle *trans,
int remove_from_free_space_tree(struct btrfs_trans_handle *trans,
u64 start, u64 size)
{
- struct btrfs_block_group_cache *block_group;
+ struct btrfs_block_group *block_group;
struct btrfs_path *path;
int ret;
@@ -846,7 +845,7 @@ out:
}
static int add_free_space_extent(struct btrfs_trans_handle *trans,
- struct btrfs_block_group_cache *block_group,
+ struct btrfs_block_group *block_group,
struct btrfs_path *path,
u64 start, u64 size)
{
@@ -880,7 +879,7 @@ static int add_free_space_extent(struct btrfs_trans_handle *trans,
new_key.offset = size;
/* Search for a neighbor on the left. */
- if (start == block_group->key.objectid)
+ if (start == block_group->start)
goto right;
key.objectid = start - 1;
key.type = (u8)-1;
@@ -900,8 +899,8 @@ static int add_free_space_extent(struct btrfs_trans_handle *trans,
found_start = key.objectid;
found_end = key.objectid + key.offset;
- ASSERT(found_start >= block_group->key.objectid &&
- found_end > block_group->key.objectid);
+ ASSERT(found_start >= block_group->start &&
+ found_end > block_group->start);
ASSERT(found_start < start && found_end <= start);
/*
@@ -920,7 +919,7 @@ static int add_free_space_extent(struct btrfs_trans_handle *trans,
right:
/* Search for a neighbor on the right. */
- if (end == block_group->key.objectid + block_group->key.offset)
+ if (end == block_group->start + block_group->length)
goto insert;
key.objectid = end;
key.type = (u8)-1;
@@ -940,8 +939,8 @@ right:
found_start = key.objectid;
found_end = key.objectid + key.offset;
- ASSERT(found_start >= block_group->key.objectid &&
- found_end > block_group->key.objectid);
+ ASSERT(found_start >= block_group->start &&
+ found_end > block_group->start);
ASSERT((found_start < start && found_end <= start) ||
(found_start >= end && found_end > end));
@@ -974,7 +973,7 @@ out:
EXPORT_FOR_TESTS
int __add_to_free_space_tree(struct btrfs_trans_handle *trans,
- struct btrfs_block_group_cache *block_group,
+ struct btrfs_block_group *block_group,
struct btrfs_path *path, u64 start, u64 size)
{
struct btrfs_free_space_info *info;
@@ -1005,7 +1004,7 @@ int __add_to_free_space_tree(struct btrfs_trans_handle *trans,
int add_to_free_space_tree(struct btrfs_trans_handle *trans,
u64 start, u64 size)
{
- struct btrfs_block_group_cache *block_group;
+ struct btrfs_block_group *block_group;
struct btrfs_path *path;
int ret;
@@ -1043,7 +1042,7 @@ out:
* through the normal add/remove hooks.
*/
static int populate_free_space_tree(struct btrfs_trans_handle *trans,
- struct btrfs_block_group_cache *block_group)
+ struct btrfs_block_group *block_group)
{
struct btrfs_root *extent_root = trans->fs_info->extent_root;
struct btrfs_path *path, *path2;
@@ -1075,7 +1074,7 @@ static int populate_free_space_tree(struct btrfs_trans_handle *trans,
* BLOCK_GROUP_ITEM, so an extent may precede the block group that it's
* contained in.
*/
- key.objectid = block_group->key.objectid;
+ key.objectid = block_group->start;
key.type = BTRFS_EXTENT_ITEM_KEY;
key.offset = 0;
@@ -1084,8 +1083,8 @@ static int populate_free_space_tree(struct btrfs_trans_handle *trans,
goto out_locked;
ASSERT(ret == 0);
- start = block_group->key.objectid;
- end = block_group->key.objectid + block_group->key.offset;
+ start = block_group->start;
+ end = block_group->start + block_group->length;
while (1) {
btrfs_item_key_to_cpu(path->nodes[0], &key, path->slots[0]);
@@ -1109,7 +1108,7 @@ static int populate_free_space_tree(struct btrfs_trans_handle *trans,
else
start += key.offset;
} else if (key.type == BTRFS_BLOCK_GROUP_ITEM_KEY) {
- if (key.objectid != block_group->key.objectid)
+ if (key.objectid != block_group->start)
break;
}
@@ -1140,7 +1139,7 @@ int btrfs_create_free_space_tree(struct btrfs_fs_info *fs_info)
struct btrfs_trans_handle *trans;
struct btrfs_root *tree_root = fs_info->tree_root;
struct btrfs_root *free_space_root;
- struct btrfs_block_group_cache *block_group;
+ struct btrfs_block_group *block_group;
struct rb_node *node;
int ret;
@@ -1159,7 +1158,7 @@ int btrfs_create_free_space_tree(struct btrfs_fs_info *fs_info)
node = rb_first(&fs_info->block_group_cache_tree);
while (node) {
- block_group = rb_entry(node, struct btrfs_block_group_cache,
+ block_group = rb_entry(node, struct btrfs_block_group,
cache_node);
ret = populate_free_space_tree(trans, block_group);
if (ret)
@@ -1265,7 +1264,7 @@ abort:
}
static int __add_block_group_free_space(struct btrfs_trans_handle *trans,
- struct btrfs_block_group_cache *block_group,
+ struct btrfs_block_group *block_group,
struct btrfs_path *path)
{
int ret;
@@ -1277,12 +1276,12 @@ static int __add_block_group_free_space(struct btrfs_trans_handle *trans,
return ret;
return __add_to_free_space_tree(trans, block_group, path,
- block_group->key.objectid,
- block_group->key.offset);
+ block_group->start,
+ block_group->length);
}
int add_block_group_free_space(struct btrfs_trans_handle *trans,
- struct btrfs_block_group_cache *block_group)
+ struct btrfs_block_group *block_group)
{
struct btrfs_fs_info *fs_info = trans->fs_info;
struct btrfs_path *path = NULL;
@@ -1312,7 +1311,7 @@ out:
}
int remove_block_group_free_space(struct btrfs_trans_handle *trans,
- struct btrfs_block_group_cache *block_group)
+ struct btrfs_block_group *block_group)
{
struct btrfs_root *root = trans->fs_info->free_space_root;
struct btrfs_path *path;
@@ -1336,8 +1335,8 @@ int remove_block_group_free_space(struct btrfs_trans_handle *trans,
goto out;
}
- start = block_group->key.objectid;
- end = block_group->key.objectid + block_group->key.offset;
+ start = block_group->start;
+ end = block_group->start + block_group->length;
key.objectid = end - 1;
key.type = (u8)-1;
@@ -1355,8 +1354,8 @@ int remove_block_group_free_space(struct btrfs_trans_handle *trans,
btrfs_item_key_to_cpu(leaf, &found_key, path->slots[0] - 1);
if (found_key.type == BTRFS_FREE_SPACE_INFO_KEY) {
- ASSERT(found_key.objectid == block_group->key.objectid);
- ASSERT(found_key.offset == block_group->key.offset);
+ ASSERT(found_key.objectid == block_group->start);
+ ASSERT(found_key.offset == block_group->length);
done = 1;
nr++;
path->slots[0]--;
@@ -1391,7 +1390,7 @@ static int load_free_space_bitmaps(struct btrfs_caching_control *caching_ctl,
struct btrfs_path *path,
u32 expected_extent_count)
{
- struct btrfs_block_group_cache *block_group;
+ struct btrfs_block_group *block_group;
struct btrfs_fs_info *fs_info;
struct btrfs_root *root;
struct btrfs_key key;
@@ -1407,7 +1406,7 @@ static int load_free_space_bitmaps(struct btrfs_caching_control *caching_ctl,
fs_info = block_group->fs_info;
root = fs_info->free_space_root;
- end = block_group->key.objectid + block_group->key.offset;
+ end = block_group->start + block_group->length;
while (1) {
ret = btrfs_next_item(root, path);
@@ -1454,7 +1453,7 @@ static int load_free_space_bitmaps(struct btrfs_caching_control *caching_ctl,
if (extent_count != expected_extent_count) {
btrfs_err(fs_info,
"incorrect extent count for %llu; counted %u, expected %u",
- block_group->key.objectid, extent_count,
+ block_group->start, extent_count,
expected_extent_count);
ASSERT(0);
ret = -EIO;
@@ -1472,7 +1471,7 @@ static int load_free_space_extents(struct btrfs_caching_control *caching_ctl,
struct btrfs_path *path,
u32 expected_extent_count)
{
- struct btrfs_block_group_cache *block_group;
+ struct btrfs_block_group *block_group;
struct btrfs_fs_info *fs_info;
struct btrfs_root *root;
struct btrfs_key key;
@@ -1485,7 +1484,7 @@ static int load_free_space_extents(struct btrfs_caching_control *caching_ctl,
fs_info = block_group->fs_info;
root = fs_info->free_space_root;
- end = block_group->key.objectid + block_group->key.offset;
+ end = block_group->start + block_group->length;
while (1) {
ret = btrfs_next_item(root, path);
@@ -1516,7 +1515,7 @@ static int load_free_space_extents(struct btrfs_caching_control *caching_ctl,
if (extent_count != expected_extent_count) {
btrfs_err(fs_info,
"incorrect extent count for %llu; counted %u, expected %u",
- block_group->key.objectid, extent_count,
+ block_group->start, extent_count,
expected_extent_count);
ASSERT(0);
ret = -EIO;
@@ -1532,7 +1531,7 @@ out:
int load_free_space_tree(struct btrfs_caching_control *caching_ctl)
{
- struct btrfs_block_group_cache *block_group;
+ struct btrfs_block_group *block_group;
struct btrfs_free_space_info *info;
struct btrfs_path *path;
u32 extent_count, flags;
diff --git a/fs/btrfs/free-space-tree.h b/fs/btrfs/free-space-tree.h
index 360d50e1cdea..dc2463e4cfe3 100644
--- a/fs/btrfs/free-space-tree.h
+++ b/fs/btrfs/free-space-tree.h
@@ -16,14 +16,14 @@ struct btrfs_caching_control;
#define BTRFS_FREE_SPACE_BITMAP_SIZE 256
#define BTRFS_FREE_SPACE_BITMAP_BITS (BTRFS_FREE_SPACE_BITMAP_SIZE * BITS_PER_BYTE)
-void set_free_space_tree_thresholds(struct btrfs_block_group_cache *block_group);
+void set_free_space_tree_thresholds(struct btrfs_block_group *block_group);
int btrfs_create_free_space_tree(struct btrfs_fs_info *fs_info);
int btrfs_clear_free_space_tree(struct btrfs_fs_info *fs_info);
int load_free_space_tree(struct btrfs_caching_control *caching_ctl);
int add_block_group_free_space(struct btrfs_trans_handle *trans,
- struct btrfs_block_group_cache *block_group);
+ struct btrfs_block_group *block_group);
int remove_block_group_free_space(struct btrfs_trans_handle *trans,
- struct btrfs_block_group_cache *block_group);
+ struct btrfs_block_group *block_group);
int add_to_free_space_tree(struct btrfs_trans_handle *trans,
u64 start, u64 size);
int remove_from_free_space_tree(struct btrfs_trans_handle *trans,
@@ -32,21 +32,21 @@ int remove_from_free_space_tree(struct btrfs_trans_handle *trans,
#ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS
struct btrfs_free_space_info *
search_free_space_info(struct btrfs_trans_handle *trans,
- struct btrfs_block_group_cache *block_group,
+ struct btrfs_block_group *block_group,
struct btrfs_path *path, int cow);
int __add_to_free_space_tree(struct btrfs_trans_handle *trans,
- struct btrfs_block_group_cache *block_group,
+ struct btrfs_block_group *block_group,
struct btrfs_path *path, u64 start, u64 size);
int __remove_from_free_space_tree(struct btrfs_trans_handle *trans,
- struct btrfs_block_group_cache *block_group,
+ struct btrfs_block_group *block_group,
struct btrfs_path *path, u64 start, u64 size);
int convert_free_space_to_bitmaps(struct btrfs_trans_handle *trans,
- struct btrfs_block_group_cache *block_group,
+ struct btrfs_block_group *block_group,
struct btrfs_path *path);
int convert_free_space_to_extents(struct btrfs_trans_handle *trans,
- struct btrfs_block_group_cache *block_group,
+ struct btrfs_block_group *block_group,
struct btrfs_path *path);
-int free_space_test_bit(struct btrfs_block_group_cache *block_group,
+int free_space_test_bit(struct btrfs_block_group *block_group,
struct btrfs_path *path, u64 offset);
#endif
diff --git a/fs/btrfs/inode-map.c b/fs/btrfs/inode-map.c
index 63cad7865d75..37345fb6191d 100644
--- a/fs/btrfs/inode-map.c
+++ b/fs/btrfs/inode-map.c
@@ -501,13 +501,13 @@ again:
ret = btrfs_prealloc_file_range_trans(inode, trans, 0, 0, prealloc,
prealloc, prealloc, &alloc_hint);
if (ret) {
- btrfs_delalloc_release_extents(BTRFS_I(inode), prealloc, true);
+ btrfs_delalloc_release_extents(BTRFS_I(inode), prealloc);
btrfs_delalloc_release_metadata(BTRFS_I(inode), prealloc, true);
goto out_put;
}
ret = btrfs_write_out_ino_cache(root, trans, path, inode);
- btrfs_delalloc_release_extents(BTRFS_I(inode), prealloc, false);
+ btrfs_delalloc_release_extents(BTRFS_I(inode), prealloc);
out_put:
iput(inode);
out_release:
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 0f2754eaa05b..56032c518b26 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -368,6 +368,7 @@ struct async_chunk {
u64 end;
unsigned int write_flags;
struct list_head extents;
+ struct cgroup_subsys_state *blkcg_css;
struct btrfs_work work;
atomic_t *pending;
};
@@ -474,6 +475,7 @@ static noinline int compress_file_range(struct async_chunk *async_chunk)
u64 start = async_chunk->start;
u64 end = async_chunk->end;
u64 actual_end;
+ u64 i_size;
int ret = 0;
struct page **pages = NULL;
unsigned long nr_pages;
@@ -488,7 +490,19 @@ static noinline int compress_file_range(struct async_chunk *async_chunk)
inode_should_defrag(BTRFS_I(inode), start, end, end - start + 1,
SZ_16K);
- actual_end = min_t(u64, i_size_read(inode), end + 1);
+ /*
+ * We need to save i_size before now because it could change in between
+ * us evaluating the size and assigning it. This is because we lock and
+ * unlock the page in truncate and fallocate, and then modify the i_size
+ * later on.
+ *
+ * The barriers are to emulate READ_ONCE, remove that once i_size_read
+ * does that for us.
+ */
+ barrier();
+ i_size = i_size_read(inode);
+ barrier();
+ actual_end = min_t(u64, i_size, end + 1);
again:
will_compress = 0;
nr_pages = (end >> PAGE_SHIFT) - (start >> PAGE_SHIFT) + 1;
@@ -699,10 +713,12 @@ cleanup_and_bail_uncompressed:
* to our extent and set things up for the async work queue to run
* cow_file_range to do the normal delalloc dance.
*/
- if (page_offset(async_chunk->locked_page) >= start &&
- page_offset(async_chunk->locked_page) <= end)
+ if (async_chunk->locked_page &&
+ (page_offset(async_chunk->locked_page) >= start &&
+ page_offset(async_chunk->locked_page)) <= end) {
__set_page_dirty_nobuffers(async_chunk->locked_page);
/* unlocked later on in the async handlers */
+ }
if (redirty)
extent_range_redirty_for_io(inode, start, end);
@@ -782,7 +798,7 @@ retry:
async_extent->start +
async_extent->ram_size - 1,
WB_SYNC_ALL);
- else if (ret)
+ else if (ret && async_chunk->locked_page)
unlock_page(async_chunk->locked_page);
kfree(async_extent);
cond_resched();
@@ -865,7 +881,8 @@ retry:
ins.objectid,
ins.offset, async_extent->pages,
async_extent->nr_pages,
- async_chunk->write_flags)) {
+ async_chunk->write_flags,
+ async_chunk->blkcg_css)) {
struct page *p = async_extent->pages[0];
const u64 start = async_extent->start;
const u64 end = start + async_extent->ram_size - 1;
@@ -1183,6 +1200,8 @@ static noinline void async_cow_free(struct btrfs_work *work)
async_chunk = container_of(work, struct async_chunk, work);
if (async_chunk->inode)
btrfs_add_delayed_iput(async_chunk->inode);
+ if (async_chunk->blkcg_css)
+ css_put(async_chunk->blkcg_css);
/*
* Since the pointer to 'pending' is at the beginning of the array of
* async_chunk's, freeing it ensures the whole array has been freed.
@@ -1191,12 +1210,14 @@ static noinline void async_cow_free(struct btrfs_work *work)
kvfree(async_chunk->pending);
}
-static int cow_file_range_async(struct inode *inode, struct page *locked_page,
+static int cow_file_range_async(struct inode *inode,
+ struct writeback_control *wbc,
+ struct page *locked_page,
u64 start, u64 end, int *page_started,
- unsigned long *nr_written,
- unsigned int write_flags)
+ unsigned long *nr_written)
{
struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
+ struct cgroup_subsys_state *blkcg_css = wbc_blkcg_css(wbc);
struct async_cow *ctx;
struct async_chunk *async_chunk;
unsigned long nr_pages;
@@ -1205,6 +1226,7 @@ static int cow_file_range_async(struct inode *inode, struct page *locked_page,
int i;
bool should_compress;
unsigned nofs_flag;
+ const unsigned int write_flags = wbc_to_write_flags(wbc);
unlock_extent(&BTRFS_I(inode)->io_tree, start, end);
@@ -1251,14 +1273,45 @@ static int cow_file_range_async(struct inode *inode, struct page *locked_page,
async_chunk[i].inode = inode;
async_chunk[i].start = start;
async_chunk[i].end = cur_end;
- async_chunk[i].locked_page = locked_page;
async_chunk[i].write_flags = write_flags;
INIT_LIST_HEAD(&async_chunk[i].extents);
- btrfs_init_work(&async_chunk[i].work,
- btrfs_delalloc_helper,
- async_cow_start, async_cow_submit,
- async_cow_free);
+ /*
+ * The locked_page comes all the way from writepage and its
+ * the original page we were actually given. As we spread
+ * this large delalloc region across multiple async_chunk
+ * structs, only the first struct needs a pointer to locked_page
+ *
+ * This way we don't need racey decisions about who is supposed
+ * to unlock it.
+ */
+ if (locked_page) {
+ /*
+ * Depending on the compressibility, the pages might or
+ * might not go through async. We want all of them to
+ * be accounted against wbc once. Let's do it here
+ * before the paths diverge. wbc accounting is used
+ * only for foreign writeback detection and doesn't
+ * need full accuracy. Just account the whole thing
+ * against the first page.
+ */
+ wbc_account_cgroup_owner(wbc, locked_page,
+ cur_end - start);
+ async_chunk[i].locked_page = locked_page;
+ locked_page = NULL;
+ } else {
+ async_chunk[i].locked_page = NULL;
+ }
+
+ if (blkcg_css != blkcg_root_css) {
+ css_get(blkcg_css);
+ async_chunk[i].blkcg_css = blkcg_css;
+ } else {
+ async_chunk[i].blkcg_css = NULL;
+ }
+
+ btrfs_init_work(&async_chunk[i].work, async_cow_start,
+ async_cow_submit, async_cow_free);
nr_pages = DIV_ROUND_UP(cur_end - start, PAGE_SIZE);
atomic_add(nr_pages, &fs_info->async_delalloc_pages);
@@ -1684,7 +1737,6 @@ int btrfs_run_delalloc_range(struct inode *inode, struct page *locked_page,
{
int ret;
int force_cow = need_force_cow(inode, start, end);
- unsigned int write_flags = wbc_to_write_flags(wbc);
if (BTRFS_I(inode)->flags & BTRFS_INODE_NODATACOW && !force_cow) {
ret = run_delalloc_nocow(inode, locked_page, start, end,
@@ -1699,9 +1751,8 @@ int btrfs_run_delalloc_range(struct inode *inode, struct page *locked_page,
} else {
set_bit(BTRFS_INODE_HAS_ASYNC_EXTENT,
&BTRFS_I(inode)->runtime_flags);
- ret = cow_file_range_async(inode, locked_page, start, end,
- page_started, nr_written,
- write_flags);
+ ret = cow_file_range_async(inode, wbc, locked_page, start, end,
+ page_started, nr_written);
}
if (ret)
btrfs_cleanup_ordered_extents(inode, locked_page, start,
@@ -2097,7 +2148,7 @@ static blk_status_t btrfs_submit_bio_hook(struct inode *inode, struct bio *bio,
}
mapit:
- ret = btrfs_map_bio(fs_info, bio, mirror_num, 0);
+ ret = btrfs_map_bio(fs_info, bio, mirror_num);
out:
if (ret) {
@@ -2201,12 +2252,16 @@ again:
mapping_set_error(page->mapping, ret);
end_extent_writepage(page, ret, page_start, page_end);
ClearPageChecked(page);
- goto out;
+ goto out_reserved;
}
ClearPageChecked(page);
set_page_dirty(page);
- btrfs_delalloc_release_extents(BTRFS_I(inode), PAGE_SIZE, false);
+out_reserved:
+ btrfs_delalloc_release_extents(BTRFS_I(inode), PAGE_SIZE);
+ if (ret)
+ btrfs_delalloc_release_space(inode, data_reserved, page_start,
+ PAGE_SIZE, true);
out:
unlock_extent_cached(&BTRFS_I(inode)->io_tree, page_start, page_end,
&cached_state);
@@ -2247,8 +2302,7 @@ int btrfs_writepage_cow_fixup(struct page *page, u64 start, u64 end)
SetPageChecked(page);
get_page(page);
- btrfs_init_work(&fixup->work, btrfs_fixup_helper,
- btrfs_writepage_fixup_worker, NULL, NULL);
+ btrfs_init_work(&fixup->work, btrfs_writepage_fixup_worker, NULL, NULL);
fixup->page = page;
btrfs_queue_work(fs_info->fixup_workers, &fixup->work);
return -EBUSY;
@@ -2662,7 +2716,7 @@ static noinline int relink_extent_backref(struct btrfs_path *path,
key.type = BTRFS_INODE_ITEM_KEY;
key.offset = 0;
- inode = btrfs_iget(fs_info->sb, &key, root, NULL);
+ inode = btrfs_iget(fs_info->sb, &key, root);
if (IS_ERR(inode)) {
srcu_read_unlock(&fs_info->subvol_srcu, index);
return 0;
@@ -2986,7 +3040,7 @@ out_kfree:
static void btrfs_release_delalloc_bytes(struct btrfs_fs_info *fs_info,
u64 start, u64 len)
{
- struct btrfs_block_group_cache *cache;
+ struct btrfs_block_group *cache;
cache = btrfs_lookup_block_group(fs_info, start);
ASSERT(cache);
@@ -3014,7 +3068,7 @@ static int btrfs_finish_ordered_io(struct btrfs_ordered_extent *ordered_extent)
int compress_type = 0;
int ret = 0;
u64 logical_len = ordered_extent->len;
- bool nolock;
+ bool freespace_inode;
bool truncated = false;
bool range_locked = false;
bool clear_new_delalloc_bytes = false;
@@ -3025,7 +3079,7 @@ static int btrfs_finish_ordered_io(struct btrfs_ordered_extent *ordered_extent)
!test_bit(BTRFS_ORDERED_DIRECT, &ordered_extent->flags))
clear_new_delalloc_bytes = true;
- nolock = btrfs_is_free_space_inode(BTRFS_I(inode));
+ freespace_inode = btrfs_is_free_space_inode(BTRFS_I(inode));
if (test_bit(BTRFS_ORDERED_IOERR, &ordered_extent->flags)) {
ret = -EIO;
@@ -3056,8 +3110,8 @@ static int btrfs_finish_ordered_io(struct btrfs_ordered_extent *ordered_extent)
btrfs_qgroup_free_data(inode, NULL, ordered_extent->file_offset,
ordered_extent->len);
btrfs_ordered_update_i_size(inode, 0, ordered_extent);
- if (nolock)
- trans = btrfs_join_transaction_nolock(root);
+ if (freespace_inode)
+ trans = btrfs_join_transaction_spacecache(root);
else
trans = btrfs_join_transaction(root);
if (IS_ERR(trans)) {
@@ -3091,8 +3145,8 @@ static int btrfs_finish_ordered_io(struct btrfs_ordered_extent *ordered_extent)
EXTENT_DEFRAG, 0, 0, &cached_state);
}
- if (nolock)
- trans = btrfs_join_transaction_nolock(root);
+ if (freespace_inode)
+ trans = btrfs_join_transaction_spacecache(root);
else
trans = btrfs_join_transaction(root);
if (IS_ERR(trans)) {
@@ -3241,7 +3295,6 @@ void btrfs_writepage_endio_finish_ordered(struct page *page, u64 start,
struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
struct btrfs_ordered_extent *ordered_extent = NULL;
struct btrfs_workqueue *wq;
- btrfs_work_func_t func;
trace_btrfs_writepage_end_io_hook(page, start, end, uptodate);
@@ -3250,16 +3303,12 @@ void btrfs_writepage_endio_finish_ordered(struct page *page, u64 start,
end - start + 1, uptodate))
return;
- if (btrfs_is_free_space_inode(BTRFS_I(inode))) {
+ if (btrfs_is_free_space_inode(BTRFS_I(inode)))
wq = fs_info->endio_freespace_worker;
- func = btrfs_freespace_write_helper;
- } else {
+ else
wq = fs_info->endio_write_workers;
- func = btrfs_endio_write_helper;
- }
- btrfs_init_work(&ordered_extent->work, func, finish_ordered_fn, NULL,
- NULL);
+ btrfs_init_work(&ordered_extent->work, finish_ordered_fn, NULL, NULL);
btrfs_queue_work(wq, &ordered_extent->work);
}
@@ -3518,7 +3567,7 @@ int btrfs_orphan_cleanup(struct btrfs_root *root)
found_key.objectid = found_key.offset;
found_key.type = BTRFS_INODE_ITEM_KEY;
found_key.offset = 0;
- inode = btrfs_iget(fs_info->sb, &found_key, root, NULL);
+ inode = btrfs_iget(fs_info->sb, &found_key, root);
ret = PTR_ERR_OR_ZERO(inode);
if (ret && ret != -ENOENT)
goto out;
@@ -4951,7 +5000,7 @@ again:
if (!page) {
btrfs_delalloc_release_space(inode, data_reserved,
block_start, blocksize, true);
- btrfs_delalloc_release_extents(BTRFS_I(inode), blocksize, true);
+ btrfs_delalloc_release_extents(BTRFS_I(inode), blocksize);
ret = -ENOMEM;
goto out;
}
@@ -5018,7 +5067,7 @@ out_unlock:
if (ret)
btrfs_delalloc_release_space(inode, data_reserved, block_start,
blocksize, true);
- btrfs_delalloc_release_extents(BTRFS_I(inode), blocksize, (ret != 0));
+ btrfs_delalloc_release_extents(BTRFS_I(inode), blocksize);
unlock_page(page);
put_page(page);
out:
@@ -5140,7 +5189,6 @@ int btrfs_cont_expand(struct inode *inode, loff_t oldsize, loff_t size)
hole_em->block_len = 0;
hole_em->orig_block_len = 0;
hole_em->ram_bytes = hole_size;
- hole_em->bdev = fs_info->fs_devices->latest_bdev;
hole_em->compress_type = BTRFS_COMPRESS_NONE;
hole_em->generation = fs_info->generation;
@@ -5737,12 +5785,14 @@ static struct inode *btrfs_iget_locked(struct super_block *s,
return inode;
}
-/* Get an inode object given its location and corresponding root.
- * Returns in *is_new if the inode was read from disk
+/*
+ * Get an inode object given its location and corresponding root.
+ * Path can be preallocated to prevent recursing back to iget through
+ * allocator. NULL is also valid but may require an additional allocation
+ * later.
*/
struct inode *btrfs_iget_path(struct super_block *s, struct btrfs_key *location,
- struct btrfs_root *root, int *new,
- struct btrfs_path *path)
+ struct btrfs_root *root, struct btrfs_path *path)
{
struct inode *inode;
@@ -5757,8 +5807,6 @@ struct inode *btrfs_iget_path(struct super_block *s, struct btrfs_key *location,
if (!ret) {
inode_tree_add(inode);
unlock_new_inode(inode);
- if (new)
- *new = 1;
} else {
iget_failed(inode);
/*
@@ -5776,9 +5824,9 @@ struct inode *btrfs_iget_path(struct super_block *s, struct btrfs_key *location,
}
struct inode *btrfs_iget(struct super_block *s, struct btrfs_key *location,
- struct btrfs_root *root, int *new)
+ struct btrfs_root *root)
{
- return btrfs_iget_path(s, location, root, new, NULL);
+ return btrfs_iget_path(s, location, root, NULL);
}
static struct inode *new_simple_dir(struct super_block *s,
@@ -5844,7 +5892,7 @@ struct inode *btrfs_lookup_dentry(struct inode *dir, struct dentry *dentry)
return ERR_PTR(ret);
if (location.type == BTRFS_INODE_ITEM_KEY) {
- inode = btrfs_iget(dir->i_sb, &location, root, NULL);
+ inode = btrfs_iget(dir->i_sb, &location, root);
if (IS_ERR(inode))
return inode;
@@ -5869,7 +5917,7 @@ struct inode *btrfs_lookup_dentry(struct inode *dir, struct dentry *dentry)
else
inode = new_simple_dir(dir->i_sb, &location, sub_root);
} else {
- inode = btrfs_iget(dir->i_sb, &location, sub_root, NULL);
+ inode = btrfs_iget(dir->i_sb, &location, sub_root);
}
srcu_read_unlock(&fs_info->subvol_srcu, index);
@@ -6918,8 +6966,6 @@ struct extent_map *btrfs_get_extent(struct btrfs_inode *inode,
read_lock(&em_tree->lock);
em = lookup_extent_mapping(em_tree, start, len);
- if (em)
- em->bdev = fs_info->fs_devices->latest_bdev;
read_unlock(&em_tree->lock);
if (em) {
@@ -6935,7 +6981,6 @@ struct extent_map *btrfs_get_extent(struct btrfs_inode *inode,
err = -ENOMEM;
goto out;
}
- em->bdev = fs_info->fs_devices->latest_bdev;
em->start = EXTENT_MAP_HOLE;
em->orig_start = EXTENT_MAP_HOLE;
em->len = (u64)-1;
@@ -7194,7 +7239,6 @@ struct extent_map *btrfs_get_extent_fiemap(struct btrfs_inode *inode,
err = -ENOMEM;
goto out;
}
- em->bdev = NULL;
ASSERT(hole_em);
/*
@@ -7554,7 +7598,6 @@ static struct extent_map *create_io_em(struct inode *inode, u64 start, u64 len,
{
struct extent_map_tree *em_tree;
struct extent_map *em;
- struct btrfs_root *root = BTRFS_I(inode)->root;
int ret;
ASSERT(type == BTRFS_ORDERED_PREALLOC ||
@@ -7572,7 +7615,6 @@ static struct extent_map *create_io_em(struct inode *inode, u64 start, u64 len,
em->len = len;
em->block_len = block_len;
em->block_start = block_start;
- em->bdev = root->fs_info->fs_devices->latest_bdev;
em->orig_block_len = orig_block_len;
em->ram_bytes = ram_bytes;
em->generation = -1;
@@ -7611,6 +7653,8 @@ static int btrfs_get_blocks_direct_read(struct extent_map *em,
struct inode *inode,
u64 start, u64 len)
{
+ struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
+
if (em->block_start == EXTENT_MAP_HOLE ||
test_bit(EXTENT_FLAG_PREALLOC, &em->flags))
return -ENOENT;
@@ -7620,7 +7664,7 @@ static int btrfs_get_blocks_direct_read(struct extent_map *em,
bh_result->b_blocknr = (em->block_start + (start - em->start)) >>
inode->i_blkbits;
bh_result->b_size = len;
- bh_result->b_bdev = em->bdev;
+ bh_result->b_bdev = fs_info->fs_devices->latest_bdev;
set_buffer_mapped(bh_result);
return 0;
@@ -7703,7 +7747,7 @@ skip_cow:
bh_result->b_blocknr = (em->block_start + (start - em->start)) >>
inode->i_blkbits;
bh_result->b_size = len;
- bh_result->b_bdev = em->bdev;
+ bh_result->b_bdev = fs_info->fs_devices->latest_bdev;
set_buffer_mapped(bh_result);
if (!test_bit(EXTENT_FLAG_PREALLOC, &em->flags))
@@ -7845,7 +7889,7 @@ static inline blk_status_t submit_dio_repair_bio(struct inode *inode,
if (ret)
return ret;
- ret = btrfs_map_bio(fs_info, bio, mirror_num, 0);
+ ret = btrfs_map_bio(fs_info, bio, mirror_num);
return ret;
}
@@ -8198,18 +8242,14 @@ static void __endio_write_update_ordered(struct inode *inode,
struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
struct btrfs_ordered_extent *ordered = NULL;
struct btrfs_workqueue *wq;
- btrfs_work_func_t func;
u64 ordered_offset = offset;
u64 ordered_bytes = bytes;
u64 last_offset;
- if (btrfs_is_free_space_inode(BTRFS_I(inode))) {
+ if (btrfs_is_free_space_inode(BTRFS_I(inode)))
wq = fs_info->endio_freespace_worker;
- func = btrfs_freespace_write_helper;
- } else {
+ else
wq = fs_info->endio_write_workers;
- func = btrfs_endio_write_helper;
- }
while (ordered_offset < offset + bytes) {
last_offset = ordered_offset;
@@ -8217,9 +8257,8 @@ static void __endio_write_update_ordered(struct inode *inode,
&ordered_offset,
ordered_bytes,
uptodate)) {
- btrfs_init_work(&ordered->work, func,
- finish_ordered_fn,
- NULL, NULL);
+ btrfs_init_work(&ordered->work, finish_ordered_fn, NULL,
+ NULL);
btrfs_queue_work(wq, &ordered->work);
}
/*
@@ -8376,7 +8415,7 @@ static inline blk_status_t btrfs_submit_dio_bio(struct bio *bio,
goto err;
}
map:
- ret = btrfs_map_bio(fs_info, bio, 0, 0);
+ ret = btrfs_map_bio(fs_info, bio, 0);
err:
return ret;
}
@@ -8709,7 +8748,7 @@ static ssize_t btrfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
} else if (ret >= 0 && (size_t)ret < count)
btrfs_delalloc_release_space(inode, data_reserved,
offset, count - (size_t)ret, true);
- btrfs_delalloc_release_extents(BTRFS_I(inode), count, false);
+ btrfs_delalloc_release_extents(BTRFS_I(inode), count);
}
out:
if (wakeup)
@@ -9059,7 +9098,7 @@ again:
unlock_extent_cached(io_tree, page_start, page_end, &cached_state);
if (!ret2) {
- btrfs_delalloc_release_extents(BTRFS_I(inode), PAGE_SIZE, true);
+ btrfs_delalloc_release_extents(BTRFS_I(inode), PAGE_SIZE);
sb_end_pagefault(inode->i_sb);
extent_changeset_free(data_reserved);
return VM_FAULT_LOCKED;
@@ -9068,7 +9107,7 @@ again:
out_unlock:
unlock_page(page);
out:
- btrfs_delalloc_release_extents(BTRFS_I(inode), PAGE_SIZE, (ret != 0));
+ btrfs_delalloc_release_extents(BTRFS_I(inode), PAGE_SIZE);
btrfs_delalloc_release_space(inode, data_reserved, page_start,
reserved_space, (ret != 0));
out_noreserve:
@@ -9308,7 +9347,6 @@ struct inode *btrfs_alloc_inode(struct super_block *sb)
ei->io_failure_tree.track_uptodate = true;
atomic_set(&ei->sync_writers, 0);
mutex_init(&ei->log_mutex);
- mutex_init(&ei->delalloc_mutex);
btrfs_ordered_inode_tree_init(&ei->ordered_tree);
INIT_LIST_HEAD(&ei->delalloc_inodes);
INIT_LIST_HEAD(&ei->delayed_iput);
@@ -9537,6 +9575,9 @@ static int btrfs_rename_exchange(struct inode *old_dir,
goto out_notrans;
}
+ if (dest != root)
+ btrfs_record_root_in_trans(trans, dest);
+
/*
* We need to find a free sequence number both in the source and
* in the destination directory for the exchange.
@@ -9731,6 +9772,18 @@ out_fail:
commit_transaction = true;
}
if (commit_transaction) {
+ /*
+ * We may have set commit_transaction when logging the new name
+ * in the destination root, in which case we left the source
+ * root context in the list of log contextes. So make sure we
+ * remove it to avoid invalid memory accesses, since the context
+ * was allocated in our stack frame.
+ */
+ if (sync_log_root) {
+ mutex_lock(&root->log_mutex);
+ list_del_init(&ctx_root.list);
+ mutex_unlock(&root->log_mutex);
+ }
ret = btrfs_commit_transaction(trans);
} else {
int ret2;
@@ -9744,6 +9797,9 @@ out_notrans:
if (old_ino == BTRFS_FIRST_FREE_OBJECTID)
up_read(&fs_info->subvol_sem);
+ ASSERT(list_empty(&ctx_root.list));
+ ASSERT(list_empty(&ctx_dest.list));
+
return ret;
}
@@ -10088,8 +10144,7 @@ static struct btrfs_delalloc_work *btrfs_alloc_delalloc_work(struct inode *inode
init_completion(&work->completion);
INIT_LIST_HEAD(&work->list);
work->inode = inode;
- btrfs_init_work(&work->work, btrfs_flush_delalloc_helper,
- btrfs_run_delalloc_work, NULL, NULL);
+ btrfs_init_work(&work->work, btrfs_run_delalloc_work, NULL, NULL);
return work;
}
@@ -10422,7 +10477,6 @@ static int __btrfs_prealloc_file_range(struct inode *inode, int mode,
em->block_len = ins.offset;
em->orig_block_len = ins.offset;
em->ram_bytes = ins.offset;
- em->bdev = fs_info->fs_devices->latest_bdev;
set_bit(EXTENT_FLAG_PREALLOC, &em->flags);
em->generation = trans->transid;
@@ -10778,7 +10832,7 @@ static int btrfs_swap_activate(struct swap_info_struct *sis, struct file *file,
start = 0;
while (start < isize) {
u64 logical_block_start, physical_block_start;
- struct btrfs_block_group_cache *bg;
+ struct btrfs_block_group *bg;
u64 len = isize - start;
em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, start, len, 0);
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index de730e56d3f5..a1ee0b775e65 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -479,10 +479,9 @@ static int btrfs_ioctl_getversion(struct file *file, int __user *arg)
return put_user(inode->i_generation, arg);
}
-static noinline int btrfs_ioctl_fitrim(struct file *file, void __user *arg)
+static noinline int btrfs_ioctl_fitrim(struct btrfs_fs_info *fs_info,
+ void __user *arg)
{
- struct inode *inode = file_inode(file);
- struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
struct btrfs_device *device;
struct request_queue *q;
struct fstrim_range range;
@@ -541,7 +540,7 @@ static noinline int btrfs_ioctl_fitrim(struct file *file, void __user *arg)
return 0;
}
-int btrfs_is_empty_uuid(u8 *uuid)
+int __pure btrfs_is_empty_uuid(u8 *uuid)
{
int i;
@@ -1360,8 +1359,7 @@ again:
unlock_page(pages[i]);
put_page(pages[i]);
}
- btrfs_delalloc_release_extents(BTRFS_I(inode), page_cnt << PAGE_SHIFT,
- false);
+ btrfs_delalloc_release_extents(BTRFS_I(inode), page_cnt << PAGE_SHIFT);
extent_changeset_free(data_reserved);
return i_done;
out:
@@ -1372,8 +1370,7 @@ out:
btrfs_delalloc_release_space(inode, data_reserved,
start_index << PAGE_SHIFT,
page_cnt << PAGE_SHIFT, true);
- btrfs_delalloc_release_extents(BTRFS_I(inode), page_cnt << PAGE_SHIFT,
- true);
+ btrfs_delalloc_release_extents(BTRFS_I(inode), page_cnt << PAGE_SHIFT);
extent_changeset_free(data_reserved);
return ret;
@@ -1411,7 +1408,7 @@ int btrfs_defrag_file(struct inode *inode, struct file *file,
return -EINVAL;
if (do_compress) {
- if (range->compress_type > BTRFS_COMPRESS_TYPES)
+ if (range->compress_type >= BTRFS_NR_COMPRESS_TYPES)
return -EINVAL;
if (range->compress_type)
compress_type = range->compress_type;
@@ -2464,7 +2461,7 @@ static int btrfs_search_path_in_tree_user(struct inode *inode,
goto out;
}
- temp_inode = btrfs_iget(sb, &key2, root, NULL);
+ temp_inode = btrfs_iget(sb, &key2, root);
if (IS_ERR(temp_inode)) {
ret = PTR_ERR(temp_inode);
goto out;
@@ -4034,16 +4031,15 @@ out:
static void get_block_group_info(struct list_head *groups_list,
struct btrfs_ioctl_space_info *space)
{
- struct btrfs_block_group_cache *block_group;
+ struct btrfs_block_group *block_group;
space->total_bytes = 0;
space->used_bytes = 0;
space->flags = 0;
list_for_each_entry(block_group, groups_list, list) {
space->flags = block_group->flags;
- space->total_bytes += block_group->key.offset;
- space->used_bytes +=
- btrfs_block_group_used(&block_group->item);
+ space->total_bytes += block_group->length;
+ space->used_bytes += block_group->used;
}
}
@@ -4197,9 +4193,6 @@ static noinline long btrfs_ioctl_start_sync(struct btrfs_root *root,
u64 transid;
int ret;
- btrfs_warn(root->fs_info,
- "START_SYNC ioctl is deprecated and will be removed in kernel 5.7");
-
trans = btrfs_attach_transaction_barrier(root);
if (IS_ERR(trans)) {
if (PTR_ERR(trans) != -ENOENT)
@@ -4227,9 +4220,6 @@ static noinline long btrfs_ioctl_wait_sync(struct btrfs_fs_info *fs_info,
{
u64 transid;
- btrfs_warn(fs_info,
- "WAIT_SYNC ioctl is deprecated and will be removed in kernel 5.7");
-
if (argp) {
if (copy_from_user(&transid, argp, sizeof(transid)))
return -EFAULT;
@@ -4960,10 +4950,9 @@ drop_write:
return ret;
}
-static long btrfs_ioctl_quota_rescan_status(struct file *file, void __user *arg)
+static long btrfs_ioctl_quota_rescan_status(struct btrfs_fs_info *fs_info,
+ void __user *arg)
{
- struct inode *inode = file_inode(file);
- struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
struct btrfs_ioctl_quota_rescan_args *qsa;
int ret = 0;
@@ -4986,11 +4975,9 @@ static long btrfs_ioctl_quota_rescan_status(struct file *file, void __user *arg)
return ret;
}
-static long btrfs_ioctl_quota_rescan_wait(struct file *file, void __user *arg)
+static long btrfs_ioctl_quota_rescan_wait(struct btrfs_fs_info *fs_info,
+ void __user *arg)
{
- struct inode *inode = file_inode(file);
- struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
-
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
@@ -5162,10 +5149,9 @@ out:
return ret;
}
-static int btrfs_ioctl_get_fslabel(struct file *file, void __user *arg)
+static int btrfs_ioctl_get_fslabel(struct btrfs_fs_info *fs_info,
+ void __user *arg)
{
- struct inode *inode = file_inode(file);
- struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
size_t len;
int ret;
char label[BTRFS_LABEL_SIZE];
@@ -5249,10 +5235,9 @@ int btrfs_ioctl_get_supported_features(void __user *arg)
return 0;
}
-static int btrfs_ioctl_get_features(struct file *file, void __user *arg)
+static int btrfs_ioctl_get_features(struct btrfs_fs_info *fs_info,
+ void __user *arg)
{
- struct inode *inode = file_inode(file);
- struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
struct btrfs_super_block *super_block = fs_info->super_copy;
struct btrfs_ioctl_feature_flags features;
@@ -5453,11 +5438,11 @@ long btrfs_ioctl(struct file *file, unsigned int
case FS_IOC_GETVERSION:
return btrfs_ioctl_getversion(file, argp);
case FS_IOC_GETFSLABEL:
- return btrfs_ioctl_get_fslabel(file, argp);
+ return btrfs_ioctl_get_fslabel(fs_info, argp);
case FS_IOC_SETFSLABEL:
return btrfs_ioctl_set_fslabel(file, argp);
case FITRIM:
- return btrfs_ioctl_fitrim(file, argp);
+ return btrfs_ioctl_fitrim(fs_info, argp);
case BTRFS_IOC_SNAP_CREATE:
return btrfs_ioctl_snap_create(file, argp, 0);
case BTRFS_IOC_SNAP_CREATE_V2:
@@ -5562,15 +5547,15 @@ long btrfs_ioctl(struct file *file, unsigned int
case BTRFS_IOC_QUOTA_RESCAN:
return btrfs_ioctl_quota_rescan(file, argp);
case BTRFS_IOC_QUOTA_RESCAN_STATUS:
- return btrfs_ioctl_quota_rescan_status(file, argp);
+ return btrfs_ioctl_quota_rescan_status(fs_info, argp);
case BTRFS_IOC_QUOTA_RESCAN_WAIT:
- return btrfs_ioctl_quota_rescan_wait(file, argp);
+ return btrfs_ioctl_quota_rescan_wait(fs_info, argp);
case BTRFS_IOC_DEV_REPLACE:
return btrfs_ioctl_dev_replace(fs_info, argp);
case BTRFS_IOC_GET_SUPPORTED_FEATURES:
return btrfs_ioctl_get_supported_features(argp);
case BTRFS_IOC_GET_FEATURES:
- return btrfs_ioctl_get_features(file, argp);
+ return btrfs_ioctl_get_features(fs_info, argp);
case BTRFS_IOC_SET_FEATURES:
return btrfs_ioctl_set_features(file, argp);
case FS_IOC_FSGETXATTR:
diff --git a/fs/btrfs/locking.c b/fs/btrfs/locking.c
index 7f9a578a1a20..571c4826c428 100644
--- a/fs/btrfs/locking.c
+++ b/fs/btrfs/locking.c
@@ -13,65 +13,164 @@
#include "extent_io.h"
#include "locking.h"
+/*
+ * Extent buffer locking
+ * =====================
+ *
+ * The locks use a custom scheme that allows to do more operations than are
+ * available fromt current locking primitives. The building blocks are still
+ * rwlock and wait queues.
+ *
+ * Required semantics:
+ *
+ * - reader/writer exclusion
+ * - writer/writer exclusion
+ * - reader/reader sharing
+ * - spinning lock semantics
+ * - blocking lock semantics
+ * - try-lock semantics for readers and writers
+ * - one level nesting, allowing read lock to be taken by the same thread that
+ * already has write lock
+ *
+ * The extent buffer locks (also called tree locks) manage access to eb data
+ * related to the storage in the b-tree (keys, items, but not the individual
+ * members of eb).
+ * We want concurrency of many readers and safe updates. The underlying locking
+ * is done by read-write spinlock and the blocking part is implemented using
+ * counters and wait queues.
+ *
+ * spinning semantics - the low-level rwlock is held so all other threads that
+ * want to take it are spinning on it.
+ *
+ * blocking semantics - the low-level rwlock is not held but the counter
+ * denotes how many times the blocking lock was held;
+ * sleeping is possible
+ *
+ * Write lock always allows only one thread to access the data.
+ *
+ *
+ * Debugging
+ * ---------
+ *
+ * There are additional state counters that are asserted in various contexts,
+ * removed from non-debug build to reduce extent_buffer size and for
+ * performance reasons.
+ *
+ *
+ * Lock nesting
+ * ------------
+ *
+ * A write operation on a tree might indirectly start a look up on the same
+ * tree. This can happen when btrfs_cow_block locks the tree and needs to
+ * lookup free extents.
+ *
+ * btrfs_cow_block
+ * ..
+ * alloc_tree_block_no_bg_flush
+ * btrfs_alloc_tree_block
+ * btrfs_reserve_extent
+ * ..
+ * load_free_space_cache
+ * ..
+ * btrfs_lookup_file_extent
+ * btrfs_search_slot
+ *
+ *
+ * Locking pattern - spinning
+ * --------------------------
+ *
+ * The simple locking scenario, the +--+ denotes the spinning section.
+ *
+ * +- btrfs_tree_lock
+ * | - extent_buffer::rwlock is held
+ * | - no heavy operations should happen, eg. IO, memory allocations, large
+ * | structure traversals
+ * +- btrfs_tree_unock
+*
+*
+ * Locking pattern - blocking
+ * --------------------------
+ *
+ * The blocking write uses the following scheme. The +--+ denotes the spinning
+ * section.
+ *
+ * +- btrfs_tree_lock
+ * |
+ * +- btrfs_set_lock_blocking_write
+ *
+ * - allowed: IO, memory allocations, etc.
+ *
+ * -- btrfs_tree_unlock - note, no explicit unblocking necessary
+ *
+ *
+ * Blocking read is similar.
+ *
+ * +- btrfs_tree_read_lock
+ * |
+ * +- btrfs_set_lock_blocking_read
+ *
+ * - heavy operations allowed
+ *
+ * +- btrfs_tree_read_unlock_blocking
+ * |
+ * +- btrfs_tree_read_unlock
+ *
+ */
+
#ifdef CONFIG_BTRFS_DEBUG
-static void btrfs_assert_spinning_writers_get(struct extent_buffer *eb)
+static inline void btrfs_assert_spinning_writers_get(struct extent_buffer *eb)
{
WARN_ON(eb->spinning_writers);
eb->spinning_writers++;
}
-static void btrfs_assert_spinning_writers_put(struct extent_buffer *eb)
+static inline void btrfs_assert_spinning_writers_put(struct extent_buffer *eb)
{
WARN_ON(eb->spinning_writers != 1);
eb->spinning_writers--;
}
-static void btrfs_assert_no_spinning_writers(struct extent_buffer *eb)
+static inline void btrfs_assert_no_spinning_writers(struct extent_buffer *eb)
{
WARN_ON(eb->spinning_writers);
}
-static void btrfs_assert_spinning_readers_get(struct extent_buffer *eb)
+static inline void btrfs_assert_spinning_readers_get(struct extent_buffer *eb)
{
atomic_inc(&eb->spinning_readers);
}
-static void btrfs_assert_spinning_readers_put(struct extent_buffer *eb)
+static inline void btrfs_assert_spinning_readers_put(struct extent_buffer *eb)
{
WARN_ON(atomic_read(&eb->spinning_readers) == 0);
atomic_dec(&eb->spinning_readers);
}
-static void btrfs_assert_tree_read_locks_get(struct extent_buffer *eb)
+static inline void btrfs_assert_tree_read_locks_get(struct extent_buffer *eb)
{
atomic_inc(&eb->read_locks);
}
-static void btrfs_assert_tree_read_locks_put(struct extent_buffer *eb)
+static inline void btrfs_assert_tree_read_locks_put(struct extent_buffer *eb)
{
atomic_dec(&eb->read_locks);
}
-static void btrfs_assert_tree_read_locked(struct extent_buffer *eb)
+static inline void btrfs_assert_tree_read_locked(struct extent_buffer *eb)
{
BUG_ON(!atomic_read(&eb->read_locks));
}
-static void btrfs_assert_tree_write_locks_get(struct extent_buffer *eb)
+static inline void btrfs_assert_tree_write_locks_get(struct extent_buffer *eb)
{
eb->write_locks++;
}
-static void btrfs_assert_tree_write_locks_put(struct extent_buffer *eb)
+static inline void btrfs_assert_tree_write_locks_put(struct extent_buffer *eb)
{
eb->write_locks--;
}
-void btrfs_assert_tree_locked(struct extent_buffer *eb)
-{
- BUG_ON(!eb->write_locks);
-}
-
#else
static void btrfs_assert_spinning_writers_get(struct extent_buffer *eb) { }
static void btrfs_assert_spinning_writers_put(struct extent_buffer *eb) { }
@@ -81,11 +180,19 @@ static void btrfs_assert_spinning_readers_get(struct extent_buffer *eb) { }
static void btrfs_assert_tree_read_locked(struct extent_buffer *eb) { }
static void btrfs_assert_tree_read_locks_get(struct extent_buffer *eb) { }
static void btrfs_assert_tree_read_locks_put(struct extent_buffer *eb) { }
-void btrfs_assert_tree_locked(struct extent_buffer *eb) { }
static void btrfs_assert_tree_write_locks_get(struct extent_buffer *eb) { }
static void btrfs_assert_tree_write_locks_put(struct extent_buffer *eb) { }
#endif
+/*
+ * Mark already held read lock as blocking. Can be nested in write lock by the
+ * same thread.
+ *
+ * Use when there are potentially long operations ahead so other thread waiting
+ * on the lock will not actively spin but sleep instead.
+ *
+ * The rwlock is released and blocking reader counter is increased.
+ */
void btrfs_set_lock_blocking_read(struct extent_buffer *eb)
{
trace_btrfs_set_lock_blocking_read(eb);
@@ -102,6 +209,14 @@ void btrfs_set_lock_blocking_read(struct extent_buffer *eb)
read_unlock(&eb->lock);
}
+/*
+ * Mark already held write lock as blocking.
+ *
+ * Use when there are potentially long operations ahead so other threads
+ * waiting on the lock will not actively spin but sleep instead.
+ *
+ * The rwlock is released and blocking writers is set.
+ */
void btrfs_set_lock_blocking_write(struct extent_buffer *eb)
{
trace_btrfs_set_lock_blocking_write(eb);
@@ -115,14 +230,19 @@ void btrfs_set_lock_blocking_write(struct extent_buffer *eb)
if (eb->blocking_writers == 0) {
btrfs_assert_spinning_writers_put(eb);
btrfs_assert_tree_locked(eb);
- eb->blocking_writers++;
+ WRITE_ONCE(eb->blocking_writers, 1);
write_unlock(&eb->lock);
}
}
/*
- * take a spinning read lock. This will wait for any blocking
- * writers
+ * Lock the extent buffer for read. Wait for any writers (spinning or blocking).
+ * Can be nested in write lock by the same thread.
+ *
+ * Use when the locked section does only lightweight actions and busy waiting
+ * would be cheaper than making other threads do the wait/wake loop.
+ *
+ * The rwlock is held upon exit.
*/
void btrfs_tree_read_lock(struct extent_buffer *eb)
{
@@ -134,23 +254,24 @@ again:
read_lock(&eb->lock);
BUG_ON(eb->blocking_writers == 0 &&
current->pid == eb->lock_owner);
- if (eb->blocking_writers && current->pid == eb->lock_owner) {
- /*
- * This extent is already write-locked by our thread. We allow
- * an additional read lock to be added because it's for the same
- * thread. btrfs_find_all_roots() depends on this as it may be
- * called on a partly (write-)locked tree.
- */
- BUG_ON(eb->lock_nested);
- eb->lock_nested = true;
- read_unlock(&eb->lock);
- trace_btrfs_tree_read_lock(eb, start_ns);
- return;
- }
if (eb->blocking_writers) {
+ if (current->pid == eb->lock_owner) {
+ /*
+ * This extent is already write-locked by our thread.
+ * We allow an additional read lock to be added because
+ * it's for the same thread. btrfs_find_all_roots()
+ * depends on this as it may be called on a partly
+ * (write-)locked tree.
+ */
+ BUG_ON(eb->lock_nested);
+ eb->lock_nested = true;
+ read_unlock(&eb->lock);
+ trace_btrfs_tree_read_lock(eb, start_ns);
+ return;
+ }
read_unlock(&eb->lock);
wait_event(eb->write_lock_wq,
- eb->blocking_writers == 0);
+ READ_ONCE(eb->blocking_writers) == 0);
goto again;
}
btrfs_assert_tree_read_locks_get(eb);
@@ -159,17 +280,19 @@ again:
}
/*
- * take a spinning read lock.
- * returns 1 if we get the read lock and 0 if we don't
- * this won't wait for blocking writers
+ * Lock extent buffer for read, optimistically expecting that there are no
+ * contending blocking writers. If there are, don't wait.
+ *
+ * Return 1 if the rwlock has been taken, 0 otherwise
*/
int btrfs_tree_read_lock_atomic(struct extent_buffer *eb)
{
- if (eb->blocking_writers)
+ if (READ_ONCE(eb->blocking_writers))
return 0;
read_lock(&eb->lock);
- if (eb->blocking_writers) {
+ /* Refetch value after lock */
+ if (READ_ONCE(eb->blocking_writers)) {
read_unlock(&eb->lock);
return 0;
}
@@ -180,18 +303,20 @@ int btrfs_tree_read_lock_atomic(struct extent_buffer *eb)
}
/*
- * returns 1 if we get the read lock and 0 if we don't
- * this won't wait for blocking writers
+ * Try-lock for read. Don't block or wait for contending writers.
+ *
+ * Retrun 1 if the rwlock has been taken, 0 otherwise
*/
int btrfs_try_tree_read_lock(struct extent_buffer *eb)
{
- if (eb->blocking_writers)
+ if (READ_ONCE(eb->blocking_writers))
return 0;
if (!read_trylock(&eb->lock))
return 0;
- if (eb->blocking_writers) {
+ /* Refetch value after lock */
+ if (READ_ONCE(eb->blocking_writers)) {
read_unlock(&eb->lock);
return 0;
}
@@ -202,16 +327,19 @@ int btrfs_try_tree_read_lock(struct extent_buffer *eb)
}
/*
- * returns 1 if we get the read lock and 0 if we don't
- * this won't wait for blocking writers or readers
+ * Try-lock for write. May block until the lock is uncontended, but does not
+ * wait until it is free.
+ *
+ * Retrun 1 if the rwlock has been taken, 0 otherwise
*/
int btrfs_try_tree_write_lock(struct extent_buffer *eb)
{
- if (eb->blocking_writers || atomic_read(&eb->blocking_readers))
+ if (READ_ONCE(eb->blocking_writers) || atomic_read(&eb->blocking_readers))
return 0;
write_lock(&eb->lock);
- if (eb->blocking_writers || atomic_read(&eb->blocking_readers)) {
+ /* Refetch value after lock */
+ if (READ_ONCE(eb->blocking_writers) || atomic_read(&eb->blocking_readers)) {
write_unlock(&eb->lock);
return 0;
}
@@ -223,7 +351,10 @@ int btrfs_try_tree_write_lock(struct extent_buffer *eb)
}
/*
- * drop a spinning read lock
+ * Release read lock. Must be used only if the lock is in spinning mode. If
+ * the read lock is nested, must pair with read lock before the write unlock.
+ *
+ * The rwlock is not held upon exit.
*/
void btrfs_tree_read_unlock(struct extent_buffer *eb)
{
@@ -245,7 +376,11 @@ void btrfs_tree_read_unlock(struct extent_buffer *eb)
}
/*
- * drop a blocking read lock
+ * Release read lock, previously set to blocking by a pairing call to
+ * btrfs_set_lock_blocking_read(). Can be nested in write lock by the same
+ * thread.
+ *
+ * State of rwlock is unchanged, last reader wakes waiting threads.
*/
void btrfs_tree_read_unlock_blocking(struct extent_buffer *eb)
{
@@ -269,8 +404,10 @@ void btrfs_tree_read_unlock_blocking(struct extent_buffer *eb)
}
/*
- * take a spinning write lock. This will wait for both
- * blocking readers or writers
+ * Lock for write. Wait for all blocking and spinning readers and writers. This
+ * starts context where reader lock could be nested by the same thread.
+ *
+ * The rwlock is held for write upon exit.
*/
void btrfs_tree_lock(struct extent_buffer *eb)
{
@@ -282,9 +419,11 @@ void btrfs_tree_lock(struct extent_buffer *eb)
WARN_ON(eb->lock_owner == current->pid);
again:
wait_event(eb->read_lock_wq, atomic_read(&eb->blocking_readers) == 0);
- wait_event(eb->write_lock_wq, eb->blocking_writers == 0);
+ wait_event(eb->write_lock_wq, READ_ONCE(eb->blocking_writers) == 0);
write_lock(&eb->lock);
- if (atomic_read(&eb->blocking_readers) || eb->blocking_writers) {
+ /* Refetch value after lock */
+ if (atomic_read(&eb->blocking_readers) ||
+ READ_ONCE(eb->blocking_writers)) {
write_unlock(&eb->lock);
goto again;
}
@@ -295,10 +434,19 @@ again:
}
/*
- * drop a spinning or a blocking write lock.
+ * Release the write lock, either blocking or spinning (ie. there's no need
+ * for an explicit blocking unlock, like btrfs_tree_read_unlock_blocking).
+ * This also ends the context for nesting, the read lock must have been
+ * released already.
+ *
+ * Tasks blocked and waiting are woken, rwlock is not held upon exit.
*/
void btrfs_tree_unlock(struct extent_buffer *eb)
{
+ /*
+ * This is read both locked and unlocked but always by the same thread
+ * that already owns the lock so we don't need to use READ_ONCE
+ */
int blockers = eb->blocking_writers;
BUG_ON(blockers > 1);
@@ -310,7 +458,8 @@ void btrfs_tree_unlock(struct extent_buffer *eb)
if (blockers) {
btrfs_assert_no_spinning_writers(eb);
- eb->blocking_writers--;
+ /* Unlocked write */
+ WRITE_ONCE(eb->blocking_writers, 0);
/*
* We need to order modifying blocking_writers above with
* actually waking up the sleepers to ensure they see the
@@ -322,3 +471,55 @@ void btrfs_tree_unlock(struct extent_buffer *eb)
write_unlock(&eb->lock);
}
}
+
+/*
+ * Set all locked nodes in the path to blocking locks. This should be done
+ * before scheduling
+ */
+void btrfs_set_path_blocking(struct btrfs_path *p)
+{
+ int i;
+
+ for (i = 0; i < BTRFS_MAX_LEVEL; i++) {
+ if (!p->nodes[i] || !p->locks[i])
+ continue;
+ /*
+ * If we currently have a spinning reader or writer lock this
+ * will bump the count of blocking holders and drop the
+ * spinlock.
+ */
+ if (p->locks[i] == BTRFS_READ_LOCK) {
+ btrfs_set_lock_blocking_read(p->nodes[i]);
+ p->locks[i] = BTRFS_READ_LOCK_BLOCKING;
+ } else if (p->locks[i] == BTRFS_WRITE_LOCK) {
+ btrfs_set_lock_blocking_write(p->nodes[i]);
+ p->locks[i] = BTRFS_WRITE_LOCK_BLOCKING;
+ }
+ }
+}
+
+/*
+ * This releases any locks held in the path starting at level and going all the
+ * way up to the root.
+ *
+ * btrfs_search_slot will keep the lock held on higher nodes in a few corner
+ * cases, such as COW of the block at slot zero in the node. This ignores
+ * those rules, and it should only be called when there are no more updates to
+ * be done higher up in the tree.
+ */
+void btrfs_unlock_up_safe(struct btrfs_path *path, int level)
+{
+ int i;
+
+ if (path->keep_locks)
+ return;
+
+ for (i = level; i < BTRFS_MAX_LEVEL; i++) {
+ if (!path->nodes[i])
+ continue;
+ if (!path->locks[i])
+ continue;
+ btrfs_tree_unlock_rw(path->nodes[i], path->locks[i]);
+ path->locks[i] = 0;
+ }
+}
diff --git a/fs/btrfs/locking.h b/fs/btrfs/locking.h
index b775a4207ed9..21a285883e89 100644
--- a/fs/btrfs/locking.h
+++ b/fs/btrfs/locking.h
@@ -6,6 +6,8 @@
#ifndef BTRFS_LOCKING_H
#define BTRFS_LOCKING_H
+#include "extent_io.h"
+
#define BTRFS_WRITE_LOCK 1
#define BTRFS_READ_LOCK 2
#define BTRFS_WRITE_LOCK_BLOCKING 3
@@ -19,11 +21,20 @@ void btrfs_tree_read_unlock(struct extent_buffer *eb);
void btrfs_tree_read_unlock_blocking(struct extent_buffer *eb);
void btrfs_set_lock_blocking_read(struct extent_buffer *eb);
void btrfs_set_lock_blocking_write(struct extent_buffer *eb);
-void btrfs_assert_tree_locked(struct extent_buffer *eb);
int btrfs_try_tree_read_lock(struct extent_buffer *eb);
int btrfs_try_tree_write_lock(struct extent_buffer *eb);
int btrfs_tree_read_lock_atomic(struct extent_buffer *eb);
+#ifdef CONFIG_BTRFS_DEBUG
+static inline void btrfs_assert_tree_locked(struct extent_buffer *eb) {
+ BUG_ON(!eb->write_locks);
+}
+#else
+static inline void btrfs_assert_tree_locked(struct extent_buffer *eb) { }
+#endif
+
+void btrfs_set_path_blocking(struct btrfs_path *p);
+void btrfs_unlock_up_safe(struct btrfs_path *path, int level);
static inline void btrfs_tree_unlock_rw(struct extent_buffer *eb, int rw)
{
diff --git a/fs/btrfs/lzo.c b/fs/btrfs/lzo.c
index acad4174f68d..aa9cd11f4b78 100644
--- a/fs/btrfs/lzo.c
+++ b/fs/btrfs/lzo.c
@@ -63,27 +63,7 @@ struct workspace {
static struct workspace_manager wsm;
-static void lzo_init_workspace_manager(void)
-{
- btrfs_init_workspace_manager(&wsm, &btrfs_lzo_compress);
-}
-
-static void lzo_cleanup_workspace_manager(void)
-{
- btrfs_cleanup_workspace_manager(&wsm);
-}
-
-static struct list_head *lzo_get_workspace(unsigned int level)
-{
- return btrfs_get_workspace(&wsm, level);
-}
-
-static void lzo_put_workspace(struct list_head *ws)
-{
- btrfs_put_workspace(&wsm, ws);
-}
-
-static void lzo_free_workspace(struct list_head *ws)
+void lzo_free_workspace(struct list_head *ws)
{
struct workspace *workspace = list_entry(ws, struct workspace, list);
@@ -93,7 +73,7 @@ static void lzo_free_workspace(struct list_head *ws)
kfree(workspace);
}
-static struct list_head *lzo_alloc_workspace(unsigned int level)
+struct list_head *lzo_alloc_workspace(unsigned int level)
{
struct workspace *workspace;
@@ -131,13 +111,9 @@ static inline size_t read_compress_length(const char *buf)
return le32_to_cpu(dlen);
}
-static int lzo_compress_pages(struct list_head *ws,
- struct address_space *mapping,
- u64 start,
- struct page **pages,
- unsigned long *out_pages,
- unsigned long *total_in,
- unsigned long *total_out)
+int lzo_compress_pages(struct list_head *ws, struct address_space *mapping,
+ u64 start, struct page **pages, unsigned long *out_pages,
+ unsigned long *total_in, unsigned long *total_out)
{
struct workspace *workspace = list_entry(ws, struct workspace, list);
int ret = 0;
@@ -303,7 +279,7 @@ out:
return ret;
}
-static int lzo_decompress_bio(struct list_head *ws, struct compressed_bio *cb)
+int lzo_decompress_bio(struct list_head *ws, struct compressed_bio *cb)
{
struct workspace *workspace = list_entry(ws, struct workspace, list);
int ret = 0, ret2;
@@ -444,10 +420,9 @@ done:
return ret;
}
-static int lzo_decompress(struct list_head *ws, unsigned char *data_in,
- struct page *dest_page,
- unsigned long start_byte,
- size_t srclen, size_t destlen)
+int lzo_decompress(struct list_head *ws, unsigned char *data_in,
+ struct page *dest_page, unsigned long start_byte, size_t srclen,
+ size_t destlen)
{
struct workspace *workspace = list_entry(ws, struct workspace, list);
size_t in_len;
@@ -508,15 +483,7 @@ out:
}
const struct btrfs_compress_op btrfs_lzo_compress = {
- .init_workspace_manager = lzo_init_workspace_manager,
- .cleanup_workspace_manager = lzo_cleanup_workspace_manager,
- .get_workspace = lzo_get_workspace,
- .put_workspace = lzo_put_workspace,
- .alloc_workspace = lzo_alloc_workspace,
- .free_workspace = lzo_free_workspace,
- .compress_pages = lzo_compress_pages,
- .decompress_bio = lzo_decompress_bio,
- .decompress = lzo_decompress,
+ .workspace_manager = &wsm,
.max_level = 1,
.default_level = 1,
};
diff --git a/fs/btrfs/misc.h b/fs/btrfs/misc.h
index 7d564924dfeb..72bab64ecf60 100644
--- a/fs/btrfs/misc.h
+++ b/fs/btrfs/misc.h
@@ -47,4 +47,15 @@ static inline u64 div_factor_fine(u64 num, int factor)
return div_u64(num, 100);
}
+/* Copy of is_power_of_two that is 64bit safe */
+static inline bool is_power_of_two_u64(u64 n)
+{
+ return n != 0 && (n & (n - 1)) == 0;
+}
+
+static inline bool has_single_bit_set(u64 n)
+{
+ return is_power_of_two_u64(n);
+}
+
#endif
diff --git a/fs/btrfs/ordered-data.c b/fs/btrfs/ordered-data.c
index 24b6c72b9a59..fb09bc2f8e4d 100644
--- a/fs/btrfs/ordered-data.c
+++ b/fs/btrfs/ordered-data.c
@@ -547,7 +547,6 @@ u64 btrfs_wait_ordered_extents(struct btrfs_root *root, u64 nr,
spin_unlock(&root->ordered_extent_lock);
btrfs_init_work(&ordered->flush_work,
- btrfs_flush_delalloc_helper,
btrfs_run_ordered_extent_work, NULL, NULL);
list_add_tail(&ordered->work_list, &works);
btrfs_queue_work(fs_info->flush_workers, &ordered->flush_work);
@@ -573,12 +572,11 @@ u64 btrfs_wait_ordered_extents(struct btrfs_root *root, u64 nr,
return count;
}
-u64 btrfs_wait_ordered_roots(struct btrfs_fs_info *fs_info, u64 nr,
+void btrfs_wait_ordered_roots(struct btrfs_fs_info *fs_info, u64 nr,
const u64 range_start, const u64 range_len)
{
struct btrfs_root *root;
struct list_head splice;
- u64 total_done = 0;
u64 done;
INIT_LIST_HEAD(&splice);
@@ -598,7 +596,6 @@ u64 btrfs_wait_ordered_roots(struct btrfs_fs_info *fs_info, u64 nr,
done = btrfs_wait_ordered_extents(root, nr,
range_start, range_len);
btrfs_put_fs_root(root);
- total_done += done;
spin_lock(&fs_info->ordered_root_lock);
if (nr != U64_MAX) {
@@ -608,8 +605,6 @@ u64 btrfs_wait_ordered_roots(struct btrfs_fs_info *fs_info, u64 nr,
list_splice_tail(&splice, &fs_info->ordered_roots);
spin_unlock(&fs_info->ordered_root_lock);
mutex_unlock(&fs_info->ordered_operations_mutex);
-
- return total_done;
}
/*
diff --git a/fs/btrfs/ordered-data.h b/fs/btrfs/ordered-data.h
index 5204171ea962..4eb0319a86d7 100644
--- a/fs/btrfs/ordered-data.h
+++ b/fs/btrfs/ordered-data.h
@@ -186,7 +186,7 @@ int btrfs_find_ordered_sum(struct inode *inode, u64 offset, u64 disk_bytenr,
u8 *sum, int len);
u64 btrfs_wait_ordered_extents(struct btrfs_root *root, u64 nr,
const u64 range_start, const u64 range_len);
-u64 btrfs_wait_ordered_roots(struct btrfs_fs_info *fs_info, u64 nr,
+void btrfs_wait_ordered_roots(struct btrfs_fs_info *fs_info, u64 nr,
const u64 range_start, const u64 range_len);
void btrfs_lock_and_flush_ordered_range(struct extent_io_tree *tree,
struct btrfs_inode *inode, u64 start,
diff --git a/fs/btrfs/print-tree.c b/fs/btrfs/print-tree.c
index 9cb50577d982..873b6b694107 100644
--- a/fs/btrfs/print-tree.c
+++ b/fs/btrfs/print-tree.c
@@ -266,9 +266,9 @@ void btrfs_print_leaf(struct extent_buffer *l)
struct btrfs_block_group_item);
pr_info(
"\t\tblock group used %llu chunk_objectid %llu flags %llu\n",
- btrfs_disk_block_group_used(l, bi),
- btrfs_disk_block_group_chunk_objectid(l, bi),
- btrfs_disk_block_group_flags(l, bi));
+ btrfs_block_group_used(l, bi),
+ btrfs_block_group_chunk_objectid(l, bi),
+ btrfs_block_group_flags(l, bi));
break;
case BTRFS_CHUNK_ITEM_KEY:
print_chunk(l, btrfs_item_ptr(l, i,
diff --git a/fs/btrfs/props.c b/fs/btrfs/props.c
index 1e664e0b59b8..deb59e7cfcac 100644
--- a/fs/btrfs/props.c
+++ b/fs/btrfs/props.c
@@ -416,11 +416,11 @@ int btrfs_subvol_inherit_props(struct btrfs_trans_handle *trans,
key.type = BTRFS_INODE_ITEM_KEY;
key.offset = 0;
- parent_inode = btrfs_iget(sb, &key, parent_root, NULL);
+ parent_inode = btrfs_iget(sb, &key, parent_root);
if (IS_ERR(parent_inode))
return PTR_ERR(parent_inode);
- child_inode = btrfs_iget(sb, &key, root, NULL);
+ child_inode = btrfs_iget(sb, &key, root);
if (IS_ERR(child_inode)) {
iput(parent_inode);
return PTR_ERR(child_inode);
@@ -437,8 +437,6 @@ void __init btrfs_props_init(void)
{
int i;
- hash_init(prop_handlers_ht);
-
for (i = 0; i < ARRAY_SIZE(prop_handlers); i++) {
struct prop_handler *p = &prop_handlers[i];
u64 h = btrfs_name_hash(p->xattr_name, strlen(p->xattr_name));
diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c
index c4bb69941c77..93aeb2e539a4 100644
--- a/fs/btrfs/qgroup.c
+++ b/fs/btrfs/qgroup.c
@@ -1811,7 +1811,7 @@ static int qgroup_trace_extent_swap(struct btrfs_trans_handle* trans,
btrfs_item_key_to_cpu(dst_path->nodes[dst_level], &key, 0);
/* For src_path */
- extent_buffer_get(src_eb);
+ atomic_inc(&src_eb->refs);
src_path->nodes[root_level] = src_eb;
src_path->slots[root_level] = dst_path->slots[root_level];
src_path->locks[root_level] = 0;
@@ -2067,7 +2067,7 @@ static int qgroup_trace_subtree_swap(struct btrfs_trans_handle *trans,
goto out;
}
/* For dst_path */
- extent_buffer_get(dst_eb);
+ atomic_inc(&dst_eb->refs);
dst_path->nodes[level] = dst_eb;
dst_path->slots[level] = 0;
dst_path->locks[level] = 0;
@@ -2126,7 +2126,7 @@ int btrfs_qgroup_trace_subtree(struct btrfs_trans_handle *trans,
* walk back up the tree (adjusting slot pointers as we go)
* and restart the search process.
*/
- extent_buffer_get(root_eb); /* For path */
+ atomic_inc(&root_eb->refs); /* For path */
path->nodes[root_level] = root_eb;
path->slots[root_level] = 0;
path->locks[root_level] = 0; /* so release_path doesn't try to unlock */
@@ -3277,10 +3277,7 @@ qgroup_rescan_init(struct btrfs_fs_info *fs_info, u64 progress_objectid,
spin_unlock(&fs_info->qgroup_lock);
mutex_unlock(&fs_info->qgroup_rescan_lock);
- memset(&fs_info->qgroup_rescan_work, 0,
- sizeof(fs_info->qgroup_rescan_work));
btrfs_init_work(&fs_info->qgroup_rescan_work,
- btrfs_qgroup_rescan_helper,
btrfs_qgroup_rescan_worker, NULL, NULL);
return 0;
}
@@ -3629,7 +3626,7 @@ int __btrfs_qgroup_reserve_meta(struct btrfs_root *root, int num_bytes,
return 0;
BUG_ON(num_bytes != round_down(num_bytes, fs_info->nodesize));
- trace_qgroup_meta_reserve(root, type, (s64)num_bytes);
+ trace_qgroup_meta_reserve(root, (s64)num_bytes, type);
ret = qgroup_reserve(root, num_bytes, enforce, type);
if (ret < 0)
return ret;
@@ -3676,7 +3673,7 @@ void __btrfs_qgroup_free_meta(struct btrfs_root *root, int num_bytes,
*/
num_bytes = sub_root_meta_rsv(root, num_bytes, type);
BUG_ON(num_bytes != round_down(num_bytes, fs_info->nodesize));
- trace_qgroup_meta_reserve(root, type, -(s64)num_bytes);
+ trace_qgroup_meta_reserve(root, -(s64)num_bytes, type);
btrfs_qgroup_free_refroot(fs_info, root->root_key.objectid,
num_bytes, type);
}
@@ -3826,7 +3823,7 @@ out:
*/
int btrfs_qgroup_add_swapped_blocks(struct btrfs_trans_handle *trans,
struct btrfs_root *subvol_root,
- struct btrfs_block_group_cache *bg,
+ struct btrfs_block_group *bg,
struct extent_buffer *subvol_parent, int subvol_slot,
struct extent_buffer *reloc_parent, int reloc_slot,
u64 last_snapshot)
diff --git a/fs/btrfs/qgroup.h b/fs/btrfs/qgroup.h
index 46ba7bd2961c..236f12224d52 100644
--- a/fs/btrfs/qgroup.h
+++ b/fs/btrfs/qgroup.h
@@ -408,7 +408,7 @@ void btrfs_qgroup_init_swapped_blocks(
void btrfs_qgroup_clean_swapped_blocks(struct btrfs_root *root);
int btrfs_qgroup_add_swapped_blocks(struct btrfs_trans_handle *trans,
struct btrfs_root *subvol_root,
- struct btrfs_block_group_cache *bg,
+ struct btrfs_block_group *bg,
struct extent_buffer *subvol_parent, int subvol_slot,
struct extent_buffer *reloc_parent, int reloc_slot,
u64 last_snapshot);
diff --git a/fs/btrfs/raid56.c b/fs/btrfs/raid56.c
index 57a2ac721985..a8e53c8e7b01 100644
--- a/fs/btrfs/raid56.c
+++ b/fs/btrfs/raid56.c
@@ -190,7 +190,7 @@ static void scrub_parity_work(struct btrfs_work *work);
static void start_async_work(struct btrfs_raid_bio *rbio, btrfs_func_t work_func)
{
- btrfs_init_work(&rbio->work, btrfs_rmw_helper, work_func, NULL, NULL);
+ btrfs_init_work(&rbio->work, work_func, NULL, NULL);
btrfs_queue_work(rbio->fs_info->rmw_workers, &rbio->work);
}
@@ -671,8 +671,7 @@ static struct page *rbio_qstripe_page(struct btrfs_raid_bio *rbio, int index)
*/
static noinline int lock_stripe_add(struct btrfs_raid_bio *rbio)
{
- int bucket = rbio_bucket(rbio);
- struct btrfs_stripe_hash *h = rbio->fs_info->stripe_hash_table->table + bucket;
+ struct btrfs_stripe_hash *h;
struct btrfs_raid_bio *cur;
struct btrfs_raid_bio *pending;
unsigned long flags;
@@ -680,64 +679,63 @@ static noinline int lock_stripe_add(struct btrfs_raid_bio *rbio)
struct btrfs_raid_bio *cache_drop = NULL;
int ret = 0;
+ h = rbio->fs_info->stripe_hash_table->table + rbio_bucket(rbio);
+
spin_lock_irqsave(&h->lock, flags);
list_for_each_entry(cur, &h->hash_list, hash_list) {
- if (cur->bbio->raid_map[0] == rbio->bbio->raid_map[0]) {
- spin_lock(&cur->bio_list_lock);
-
- /* can we steal this cached rbio's pages? */
- if (bio_list_empty(&cur->bio_list) &&
- list_empty(&cur->plug_list) &&
- test_bit(RBIO_CACHE_BIT, &cur->flags) &&
- !test_bit(RBIO_RMW_LOCKED_BIT, &cur->flags)) {
- list_del_init(&cur->hash_list);
- refcount_dec(&cur->refs);
-
- steal_rbio(cur, rbio);
- cache_drop = cur;
- spin_unlock(&cur->bio_list_lock);
+ if (cur->bbio->raid_map[0] != rbio->bbio->raid_map[0])
+ continue;
- goto lockit;
- }
+ spin_lock(&cur->bio_list_lock);
- /* can we merge into the lock owner? */
- if (rbio_can_merge(cur, rbio)) {
- merge_rbio(cur, rbio);
- spin_unlock(&cur->bio_list_lock);
- freeit = rbio;
- ret = 1;
- goto out;
- }
+ /* Can we steal this cached rbio's pages? */
+ if (bio_list_empty(&cur->bio_list) &&
+ list_empty(&cur->plug_list) &&
+ test_bit(RBIO_CACHE_BIT, &cur->flags) &&
+ !test_bit(RBIO_RMW_LOCKED_BIT, &cur->flags)) {
+ list_del_init(&cur->hash_list);
+ refcount_dec(&cur->refs);
+ steal_rbio(cur, rbio);
+ cache_drop = cur;
+ spin_unlock(&cur->bio_list_lock);
- /*
- * we couldn't merge with the running
- * rbio, see if we can merge with the
- * pending ones. We don't have to
- * check for rmw_locked because there
- * is no way they are inside finish_rmw
- * right now
- */
- list_for_each_entry(pending, &cur->plug_list,
- plug_list) {
- if (rbio_can_merge(pending, rbio)) {
- merge_rbio(pending, rbio);
- spin_unlock(&cur->bio_list_lock);
- freeit = rbio;
- ret = 1;
- goto out;
- }
- }
+ goto lockit;
+ }
- /* no merging, put us on the tail of the plug list,
- * our rbio will be started with the currently
- * running rbio unlocks
- */
- list_add_tail(&rbio->plug_list, &cur->plug_list);
+ /* Can we merge into the lock owner? */
+ if (rbio_can_merge(cur, rbio)) {
+ merge_rbio(cur, rbio);
spin_unlock(&cur->bio_list_lock);
+ freeit = rbio;
ret = 1;
goto out;
}
+
+
+ /*
+ * We couldn't merge with the running rbio, see if we can merge
+ * with the pending ones. We don't have to check for rmw_locked
+ * because there is no way they are inside finish_rmw right now
+ */
+ list_for_each_entry(pending, &cur->plug_list, plug_list) {
+ if (rbio_can_merge(pending, rbio)) {
+ merge_rbio(pending, rbio);
+ spin_unlock(&cur->bio_list_lock);
+ freeit = rbio;
+ ret = 1;
+ goto out;
+ }
+ }
+
+ /*
+ * No merging, put us on the tail of the plug list, our rbio
+ * will be started with the currently running rbio unlocks
+ */
+ list_add_tail(&rbio->plug_list, &cur->plug_list);
+ spin_unlock(&cur->bio_list_lock);
+ ret = 1;
+ goto out;
}
lockit:
refcount_inc(&rbio->refs);
@@ -1743,8 +1741,7 @@ static void btrfs_raid_unplug(struct blk_plug_cb *cb, bool from_schedule)
plug = container_of(cb, struct btrfs_plug_cb, cb);
if (from_schedule) {
- btrfs_init_work(&plug->work, btrfs_rmw_helper,
- unplug_work, NULL, NULL);
+ btrfs_init_work(&plug->work, unplug_work, NULL, NULL);
btrfs_queue_work(plug->info->rmw_workers,
&plug->work);
return;
diff --git a/fs/btrfs/reada.c b/fs/btrfs/reada.c
index ee6f60547a8d..243a2e44526e 100644
--- a/fs/btrfs/reada.c
+++ b/fs/btrfs/reada.c
@@ -227,7 +227,7 @@ static struct reada_zone *reada_find_zone(struct btrfs_device *dev, u64 logical,
struct btrfs_fs_info *fs_info = dev->fs_info;
int ret;
struct reada_zone *zone;
- struct btrfs_block_group_cache *cache = NULL;
+ struct btrfs_block_group *cache = NULL;
u64 start;
u64 end;
int i;
@@ -248,8 +248,8 @@ static struct reada_zone *reada_find_zone(struct btrfs_device *dev, u64 logical,
if (!cache)
return NULL;
- start = cache->key.objectid;
- end = start + cache->key.offset - 1;
+ start = cache->start;
+ end = start + cache->length - 1;
btrfs_put_block_group(cache);
zone = kzalloc(sizeof(*zone), GFP_KERNEL);
@@ -752,21 +752,19 @@ static int reada_start_machine_dev(struct btrfs_device *dev)
static void reada_start_machine_worker(struct btrfs_work *work)
{
struct reada_machine_work *rmw;
- struct btrfs_fs_info *fs_info;
int old_ioprio;
rmw = container_of(work, struct reada_machine_work, work);
- fs_info = rmw->fs_info;
-
- kfree(rmw);
old_ioprio = IOPRIO_PRIO_VALUE(task_nice_ioclass(current),
task_nice_ioprio(current));
set_task_ioprio(current, BTRFS_IOPRIO_READA);
- __reada_start_machine(fs_info);
+ __reada_start_machine(rmw->fs_info);
set_task_ioprio(current, old_ioprio);
- atomic_dec(&fs_info->reada_works_cnt);
+ atomic_dec(&rmw->fs_info->reada_works_cnt);
+
+ kfree(rmw);
}
static void __reada_start_machine(struct btrfs_fs_info *fs_info)
@@ -821,8 +819,7 @@ static void reada_start_machine(struct btrfs_fs_info *fs_info)
/* FIXME we cannot handle this properly right now */
BUG();
}
- btrfs_init_work(&rmw->work, btrfs_readahead_helper,
- reada_start_machine_worker, NULL, NULL);
+ btrfs_init_work(&rmw->work, reada_start_machine_worker, NULL, NULL);
rmw->fs_info = fs_info;
btrfs_queue_work(fs_info->readahead_workers, &rmw->work);
diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c
index 00504657b602..d897a8e5e430 100644
--- a/fs/btrfs/relocation.c
+++ b/fs/btrfs/relocation.c
@@ -147,7 +147,7 @@ struct file_extent_cluster {
struct reloc_control {
/* block group to relocate */
- struct btrfs_block_group_cache *block_group;
+ struct btrfs_block_group *block_group;
/* extent tree */
struct btrfs_root *extent_root;
/* inode for moving data */
@@ -1560,11 +1560,10 @@ again:
return NULL;
}
-static int in_block_group(u64 bytenr,
- struct btrfs_block_group_cache *block_group)
+static int in_block_group(u64 bytenr, struct btrfs_block_group *block_group)
{
- if (bytenr >= block_group->key.objectid &&
- bytenr < block_group->key.objectid + block_group->key.offset)
+ if (bytenr >= block_group->start &&
+ bytenr < block_group->start + block_group->length)
return 1;
return 0;
}
@@ -2246,7 +2245,7 @@ static noinline_for_stack int merge_reloc_root(struct reloc_control *rc,
if (btrfs_disk_key_objectid(&root_item->drop_progress) == 0) {
level = btrfs_root_level(root_item);
- extent_buffer_get(reloc_root->node);
+ atomic_inc(&reloc_root->node->refs);
path->nodes[level] = reloc_root->node;
path->slots[level] = 0;
} else {
@@ -3195,7 +3194,6 @@ static noinline_for_stack
int setup_extent_mapping(struct inode *inode, u64 start, u64 end,
u64 block_start)
{
- struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
struct extent_map_tree *em_tree = &BTRFS_I(inode)->extent_tree;
struct extent_map *em;
int ret = 0;
@@ -3208,7 +3206,6 @@ int setup_extent_mapping(struct inode *inode, u64 start, u64 end,
em->len = end + 1 - start;
em->block_len = em->len;
em->block_start = block_start;
- em->bdev = fs_info->fs_devices->latest_bdev;
set_bit(EXTENT_FLAG_PINNED, &em->flags);
lock_extent(&BTRFS_I(inode)->io_tree, start, end);
@@ -3277,6 +3274,8 @@ static int relocate_file_extent_cluster(struct inode *inode,
if (!page) {
btrfs_delalloc_release_metadata(BTRFS_I(inode),
PAGE_SIZE, true);
+ btrfs_delalloc_release_extents(BTRFS_I(inode),
+ PAGE_SIZE);
ret = -ENOMEM;
goto out;
}
@@ -3297,7 +3296,7 @@ static int relocate_file_extent_cluster(struct inode *inode,
btrfs_delalloc_release_metadata(BTRFS_I(inode),
PAGE_SIZE, true);
btrfs_delalloc_release_extents(BTRFS_I(inode),
- PAGE_SIZE, true);
+ PAGE_SIZE);
ret = -EIO;
goto out;
}
@@ -3326,7 +3325,7 @@ static int relocate_file_extent_cluster(struct inode *inode,
btrfs_delalloc_release_metadata(BTRFS_I(inode),
PAGE_SIZE, true);
btrfs_delalloc_release_extents(BTRFS_I(inode),
- PAGE_SIZE, true);
+ PAGE_SIZE);
clear_extent_bits(&BTRFS_I(inode)->io_tree,
page_start, page_end,
@@ -3342,8 +3341,7 @@ static int relocate_file_extent_cluster(struct inode *inode,
put_page(page);
index++;
- btrfs_delalloc_release_extents(BTRFS_I(inode), PAGE_SIZE,
- false);
+ btrfs_delalloc_release_extents(BTRFS_I(inode), PAGE_SIZE);
balance_dirty_pages_ratelimited(inode->i_mapping);
btrfs_throttle(fs_info);
}
@@ -3543,7 +3541,7 @@ static int block_use_full_backref(struct reloc_control *rc,
}
static int delete_block_group_cache(struct btrfs_fs_info *fs_info,
- struct btrfs_block_group_cache *block_group,
+ struct btrfs_block_group *block_group,
struct inode *inode,
u64 ino)
{
@@ -3559,7 +3557,7 @@ static int delete_block_group_cache(struct btrfs_fs_info *fs_info,
key.type = BTRFS_INODE_ITEM_KEY;
key.offset = 0;
- inode = btrfs_iget(fs_info->sb, &key, root, NULL);
+ inode = btrfs_iget(fs_info->sb, &key, root);
if (IS_ERR(inode))
return -ENOENT;
@@ -3862,7 +3860,7 @@ int find_next_extent(struct reloc_control *rc, struct btrfs_path *path,
u64 start, end, last;
int ret;
- last = rc->block_group->key.objectid + rc->block_group->key.offset;
+ last = rc->block_group->start + rc->block_group->length;
while (1) {
cond_resched();
if (rc->search_start >= last) {
@@ -3979,7 +3977,7 @@ int prepare_to_relocate(struct reloc_control *rc)
return -ENOMEM;
memset(&rc->cluster, 0, sizeof(rc->cluster));
- rc->search_start = rc->block_group->key.objectid;
+ rc->search_start = rc->block_group->start;
rc->extents_found = 0;
rc->nodes_relocated = 0;
rc->merging_rsv_size = 0;
@@ -4218,7 +4216,7 @@ out:
*/
static noinline_for_stack
struct inode *create_reloc_inode(struct btrfs_fs_info *fs_info,
- struct btrfs_block_group_cache *group)
+ struct btrfs_block_group *group)
{
struct inode *inode = NULL;
struct btrfs_trans_handle *trans;
@@ -4245,9 +4243,9 @@ struct inode *create_reloc_inode(struct btrfs_fs_info *fs_info,
key.objectid = objectid;
key.type = BTRFS_INODE_ITEM_KEY;
key.offset = 0;
- inode = btrfs_iget(fs_info->sb, &key, root, NULL);
+ inode = btrfs_iget(fs_info->sb, &key, root);
BUG_ON(IS_ERR(inode));
- BTRFS_I(inode)->index_cnt = group->key.objectid;
+ BTRFS_I(inode)->index_cnt = group->start;
err = btrfs_orphan_add(trans, BTRFS_I(inode));
out:
@@ -4282,7 +4280,7 @@ static struct reloc_control *alloc_reloc_control(struct btrfs_fs_info *fs_info)
* Print the block group being relocated
*/
static void describe_relocation(struct btrfs_fs_info *fs_info,
- struct btrfs_block_group_cache *block_group)
+ struct btrfs_block_group *block_group)
{
char buf[128] = {'\0'};
@@ -4290,7 +4288,7 @@ static void describe_relocation(struct btrfs_fs_info *fs_info,
btrfs_info(fs_info,
"relocating block group %llu flags %s",
- block_group->key.objectid, buf);
+ block_group->start, buf);
}
/*
@@ -4298,7 +4296,7 @@ static void describe_relocation(struct btrfs_fs_info *fs_info,
*/
int btrfs_relocate_block_group(struct btrfs_fs_info *fs_info, u64 group_start)
{
- struct btrfs_block_group_cache *bg;
+ struct btrfs_block_group *bg;
struct btrfs_root *extent_root = fs_info->extent_root;
struct reloc_control *rc;
struct inode *inode;
@@ -4325,7 +4323,7 @@ int btrfs_relocate_block_group(struct btrfs_fs_info *fs_info, u64 group_start)
rc->extent_root = extent_root;
rc->block_group = bg;
- ret = btrfs_inc_block_group_ro(rc->block_group);
+ ret = btrfs_inc_block_group_ro(rc->block_group, true);
if (ret) {
err = ret;
goto out;
@@ -4363,8 +4361,8 @@ int btrfs_relocate_block_group(struct btrfs_fs_info *fs_info, u64 group_start)
btrfs_wait_block_group_reservations(rc->block_group);
btrfs_wait_nocow_writers(rc->block_group);
btrfs_wait_ordered_roots(fs_info, U64_MAX,
- rc->block_group->key.objectid,
- rc->block_group->key.offset);
+ rc->block_group->start,
+ rc->block_group->length);
while (1) {
mutex_lock(&fs_info->cleaner_mutex);
@@ -4404,7 +4402,7 @@ int btrfs_relocate_block_group(struct btrfs_fs_info *fs_info, u64 group_start)
WARN_ON(rc->block_group->pinned > 0);
WARN_ON(rc->block_group->reserved > 0);
- WARN_ON(btrfs_block_group_used(&rc->block_group->item) > 0);
+ WARN_ON(rc->block_group->used > 0);
out:
if (err && rw)
btrfs_dec_block_group_ro(rc->block_group);
@@ -4687,7 +4685,7 @@ int btrfs_reloc_cow_block(struct btrfs_trans_handle *trans,
node->new_bytenr != buf->start);
drop_node_buffer(node);
- extent_buffer_get(cow);
+ atomic_inc(&cow->refs);
node->eb = cow;
node->new_bytenr = cow->start;
diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c
index f7d4e03f4c5d..21de630b0730 100644
--- a/fs/btrfs/scrub.c
+++ b/fs/btrfs/scrub.c
@@ -389,8 +389,7 @@ static struct full_stripe_lock *search_full_stripe_lock(
*
* Caller must ensure @cache is a RAID56 block group.
*/
-static u64 get_full_stripe_logical(struct btrfs_block_group_cache *cache,
- u64 bytenr)
+static u64 get_full_stripe_logical(struct btrfs_block_group *cache, u64 bytenr)
{
u64 ret;
@@ -404,8 +403,8 @@ static u64 get_full_stripe_logical(struct btrfs_block_group_cache *cache,
* round_down() can only handle power of 2, while RAID56 full
* stripe length can be 64KiB * n, so we need to manually round down.
*/
- ret = div64_u64(bytenr - cache->key.objectid, cache->full_stripe_len) *
- cache->full_stripe_len + cache->key.objectid;
+ ret = div64_u64(bytenr - cache->start, cache->full_stripe_len) *
+ cache->full_stripe_len + cache->start;
return ret;
}
@@ -423,7 +422,7 @@ static u64 get_full_stripe_logical(struct btrfs_block_group_cache *cache,
static int lock_full_stripe(struct btrfs_fs_info *fs_info, u64 bytenr,
bool *locked_ret)
{
- struct btrfs_block_group_cache *bg_cache;
+ struct btrfs_block_group *bg_cache;
struct btrfs_full_stripe_locks_tree *locks_root;
struct full_stripe_lock *existing;
u64 fstripe_start;
@@ -470,7 +469,7 @@ out:
static int unlock_full_stripe(struct btrfs_fs_info *fs_info, u64 bytenr,
bool locked)
{
- struct btrfs_block_group_cache *bg_cache;
+ struct btrfs_block_group *bg_cache;
struct btrfs_full_stripe_locks_tree *locks_root;
struct full_stripe_lock *fstripe_lock;
u64 fstripe_start;
@@ -598,8 +597,8 @@ static noinline_for_stack struct scrub_ctx *scrub_setup_ctx(
sbio->index = i;
sbio->sctx = sctx;
sbio->page_count = 0;
- btrfs_init_work(&sbio->work, btrfs_scrub_helper,
- scrub_bio_end_io_worker, NULL, NULL);
+ btrfs_init_work(&sbio->work, scrub_bio_end_io_worker, NULL,
+ NULL);
if (i != SCRUB_BIOS_PER_SCTX - 1)
sctx->bios[i]->next_free = i + 1;
@@ -1720,8 +1719,7 @@ static void scrub_wr_bio_end_io(struct bio *bio)
sbio->status = bio->bi_status;
sbio->bio = bio;
- btrfs_init_work(&sbio->work, btrfs_scrubwrc_helper,
- scrub_wr_bio_end_io_worker, NULL, NULL);
+ btrfs_init_work(&sbio->work, scrub_wr_bio_end_io_worker, NULL, NULL);
btrfs_queue_work(fs_info->scrub_wr_completion_workers, &sbio->work);
}
@@ -2149,14 +2147,13 @@ static void scrub_missing_raid56_worker(struct btrfs_work *work)
scrub_write_block_to_dev_replace(sblock);
}
- scrub_block_put(sblock);
-
if (sctx->is_dev_replace && sctx->flush_all_writes) {
mutex_lock(&sctx->wr_lock);
scrub_wr_submit(sctx);
mutex_unlock(&sctx->wr_lock);
}
+ scrub_block_put(sblock);
scrub_pending_bio_dec(sctx);
}
@@ -2204,8 +2201,7 @@ static void scrub_missing_raid56_pages(struct scrub_block *sblock)
raid56_add_scrub_pages(rbio, spage->page, spage->logical);
}
- btrfs_init_work(&sblock->work, btrfs_scrub_helper,
- scrub_missing_raid56_worker, NULL, NULL);
+ btrfs_init_work(&sblock->work, scrub_missing_raid56_worker, NULL, NULL);
scrub_block_get(sblock);
scrub_pending_bio_inc(sctx);
raid56_submit_missing_rbio(rbio);
@@ -2743,8 +2739,8 @@ static void scrub_parity_bio_endio(struct bio *bio)
bio_put(bio);
- btrfs_init_work(&sparity->work, btrfs_scrubparity_helper,
- scrub_parity_bio_endio_worker, NULL, NULL);
+ btrfs_init_work(&sparity->work, scrub_parity_bio_endio_worker, NULL,
+ NULL);
btrfs_queue_work(fs_info->scrub_parity_workers, &sparity->work);
}
@@ -3420,7 +3416,7 @@ static noinline_for_stack int scrub_chunk(struct scrub_ctx *sctx,
struct btrfs_device *scrub_dev,
u64 chunk_offset, u64 length,
u64 dev_offset,
- struct btrfs_block_group_cache *cache)
+ struct btrfs_block_group *cache)
{
struct btrfs_fs_info *fs_info = sctx->fs_info;
struct extent_map_tree *map_tree = &fs_info->mapping_tree;
@@ -3484,7 +3480,7 @@ int scrub_enumerate_chunks(struct scrub_ctx *sctx,
struct extent_buffer *l;
struct btrfs_key key;
struct btrfs_key found_key;
- struct btrfs_block_group_cache *cache;
+ struct btrfs_block_group *cache;
struct btrfs_dev_replace *dev_replace = &fs_info->dev_replace;
path = btrfs_alloc_path();
@@ -3563,46 +3559,26 @@ int scrub_enumerate_chunks(struct scrub_ctx *sctx,
* -> btrfs_scrub_pause()
*/
scrub_pause_on(fs_info);
- ret = btrfs_inc_block_group_ro(cache);
- if (!ret && sctx->is_dev_replace) {
- /*
- * If we are doing a device replace wait for any tasks
- * that started delalloc right before we set the block
- * group to RO mode, as they might have just allocated
- * an extent from it or decided they could do a nocow
- * write. And if any such tasks did that, wait for their
- * ordered extents to complete and then commit the
- * current transaction, so that we can later see the new
- * extent items in the extent tree - the ordered extents
- * create delayed data references (for cow writes) when
- * they complete, which will be run and insert the
- * corresponding extent items into the extent tree when
- * we commit the transaction they used when running
- * inode.c:btrfs_finish_ordered_io(). We later use
- * the commit root of the extent tree to find extents
- * to copy from the srcdev into the tgtdev, and we don't
- * want to miss any new extents.
- */
- btrfs_wait_block_group_reservations(cache);
- btrfs_wait_nocow_writers(cache);
- ret = btrfs_wait_ordered_roots(fs_info, U64_MAX,
- cache->key.objectid,
- cache->key.offset);
- if (ret > 0) {
- struct btrfs_trans_handle *trans;
-
- trans = btrfs_join_transaction(root);
- if (IS_ERR(trans))
- ret = PTR_ERR(trans);
- else
- ret = btrfs_commit_transaction(trans);
- if (ret) {
- scrub_pause_off(fs_info);
- btrfs_put_block_group(cache);
- break;
- }
- }
- }
+
+ /*
+ * Don't do chunk preallocation for scrub.
+ *
+ * This is especially important for SYSTEM bgs, or we can hit
+ * -EFBIG from btrfs_finish_chunk_alloc() like:
+ * 1. The only SYSTEM bg is marked RO.
+ * Since SYSTEM bg is small, that's pretty common.
+ * 2. New SYSTEM bg will be allocated
+ * Due to regular version will allocate new chunk.
+ * 3. New SYSTEM bg is empty and will get cleaned up
+ * Before cleanup really happens, it's marked RO again.
+ * 4. Empty SYSTEM bg get scrubbed
+ * We go back to 2.
+ *
+ * This can easily boost the amount of SYSTEM chunks if cleaner
+ * thread can't be triggered fast enough, and use up all space
+ * of btrfs_super_block::sys_chunk_array
+ */
+ ret = btrfs_inc_block_group_ro(cache, false);
scrub_pause_off(fs_info);
if (ret == 0) {
@@ -3623,7 +3599,7 @@ int scrub_enumerate_chunks(struct scrub_ctx *sctx,
break;
}
- down_write(&fs_info->dev_replace.rwsem);
+ down_write(&dev_replace->rwsem);
dev_replace->cursor_right = found_key.offset + length;
dev_replace->cursor_left = found_key.offset;
dev_replace->item_needs_writeback = 1;
@@ -3664,10 +3640,10 @@ int scrub_enumerate_chunks(struct scrub_ctx *sctx,
scrub_pause_off(fs_info);
- down_write(&fs_info->dev_replace.rwsem);
+ down_write(&dev_replace->rwsem);
dev_replace->cursor_left = dev_replace->cursor_right;
dev_replace->item_needs_writeback = 1;
- up_write(&fs_info->dev_replace.rwsem);
+ up_write(&dev_replace->rwsem);
if (ro_set)
btrfs_dec_block_group_ro(cache);
@@ -3681,7 +3657,7 @@ int scrub_enumerate_chunks(struct scrub_ctx *sctx,
*/
spin_lock(&cache->lock);
if (!cache->removed && !cache->ro && cache->reserved == 0 &&
- btrfs_block_group_used(&cache->item) == 0) {
+ cache->used == 0) {
spin_unlock(&cache->lock);
btrfs_mark_bg_unused(cache);
} else {
diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c
index 123ac54af071..ae2db5eb1549 100644
--- a/fs/btrfs/send.c
+++ b/fs/btrfs/send.c
@@ -25,6 +25,14 @@
#include "compression.h"
/*
+ * Maximum number of references an extent can have in order for us to attempt to
+ * issue clone operations instead of write operations. This currently exists to
+ * avoid hitting limitations of the backreference walking code (taking a lot of
+ * time and using too much memory for extents with large number of references).
+ */
+#define SEND_MAX_EXTENT_REFS 64
+
+/*
* A fs_path is a helper to dynamically build path names with unknown size.
* It reallocates the internal buffer on demand.
* It allows fast adding of path elements on the right side (normal path) and
@@ -1248,12 +1256,20 @@ static int __iterate_backrefs(u64 ino, u64 offset, u64 root, void *ctx_)
*/
if (found->root == bctx->sctx->send_root) {
/*
- * TODO for the moment we don't accept clones from the inode
- * that is currently send. We may change this when
- * BTRFS_IOC_CLONE_RANGE supports cloning from and to the same
- * file.
+ * If the source inode was not yet processed we can't issue a
+ * clone operation, as the source extent does not exist yet at
+ * the destination of the stream.
*/
- if (ino >= bctx->cur_objectid)
+ if (ino > bctx->cur_objectid)
+ return 0;
+ /*
+ * We clone from the inode currently being sent as long as the
+ * source extent is already processed, otherwise we could try
+ * to clone from an extent that does not exist yet at the
+ * destination of the stream.
+ */
+ if (ino == bctx->cur_objectid &&
+ offset >= bctx->sctx->cur_inode_next_write_offset)
return 0;
}
@@ -1302,6 +1318,7 @@ static int find_extent_clone(struct send_ctx *sctx,
struct clone_root *cur_clone_root;
struct btrfs_key found_key;
struct btrfs_path *tmp_path;
+ struct btrfs_extent_item *ei;
int compressed;
u32 i;
@@ -1349,7 +1366,6 @@ static int find_extent_clone(struct send_ctx *sctx,
ret = extent_from_logical(fs_info, disk_byte, tmp_path,
&found_key, &flags);
up_read(&fs_info->commit_root_sem);
- btrfs_release_path(tmp_path);
if (ret < 0)
goto out;
@@ -1358,6 +1374,21 @@ static int find_extent_clone(struct send_ctx *sctx,
goto out;
}
+ ei = btrfs_item_ptr(tmp_path->nodes[0], tmp_path->slots[0],
+ struct btrfs_extent_item);
+ /*
+ * Backreference walking (iterate_extent_inodes() below) is currently
+ * too expensive when an extent has a large number of references, both
+ * in time spent and used memory. So for now just fallback to write
+ * operations instead of clone operations when an extent has more than
+ * a certain amount of references.
+ */
+ if (btrfs_extent_refs(tmp_path->nodes[0], ei) > SEND_MAX_EXTENT_REFS) {
+ ret = -ENOENT;
+ goto out;
+ }
+ btrfs_release_path(tmp_path);
+
/*
* Setup the clone roots.
*/
@@ -4779,7 +4810,7 @@ static ssize_t fill_read_buf(struct send_ctx *sctx, u64 offset, u32 len)
key.type = BTRFS_INODE_ITEM_KEY;
key.offset = 0;
- inode = btrfs_iget(fs_info->sb, &key, root, NULL);
+ inode = btrfs_iget(fs_info->sb, &key, root);
if (IS_ERR(inode))
return PTR_ERR(inode);
diff --git a/fs/btrfs/space-info.c b/fs/btrfs/space-info.c
index 98dc092a905e..f09aa6ee9113 100644
--- a/fs/btrfs/space-info.c
+++ b/fs/btrfs/space-info.c
@@ -10,7 +10,7 @@
#include "transaction.h"
#include "block-group.h"
-u64 btrfs_space_info_used(struct btrfs_space_info *s_info,
+u64 __pure btrfs_space_info_used(struct btrfs_space_info *s_info,
bool may_use_included)
{
ASSERT(s_info);
@@ -58,7 +58,6 @@ static int create_space_info(struct btrfs_fs_info *info, u64 flags)
spin_lock_init(&space_info->lock);
space_info->flags = flags & BTRFS_BLOCK_GROUP_TYPE_MASK;
space_info->force_alloc = CHUNK_ALLOC_NO_FORCE;
- init_waitqueue_head(&space_info->wait);
INIT_LIST_HEAD(&space_info->ro_bgs);
INIT_LIST_HEAD(&space_info->tickets);
INIT_LIST_HEAD(&space_info->priority_tickets);
@@ -285,7 +284,7 @@ void btrfs_dump_space_info(struct btrfs_fs_info *fs_info,
struct btrfs_space_info *info, u64 bytes,
int dump_block_groups)
{
- struct btrfs_block_group_cache *cache;
+ struct btrfs_block_group *cache;
int index = 0;
spin_lock(&info->lock);
@@ -301,8 +300,7 @@ again:
spin_lock(&cache->lock);
btrfs_info(fs_info,
"block group %llu has %llu bytes, %llu used %llu pinned %llu reserved %s",
- cache->key.objectid, cache->key.offset,
- btrfs_block_group_used(&cache->item), cache->pinned,
+ cache->start, cache->length, cache->used, cache->pinned,
cache->reserved, cache->ro ? "[readonly]" : "");
btrfs_dump_free_space(cache, bytes);
spin_unlock(&cache->lock);
@@ -893,6 +891,15 @@ static void wait_reserve_ticket(struct btrfs_fs_info *fs_info,
while (ticket->bytes > 0 && ticket->error == 0) {
ret = prepare_to_wait_event(&ticket->wait, &wait, TASK_KILLABLE);
if (ret) {
+ /*
+ * Delete us from the list. After we unlock the space
+ * info, we don't want the async reclaim job to reserve
+ * space for this ticket. If that would happen, then the
+ * ticket's task would not known that space was reserved
+ * despite getting an error, resulting in a space leak
+ * (bytes_may_use counter of our space_info).
+ */
+ list_del_init(&ticket->list);
ticket->error = -EINTR;
break;
}
@@ -945,12 +952,24 @@ static int handle_reserve_ticket(struct btrfs_fs_info *fs_info,
spin_lock(&space_info->lock);
ret = ticket->error;
if (ticket->bytes || ticket->error) {
+ /*
+ * Need to delete here for priority tickets. For regular tickets
+ * either the async reclaim job deletes the ticket from the list
+ * or we delete it ourselves at wait_reserve_ticket().
+ */
list_del_init(&ticket->list);
if (!ret)
ret = -ENOSPC;
}
spin_unlock(&space_info->lock);
ASSERT(list_empty(&ticket->list));
+ /*
+ * Check that we can't have an error set if the reservation succeeded,
+ * as that would confuse tasks and lead them to error out without
+ * releasing reserved space (if an error happens the expectation is that
+ * space wasn't reserved at all).
+ */
+ ASSERT(!(ticket->bytes == 0 && ticket->error));
return ret;
}
diff --git a/fs/btrfs/space-info.h b/fs/btrfs/space-info.h
index 8867e84aa33d..1a349e3f9cc1 100644
--- a/fs/btrfs/space-info.h
+++ b/fs/btrfs/space-info.h
@@ -63,7 +63,6 @@ struct btrfs_space_info {
struct rw_semaphore groups_sem;
/* for block groups in our same type */
struct list_head block_groups[BTRFS_NR_RAID_TYPES];
- wait_queue_head_t wait;
struct kobject kobj;
struct kobject *block_group_kobjs[BTRFS_NR_RAID_TYPES];
@@ -116,7 +115,7 @@ void btrfs_update_space_info(struct btrfs_fs_info *info, u64 flags,
struct btrfs_space_info **space_info);
struct btrfs_space_info *btrfs_find_space_info(struct btrfs_fs_info *info,
u64 flags);
-u64 btrfs_space_info_used(struct btrfs_space_info *s_info,
+u64 __pure btrfs_space_info_used(struct btrfs_space_info *s_info,
bool may_use_included);
void btrfs_clear_space_info_full(struct btrfs_fs_info *info);
void btrfs_dump_space_info(struct btrfs_fs_info *fs_info,
diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index 1b151af25772..f452a94abdc3 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -66,7 +66,7 @@ static struct file_system_type btrfs_root_fs_type;
static int btrfs_remount(struct super_block *sb, int *flags, char *data);
-const char *btrfs_decode_error(int errno)
+const char * __attribute_const__ btrfs_decode_error(int errno)
{
char *errstr = "unknown";
@@ -187,7 +187,7 @@ static struct ratelimit_state printk_limits[] = {
RATELIMIT_STATE_INIT(printk_limits[7], DEFAULT_RATELIMIT_INTERVAL, 100),
};
-void btrfs_printk(const struct btrfs_fs_info *fs_info, const char *fmt, ...)
+void __cold btrfs_printk(const struct btrfs_fs_info *fs_info, const char *fmt, ...)
{
char lvl[PRINTK_MAX_SINGLE_HEADER_LEN + 1] = "\0";
struct va_format vaf;
@@ -1219,7 +1219,7 @@ static int btrfs_fill_super(struct super_block *sb,
key.objectid = BTRFS_FIRST_FREE_OBJECTID;
key.type = BTRFS_INODE_ITEM_KEY;
key.offset = 0;
- inode = btrfs_iget(sb, &key, fs_info->fs_root, NULL);
+ inode = btrfs_iget(sb, &key, fs_info->fs_root);
if (IS_ERR(inode)) {
err = PTR_ERR(inode);
goto fail_close;
@@ -1669,7 +1669,6 @@ static void btrfs_resize_thread_pool(struct btrfs_fs_info *fs_info,
btrfs_workqueue_set_max(fs_info->workers, new_pool_size);
btrfs_workqueue_set_max(fs_info->delalloc_workers, new_pool_size);
- btrfs_workqueue_set_max(fs_info->submit_workers, new_pool_size);
btrfs_workqueue_set_max(fs_info->caching_workers, new_pool_size);
btrfs_workqueue_set_max(fs_info->endio_workers, new_pool_size);
btrfs_workqueue_set_max(fs_info->endio_meta_workers, new_pool_size);
@@ -1936,6 +1935,10 @@ static inline int btrfs_calc_avail_data_space(struct btrfs_fs_info *fs_info,
num_stripes = nr_devices;
else if (type & BTRFS_BLOCK_GROUP_RAID1)
num_stripes = 2;
+ else if (type & BTRFS_BLOCK_GROUP_RAID1C3)
+ num_stripes = 3;
+ else if (type & BTRFS_BLOCK_GROUP_RAID1C4)
+ num_stripes = 4;
else if (type & BTRFS_BLOCK_GROUP_RAID10)
num_stripes = 4;
@@ -2022,7 +2025,6 @@ static int btrfs_statfs(struct dentry *dentry, struct kstatfs *buf)
{
struct btrfs_fs_info *fs_info = btrfs_sb(dentry->d_sb);
struct btrfs_super_block *disk_super = fs_info->super_copy;
- struct list_head *head = &fs_info->space_info;
struct btrfs_space_info *found;
u64 total_used = 0;
u64 total_free_data = 0;
@@ -2036,7 +2038,7 @@ static int btrfs_statfs(struct dentry *dentry, struct kstatfs *buf)
int mixed = 0;
rcu_read_lock();
- list_for_each_entry_rcu(found, head, list) {
+ list_for_each_entry_rcu(found, &fs_info->space_info, list) {
if (found->flags & BTRFS_BLOCK_GROUP_DATA) {
int i;
@@ -2297,7 +2299,7 @@ static const struct super_operations btrfs_super_ops = {
static const struct file_operations btrfs_ctl_fops = {
.open = btrfs_control_open,
.unlocked_ioctl = btrfs_control_ioctl,
- .compat_ioctl = btrfs_control_ioctl,
+ .compat_ioctl = compat_ptr_ioctl,
.owner = THIS_MODULE,
.llseek = noop_llseek,
};
@@ -2360,10 +2362,14 @@ static int __init init_btrfs_fs(void)
if (err)
goto free_cachep;
- err = extent_map_init();
+ err = extent_state_cache_init();
if (err)
goto free_extent_io;
+ err = extent_map_init();
+ if (err)
+ goto free_extent_state_cache;
+
err = ordered_data_init();
if (err)
goto free_extent_map;
@@ -2422,6 +2428,8 @@ free_ordered_data:
ordered_data_exit();
free_extent_map:
extent_map_exit();
+free_extent_state_cache:
+ extent_state_cache_exit();
free_extent_io:
extent_io_exit();
free_cachep:
@@ -2442,6 +2450,7 @@ static void __exit exit_btrfs_fs(void)
btrfs_prelim_ref_exit();
ordered_data_exit();
extent_map_exit();
+ extent_state_cache_exit();
extent_io_exit();
btrfs_interface_exit();
btrfs_end_io_wq_exit();
@@ -2456,3 +2465,6 @@ module_exit(exit_btrfs_fs)
MODULE_LICENSE("GPL");
MODULE_SOFTDEP("pre: crc32c");
+MODULE_SOFTDEP("pre: xxhash64");
+MODULE_SOFTDEP("pre: sha256");
+MODULE_SOFTDEP("pre: blake2b-256");
diff --git a/fs/btrfs/sysfs.c b/fs/btrfs/sysfs.c
index f6d3c80f2e28..5ebbe8a5ee76 100644
--- a/fs/btrfs/sysfs.c
+++ b/fs/btrfs/sysfs.c
@@ -9,6 +9,7 @@
#include <linux/spinlock.h>
#include <linux/completion.h>
#include <linux/bug.h>
+#include <crypto/hash.h>
#include "ctree.h"
#include "disk-io.h"
@@ -258,6 +259,7 @@ BTRFS_FEAT_ATTR_INCOMPAT(skinny_metadata, SKINNY_METADATA);
BTRFS_FEAT_ATTR_INCOMPAT(no_holes, NO_HOLES);
BTRFS_FEAT_ATTR_INCOMPAT(metadata_uuid, METADATA_UUID);
BTRFS_FEAT_ATTR_COMPAT_RO(free_space_tree, FREE_SPACE_TREE);
+BTRFS_FEAT_ATTR_INCOMPAT(raid1c34, RAID1C34);
static struct attribute *btrfs_supported_feature_attrs[] = {
BTRFS_FEAT_ATTR_PTR(mixed_backref),
@@ -272,6 +274,7 @@ static struct attribute *btrfs_supported_feature_attrs[] = {
BTRFS_FEAT_ATTR_PTR(no_holes),
BTRFS_FEAT_ATTR_PTR(metadata_uuid),
BTRFS_FEAT_ATTR_PTR(free_space_tree),
+ BTRFS_FEAT_ATTR_PTR(raid1c34),
NULL
};
@@ -295,8 +298,30 @@ static ssize_t rmdir_subvol_show(struct kobject *kobj,
}
BTRFS_ATTR(static_feature, rmdir_subvol, rmdir_subvol_show);
+static ssize_t supported_checksums_show(struct kobject *kobj,
+ struct kobj_attribute *a, char *buf)
+{
+ ssize_t ret = 0;
+ int i;
+
+ for (i = 0; i < btrfs_get_num_csums(); i++) {
+ /*
+ * This "trick" only works as long as 'enum btrfs_csum_type' has
+ * no holes in it
+ */
+ ret += snprintf(buf + ret, PAGE_SIZE - ret, "%s%s",
+ (i == 0 ? "" : " "), btrfs_super_csum_name(i));
+
+ }
+
+ ret += snprintf(buf + ret, PAGE_SIZE - ret, "\n");
+ return ret;
+}
+BTRFS_ATTR(static_feature, supported_checksums, supported_checksums_show);
+
static struct attribute *btrfs_supported_static_feature_attrs[] = {
BTRFS_ATTR_PTR(static_feature, rmdir_subvol),
+ BTRFS_ATTR_PTR(static_feature, supported_checksums),
NULL
};
@@ -372,16 +397,16 @@ static ssize_t raid_bytes_show(struct kobject *kobj,
{
struct btrfs_space_info *sinfo = to_space_info(kobj->parent);
- struct btrfs_block_group_cache *block_group;
+ struct btrfs_block_group *block_group;
int index = btrfs_bg_flags_to_raid_index(to_raid_kobj(kobj)->flags);
u64 val = 0;
down_read(&sinfo->groups_sem);
list_for_each_entry(block_group, &sinfo->block_groups[index], list) {
if (&attr->attr == BTRFS_ATTR_PTR(raid, total_bytes))
- val += block_group->key.offset;
+ val += block_group->length;
else
- val += btrfs_block_group_used(&block_group->item);
+ val += block_group->used;
}
up_read(&sinfo->groups_sem);
return snprintf(buf, PAGE_SIZE, "%llu\n", val);
@@ -604,6 +629,19 @@ static ssize_t btrfs_metadata_uuid_show(struct kobject *kobj,
BTRFS_ATTR(, metadata_uuid, btrfs_metadata_uuid_show);
+static ssize_t btrfs_checksum_show(struct kobject *kobj,
+ struct kobj_attribute *a, char *buf)
+{
+ struct btrfs_fs_info *fs_info = to_fs_info(kobj);
+ u16 csum_type = btrfs_super_csum_type(fs_info->super_copy);
+
+ return snprintf(buf, PAGE_SIZE, "%s (%s)\n",
+ btrfs_super_csum_name(csum_type),
+ crypto_shash_driver_name(fs_info->csum_shash));
+}
+
+BTRFS_ATTR(, checksum, btrfs_checksum_show);
+
static const struct attribute *btrfs_attrs[] = {
BTRFS_ATTR_PTR(, label),
BTRFS_ATTR_PTR(, nodesize),
@@ -611,6 +649,7 @@ static const struct attribute *btrfs_attrs[] = {
BTRFS_ATTR_PTR(, clone_alignment),
BTRFS_ATTR_PTR(, quota_override),
BTRFS_ATTR_PTR(, metadata_uuid),
+ BTRFS_ATTR_PTR(, checksum),
NULL,
};
@@ -822,7 +861,7 @@ static void init_feature_attrs(void)
* Create a sysfs entry for a given block group type at path
* /sys/fs/btrfs/UUID/allocation/data/TYPE
*/
-void btrfs_sysfs_add_block_group_type(struct btrfs_block_group_cache *cache)
+void btrfs_sysfs_add_block_group_type(struct btrfs_block_group *cache)
{
struct btrfs_fs_info *fs_info = cache->fs_info;
struct btrfs_space_info *space_info = cache->space_info;
diff --git a/fs/btrfs/sysfs.h b/fs/btrfs/sysfs.h
index 610e9c36a94c..e10c3adfc30f 100644
--- a/fs/btrfs/sysfs.h
+++ b/fs/btrfs/sysfs.h
@@ -32,7 +32,7 @@ int __init btrfs_init_sysfs(void);
void __cold btrfs_exit_sysfs(void);
int btrfs_sysfs_add_mounted(struct btrfs_fs_info *fs_info);
void btrfs_sysfs_remove_mounted(struct btrfs_fs_info *fs_info);
-void btrfs_sysfs_add_block_group_type(struct btrfs_block_group_cache *cache);
+void btrfs_sysfs_add_block_group_type(struct btrfs_block_group *cache);
int btrfs_sysfs_add_space_info_type(struct btrfs_fs_info *fs_info,
struct btrfs_space_info *space_info);
void btrfs_sysfs_remove_space_info(struct btrfs_space_info *space_info);
diff --git a/fs/btrfs/tests/btrfs-tests.c b/fs/btrfs/tests/btrfs-tests.c
index 99fe9bf3fdac..a7aca4141788 100644
--- a/fs/btrfs/tests/btrfs-tests.c
+++ b/fs/btrfs/tests/btrfs-tests.c
@@ -202,11 +202,11 @@ void btrfs_free_dummy_root(struct btrfs_root *root)
kfree(root);
}
-struct btrfs_block_group_cache *
+struct btrfs_block_group *
btrfs_alloc_dummy_block_group(struct btrfs_fs_info *fs_info,
unsigned long length)
{
- struct btrfs_block_group_cache *cache;
+ struct btrfs_block_group *cache;
cache = kzalloc(sizeof(*cache), GFP_KERNEL);
if (!cache)
@@ -218,9 +218,8 @@ btrfs_alloc_dummy_block_group(struct btrfs_fs_info *fs_info,
return NULL;
}
- cache->key.objectid = 0;
- cache->key.offset = length;
- cache->key.type = BTRFS_BLOCK_GROUP_ITEM_KEY;
+ cache->start = 0;
+ cache->length = length;
cache->full_stripe_len = fs_info->sectorsize;
cache->fs_info = fs_info;
@@ -233,7 +232,7 @@ btrfs_alloc_dummy_block_group(struct btrfs_fs_info *fs_info,
return cache;
}
-void btrfs_free_dummy_block_group(struct btrfs_block_group_cache *cache)
+void btrfs_free_dummy_block_group(struct btrfs_block_group *cache)
{
if (!cache)
return;
diff --git a/fs/btrfs/tests/btrfs-tests.h b/fs/btrfs/tests/btrfs-tests.h
index ee277bbd939b..9e52527357d8 100644
--- a/fs/btrfs/tests/btrfs-tests.h
+++ b/fs/btrfs/tests/btrfs-tests.h
@@ -41,9 +41,9 @@ struct inode *btrfs_new_test_inode(void);
struct btrfs_fs_info *btrfs_alloc_dummy_fs_info(u32 nodesize, u32 sectorsize);
void btrfs_free_dummy_fs_info(struct btrfs_fs_info *fs_info);
void btrfs_free_dummy_root(struct btrfs_root *root);
-struct btrfs_block_group_cache *
+struct btrfs_block_group *
btrfs_alloc_dummy_block_group(struct btrfs_fs_info *fs_info, unsigned long length);
-void btrfs_free_dummy_block_group(struct btrfs_block_group_cache *cache);
+void btrfs_free_dummy_block_group(struct btrfs_block_group *cache);
void btrfs_init_dummy_trans(struct btrfs_trans_handle *trans,
struct btrfs_fs_info *fs_info);
#else
diff --git a/fs/btrfs/tests/free-space-tests.c b/fs/btrfs/tests/free-space-tests.c
index 43ec7060fcd2..aebdf23f0cdd 100644
--- a/fs/btrfs/tests/free-space-tests.c
+++ b/fs/btrfs/tests/free-space-tests.c
@@ -17,7 +17,7 @@
* entry and remove space from either end and the middle, and make sure we can
* remove space that covers adjacent extent entries.
*/
-static int test_extents(struct btrfs_block_group_cache *cache)
+static int test_extents(struct btrfs_block_group *cache)
{
int ret = 0;
@@ -87,8 +87,7 @@ static int test_extents(struct btrfs_block_group_cache *cache)
return 0;
}
-static int test_bitmaps(struct btrfs_block_group_cache *cache,
- u32 sectorsize)
+static int test_bitmaps(struct btrfs_block_group *cache, u32 sectorsize)
{
u64 next_bitmap_offset;
int ret;
@@ -156,7 +155,7 @@ static int test_bitmaps(struct btrfs_block_group_cache *cache,
}
/* This is the high grade jackassery */
-static int test_bitmaps_and_extents(struct btrfs_block_group_cache *cache,
+static int test_bitmaps_and_extents(struct btrfs_block_group *cache,
u32 sectorsize)
{
u64 bitmap_offset = (u64)(BITS_PER_BITMAP * sectorsize);
@@ -331,7 +330,7 @@ static bool test_use_bitmap(struct btrfs_free_space_ctl *ctl,
/* Used by test_steal_space_from_bitmap_to_extent(). */
static int
-check_num_extents_and_bitmaps(const struct btrfs_block_group_cache *cache,
+check_num_extents_and_bitmaps(const struct btrfs_block_group *cache,
const int num_extents,
const int num_bitmaps)
{
@@ -351,7 +350,7 @@ check_num_extents_and_bitmaps(const struct btrfs_block_group_cache *cache,
}
/* Used by test_steal_space_from_bitmap_to_extent(). */
-static int check_cache_empty(struct btrfs_block_group_cache *cache)
+static int check_cache_empty(struct btrfs_block_group *cache)
{
u64 offset;
u64 max_extent_size;
@@ -393,7 +392,7 @@ static int check_cache_empty(struct btrfs_block_group_cache *cache)
* requests.
*/
static int
-test_steal_space_from_bitmap_to_extent(struct btrfs_block_group_cache *cache,
+test_steal_space_from_bitmap_to_extent(struct btrfs_block_group *cache,
u32 sectorsize)
{
int ret;
@@ -829,7 +828,7 @@ test_steal_space_from_bitmap_to_extent(struct btrfs_block_group_cache *cache,
int btrfs_test_free_space_cache(u32 sectorsize, u32 nodesize)
{
struct btrfs_fs_info *fs_info;
- struct btrfs_block_group_cache *cache;
+ struct btrfs_block_group *cache;
struct btrfs_root *root = NULL;
int ret = -ENOMEM;
diff --git a/fs/btrfs/tests/free-space-tree-tests.c b/fs/btrfs/tests/free-space-tree-tests.c
index bc92df977630..1a846bf6e197 100644
--- a/fs/btrfs/tests/free-space-tree-tests.c
+++ b/fs/btrfs/tests/free-space-tree-tests.c
@@ -18,7 +18,7 @@ struct free_space_extent {
static int __check_free_space_extents(struct btrfs_trans_handle *trans,
struct btrfs_fs_info *fs_info,
- struct btrfs_block_group_cache *cache,
+ struct btrfs_block_group *cache,
struct btrfs_path *path,
const struct free_space_extent * const extents,
unsigned int num_extents)
@@ -48,7 +48,7 @@ static int __check_free_space_extents(struct btrfs_trans_handle *trans,
if (flags & BTRFS_FREE_SPACE_USING_BITMAPS) {
if (path->slots[0] != 0)
goto invalid;
- end = cache->key.objectid + cache->key.offset;
+ end = cache->start + cache->length;
i = 0;
while (++path->slots[0] < btrfs_header_nritems(path->nodes[0])) {
btrfs_item_key_to_cpu(path->nodes[0], &key, path->slots[0]);
@@ -107,7 +107,7 @@ invalid:
static int check_free_space_extents(struct btrfs_trans_handle *trans,
struct btrfs_fs_info *fs_info,
- struct btrfs_block_group_cache *cache,
+ struct btrfs_block_group *cache,
struct btrfs_path *path,
const struct free_space_extent * const extents,
unsigned int num_extents)
@@ -150,12 +150,12 @@ static int check_free_space_extents(struct btrfs_trans_handle *trans,
static int test_empty_block_group(struct btrfs_trans_handle *trans,
struct btrfs_fs_info *fs_info,
- struct btrfs_block_group_cache *cache,
+ struct btrfs_block_group *cache,
struct btrfs_path *path,
u32 alignment)
{
const struct free_space_extent extents[] = {
- {cache->key.objectid, cache->key.offset},
+ {cache->start, cache->length},
};
return check_free_space_extents(trans, fs_info, cache, path,
@@ -164,7 +164,7 @@ static int test_empty_block_group(struct btrfs_trans_handle *trans,
static int test_remove_all(struct btrfs_trans_handle *trans,
struct btrfs_fs_info *fs_info,
- struct btrfs_block_group_cache *cache,
+ struct btrfs_block_group *cache,
struct btrfs_path *path,
u32 alignment)
{
@@ -172,8 +172,8 @@ static int test_remove_all(struct btrfs_trans_handle *trans,
int ret;
ret = __remove_from_free_space_tree(trans, cache, path,
- cache->key.objectid,
- cache->key.offset);
+ cache->start,
+ cache->length);
if (ret) {
test_err("could not remove free space");
return ret;
@@ -185,18 +185,17 @@ static int test_remove_all(struct btrfs_trans_handle *trans,
static int test_remove_beginning(struct btrfs_trans_handle *trans,
struct btrfs_fs_info *fs_info,
- struct btrfs_block_group_cache *cache,
+ struct btrfs_block_group *cache,
struct btrfs_path *path,
u32 alignment)
{
const struct free_space_extent extents[] = {
- {cache->key.objectid + alignment,
- cache->key.offset - alignment},
+ {cache->start + alignment, cache->length - alignment},
};
int ret;
ret = __remove_from_free_space_tree(trans, cache, path,
- cache->key.objectid, alignment);
+ cache->start, alignment);
if (ret) {
test_err("could not remove free space");
return ret;
@@ -209,19 +208,18 @@ static int test_remove_beginning(struct btrfs_trans_handle *trans,
static int test_remove_end(struct btrfs_trans_handle *trans,
struct btrfs_fs_info *fs_info,
- struct btrfs_block_group_cache *cache,
+ struct btrfs_block_group *cache,
struct btrfs_path *path,
u32 alignment)
{
const struct free_space_extent extents[] = {
- {cache->key.objectid, cache->key.offset - alignment},
+ {cache->start, cache->length - alignment},
};
int ret;
ret = __remove_from_free_space_tree(trans, cache, path,
- cache->key.objectid +
- cache->key.offset - alignment,
- alignment);
+ cache->start + cache->length - alignment,
+ alignment);
if (ret) {
test_err("could not remove free space");
return ret;
@@ -233,19 +231,18 @@ static int test_remove_end(struct btrfs_trans_handle *trans,
static int test_remove_middle(struct btrfs_trans_handle *trans,
struct btrfs_fs_info *fs_info,
- struct btrfs_block_group_cache *cache,
+ struct btrfs_block_group *cache,
struct btrfs_path *path,
u32 alignment)
{
const struct free_space_extent extents[] = {
- {cache->key.objectid, alignment},
- {cache->key.objectid + 2 * alignment,
- cache->key.offset - 2 * alignment},
+ {cache->start, alignment},
+ {cache->start + 2 * alignment, cache->length - 2 * alignment},
};
int ret;
ret = __remove_from_free_space_tree(trans, cache, path,
- cache->key.objectid + alignment,
+ cache->start + alignment,
alignment);
if (ret) {
test_err("could not remove free space");
@@ -258,24 +255,23 @@ static int test_remove_middle(struct btrfs_trans_handle *trans,
static int test_merge_left(struct btrfs_trans_handle *trans,
struct btrfs_fs_info *fs_info,
- struct btrfs_block_group_cache *cache,
+ struct btrfs_block_group *cache,
struct btrfs_path *path,
u32 alignment)
{
const struct free_space_extent extents[] = {
- {cache->key.objectid, 2 * alignment},
+ {cache->start, 2 * alignment},
};
int ret;
ret = __remove_from_free_space_tree(trans, cache, path,
- cache->key.objectid,
- cache->key.offset);
+ cache->start, cache->length);
if (ret) {
test_err("could not remove free space");
return ret;
}
- ret = __add_to_free_space_tree(trans, cache, path, cache->key.objectid,
+ ret = __add_to_free_space_tree(trans, cache, path, cache->start,
alignment);
if (ret) {
test_err("could not add free space");
@@ -283,7 +279,7 @@ static int test_merge_left(struct btrfs_trans_handle *trans,
}
ret = __add_to_free_space_tree(trans, cache, path,
- cache->key.objectid + alignment,
+ cache->start + alignment,
alignment);
if (ret) {
test_err("could not add free space");
@@ -296,25 +292,24 @@ static int test_merge_left(struct btrfs_trans_handle *trans,
static int test_merge_right(struct btrfs_trans_handle *trans,
struct btrfs_fs_info *fs_info,
- struct btrfs_block_group_cache *cache,
+ struct btrfs_block_group *cache,
struct btrfs_path *path,
u32 alignment)
{
const struct free_space_extent extents[] = {
- {cache->key.objectid + alignment, 2 * alignment},
+ {cache->start + alignment, 2 * alignment},
};
int ret;
ret = __remove_from_free_space_tree(trans, cache, path,
- cache->key.objectid,
- cache->key.offset);
+ cache->start, cache->length);
if (ret) {
test_err("could not remove free space");
return ret;
}
ret = __add_to_free_space_tree(trans, cache, path,
- cache->key.objectid + 2 * alignment,
+ cache->start + 2 * alignment,
alignment);
if (ret) {
test_err("could not add free space");
@@ -322,7 +317,7 @@ static int test_merge_right(struct btrfs_trans_handle *trans,
}
ret = __add_to_free_space_tree(trans, cache, path,
- cache->key.objectid + alignment,
+ cache->start + alignment,
alignment);
if (ret) {
test_err("could not add free space");
@@ -335,24 +330,23 @@ static int test_merge_right(struct btrfs_trans_handle *trans,
static int test_merge_both(struct btrfs_trans_handle *trans,
struct btrfs_fs_info *fs_info,
- struct btrfs_block_group_cache *cache,
+ struct btrfs_block_group *cache,
struct btrfs_path *path,
u32 alignment)
{
const struct free_space_extent extents[] = {
- {cache->key.objectid, 3 * alignment},
+ {cache->start, 3 * alignment},
};
int ret;
ret = __remove_from_free_space_tree(trans, cache, path,
- cache->key.objectid,
- cache->key.offset);
+ cache->start, cache->length);
if (ret) {
test_err("could not remove free space");
return ret;
}
- ret = __add_to_free_space_tree(trans, cache, path, cache->key.objectid,
+ ret = __add_to_free_space_tree(trans, cache, path, cache->start,
alignment);
if (ret) {
test_err("could not add free space");
@@ -360,16 +354,14 @@ static int test_merge_both(struct btrfs_trans_handle *trans,
}
ret = __add_to_free_space_tree(trans, cache, path,
- cache->key.objectid + 2 * alignment,
- alignment);
+ cache->start + 2 * alignment, alignment);
if (ret) {
test_err("could not add free space");
return ret;
}
ret = __add_to_free_space_tree(trans, cache, path,
- cache->key.objectid + alignment,
- alignment);
+ cache->start + alignment, alignment);
if (ret) {
test_err("could not add free space");
return ret;
@@ -381,26 +373,25 @@ static int test_merge_both(struct btrfs_trans_handle *trans,
static int test_merge_none(struct btrfs_trans_handle *trans,
struct btrfs_fs_info *fs_info,
- struct btrfs_block_group_cache *cache,
+ struct btrfs_block_group *cache,
struct btrfs_path *path,
u32 alignment)
{
const struct free_space_extent extents[] = {
- {cache->key.objectid, alignment},
- {cache->key.objectid + 2 * alignment, alignment},
- {cache->key.objectid + 4 * alignment, alignment},
+ {cache->start, alignment},
+ {cache->start + 2 * alignment, alignment},
+ {cache->start + 4 * alignment, alignment},
};
int ret;
ret = __remove_from_free_space_tree(trans, cache, path,
- cache->key.objectid,
- cache->key.offset);
+ cache->start, cache->length);
if (ret) {
test_err("could not remove free space");
return ret;
}
- ret = __add_to_free_space_tree(trans, cache, path, cache->key.objectid,
+ ret = __add_to_free_space_tree(trans, cache, path, cache->start,
alignment);
if (ret) {
test_err("could not add free space");
@@ -408,16 +399,14 @@ static int test_merge_none(struct btrfs_trans_handle *trans,
}
ret = __add_to_free_space_tree(trans, cache, path,
- cache->key.objectid + 4 * alignment,
- alignment);
+ cache->start + 4 * alignment, alignment);
if (ret) {
test_err("could not add free space");
return ret;
}
ret = __add_to_free_space_tree(trans, cache, path,
- cache->key.objectid + 2 * alignment,
- alignment);
+ cache->start + 2 * alignment, alignment);
if (ret) {
test_err("could not add free space");
return ret;
@@ -429,7 +418,7 @@ static int test_merge_none(struct btrfs_trans_handle *trans,
typedef int (*test_func_t)(struct btrfs_trans_handle *,
struct btrfs_fs_info *,
- struct btrfs_block_group_cache *,
+ struct btrfs_block_group *,
struct btrfs_path *,
u32 alignment);
@@ -438,7 +427,7 @@ static int run_test(test_func_t test_func, int bitmaps, u32 sectorsize,
{
struct btrfs_fs_info *fs_info;
struct btrfs_root *root = NULL;
- struct btrfs_block_group_cache *cache = NULL;
+ struct btrfs_block_group *cache = NULL;
struct btrfs_trans_handle trans;
struct btrfs_path *path = NULL;
int ret;
diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c
index 8624bdee8c5b..cfc08ef9b876 100644
--- a/fs/btrfs/transaction.c
+++ b/fs/btrfs/transaction.c
@@ -24,9 +24,79 @@
#define BTRFS_ROOT_TRANS_TAG 0
+/*
+ * Transaction states and transitions
+ *
+ * No running transaction (fs tree blocks are not modified)
+ * |
+ * | To next stage:
+ * | Call start_transaction() variants. Except btrfs_join_transaction_nostart().
+ * V
+ * Transaction N [[TRANS_STATE_RUNNING]]
+ * |
+ * | New trans handles can be attached to transaction N by calling all
+ * | start_transaction() variants.
+ * |
+ * | To next stage:
+ * | Call btrfs_commit_transaction() on any trans handle attached to
+ * | transaction N
+ * V
+ * Transaction N [[TRANS_STATE_COMMIT_START]]
+ * |
+ * | Will wait for previous running transaction to completely finish if there
+ * | is one
+ * |
+ * | Then one of the following happes:
+ * | - Wait for all other trans handle holders to release.
+ * | The btrfs_commit_transaction() caller will do the commit work.
+ * | - Wait for current transaction to be committed by others.
+ * | Other btrfs_commit_transaction() caller will do the commit work.
+ * |
+ * | At this stage, only btrfs_join_transaction*() variants can attach
+ * | to this running transaction.
+ * | All other variants will wait for current one to finish and attach to
+ * | transaction N+1.
+ * |
+ * | To next stage:
+ * | Caller is chosen to commit transaction N, and all other trans handle
+ * | haven been released.
+ * V
+ * Transaction N [[TRANS_STATE_COMMIT_DOING]]
+ * |
+ * | The heavy lifting transaction work is started.
+ * | From running delayed refs (modifying extent tree) to creating pending
+ * | snapshots, running qgroups.
+ * | In short, modify supporting trees to reflect modifications of subvolume
+ * | trees.
+ * |
+ * | At this stage, all start_transaction() calls will wait for this
+ * | transaction to finish and attach to transaction N+1.
+ * |
+ * | To next stage:
+ * | Until all supporting trees are updated.
+ * V
+ * Transaction N [[TRANS_STATE_UNBLOCKED]]
+ * | Transaction N+1
+ * | All needed trees are modified, thus we only [[TRANS_STATE_RUNNING]]
+ * | need to write them back to disk and update |
+ * | super blocks. |
+ * | |
+ * | At this stage, new transaction is allowed to |
+ * | start. |
+ * | All new start_transaction() calls will be |
+ * | attached to transid N+1. |
+ * | |
+ * | To next stage: |
+ * | Until all tree blocks are super blocks are |
+ * | written to block devices |
+ * V |
+ * Transaction N [[TRANS_STATE_COMPLETED]] V
+ * All tree blocks and super blocks are written. Transaction N+1
+ * This transaction is finished and all its [[TRANS_STATE_COMMIT_START]]
+ * data structures will be cleaned up. | Life goes on
+ */
static const unsigned int btrfs_blocked_trans_types[TRANS_STATE_MAX] = {
[TRANS_STATE_RUNNING] = 0U,
- [TRANS_STATE_BLOCKED] = __TRANS_START,
[TRANS_STATE_COMMIT_START] = (__TRANS_START | __TRANS_ATTACH),
[TRANS_STATE_COMMIT_DOING] = (__TRANS_START |
__TRANS_ATTACH |
@@ -63,10 +133,10 @@ void btrfs_put_transaction(struct btrfs_transaction *transaction)
* discard the physical locations of the block groups.
*/
while (!list_empty(&transaction->deleted_bgs)) {
- struct btrfs_block_group_cache *cache;
+ struct btrfs_block_group *cache;
cache = list_first_entry(&transaction->deleted_bgs,
- struct btrfs_block_group_cache,
+ struct btrfs_block_group,
bg_list);
list_del_init(&cache->bg_list);
btrfs_put_block_group_trimming(cache);
@@ -383,7 +453,7 @@ int btrfs_record_root_in_trans(struct btrfs_trans_handle *trans,
static inline int is_transaction_blocked(struct btrfs_transaction *trans)
{
- return (trans->state >= TRANS_STATE_BLOCKED &&
+ return (trans->state >= TRANS_STATE_COMMIT_START &&
trans->state < TRANS_STATE_UNBLOCKED &&
!trans->aborted);
}
@@ -570,7 +640,7 @@ again:
INIT_LIST_HEAD(&h->new_bgs);
smp_mb();
- if (cur_trans->state >= TRANS_STATE_BLOCKED &&
+ if (cur_trans->state >= TRANS_STATE_COMMIT_START &&
may_wait_transaction(fs_info, type)) {
current->journal_info = h;
btrfs_commit_transaction(h);
@@ -659,7 +729,7 @@ struct btrfs_trans_handle *btrfs_join_transaction(struct btrfs_root *root)
true);
}
-struct btrfs_trans_handle *btrfs_join_transaction_nolock(struct btrfs_root *root)
+struct btrfs_trans_handle *btrfs_join_transaction_spacecache(struct btrfs_root *root)
{
return start_transaction(root, 0, TRANS_JOIN_NOLOCK,
BTRFS_RESERVE_NO_FLUSH, true);
@@ -798,7 +868,7 @@ int btrfs_should_end_transaction(struct btrfs_trans_handle *trans)
struct btrfs_transaction *cur_trans = trans->transaction;
smp_mb();
- if (cur_trans->state >= TRANS_STATE_BLOCKED ||
+ if (cur_trans->state >= TRANS_STATE_COMMIT_START ||
cur_trans->delayed_refs.flushing)
return 1;
@@ -831,7 +901,6 @@ static int __btrfs_end_transaction(struct btrfs_trans_handle *trans,
{
struct btrfs_fs_info *info = trans->fs_info;
struct btrfs_transaction *cur_trans = trans->transaction;
- int lock = (trans->type != TRANS_JOIN_NOLOCK);
int err = 0;
if (refcount_read(&trans->use_count) > 1) {
@@ -847,13 +916,6 @@ static int __btrfs_end_transaction(struct btrfs_trans_handle *trans,
btrfs_trans_release_chunk_metadata(trans);
- if (lock && READ_ONCE(cur_trans->state) == TRANS_STATE_BLOCKED) {
- if (throttle)
- return btrfs_commit_transaction(trans);
- else
- wake_up_process(info->transaction_kthread);
- }
-
if (trans->type & __TRANS_FREEZABLE)
sb_end_intwrite(info->sb);
@@ -990,7 +1052,7 @@ static int __btrfs_wait_marked_extents(struct btrfs_fs_info *fs_info,
return werr;
}
-int btrfs_wait_extents(struct btrfs_fs_info *fs_info,
+static int btrfs_wait_extents(struct btrfs_fs_info *fs_info,
struct extent_io_tree *dirty_pages)
{
bool errors = false;
@@ -1875,7 +1937,7 @@ static void cleanup_transaction(struct btrfs_trans_handle *trans, int err)
static void btrfs_cleanup_pending_block_groups(struct btrfs_trans_handle *trans)
{
struct btrfs_fs_info *fs_info = trans->fs_info;
- struct btrfs_block_group_cache *block_group, *tmp;
+ struct btrfs_block_group *block_group, *tmp;
list_for_each_entry_safe(block_group, tmp, &trans->new_bgs, bg_list) {
btrfs_delayed_refs_rsv_release(fs_info, 1);
@@ -1949,6 +2011,8 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans)
struct btrfs_transaction *prev_trans = NULL;
int ret;
+ ASSERT(refcount_read(&trans->use_count) == 1);
+
/* Stop the commit early if ->aborted is set */
if (unlikely(READ_ONCE(cur_trans->aborted))) {
ret = cur_trans->aborted;
diff --git a/fs/btrfs/transaction.h b/fs/btrfs/transaction.h
index 2c5a6f6e5bb0..49f7196368f5 100644
--- a/fs/btrfs/transaction.h
+++ b/fs/btrfs/transaction.h
@@ -13,7 +13,6 @@
enum btrfs_trans_state {
TRANS_STATE_RUNNING,
- TRANS_STATE_BLOCKED,
TRANS_STATE_COMMIT_START,
TRANS_STATE_COMMIT_DOING,
TRANS_STATE_UNBLOCKED,
@@ -184,7 +183,7 @@ struct btrfs_trans_handle *btrfs_start_transaction_fallback_global_rsv(
unsigned int num_items,
int min_factor);
struct btrfs_trans_handle *btrfs_join_transaction(struct btrfs_root *root);
-struct btrfs_trans_handle *btrfs_join_transaction_nolock(struct btrfs_root *root);
+struct btrfs_trans_handle *btrfs_join_transaction_spacecache(struct btrfs_root *root);
struct btrfs_trans_handle *btrfs_join_transaction_nostart(struct btrfs_root *root);
struct btrfs_trans_handle *btrfs_attach_transaction(struct btrfs_root *root);
struct btrfs_trans_handle *btrfs_attach_transaction_barrier(
@@ -218,8 +217,6 @@ int btrfs_record_root_in_trans(struct btrfs_trans_handle *trans,
struct btrfs_root *root);
int btrfs_write_marked_extents(struct btrfs_fs_info *fs_info,
struct extent_io_tree *dirty_pages, int mark);
-int btrfs_wait_extents(struct btrfs_fs_info *fs_info,
- struct extent_io_tree *dirty_pages);
int btrfs_wait_tree_log_extents(struct btrfs_root *root, int mark);
int btrfs_transaction_blocked(struct btrfs_fs_info *info);
int btrfs_transaction_in_commit(struct btrfs_fs_info *info);
diff --git a/fs/btrfs/tree-checker.c b/fs/btrfs/tree-checker.c
index 43e488f5d063..493d4d9e0f79 100644
--- a/fs/btrfs/tree-checker.c
+++ b/fs/btrfs/tree-checker.c
@@ -23,6 +23,7 @@
#include "disk-io.h"
#include "compression.h"
#include "volumes.h"
+#include "misc.h"
/*
* Error message should follow the following format:
@@ -124,6 +125,74 @@ static u64 file_extent_end(struct extent_buffer *leaf,
return end;
}
+/*
+ * Customized report for dir_item, the only new important information is
+ * key->objectid, which represents inode number
+ */
+__printf(3, 4)
+__cold
+static void dir_item_err(const struct extent_buffer *eb, int slot,
+ const char *fmt, ...)
+{
+ const struct btrfs_fs_info *fs_info = eb->fs_info;
+ struct btrfs_key key;
+ struct va_format vaf;
+ va_list args;
+
+ btrfs_item_key_to_cpu(eb, &key, slot);
+ va_start(args, fmt);
+
+ vaf.fmt = fmt;
+ vaf.va = &args;
+
+ btrfs_crit(fs_info,
+ "corrupt %s: root=%llu block=%llu slot=%d ino=%llu, %pV",
+ btrfs_header_level(eb) == 0 ? "leaf" : "node",
+ btrfs_header_owner(eb), btrfs_header_bytenr(eb), slot,
+ key.objectid, &vaf);
+ va_end(args);
+}
+
+/*
+ * This functions checks prev_key->objectid, to ensure current key and prev_key
+ * share the same objectid as inode number.
+ *
+ * This is to detect missing INODE_ITEM in subvolume trees.
+ *
+ * Return true if everything is OK or we don't need to check.
+ * Return false if anything is wrong.
+ */
+static bool check_prev_ino(struct extent_buffer *leaf,
+ struct btrfs_key *key, int slot,
+ struct btrfs_key *prev_key)
+{
+ /* No prev key, skip check */
+ if (slot == 0)
+ return true;
+
+ /* Only these key->types needs to be checked */
+ ASSERT(key->type == BTRFS_XATTR_ITEM_KEY ||
+ key->type == BTRFS_INODE_REF_KEY ||
+ key->type == BTRFS_DIR_INDEX_KEY ||
+ key->type == BTRFS_DIR_ITEM_KEY ||
+ key->type == BTRFS_EXTENT_DATA_KEY);
+
+ /*
+ * Only subvolume trees along with their reloc trees need this check.
+ * Things like log tree doesn't follow this ino requirement.
+ */
+ if (!is_fstree(btrfs_header_owner(leaf)))
+ return true;
+
+ if (key->objectid == prev_key->objectid)
+ return true;
+
+ /* Error found */
+ dir_item_err(leaf, slot,
+ "invalid previous key objectid, have %llu expect %llu",
+ prev_key->objectid, key->objectid);
+ return false;
+}
static int check_extent_data_item(struct extent_buffer *leaf,
struct btrfs_key *key, int slot,
struct btrfs_key *prev_key)
@@ -141,13 +210,33 @@ static int check_extent_data_item(struct extent_buffer *leaf,
return -EUCLEAN;
}
+ /*
+ * Previous key must have the same key->objectid (ino).
+ * It can be XATTR_ITEM, INODE_ITEM or just another EXTENT_DATA.
+ * But if objectids mismatch, it means we have a missing
+ * INODE_ITEM.
+ */
+ if (!check_prev_ino(leaf, key, slot, prev_key))
+ return -EUCLEAN;
+
fi = btrfs_item_ptr(leaf, slot, struct btrfs_file_extent_item);
- if (btrfs_file_extent_type(leaf, fi) > BTRFS_FILE_EXTENT_TYPES) {
+ /*
+ * Make sure the item contains at least inline header, so the file
+ * extent type is not some garbage.
+ */
+ if (item_size < BTRFS_FILE_EXTENT_INLINE_DATA_START) {
+ file_extent_err(leaf, slot,
+ "invalid item size, have %u expect [%lu, %u)",
+ item_size, BTRFS_FILE_EXTENT_INLINE_DATA_START,
+ SZ_4K);
+ return -EUCLEAN;
+ }
+ if (btrfs_file_extent_type(leaf, fi) >= BTRFS_NR_FILE_EXTENT_TYPES) {
file_extent_err(leaf, slot,
"invalid type for file extent, have %u expect range [0, %u]",
btrfs_file_extent_type(leaf, fi),
- BTRFS_FILE_EXTENT_TYPES);
+ BTRFS_NR_FILE_EXTENT_TYPES - 1);
return -EUCLEAN;
}
@@ -155,11 +244,11 @@ static int check_extent_data_item(struct extent_buffer *leaf,
* Support for new compression/encryption must introduce incompat flag,
* and must be caught in open_ctree().
*/
- if (btrfs_file_extent_compression(leaf, fi) > BTRFS_COMPRESS_TYPES) {
+ if (btrfs_file_extent_compression(leaf, fi) >= BTRFS_NR_COMPRESS_TYPES) {
file_extent_err(leaf, slot,
"invalid compression for file extent, have %u expect range [0, %u]",
btrfs_file_extent_compression(leaf, fi),
- BTRFS_COMPRESS_TYPES);
+ BTRFS_NR_COMPRESS_TYPES - 1);
return -EUCLEAN;
}
if (btrfs_file_extent_encryption(leaf, fi)) {
@@ -270,42 +359,17 @@ static int check_csum_item(struct extent_buffer *leaf, struct btrfs_key *key,
return 0;
}
-/*
- * Customized reported for dir_item, only important new info is key->objectid,
- * which represents inode number
- */
-__printf(3, 4)
-__cold
-static void dir_item_err(const struct extent_buffer *eb, int slot,
- const char *fmt, ...)
-{
- const struct btrfs_fs_info *fs_info = eb->fs_info;
- struct btrfs_key key;
- struct va_format vaf;
- va_list args;
-
- btrfs_item_key_to_cpu(eb, &key, slot);
- va_start(args, fmt);
-
- vaf.fmt = fmt;
- vaf.va = &args;
-
- btrfs_crit(fs_info,
- "corrupt %s: root=%llu block=%llu slot=%d ino=%llu, %pV",
- btrfs_header_level(eb) == 0 ? "leaf" : "node",
- btrfs_header_owner(eb), btrfs_header_bytenr(eb), slot,
- key.objectid, &vaf);
- va_end(args);
-}
-
static int check_dir_item(struct extent_buffer *leaf,
- struct btrfs_key *key, int slot)
+ struct btrfs_key *key, struct btrfs_key *prev_key,
+ int slot)
{
struct btrfs_fs_info *fs_info = leaf->fs_info;
struct btrfs_dir_item *di;
u32 item_size = btrfs_item_size_nr(leaf, slot);
u32 cur = 0;
+ if (!check_prev_ino(leaf, key, slot, prev_key))
+ return -EUCLEAN;
di = btrfs_item_ptr(leaf, slot, struct btrfs_dir_item);
while (cur < item_size) {
u32 name_len;
@@ -459,23 +523,23 @@ static int check_block_group_item(struct extent_buffer *leaf,
read_extent_buffer(leaf, &bgi, btrfs_item_ptr_offset(leaf, slot),
sizeof(bgi));
- if (btrfs_block_group_chunk_objectid(&bgi) !=
+ if (btrfs_stack_block_group_chunk_objectid(&bgi) !=
BTRFS_FIRST_CHUNK_TREE_OBJECTID) {
block_group_err(leaf, slot,
"invalid block group chunk objectid, have %llu expect %llu",
- btrfs_block_group_chunk_objectid(&bgi),
+ btrfs_stack_block_group_chunk_objectid(&bgi),
BTRFS_FIRST_CHUNK_TREE_OBJECTID);
return -EUCLEAN;
}
- if (btrfs_block_group_used(&bgi) > key->offset) {
+ if (btrfs_stack_block_group_used(&bgi) > key->offset) {
block_group_err(leaf, slot,
"invalid block group used, have %llu expect [0, %llu)",
- btrfs_block_group_used(&bgi), key->offset);
+ btrfs_stack_block_group_used(&bgi), key->offset);
return -EUCLEAN;
}
- flags = btrfs_block_group_flags(&bgi);
+ flags = btrfs_stack_block_group_flags(&bgi);
if (hweight64(flags & BTRFS_BLOCK_GROUP_PROFILE_MASK) > 1) {
block_group_err(leaf, slot,
"invalid profile flags, have 0x%llx (%lu bits set) expect no more than 1 bit set",
@@ -609,7 +673,7 @@ int btrfs_check_chunk_valid(struct extent_buffer *leaf,
return -EUCLEAN;
}
- if (!is_power_of_2(type & BTRFS_BLOCK_GROUP_PROFILE_MASK) &&
+ if (!has_single_bit_set(type & BTRFS_BLOCK_GROUP_PROFILE_MASK) &&
(type & BTRFS_BLOCK_GROUP_PROFILE_MASK) != 0) {
chunk_err(leaf, chunk, logical,
"invalid chunk profile flag: 0x%llx, expect 0 or 1 bit set",
@@ -686,9 +750,7 @@ static void dev_item_err(const struct extent_buffer *eb, int slot,
static int check_dev_item(struct extent_buffer *leaf,
struct btrfs_key *key, int slot)
{
- struct btrfs_fs_info *fs_info = leaf->fs_info;
struct btrfs_dev_item *ditem;
- u64 max_devid = max(BTRFS_MAX_DEVS(fs_info), BTRFS_MAX_DEVS_SYS_CHUNK);
if (key->objectid != BTRFS_DEV_ITEMS_OBJECTID) {
dev_item_err(leaf, slot,
@@ -696,12 +758,6 @@ static int check_dev_item(struct extent_buffer *leaf,
key->objectid, BTRFS_DEV_ITEMS_OBJECTID);
return -EUCLEAN;
}
- if (key->offset > max_devid) {
- dev_item_err(leaf, slot,
- "invalid devid: has=%llu expect=[0, %llu]",
- key->offset, max_devid);
- return -EUCLEAN;
- }
ditem = btrfs_item_ptr(leaf, slot, struct btrfs_dev_item);
if (btrfs_device_id(leaf, ditem) != key->offset) {
dev_item_err(leaf, slot,
@@ -793,11 +849,11 @@ static int check_inode_item(struct extent_buffer *leaf,
}
/*
- * S_IFMT is not bit mapped so we can't completely rely on is_power_of_2,
- * but is_power_of_2() can save us from checking FIFO/CHR/DIR/REG.
- * Only needs to check BLK, LNK and SOCKS
+ * S_IFMT is not bit mapped so we can't completely rely on
+ * is_power_of_2/has_single_bit_set, but it can save us from checking
+ * FIFO/CHR/DIR/REG. Only needs to check BLK, LNK and SOCKS
*/
- if (!is_power_of_2(mode & S_IFMT)) {
+ if (!has_single_bit_set(mode & S_IFMT)) {
if (!S_ISLNK(mode) && !S_ISBLK(mode) && !S_ISSOCK(mode)) {
inode_item_err(fs_info, leaf, slot,
"invalid mode: has 0%o expect valid S_IF* bit(s)",
@@ -1018,8 +1074,8 @@ static int check_extent_item(struct extent_buffer *leaf,
btrfs_super_generation(fs_info->super_copy) + 1);
return -EUCLEAN;
}
- if (!is_power_of_2(flags & (BTRFS_EXTENT_FLAG_DATA |
- BTRFS_EXTENT_FLAG_TREE_BLOCK))) {
+ if (!has_single_bit_set(flags & (BTRFS_EXTENT_FLAG_DATA |
+ BTRFS_EXTENT_FLAG_TREE_BLOCK))) {
extent_err(leaf, slot,
"invalid extent flag, have 0x%llx expect 1 bit set in 0x%llx",
flags, BTRFS_EXTENT_FLAG_DATA |
@@ -1232,6 +1288,58 @@ static int check_extent_data_ref(struct extent_buffer *leaf,
return 0;
}
+#define inode_ref_err(fs_info, eb, slot, fmt, args...) \
+ inode_item_err(fs_info, eb, slot, fmt, ##args)
+static int check_inode_ref(struct extent_buffer *leaf,
+ struct btrfs_key *key, struct btrfs_key *prev_key,
+ int slot)
+{
+ struct btrfs_inode_ref *iref;
+ unsigned long ptr;
+ unsigned long end;
+
+ if (!check_prev_ino(leaf, key, slot, prev_key))
+ return -EUCLEAN;
+ /* namelen can't be 0, so item_size == sizeof() is also invalid */
+ if (btrfs_item_size_nr(leaf, slot) <= sizeof(*iref)) {
+ inode_ref_err(fs_info, leaf, slot,
+ "invalid item size, have %u expect (%zu, %u)",
+ btrfs_item_size_nr(leaf, slot),
+ sizeof(*iref), BTRFS_LEAF_DATA_SIZE(leaf->fs_info));
+ return -EUCLEAN;
+ }
+
+ ptr = btrfs_item_ptr_offset(leaf, slot);
+ end = ptr + btrfs_item_size_nr(leaf, slot);
+ while (ptr < end) {
+ u16 namelen;
+
+ if (ptr + sizeof(iref) > end) {
+ inode_ref_err(fs_info, leaf, slot,
+ "inode ref overflow, ptr %lu end %lu inode_ref_size %zu",
+ ptr, end, sizeof(iref));
+ return -EUCLEAN;
+ }
+
+ iref = (struct btrfs_inode_ref *)ptr;
+ namelen = btrfs_inode_ref_name_len(leaf, iref);
+ if (ptr + sizeof(*iref) + namelen > end) {
+ inode_ref_err(fs_info, leaf, slot,
+ "inode ref overflow, ptr %lu end %lu namelen %u",
+ ptr, end, namelen);
+ return -EUCLEAN;
+ }
+
+ /*
+ * NOTE: In theory we should record all found index numbers
+ * to find any duplicated indexes, but that will be too time
+ * consuming for inodes with too many hard links.
+ */
+ ptr += sizeof(*iref) + namelen;
+ }
+ return 0;
+}
+
/*
* Common point to switch the item-specific validation.
*/
@@ -1252,7 +1360,10 @@ static int check_leaf_item(struct extent_buffer *leaf,
case BTRFS_DIR_ITEM_KEY:
case BTRFS_DIR_INDEX_KEY:
case BTRFS_XATTR_ITEM_KEY:
- ret = check_dir_item(leaf, key, slot);
+ ret = check_dir_item(leaf, key, prev_key, slot);
+ break;
+ case BTRFS_INODE_REF_KEY:
+ ret = check_inode_ref(leaf, key, prev_key, slot);
break;
case BTRFS_BLOCK_GROUP_ITEM_KEY:
ret = check_block_group_item(leaf, key, slot);
diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index 8a6cc600bf18..6f757361db53 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -559,7 +559,7 @@ static noinline struct inode *read_one_inode(struct btrfs_root *root,
key.objectid = objectid;
key.type = BTRFS_INODE_ITEM_KEY;
key.offset = 0;
- inode = btrfs_iget(root->fs_info->sb, &key, root, NULL);
+ inode = btrfs_iget(root->fs_info->sb, &key, root);
if (IS_ERR(inode))
inode = NULL;
return inode;
@@ -945,54 +945,32 @@ static noinline int backref_in_log(struct btrfs_root *log,
const char *name, int namelen)
{
struct btrfs_path *path;
- struct btrfs_inode_ref *ref;
- unsigned long ptr;
- unsigned long ptr_end;
- unsigned long name_ptr;
- int found_name_len;
- int item_size;
int ret;
- int match = 0;
path = btrfs_alloc_path();
if (!path)
return -ENOMEM;
ret = btrfs_search_slot(NULL, log, key, path, 0, 0);
- if (ret != 0)
+ if (ret < 0) {
goto out;
-
- ptr = btrfs_item_ptr_offset(path->nodes[0], path->slots[0]);
-
- if (key->type == BTRFS_INODE_EXTREF_KEY) {
- if (btrfs_find_name_in_ext_backref(path->nodes[0],
- path->slots[0],
- ref_objectid,
- name, namelen))
- match = 1;
-
+ } else if (ret == 1) {
+ ret = 0;
goto out;
}
- item_size = btrfs_item_size_nr(path->nodes[0], path->slots[0]);
- ptr_end = ptr + item_size;
- while (ptr < ptr_end) {
- ref = (struct btrfs_inode_ref *)ptr;
- found_name_len = btrfs_inode_ref_name_len(path->nodes[0], ref);
- if (found_name_len == namelen) {
- name_ptr = (unsigned long)(ref + 1);
- ret = memcmp_extent_buffer(path->nodes[0], name,
- name_ptr, namelen);
- if (ret == 0) {
- match = 1;
- goto out;
- }
- }
- ptr = (unsigned long)(ref + 1) + found_name_len;
- }
+ if (key->type == BTRFS_INODE_EXTREF_KEY)
+ ret = !!btrfs_find_name_in_ext_backref(path->nodes[0],
+ path->slots[0],
+ ref_objectid,
+ name, namelen);
+ else
+ ret = !!btrfs_find_name_in_backref(path->nodes[0],
+ path->slots[0],
+ name, namelen);
out:
btrfs_free_path(path);
- return match;
+ return ret;
}
static inline int __add_inode_ref(struct btrfs_trans_handle *trans,
@@ -1050,10 +1028,13 @@ again:
(unsigned long)(victim_ref + 1),
victim_name_len);
- if (!backref_in_log(log_root, &search_key,
- parent_objectid,
- victim_name,
- victim_name_len)) {
+ ret = backref_in_log(log_root, &search_key,
+ parent_objectid, victim_name,
+ victim_name_len);
+ if (ret < 0) {
+ kfree(victim_name);
+ return ret;
+ } else if (!ret) {
inc_nlink(&inode->vfs_inode);
btrfs_release_path(path);
@@ -1115,10 +1096,12 @@ again:
search_key.offset = btrfs_extref_hash(parent_objectid,
victim_name,
victim_name_len);
- ret = 0;
- if (!backref_in_log(log_root, &search_key,
- parent_objectid, victim_name,
- victim_name_len)) {
+ ret = backref_in_log(log_root, &search_key,
+ parent_objectid, victim_name,
+ victim_name_len);
+ if (ret < 0) {
+ return ret;
+ } else if (!ret) {
ret = -ENOENT;
victim_parent = read_one_inode(root,
parent_objectid);
@@ -1885,30 +1868,6 @@ static noinline int insert_one_name(struct btrfs_trans_handle *trans,
}
/*
- * Return true if an inode reference exists in the log for the given name,
- * inode and parent inode.
- */
-static bool name_in_log_ref(struct btrfs_root *log_root,
- const char *name, const int name_len,
- const u64 dirid, const u64 ino)
-{
- struct btrfs_key search_key;
-
- search_key.objectid = ino;
- search_key.type = BTRFS_INODE_REF_KEY;
- search_key.offset = dirid;
- if (backref_in_log(log_root, &search_key, dirid, name, name_len))
- return true;
-
- search_key.type = BTRFS_INODE_EXTREF_KEY;
- search_key.offset = btrfs_extref_hash(dirid, name, name_len);
- if (backref_in_log(log_root, &search_key, dirid, name, name_len))
- return true;
-
- return false;
-}
-
-/*
* take a single entry in a log directory item and replay it into
* the subvolume.
*
@@ -2024,8 +1983,31 @@ out:
return ret;
insert:
- if (name_in_log_ref(root->log_root, name, name_len,
- key->objectid, log_key.objectid)) {
+ /*
+ * Check if the inode reference exists in the log for the given name,
+ * inode and parent inode
+ */
+ found_key.objectid = log_key.objectid;
+ found_key.type = BTRFS_INODE_REF_KEY;
+ found_key.offset = key->objectid;
+ ret = backref_in_log(root->log_root, &found_key, 0, name, name_len);
+ if (ret < 0) {
+ goto out;
+ } else if (ret) {
+ /* The dentry will be added later. */
+ ret = 0;
+ update_size = false;
+ goto out;
+ }
+
+ found_key.objectid = log_key.objectid;
+ found_key.type = BTRFS_INODE_EXTREF_KEY;
+ found_key.offset = key->objectid;
+ ret = backref_in_log(root->log_root, &found_key, key->objectid, name,
+ name_len);
+ if (ret < 0) {
+ goto out;
+ } else if (ret) {
/* The dentry will be added later. */
ret = 0;
update_size = false;
@@ -2869,7 +2851,7 @@ static int walk_log_tree(struct btrfs_trans_handle *trans,
level = btrfs_header_level(log->node);
orig_level = level;
path->nodes[level] = log->node;
- extent_buffer_get(log->node);
+ atomic_inc(&log->node->refs);
path->slots[level] = 0;
while (1) {
@@ -4983,7 +4965,7 @@ static int log_conflicting_inodes(struct btrfs_trans_handle *trans,
key.objectid = ino;
key.type = BTRFS_INODE_ITEM_KEY;
key.offset = 0;
- inode = btrfs_iget(fs_info->sb, &key, root, NULL);
+ inode = btrfs_iget(fs_info->sb, &key, root);
/*
* If the other inode that had a conflicting dir entry was
* deleted in the current transaction, we need to log its parent
@@ -4993,8 +4975,7 @@ static int log_conflicting_inodes(struct btrfs_trans_handle *trans,
ret = PTR_ERR(inode);
if (ret == -ENOENT) {
key.objectid = parent;
- inode = btrfs_iget(fs_info->sb, &key, root,
- NULL);
+ inode = btrfs_iget(fs_info->sb, &key, root);
if (IS_ERR(inode)) {
ret = PTR_ERR(inode);
} else {
@@ -5699,7 +5680,7 @@ process_leaf:
continue;
btrfs_release_path(path);
- di_inode = btrfs_iget(fs_info->sb, &di_key, root, NULL);
+ di_inode = btrfs_iget(fs_info->sb, &di_key, root);
if (IS_ERR(di_inode)) {
ret = PTR_ERR(di_inode);
goto next_dir_inode;
@@ -5825,8 +5806,7 @@ static int btrfs_log_all_parents(struct btrfs_trans_handle *trans,
cur_offset = item_size;
}
- dir_inode = btrfs_iget(fs_info->sb, &inode_key,
- root, NULL);
+ dir_inode = btrfs_iget(fs_info->sb, &inode_key, root);
/*
* If the parent inode was deleted, return an error to
* fallback to a transaction commit. This is to prevent
@@ -5900,7 +5880,7 @@ static int log_new_ancestors(struct btrfs_trans_handle *trans,
search_key.objectid = found_key.offset;
search_key.type = BTRFS_INODE_ITEM_KEY;
search_key.offset = 0;
- inode = btrfs_iget(fs_info->sb, &search_key, root, NULL);
+ inode = btrfs_iget(fs_info->sb, &search_key, root);
if (IS_ERR(inode))
return PTR_ERR(inode);
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index bdfe4493e43a..d8e5560db285 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -58,6 +58,30 @@ const struct btrfs_raid_attr btrfs_raid_array[BTRFS_NR_RAID_TYPES] = {
.bg_flag = BTRFS_BLOCK_GROUP_RAID1,
.mindev_error = BTRFS_ERROR_DEV_RAID1_MIN_NOT_MET,
},
+ [BTRFS_RAID_RAID1C3] = {
+ .sub_stripes = 1,
+ .dev_stripes = 1,
+ .devs_max = 0,
+ .devs_min = 3,
+ .tolerated_failures = 2,
+ .devs_increment = 3,
+ .ncopies = 3,
+ .raid_name = "raid1c3",
+ .bg_flag = BTRFS_BLOCK_GROUP_RAID1C3,
+ .mindev_error = BTRFS_ERROR_DEV_RAID1C3_MIN_NOT_MET,
+ },
+ [BTRFS_RAID_RAID1C4] = {
+ .sub_stripes = 1,
+ .dev_stripes = 1,
+ .devs_max = 0,
+ .devs_min = 4,
+ .tolerated_failures = 3,
+ .devs_increment = 4,
+ .ncopies = 4,
+ .raid_name = "raid1c4",
+ .bg_flag = BTRFS_BLOCK_GROUP_RAID1C4,
+ .mindev_error = BTRFS_ERROR_DEV_RAID1C4_MIN_NOT_MET,
+ },
[BTRFS_RAID_DUP] = {
.sub_stripes = 1,
.dev_stripes = 2,
@@ -297,7 +321,7 @@ static int __btrfs_map_block(struct btrfs_fs_info *fs_info,
DEFINE_MUTEX(uuid_mutex);
static LIST_HEAD(fs_uuids);
-struct list_head *btrfs_get_fs_uuids(void)
+struct list_head * __attribute_const__ btrfs_get_fs_uuids(void)
{
return &fs_uuids;
}
@@ -397,8 +421,6 @@ static struct btrfs_device *__alloc_device(void)
INIT_LIST_HEAD(&dev->dev_alloc_list);
INIT_LIST_HEAD(&dev->post_commit_list);
- spin_lock_init(&dev->io_lock);
-
atomic_set(&dev->reada_in_flight, 0);
atomic_set(&dev->dev_stats_ccnt, 0);
btrfs_device_data_ordered_init(dev);
@@ -501,212 +523,6 @@ error:
return ret;
}
-static void requeue_list(struct btrfs_pending_bios *pending_bios,
- struct bio *head, struct bio *tail)
-{
-
- struct bio *old_head;
-
- old_head = pending_bios->head;
- pending_bios->head = head;
- if (pending_bios->tail)
- tail->bi_next = old_head;
- else
- pending_bios->tail = tail;
-}
-
-/*
- * we try to collect pending bios for a device so we don't get a large
- * number of procs sending bios down to the same device. This greatly
- * improves the schedulers ability to collect and merge the bios.
- *
- * But, it also turns into a long list of bios to process and that is sure
- * to eventually make the worker thread block. The solution here is to
- * make some progress and then put this work struct back at the end of
- * the list if the block device is congested. This way, multiple devices
- * can make progress from a single worker thread.
- */
-static noinline void run_scheduled_bios(struct btrfs_device *device)
-{
- struct btrfs_fs_info *fs_info = device->fs_info;
- struct bio *pending;
- struct backing_dev_info *bdi;
- struct btrfs_pending_bios *pending_bios;
- struct bio *tail;
- struct bio *cur;
- int again = 0;
- unsigned long num_run;
- unsigned long batch_run = 0;
- unsigned long last_waited = 0;
- int force_reg = 0;
- int sync_pending = 0;
- struct blk_plug plug;
-
- /*
- * this function runs all the bios we've collected for
- * a particular device. We don't want to wander off to
- * another device without first sending all of these down.
- * So, setup a plug here and finish it off before we return
- */
- blk_start_plug(&plug);
-
- bdi = device->bdev->bd_bdi;
-
-loop:
- spin_lock(&device->io_lock);
-
-loop_lock:
- num_run = 0;
-
- /* take all the bios off the list at once and process them
- * later on (without the lock held). But, remember the
- * tail and other pointers so the bios can be properly reinserted
- * into the list if we hit congestion
- */
- if (!force_reg && device->pending_sync_bios.head) {
- pending_bios = &device->pending_sync_bios;
- force_reg = 1;
- } else {
- pending_bios = &device->pending_bios;
- force_reg = 0;
- }
-
- pending = pending_bios->head;
- tail = pending_bios->tail;
- WARN_ON(pending && !tail);
-
- /*
- * if pending was null this time around, no bios need processing
- * at all and we can stop. Otherwise it'll loop back up again
- * and do an additional check so no bios are missed.
- *
- * device->running_pending is used to synchronize with the
- * schedule_bio code.
- */
- if (device->pending_sync_bios.head == NULL &&
- device->pending_bios.head == NULL) {
- again = 0;
- device->running_pending = 0;
- } else {
- again = 1;
- device->running_pending = 1;
- }
-
- pending_bios->head = NULL;
- pending_bios->tail = NULL;
-
- spin_unlock(&device->io_lock);
-
- while (pending) {
-
- rmb();
- /* we want to work on both lists, but do more bios on the
- * sync list than the regular list
- */
- if ((num_run > 32 &&
- pending_bios != &device->pending_sync_bios &&
- device->pending_sync_bios.head) ||
- (num_run > 64 && pending_bios == &device->pending_sync_bios &&
- device->pending_bios.head)) {
- spin_lock(&device->io_lock);
- requeue_list(pending_bios, pending, tail);
- goto loop_lock;
- }
-
- cur = pending;
- pending = pending->bi_next;
- cur->bi_next = NULL;
-
- BUG_ON(atomic_read(&cur->__bi_cnt) == 0);
-
- /*
- * if we're doing the sync list, record that our
- * plug has some sync requests on it
- *
- * If we're doing the regular list and there are
- * sync requests sitting around, unplug before
- * we add more
- */
- if (pending_bios == &device->pending_sync_bios) {
- sync_pending = 1;
- } else if (sync_pending) {
- blk_finish_plug(&plug);
- blk_start_plug(&plug);
- sync_pending = 0;
- }
-
- btrfsic_submit_bio(cur);
- num_run++;
- batch_run++;
-
- cond_resched();
-
- /*
- * we made progress, there is more work to do and the bdi
- * is now congested. Back off and let other work structs
- * run instead
- */
- if (pending && bdi_write_congested(bdi) && batch_run > 8 &&
- fs_info->fs_devices->open_devices > 1) {
- struct io_context *ioc;
-
- ioc = current->io_context;
-
- /*
- * the main goal here is that we don't want to
- * block if we're going to be able to submit
- * more requests without blocking.
- *
- * This code does two great things, it pokes into
- * the elevator code from a filesystem _and_
- * it makes assumptions about how batching works.
- */
- if (ioc && ioc->nr_batch_requests > 0 &&
- time_before(jiffies, ioc->last_waited + HZ/50UL) &&
- (last_waited == 0 ||
- ioc->last_waited == last_waited)) {
- /*
- * we want to go through our batch of
- * requests and stop. So, we copy out
- * the ioc->last_waited time and test
- * against it before looping
- */
- last_waited = ioc->last_waited;
- cond_resched();
- continue;
- }
- spin_lock(&device->io_lock);
- requeue_list(pending_bios, pending, tail);
- device->running_pending = 1;
-
- spin_unlock(&device->io_lock);
- btrfs_queue_work(fs_info->submit_workers,
- &device->work);
- goto done;
- }
- }
-
- cond_resched();
- if (again)
- goto loop;
-
- spin_lock(&device->io_lock);
- if (device->pending_bios.head || device->pending_sync_bios.head)
- goto loop_lock;
- spin_unlock(&device->io_lock);
-
-done:
- blk_finish_plug(&plug);
-}
-
-static void pending_bios_fn(struct btrfs_work *work)
-{
- struct btrfs_device *device;
-
- device = container_of(work, struct btrfs_device, work);
- run_scheduled_bios(device);
-}
-
static bool device_path_matched(const char *path, struct btrfs_device *device)
{
int found;
@@ -818,7 +634,7 @@ static int btrfs_open_one_device(struct btrfs_fs_devices *fs_devices,
}
clear_bit(BTRFS_DEV_STATE_WRITEABLE, &device->dev_state);
- fs_devices->seeding = 1;
+ fs_devices->seeding = true;
} else {
if (bdev_read_only(bdev))
clear_bit(BTRFS_DEV_STATE_WRITEABLE, &device->dev_state);
@@ -828,7 +644,7 @@ static int btrfs_open_one_device(struct btrfs_fs_devices *fs_devices,
q = bdev_get_queue(bdev);
if (!blk_queue_nonrot(q))
- fs_devices->rotating = 1;
+ fs_devices->rotating = true;
device->bdev = bdev;
clear_bit(BTRFS_DEV_STATE_IN_FS_METADATA, &device->dev_state);
@@ -1005,11 +821,15 @@ static noinline struct btrfs_device *device_list_add(const char *path,
*new_device_added = true;
if (disk_super->label[0])
- pr_info("BTRFS: device label %s devid %llu transid %llu %s\n",
- disk_super->label, devid, found_transid, path);
+ pr_info(
+ "BTRFS: device label %s devid %llu transid %llu %s scanned by %s (%d)\n",
+ disk_super->label, devid, found_transid, path,
+ current->comm, task_pid_nr(current));
else
- pr_info("BTRFS: device fsid %pU devid %llu transid %llu %s\n",
- disk_super->fsid, devid, found_transid, path);
+ pr_info(
+ "BTRFS: device fsid %pU devid %llu transid %llu %s scanned by %s (%d)\n",
+ disk_super->fsid, devid, found_transid, path,
+ current->comm, task_pid_nr(current));
} else if (!device->name || strcmp(device->name->str, path)) {
/*
@@ -1295,7 +1115,7 @@ static int close_fs_devices(struct btrfs_fs_devices *fs_devices)
WARN_ON(fs_devices->open_devices);
WARN_ON(fs_devices->rw_devices);
fs_devices->opened = 0;
- fs_devices->seeding = 0;
+ fs_devices->seeding = false;
return 0;
}
@@ -2048,7 +1868,7 @@ static struct btrfs_device * btrfs_find_next_active_device(
* where this function called, there should be always be another device (or
* this_dev) which is active.
*/
-void btrfs_assign_next_active_device(struct btrfs_device *device,
+void __cold btrfs_assign_next_active_device(struct btrfs_device *device,
struct btrfs_device *this_dev)
{
struct btrfs_fs_info *fs_info = device->fs_info;
@@ -2450,11 +2270,11 @@ static int btrfs_prepare_sprout(struct btrfs_fs_info *fs_info)
list_splice_init(&fs_devices->alloc_list, &seed_devices->alloc_list);
mutex_unlock(&fs_info->chunk_mutex);
- fs_devices->seeding = 0;
+ fs_devices->seeding = false;
fs_devices->num_devices = 0;
fs_devices->open_devices = 0;
fs_devices->missing_devices = 0;
- fs_devices->rotating = 0;
+ fs_devices->rotating = false;
fs_devices->seed = seed_devices;
generate_random_uuid(fs_devices->fsid);
@@ -2649,7 +2469,7 @@ int btrfs_init_new_device(struct btrfs_fs_info *fs_info, const char *device_path
atomic64_add(device->total_bytes, &fs_info->free_chunk_space);
if (!blk_queue_nonrot(q))
- fs_devices->rotating = 1;
+ fs_devices->rotating = true;
orig_super_total_bytes = btrfs_super_total_bytes(fs_info->super_copy);
btrfs_set_super_total_bytes(fs_info->super_copy,
@@ -3177,7 +2997,7 @@ error:
static int btrfs_may_alloc_data_chunk(struct btrfs_fs_info *fs_info,
u64 chunk_offset)
{
- struct btrfs_block_group_cache *cache;
+ struct btrfs_block_group *cache;
u64 bytes_used;
u64 chunk_type;
@@ -3186,27 +3006,28 @@ static int btrfs_may_alloc_data_chunk(struct btrfs_fs_info *fs_info,
chunk_type = cache->flags;
btrfs_put_block_group(cache);
- if (chunk_type & BTRFS_BLOCK_GROUP_DATA) {
- spin_lock(&fs_info->data_sinfo->lock);
- bytes_used = fs_info->data_sinfo->bytes_used;
- spin_unlock(&fs_info->data_sinfo->lock);
+ if (!(chunk_type & BTRFS_BLOCK_GROUP_DATA))
+ return 0;
+
+ spin_lock(&fs_info->data_sinfo->lock);
+ bytes_used = fs_info->data_sinfo->bytes_used;
+ spin_unlock(&fs_info->data_sinfo->lock);
- if (!bytes_used) {
- struct btrfs_trans_handle *trans;
- int ret;
+ if (!bytes_used) {
+ struct btrfs_trans_handle *trans;
+ int ret;
- trans = btrfs_join_transaction(fs_info->tree_root);
- if (IS_ERR(trans))
- return PTR_ERR(trans);
+ trans = btrfs_join_transaction(fs_info->tree_root);
+ if (IS_ERR(trans))
+ return PTR_ERR(trans);
- ret = btrfs_force_chunk_alloc(trans,
- BTRFS_BLOCK_GROUP_DATA);
- btrfs_end_transaction(trans);
- if (ret < 0)
- return ret;
- return 1;
- }
+ ret = btrfs_force_chunk_alloc(trans, BTRFS_BLOCK_GROUP_DATA);
+ btrfs_end_transaction(trans);
+ if (ret < 0)
+ return ret;
+ return 1;
}
+
return 0;
}
@@ -3385,28 +3206,28 @@ static int chunk_profiles_filter(u64 chunk_type,
static int chunk_usage_range_filter(struct btrfs_fs_info *fs_info, u64 chunk_offset,
struct btrfs_balance_args *bargs)
{
- struct btrfs_block_group_cache *cache;
+ struct btrfs_block_group *cache;
u64 chunk_used;
u64 user_thresh_min;
u64 user_thresh_max;
int ret = 1;
cache = btrfs_lookup_block_group(fs_info, chunk_offset);
- chunk_used = btrfs_block_group_used(&cache->item);
+ chunk_used = cache->used;
if (bargs->usage_min == 0)
user_thresh_min = 0;
else
- user_thresh_min = div_factor_fine(cache->key.offset,
- bargs->usage_min);
+ user_thresh_min = div_factor_fine(cache->length,
+ bargs->usage_min);
if (bargs->usage_max == 0)
user_thresh_max = 1;
else if (bargs->usage_max > 100)
- user_thresh_max = cache->key.offset;
+ user_thresh_max = cache->length;
else
- user_thresh_max = div_factor_fine(cache->key.offset,
- bargs->usage_max);
+ user_thresh_max = div_factor_fine(cache->length,
+ bargs->usage_max);
if (user_thresh_min <= chunk_used && chunk_used < user_thresh_max)
ret = 0;
@@ -3418,20 +3239,19 @@ static int chunk_usage_range_filter(struct btrfs_fs_info *fs_info, u64 chunk_off
static int chunk_usage_filter(struct btrfs_fs_info *fs_info,
u64 chunk_offset, struct btrfs_balance_args *bargs)
{
- struct btrfs_block_group_cache *cache;
+ struct btrfs_block_group *cache;
u64 chunk_used, user_thresh;
int ret = 1;
cache = btrfs_lookup_block_group(fs_info, chunk_offset);
- chunk_used = btrfs_block_group_used(&cache->item);
+ chunk_used = cache->used;
if (bargs->usage_min == 0)
user_thresh = 1;
else if (bargs->usage > 100)
- user_thresh = cache->key.offset;
+ user_thresh = cache->length;
else
- user_thresh = div_factor_fine(cache->key.offset,
- bargs->usage);
+ user_thresh = div_factor_fine(cache->length, bargs->usage);
if (chunk_used < user_thresh)
ret = 0;
@@ -3844,12 +3664,7 @@ static int alloc_profile_is_valid(u64 flags, int extended)
if (flags == 0)
return !extended; /* "0" is valid for usual profiles */
- /* true if exactly one bit set */
- /*
- * Don't use is_power_of_2(unsigned long) because it won't work
- * for the single profile (1ULL << 48) on 32-bit CPUs.
- */
- return flags != 0 && (flags & (flags - 1)) == 0;
+ return has_single_bit_set(flags);
}
static inline int balance_need_close(struct btrfs_fs_info *fs_info)
@@ -4036,7 +3851,7 @@ int btrfs_balance(struct btrfs_fs_info *fs_info,
int ret;
u64 num_devices;
unsigned seq;
- bool reducing_integrity;
+ bool reducing_redundancy;
int i;
if (btrfs_fs_closing(fs_info) ||
@@ -4119,9 +3934,9 @@ int btrfs_balance(struct btrfs_fs_info *fs_info,
((bctl->meta.flags & BTRFS_BALANCE_ARGS_CONVERT) &&
(fs_info->avail_metadata_alloc_bits & allowed) &&
!(bctl->meta.target & allowed)))
- reducing_integrity = true;
+ reducing_redundancy = true;
else
- reducing_integrity = false;
+ reducing_redundancy = false;
/* if we're not converting, the target field is uninitialized */
meta_target = (bctl->meta.flags & BTRFS_BALANCE_ARGS_CONVERT) ?
@@ -4130,13 +3945,13 @@ int btrfs_balance(struct btrfs_fs_info *fs_info,
bctl->data.target : fs_info->avail_data_alloc_bits;
} while (read_seqretry(&fs_info->profiles_lock, seq));
- if (reducing_integrity) {
+ if (reducing_redundancy) {
if (bctl->flags & BTRFS_BALANCE_FORCE) {
btrfs_info(fs_info,
- "balance: force reducing metadata integrity");
+ "balance: force reducing metadata redundancy");
} else {
btrfs_err(fs_info,
- "balance: reduces metadata integrity, use --force if you want this");
+ "balance: reduces metadata redundancy, use --force if you want this");
ret = -EINVAL;
goto out;
}
@@ -4902,6 +4717,14 @@ static void check_raid56_incompat_flag(struct btrfs_fs_info *info, u64 type)
btrfs_set_fs_incompat(info, RAID56);
}
+static void check_raid1c34_incompat_flag(struct btrfs_fs_info *info, u64 type)
+{
+ if (!(type & (BTRFS_BLOCK_GROUP_RAID1C3 | BTRFS_BLOCK_GROUP_RAID1C4)))
+ return;
+
+ btrfs_set_fs_incompat(info, RAID1C34);
+}
+
static int __btrfs_alloc_chunk(struct btrfs_trans_handle *trans,
u64 start, u64 type)
{
@@ -4967,6 +4790,7 @@ static int __btrfs_alloc_chunk(struct btrfs_trans_handle *trans,
} else if (type & BTRFS_BLOCK_GROUP_SYSTEM) {
max_stripe_size = SZ_32M;
max_chunk_size = 2 * max_stripe_size;
+ devs_max = min_t(int, devs_max, BTRFS_MAX_DEVS_SYS_CHUNK);
} else {
btrfs_err(info, "invalid chunk type 0x%llx requested",
type);
@@ -5047,8 +4871,11 @@ static int __btrfs_alloc_chunk(struct btrfs_trans_handle *trans,
sort(devices_info, ndevs, sizeof(struct btrfs_device_info),
btrfs_cmp_device_info, NULL);
- /* round down to number of usable stripes */
- ndevs = round_down(ndevs, devs_increment);
+ /*
+ * Round down to number of usable stripes, devs_increment can be any
+ * number so we can't use round_down()
+ */
+ ndevs -= ndevs % devs_increment;
if (ndevs < devs_min) {
ret = -ENOSPC;
@@ -5164,6 +4991,7 @@ static int __btrfs_alloc_chunk(struct btrfs_trans_handle *trans,
free_extent_map(em);
check_raid56_incompat_flag(info, type);
+ check_raid1c34_incompat_flag(info, type);
kfree(devices_info);
return 0;
@@ -5582,12 +5410,13 @@ void btrfs_put_bbio(struct btrfs_bio *bbio)
* replace.
*/
static int __btrfs_map_block_for_discard(struct btrfs_fs_info *fs_info,
- u64 logical, u64 length,
+ u64 logical, u64 *length_ret,
struct btrfs_bio **bbio_ret)
{
struct extent_map *em;
struct map_lookup *map;
struct btrfs_bio *bbio;
+ u64 length = *length_ret;
u64 offset;
u64 stripe_nr;
u64 stripe_nr_end;
@@ -5620,7 +5449,8 @@ static int __btrfs_map_block_for_discard(struct btrfs_fs_info *fs_info,
}
offset = logical - em->start;
- length = min_t(u64, em->len - offset, length);
+ length = min_t(u64, em->start + em->len - logical, length);
+ *length_ret = length;
stripe_len = map->stripe_len;
/*
@@ -6035,7 +5865,7 @@ static int __btrfs_map_block(struct btrfs_fs_info *fs_info,
if (op == BTRFS_MAP_DISCARD)
return __btrfs_map_block_for_discard(fs_info, logical,
- *length, bbio_ret);
+ length, bbio_ret);
ret = btrfs_get_io_geometry(fs_info, op, logical, *length, &geom);
if (ret < 0)
@@ -6415,52 +6245,8 @@ static void btrfs_end_bio(struct bio *bio)
}
}
-/*
- * see run_scheduled_bios for a description of why bios are collected for
- * async submit.
- *
- * This will add one bio to the pending list for a device and make sure
- * the work struct is scheduled.
- */
-static noinline void btrfs_schedule_bio(struct btrfs_device *device,
- struct bio *bio)
-{
- struct btrfs_fs_info *fs_info = device->fs_info;
- int should_queue = 1;
- struct btrfs_pending_bios *pending_bios;
-
- /* don't bother with additional async steps for reads, right now */
- if (bio_op(bio) == REQ_OP_READ) {
- btrfsic_submit_bio(bio);
- return;
- }
-
- WARN_ON(bio->bi_next);
- bio->bi_next = NULL;
-
- spin_lock(&device->io_lock);
- if (op_is_sync(bio->bi_opf))
- pending_bios = &device->pending_sync_bios;
- else
- pending_bios = &device->pending_bios;
-
- if (pending_bios->tail)
- pending_bios->tail->bi_next = bio;
-
- pending_bios->tail = bio;
- if (!pending_bios->head)
- pending_bios->head = bio;
- if (device->running_pending)
- should_queue = 0;
-
- spin_unlock(&device->io_lock);
-
- if (should_queue)
- btrfs_queue_work(fs_info->submit_workers, &device->work);
-}
-
static void submit_stripe_bio(struct btrfs_bio *bbio, struct bio *bio,
- u64 physical, int dev_nr, int async)
+ u64 physical, int dev_nr)
{
struct btrfs_device *dev = bbio->stripes[dev_nr].dev;
struct btrfs_fs_info *fs_info = bbio->fs_info;
@@ -6478,10 +6264,7 @@ static void submit_stripe_bio(struct btrfs_bio *bbio, struct bio *bio,
btrfs_bio_counter_inc_noblocked(fs_info);
- if (async)
- btrfs_schedule_bio(dev, bio);
- else
- btrfsic_submit_bio(bio);
+ btrfsic_submit_bio(bio);
}
static void bbio_error(struct btrfs_bio *bbio, struct bio *bio, u64 logical)
@@ -6502,7 +6285,7 @@ static void bbio_error(struct btrfs_bio *bbio, struct bio *bio, u64 logical)
}
blk_status_t btrfs_map_bio(struct btrfs_fs_info *fs_info, struct bio *bio,
- int mirror_num, int async_submit)
+ int mirror_num)
{
struct btrfs_device *dev;
struct bio *first_bio = bio;
@@ -6571,7 +6354,7 @@ blk_status_t btrfs_map_bio(struct btrfs_fs_info *fs_info, struct bio *bio,
bio = first_bio;
submit_stripe_bio(bbio, bio, bbio->stripes[dev_nr].physical,
- dev_nr, async_submit);
+ dev_nr);
}
btrfs_bio_counter_dec(fs_info);
return BLK_STS_OK;
@@ -6675,9 +6458,6 @@ struct btrfs_device *btrfs_alloc_device(struct btrfs_fs_info *fs_info,
else
generate_random_uuid(dev->uuid);
- btrfs_init_work(&dev->work, btrfs_submit_helper,
- pending_bios_fn, NULL, NULL);
-
return dev;
}
@@ -6874,7 +6654,7 @@ static struct btrfs_fs_devices *open_seed_devices(struct btrfs_fs_info *fs_info,
if (IS_ERR(fs_devices))
return fs_devices;
- fs_devices->seeding = 1;
+ fs_devices->seeding = true;
fs_devices->opened = 1;
return fs_devices;
}
@@ -7063,48 +6843,49 @@ int btrfs_read_sys_array(struct btrfs_fs_info *fs_info)
sb_array_offset += len;
cur_offset += len;
- if (key.type == BTRFS_CHUNK_ITEM_KEY) {
- chunk = (struct btrfs_chunk *)sb_array_offset;
- /*
- * At least one btrfs_chunk with one stripe must be
- * present, exact stripe count check comes afterwards
- */
- len = btrfs_chunk_item_size(1);
- if (cur_offset + len > array_size)
- goto out_short_read;
-
- num_stripes = btrfs_chunk_num_stripes(sb, chunk);
- if (!num_stripes) {
- btrfs_err(fs_info,
- "invalid number of stripes %u in sys_array at offset %u",
- num_stripes, cur_offset);
- ret = -EIO;
- break;
- }
+ if (key.type != BTRFS_CHUNK_ITEM_KEY) {
+ btrfs_err(fs_info,
+ "unexpected item type %u in sys_array at offset %u",
+ (u32)key.type, cur_offset);
+ ret = -EIO;
+ break;
+ }
- type = btrfs_chunk_type(sb, chunk);
- if ((type & BTRFS_BLOCK_GROUP_SYSTEM) == 0) {
- btrfs_err(fs_info,
- "invalid chunk type %llu in sys_array at offset %u",
- type, cur_offset);
- ret = -EIO;
- break;
- }
+ chunk = (struct btrfs_chunk *)sb_array_offset;
+ /*
+ * At least one btrfs_chunk with one stripe must be present,
+ * exact stripe count check comes afterwards
+ */
+ len = btrfs_chunk_item_size(1);
+ if (cur_offset + len > array_size)
+ goto out_short_read;
- len = btrfs_chunk_item_size(num_stripes);
- if (cur_offset + len > array_size)
- goto out_short_read;
+ num_stripes = btrfs_chunk_num_stripes(sb, chunk);
+ if (!num_stripes) {
+ btrfs_err(fs_info,
+ "invalid number of stripes %u in sys_array at offset %u",
+ num_stripes, cur_offset);
+ ret = -EIO;
+ break;
+ }
- ret = read_one_chunk(&key, sb, chunk);
- if (ret)
- break;
- } else {
+ type = btrfs_chunk_type(sb, chunk);
+ if ((type & BTRFS_BLOCK_GROUP_SYSTEM) == 0) {
btrfs_err(fs_info,
- "unexpected item type %u in sys_array at offset %u",
- (u32)key.type, cur_offset);
+ "invalid chunk type %llu in sys_array at offset %u",
+ type, cur_offset);
ret = -EIO;
break;
}
+
+ len = btrfs_chunk_item_size(num_stripes);
+ if (cur_offset + len > array_size)
+ goto out_short_read;
+
+ ret = read_one_chunk(&key, sb, chunk);
+ if (ret)
+ break;
+
array_ptr += len;
sb_array_offset += len;
cur_offset += len;
diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h
index a7da1f3e3627..fc1b564b9cfe 100644
--- a/fs/btrfs/volumes.h
+++ b/fs/btrfs/volumes.h
@@ -18,10 +18,6 @@ extern struct mutex uuid_mutex;
#define BTRFS_STRIPE_LEN SZ_64K
struct buffer_head;
-struct btrfs_pending_bios {
- struct bio *head;
- struct bio *tail;
-};
struct btrfs_io_geometry {
/* remaining bytes before crossing a stripe */
@@ -68,13 +64,6 @@ struct btrfs_device {
u64 generation;
- spinlock_t io_lock ____cacheline_aligned;
- int running_pending;
- /* regular prio bios */
- struct btrfs_pending_bios pending_bios;
- /* sync bios */
- struct btrfs_pending_bios pending_sync_bios;
-
struct block_device *bdev;
/* the mode sent to blkdev_get */
@@ -254,14 +243,14 @@ struct btrfs_fs_devices {
struct list_head alloc_list;
struct btrfs_fs_devices *seed;
- int seeding;
+ bool seeding;
int opened;
/* set when we find or add a device that doesn't have the
* nonrot flag set
*/
- int rotating;
+ bool rotating;
struct btrfs_fs_info *fs_info;
/* sysfs kobjects */
@@ -330,7 +319,6 @@ struct btrfs_bio {
u64 map_type; /* get from map_lookup->type */
bio_end_io_t *end_io;
struct bio *orig_bio;
- unsigned long flags;
void *private;
atomic_t error;
int max_errors;
@@ -436,7 +424,7 @@ int btrfs_read_chunk_tree(struct btrfs_fs_info *fs_info);
int btrfs_alloc_chunk(struct btrfs_trans_handle *trans, u64 type);
void btrfs_mapping_tree_free(struct extent_map_tree *tree);
blk_status_t btrfs_map_bio(struct btrfs_fs_info *fs_info, struct bio *bio,
- int mirror_num, int async_submit);
+ int mirror_num);
int btrfs_open_devices(struct btrfs_fs_devices *fs_devices,
fmode_t flags, void *holder);
struct btrfs_device *btrfs_scan_one_device(const char *path,
@@ -557,6 +545,10 @@ static inline enum btrfs_raid_types btrfs_bg_flags_to_raid_index(u64 flags)
return BTRFS_RAID_RAID10;
else if (flags & BTRFS_BLOCK_GROUP_RAID1)
return BTRFS_RAID_RAID1;
+ else if (flags & BTRFS_BLOCK_GROUP_RAID1C3)
+ return BTRFS_RAID_RAID1C3;
+ else if (flags & BTRFS_BLOCK_GROUP_RAID1C4)
+ return BTRFS_RAID_RAID1C4;
else if (flags & BTRFS_BLOCK_GROUP_DUP)
return BTRFS_RAID_DUP;
else if (flags & BTRFS_BLOCK_GROUP_RAID0)
@@ -571,7 +563,7 @@ static inline enum btrfs_raid_types btrfs_bg_flags_to_raid_index(u64 flags)
void btrfs_commit_device_sizes(struct btrfs_transaction *trans);
-struct list_head *btrfs_get_fs_uuids(void);
+struct list_head * __attribute_const__ btrfs_get_fs_uuids(void);
void btrfs_set_fs_info_ptr(struct btrfs_fs_info *fs_info);
void btrfs_reset_fs_info_ptr(struct btrfs_fs_info *fs_info);
bool btrfs_check_rw_degradable(struct btrfs_fs_info *fs_info,
diff --git a/fs/btrfs/zlib.c b/fs/btrfs/zlib.c
index df1aace5df50..a6c90a003c12 100644
--- a/fs/btrfs/zlib.c
+++ b/fs/btrfs/zlib.c
@@ -29,19 +29,9 @@ struct workspace {
static struct workspace_manager wsm;
-static void zlib_init_workspace_manager(void)
+struct list_head *zlib_get_workspace(unsigned int level)
{
- btrfs_init_workspace_manager(&wsm, &btrfs_zlib_compress);
-}
-
-static void zlib_cleanup_workspace_manager(void)
-{
- btrfs_cleanup_workspace_manager(&wsm);
-}
-
-static struct list_head *zlib_get_workspace(unsigned int level)
-{
- struct list_head *ws = btrfs_get_workspace(&wsm, level);
+ struct list_head *ws = btrfs_get_workspace(BTRFS_COMPRESS_ZLIB, level);
struct workspace *workspace = list_entry(ws, struct workspace, list);
workspace->level = level;
@@ -49,12 +39,7 @@ static struct list_head *zlib_get_workspace(unsigned int level)
return ws;
}
-static void zlib_put_workspace(struct list_head *ws)
-{
- btrfs_put_workspace(&wsm, ws);
-}
-
-static void zlib_free_workspace(struct list_head *ws)
+void zlib_free_workspace(struct list_head *ws)
{
struct workspace *workspace = list_entry(ws, struct workspace, list);
@@ -63,7 +48,7 @@ static void zlib_free_workspace(struct list_head *ws)
kfree(workspace);
}
-static struct list_head *zlib_alloc_workspace(unsigned int level)
+struct list_head *zlib_alloc_workspace(unsigned int level)
{
struct workspace *workspace;
int workspacesize;
@@ -88,13 +73,9 @@ fail:
return ERR_PTR(-ENOMEM);
}
-static int zlib_compress_pages(struct list_head *ws,
- struct address_space *mapping,
- u64 start,
- struct page **pages,
- unsigned long *out_pages,
- unsigned long *total_in,
- unsigned long *total_out)
+int zlib_compress_pages(struct list_head *ws, struct address_space *mapping,
+ u64 start, struct page **pages, unsigned long *out_pages,
+ unsigned long *total_in, unsigned long *total_out)
{
struct workspace *workspace = list_entry(ws, struct workspace, list);
int ret;
@@ -228,7 +209,7 @@ out:
return ret;
}
-static int zlib_decompress_bio(struct list_head *ws, struct compressed_bio *cb)
+int zlib_decompress_bio(struct list_head *ws, struct compressed_bio *cb)
{
struct workspace *workspace = list_entry(ws, struct workspace, list);
int ret = 0, ret2;
@@ -319,10 +300,9 @@ done:
return ret;
}
-static int zlib_decompress(struct list_head *ws, unsigned char *data_in,
- struct page *dest_page,
- unsigned long start_byte,
- size_t srclen, size_t destlen)
+int zlib_decompress(struct list_head *ws, unsigned char *data_in,
+ struct page *dest_page, unsigned long start_byte, size_t srclen,
+ size_t destlen)
{
struct workspace *workspace = list_entry(ws, struct workspace, list);
int ret = 0;
@@ -419,15 +399,7 @@ next:
}
const struct btrfs_compress_op btrfs_zlib_compress = {
- .init_workspace_manager = zlib_init_workspace_manager,
- .cleanup_workspace_manager = zlib_cleanup_workspace_manager,
- .get_workspace = zlib_get_workspace,
- .put_workspace = zlib_put_workspace,
- .alloc_workspace = zlib_alloc_workspace,
- .free_workspace = zlib_free_workspace,
- .compress_pages = zlib_compress_pages,
- .decompress_bio = zlib_decompress_bio,
- .decompress = zlib_decompress,
+ .workspace_manager = &wsm,
.max_level = 9,
.default_level = BTRFS_ZLIB_DEFAULT_LEVEL,
};
diff --git a/fs/btrfs/zstd.c b/fs/btrfs/zstd.c
index 764d47b107e5..9a4871636c6c 100644
--- a/fs/btrfs/zstd.c
+++ b/fs/btrfs/zstd.c
@@ -91,9 +91,8 @@ static inline struct workspace *list_to_workspace(struct list_head *list)
return container_of(list, struct workspace, list);
}
-static void zstd_free_workspace(struct list_head *ws);
-static struct list_head *zstd_alloc_workspace(unsigned int level);
-
+void zstd_free_workspace(struct list_head *ws);
+struct list_head *zstd_alloc_workspace(unsigned int level);
/*
* zstd_reclaim_timer_fn - reclaim timer
* @t: timer
@@ -168,7 +167,7 @@ static void zstd_calc_ws_mem_sizes(void)
}
}
-static void zstd_init_workspace_manager(void)
+void zstd_init_workspace_manager(void)
{
struct list_head *ws;
int i;
@@ -194,7 +193,7 @@ static void zstd_init_workspace_manager(void)
}
}
-static void zstd_cleanup_workspace_manager(void)
+void zstd_cleanup_workspace_manager(void)
{
struct workspace *workspace;
int i;
@@ -261,7 +260,7 @@ static struct list_head *zstd_find_workspace(unsigned int level)
* attempt to allocate a new workspace. If we fail to allocate one due to
* memory pressure, go to sleep waiting for the max level workspace to free up.
*/
-static struct list_head *zstd_get_workspace(unsigned int level)
+struct list_head *zstd_get_workspace(unsigned int level)
{
struct list_head *ws;
unsigned int nofs_flag;
@@ -302,7 +301,7 @@ again:
* isn't set, it is also set here. Only the max level workspace tries and wakes
* up waiting workspaces.
*/
-static void zstd_put_workspace(struct list_head *ws)
+void zstd_put_workspace(struct list_head *ws)
{
struct workspace *workspace = list_to_workspace(ws);
@@ -332,7 +331,7 @@ static void zstd_put_workspace(struct list_head *ws)
cond_wake_up(&wsm.wait);
}
-static void zstd_free_workspace(struct list_head *ws)
+void zstd_free_workspace(struct list_head *ws)
{
struct workspace *workspace = list_entry(ws, struct workspace, list);
@@ -341,7 +340,7 @@ static void zstd_free_workspace(struct list_head *ws)
kfree(workspace);
}
-static struct list_head *zstd_alloc_workspace(unsigned int level)
+struct list_head *zstd_alloc_workspace(unsigned int level)
{
struct workspace *workspace;
@@ -367,13 +366,9 @@ fail:
return ERR_PTR(-ENOMEM);
}
-static int zstd_compress_pages(struct list_head *ws,
- struct address_space *mapping,
- u64 start,
- struct page **pages,
- unsigned long *out_pages,
- unsigned long *total_in,
- unsigned long *total_out)
+int zstd_compress_pages(struct list_head *ws, struct address_space *mapping,
+ u64 start, struct page **pages, unsigned long *out_pages,
+ unsigned long *total_in, unsigned long *total_out)
{
struct workspace *workspace = list_entry(ws, struct workspace, list);
ZSTD_CStream *stream;
@@ -548,7 +543,7 @@ out:
return ret;
}
-static int zstd_decompress_bio(struct list_head *ws, struct compressed_bio *cb)
+int zstd_decompress_bio(struct list_head *ws, struct compressed_bio *cb)
{
struct workspace *workspace = list_entry(ws, struct workspace, list);
struct page **pages_in = cb->compressed_pages;
@@ -626,10 +621,9 @@ done:
return ret;
}
-static int zstd_decompress(struct list_head *ws, unsigned char *data_in,
- struct page *dest_page,
- unsigned long start_byte,
- size_t srclen, size_t destlen)
+int zstd_decompress(struct list_head *ws, unsigned char *data_in,
+ struct page *dest_page, unsigned long start_byte, size_t srclen,
+ size_t destlen)
{
struct workspace *workspace = list_entry(ws, struct workspace, list);
ZSTD_DStream *stream;
@@ -712,15 +706,8 @@ finish:
}
const struct btrfs_compress_op btrfs_zstd_compress = {
- .init_workspace_manager = zstd_init_workspace_manager,
- .cleanup_workspace_manager = zstd_cleanup_workspace_manager,
- .get_workspace = zstd_get_workspace,
- .put_workspace = zstd_put_workspace,
- .alloc_workspace = zstd_alloc_workspace,
- .free_workspace = zstd_free_workspace,
- .compress_pages = zstd_compress_pages,
- .decompress_bio = zstd_decompress_bio,
- .decompress = zstd_decompress,
+ /* ZSTD uses own workspace manager */
+ .workspace_manager = NULL,
.max_level = ZSTD_BTRFS_MAX_LEVEL,
.default_level = ZSTD_BTRFS_DEFAULT_LEVEL,
};
diff --git a/fs/buffer.c b/fs/buffer.c
index 86a38b979323..d8c7242426bb 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -47,6 +47,9 @@
#include <linux/pagevec.h>
#include <linux/sched/mm.h>
#include <trace/events/block.h>
+#include <linux/fscrypt.h>
+
+#include "internal.h"
static int fsync_buffers_list(spinlock_t *lock, struct list_head *list);
static int submit_bh_wbc(int op, int op_flags, struct buffer_head *bh,
@@ -246,10 +249,6 @@ out:
return ret;
}
-/*
- * I/O completion handler for block_read_full_page() - pages
- * which come unlocked at the end of I/O.
- */
static void end_buffer_async_read(struct buffer_head *bh, int uptodate)
{
unsigned long flags;
@@ -307,6 +306,47 @@ still_busy:
return;
}
+struct decrypt_bh_ctx {
+ struct work_struct work;
+ struct buffer_head *bh;
+};
+
+static void decrypt_bh(struct work_struct *work)
+{
+ struct decrypt_bh_ctx *ctx =
+ container_of(work, struct decrypt_bh_ctx, work);
+ struct buffer_head *bh = ctx->bh;
+ int err;
+
+ err = fscrypt_decrypt_pagecache_blocks(bh->b_page, bh->b_size,
+ bh_offset(bh));
+ end_buffer_async_read(bh, err == 0);
+ kfree(ctx);
+}
+
+/*
+ * I/O completion handler for block_read_full_page() - pages
+ * which come unlocked at the end of I/O.
+ */
+static void end_buffer_async_read_io(struct buffer_head *bh, int uptodate)
+{
+ /* Decrypt if needed */
+ if (uptodate && IS_ENABLED(CONFIG_FS_ENCRYPTION) &&
+ IS_ENCRYPTED(bh->b_page->mapping->host) &&
+ S_ISREG(bh->b_page->mapping->host->i_mode)) {
+ struct decrypt_bh_ctx *ctx = kmalloc(sizeof(*ctx), GFP_ATOMIC);
+
+ if (ctx) {
+ INIT_WORK(&ctx->work, decrypt_bh);
+ ctx->bh = bh;
+ fscrypt_enqueue_decrypt_work(&ctx->work);
+ return;
+ }
+ uptodate = 0;
+ }
+ end_buffer_async_read(bh, uptodate);
+}
+
/*
* Completion handler for block_write_full_page() - pages which are unlocked
* during I/O, and which have PageWriteback cleared upon I/O completion.
@@ -379,7 +419,7 @@ EXPORT_SYMBOL(end_buffer_async_write);
*/
static void mark_buffer_async_read(struct buffer_head *bh)
{
- bh->b_end_io = end_buffer_async_read;
+ bh->b_end_io = end_buffer_async_read_io;
set_buffer_async_read(bh);
}
@@ -1385,10 +1425,10 @@ static bool has_bh_in_lru(int cpu, void *dummy)
for (i = 0; i < BH_LRU_SIZE; i++) {
if (b->bhs[i])
- return 1;
+ return true;
}
- return 0;
+ return false;
}
void invalidate_bh_lrus(void)
diff --git a/fs/ceph/cache.c b/fs/ceph/cache.c
index b2ec29eeb4c4..73f24f307a4a 100644
--- a/fs/ceph/cache.c
+++ b/fs/ceph/cache.c
@@ -8,6 +8,7 @@
#include <linux/ceph/ceph_debug.h>
+#include <linux/fs_context.h>
#include "super.h"
#include "cache.h"
@@ -49,7 +50,7 @@ void ceph_fscache_unregister(void)
fscache_unregister_netfs(&ceph_cache_netfs);
}
-int ceph_fscache_register_fs(struct ceph_fs_client* fsc)
+int ceph_fscache_register_fs(struct ceph_fs_client* fsc, struct fs_context *fc)
{
const struct ceph_fsid *fsid = &fsc->client->fsid;
const char *fscache_uniq = fsc->mount_options->fscache_uniq;
@@ -66,8 +67,8 @@ int ceph_fscache_register_fs(struct ceph_fs_client* fsc)
if (uniq_len && memcmp(ent->uniquifier, fscache_uniq, uniq_len))
continue;
- pr_err("fscache cookie already registered for fsid %pU\n", fsid);
- pr_err(" use fsc=%%s mount option to specify a uniquifier\n");
+ errorf(fc, "ceph: fscache cookie already registered for fsid %pU, use fsc=<uniquifier> option",
+ fsid);
err = -EBUSY;
goto out_unlock;
}
@@ -95,7 +96,7 @@ int ceph_fscache_register_fs(struct ceph_fs_client* fsc)
list_add_tail(&ent->list, &ceph_fscache_list);
} else {
kfree(ent);
- pr_err("unable to register fscache cookie for fsid %pU\n",
+ errorf(fc, "ceph: unable to register fscache cookie for fsid %pU",
fsid);
/* all other fs ignore this error */
}
diff --git a/fs/ceph/cache.h b/fs/ceph/cache.h
index e486fac3434d..89dbdd1eb14a 100644
--- a/fs/ceph/cache.h
+++ b/fs/ceph/cache.h
@@ -16,7 +16,7 @@ extern struct fscache_netfs ceph_cache_netfs;
int ceph_fscache_register(void);
void ceph_fscache_unregister(void);
-int ceph_fscache_register_fs(struct ceph_fs_client* fsc);
+int ceph_fscache_register_fs(struct ceph_fs_client* fsc, struct fs_context *fc);
void ceph_fscache_unregister_fs(struct ceph_fs_client* fsc);
void ceph_fscache_register_inode_cookie(struct inode *inode);
@@ -88,7 +88,8 @@ static inline void ceph_fscache_unregister(void)
{
}
-static inline int ceph_fscache_register_fs(struct ceph_fs_client* fsc)
+static inline int ceph_fscache_register_fs(struct ceph_fs_client* fsc,
+ struct fs_context *fc)
{
return 0;
}
diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c
index d3b9c9d5c1bd..f5a38910a82b 100644
--- a/fs/ceph/caps.c
+++ b/fs/ceph/caps.c
@@ -1058,6 +1058,11 @@ void __ceph_remove_cap(struct ceph_cap *cap, bool queue_release)
dout("__ceph_remove_cap %p from %p\n", cap, &ci->vfs_inode);
+ /* remove from inode's cap rbtree, and clear auth cap */
+ rb_erase(&cap->ci_node, &ci->i_caps);
+ if (ci->i_auth_cap == cap)
+ ci->i_auth_cap = NULL;
+
/* remove from session list */
spin_lock(&session->s_cap_lock);
if (session->s_cap_iterator == cap) {
@@ -1091,11 +1096,6 @@ void __ceph_remove_cap(struct ceph_cap *cap, bool queue_release)
spin_unlock(&session->s_cap_lock);
- /* remove from inode list */
- rb_erase(&cap->ci_node, &ci->i_caps);
- if (ci->i_auth_cap == cap)
- ci->i_auth_cap = NULL;
-
if (removed)
ceph_put_cap(mdsc, cap);
diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c
index 4ca0b8ff9a72..2e4764fd1872 100644
--- a/fs/ceph/dir.c
+++ b/fs/ceph/dir.c
@@ -1553,36 +1553,37 @@ static int ceph_d_revalidate(struct dentry *dentry, unsigned int flags)
{
int valid = 0;
struct dentry *parent;
- struct inode *dir;
+ struct inode *dir, *inode;
if (flags & LOOKUP_RCU) {
parent = READ_ONCE(dentry->d_parent);
dir = d_inode_rcu(parent);
if (!dir)
return -ECHILD;
+ inode = d_inode_rcu(dentry);
} else {
parent = dget_parent(dentry);
dir = d_inode(parent);
+ inode = d_inode(dentry);
}
dout("d_revalidate %p '%pd' inode %p offset %lld\n", dentry,
- dentry, d_inode(dentry), ceph_dentry(dentry)->offset);
+ dentry, inode, ceph_dentry(dentry)->offset);
/* always trust cached snapped dentries, snapdir dentry */
if (ceph_snap(dir) != CEPH_NOSNAP) {
dout("d_revalidate %p '%pd' inode %p is SNAPPED\n", dentry,
- dentry, d_inode(dentry));
+ dentry, inode);
valid = 1;
- } else if (d_really_is_positive(dentry) &&
- ceph_snap(d_inode(dentry)) == CEPH_SNAPDIR) {
+ } else if (inode && ceph_snap(inode) == CEPH_SNAPDIR) {
valid = 1;
} else {
valid = dentry_lease_is_valid(dentry, flags);
if (valid == -ECHILD)
return valid;
if (valid || dir_lease_is_valid(dir, dentry)) {
- if (d_really_is_positive(dentry))
- valid = ceph_is_any_caps(d_inode(dentry));
+ if (inode)
+ valid = ceph_is_any_caps(inode);
else
valid = 1;
}
@@ -1808,6 +1809,7 @@ const struct file_operations ceph_dir_fops = {
.open = ceph_open,
.release = ceph_release,
.unlocked_ioctl = ceph_ioctl,
+ .compat_ioctl = compat_ptr_ioctl,
.fsync = ceph_fsync,
.lock = ceph_lock,
.flock = ceph_flock,
diff --git a/fs/ceph/file.c b/fs/ceph/file.c
index d277f71abe0b..11929d2bb594 100644
--- a/fs/ceph/file.c
+++ b/fs/ceph/file.c
@@ -462,6 +462,9 @@ int ceph_atomic_open(struct inode *dir, struct dentry *dentry,
err = ceph_security_init_secctx(dentry, mode, &as_ctx);
if (err < 0)
goto out_ctx;
+ } else if (!d_in_lookup(dentry)) {
+ /* If it's not being looked up, it's negative */
+ return -ENOENT;
}
/* do the open */
@@ -750,6 +753,9 @@ static void ceph_aio_complete(struct inode *inode,
if (!atomic_dec_and_test(&aio_req->pending_reqs))
return;
+ if (aio_req->iocb->ki_flags & IOCB_DIRECT)
+ inode_dio_end(inode);
+
ret = aio_req->error;
if (!ret)
ret = aio_req->total_len;
@@ -1088,6 +1094,7 @@ ceph_direct_read_write(struct kiocb *iocb, struct iov_iter *iter,
CEPH_CAP_FILE_RD);
list_splice(&aio_req->osd_reqs, &osd_reqs);
+ inode_dio_begin(inode);
while (!list_empty(&osd_reqs)) {
req = list_first_entry(&osd_reqs,
struct ceph_osd_request,
@@ -1261,14 +1268,24 @@ again:
dout("aio_read %p %llx.%llx %llu~%u trying to get caps on %p\n",
inode, ceph_vinop(inode), iocb->ki_pos, (unsigned)len, inode);
+ if (iocb->ki_flags & IOCB_DIRECT)
+ ceph_start_io_direct(inode);
+ else
+ ceph_start_io_read(inode);
+
if (fi->fmode & CEPH_FILE_MODE_LAZY)
want = CEPH_CAP_FILE_CACHE | CEPH_CAP_FILE_LAZYIO;
else
want = CEPH_CAP_FILE_CACHE;
ret = ceph_get_caps(filp, CEPH_CAP_FILE_RD, want, -1,
&got, &pinned_page);
- if (ret < 0)
+ if (ret < 0) {
+ if (iocb->ki_flags & IOCB_DIRECT)
+ ceph_end_io_direct(inode);
+ else
+ ceph_end_io_read(inode);
return ret;
+ }
if ((got & (CEPH_CAP_FILE_CACHE|CEPH_CAP_FILE_LAZYIO)) == 0 ||
(iocb->ki_flags & IOCB_DIRECT) ||
@@ -1280,16 +1297,12 @@ again:
if (ci->i_inline_version == CEPH_INLINE_NONE) {
if (!retry_op && (iocb->ki_flags & IOCB_DIRECT)) {
- ceph_start_io_direct(inode);
ret = ceph_direct_read_write(iocb, to,
NULL, NULL);
- ceph_end_io_direct(inode);
if (ret >= 0 && ret < len)
retry_op = CHECK_EOF;
} else {
- ceph_start_io_read(inode);
ret = ceph_sync_read(iocb, to, &retry_op);
- ceph_end_io_read(inode);
}
} else {
retry_op = READ_INLINE;
@@ -1300,11 +1313,10 @@ again:
inode, ceph_vinop(inode), iocb->ki_pos, (unsigned)len,
ceph_cap_string(got));
ceph_add_rw_context(fi, &rw_ctx);
- ceph_start_io_read(inode);
ret = generic_file_read_iter(iocb, to);
- ceph_end_io_read(inode);
ceph_del_rw_context(fi, &rw_ctx);
}
+
dout("aio_read %p %llx.%llx dropping cap refs on %s = %d\n",
inode, ceph_vinop(inode), ceph_cap_string(got), (int)ret);
if (pinned_page) {
@@ -1312,6 +1324,12 @@ again:
pinned_page = NULL;
}
ceph_put_cap_refs(ci, got);
+
+ if (iocb->ki_flags & IOCB_DIRECT)
+ ceph_end_io_direct(inode);
+ else
+ ceph_end_io_read(inode);
+
if (retry_op > HAVE_RETRIED && ret >= 0) {
int statret;
struct page *page = NULL;
@@ -1956,10 +1974,18 @@ static ssize_t __ceph_copy_file_range(struct file *src_file, loff_t src_off,
if (ceph_test_mount_opt(src_fsc, NOCOPYFROM))
return -EOPNOTSUPP;
+ /*
+ * Striped file layouts require that we copy partial objects, but the
+ * OSD copy-from operation only supports full-object copies. Limit
+ * this to non-striped file layouts for now.
+ */
if ((src_ci->i_layout.stripe_unit != dst_ci->i_layout.stripe_unit) ||
- (src_ci->i_layout.stripe_count != dst_ci->i_layout.stripe_count) ||
- (src_ci->i_layout.object_size != dst_ci->i_layout.object_size))
+ (src_ci->i_layout.stripe_count != 1) ||
+ (dst_ci->i_layout.stripe_count != 1) ||
+ (src_ci->i_layout.object_size != dst_ci->i_layout.object_size)) {
+ dout("Invalid src/dst files layout\n");
return -EOPNOTSUPP;
+ }
if (len < src_ci->i_layout.object_size)
return -EOPNOTSUPP; /* no remote copy will be done */
@@ -2162,7 +2188,7 @@ const struct file_operations ceph_file_fops = {
.splice_read = generic_file_splice_read,
.splice_write = iter_file_splice_write,
.unlocked_ioctl = ceph_ioctl,
- .compat_ioctl = ceph_ioctl,
+ .compat_ioctl = compat_ptr_ioctl,
.fallocate = ceph_fallocate,
.copy_file_range = ceph_copy_file_range,
};
diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c
index 9f135624ae47..c07407586ce8 100644
--- a/fs/ceph/inode.c
+++ b/fs/ceph/inode.c
@@ -1434,6 +1434,7 @@ retry_lookup:
dout(" final dn %p\n", dn);
} else if ((req->r_op == CEPH_MDS_OP_LOOKUPSNAP ||
req->r_op == CEPH_MDS_OP_MKSNAP) &&
+ test_bit(CEPH_MDS_R_PARENT_LOCKED, &req->r_req_flags) &&
!test_bit(CEPH_MDS_R_ABORTED, &req->r_req_flags)) {
struct inode *dir = req->r_parent;
diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index a8a8f84f3bbf..068b029cf073 100644
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -384,8 +384,8 @@ static int parse_reply_info_readdir(void **p, void *end,
}
done:
- if (*p != end)
- goto bad;
+ /* Skip over any unrecognized fields */
+ *p = end;
return 0;
bad:
@@ -406,12 +406,10 @@ static int parse_reply_info_filelock(void **p, void *end,
goto bad;
info->filelock_reply = *p;
- *p += sizeof(*info->filelock_reply);
- if (unlikely(*p != end))
- goto bad;
+ /* Skip over any unrecognized fields */
+ *p = end;
return 0;
-
bad:
return -EIO;
}
@@ -425,18 +423,21 @@ static int parse_reply_info_create(void **p, void *end,
{
if (features == (u64)-1 ||
(features & CEPH_FEATURE_REPLY_CREATE_INODE)) {
+ /* Malformed reply? */
if (*p == end) {
info->has_create_ino = false;
} else {
info->has_create_ino = true;
- info->ino = ceph_decode_64(p);
+ ceph_decode_64_safe(p, end, info->ino, bad);
}
+ } else {
+ if (*p != end)
+ goto bad;
}
- if (unlikely(*p != end))
- goto bad;
+ /* Skip over any unrecognized fields */
+ *p = end;
return 0;
-
bad:
return -EIO;
}
@@ -2181,13 +2182,17 @@ retry:
}
base = ceph_ino(d_inode(temp));
rcu_read_unlock();
- if (pos < 0 || read_seqretry(&rename_lock, seq)) {
- pr_err("build_path did not end path lookup where "
- "expected, pos is %d\n", pos);
- /* presumably this is only possible if racing with a
- rename of one of the parent directories (we can not
- lock the dentries above us to prevent this, but
- retrying should be harmless) */
+
+ if (read_seqretry(&rename_lock, seq))
+ goto retry;
+
+ if (pos < 0) {
+ /*
+ * A rename didn't occur, but somehow we didn't end up where
+ * we thought we would. Throw a warning and try again.
+ */
+ pr_warn("build_path did not end path lookup where "
+ "expected, pos is %d\n", pos);
goto retry;
}
@@ -2344,6 +2349,7 @@ static struct ceph_msg *create_request_message(struct ceph_mds_client *mdsc,
head->op = cpu_to_le32(req->r_op);
head->caller_uid = cpu_to_le32(from_kuid(&init_user_ns, req->r_uid));
head->caller_gid = cpu_to_le32(from_kgid(&init_user_ns, req->r_gid));
+ head->ino = 0;
head->args = req->r_args;
ceph_encode_filepath(&p, end, ino1, path1);
diff --git a/fs/ceph/mdsmap.c b/fs/ceph/mdsmap.c
index ce2d00da5096..aeec1d6e3769 100644
--- a/fs/ceph/mdsmap.c
+++ b/fs/ceph/mdsmap.c
@@ -20,7 +20,7 @@
int ceph_mdsmap_get_random_mds(struct ceph_mdsmap *m)
{
int n = 0;
- int i;
+ int i, j;
/* special case for one mds */
if (1 == m->m_num_mds && m->m_info[0].state > 0)
@@ -35,9 +35,12 @@ int ceph_mdsmap_get_random_mds(struct ceph_mdsmap *m)
/* pick */
n = prandom_u32() % n;
- for (i = 0; n > 0; i++, n--)
- while (m->m_info[i].state <= 0)
- i++;
+ for (j = 0, i = 0; i < m->m_num_mds; i++) {
+ if (m->m_info[i].state > 0)
+ j++;
+ if (j > n)
+ break;
+ }
return i;
}
diff --git a/fs/ceph/super.c b/fs/ceph/super.c
index edfd643a8205..9c9a7c68eea3 100644
--- a/fs/ceph/super.c
+++ b/fs/ceph/super.c
@@ -9,7 +9,8 @@
#include <linux/in6.h>
#include <linux/module.h>
#include <linux/mount.h>
-#include <linux/parser.h>
+#include <linux/fs_context.h>
+#include <linux/fs_parser.h>
#include <linux/sched.h>
#include <linux/seq_file.h>
#include <linux/slab.h>
@@ -138,271 +139,308 @@ enum {
Opt_readdir_max_entries,
Opt_readdir_max_bytes,
Opt_congestion_kb,
- Opt_last_int,
/* int args above */
Opt_snapdirname,
Opt_mds_namespace,
- Opt_fscache_uniq,
Opt_recover_session,
- Opt_last_string,
+ Opt_source,
/* string args above */
Opt_dirstat,
- Opt_nodirstat,
Opt_rbytes,
- Opt_norbytes,
Opt_asyncreaddir,
- Opt_noasyncreaddir,
Opt_dcache,
- Opt_nodcache,
Opt_ino32,
- Opt_noino32,
Opt_fscache,
- Opt_nofscache,
Opt_poolperm,
- Opt_nopoolperm,
Opt_require_active_mds,
- Opt_norequire_active_mds,
-#ifdef CONFIG_CEPH_FS_POSIX_ACL
Opt_acl,
-#endif
- Opt_noacl,
Opt_quotadf,
- Opt_noquotadf,
Opt_copyfrom,
- Opt_nocopyfrom,
};
-static match_table_t fsopt_tokens = {
- {Opt_wsize, "wsize=%d"},
- {Opt_rsize, "rsize=%d"},
- {Opt_rasize, "rasize=%d"},
- {Opt_caps_wanted_delay_min, "caps_wanted_delay_min=%d"},
- {Opt_caps_wanted_delay_max, "caps_wanted_delay_max=%d"},
- {Opt_caps_max, "caps_max=%d"},
- {Opt_readdir_max_entries, "readdir_max_entries=%d"},
- {Opt_readdir_max_bytes, "readdir_max_bytes=%d"},
- {Opt_congestion_kb, "write_congestion_kb=%d"},
- /* int args above */
- {Opt_snapdirname, "snapdirname=%s"},
- {Opt_mds_namespace, "mds_namespace=%s"},
- {Opt_recover_session, "recover_session=%s"},
- {Opt_fscache_uniq, "fsc=%s"},
- /* string args above */
- {Opt_dirstat, "dirstat"},
- {Opt_nodirstat, "nodirstat"},
- {Opt_rbytes, "rbytes"},
- {Opt_norbytes, "norbytes"},
- {Opt_asyncreaddir, "asyncreaddir"},
- {Opt_noasyncreaddir, "noasyncreaddir"},
- {Opt_dcache, "dcache"},
- {Opt_nodcache, "nodcache"},
- {Opt_ino32, "ino32"},
- {Opt_noino32, "noino32"},
- {Opt_fscache, "fsc"},
- {Opt_nofscache, "nofsc"},
- {Opt_poolperm, "poolperm"},
- {Opt_nopoolperm, "nopoolperm"},
- {Opt_require_active_mds, "require_active_mds"},
- {Opt_norequire_active_mds, "norequire_active_mds"},
-#ifdef CONFIG_CEPH_FS_POSIX_ACL
- {Opt_acl, "acl"},
-#endif
- {Opt_noacl, "noacl"},
- {Opt_quotadf, "quotadf"},
- {Opt_noquotadf, "noquotadf"},
- {Opt_copyfrom, "copyfrom"},
- {Opt_nocopyfrom, "nocopyfrom"},
- {-1, NULL}
+enum ceph_recover_session_mode {
+ ceph_recover_session_no,
+ ceph_recover_session_clean
+};
+
+static const struct fs_parameter_enum ceph_mount_param_enums[] = {
+ { Opt_recover_session, "no", ceph_recover_session_no },
+ { Opt_recover_session, "clean", ceph_recover_session_clean },
+ {}
+};
+
+static const struct fs_parameter_spec ceph_mount_param_specs[] = {
+ fsparam_flag_no ("acl", Opt_acl),
+ fsparam_flag_no ("asyncreaddir", Opt_asyncreaddir),
+ fsparam_u32 ("caps_max", Opt_caps_max),
+ fsparam_u32 ("caps_wanted_delay_max", Opt_caps_wanted_delay_max),
+ fsparam_u32 ("caps_wanted_delay_min", Opt_caps_wanted_delay_min),
+ fsparam_s32 ("write_congestion_kb", Opt_congestion_kb),
+ fsparam_flag_no ("copyfrom", Opt_copyfrom),
+ fsparam_flag_no ("dcache", Opt_dcache),
+ fsparam_flag_no ("dirstat", Opt_dirstat),
+ __fsparam (fs_param_is_string, "fsc", Opt_fscache,
+ fs_param_neg_with_no | fs_param_v_optional),
+ fsparam_flag_no ("ino32", Opt_ino32),
+ fsparam_string ("mds_namespace", Opt_mds_namespace),
+ fsparam_flag_no ("poolperm", Opt_poolperm),
+ fsparam_flag_no ("quotadf", Opt_quotadf),
+ fsparam_u32 ("rasize", Opt_rasize),
+ fsparam_flag_no ("rbytes", Opt_rbytes),
+ fsparam_s32 ("readdir_max_bytes", Opt_readdir_max_bytes),
+ fsparam_s32 ("readdir_max_entries", Opt_readdir_max_entries),
+ fsparam_enum ("recover_session", Opt_recover_session),
+ fsparam_flag_no ("require_active_mds", Opt_require_active_mds),
+ fsparam_u32 ("rsize", Opt_rsize),
+ fsparam_string ("snapdirname", Opt_snapdirname),
+ fsparam_string ("source", Opt_source),
+ fsparam_u32 ("wsize", Opt_wsize),
+ {}
+};
+
+static const struct fs_parameter_description ceph_mount_parameters = {
+ .name = "ceph",
+ .specs = ceph_mount_param_specs,
+ .enums = ceph_mount_param_enums,
};
-static int parse_fsopt_token(char *c, void *private)
+struct ceph_parse_opts_ctx {
+ struct ceph_options *copts;
+ struct ceph_mount_options *opts;
+};
+
+/*
+ * Parse the source parameter. Distinguish the server list from the path.
+ * Internally we do not include the leading '/' in the path.
+ *
+ * The source will look like:
+ * <server_spec>[,<server_spec>...]:[<path>]
+ * where
+ * <server_spec> is <ip>[:<port>]
+ * <path> is optional, but if present must begin with '/'
+ */
+static int ceph_parse_source(struct fs_parameter *param, struct fs_context *fc)
{
- struct ceph_mount_options *fsopt = private;
- substring_t argstr[MAX_OPT_ARGS];
- int token, intval, ret;
+ struct ceph_parse_opts_ctx *pctx = fc->fs_private;
+ struct ceph_mount_options *fsopt = pctx->opts;
+ char *dev_name = param->string, *dev_name_end;
+ int ret;
- token = match_token((char *)c, fsopt_tokens, argstr);
- if (token < 0)
- return -EINVAL;
+ dout("%s '%s'\n", __func__, dev_name);
+ if (!dev_name || !*dev_name)
+ return invalf(fc, "ceph: Empty source");
- if (token < Opt_last_int) {
- ret = match_int(&argstr[0], &intval);
- if (ret < 0) {
- pr_err("bad option arg (not int) at '%s'\n", c);
- return ret;
+ dev_name_end = strchr(dev_name, '/');
+ if (dev_name_end) {
+ if (strlen(dev_name_end) > 1) {
+ kfree(fsopt->server_path);
+ fsopt->server_path = kstrdup(dev_name_end, GFP_KERNEL);
+ if (!fsopt->server_path)
+ return -ENOMEM;
}
- dout("got int token %d val %d\n", token, intval);
- } else if (token > Opt_last_int && token < Opt_last_string) {
- dout("got string token %d val %s\n", token,
- argstr[0].from);
} else {
- dout("got token %d\n", token);
+ dev_name_end = dev_name + strlen(dev_name);
}
+ dev_name_end--; /* back up to ':' separator */
+ if (dev_name_end < dev_name || *dev_name_end != ':')
+ return invalf(fc, "ceph: No path or : separator in source");
+
+ dout("device name '%.*s'\n", (int)(dev_name_end - dev_name), dev_name);
+ if (fsopt->server_path)
+ dout("server path '%s'\n", fsopt->server_path);
+
+ ret = ceph_parse_mon_ips(param->string, dev_name_end - dev_name,
+ pctx->copts, fc);
+ if (ret)
+ return ret;
+
+ fc->source = param->string;
+ param->string = NULL;
+ return 0;
+}
+
+static int ceph_parse_mount_param(struct fs_context *fc,
+ struct fs_parameter *param)
+{
+ struct ceph_parse_opts_ctx *pctx = fc->fs_private;
+ struct ceph_mount_options *fsopt = pctx->opts;
+ struct fs_parse_result result;
+ unsigned int mode;
+ int token, ret;
+
+ ret = ceph_parse_param(param, pctx->copts, fc);
+ if (ret != -ENOPARAM)
+ return ret;
+
+ token = fs_parse(fc, &ceph_mount_parameters, param, &result);
+ dout("%s fs_parse '%s' token %d\n", __func__, param->key, token);
+ if (token < 0)
+ return token;
+
switch (token) {
case Opt_snapdirname:
kfree(fsopt->snapdir_name);
- fsopt->snapdir_name = kstrndup(argstr[0].from,
- argstr[0].to-argstr[0].from,
- GFP_KERNEL);
- if (!fsopt->snapdir_name)
- return -ENOMEM;
+ fsopt->snapdir_name = param->string;
+ param->string = NULL;
break;
case Opt_mds_namespace:
kfree(fsopt->mds_namespace);
- fsopt->mds_namespace = kstrndup(argstr[0].from,
- argstr[0].to-argstr[0].from,
- GFP_KERNEL);
- if (!fsopt->mds_namespace)
- return -ENOMEM;
+ fsopt->mds_namespace = param->string;
+ param->string = NULL;
break;
case Opt_recover_session:
- if (!strncmp(argstr[0].from, "no",
- argstr[0].to - argstr[0].from)) {
+ mode = result.uint_32;
+ if (mode == ceph_recover_session_no)
fsopt->flags &= ~CEPH_MOUNT_OPT_CLEANRECOVER;
- } else if (!strncmp(argstr[0].from, "clean",
- argstr[0].to - argstr[0].from)) {
+ else if (mode == ceph_recover_session_clean)
fsopt->flags |= CEPH_MOUNT_OPT_CLEANRECOVER;
- } else {
- return -EINVAL;
- }
- break;
- case Opt_fscache_uniq:
- kfree(fsopt->fscache_uniq);
- fsopt->fscache_uniq = kstrndup(argstr[0].from,
- argstr[0].to-argstr[0].from,
- GFP_KERNEL);
- if (!fsopt->fscache_uniq)
- return -ENOMEM;
- fsopt->flags |= CEPH_MOUNT_OPT_FSCACHE;
+ else
+ BUG();
break;
- /* misc */
+ case Opt_source:
+ if (fc->source)
+ return invalf(fc, "ceph: Multiple sources specified");
+ return ceph_parse_source(param, fc);
case Opt_wsize:
- if (intval < (int)PAGE_SIZE || intval > CEPH_MAX_WRITE_SIZE)
- return -EINVAL;
- fsopt->wsize = ALIGN(intval, PAGE_SIZE);
+ if (result.uint_32 < PAGE_SIZE ||
+ result.uint_32 > CEPH_MAX_WRITE_SIZE)
+ goto out_of_range;
+ fsopt->wsize = ALIGN(result.uint_32, PAGE_SIZE);
break;
case Opt_rsize:
- if (intval < (int)PAGE_SIZE || intval > CEPH_MAX_READ_SIZE)
- return -EINVAL;
- fsopt->rsize = ALIGN(intval, PAGE_SIZE);
+ if (result.uint_32 < PAGE_SIZE ||
+ result.uint_32 > CEPH_MAX_READ_SIZE)
+ goto out_of_range;
+ fsopt->rsize = ALIGN(result.uint_32, PAGE_SIZE);
break;
case Opt_rasize:
- if (intval < 0)
- return -EINVAL;
- fsopt->rasize = ALIGN(intval, PAGE_SIZE);
+ fsopt->rasize = ALIGN(result.uint_32, PAGE_SIZE);
break;
case Opt_caps_wanted_delay_min:
- if (intval < 1)
- return -EINVAL;
- fsopt->caps_wanted_delay_min = intval;
+ if (result.uint_32 < 1)
+ goto out_of_range;
+ fsopt->caps_wanted_delay_min = result.uint_32;
break;
case Opt_caps_wanted_delay_max:
- if (intval < 1)
- return -EINVAL;
- fsopt->caps_wanted_delay_max = intval;
+ if (result.uint_32 < 1)
+ goto out_of_range;
+ fsopt->caps_wanted_delay_max = result.uint_32;
break;
case Opt_caps_max:
- if (intval < 0)
- return -EINVAL;
- fsopt->caps_max = intval;
+ fsopt->caps_max = result.uint_32;
break;
case Opt_readdir_max_entries:
- if (intval < 1)
- return -EINVAL;
- fsopt->max_readdir = intval;
+ if (result.uint_32 < 1)
+ goto out_of_range;
+ fsopt->max_readdir = result.uint_32;
break;
case Opt_readdir_max_bytes:
- if (intval < (int)PAGE_SIZE && intval != 0)
- return -EINVAL;
- fsopt->max_readdir_bytes = intval;
+ if (result.uint_32 < PAGE_SIZE && result.uint_32 != 0)
+ goto out_of_range;
+ fsopt->max_readdir_bytes = result.uint_32;
break;
case Opt_congestion_kb:
- if (intval < 1024) /* at least 1M */
- return -EINVAL;
- fsopt->congestion_kb = intval;
+ if (result.uint_32 < 1024) /* at least 1M */
+ goto out_of_range;
+ fsopt->congestion_kb = result.uint_32;
break;
case Opt_dirstat:
- fsopt->flags |= CEPH_MOUNT_OPT_DIRSTAT;
- break;
- case Opt_nodirstat:
- fsopt->flags &= ~CEPH_MOUNT_OPT_DIRSTAT;
+ if (!result.negated)
+ fsopt->flags |= CEPH_MOUNT_OPT_DIRSTAT;
+ else
+ fsopt->flags &= ~CEPH_MOUNT_OPT_DIRSTAT;
break;
case Opt_rbytes:
- fsopt->flags |= CEPH_MOUNT_OPT_RBYTES;
- break;
- case Opt_norbytes:
- fsopt->flags &= ~CEPH_MOUNT_OPT_RBYTES;
+ if (!result.negated)
+ fsopt->flags |= CEPH_MOUNT_OPT_RBYTES;
+ else
+ fsopt->flags &= ~CEPH_MOUNT_OPT_RBYTES;
break;
case Opt_asyncreaddir:
- fsopt->flags &= ~CEPH_MOUNT_OPT_NOASYNCREADDIR;
- break;
- case Opt_noasyncreaddir:
- fsopt->flags |= CEPH_MOUNT_OPT_NOASYNCREADDIR;
+ if (!result.negated)
+ fsopt->flags &= ~CEPH_MOUNT_OPT_NOASYNCREADDIR;
+ else
+ fsopt->flags |= CEPH_MOUNT_OPT_NOASYNCREADDIR;
break;
case Opt_dcache:
- fsopt->flags |= CEPH_MOUNT_OPT_DCACHE;
- break;
- case Opt_nodcache:
- fsopt->flags &= ~CEPH_MOUNT_OPT_DCACHE;
+ if (!result.negated)
+ fsopt->flags |= CEPH_MOUNT_OPT_DCACHE;
+ else
+ fsopt->flags &= ~CEPH_MOUNT_OPT_DCACHE;
break;
case Opt_ino32:
- fsopt->flags |= CEPH_MOUNT_OPT_INO32;
- break;
- case Opt_noino32:
- fsopt->flags &= ~CEPH_MOUNT_OPT_INO32;
+ if (!result.negated)
+ fsopt->flags |= CEPH_MOUNT_OPT_INO32;
+ else
+ fsopt->flags &= ~CEPH_MOUNT_OPT_INO32;
break;
+
case Opt_fscache:
- fsopt->flags |= CEPH_MOUNT_OPT_FSCACHE;
- kfree(fsopt->fscache_uniq);
- fsopt->fscache_uniq = NULL;
- break;
- case Opt_nofscache:
- fsopt->flags &= ~CEPH_MOUNT_OPT_FSCACHE;
+#ifdef CONFIG_CEPH_FSCACHE
kfree(fsopt->fscache_uniq);
fsopt->fscache_uniq = NULL;
+ if (result.negated) {
+ fsopt->flags &= ~CEPH_MOUNT_OPT_FSCACHE;
+ } else {
+ fsopt->flags |= CEPH_MOUNT_OPT_FSCACHE;
+ fsopt->fscache_uniq = param->string;
+ param->string = NULL;
+ }
break;
+#else
+ return invalf(fc, "ceph: fscache support is disabled");
+#endif
case Opt_poolperm:
- fsopt->flags &= ~CEPH_MOUNT_OPT_NOPOOLPERM;
- break;
- case Opt_nopoolperm:
- fsopt->flags |= CEPH_MOUNT_OPT_NOPOOLPERM;
+ if (!result.negated)
+ fsopt->flags &= ~CEPH_MOUNT_OPT_NOPOOLPERM;
+ else
+ fsopt->flags |= CEPH_MOUNT_OPT_NOPOOLPERM;
break;
case Opt_require_active_mds:
- fsopt->flags &= ~CEPH_MOUNT_OPT_MOUNTWAIT;
- break;
- case Opt_norequire_active_mds:
- fsopt->flags |= CEPH_MOUNT_OPT_MOUNTWAIT;
+ if (!result.negated)
+ fsopt->flags &= ~CEPH_MOUNT_OPT_MOUNTWAIT;
+ else
+ fsopt->flags |= CEPH_MOUNT_OPT_MOUNTWAIT;
break;
case Opt_quotadf:
- fsopt->flags &= ~CEPH_MOUNT_OPT_NOQUOTADF;
- break;
- case Opt_noquotadf:
- fsopt->flags |= CEPH_MOUNT_OPT_NOQUOTADF;
+ if (!result.negated)
+ fsopt->flags &= ~CEPH_MOUNT_OPT_NOQUOTADF;
+ else
+ fsopt->flags |= CEPH_MOUNT_OPT_NOQUOTADF;
break;
case Opt_copyfrom:
- fsopt->flags &= ~CEPH_MOUNT_OPT_NOCOPYFROM;
+ if (!result.negated)
+ fsopt->flags &= ~CEPH_MOUNT_OPT_NOCOPYFROM;
+ else
+ fsopt->flags |= CEPH_MOUNT_OPT_NOCOPYFROM;
break;
- case Opt_nocopyfrom:
- fsopt->flags |= CEPH_MOUNT_OPT_NOCOPYFROM;
- break;
-#ifdef CONFIG_CEPH_FS_POSIX_ACL
case Opt_acl:
- fsopt->sb_flags |= SB_POSIXACL;
- break;
+ if (!result.negated) {
+#ifdef CONFIG_CEPH_FS_POSIX_ACL
+ fc->sb_flags |= SB_POSIXACL;
+#else
+ return invalf(fc, "ceph: POSIX ACL support is disabled");
#endif
- case Opt_noacl:
- fsopt->sb_flags &= ~SB_POSIXACL;
+ } else {
+ fc->sb_flags &= ~SB_POSIXACL;
+ }
break;
default:
- BUG_ON(token);
+ BUG();
}
return 0;
+
+out_of_range:
+ return invalf(fc, "ceph: %s out of range", param->key);
}
static void destroy_mount_options(struct ceph_mount_options *args)
{
dout("destroy_mount_options %p\n", args);
+ if (!args)
+ return;
+
kfree(args->snapdir_name);
kfree(args->mds_namespace);
kfree(args->server_path);
@@ -450,91 +488,6 @@ static int compare_mount_options(struct ceph_mount_options *new_fsopt,
return ceph_compare_options(new_opt, fsc->client);
}
-static int parse_mount_options(struct ceph_mount_options **pfsopt,
- struct ceph_options **popt,
- int flags, char *options,
- const char *dev_name)
-{
- struct ceph_mount_options *fsopt;
- const char *dev_name_end;
- int err;
-
- if (!dev_name || !*dev_name)
- return -EINVAL;
-
- fsopt = kzalloc(sizeof(*fsopt), GFP_KERNEL);
- if (!fsopt)
- return -ENOMEM;
-
- dout("parse_mount_options %p, dev_name '%s'\n", fsopt, dev_name);
-
- fsopt->sb_flags = flags;
- fsopt->flags = CEPH_MOUNT_OPT_DEFAULT;
-
- fsopt->wsize = CEPH_MAX_WRITE_SIZE;
- fsopt->rsize = CEPH_MAX_READ_SIZE;
- fsopt->rasize = CEPH_RASIZE_DEFAULT;
- fsopt->snapdir_name = kstrdup(CEPH_SNAPDIRNAME_DEFAULT, GFP_KERNEL);
- if (!fsopt->snapdir_name) {
- err = -ENOMEM;
- goto out;
- }
-
- fsopt->caps_wanted_delay_min = CEPH_CAPS_WANTED_DELAY_MIN_DEFAULT;
- fsopt->caps_wanted_delay_max = CEPH_CAPS_WANTED_DELAY_MAX_DEFAULT;
- fsopt->max_readdir = CEPH_MAX_READDIR_DEFAULT;
- fsopt->max_readdir_bytes = CEPH_MAX_READDIR_BYTES_DEFAULT;
- fsopt->congestion_kb = default_congestion_kb();
-
- /*
- * Distinguish the server list from the path in "dev_name".
- * Internally we do not include the leading '/' in the path.
- *
- * "dev_name" will look like:
- * <server_spec>[,<server_spec>...]:[<path>]
- * where
- * <server_spec> is <ip>[:<port>]
- * <path> is optional, but if present must begin with '/'
- */
- dev_name_end = strchr(dev_name, '/');
- if (dev_name_end) {
- if (strlen(dev_name_end) > 1) {
- fsopt->server_path = kstrdup(dev_name_end, GFP_KERNEL);
- if (!fsopt->server_path) {
- err = -ENOMEM;
- goto out;
- }
- }
- } else {
- dev_name_end = dev_name + strlen(dev_name);
- }
- err = -EINVAL;
- dev_name_end--; /* back up to ':' separator */
- if (dev_name_end < dev_name || *dev_name_end != ':') {
- pr_err("device name is missing path (no : separator in %s)\n",
- dev_name);
- goto out;
- }
- dout("device name '%.*s'\n", (int)(dev_name_end - dev_name), dev_name);
- if (fsopt->server_path)
- dout("server path '%s'\n", fsopt->server_path);
-
- *popt = ceph_parse_options(options, dev_name, dev_name_end,
- parse_fsopt_token, (void *)fsopt);
- if (IS_ERR(*popt)) {
- err = PTR_ERR(*popt);
- goto out;
- }
-
- /* success */
- *pfsopt = fsopt;
- return 0;
-
-out:
- destroy_mount_options(fsopt);
- return err;
-}
-
/**
* ceph_show_options - Show mount options in /proc/mounts
* @m: seq_file to write to
@@ -578,7 +531,7 @@ static int ceph_show_options(struct seq_file *m, struct dentry *root)
seq_puts(m, ",noquotadf");
#ifdef CONFIG_CEPH_FS_POSIX_ACL
- if (fsopt->sb_flags & SB_POSIXACL)
+ if (root->d_sb->s_flags & SB_POSIXACL)
seq_puts(m, ",acl");
else
seq_puts(m, ",noacl");
@@ -851,12 +804,6 @@ static void ceph_umount_begin(struct super_block *sb)
fsc->filp_gen++; // invalidate open files
}
-static int ceph_remount(struct super_block *sb, int *flags, char *data)
-{
- sync_filesystem(sb);
- return 0;
-}
-
static const struct super_operations ceph_super_ops = {
.alloc_inode = ceph_alloc_inode,
.free_inode = ceph_free_inode,
@@ -865,7 +812,6 @@ static const struct super_operations ceph_super_ops = {
.evict_inode = ceph_evict_inode,
.sync_fs = ceph_sync_fs,
.put_super = ceph_put_super,
- .remount_fs = ceph_remount,
.show_options = ceph_show_options,
.statfs = ceph_statfs,
.umount_begin = ceph_umount_begin,
@@ -926,7 +872,8 @@ out:
/*
* mount: join the ceph cluster, and open root directory.
*/
-static struct dentry *ceph_real_mount(struct ceph_fs_client *fsc)
+static struct dentry *ceph_real_mount(struct ceph_fs_client *fsc,
+ struct fs_context *fc)
{
int err;
unsigned long started = jiffies; /* note the start time */
@@ -943,7 +890,7 @@ static struct dentry *ceph_real_mount(struct ceph_fs_client *fsc)
/* setup fscache */
if (fsc->mount_options->flags & CEPH_MOUNT_OPT_FSCACHE) {
- err = ceph_fscache_register_fs(fsc);
+ err = ceph_fscache_register_fs(fsc, fc);
if (err < 0)
goto out;
}
@@ -978,18 +925,16 @@ out:
return ERR_PTR(err);
}
-static int ceph_set_super(struct super_block *s, void *data)
+static int ceph_set_super(struct super_block *s, struct fs_context *fc)
{
- struct ceph_fs_client *fsc = data;
+ struct ceph_fs_client *fsc = s->s_fs_info;
int ret;
- dout("set_super %p data %p\n", s, data);
+ dout("set_super %p\n", s);
- s->s_flags = fsc->mount_options->sb_flags;
s->s_maxbytes = MAX_LFS_FILESIZE;
s->s_xattr = ceph_xattr_handlers;
- s->s_fs_info = fsc;
fsc->sb = s;
fsc->max_file_size = 1ULL << 40; /* temp value until we get mdsmap */
@@ -1001,24 +946,18 @@ static int ceph_set_super(struct super_block *s, void *data)
s->s_time_min = 0;
s->s_time_max = U32_MAX;
- ret = set_anon_super(s, NULL); /* what is that second arg for? */
+ ret = set_anon_super_fc(s, fc);
if (ret != 0)
- goto fail;
-
- return ret;
-
-fail:
- s->s_fs_info = NULL;
- fsc->sb = NULL;
+ fsc->sb = NULL;
return ret;
}
/*
* share superblock if same fs AND options
*/
-static int ceph_compare_super(struct super_block *sb, void *data)
+static int ceph_compare_super(struct super_block *sb, struct fs_context *fc)
{
- struct ceph_fs_client *new = data;
+ struct ceph_fs_client *new = fc->s_fs_info;
struct ceph_mount_options *fsopt = new->mount_options;
struct ceph_options *opt = new->client->options;
struct ceph_fs_client *other = ceph_sb_to_client(sb);
@@ -1034,7 +973,7 @@ static int ceph_compare_super(struct super_block *sb, void *data)
dout("fsid doesn't match\n");
return 0;
}
- if (fsopt->sb_flags != other->mount_options->sb_flags) {
+ if (fc->sb_flags != (sb->s_flags & ~SB_BORN)) {
dout("flags differ\n");
return 0;
}
@@ -1064,46 +1003,46 @@ static int ceph_setup_bdi(struct super_block *sb, struct ceph_fs_client *fsc)
return 0;
}
-static struct dentry *ceph_mount(struct file_system_type *fs_type,
- int flags, const char *dev_name, void *data)
+static int ceph_get_tree(struct fs_context *fc)
{
+ struct ceph_parse_opts_ctx *pctx = fc->fs_private;
struct super_block *sb;
struct ceph_fs_client *fsc;
struct dentry *res;
+ int (*compare_super)(struct super_block *, struct fs_context *) =
+ ceph_compare_super;
int err;
- int (*compare_super)(struct super_block *, void *) = ceph_compare_super;
- struct ceph_mount_options *fsopt = NULL;
- struct ceph_options *opt = NULL;
- dout("ceph_mount\n");
+ dout("ceph_get_tree\n");
+
+ if (!fc->source)
+ return invalf(fc, "ceph: No source");
#ifdef CONFIG_CEPH_FS_POSIX_ACL
- flags |= SB_POSIXACL;
+ fc->sb_flags |= SB_POSIXACL;
#endif
- err = parse_mount_options(&fsopt, &opt, flags, data, dev_name);
- if (err < 0) {
- res = ERR_PTR(err);
- goto out_final;
- }
/* create client (which we may/may not use) */
- fsc = create_fs_client(fsopt, opt);
+ fsc = create_fs_client(pctx->opts, pctx->copts);
+ pctx->opts = NULL;
+ pctx->copts = NULL;
if (IS_ERR(fsc)) {
- res = ERR_CAST(fsc);
+ err = PTR_ERR(fsc);
goto out_final;
}
err = ceph_mdsc_init(fsc);
- if (err < 0) {
- res = ERR_PTR(err);
+ if (err < 0)
goto out;
- }
if (ceph_test_opt(fsc->client, NOSHARE))
compare_super = NULL;
- sb = sget(fs_type, compare_super, ceph_set_super, flags, fsc);
+
+ fc->s_fs_info = fsc;
+ sb = sget_fc(fc, compare_super, ceph_set_super);
+ fc->s_fs_info = NULL;
if (IS_ERR(sb)) {
- res = ERR_CAST(sb);
+ err = PTR_ERR(sb);
goto out;
}
@@ -1114,18 +1053,19 @@ static struct dentry *ceph_mount(struct file_system_type *fs_type,
} else {
dout("get_sb using new client %p\n", fsc);
err = ceph_setup_bdi(sb, fsc);
- if (err < 0) {
- res = ERR_PTR(err);
+ if (err < 0)
goto out_splat;
- }
}
- res = ceph_real_mount(fsc);
- if (IS_ERR(res))
+ res = ceph_real_mount(fsc, fc);
+ if (IS_ERR(res)) {
+ err = PTR_ERR(res);
goto out_splat;
+ }
dout("root %p inode %p ino %llx.%llx\n", res,
d_inode(res), ceph_vinop(d_inode(res)));
- return res;
+ fc->root = fsc->sb->s_root;
+ return 0;
out_splat:
ceph_mdsc_close_sessions(fsc->mdsc);
@@ -1135,8 +1075,79 @@ out_splat:
out:
destroy_fs_client(fsc);
out_final:
- dout("ceph_mount fail %ld\n", PTR_ERR(res));
- return res;
+ dout("ceph_get_tree fail %d\n", err);
+ return err;
+}
+
+static void ceph_free_fc(struct fs_context *fc)
+{
+ struct ceph_parse_opts_ctx *pctx = fc->fs_private;
+
+ if (pctx) {
+ destroy_mount_options(pctx->opts);
+ ceph_destroy_options(pctx->copts);
+ kfree(pctx);
+ }
+}
+
+static int ceph_reconfigure_fc(struct fs_context *fc)
+{
+ sync_filesystem(fc->root->d_sb);
+ return 0;
+}
+
+static const struct fs_context_operations ceph_context_ops = {
+ .free = ceph_free_fc,
+ .parse_param = ceph_parse_mount_param,
+ .get_tree = ceph_get_tree,
+ .reconfigure = ceph_reconfigure_fc,
+};
+
+/*
+ * Set up the filesystem mount context.
+ */
+static int ceph_init_fs_context(struct fs_context *fc)
+{
+ struct ceph_parse_opts_ctx *pctx;
+ struct ceph_mount_options *fsopt;
+
+ pctx = kzalloc(sizeof(*pctx), GFP_KERNEL);
+ if (!pctx)
+ return -ENOMEM;
+
+ pctx->copts = ceph_alloc_options();
+ if (!pctx->copts)
+ goto nomem;
+
+ pctx->opts = kzalloc(sizeof(*pctx->opts), GFP_KERNEL);
+ if (!pctx->opts)
+ goto nomem;
+
+ fsopt = pctx->opts;
+ fsopt->flags = CEPH_MOUNT_OPT_DEFAULT;
+
+ fsopt->wsize = CEPH_MAX_WRITE_SIZE;
+ fsopt->rsize = CEPH_MAX_READ_SIZE;
+ fsopt->rasize = CEPH_RASIZE_DEFAULT;
+ fsopt->snapdir_name = kstrdup(CEPH_SNAPDIRNAME_DEFAULT, GFP_KERNEL);
+ if (!fsopt->snapdir_name)
+ goto nomem;
+
+ fsopt->caps_wanted_delay_min = CEPH_CAPS_WANTED_DELAY_MIN_DEFAULT;
+ fsopt->caps_wanted_delay_max = CEPH_CAPS_WANTED_DELAY_MAX_DEFAULT;
+ fsopt->max_readdir = CEPH_MAX_READDIR_DEFAULT;
+ fsopt->max_readdir_bytes = CEPH_MAX_READDIR_BYTES_DEFAULT;
+ fsopt->congestion_kb = default_congestion_kb();
+
+ fc->fs_private = pctx;
+ fc->ops = &ceph_context_ops;
+ return 0;
+
+nomem:
+ destroy_mount_options(pctx->opts);
+ ceph_destroy_options(pctx->copts);
+ kfree(pctx);
+ return -ENOMEM;
}
static void ceph_kill_sb(struct super_block *s)
@@ -1163,7 +1174,7 @@ static void ceph_kill_sb(struct super_block *s)
static struct file_system_type ceph_fs_type = {
.owner = THIS_MODULE,
.name = "ceph",
- .mount = ceph_mount,
+ .init_fs_context = ceph_init_fs_context,
.kill_sb = ceph_kill_sb,
.fs_flags = FS_RENAME_DOES_D_MOVE,
};
diff --git a/fs/ceph/super.h b/fs/ceph/super.h
index f98d9247f9cb..f0f9cb7447ac 100644
--- a/fs/ceph/super.h
+++ b/fs/ceph/super.h
@@ -74,7 +74,6 @@
struct ceph_mount_options {
int flags;
- int sb_flags;
int wsize; /* max write size */
int rsize; /* max read size */
@@ -407,22 +406,26 @@ struct ceph_inode_info {
struct inode vfs_inode; /* at end */
};
-static inline struct ceph_inode_info *ceph_inode(struct inode *inode)
+static inline struct ceph_inode_info *
+ceph_inode(const struct inode *inode)
{
return container_of(inode, struct ceph_inode_info, vfs_inode);
}
-static inline struct ceph_fs_client *ceph_inode_to_client(struct inode *inode)
+static inline struct ceph_fs_client *
+ceph_inode_to_client(const struct inode *inode)
{
return (struct ceph_fs_client *)inode->i_sb->s_fs_info;
}
-static inline struct ceph_fs_client *ceph_sb_to_client(struct super_block *sb)
+static inline struct ceph_fs_client *
+ceph_sb_to_client(const struct super_block *sb)
{
return (struct ceph_fs_client *)sb->s_fs_info;
}
-static inline struct ceph_vino ceph_vino(struct inode *inode)
+static inline struct ceph_vino
+ceph_vino(const struct inode *inode)
{
return ceph_inode(inode)->i_vino;
}
diff --git a/fs/cifs/cifs_debug.c b/fs/cifs/cifs_debug.c
index 0b4eee3bed66..19f6e592b941 100644
--- a/fs/cifs/cifs_debug.c
+++ b/fs/cifs/cifs_debug.c
@@ -122,6 +122,27 @@ static void cifs_debug_tcon(struct seq_file *m, struct cifs_tcon *tcon)
}
static void
+cifs_dump_channel(struct seq_file *m, int i, struct cifs_chan *chan)
+{
+ struct TCP_Server_Info *server = chan->server;
+
+ seq_printf(m, "\t\tChannel %d Number of credits: %d Dialect 0x%x "
+ "TCP status: %d Instance: %d Local Users To Server: %d "
+ "SecMode: 0x%x Req On Wire: %d In Send: %d "
+ "In MaxReq Wait: %d\n",
+ i+1,
+ server->credits,
+ server->dialect,
+ server->tcpStatus,
+ server->reconnect_instance,
+ server->srv_count,
+ server->sec_mode,
+ in_flight(server),
+ atomic_read(&server->in_send),
+ atomic_read(&server->num_waiters));
+}
+
+static void
cifs_dump_iface(struct seq_file *m, struct cifs_server_iface *iface)
{
struct sockaddr_in *ipv4 = (struct sockaddr_in *)&iface->sockaddr;
@@ -256,6 +277,11 @@ static int cifs_debug_data_proc_show(struct seq_file *m, void *v)
if (!server->rdma)
goto skip_rdma;
+ if (!server->smbd_conn) {
+ seq_printf(m, "\nSMBDirect transport not available");
+ goto skip_rdma;
+ }
+
seq_printf(m, "\nSMBDirect (in hex) protocol version: %x "
"transport status: %x",
server->smbd_conn->protocol,
@@ -360,11 +386,10 @@ skip_rdma:
server->srv_count,
server->sec_mode, in_flight(server));
-#ifdef CONFIG_CIFS_STATS2
seq_printf(m, " In Send: %d In MaxReq Wait: %d",
atomic_read(&server->in_send),
atomic_read(&server->num_waiters));
-#endif
+
/* dump session id helpful for use with network trace */
seq_printf(m, " SessionId: 0x%llx", ses->Suid);
if (ses->session_flags & SMB2_SESSION_FLAG_ENCRYPT_DATA)
@@ -372,6 +397,13 @@ skip_rdma:
if (ses->sign)
seq_puts(m, " signed");
+ if (ses->chan_count > 1) {
+ seq_printf(m, "\n\n\tExtra Channels: %zu\n",
+ ses->chan_count-1);
+ for (j = 1; j < ses->chan_count; j++)
+ cifs_dump_channel(m, j, &ses->chans[j]);
+ }
+
seq_puts(m, "\n\tShares:");
j = 0;
@@ -410,8 +442,13 @@ skip_rdma:
seq_printf(m, "\n\tServer interfaces: %zu\n",
ses->iface_count);
for (j = 0; j < ses->iface_count; j++) {
+ struct cifs_server_iface *iface;
+
+ iface = &ses->iface_list[j];
seq_printf(m, "\t%d)", j);
- cifs_dump_iface(m, &ses->iface_list[j]);
+ cifs_dump_iface(m, iface);
+ if (is_ses_using_iface(ses, iface))
+ seq_puts(m, "\t\t[CONNECTED]\n");
}
spin_unlock(&ses->iface_lock);
}
diff --git a/fs/cifs/cifs_spnego.c b/fs/cifs/cifs_spnego.c
index 7f01c6e60791..7b9b876b513b 100644
--- a/fs/cifs/cifs_spnego.c
+++ b/fs/cifs/cifs_spnego.c
@@ -98,7 +98,7 @@ struct key_type cifs_spnego_key_type = {
struct key *
cifs_get_spnego_key(struct cifs_ses *sesInfo)
{
- struct TCP_Server_Info *server = sesInfo->server;
+ struct TCP_Server_Info *server = cifs_ses_server(sesInfo);
struct sockaddr_in *sa = (struct sockaddr_in *) &server->dstaddr;
struct sockaddr_in6 *sa6 = (struct sockaddr_in6 *) &server->dstaddr;
char *description, *dp;
diff --git a/fs/cifs/cifsacl.c b/fs/cifs/cifsacl.c
index f842944a5c76..06ffe52bdcfa 100644
--- a/fs/cifs/cifsacl.c
+++ b/fs/cifs/cifsacl.c
@@ -39,8 +39,6 @@ static const struct cifs_sid sid_everyone = {
/* security id for Authenticated Users system group */
static const struct cifs_sid sid_authusers = {
1, 1, {0, 0, 0, 0, 0, 5}, {cpu_to_le32(11)} };
-/* group users */
-static const struct cifs_sid sid_user = {1, 2 , {0, 0, 0, 0, 0, 5}, {} };
/* S-1-22-1 Unmapped Unix users */
static const struct cifs_sid sid_unix_users = {1, 1, {0, 0, 0, 0, 0, 22},
diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c
index c049c7b3aa87..5492b9860baa 100644
--- a/fs/cifs/cifsfs.c
+++ b/fs/cifs/cifsfs.c
@@ -119,6 +119,7 @@ extern mempool_t *cifs_mid_poolp;
struct workqueue_struct *cifsiod_wq;
struct workqueue_struct *decrypt_wq;
+struct workqueue_struct *fileinfo_put_wq;
struct workqueue_struct *cifsoplockd_wq;
__u32 cifs_lock_secret;
@@ -169,7 +170,13 @@ cifs_read_super(struct super_block *sb)
else
sb->s_maxbytes = MAX_NON_LFS;
- /* Some very old servers like DOS and OS/2 used 2 second granularity */
+ /*
+ * Some very old servers like DOS and OS/2 used 2 second granularity
+ * (while all current servers use 100ns granularity - see MS-DTYP)
+ * but 1 second is the maximum allowed granularity for the VFS
+ * so for old servers set time granularity to 1 second while for
+ * everything else (current servers) set it to 100ns.
+ */
if ((tcon->ses->server->vals->protocol_id == SMB10_PROT_ID) &&
((tcon->ses->capabilities &
tcon->ses->server->vals->cap_nt_find) == 0) &&
@@ -607,6 +614,10 @@ cifs_show_options(struct seq_file *s, struct dentry *root)
/* convert actimeo and display it in seconds */
seq_printf(s, ",actimeo=%lu", cifs_sb->actimeo / HZ);
+ if (tcon->ses->chan_max > 1)
+ seq_printf(s, ",multichannel,max_channel=%zu",
+ tcon->ses->chan_max);
+
return 0;
}
@@ -719,11 +730,6 @@ cifs_get_root(struct smb_vol *vol, struct super_block *sb)
struct inode *dir = d_inode(dentry);
struct dentry *child;
- if (!dir) {
- dput(dentry);
- dentry = ERR_PTR(-ENOENT);
- break;
- }
if (!S_ISDIR(dir->i_mode)) {
dput(dentry);
dentry = ERR_PTR(-ENOTDIR);
@@ -740,7 +746,7 @@ cifs_get_root(struct smb_vol *vol, struct super_block *sb)
while (*s && *s != sep)
s++;
- child = lookup_one_len_unlocked(p, dentry, s - p);
+ child = lookup_positive_unlocked(p, dentry, s - p);
dput(dentry);
dentry = child;
} while (!IS_ERR(dentry));
@@ -1213,6 +1219,7 @@ const struct file_operations cifs_file_ops = {
.open = cifs_open,
.release = cifs_close,
.lock = cifs_lock,
+ .flock = cifs_flock,
.fsync = cifs_fsync,
.flush = cifs_flush,
.mmap = cifs_file_mmap,
@@ -1232,6 +1239,7 @@ const struct file_operations cifs_file_strict_ops = {
.open = cifs_open,
.release = cifs_close,
.lock = cifs_lock,
+ .flock = cifs_flock,
.fsync = cifs_strict_fsync,
.flush = cifs_flush,
.mmap = cifs_file_strict_mmap,
@@ -1251,6 +1259,7 @@ const struct file_operations cifs_file_direct_ops = {
.open = cifs_open,
.release = cifs_close,
.lock = cifs_lock,
+ .flock = cifs_flock,
.fsync = cifs_fsync,
.flush = cifs_flush,
.mmap = cifs_file_mmap,
@@ -1537,7 +1546,7 @@ init_cifs(void)
/*
* Consider in future setting limit!=0 maybe to min(num_of_cores - 1, 3)
* so that we don't launch too many worker threads but
- * Documentation/workqueue.txt recommends setting it to 0
+ * Documentation/core-api/workqueue.rst recommends setting it to 0
*/
/* WQ_UNBOUND allows decrypt tasks to run on any CPU */
@@ -1548,11 +1557,18 @@ init_cifs(void)
goto out_destroy_cifsiod_wq;
}
+ fileinfo_put_wq = alloc_workqueue("cifsfileinfoput",
+ WQ_UNBOUND|WQ_FREEZABLE|WQ_MEM_RECLAIM, 0);
+ if (!fileinfo_put_wq) {
+ rc = -ENOMEM;
+ goto out_destroy_decrypt_wq;
+ }
+
cifsoplockd_wq = alloc_workqueue("cifsoplockd",
WQ_FREEZABLE|WQ_MEM_RECLAIM, 0);
if (!cifsoplockd_wq) {
rc = -ENOMEM;
- goto out_destroy_decrypt_wq;
+ goto out_destroy_fileinfo_put_wq;
}
rc = cifs_fscache_register();
@@ -1618,6 +1634,8 @@ out_unreg_fscache:
cifs_fscache_unregister();
out_destroy_cifsoplockd_wq:
destroy_workqueue(cifsoplockd_wq);
+out_destroy_fileinfo_put_wq:
+ destroy_workqueue(fileinfo_put_wq);
out_destroy_decrypt_wq:
destroy_workqueue(decrypt_wq);
out_destroy_cifsiod_wq:
@@ -1647,6 +1665,7 @@ exit_cifs(void)
cifs_fscache_unregister();
destroy_workqueue(cifsoplockd_wq);
destroy_workqueue(decrypt_wq);
+ destroy_workqueue(fileinfo_put_wq);
destroy_workqueue(cifsiod_wq);
cifs_proc_clean();
}
@@ -1657,17 +1676,17 @@ MODULE_DESCRIPTION
("VFS to access SMB3 servers e.g. Samba, Macs, Azure and Windows (and "
"also older servers complying with the SNIA CIFS Specification)");
MODULE_VERSION(CIFS_VERSION);
-MODULE_SOFTDEP("pre: ecb");
-MODULE_SOFTDEP("pre: hmac");
-MODULE_SOFTDEP("pre: md4");
-MODULE_SOFTDEP("pre: md5");
-MODULE_SOFTDEP("pre: nls");
-MODULE_SOFTDEP("pre: aes");
-MODULE_SOFTDEP("pre: cmac");
-MODULE_SOFTDEP("pre: sha256");
-MODULE_SOFTDEP("pre: sha512");
-MODULE_SOFTDEP("pre: aead2");
-MODULE_SOFTDEP("pre: ccm");
-MODULE_SOFTDEP("pre: gcm");
+MODULE_SOFTDEP("ecb");
+MODULE_SOFTDEP("hmac");
+MODULE_SOFTDEP("md4");
+MODULE_SOFTDEP("md5");
+MODULE_SOFTDEP("nls");
+MODULE_SOFTDEP("aes");
+MODULE_SOFTDEP("cmac");
+MODULE_SOFTDEP("sha256");
+MODULE_SOFTDEP("sha512");
+MODULE_SOFTDEP("aead2");
+MODULE_SOFTDEP("ccm");
+MODULE_SOFTDEP("gcm");
module_init(init_cifs)
module_exit(exit_cifs)
diff --git a/fs/cifs/cifsfs.h b/fs/cifs/cifsfs.h
index bc4ca94137f2..b59dc7478130 100644
--- a/fs/cifs/cifsfs.h
+++ b/fs/cifs/cifsfs.h
@@ -108,6 +108,7 @@ extern ssize_t cifs_strict_readv(struct kiocb *iocb, struct iov_iter *to);
extern ssize_t cifs_user_writev(struct kiocb *iocb, struct iov_iter *from);
extern ssize_t cifs_direct_writev(struct kiocb *iocb, struct iov_iter *from);
extern ssize_t cifs_strict_writev(struct kiocb *iocb, struct iov_iter *from);
+extern int cifs_flock(struct file *pfile, int cmd, struct file_lock *plock);
extern int cifs_lock(struct file *, int, struct file_lock *);
extern int cifs_fsync(struct file *, loff_t, loff_t, int);
extern int cifs_strict_fsync(struct file *, loff_t, loff_t, int);
@@ -152,5 +153,5 @@ extern long cifs_ioctl(struct file *filep, unsigned int cmd, unsigned long arg);
extern const struct export_operations cifs_export_ops;
#endif /* CONFIG_CIFS_NFSD_EXPORT */
-#define CIFS_VERSION "2.23"
+#define CIFS_VERSION "2.24"
#endif /* _CIFSFS_H */
diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h
index 50dfd9049370..d34a4ed8c57d 100644
--- a/fs/cifs/cifsglob.h
+++ b/fs/cifs/cifsglob.h
@@ -230,7 +230,8 @@ struct smb_version_operations {
bool (*compare_fids)(struct cifsFileInfo *, struct cifsFileInfo *);
/* setup request: allocate mid, sign message */
struct mid_q_entry *(*setup_request)(struct cifs_ses *,
- struct smb_rqst *);
+ struct TCP_Server_Info *,
+ struct smb_rqst *);
/* setup async request: allocate mid, sign message */
struct mid_q_entry *(*setup_async_request)(struct TCP_Server_Info *,
struct smb_rqst *);
@@ -268,8 +269,9 @@ struct smb_version_operations {
int (*check_message)(char *, unsigned int, struct TCP_Server_Info *);
bool (*is_oplock_break)(char *, struct TCP_Server_Info *);
int (*handle_cancelled_mid)(char *, struct TCP_Server_Info *);
- void (*downgrade_oplock)(struct TCP_Server_Info *,
- struct cifsInodeInfo *, bool);
+ void (*downgrade_oplock)(struct TCP_Server_Info *server,
+ struct cifsInodeInfo *cinode, __u32 oplock,
+ unsigned int epoch, bool *purge_cache);
/* process transaction2 response */
bool (*check_trans2)(struct mid_q_entry *, struct TCP_Server_Info *,
char *, int);
@@ -591,6 +593,10 @@ struct smb_vol {
bool resilient:1; /* noresilient not required since not fored for CA */
bool domainauto:1;
bool rdma:1;
+ bool multichannel:1;
+ bool use_client_guid:1;
+ /* reuse existing guid for multichannel */
+ u8 client_guid[SMB2_CLIENT_GUID_SIZE];
unsigned int bsize;
unsigned int rsize;
unsigned int wsize;
@@ -607,6 +613,7 @@ struct smb_vol {
__u64 snapshot_time; /* needed for timewarp tokens */
__u32 handle_timeout; /* persistent and durable handle timeout in ms */
unsigned int max_credits; /* smb3 max_credits 10 < credits < 60000 */
+ unsigned int max_channels;
__u16 compression; /* compression algorithm 0xFFFF default 0=disabled */
bool rootfs:1; /* if it's a SMB root file system */
};
@@ -736,12 +743,12 @@ struct TCP_Server_Info {
/* Total size of this PDU. Only valid from cifs_demultiplex_thread */
unsigned int pdu_size;
unsigned int total_read; /* total amount of data read in this pass */
+ atomic_t in_send; /* requests trying to send */
+ atomic_t num_waiters; /* blocked waiting to get in sendrecv */
#ifdef CONFIG_CIFS_FSCACHE
struct fscache_cookie *fscache; /* client index cache cookie */
#endif
#ifdef CONFIG_CIFS_STATS2
- atomic_t in_send; /* requests trying to send */
- atomic_t num_waiters; /* blocked waiting to get in sendrecv */
atomic_t num_cmds[NUMBER_OF_SMB2_COMMANDS]; /* total requests by cmd */
atomic_t smb2slowcmd[NUMBER_OF_SMB2_COMMANDS]; /* count resps > 1 sec */
__u64 time_per_cmd[NUMBER_OF_SMB2_COMMANDS]; /* total time per cmd */
@@ -953,6 +960,11 @@ struct cifs_server_iface {
struct sockaddr_storage sockaddr;
};
+struct cifs_chan {
+ struct TCP_Server_Info *server;
+ __u8 signkey[SMB3_SIGN_KEY_SIZE];
+};
+
/*
* Session structure. One of these for each uid session with a particular host
*/
@@ -983,12 +995,15 @@ struct cifs_ses {
bool sign; /* is signing required? */
bool need_reconnect:1; /* connection reset, uid now invalid */
bool domainAuto:1;
+ bool binding:1; /* are we binding the session? */
__u16 session_flags;
__u8 smb3signingkey[SMB3_SIGN_KEY_SIZE];
__u8 smb3encryptionkey[SMB3_SIGN_KEY_SIZE];
__u8 smb3decryptionkey[SMB3_SIGN_KEY_SIZE];
__u8 preauth_sha_hash[SMB2_PREAUTH_HASH_SIZE];
+ __u8 binding_preauth_sha_hash[SMB2_PREAUTH_HASH_SIZE];
+
/*
* Network interfaces available on the server this session is
* connected to.
@@ -1002,8 +1017,37 @@ struct cifs_ses {
struct cifs_server_iface *iface_list;
size_t iface_count;
unsigned long iface_last_update; /* jiffies */
+
+#define CIFS_MAX_CHANNELS 16
+ struct cifs_chan chans[CIFS_MAX_CHANNELS];
+ size_t chan_count;
+ size_t chan_max;
+ atomic_t chan_seq; /* round robin state */
};
+/*
+ * When binding a new channel, we need to access the channel which isn't fully
+ * established yet (one past the established count)
+ */
+
+static inline
+struct cifs_chan *cifs_ses_binding_channel(struct cifs_ses *ses)
+{
+ if (ses->binding)
+ return &ses->chans[ses->chan_count];
+ else
+ return NULL;
+}
+
+static inline
+struct TCP_Server_Info *cifs_ses_server(struct cifs_ses *ses)
+{
+ if (ses->binding)
+ return ses->chans[ses->chan_count].server;
+ else
+ return ses->server;
+}
+
static inline bool
cap_unix(struct cifs_ses *ses)
{
@@ -1260,11 +1304,14 @@ struct cifsFileInfo {
unsigned int f_flags;
bool invalidHandle:1; /* file closed via session abend */
bool oplock_break_cancelled:1;
+ unsigned int oplock_epoch; /* epoch from the lease break */
+ __u32 oplock_level; /* oplock/lease level from the lease break */
int count;
spinlock_t file_info_lock; /* protects four flag/count fields above */
struct mutex fh_mutex; /* prevents reopen race after dead ses*/
struct cifs_search_info srch_inf;
struct work_struct oplock_break; /* work for oplock breaks */
+ struct work_struct put; /* work for the final part of _put */
};
struct cifs_io_parms {
@@ -1370,7 +1417,8 @@ cifsFileInfo_get_locked(struct cifsFileInfo *cifs_file)
}
struct cifsFileInfo *cifsFileInfo_get(struct cifsFileInfo *cifs_file);
-void _cifsFileInfo_put(struct cifsFileInfo *cifs_file, bool wait_oplock_hdlr);
+void _cifsFileInfo_put(struct cifsFileInfo *cifs_file, bool wait_oplock_hdlr,
+ bool offload);
void cifsFileInfo_put(struct cifsFileInfo *cifs_file);
#define CIFS_CACHE_READ_FLG 1
@@ -1391,6 +1439,11 @@ void cifsFileInfo_put(struct cifsFileInfo *cifs_file);
struct cifsInodeInfo {
bool can_cache_brlcks;
struct list_head llist; /* locks helb by this inode */
+ /*
+ * NOTE: Some code paths call down_read(lock_sem) twice, so
+ * we must always use use cifs_down_write() instead of down_write()
+ * for this semaphore to avoid deadlocks.
+ */
struct rw_semaphore lock_sem; /* protect the fields above */
/* BB add in lists for dirty pages i.e. write caching info for oplock */
struct list_head openFileList;
@@ -1400,7 +1453,7 @@ struct cifsInodeInfo {
unsigned int epoch; /* used to track lease state changes */
#define CIFS_INODE_PENDING_OPLOCK_BREAK (0) /* oplock break in progress */
#define CIFS_INODE_PENDING_WRITERS (1) /* Writes in progress */
-#define CIFS_INODE_DOWNGRADE_OPLOCK_TO_L2 (2) /* Downgrade oplock to L2 */
+#define CIFS_INODE_FLAG_UNUSED (2) /* Unused flag */
#define CIFS_INO_DELETE_PENDING (3) /* delete pending on server */
#define CIFS_INO_INVALID_MAPPING (4) /* pagecache is invalid */
#define CIFS_INO_LOCK (5) /* lock bit for synchronization */
@@ -1519,6 +1572,7 @@ struct mid_q_entry {
struct TCP_Server_Info *server; /* server corresponding to this mid */
__u64 mid; /* multiplex id */
__u16 credits; /* number of credits consumed by this mid */
+ __u16 credits_received; /* number of credits from the response */
__u32 pid; /* process id */
__u32 sequence_number; /* for CIFS signing */
unsigned long when_alloc; /* when mid was created */
@@ -1546,12 +1600,12 @@ struct close_cancelled_open {
struct cifs_fid fid;
struct cifs_tcon *tcon;
struct work_struct work;
+ __u64 mid;
+ __u16 cmd;
};
/* Make code in transport.c a little cleaner by moving
update of optional stats into function below */
-#ifdef CONFIG_CIFS_STATS2
-
static inline void cifs_in_send_inc(struct TCP_Server_Info *server)
{
atomic_inc(&server->in_send);
@@ -1572,26 +1626,12 @@ static inline void cifs_num_waiters_dec(struct TCP_Server_Info *server)
atomic_dec(&server->num_waiters);
}
+#ifdef CONFIG_CIFS_STATS2
static inline void cifs_save_when_sent(struct mid_q_entry *mid)
{
mid->when_sent = jiffies;
}
#else
-static inline void cifs_in_send_inc(struct TCP_Server_Info *server)
-{
-}
-static inline void cifs_in_send_dec(struct TCP_Server_Info *server)
-{
-}
-
-static inline void cifs_num_waiters_inc(struct TCP_Server_Info *server)
-{
-}
-
-static inline void cifs_num_waiters_dec(struct TCP_Server_Info *server)
-{
-}
-
static inline void cifs_save_when_sent(struct mid_q_entry *mid)
{
}
@@ -1902,6 +1942,7 @@ void cifs_queue_oplock_break(struct cifsFileInfo *cfile);
extern const struct slow_work_ops cifs_oplock_break_ops;
extern struct workqueue_struct *cifsiod_wq;
extern struct workqueue_struct *decrypt_wq;
+extern struct workqueue_struct *fileinfo_put_wq;
extern struct workqueue_struct *cifsoplockd_wq;
extern __u32 cifs_lock_secret;
@@ -1932,4 +1973,10 @@ extern struct smb_version_values smb302_values;
#define ALT_SMB311_VERSION_STRING "3.11"
extern struct smb_version_operations smb311_operations;
extern struct smb_version_values smb311_values;
+
+static inline bool is_smb1_server(struct TCP_Server_Info *server)
+{
+ return strcmp(server->vals->version_string, SMB1_VERSION_STRING) == 0;
+}
+
#endif /* _CIFS_GLOB_H */
diff --git a/fs/cifs/cifsproto.h b/fs/cifs/cifsproto.h
index e53e9f62b87b..1ed695336f62 100644
--- a/fs/cifs/cifsproto.h
+++ b/fs/cifs/cifsproto.h
@@ -109,6 +109,7 @@ extern int SendReceive(const unsigned int /* xid */ , struct cifs_ses *,
extern int SendReceiveNoRsp(const unsigned int xid, struct cifs_ses *ses,
char *in_buf, int flags);
extern struct mid_q_entry *cifs_setup_request(struct cifs_ses *,
+ struct TCP_Server_Info *,
struct smb_rqst *);
extern struct mid_q_entry *cifs_setup_async_request(struct TCP_Server_Info *,
struct smb_rqst *);
@@ -170,6 +171,7 @@ extern int cifs_unlock_range(struct cifsFileInfo *cfile,
struct file_lock *flock, const unsigned int xid);
extern int cifs_push_mandatory_locks(struct cifsFileInfo *cfile);
+extern void cifs_down_write(struct rw_semaphore *sem);
extern struct cifsFileInfo *cifs_new_fileinfo(struct cifs_fid *fid,
struct file *file,
struct tcon_link *tlink,
@@ -241,6 +243,7 @@ extern void cifs_add_pending_open_locked(struct cifs_fid *fid,
struct tcon_link *tlink,
struct cifs_pending_open *open);
extern void cifs_del_pending_open(struct cifs_pending_open *open);
+extern struct TCP_Server_Info *cifs_get_tcp_session(struct smb_vol *vol);
extern void cifs_put_tcp_session(struct TCP_Server_Info *server,
int from_reconnect);
extern void cifs_put_tcon(struct cifs_tcon *tcon);
@@ -583,6 +586,12 @@ void cifs_free_hash(struct crypto_shash **shash, struct sdesc **sdesc);
extern void rqst_page_get_length(struct smb_rqst *rqst, unsigned int page,
unsigned int *len, unsigned int *offset);
+int cifs_try_adding_channels(struct cifs_ses *ses);
+int cifs_ses_add_channel(struct cifs_ses *ses,
+ struct cifs_server_iface *iface);
+bool is_server_using_iface(struct TCP_Server_Info *server,
+ struct cifs_server_iface *iface);
+bool is_ses_using_iface(struct cifs_ses *ses, struct cifs_server_iface *iface);
void extract_unc_hostname(const char *unc, const char **h, size_t *len);
int copy_path_name(char *dst, const char *src);
diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c
index a64dfa95a925..86d1baedf21c 100644
--- a/fs/cifs/connect.c
+++ b/fs/cifs/connect.c
@@ -97,6 +97,7 @@ enum {
Opt_persistent, Opt_nopersistent,
Opt_resilient, Opt_noresilient,
Opt_domainauto, Opt_rdma, Opt_modesid, Opt_rootfs,
+ Opt_multichannel, Opt_nomultichannel,
Opt_compress,
/* Mount options which take numeric value */
@@ -106,7 +107,7 @@ enum {
Opt_min_enc_offload,
Opt_blocksize, Opt_rsize, Opt_wsize, Opt_actimeo,
Opt_echo_interval, Opt_max_credits, Opt_handletimeout,
- Opt_snapshot,
+ Opt_snapshot, Opt_max_channels,
/* Mount options which take string value */
Opt_user, Opt_pass, Opt_ip,
@@ -199,6 +200,8 @@ static const match_table_t cifs_mount_option_tokens = {
{ Opt_noresilient, "noresilienthandles"},
{ Opt_domainauto, "domainauto"},
{ Opt_rdma, "rdma"},
+ { Opt_multichannel, "multichannel" },
+ { Opt_nomultichannel, "nomultichannel" },
{ Opt_backupuid, "backupuid=%s" },
{ Opt_backupgid, "backupgid=%s" },
@@ -218,6 +221,7 @@ static const match_table_t cifs_mount_option_tokens = {
{ Opt_echo_interval, "echo_interval=%s" },
{ Opt_max_credits, "max_credits=%s" },
{ Opt_snapshot, "snapshot=%s" },
+ { Opt_max_channels, "max_channels=%s" },
{ Opt_compress, "compress=%s" },
{ Opt_blank_user, "user=" },
@@ -387,7 +391,7 @@ static inline int reconn_set_ipaddr(struct TCP_Server_Info *server)
#ifdef CONFIG_CIFS_DFS_UPCALL
struct super_cb_data {
struct TCP_Server_Info *server;
- struct cifs_sb_info *cifs_sb;
+ struct super_block *sb;
};
/* These functions must be called with server->srv_mutex held */
@@ -398,25 +402,39 @@ static void super_cb(struct super_block *sb, void *arg)
struct cifs_sb_info *cifs_sb;
struct cifs_tcon *tcon;
- if (d->cifs_sb)
+ if (d->sb)
return;
cifs_sb = CIFS_SB(sb);
tcon = cifs_sb_master_tcon(cifs_sb);
if (tcon->ses->server == d->server)
- d->cifs_sb = cifs_sb;
+ d->sb = sb;
}
-static inline struct cifs_sb_info *
-find_super_by_tcp(struct TCP_Server_Info *server)
+static struct super_block *get_tcp_super(struct TCP_Server_Info *server)
{
struct super_cb_data d = {
.server = server,
- .cifs_sb = NULL,
+ .sb = NULL,
};
iterate_supers_type(&cifs_fs_type, super_cb, &d);
- return d.cifs_sb ? d.cifs_sb : ERR_PTR(-ENOENT);
+
+ if (unlikely(!d.sb))
+ return ERR_PTR(-ENOENT);
+ /*
+ * Grab an active reference in order to prevent automounts (DFS links)
+ * of expiring and then freeing up our cifs superblock pointer while
+ * we're doing failover.
+ */
+ cifs_sb_active(d.sb);
+ return d.sb;
+}
+
+static inline void put_tcp_super(struct super_block *sb)
+{
+ if (!IS_ERR_OR_NULL(sb))
+ cifs_sb_deactive(sb);
}
static void reconn_inval_dfs_target(struct TCP_Server_Info *server,
@@ -480,6 +498,7 @@ cifs_reconnect(struct TCP_Server_Info *server)
struct mid_q_entry *mid_entry;
struct list_head retry_list;
#ifdef CONFIG_CIFS_DFS_UPCALL
+ struct super_block *sb = NULL;
struct cifs_sb_info *cifs_sb = NULL;
struct dfs_cache_tgt_list tgt_list = {0};
struct dfs_cache_tgt_iterator *tgt_it = NULL;
@@ -489,13 +508,15 @@ cifs_reconnect(struct TCP_Server_Info *server)
server->nr_targets = 1;
#ifdef CONFIG_CIFS_DFS_UPCALL
spin_unlock(&GlobalMid_Lock);
- cifs_sb = find_super_by_tcp(server);
- if (IS_ERR(cifs_sb)) {
- rc = PTR_ERR(cifs_sb);
+ sb = get_tcp_super(server);
+ if (IS_ERR(sb)) {
+ rc = PTR_ERR(sb);
cifs_dbg(FYI, "%s: will not do DFS failover: rc = %d\n",
__func__, rc);
- cifs_sb = NULL;
+ sb = NULL;
} else {
+ cifs_sb = CIFS_SB(sb);
+
rc = reconn_setup_dfs_targets(cifs_sb, &tgt_list, &tgt_it);
if (rc && (rc != -EOPNOTSUPP)) {
cifs_server_dbg(VFS, "%s: no target servers for DFS failover\n",
@@ -512,6 +533,10 @@ cifs_reconnect(struct TCP_Server_Info *server)
/* the demux thread will exit normally
next time through the loop */
spin_unlock(&GlobalMid_Lock);
+#ifdef CONFIG_CIFS_DFS_UPCALL
+ dfs_cache_free_tgts(&tgt_list);
+ put_tcp_super(sb);
+#endif
return rc;
} else
server->tcpStatus = CifsNeedReconnect;
@@ -564,9 +589,11 @@ cifs_reconnect(struct TCP_Server_Info *server)
spin_lock(&GlobalMid_Lock);
list_for_each_safe(tmp, tmp2, &server->pending_mid_q) {
mid_entry = list_entry(tmp, struct mid_q_entry, qhead);
+ kref_get(&mid_entry->refcount);
if (mid_entry->mid_state == MID_REQUEST_SUBMITTED)
mid_entry->mid_state = MID_RETRY_NEEDED;
list_move(&mid_entry->qhead, &retry_list);
+ mid_entry->mid_flags |= MID_DELETED;
}
spin_unlock(&GlobalMid_Lock);
mutex_unlock(&server->srv_mutex);
@@ -576,6 +603,7 @@ cifs_reconnect(struct TCP_Server_Info *server)
mid_entry = list_entry(tmp, struct mid_q_entry, qhead);
list_del_init(&mid_entry->qhead);
mid_entry->callback(mid_entry);
+ cifs_mid_q_entry_release(mid_entry);
}
if (cifs_rdma_enabled(server)) {
@@ -635,7 +663,10 @@ cifs_reconnect(struct TCP_Server_Info *server)
__func__, rc);
}
dfs_cache_free_tgts(&tgt_list);
+
}
+
+ put_tcp_super(sb);
#endif
if (server->tcpStatus == CifsNeedNegotiate)
mod_delayed_work(cifsiod_wq, &server->echo, 0);
@@ -895,11 +926,27 @@ dequeue_mid(struct mid_q_entry *mid, bool malformed)
if (mid->mid_flags & MID_DELETED)
printk_once(KERN_WARNING
"trying to dequeue a deleted mid\n");
- else
+ else {
list_del_init(&mid->qhead);
+ mid->mid_flags |= MID_DELETED;
+ }
spin_unlock(&GlobalMid_Lock);
}
+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;
+
+ /*
+ * SMB1 does not use credits.
+ */
+ if (server->vals->header_preamble_size)
+ return 0;
+
+ return le16_to_cpu(shdr->CreditRequest);
+}
+
static void
handle_mid(struct mid_q_entry *mid, struct TCP_Server_Info *server,
char *buf, int malformed)
@@ -907,6 +954,7 @@ handle_mid(struct mid_q_entry *mid, struct TCP_Server_Info *server,
if (server->ops->check_trans2 &&
server->ops->check_trans2(mid, server, buf, malformed))
return;
+ mid->credits_received = smb2_get_credits_from_hdr(buf, server);
mid->resp_buf = buf;
mid->large_buf = server->large_buf;
/* Was previous buf put in mpx struct for multi-rsp? */
@@ -966,8 +1014,10 @@ static void clean_demultiplex_info(struct TCP_Server_Info *server)
list_for_each_safe(tmp, tmp2, &server->pending_mid_q) {
mid_entry = list_entry(tmp, struct mid_q_entry, qhead);
cifs_dbg(FYI, "Clearing mid 0x%llx\n", mid_entry->mid);
+ kref_get(&mid_entry->refcount);
mid_entry->mid_state = MID_SHUTDOWN;
list_move(&mid_entry->qhead, &dispose_list);
+ mid_entry->mid_flags |= MID_DELETED;
}
spin_unlock(&GlobalMid_Lock);
@@ -977,6 +1027,7 @@ static void clean_demultiplex_info(struct TCP_Server_Info *server)
cifs_dbg(FYI, "Callback mid 0x%llx\n", mid_entry->mid);
list_del_init(&mid_entry->qhead);
mid_entry->callback(mid_entry);
+ cifs_mid_q_entry_release(mid_entry);
}
/* 1/8th of sec is more than enough time for them to exit */
msleep(125);
@@ -1214,12 +1265,6 @@ next_pdu:
for (i = 0; i < num_mids; i++) {
if (mids[i] != NULL) {
mids[i]->resp_buf_size = server->pdu_size;
- if ((mids[i]->mid_flags & MID_WAIT_CANCELLED) &&
- mids[i]->mid_state == MID_RESPONSE_RECEIVED &&
- server->ops->handle_cancelled_mid)
- server->ops->handle_cancelled_mid(
- mids[i]->resp_buf,
- server);
if (!mids[i]->multiRsp || mids[i]->multiEnd)
mids[i]->callback(mids[i]);
@@ -1664,6 +1709,10 @@ cifs_parse_mount_options(const char *mountdata, const char *devname,
vol->echo_interval = SMB_ECHO_INTERVAL_DEFAULT;
+ /* default to no multichannel (single server connection) */
+ vol->multichannel = false;
+ vol->max_channels = 1;
+
if (!mountdata)
goto cifs_parse_mount_err;
@@ -1957,6 +2006,12 @@ cifs_parse_mount_options(const char *mountdata, const char *devname,
case Opt_rdma:
vol->rdma = true;
break;
+ case Opt_multichannel:
+ vol->multichannel = true;
+ break;
+ case Opt_nomultichannel:
+ vol->multichannel = false;
+ break;
case Opt_compress:
vol->compression = UNKNOWN_TYPE;
cifs_dbg(VFS,
@@ -2120,6 +2175,15 @@ cifs_parse_mount_options(const char *mountdata, const char *devname,
}
vol->max_credits = option;
break;
+ case Opt_max_channels:
+ if (get_option_ul(args, &option) || option < 1 ||
+ option > CIFS_MAX_CHANNELS) {
+ cifs_dbg(VFS, "%s: Invalid max_channels value, needs to be 1-%d\n",
+ __func__, CIFS_MAX_CHANNELS);
+ goto cifs_parse_mount_err;
+ }
+ vol->max_channels = option;
+ break;
/* String Arguments */
@@ -2705,7 +2769,7 @@ cifs_put_tcp_session(struct TCP_Server_Info *server, int from_reconnect)
send_sig(SIGKILL, task, 1);
}
-static struct TCP_Server_Info *
+struct TCP_Server_Info *
cifs_get_tcp_session(struct smb_vol *volume_info)
{
struct TCP_Server_Info *tcp_ses = NULL;
@@ -2764,7 +2828,11 @@ cifs_get_tcp_session(struct smb_vol *volume_info)
sizeof(tcp_ses->srcaddr));
memcpy(&tcp_ses->dstaddr, &volume_info->dstaddr,
sizeof(tcp_ses->dstaddr));
- generate_random_uuid(tcp_ses->client_guid);
+ if (volume_info->use_client_guid)
+ memcpy(tcp_ses->client_guid, volume_info->client_guid,
+ SMB2_CLIENT_GUID_SIZE);
+ else
+ generate_random_uuid(tcp_ses->client_guid);
/*
* at this point we are the only ones with the pointer
* to the struct since the kernel thread not created yet
@@ -2853,6 +2921,13 @@ static int match_session(struct cifs_ses *ses, struct smb_vol *vol)
vol->sectype != ses->sectype)
return 0;
+ /*
+ * If an existing session is limited to less channels than
+ * requested, it should not be reused
+ */
+ if (ses->chan_max < vol->max_channels)
+ return 0;
+
switch (ses->sectype) {
case Kerberos:
if (!uid_eq(vol->cred_uid, ses->cred_uid))
@@ -3023,6 +3098,14 @@ void cifs_put_smb_ses(struct cifs_ses *ses)
list_del_init(&ses->smb_ses_list);
spin_unlock(&cifs_tcp_ses_lock);
+ /* close any extra channels */
+ if (ses->chan_count > 1) {
+ int i;
+
+ for (i = 1; i < ses->chan_count; i++)
+ cifs_put_tcp_session(ses->chans[i].server, 0);
+ }
+
sesInfoFree(ses);
cifs_put_tcp_session(server, 0);
}
@@ -3269,14 +3352,25 @@ cifs_get_smb_ses(struct TCP_Server_Info *server, struct smb_vol *volume_info)
ses->sectype = volume_info->sectype;
ses->sign = volume_info->sign;
mutex_lock(&ses->session_mutex);
+
+ /* add server as first channel */
+ ses->chans[0].server = server;
+ ses->chan_count = 1;
+ ses->chan_max = volume_info->multichannel ? volume_info->max_channels:1;
+
rc = cifs_negotiate_protocol(xid, ses);
if (!rc)
rc = cifs_setup_session(xid, ses, volume_info->local_nls);
+
+ /* each channel uses a different signing key */
+ memcpy(ses->chans[0].signkey, ses->smb3signingkey,
+ sizeof(ses->smb3signingkey));
+
mutex_unlock(&ses->session_mutex);
if (rc)
goto get_ses_fail;
- /* success, put it on the list */
+ /* success, put it on the list and add it as first channel */
spin_lock(&cifs_tcp_ses_lock);
list_add(&ses->smb_ses_list, &server->smb_ses_list);
spin_unlock(&cifs_tcp_ses_lock);
@@ -3882,8 +3976,12 @@ generic_ip_connect(struct TCP_Server_Info *server)
rc = socket->ops->connect(socket, saddr, slen,
server->noblockcnt ? O_NONBLOCK : 0);
-
- if (rc == -EINPROGRESS)
+ /*
+ * When mounting SMB root file systems, we do not want to block in
+ * connect. Otherwise bail out and then let cifs_reconnect() perform
+ * reconnect failover - if possible.
+ */
+ if (server->noblockcnt && rc == -EINPROGRESS)
rc = 0;
if (rc < 0) {
cifs_dbg(FYI, "Error %d connecting to server\n", rc);
@@ -4688,6 +4786,17 @@ static int is_path_remote(struct cifs_sb_info *cifs_sb, struct smb_vol *vol,
}
#ifdef CONFIG_CIFS_DFS_UPCALL
+static inline void set_root_tcon(struct cifs_sb_info *cifs_sb,
+ struct cifs_tcon *tcon,
+ struct cifs_tcon **root)
+{
+ spin_lock(&cifs_tcp_ses_lock);
+ tcon->tc_count++;
+ tcon->remap = cifs_remap(cifs_sb);
+ spin_unlock(&cifs_tcp_ses_lock);
+ *root = tcon;
+}
+
int cifs_mount(struct cifs_sb_info *cifs_sb, struct smb_vol *vol)
{
int rc = 0;
@@ -4789,18 +4898,10 @@ int cifs_mount(struct cifs_sb_info *cifs_sb, struct smb_vol *vol)
/* Cache out resolved root server */
(void)dfs_cache_find(xid, ses, cifs_sb->local_nls, cifs_remap(cifs_sb),
root_path + 1, NULL, NULL);
- /*
- * Save root tcon for additional DFS requests to update or create a new
- * DFS cache entry, or even perform DFS failover.
- */
- spin_lock(&cifs_tcp_ses_lock);
- tcon->tc_count++;
- tcon->dfs_path = root_path;
+ kfree(root_path);
root_path = NULL;
- tcon->remap = cifs_remap(cifs_sb);
- spin_unlock(&cifs_tcp_ses_lock);
- root_tcon = tcon;
+ set_root_tcon(cifs_sb, tcon, &root_tcon);
for (count = 1; ;) {
if (!rc && tcon) {
@@ -4837,6 +4938,15 @@ int cifs_mount(struct cifs_sb_info *cifs_sb, struct smb_vol *vol)
mount_put_conns(cifs_sb, xid, server, ses, tcon);
rc = mount_get_conns(vol, cifs_sb, &xid, &server, &ses,
&tcon);
+ /*
+ * Ensure that DFS referrals go through new root server.
+ */
+ if (!rc && tcon &&
+ (tcon->share_flags & (SHI1005_FLAGS_DFS |
+ SHI1005_FLAGS_DFS_ROOT))) {
+ cifs_put_tcon(root_tcon);
+ set_root_tcon(cifs_sb, tcon, &root_tcon);
+ }
}
if (rc) {
if (rc == -EACCES || rc == -EOPNOTSUPP)
@@ -4885,6 +4995,7 @@ int cifs_mount(struct cifs_sb_info *cifs_sb, struct smb_vol *vol)
cifs_autodisable_serverino(cifs_sb);
out:
free_xid(xid);
+ cifs_try_adding_channels(ses);
return mount_setup_tlink(cifs_sb, ses, tcon);
error:
@@ -5130,7 +5241,7 @@ int
cifs_negotiate_protocol(const unsigned int xid, struct cifs_ses *ses)
{
int rc = 0;
- struct TCP_Server_Info *server = ses->server;
+ struct TCP_Server_Info *server = cifs_ses_server(ses);
if (!server->ops->need_neg || !server->ops->negotiate)
return -ENOSYS;
@@ -5157,23 +5268,25 @@ cifs_setup_session(const unsigned int xid, struct cifs_ses *ses,
struct nls_table *nls_info)
{
int rc = -ENOSYS;
- struct TCP_Server_Info *server = ses->server;
-
- ses->capabilities = server->capabilities;
- if (linuxExtEnabled == 0)
- ses->capabilities &= (~server->vals->cap_unix);
+ struct TCP_Server_Info *server = cifs_ses_server(ses);
+
+ if (!ses->binding) {
+ ses->capabilities = server->capabilities;
+ if (linuxExtEnabled == 0)
+ ses->capabilities &= (~server->vals->cap_unix);
+
+ if (ses->auth_key.response) {
+ cifs_dbg(FYI, "Free previous auth_key.response = %p\n",
+ ses->auth_key.response);
+ kfree(ses->auth_key.response);
+ ses->auth_key.response = NULL;
+ ses->auth_key.len = 0;
+ }
+ }
cifs_dbg(FYI, "Security Mode: 0x%x Capabilities: 0x%x TimeAdjust: %d\n",
server->sec_mode, server->capabilities, server->timeAdj);
- if (ses->auth_key.response) {
- cifs_dbg(FYI, "Free previous auth_key.response = %p\n",
- ses->auth_key.response);
- kfree(ses->auth_key.response);
- ses->auth_key.response = NULL;
- ses->auth_key.len = 0;
- }
-
if (server->ops->sess_setup)
rc = server->ops->sess_setup(xid, ses, nls_info);
diff --git a/fs/cifs/dfs_cache.c b/fs/cifs/dfs_cache.c
index 1692c0c6c23a..2faa05860a48 100644
--- a/fs/cifs/dfs_cache.c
+++ b/fs/cifs/dfs_cache.c
@@ -1317,7 +1317,6 @@ static struct cifs_ses *find_root_ses(struct dfs_cache_vol_info *vi,
int rc;
struct dfs_info3_param ref = {0};
char *mdata = NULL, *devname = NULL;
- bool is_smb3 = tcon->ses->server->vals->header_preamble_size == 0;
struct TCP_Server_Info *server;
struct cifs_ses *ses;
struct smb_vol vol;
@@ -1344,7 +1343,7 @@ static struct cifs_ses *find_root_ses(struct dfs_cache_vol_info *vi,
goto out;
}
- rc = cifs_setup_volume_info(&vol, mdata, devname, is_smb3);
+ rc = cifs_setup_volume_info(&vol, mdata, devname, false);
kfree(devname);
if (rc) {
diff --git a/fs/cifs/dir.c b/fs/cifs/dir.c
index 7ce689d31aa2..f3b79012ff29 100644
--- a/fs/cifs/dir.c
+++ b/fs/cifs/dir.c
@@ -244,10 +244,8 @@ cifs_do_create(struct inode *inode, struct dentry *direntry, unsigned int xid,
*oplock = REQ_OPLOCK;
full_path = build_path_from_dentry(direntry);
- if (full_path == NULL) {
- rc = -ENOMEM;
- goto out;
- }
+ if (!full_path)
+ return -ENOMEM;
if (tcon->unix_ext && cap_unix(tcon->ses) && !tcon->broken_posix_open &&
(CIFS_UNIX_POSIX_PATH_OPS_CAP &
diff --git a/fs/cifs/file.c b/fs/cifs/file.c
index 5ad15de2bb4f..f1fe9c44d298 100644
--- a/fs/cifs/file.c
+++ b/fs/cifs/file.c
@@ -281,6 +281,15 @@ cifs_has_mand_locks(struct cifsInodeInfo *cinode)
return has_locks;
}
+void
+cifs_down_write(struct rw_semaphore *sem)
+{
+ while (!down_write_trylock(sem))
+ msleep(10);
+}
+
+static void cifsFileInfo_put_work(struct work_struct *work);
+
struct cifsFileInfo *
cifs_new_fileinfo(struct cifs_fid *fid, struct file *file,
struct tcon_link *tlink, __u32 oplock)
@@ -306,7 +315,7 @@ cifs_new_fileinfo(struct cifs_fid *fid, struct file *file,
INIT_LIST_HEAD(&fdlocks->locks);
fdlocks->cfile = cfile;
cfile->llist = fdlocks;
- down_write(&cinode->lock_sem);
+ cifs_down_write(&cinode->lock_sem);
list_add(&fdlocks->llist, &cinode->llist);
up_write(&cinode->lock_sem);
@@ -318,6 +327,7 @@ cifs_new_fileinfo(struct cifs_fid *fid, struct file *file,
cfile->invalidHandle = false;
cfile->tlink = cifs_get_tlink(tlink);
INIT_WORK(&cfile->oplock_break, cifs_oplock_break);
+ INIT_WORK(&cfile->put, cifsFileInfo_put_work);
mutex_init(&cfile->fh_mutex);
spin_lock_init(&cfile->file_info_lock);
@@ -368,6 +378,41 @@ cifsFileInfo_get(struct cifsFileInfo *cifs_file)
return cifs_file;
}
+static void cifsFileInfo_put_final(struct cifsFileInfo *cifs_file)
+{
+ struct inode *inode = d_inode(cifs_file->dentry);
+ struct cifsInodeInfo *cifsi = CIFS_I(inode);
+ struct cifsLockInfo *li, *tmp;
+ struct super_block *sb = inode->i_sb;
+
+ /*
+ * Delete any outstanding lock records. We'll lose them when the file
+ * is closed anyway.
+ */
+ cifs_down_write(&cifsi->lock_sem);
+ list_for_each_entry_safe(li, tmp, &cifs_file->llist->locks, llist) {
+ list_del(&li->llist);
+ cifs_del_lock_waiters(li);
+ kfree(li);
+ }
+ list_del(&cifs_file->llist->llist);
+ kfree(cifs_file->llist);
+ up_write(&cifsi->lock_sem);
+
+ cifs_put_tlink(cifs_file->tlink);
+ dput(cifs_file->dentry);
+ cifs_sb_deactive(sb);
+ kfree(cifs_file);
+}
+
+static void cifsFileInfo_put_work(struct work_struct *work)
+{
+ struct cifsFileInfo *cifs_file = container_of(work,
+ struct cifsFileInfo, put);
+
+ cifsFileInfo_put_final(cifs_file);
+}
+
/**
* cifsFileInfo_put - release a reference of file priv data
*
@@ -375,15 +420,15 @@ cifsFileInfo_get(struct cifsFileInfo *cifs_file)
*/
void cifsFileInfo_put(struct cifsFileInfo *cifs_file)
{
- _cifsFileInfo_put(cifs_file, true);
+ _cifsFileInfo_put(cifs_file, true, true);
}
/**
* _cifsFileInfo_put - release a reference of file priv data
*
* This may involve closing the filehandle @cifs_file out on the
- * server. Must be called without holding tcon->open_file_lock and
- * cifs_file->file_info_lock.
+ * server. Must be called without holding tcon->open_file_lock,
+ * cinode->open_file_lock and cifs_file->file_info_lock.
*
* If @wait_for_oplock_handler is true and we are releasing the last
* reference, wait for any running oplock break handler of the file
@@ -391,7 +436,8 @@ void cifsFileInfo_put(struct cifsFileInfo *cifs_file)
* oplock break handler, you need to pass false.
*
*/
-void _cifsFileInfo_put(struct cifsFileInfo *cifs_file, bool wait_oplock_handler)
+void _cifsFileInfo_put(struct cifsFileInfo *cifs_file,
+ bool wait_oplock_handler, bool offload)
{
struct inode *inode = d_inode(cifs_file->dentry);
struct cifs_tcon *tcon = tlink_tcon(cifs_file->tlink);
@@ -399,16 +445,16 @@ void _cifsFileInfo_put(struct cifsFileInfo *cifs_file, bool wait_oplock_handler)
struct cifsInodeInfo *cifsi = CIFS_I(inode);
struct super_block *sb = inode->i_sb;
struct cifs_sb_info *cifs_sb = CIFS_SB(sb);
- struct cifsLockInfo *li, *tmp;
struct cifs_fid fid;
struct cifs_pending_open open;
bool oplock_break_cancelled;
spin_lock(&tcon->open_file_lock);
-
+ spin_lock(&cifsi->open_file_lock);
spin_lock(&cifs_file->file_info_lock);
if (--cifs_file->count > 0) {
spin_unlock(&cifs_file->file_info_lock);
+ spin_unlock(&cifsi->open_file_lock);
spin_unlock(&tcon->open_file_lock);
return;
}
@@ -421,9 +467,7 @@ void _cifsFileInfo_put(struct cifsFileInfo *cifs_file, bool wait_oplock_handler)
cifs_add_pending_open_locked(&fid, cifs_file->tlink, &open);
/* remove it from the lists */
- spin_lock(&cifsi->open_file_lock);
list_del(&cifs_file->flist);
- spin_unlock(&cifsi->open_file_lock);
list_del(&cifs_file->tlist);
atomic_dec(&tcon->num_local_opens);
@@ -440,6 +484,7 @@ void _cifsFileInfo_put(struct cifsFileInfo *cifs_file, bool wait_oplock_handler)
cifs_set_oplock_level(cifsi, 0);
}
+ spin_unlock(&cifsi->open_file_lock);
spin_unlock(&tcon->open_file_lock);
oplock_break_cancelled = wait_oplock_handler ?
@@ -460,24 +505,10 @@ void _cifsFileInfo_put(struct cifsFileInfo *cifs_file, bool wait_oplock_handler)
cifs_del_pending_open(&open);
- /*
- * Delete any outstanding lock records. We'll lose them when the file
- * is closed anyway.
- */
- down_write(&cifsi->lock_sem);
- list_for_each_entry_safe(li, tmp, &cifs_file->llist->locks, llist) {
- list_del(&li->llist);
- cifs_del_lock_waiters(li);
- kfree(li);
- }
- list_del(&cifs_file->llist->llist);
- kfree(cifs_file->llist);
- up_write(&cifsi->lock_sem);
-
- cifs_put_tlink(cifs_file->tlink);
- dput(cifs_file->dentry);
- cifs_sb_deactive(sb);
- kfree(cifs_file);
+ if (offload)
+ queue_work(fileinfo_put_wq, &cifs_file->put);
+ else
+ cifsFileInfo_put_final(cifs_file);
}
int cifs_open(struct inode *inode, struct file *file)
@@ -721,6 +752,13 @@ cifs_reopen_file(struct cifsFileInfo *cfile, bool can_flush)
if (backup_cred(cifs_sb))
create_options |= CREATE_OPEN_BACKUP_INTENT;
+ /* O_SYNC also has bit for O_DSYNC so following check picks up either */
+ if (cfile->f_flags & O_SYNC)
+ create_options |= CREATE_WRITE_THROUGH;
+
+ if (cfile->f_flags & O_DIRECT)
+ create_options |= CREATE_NO_BUFFER;
+
if (server->ops->get_lease_key)
server->ops->get_lease_key(inode, &cfile->fid);
@@ -801,7 +839,7 @@ reopen_error_exit:
int cifs_close(struct inode *inode, struct file *file)
{
if (file->private_data != NULL) {
- cifsFileInfo_put(file->private_data);
+ _cifsFileInfo_put(file->private_data, true, false);
file->private_data = NULL;
}
@@ -1027,7 +1065,7 @@ static void
cifs_lock_add(struct cifsFileInfo *cfile, struct cifsLockInfo *lock)
{
struct cifsInodeInfo *cinode = CIFS_I(d_inode(cfile->dentry));
- down_write(&cinode->lock_sem);
+ cifs_down_write(&cinode->lock_sem);
list_add_tail(&lock->llist, &cfile->llist->locks);
up_write(&cinode->lock_sem);
}
@@ -1049,7 +1087,7 @@ cifs_lock_add_if(struct cifsFileInfo *cfile, struct cifsLockInfo *lock,
try_again:
exist = false;
- down_write(&cinode->lock_sem);
+ cifs_down_write(&cinode->lock_sem);
exist = cifs_find_lock_conflict(cfile, lock->offset, lock->length,
lock->type, lock->flags, &conf_lock,
@@ -1072,7 +1110,7 @@ try_again:
(lock->blist.next == &lock->blist));
if (!rc)
goto try_again;
- down_write(&cinode->lock_sem);
+ cifs_down_write(&cinode->lock_sem);
list_del_init(&lock->blist);
}
@@ -1125,7 +1163,7 @@ cifs_posix_lock_set(struct file *file, struct file_lock *flock)
return rc;
try_again:
- down_write(&cinode->lock_sem);
+ cifs_down_write(&cinode->lock_sem);
if (!cinode->can_cache_brlcks) {
up_write(&cinode->lock_sem);
return rc;
@@ -1331,7 +1369,7 @@ cifs_push_locks(struct cifsFileInfo *cfile)
int rc = 0;
/* we are going to update can_cache_brlcks here - need a write access */
- down_write(&cinode->lock_sem);
+ cifs_down_write(&cinode->lock_sem);
if (!cinode->can_cache_brlcks) {
up_write(&cinode->lock_sem);
return rc;
@@ -1522,7 +1560,7 @@ cifs_unlock_range(struct cifsFileInfo *cfile, struct file_lock *flock,
if (!buf)
return -ENOMEM;
- down_write(&cinode->lock_sem);
+ cifs_down_write(&cinode->lock_sem);
for (i = 0; i < 2; i++) {
cur = buf;
num = 0;
@@ -1674,7 +1712,7 @@ cifs_setlk(struct file *file, struct file_lock *flock, __u32 type,
rc = server->ops->mand_unlock_range(cfile, flock, xid);
out:
- if (flock->fl_flags & FL_POSIX) {
+ if ((flock->fl_flags & FL_POSIX) || (flock->fl_flags & FL_FLOCK)) {
/*
* If this is a request to remove all locks because we
* are closing the file, it doesn't matter if the
@@ -1691,6 +1729,52 @@ out:
return rc;
}
+int cifs_flock(struct file *file, int cmd, struct file_lock *fl)
+{
+ int rc, xid;
+ int lock = 0, unlock = 0;
+ bool wait_flag = false;
+ bool posix_lck = false;
+ struct cifs_sb_info *cifs_sb;
+ struct cifs_tcon *tcon;
+ struct cifsFileInfo *cfile;
+ __u32 type;
+
+ rc = -EACCES;
+ xid = get_xid();
+
+ if (!(fl->fl_flags & FL_FLOCK))
+ return -ENOLCK;
+
+ cfile = (struct cifsFileInfo *)file->private_data;
+ tcon = tlink_tcon(cfile->tlink);
+
+ cifs_read_flock(fl, &type, &lock, &unlock, &wait_flag,
+ tcon->ses->server);
+ cifs_sb = CIFS_FILE_SB(file);
+
+ if (cap_unix(tcon->ses) &&
+ (CIFS_UNIX_FCNTL_CAP & le64_to_cpu(tcon->fsUnixInfo.Capability)) &&
+ ((cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NOPOSIXBRL) == 0))
+ posix_lck = true;
+
+ if (!lock && !unlock) {
+ /*
+ * if no lock or unlock then nothing to do since we do not
+ * know what it is
+ */
+ free_xid(xid);
+ return -EOPNOTSUPP;
+ }
+
+ rc = cifs_setlk(file, fl, type, wait_flag, posix_lck, lock, unlock,
+ xid);
+ free_xid(xid);
+ return rc;
+
+
+}
+
int cifs_lock(struct file *file, int cmd, struct file_lock *flock)
{
int rc, xid;
@@ -2750,9 +2834,17 @@ cifs_resend_wdata(struct cifs_writedata *wdata, struct list_head *wdata_list,
if (!rc) {
if (wdata->cfile->invalidHandle)
rc = -EAGAIN;
- else
+ else {
+#ifdef CONFIG_CIFS_SMB_DIRECT
+ if (wdata->mr) {
+ wdata->mr->need_invalidate = true;
+ smbd_deregister_mr(wdata->mr);
+ wdata->mr = NULL;
+ }
+#endif
rc = server->ops->async_writev(wdata,
cifs_uncached_writedata_release);
+ }
}
/* If the write was successfully sent, we are done */
@@ -3475,8 +3567,16 @@ static int cifs_resend_rdata(struct cifs_readdata *rdata,
if (!rc) {
if (rdata->cfile->invalidHandle)
rc = -EAGAIN;
- else
+ else {
+#ifdef CONFIG_CIFS_SMB_DIRECT
+ if (rdata->mr) {
+ rdata->mr->need_invalidate = true;
+ smbd_deregister_mr(rdata->mr);
+ rdata->mr = NULL;
+ }
+#endif
rc = server->ops->async_readv(rdata);
+ }
}
/* If the read was successfully sent, we are done */
@@ -4630,12 +4730,13 @@ void cifs_oplock_break(struct work_struct *work)
struct cifs_tcon *tcon = tlink_tcon(cfile->tlink);
struct TCP_Server_Info *server = tcon->ses->server;
int rc = 0;
+ bool purge_cache = false;
wait_on_bit(&cinode->flags, CIFS_INODE_PENDING_WRITERS,
TASK_UNINTERRUPTIBLE);
- server->ops->downgrade_oplock(server, cinode,
- test_bit(CIFS_INODE_DOWNGRADE_OPLOCK_TO_L2, &cinode->flags));
+ server->ops->downgrade_oplock(server, cinode, cfile->oplock_level,
+ cfile->oplock_epoch, &purge_cache);
if (!CIFS_CACHE_WRITE(cinode) && CIFS_CACHE_READ(cinode) &&
cifs_has_mand_locks(cinode)) {
@@ -4650,18 +4751,21 @@ void cifs_oplock_break(struct work_struct *work)
else
break_lease(inode, O_WRONLY);
rc = filemap_fdatawrite(inode->i_mapping);
- if (!CIFS_CACHE_READ(cinode)) {
+ if (!CIFS_CACHE_READ(cinode) || purge_cache) {
rc = filemap_fdatawait(inode->i_mapping);
mapping_set_error(inode->i_mapping, rc);
cifs_zap_mapping(inode);
}
cifs_dbg(FYI, "Oplock flush inode %p rc %d\n", inode, rc);
+ if (CIFS_CACHE_WRITE(cinode))
+ goto oplock_break_ack;
}
rc = cifs_push_locks(cfile);
if (rc)
cifs_dbg(VFS, "Push locks rc = %d\n", rc);
+oplock_break_ack:
/*
* releasing stale oplock after recent reconnect of smb session using
* a now incorrect file handle is not a data integrity issue but do
@@ -4673,7 +4777,7 @@ void cifs_oplock_break(struct work_struct *work)
cinode);
cifs_dbg(FYI, "Oplock release rc = %d\n", rc);
}
- _cifsFileInfo_put(cfile, false /* do not wait for ourself */);
+ _cifsFileInfo_put(cfile, false /* do not wait for ourself */, false);
cifs_done_oplock_break(cinode);
}
diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c
index 5dcc95b38310..8a76195e8a69 100644
--- a/fs/cifs/inode.c
+++ b/fs/cifs/inode.c
@@ -727,22 +727,138 @@ static __u64 simple_hashstr(const char *str)
return hash;
}
+/**
+ * cifs_backup_query_path_info - SMB1 fallback code to get ino
+ *
+ * Fallback code to get file metadata when we don't have access to
+ * @full_path (EACCESS) and have backup creds.
+ *
+ * @data will be set to search info result buffer
+ * @resp_buf will be set to cifs resp buf and needs to be freed with
+ * cifs_buf_release() when done with @data.
+ */
+static int
+cifs_backup_query_path_info(int xid,
+ struct cifs_tcon *tcon,
+ struct super_block *sb,
+ const char *full_path,
+ void **resp_buf,
+ FILE_ALL_INFO **data)
+{
+ struct cifs_sb_info *cifs_sb = CIFS_SB(sb);
+ struct cifs_search_info info = {0};
+ u16 flags;
+ int rc;
+
+ *resp_buf = NULL;
+ info.endOfSearch = false;
+ if (tcon->unix_ext)
+ info.info_level = SMB_FIND_FILE_UNIX;
+ else if ((tcon->ses->capabilities &
+ tcon->ses->server->vals->cap_nt_find) == 0)
+ info.info_level = SMB_FIND_FILE_INFO_STANDARD;
+ else if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SERVER_INUM)
+ info.info_level = SMB_FIND_FILE_ID_FULL_DIR_INFO;
+ else /* no srvino useful for fallback to some netapp */
+ info.info_level = SMB_FIND_FILE_DIRECTORY_INFO;
+
+ flags = CIFS_SEARCH_CLOSE_ALWAYS |
+ CIFS_SEARCH_CLOSE_AT_END |
+ CIFS_SEARCH_BACKUP_SEARCH;
+
+ rc = CIFSFindFirst(xid, tcon, full_path,
+ cifs_sb, NULL, flags, &info, false);
+ if (rc)
+ return rc;
+
+ *resp_buf = (void *)info.ntwrk_buf_start;
+ *data = (FILE_ALL_INFO *)info.srch_entries_start;
+ return 0;
+}
+
+static void
+cifs_set_fattr_ino(int xid,
+ struct cifs_tcon *tcon,
+ struct super_block *sb,
+ struct inode **inode,
+ const char *full_path,
+ FILE_ALL_INFO *data,
+ struct cifs_fattr *fattr)
+{
+ struct cifs_sb_info *cifs_sb = CIFS_SB(sb);
+ struct TCP_Server_Info *server = tcon->ses->server;
+ int rc;
+
+ if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SERVER_INUM)) {
+ if (*inode)
+ fattr->cf_uniqueid = CIFS_I(*inode)->uniqueid;
+ else
+ fattr->cf_uniqueid = iunique(sb, ROOT_I);
+ return;
+ }
+
+ /*
+ * If we have an inode pass a NULL tcon to ensure we don't
+ * make a round trip to the server. This only works for SMB2+.
+ */
+ rc = server->ops->get_srv_inum(xid,
+ *inode ? NULL : tcon,
+ cifs_sb, full_path,
+ &fattr->cf_uniqueid,
+ data);
+ if (rc) {
+ /*
+ * If that fails reuse existing ino or generate one
+ * and disable server ones
+ */
+ if (*inode)
+ fattr->cf_uniqueid = CIFS_I(*inode)->uniqueid;
+ else {
+ fattr->cf_uniqueid = iunique(sb, ROOT_I);
+ cifs_autodisable_serverino(cifs_sb);
+ }
+ return;
+ }
+
+ /* If no errors, check for zero root inode (invalid) */
+ if (fattr->cf_uniqueid == 0 && strlen(full_path) == 0) {
+ cifs_dbg(FYI, "Invalid (0) inodenum\n");
+ if (*inode) {
+ /* reuse */
+ fattr->cf_uniqueid = CIFS_I(*inode)->uniqueid;
+ } else {
+ /* make an ino by hashing the UNC */
+ fattr->cf_flags |= CIFS_FATTR_FAKE_ROOT_INO;
+ fattr->cf_uniqueid = simple_hashstr(tcon->treeName);
+ }
+ }
+}
+
+static inline bool is_inode_cache_good(struct inode *ino)
+{
+ return ino && CIFS_CACHE_READ(CIFS_I(ino)) && CIFS_I(ino)->time != 0;
+}
+
int
-cifs_get_inode_info(struct inode **inode, const char *full_path,
- FILE_ALL_INFO *data, struct super_block *sb, int xid,
+cifs_get_inode_info(struct inode **inode,
+ const char *full_path,
+ FILE_ALL_INFO *in_data,
+ struct super_block *sb, int xid,
const struct cifs_fid *fid)
{
- __u16 srchflgs;
- int rc = 0, tmprc = ENOSYS;
+
struct cifs_tcon *tcon;
struct TCP_Server_Info *server;
struct tcon_link *tlink;
struct cifs_sb_info *cifs_sb = CIFS_SB(sb);
- char *buf = NULL;
bool adjust_tz = false;
- struct cifs_fattr fattr;
- struct cifs_search_info *srchinf = NULL;
+ struct cifs_fattr fattr = {0};
bool symlink = false;
+ FILE_ALL_INFO *data = in_data;
+ FILE_ALL_INFO *tmp_data = NULL;
+ void *smb1_backup_rsp_buf = NULL;
+ int rc = 0;
+ int tmprc = 0;
tlink = cifs_sb_tlink(cifs_sb);
if (IS_ERR(tlink))
@@ -750,142 +866,88 @@ cifs_get_inode_info(struct inode **inode, const char *full_path,
tcon = tlink_tcon(tlink);
server = tcon->ses->server;
- cifs_dbg(FYI, "Getting info on %s\n", full_path);
+ /*
+ * 1. Fetch file metadata if not provided (data)
+ */
- if ((data == NULL) && (*inode != NULL)) {
- if (CIFS_CACHE_READ(CIFS_I(*inode)) &&
- CIFS_I(*inode)->time != 0) {
+ if (!data) {
+ if (is_inode_cache_good(*inode)) {
cifs_dbg(FYI, "No need to revalidate cached inode sizes\n");
- goto cgii_exit;
- }
- }
-
- /* if inode info is not passed, get it from server */
- if (data == NULL) {
- if (!server->ops->query_path_info) {
- rc = -ENOSYS;
- goto cgii_exit;
+ goto out;
}
- buf = kmalloc(sizeof(FILE_ALL_INFO), GFP_KERNEL);
- if (buf == NULL) {
+ tmp_data = kmalloc(sizeof(FILE_ALL_INFO), GFP_KERNEL);
+ if (!tmp_data) {
rc = -ENOMEM;
- goto cgii_exit;
+ goto out;
}
- data = (FILE_ALL_INFO *)buf;
- rc = server->ops->query_path_info(xid, tcon, cifs_sb, full_path,
- data, &adjust_tz, &symlink);
+ rc = server->ops->query_path_info(xid, tcon, cifs_sb,
+ full_path, tmp_data,
+ &adjust_tz, &symlink);
+ data = tmp_data;
}
- if (!rc) {
- cifs_all_info_to_fattr(&fattr, data, sb, adjust_tz,
- symlink);
- } else if (rc == -EREMOTE) {
+ /*
+ * 2. Convert it to internal cifs metadata (fattr)
+ */
+
+ switch (rc) {
+ case 0:
+ cifs_all_info_to_fattr(&fattr, data, sb, adjust_tz, symlink);
+ break;
+ case -EREMOTE:
+ /* DFS link, no metadata available on this server */
cifs_create_dfs_fattr(&fattr, sb);
rc = 0;
- } else if ((rc == -EACCES) && backup_cred(cifs_sb) &&
- (strcmp(server->vals->version_string, SMB1_VERSION_STRING)
- == 0)) {
+ break;
+ case -EACCES:
/*
- * For SMB2 and later the backup intent flag is already
- * sent if needed on open and there is no path based
- * FindFirst operation to use to retry with
+ * perm errors, try again with backup flags if possible
+ *
+ * For SMB2 and later the backup intent flag
+ * is already sent if needed on open and there
+ * is no path based FindFirst operation to use
+ * to retry with
*/
+ if (backup_cred(cifs_sb) && is_smb1_server(server)) {
+ /* for easier reading */
+ FILE_DIRECTORY_INFO *fdi;
+ SEARCH_ID_FULL_DIR_INFO *si;
+
+ rc = cifs_backup_query_path_info(xid, tcon, sb,
+ full_path,
+ &smb1_backup_rsp_buf,
+ &data);
+ if (rc)
+ goto out;
- srchinf = kzalloc(sizeof(struct cifs_search_info),
- GFP_KERNEL);
- if (srchinf == NULL) {
- rc = -ENOMEM;
- goto cgii_exit;
- }
+ fdi = (FILE_DIRECTORY_INFO *)data;
+ si = (SEARCH_ID_FULL_DIR_INFO *)data;
- srchinf->endOfSearch = false;
- if (tcon->unix_ext)
- srchinf->info_level = SMB_FIND_FILE_UNIX;
- else if ((tcon->ses->capabilities &
- tcon->ses->server->vals->cap_nt_find) == 0)
- srchinf->info_level = SMB_FIND_FILE_INFO_STANDARD;
- else if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SERVER_INUM)
- srchinf->info_level = SMB_FIND_FILE_ID_FULL_DIR_INFO;
- else /* no srvino useful for fallback to some netapp */
- srchinf->info_level = SMB_FIND_FILE_DIRECTORY_INFO;
-
- srchflgs = CIFS_SEARCH_CLOSE_ALWAYS |
- CIFS_SEARCH_CLOSE_AT_END |
- CIFS_SEARCH_BACKUP_SEARCH;
-
- rc = CIFSFindFirst(xid, tcon, full_path,
- cifs_sb, NULL, srchflgs, srchinf, false);
- if (!rc) {
- data = (FILE_ALL_INFO *)srchinf->srch_entries_start;
+ cifs_dir_info_to_fattr(&fattr, fdi, cifs_sb);
+ fattr.cf_uniqueid = le64_to_cpu(si->UniqueId);
+ /* uniqueid set, skip get inum step */
+ goto handle_mnt_opt;
+ } else {
+ /* nothing we can do, bail out */
+ goto out;
+ }
+ break;
+ default:
+ cifs_dbg(FYI, "%s: unhandled err rc %d\n", __func__, rc);
+ goto out;
+ }
- cifs_dir_info_to_fattr(&fattr,
- (FILE_DIRECTORY_INFO *)data, cifs_sb);
- fattr.cf_uniqueid = le64_to_cpu(
- ((SEARCH_ID_FULL_DIR_INFO *)data)->UniqueId);
+ /*
+ * 3. Get or update inode number (fattr.cf_uniqueid)
+ */
- cifs_buf_release(srchinf->ntwrk_buf_start);
- }
- kfree(srchinf);
- if (rc)
- goto cgii_exit;
- } else
- goto cgii_exit;
+ cifs_set_fattr_ino(xid, tcon, sb, inode, full_path, data, &fattr);
/*
- * If an inode wasn't passed in, then get the inode number
- *
- * Is an i_ino of zero legal? Can we use that to check if the server
- * supports returning inode numbers? Are there other sanity checks we
- * can use to ensure that the server is really filling in that field?
+ * 4. Tweak fattr based on mount options
*/
- if (*inode == NULL) {
- if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SERVER_INUM) {
- if (server->ops->get_srv_inum)
- tmprc = server->ops->get_srv_inum(xid,
- tcon, cifs_sb, full_path,
- &fattr.cf_uniqueid, data);
- if (tmprc) {
- cifs_dbg(FYI, "GetSrvInodeNum rc %d\n",
- tmprc);
- fattr.cf_uniqueid = iunique(sb, ROOT_I);
- cifs_autodisable_serverino(cifs_sb);
- } else if ((fattr.cf_uniqueid == 0) &&
- strlen(full_path) == 0) {
- /* some servers ret bad root ino ie 0 */
- cifs_dbg(FYI, "Invalid (0) inodenum\n");
- fattr.cf_flags |=
- CIFS_FATTR_FAKE_ROOT_INO;
- fattr.cf_uniqueid =
- simple_hashstr(tcon->treeName);
- }
- } else
- fattr.cf_uniqueid = iunique(sb, ROOT_I);
- } else {
- if ((cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SERVER_INUM)
- && server->ops->get_srv_inum) {
- /*
- * Pass a NULL tcon to ensure we don't make a round
- * trip to the server. This only works for SMB2+.
- */
- tmprc = server->ops->get_srv_inum(xid,
- NULL, cifs_sb, full_path,
- &fattr.cf_uniqueid, data);
- if (tmprc)
- fattr.cf_uniqueid = CIFS_I(*inode)->uniqueid;
- else if ((fattr.cf_uniqueid == 0) &&
- strlen(full_path) == 0) {
- /*
- * Reuse existing root inode num since
- * inum zero for root causes ls of . and .. to
- * not be returned
- */
- cifs_dbg(FYI, "Srv ret 0 inode num for root\n");
- fattr.cf_uniqueid = CIFS_I(*inode)->uniqueid;
- }
- } else
- fattr.cf_uniqueid = CIFS_I(*inode)->uniqueid;
- }
+handle_mnt_opt:
/* query for SFU type info if supported and needed */
if (fattr.cf_cifsattrs & ATTR_SYSTEM &&
cifs_sb->mnt_cifs_flags & CIFS_MOUNT_UNX_EMUL) {
@@ -900,8 +962,8 @@ cifs_get_inode_info(struct inode **inode, const char *full_path,
full_path, fid);
if (rc) {
cifs_dbg(FYI, "%s: Get mode from SID failed. rc=%d\n",
- __func__, rc);
- goto cgii_exit;
+ __func__, rc);
+ goto out;
}
} else if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_CIFS_ACL) {
rc = cifs_acl_to_fattr(cifs_sb, &fattr, *inode, false,
@@ -909,7 +971,7 @@ cifs_get_inode_info(struct inode **inode, const char *full_path,
if (rc) {
cifs_dbg(FYI, "%s: Getting ACL failed with error: %d\n",
__func__, rc);
- goto cgii_exit;
+ goto out;
}
}
@@ -925,6 +987,10 @@ cifs_get_inode_info(struct inode **inode, const char *full_path,
cifs_dbg(FYI, "check_mf_symlink: %d\n", tmprc);
}
+ /*
+ * 5. Update inode with final fattr data
+ */
+
if (!*inode) {
*inode = cifs_iget(sb, &fattr);
if (!*inode)
@@ -937,7 +1003,7 @@ cifs_get_inode_info(struct inode **inode, const char *full_path,
CIFS_I(*inode)->uniqueid != fattr.cf_uniqueid)) {
CIFS_I(*inode)->time = 0; /* force reval */
rc = -ESTALE;
- goto cgii_exit;
+ goto out;
}
/* if filetype is different, return error */
@@ -945,18 +1011,15 @@ cifs_get_inode_info(struct inode **inode, const char *full_path,
(fattr.cf_mode & S_IFMT))) {
CIFS_I(*inode)->time = 0; /* force reval */
rc = -ESTALE;
- goto cgii_exit;
+ goto out;
}
cifs_fattr_to_inode(*inode, &fattr);
}
-
-cgii_exit:
- if ((*inode) && ((*inode)->i_ino == 0))
- cifs_dbg(FYI, "inode number of zero returned\n");
-
- kfree(buf);
+out:
+ cifs_buf_release(smb1_backup_rsp_buf);
cifs_put_tlink(tlink);
+ kfree(tmp_data);
return rc;
}
@@ -2475,9 +2538,9 @@ cifs_setattr_nounix(struct dentry *direntry, struct iattr *attrs)
rc = tcon->ses->server->ops->flush(xid, tcon, &wfile->fid);
cifsFileInfo_put(wfile);
if (rc)
- return rc;
+ goto cifs_setattr_exit;
} else if (rc != -EBADF)
- return rc;
+ goto cifs_setattr_exit;
else
rc = 0;
}
diff --git a/fs/cifs/misc.c b/fs/cifs/misc.c
index 5ad83bdb9bea..40ca394fd5de 100644
--- a/fs/cifs/misc.c
+++ b/fs/cifs/misc.c
@@ -488,21 +488,10 @@ is_valid_oplock_break(char *buffer, struct TCP_Server_Info *srv)
set_bit(CIFS_INODE_PENDING_OPLOCK_BREAK,
&pCifsInode->flags);
- /*
- * Set flag if the server downgrades the oplock
- * to L2 else clear.
- */
- if (pSMB->OplockLevel)
- set_bit(
- CIFS_INODE_DOWNGRADE_OPLOCK_TO_L2,
- &pCifsInode->flags);
- else
- clear_bit(
- CIFS_INODE_DOWNGRADE_OPLOCK_TO_L2,
- &pCifsInode->flags);
-
- cifs_queue_oplock_break(netfile);
+ netfile->oplock_epoch = 0;
+ netfile->oplock_level = pSMB->OplockLevel;
netfile->oplock_break_cancelled = false;
+ cifs_queue_oplock_break(netfile);
spin_unlock(&tcon->open_file_lock);
spin_unlock(&cifs_tcp_ses_lock);
diff --git a/fs/cifs/sess.c b/fs/cifs/sess.c
index 85bd644f9773..fb3bdc44775c 100644
--- a/fs/cifs/sess.c
+++ b/fs/cifs/sess.c
@@ -31,6 +31,231 @@
#include <linux/utsname.h>
#include <linux/slab.h>
#include "cifs_spnego.h"
+#include "smb2proto.h"
+
+bool
+is_server_using_iface(struct TCP_Server_Info *server,
+ struct cifs_server_iface *iface)
+{
+ struct sockaddr_in *i4 = (struct sockaddr_in *)&iface->sockaddr;
+ struct sockaddr_in6 *i6 = (struct sockaddr_in6 *)&iface->sockaddr;
+ struct sockaddr_in *s4 = (struct sockaddr_in *)&server->dstaddr;
+ struct sockaddr_in6 *s6 = (struct sockaddr_in6 *)&server->dstaddr;
+
+ if (server->dstaddr.ss_family != iface->sockaddr.ss_family)
+ return false;
+ if (server->dstaddr.ss_family == AF_INET) {
+ if (s4->sin_addr.s_addr != i4->sin_addr.s_addr)
+ return false;
+ } else if (server->dstaddr.ss_family == AF_INET6) {
+ if (memcmp(&s6->sin6_addr, &i6->sin6_addr,
+ sizeof(i6->sin6_addr)) != 0)
+ return false;
+ } else {
+ /* unknown family.. */
+ return false;
+ }
+ return true;
+}
+
+bool is_ses_using_iface(struct cifs_ses *ses, struct cifs_server_iface *iface)
+{
+ int i;
+
+ for (i = 0; i < ses->chan_count; i++) {
+ if (is_server_using_iface(ses->chans[i].server, iface))
+ return true;
+ }
+ return false;
+}
+
+/* returns number of channels added */
+int cifs_try_adding_channels(struct cifs_ses *ses)
+{
+ int old_chan_count = ses->chan_count;
+ int left = ses->chan_max - ses->chan_count;
+ int i = 0;
+ int rc = 0;
+ int tries = 0;
+
+ if (left <= 0) {
+ cifs_dbg(FYI,
+ "ses already at max_channels (%zu), nothing to open\n",
+ ses->chan_max);
+ return 0;
+ }
+
+ if (ses->server->dialect < SMB30_PROT_ID) {
+ cifs_dbg(VFS, "multichannel is not supported on this protocol version, use 3.0 or above\n");
+ return 0;
+ }
+
+ /*
+ * Keep connecting to same, fastest, iface for all channels as
+ * long as its RSS. Try next fastest one if not RSS or channel
+ * creation fails.
+ */
+ while (left > 0) {
+ struct cifs_server_iface *iface;
+
+ tries++;
+ if (tries > 3*ses->chan_max) {
+ cifs_dbg(FYI, "too many attempt at opening channels (%d channels left to open)\n",
+ left);
+ break;
+ }
+
+ iface = &ses->iface_list[i];
+ if (is_ses_using_iface(ses, iface) && !iface->rss_capable) {
+ i = (i+1) % ses->iface_count;
+ continue;
+ }
+
+ rc = cifs_ses_add_channel(ses, iface);
+ if (rc) {
+ cifs_dbg(FYI, "failed to open extra channel on iface#%d rc=%d\n",
+ i, rc);
+ i = (i+1) % ses->iface_count;
+ continue;
+ }
+
+ cifs_dbg(FYI, "successfully opened new channel on iface#%d\n",
+ i);
+ left--;
+ }
+
+ return ses->chan_count - old_chan_count;
+}
+
+int
+cifs_ses_add_channel(struct cifs_ses *ses, struct cifs_server_iface *iface)
+{
+ struct cifs_chan *chan;
+ struct smb_vol vol = {NULL};
+ static const char unc_fmt[] = "\\%s\\foo";
+ char unc[sizeof(unc_fmt)+SERVER_NAME_LEN_WITH_NULL] = {0};
+ struct sockaddr_in *ipv4 = (struct sockaddr_in *)&iface->sockaddr;
+ struct sockaddr_in6 *ipv6 = (struct sockaddr_in6 *)&iface->sockaddr;
+ int rc;
+ unsigned int xid = get_xid();
+
+ cifs_dbg(FYI, "adding channel to ses %p (speed:%zu bps rdma:%s ",
+ ses, iface->speed, iface->rdma_capable ? "yes" : "no");
+ if (iface->sockaddr.ss_family == AF_INET)
+ cifs_dbg(FYI, "ip:%pI4)\n", &ipv4->sin_addr);
+ else
+ cifs_dbg(FYI, "ip:%pI6)\n", &ipv6->sin6_addr);
+
+ /*
+ * Setup a smb_vol with mostly the same info as the existing
+ * session and overwrite it with the requested iface data.
+ *
+ * We need to setup at least the fields used for negprot and
+ * sesssetup.
+ *
+ * We only need the volume here, so we can reuse memory from
+ * the session and server without caring about memory
+ * management.
+ */
+
+ /* Always make new connection for now (TODO?) */
+ vol.nosharesock = true;
+
+ /* Auth */
+ vol.domainauto = ses->domainAuto;
+ vol.domainname = ses->domainName;
+ vol.username = ses->user_name;
+ vol.password = ses->password;
+ vol.sectype = ses->sectype;
+ vol.sign = ses->sign;
+
+ /* UNC and paths */
+ /* XXX: Use ses->server->hostname? */
+ sprintf(unc, unc_fmt, ses->serverName);
+ vol.UNC = unc;
+ vol.prepath = "";
+
+ /* Re-use same version as master connection */
+ vol.vals = ses->server->vals;
+ vol.ops = ses->server->ops;
+
+ vol.noblocksnd = ses->server->noblocksnd;
+ vol.noautotune = ses->server->noautotune;
+ vol.sockopt_tcp_nodelay = ses->server->tcp_nodelay;
+ vol.echo_interval = ses->server->echo_interval / HZ;
+
+ /*
+ * This will be used for encoding/decoding user/domain/pw
+ * during sess setup auth.
+ *
+ * XXX: We use the default for simplicity but the proper way
+ * would be to use the one that ses used, which is not
+ * stored. This might break when dealing with non-ascii
+ * strings.
+ */
+ vol.local_nls = load_nls_default();
+
+ /* Use RDMA if possible */
+ vol.rdma = iface->rdma_capable;
+ memcpy(&vol.dstaddr, &iface->sockaddr, sizeof(struct sockaddr_storage));
+
+ /* reuse master con client guid */
+ memcpy(&vol.client_guid, ses->server->client_guid,
+ SMB2_CLIENT_GUID_SIZE);
+ vol.use_client_guid = true;
+
+ mutex_lock(&ses->session_mutex);
+
+ chan = &ses->chans[ses->chan_count];
+ chan->server = cifs_get_tcp_session(&vol);
+ if (IS_ERR(chan->server)) {
+ rc = PTR_ERR(chan->server);
+ chan->server = NULL;
+ goto out;
+ }
+
+ /*
+ * We need to allocate the server crypto now as we will need
+ * to sign packets before we generate the channel signing key
+ * (we sign with the session key)
+ */
+ rc = smb311_crypto_shash_allocate(chan->server);
+ if (rc) {
+ cifs_dbg(VFS, "%s: crypto alloc failed\n", __func__);
+ goto out;
+ }
+
+ ses->binding = true;
+ rc = cifs_negotiate_protocol(xid, ses);
+ if (rc)
+ goto out;
+
+ rc = cifs_setup_session(xid, ses, vol.local_nls);
+ if (rc)
+ goto out;
+
+ /* success, put it on the list
+ * XXX: sharing ses between 2 tcp server is not possible, the
+ * way "internal" linked lists works in linux makes element
+ * only able to belong to one list
+ *
+ * the binding session is already established so the rest of
+ * the code should be able to look it up, no need to add the
+ * ses to the new server.
+ */
+
+ ses->chan_count++;
+ atomic_set(&ses->chan_seq, 0);
+out:
+ ses->binding = false;
+ mutex_unlock(&ses->session_mutex);
+
+ if (rc && chan->server)
+ cifs_put_tcp_session(chan->server, 0);
+ unload_nls(vol.local_nls);
+
+ return rc;
+}
static __u32 cifs_ssetup_hdr(struct cifs_ses *ses, SESSION_SETUP_ANDX *pSMB)
{
@@ -342,6 +567,7 @@ int decode_ntlmssp_challenge(char *bcc_ptr, int blob_len,
void build_ntlmssp_negotiate_blob(unsigned char *pbuffer,
struct cifs_ses *ses)
{
+ struct TCP_Server_Info *server = cifs_ses_server(ses);
NEGOTIATE_MESSAGE *sec_blob = (NEGOTIATE_MESSAGE *)pbuffer;
__u32 flags;
@@ -354,9 +580,9 @@ void build_ntlmssp_negotiate_blob(unsigned char *pbuffer,
NTLMSSP_NEGOTIATE_128 | NTLMSSP_NEGOTIATE_UNICODE |
NTLMSSP_NEGOTIATE_NTLM | NTLMSSP_NEGOTIATE_EXTENDED_SEC |
NTLMSSP_NEGOTIATE_SEAL;
- if (ses->server->sign)
+ if (server->sign)
flags |= NTLMSSP_NEGOTIATE_SIGN;
- if (!ses->server->session_estab || ses->ntlmssp->sesskey_per_smbsess)
+ if (!server->session_estab || ses->ntlmssp->sesskey_per_smbsess)
flags |= NTLMSSP_NEGOTIATE_KEY_XCH;
sec_blob->NegotiateFlags = cpu_to_le32(flags);
diff --git a/fs/cifs/smb1ops.c b/fs/cifs/smb1ops.c
index b7421a096319..d70a2bb062df 100644
--- a/fs/cifs/smb1ops.c
+++ b/fs/cifs/smb1ops.c
@@ -171,6 +171,9 @@ cifs_get_next_mid(struct TCP_Server_Info *server)
/* we do not want to loop forever */
last_mid = cur_mid;
cur_mid++;
+ /* avoid 0xFFFF MID */
+ if (cur_mid == 0xffff)
+ cur_mid++;
/*
* This nested loop looks more expensive than it is.
@@ -366,12 +369,10 @@ coalesce_t2(char *second_buf, struct smb_hdr *target_hdr)
static void
cifs_downgrade_oplock(struct TCP_Server_Info *server,
- struct cifsInodeInfo *cinode, bool set_level2)
+ struct cifsInodeInfo *cinode, __u32 oplock,
+ unsigned int epoch, bool *purge_cache)
{
- if (set_level2)
- cifs_set_oplock_level(cinode, OPLOCK_READ);
- else
- cifs_set_oplock_level(cinode, 0);
+ cifs_set_oplock_level(cinode, oplock);
}
static bool
diff --git a/fs/cifs/smb2file.c b/fs/cifs/smb2file.c
index e6a1fc72018f..8b0b512c5792 100644
--- a/fs/cifs/smb2file.c
+++ b/fs/cifs/smb2file.c
@@ -145,7 +145,7 @@ smb2_unlock_range(struct cifsFileInfo *cfile, struct file_lock *flock,
cur = buf;
- down_write(&cinode->lock_sem);
+ cifs_down_write(&cinode->lock_sem);
list_for_each_entry_safe(li, tmp, &cfile->llist->locks, llist) {
if (flock->fl_start > li->offset ||
(flock->fl_start + length) <
diff --git a/fs/cifs/smb2misc.c b/fs/cifs/smb2misc.c
index e311f58dc1c8..0516fc482d43 100644
--- a/fs/cifs/smb2misc.c
+++ b/fs/cifs/smb2misc.c
@@ -29,6 +29,7 @@
#include "cifs_unicode.h"
#include "smb2status.h"
#include "smb2glob.h"
+#include "nterr.h"
static int
check_smb2_hdr(struct smb2_sync_hdr *shdr, __u64 mid)
@@ -249,16 +250,10 @@ smb2_check_message(char *buf, unsigned int len, struct TCP_Server_Info *srvr)
* of junk. Other servers match RFC1001 len to actual
* SMB2/SMB3 frame length (header + smb2 response specific data)
* Some windows servers also pad up to 8 bytes when compounding.
- * If pad is longer than eight bytes, log the server behavior
- * (once), since may indicate a problem but allow it and continue
- * since the frame is parseable.
*/
- if (clc_len < len) {
- pr_warn_once(
- "srv rsp padded more than expected. Length %d not %d for cmd:%d mid:%llu\n",
- len, clc_len, command, mid);
+ if (clc_len < len)
return 0;
- }
+
pr_warn_once(
"srv rsp too short, len %d not %d. cmd:%d mid:%llu\n",
len, clc_len, command, mid);
@@ -534,7 +529,7 @@ smb2_tcon_has_lease(struct cifs_tcon *tcon, struct smb2_lease_break *rsp,
cifs_dbg(FYI, "found in the open list\n");
cifs_dbg(FYI, "lease key match, lease break 0x%x\n",
- le32_to_cpu(rsp->NewLeaseState));
+ lease_state);
if (ack_req)
cfile->oplock_break_cancelled = false;
@@ -543,17 +538,8 @@ smb2_tcon_has_lease(struct cifs_tcon *tcon, struct smb2_lease_break *rsp,
set_bit(CIFS_INODE_PENDING_OPLOCK_BREAK, &cinode->flags);
- /*
- * Set or clear flags depending on the lease state being READ.
- * HANDLE caching flag should be added when the client starts
- * to defer closing remote file handles with HANDLE leases.
- */
- if (lease_state & SMB2_LEASE_READ_CACHING_HE)
- set_bit(CIFS_INODE_DOWNGRADE_OPLOCK_TO_L2,
- &cinode->flags);
- else
- clear_bit(CIFS_INODE_DOWNGRADE_OPLOCK_TO_L2,
- &cinode->flags);
+ cfile->oplock_epoch = le16_to_cpu(rsp->Epoch);
+ cfile->oplock_level = lease_state;
cifs_queue_oplock_break(cfile);
kfree(lw);
@@ -576,7 +562,7 @@ smb2_tcon_has_lease(struct cifs_tcon *tcon, struct smb2_lease_break *rsp,
cifs_dbg(FYI, "found in the pending open list\n");
cifs_dbg(FYI, "lease key match, lease break 0x%x\n",
- le32_to_cpu(rsp->NewLeaseState));
+ lease_state);
open->oplock = lease_state;
}
@@ -673,10 +659,10 @@ smb2_is_valid_oplock_break(char *buffer, struct TCP_Server_Info *server)
spin_lock(&cifs_tcp_ses_lock);
list_for_each(tmp, &server->smb_ses_list) {
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);
- cifs_stats_inc(&tcon->stats.cifs_stats.num_oplock_brks);
spin_lock(&tcon->open_file_lock);
list_for_each(tmp2, &tcon->openFileList) {
cfile = list_entry(tmp2, struct cifsFileInfo,
@@ -688,6 +674,8 @@ smb2_is_valid_oplock_break(char *buffer, struct TCP_Server_Info *server)
continue;
cifs_dbg(FYI, "file id match, oplock break\n");
+ cifs_stats_inc(
+ &tcon->stats.cifs_stats.num_oplock_brks);
cinode = CIFS_I(d_inode(cfile->dentry));
spin_lock(&cfile->file_info_lock);
if (!CIFS_CACHE_WRITE(cinode) &&
@@ -699,18 +687,9 @@ smb2_is_valid_oplock_break(char *buffer, struct TCP_Server_Info *server)
set_bit(CIFS_INODE_PENDING_OPLOCK_BREAK,
&cinode->flags);
- /*
- * Set flag if the server downgrades the oplock
- * to L2 else clear.
- */
- if (rsp->OplockLevel)
- set_bit(
- CIFS_INODE_DOWNGRADE_OPLOCK_TO_L2,
- &cinode->flags);
- else
- clear_bit(
- CIFS_INODE_DOWNGRADE_OPLOCK_TO_L2,
- &cinode->flags);
+ cfile->oplock_epoch = 0;
+ cfile->oplock_level = rsp->OplockLevel;
+
spin_unlock(&cfile->file_info_lock);
cifs_queue_oplock_break(cfile);
@@ -720,9 +699,6 @@ smb2_is_valid_oplock_break(char *buffer, struct TCP_Server_Info *server)
return true;
}
spin_unlock(&tcon->open_file_lock);
- spin_unlock(&cifs_tcp_ses_lock);
- cifs_dbg(FYI, "No matching file for oplock break\n");
- return true;
}
}
spin_unlock(&cifs_tcp_ses_lock);
@@ -735,45 +711,98 @@ smb2_cancelled_close_fid(struct work_struct *work)
{
struct close_cancelled_open *cancelled = container_of(work,
struct close_cancelled_open, work);
+ struct cifs_tcon *tcon = cancelled->tcon;
+ int rc;
- cifs_dbg(VFS, "Close unmatched open\n");
+ if (cancelled->mid)
+ cifs_tcon_dbg(VFS, "Close unmatched open for MID:%llx\n",
+ cancelled->mid);
+ else
+ cifs_tcon_dbg(VFS, "Close interrupted close\n");
- SMB2_close(0, cancelled->tcon, cancelled->fid.persistent_fid,
- cancelled->fid.volatile_fid);
- cifs_put_tcon(cancelled->tcon);
+ rc = SMB2_close(0, tcon, cancelled->fid.persistent_fid,
+ cancelled->fid.volatile_fid);
+ if (rc)
+ cifs_tcon_dbg(VFS, "Close cancelled mid failed rc:%d\n", rc);
+
+ cifs_put_tcon(tcon);
kfree(cancelled);
}
+/*
+ * Caller should already has an extra reference to @tcon
+ * This function is used to queue work to close a handle to prevent leaks
+ * on the server.
+ * We handle two cases. If an open was interrupted after we sent the
+ * SMB2_CREATE to the server but before we processed the reply, and second
+ * if a close was interrupted before we sent the SMB2_CLOSE to the server.
+ */
+static int
+__smb2_handle_cancelled_cmd(struct cifs_tcon *tcon, __u16 cmd, __u64 mid,
+ __u64 persistent_fid, __u64 volatile_fid)
+{
+ struct close_cancelled_open *cancelled;
+
+ cancelled = kzalloc(sizeof(*cancelled), GFP_KERNEL);
+ if (!cancelled)
+ return -ENOMEM;
+
+ cancelled->fid.persistent_fid = persistent_fid;
+ cancelled->fid.volatile_fid = volatile_fid;
+ cancelled->tcon = tcon;
+ cancelled->cmd = cmd;
+ cancelled->mid = mid;
+ INIT_WORK(&cancelled->work, smb2_cancelled_close_fid);
+ WARN_ON(queue_work(cifsiod_wq, &cancelled->work) == false);
+
+ return 0;
+}
+
+int
+smb2_handle_cancelled_close(struct cifs_tcon *tcon, __u64 persistent_fid,
+ __u64 volatile_fid)
+{
+ int rc;
+
+ cifs_dbg(FYI, "%s: tc_count=%d\n", __func__, tcon->tc_count);
+ spin_lock(&cifs_tcp_ses_lock);
+ tcon->tc_count++;
+ spin_unlock(&cifs_tcp_ses_lock);
+
+ rc = __smb2_handle_cancelled_cmd(tcon, SMB2_CLOSE_HE, 0,
+ persistent_fid, volatile_fid);
+ if (rc)
+ cifs_put_tcon(tcon);
+
+ return rc;
+}
+
int
smb2_handle_cancelled_mid(char *buffer, struct TCP_Server_Info *server)
{
struct smb2_sync_hdr *sync_hdr = (struct smb2_sync_hdr *)buffer;
struct smb2_create_rsp *rsp = (struct smb2_create_rsp *)buffer;
struct cifs_tcon *tcon;
- struct close_cancelled_open *cancelled;
+ int rc;
if (sync_hdr->Command != SMB2_CREATE ||
sync_hdr->Status != STATUS_SUCCESS)
return 0;
- cancelled = kzalloc(sizeof(*cancelled), GFP_KERNEL);
- if (!cancelled)
- return -ENOMEM;
-
tcon = smb2_find_smb_tcon(server, sync_hdr->SessionId,
sync_hdr->TreeId);
- if (!tcon) {
- kfree(cancelled);
+ if (!tcon)
return -ENOENT;
- }
- cancelled->fid.persistent_fid = rsp->PersistentFileId;
- cancelled->fid.volatile_fid = rsp->VolatileFileId;
- cancelled->tcon = tcon;
- INIT_WORK(&cancelled->work, smb2_cancelled_close_fid);
- queue_work(cifsiod_wq, &cancelled->work);
+ rc = __smb2_handle_cancelled_cmd(tcon,
+ le16_to_cpu(sync_hdr->Command),
+ le64_to_cpu(sync_hdr->MessageId),
+ rsp->PersistentFileId,
+ rsp->VolatileFileId);
+ if (rc)
+ cifs_put_tcon(tcon);
- return 0;
+ return rc;
}
/**
@@ -788,23 +817,37 @@ 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 TCP_Server_Info *server = cifs_ses_server(ses);
- if (ses->server->tcpStatus == CifsGood) {
- /* skip non smb311 connections */
- if (ses->server->dialect != SMB311_PROT_ID)
- return 0;
+ hdr = (struct smb2_sync_hdr *)iov[0].iov_base;
+ /* neg prot are always taken */
+ if (hdr->Command == SMB2_NEGOTIATE)
+ goto ok;
- /* skip last sess setup response */
- hdr = (struct smb2_sync_hdr *)iov[0].iov_base;
- if (hdr->Flags & SMB2_FLAGS_SIGNED)
- return 0;
- }
+ /*
+ * If we process a command which wasn't a negprot it means the
+ * neg prot was already done, so the server dialect was set
+ * and we can test it. Preauth requires 3.1.1 for now.
+ */
+ if (server->dialect != SMB311_PROT_ID)
+ return 0;
+
+ if (hdr->Command != SMB2_SESSION_SETUP)
+ return 0;
+
+ /* skip last sess setup response */
+ if ((hdr->Flags & SMB2_FLAGS_SERVER_TO_REDIR)
+ && (hdr->Status == NT_STATUS_OK
+ || (hdr->Status !=
+ cpu_to_le32(NT_STATUS_MORE_PROCESSING_REQUIRED))))
+ return 0;
- rc = smb311_crypto_shash_allocate(ses->server);
+ok:
+ rc = smb311_crypto_shash_allocate(server);
if (rc)
return rc;
- d = ses->server->secmech.sdescsha512;
+ d = server->secmech.sdescsha512;
rc = crypto_shash_init(&d->shash);
if (rc) {
cifs_dbg(VFS, "%s: could not init sha512 shash\n", __func__);
diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c
index 4c0922596467..a7f328f79c6f 100644
--- a/fs/cifs/smb2ops.c
+++ b/fs/cifs/smb2ops.c
@@ -10,6 +10,7 @@
#include <linux/falloc.h>
#include <linux/scatterlist.h>
#include <linux/uuid.h>
+#include <linux/sort.h>
#include <crypto/aead.h>
#include "cifsglob.h"
#include "smb2pdu.h"
@@ -151,13 +152,7 @@ smb2_get_credits_field(struct TCP_Server_Info *server, const int optype)
static unsigned int
smb2_get_credits(struct mid_q_entry *mid)
{
- struct smb2_sync_hdr *shdr = (struct smb2_sync_hdr *)mid->resp_buf;
-
- if (mid->mid_state == MID_RESPONSE_RECEIVED
- || mid->mid_state == MID_RESPONSE_MALFORMED)
- return le16_to_cpu(shdr->CreditRequest);
-
- return 0;
+ return mid->credits_received;
}
static int
@@ -315,7 +310,7 @@ smb2_negotiate(const unsigned int xid, struct cifs_ses *ses)
{
int rc;
- ses->server->CurrentMid = 0;
+ cifs_ses_server(ses)->CurrentMid = 0;
rc = SMB2_negotiate(xid, ses);
/* BB we probably don't need to retry with modern servers */
if (rc == -EAGAIN)
@@ -558,6 +553,13 @@ out:
return rc;
}
+static int compare_iface(const void *ia, const void *ib)
+{
+ const struct cifs_server_iface *a = (struct cifs_server_iface *)ia;
+ const struct cifs_server_iface *b = (struct cifs_server_iface *)ib;
+
+ return a->speed == b->speed ? 0 : (a->speed > b->speed ? -1 : 1);
+}
static int
SMB3_request_interfaces(const unsigned int xid, struct cifs_tcon *tcon)
@@ -587,6 +589,9 @@ SMB3_request_interfaces(const unsigned int xid, struct cifs_tcon *tcon)
if (rc)
goto out;
+ /* sort interfaces from fastest to slowest */
+ sort(iface_list, iface_count, sizeof(*iface_list), compare_iface, NULL);
+
spin_lock(&ses->iface_lock);
kfree(ses->iface_list);
ses->iface_list = iface_list;
@@ -1402,15 +1407,10 @@ smb2_ioctl_query_info(const unsigned int xid,
if (smb3_encryption_required(tcon))
flags |= CIFS_TRANSFORM_REQ;
- buffer = kmalloc(qi.output_buffer_length, GFP_KERNEL);
- if (buffer == NULL)
- return -ENOMEM;
-
- if (copy_from_user(buffer, arg + sizeof(struct smb_query_info),
- qi.output_buffer_length)) {
- rc = -EFAULT;
- goto iqinf_exit;
- }
+ buffer = memdup_user(arg + sizeof(struct smb_query_info),
+ qi.output_buffer_length);
+ if (IS_ERR(buffer))
+ return PTR_ERR(buffer);
/* Open */
memset(&open_iov, 0, sizeof(open_iov));
@@ -1529,35 +1529,32 @@ smb2_ioctl_query_info(const unsigned int xid,
if (le32_to_cpu(io_rsp->OutputCount) < qi.input_buffer_length)
qi.input_buffer_length = le32_to_cpu(io_rsp->OutputCount);
if (qi.input_buffer_length > 0 &&
- le32_to_cpu(io_rsp->OutputOffset) + qi.input_buffer_length > rsp_iov[1].iov_len) {
- rc = -EFAULT;
- goto iqinf_exit;
- }
- if (copy_to_user(&pqi->input_buffer_length, &qi.input_buffer_length,
- sizeof(qi.input_buffer_length))) {
- rc = -EFAULT;
- goto iqinf_exit;
- }
+ le32_to_cpu(io_rsp->OutputOffset) + qi.input_buffer_length
+ > rsp_iov[1].iov_len)
+ goto e_fault;
+
+ if (copy_to_user(&pqi->input_buffer_length,
+ &qi.input_buffer_length,
+ sizeof(qi.input_buffer_length)))
+ goto e_fault;
+
if (copy_to_user((void __user *)pqi + sizeof(struct smb_query_info),
(const void *)io_rsp + le32_to_cpu(io_rsp->OutputOffset),
- qi.input_buffer_length)) {
- rc = -EFAULT;
- goto iqinf_exit;
- }
+ qi.input_buffer_length))
+ goto e_fault;
} else {
pqi = (struct smb_query_info __user *)arg;
qi_rsp = (struct smb2_query_info_rsp *)rsp_iov[1].iov_base;
if (le32_to_cpu(qi_rsp->OutputBufferLength) < qi.input_buffer_length)
qi.input_buffer_length = le32_to_cpu(qi_rsp->OutputBufferLength);
- if (copy_to_user(&pqi->input_buffer_length, &qi.input_buffer_length,
- sizeof(qi.input_buffer_length))) {
- rc = -EFAULT;
- goto iqinf_exit;
- }
- if (copy_to_user(pqi + 1, qi_rsp->Buffer, qi.input_buffer_length)) {
- rc = -EFAULT;
- goto iqinf_exit;
- }
+ if (copy_to_user(&pqi->input_buffer_length,
+ &qi.input_buffer_length,
+ sizeof(qi.input_buffer_length)))
+ goto e_fault;
+
+ if (copy_to_user(pqi + 1, qi_rsp->Buffer,
+ qi.input_buffer_length))
+ goto e_fault;
}
iqinf_exit:
@@ -1573,6 +1570,10 @@ smb2_ioctl_query_info(const unsigned int xid,
free_rsp_buf(resp_buftype[1], rsp_iov[1].iov_base);
free_rsp_buf(resp_buftype[2], rsp_iov[2].iov_base);
return rc;
+
+e_fault:
+ rc = -EFAULT;
+ goto iqinf_exit;
}
static ssize_t
@@ -3281,22 +3282,38 @@ static long smb3_fallocate(struct file *file, struct cifs_tcon *tcon, int mode,
static void
smb2_downgrade_oplock(struct TCP_Server_Info *server,
- struct cifsInodeInfo *cinode, bool set_level2)
+ struct cifsInodeInfo *cinode, __u32 oplock,
+ unsigned int epoch, bool *purge_cache)
{
- if (set_level2)
- server->ops->set_oplock_level(cinode, SMB2_OPLOCK_LEVEL_II,
- 0, NULL);
- else
- server->ops->set_oplock_level(cinode, 0, 0, NULL);
+ server->ops->set_oplock_level(cinode, oplock, 0, NULL);
}
static void
-smb21_downgrade_oplock(struct TCP_Server_Info *server,
- struct cifsInodeInfo *cinode, bool set_level2)
+smb21_set_oplock_level(struct cifsInodeInfo *cinode, __u32 oplock,
+ unsigned int epoch, bool *purge_cache);
+
+static void
+smb3_downgrade_oplock(struct TCP_Server_Info *server,
+ struct cifsInodeInfo *cinode, __u32 oplock,
+ unsigned int epoch, bool *purge_cache)
{
- server->ops->set_oplock_level(cinode,
- set_level2 ? SMB2_LEASE_READ_CACHING_HE :
- 0, 0, NULL);
+ unsigned int old_state = cinode->oplock;
+ unsigned int old_epoch = cinode->epoch;
+ unsigned int new_state;
+
+ if (epoch > old_epoch) {
+ smb21_set_oplock_level(cinode, oplock, 0, NULL);
+ cinode->epoch = epoch;
+ }
+
+ new_state = cinode->oplock;
+ *purge_cache = false;
+
+ if ((old_state & CIFS_CACHE_READ_FLG) != 0 &&
+ (new_state & CIFS_CACHE_READ_FLG) == 0)
+ *purge_cache = true;
+ else if (old_state == new_state && (epoch - old_epoch > 1))
+ *purge_cache = true;
}
static void
@@ -3598,14 +3615,16 @@ smb2_get_enc_key(struct TCP_Server_Info *server, __u64 ses_id, int enc, u8 *key)
u8 *ses_enc_key;
spin_lock(&cifs_tcp_ses_lock);
- list_for_each_entry(ses, &server->smb_ses_list, smb_ses_list) {
- if (ses->Suid != ses_id)
- continue;
- ses_enc_key = enc ? ses->smb3encryptionkey :
- ses->smb3decryptionkey;
- memcpy(key, ses_enc_key, SMB3_SIGN_KEY_SIZE);
- spin_unlock(&cifs_tcp_ses_lock);
- return 0;
+ list_for_each_entry(server, &cifs_tcp_ses_list, tcp_ses_list) {
+ list_for_each_entry(ses, &server->smb_ses_list, smb_ses_list) {
+ if (ses->Suid == ses_id) {
+ ses_enc_key = enc ? ses->smb3encryptionkey :
+ ses->smb3decryptionkey;
+ memcpy(key, ses_enc_key, SMB3_SIGN_KEY_SIZE);
+ spin_unlock(&cifs_tcp_ses_lock);
+ return 0;
+ }
+ }
}
spin_unlock(&cifs_tcp_ses_lock);
@@ -4084,6 +4103,7 @@ free_pages:
kfree(dw->ppages);
cifs_small_buf_release(dw->buf);
+ kfree(dw);
}
@@ -4157,7 +4177,7 @@ receive_encrypted_read(struct TCP_Server_Info *server, struct mid_q_entry **mid,
dw->server = server;
dw->ppages = pages;
dw->len = len;
- queue_work(cifsiod_wq, &dw->decrypt);
+ queue_work(decrypt_wq, &dw->decrypt);
*num_mids = 0; /* worker thread takes care of finding mid */
return -1;
}
@@ -4555,7 +4575,7 @@ struct smb_version_operations smb21_operations = {
.print_stats = smb2_print_stats,
.is_oplock_break = smb2_is_valid_oplock_break,
.handle_cancelled_mid = smb2_handle_cancelled_mid,
- .downgrade_oplock = smb21_downgrade_oplock,
+ .downgrade_oplock = smb2_downgrade_oplock,
.need_neg = smb2_need_neg,
.negotiate = smb2_negotiate,
.negotiate_wsize = smb2_negotiate_wsize,
@@ -4655,7 +4675,7 @@ struct smb_version_operations smb30_operations = {
.dump_share_caps = smb2_dump_share_caps,
.is_oplock_break = smb2_is_valid_oplock_break,
.handle_cancelled_mid = smb2_handle_cancelled_mid,
- .downgrade_oplock = smb21_downgrade_oplock,
+ .downgrade_oplock = smb3_downgrade_oplock,
.need_neg = smb2_need_neg,
.negotiate = smb2_negotiate,
.negotiate_wsize = smb3_negotiate_wsize,
@@ -4763,7 +4783,7 @@ struct smb_version_operations smb311_operations = {
.dump_share_caps = smb2_dump_share_caps,
.is_oplock_break = smb2_is_valid_oplock_break,
.handle_cancelled_mid = smb2_handle_cancelled_mid,
- .downgrade_oplock = smb21_downgrade_oplock,
+ .downgrade_oplock = smb3_downgrade_oplock,
.need_neg = smb2_need_neg,
.negotiate = smb2_negotiate,
.negotiate_wsize = smb3_negotiate_wsize,
diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c
index 05149862aea4..ed77f94dbf1d 100644
--- a/fs/cifs/smb2pdu.c
+++ b/fs/cifs/smb2pdu.c
@@ -252,7 +252,7 @@ smb2_reconnect(__le16 smb2_command, struct cifs_tcon *tcon)
if (tcon == NULL)
return 0;
- if (smb2_command == SMB2_TREE_CONNECT || smb2_command == SMB2_IOCTL)
+ if (smb2_command == SMB2_TREE_CONNECT)
return 0;
if (tcon->tidStatus == CifsExiting) {
@@ -426,16 +426,9 @@ fill_small_buf(__le16 smb2_command, struct cifs_tcon *tcon, void *buf,
* SMB information in the SMB header. If the return code is zero, this
* function must have filled in request_buf pointer.
*/
-static int
-smb2_plain_req_init(__le16 smb2_command, struct cifs_tcon *tcon,
- void **request_buf, unsigned int *total_len)
+static int __smb2_plain_req_init(__le16 smb2_command, struct cifs_tcon *tcon,
+ void **request_buf, unsigned int *total_len)
{
- int rc;
-
- rc = smb2_reconnect(smb2_command, tcon);
- if (rc)
- return rc;
-
/* BB eventually switch this to SMB2 specific small buf size */
if (smb2_command == SMB2_SET_INFO)
*request_buf = cifs_buf_get();
@@ -456,7 +449,31 @@ smb2_plain_req_init(__le16 smb2_command, struct cifs_tcon *tcon,
cifs_stats_inc(&tcon->num_smbs_sent);
}
- return rc;
+ return 0;
+}
+
+static int smb2_plain_req_init(__le16 smb2_command, struct cifs_tcon *tcon,
+ void **request_buf, unsigned int *total_len)
+{
+ int rc;
+
+ rc = smb2_reconnect(smb2_command, tcon);
+ if (rc)
+ return rc;
+
+ return __smb2_plain_req_init(smb2_command, tcon, request_buf,
+ total_len);
+}
+
+static int smb2_ioctl_req_init(u32 opcode, struct cifs_tcon *tcon,
+ void **request_buf, unsigned int *total_len)
+{
+ /* Skip reconnect only for FSCTL_VALIDATE_NEGOTIATE_INFO IOCTLs */
+ if (opcode == FSCTL_VALIDATE_NEGOTIATE_INFO) {
+ return __smb2_plain_req_init(SMB2_IOCTL, tcon, request_buf,
+ total_len);
+ }
+ return smb2_plain_req_init(SMB2_IOCTL, tcon, request_buf, total_len);
}
/* For explanation of negotiate contexts see MS-SMB2 section 2.2.3.1 */
@@ -791,7 +808,7 @@ SMB2_negotiate(const unsigned int xid, struct cifs_ses *ses)
struct kvec rsp_iov;
int rc = 0;
int resp_buftype;
- struct TCP_Server_Info *server = ses->server;
+ struct TCP_Server_Info *server = cifs_ses_server(ses);
int blob_offset, blob_length;
char *security_blob;
int flags = CIFS_NEG_OP;
@@ -813,7 +830,7 @@ SMB2_negotiate(const unsigned int xid, struct cifs_ses *ses)
memset(server->preauth_sha_hash, 0, SMB2_PREAUTH_HASH_SIZE);
memset(ses->preauth_sha_hash, 0, SMB2_PREAUTH_HASH_SIZE);
- if (strcmp(ses->server->vals->version_string,
+ if (strcmp(server->vals->version_string,
SMB3ANY_VERSION_STRING) == 0) {
req->Dialects[0] = cpu_to_le16(SMB30_PROT_ID);
req->Dialects[1] = cpu_to_le16(SMB302_PROT_ID);
@@ -829,7 +846,7 @@ SMB2_negotiate(const unsigned int xid, struct cifs_ses *ses)
total_len += 8;
} else {
/* otherwise send specific dialect */
- req->Dialects[0] = cpu_to_le16(ses->server->vals->protocol_id);
+ req->Dialects[0] = cpu_to_le16(server->vals->protocol_id);
req->DialectCount = cpu_to_le16(1);
total_len += 2;
}
@@ -1171,7 +1188,7 @@ SMB2_sess_alloc_buffer(struct SMB2_sess_data *sess_data)
int rc;
struct cifs_ses *ses = sess_data->ses;
struct smb2_sess_setup_req *req;
- struct TCP_Server_Info *server = ses->server;
+ struct TCP_Server_Info *server = cifs_ses_server(ses);
unsigned int total_len;
rc = smb2_plain_req_init(SMB2_SESSION_SETUP, NULL, (void **) &req,
@@ -1179,13 +1196,21 @@ SMB2_sess_alloc_buffer(struct SMB2_sess_data *sess_data)
if (rc)
return rc;
- /* First session, not a reauthenticate */
- req->sync_hdr.SessionId = 0;
-
- /* if reconnect, we need to send previous sess id, otherwise it is 0 */
- req->PreviousSessionId = sess_data->previous_session;
-
- req->Flags = 0; /* MBZ */
+ if (sess_data->ses->binding) {
+ req->sync_hdr.SessionId = sess_data->ses->Suid;
+ req->sync_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;
+ /*
+ * if reconnect, we need to send previous sess id
+ * otherwise it is 0
+ */
+ req->PreviousSessionId = 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);
@@ -1258,28 +1283,33 @@ SMB2_sess_establish_session(struct SMB2_sess_data *sess_data)
{
int rc = 0;
struct cifs_ses *ses = sess_data->ses;
+ struct TCP_Server_Info *server = cifs_ses_server(ses);
- mutex_lock(&ses->server->srv_mutex);
- if (ses->server->ops->generate_signingkey) {
- rc = ses->server->ops->generate_signingkey(ses);
+ mutex_lock(&server->srv_mutex);
+ if (server->ops->generate_signingkey) {
+ rc = server->ops->generate_signingkey(ses);
if (rc) {
cifs_dbg(FYI,
"SMB3 session key generation failed\n");
- mutex_unlock(&ses->server->srv_mutex);
+ mutex_unlock(&server->srv_mutex);
return rc;
}
}
- if (!ses->server->session_estab) {
- ses->server->sequence_number = 0x2;
- ses->server->session_estab = true;
+ if (!server->session_estab) {
+ server->sequence_number = 0x2;
+ server->session_estab = true;
}
- mutex_unlock(&ses->server->srv_mutex);
+ mutex_unlock(&server->srv_mutex);
cifs_dbg(FYI, "SMB2/3 session established successfully\n");
- spin_lock(&GlobalMid_Lock);
- ses->status = CifsGood;
- ses->need_reconnect = false;
- spin_unlock(&GlobalMid_Lock);
+ /* keep existing ses state if binding */
+ if (!ses->binding) {
+ spin_lock(&GlobalMid_Lock);
+ ses->status = CifsGood;
+ ses->need_reconnect = false;
+ spin_unlock(&GlobalMid_Lock);
+ }
+
return rc;
}
@@ -1317,16 +1347,19 @@ SMB2_auth_kerberos(struct SMB2_sess_data *sess_data)
goto out_put_spnego_key;
}
- ses->auth_key.response = kmemdup(msg->data, msg->sesskey_len,
- GFP_KERNEL);
- if (!ses->auth_key.response) {
- cifs_dbg(VFS,
- "Kerberos can't allocate (%u bytes) memory",
- msg->sesskey_len);
- rc = -ENOMEM;
- goto out_put_spnego_key;
+ /* keep session key if binding */
+ if (!ses->binding) {
+ ses->auth_key.response = kmemdup(msg->data, msg->sesskey_len,
+ GFP_KERNEL);
+ if (!ses->auth_key.response) {
+ cifs_dbg(VFS,
+ "Kerberos can't allocate (%u bytes) memory",
+ msg->sesskey_len);
+ rc = -ENOMEM;
+ goto out_put_spnego_key;
+ }
+ ses->auth_key.len = msg->sesskey_len;
}
- ses->auth_key.len = msg->sesskey_len;
sess_data->iov[1].iov_base = msg->data + msg->sesskey_len;
sess_data->iov[1].iov_len = msg->secblob_len;
@@ -1336,9 +1369,11 @@ SMB2_auth_kerberos(struct SMB2_sess_data *sess_data)
goto out_put_spnego_key;
rsp = (struct smb2_sess_setup_rsp *)sess_data->iov[0].iov_base;
- ses->Suid = rsp->sync_hdr.SessionId;
-
- ses->session_flags = le16_to_cpu(rsp->SessionFlags);
+ /* keep session id and flags if binding */
+ if (!ses->binding) {
+ ses->Suid = rsp->sync_hdr.SessionId;
+ ses->session_flags = le16_to_cpu(rsp->SessionFlags);
+ }
rc = SMB2_sess_establish_session(sess_data);
out_put_spnego_key:
@@ -1432,9 +1467,11 @@ SMB2_sess_auth_rawntlmssp_negotiate(struct SMB2_sess_data *sess_data)
cifs_dbg(FYI, "rawntlmssp session setup challenge phase\n");
-
- ses->Suid = rsp->sync_hdr.SessionId;
- ses->session_flags = le16_to_cpu(rsp->SessionFlags);
+ /* keep existing ses id and flags if binding */
+ if (!ses->binding) {
+ ses->Suid = rsp->sync_hdr.SessionId;
+ ses->session_flags = le16_to_cpu(rsp->SessionFlags);
+ }
out:
kfree(ntlmssp_blob);
@@ -1491,8 +1528,11 @@ SMB2_sess_auth_rawntlmssp_authenticate(struct SMB2_sess_data *sess_data)
rsp = (struct smb2_sess_setup_rsp *)sess_data->iov[0].iov_base;
- ses->Suid = rsp->sync_hdr.SessionId;
- ses->session_flags = le16_to_cpu(rsp->SessionFlags);
+ /* keep existing ses id and flags if binding */
+ if (!ses->binding) {
+ ses->Suid = rsp->sync_hdr.SessionId;
+ ses->session_flags = le16_to_cpu(rsp->SessionFlags);
+ }
rc = SMB2_sess_establish_session(sess_data);
out:
@@ -1509,7 +1549,7 @@ SMB2_select_sec(struct cifs_ses *ses, struct SMB2_sess_data *sess_data)
{
int type;
- type = smb2_select_sectype(ses->server, ses->sectype);
+ type = smb2_select_sectype(cifs_ses_server(ses), ses->sectype);
cifs_dbg(FYI, "sess setup type %d\n", type);
if (type == Unspecified) {
cifs_dbg(VFS,
@@ -1537,7 +1577,7 @@ SMB2_sess_setup(const unsigned int xid, struct cifs_ses *ses,
const struct nls_table *nls_cp)
{
int rc = 0;
- struct TCP_Server_Info *server = ses->server;
+ struct TCP_Server_Info *server = cifs_ses_server(ses);
struct SMB2_sess_data *sess_data;
cifs_dbg(FYI, "Session Setup\n");
@@ -1563,7 +1603,7 @@ SMB2_sess_setup(const unsigned int xid, struct cifs_ses *ses,
/*
* Initialize the session hash with the server one.
*/
- memcpy(ses->preauth_sha_hash, ses->server->preauth_sha_hash,
+ memcpy(ses->preauth_sha_hash, server->preauth_sha_hash,
SMB2_PREAUTH_HASH_SIZE);
while (sess_data->func)
@@ -1807,6 +1847,8 @@ SMB2_tdis(const unsigned int xid, struct cifs_tcon *tcon)
if ((tcon->need_reconnect) || (tcon->ses->need_reconnect))
return 0;
+ close_shroot(&tcon->crfid);
+
rc = smb2_plain_req_init(SMB2_TREE_DISCONNECT, tcon, (void **) &req,
&total_len);
if (rc)
@@ -2661,7 +2703,7 @@ SMB2_ioctl_init(struct cifs_tcon *tcon, struct smb_rqst *rqst,
int rc;
char *in_data_buf;
- rc = smb2_plain_req_init(SMB2_IOCTL, tcon, (void **) &req, &total_len);
+ rc = smb2_ioctl_req_init(opcode, tcon, (void **) &req, &total_len);
if (rc)
return rc;
@@ -2972,7 +3014,21 @@ int
SMB2_close(const unsigned int xid, struct cifs_tcon *tcon,
u64 persistent_fid, u64 volatile_fid)
{
- return SMB2_close_flags(xid, tcon, persistent_fid, volatile_fid, 0);
+ int rc;
+ int tmp_rc;
+
+ rc = SMB2_close_flags(xid, tcon, persistent_fid, volatile_fid, 0);
+
+ /* retry close in a worker thread if this one is interrupted */
+ if (rc == -EINTR) {
+ tmp_rc = smb2_handle_cancelled_close(tcon, persistent_fid,
+ volatile_fid);
+ if (tmp_rc)
+ cifs_dbg(VFS, "handle cancelled close fid 0x%llx returned error %d\n",
+ persistent_fid, tmp_rc);
+ }
+
+ return rc;
}
int
diff --git a/fs/cifs/smb2pdu.h b/fs/cifs/smb2pdu.h
index ea735d59c36e..f264e1d36fe1 100644
--- a/fs/cifs/smb2pdu.h
+++ b/fs/cifs/smb2pdu.h
@@ -838,6 +838,7 @@ struct create_durable_handle_reconnect_v2 {
struct create_context ccontext;
__u8 Name[8];
struct durable_reconnect_context_v2 dcontext;
+ __u8 Pad[4];
} __packed;
/* See MS-SMB2 2.2.13.2.5 */
@@ -1385,7 +1386,7 @@ struct smb2_oplock_break {
struct smb2_lease_break {
struct smb2_sync_hdr sync_hdr;
__le16 StructureSize; /* Must be 44 */
- __le16 Reserved;
+ __le16 Epoch;
__le32 Flags;
__u8 LeaseKey[16];
__le32 CurrentLeaseState;
diff --git a/fs/cifs/smb2proto.h b/fs/cifs/smb2proto.h
index 71b2930b8e0b..d21a5fcc8d06 100644
--- a/fs/cifs/smb2proto.h
+++ b/fs/cifs/smb2proto.h
@@ -46,7 +46,8 @@ extern int smb2_verify_signature(struct smb_rqst *, struct TCP_Server_Info *);
extern int smb2_check_receive(struct mid_q_entry *mid,
struct TCP_Server_Info *server, bool log_error);
extern struct mid_q_entry *smb2_setup_request(struct cifs_ses *ses,
- struct smb_rqst *rqst);
+ struct TCP_Server_Info *,
+ struct smb_rqst *rqst);
extern struct mid_q_entry *smb2_setup_async_request(
struct TCP_Server_Info *server, struct smb_rqst *rqst);
extern struct cifs_ses *smb2_find_smb_ses(struct TCP_Server_Info *server,
@@ -212,6 +213,9 @@ extern int SMB2_set_compression(const unsigned int xid, struct cifs_tcon *tcon,
extern int SMB2_oplock_break(const unsigned int xid, struct cifs_tcon *tcon,
const u64 persistent_fid, const u64 volatile_fid,
const __u8 oplock_level);
+extern int smb2_handle_cancelled_close(struct cifs_tcon *tcon,
+ __u64 persistent_fid,
+ __u64 volatile_fid);
extern int smb2_handle_cancelled_mid(char *buffer,
struct TCP_Server_Info *server);
void smb2_cancelled_close_fid(struct work_struct *work);
diff --git a/fs/cifs/smb2transport.c b/fs/cifs/smb2transport.c
index 148d7942c796..387c88704c52 100644
--- a/fs/cifs/smb2transport.c
+++ b/fs/cifs/smb2transport.c
@@ -98,6 +98,61 @@ err:
return rc;
}
+
+static
+int smb2_get_sign_key(__u64 ses_id, struct TCP_Server_Info *server, u8 *key)
+{
+ struct cifs_chan *chan;
+ struct cifs_ses *ses = NULL;
+ int i;
+ int rc = 0;
+
+ spin_lock(&cifs_tcp_ses_lock);
+
+ list_for_each_entry(server, &cifs_tcp_ses_list, tcp_ses_list) {
+ list_for_each_entry(ses, &server->smb_ses_list, smb_ses_list) {
+ if (ses->Suid == ses_id)
+ goto found;
+ }
+ }
+ cifs_server_dbg(VFS, "%s: Could not find session 0x%llx\n",
+ __func__, ses_id);
+ rc = -ENOENT;
+ goto out;
+
+found:
+ if (ses->binding) {
+ /*
+ * If we are in the process of binding a new channel
+ * to an existing session, use the master connection
+ * session key
+ */
+ memcpy(key, ses->smb3signingkey, SMB3_SIGN_KEY_SIZE);
+ goto out;
+ }
+
+ /*
+ * Otherwise, use the channel key.
+ */
+
+ for (i = 0; i < ses->chan_count; i++) {
+ chan = ses->chans + i;
+ if (chan->server == server) {
+ memcpy(key, chan->signkey, SMB3_SIGN_KEY_SIZE);
+ goto out;
+ }
+ }
+
+ cifs_dbg(VFS,
+ "%s: Could not find channel signing key for session 0x%llx\n",
+ __func__, ses_id);
+ rc = -ENOENT;
+
+out:
+ spin_unlock(&cifs_tcp_ses_lock);
+ return rc;
+}
+
static struct cifs_ses *
smb2_find_smb_ses_unlocked(struct TCP_Server_Info *server, __u64 ses_id)
{
@@ -328,21 +383,45 @@ generate_smb3signingkey(struct cifs_ses *ses,
{
int rc;
- rc = generate_key(ses, ptriplet->signing.label,
- ptriplet->signing.context, ses->smb3signingkey,
- SMB3_SIGN_KEY_SIZE);
- if (rc)
- return rc;
+ /*
+ * All channels use the same encryption/decryption keys but
+ * they have their own signing key.
+ *
+ * When we generate the keys, check if it is for a new channel
+ * (binding) in which case we only need to generate a signing
+ * key and store it in the channel as to not overwrite the
+ * master connection signing key stored in the session
+ */
- rc = generate_key(ses, ptriplet->encryption.label,
- ptriplet->encryption.context, ses->smb3encryptionkey,
- SMB3_SIGN_KEY_SIZE);
- if (rc)
- return rc;
+ if (ses->binding) {
+ rc = generate_key(ses, ptriplet->signing.label,
+ ptriplet->signing.context,
+ cifs_ses_binding_channel(ses)->signkey,
+ SMB3_SIGN_KEY_SIZE);
+ if (rc)
+ return rc;
+ } else {
+ rc = generate_key(ses, ptriplet->signing.label,
+ ptriplet->signing.context,
+ ses->smb3signingkey,
+ SMB3_SIGN_KEY_SIZE);
+ if (rc)
+ return rc;
- rc = generate_key(ses, ptriplet->decryption.label,
- ptriplet->decryption.context,
- ses->smb3decryptionkey, SMB3_SIGN_KEY_SIZE);
+ memcpy(ses->chans[0].signkey, ses->smb3signingkey,
+ SMB3_SIGN_KEY_SIZE);
+
+ rc = generate_key(ses, ptriplet->encryption.label,
+ ptriplet->encryption.context,
+ ses->smb3encryptionkey,
+ SMB3_SIGN_KEY_SIZE);
+ rc = generate_key(ses, ptriplet->decryption.label,
+ ptriplet->decryption.context,
+ ses->smb3decryptionkey,
+ SMB3_SIGN_KEY_SIZE);
+ if (rc)
+ return rc;
+ }
if (rc)
return rc;
@@ -431,21 +510,19 @@ smb3_calc_signature(struct smb_rqst *rqst, struct TCP_Server_Info *server)
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 cifs_ses *ses;
struct shash_desc *shash = &server->secmech.sdesccmacaes->shash;
struct smb_rqst drqst;
+ u8 key[SMB3_SIGN_KEY_SIZE];
- ses = smb2_find_smb_ses(server, shdr->SessionId);
- if (!ses) {
- cifs_server_dbg(VFS, "%s: Could not find session\n", __func__);
+ rc = smb2_get_sign_key(shdr->SessionId, server, key);
+ if (rc)
return 0;
- }
memset(smb3_signature, 0x0, SMB2_CMACAES_SIZE);
memset(shdr->Signature, 0x0, SMB2_SIGNATURE_SIZE);
rc = crypto_shash_setkey(server->secmech.cmacaes,
- ses->smb3signingkey, SMB2_CMACAES_SIZE);
+ key, SMB2_CMACAES_SIZE);
if (rc) {
cifs_server_dbg(VFS, "%s: Could not set key for cmac aes\n", __func__);
return rc;
@@ -494,16 +571,25 @@ static int
smb2_sign_rqst(struct smb_rqst *rqst, struct TCP_Server_Info *server)
{
int rc = 0;
- struct smb2_sync_hdr *shdr =
- (struct smb2_sync_hdr *)rqst->rq_iov[0].iov_base;
+ struct smb2_sync_hdr *shdr;
+ struct smb2_sess_setup_req *ssr;
+ bool is_binding;
+ bool is_signed;
- if (!(shdr->Flags & SMB2_FLAGS_SIGNED) ||
- server->tcpStatus == CifsNeedNegotiate)
- return rc;
+ shdr = (struct smb2_sync_hdr *)rqst->rq_iov[0].iov_base;
+ ssr = (struct smb2_sess_setup_req *)shdr;
+
+ is_binding = shdr->Command == SMB2_SESSION_SETUP &&
+ (ssr->Flags & SMB2_SESSION_REQ_FLAG_BINDING);
+ is_signed = shdr->Flags & SMB2_FLAGS_SIGNED;
- if (!server->session_estab) {
+ if (!is_signed)
+ return 0;
+ if (server->tcpStatus == CifsNeedNegotiate)
+ return 0;
+ if (!is_binding && !server->session_estab) {
strncpy(shdr->Signature, "BSRSPYL", 8);
- return rc;
+ return 0;
}
rc = server->ops->calc_signature(rqst, server);
@@ -610,18 +696,18 @@ smb2_mid_entry_alloc(const struct smb2_sync_hdr *shdr,
}
static int
-smb2_get_mid_entry(struct cifs_ses *ses, struct smb2_sync_hdr *shdr,
- struct mid_q_entry **mid)
+smb2_get_mid_entry(struct cifs_ses *ses, struct TCP_Server_Info *server,
+ struct smb2_sync_hdr *shdr, struct mid_q_entry **mid)
{
- if (ses->server->tcpStatus == CifsExiting)
+ if (server->tcpStatus == CifsExiting)
return -ENOENT;
- if (ses->server->tcpStatus == CifsNeedReconnect) {
+ if (server->tcpStatus == CifsNeedReconnect) {
cifs_dbg(FYI, "tcp session dead - return to caller to retry\n");
return -EAGAIN;
}
- if (ses->server->tcpStatus == CifsNeedNegotiate &&
+ if (server->tcpStatus == CifsNeedNegotiate &&
shdr->Command != SMB2_NEGOTIATE)
return -EAGAIN;
@@ -638,11 +724,11 @@ smb2_get_mid_entry(struct cifs_ses *ses, struct smb2_sync_hdr *shdr,
/* else ok - we are shutting down the session */
}
- *mid = smb2_mid_entry_alloc(shdr, ses->server);
+ *mid = smb2_mid_entry_alloc(shdr, server);
if (*mid == NULL)
return -ENOMEM;
spin_lock(&GlobalMid_Lock);
- list_add_tail(&(*mid)->qhead, &ses->server->pending_mid_q);
+ list_add_tail(&(*mid)->qhead, &server->pending_mid_q);
spin_unlock(&GlobalMid_Lock);
return 0;
@@ -675,24 +761,25 @@ smb2_check_receive(struct mid_q_entry *mid, struct TCP_Server_Info *server,
}
struct mid_q_entry *
-smb2_setup_request(struct cifs_ses *ses, struct smb_rqst *rqst)
+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 mid_q_entry *mid;
- smb2_seq_num_into_buf(ses->server, shdr);
+ smb2_seq_num_into_buf(server, shdr);
- rc = smb2_get_mid_entry(ses, shdr, &mid);
+ rc = smb2_get_mid_entry(ses, server, shdr, &mid);
if (rc) {
- revert_current_mid_from_hdr(ses->server, shdr);
+ revert_current_mid_from_hdr(server, shdr);
return ERR_PTR(rc);
}
- rc = smb2_sign_rqst(rqst, ses->server);
+ rc = smb2_sign_rqst(rqst, server);
if (rc) {
- revert_current_mid_from_hdr(ses->server, shdr);
+ revert_current_mid_from_hdr(server, shdr);
cifs_delete_mid(mid);
return ERR_PTR(rc);
}
diff --git a/fs/cifs/smbdirect.c b/fs/cifs/smbdirect.c
index 3c91fa97c9a8..5b1b97e9e0c9 100644
--- a/fs/cifs/smbdirect.c
+++ b/fs/cifs/smbdirect.c
@@ -1069,7 +1069,7 @@ static int smbd_post_send_data(
if (n_vec > SMBDIRECT_MAX_SGE) {
cifs_dbg(VFS, "Can't fit data to SGL, n_vec=%d\n", n_vec);
- return -ENOMEM;
+ return -EINVAL;
}
sg_init_table(sgl, n_vec);
@@ -1476,6 +1476,7 @@ void smbd_destroy(struct TCP_Server_Info *server)
info->transport_status = SMBD_DESTROYED;
destroy_workqueue(info->workqueue);
+ log_rdma_event(INFO, "rdma session destroyed\n");
kfree(info);
}
@@ -1505,8 +1506,9 @@ create_conn:
log_rdma_event(INFO, "creating rdma session\n");
server->smbd_conn = smbd_get_connection(
server, (struct sockaddr *) &server->dstaddr);
- log_rdma_event(INFO, "created rdma session info=%p\n",
- server->smbd_conn);
+
+ if (server->smbd_conn)
+ cifs_dbg(VFS, "RDMA transport re-established\n");
return server->smbd_conn ? 0 : -ENOENT;
}
@@ -1970,7 +1972,7 @@ read_rfc1002_done:
if (info->transport_status != SMBD_CONNECTED) {
log_read(ERR, "disconnected\n");
- return 0;
+ return -ECONNABORTED;
}
goto again;
@@ -2269,12 +2271,7 @@ static void smbd_mr_recovery_work(struct work_struct *work)
int rc;
list_for_each_entry(smbdirect_mr, &info->mr_list, list) {
- if (smbdirect_mr->state == MR_INVALIDATED)
- ib_dma_unmap_sg(
- info->id->device, smbdirect_mr->sgl,
- smbdirect_mr->sgl_count,
- smbdirect_mr->dir);
- else if (smbdirect_mr->state == MR_ERROR) {
+ if (smbdirect_mr->state == MR_ERROR) {
/* recover this MR entry */
rc = ib_dereg_mr(smbdirect_mr->mr);
@@ -2602,11 +2599,20 @@ int smbd_deregister_mr(struct smbd_mr *smbdirect_mr)
*/
smbdirect_mr->state = MR_INVALIDATED;
- /*
- * Schedule the work to do MR recovery for future I/Os
- * MR recovery is slow and we don't want it to block the current I/O
- */
- queue_work(info->workqueue, &info->mr_recovery_work);
+ if (smbdirect_mr->state == MR_INVALIDATED) {
+ ib_dma_unmap_sg(
+ info->id->device, smbdirect_mr->sgl,
+ smbdirect_mr->sgl_count,
+ smbdirect_mr->dir);
+ smbdirect_mr->state = MR_READY;
+ if (atomic_inc_return(&info->mr_ready_count) == 1)
+ wake_up_interruptible(&info->wait_mr);
+ } else
+ /*
+ * Schedule the work to do MR recovery for future I/Os MR
+ * recovery is slow and don't want it to block current I/O
+ */
+ queue_work(info->workqueue, &info->mr_recovery_work);
done:
if (atomic_dec_and_test(&info->mr_used_count))
diff --git a/fs/cifs/transport.c b/fs/cifs/transport.c
index 308ad0f495e1..3d2e11f85cba 100644
--- a/fs/cifs/transport.c
+++ b/fs/cifs/transport.c
@@ -86,29 +86,21 @@ AllocMidQEntry(const struct smb_hdr *smb_buffer, struct TCP_Server_Info *server)
static void _cifs_mid_q_entry_release(struct kref *refcount)
{
- struct mid_q_entry *mid = container_of(refcount, struct mid_q_entry,
- refcount);
-
- mempool_free(mid, cifs_mid_poolp);
-}
-
-void cifs_mid_q_entry_release(struct mid_q_entry *midEntry)
-{
- spin_lock(&GlobalMid_Lock);
- kref_put(&midEntry->refcount, _cifs_mid_q_entry_release);
- spin_unlock(&GlobalMid_Lock);
-}
-
-void
-DeleteMidQEntry(struct mid_q_entry *midEntry)
-{
+ struct mid_q_entry *midEntry =
+ container_of(refcount, struct mid_q_entry, refcount);
#ifdef CONFIG_CIFS_STATS2
__le16 command = midEntry->server->vals->lock_cmd;
__u16 smb_cmd = le16_to_cpu(midEntry->command);
unsigned long now;
unsigned long roundtrip_time;
- struct TCP_Server_Info *server = midEntry->server;
#endif
+ struct TCP_Server_Info *server = midEntry->server;
+
+ if (midEntry->resp_buf && (midEntry->mid_flags & MID_WAIT_CANCELLED) &&
+ midEntry->mid_state == MID_RESPONSE_RECEIVED &&
+ server->ops->handle_cancelled_mid)
+ server->ops->handle_cancelled_mid(midEntry->resp_buf, server);
+
midEntry->mid_state = MID_FREE;
atomic_dec(&midCount);
if (midEntry->large_buf)
@@ -166,6 +158,19 @@ DeleteMidQEntry(struct mid_q_entry *midEntry)
}
}
#endif
+
+ mempool_free(midEntry, cifs_mid_poolp);
+}
+
+void cifs_mid_q_entry_release(struct mid_q_entry *midEntry)
+{
+ spin_lock(&GlobalMid_Lock);
+ kref_put(&midEntry->refcount, _cifs_mid_q_entry_release);
+ spin_unlock(&GlobalMid_Lock);
+}
+
+void DeleteMidQEntry(struct mid_q_entry *midEntry)
+{
cifs_mid_q_entry_release(midEntry);
}
@@ -173,8 +178,10 @@ void
cifs_delete_mid(struct mid_q_entry *mid)
{
spin_lock(&GlobalMid_Lock);
- list_del_init(&mid->qhead);
- mid->mid_flags |= MID_DELETED;
+ if (!(mid->mid_flags & MID_DELETED)) {
+ list_del_init(&mid->qhead);
+ mid->mid_flags |= MID_DELETED;
+ }
spin_unlock(&GlobalMid_Lock);
DeleteMidQEntry(mid);
@@ -318,8 +325,11 @@ __smb_send_rqst(struct TCP_Server_Info *server, int num_rqst,
int val = 1;
__be32 rfc1002_marker;
- if (cifs_rdma_enabled(server) && server->smbd_conn) {
- rc = smbd_send(server, num_rqst, rqst);
+ if (cifs_rdma_enabled(server)) {
+ /* return -EAGAIN when connecting or reconnecting */
+ rc = -EAGAIN;
+ if (server->smbd_conn)
+ rc = smbd_send(server, num_rqst, rqst);
goto smbd_done;
}
@@ -872,7 +882,10 @@ cifs_sync_mid_result(struct mid_q_entry *mid, struct TCP_Server_Info *server)
rc = -EHOSTDOWN;
break;
default:
- list_del_init(&mid->qhead);
+ if (!(mid->mid_flags & MID_DELETED)) {
+ list_del_init(&mid->qhead);
+ mid->mid_flags |= MID_DELETED;
+ }
cifs_server_dbg(VFS, "%s: invalid mid state mid=%llu state=%d\n",
__func__, mid->mid, mid->mid_state);
rc = -EIO;
@@ -923,7 +936,8 @@ cifs_check_receive(struct mid_q_entry *mid, struct TCP_Server_Info *server,
}
struct mid_q_entry *
-cifs_setup_request(struct cifs_ses *ses, struct smb_rqst *rqst)
+cifs_setup_request(struct cifs_ses *ses, struct TCP_Server_Info *ignored,
+ struct smb_rqst *rqst)
{
int rc;
struct smb_hdr *hdr = (struct smb_hdr *)rqst->rq_iov[0].iov_base;
@@ -995,7 +1009,18 @@ compound_send_recv(const unsigned int xid, struct cifs_ses *ses,
return -EIO;
}
- server = ses->server;
+ if (!ses->binding) {
+ uint index = 0;
+
+ if (ses->chan_count > 1) {
+ index = (uint)atomic_inc_return(&ses->chan_seq);
+ index %= ses->chan_count;
+ }
+ server = ses->chans[index].server;
+ } else {
+ server = cifs_ses_server(ses);
+ }
+
if (server->tcpStatus == CifsExiting)
return -ENOENT;
@@ -1040,7 +1065,7 @@ compound_send_recv(const unsigned int xid, struct cifs_ses *ses,
}
for (i = 0; i < num_rqst; i++) {
- midQ[i] = server->ops->setup_request(ses, &rqst[i]);
+ midQ[i] = server->ops->setup_request(ses, server, &rqst[i]);
if (IS_ERR(midQ[i])) {
revert_current_mid(server, i);
for (j = 0; j < i; j++)
@@ -1115,8 +1140,8 @@ compound_send_recv(const unsigned int xid, struct cifs_ses *ses,
midQ[i]->mid, le16_to_cpu(midQ[i]->command));
send_cancel(server, &rqst[i], midQ[i]);
spin_lock(&GlobalMid_Lock);
+ midQ[i]->mid_flags |= MID_WAIT_CANCELLED;
if (midQ[i]->mid_state == MID_REQUEST_SUBMITTED) {
- midQ[i]->mid_flags |= MID_WAIT_CANCELLED;
midQ[i]->callback = cifs_cancelled_callback;
cancelled_mid[i] = true;
credits[i].value = 0;
@@ -1283,7 +1308,7 @@ SendReceive(const unsigned int xid, struct cifs_ses *ses,
rc = allocate_mid(ses, in_buf, &midQ);
if (rc) {
- mutex_unlock(&ses->server->srv_mutex);
+ mutex_unlock(&server->srv_mutex);
/* Update # of requests on wire to server */
add_credits(server, &credits, 0);
return rc;
diff --git a/fs/compat_binfmt_elf.c b/fs/compat_binfmt_elf.c
index b7f9ffa1d5f1..aaad4ca1217e 100644
--- a/fs/compat_binfmt_elf.c
+++ b/fs/compat_binfmt_elf.c
@@ -48,8 +48,8 @@
#define elf_prstatus compat_elf_prstatus
#define elf_prpsinfo compat_elf_prpsinfo
-#undef ns_to_timeval
-#define ns_to_timeval ns_to_old_timeval32
+#undef ns_to_kernel_old_timeval
+#define ns_to_kernel_old_timeval ns_to_old_timeval32
/*
* To use this file, asm/elf.h must define compat_elf_check_arch.
diff --git a/fs/compat_ioctl.c b/fs/compat_ioctl.c
index 62e530814cef..358ea2ecf36b 100644
--- a/fs/compat_ioctl.c
+++ b/fs/compat_ioctl.c
@@ -11,8 +11,6 @@
* ioctls.
*/
-#include <linux/joystick.h>
-
#include <linux/types.h>
#include <linux/compat.h>
#include <linux/kernel.h>
@@ -27,13 +25,9 @@
#include <linux/file.h>
#include <linux/ppp-ioctl.h>
#include <linux/if_pppox.h>
-#include <linux/mtio.h>
#include <linux/tty.h>
#include <linux/vt_kern.h>
-#include <linux/raw.h>
#include <linux/blkdev.h>
-#include <linux/rtc.h>
-#include <linux/pci.h>
#include <linux/serial.h>
#include <linux/ctype.h>
#include <linux/syscalls.h>
@@ -42,13 +36,6 @@
#include "internal.h"
-#include <net/bluetooth/bluetooth.h>
-#include <net/bluetooth/hci_sock.h>
-#include <net/bluetooth/rfcomm.h>
-
-#include <linux/capi.h>
-#include <linux/gigaset_dev.h>
-
#ifdef CONFIG_BLOCK
#include <linux/cdrom.h>
#include <linux/fd.h>
@@ -60,451 +47,11 @@
#include <linux/uaccess.h>
#include <linux/watchdog.h>
-#include <linux/soundcard.h>
-
#include <linux/hiddev.h>
#include <linux/sort.h>
-#ifdef CONFIG_SPARC
-#include <linux/fb.h>
-#include <asm/fbio.h>
-#endif
-
-#define convert_in_user(srcptr, dstptr) \
-({ \
- typeof(*srcptr) val; \
- \
- get_user(val, srcptr) || put_user(val, dstptr); \
-})
-
-static int do_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
-{
- int err;
-
- err = security_file_ioctl(file, cmd, arg);
- if (err)
- return err;
-
- return vfs_ioctl(file, cmd, arg);
-}
-
-#ifdef CONFIG_BLOCK
-typedef struct sg_io_hdr32 {
- compat_int_t interface_id; /* [i] 'S' for SCSI generic (required) */
- compat_int_t dxfer_direction; /* [i] data transfer direction */
- unsigned char cmd_len; /* [i] SCSI command length ( <= 16 bytes) */
- unsigned char mx_sb_len; /* [i] max length to write to sbp */
- unsigned short iovec_count; /* [i] 0 implies no scatter gather */
- compat_uint_t dxfer_len; /* [i] byte count of data transfer */
- compat_uint_t dxferp; /* [i], [*io] points to data transfer memory
- or scatter gather list */
- compat_uptr_t cmdp; /* [i], [*i] points to command to perform */
- compat_uptr_t sbp; /* [i], [*o] points to sense_buffer memory */
- compat_uint_t timeout; /* [i] MAX_UINT->no timeout (unit: millisec) */
- compat_uint_t flags; /* [i] 0 -> default, see SG_FLAG... */
- compat_int_t pack_id; /* [i->o] unused internally (normally) */
- compat_uptr_t usr_ptr; /* [i->o] unused internally */
- unsigned char status; /* [o] scsi status */
- unsigned char masked_status; /* [o] shifted, masked scsi status */
- unsigned char msg_status; /* [o] messaging level data (optional) */
- unsigned char sb_len_wr; /* [o] byte count actually written to sbp */
- unsigned short host_status; /* [o] errors from host adapter */
- unsigned short driver_status; /* [o] errors from software driver */
- compat_int_t resid; /* [o] dxfer_len - actual_transferred */
- compat_uint_t duration; /* [o] time taken by cmd (unit: millisec) */
- compat_uint_t info; /* [o] auxiliary information */
-} sg_io_hdr32_t; /* 64 bytes long (on sparc32) */
-
-typedef struct sg_iovec32 {
- compat_uint_t iov_base;
- compat_uint_t iov_len;
-} sg_iovec32_t;
-
-static int sg_build_iovec(sg_io_hdr_t __user *sgio, void __user *dxferp, u16 iovec_count)
-{
- sg_iovec_t __user *iov = (sg_iovec_t __user *) (sgio + 1);
- sg_iovec32_t __user *iov32 = dxferp;
- int i;
-
- for (i = 0; i < iovec_count; i++) {
- u32 base, len;
-
- if (get_user(base, &iov32[i].iov_base) ||
- get_user(len, &iov32[i].iov_len) ||
- put_user(compat_ptr(base), &iov[i].iov_base) ||
- put_user(len, &iov[i].iov_len))
- return -EFAULT;
- }
-
- if (put_user(iov, &sgio->dxferp))
- return -EFAULT;
- return 0;
-}
-
-static int sg_ioctl_trans(struct file *file, unsigned int cmd,
- sg_io_hdr32_t __user *sgio32)
-{
- sg_io_hdr_t __user *sgio;
- u16 iovec_count;
- u32 data;
- void __user *dxferp;
- int err;
- int interface_id;
-
- if (get_user(interface_id, &sgio32->interface_id))
- return -EFAULT;
- if (interface_id != 'S')
- return do_ioctl(file, cmd, (unsigned long)sgio32);
-
- if (get_user(iovec_count, &sgio32->iovec_count))
- return -EFAULT;
-
- {
- void __user *top = compat_alloc_user_space(0);
- void __user *new = compat_alloc_user_space(sizeof(sg_io_hdr_t) +
- (iovec_count * sizeof(sg_iovec_t)));
- if (new > top)
- return -EINVAL;
-
- sgio = new;
- }
-
- /* Ok, now construct. */
- if (copy_in_user(&sgio->interface_id, &sgio32->interface_id,
- (2 * sizeof(int)) +
- (2 * sizeof(unsigned char)) +
- (1 * sizeof(unsigned short)) +
- (1 * sizeof(unsigned int))))
- return -EFAULT;
-
- if (get_user(data, &sgio32->dxferp))
- return -EFAULT;
- dxferp = compat_ptr(data);
- if (iovec_count) {
- if (sg_build_iovec(sgio, dxferp, iovec_count))
- return -EFAULT;
- } else {
- if (put_user(dxferp, &sgio->dxferp))
- return -EFAULT;
- }
-
- {
- unsigned char __user *cmdp;
- unsigned char __user *sbp;
-
- if (get_user(data, &sgio32->cmdp))
- return -EFAULT;
- cmdp = compat_ptr(data);
-
- if (get_user(data, &sgio32->sbp))
- return -EFAULT;
- sbp = compat_ptr(data);
-
- if (put_user(cmdp, &sgio->cmdp) ||
- put_user(sbp, &sgio->sbp))
- return -EFAULT;
- }
-
- if (copy_in_user(&sgio->timeout, &sgio32->timeout,
- 3 * sizeof(int)))
- return -EFAULT;
-
- if (get_user(data, &sgio32->usr_ptr))
- return -EFAULT;
- if (put_user(compat_ptr(data), &sgio->usr_ptr))
- return -EFAULT;
-
- err = do_ioctl(file, cmd, (unsigned long) sgio);
-
- if (err >= 0) {
- void __user *datap;
-
- if (copy_in_user(&sgio32->pack_id, &sgio->pack_id,
- sizeof(int)) ||
- get_user(datap, &sgio->usr_ptr) ||
- put_user((u32)(unsigned long)datap,
- &sgio32->usr_ptr) ||
- copy_in_user(&sgio32->status, &sgio->status,
- (4 * sizeof(unsigned char)) +
- (2 * sizeof(unsigned short)) +
- (3 * sizeof(int))))
- err = -EFAULT;
- }
-
- return err;
-}
-
-struct compat_sg_req_info { /* used by SG_GET_REQUEST_TABLE ioctl() */
- char req_state;
- char orphan;
- char sg_io_owned;
- char problem;
- int pack_id;
- compat_uptr_t usr_ptr;
- unsigned int duration;
- int unused;
-};
-
-static int sg_grt_trans(struct file *file,
- unsigned int cmd, struct compat_sg_req_info __user *o)
-{
- int err, i;
- sg_req_info_t __user *r;
- r = compat_alloc_user_space(sizeof(sg_req_info_t)*SG_MAX_QUEUE);
- err = do_ioctl(file, cmd, (unsigned long)r);
- if (err < 0)
- return err;
- for (i = 0; i < SG_MAX_QUEUE; i++) {
- void __user *ptr;
- int d;
-
- if (copy_in_user(o + i, r + i, offsetof(sg_req_info_t, usr_ptr)) ||
- get_user(ptr, &r[i].usr_ptr) ||
- get_user(d, &r[i].duration) ||
- put_user((u32)(unsigned long)(ptr), &o[i].usr_ptr) ||
- put_user(d, &o[i].duration))
- return -EFAULT;
- }
- return err;
-}
-#endif /* CONFIG_BLOCK */
-
-struct sock_fprog32 {
- unsigned short len;
- compat_caddr_t filter;
-};
-
-#define PPPIOCSPASS32 _IOW('t', 71, struct sock_fprog32)
-#define PPPIOCSACTIVE32 _IOW('t', 70, struct sock_fprog32)
-
-static int ppp_sock_fprog_ioctl_trans(struct file *file,
- unsigned int cmd, struct sock_fprog32 __user *u_fprog32)
-{
- struct sock_fprog __user *u_fprog64 = compat_alloc_user_space(sizeof(struct sock_fprog));
- void __user *fptr64;
- u32 fptr32;
- u16 flen;
-
- if (get_user(flen, &u_fprog32->len) ||
- get_user(fptr32, &u_fprog32->filter))
- return -EFAULT;
-
- fptr64 = compat_ptr(fptr32);
-
- if (put_user(flen, &u_fprog64->len) ||
- put_user(fptr64, &u_fprog64->filter))
- return -EFAULT;
-
- if (cmd == PPPIOCSPASS32)
- cmd = PPPIOCSPASS;
- else
- cmd = PPPIOCSACTIVE;
-
- return do_ioctl(file, cmd, (unsigned long) u_fprog64);
-}
-
-struct ppp_option_data32 {
- compat_caddr_t ptr;
- u32 length;
- compat_int_t transmit;
-};
-#define PPPIOCSCOMPRESS32 _IOW('t', 77, struct ppp_option_data32)
-
-struct ppp_idle32 {
- compat_time_t xmit_idle;
- compat_time_t recv_idle;
-};
-#define PPPIOCGIDLE32 _IOR('t', 63, struct ppp_idle32)
-
-static int ppp_gidle(struct file *file, unsigned int cmd,
- struct ppp_idle32 __user *idle32)
-{
- struct ppp_idle __user *idle;
- __kernel_time_t xmit, recv;
- int err;
-
- idle = compat_alloc_user_space(sizeof(*idle));
-
- err = do_ioctl(file, PPPIOCGIDLE, (unsigned long) idle);
-
- if (!err) {
- if (get_user(xmit, &idle->xmit_idle) ||
- get_user(recv, &idle->recv_idle) ||
- put_user(xmit, &idle32->xmit_idle) ||
- put_user(recv, &idle32->recv_idle))
- err = -EFAULT;
- }
- return err;
-}
-
-static int ppp_scompress(struct file *file, unsigned int cmd,
- struct ppp_option_data32 __user *odata32)
-{
- struct ppp_option_data __user *odata;
- __u32 data;
- void __user *datap;
-
- odata = compat_alloc_user_space(sizeof(*odata));
-
- if (get_user(data, &odata32->ptr))
- return -EFAULT;
-
- datap = compat_ptr(data);
- if (put_user(datap, &odata->ptr))
- return -EFAULT;
-
- if (copy_in_user(&odata->length, &odata32->length,
- sizeof(__u32) + sizeof(int)))
- return -EFAULT;
-
- return do_ioctl(file, PPPIOCSCOMPRESS, (unsigned long) odata);
-}
-
-#ifdef CONFIG_BLOCK
-struct mtget32 {
- compat_long_t mt_type;
- compat_long_t mt_resid;
- compat_long_t mt_dsreg;
- compat_long_t mt_gstat;
- compat_long_t mt_erreg;
- compat_daddr_t mt_fileno;
- compat_daddr_t mt_blkno;
-};
-#define MTIOCGET32 _IOR('m', 2, struct mtget32)
-
-struct mtpos32 {
- compat_long_t mt_blkno;
-};
-#define MTIOCPOS32 _IOR('m', 3, struct mtpos32)
-
-static int mt_ioctl_trans(struct file *file,
- unsigned int cmd, void __user *argp)
-{
- /* NULL initialization to make gcc shut up */
- struct mtget __user *get = NULL;
- struct mtget32 __user *umget32;
- struct mtpos __user *pos = NULL;
- struct mtpos32 __user *upos32;
- unsigned long kcmd;
- void *karg;
- int err = 0;
-
- switch(cmd) {
- case MTIOCPOS32:
- kcmd = MTIOCPOS;
- pos = compat_alloc_user_space(sizeof(*pos));
- karg = pos;
- break;
- default: /* MTIOCGET32 */
- kcmd = MTIOCGET;
- get = compat_alloc_user_space(sizeof(*get));
- karg = get;
- break;
- }
- if (karg == NULL)
- return -EFAULT;
- err = do_ioctl(file, kcmd, (unsigned long)karg);
- if (err)
- return err;
- switch (cmd) {
- case MTIOCPOS32:
- upos32 = argp;
- err = convert_in_user(&pos->mt_blkno, &upos32->mt_blkno);
- break;
- case MTIOCGET32:
- umget32 = argp;
- err = convert_in_user(&get->mt_type, &umget32->mt_type);
- err |= convert_in_user(&get->mt_resid, &umget32->mt_resid);
- err |= convert_in_user(&get->mt_dsreg, &umget32->mt_dsreg);
- err |= convert_in_user(&get->mt_gstat, &umget32->mt_gstat);
- err |= convert_in_user(&get->mt_erreg, &umget32->mt_erreg);
- err |= convert_in_user(&get->mt_fileno, &umget32->mt_fileno);
- err |= convert_in_user(&get->mt_blkno, &umget32->mt_blkno);
- break;
- }
- return err ? -EFAULT: 0;
-}
-
-#endif /* CONFIG_BLOCK */
-
-/* Bluetooth ioctls */
-#define HCIUARTSETPROTO _IOW('U', 200, int)
-#define HCIUARTGETPROTO _IOR('U', 201, int)
-#define HCIUARTGETDEVICE _IOR('U', 202, int)
-#define HCIUARTSETFLAGS _IOW('U', 203, int)
-#define HCIUARTGETFLAGS _IOR('U', 204, int)
-
-#define RTC_IRQP_READ32 _IOR('p', 0x0b, compat_ulong_t)
-#define RTC_IRQP_SET32 _IOW('p', 0x0c, compat_ulong_t)
-#define RTC_EPOCH_READ32 _IOR('p', 0x0d, compat_ulong_t)
-#define RTC_EPOCH_SET32 _IOW('p', 0x0e, compat_ulong_t)
-
-static int rtc_ioctl(struct file *file,
- unsigned cmd, void __user *argp)
-{
- unsigned long __user *valp = compat_alloc_user_space(sizeof(*valp));
- int ret;
-
- if (valp == NULL)
- return -EFAULT;
- switch (cmd) {
- case RTC_IRQP_READ32:
- case RTC_EPOCH_READ32:
- ret = do_ioctl(file, (cmd == RTC_IRQP_READ32) ?
- RTC_IRQP_READ : RTC_EPOCH_READ,
- (unsigned long)valp);
- if (ret)
- return ret;
- return convert_in_user(valp, (unsigned int __user *)argp);
- case RTC_IRQP_SET32:
- return do_ioctl(file, RTC_IRQP_SET, (unsigned long)argp);
- case RTC_EPOCH_SET32:
- return do_ioctl(file, RTC_EPOCH_SET, (unsigned long)argp);
- }
-
- return -ENOIOCTLCMD;
-}
-
-/* on ia32 l_start is on a 32-bit boundary */
-#if defined(CONFIG_IA64) || defined(CONFIG_X86_64)
-struct space_resv_32 {
- __s16 l_type;
- __s16 l_whence;
- __s64 l_start __attribute__((packed));
- /* len == 0 means until end of file */
- __s64 l_len __attribute__((packed));
- __s32 l_sysid;
- __u32 l_pid;
- __s32 l_pad[4]; /* reserve area */
-};
-
-#define FS_IOC_RESVSP_32 _IOW ('X', 40, struct space_resv_32)
-#define FS_IOC_UNRESVSP_32 _IOW ('X', 41, struct space_resv_32)
-#define FS_IOC_RESVSP64_32 _IOW ('X', 42, struct space_resv_32)
-#define FS_IOC_UNRESVSP64_32 _IOW ('X', 43, struct space_resv_32)
-#define FS_IOC_ZERO_RANGE_32 _IOW ('X', 57, struct space_resv_32)
-
-/* just account for different alignment */
-static int compat_ioctl_preallocate(struct file *file, int mode,
- struct space_resv_32 __user *p32)
-{
- struct space_resv __user *p = compat_alloc_user_space(sizeof(*p));
-
- if (copy_in_user(&p->l_type, &p32->l_type, sizeof(s16)) ||
- copy_in_user(&p->l_whence, &p32->l_whence, sizeof(s16)) ||
- copy_in_user(&p->l_start, &p32->l_start, sizeof(s64)) ||
- copy_in_user(&p->l_len, &p32->l_len, sizeof(s64)) ||
- copy_in_user(&p->l_sysid, &p32->l_sysid, sizeof(s32)) ||
- copy_in_user(&p->l_pid, &p32->l_pid, sizeof(u32)) ||
- copy_in_user(&p->l_pad, &p32->l_pad, 4*sizeof(u32)))
- return -EFAULT;
-
- return ioctl_preallocate(file, mode, p);
-}
-#endif
-
/*
* simple reversible transform to make our table more evenly
* distributed after sorting.
@@ -512,33 +59,7 @@ static int compat_ioctl_preallocate(struct file *file, int mode,
#define XFORM(i) (((i) ^ ((i) << 27) ^ ((i) << 17)) & 0xffffffff)
#define COMPATIBLE_IOCTL(cmd) XFORM((u32)cmd),
-/* ioctl should not be warned about even if it's not implemented.
- Valid reasons to use this:
- - It is implemented with ->compat_ioctl on some device, but programs
- call it on others too.
- - The ioctl is not implemented in the native kernel, but programs
- call it commonly anyways.
- Most other reasons are not valid. */
-#define IGNORE_IOCTL(cmd) COMPATIBLE_IOCTL(cmd)
-
static unsigned int ioctl_pointer[] = {
-/* compatible ioctls first */
-/* Little t */
-COMPATIBLE_IOCTL(TIOCOUTQ)
-/* Little f */
-COMPATIBLE_IOCTL(FIOCLEX)
-COMPATIBLE_IOCTL(FIONCLEX)
-COMPATIBLE_IOCTL(FIOASYNC)
-COMPATIBLE_IOCTL(FIONBIO)
-COMPATIBLE_IOCTL(FIONREAD) /* This is also TIOCINQ */
-COMPATIBLE_IOCTL(FS_IOC_FIEMAP)
-/* 0x00 */
-COMPATIBLE_IOCTL(FIBMAP)
-COMPATIBLE_IOCTL(FIGETBSZ)
-/* 'X' - originally XFS but some now in the VFS */
-COMPATIBLE_IOCTL(FIFREEZE)
-COMPATIBLE_IOCTL(FITHAW)
-COMPATIBLE_IOCTL(FITRIM)
#ifdef CONFIG_BLOCK
/* Big S */
COMPATIBLE_IOCTL(SCSI_IOCTL_GET_IDLUN)
@@ -550,43 +71,10 @@ COMPATIBLE_IOCTL(SCSI_IOCTL_SEND_COMMAND)
COMPATIBLE_IOCTL(SCSI_IOCTL_PROBE_HOST)
COMPATIBLE_IOCTL(SCSI_IOCTL_GET_PCI)
#endif
-/* Big V (don't complain on serial console) */
-IGNORE_IOCTL(VT_OPENQRY)
-IGNORE_IOCTL(VT_GETMODE)
-/* Little p (/dev/rtc, /dev/envctrl, etc.) */
-COMPATIBLE_IOCTL(RTC_AIE_ON)
-COMPATIBLE_IOCTL(RTC_AIE_OFF)
-COMPATIBLE_IOCTL(RTC_UIE_ON)
-COMPATIBLE_IOCTL(RTC_UIE_OFF)
-COMPATIBLE_IOCTL(RTC_PIE_ON)
-COMPATIBLE_IOCTL(RTC_PIE_OFF)
-COMPATIBLE_IOCTL(RTC_WIE_ON)
-COMPATIBLE_IOCTL(RTC_WIE_OFF)
-COMPATIBLE_IOCTL(RTC_ALM_SET)
-COMPATIBLE_IOCTL(RTC_ALM_READ)
-COMPATIBLE_IOCTL(RTC_RD_TIME)
-COMPATIBLE_IOCTL(RTC_SET_TIME)
-COMPATIBLE_IOCTL(RTC_WKALM_SET)
-COMPATIBLE_IOCTL(RTC_WKALM_RD)
-/*
- * These two are only for the sbus rtc driver, but
- * hwclock tries them on every rtc device first when
- * running on sparc. On other architectures the entries
- * are useless but harmless.
- */
-COMPATIBLE_IOCTL(_IOR('p', 20, int[7])) /* RTCGET */
-COMPATIBLE_IOCTL(_IOW('p', 21, int[7])) /* RTCSET */
-/* Little m */
-COMPATIBLE_IOCTL(MTIOCTOP)
-/* Socket level stuff */
-COMPATIBLE_IOCTL(FIOQSIZE)
#ifdef CONFIG_BLOCK
-/* md calls this on random blockdevs */
-IGNORE_IOCTL(RAID_VERSION)
-/* qemu/qemu-img might call these two on plain files for probing */
-IGNORE_IOCTL(CDROM_DRIVE_STATUS)
-IGNORE_IOCTL(FDGETPRM32)
/* SG stuff */
+COMPATIBLE_IOCTL(SG_IO)
+COMPATIBLE_IOCTL(SG_GET_REQUEST_TABLE)
COMPATIBLE_IOCTL(SG_SET_TIMEOUT)
COMPATIBLE_IOCTL(SG_GET_TIMEOUT)
COMPATIBLE_IOCTL(SG_EMULATED_HOST)
@@ -610,314 +98,6 @@ COMPATIBLE_IOCTL(SG_GET_REQUEST_TABLE)
COMPATIBLE_IOCTL(SG_SET_KEEP_ORPHAN)
COMPATIBLE_IOCTL(SG_GET_KEEP_ORPHAN)
#endif
-/* PPP stuff */
-COMPATIBLE_IOCTL(PPPIOCGFLAGS)
-COMPATIBLE_IOCTL(PPPIOCSFLAGS)
-COMPATIBLE_IOCTL(PPPIOCGASYNCMAP)
-COMPATIBLE_IOCTL(PPPIOCSASYNCMAP)
-COMPATIBLE_IOCTL(PPPIOCGUNIT)
-COMPATIBLE_IOCTL(PPPIOCGRASYNCMAP)
-COMPATIBLE_IOCTL(PPPIOCSRASYNCMAP)
-COMPATIBLE_IOCTL(PPPIOCGMRU)
-COMPATIBLE_IOCTL(PPPIOCSMRU)
-COMPATIBLE_IOCTL(PPPIOCSMAXCID)
-COMPATIBLE_IOCTL(PPPIOCGXASYNCMAP)
-COMPATIBLE_IOCTL(PPPIOCSXASYNCMAP)
-COMPATIBLE_IOCTL(PPPIOCXFERUNIT)
-/* PPPIOCSCOMPRESS is translated */
-COMPATIBLE_IOCTL(PPPIOCGNPMODE)
-COMPATIBLE_IOCTL(PPPIOCSNPMODE)
-COMPATIBLE_IOCTL(PPPIOCGDEBUG)
-COMPATIBLE_IOCTL(PPPIOCSDEBUG)
-/* PPPIOCSPASS is translated */
-/* PPPIOCSACTIVE is translated */
-/* PPPIOCGIDLE is translated */
-COMPATIBLE_IOCTL(PPPIOCNEWUNIT)
-COMPATIBLE_IOCTL(PPPIOCATTACH)
-COMPATIBLE_IOCTL(PPPIOCDETACH)
-COMPATIBLE_IOCTL(PPPIOCSMRRU)
-COMPATIBLE_IOCTL(PPPIOCCONNECT)
-COMPATIBLE_IOCTL(PPPIOCDISCONN)
-COMPATIBLE_IOCTL(PPPIOCATTCHAN)
-COMPATIBLE_IOCTL(PPPIOCGCHAN)
-COMPATIBLE_IOCTL(PPPIOCGL2TPSTATS)
-/* Big A */
-/* sparc only */
-/* Big Q for sound/OSS */
-COMPATIBLE_IOCTL(SNDCTL_SEQ_RESET)
-COMPATIBLE_IOCTL(SNDCTL_SEQ_SYNC)
-COMPATIBLE_IOCTL(SNDCTL_SYNTH_INFO)
-COMPATIBLE_IOCTL(SNDCTL_SEQ_CTRLRATE)
-COMPATIBLE_IOCTL(SNDCTL_SEQ_GETOUTCOUNT)
-COMPATIBLE_IOCTL(SNDCTL_SEQ_GETINCOUNT)
-COMPATIBLE_IOCTL(SNDCTL_SEQ_PERCMODE)
-COMPATIBLE_IOCTL(SNDCTL_FM_LOAD_INSTR)
-COMPATIBLE_IOCTL(SNDCTL_SEQ_TESTMIDI)
-COMPATIBLE_IOCTL(SNDCTL_SEQ_RESETSAMPLES)
-COMPATIBLE_IOCTL(SNDCTL_SEQ_NRSYNTHS)
-COMPATIBLE_IOCTL(SNDCTL_SEQ_NRMIDIS)
-COMPATIBLE_IOCTL(SNDCTL_MIDI_INFO)
-COMPATIBLE_IOCTL(SNDCTL_SEQ_THRESHOLD)
-COMPATIBLE_IOCTL(SNDCTL_SYNTH_MEMAVL)
-COMPATIBLE_IOCTL(SNDCTL_FM_4OP_ENABLE)
-COMPATIBLE_IOCTL(SNDCTL_SEQ_PANIC)
-COMPATIBLE_IOCTL(SNDCTL_SEQ_OUTOFBAND)
-COMPATIBLE_IOCTL(SNDCTL_SEQ_GETTIME)
-COMPATIBLE_IOCTL(SNDCTL_SYNTH_ID)
-COMPATIBLE_IOCTL(SNDCTL_SYNTH_CONTROL)
-COMPATIBLE_IOCTL(SNDCTL_SYNTH_REMOVESAMPLE)
-/* Big T for sound/OSS */
-COMPATIBLE_IOCTL(SNDCTL_TMR_TIMEBASE)
-COMPATIBLE_IOCTL(SNDCTL_TMR_START)
-COMPATIBLE_IOCTL(SNDCTL_TMR_STOP)
-COMPATIBLE_IOCTL(SNDCTL_TMR_CONTINUE)
-COMPATIBLE_IOCTL(SNDCTL_TMR_TEMPO)
-COMPATIBLE_IOCTL(SNDCTL_TMR_SOURCE)
-COMPATIBLE_IOCTL(SNDCTL_TMR_METRONOME)
-COMPATIBLE_IOCTL(SNDCTL_TMR_SELECT)
-/* Little m for sound/OSS */
-COMPATIBLE_IOCTL(SNDCTL_MIDI_PRETIME)
-COMPATIBLE_IOCTL(SNDCTL_MIDI_MPUMODE)
-COMPATIBLE_IOCTL(SNDCTL_MIDI_MPUCMD)
-/* Big P for sound/OSS */
-COMPATIBLE_IOCTL(SNDCTL_DSP_RESET)
-COMPATIBLE_IOCTL(SNDCTL_DSP_SYNC)
-COMPATIBLE_IOCTL(SNDCTL_DSP_SPEED)
-COMPATIBLE_IOCTL(SNDCTL_DSP_STEREO)
-COMPATIBLE_IOCTL(SNDCTL_DSP_GETBLKSIZE)
-COMPATIBLE_IOCTL(SNDCTL_DSP_CHANNELS)
-COMPATIBLE_IOCTL(SOUND_PCM_WRITE_FILTER)
-COMPATIBLE_IOCTL(SNDCTL_DSP_POST)
-COMPATIBLE_IOCTL(SNDCTL_DSP_SUBDIVIDE)
-COMPATIBLE_IOCTL(SNDCTL_DSP_SETFRAGMENT)
-COMPATIBLE_IOCTL(SNDCTL_DSP_GETFMTS)
-COMPATIBLE_IOCTL(SNDCTL_DSP_SETFMT)
-COMPATIBLE_IOCTL(SNDCTL_DSP_GETOSPACE)
-COMPATIBLE_IOCTL(SNDCTL_DSP_GETISPACE)
-COMPATIBLE_IOCTL(SNDCTL_DSP_NONBLOCK)
-COMPATIBLE_IOCTL(SNDCTL_DSP_GETCAPS)
-COMPATIBLE_IOCTL(SNDCTL_DSP_GETTRIGGER)
-COMPATIBLE_IOCTL(SNDCTL_DSP_SETTRIGGER)
-COMPATIBLE_IOCTL(SNDCTL_DSP_GETIPTR)
-COMPATIBLE_IOCTL(SNDCTL_DSP_GETOPTR)
-/* SNDCTL_DSP_MAPINBUF, XXX needs translation */
-/* SNDCTL_DSP_MAPOUTBUF, XXX needs translation */
-COMPATIBLE_IOCTL(SNDCTL_DSP_SETSYNCRO)
-COMPATIBLE_IOCTL(SNDCTL_DSP_SETDUPLEX)
-COMPATIBLE_IOCTL(SNDCTL_DSP_GETODELAY)
-COMPATIBLE_IOCTL(SNDCTL_DSP_PROFILE)
-COMPATIBLE_IOCTL(SOUND_PCM_READ_RATE)
-COMPATIBLE_IOCTL(SOUND_PCM_READ_CHANNELS)
-COMPATIBLE_IOCTL(SOUND_PCM_READ_BITS)
-COMPATIBLE_IOCTL(SOUND_PCM_READ_FILTER)
-/* Big C for sound/OSS */
-COMPATIBLE_IOCTL(SNDCTL_COPR_RESET)
-COMPATIBLE_IOCTL(SNDCTL_COPR_LOAD)
-COMPATIBLE_IOCTL(SNDCTL_COPR_RDATA)
-COMPATIBLE_IOCTL(SNDCTL_COPR_RCODE)
-COMPATIBLE_IOCTL(SNDCTL_COPR_WDATA)
-COMPATIBLE_IOCTL(SNDCTL_COPR_WCODE)
-COMPATIBLE_IOCTL(SNDCTL_COPR_RUN)
-COMPATIBLE_IOCTL(SNDCTL_COPR_HALT)
-COMPATIBLE_IOCTL(SNDCTL_COPR_SENDMSG)
-COMPATIBLE_IOCTL(SNDCTL_COPR_RCVMSG)
-/* Big M for sound/OSS */
-COMPATIBLE_IOCTL(SOUND_MIXER_READ_VOLUME)
-COMPATIBLE_IOCTL(SOUND_MIXER_READ_BASS)
-COMPATIBLE_IOCTL(SOUND_MIXER_READ_TREBLE)
-COMPATIBLE_IOCTL(SOUND_MIXER_READ_SYNTH)
-COMPATIBLE_IOCTL(SOUND_MIXER_READ_PCM)
-COMPATIBLE_IOCTL(SOUND_MIXER_READ_SPEAKER)
-COMPATIBLE_IOCTL(SOUND_MIXER_READ_LINE)
-COMPATIBLE_IOCTL(SOUND_MIXER_READ_MIC)
-COMPATIBLE_IOCTL(SOUND_MIXER_READ_CD)
-COMPATIBLE_IOCTL(SOUND_MIXER_READ_IMIX)
-COMPATIBLE_IOCTL(SOUND_MIXER_READ_ALTPCM)
-COMPATIBLE_IOCTL(SOUND_MIXER_READ_RECLEV)
-COMPATIBLE_IOCTL(SOUND_MIXER_READ_IGAIN)
-COMPATIBLE_IOCTL(SOUND_MIXER_READ_OGAIN)
-COMPATIBLE_IOCTL(SOUND_MIXER_READ_LINE1)
-COMPATIBLE_IOCTL(SOUND_MIXER_READ_LINE2)
-COMPATIBLE_IOCTL(SOUND_MIXER_READ_LINE3)
-COMPATIBLE_IOCTL(MIXER_READ(SOUND_MIXER_DIGITAL1))
-COMPATIBLE_IOCTL(MIXER_READ(SOUND_MIXER_DIGITAL2))
-COMPATIBLE_IOCTL(MIXER_READ(SOUND_MIXER_DIGITAL3))
-COMPATIBLE_IOCTL(MIXER_READ(SOUND_MIXER_PHONEIN))
-COMPATIBLE_IOCTL(MIXER_READ(SOUND_MIXER_PHONEOUT))
-COMPATIBLE_IOCTL(MIXER_READ(SOUND_MIXER_VIDEO))
-COMPATIBLE_IOCTL(MIXER_READ(SOUND_MIXER_RADIO))
-COMPATIBLE_IOCTL(MIXER_READ(SOUND_MIXER_MONITOR))
-COMPATIBLE_IOCTL(SOUND_MIXER_READ_MUTE)
-/* SOUND_MIXER_READ_ENHANCE, same value as READ_MUTE */
-/* SOUND_MIXER_READ_LOUD, same value as READ_MUTE */
-COMPATIBLE_IOCTL(SOUND_MIXER_READ_RECSRC)
-COMPATIBLE_IOCTL(SOUND_MIXER_READ_DEVMASK)
-COMPATIBLE_IOCTL(SOUND_MIXER_READ_RECMASK)
-COMPATIBLE_IOCTL(SOUND_MIXER_READ_STEREODEVS)
-COMPATIBLE_IOCTL(SOUND_MIXER_READ_CAPS)
-COMPATIBLE_IOCTL(SOUND_MIXER_WRITE_VOLUME)
-COMPATIBLE_IOCTL(SOUND_MIXER_WRITE_BASS)
-COMPATIBLE_IOCTL(SOUND_MIXER_WRITE_TREBLE)
-COMPATIBLE_IOCTL(SOUND_MIXER_WRITE_SYNTH)
-COMPATIBLE_IOCTL(SOUND_MIXER_WRITE_PCM)
-COMPATIBLE_IOCTL(SOUND_MIXER_WRITE_SPEAKER)
-COMPATIBLE_IOCTL(SOUND_MIXER_WRITE_LINE)
-COMPATIBLE_IOCTL(SOUND_MIXER_WRITE_MIC)
-COMPATIBLE_IOCTL(SOUND_MIXER_WRITE_CD)
-COMPATIBLE_IOCTL(SOUND_MIXER_WRITE_IMIX)
-COMPATIBLE_IOCTL(SOUND_MIXER_WRITE_ALTPCM)
-COMPATIBLE_IOCTL(SOUND_MIXER_WRITE_RECLEV)
-COMPATIBLE_IOCTL(SOUND_MIXER_WRITE_IGAIN)
-COMPATIBLE_IOCTL(SOUND_MIXER_WRITE_OGAIN)
-COMPATIBLE_IOCTL(SOUND_MIXER_WRITE_LINE1)
-COMPATIBLE_IOCTL(SOUND_MIXER_WRITE_LINE2)
-COMPATIBLE_IOCTL(SOUND_MIXER_WRITE_LINE3)
-COMPATIBLE_IOCTL(MIXER_WRITE(SOUND_MIXER_DIGITAL1))
-COMPATIBLE_IOCTL(MIXER_WRITE(SOUND_MIXER_DIGITAL2))
-COMPATIBLE_IOCTL(MIXER_WRITE(SOUND_MIXER_DIGITAL3))
-COMPATIBLE_IOCTL(MIXER_WRITE(SOUND_MIXER_PHONEIN))
-COMPATIBLE_IOCTL(MIXER_WRITE(SOUND_MIXER_PHONEOUT))
-COMPATIBLE_IOCTL(MIXER_WRITE(SOUND_MIXER_VIDEO))
-COMPATIBLE_IOCTL(MIXER_WRITE(SOUND_MIXER_RADIO))
-COMPATIBLE_IOCTL(MIXER_WRITE(SOUND_MIXER_MONITOR))
-COMPATIBLE_IOCTL(SOUND_MIXER_WRITE_MUTE)
-/* SOUND_MIXER_WRITE_ENHANCE, same value as WRITE_MUTE */
-/* SOUND_MIXER_WRITE_LOUD, same value as WRITE_MUTE */
-COMPATIBLE_IOCTL(SOUND_MIXER_WRITE_RECSRC)
-COMPATIBLE_IOCTL(SOUND_MIXER_INFO)
-COMPATIBLE_IOCTL(SOUND_OLD_MIXER_INFO)
-COMPATIBLE_IOCTL(SOUND_MIXER_ACCESS)
-COMPATIBLE_IOCTL(SOUND_MIXER_AGC)
-COMPATIBLE_IOCTL(SOUND_MIXER_3DSE)
-COMPATIBLE_IOCTL(SOUND_MIXER_PRIVATE1)
-COMPATIBLE_IOCTL(SOUND_MIXER_PRIVATE2)
-COMPATIBLE_IOCTL(SOUND_MIXER_PRIVATE3)
-COMPATIBLE_IOCTL(SOUND_MIXER_PRIVATE4)
-COMPATIBLE_IOCTL(SOUND_MIXER_PRIVATE5)
-COMPATIBLE_IOCTL(SOUND_MIXER_GETLEVELS)
-COMPATIBLE_IOCTL(SOUND_MIXER_SETLEVELS)
-COMPATIBLE_IOCTL(OSS_GETVERSION)
-/* Raw devices */
-COMPATIBLE_IOCTL(RAW_SETBIND)
-COMPATIBLE_IOCTL(RAW_GETBIND)
-/* Watchdog */
-COMPATIBLE_IOCTL(WDIOC_GETSUPPORT)
-COMPATIBLE_IOCTL(WDIOC_GETSTATUS)
-COMPATIBLE_IOCTL(WDIOC_GETBOOTSTATUS)
-COMPATIBLE_IOCTL(WDIOC_GETTEMP)
-COMPATIBLE_IOCTL(WDIOC_SETOPTIONS)
-COMPATIBLE_IOCTL(WDIOC_KEEPALIVE)
-COMPATIBLE_IOCTL(WDIOC_SETTIMEOUT)
-COMPATIBLE_IOCTL(WDIOC_GETTIMEOUT)
-COMPATIBLE_IOCTL(WDIOC_SETPRETIMEOUT)
-COMPATIBLE_IOCTL(WDIOC_GETPRETIMEOUT)
-/* Big R */
-COMPATIBLE_IOCTL(RNDGETENTCNT)
-COMPATIBLE_IOCTL(RNDADDTOENTCNT)
-COMPATIBLE_IOCTL(RNDGETPOOL)
-COMPATIBLE_IOCTL(RNDADDENTROPY)
-COMPATIBLE_IOCTL(RNDZAPENTCNT)
-COMPATIBLE_IOCTL(RNDCLEARPOOL)
-/* Bluetooth */
-COMPATIBLE_IOCTL(HCIDEVUP)
-COMPATIBLE_IOCTL(HCIDEVDOWN)
-COMPATIBLE_IOCTL(HCIDEVRESET)
-COMPATIBLE_IOCTL(HCIDEVRESTAT)
-COMPATIBLE_IOCTL(HCIGETDEVLIST)
-COMPATIBLE_IOCTL(HCIGETDEVINFO)
-COMPATIBLE_IOCTL(HCIGETCONNLIST)
-COMPATIBLE_IOCTL(HCIGETCONNINFO)
-COMPATIBLE_IOCTL(HCIGETAUTHINFO)
-COMPATIBLE_IOCTL(HCISETRAW)
-COMPATIBLE_IOCTL(HCISETSCAN)
-COMPATIBLE_IOCTL(HCISETAUTH)
-COMPATIBLE_IOCTL(HCISETENCRYPT)
-COMPATIBLE_IOCTL(HCISETPTYPE)
-COMPATIBLE_IOCTL(HCISETLINKPOL)
-COMPATIBLE_IOCTL(HCISETLINKMODE)
-COMPATIBLE_IOCTL(HCISETACLMTU)
-COMPATIBLE_IOCTL(HCISETSCOMTU)
-COMPATIBLE_IOCTL(HCIBLOCKADDR)
-COMPATIBLE_IOCTL(HCIUNBLOCKADDR)
-COMPATIBLE_IOCTL(HCIINQUIRY)
-COMPATIBLE_IOCTL(HCIUARTSETPROTO)
-COMPATIBLE_IOCTL(HCIUARTGETPROTO)
-COMPATIBLE_IOCTL(HCIUARTGETDEVICE)
-COMPATIBLE_IOCTL(HCIUARTSETFLAGS)
-COMPATIBLE_IOCTL(HCIUARTGETFLAGS)
-COMPATIBLE_IOCTL(RFCOMMCREATEDEV)
-COMPATIBLE_IOCTL(RFCOMMRELEASEDEV)
-COMPATIBLE_IOCTL(RFCOMMGETDEVLIST)
-COMPATIBLE_IOCTL(RFCOMMGETDEVINFO)
-COMPATIBLE_IOCTL(RFCOMMSTEALDLC)
-/* CAPI */
-COMPATIBLE_IOCTL(CAPI_REGISTER)
-COMPATIBLE_IOCTL(CAPI_GET_MANUFACTURER)
-COMPATIBLE_IOCTL(CAPI_GET_VERSION)
-COMPATIBLE_IOCTL(CAPI_GET_SERIAL)
-COMPATIBLE_IOCTL(CAPI_GET_PROFILE)
-COMPATIBLE_IOCTL(CAPI_MANUFACTURER_CMD)
-COMPATIBLE_IOCTL(CAPI_GET_ERRCODE)
-COMPATIBLE_IOCTL(CAPI_INSTALLED)
-COMPATIBLE_IOCTL(CAPI_GET_FLAGS)
-COMPATIBLE_IOCTL(CAPI_SET_FLAGS)
-COMPATIBLE_IOCTL(CAPI_CLR_FLAGS)
-COMPATIBLE_IOCTL(CAPI_NCCI_OPENCOUNT)
-COMPATIBLE_IOCTL(CAPI_NCCI_GETUNIT)
-/* Misc. */
-COMPATIBLE_IOCTL(0x41545900) /* ATYIO_CLKR */
-COMPATIBLE_IOCTL(0x41545901) /* ATYIO_CLKW */
-COMPATIBLE_IOCTL(PCIIOC_CONTROLLER)
-COMPATIBLE_IOCTL(PCIIOC_MMAP_IS_IO)
-COMPATIBLE_IOCTL(PCIIOC_MMAP_IS_MEM)
-COMPATIBLE_IOCTL(PCIIOC_WRITE_COMBINE)
-/* hiddev */
-COMPATIBLE_IOCTL(HIDIOCGVERSION)
-COMPATIBLE_IOCTL(HIDIOCAPPLICATION)
-COMPATIBLE_IOCTL(HIDIOCGDEVINFO)
-COMPATIBLE_IOCTL(HIDIOCGSTRING)
-COMPATIBLE_IOCTL(HIDIOCINITREPORT)
-COMPATIBLE_IOCTL(HIDIOCGREPORT)
-COMPATIBLE_IOCTL(HIDIOCSREPORT)
-COMPATIBLE_IOCTL(HIDIOCGREPORTINFO)
-COMPATIBLE_IOCTL(HIDIOCGFIELDINFO)
-COMPATIBLE_IOCTL(HIDIOCGUSAGE)
-COMPATIBLE_IOCTL(HIDIOCSUSAGE)
-COMPATIBLE_IOCTL(HIDIOCGUCODE)
-COMPATIBLE_IOCTL(HIDIOCGFLAG)
-COMPATIBLE_IOCTL(HIDIOCSFLAG)
-COMPATIBLE_IOCTL(HIDIOCGCOLLECTIONINDEX)
-COMPATIBLE_IOCTL(HIDIOCGCOLLECTIONINFO)
-/* joystick */
-COMPATIBLE_IOCTL(JSIOCGVERSION)
-COMPATIBLE_IOCTL(JSIOCGAXES)
-COMPATIBLE_IOCTL(JSIOCGBUTTONS)
-COMPATIBLE_IOCTL(JSIOCGNAME(0))
-
-/* fat 'r' ioctls. These are handled by fat with ->compat_ioctl,
- but we don't want warnings on other file systems. So declare
- them as compatible here. */
-#define VFAT_IOCTL_READDIR_BOTH32 _IOR('r', 1, struct compat_dirent[2])
-#define VFAT_IOCTL_READDIR_SHORT32 _IOR('r', 2, struct compat_dirent[2])
-
-IGNORE_IOCTL(VFAT_IOCTL_READDIR_BOTH32)
-IGNORE_IOCTL(VFAT_IOCTL_READDIR_SHORT32)
-
-#ifdef CONFIG_SPARC
-/* Sparc framebuffers, handled in sbusfb_compat_ioctl() */
-IGNORE_IOCTL(FBIOGTYPE)
-IGNORE_IOCTL(FBIOSATTR)
-IGNORE_IOCTL(FBIOGATTR)
-IGNORE_IOCTL(FBIOSVIDEO)
-IGNORE_IOCTL(FBIOGVIDEO)
-IGNORE_IOCTL(FBIOSCURPOS)
-IGNORE_IOCTL(FBIOGCURPOS)
-IGNORE_IOCTL(FBIOGCURMAX)
-IGNORE_IOCTL(FBIOPUTCMAP32)
-IGNORE_IOCTL(FBIOGETCMAP32)
-IGNORE_IOCTL(FBIOSCURSOR32)
-IGNORE_IOCTL(FBIOGCURSOR32)
-#endif
};
/*
@@ -930,51 +110,12 @@ IGNORE_IOCTL(FBIOGCURSOR32)
static long do_ioctl_trans(unsigned int cmd,
unsigned long arg, struct file *file)
{
- void __user *argp = compat_ptr(arg);
-
- switch (cmd) {
- case PPPIOCGIDLE32:
- return ppp_gidle(file, cmd, argp);
- case PPPIOCSCOMPRESS32:
- return ppp_scompress(file, cmd, argp);
- case PPPIOCSPASS32:
- case PPPIOCSACTIVE32:
- return ppp_sock_fprog_ioctl_trans(file, cmd, argp);
-#ifdef CONFIG_BLOCK
- case SG_IO:
- return sg_ioctl_trans(file, cmd, argp);
- case SG_GET_REQUEST_TABLE:
- return sg_grt_trans(file, cmd, argp);
- case MTIOCGET32:
- case MTIOCPOS32:
- return mt_ioctl_trans(file, cmd, argp);
-#endif
- /* Not implemented in the native kernel */
- case RTC_IRQP_READ32:
- case RTC_IRQP_SET32:
- case RTC_EPOCH_READ32:
- case RTC_EPOCH_SET32:
- return rtc_ioctl(file, cmd, argp);
- }
-
- /*
- * These take an integer instead of a pointer as 'arg',
- * so we must not do a compat_ptr() translation.
- */
- switch (cmd) {
- /* RAID */
- case HOT_REMOVE_DISK:
- case HOT_ADD_DISK:
- case SET_DISK_FAULTY:
- case SET_BITMAP_FILE:
- return vfs_ioctl(file, cmd, arg);
- }
-
return -ENOIOCTLCMD;
}
static int compat_ioctl_check_table(unsigned int xcmd)
{
+#ifdef CONFIG_BLOCK
int i;
const int max = ARRAY_SIZE(ioctl_pointer) - 1;
@@ -993,6 +134,9 @@ static int compat_ioctl_check_table(unsigned int xcmd)
i--;
return ioctl_pointer[i] == xcmd;
+#else
+ return 0;
+#endif
}
COMPAT_SYSCALL_DEFINE3(ioctl, unsigned int, fd, unsigned int, cmd,
@@ -1009,20 +153,40 @@ COMPAT_SYSCALL_DEFINE3(ioctl, unsigned int, fd, unsigned int, cmd,
if (error)
goto out_fput;
- /*
- * To allow the compat_ioctl handlers to be self contained
- * we need to check the common ioctls here first.
- * Just handle them with the standard handlers below.
- */
switch (cmd) {
+ /* these are never seen by ->ioctl(), no argument or int argument */
case FIOCLEX:
case FIONCLEX:
+ case FIFREEZE:
+ case FITHAW:
+ case FICLONE:
+ goto do_ioctl;
+ /* these are never seen by ->ioctl(), pointer argument */
case FIONBIO:
case FIOASYNC:
case FIOQSIZE:
- break;
-
-#if defined(CONFIG_IA64) || defined(CONFIG_X86_64)
+ case FS_IOC_FIEMAP:
+ case FIGETBSZ:
+ case FICLONERANGE:
+ case FIDEDUPERANGE:
+ goto found_handler;
+ /*
+ * The next group is the stuff handled inside file_ioctl().
+ * For regular files these never reach ->ioctl(); for
+ * devices, sockets, etc. they do and one (FIONREAD) is
+ * even accepted in some cases. In all those cases
+ * argument has the same type, so we can handle these
+ * here, shunting them towards do_vfs_ioctl().
+ * ->compat_ioctl() will never see any of those.
+ */
+ /* pointer argument, never actually handled by ->ioctl() */
+ case FIBMAP:
+ goto found_handler;
+ /* handled by some ->ioctl(); always a pointer to int */
+ case FIONREAD:
+ goto found_handler;
+ /* these get messy on amd64 due to alignment differences */
+#if defined(CONFIG_X86_64)
case FS_IOC_RESVSP_32:
case FS_IOC_RESVSP64_32:
error = compat_ioctl_preallocate(f.file, 0, compat_ptr(arg));
@@ -1039,32 +203,12 @@ COMPAT_SYSCALL_DEFINE3(ioctl, unsigned int, fd, unsigned int, cmd,
#else
case FS_IOC_RESVSP:
case FS_IOC_RESVSP64:
- error = ioctl_preallocate(f.file, 0, compat_ptr(arg));
- goto out_fput;
case FS_IOC_UNRESVSP:
case FS_IOC_UNRESVSP64:
- error = ioctl_preallocate(f.file, FALLOC_FL_PUNCH_HOLE,
- compat_ptr(arg));
- goto out_fput;
case FS_IOC_ZERO_RANGE:
- error = ioctl_preallocate(f.file, FALLOC_FL_ZERO_RANGE,
- compat_ptr(arg));
- goto out_fput;
+ goto found_handler;
#endif
- case FICLONE:
- case FICLONERANGE:
- case FIDEDUPERANGE:
- case FS_IOC_FIEMAP:
- goto do_ioctl;
-
- case FIBMAP:
- case FIGETBSZ:
- case FIONREAD:
- if (S_ISREG(file_inode(f.file)->i_mode))
- break;
- /*FALL THROUGH*/
-
default:
if (f.file->f_op->compat_ioctl) {
error = f.file->f_op->compat_ioctl(f.file, cmd, arg);
diff --git a/fs/configfs/symlink.c b/fs/configfs/symlink.c
index dc5dbf6a81d7..cb61467478ca 100644
--- a/fs/configfs/symlink.c
+++ b/fs/configfs/symlink.c
@@ -101,7 +101,7 @@ static int create_link(struct config_item *parent_item,
}
target_sd->s_links++;
spin_unlock(&configfs_dirent_lock);
- ret = configfs_get_target_path(item, item, body);
+ ret = configfs_get_target_path(parent_item, item, body);
if (!ret)
ret = configfs_create_link(target_sd, parent_item->ci_dentry,
dentry, body);
diff --git a/fs/cramfs/inode.c b/fs/cramfs/inode.c
index d12ea28836a5..2f04024c3588 100644
--- a/fs/cramfs/inode.c
+++ b/fs/cramfs/inode.c
@@ -958,8 +958,8 @@ static int cramfs_get_tree(struct fs_context *fc)
if (IS_ENABLED(CONFIG_CRAMFS_MTD)) {
ret = get_tree_mtd(fc, cramfs_mtd_fill_super);
- if (ret < 0)
- return ret;
+ if (!ret)
+ return 0;
}
if (IS_ENABLED(CONFIG_CRAMFS_BLOCKDEV))
ret = get_tree_bdev(fc, cramfs_blkdev_fill_super);
diff --git a/fs/crypto/bio.c b/fs/crypto/bio.c
index 82da2510721f..1f4b8a277060 100644
--- a/fs/crypto/bio.c
+++ b/fs/crypto/bio.c
@@ -26,7 +26,7 @@
#include <linux/namei.h>
#include "fscrypt_private.h"
-static void __fscrypt_decrypt_bio(struct bio *bio, bool done)
+void fscrypt_decrypt_bio(struct bio *bio)
{
struct bio_vec *bv;
struct bvec_iter_all iter_all;
@@ -37,37 +37,10 @@ static void __fscrypt_decrypt_bio(struct bio *bio, bool done)
bv->bv_offset);
if (ret)
SetPageError(page);
- else if (done)
- SetPageUptodate(page);
- if (done)
- unlock_page(page);
}
}
-
-void fscrypt_decrypt_bio(struct bio *bio)
-{
- __fscrypt_decrypt_bio(bio, false);
-}
EXPORT_SYMBOL(fscrypt_decrypt_bio);
-static void completion_pages(struct work_struct *work)
-{
- struct fscrypt_ctx *ctx = container_of(work, struct fscrypt_ctx, work);
- struct bio *bio = ctx->bio;
-
- __fscrypt_decrypt_bio(bio, true);
- fscrypt_release_ctx(ctx);
- bio_put(bio);
-}
-
-void fscrypt_enqueue_decrypt_bio(struct fscrypt_ctx *ctx, struct bio *bio)
-{
- INIT_WORK(&ctx->work, completion_pages);
- ctx->bio = bio;
- fscrypt_enqueue_decrypt_work(&ctx->work);
-}
-EXPORT_SYMBOL(fscrypt_enqueue_decrypt_bio);
-
int fscrypt_zeroout_range(const struct inode *inode, pgoff_t lblk,
sector_t pblk, unsigned int len)
{
diff --git a/fs/crypto/crypto.c b/fs/crypto/crypto.c
index 32a7ad0098cc..3719efa546c6 100644
--- a/fs/crypto/crypto.c
+++ b/fs/crypto/crypto.c
@@ -27,29 +27,20 @@
#include <linux/ratelimit.h>
#include <linux/dcache.h>
#include <linux/namei.h>
-#include <crypto/aes.h>
#include <crypto/skcipher.h>
#include "fscrypt_private.h"
static unsigned int num_prealloc_crypto_pages = 32;
-static unsigned int num_prealloc_crypto_ctxs = 128;
module_param(num_prealloc_crypto_pages, uint, 0444);
MODULE_PARM_DESC(num_prealloc_crypto_pages,
"Number of crypto pages to preallocate");
-module_param(num_prealloc_crypto_ctxs, uint, 0444);
-MODULE_PARM_DESC(num_prealloc_crypto_ctxs,
- "Number of crypto contexts to preallocate");
static mempool_t *fscrypt_bounce_page_pool = NULL;
-static LIST_HEAD(fscrypt_free_ctxs);
-static DEFINE_SPINLOCK(fscrypt_ctx_lock);
-
static struct workqueue_struct *fscrypt_read_workqueue;
static DEFINE_MUTEX(fscrypt_init_mutex);
-static struct kmem_cache *fscrypt_ctx_cachep;
struct kmem_cache *fscrypt_info_cachep;
void fscrypt_enqueue_decrypt_work(struct work_struct *work)
@@ -58,62 +49,6 @@ void fscrypt_enqueue_decrypt_work(struct work_struct *work)
}
EXPORT_SYMBOL(fscrypt_enqueue_decrypt_work);
-/**
- * fscrypt_release_ctx() - Release a decryption context
- * @ctx: The decryption context to release.
- *
- * If the decryption context was allocated from the pre-allocated pool, return
- * it to that pool. Else, free it.
- */
-void fscrypt_release_ctx(struct fscrypt_ctx *ctx)
-{
- unsigned long flags;
-
- if (ctx->flags & FS_CTX_REQUIRES_FREE_ENCRYPT_FL) {
- kmem_cache_free(fscrypt_ctx_cachep, ctx);
- } else {
- spin_lock_irqsave(&fscrypt_ctx_lock, flags);
- list_add(&ctx->free_list, &fscrypt_free_ctxs);
- spin_unlock_irqrestore(&fscrypt_ctx_lock, flags);
- }
-}
-EXPORT_SYMBOL(fscrypt_release_ctx);
-
-/**
- * fscrypt_get_ctx() - Get a decryption context
- * @gfp_flags: The gfp flag for memory allocation
- *
- * Allocate and initialize a decryption context.
- *
- * Return: A new decryption context on success; an ERR_PTR() otherwise.
- */
-struct fscrypt_ctx *fscrypt_get_ctx(gfp_t gfp_flags)
-{
- struct fscrypt_ctx *ctx;
- unsigned long flags;
-
- /*
- * First try getting a ctx from the free list so that we don't have to
- * call into the slab allocator.
- */
- spin_lock_irqsave(&fscrypt_ctx_lock, flags);
- ctx = list_first_entry_or_null(&fscrypt_free_ctxs,
- struct fscrypt_ctx, free_list);
- if (ctx)
- list_del(&ctx->free_list);
- spin_unlock_irqrestore(&fscrypt_ctx_lock, flags);
- if (!ctx) {
- ctx = kmem_cache_zalloc(fscrypt_ctx_cachep, gfp_flags);
- if (!ctx)
- return ERR_PTR(-ENOMEM);
- ctx->flags |= FS_CTX_REQUIRES_FREE_ENCRYPT_FL;
- } else {
- ctx->flags &= ~FS_CTX_REQUIRES_FREE_ENCRYPT_FL;
- }
- return ctx;
-}
-EXPORT_SYMBOL(fscrypt_get_ctx);
-
struct page *fscrypt_alloc_bounce_page(gfp_t gfp_flags)
{
return mempool_alloc(fscrypt_bounce_page_pool, gfp_flags);
@@ -138,14 +73,17 @@ EXPORT_SYMBOL(fscrypt_free_bounce_page);
void fscrypt_generate_iv(union fscrypt_iv *iv, u64 lblk_num,
const struct fscrypt_info *ci)
{
+ u8 flags = fscrypt_policy_flags(&ci->ci_policy);
+
memset(iv, 0, ci->ci_mode->ivsize);
- iv->lblk_num = cpu_to_le64(lblk_num);
- if (fscrypt_is_direct_key_policy(&ci->ci_policy))
+ if (flags & FSCRYPT_POLICY_FLAG_IV_INO_LBLK_64) {
+ WARN_ON_ONCE((u32)lblk_num != lblk_num);
+ lblk_num |= (u64)ci->ci_inode->i_ino << 32;
+ } else if (flags & FSCRYPT_POLICY_FLAG_DIRECT_KEY) {
memcpy(iv->nonce, ci->ci_nonce, FS_KEY_DERIVATION_NONCE_SIZE);
-
- if (ci->ci_essiv_tfm != NULL)
- crypto_cipher_encrypt_one(ci->ci_essiv_tfm, iv->raw, iv->raw);
+ }
+ iv->lblk_num = cpu_to_le64(lblk_num);
}
/* Encrypt or decrypt a single filesystem block of file contents */
@@ -396,17 +334,6 @@ const struct dentry_operations fscrypt_d_ops = {
.d_revalidate = fscrypt_d_revalidate,
};
-static void fscrypt_destroy(void)
-{
- struct fscrypt_ctx *pos, *n;
-
- list_for_each_entry_safe(pos, n, &fscrypt_free_ctxs, free_list)
- kmem_cache_free(fscrypt_ctx_cachep, pos);
- INIT_LIST_HEAD(&fscrypt_free_ctxs);
- mempool_destroy(fscrypt_bounce_page_pool);
- fscrypt_bounce_page_pool = NULL;
-}
-
/**
* fscrypt_initialize() - allocate major buffers for fs encryption.
* @cop_flags: fscrypt operations flags
@@ -414,11 +341,11 @@ static void fscrypt_destroy(void)
* We only call this when we start accessing encrypted files, since it
* results in memory getting allocated that wouldn't otherwise be used.
*
- * Return: Zero on success, non-zero otherwise.
+ * Return: 0 on success; -errno on failure
*/
int fscrypt_initialize(unsigned int cop_flags)
{
- int i, res = -ENOMEM;
+ int err = 0;
/* No need to allocate a bounce page pool if this FS won't use it. */
if (cop_flags & FS_CFLG_OWN_PAGES)
@@ -426,29 +353,18 @@ int fscrypt_initialize(unsigned int cop_flags)
mutex_lock(&fscrypt_init_mutex);
if (fscrypt_bounce_page_pool)
- goto already_initialized;
-
- for (i = 0; i < num_prealloc_crypto_ctxs; i++) {
- struct fscrypt_ctx *ctx;
-
- ctx = kmem_cache_zalloc(fscrypt_ctx_cachep, GFP_NOFS);
- if (!ctx)
- goto fail;
- list_add(&ctx->free_list, &fscrypt_free_ctxs);
- }
+ goto out_unlock;
+ err = -ENOMEM;
fscrypt_bounce_page_pool =
mempool_create_page_pool(num_prealloc_crypto_pages, 0);
if (!fscrypt_bounce_page_pool)
- goto fail;
+ goto out_unlock;
-already_initialized:
- mutex_unlock(&fscrypt_init_mutex);
- return 0;
-fail:
- fscrypt_destroy();
+ err = 0;
+out_unlock:
mutex_unlock(&fscrypt_init_mutex);
- return res;
+ return err;
}
void fscrypt_msg(const struct inode *inode, const char *level,
@@ -494,13 +410,9 @@ static int __init fscrypt_init(void)
if (!fscrypt_read_workqueue)
goto fail;
- fscrypt_ctx_cachep = KMEM_CACHE(fscrypt_ctx, SLAB_RECLAIM_ACCOUNT);
- if (!fscrypt_ctx_cachep)
- goto fail_free_queue;
-
fscrypt_info_cachep = KMEM_CACHE(fscrypt_info, SLAB_RECLAIM_ACCOUNT);
if (!fscrypt_info_cachep)
- goto fail_free_ctx;
+ goto fail_free_queue;
err = fscrypt_init_keyring();
if (err)
@@ -510,8 +422,6 @@ static int __init fscrypt_init(void)
fail_free_info:
kmem_cache_destroy(fscrypt_info_cachep);
-fail_free_ctx:
- kmem_cache_destroy(fscrypt_ctx_cachep);
fail_free_queue:
destroy_workqueue(fscrypt_read_workqueue);
fail:
diff --git a/fs/crypto/fscrypt_private.h b/fs/crypto/fscrypt_private.h
index e84efc01512e..130b50e5a011 100644
--- a/fs/crypto/fscrypt_private.h
+++ b/fs/crypto/fscrypt_private.h
@@ -163,11 +163,8 @@ struct fscrypt_info {
/* The actual crypto transform used for encryption and decryption */
struct crypto_skcipher *ci_ctfm;
- /*
- * Cipher for ESSIV IV generation. Only set for CBC contents
- * encryption, otherwise is NULL.
- */
- struct crypto_cipher *ci_essiv_tfm;
+ /* True if the key should be freed when this fscrypt_info is freed */
+ bool ci_owns_key;
/*
* Encryption mode used for this inode. It corresponds to either the
@@ -209,8 +206,6 @@ typedef enum {
FS_ENCRYPT,
} fscrypt_direction_t;
-#define FS_CTX_REQUIRES_FREE_ENCRYPT_FL 0x00000001
-
static inline bool fscrypt_valid_enc_modes(u32 contents_mode,
u32 filenames_mode)
{
@@ -289,7 +284,8 @@ extern int fscrypt_init_hkdf(struct fscrypt_hkdf *hkdf, const u8 *master_key,
*/
#define HKDF_CONTEXT_KEY_IDENTIFIER 1
#define HKDF_CONTEXT_PER_FILE_KEY 2
-#define HKDF_CONTEXT_PER_MODE_KEY 3
+#define HKDF_CONTEXT_DIRECT_KEY 3
+#define HKDF_CONTEXT_IV_INO_LBLK_64_KEY 4
extern int fscrypt_hkdf_expand(struct fscrypt_hkdf *hkdf, u8 context,
const u8 *info, unsigned int infolen,
@@ -386,8 +382,14 @@ struct fscrypt_master_key {
struct list_head mk_decrypted_inodes;
spinlock_t mk_decrypted_inodes_lock;
- /* Per-mode tfms for DIRECT_KEY policies, allocated on-demand */
- struct crypto_skcipher *mk_mode_keys[__FSCRYPT_MODE_MAX + 1];
+ /* Crypto API transforms for DIRECT_KEY policies, allocated on-demand */
+ struct crypto_skcipher *mk_direct_tfms[__FSCRYPT_MODE_MAX + 1];
+
+ /*
+ * Crypto API transforms for filesystem-layer implementation of
+ * IV_INO_LBLK_64 policies, allocated on-demand.
+ */
+ struct crypto_skcipher *mk_iv_ino_lblk_64_tfms[__FSCRYPT_MODE_MAX + 1];
} __randomize_layout;
@@ -443,8 +445,7 @@ struct fscrypt_mode {
const char *cipher_str;
int keysize;
int ivsize;
- bool logged_impl_name;
- bool needs_essiv;
+ int logged_impl_name;
};
static inline bool
diff --git a/fs/crypto/keyring.c b/fs/crypto/keyring.c
index c34fa7c61b43..040df1f5e1c8 100644
--- a/fs/crypto/keyring.c
+++ b/fs/crypto/keyring.c
@@ -43,8 +43,10 @@ static void free_master_key(struct fscrypt_master_key *mk)
wipe_master_key_secret(&mk->mk_secret);
- for (i = 0; i < ARRAY_SIZE(mk->mk_mode_keys); i++)
- crypto_free_skcipher(mk->mk_mode_keys[i]);
+ for (i = 0; i <= __FSCRYPT_MODE_MAX; i++) {
+ crypto_free_skcipher(mk->mk_direct_tfms[i]);
+ crypto_free_skcipher(mk->mk_iv_ino_lblk_64_tfms[i]);
+ }
key_put(mk->mk_users);
kzfree(mk);
diff --git a/fs/crypto/keysetup.c b/fs/crypto/keysetup.c
index d71c2d6dd162..f577bb6613f9 100644
--- a/fs/crypto/keysetup.c
+++ b/fs/crypto/keysetup.c
@@ -8,15 +8,11 @@
* Heavily modified since then.
*/
-#include <crypto/aes.h>
-#include <crypto/sha.h>
#include <crypto/skcipher.h>
#include <linux/key.h>
#include "fscrypt_private.h"
-static struct crypto_shash *essiv_hash_tfm;
-
static struct fscrypt_mode available_modes[] = {
[FSCRYPT_MODE_AES_256_XTS] = {
.friendly_name = "AES-256-XTS",
@@ -31,11 +27,10 @@ static struct fscrypt_mode available_modes[] = {
.ivsize = 16,
},
[FSCRYPT_MODE_AES_128_CBC] = {
- .friendly_name = "AES-128-CBC",
- .cipher_str = "cbc(aes)",
+ .friendly_name = "AES-128-CBC-ESSIV",
+ .cipher_str = "essiv(cbc(aes),sha256)",
.keysize = 16,
.ivsize = 16,
- .needs_essiv = true,
},
[FSCRYPT_MODE_AES_128_CTS] = {
.friendly_name = "AES-128-CTS-CBC",
@@ -86,15 +81,13 @@ struct crypto_skcipher *fscrypt_allocate_skcipher(struct fscrypt_mode *mode,
mode->cipher_str, PTR_ERR(tfm));
return tfm;
}
- if (unlikely(!mode->logged_impl_name)) {
+ if (!xchg(&mode->logged_impl_name, 1)) {
/*
* fscrypt performance can vary greatly depending on which
* crypto algorithm implementation is used. Help people debug
* performance problems by logging the ->cra_driver_name the
- * first time a mode is used. Note that multiple threads can
- * race here, but it doesn't really matter.
+ * first time a mode is used.
*/
- mode->logged_impl_name = true;
pr_info("fscrypt: %s using implementation \"%s\"\n",
mode->friendly_name,
crypto_skcipher_alg(tfm)->base.cra_driver_name);
@@ -111,131 +104,64 @@ err_free_tfm:
return ERR_PTR(err);
}
-static int derive_essiv_salt(const u8 *key, int keysize, u8 *salt)
-{
- struct crypto_shash *tfm = READ_ONCE(essiv_hash_tfm);
-
- /* init hash transform on demand */
- if (unlikely(!tfm)) {
- struct crypto_shash *prev_tfm;
-
- tfm = crypto_alloc_shash("sha256", 0, 0);
- if (IS_ERR(tfm)) {
- if (PTR_ERR(tfm) == -ENOENT) {
- fscrypt_warn(NULL,
- "Missing crypto API support for SHA-256");
- return -ENOPKG;
- }
- fscrypt_err(NULL,
- "Error allocating SHA-256 transform: %ld",
- PTR_ERR(tfm));
- return PTR_ERR(tfm);
- }
- prev_tfm = cmpxchg(&essiv_hash_tfm, NULL, tfm);
- if (prev_tfm) {
- crypto_free_shash(tfm);
- tfm = prev_tfm;
- }
- }
-
- {
- SHASH_DESC_ON_STACK(desc, tfm);
- desc->tfm = tfm;
-
- return crypto_shash_digest(desc, key, keysize, salt);
- }
-}
-
-static int init_essiv_generator(struct fscrypt_info *ci, const u8 *raw_key,
- int keysize)
-{
- int err;
- struct crypto_cipher *essiv_tfm;
- u8 salt[SHA256_DIGEST_SIZE];
-
- if (WARN_ON(ci->ci_mode->ivsize != AES_BLOCK_SIZE))
- return -EINVAL;
-
- essiv_tfm = crypto_alloc_cipher("aes", 0, 0);
- if (IS_ERR(essiv_tfm))
- return PTR_ERR(essiv_tfm);
-
- ci->ci_essiv_tfm = essiv_tfm;
-
- err = derive_essiv_salt(raw_key, keysize, salt);
- if (err)
- goto out;
-
- /*
- * Using SHA256 to derive the salt/key will result in AES-256 being
- * used for IV generation. File contents encryption will still use the
- * configured keysize (AES-128) nevertheless.
- */
- err = crypto_cipher_setkey(essiv_tfm, salt, sizeof(salt));
- if (err)
- goto out;
-
-out:
- memzero_explicit(salt, sizeof(salt));
- return err;
-}
-
-/* Given the per-file key, set up the file's crypto transform object(s) */
+/* Given the per-file key, set up the file's crypto transform object */
int fscrypt_set_derived_key(struct fscrypt_info *ci, const u8 *derived_key)
{
- struct fscrypt_mode *mode = ci->ci_mode;
- struct crypto_skcipher *ctfm;
- int err;
-
- ctfm = fscrypt_allocate_skcipher(mode, derived_key, ci->ci_inode);
- if (IS_ERR(ctfm))
- return PTR_ERR(ctfm);
+ struct crypto_skcipher *tfm;
- ci->ci_ctfm = ctfm;
+ tfm = fscrypt_allocate_skcipher(ci->ci_mode, derived_key, ci->ci_inode);
+ if (IS_ERR(tfm))
+ return PTR_ERR(tfm);
- if (mode->needs_essiv) {
- err = init_essiv_generator(ci, derived_key, mode->keysize);
- if (err) {
- fscrypt_warn(ci->ci_inode,
- "Error initializing ESSIV generator: %d",
- err);
- return err;
- }
- }
+ ci->ci_ctfm = tfm;
+ ci->ci_owns_key = true;
return 0;
}
static int setup_per_mode_key(struct fscrypt_info *ci,
- struct fscrypt_master_key *mk)
+ struct fscrypt_master_key *mk,
+ struct crypto_skcipher **tfms,
+ u8 hkdf_context, bool include_fs_uuid)
{
+ const struct inode *inode = ci->ci_inode;
+ const struct super_block *sb = inode->i_sb;
struct fscrypt_mode *mode = ci->ci_mode;
u8 mode_num = mode - available_modes;
struct crypto_skcipher *tfm, *prev_tfm;
u8 mode_key[FSCRYPT_MAX_KEY_SIZE];
+ u8 hkdf_info[sizeof(mode_num) + sizeof(sb->s_uuid)];
+ unsigned int hkdf_infolen = 0;
int err;
- if (WARN_ON(mode_num >= ARRAY_SIZE(mk->mk_mode_keys)))
+ if (WARN_ON(mode_num > __FSCRYPT_MODE_MAX))
return -EINVAL;
/* pairs with cmpxchg() below */
- tfm = READ_ONCE(mk->mk_mode_keys[mode_num]);
+ tfm = READ_ONCE(tfms[mode_num]);
if (likely(tfm != NULL))
goto done;
BUILD_BUG_ON(sizeof(mode_num) != 1);
+ BUILD_BUG_ON(sizeof(sb->s_uuid) != 16);
+ BUILD_BUG_ON(sizeof(hkdf_info) != 17);
+ hkdf_info[hkdf_infolen++] = mode_num;
+ if (include_fs_uuid) {
+ memcpy(&hkdf_info[hkdf_infolen], &sb->s_uuid,
+ sizeof(sb->s_uuid));
+ hkdf_infolen += sizeof(sb->s_uuid);
+ }
err = fscrypt_hkdf_expand(&mk->mk_secret.hkdf,
- HKDF_CONTEXT_PER_MODE_KEY,
- &mode_num, sizeof(mode_num),
+ hkdf_context, hkdf_info, hkdf_infolen,
mode_key, mode->keysize);
if (err)
return err;
- tfm = fscrypt_allocate_skcipher(mode, mode_key, ci->ci_inode);
+ tfm = fscrypt_allocate_skcipher(mode, mode_key, inode);
memzero_explicit(mode_key, mode->keysize);
if (IS_ERR(tfm))
return PTR_ERR(tfm);
/* pairs with READ_ONCE() above */
- prev_tfm = cmpxchg(&mk->mk_mode_keys[mode_num], NULL, tfm);
+ prev_tfm = cmpxchg(&tfms[mode_num], NULL, tfm);
if (prev_tfm != NULL) {
crypto_free_skcipher(tfm);
tfm = prev_tfm;
@@ -266,7 +192,19 @@ static int fscrypt_setup_v2_file_key(struct fscrypt_info *ci,
ci->ci_mode->friendly_name);
return -EINVAL;
}
- return setup_per_mode_key(ci, mk);
+ return setup_per_mode_key(ci, mk, mk->mk_direct_tfms,
+ HKDF_CONTEXT_DIRECT_KEY, false);
+ } else if (ci->ci_policy.v2.flags &
+ FSCRYPT_POLICY_FLAG_IV_INO_LBLK_64) {
+ /*
+ * IV_INO_LBLK_64: encryption keys are derived from (master_key,
+ * mode_num, filesystem_uuid), and inode number is included in
+ * the IVs. This format is optimized for use with inline
+ * encryption hardware compliant with the UFS or eMMC standards.
+ */
+ return setup_per_mode_key(ci, mk, mk->mk_iv_ino_lblk_64_tfms,
+ HKDF_CONTEXT_IV_INO_LBLK_64_KEY,
+ true);
}
err = fscrypt_hkdf_expand(&mk->mk_secret.hkdf,
@@ -388,13 +326,10 @@ static void put_crypt_info(struct fscrypt_info *ci)
if (!ci)
return;
- if (ci->ci_direct_key) {
+ if (ci->ci_direct_key)
fscrypt_put_direct_key(ci->ci_direct_key);
- } else if ((ci->ci_ctfm != NULL || ci->ci_essiv_tfm != NULL) &&
- !fscrypt_is_direct_key_policy(&ci->ci_policy)) {
+ else if (ci->ci_owns_key)
crypto_free_skcipher(ci->ci_ctfm);
- crypto_free_cipher(ci->ci_essiv_tfm);
- }
key = ci->ci_master_key;
if (key) {
@@ -415,6 +350,7 @@ static void put_crypt_info(struct fscrypt_info *ci)
key_invalidate(key);
key_put(key);
}
+ memzero_explicit(ci, sizeof(*ci));
kmem_cache_free(fscrypt_info_cachep, ci);
}
diff --git a/fs/crypto/keysetup_v1.c b/fs/crypto/keysetup_v1.c
index ad1a36c370c3..5298ef22aa85 100644
--- a/fs/crypto/keysetup_v1.c
+++ b/fs/crypto/keysetup_v1.c
@@ -270,10 +270,6 @@ static int setup_v1_file_key_direct(struct fscrypt_info *ci,
return -EINVAL;
}
- /* ESSIV implies 16-byte IVs which implies !DIRECT_KEY */
- if (WARN_ON(mode->needs_essiv))
- return -EINVAL;
-
dk = fscrypt_get_direct_key(ci, raw_master_key);
if (IS_ERR(dk))
return PTR_ERR(dk);
diff --git a/fs/crypto/policy.c b/fs/crypto/policy.c
index 4072ba644595..96f528071bed 100644
--- a/fs/crypto/policy.c
+++ b/fs/crypto/policy.c
@@ -29,6 +29,40 @@ bool fscrypt_policies_equal(const union fscrypt_policy *policy1,
return !memcmp(policy1, policy2, fscrypt_policy_size(policy1));
}
+static bool supported_iv_ino_lblk_64_policy(
+ const struct fscrypt_policy_v2 *policy,
+ const struct inode *inode)
+{
+ struct super_block *sb = inode->i_sb;
+ int ino_bits = 64, lblk_bits = 64;
+
+ if (policy->flags & FSCRYPT_POLICY_FLAG_DIRECT_KEY) {
+ fscrypt_warn(inode,
+ "The DIRECT_KEY and IV_INO_LBLK_64 flags are mutually exclusive");
+ return false;
+ }
+ /*
+ * It's unsafe to include inode numbers in the IVs if the filesystem can
+ * potentially renumber inodes, e.g. via filesystem shrinking.
+ */
+ if (!sb->s_cop->has_stable_inodes ||
+ !sb->s_cop->has_stable_inodes(sb)) {
+ fscrypt_warn(inode,
+ "Can't use IV_INO_LBLK_64 policy on filesystem '%s' because it doesn't have stable inode numbers",
+ sb->s_id);
+ return false;
+ }
+ if (sb->s_cop->get_ino_and_lblk_bits)
+ sb->s_cop->get_ino_and_lblk_bits(sb, &ino_bits, &lblk_bits);
+ if (ino_bits > 32 || lblk_bits > 32) {
+ fscrypt_warn(inode,
+ "Can't use IV_INO_LBLK_64 policy on filesystem '%s' because it doesn't use 32-bit inode and block numbers",
+ sb->s_id);
+ return false;
+ }
+ return true;
+}
+
/**
* fscrypt_supported_policy - check whether an encryption policy is supported
*
@@ -55,7 +89,8 @@ bool fscrypt_supported_policy(const union fscrypt_policy *policy_u,
return false;
}
- if (policy->flags & ~FSCRYPT_POLICY_FLAGS_VALID) {
+ if (policy->flags & ~(FSCRYPT_POLICY_FLAGS_PAD_MASK |
+ FSCRYPT_POLICY_FLAG_DIRECT_KEY)) {
fscrypt_warn(inode,
"Unsupported encryption flags (0x%02x)",
policy->flags);
@@ -83,6 +118,10 @@ bool fscrypt_supported_policy(const union fscrypt_policy *policy_u,
return false;
}
+ if ((policy->flags & FSCRYPT_POLICY_FLAG_IV_INO_LBLK_64) &&
+ !supported_iv_ino_lblk_64_policy(policy, inode))
+ return false;
+
if (memchr_inv(policy->__reserved, 0,
sizeof(policy->__reserved))) {
fscrypt_warn(inode,
diff --git a/fs/dax.c b/fs/dax.c
index 68eef98cd9c4..1f1f0201cad1 100644
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -220,10 +220,11 @@ static void *get_unlocked_entry(struct xa_state *xas, unsigned int order)
for (;;) {
entry = xas_find_conflict(xas);
+ if (!entry || WARN_ON_ONCE(!xa_is_value(entry)))
+ return entry;
if (dax_entry_order(entry) < order)
return XA_RETRY_ENTRY;
- if (!entry || WARN_ON_ONCE(!xa_is_value(entry)) ||
- !dax_is_locked(entry))
+ if (!dax_is_locked(entry))
return entry;
wq = dax_entry_waitqueue(xas, entry, &ewait.key);
diff --git a/fs/dcache.c b/fs/dcache.c
index e88cf0554e65..a2749a700230 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -319,7 +319,7 @@ static inline void __d_set_inode_and_type(struct dentry *dentry,
flags = READ_ONCE(dentry->d_flags);
flags &= ~(DCACHE_ENTRY_TYPE | DCACHE_FALLTHRU);
flags |= type_flags;
- WRITE_ONCE(dentry->d_flags, flags);
+ smp_store_release(&dentry->d_flags, flags);
}
static inline void __d_clear_type_and_inode(struct dentry *dentry)
@@ -903,17 +903,19 @@ struct dentry *dget_parent(struct dentry *dentry)
{
int gotref;
struct dentry *ret;
+ unsigned seq;
/*
* Do optimistic parent lookup without any
* locking.
*/
rcu_read_lock();
+ seq = raw_seqcount_begin(&dentry->d_seq);
ret = READ_ONCE(dentry->d_parent);
gotref = lockref_get_not_zero(&ret->d_lockref);
rcu_read_unlock();
if (likely(gotref)) {
- if (likely(ret == READ_ONCE(dentry->d_parent)))
+ if (!read_seqcount_retry(&dentry->d_seq, seq))
return ret;
dput(ret);
}
@@ -1319,7 +1321,7 @@ resume:
if (!list_empty(&dentry->d_subdirs)) {
spin_unlock(&this_parent->d_lock);
- spin_release(&dentry->d_lock.dep_map, 1, _RET_IP_);
+ spin_release(&dentry->d_lock.dep_map, _RET_IP_);
this_parent = dentry;
spin_acquire(&this_parent->d_lock.dep_map, 0, 1, _RET_IP_);
goto repeat;
diff --git a/fs/debugfs/file.c b/fs/debugfs/file.c
index 87846aad594b..dede25247b81 100644
--- a/fs/debugfs/file.c
+++ b/fs/debugfs/file.c
@@ -420,20 +420,11 @@ DEFINE_DEBUGFS_ATTRIBUTE(fops_u8_wo, NULL, debugfs_u8_set, "%llu\n");
* This function creates a file in debugfs with the given name that
* contains the value of the variable @value. If the @mode variable is so
* set, it can be read from, and written to.
- *
- * This function will return a pointer to a dentry if it succeeds. This
- * pointer must be passed to the debugfs_remove() function when the file is
- * to be removed (no automatic cleanup happens if your module is unloaded,
- * you are responsible here.) If an error occurs, %ERR_PTR(-ERROR) will be
- * returned.
- *
- * If debugfs is not enabled in the kernel, the value %ERR_PTR(-ENODEV) will
- * be returned.
*/
-struct dentry *debugfs_create_u8(const char *name, umode_t mode,
- struct dentry *parent, u8 *value)
+void debugfs_create_u8(const char *name, umode_t mode, struct dentry *parent,
+ u8 *value)
{
- return debugfs_create_mode_unsafe(name, mode, parent, value, &fops_u8,
+ debugfs_create_mode_unsafe(name, mode, parent, value, &fops_u8,
&fops_u8_ro, &fops_u8_wo);
}
EXPORT_SYMBOL_GPL(debugfs_create_u8);
@@ -465,20 +456,11 @@ DEFINE_DEBUGFS_ATTRIBUTE(fops_u16_wo, NULL, debugfs_u16_set, "%llu\n");
* This function creates a file in debugfs with the given name that
* contains the value of the variable @value. If the @mode variable is so
* set, it can be read from, and written to.
- *
- * This function will return a pointer to a dentry if it succeeds. This
- * pointer must be passed to the debugfs_remove() function when the file is
- * to be removed (no automatic cleanup happens if your module is unloaded,
- * you are responsible here.) If an error occurs, %ERR_PTR(-ERROR) will be
- * returned.
- *
- * If debugfs is not enabled in the kernel, the value %ERR_PTR(-ENODEV) will
- * be returned.
*/
-struct dentry *debugfs_create_u16(const char *name, umode_t mode,
- struct dentry *parent, u16 *value)
+void debugfs_create_u16(const char *name, umode_t mode, struct dentry *parent,
+ u16 *value)
{
- return debugfs_create_mode_unsafe(name, mode, parent, value, &fops_u16,
+ debugfs_create_mode_unsafe(name, mode, parent, value, &fops_u16,
&fops_u16_ro, &fops_u16_wo);
}
EXPORT_SYMBOL_GPL(debugfs_create_u16);
@@ -556,20 +538,11 @@ DEFINE_DEBUGFS_ATTRIBUTE(fops_u64_wo, NULL, debugfs_u64_set, "%llu\n");
* This function creates a file in debugfs with the given name that
* contains the value of the variable @value. If the @mode variable is so
* set, it can be read from, and written to.
- *
- * This function will return a pointer to a dentry if it succeeds. This
- * pointer must be passed to the debugfs_remove() function when the file is
- * to be removed (no automatic cleanup happens if your module is unloaded,
- * you are responsible here.) If an error occurs, %ERR_PTR(-ERROR) will be
- * returned.
- *
- * If debugfs is not enabled in the kernel, the value %ERR_PTR(-ENODEV) will
- * be returned.
*/
-struct dentry *debugfs_create_u64(const char *name, umode_t mode,
- struct dentry *parent, u64 *value)
+void debugfs_create_u64(const char *name, umode_t mode, struct dentry *parent,
+ u64 *value)
{
- return debugfs_create_mode_unsafe(name, mode, parent, value, &fops_u64,
+ debugfs_create_mode_unsafe(name, mode, parent, value, &fops_u64,
&fops_u64_ro, &fops_u64_wo);
}
EXPORT_SYMBOL_GPL(debugfs_create_u64);
@@ -660,10 +633,10 @@ DEFINE_DEBUGFS_ATTRIBUTE(fops_x64_wo, NULL, debugfs_u64_set, "0x%016llx\n");
* @value: a pointer to the variable that the file should read to and write
* from.
*/
-struct dentry *debugfs_create_x8(const char *name, umode_t mode,
- struct dentry *parent, u8 *value)
+void debugfs_create_x8(const char *name, umode_t mode, struct dentry *parent,
+ u8 *value)
{
- return debugfs_create_mode_unsafe(name, mode, parent, value, &fops_x8,
+ debugfs_create_mode_unsafe(name, mode, parent, value, &fops_x8,
&fops_x8_ro, &fops_x8_wo);
}
EXPORT_SYMBOL_GPL(debugfs_create_x8);
@@ -678,10 +651,10 @@ EXPORT_SYMBOL_GPL(debugfs_create_x8);
* @value: a pointer to the variable that the file should read to and write
* from.
*/
-struct dentry *debugfs_create_x16(const char *name, umode_t mode,
- struct dentry *parent, u16 *value)
+void debugfs_create_x16(const char *name, umode_t mode, struct dentry *parent,
+ u16 *value)
{
- return debugfs_create_mode_unsafe(name, mode, parent, value, &fops_x16,
+ debugfs_create_mode_unsafe(name, mode, parent, value, &fops_x16,
&fops_x16_ro, &fops_x16_wo);
}
EXPORT_SYMBOL_GPL(debugfs_create_x16);
@@ -696,10 +669,10 @@ EXPORT_SYMBOL_GPL(debugfs_create_x16);
* @value: a pointer to the variable that the file should read to and write
* from.
*/
-struct dentry *debugfs_create_x32(const char *name, umode_t mode,
- struct dentry *parent, u32 *value)
+void debugfs_create_x32(const char *name, umode_t mode, struct dentry *parent,
+ u32 *value)
{
- return debugfs_create_mode_unsafe(name, mode, parent, value, &fops_x32,
+ debugfs_create_mode_unsafe(name, mode, parent, value, &fops_x32,
&fops_x32_ro, &fops_x32_wo);
}
EXPORT_SYMBOL_GPL(debugfs_create_x32);
@@ -714,10 +687,10 @@ EXPORT_SYMBOL_GPL(debugfs_create_x32);
* @value: a pointer to the variable that the file should read to and write
* from.
*/
-struct dentry *debugfs_create_x64(const char *name, umode_t mode,
- struct dentry *parent, u64 *value)
+void debugfs_create_x64(const char *name, umode_t mode, struct dentry *parent,
+ u64 *value)
{
- return debugfs_create_mode_unsafe(name, mode, parent, value, &fops_x64,
+ debugfs_create_mode_unsafe(name, mode, parent, value, &fops_x64,
&fops_x64_ro, &fops_x64_wo);
}
EXPORT_SYMBOL_GPL(debugfs_create_x64);
@@ -748,12 +721,11 @@ DEFINE_DEBUGFS_ATTRIBUTE(fops_size_t_wo, NULL, debugfs_size_t_set, "%llu\n");
* @value: a pointer to the variable that the file should read to and write
* from.
*/
-struct dentry *debugfs_create_size_t(const char *name, umode_t mode,
- struct dentry *parent, size_t *value)
+void debugfs_create_size_t(const char *name, umode_t mode,
+ struct dentry *parent, size_t *value)
{
- return debugfs_create_mode_unsafe(name, mode, parent, value,
- &fops_size_t, &fops_size_t_ro,
- &fops_size_t_wo);
+ debugfs_create_mode_unsafe(name, mode, parent, value, &fops_size_t,
+ &fops_size_t_ro, &fops_size_t_wo);
}
EXPORT_SYMBOL_GPL(debugfs_create_size_t);
@@ -785,12 +757,11 @@ DEFINE_DEBUGFS_ATTRIBUTE(fops_atomic_t_wo, NULL, debugfs_atomic_t_set,
* @value: a pointer to the variable that the file should read to and write
* from.
*/
-struct dentry *debugfs_create_atomic_t(const char *name, umode_t mode,
- struct dentry *parent, atomic_t *value)
+void debugfs_create_atomic_t(const char *name, umode_t mode,
+ struct dentry *parent, atomic_t *value)
{
- return debugfs_create_mode_unsafe(name, mode, parent, value,
- &fops_atomic_t, &fops_atomic_t_ro,
- &fops_atomic_t_wo);
+ debugfs_create_mode_unsafe(name, mode, parent, value, &fops_atomic_t,
+ &fops_atomic_t_ro, &fops_atomic_t_wo);
}
EXPORT_SYMBOL_GPL(debugfs_create_atomic_t);
diff --git a/fs/debugfs/inode.c b/fs/debugfs/inode.c
index 7b975dbb2bb4..f4d8df5e4714 100644
--- a/fs/debugfs/inode.c
+++ b/fs/debugfs/inode.c
@@ -299,13 +299,9 @@ struct dentry *debugfs_lookup(const char *name, struct dentry *parent)
if (!parent)
parent = debugfs_mount->mnt_root;
- dentry = lookup_one_len_unlocked(name, parent, strlen(name));
+ dentry = lookup_positive_unlocked(name, parent, strlen(name));
if (IS_ERR(dentry))
return NULL;
- if (!d_really_is_positive(dentry)) {
- dput(dentry);
- return NULL;
- }
return dentry;
}
EXPORT_SYMBOL_GPL(debugfs_lookup);
diff --git a/fs/direct-io.c b/fs/direct-io.c
index ae196784f487..0ec4f270139f 100644
--- a/fs/direct-io.c
+++ b/fs/direct-io.c
@@ -221,29 +221,7 @@ static inline struct page *dio_get_page(struct dio *dio,
}
/*
- * Warn about a page cache invalidation failure during a direct io write.
- */
-void dio_warn_stale_pagecache(struct file *filp)
-{
- static DEFINE_RATELIMIT_STATE(_rs, 86400 * HZ, DEFAULT_RATELIMIT_BURST);
- char pathname[128];
- struct inode *inode = file_inode(filp);
- char *path;
-
- errseq_set(&inode->i_mapping->wb_err, -EIO);
- if (__ratelimit(&_rs)) {
- path = file_path(filp, pathname, sizeof(pathname));
- if (IS_ERR(path))
- path = "(unknown)";
- pr_crit("Page cache invalidation failure on direct I/O. Possible data corruption due to collision with buffered I/O!\n");
- pr_crit("File: %s PID: %d Comm: %.20s\n", path, current->pid,
- current->comm);
- }
-}
-
-/**
* dio_complete() - called when all DIO BIO I/O has been completed
- * @offset: the byte offset in the file of the completed operation
*
* This drops i_dio_count, lets interested parties know that a DIO operation
* has completed, and calculates the resulting return code for the operation.
diff --git a/fs/ecryptfs/file.c b/fs/ecryptfs/file.c
index feecb57defa7..5fb45d865ce5 100644
--- a/fs/ecryptfs/file.c
+++ b/fs/ecryptfs/file.c
@@ -378,6 +378,7 @@ ecryptfs_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
return rc;
switch (cmd) {
+ case FITRIM:
case FS_IOC32_GETFLAGS:
case FS_IOC32_SETFLAGS:
case FS_IOC32_GETVERSION:
diff --git a/fs/ecryptfs/inode.c b/fs/ecryptfs/inode.c
index 18426f4855f1..e23752d9a79f 100644
--- a/fs/ecryptfs/inode.c
+++ b/fs/ecryptfs/inode.c
@@ -128,13 +128,20 @@ static int ecryptfs_do_unlink(struct inode *dir, struct dentry *dentry,
struct inode *inode)
{
struct dentry *lower_dentry = ecryptfs_dentry_to_lower(dentry);
- struct inode *lower_dir_inode = ecryptfs_inode_to_lower(dir);
struct dentry *lower_dir_dentry;
+ struct inode *lower_dir_inode;
int rc;
- dget(lower_dentry);
- lower_dir_dentry = lock_parent(lower_dentry);
- rc = vfs_unlink(lower_dir_inode, lower_dentry, NULL);
+ lower_dir_dentry = ecryptfs_dentry_to_lower(dentry->d_parent);
+ lower_dir_inode = d_inode(lower_dir_dentry);
+ inode_lock_nested(lower_dir_inode, I_MUTEX_PARENT);
+ dget(lower_dentry); // don't even try to make the lower negative
+ if (lower_dentry->d_parent != lower_dir_dentry)
+ rc = -EINVAL;
+ else if (d_unhashed(lower_dentry))
+ rc = -EINVAL;
+ else
+ rc = vfs_unlink(lower_dir_inode, lower_dentry, NULL);
if (rc) {
printk(KERN_ERR "Error in vfs_unlink; rc = [%d]\n", rc);
goto out_unlock;
@@ -142,10 +149,11 @@ static int ecryptfs_do_unlink(struct inode *dir, struct dentry *dentry,
fsstack_copy_attr_times(dir, lower_dir_inode);
set_nlink(inode, ecryptfs_inode_to_lower(inode)->i_nlink);
inode->i_ctime = dir->i_ctime;
- d_drop(dentry);
out_unlock:
- unlock_dir(lower_dir_dentry);
dput(lower_dentry);
+ inode_unlock(lower_dir_inode);
+ if (!rc)
+ d_drop(dentry);
return rc;
}
@@ -311,9 +319,9 @@ static int ecryptfs_i_size_read(struct dentry *dentry, struct inode *inode)
static struct dentry *ecryptfs_lookup_interpose(struct dentry *dentry,
struct dentry *lower_dentry)
{
- struct inode *inode, *lower_inode = d_inode(lower_dentry);
+ struct path *path = ecryptfs_dentry_to_lower_path(dentry->d_parent);
+ struct inode *inode, *lower_inode;
struct ecryptfs_dentry_info *dentry_info;
- struct vfsmount *lower_mnt;
int rc = 0;
dentry_info = kmem_cache_alloc(ecryptfs_dentry_info_cache, GFP_KERNEL);
@@ -322,16 +330,23 @@ static struct dentry *ecryptfs_lookup_interpose(struct dentry *dentry,
return ERR_PTR(-ENOMEM);
}
- lower_mnt = mntget(ecryptfs_dentry_to_lower_mnt(dentry->d_parent));
fsstack_copy_attr_atime(d_inode(dentry->d_parent),
- d_inode(lower_dentry->d_parent));
+ d_inode(path->dentry));
BUG_ON(!d_count(lower_dentry));
ecryptfs_set_dentry_private(dentry, dentry_info);
- dentry_info->lower_path.mnt = lower_mnt;
+ dentry_info->lower_path.mnt = mntget(path->mnt);
dentry_info->lower_path.dentry = lower_dentry;
- if (d_really_is_negative(lower_dentry)) {
+ /*
+ * negative dentry can go positive under us here - its parent is not
+ * locked. That's OK and that could happen just as we return from
+ * ecryptfs_lookup() anyway. Just need to be careful and fetch
+ * ->d_inode only once - it's not stable here.
+ */
+ lower_inode = READ_ONCE(lower_dentry->d_inode);
+
+ if (!lower_inode) {
/* We want to add because we couldn't find in lower */
d_add(dentry, NULL);
return NULL;
@@ -512,22 +527,30 @@ static int ecryptfs_rmdir(struct inode *dir, struct dentry *dentry)
{
struct dentry *lower_dentry;
struct dentry *lower_dir_dentry;
+ struct inode *lower_dir_inode;
int rc;
lower_dentry = ecryptfs_dentry_to_lower(dentry);
- dget(dentry);
- lower_dir_dentry = lock_parent(lower_dentry);
- dget(lower_dentry);
- rc = vfs_rmdir(d_inode(lower_dir_dentry), lower_dentry);
- dput(lower_dentry);
- if (!rc && d_really_is_positive(dentry))
+ lower_dir_dentry = ecryptfs_dentry_to_lower(dentry->d_parent);
+ lower_dir_inode = d_inode(lower_dir_dentry);
+
+ inode_lock_nested(lower_dir_inode, I_MUTEX_PARENT);
+ dget(lower_dentry); // don't even try to make the lower negative
+ if (lower_dentry->d_parent != lower_dir_dentry)
+ rc = -EINVAL;
+ else if (d_unhashed(lower_dentry))
+ rc = -EINVAL;
+ else
+ rc = vfs_rmdir(lower_dir_inode, lower_dentry);
+ if (!rc) {
clear_nlink(d_inode(dentry));
- fsstack_copy_attr_times(dir, d_inode(lower_dir_dentry));
- set_nlink(dir, d_inode(lower_dir_dentry)->i_nlink);
- unlock_dir(lower_dir_dentry);
+ fsstack_copy_attr_times(dir, lower_dir_inode);
+ set_nlink(dir, lower_dir_inode->i_nlink);
+ }
+ dput(lower_dentry);
+ inode_unlock(lower_dir_inode);
if (!rc)
d_drop(dentry);
- dput(dentry);
return rc;
}
@@ -565,20 +588,22 @@ ecryptfs_rename(struct inode *old_dir, struct dentry *old_dentry,
struct dentry *lower_new_dentry;
struct dentry *lower_old_dir_dentry;
struct dentry *lower_new_dir_dentry;
- struct dentry *trap = NULL;
+ struct dentry *trap;
struct inode *target_inode;
if (flags)
return -EINVAL;
+ lower_old_dir_dentry = ecryptfs_dentry_to_lower(old_dentry->d_parent);
+ lower_new_dir_dentry = ecryptfs_dentry_to_lower(new_dentry->d_parent);
+
lower_old_dentry = ecryptfs_dentry_to_lower(old_dentry);
lower_new_dentry = ecryptfs_dentry_to_lower(new_dentry);
- dget(lower_old_dentry);
- dget(lower_new_dentry);
- lower_old_dir_dentry = dget_parent(lower_old_dentry);
- lower_new_dir_dentry = dget_parent(lower_new_dentry);
+
target_inode = d_inode(new_dentry);
+
trap = lock_rename(lower_old_dir_dentry, lower_new_dir_dentry);
+ dget(lower_new_dentry);
rc = -EINVAL;
if (lower_old_dentry->d_parent != lower_old_dir_dentry)
goto out_lock;
@@ -606,11 +631,8 @@ ecryptfs_rename(struct inode *old_dir, struct dentry *old_dentry,
if (new_dir != old_dir)
fsstack_copy_attr_all(old_dir, d_inode(lower_old_dir_dentry));
out_lock:
- unlock_rename(lower_old_dir_dentry, lower_new_dir_dentry);
- dput(lower_new_dir_dentry);
- dput(lower_old_dir_dentry);
dput(lower_new_dentry);
- dput(lower_old_dentry);
+ unlock_rename(lower_old_dir_dentry, lower_new_dir_dentry);
return rc;
}
diff --git a/fs/erofs/Kconfig b/fs/erofs/Kconfig
index 9d634d3a1845..74b0aaa7114c 100644
--- a/fs/erofs/Kconfig
+++ b/fs/erofs/Kconfig
@@ -3,6 +3,7 @@
config EROFS_FS
tristate "EROFS filesystem support"
depends on BLOCK
+ select LIBCRC32C
help
EROFS (Enhanced Read-Only File System) is a lightweight
read-only file system with modern designs (eg. page-sized
diff --git a/fs/erofs/decompressor.c b/fs/erofs/decompressor.c
index 19f89f9fb10c..2890a67a1ded 100644
--- a/fs/erofs/decompressor.c
+++ b/fs/erofs/decompressor.c
@@ -73,7 +73,7 @@ static int z_erofs_lz4_prepare_destpages(struct z_erofs_decompress_req *rq,
victim = availables[--top];
get_page(victim);
} else {
- victim = erofs_allocpage(pagepool, GFP_KERNEL, false);
+ victim = erofs_allocpage(pagepool, GFP_KERNEL);
if (!victim)
return -ENOMEM;
victim->mapping = Z_EROFS_MAPPING_STAGING;
diff --git a/fs/erofs/erofs_fs.h b/fs/erofs/erofs_fs.h
index b1ee5654750d..385fa49c7749 100644
--- a/fs/erofs/erofs_fs.h
+++ b/fs/erofs/erofs_fs.h
@@ -11,6 +11,8 @@
#define EROFS_SUPER_OFFSET 1024
+#define EROFS_FEATURE_COMPAT_SB_CHKSUM 0x00000001
+
/*
* Any bits that aren't in EROFS_ALL_FEATURE_INCOMPAT should
* be incompatible with this kernel version.
@@ -37,7 +39,6 @@ struct erofs_super_block {
__u8 uuid[16]; /* 128-bit uuid for volume */
__u8 volume_name[16]; /* volume name */
__le32 feature_incompat;
-
__u8 reserved2[44];
};
diff --git a/fs/erofs/internal.h b/fs/erofs/internal.h
index 544a453f3076..1ed5beff7d11 100644
--- a/fs/erofs/internal.h
+++ b/fs/erofs/internal.h
@@ -85,6 +85,7 @@ struct erofs_sb_info {
u8 uuid[16]; /* 128-bit uuid for volume */
u8 volume_name[16]; /* volume name */
+ u32 feature_compat;
u32 feature_incompat;
unsigned int mount_opt;
@@ -278,9 +279,7 @@ static inline unsigned int erofs_inode_datalayout(unsigned int value)
extern const struct super_operations erofs_sops;
extern const struct address_space_operations erofs_raw_access_aops;
-#ifdef CONFIG_EROFS_FS_ZIP
-extern const struct address_space_operations z_erofs_vle_normalaccess_aops;
-#endif
+extern const struct address_space_operations z_erofs_aops;
/*
* Logical to physical block mapping, used by erofs_map_blocks()
@@ -382,7 +381,7 @@ int erofs_namei(struct inode *dir, struct qstr *name,
extern const struct file_operations erofs_dir_fops;
/* utils.c / zdata.c */
-struct page *erofs_allocpage(struct list_head *pool, gfp_t gfp, bool nofail);
+struct page *erofs_allocpage(struct list_head *pool, gfp_t gfp);
#if (EROFS_PCPUBUF_NR_PAGES > 0)
void *erofs_get_pcpubuf(unsigned int pagenr);
diff --git a/fs/erofs/super.c b/fs/erofs/super.c
index 0e369494f2f2..057e6d7b5b7f 100644
--- a/fs/erofs/super.c
+++ b/fs/erofs/super.c
@@ -9,6 +9,7 @@
#include <linux/statfs.h>
#include <linux/parser.h>
#include <linux/seq_file.h>
+#include <linux/crc32c.h>
#include "xattr.h"
#define CREATE_TRACE_POINTS
@@ -46,6 +47,30 @@ void _erofs_info(struct super_block *sb, const char *function,
va_end(args);
}
+static int erofs_superblock_csum_verify(struct super_block *sb, void *sbdata)
+{
+ struct erofs_super_block *dsb;
+ u32 expected_crc, crc;
+
+ dsb = kmemdup(sbdata + EROFS_SUPER_OFFSET,
+ EROFS_BLKSIZ - EROFS_SUPER_OFFSET, GFP_KERNEL);
+ if (!dsb)
+ return -ENOMEM;
+
+ expected_crc = le32_to_cpu(dsb->checksum);
+ dsb->checksum = 0;
+ /* to allow for x86 boot sectors and other oddities. */
+ crc = crc32c(~0, dsb, EROFS_BLKSIZ - EROFS_SUPER_OFFSET);
+ kfree(dsb);
+
+ if (crc != expected_crc) {
+ erofs_err(sb, "invalid checksum 0x%08x, 0x%08x expected",
+ crc, expected_crc);
+ return -EBADMSG;
+ }
+ return 0;
+}
+
static void erofs_inode_init_once(void *ptr)
{
struct erofs_inode *vi = ptr;
@@ -112,7 +137,7 @@ static int erofs_read_superblock(struct super_block *sb)
sbi = EROFS_SB(sb);
- data = kmap_atomic(page);
+ data = kmap(page);
dsb = (struct erofs_super_block *)(data + EROFS_SUPER_OFFSET);
ret = -EINVAL;
@@ -121,6 +146,13 @@ static int erofs_read_superblock(struct super_block *sb)
goto out;
}
+ sbi->feature_compat = le32_to_cpu(dsb->feature_compat);
+ if (sbi->feature_compat & EROFS_FEATURE_COMPAT_SB_CHKSUM) {
+ ret = erofs_superblock_csum_verify(sb, data);
+ if (ret)
+ goto out;
+ }
+
blkszbits = dsb->blkszbits;
/* 9(512 bytes) + LOG_SECTORS_PER_BLOCK == LOG_BLOCK_SIZE */
if (blkszbits != LOG_BLOCK_SIZE) {
@@ -155,7 +187,7 @@ static int erofs_read_superblock(struct super_block *sb)
}
ret = 0;
out:
- kunmap_atomic(data);
+ kunmap(page);
put_page(page);
return ret;
}
@@ -566,9 +598,6 @@ static int erofs_show_options(struct seq_file *seq, struct dentry *root)
seq_puts(seq, ",cache_strategy=readahead");
} else if (sbi->cache_strategy == EROFS_ZIP_CACHE_READAROUND) {
seq_puts(seq, ",cache_strategy=readaround");
- } else {
- seq_puts(seq, ",cache_strategy=(unknown)");
- DBG_BUGON(1);
}
#endif
return 0;
diff --git a/fs/erofs/utils.c b/fs/erofs/utils.c
index d92b3e753a6f..1e8e1450d5b0 100644
--- a/fs/erofs/utils.c
+++ b/fs/erofs/utils.c
@@ -7,7 +7,7 @@
#include "internal.h"
#include <linux/pagevec.h>
-struct page *erofs_allocpage(struct list_head *pool, gfp_t gfp, bool nofail)
+struct page *erofs_allocpage(struct list_head *pool, gfp_t gfp)
{
struct page *page;
@@ -16,7 +16,7 @@ struct page *erofs_allocpage(struct list_head *pool, gfp_t gfp, bool nofail)
DBG_BUGON(page_ref_count(page) != 1);
list_del(&page->lru);
} else {
- page = alloc_pages(gfp | (nofail ? __GFP_NOFAIL : 0), 0);
+ page = alloc_page(gfp);
}
return page;
}
@@ -149,8 +149,7 @@ static void erofs_workgroup_unfreeze_final(struct erofs_workgroup *grp)
}
static bool erofs_try_to_release_workgroup(struct erofs_sb_info *sbi,
- struct erofs_workgroup *grp,
- bool cleanup)
+ struct erofs_workgroup *grp)
{
/*
* If managed cache is on, refcount of workgroups
@@ -188,8 +187,7 @@ static bool erofs_try_to_release_workgroup(struct erofs_sb_info *sbi,
}
static unsigned long erofs_shrink_workstation(struct erofs_sb_info *sbi,
- unsigned long nr_shrink,
- bool cleanup)
+ unsigned long nr_shrink)
{
pgoff_t first_index = 0;
void *batch[PAGEVEC_SIZE];
@@ -208,7 +206,7 @@ repeat:
first_index = grp->index + 1;
/* try to shrink each valid workgroup */
- if (!erofs_try_to_release_workgroup(sbi, grp, cleanup))
+ if (!erofs_try_to_release_workgroup(sbi, grp))
continue;
++freed;
@@ -245,7 +243,8 @@ void erofs_shrinker_unregister(struct super_block *sb)
struct erofs_sb_info *const sbi = EROFS_SB(sb);
mutex_lock(&sbi->umount_mutex);
- erofs_shrink_workstation(sbi, ~0UL, true);
+ /* clean up all remaining workgroups in memory */
+ erofs_shrink_workstation(sbi, ~0UL);
spin_lock(&erofs_sb_list_lock);
list_del(&sbi->list);
@@ -294,7 +293,7 @@ static unsigned long erofs_shrink_scan(struct shrinker *shrink,
spin_unlock(&erofs_sb_list_lock);
sbi->shrinker_run_no = run_no;
- freed += erofs_shrink_workstation(sbi, nr, false);
+ freed += erofs_shrink_workstation(sbi, nr);
spin_lock(&erofs_sb_list_lock);
/* Get the next list element before we move this one */
diff --git a/fs/erofs/zdata.c b/fs/erofs/zdata.c
index fad80c97d247..ca99425a4536 100644
--- a/fs/erofs/zdata.c
+++ b/fs/erofs/zdata.c
@@ -337,9 +337,9 @@ retry:
return COLLECT_PRIMARY; /* :( better luck next time */
}
-static struct z_erofs_collection *cllookup(struct z_erofs_collector *clt,
- struct inode *inode,
- struct erofs_map_blocks *map)
+static int z_erofs_lookup_collection(struct z_erofs_collector *clt,
+ struct inode *inode,
+ struct erofs_map_blocks *map)
{
struct erofs_workgroup *grp;
struct z_erofs_pcluster *pcl;
@@ -349,20 +349,20 @@ static struct z_erofs_collection *cllookup(struct z_erofs_collector *clt,
grp = erofs_find_workgroup(inode->i_sb, map->m_pa >> PAGE_SHIFT, &tag);
if (!grp)
- return NULL;
+ return -ENOENT;
pcl = container_of(grp, struct z_erofs_pcluster, obj);
if (clt->owned_head == &pcl->next || pcl == clt->tailpcl) {
DBG_BUGON(1);
erofs_workgroup_put(grp);
- return ERR_PTR(-EFSCORRUPTED);
+ return -EFSCORRUPTED;
}
cl = z_erofs_primarycollection(pcl);
if (cl->pageofs != (map->m_la & ~PAGE_MASK)) {
DBG_BUGON(1);
erofs_workgroup_put(grp);
- return ERR_PTR(-EFSCORRUPTED);
+ return -EFSCORRUPTED;
}
length = READ_ONCE(pcl->length);
@@ -370,7 +370,7 @@ static struct z_erofs_collection *cllookup(struct z_erofs_collector *clt,
if ((map->m_llen << Z_EROFS_PCLUSTER_LENGTH_BIT) > length) {
DBG_BUGON(1);
erofs_workgroup_put(grp);
- return ERR_PTR(-EFSCORRUPTED);
+ return -EFSCORRUPTED;
}
} else {
unsigned int llen = map->m_llen << Z_EROFS_PCLUSTER_LENGTH_BIT;
@@ -394,12 +394,12 @@ static struct z_erofs_collection *cllookup(struct z_erofs_collector *clt,
clt->tailpcl = NULL;
clt->pcl = pcl;
clt->cl = cl;
- return cl;
+ return 0;
}
-static struct z_erofs_collection *clregister(struct z_erofs_collector *clt,
- struct inode *inode,
- struct erofs_map_blocks *map)
+static int z_erofs_register_collection(struct z_erofs_collector *clt,
+ struct inode *inode,
+ struct erofs_map_blocks *map)
{
struct z_erofs_pcluster *pcl;
struct z_erofs_collection *cl;
@@ -408,7 +408,7 @@ static struct z_erofs_collection *clregister(struct z_erofs_collector *clt,
/* no available workgroup, let's allocate one */
pcl = kmem_cache_alloc(pcluster_cachep, GFP_NOFS);
if (!pcl)
- return ERR_PTR(-ENOMEM);
+ return -ENOMEM;
z_erofs_pcluster_init_always(pcl);
pcl->obj.index = map->m_pa >> PAGE_SHIFT;
@@ -442,7 +442,7 @@ static struct z_erofs_collection *clregister(struct z_erofs_collector *clt,
if (err) {
mutex_unlock(&cl->lock);
kmem_cache_free(pcluster_cachep, pcl);
- return ERR_PTR(-EAGAIN);
+ return -EAGAIN;
}
/* used to check tail merging loop due to corrupted images */
if (clt->owned_head == Z_EROFS_PCLUSTER_TAIL)
@@ -450,14 +450,14 @@ static struct z_erofs_collection *clregister(struct z_erofs_collector *clt,
clt->owned_head = &pcl->next;
clt->pcl = pcl;
clt->cl = cl;
- return cl;
+ return 0;
}
static int z_erofs_collector_begin(struct z_erofs_collector *clt,
struct inode *inode,
struct erofs_map_blocks *map)
{
- struct z_erofs_collection *cl;
+ int ret;
DBG_BUGON(clt->cl);
@@ -471,19 +471,22 @@ static int z_erofs_collector_begin(struct z_erofs_collector *clt,
}
repeat:
- cl = cllookup(clt, inode, map);
- if (!cl) {
- cl = clregister(clt, inode, map);
+ ret = z_erofs_lookup_collection(clt, inode, map);
+ if (ret == -ENOENT) {
+ ret = z_erofs_register_collection(clt, inode, map);
- if (cl == ERR_PTR(-EAGAIN))
+ /* someone registered at the same time, give another try */
+ if (ret == -EAGAIN) {
+ cond_resched();
goto repeat;
+ }
}
- if (IS_ERR(cl))
- return PTR_ERR(cl);
+ if (ret)
+ return ret;
z_erofs_pagevec_ctor_init(&clt->vector, Z_EROFS_NR_INLINE_PAGEVECS,
- cl->pagevec, cl->vcnt);
+ clt->cl->pagevec, clt->cl->vcnt);
clt->compressedpages = clt->pcl->compressed_pages;
if (clt->mode <= COLLECT_PRIMARY) /* cannot do in-place I/O */
@@ -543,15 +546,6 @@ static bool z_erofs_collector_end(struct z_erofs_collector *clt)
return true;
}
-static inline struct page *__stagingpage_alloc(struct list_head *pagepool,
- gfp_t gfp)
-{
- struct page *page = erofs_allocpage(pagepool, gfp, true);
-
- page->mapping = Z_EROFS_MAPPING_STAGING;
- return page;
-}
-
static bool should_alloc_managed_pages(struct z_erofs_decompress_frontend *fe,
unsigned int cachestrategy,
erofs_off_t la)
@@ -571,7 +565,7 @@ static int z_erofs_do_read_page(struct z_erofs_decompress_frontend *fe,
struct list_head *pagepool)
{
struct inode *const inode = fe->inode;
- struct erofs_sb_info *const sbi __maybe_unused = EROFS_I_SB(inode);
+ struct erofs_sb_info *const sbi = EROFS_I_SB(inode);
struct erofs_map_blocks *const map = &fe->map;
struct z_erofs_collector *const clt = &fe->clt;
const loff_t offset = page_offset(page);
@@ -658,8 +652,9 @@ retry:
/* should allocate an additional staging page for pagevec */
if (err == -EAGAIN) {
struct page *const newpage =
- __stagingpage_alloc(pagepool, GFP_NOFS);
+ erofs_allocpage(pagepool, GFP_NOFS | __GFP_NOFAIL);
+ newpage->mapping = Z_EROFS_MAPPING_STAGING;
err = z_erofs_attach_page(clt, newpage,
Z_EROFS_PAGE_TYPE_EXCLUSIVE);
if (!err)
@@ -698,13 +693,11 @@ err_out:
goto out;
}
-static void z_erofs_vle_unzip_kickoff(void *ptr, int bios)
+static void z_erofs_decompress_kickoff(struct z_erofs_decompressqueue *io,
+ bool sync, int bios)
{
- tagptr1_t t = tagptr_init(tagptr1_t, ptr);
- struct z_erofs_unzip_io *io = tagptr_unfold_ptr(t);
- bool background = tagptr_unfold_tags(t);
-
- if (!background) {
+ /* wake up the caller thread for sync decompression */
+ if (sync) {
unsigned long flags;
spin_lock_irqsave(&io->u.wait.lock, flags);
@@ -718,37 +711,30 @@ static void z_erofs_vle_unzip_kickoff(void *ptr, int bios)
queue_work(z_erofs_workqueue, &io->u.work);
}
-static inline void z_erofs_vle_read_endio(struct bio *bio)
+static void z_erofs_decompressqueue_endio(struct bio *bio)
{
- struct erofs_sb_info *sbi = NULL;
+ tagptr1_t t = tagptr_init(tagptr1_t, bio->bi_private);
+ struct z_erofs_decompressqueue *q = tagptr_unfold_ptr(t);
blk_status_t err = bio->bi_status;
struct bio_vec *bvec;
struct bvec_iter_all iter_all;
bio_for_each_segment_all(bvec, bio, iter_all) {
struct page *page = bvec->bv_page;
- bool cachemngd = false;
DBG_BUGON(PageUptodate(page));
DBG_BUGON(!page->mapping);
- if (!sbi && !z_erofs_page_is_staging(page))
- sbi = EROFS_SB(page->mapping->host->i_sb);
-
- /* sbi should already be gotten if the page is managed */
- if (sbi)
- cachemngd = erofs_page_is_managed(sbi, page);
-
if (err)
SetPageError(page);
- else if (cachemngd)
- SetPageUptodate(page);
- if (cachemngd)
+ if (erofs_page_is_managed(EROFS_SB(q->sb), page)) {
+ if (!err)
+ SetPageUptodate(page);
unlock_page(page);
+ }
}
-
- z_erofs_vle_unzip_kickoff(bio->bi_private, -1);
+ z_erofs_decompress_kickoff(q, tagptr_unfold_tags(t), -1);
bio_put(bio);
}
@@ -953,9 +939,8 @@ out:
return err;
}
-static void z_erofs_vle_unzip_all(struct super_block *sb,
- struct z_erofs_unzip_io *io,
- struct list_head *pagepool)
+static void z_erofs_decompress_queue(const struct z_erofs_decompressqueue *io,
+ struct list_head *pagepool)
{
z_erofs_next_pcluster_t owned = io->head;
@@ -971,21 +956,21 @@ static void z_erofs_vle_unzip_all(struct super_block *sb,
pcl = container_of(owned, struct z_erofs_pcluster, next);
owned = READ_ONCE(pcl->next);
- z_erofs_decompress_pcluster(sb, pcl, pagepool);
+ z_erofs_decompress_pcluster(io->sb, pcl, pagepool);
}
}
-static void z_erofs_vle_unzip_wq(struct work_struct *work)
+static void z_erofs_decompressqueue_work(struct work_struct *work)
{
- struct z_erofs_unzip_io_sb *iosb =
- container_of(work, struct z_erofs_unzip_io_sb, io.u.work);
+ struct z_erofs_decompressqueue *bgq =
+ container_of(work, struct z_erofs_decompressqueue, u.work);
LIST_HEAD(pagepool);
- DBG_BUGON(iosb->io.head == Z_EROFS_PCLUSTER_TAIL_CLOSED);
- z_erofs_vle_unzip_all(iosb->sb, &iosb->io, &pagepool);
+ DBG_BUGON(bgq->head == Z_EROFS_PCLUSTER_TAIL_CLOSED);
+ z_erofs_decompress_queue(bgq, &pagepool);
put_pages_list(&pagepool);
- kvfree(iosb);
+ kvfree(bgq);
}
static struct page *pickup_page_for_submission(struct z_erofs_pcluster *pcl,
@@ -994,8 +979,6 @@ static struct page *pickup_page_for_submission(struct z_erofs_pcluster *pcl,
struct address_space *mc,
gfp_t gfp)
{
- /* determined at compile time to avoid too many #ifdefs */
- const bool nocache = __builtin_constant_p(mc) ? !mc : false;
const pgoff_t index = pcl->obj.index;
bool tocache = false;
@@ -1016,7 +999,7 @@ repeat:
* the cached page has not been allocated and
* an placeholder is out there, prepare it now.
*/
- if (!nocache && page == PAGE_UNALLOCATED) {
+ if (page == PAGE_UNALLOCATED) {
tocache = true;
goto out_allocpage;
}
@@ -1029,21 +1012,6 @@ repeat:
mapping = READ_ONCE(page->mapping);
/*
- * if managed cache is disabled, it's no way to
- * get such a cached-like page.
- */
- if (nocache) {
- /* if managed cache is disabled, it is impossible `justfound' */
- DBG_BUGON(justfound);
-
- /* and it should be locked, not uptodate, and not truncated */
- DBG_BUGON(!PageLocked(page));
- DBG_BUGON(PageUptodate(page));
- DBG_BUGON(!mapping);
- goto out;
- }
-
- /*
* unmanaged (file) pages are all locked solidly,
* therefore it is impossible for `mapping' to be NULL.
*/
@@ -1093,50 +1061,52 @@ repeat:
unlock_page(page);
put_page(page);
out_allocpage:
- page = __stagingpage_alloc(pagepool, gfp);
- if (oldpage != cmpxchg(&pcl->compressed_pages[nr], oldpage, page)) {
- list_add(&page->lru, pagepool);
- cpu_relax();
- goto repeat;
- }
- if (nocache || !tocache)
- goto out;
- if (add_to_page_cache_lru(page, mc, index + nr, gfp)) {
+ page = erofs_allocpage(pagepool, gfp | __GFP_NOFAIL);
+ if (!tocache || add_to_page_cache_lru(page, mc, index + nr, gfp)) {
+ /* non-LRU / non-movable temporary page is needed */
page->mapping = Z_EROFS_MAPPING_STAGING;
- goto out;
+ tocache = false;
}
+ if (oldpage != cmpxchg(&pcl->compressed_pages[nr], oldpage, page)) {
+ if (tocache) {
+ /* since it added to managed cache successfully */
+ unlock_page(page);
+ put_page(page);
+ } else {
+ list_add(&page->lru, pagepool);
+ }
+ cond_resched();
+ goto repeat;
+ }
set_page_private(page, (unsigned long)pcl);
SetPagePrivate(page);
out: /* the only exit (for tracing and debugging) */
return page;
}
-static struct z_erofs_unzip_io *jobqueue_init(struct super_block *sb,
- struct z_erofs_unzip_io *io,
- bool foreground)
+static struct z_erofs_decompressqueue *
+jobqueue_init(struct super_block *sb,
+ struct z_erofs_decompressqueue *fgq, bool *fg)
{
- struct z_erofs_unzip_io_sb *iosb;
-
- if (foreground) {
- /* waitqueue available for foreground io */
- DBG_BUGON(!io);
+ struct z_erofs_decompressqueue *q;
- init_waitqueue_head(&io->u.wait);
- atomic_set(&io->pending_bios, 0);
- goto out;
+ if (fg && !*fg) {
+ q = kvzalloc(sizeof(*q), GFP_KERNEL | __GFP_NOWARN);
+ if (!q) {
+ *fg = true;
+ goto fg_out;
+ }
+ INIT_WORK(&q->u.work, z_erofs_decompressqueue_work);
+ } else {
+fg_out:
+ q = fgq;
+ init_waitqueue_head(&fgq->u.wait);
+ atomic_set(&fgq->pending_bios, 0);
}
-
- iosb = kvzalloc(sizeof(*iosb), GFP_KERNEL | __GFP_NOFAIL);
- DBG_BUGON(!iosb);
-
- /* initialize fields in the allocated descriptor */
- io = &iosb->io;
- iosb->sb = sb;
- INIT_WORK(&io->u.work, z_erofs_vle_unzip_wq);
-out:
- io->head = Z_EROFS_PCLUSTER_TAIL_CLOSED;
- return io;
+ q->sb = sb;
+ q->head = Z_EROFS_PCLUSTER_TAIL_CLOSED;
+ return q;
}
/* define decompression jobqueue types */
@@ -1147,22 +1117,17 @@ enum {
};
static void *jobqueueset_init(struct super_block *sb,
- z_erofs_next_pcluster_t qtail[],
- struct z_erofs_unzip_io *q[],
- struct z_erofs_unzip_io *fgq,
- bool forcefg)
+ struct z_erofs_decompressqueue *q[],
+ struct z_erofs_decompressqueue *fgq, bool *fg)
{
/*
* if managed cache is enabled, bypass jobqueue is needed,
* no need to read from device for all pclusters in this queue.
*/
- q[JQ_BYPASS] = jobqueue_init(sb, fgq + JQ_BYPASS, true);
- qtail[JQ_BYPASS] = &q[JQ_BYPASS]->head;
-
- q[JQ_SUBMIT] = jobqueue_init(sb, fgq + JQ_SUBMIT, forcefg);
- qtail[JQ_SUBMIT] = &q[JQ_SUBMIT]->head;
+ q[JQ_BYPASS] = jobqueue_init(sb, fgq + JQ_BYPASS, NULL);
+ q[JQ_SUBMIT] = jobqueue_init(sb, fgq + JQ_SUBMIT, fg);
- return tagptr_cast_ptr(tagptr_fold(tagptr1_t, q[JQ_SUBMIT], !forcefg));
+ return tagptr_cast_ptr(tagptr_fold(tagptr1_t, q[JQ_SUBMIT], *fg));
}
static void move_to_bypass_jobqueue(struct z_erofs_pcluster *pcl,
@@ -1184,9 +1149,8 @@ static void move_to_bypass_jobqueue(struct z_erofs_pcluster *pcl,
qtail[JQ_BYPASS] = &pcl->next;
}
-static bool postsubmit_is_all_bypassed(struct z_erofs_unzip_io *q[],
- unsigned int nr_bios,
- bool force_fg)
+static bool postsubmit_is_all_bypassed(struct z_erofs_decompressqueue *q[],
+ unsigned int nr_bios, bool force_fg)
{
/*
* although background is preferred, no one is pending for submission.
@@ -1195,19 +1159,19 @@ static bool postsubmit_is_all_bypassed(struct z_erofs_unzip_io *q[],
if (force_fg || nr_bios)
return false;
- kvfree(container_of(q[JQ_SUBMIT], struct z_erofs_unzip_io_sb, io));
+ kvfree(q[JQ_SUBMIT]);
return true;
}
-static bool z_erofs_vle_submit_all(struct super_block *sb,
- z_erofs_next_pcluster_t owned_head,
- struct list_head *pagepool,
- struct z_erofs_unzip_io *fgq,
- bool force_fg)
+static bool z_erofs_submit_queue(struct super_block *sb,
+ z_erofs_next_pcluster_t owned_head,
+ struct list_head *pagepool,
+ struct z_erofs_decompressqueue *fgq,
+ bool *force_fg)
{
- struct erofs_sb_info *const sbi __maybe_unused = EROFS_SB(sb);
+ struct erofs_sb_info *const sbi = EROFS_SB(sb);
z_erofs_next_pcluster_t qtail[NR_JOBQUEUES];
- struct z_erofs_unzip_io *q[NR_JOBQUEUES];
+ struct z_erofs_decompressqueue *q[NR_JOBQUEUES];
struct bio *bio;
void *bi_private;
/* since bio will be NULL, no need to initialize last_index */
@@ -1221,7 +1185,9 @@ static bool z_erofs_vle_submit_all(struct super_block *sb,
force_submit = false;
bio = NULL;
nr_bios = 0;
- bi_private = jobqueueset_init(sb, qtail, q, fgq, force_fg);
+ bi_private = jobqueueset_init(sb, q, fgq, force_fg);
+ qtail[JQ_BYPASS] = &q[JQ_BYPASS]->head;
+ qtail[JQ_SUBMIT] = &q[JQ_SUBMIT]->head;
/* by default, all need io submission */
q[JQ_SUBMIT]->head = owned_head;
@@ -1268,7 +1234,7 @@ submit_bio_retry:
if (!bio) {
bio = bio_alloc(GFP_NOIO, BIO_MAX_PAGES);
- bio->bi_end_io = z_erofs_vle_read_endio;
+ bio->bi_end_io = z_erofs_decompressqueue_endio;
bio_set_dev(bio, sb->s_bdev);
bio->bi_iter.bi_sector = (sector_t)(first_index + i) <<
LOG_SECTORS_PER_BLOCK;
@@ -1297,40 +1263,38 @@ skippage:
if (bio)
submit_bio(bio);
- if (postsubmit_is_all_bypassed(q, nr_bios, force_fg))
+ if (postsubmit_is_all_bypassed(q, nr_bios, *force_fg))
return true;
- z_erofs_vle_unzip_kickoff(bi_private, nr_bios);
+ z_erofs_decompress_kickoff(q[JQ_SUBMIT], *force_fg, nr_bios);
return true;
}
-static void z_erofs_submit_and_unzip(struct super_block *sb,
- struct z_erofs_collector *clt,
- struct list_head *pagepool,
- bool force_fg)
+static void z_erofs_runqueue(struct super_block *sb,
+ struct z_erofs_collector *clt,
+ struct list_head *pagepool, bool force_fg)
{
- struct z_erofs_unzip_io io[NR_JOBQUEUES];
+ struct z_erofs_decompressqueue io[NR_JOBQUEUES];
- if (!z_erofs_vle_submit_all(sb, clt->owned_head,
- pagepool, io, force_fg))
+ if (!z_erofs_submit_queue(sb, clt->owned_head,
+ pagepool, io, &force_fg))
return;
- /* decompress no I/O pclusters immediately */
- z_erofs_vle_unzip_all(sb, &io[JQ_BYPASS], pagepool);
+ /* handle bypass queue (no i/o pclusters) immediately */
+ z_erofs_decompress_queue(&io[JQ_BYPASS], pagepool);
if (!force_fg)
return;
/* wait until all bios are completed */
- wait_event(io[JQ_SUBMIT].u.wait,
- !atomic_read(&io[JQ_SUBMIT].pending_bios));
+ io_wait_event(io[JQ_SUBMIT].u.wait,
+ !atomic_read(&io[JQ_SUBMIT].pending_bios));
- /* let's synchronous decompression */
- z_erofs_vle_unzip_all(sb, &io[JQ_SUBMIT], pagepool);
+ /* handle synchronous decompress queue in the caller context */
+ z_erofs_decompress_queue(&io[JQ_SUBMIT], pagepool);
}
-static int z_erofs_vle_normalaccess_readpage(struct file *file,
- struct page *page)
+static int z_erofs_readpage(struct file *file, struct page *page)
{
struct inode *const inode = page->mapping->host;
struct z_erofs_decompress_frontend f = DECOMPRESS_FRONTEND_INIT(inode);
@@ -1345,7 +1309,7 @@ static int z_erofs_vle_normalaccess_readpage(struct file *file,
(void)z_erofs_collector_end(&f.clt);
/* if some compressed cluster ready, need submit them anyway */
- z_erofs_submit_and_unzip(inode->i_sb, &f.clt, &pagepool, true);
+ z_erofs_runqueue(inode->i_sb, &f.clt, &pagepool, true);
if (err)
erofs_err(inode->i_sb, "failed to read, err [%d]", err);
@@ -1364,10 +1328,8 @@ static bool should_decompress_synchronously(struct erofs_sb_info *sbi,
return nr <= sbi->max_sync_decompress_pages;
}
-static int z_erofs_vle_normalaccess_readpages(struct file *filp,
- struct address_space *mapping,
- struct list_head *pages,
- unsigned int nr_pages)
+static int z_erofs_readpages(struct file *filp, struct address_space *mapping,
+ struct list_head *pages, unsigned int nr_pages)
{
struct inode *const inode = mapping->host;
struct erofs_sb_info *const sbi = EROFS_I_SB(inode);
@@ -1422,7 +1384,7 @@ static int z_erofs_vle_normalaccess_readpages(struct file *filp,
(void)z_erofs_collector_end(&f.clt);
- z_erofs_submit_and_unzip(inode->i_sb, &f.clt, &pagepool, sync);
+ z_erofs_runqueue(inode->i_sb, &f.clt, &pagepool, sync);
if (f.map.mpage)
put_page(f.map.mpage);
@@ -1432,8 +1394,8 @@ static int z_erofs_vle_normalaccess_readpages(struct file *filp,
return 0;
}
-const struct address_space_operations z_erofs_vle_normalaccess_aops = {
- .readpage = z_erofs_vle_normalaccess_readpage,
- .readpages = z_erofs_vle_normalaccess_readpages,
+const struct address_space_operations z_erofs_aops = {
+ .readpage = z_erofs_readpage,
+ .readpages = z_erofs_readpages,
};
diff --git a/fs/erofs/zdata.h b/fs/erofs/zdata.h
index faf950189bd7..7824f5563a55 100644
--- a/fs/erofs/zdata.h
+++ b/fs/erofs/zdata.h
@@ -84,7 +84,8 @@ struct z_erofs_pcluster {
#define Z_EROFS_WORKGROUP_SIZE sizeof(struct z_erofs_pcluster)
-struct z_erofs_unzip_io {
+struct z_erofs_decompressqueue {
+ struct super_block *sb;
atomic_t pending_bios;
z_erofs_next_pcluster_t head;
@@ -94,11 +95,6 @@ struct z_erofs_unzip_io {
} u;
};
-struct z_erofs_unzip_io_sb {
- struct z_erofs_unzip_io io;
- struct super_block *sb;
-};
-
#define MNGD_MAPPING(sbi) ((sbi)->managed_cache->i_mapping)
static inline bool erofs_page_is_managed(const struct erofs_sb_info *sbi,
struct page *page)
diff --git a/fs/erofs/zmap.c b/fs/erofs/zmap.c
index 6a26c293ae2d..736db3a4cdef 100644
--- a/fs/erofs/zmap.c
+++ b/fs/erofs/zmap.c
@@ -22,11 +22,11 @@ int z_erofs_fill_inode(struct inode *inode)
set_bit(EROFS_I_Z_INITED_BIT, &vi->flags);
}
- inode->i_mapping->a_ops = &z_erofs_vle_normalaccess_aops;
+ inode->i_mapping->a_ops = &z_erofs_aops;
return 0;
}
-static int fill_inode_lazy(struct inode *inode)
+static int z_erofs_fill_inode_lazy(struct inode *inode)
{
struct erofs_inode *const vi = EROFS_I(inode);
struct super_block *const sb = inode->i_sb;
@@ -138,8 +138,8 @@ static int z_erofs_reload_indexes(struct z_erofs_maprecorder *m,
return 0;
}
-static int vle_legacy_load_cluster_from_disk(struct z_erofs_maprecorder *m,
- unsigned long lcn)
+static int legacy_load_cluster_from_disk(struct z_erofs_maprecorder *m,
+ unsigned long lcn)
{
struct inode *const inode = m->inode;
struct erofs_inode *const vi = EROFS_I(inode);
@@ -311,13 +311,13 @@ out:
return unpack_compacted_index(m, amortizedshift, erofs_blkoff(pos));
}
-static int vle_load_cluster_from_disk(struct z_erofs_maprecorder *m,
- unsigned int lcn)
+static int z_erofs_load_cluster_from_disk(struct z_erofs_maprecorder *m,
+ unsigned int lcn)
{
const unsigned int datamode = EROFS_I(m->inode)->datalayout;
if (datamode == EROFS_INODE_FLAT_COMPRESSION_LEGACY)
- return vle_legacy_load_cluster_from_disk(m, lcn);
+ return legacy_load_cluster_from_disk(m, lcn);
if (datamode == EROFS_INODE_FLAT_COMPRESSION)
return compacted_load_cluster_from_disk(m, lcn);
@@ -325,8 +325,8 @@ static int vle_load_cluster_from_disk(struct z_erofs_maprecorder *m,
return -EINVAL;
}
-static int vle_extent_lookback(struct z_erofs_maprecorder *m,
- unsigned int lookback_distance)
+static int z_erofs_extent_lookback(struct z_erofs_maprecorder *m,
+ unsigned int lookback_distance)
{
struct erofs_inode *const vi = EROFS_I(m->inode);
struct erofs_map_blocks *const map = m->map;
@@ -343,7 +343,7 @@ static int vle_extent_lookback(struct z_erofs_maprecorder *m,
/* load extent head logical cluster if needed */
lcn -= lookback_distance;
- err = vle_load_cluster_from_disk(m, lcn);
+ err = z_erofs_load_cluster_from_disk(m, lcn);
if (err)
return err;
@@ -356,7 +356,7 @@ static int vle_extent_lookback(struct z_erofs_maprecorder *m,
DBG_BUGON(1);
return -EFSCORRUPTED;
}
- return vle_extent_lookback(m, m->delta[0]);
+ return z_erofs_extent_lookback(m, m->delta[0]);
case Z_EROFS_VLE_CLUSTER_TYPE_PLAIN:
map->m_flags &= ~EROFS_MAP_ZIPPED;
/* fallthrough */
@@ -396,7 +396,7 @@ int z_erofs_map_blocks_iter(struct inode *inode,
goto out;
}
- err = fill_inode_lazy(inode);
+ err = z_erofs_fill_inode_lazy(inode);
if (err)
goto out;
@@ -405,7 +405,7 @@ int z_erofs_map_blocks_iter(struct inode *inode,
m.lcn = ofs >> lclusterbits;
endoff = ofs & ((1 << lclusterbits) - 1);
- err = vle_load_cluster_from_disk(&m, m.lcn);
+ err = z_erofs_load_cluster_from_disk(&m, m.lcn);
if (err)
goto unmap_out;
@@ -436,7 +436,7 @@ int z_erofs_map_blocks_iter(struct inode *inode,
/* fallthrough */
case Z_EROFS_VLE_CLUSTER_TYPE_NONHEAD:
/* get the correspoinding first chunk */
- err = vle_extent_lookback(&m, m.delta[0]);
+ err = z_erofs_extent_lookback(&m, m.delta[0]);
if (err)
goto unmap_out;
break;
diff --git a/fs/eventpoll.c b/fs/eventpoll.c
index c4159bcc05d9..67a395039268 100644
--- a/fs/eventpoll.c
+++ b/fs/eventpoll.c
@@ -551,28 +551,23 @@ out_unlock:
*/
#ifdef CONFIG_DEBUG_LOCK_ALLOC
-static struct nested_calls poll_safewake_ncalls;
-
-static int ep_poll_wakeup_proc(void *priv, void *cookie, int call_nests)
-{
- unsigned long flags;
- wait_queue_head_t *wqueue = (wait_queue_head_t *)cookie;
-
- spin_lock_irqsave_nested(&wqueue->lock, flags, call_nests + 1);
- wake_up_locked_poll(wqueue, EPOLLIN);
- spin_unlock_irqrestore(&wqueue->lock, flags);
-
- return 0;
-}
+static DEFINE_PER_CPU(int, wakeup_nest);
static void ep_poll_safewake(wait_queue_head_t *wq)
{
- int this_cpu = get_cpu();
-
- ep_call_nested(&poll_safewake_ncalls,
- ep_poll_wakeup_proc, NULL, wq, (void *) (long) this_cpu);
+ unsigned long flags;
+ int subclass;
- put_cpu();
+ local_irq_save(flags);
+ preempt_disable();
+ subclass = __this_cpu_read(wakeup_nest);
+ spin_lock_nested(&wq->lock, subclass + 1);
+ __this_cpu_inc(wakeup_nest);
+ wake_up_locked_poll(wq, POLLIN);
+ __this_cpu_dec(wakeup_nest);
+ spin_unlock(&wq->lock);
+ local_irq_restore(flags);
+ preempt_enable();
}
#else
@@ -671,7 +666,6 @@ static __poll_t ep_scan_ready_list(struct eventpoll *ep,
void *priv, int depth, bool ep_locked)
{
__poll_t res;
- int pwake = 0;
struct epitem *epi, *nepi;
LIST_HEAD(txlist);
@@ -738,26 +732,11 @@ static __poll_t ep_scan_ready_list(struct eventpoll *ep,
*/
list_splice(&txlist, &ep->rdllist);
__pm_relax(ep->ws);
-
- if (!list_empty(&ep->rdllist)) {
- /*
- * Wake up (if active) both the eventpoll wait list and
- * the ->poll() wait list (delayed after we release the lock).
- */
- if (waitqueue_active(&ep->wq))
- wake_up(&ep->wq);
- if (waitqueue_active(&ep->poll_wait))
- pwake++;
- }
write_unlock_irq(&ep->lock);
if (!ep_locked)
mutex_unlock(&ep->mtx);
- /* We have to call this outside the lock */
- if (pwake)
- ep_poll_safewake(&ep->poll_wait);
-
return res;
}
@@ -2370,11 +2349,6 @@ static int __init eventpoll_init(void)
*/
ep_nested_calls_init(&poll_loop_ncalls);
-#ifdef CONFIG_DEBUG_LOCK_ALLOC
- /* Initialize the structure used to perform safe poll wait head wake ups */
- ep_nested_calls_init(&poll_safewake_ncalls);
-#endif
-
/*
* We can have many thousands of epitems, so prevent this from
* using an extra cache line on 64-bit (and smaller) CPUs
diff --git a/fs/exec.c b/fs/exec.c
index 555e93c7dec8..74d88dab98dd 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -59,7 +59,6 @@
#include <linux/kmod.h>
#include <linux/fsnotify.h>
#include <linux/fs_struct.h>
-#include <linux/pipe_fs_i.h>
#include <linux/oom.h>
#include <linux/compat.h>
#include <linux/vmalloc.h>
@@ -1015,7 +1014,7 @@ static int exec_mmap(struct mm_struct *mm)
/* Notify parent that we're no longer interested in the old VM */
tsk = current;
old_mm = current->mm;
- mm_release(tsk, old_mm);
+ exec_mm_release(tsk, old_mm);
if (old_mm) {
sync_mm_rss(old_mm);
@@ -1132,7 +1131,7 @@ static int de_thread(struct task_struct *tsk)
* also take its birthdate (always earlier than our own).
*/
tsk->start_time = leader->start_time;
- tsk->real_start_time = leader->real_start_time;
+ tsk->start_boottime = leader->start_boottime;
BUG_ON(!same_thread_group(leader, tsk));
BUG_ON(has_group_leader_pid(tsk));
diff --git a/fs/exportfs/expfs.c b/fs/exportfs/expfs.c
index 09bc68708d28..2dd55b172d57 100644
--- a/fs/exportfs/expfs.c
+++ b/fs/exportfs/expfs.c
@@ -519,26 +519,33 @@ struct dentry *exportfs_decode_fh(struct vfsmount *mnt, struct fid *fid,
* inode is actually connected to the parent.
*/
err = exportfs_get_name(mnt, target_dir, nbuf, result);
- if (!err) {
- inode_lock(target_dir->d_inode);
- nresult = lookup_one_len(nbuf, target_dir,
- strlen(nbuf));
- inode_unlock(target_dir->d_inode);
- if (!IS_ERR(nresult)) {
- if (nresult->d_inode) {
- dput(result);
- result = nresult;
- } else
- dput(nresult);
- }
+ if (err) {
+ dput(target_dir);
+ goto err_result;
}
+ inode_lock(target_dir->d_inode);
+ nresult = lookup_one_len(nbuf, target_dir, strlen(nbuf));
+ if (!IS_ERR(nresult)) {
+ if (unlikely(nresult->d_inode != result->d_inode)) {
+ dput(nresult);
+ nresult = ERR_PTR(-ESTALE);
+ }
+ }
+ inode_unlock(target_dir->d_inode);
/*
* At this point we are done with the parent, but it's pinned
* by the child dentry anyway.
*/
dput(target_dir);
+ if (IS_ERR(nresult)) {
+ err = PTR_ERR(nresult);
+ goto err_result;
+ }
+ dput(result);
+ result = nresult;
+
/*
* And finally make sure the dentry is actually acceptable
* to NFSD.
diff --git a/fs/ext2/balloc.c b/fs/ext2/balloc.c
index e0cc55164505..fa9c951d3471 100644
--- a/fs/ext2/balloc.c
+++ b/fs/ext2/balloc.c
@@ -269,7 +269,7 @@ goal_in_my_reservation(struct ext2_reserve_window *rsv, ext2_grpblk_t grp_goal,
ext2_fsblk_t group_first_block, group_last_block;
group_first_block = ext2_group_first_block_no(sb, group);
- group_last_block = group_first_block + EXT2_BLOCKS_PER_GROUP(sb) - 1;
+ group_last_block = ext2_group_last_block_no(sb, group);
if ((rsv->_rsv_start > group_last_block) ||
(rsv->_rsv_end < group_first_block))
@@ -666,37 +666,24 @@ ext2_try_to_allocate(struct super_block *sb, int group,
unsigned long *count,
struct ext2_reserve_window *my_rsv)
{
- ext2_fsblk_t group_first_block;
+ ext2_fsblk_t group_first_block = ext2_group_first_block_no(sb, group);
+ ext2_fsblk_t group_last_block = ext2_group_last_block_no(sb, group);
ext2_grpblk_t start, end;
unsigned long num = 0;
+ start = 0;
+ end = group_last_block - group_first_block + 1;
/* we do allocation within the reservation window if we have a window */
if (my_rsv) {
- group_first_block = ext2_group_first_block_no(sb, group);
if (my_rsv->_rsv_start >= group_first_block)
start = my_rsv->_rsv_start - group_first_block;
- else
- /* reservation window cross group boundary */
- start = 0;
- end = my_rsv->_rsv_end - group_first_block + 1;
- if (end > EXT2_BLOCKS_PER_GROUP(sb))
- /* reservation window crosses group boundary */
- end = EXT2_BLOCKS_PER_GROUP(sb);
- if ((start <= grp_goal) && (grp_goal < end))
- start = grp_goal;
- else
+ if (my_rsv->_rsv_end < group_last_block)
+ end = my_rsv->_rsv_end - group_first_block + 1;
+ if (grp_goal < start || grp_goal >= end)
grp_goal = -1;
- } else {
- if (grp_goal > 0)
- start = grp_goal;
- else
- start = 0;
- end = EXT2_BLOCKS_PER_GROUP(sb);
}
-
BUG_ON(start > EXT2_BLOCKS_PER_GROUP(sb));
-repeat:
if (grp_goal < 0) {
grp_goal = find_next_usable_block(start, bitmap_bh, end);
if (grp_goal < 0)
@@ -711,32 +698,23 @@ repeat:
;
}
}
- start = grp_goal;
- if (ext2_set_bit_atomic(sb_bgl_lock(EXT2_SB(sb), group), grp_goal,
- bitmap_bh->b_data)) {
- /*
- * The block was allocated by another thread, or it was
- * allocated and then freed by another thread
- */
- start++;
- grp_goal++;
- if (start >= end)
- goto fail_access;
- goto repeat;
- }
- num++;
- grp_goal++;
- while (num < *count && grp_goal < end
- && !ext2_set_bit_atomic(sb_bgl_lock(EXT2_SB(sb), group),
+ for (; num < *count && grp_goal < end; grp_goal++) {
+ if (ext2_set_bit_atomic(sb_bgl_lock(EXT2_SB(sb), group),
grp_goal, bitmap_bh->b_data)) {
+ if (num == 0)
+ continue;
+ break;
+ }
num++;
- grp_goal++;
}
+
+ if (num == 0)
+ goto fail_access;
+
*count = num;
return grp_goal - num;
fail_access:
- *count = num;
return -1;
}
@@ -754,10 +732,9 @@ fail_access:
* but we will shift to the place where start_block is,
* then start from there, when looking for a reservable space.
*
- * @size: the target new reservation window size
+ * @sb: the super block.
*
- * @group_first_block: the first block we consider to start
- * the real search from
+ * @start_block: the first block we consider to start the real search from
*
* @last_block:
* the maximum block number that our goal reservable space
@@ -908,7 +885,7 @@ static int alloc_new_reservation(struct ext2_reserve_window_node *my_rsv,
spinlock_t *rsv_lock = &EXT2_SB(sb)->s_rsv_window_lock;
group_first_block = ext2_group_first_block_no(sb, group);
- group_end_block = group_first_block + (EXT2_BLOCKS_PER_GROUP(sb) - 1);
+ group_end_block = ext2_group_last_block_no(sb, group);
if (grp_goal < 0)
start_block = group_first_block;
@@ -1115,7 +1092,7 @@ ext2_try_to_allocate_with_rsv(struct super_block *sb, unsigned int group,
* first block is the block number of the first block in this group
*/
group_first_block = ext2_group_first_block_no(sb, group);
- group_last_block = group_first_block + (EXT2_BLOCKS_PER_GROUP(sb) - 1);
+ group_last_block = ext2_group_last_block_no(sb, group);
/*
* Basically we will allocate a new block from inode's reservation
@@ -1313,6 +1290,13 @@ retry_alloc:
if (free_blocks > 0) {
grp_target_blk = ((goal - le32_to_cpu(es->s_first_data_block)) %
EXT2_BLOCKS_PER_GROUP(sb));
+ /*
+ * In case we retry allocation (due to fs reservation not
+ * working out or fs corruption), the bitmap_bh is non-null
+ * pointer and we have to release it before calling
+ * read_block_bitmap().
+ */
+ brelse(bitmap_bh);
bitmap_bh = read_block_bitmap(sb, group_no);
if (!bitmap_bh)
goto io_error;
@@ -1404,6 +1388,7 @@ allocated:
* use. So we may want to selectively mark some of the blocks
* as free
*/
+ num = *count;
goto retry_alloc;
}
diff --git a/fs/ext2/ext2.h b/fs/ext2/ext2.h
index 10ab238de9a6..8178bd38a9d6 100644
--- a/fs/ext2/ext2.h
+++ b/fs/ext2/ext2.h
@@ -813,6 +813,18 @@ ext2_group_first_block_no(struct super_block *sb, unsigned long group_no)
le32_to_cpu(EXT2_SB(sb)->s_es->s_first_data_block);
}
+static inline ext2_fsblk_t
+ext2_group_last_block_no(struct super_block *sb, unsigned long group_no)
+{
+ struct ext2_sb_info *sbi = EXT2_SB(sb);
+
+ if (group_no == sbi->s_groups_count - 1)
+ return le32_to_cpu(sbi->s_es->s_blocks_count) - 1;
+ else
+ return ext2_group_first_block_no(sb, group_no) +
+ EXT2_BLOCKS_PER_GROUP(sb) - 1;
+}
+
#define ext2_set_bit __test_and_set_bit_le
#define ext2_clear_bit __test_and_clear_bit_le
#define ext2_test_bit test_bit_le
diff --git a/fs/ext2/inode.c b/fs/ext2/inode.c
index 467c13ff6b40..119667e65890 100644
--- a/fs/ext2/inode.c
+++ b/fs/ext2/inode.c
@@ -701,10 +701,13 @@ static int ext2_get_blocks(struct inode *inode,
if (!partial) {
count++;
mutex_unlock(&ei->truncate_mutex);
- if (err)
- goto cleanup;
goto got_it;
}
+
+ if (err) {
+ mutex_unlock(&ei->truncate_mutex);
+ goto cleanup;
+ }
}
/*
diff --git a/fs/ext2/ioctl.c b/fs/ext2/ioctl.c
index 1b853fb0b163..32a8d10b579d 100644
--- a/fs/ext2/ioctl.c
+++ b/fs/ext2/ioctl.c
@@ -145,10 +145,13 @@ setversion_out:
if (ei->i_block_alloc_info){
struct ext2_reserve_window_node *rsv = &ei->i_block_alloc_info->rsv_window_node;
rsv->rsv_goal_size = rsv_window_size;
+ } else {
+ ret = -ENOMEM;
}
+
mutex_unlock(&ei->truncate_mutex);
mnt_drop_write_file(filp);
- return 0;
+ return ret;
}
default:
return -ENOTTY;
diff --git a/fs/ext2/super.c b/fs/ext2/super.c
index 30c630d73f0f..bcffe25da2f0 100644
--- a/fs/ext2/super.c
+++ b/fs/ext2/super.c
@@ -702,13 +702,7 @@ static int ext2_check_descriptors(struct super_block *sb)
for (i = 0; i < sbi->s_groups_count; i++) {
struct ext2_group_desc *gdp = ext2_get_group_desc(sb, i, NULL);
ext2_fsblk_t first_block = ext2_group_first_block_no(sb, i);
- ext2_fsblk_t last_block;
-
- if (i == sbi->s_groups_count - 1)
- last_block = le32_to_cpu(sbi->s_es->s_blocks_count) - 1;
- else
- last_block = first_block +
- (EXT2_BLOCKS_PER_GROUP(sb) - 1);
+ ext2_fsblk_t last_block = ext2_group_last_block_no(sb, i);
if (le32_to_cpu(gdp->bg_block_bitmap) < first_block ||
le32_to_cpu(gdp->bg_block_bitmap) > last_block)
@@ -806,7 +800,6 @@ static unsigned long descriptor_loc(struct super_block *sb,
{
struct ext2_sb_info *sbi = EXT2_SB(sb);
unsigned long bg, first_meta_bg;
- int has_super = 0;
first_meta_bg = le32_to_cpu(sbi->s_es->s_first_meta_bg);
@@ -814,10 +807,8 @@ static unsigned long descriptor_loc(struct super_block *sb,
nr < first_meta_bg)
return (logic_sb_block + nr + 1);
bg = sbi->s_desc_per_block * nr;
- if (ext2_bg_has_super(sb, bg))
- has_super = 1;
- return ext2_group_first_block_no(sb, bg) + has_super;
+ return ext2_group_first_block_no(sb, bg) + ext2_bg_has_super(sb, bg);
}
static int ext2_fill_super(struct super_block *sb, void *data, int silent)
diff --git a/fs/ext4/Kconfig b/fs/ext4/Kconfig
index cbb5ca830e57..ef42ab040905 100644
--- a/fs/ext4/Kconfig
+++ b/fs/ext4/Kconfig
@@ -106,3 +106,20 @@ config EXT4_DEBUG
If you select Y here, then you will be able to turn on debugging
with a command such as:
echo 1 > /sys/module/ext4/parameters/mballoc_debug
+
+config EXT4_KUNIT_TESTS
+ bool "KUnit tests for ext4"
+ select EXT4_FS
+ depends on KUNIT
+ help
+ This builds the ext4 KUnit tests.
+
+ KUnit tests run during boot and output the results to the debug log
+ in TAP format (http://testanything.org/). Only useful for kernel devs
+ running KUnit test harness and are not for inclusion into a production
+ build.
+
+ For more information on KUnit and unit tests in general please refer
+ to the KUnit documentation in Documentation/dev-tools/kunit/.
+
+ If unsure, say N.
diff --git a/fs/ext4/Makefile b/fs/ext4/Makefile
index b17ddc229ac5..840b91d040f1 100644
--- a/fs/ext4/Makefile
+++ b/fs/ext4/Makefile
@@ -13,4 +13,5 @@ ext4-y := balloc.o bitmap.o block_validity.o dir.o ext4_jbd2.o extents.o \
ext4-$(CONFIG_EXT4_FS_POSIX_ACL) += acl.o
ext4-$(CONFIG_EXT4_FS_SECURITY) += xattr_security.o
+ext4-$(CONFIG_EXT4_KUNIT_TESTS) += inode-test.o
ext4-$(CONFIG_FS_VERITY) += verity.o
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 03db3e71676c..f8578caba40d 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -198,6 +198,12 @@ struct ext4_system_blocks {
*/
#define EXT4_IO_END_UNWRITTEN 0x0001
+struct ext4_io_end_vec {
+ struct list_head list; /* list of io_end_vec */
+ loff_t offset; /* offset in the file */
+ ssize_t size; /* size of the extent */
+};
+
/*
* For converting unwritten extents on a work queue. 'handle' is used for
* buffered writeback.
@@ -211,8 +217,7 @@ typedef struct ext4_io_end {
* bios covering the extent */
unsigned int flag; /* unwritten or not */
atomic_t count; /* reference counter */
- loff_t offset; /* offset in the file */
- ssize_t size; /* size of the extent */
+ struct list_head list_vec; /* list of ext4_io_end_vec */
} ext4_io_end_t;
struct ext4_io_submit {
@@ -1579,7 +1584,6 @@ enum {
EXT4_STATE_NO_EXPAND, /* No space for expansion */
EXT4_STATE_DA_ALLOC_CLOSE, /* Alloc DA blks on close */
EXT4_STATE_EXT_MIGRATE, /* Inode is migrating */
- EXT4_STATE_DIO_UNWRITTEN, /* need convert on dio done*/
EXT4_STATE_NEWENTRY, /* File just added to dir */
EXT4_STATE_MAY_INLINE_DATA, /* may have in-inode data */
EXT4_STATE_EXT_PRECACHED, /* extents have been precached */
@@ -1678,6 +1682,7 @@ static inline bool ext4_verity_in_progress(struct inode *inode)
#define EXT4_FEATURE_COMPAT_RESIZE_INODE 0x0010
#define EXT4_FEATURE_COMPAT_DIR_INDEX 0x0020
#define EXT4_FEATURE_COMPAT_SPARSE_SUPER2 0x0200
+#define EXT4_FEATURE_COMPAT_STABLE_INODES 0x0800
#define EXT4_FEATURE_RO_COMPAT_SPARSE_SUPER 0x0001
#define EXT4_FEATURE_RO_COMPAT_LARGE_FILE 0x0002
@@ -1779,6 +1784,7 @@ EXT4_FEATURE_COMPAT_FUNCS(xattr, EXT_ATTR)
EXT4_FEATURE_COMPAT_FUNCS(resize_inode, RESIZE_INODE)
EXT4_FEATURE_COMPAT_FUNCS(dir_index, DIR_INDEX)
EXT4_FEATURE_COMPAT_FUNCS(sparse_super2, SPARSE_SUPER2)
+EXT4_FEATURE_COMPAT_FUNCS(stable_inodes, STABLE_INODES)
EXT4_FEATURE_RO_COMPAT_FUNCS(sparse_super, SPARSE_SUPER)
EXT4_FEATURE_RO_COMPAT_FUNCS(large_file, LARGE_FILE)
@@ -2560,8 +2566,6 @@ int ext4_get_block_unwritten(struct inode *inode, sector_t iblock,
struct buffer_head *bh_result, int create);
int ext4_get_block(struct inode *inode, sector_t iblock,
struct buffer_head *bh_result, int create);
-int ext4_dio_get_block(struct inode *inode, sector_t iblock,
- struct buffer_head *bh_result, int create);
int ext4_da_get_block_prep(struct inode *inode, sector_t iblock,
struct buffer_head *bh, int create);
int ext4_walk_page_buffers(handle_t *handle,
@@ -2604,7 +2608,6 @@ extern int ext4_can_truncate(struct inode *inode);
extern int ext4_truncate(struct inode *);
extern int ext4_break_layouts(struct inode *);
extern int ext4_punch_hole(struct inode *inode, loff_t offset, loff_t length);
-extern int ext4_truncate_restart_trans(handle_t *, struct inode *, int nblocks);
extern void ext4_set_inode_flags(struct inode *);
extern int ext4_alloc_da_blocks(struct inode *inode);
extern void ext4_set_aops(struct inode *inode);
@@ -3264,6 +3267,8 @@ extern long ext4_fallocate(struct file *file, int mode, loff_t offset,
loff_t len);
extern int ext4_convert_unwritten_extents(handle_t *handle, struct inode *inode,
loff_t offset, ssize_t len);
+extern int ext4_convert_unwritten_io_end_vec(handle_t *handle,
+ ext4_io_end_t *io_end);
extern int ext4_map_blocks(handle_t *handle, struct inode *inode,
struct ext4_map_blocks *map, int flags);
extern int ext4_ext_calc_metadata_amount(struct inode *inode,
@@ -3296,6 +3301,10 @@ extern int ext4_swap_extents(handle_t *handle, struct inode *inode1,
ext4_lblk_t lblk2, ext4_lblk_t count,
int mark_unwritten,int *err);
extern int ext4_clu_mapped(struct inode *inode, ext4_lblk_t lclu);
+extern int ext4_datasem_ensure_credits(handle_t *handle, struct inode *inode,
+ int check_cred, int restart_cred,
+ int revoke_cred);
+
/* move_extent.c */
extern void ext4_double_down_write_data_sem(struct inode *first,
@@ -3322,6 +3331,8 @@ extern int ext4_bio_write_page(struct ext4_io_submit *io,
int len,
struct writeback_control *wbc,
bool keep_towrite);
+extern struct ext4_io_end_vec *ext4_alloc_io_end_vec(ext4_io_end_t *io_end);
+extern struct ext4_io_end_vec *ext4_last_io_end_vec(ext4_io_end_t *io_end);
/* mmp.c */
extern int ext4_multi_mount_protect(struct super_block *, ext4_fsblk_t);
@@ -3379,6 +3390,7 @@ static inline void ext4_clear_io_unwritten_flag(ext4_io_end_t *io_end)
}
extern const struct iomap_ops ext4_iomap_ops;
+extern const struct iomap_ops ext4_iomap_report_ops;
static inline int ext4_buffer_uptodate(struct buffer_head *bh)
{
diff --git a/fs/ext4/ext4_jbd2.c b/fs/ext4/ext4_jbd2.c
index 7c70b08d104c..d3b8cdea5df7 100644
--- a/fs/ext4/ext4_jbd2.c
+++ b/fs/ext4/ext4_jbd2.c
@@ -65,12 +65,14 @@ static int ext4_journal_check_start(struct super_block *sb)
}
handle_t *__ext4_journal_start_sb(struct super_block *sb, unsigned int line,
- int type, int blocks, int rsv_blocks)
+ int type, int blocks, int rsv_blocks,
+ int revoke_creds)
{
journal_t *journal;
int err;
- trace_ext4_journal_start(sb, blocks, rsv_blocks, _RET_IP_);
+ trace_ext4_journal_start(sb, blocks, rsv_blocks, revoke_creds,
+ _RET_IP_);
err = ext4_journal_check_start(sb);
if (err < 0)
return ERR_PTR(err);
@@ -78,8 +80,8 @@ handle_t *__ext4_journal_start_sb(struct super_block *sb, unsigned int line,
journal = EXT4_SB(sb)->s_journal;
if (!journal)
return ext4_get_nojournal();
- return jbd2__journal_start(journal, blocks, rsv_blocks, GFP_NOFS,
- type, line);
+ return jbd2__journal_start(journal, blocks, rsv_blocks, revoke_creds,
+ GFP_NOFS, type, line);
}
int __ext4_journal_stop(const char *where, unsigned int line, handle_t *handle)
@@ -119,8 +121,8 @@ handle_t *__ext4_journal_start_reserved(handle_t *handle, unsigned int line,
return ext4_get_nojournal();
sb = handle->h_journal->j_private;
- trace_ext4_journal_start_reserved(sb, handle->h_buffer_credits,
- _RET_IP_);
+ trace_ext4_journal_start_reserved(sb,
+ jbd2_handle_buffer_credits(handle), _RET_IP_);
err = ext4_journal_check_start(sb);
if (err < 0) {
jbd2_journal_free_reserved(handle);
@@ -133,6 +135,19 @@ handle_t *__ext4_journal_start_reserved(handle_t *handle, unsigned int line,
return handle;
}
+int __ext4_journal_ensure_credits(handle_t *handle, int check_cred,
+ int extend_cred, int revoke_cred)
+{
+ if (!ext4_handle_valid(handle))
+ return 0;
+ if (jbd2_handle_buffer_credits(handle) >= check_cred &&
+ handle->h_revoke_credits >= revoke_cred)
+ return 0;
+ extend_cred = max(0, extend_cred - jbd2_handle_buffer_credits(handle));
+ revoke_cred = max(0, revoke_cred - handle->h_revoke_credits);
+ return ext4_journal_extend(handle, extend_cred, revoke_cred);
+}
+
static void ext4_journal_abort_handle(const char *caller, unsigned int line,
const char *err_fn,
struct buffer_head *bh,
@@ -278,7 +293,7 @@ int __ext4_handle_dirty_metadata(const char *where, unsigned int line,
handle->h_type,
handle->h_line_no,
handle->h_requested_credits,
- handle->h_buffer_credits, err);
+ jbd2_handle_buffer_credits(handle), err);
return err;
}
ext4_error_inode(inode, where, line,
@@ -289,7 +304,8 @@ int __ext4_handle_dirty_metadata(const char *where, unsigned int line,
handle->h_type,
handle->h_line_no,
handle->h_requested_credits,
- handle->h_buffer_credits, err);
+ jbd2_handle_buffer_credits(handle),
+ err);
}
} else {
if (inode)
diff --git a/fs/ext4/ext4_jbd2.h b/fs/ext4/ext4_jbd2.h
index ef8fcf7d0d3b..a6b9b66dbfad 100644
--- a/fs/ext4/ext4_jbd2.h
+++ b/fs/ext4/ext4_jbd2.h
@@ -261,7 +261,8 @@ int __ext4_handle_dirty_super(const char *where, unsigned int line,
__ext4_handle_dirty_super(__func__, __LINE__, (handle), (sb))
handle_t *__ext4_journal_start_sb(struct super_block *sb, unsigned int line,
- int type, int blocks, int rsv_blocks);
+ int type, int blocks, int rsv_blocks,
+ int revoke_creds);
int __ext4_journal_stop(const char *where, unsigned int line, handle_t *handle);
#define EXT4_NOJOURNAL_MAX_REF_COUNT ((unsigned long) 4096)
@@ -288,28 +289,41 @@ static inline int ext4_handle_is_aborted(handle_t *handle)
return 0;
}
-static inline int ext4_handle_has_enough_credits(handle_t *handle, int needed)
+static inline int ext4_free_metadata_revoke_credits(struct super_block *sb,
+ int blocks)
{
- if (ext4_handle_valid(handle) && handle->h_buffer_credits < needed)
- return 0;
- return 1;
+ /* Freeing each metadata block can result in freeing one cluster */
+ return blocks * EXT4_SB(sb)->s_cluster_ratio;
+}
+
+static inline int ext4_trans_default_revoke_credits(struct super_block *sb)
+{
+ return ext4_free_metadata_revoke_credits(sb, 8);
}
#define ext4_journal_start_sb(sb, type, nblocks) \
- __ext4_journal_start_sb((sb), __LINE__, (type), (nblocks), 0)
+ __ext4_journal_start_sb((sb), __LINE__, (type), (nblocks), 0, \
+ ext4_trans_default_revoke_credits(sb))
#define ext4_journal_start(inode, type, nblocks) \
- __ext4_journal_start((inode), __LINE__, (type), (nblocks), 0)
+ __ext4_journal_start((inode), __LINE__, (type), (nblocks), 0, \
+ ext4_trans_default_revoke_credits((inode)->i_sb))
+
+#define ext4_journal_start_with_reserve(inode, type, blocks, rsv_blocks)\
+ __ext4_journal_start((inode), __LINE__, (type), (blocks), (rsv_blocks),\
+ ext4_trans_default_revoke_credits((inode)->i_sb))
-#define ext4_journal_start_with_reserve(inode, type, blocks, rsv_blocks) \
- __ext4_journal_start((inode), __LINE__, (type), (blocks), (rsv_blocks))
+#define ext4_journal_start_with_revoke(inode, type, blocks, revoke_creds) \
+ __ext4_journal_start((inode), __LINE__, (type), (blocks), 0, \
+ (revoke_creds))
static inline handle_t *__ext4_journal_start(struct inode *inode,
unsigned int line, int type,
- int blocks, int rsv_blocks)
+ int blocks, int rsv_blocks,
+ int revoke_creds)
{
return __ext4_journal_start_sb(inode->i_sb, line, type, blocks,
- rsv_blocks);
+ rsv_blocks, revoke_creds);
}
#define ext4_journal_stop(handle) \
@@ -332,20 +346,68 @@ static inline handle_t *ext4_journal_current_handle(void)
return journal_current_handle();
}
-static inline int ext4_journal_extend(handle_t *handle, int nblocks)
+static inline int ext4_journal_extend(handle_t *handle, int nblocks, int revoke)
{
if (ext4_handle_valid(handle))
- return jbd2_journal_extend(handle, nblocks);
+ return jbd2_journal_extend(handle, nblocks, revoke);
return 0;
}
-static inline int ext4_journal_restart(handle_t *handle, int nblocks)
+static inline int ext4_journal_restart(handle_t *handle, int nblocks,
+ int revoke)
{
if (ext4_handle_valid(handle))
- return jbd2_journal_restart(handle, nblocks);
+ return jbd2__journal_restart(handle, nblocks, revoke, GFP_NOFS);
return 0;
}
+int __ext4_journal_ensure_credits(handle_t *handle, int check_cred,
+ int extend_cred, int revoke_cred);
+
+
+/*
+ * Ensure @handle has at least @check_creds credits available. If not,
+ * transaction will be extended or restarted to contain at least @extend_cred
+ * credits. Before restarting transaction @fn is executed to allow for cleanup
+ * before the transaction is restarted.
+ *
+ * The return value is < 0 in case of error, 0 in case the handle has enough
+ * credits or transaction extension succeeded, 1 in case transaction had to be
+ * restarted.
+ */
+#define ext4_journal_ensure_credits_fn(handle, check_cred, extend_cred, \
+ revoke_cred, fn) \
+({ \
+ __label__ __ensure_end; \
+ int err = __ext4_journal_ensure_credits((handle), (check_cred), \
+ (extend_cred), (revoke_cred)); \
+ \
+ if (err <= 0) \
+ goto __ensure_end; \
+ err = (fn); \
+ if (err < 0) \
+ goto __ensure_end; \
+ err = ext4_journal_restart((handle), (extend_cred), (revoke_cred)); \
+ if (err == 0) \
+ err = 1; \
+__ensure_end: \
+ err; \
+})
+
+/*
+ * Ensure given handle has at least requested amount of credits available,
+ * possibly restarting transaction if needed. We also make sure the transaction
+ * has space for at least ext4_trans_default_revoke_credits(sb) revoke records
+ * as freeing one or two blocks is very common pattern and requesting this is
+ * very cheap.
+ */
+static inline int ext4_journal_ensure_credits(handle_t *handle, int credits,
+ int revoke_creds)
+{
+ return ext4_journal_ensure_credits_fn(handle, credits, credits,
+ revoke_creds, 0);
+}
+
static inline int ext4_journal_blocks_per_page(struct inode *inode)
{
if (EXT4_JOURNAL(inode) != NULL)
@@ -407,6 +469,7 @@ static inline int ext4_inode_journal_mode(struct inode *inode)
return EXT4_INODE_WRITEBACK_DATA_MODE; /* writeback */
/* We do not support data journalling with delayed allocation */
if (!S_ISREG(inode->i_mode) ||
+ ext4_test_inode_flag(inode, EXT4_INODE_EA_INODE) ||
test_opt(inode->i_sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA ||
(ext4_test_inode_flag(inode, EXT4_INODE_JOURNAL_DATA) &&
!test_opt(inode->i_sb, DELALLOC))) {
@@ -437,6 +500,19 @@ static inline int ext4_should_writeback_data(struct inode *inode)
return ext4_inode_journal_mode(inode) & EXT4_INODE_WRITEBACK_DATA_MODE;
}
+static inline int ext4_free_data_revoke_credits(struct inode *inode, int blocks)
+{
+ if (test_opt(inode->i_sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA)
+ return 0;
+ if (!ext4_should_journal_data(inode))
+ return 0;
+ /*
+ * Data blocks in one extent are contiguous, just account for partial
+ * clusters at extent boundaries
+ */
+ return blocks + 2*(EXT4_SB(inode->i_sb)->s_cluster_ratio - 1);
+}
+
/*
* This function controls whether or not we should try to go down the
* dioread_nolock code paths, which makes it safe to avoid taking
diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index fb0f99dc8c22..0e8708b77da6 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -100,29 +100,41 @@ static int ext4_split_extent_at(handle_t *handle,
static int ext4_find_delayed_extent(struct inode *inode,
struct extent_status *newes);
-static int ext4_ext_truncate_extend_restart(handle_t *handle,
- struct inode *inode,
- int needed)
+static int ext4_ext_trunc_restart_fn(struct inode *inode, int *dropped)
{
- int err;
-
- if (!ext4_handle_valid(handle))
- return 0;
- if (handle->h_buffer_credits >= needed)
- return 0;
/*
- * If we need to extend the journal get a few extra blocks
- * while we're at it for efficiency's sake.
+ * Drop i_data_sem to avoid deadlock with ext4_map_blocks. At this
+ * moment, get_block can be called only for blocks inside i_size since
+ * page cache has been already dropped and writes are blocked by
+ * i_mutex. So we can safely drop the i_data_sem here.
*/
- needed += 3;
- err = ext4_journal_extend(handle, needed - handle->h_buffer_credits);
- if (err <= 0)
- return err;
- err = ext4_truncate_restart_trans(handle, inode, needed);
- if (err == 0)
- err = -EAGAIN;
+ BUG_ON(EXT4_JOURNAL(inode) == NULL);
+ ext4_discard_preallocations(inode);
+ up_write(&EXT4_I(inode)->i_data_sem);
+ *dropped = 1;
+ return 0;
+}
- return err;
+/*
+ * Make sure 'handle' has at least 'check_cred' credits. If not, restart
+ * transaction with 'restart_cred' credits. The function drops i_data_sem
+ * when restarting transaction and gets it after transaction is restarted.
+ *
+ * The function returns 0 on success, 1 if transaction had to be restarted,
+ * and < 0 in case of fatal error.
+ */
+int ext4_datasem_ensure_credits(handle_t *handle, struct inode *inode,
+ int check_cred, int restart_cred,
+ int revoke_cred)
+{
+ int ret;
+ int dropped = 0;
+
+ ret = ext4_journal_ensure_credits_fn(handle, check_cred, restart_cred,
+ revoke_cred, ext4_ext_trunc_restart_fn(inode, &dropped));
+ if (dropped)
+ down_write(&EXT4_I(inode)->i_data_sem);
+ return ret;
}
/*
@@ -1753,16 +1765,9 @@ ext4_can_extents_be_merged(struct inode *inode, struct ext4_extent *ex1,
*/
if (ext1_ee_len + ext2_ee_len > EXT_INIT_MAX_LEN)
return 0;
- /*
- * The check for IO to unwritten extent is somewhat racy as we
- * increment i_unwritten / set EXT4_STATE_DIO_UNWRITTEN only after
- * dropping i_data_sem. But reserved blocks should save us in that
- * case.
- */
+
if (ext4_ext_is_unwritten(ex1) &&
- (ext4_test_inode_state(inode, EXT4_STATE_DIO_UNWRITTEN) ||
- atomic_read(&EXT4_I(inode)->i_unwritten) ||
- (ext1_ee_len + ext2_ee_len > EXT_UNWRITTEN_MAX_LEN)))
+ ext1_ee_len + ext2_ee_len > EXT_UNWRITTEN_MAX_LEN)
return 0;
#ifdef AGGRESSIVE_TEST
if (ext1_ee_len >= 4)
@@ -1840,7 +1845,8 @@ static void ext4_ext_try_to_merge_up(handle_t *handle,
* group descriptor to release the extent tree block. If we
* can't get the journal credits, give up.
*/
- if (ext4_journal_extend(handle, 2))
+ if (ext4_journal_extend(handle, 2,
+ ext4_free_metadata_revoke_credits(inode->i_sb, 1)))
return;
/*
@@ -2727,7 +2733,7 @@ ext4_ext_rm_leaf(handle_t *handle, struct inode *inode,
{
struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
int err = 0, correct_index = 0;
- int depth = ext_depth(inode), credits;
+ int depth = ext_depth(inode), credits, revoke_credits;
struct ext4_extent_header *eh;
ext4_lblk_t a, b;
unsigned num;
@@ -2819,10 +2825,23 @@ ext4_ext_rm_leaf(handle_t *handle, struct inode *inode,
credits += (ext_depth(inode)) + 1;
}
credits += EXT4_MAXQUOTAS_TRANS_BLOCKS(inode->i_sb);
-
- err = ext4_ext_truncate_extend_restart(handle, inode, credits);
- if (err)
+ /*
+ * We may end up freeing some index blocks and data from the
+ * punched range. Note that partial clusters are accounted for
+ * by ext4_free_data_revoke_credits().
+ */
+ revoke_credits =
+ ext4_free_metadata_revoke_credits(inode->i_sb,
+ ext_depth(inode)) +
+ ext4_free_data_revoke_credits(inode, b - a + 1);
+
+ err = ext4_datasem_ensure_credits(handle, inode, credits,
+ credits, revoke_credits);
+ if (err) {
+ if (err > 0)
+ err = -EAGAIN;
goto out;
+ }
err = ext4_ext_get_access(handle, inode, path + depth);
if (err)
@@ -2948,7 +2967,9 @@ int ext4_ext_remove_space(struct inode *inode, ext4_lblk_t start,
ext_debug("truncate since %u to %u\n", start, end);
/* probably first extent we're gonna free will be last in block */
- handle = ext4_journal_start(inode, EXT4_HT_TRUNCATE, depth + 1);
+ handle = ext4_journal_start_with_revoke(inode, EXT4_HT_TRUNCATE,
+ depth + 1,
+ ext4_free_metadata_revoke_credits(inode->i_sb, depth));
if (IS_ERR(handle))
return PTR_ERR(handle);
@@ -4962,23 +4983,13 @@ int ext4_convert_unwritten_extents(handle_t *handle, struct inode *inode,
int ret = 0;
int ret2 = 0;
struct ext4_map_blocks map;
- unsigned int credits, blkbits = inode->i_blkbits;
+ unsigned int blkbits = inode->i_blkbits;
+ unsigned int credits = 0;
map.m_lblk = offset >> blkbits;
max_blocks = EXT4_MAX_BLOCKS(len, offset, blkbits);
- /*
- * This is somewhat ugly but the idea is clear: When transaction is
- * reserved, everything goes into it. Otherwise we rather start several
- * smaller transactions for conversion of each extent separately.
- */
- if (handle) {
- handle = ext4_journal_start_reserved(handle,
- EXT4_HT_EXT_CONVERT);
- if (IS_ERR(handle))
- return PTR_ERR(handle);
- credits = 0;
- } else {
+ if (!handle) {
/*
* credits to insert 1 extent into extent tree
*/
@@ -5009,11 +5020,40 @@ int ext4_convert_unwritten_extents(handle_t *handle, struct inode *inode,
if (ret <= 0 || ret2)
break;
}
- if (!credits)
- ret2 = ext4_journal_stop(handle);
return ret > 0 ? ret2 : ret;
}
+int ext4_convert_unwritten_io_end_vec(handle_t *handle, ext4_io_end_t *io_end)
+{
+ int ret, err = 0;
+ struct ext4_io_end_vec *io_end_vec;
+
+ /*
+ * This is somewhat ugly but the idea is clear: When transaction is
+ * reserved, everything goes into it. Otherwise we rather start several
+ * smaller transactions for conversion of each extent separately.
+ */
+ if (handle) {
+ handle = ext4_journal_start_reserved(handle,
+ EXT4_HT_EXT_CONVERT);
+ if (IS_ERR(handle))
+ return PTR_ERR(handle);
+ }
+
+ list_for_each_entry(io_end_vec, &io_end->list_vec, list) {
+ ret = ext4_convert_unwritten_extents(handle, io_end->inode,
+ io_end_vec->offset,
+ io_end_vec->size);
+ if (ret)
+ break;
+ }
+
+ if (handle)
+ err = ext4_journal_stop(handle);
+
+ return ret < 0 ? ret : err;
+}
+
/*
* If newes is not existing extent (newes->ec_pblk equals zero) find
* delayed extent at start of newes and update newes accordingly and
@@ -5206,13 +5246,10 @@ ext4_access_path(handle_t *handle, struct inode *inode,
* descriptor) for each block group; assume two block
* groups
*/
- if (handle->h_buffer_credits < 7) {
- credits = ext4_writepage_trans_blocks(inode);
- err = ext4_ext_truncate_extend_restart(handle, inode, credits);
- /* EAGAIN is success */
- if (err && err != -EAGAIN)
- return err;
- }
+ credits = ext4_writepage_trans_blocks(inode);
+ err = ext4_datasem_ensure_credits(handle, inode, 7, credits, 0);
+ if (err < 0)
+ return err;
err = ext4_ext_get_access(handle, inode, path);
return err;
diff --git a/fs/ext4/file.c b/fs/ext4/file.c
index 8d2bbcc2d813..6a7293a5cda2 100644
--- a/fs/ext4/file.c
+++ b/fs/ext4/file.c
@@ -29,10 +29,58 @@
#include <linux/pagevec.h>
#include <linux/uio.h>
#include <linux/mman.h>
+#include <linux/backing-dev.h>
#include "ext4.h"
#include "ext4_jbd2.h"
#include "xattr.h"
#include "acl.h"
+#include "truncate.h"
+
+static bool ext4_dio_supported(struct inode *inode)
+{
+ if (IS_ENABLED(CONFIG_FS_ENCRYPTION) && IS_ENCRYPTED(inode))
+ return false;
+ if (fsverity_active(inode))
+ return false;
+ if (ext4_should_journal_data(inode))
+ return false;
+ if (ext4_has_inline_data(inode))
+ return false;
+ return true;
+}
+
+static ssize_t ext4_dio_read_iter(struct kiocb *iocb, struct iov_iter *to)
+{
+ ssize_t ret;
+ struct inode *inode = file_inode(iocb->ki_filp);
+
+ if (iocb->ki_flags & IOCB_NOWAIT) {
+ if (!inode_trylock_shared(inode))
+ return -EAGAIN;
+ } else {
+ inode_lock_shared(inode);
+ }
+
+ if (!ext4_dio_supported(inode)) {
+ inode_unlock_shared(inode);
+ /*
+ * Fallback to buffered I/O if the operation being performed on
+ * the inode is not supported by direct I/O. The IOCB_DIRECT
+ * flag needs to be cleared here in order to ensure that the
+ * direct I/O path within generic_file_read_iter() is not
+ * taken.
+ */
+ iocb->ki_flags &= ~IOCB_DIRECT;
+ return generic_file_read_iter(iocb, to);
+ }
+
+ ret = iomap_dio_rw(iocb, to, &ext4_iomap_ops, NULL,
+ is_sync_kiocb(iocb));
+ inode_unlock_shared(inode);
+
+ file_accessed(iocb->ki_filp);
+ return ret;
+}
#ifdef CONFIG_FS_DAX
static ssize_t ext4_dax_read_iter(struct kiocb *iocb, struct iov_iter *to)
@@ -64,16 +112,21 @@ static ssize_t ext4_dax_read_iter(struct kiocb *iocb, struct iov_iter *to)
static ssize_t ext4_file_read_iter(struct kiocb *iocb, struct iov_iter *to)
{
- if (unlikely(ext4_forced_shutdown(EXT4_SB(file_inode(iocb->ki_filp)->i_sb))))
+ struct inode *inode = file_inode(iocb->ki_filp);
+
+ if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb))))
return -EIO;
if (!iov_iter_count(to))
return 0; /* skip atime */
#ifdef CONFIG_FS_DAX
- if (IS_DAX(file_inode(iocb->ki_filp)))
+ if (IS_DAX(inode))
return ext4_dax_read_iter(iocb, to);
#endif
+ if (iocb->ki_flags & IOCB_DIRECT)
+ return ext4_dio_read_iter(iocb, to);
+
return generic_file_read_iter(iocb, to);
}
@@ -103,13 +156,6 @@ static int ext4_release_file(struct inode *inode, struct file *filp)
return 0;
}
-static void ext4_unwritten_wait(struct inode *inode)
-{
- wait_queue_head_t *wq = ext4_ioend_wq(inode);
-
- wait_event(*wq, (atomic_read(&EXT4_I(inode)->i_unwritten) == 0));
-}
-
/*
* This tests whether the IO in question is block-aligned or not.
* Ext4 utilizes unwritten extents when hole-filling during direct IO, and they
@@ -162,13 +208,13 @@ static ssize_t ext4_write_checks(struct kiocb *iocb, struct iov_iter *from)
struct inode *inode = file_inode(iocb->ki_filp);
ssize_t ret;
+ if (unlikely(IS_IMMUTABLE(inode)))
+ return -EPERM;
+
ret = generic_write_checks(iocb, from);
if (ret <= 0)
return ret;
- if (unlikely(IS_IMMUTABLE(inode)))
- return -EPERM;
-
/*
* If we have encountered a bitmap-format file, the size limit
* is smaller than s_maxbytes, which is for extent-mapped files.
@@ -180,56 +226,266 @@ static ssize_t ext4_write_checks(struct kiocb *iocb, struct iov_iter *from)
return -EFBIG;
iov_iter_truncate(from, sbi->s_bitmap_maxbytes - iocb->ki_pos);
}
+
+ ret = file_modified(iocb->ki_filp);
+ if (ret)
+ return ret;
+
return iov_iter_count(from);
}
-#ifdef CONFIG_FS_DAX
-static ssize_t
-ext4_dax_write_iter(struct kiocb *iocb, struct iov_iter *from)
+static ssize_t ext4_buffered_write_iter(struct kiocb *iocb,
+ struct iov_iter *from)
{
- struct inode *inode = file_inode(iocb->ki_filp);
ssize_t ret;
+ struct inode *inode = file_inode(iocb->ki_filp);
- if (!inode_trylock(inode)) {
- if (iocb->ki_flags & IOCB_NOWAIT)
- return -EAGAIN;
- inode_lock(inode);
- }
+ if (iocb->ki_flags & IOCB_NOWAIT)
+ return -EOPNOTSUPP;
+
+ inode_lock(inode);
ret = ext4_write_checks(iocb, from);
if (ret <= 0)
goto out;
- ret = file_remove_privs(iocb->ki_filp);
- if (ret)
- goto out;
- ret = file_update_time(iocb->ki_filp);
- if (ret)
- goto out;
- ret = dax_iomap_rw(iocb, from, &ext4_iomap_ops);
+ current->backing_dev_info = inode_to_bdi(inode);
+ ret = generic_perform_write(iocb->ki_filp, from, iocb->ki_pos);
+ current->backing_dev_info = NULL;
+
out:
inode_unlock(inode);
- if (ret > 0)
+ if (likely(ret > 0)) {
+ iocb->ki_pos += ret;
ret = generic_write_sync(iocb, ret);
+ }
+
return ret;
}
-#endif
-static ssize_t
-ext4_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
+static ssize_t ext4_handle_inode_extension(struct inode *inode, loff_t offset,
+ ssize_t written, size_t count)
{
+ handle_t *handle;
+ bool truncate = false;
+ u8 blkbits = inode->i_blkbits;
+ ext4_lblk_t written_blk, end_blk;
+
+ /*
+ * Note that EXT4_I(inode)->i_disksize can get extended up to
+ * inode->i_size while the I/O was running due to writeback of delalloc
+ * blocks. But, the code in ext4_iomap_alloc() is careful to use
+ * zeroed/unwritten extents if this is possible; thus we won't leave
+ * uninitialized blocks in a file even if we didn't succeed in writing
+ * as much as we intended.
+ */
+ WARN_ON_ONCE(i_size_read(inode) < EXT4_I(inode)->i_disksize);
+ if (offset + count <= EXT4_I(inode)->i_disksize) {
+ /*
+ * We need to ensure that the inode is removed from the orphan
+ * list if it has been added prematurely, due to writeback of
+ * delalloc blocks.
+ */
+ if (!list_empty(&EXT4_I(inode)->i_orphan) && inode->i_nlink) {
+ handle = ext4_journal_start(inode, EXT4_HT_INODE, 2);
+
+ if (IS_ERR(handle)) {
+ ext4_orphan_del(NULL, inode);
+ return PTR_ERR(handle);
+ }
+
+ ext4_orphan_del(handle, inode);
+ ext4_journal_stop(handle);
+ }
+
+ return written;
+ }
+
+ if (written < 0)
+ goto truncate;
+
+ handle = ext4_journal_start(inode, EXT4_HT_INODE, 2);
+ if (IS_ERR(handle)) {
+ written = PTR_ERR(handle);
+ goto truncate;
+ }
+
+ if (ext4_update_inode_size(inode, offset + written))
+ ext4_mark_inode_dirty(handle, inode);
+
+ /*
+ * We may need to truncate allocated but not written blocks beyond EOF.
+ */
+ written_blk = ALIGN(offset + written, 1 << blkbits);
+ end_blk = ALIGN(offset + count, 1 << blkbits);
+ if (written_blk < end_blk && ext4_can_truncate(inode))
+ truncate = true;
+
+ /*
+ * Remove the inode from the orphan list if it has been extended and
+ * everything went OK.
+ */
+ if (!truncate && inode->i_nlink)
+ ext4_orphan_del(handle, inode);
+ ext4_journal_stop(handle);
+
+ if (truncate) {
+truncate:
+ ext4_truncate_failed_write(inode);
+ /*
+ * If the truncate operation failed early, then the inode may
+ * still be on the orphan list. In that case, we need to try
+ * remove the inode from the in-memory linked list.
+ */
+ if (inode->i_nlink)
+ ext4_orphan_del(NULL, inode);
+ }
+
+ return written;
+}
+
+static int ext4_dio_write_end_io(struct kiocb *iocb, ssize_t size,
+ int error, unsigned int flags)
+{
+ loff_t offset = iocb->ki_pos;
struct inode *inode = file_inode(iocb->ki_filp);
- int o_direct = iocb->ki_flags & IOCB_DIRECT;
- int unaligned_aio = 0;
- int overwrite = 0;
+
+ if (error)
+ return error;
+
+ if (size && flags & IOMAP_DIO_UNWRITTEN)
+ return ext4_convert_unwritten_extents(NULL, inode,
+ offset, size);
+
+ return 0;
+}
+
+static const struct iomap_dio_ops ext4_dio_write_ops = {
+ .end_io = ext4_dio_write_end_io,
+};
+
+static ssize_t ext4_dio_write_iter(struct kiocb *iocb, struct iov_iter *from)
+{
ssize_t ret;
+ size_t count;
+ loff_t offset;
+ handle_t *handle;
+ struct inode *inode = file_inode(iocb->ki_filp);
+ bool extend = false, overwrite = false, unaligned_aio = false;
- if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb))))
- return -EIO;
+ if (iocb->ki_flags & IOCB_NOWAIT) {
+ if (!inode_trylock(inode))
+ return -EAGAIN;
+ } else {
+ inode_lock(inode);
+ }
+
+ if (!ext4_dio_supported(inode)) {
+ inode_unlock(inode);
+ /*
+ * Fallback to buffered I/O if the inode does not support
+ * direct I/O.
+ */
+ return ext4_buffered_write_iter(iocb, from);
+ }
+
+ ret = ext4_write_checks(iocb, from);
+ if (ret <= 0) {
+ inode_unlock(inode);
+ return ret;
+ }
+
+ /*
+ * Unaligned asynchronous direct I/O must be serialized among each
+ * other as the zeroing of partial blocks of two competing unaligned
+ * asynchronous direct I/O writes can result in data corruption.
+ */
+ offset = iocb->ki_pos;
+ count = iov_iter_count(from);
+ if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS) &&
+ !is_sync_kiocb(iocb) && ext4_unaligned_aio(inode, from, offset)) {
+ unaligned_aio = true;
+ inode_dio_wait(inode);
+ }
+
+ /*
+ * Determine whether the I/O will overwrite allocated and initialized
+ * blocks. If so, check to see whether it is possible to take the
+ * dioread_nolock path.
+ */
+ if (!unaligned_aio && ext4_overwrite_io(inode, offset, count) &&
+ ext4_should_dioread_nolock(inode)) {
+ overwrite = true;
+ downgrade_write(&inode->i_rwsem);
+ }
+
+ if (offset + count > EXT4_I(inode)->i_disksize) {
+ handle = ext4_journal_start(inode, EXT4_HT_INODE, 2);
+ if (IS_ERR(handle)) {
+ ret = PTR_ERR(handle);
+ goto out;
+ }
+
+ ret = ext4_orphan_add(handle, inode);
+ if (ret) {
+ ext4_journal_stop(handle);
+ goto out;
+ }
+
+ extend = true;
+ ext4_journal_stop(handle);
+ }
+
+ ret = iomap_dio_rw(iocb, from, &ext4_iomap_ops, &ext4_dio_write_ops,
+ is_sync_kiocb(iocb) || unaligned_aio || extend);
+
+ if (extend)
+ ret = ext4_handle_inode_extension(inode, offset, ret, count);
+
+out:
+ if (overwrite)
+ inode_unlock_shared(inode);
+ else
+ inode_unlock(inode);
+
+ if (ret >= 0 && iov_iter_count(from)) {
+ ssize_t err;
+ loff_t endbyte;
+
+ offset = iocb->ki_pos;
+ err = ext4_buffered_write_iter(iocb, from);
+ if (err < 0)
+ return err;
+
+ /*
+ * We need to ensure that the pages within the page cache for
+ * the range covered by this I/O are written to disk and
+ * invalidated. This is in attempt to preserve the expected
+ * direct I/O semantics in the case we fallback to buffered I/O
+ * to complete off the I/O request.
+ */
+ ret += err;
+ endbyte = offset + err - 1;
+ err = filemap_write_and_wait_range(iocb->ki_filp->f_mapping,
+ offset, endbyte);
+ if (!err)
+ invalidate_mapping_pages(iocb->ki_filp->f_mapping,
+ offset >> PAGE_SHIFT,
+ endbyte >> PAGE_SHIFT);
+ }
+
+ return ret;
+}
#ifdef CONFIG_FS_DAX
- if (IS_DAX(inode))
- return ext4_dax_write_iter(iocb, from);
-#endif
+static ssize_t
+ext4_dax_write_iter(struct kiocb *iocb, struct iov_iter *from)
+{
+ ssize_t ret;
+ size_t count;
+ loff_t offset;
+ handle_t *handle;
+ bool extend = false;
+ struct inode *inode = file_inode(iocb->ki_filp);
if (!inode_trylock(inode)) {
if (iocb->ki_flags & IOCB_NOWAIT)
@@ -241,49 +497,55 @@ ext4_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
if (ret <= 0)
goto out;
- /*
- * Unaligned direct AIO must be serialized among each other as zeroing
- * of partial blocks of two competing unaligned AIOs can result in data
- * corruption.
- */
- if (o_direct && ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS) &&
- !is_sync_kiocb(iocb) &&
- ext4_unaligned_aio(inode, from, iocb->ki_pos)) {
- unaligned_aio = 1;
- ext4_unwritten_wait(inode);
- }
+ offset = iocb->ki_pos;
+ count = iov_iter_count(from);
- iocb->private = &overwrite;
- /* Check whether we do a DIO overwrite or not */
- if (o_direct && !unaligned_aio) {
- if (ext4_overwrite_io(inode, iocb->ki_pos, iov_iter_count(from))) {
- if (ext4_should_dioread_nolock(inode))
- overwrite = 1;
- } else if (iocb->ki_flags & IOCB_NOWAIT) {
- ret = -EAGAIN;
+ if (offset + count > EXT4_I(inode)->i_disksize) {
+ handle = ext4_journal_start(inode, EXT4_HT_INODE, 2);
+ if (IS_ERR(handle)) {
+ ret = PTR_ERR(handle);
goto out;
}
- }
- ret = __generic_file_write_iter(iocb, from);
- /*
- * Unaligned direct AIO must be the only IO in flight. Otherwise
- * overlapping aligned IO after unaligned might result in data
- * corruption.
- */
- if (ret == -EIOCBQUEUED && unaligned_aio)
- ext4_unwritten_wait(inode);
- inode_unlock(inode);
+ ret = ext4_orphan_add(handle, inode);
+ if (ret) {
+ ext4_journal_stop(handle);
+ goto out;
+ }
- if (ret > 0)
- ret = generic_write_sync(iocb, ret);
+ extend = true;
+ ext4_journal_stop(handle);
+ }
- return ret;
+ ret = dax_iomap_rw(iocb, from, &ext4_iomap_ops);
+ if (extend)
+ ret = ext4_handle_inode_extension(inode, offset, ret, count);
out:
inode_unlock(inode);
+ if (ret > 0)
+ ret = generic_write_sync(iocb, ret);
return ret;
}
+#endif
+
+static ssize_t
+ext4_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
+{
+ struct inode *inode = file_inode(iocb->ki_filp);
+
+ if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb))))
+ return -EIO;
+
+#ifdef CONFIG_FS_DAX
+ if (IS_DAX(inode))
+ return ext4_dax_write_iter(iocb, from);
+#endif
+ if (iocb->ki_flags & IOCB_DIRECT)
+ return ext4_dio_write_iter(iocb, from);
+
+ return ext4_buffered_write_iter(iocb, from);
+}
#ifdef CONFIG_FS_DAX
static vm_fault_t ext4_dax_huge_fault(struct vm_fault *vmf,
@@ -494,12 +756,14 @@ loff_t ext4_llseek(struct file *file, loff_t offset, int whence)
maxbytes, i_size_read(inode));
case SEEK_HOLE:
inode_lock_shared(inode);
- offset = iomap_seek_hole(inode, offset, &ext4_iomap_ops);
+ offset = iomap_seek_hole(inode, offset,
+ &ext4_iomap_report_ops);
inode_unlock_shared(inode);
break;
case SEEK_DATA:
inode_lock_shared(inode);
- offset = iomap_seek_data(inode, offset, &ext4_iomap_ops);
+ offset = iomap_seek_data(inode, offset,
+ &ext4_iomap_report_ops);
inode_unlock_shared(inode);
break;
}
diff --git a/fs/ext4/fsync.c b/fs/ext4/fsync.c
index 5508baa11bb6..e10206e7f4bb 100644
--- a/fs/ext4/fsync.c
+++ b/fs/ext4/fsync.c
@@ -80,6 +80,43 @@ static int ext4_sync_parent(struct inode *inode)
return ret;
}
+static int ext4_fsync_nojournal(struct inode *inode, bool datasync,
+ bool *needs_barrier)
+{
+ int ret, err;
+
+ ret = sync_mapping_buffers(inode->i_mapping);
+ if (!(inode->i_state & I_DIRTY_ALL))
+ return ret;
+ if (datasync && !(inode->i_state & I_DIRTY_DATASYNC))
+ return ret;
+
+ err = sync_inode_metadata(inode, 1);
+ if (!ret)
+ ret = err;
+
+ if (!ret)
+ ret = ext4_sync_parent(inode);
+ if (test_opt(inode->i_sb, BARRIER))
+ *needs_barrier = true;
+
+ return ret;
+}
+
+static int ext4_fsync_journal(struct inode *inode, bool datasync,
+ bool *needs_barrier)
+{
+ struct ext4_inode_info *ei = EXT4_I(inode);
+ journal_t *journal = EXT4_SB(inode->i_sb)->s_journal;
+ tid_t commit_tid = datasync ? ei->i_datasync_tid : ei->i_sync_tid;
+
+ if (journal->j_flags & JBD2_BARRIER &&
+ !jbd2_trans_will_send_data_barrier(journal, commit_tid))
+ *needs_barrier = true;
+
+ return jbd2_complete_transaction(journal, commit_tid);
+}
+
/*
* akpm: A new design for ext4_sync_file().
*
@@ -91,17 +128,14 @@ static int ext4_sync_parent(struct inode *inode)
* What we do is just kick off a commit and wait on it. This will snapshot the
* inode to disk.
*/
-
int ext4_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
{
- struct inode *inode = file->f_mapping->host;
- struct ext4_inode_info *ei = EXT4_I(inode);
- journal_t *journal = EXT4_SB(inode->i_sb)->s_journal;
int ret = 0, err;
- tid_t commit_tid;
bool needs_barrier = false;
+ struct inode *inode = file->f_mapping->host;
+ struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
- if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb))))
+ if (unlikely(ext4_forced_shutdown(sbi)))
return -EIO;
J_ASSERT(ext4_journal_current_handle() == NULL);
@@ -111,23 +145,15 @@ int ext4_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
if (sb_rdonly(inode->i_sb)) {
/* Make sure that we read updated s_mount_flags value */
smp_rmb();
- if (EXT4_SB(inode->i_sb)->s_mount_flags & EXT4_MF_FS_ABORTED)
+ if (sbi->s_mount_flags & EXT4_MF_FS_ABORTED)
ret = -EROFS;
goto out;
}
- if (!journal) {
- ret = __generic_file_fsync(file, start, end, datasync);
- if (!ret)
- ret = ext4_sync_parent(inode);
- if (test_opt(inode->i_sb, BARRIER))
- goto issue_flush;
- goto out;
- }
-
ret = file_write_and_wait_range(file, start, end);
if (ret)
return ret;
+
/*
* data=writeback,ordered:
* The caller's filemap_fdatawrite()/wait will sync the data.
@@ -142,18 +168,14 @@ int ext4_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
* (they were dirtied by commit). But that's OK - the blocks are
* safe in-journal, which is all fsync() needs to ensure.
*/
- if (ext4_should_journal_data(inode)) {
+ if (!sbi->s_journal)
+ ret = ext4_fsync_nojournal(inode, datasync, &needs_barrier);
+ else if (ext4_should_journal_data(inode))
ret = ext4_force_commit(inode->i_sb);
- goto out;
- }
+ else
+ ret = ext4_fsync_journal(inode, datasync, &needs_barrier);
- commit_tid = datasync ? ei->i_datasync_tid : ei->i_sync_tid;
- if (journal->j_flags & JBD2_BARRIER &&
- !jbd2_trans_will_send_data_barrier(journal, commit_tid))
- needs_barrier = true;
- ret = jbd2_complete_transaction(journal, commit_tid);
if (needs_barrier) {
- issue_flush:
err = blkdev_issue_flush(inode->i_sb->s_bdev, GFP_KERNEL, NULL);
if (!ret)
ret = err;
diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c
index 764ff4c56233..dc333e8e51e8 100644
--- a/fs/ext4/ialloc.c
+++ b/fs/ext4/ialloc.c
@@ -265,13 +265,8 @@ void ext4_free_inode(handle_t *handle, struct inode *inode)
ext4_debug("freeing inode %lu\n", ino);
trace_ext4_free_inode(inode);
- /*
- * Note: we must free any quota before locking the superblock,
- * as writing the quota to disk may need the lock as well.
- */
dquot_initialize(inode);
dquot_free_inode(inode);
- dquot_drop(inode);
is_directory = S_ISDIR(inode->i_mode);
@@ -927,7 +922,7 @@ repeat_in_this_group:
BUG_ON(nblocks <= 0);
handle = __ext4_journal_start_sb(dir->i_sb, line_no,
handle_type, nblocks,
- 0);
+ 0, 0);
if (IS_ERR(handle)) {
err = PTR_ERR(handle);
ext4_std_error(sb, err);
diff --git a/fs/ext4/indirect.c b/fs/ext4/indirect.c
index 36699a131168..3a4ab70fe9e0 100644
--- a/fs/ext4/indirect.c
+++ b/fs/ext4/indirect.c
@@ -331,11 +331,14 @@ static int ext4_alloc_branch(handle_t *handle,
for (i = 0; i <= indirect_blks; i++) {
if (i == indirect_blks) {
new_blocks[i] = ext4_mb_new_blocks(handle, ar, &err);
- } else
+ } else {
ar->goal = new_blocks[i] = ext4_new_meta_blocks(handle,
ar->inode, ar->goal,
ar->flags & EXT4_MB_DELALLOC_RESERVED,
NULL, &err);
+ /* Simplify error cleanup... */
+ branch[i+1].bh = NULL;
+ }
if (err) {
i--;
goto failed;
@@ -377,18 +380,25 @@ static int ext4_alloc_branch(handle_t *handle,
}
return 0;
failed:
+ if (i == indirect_blks) {
+ /* Free data blocks */
+ ext4_free_blocks(handle, ar->inode, NULL, new_blocks[i],
+ ar->len, 0);
+ i--;
+ }
for (; i >= 0; i--) {
/*
* We want to ext4_forget() only freshly allocated indirect
- * blocks. Buffer for new_blocks[i-1] is at branch[i].bh and
- * buffer at branch[0].bh is indirect block / inode already
- * existing before ext4_alloc_branch() was called.
+ * blocks. Buffer for new_blocks[i] is at branch[i+1].bh
+ * (buffer at branch[0].bh is indirect block / inode already
+ * existing before ext4_alloc_branch() was called). Also
+ * because blocks are freshly allocated, we don't need to
+ * revoke them which is why we don't set
+ * EXT4_FREE_BLOCKS_METADATA.
*/
- if (i > 0 && i != indirect_blks && branch[i].bh)
- ext4_forget(handle, 1, ar->inode, branch[i].bh,
- branch[i].bh->b_blocknr);
- ext4_free_blocks(handle, ar->inode, NULL, new_blocks[i],
- (i == indirect_blks) ? ar->len : 1, 0);
+ ext4_free_blocks(handle, ar->inode, branch[i+1].bh,
+ new_blocks[i], 1,
+ branch[i+1].bh ? EXT4_FREE_BLOCKS_FORGET : 0);
}
return err;
}
@@ -689,27 +699,63 @@ int ext4_ind_trans_blocks(struct inode *inode, int nrblocks)
return DIV_ROUND_UP(nrblocks, EXT4_ADDR_PER_BLOCK(inode->i_sb)) + 4;
}
+static int ext4_ind_trunc_restart_fn(handle_t *handle, struct inode *inode,
+ struct buffer_head *bh, int *dropped)
+{
+ int err;
+
+ if (bh) {
+ BUFFER_TRACE(bh, "call ext4_handle_dirty_metadata");
+ err = ext4_handle_dirty_metadata(handle, inode, bh);
+ if (unlikely(err))
+ return err;
+ }
+ err = ext4_mark_inode_dirty(handle, inode);
+ if (unlikely(err))
+ return err;
+ /*
+ * Drop i_data_sem to avoid deadlock with ext4_map_blocks. At this
+ * moment, get_block can be called only for blocks inside i_size since
+ * page cache has been already dropped and writes are blocked by
+ * i_mutex. So we can safely drop the i_data_sem here.
+ */
+ BUG_ON(EXT4_JOURNAL(inode) == NULL);
+ ext4_discard_preallocations(inode);
+ up_write(&EXT4_I(inode)->i_data_sem);
+ *dropped = 1;
+ return 0;
+}
+
/*
* Truncate transactions can be complex and absolutely huge. So we need to
* be able to restart the transaction at a conventient checkpoint to make
* sure we don't overflow the journal.
*
* Try to extend this transaction for the purposes of truncation. If
- * extend fails, we need to propagate the failure up and restart the
- * transaction in the top-level truncate loop. --sct
- *
- * Returns 0 if we managed to create more room. If we can't create more
- * room, and the transaction must be restarted we return 1.
+ * extend fails, we restart transaction.
*/
-static int try_to_extend_transaction(handle_t *handle, struct inode *inode)
+static int ext4_ind_truncate_ensure_credits(handle_t *handle,
+ struct inode *inode,
+ struct buffer_head *bh,
+ int revoke_creds)
{
- if (!ext4_handle_valid(handle))
- return 0;
- if (ext4_handle_has_enough_credits(handle, EXT4_RESERVE_TRANS_BLOCKS+1))
- return 0;
- if (!ext4_journal_extend(handle, ext4_blocks_for_truncate(inode)))
- return 0;
- return 1;
+ int ret;
+ int dropped = 0;
+
+ ret = ext4_journal_ensure_credits_fn(handle, EXT4_RESERVE_TRANS_BLOCKS,
+ ext4_blocks_for_truncate(inode), revoke_creds,
+ ext4_ind_trunc_restart_fn(handle, inode, bh, &dropped));
+ if (dropped)
+ down_write(&EXT4_I(inode)->i_data_sem);
+ if (ret <= 0)
+ return ret;
+ if (bh) {
+ BUFFER_TRACE(bh, "retaking write access");
+ ret = ext4_journal_get_write_access(handle, bh);
+ if (unlikely(ret))
+ return ret;
+ }
+ return 0;
}
/*
@@ -844,27 +890,10 @@ static int ext4_clear_blocks(handle_t *handle, struct inode *inode,
return 1;
}
- if (try_to_extend_transaction(handle, inode)) {
- if (bh) {
- BUFFER_TRACE(bh, "call ext4_handle_dirty_metadata");
- err = ext4_handle_dirty_metadata(handle, inode, bh);
- if (unlikely(err))
- goto out_err;
- }
- err = ext4_mark_inode_dirty(handle, inode);
- if (unlikely(err))
- goto out_err;
- err = ext4_truncate_restart_trans(handle, inode,
- ext4_blocks_for_truncate(inode));
- if (unlikely(err))
- goto out_err;
- if (bh) {
- BUFFER_TRACE(bh, "retaking write access");
- err = ext4_journal_get_write_access(handle, bh);
- if (unlikely(err))
- goto out_err;
- }
- }
+ err = ext4_ind_truncate_ensure_credits(handle, inode, bh,
+ ext4_free_data_revoke_credits(inode, count));
+ if (err < 0)
+ goto out_err;
for (p = first; p < last; p++)
*p = 0;
@@ -1047,11 +1076,11 @@ static void ext4_free_branches(handle_t *handle, struct inode *inode,
*/
if (ext4_handle_is_aborted(handle))
return;
- if (try_to_extend_transaction(handle, inode)) {
- ext4_mark_inode_dirty(handle, inode);
- ext4_truncate_restart_trans(handle, inode,
- ext4_blocks_for_truncate(inode));
- }
+ if (ext4_ind_truncate_ensure_credits(handle, inode,
+ NULL,
+ ext4_free_metadata_revoke_credits(
+ inode->i_sb, 1)) < 0)
+ return;
/*
* The forget flag here is critical because if
diff --git a/fs/ext4/inode-test.c b/fs/ext4/inode-test.c
new file mode 100644
index 000000000000..92a9da1774aa
--- /dev/null
+++ b/fs/ext4/inode-test.c
@@ -0,0 +1,272 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * KUnit test of ext4 inode that verify the seconds part of [a/c/m]
+ * timestamps in ext4 inode structs are decoded correctly.
+ */
+
+#include <kunit/test.h>
+#include <linux/kernel.h>
+#include <linux/time64.h>
+
+#include "ext4.h"
+
+/*
+ * For constructing the nonnegative timestamp lower bound value.
+ * binary: 00000000 00000000 00000000 00000000
+ */
+#define LOWER_MSB_0 0L
+/*
+ * For constructing the nonnegative timestamp upper bound value.
+ * binary: 01111111 11111111 11111111 11111111
+ *
+ */
+#define UPPER_MSB_0 0x7fffffffL
+/*
+ * For constructing the negative timestamp lower bound value.
+ * binary: 10000000 00000000 00000000 00000000
+ */
+#define LOWER_MSB_1 (-0x80000000L)
+/*
+ * For constructing the negative timestamp upper bound value.
+ * binary: 11111111 11111111 11111111 11111111
+ */
+#define UPPER_MSB_1 (-1L)
+/*
+ * Upper bound for nanoseconds value supported by the encoding.
+ * binary: 00111111 11111111 11111111 11111111
+ */
+#define MAX_NANOSECONDS ((1L << 30) - 1)
+
+#define CASE_NAME_FORMAT "%s: msb:%x lower_bound:%x extra_bits: %x"
+
+#define LOWER_BOUND_NEG_NO_EXTRA_BITS_CASE\
+ "1901-12-13 Lower bound of 32bit < 0 timestamp, no extra bits"
+#define UPPER_BOUND_NEG_NO_EXTRA_BITS_CASE\
+ "1969-12-31 Upper bound of 32bit < 0 timestamp, no extra bits"
+#define LOWER_BOUND_NONNEG_NO_EXTRA_BITS_CASE\
+ "1970-01-01 Lower bound of 32bit >=0 timestamp, no extra bits"
+#define UPPER_BOUND_NONNEG_NO_EXTRA_BITS_CASE\
+ "2038-01-19 Upper bound of 32bit >=0 timestamp, no extra bits"
+#define LOWER_BOUND_NEG_LO_1_CASE\
+ "2038-01-19 Lower bound of 32bit <0 timestamp, lo extra sec bit on"
+#define UPPER_BOUND_NEG_LO_1_CASE\
+ "2106-02-07 Upper bound of 32bit <0 timestamp, lo extra sec bit on"
+#define LOWER_BOUND_NONNEG_LO_1_CASE\
+ "2106-02-07 Lower bound of 32bit >=0 timestamp, lo extra sec bit on"
+#define UPPER_BOUND_NONNEG_LO_1_CASE\
+ "2174-02-25 Upper bound of 32bit >=0 timestamp, lo extra sec bit on"
+#define LOWER_BOUND_NEG_HI_1_CASE\
+ "2174-02-25 Lower bound of 32bit <0 timestamp, hi extra sec bit on"
+#define UPPER_BOUND_NEG_HI_1_CASE\
+ "2242-03-16 Upper bound of 32bit <0 timestamp, hi extra sec bit on"
+#define LOWER_BOUND_NONNEG_HI_1_CASE\
+ "2242-03-16 Lower bound of 32bit >=0 timestamp, hi extra sec bit on"
+#define UPPER_BOUND_NONNEG_HI_1_CASE\
+ "2310-04-04 Upper bound of 32bit >=0 timestamp, hi extra sec bit on"
+#define UPPER_BOUND_NONNEG_HI_1_NS_1_CASE\
+ "2310-04-04 Upper bound of 32bit>=0 timestamp, hi extra sec bit 1. 1 ns"
+#define LOWER_BOUND_NONNEG_HI_1_NS_MAX_CASE\
+ "2378-04-22 Lower bound of 32bit>= timestamp. Extra sec bits 1. Max ns"
+#define LOWER_BOUND_NONNEG_EXTRA_BITS_1_CASE\
+ "2378-04-22 Lower bound of 32bit >=0 timestamp. All extra sec bits on"
+#define UPPER_BOUND_NONNEG_EXTRA_BITS_1_CASE\
+ "2446-05-10 Upper bound of 32bit >=0 timestamp. All extra sec bits on"
+
+struct timestamp_expectation {
+ const char *test_case_name;
+ struct timespec64 expected;
+ u32 extra_bits;
+ bool msb_set;
+ bool lower_bound;
+};
+
+static time64_t get_32bit_time(const struct timestamp_expectation * const test)
+{
+ if (test->msb_set) {
+ if (test->lower_bound)
+ return LOWER_MSB_1;
+
+ return UPPER_MSB_1;
+ }
+
+ if (test->lower_bound)
+ return LOWER_MSB_0;
+ return UPPER_MSB_0;
+}
+
+
+/*
+ * Test data is derived from the table in the Inode Timestamps section of
+ * Documentation/filesystems/ext4/inodes.rst.
+ */
+static void inode_test_xtimestamp_decoding(struct kunit *test)
+{
+ const struct timestamp_expectation test_data[] = {
+ {
+ .test_case_name = LOWER_BOUND_NEG_NO_EXTRA_BITS_CASE,
+ .msb_set = true,
+ .lower_bound = true,
+ .extra_bits = 0,
+ .expected = {.tv_sec = -0x80000000LL, .tv_nsec = 0L},
+ },
+
+ {
+ .test_case_name = UPPER_BOUND_NEG_NO_EXTRA_BITS_CASE,
+ .msb_set = true,
+ .lower_bound = false,
+ .extra_bits = 0,
+ .expected = {.tv_sec = -1LL, .tv_nsec = 0L},
+ },
+
+ {
+ .test_case_name = LOWER_BOUND_NONNEG_NO_EXTRA_BITS_CASE,
+ .msb_set = false,
+ .lower_bound = true,
+ .extra_bits = 0,
+ .expected = {0LL, 0L},
+ },
+
+ {
+ .test_case_name = UPPER_BOUND_NONNEG_NO_EXTRA_BITS_CASE,
+ .msb_set = false,
+ .lower_bound = false,
+ .extra_bits = 0,
+ .expected = {.tv_sec = 0x7fffffffLL, .tv_nsec = 0L},
+ },
+
+ {
+ .test_case_name = LOWER_BOUND_NEG_LO_1_CASE,
+ .msb_set = true,
+ .lower_bound = true,
+ .extra_bits = 1,
+ .expected = {.tv_sec = 0x80000000LL, .tv_nsec = 0L},
+ },
+
+ {
+ .test_case_name = UPPER_BOUND_NEG_LO_1_CASE,
+ .msb_set = true,
+ .lower_bound = false,
+ .extra_bits = 1,
+ .expected = {.tv_sec = 0xffffffffLL, .tv_nsec = 0L},
+ },
+
+ {
+ .test_case_name = LOWER_BOUND_NONNEG_LO_1_CASE,
+ .msb_set = false,
+ .lower_bound = true,
+ .extra_bits = 1,
+ .expected = {.tv_sec = 0x100000000LL, .tv_nsec = 0L},
+ },
+
+ {
+ .test_case_name = UPPER_BOUND_NONNEG_LO_1_CASE,
+ .msb_set = false,
+ .lower_bound = false,
+ .extra_bits = 1,
+ .expected = {.tv_sec = 0x17fffffffLL, .tv_nsec = 0L},
+ },
+
+ {
+ .test_case_name = LOWER_BOUND_NEG_HI_1_CASE,
+ .msb_set = true,
+ .lower_bound = true,
+ .extra_bits = 2,
+ .expected = {.tv_sec = 0x180000000LL, .tv_nsec = 0L},
+ },
+
+ {
+ .test_case_name = UPPER_BOUND_NEG_HI_1_CASE,
+ .msb_set = true,
+ .lower_bound = false,
+ .extra_bits = 2,
+ .expected = {.tv_sec = 0x1ffffffffLL, .tv_nsec = 0L},
+ },
+
+ {
+ .test_case_name = LOWER_BOUND_NONNEG_HI_1_CASE,
+ .msb_set = false,
+ .lower_bound = true,
+ .extra_bits = 2,
+ .expected = {.tv_sec = 0x200000000LL, .tv_nsec = 0L},
+ },
+
+ {
+ .test_case_name = UPPER_BOUND_NONNEG_HI_1_CASE,
+ .msb_set = false,
+ .lower_bound = false,
+ .extra_bits = 2,
+ .expected = {.tv_sec = 0x27fffffffLL, .tv_nsec = 0L},
+ },
+
+ {
+ .test_case_name = UPPER_BOUND_NONNEG_HI_1_NS_1_CASE,
+ .msb_set = false,
+ .lower_bound = false,
+ .extra_bits = 6,
+ .expected = {.tv_sec = 0x27fffffffLL, .tv_nsec = 1L},
+ },
+
+ {
+ .test_case_name = LOWER_BOUND_NONNEG_HI_1_NS_MAX_CASE,
+ .msb_set = false,
+ .lower_bound = true,
+ .extra_bits = 0xFFFFFFFF,
+ .expected = {.tv_sec = 0x300000000LL,
+ .tv_nsec = MAX_NANOSECONDS},
+ },
+
+ {
+ .test_case_name = LOWER_BOUND_NONNEG_EXTRA_BITS_1_CASE,
+ .msb_set = false,
+ .lower_bound = true,
+ .extra_bits = 3,
+ .expected = {.tv_sec = 0x300000000LL, .tv_nsec = 0L},
+ },
+
+ {
+ .test_case_name = UPPER_BOUND_NONNEG_EXTRA_BITS_1_CASE,
+ .msb_set = false,
+ .lower_bound = false,
+ .extra_bits = 3,
+ .expected = {.tv_sec = 0x37fffffffLL, .tv_nsec = 0L},
+ }
+ };
+
+ struct timespec64 timestamp;
+ int i;
+
+ for (i = 0; i < ARRAY_SIZE(test_data); ++i) {
+ timestamp.tv_sec = get_32bit_time(&test_data[i]);
+ ext4_decode_extra_time(&timestamp,
+ cpu_to_le32(test_data[i].extra_bits));
+
+ KUNIT_EXPECT_EQ_MSG(test,
+ test_data[i].expected.tv_sec,
+ timestamp.tv_sec,
+ CASE_NAME_FORMAT,
+ test_data[i].test_case_name,
+ test_data[i].msb_set,
+ test_data[i].lower_bound,
+ test_data[i].extra_bits);
+ KUNIT_EXPECT_EQ_MSG(test,
+ test_data[i].expected.tv_nsec,
+ timestamp.tv_nsec,
+ CASE_NAME_FORMAT,
+ test_data[i].test_case_name,
+ test_data[i].msb_set,
+ test_data[i].lower_bound,
+ test_data[i].extra_bits);
+ }
+}
+
+static struct kunit_case ext4_inode_test_cases[] = {
+ KUNIT_CASE(inode_test_xtimestamp_decoding),
+ {}
+};
+
+static struct kunit_suite ext4_inode_test_suite = {
+ .name = "ext4_inode_test",
+ .test_cases = ext4_inode_test_cases,
+};
+
+kunit_test_suite(ext4_inode_test_suite);
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index abaaf7d96ca4..28f28de0c1b6 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -164,39 +164,18 @@ int ext4_inode_is_fast_symlink(struct inode *inode)
}
/*
- * Restart the transaction associated with *handle. This does a commit,
- * so before we call here everything must be consistently dirtied against
- * this transaction.
- */
-int ext4_truncate_restart_trans(handle_t *handle, struct inode *inode,
- int nblocks)
-{
- int ret;
-
- /*
- * Drop i_data_sem to avoid deadlock with ext4_map_blocks. At this
- * moment, get_block can be called only for blocks inside i_size since
- * page cache has been already dropped and writes are blocked by
- * i_mutex. So we can safely drop the i_data_sem here.
- */
- BUG_ON(EXT4_JOURNAL(inode) == NULL);
- jbd_debug(2, "restarting handle %p\n", handle);
- up_write(&EXT4_I(inode)->i_data_sem);
- ret = ext4_journal_restart(handle, nblocks);
- down_write(&EXT4_I(inode)->i_data_sem);
- ext4_discard_preallocations(inode);
-
- return ret;
-}
-
-/*
* Called at the last iput() if i_nlink is zero.
*/
void ext4_evict_inode(struct inode *inode)
{
handle_t *handle;
int err;
- int extra_credits = 3;
+ /*
+ * Credits for final inode cleanup and freeing:
+ * sb + inode (ext4_orphan_del()), block bitmap, group descriptor
+ * (xattr block freeing), bitmap, group descriptor (inode freeing)
+ */
+ int extra_credits = 6;
struct ext4_xattr_inode_array *ea_inode_array = NULL;
trace_ext4_evict_inode(inode);
@@ -252,8 +231,12 @@ void ext4_evict_inode(struct inode *inode)
if (!IS_NOQUOTA(inode))
extra_credits += EXT4_MAXQUOTAS_DEL_BLOCKS(inode->i_sb);
+ /*
+ * Block bitmap, group descriptor, and inode are accounted in both
+ * ext4_blocks_for_truncate() and extra_credits. So subtract 3.
+ */
handle = ext4_journal_start(inode, EXT4_HT_TRUNCATE,
- ext4_blocks_for_truncate(inode)+extra_credits);
+ ext4_blocks_for_truncate(inode) + extra_credits - 3);
if (IS_ERR(handle)) {
ext4_std_error(inode->i_sb, PTR_ERR(handle));
/*
@@ -827,136 +810,6 @@ int ext4_get_block_unwritten(struct inode *inode, sector_t iblock,
#define DIO_MAX_BLOCKS 4096
/*
- * Get blocks function for the cases that need to start a transaction -
- * generally difference cases of direct IO and DAX IO. It also handles retries
- * in case of ENOSPC.
- */
-static int ext4_get_block_trans(struct inode *inode, sector_t iblock,
- struct buffer_head *bh_result, int flags)
-{
- int dio_credits;
- handle_t *handle;
- int retries = 0;
- int ret;
-
- /* Trim mapping request to maximum we can map at once for DIO */
- if (bh_result->b_size >> inode->i_blkbits > DIO_MAX_BLOCKS)
- bh_result->b_size = DIO_MAX_BLOCKS << inode->i_blkbits;
- dio_credits = ext4_chunk_trans_blocks(inode,
- bh_result->b_size >> inode->i_blkbits);
-retry:
- handle = ext4_journal_start(inode, EXT4_HT_MAP_BLOCKS, dio_credits);
- if (IS_ERR(handle))
- return PTR_ERR(handle);
-
- ret = _ext4_get_block(inode, iblock, bh_result, flags);
- ext4_journal_stop(handle);
-
- if (ret == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries))
- goto retry;
- return ret;
-}
-
-/* Get block function for DIO reads and writes to inodes without extents */
-int ext4_dio_get_block(struct inode *inode, sector_t iblock,
- struct buffer_head *bh, int create)
-{
- /* We don't expect handle for direct IO */
- WARN_ON_ONCE(ext4_journal_current_handle());
-
- if (!create)
- return _ext4_get_block(inode, iblock, bh, 0);
- return ext4_get_block_trans(inode, iblock, bh, EXT4_GET_BLOCKS_CREATE);
-}
-
-/*
- * Get block function for AIO DIO writes when we create unwritten extent if
- * blocks are not allocated yet. The extent will be converted to written
- * after IO is complete.
- */
-static int ext4_dio_get_block_unwritten_async(struct inode *inode,
- sector_t iblock, struct buffer_head *bh_result, int create)
-{
- int ret;
-
- /* We don't expect handle for direct IO */
- WARN_ON_ONCE(ext4_journal_current_handle());
-
- ret = ext4_get_block_trans(inode, iblock, bh_result,
- EXT4_GET_BLOCKS_IO_CREATE_EXT);
-
- /*
- * When doing DIO using unwritten extents, we need io_end to convert
- * unwritten extents to written on IO completion. We allocate io_end
- * once we spot unwritten extent and store it in b_private. Generic
- * DIO code keeps b_private set and furthermore passes the value to
- * our completion callback in 'private' argument.
- */
- if (!ret && buffer_unwritten(bh_result)) {
- if (!bh_result->b_private) {
- ext4_io_end_t *io_end;
-
- io_end = ext4_init_io_end(inode, GFP_KERNEL);
- if (!io_end)
- return -ENOMEM;
- bh_result->b_private = io_end;
- ext4_set_io_unwritten_flag(inode, io_end);
- }
- set_buffer_defer_completion(bh_result);
- }
-
- return ret;
-}
-
-/*
- * Get block function for non-AIO DIO writes when we create unwritten extent if
- * blocks are not allocated yet. The extent will be converted to written
- * after IO is complete by ext4_direct_IO_write().
- */
-static int ext4_dio_get_block_unwritten_sync(struct inode *inode,
- sector_t iblock, struct buffer_head *bh_result, int create)
-{
- int ret;
-
- /* We don't expect handle for direct IO */
- WARN_ON_ONCE(ext4_journal_current_handle());
-
- ret = ext4_get_block_trans(inode, iblock, bh_result,
- EXT4_GET_BLOCKS_IO_CREATE_EXT);
-
- /*
- * Mark inode as having pending DIO writes to unwritten extents.
- * ext4_direct_IO_write() checks this flag and converts extents to
- * written.
- */
- if (!ret && buffer_unwritten(bh_result))
- ext4_set_inode_state(inode, EXT4_STATE_DIO_UNWRITTEN);
-
- return ret;
-}
-
-static int ext4_dio_get_block_overwrite(struct inode *inode, sector_t iblock,
- struct buffer_head *bh_result, int create)
-{
- int ret;
-
- ext4_debug("ext4_dio_get_block_overwrite: inode %lu, create flag %d\n",
- inode->i_ino, create);
- /* We don't expect handle for direct IO */
- WARN_ON_ONCE(ext4_journal_current_handle());
-
- ret = _ext4_get_block(inode, iblock, bh_result, 0);
- /*
- * Blocks should have been preallocated! ext4_file_write_iter() checks
- * that.
- */
- WARN_ON_ONCE(!buffer_mapped(bh_result) || buffer_unwritten(bh_result));
-
- return ret;
-}
-
-
-/*
* `handle' can be NULL if create is zero
*/
struct buffer_head *ext4_getblk(handle_t *handle, struct inode *inode,
@@ -2341,6 +2194,79 @@ static int mpage_process_page_bufs(struct mpage_da_data *mpd,
}
/*
+ * mpage_process_page - update page buffers corresponding to changed extent and
+ * may submit fully mapped page for IO
+ *
+ * @mpd - description of extent to map, on return next extent to map
+ * @m_lblk - logical block mapping.
+ * @m_pblk - corresponding physical mapping.
+ * @map_bh - determines on return whether this page requires any further
+ * mapping or not.
+ * Scan given page buffers corresponding to changed extent and update buffer
+ * state according to new extent state.
+ * We map delalloc buffers to their physical location, clear unwritten bits.
+ * If the given page is not fully mapped, we update @map to the next extent in
+ * the given page that needs mapping & return @map_bh as true.
+ */
+static int mpage_process_page(struct mpage_da_data *mpd, struct page *page,
+ ext4_lblk_t *m_lblk, ext4_fsblk_t *m_pblk,
+ bool *map_bh)
+{
+ struct buffer_head *head, *bh;
+ ext4_io_end_t *io_end = mpd->io_submit.io_end;
+ ext4_lblk_t lblk = *m_lblk;
+ ext4_fsblk_t pblock = *m_pblk;
+ int err = 0;
+ int blkbits = mpd->inode->i_blkbits;
+ ssize_t io_end_size = 0;
+ struct ext4_io_end_vec *io_end_vec = ext4_last_io_end_vec(io_end);
+
+ bh = head = page_buffers(page);
+ do {
+ if (lblk < mpd->map.m_lblk)
+ continue;
+ if (lblk >= mpd->map.m_lblk + mpd->map.m_len) {
+ /*
+ * Buffer after end of mapped extent.
+ * Find next buffer in the page to map.
+ */
+ mpd->map.m_len = 0;
+ mpd->map.m_flags = 0;
+ io_end_vec->size += io_end_size;
+ io_end_size = 0;
+
+ err = mpage_process_page_bufs(mpd, head, bh, lblk);
+ if (err > 0)
+ err = 0;
+ if (!err && mpd->map.m_len && mpd->map.m_lblk > lblk) {
+ io_end_vec = ext4_alloc_io_end_vec(io_end);
+ if (IS_ERR(io_end_vec)) {
+ err = PTR_ERR(io_end_vec);
+ goto out;
+ }
+ io_end_vec->offset = mpd->map.m_lblk << blkbits;
+ }
+ *map_bh = true;
+ goto out;
+ }
+ if (buffer_delay(bh)) {
+ clear_buffer_delay(bh);
+ bh->b_blocknr = pblock++;
+ }
+ clear_buffer_unwritten(bh);
+ io_end_size += (1 << blkbits);
+ } while (lblk++, (bh = bh->b_this_page) != head);
+
+ io_end_vec->size += io_end_size;
+ io_end_size = 0;
+ *map_bh = false;
+out:
+ *m_lblk = lblk;
+ *m_pblk = pblock;
+ return err;
+}
+
+/*
* mpage_map_buffers - update buffers corresponding to changed extent and
* submit fully mapped pages for IO
*
@@ -2359,12 +2285,12 @@ static int mpage_map_and_submit_buffers(struct mpage_da_data *mpd)
struct pagevec pvec;
int nr_pages, i;
struct inode *inode = mpd->inode;
- struct buffer_head *head, *bh;
int bpp_bits = PAGE_SHIFT - inode->i_blkbits;
pgoff_t start, end;
ext4_lblk_t lblk;
- sector_t pblock;
+ ext4_fsblk_t pblock;
int err;
+ bool map_bh = false;
start = mpd->map.m_lblk >> bpp_bits;
end = (mpd->map.m_lblk + mpd->map.m_len - 1) >> bpp_bits;
@@ -2380,50 +2306,19 @@ static int mpage_map_and_submit_buffers(struct mpage_da_data *mpd)
for (i = 0; i < nr_pages; i++) {
struct page *page = pvec.pages[i];
- bh = head = page_buffers(page);
- do {
- if (lblk < mpd->map.m_lblk)
- continue;
- if (lblk >= mpd->map.m_lblk + mpd->map.m_len) {
- /*
- * Buffer after end of mapped extent.
- * Find next buffer in the page to map.
- */
- mpd->map.m_len = 0;
- mpd->map.m_flags = 0;
- /*
- * FIXME: If dioread_nolock supports
- * blocksize < pagesize, we need to make
- * sure we add size mapped so far to
- * io_end->size as the following call
- * can submit the page for IO.
- */
- err = mpage_process_page_bufs(mpd, head,
- bh, lblk);
- pagevec_release(&pvec);
- if (err > 0)
- err = 0;
- return err;
- }
- if (buffer_delay(bh)) {
- clear_buffer_delay(bh);
- bh->b_blocknr = pblock++;
- }
- clear_buffer_unwritten(bh);
- } while (lblk++, (bh = bh->b_this_page) != head);
-
+ err = mpage_process_page(mpd, page, &lblk, &pblock,
+ &map_bh);
/*
- * FIXME: This is going to break if dioread_nolock
- * supports blocksize < pagesize as we will try to
- * convert potentially unmapped parts of inode.
+ * If map_bh is true, means page may require further bh
+ * mapping, or maybe the page was submitted for IO.
+ * So we return to call further extent mapping.
*/
- mpd->io_submit.io_end->size += PAGE_SIZE;
+ if (err < 0 || map_bh == true)
+ goto out;
/* Page fully mapped - let IO run! */
err = mpage_submit_page(mpd, page);
- if (err < 0) {
- pagevec_release(&pvec);
- return err;
- }
+ if (err < 0)
+ goto out;
}
pagevec_release(&pvec);
}
@@ -2431,6 +2326,9 @@ static int mpage_map_and_submit_buffers(struct mpage_da_data *mpd)
mpd->map.m_len = 0;
mpd->map.m_flags = 0;
return 0;
+out:
+ pagevec_release(&pvec);
+ return err;
}
static int mpage_map_one_extent(handle_t *handle, struct mpage_da_data *mpd)
@@ -2510,9 +2408,13 @@ static int mpage_map_and_submit_extent(handle_t *handle,
int err;
loff_t disksize;
int progress = 0;
+ ext4_io_end_t *io_end = mpd->io_submit.io_end;
+ struct ext4_io_end_vec *io_end_vec;
- mpd->io_submit.io_end->offset =
- ((loff_t)map->m_lblk) << inode->i_blkbits;
+ io_end_vec = ext4_alloc_io_end_vec(io_end);
+ if (IS_ERR(io_end_vec))
+ return PTR_ERR(io_end_vec);
+ io_end_vec->offset = ((loff_t)map->m_lblk) << inode->i_blkbits;
do {
err = mpage_map_one_extent(handle, mpd);
if (err < 0) {
@@ -3406,473 +3308,235 @@ static bool ext4_inode_datasync_dirty(struct inode *inode)
return inode->i_state & I_DIRTY_DATASYNC;
}
-static int ext4_iomap_begin(struct inode *inode, loff_t offset, loff_t length,
- unsigned flags, struct iomap *iomap, struct iomap *srcmap)
+static void ext4_set_iomap(struct inode *inode, struct iomap *iomap,
+ struct ext4_map_blocks *map, loff_t offset,
+ loff_t length)
{
- struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
- unsigned int blkbits = inode->i_blkbits;
- unsigned long first_block, last_block;
- struct ext4_map_blocks map;
- bool delalloc = false;
- int ret;
-
- if ((offset >> blkbits) > EXT4_MAX_LOGICAL_BLOCK)
- return -EINVAL;
- first_block = offset >> blkbits;
- last_block = min_t(loff_t, (offset + length - 1) >> blkbits,
- EXT4_MAX_LOGICAL_BLOCK);
-
- if (flags & IOMAP_REPORT) {
- if (ext4_has_inline_data(inode)) {
- ret = ext4_inline_data_iomap(inode, iomap);
- if (ret != -EAGAIN) {
- if (ret == 0 && offset >= iomap->length)
- ret = -ENOENT;
- return ret;
- }
- }
- } else {
- if (WARN_ON_ONCE(ext4_has_inline_data(inode)))
- return -ERANGE;
- }
-
- map.m_lblk = first_block;
- map.m_len = last_block - first_block + 1;
-
- if (flags & IOMAP_REPORT) {
- ret = ext4_map_blocks(NULL, inode, &map, 0);
- if (ret < 0)
- return ret;
-
- if (ret == 0) {
- ext4_lblk_t end = map.m_lblk + map.m_len - 1;
- struct extent_status es;
-
- ext4_es_find_extent_range(inode, &ext4_es_is_delayed,
- map.m_lblk, end, &es);
-
- if (!es.es_len || es.es_lblk > end) {
- /* entire range is a hole */
- } else if (es.es_lblk > map.m_lblk) {
- /* range starts with a hole */
- map.m_len = es.es_lblk - map.m_lblk;
- } else {
- ext4_lblk_t offs = 0;
-
- if (es.es_lblk < map.m_lblk)
- offs = map.m_lblk - es.es_lblk;
- map.m_lblk = es.es_lblk + offs;
- map.m_len = es.es_len - offs;
- delalloc = true;
- }
- }
- } else if (flags & IOMAP_WRITE) {
- int dio_credits;
- handle_t *handle;
- int retries = 0;
-
- /* Trim mapping request to maximum we can map at once for DIO */
- if (map.m_len > DIO_MAX_BLOCKS)
- map.m_len = DIO_MAX_BLOCKS;
- dio_credits = ext4_chunk_trans_blocks(inode, map.m_len);
-retry:
- /*
- * Either we allocate blocks and then we don't get unwritten
- * extent so we have reserved enough credits, or the blocks
- * are already allocated and unwritten and in that case
- * extent conversion fits in the credits as well.
- */
- handle = ext4_journal_start(inode, EXT4_HT_MAP_BLOCKS,
- dio_credits);
- if (IS_ERR(handle))
- return PTR_ERR(handle);
-
- ret = ext4_map_blocks(handle, inode, &map,
- EXT4_GET_BLOCKS_CREATE_ZERO);
- if (ret < 0) {
- ext4_journal_stop(handle);
- if (ret == -ENOSPC &&
- ext4_should_retry_alloc(inode->i_sb, &retries))
- goto retry;
- return ret;
- }
-
- /*
- * If we added blocks beyond i_size, we need to make sure they
- * will get truncated if we crash before updating i_size in
- * ext4_iomap_end(). For faults we don't need to do that (and
- * even cannot because for orphan list operations inode_lock is
- * required) - if we happen to instantiate block beyond i_size,
- * it is because we race with truncate which has already added
- * the inode to the orphan list.
- */
- if (!(flags & IOMAP_FAULT) && first_block + map.m_len >
- (i_size_read(inode) + (1 << blkbits) - 1) >> blkbits) {
- int err;
-
- err = ext4_orphan_add(handle, inode);
- if (err < 0) {
- ext4_journal_stop(handle);
- return err;
- }
- }
- ext4_journal_stop(handle);
- } else {
- ret = ext4_map_blocks(NULL, inode, &map, 0);
- if (ret < 0)
- return ret;
- }
+ u8 blkbits = inode->i_blkbits;
+ /*
+ * Writes that span EOF might trigger an I/O size update on completion,
+ * so consider them to be dirty for the purpose of O_DSYNC, even if
+ * there is no other metadata changes being made or are pending.
+ */
iomap->flags = 0;
- if (ext4_inode_datasync_dirty(inode))
+ if (ext4_inode_datasync_dirty(inode) ||
+ offset + length > i_size_read(inode))
iomap->flags |= IOMAP_F_DIRTY;
+
+ if (map->m_flags & EXT4_MAP_NEW)
+ iomap->flags |= IOMAP_F_NEW;
+
iomap->bdev = inode->i_sb->s_bdev;
- iomap->dax_dev = sbi->s_daxdev;
- iomap->offset = (u64)first_block << blkbits;
- iomap->length = (u64)map.m_len << blkbits;
+ iomap->dax_dev = EXT4_SB(inode->i_sb)->s_daxdev;
+ iomap->offset = (u64) map->m_lblk << blkbits;
+ iomap->length = (u64) map->m_len << blkbits;
- if (ret == 0) {
- iomap->type = delalloc ? IOMAP_DELALLOC : IOMAP_HOLE;
- iomap->addr = IOMAP_NULL_ADDR;
+ /*
+ * Flags passed to ext4_map_blocks() for direct I/O writes can result
+ * in m_flags having both EXT4_MAP_MAPPED and EXT4_MAP_UNWRITTEN bits
+ * set. In order for any allocated unwritten extents to be converted
+ * into written extents correctly within the ->end_io() handler, we
+ * need to ensure that the iomap->type is set appropriately. Hence, the
+ * reason why we need to check whether the EXT4_MAP_UNWRITTEN bit has
+ * been set first.
+ */
+ if (map->m_flags & EXT4_MAP_UNWRITTEN) {
+ iomap->type = IOMAP_UNWRITTEN;
+ iomap->addr = (u64) map->m_pblk << blkbits;
+ } else if (map->m_flags & EXT4_MAP_MAPPED) {
+ iomap->type = IOMAP_MAPPED;
+ iomap->addr = (u64) map->m_pblk << blkbits;
} else {
- if (map.m_flags & EXT4_MAP_MAPPED) {
- iomap->type = IOMAP_MAPPED;
- } else if (map.m_flags & EXT4_MAP_UNWRITTEN) {
- iomap->type = IOMAP_UNWRITTEN;
- } else {
- WARN_ON_ONCE(1);
- return -EIO;
- }
- iomap->addr = (u64)map.m_pblk << blkbits;
+ iomap->type = IOMAP_HOLE;
+ iomap->addr = IOMAP_NULL_ADDR;
}
-
- if (map.m_flags & EXT4_MAP_NEW)
- iomap->flags |= IOMAP_F_NEW;
-
- return 0;
}
-static int ext4_iomap_end(struct inode *inode, loff_t offset, loff_t length,
- ssize_t written, unsigned flags, struct iomap *iomap)
+static int ext4_iomap_alloc(struct inode *inode, struct ext4_map_blocks *map,
+ unsigned int flags)
{
- int ret = 0;
handle_t *handle;
- int blkbits = inode->i_blkbits;
- bool truncate = false;
-
- if (!(flags & IOMAP_WRITE) || (flags & IOMAP_FAULT))
- return 0;
+ u8 blkbits = inode->i_blkbits;
+ int ret, dio_credits, m_flags = 0, retries = 0;
- handle = ext4_journal_start(inode, EXT4_HT_INODE, 2);
- if (IS_ERR(handle)) {
- ret = PTR_ERR(handle);
- goto orphan_del;
- }
- if (ext4_update_inode_size(inode, offset + written))
- ext4_mark_inode_dirty(handle, inode);
/*
- * We may need to truncate allocated but not written blocks beyond EOF.
+ * Trim the mapping request to the maximum value that we can map at
+ * once for direct I/O.
*/
- if (iomap->offset + iomap->length >
- ALIGN(inode->i_size, 1 << blkbits)) {
- ext4_lblk_t written_blk, end_blk;
+ if (map->m_len > DIO_MAX_BLOCKS)
+ map->m_len = DIO_MAX_BLOCKS;
+ dio_credits = ext4_chunk_trans_blocks(inode, map->m_len);
- written_blk = (offset + written) >> blkbits;
- end_blk = (offset + length) >> blkbits;
- if (written_blk < end_blk && ext4_can_truncate(inode))
- truncate = true;
- }
+retry:
/*
- * Remove inode from orphan list if we were extending a inode and
- * everything went fine.
+ * Either we allocate blocks and then don't get an unwritten extent, so
+ * in that case we have reserved enough credits. Or, the blocks are
+ * already allocated and unwritten. In that case, the extent conversion
+ * fits into the credits as well.
*/
- if (!truncate && inode->i_nlink &&
- !list_empty(&EXT4_I(inode)->i_orphan))
- ext4_orphan_del(handle, inode);
- ext4_journal_stop(handle);
- if (truncate) {
- ext4_truncate_failed_write(inode);
-orphan_del:
- /*
- * If truncate failed early the inode might still be on the
- * orphan list; we need to make sure the inode is removed from
- * the orphan list in that case.
- */
- if (inode->i_nlink)
- ext4_orphan_del(NULL, inode);
- }
- return ret;
-}
-
-const struct iomap_ops ext4_iomap_ops = {
- .iomap_begin = ext4_iomap_begin,
- .iomap_end = ext4_iomap_end,
-};
-
-static int ext4_end_io_dio(struct kiocb *iocb, loff_t offset,
- ssize_t size, void *private)
-{
- ext4_io_end_t *io_end = private;
+ handle = ext4_journal_start(inode, EXT4_HT_MAP_BLOCKS, dio_credits);
+ if (IS_ERR(handle))
+ return PTR_ERR(handle);
- /* if not async direct IO just return */
- if (!io_end)
- return 0;
+ /*
+ * DAX and direct I/O are the only two operations that are currently
+ * supported with IOMAP_WRITE.
+ */
+ WARN_ON(!IS_DAX(inode) && !(flags & IOMAP_DIRECT));
+ if (IS_DAX(inode))
+ m_flags = EXT4_GET_BLOCKS_CREATE_ZERO;
+ /*
+ * We use i_size instead of i_disksize here because delalloc writeback
+ * can complete at any point during the I/O and subsequently push the
+ * i_disksize out to i_size. This could be beyond where direct I/O is
+ * happening and thus expose allocated blocks to direct I/O reads.
+ */
+ else if ((map->m_lblk * (1 << blkbits)) >= i_size_read(inode))
+ m_flags = EXT4_GET_BLOCKS_CREATE;
+ else if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))
+ m_flags = EXT4_GET_BLOCKS_IO_CREATE_EXT;
- ext_debug("ext4_end_io_dio(): io_end 0x%p "
- "for inode %lu, iocb 0x%p, offset %llu, size %zd\n",
- io_end, io_end->inode->i_ino, iocb, offset, size);
+ ret = ext4_map_blocks(handle, inode, map, m_flags);
/*
- * Error during AIO DIO. We cannot convert unwritten extents as the
- * data was not written. Just clear the unwritten flag and drop io_end.
+ * We cannot fill holes in indirect tree based inodes as that could
+ * expose stale data in the case of a crash. Use the magic error code
+ * to fallback to buffered I/O.
*/
- if (size <= 0) {
- ext4_clear_io_unwritten_flag(io_end);
- size = 0;
- }
- io_end->offset = offset;
- io_end->size = size;
- ext4_put_io_end(io_end);
+ if (!m_flags && !ret)
+ ret = -ENOTBLK;
- return 0;
+ ext4_journal_stop(handle);
+ if (ret == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries))
+ goto retry;
+
+ return ret;
}
-/*
- * Handling of direct IO writes.
- *
- * For ext4 extent files, ext4 will do direct-io write even to holes,
- * preallocated extents, and those write extend the file, no need to
- * fall back to buffered IO.
- *
- * For holes, we fallocate those blocks, mark them as unwritten
- * If those blocks were preallocated, we mark sure they are split, but
- * still keep the range to write as unwritten.
- *
- * The unwritten extents will be converted to written when DIO is completed.
- * For async direct IO, since the IO may still pending when return, we
- * set up an end_io call back function, which will do the conversion
- * when async direct IO completed.
- *
- * If the O_DIRECT write will extend the file then add this inode to the
- * orphan list. So recovery will truncate it back to the original size
- * if the machine crashes during the write.
- *
- */
-static ssize_t ext4_direct_IO_write(struct kiocb *iocb, struct iov_iter *iter)
+
+static int ext4_iomap_begin(struct inode *inode, loff_t offset, loff_t length,
+ unsigned flags, struct iomap *iomap, struct iomap *srcmap)
{
- struct file *file = iocb->ki_filp;
- struct inode *inode = file->f_mapping->host;
- struct ext4_inode_info *ei = EXT4_I(inode);
- ssize_t ret;
- loff_t offset = iocb->ki_pos;
- size_t count = iov_iter_count(iter);
- int overwrite = 0;
- get_block_t *get_block_func = NULL;
- int dio_flags = 0;
- loff_t final_size = offset + count;
- int orphan = 0;
- handle_t *handle;
+ int ret;
+ struct ext4_map_blocks map;
+ u8 blkbits = inode->i_blkbits;
- if (final_size > inode->i_size || final_size > ei->i_disksize) {
- /* Credits for sb + inode write */
- handle = ext4_journal_start(inode, EXT4_HT_INODE, 2);
- if (IS_ERR(handle)) {
- ret = PTR_ERR(handle);
- goto out;
- }
- ret = ext4_orphan_add(handle, inode);
- if (ret) {
- ext4_journal_stop(handle);
- goto out;
- }
- orphan = 1;
- ext4_update_i_disksize(inode, inode->i_size);
- ext4_journal_stop(handle);
- }
+ if ((offset >> blkbits) > EXT4_MAX_LOGICAL_BLOCK)
+ return -EINVAL;
- BUG_ON(iocb->private == NULL);
+ if (WARN_ON_ONCE(ext4_has_inline_data(inode)))
+ return -ERANGE;
/*
- * Make all waiters for direct IO properly wait also for extent
- * conversion. This also disallows race between truncate() and
- * overwrite DIO as i_dio_count needs to be incremented under i_mutex.
+ * Calculate the first and last logical blocks respectively.
*/
- inode_dio_begin(inode);
+ map.m_lblk = offset >> blkbits;
+ map.m_len = min_t(loff_t, (offset + length - 1) >> blkbits,
+ EXT4_MAX_LOGICAL_BLOCK) - map.m_lblk + 1;
+
+ if (flags & IOMAP_WRITE)
+ ret = ext4_iomap_alloc(inode, &map, flags);
+ else
+ ret = ext4_map_blocks(NULL, inode, &map, 0);
- /* If we do a overwrite dio, i_mutex locking can be released */
- overwrite = *((int *)iocb->private);
+ if (ret < 0)
+ return ret;
- if (overwrite)
- inode_unlock(inode);
+ ext4_set_iomap(inode, iomap, &map, offset, length);
+ return 0;
+}
+
+static int ext4_iomap_end(struct inode *inode, loff_t offset, loff_t length,
+ ssize_t written, unsigned flags, struct iomap *iomap)
+{
/*
- * For extent mapped files we could direct write to holes and fallocate.
- *
- * Allocated blocks to fill the hole are marked as unwritten to prevent
- * parallel buffered read to expose the stale data before DIO complete
- * the data IO.
- *
- * As to previously fallocated extents, ext4 get_block will just simply
- * mark the buffer mapped but still keep the extents unwritten.
- *
- * For non AIO case, we will convert those unwritten extents to written
- * after return back from blockdev_direct_IO. That way we save us from
- * allocating io_end structure and also the overhead of offloading
- * the extent convertion to a workqueue.
- *
- * For async DIO, the conversion needs to be deferred when the
- * IO is completed. The ext4 end_io callback function will be
- * called to take care of the conversion work. Here for async
- * case, we allocate an io_end structure to hook to the iocb.
+ * Check to see whether an error occurred while writing out the data to
+ * the allocated blocks. If so, return the magic error code so that we
+ * fallback to buffered I/O and attempt to complete the remainder of
+ * the I/O. Any blocks that may have been allocated in preparation for
+ * the direct I/O will be reused during buffered I/O.
*/
- iocb->private = NULL;
- if (overwrite)
- get_block_func = ext4_dio_get_block_overwrite;
- else if (!ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS) ||
- round_down(offset, i_blocksize(inode)) >= inode->i_size) {
- get_block_func = ext4_dio_get_block;
- dio_flags = DIO_LOCKING | DIO_SKIP_HOLES;
- } else if (is_sync_kiocb(iocb)) {
- get_block_func = ext4_dio_get_block_unwritten_sync;
- dio_flags = DIO_LOCKING;
- } else {
- get_block_func = ext4_dio_get_block_unwritten_async;
- dio_flags = DIO_LOCKING;
- }
- ret = __blockdev_direct_IO(iocb, inode, inode->i_sb->s_bdev, iter,
- get_block_func, ext4_end_io_dio, NULL,
- dio_flags);
+ if (flags & (IOMAP_WRITE | IOMAP_DIRECT) && written == 0)
+ return -ENOTBLK;
- if (ret > 0 && !overwrite && ext4_test_inode_state(inode,
- EXT4_STATE_DIO_UNWRITTEN)) {
- int err;
- /*
- * for non AIO case, since the IO is already
- * completed, we could do the conversion right here
- */
- err = ext4_convert_unwritten_extents(NULL, inode,
- offset, ret);
- if (err < 0)
- ret = err;
- ext4_clear_inode_state(inode, EXT4_STATE_DIO_UNWRITTEN);
- }
+ return 0;
+}
- inode_dio_end(inode);
- /* take i_mutex locking again if we do a ovewrite dio */
- if (overwrite)
- inode_lock(inode);
+const struct iomap_ops ext4_iomap_ops = {
+ .iomap_begin = ext4_iomap_begin,
+ .iomap_end = ext4_iomap_end,
+};
- if (ret < 0 && final_size > inode->i_size)
- ext4_truncate_failed_write(inode);
+static bool ext4_iomap_is_delalloc(struct inode *inode,
+ struct ext4_map_blocks *map)
+{
+ struct extent_status es;
+ ext4_lblk_t offset = 0, end = map->m_lblk + map->m_len - 1;
- /* Handle extending of i_size after direct IO write */
- if (orphan) {
- int err;
+ ext4_es_find_extent_range(inode, &ext4_es_is_delayed,
+ map->m_lblk, end, &es);
- /* Credits for sb + inode write */
- handle = ext4_journal_start(inode, EXT4_HT_INODE, 2);
- if (IS_ERR(handle)) {
- /*
- * We wrote the data but cannot extend
- * i_size. Bail out. In async io case, we do
- * not return error here because we have
- * already submmitted the corresponding
- * bio. Returning error here makes the caller
- * think that this IO is done and failed
- * resulting in race with bio's completion
- * handler.
- */
- if (!ret)
- ret = PTR_ERR(handle);
- if (inode->i_nlink)
- ext4_orphan_del(NULL, inode);
+ if (!es.es_len || es.es_lblk > end)
+ return false;
- goto out;
- }
- if (inode->i_nlink)
- ext4_orphan_del(handle, inode);
- if (ret > 0) {
- loff_t end = offset + ret;
- if (end > inode->i_size || end > ei->i_disksize) {
- ext4_update_i_disksize(inode, end);
- if (end > inode->i_size)
- i_size_write(inode, end);
- /*
- * We're going to return a positive `ret'
- * here due to non-zero-length I/O, so there's
- * no way of reporting error returns from
- * ext4_mark_inode_dirty() to userspace. So
- * ignore it.
- */
- ext4_mark_inode_dirty(handle, inode);
- }
- }
- err = ext4_journal_stop(handle);
- if (ret == 0)
- ret = err;
+ if (es.es_lblk > map->m_lblk) {
+ map->m_len = es.es_lblk - map->m_lblk;
+ return false;
}
-out:
- return ret;
-}
-static ssize_t ext4_direct_IO_read(struct kiocb *iocb, struct iov_iter *iter)
-{
- struct address_space *mapping = iocb->ki_filp->f_mapping;
- struct inode *inode = mapping->host;
- size_t count = iov_iter_count(iter);
- ssize_t ret;
+ offset = map->m_lblk - es.es_lblk;
+ map->m_len = es.es_len - offset;
- /*
- * Shared inode_lock is enough for us - it protects against concurrent
- * writes & truncates and since we take care of writing back page cache,
- * we are protected against page writeback as well.
- */
- inode_lock_shared(inode);
- ret = filemap_write_and_wait_range(mapping, iocb->ki_pos,
- iocb->ki_pos + count - 1);
- if (ret)
- goto out_unlock;
- ret = __blockdev_direct_IO(iocb, inode, inode->i_sb->s_bdev,
- iter, ext4_dio_get_block, NULL, NULL, 0);
-out_unlock:
- inode_unlock_shared(inode);
- return ret;
+ return true;
}
-static ssize_t ext4_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
+static int ext4_iomap_begin_report(struct inode *inode, loff_t offset,
+ loff_t length, unsigned int flags,
+ struct iomap *iomap, struct iomap *srcmap)
{
- struct file *file = iocb->ki_filp;
- struct inode *inode = file->f_mapping->host;
- size_t count = iov_iter_count(iter);
- loff_t offset = iocb->ki_pos;
- ssize_t ret;
+ int ret;
+ bool delalloc = false;
+ struct ext4_map_blocks map;
+ u8 blkbits = inode->i_blkbits;
-#ifdef CONFIG_FS_ENCRYPTION
- if (IS_ENCRYPTED(inode) && S_ISREG(inode->i_mode))
- return 0;
-#endif
- if (fsverity_active(inode))
- return 0;
+ if ((offset >> blkbits) > EXT4_MAX_LOGICAL_BLOCK)
+ return -EINVAL;
+
+ if (ext4_has_inline_data(inode)) {
+ ret = ext4_inline_data_iomap(inode, iomap);
+ if (ret != -EAGAIN) {
+ if (ret == 0 && offset >= iomap->length)
+ ret = -ENOENT;
+ return ret;
+ }
+ }
/*
- * If we are doing data journalling we don't support O_DIRECT
+ * Calculate the first and last logical block respectively.
*/
- if (ext4_should_journal_data(inode))
- return 0;
+ map.m_lblk = offset >> blkbits;
+ map.m_len = min_t(loff_t, (offset + length - 1) >> blkbits,
+ EXT4_MAX_LOGICAL_BLOCK) - map.m_lblk + 1;
- /* Let buffer I/O handle the inline data case. */
- if (ext4_has_inline_data(inode))
- return 0;
+ ret = ext4_map_blocks(NULL, inode, &map, 0);
+ if (ret < 0)
+ return ret;
+ if (ret == 0)
+ delalloc = ext4_iomap_is_delalloc(inode, &map);
- trace_ext4_direct_IO_enter(inode, offset, count, iov_iter_rw(iter));
- if (iov_iter_rw(iter) == READ)
- ret = ext4_direct_IO_read(iocb, iter);
- else
- ret = ext4_direct_IO_write(iocb, iter);
- trace_ext4_direct_IO_exit(inode, offset, count, iov_iter_rw(iter), ret);
- return ret;
+ ext4_set_iomap(inode, iomap, &map, offset, length);
+ if (delalloc && iomap->type == IOMAP_HOLE)
+ iomap->type = IOMAP_DELALLOC;
+
+ return 0;
}
+const struct iomap_ops ext4_iomap_report_ops = {
+ .iomap_begin = ext4_iomap_begin_report,
+};
+
/*
* Pages can be marked dirty completely asynchronously from ext4's journalling
* activity. By filemap_sync_pte(), try_to_unmap_one(), etc. We cannot do
@@ -3910,7 +3574,7 @@ static const struct address_space_operations ext4_aops = {
.bmap = ext4_bmap,
.invalidatepage = ext4_invalidatepage,
.releasepage = ext4_releasepage,
- .direct_IO = ext4_direct_IO,
+ .direct_IO = noop_direct_IO,
.migratepage = buffer_migrate_page,
.is_partially_uptodate = block_is_partially_uptodate,
.error_remove_page = generic_error_remove_page,
@@ -3927,7 +3591,7 @@ static const struct address_space_operations ext4_journalled_aops = {
.bmap = ext4_bmap,
.invalidatepage = ext4_journalled_invalidatepage,
.releasepage = ext4_releasepage,
- .direct_IO = ext4_direct_IO,
+ .direct_IO = noop_direct_IO,
.is_partially_uptodate = block_is_partially_uptodate,
.error_remove_page = generic_error_remove_page,
};
@@ -3943,7 +3607,7 @@ static const struct address_space_operations ext4_da_aops = {
.bmap = ext4_bmap,
.invalidatepage = ext4_invalidatepage,
.releasepage = ext4_releasepage,
- .direct_IO = ext4_direct_IO,
+ .direct_IO = noop_direct_IO,
.migratepage = buffer_migrate_page,
.is_partially_uptodate = block_is_partially_uptodate,
.error_remove_page = generic_error_remove_page,
@@ -5450,11 +5114,15 @@ static void ext4_wait_for_tail_page_commit(struct inode *inode)
offset = inode->i_size & (PAGE_SIZE - 1);
/*
- * All buffers in the last page remain valid? Then there's nothing to
- * do. We do the check mainly to optimize the common PAGE_SIZE ==
- * blocksize case
+ * If the page is fully truncated, we don't need to wait for any commit
+ * (and we even should not as __ext4_journalled_invalidatepage() may
+ * strip all buffers from the page but keep the page dirty which can then
+ * confuse e.g. concurrent ext4_writepage() seeing dirty page without
+ * buffers). Also we don't need to wait for any commit if all buffers in
+ * the page remain valid. This is most beneficial for the common case of
+ * blocksize == PAGESIZE.
*/
- if (offset > PAGE_SIZE - i_blocksize(inode))
+ if (!offset || offset > (PAGE_SIZE - i_blocksize(inode)))
return;
while (1) {
page = find_lock_page(inode->i_mapping,
@@ -5717,12 +5385,15 @@ int ext4_getattr(const struct path *path, struct kstat *stat,
stat->attributes |= STATX_ATTR_IMMUTABLE;
if (flags & EXT4_NODUMP_FL)
stat->attributes |= STATX_ATTR_NODUMP;
+ if (flags & EXT4_VERITY_FL)
+ stat->attributes |= STATX_ATTR_VERITY;
stat->attributes_mask |= (STATX_ATTR_APPEND |
STATX_ATTR_COMPRESSED |
STATX_ATTR_ENCRYPTED |
STATX_ATTR_IMMUTABLE |
- STATX_ATTR_NODUMP);
+ STATX_ATTR_NODUMP |
+ STATX_ATTR_VERITY);
generic_fillattr(inode, stat);
return 0;
@@ -5912,8 +5583,23 @@ static int __ext4_expand_extra_isize(struct inode *inode,
{
struct ext4_inode *raw_inode;
struct ext4_xattr_ibody_header *header;
+ unsigned int inode_size = EXT4_INODE_SIZE(inode->i_sb);
+ struct ext4_inode_info *ei = EXT4_I(inode);
int error;
+ /* this was checked at iget time, but double check for good measure */
+ if ((EXT4_GOOD_OLD_INODE_SIZE + ei->i_extra_isize > inode_size) ||
+ (ei->i_extra_isize & 3)) {
+ EXT4_ERROR_INODE(inode, "bad extra_isize %u (inode size %u)",
+ ei->i_extra_isize,
+ EXT4_INODE_SIZE(inode->i_sb));
+ return -EFSCORRUPTED;
+ }
+ if ((new_extra_isize < ei->i_extra_isize) ||
+ (new_extra_isize < 4) ||
+ (new_extra_isize > inode_size - EXT4_GOOD_OLD_INODE_SIZE))
+ return -EINVAL; /* Should never happen */
+
raw_inode = ext4_raw_inode(iloc);
header = IHDR(inode, raw_inode);
@@ -5965,9 +5651,8 @@ static int ext4_try_to_expand_extra_isize(struct inode *inode,
* If this is felt to be critical, then e2fsck should be run to
* force a large enough s_min_extra_isize.
*/
- if (ext4_handle_valid(handle) &&
- jbd2_journal_extend(handle,
- EXT4_DATA_TRANS_BLOCKS(inode->i_sb)) != 0)
+ if (ext4_journal_extend(handle,
+ EXT4_DATA_TRANS_BLOCKS(inode->i_sb), 0) != 0)
return -ENOSPC;
if (ext4_write_trylock_xattr(inode, &no_expand) == 0)
diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c
index 0b7f316fd30f..e8870fff8224 100644
--- a/fs/ext4/ioctl.c
+++ b/fs/ext4/ioctl.c
@@ -1360,6 +1360,7 @@ long ext4_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
}
case EXT4_IOC_MOVE_EXT:
case EXT4_IOC_RESIZE_FS:
+ case FITRIM:
case EXT4_IOC_PRECACHE_EXTENTS:
case EXT4_IOC_SET_ENCRYPTION_POLICY:
case EXT4_IOC_GET_ENCRYPTION_PWSALT:
diff --git a/fs/ext4/migrate.c b/fs/ext4/migrate.c
index b1e4d359f73b..89725fa42573 100644
--- a/fs/ext4/migrate.c
+++ b/fs/ext4/migrate.c
@@ -50,29 +50,9 @@ static int finish_range(handle_t *handle, struct inode *inode,
needed = ext4_ext_calc_credits_for_single_extent(inode,
lb->last_block - lb->first_block + 1, path);
- /*
- * Make sure the credit we accumalated is not really high
- */
- if (needed && ext4_handle_has_enough_credits(handle,
- EXT4_RESERVE_TRANS_BLOCKS)) {
- up_write((&EXT4_I(inode)->i_data_sem));
- retval = ext4_journal_restart(handle, needed);
- down_write((&EXT4_I(inode)->i_data_sem));
- if (retval)
- goto err_out;
- } else if (needed) {
- retval = ext4_journal_extend(handle, needed);
- if (retval) {
- /*
- * IF not able to extend the journal restart the journal
- */
- up_write((&EXT4_I(inode)->i_data_sem));
- retval = ext4_journal_restart(handle, needed);
- down_write((&EXT4_I(inode)->i_data_sem));
- if (retval)
- goto err_out;
- }
- }
+ retval = ext4_datasem_ensure_credits(handle, inode, needed, needed, 0);
+ if (retval < 0)
+ goto err_out;
retval = ext4_ext_insert_extent(handle, inode, &path, &newext, 0);
err_out:
up_write((&EXT4_I(inode)->i_data_sem));
@@ -196,42 +176,30 @@ static int update_tind_extent_range(handle_t *handle, struct inode *inode,
}
-static int extend_credit_for_blkdel(handle_t *handle, struct inode *inode)
-{
- int retval = 0, needed;
-
- if (ext4_handle_has_enough_credits(handle, EXT4_RESERVE_TRANS_BLOCKS+1))
- return 0;
- /*
- * We are freeing a blocks. During this we touch
- * superblock, group descriptor and block bitmap.
- * So allocate a credit of 3. We may update
- * quota (user and group).
- */
- needed = 3 + EXT4_MAXQUOTAS_TRANS_BLOCKS(inode->i_sb);
-
- if (ext4_journal_extend(handle, needed) != 0)
- retval = ext4_journal_restart(handle, needed);
-
- return retval;
-}
-
static int free_dind_blocks(handle_t *handle,
struct inode *inode, __le32 i_data)
{
int i;
__le32 *tmp_idata;
struct buffer_head *bh;
+ struct super_block *sb = inode->i_sb;
unsigned long max_entries = inode->i_sb->s_blocksize >> 2;
+ int err;
- bh = ext4_sb_bread(inode->i_sb, le32_to_cpu(i_data), 0);
+ bh = ext4_sb_bread(sb, le32_to_cpu(i_data), 0);
if (IS_ERR(bh))
return PTR_ERR(bh);
tmp_idata = (__le32 *)bh->b_data;
for (i = 0; i < max_entries; i++) {
if (tmp_idata[i]) {
- extend_credit_for_blkdel(handle, inode);
+ err = ext4_journal_ensure_credits(handle,
+ EXT4_RESERVE_TRANS_BLOCKS,
+ ext4_free_metadata_revoke_credits(sb, 1));
+ if (err < 0) {
+ put_bh(bh);
+ return err;
+ }
ext4_free_blocks(handle, inode, NULL,
le32_to_cpu(tmp_idata[i]), 1,
EXT4_FREE_BLOCKS_METADATA |
@@ -239,7 +207,10 @@ static int free_dind_blocks(handle_t *handle,
}
}
put_bh(bh);
- extend_credit_for_blkdel(handle, inode);
+ err = ext4_journal_ensure_credits(handle, EXT4_RESERVE_TRANS_BLOCKS,
+ ext4_free_metadata_revoke_credits(sb, 1));
+ if (err < 0)
+ return err;
ext4_free_blocks(handle, inode, NULL, le32_to_cpu(i_data), 1,
EXT4_FREE_BLOCKS_METADATA |
EXT4_FREE_BLOCKS_FORGET);
@@ -270,7 +241,10 @@ static int free_tind_blocks(handle_t *handle,
}
}
put_bh(bh);
- extend_credit_for_blkdel(handle, inode);
+ retval = ext4_journal_ensure_credits(handle, EXT4_RESERVE_TRANS_BLOCKS,
+ ext4_free_metadata_revoke_credits(inode->i_sb, 1));
+ if (retval < 0)
+ return retval;
ext4_free_blocks(handle, inode, NULL, le32_to_cpu(i_data), 1,
EXT4_FREE_BLOCKS_METADATA |
EXT4_FREE_BLOCKS_FORGET);
@@ -283,7 +257,11 @@ static int free_ind_block(handle_t *handle, struct inode *inode, __le32 *i_data)
/* ei->i_data[EXT4_IND_BLOCK] */
if (i_data[0]) {
- extend_credit_for_blkdel(handle, inode);
+ retval = ext4_journal_ensure_credits(handle,
+ EXT4_RESERVE_TRANS_BLOCKS,
+ ext4_free_metadata_revoke_credits(inode->i_sb, 1));
+ if (retval < 0)
+ return retval;
ext4_free_blocks(handle, inode, NULL,
le32_to_cpu(i_data[0]), 1,
EXT4_FREE_BLOCKS_METADATA |
@@ -318,12 +296,9 @@ static int ext4_ext_swap_inode_data(handle_t *handle, struct inode *inode,
* One credit accounted for writing the
* i_data field of the original inode
*/
- retval = ext4_journal_extend(handle, 1);
- if (retval) {
- retval = ext4_journal_restart(handle, 1);
- if (retval)
- goto err_out;
- }
+ retval = ext4_journal_ensure_credits(handle, 1, 0);
+ if (retval < 0)
+ goto err_out;
i_data[0] = ei->i_data[EXT4_IND_BLOCK];
i_data[1] = ei->i_data[EXT4_DIND_BLOCK];
@@ -391,15 +366,20 @@ static int free_ext_idx(handle_t *handle, struct inode *inode,
ix = EXT_FIRST_INDEX(eh);
for (i = 0; i < le16_to_cpu(eh->eh_entries); i++, ix++) {
retval = free_ext_idx(handle, inode, ix);
- if (retval)
- break;
+ if (retval) {
+ put_bh(bh);
+ return retval;
+ }
}
}
put_bh(bh);
- extend_credit_for_blkdel(handle, inode);
+ retval = ext4_journal_ensure_credits(handle, EXT4_RESERVE_TRANS_BLOCKS,
+ ext4_free_metadata_revoke_credits(inode->i_sb, 1));
+ if (retval < 0)
+ return retval;
ext4_free_blocks(handle, inode, NULL, block, 1,
EXT4_FREE_BLOCKS_METADATA | EXT4_FREE_BLOCKS_FORGET);
- return retval;
+ return 0;
}
/*
@@ -574,9 +554,9 @@ err_out:
}
/* We mark the tmp_inode dirty via ext4_ext_tree_init. */
- if (ext4_journal_extend(handle, 1) != 0)
- ext4_journal_restart(handle, 1);
-
+ retval = ext4_journal_ensure_credits(handle, 1, 0);
+ if (retval < 0)
+ goto out_stop;
/*
* Mark the tmp_inode as of size zero
*/
@@ -594,6 +574,7 @@ err_out:
/* Reset the extent details */
ext4_ext_tree_init(handle, tmp_inode);
+out_stop:
ext4_journal_stop(handle);
out:
unlock_new_inode(tmp_inode);
diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c
index a427d2031a8d..a856997d87b5 100644
--- a/fs/ext4/namei.c
+++ b/fs/ext4/namei.c
@@ -2547,18 +2547,29 @@ static void ext4_dec_count(handle_t *handle, struct inode *inode)
}
+/*
+ * Add non-directory inode to a directory. On success, the inode reference is
+ * consumed by dentry is instantiation. This is also indicated by clearing of
+ * *inodep pointer. On failure, the caller is responsible for dropping the
+ * inode reference in the safe context.
+ */
static int ext4_add_nondir(handle_t *handle,
- struct dentry *dentry, struct inode *inode)
+ struct dentry *dentry, struct inode **inodep)
{
+ struct inode *dir = d_inode(dentry->d_parent);
+ struct inode *inode = *inodep;
int err = ext4_add_entry(handle, dentry, inode);
if (!err) {
ext4_mark_inode_dirty(handle, inode);
+ if (IS_DIRSYNC(dir))
+ ext4_handle_sync(handle);
d_instantiate_new(dentry, inode);
+ *inodep = NULL;
return 0;
}
drop_nlink(inode);
+ ext4_orphan_add(handle, inode);
unlock_new_inode(inode);
- iput(inode);
return err;
}
@@ -2592,12 +2603,12 @@ retry:
inode->i_op = &ext4_file_inode_operations;
inode->i_fop = &ext4_file_operations;
ext4_set_aops(inode);
- err = ext4_add_nondir(handle, dentry, inode);
- if (!err && IS_DIRSYNC(dir))
- ext4_handle_sync(handle);
+ err = ext4_add_nondir(handle, dentry, &inode);
}
if (handle)
ext4_journal_stop(handle);
+ if (!IS_ERR_OR_NULL(inode))
+ iput(inode);
if (err == -ENOSPC && ext4_should_retry_alloc(dir->i_sb, &retries))
goto retry;
return err;
@@ -2624,12 +2635,12 @@ retry:
if (!IS_ERR(inode)) {
init_special_inode(inode, inode->i_mode, rdev);
inode->i_op = &ext4_special_inode_operations;
- err = ext4_add_nondir(handle, dentry, inode);
- if (!err && IS_DIRSYNC(dir))
- ext4_handle_sync(handle);
+ err = ext4_add_nondir(handle, dentry, &inode);
}
if (handle)
ext4_journal_stop(handle);
+ if (!IS_ERR_OR_NULL(inode))
+ iput(inode);
if (err == -ENOSPC && ext4_should_retry_alloc(dir->i_sb, &retries))
goto retry;
return err;
@@ -2779,10 +2790,12 @@ retry:
if (err) {
out_clear_inode:
clear_nlink(inode);
+ ext4_orphan_add(handle, inode);
unlock_new_inode(inode);
ext4_mark_inode_dirty(handle, inode);
+ ext4_journal_stop(handle);
iput(inode);
- goto out_stop;
+ goto out_retry;
}
ext4_inc_count(handle, dir);
ext4_update_dx_flag(dir);
@@ -2796,6 +2809,7 @@ out_clear_inode:
out_stop:
if (handle)
ext4_journal_stop(handle);
+out_retry:
if (err == -ENOSPC && ext4_should_retry_alloc(dir->i_sb, &retries))
goto retry;
return err;
@@ -3182,18 +3196,17 @@ static int ext4_unlink(struct inode *dir, struct dentry *dentry)
if (IS_DIRSYNC(dir))
ext4_handle_sync(handle);
- if (inode->i_nlink == 0) {
- ext4_warning_inode(inode, "Deleting file '%.*s' with no links",
- dentry->d_name.len, dentry->d_name.name);
- set_nlink(inode, 1);
- }
retval = ext4_delete_entry(handle, dir, de, bh);
if (retval)
goto end_unlink;
dir->i_ctime = dir->i_mtime = current_time(dir);
ext4_update_dx_flag(dir);
ext4_mark_inode_dirty(handle, dir);
- drop_nlink(inode);
+ if (inode->i_nlink == 0)
+ ext4_warning_inode(inode, "Deleting file '%.*s' with no links",
+ dentry->d_name.len, dentry->d_name.name);
+ else
+ drop_nlink(inode);
if (!inode->i_nlink)
ext4_orphan_add(handle, inode);
inode->i_ctime = current_time(inode);
@@ -3328,12 +3341,11 @@ static int ext4_symlink(struct inode *dir,
inode->i_size = disk_link.len - 1;
}
EXT4_I(inode)->i_disksize = inode->i_size;
- err = ext4_add_nondir(handle, dentry, inode);
- if (!err && IS_DIRSYNC(dir))
- ext4_handle_sync(handle);
-
+ err = ext4_add_nondir(handle, dentry, &inode);
if (handle)
ext4_journal_stop(handle);
+ if (inode)
+ iput(inode);
goto out_free_encrypted_link;
err_drop_inode:
diff --git a/fs/ext4/page-io.c b/fs/ext4/page-io.c
index 12ceadef32c5..24aeedb8fc75 100644
--- a/fs/ext4/page-io.c
+++ b/fs/ext4/page-io.c
@@ -31,18 +31,56 @@
#include "acl.h"
static struct kmem_cache *io_end_cachep;
+static struct kmem_cache *io_end_vec_cachep;
int __init ext4_init_pageio(void)
{
io_end_cachep = KMEM_CACHE(ext4_io_end, SLAB_RECLAIM_ACCOUNT);
if (io_end_cachep == NULL)
return -ENOMEM;
+
+ io_end_vec_cachep = KMEM_CACHE(ext4_io_end_vec, 0);
+ if (io_end_vec_cachep == NULL) {
+ kmem_cache_destroy(io_end_cachep);
+ return -ENOMEM;
+ }
return 0;
}
void ext4_exit_pageio(void)
{
kmem_cache_destroy(io_end_cachep);
+ kmem_cache_destroy(io_end_vec_cachep);
+}
+
+struct ext4_io_end_vec *ext4_alloc_io_end_vec(ext4_io_end_t *io_end)
+{
+ struct ext4_io_end_vec *io_end_vec;
+
+ io_end_vec = kmem_cache_zalloc(io_end_vec_cachep, GFP_NOFS);
+ if (!io_end_vec)
+ return ERR_PTR(-ENOMEM);
+ INIT_LIST_HEAD(&io_end_vec->list);
+ list_add_tail(&io_end_vec->list, &io_end->list_vec);
+ return io_end_vec;
+}
+
+static void ext4_free_io_end_vec(ext4_io_end_t *io_end)
+{
+ struct ext4_io_end_vec *io_end_vec, *tmp;
+
+ if (list_empty(&io_end->list_vec))
+ return;
+ list_for_each_entry_safe(io_end_vec, tmp, &io_end->list_vec, list) {
+ list_del(&io_end_vec->list);
+ kmem_cache_free(io_end_vec_cachep, io_end_vec);
+ }
+}
+
+struct ext4_io_end_vec *ext4_last_io_end_vec(ext4_io_end_t *io_end)
+{
+ BUG_ON(list_empty(&io_end->list_vec));
+ return list_last_entry(&io_end->list_vec, struct ext4_io_end_vec, list);
}
/*
@@ -125,6 +163,7 @@ static void ext4_release_io_end(ext4_io_end_t *io_end)
ext4_finish_bio(bio);
bio_put(bio);
}
+ ext4_free_io_end_vec(io_end);
kmem_cache_free(io_end_cachep, io_end);
}
@@ -136,29 +175,26 @@ static void ext4_release_io_end(ext4_io_end_t *io_end)
* cannot get to ext4_ext_truncate() before all IOs overlapping that range are
* completed (happens from ext4_free_ioend()).
*/
-static int ext4_end_io(ext4_io_end_t *io)
+static int ext4_end_io_end(ext4_io_end_t *io_end)
{
- struct inode *inode = io->inode;
- loff_t offset = io->offset;
- ssize_t size = io->size;
- handle_t *handle = io->handle;
+ struct inode *inode = io_end->inode;
+ handle_t *handle = io_end->handle;
int ret = 0;
- ext4_debug("ext4_end_io_nolock: io 0x%p from inode %lu,list->next 0x%p,"
+ ext4_debug("ext4_end_io_nolock: io_end 0x%p from inode %lu,list->next 0x%p,"
"list->prev 0x%p\n",
- io, inode->i_ino, io->list.next, io->list.prev);
+ io_end, inode->i_ino, io_end->list.next, io_end->list.prev);
- io->handle = NULL; /* Following call will use up the handle */
- ret = ext4_convert_unwritten_extents(handle, inode, offset, size);
+ io_end->handle = NULL; /* Following call will use up the handle */
+ ret = ext4_convert_unwritten_io_end_vec(handle, io_end);
if (ret < 0 && !ext4_forced_shutdown(EXT4_SB(inode->i_sb))) {
ext4_msg(inode->i_sb, KERN_EMERG,
"failed to convert unwritten extents to written "
"extents -- potential data loss! "
- "(inode %lu, offset %llu, size %zd, error %d)",
- inode->i_ino, offset, size, ret);
+ "(inode %lu, error %d)", inode->i_ino, ret);
}
- ext4_clear_io_unwritten_flag(io);
- ext4_release_io_end(io);
+ ext4_clear_io_unwritten_flag(io_end);
+ ext4_release_io_end(io_end);
return ret;
}
@@ -166,21 +202,21 @@ static void dump_completed_IO(struct inode *inode, struct list_head *head)
{
#ifdef EXT4FS_DEBUG
struct list_head *cur, *before, *after;
- ext4_io_end_t *io, *io0, *io1;
+ ext4_io_end_t *io_end, *io_end0, *io_end1;
if (list_empty(head))
return;
ext4_debug("Dump inode %lu completed io list\n", inode->i_ino);
- list_for_each_entry(io, head, list) {
- cur = &io->list;
+ list_for_each_entry(io_end, head, list) {
+ cur = &io_end->list;
before = cur->prev;
- io0 = container_of(before, ext4_io_end_t, list);
+ io_end0 = container_of(before, ext4_io_end_t, list);
after = cur->next;
- io1 = container_of(after, ext4_io_end_t, list);
+ io_end1 = container_of(after, ext4_io_end_t, list);
ext4_debug("io 0x%p from inode %lu,prev 0x%p,next 0x%p\n",
- io, inode->i_ino, io0, io1);
+ io_end, inode->i_ino, io_end0, io_end1);
}
#endif
}
@@ -207,7 +243,7 @@ static void ext4_add_complete_io(ext4_io_end_t *io_end)
static int ext4_do_flush_completed_IO(struct inode *inode,
struct list_head *head)
{
- ext4_io_end_t *io;
+ ext4_io_end_t *io_end;
struct list_head unwritten;
unsigned long flags;
struct ext4_inode_info *ei = EXT4_I(inode);
@@ -219,11 +255,11 @@ static int ext4_do_flush_completed_IO(struct inode *inode,
spin_unlock_irqrestore(&ei->i_completed_io_lock, flags);
while (!list_empty(&unwritten)) {
- io = list_entry(unwritten.next, ext4_io_end_t, list);
- BUG_ON(!(io->flag & EXT4_IO_END_UNWRITTEN));
- list_del_init(&io->list);
+ io_end = list_entry(unwritten.next, ext4_io_end_t, list);
+ BUG_ON(!(io_end->flag & EXT4_IO_END_UNWRITTEN));
+ list_del_init(&io_end->list);
- err = ext4_end_io(io);
+ err = ext4_end_io_end(io_end);
if (unlikely(!ret && err))
ret = err;
}
@@ -242,19 +278,22 @@ void ext4_end_io_rsv_work(struct work_struct *work)
ext4_io_end_t *ext4_init_io_end(struct inode *inode, gfp_t flags)
{
- ext4_io_end_t *io = kmem_cache_zalloc(io_end_cachep, flags);
- if (io) {
- io->inode = inode;
- INIT_LIST_HEAD(&io->list);
- atomic_set(&io->count, 1);
+ ext4_io_end_t *io_end = kmem_cache_zalloc(io_end_cachep, flags);
+
+ if (io_end) {
+ io_end->inode = inode;
+ INIT_LIST_HEAD(&io_end->list);
+ INIT_LIST_HEAD(&io_end->list_vec);
+ atomic_set(&io_end->count, 1);
}
- return io;
+ return io_end;
}
void ext4_put_io_end_defer(ext4_io_end_t *io_end)
{
if (atomic_dec_and_test(&io_end->count)) {
- if (!(io_end->flag & EXT4_IO_END_UNWRITTEN) || !io_end->size) {
+ if (!(io_end->flag & EXT4_IO_END_UNWRITTEN) ||
+ list_empty(&io_end->list_vec)) {
ext4_release_io_end(io_end);
return;
}
@@ -268,9 +307,8 @@ int ext4_put_io_end(ext4_io_end_t *io_end)
if (atomic_dec_and_test(&io_end->count)) {
if (io_end->flag & EXT4_IO_END_UNWRITTEN) {
- err = ext4_convert_unwritten_extents(io_end->handle,
- io_end->inode, io_end->offset,
- io_end->size);
+ err = ext4_convert_unwritten_io_end_vec(io_end->handle,
+ io_end);
io_end->handle = NULL;
ext4_clear_io_unwritten_flag(io_end);
}
@@ -307,10 +345,8 @@ static void ext4_end_bio(struct bio *bio)
struct inode *inode = io_end->inode;
ext4_warning(inode->i_sb, "I/O error %d writing to inode %lu "
- "(offset %llu size %ld starting block %llu)",
+ "starting block %llu)",
bio->bi_status, inode->i_ino,
- (unsigned long long) io_end->offset,
- (long) io_end->size,
(unsigned long long)
bi_sector >> (inode->i_blkbits - 9));
mapping_set_error(inode->i_mapping,
@@ -358,14 +394,16 @@ void ext4_io_submit_init(struct ext4_io_submit *io,
io->io_end = NULL;
}
-static int io_submit_init_bio(struct ext4_io_submit *io,
- struct buffer_head *bh)
+static void io_submit_init_bio(struct ext4_io_submit *io,
+ struct buffer_head *bh)
{
struct bio *bio;
+ /*
+ * bio_alloc will _always_ be able to allocate a bio if
+ * __GFP_DIRECT_RECLAIM is set, see comments for bio_alloc_bioset().
+ */
bio = bio_alloc(GFP_NOIO, BIO_MAX_PAGES);
- if (!bio)
- return -ENOMEM;
bio->bi_iter.bi_sector = bh->b_blocknr * (bh->b_size >> 9);
bio_set_dev(bio, bh->b_bdev);
bio->bi_end_io = ext4_end_bio;
@@ -373,13 +411,12 @@ static int io_submit_init_bio(struct ext4_io_submit *io,
io->io_bio = bio;
io->io_next_block = bh->b_blocknr;
wbc_init_bio(io->io_wbc, bio);
- return 0;
}
-static int io_submit_add_bh(struct ext4_io_submit *io,
- struct inode *inode,
- struct page *page,
- struct buffer_head *bh)
+static void io_submit_add_bh(struct ext4_io_submit *io,
+ struct inode *inode,
+ struct page *page,
+ struct buffer_head *bh)
{
int ret;
@@ -388,9 +425,7 @@ submit_and_retry:
ext4_io_submit(io);
}
if (io->io_bio == NULL) {
- ret = io_submit_init_bio(io, bh);
- if (ret)
- return ret;
+ io_submit_init_bio(io, bh);
io->io_bio->bi_write_hint = inode->i_write_hint;
}
ret = bio_add_page(io->io_bio, page, bh->b_size, bh_offset(bh));
@@ -398,7 +433,6 @@ submit_and_retry:
goto submit_and_retry;
wbc_account_cgroup_owner(io->io_wbc, page, bh->b_size);
io->io_next_block++;
- return 0;
}
int ext4_bio_write_page(struct ext4_io_submit *io,
@@ -491,8 +525,14 @@ int ext4_bio_write_page(struct ext4_io_submit *io,
gfp_flags |= __GFP_NOFAIL;
goto retry_encrypt;
}
- bounce_page = NULL;
- goto out;
+
+ printk_ratelimited(KERN_ERR "%s: ret = %d\n", __func__, ret);
+ redirty_page_for_writepage(wbc, page);
+ do {
+ clear_buffer_async_write(bh);
+ bh = bh->b_this_page;
+ } while (bh != head);
+ goto unlock;
}
}
@@ -500,30 +540,13 @@ int ext4_bio_write_page(struct ext4_io_submit *io,
do {
if (!buffer_async_write(bh))
continue;
- ret = io_submit_add_bh(io, inode, bounce_page ?: page, bh);
- if (ret) {
- /*
- * We only get here on ENOMEM. Not much else
- * we can do but mark the page as dirty, and
- * better luck next time.
- */
- break;
- }
+ io_submit_add_bh(io, inode,
+ bounce_page ? bounce_page : page, bh);
nr_submitted++;
clear_buffer_dirty(bh);
} while ((bh = bh->b_this_page) != head);
- /* Error stopped previous loop? Clean up buffers... */
- if (ret) {
- out:
- fscrypt_free_bounce_page(bounce_page);
- printk_ratelimited(KERN_ERR "%s: ret = %d\n", __func__, ret);
- redirty_page_for_writepage(wbc, page);
- do {
- clear_buffer_async_write(bh);
- bh = bh->b_this_page;
- } while (bh != head);
- }
+unlock:
unlock_page(page);
/* Nothing submitted - we have to end page writeback */
if (!nr_submitted)
diff --git a/fs/ext4/readpage.c b/fs/ext4/readpage.c
index a30b203fa461..fef7755300c3 100644
--- a/fs/ext4/readpage.c
+++ b/fs/ext4/readpage.c
@@ -360,10 +360,12 @@ int ext4_mpage_readpages(struct address_space *mapping,
if (bio == NULL) {
struct bio_post_read_ctx *ctx;
+ /*
+ * bio_alloc will _always_ be able to allocate a bio if
+ * __GFP_DIRECT_RECLAIM is set, see bio_alloc_bioset().
+ */
bio = bio_alloc(GFP_KERNEL,
min_t(int, nr_pages, BIO_MAX_PAGES));
- if (!bio)
- goto set_error_page;
ctx = get_bio_post_read_ctx(inode, bio, page->index);
if (IS_ERR(ctx)) {
bio_put(bio);
diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c
index c0e9aef376a7..a8c0f2b5b6e1 100644
--- a/fs/ext4/resize.c
+++ b/fs/ext4/resize.c
@@ -388,28 +388,10 @@ static struct buffer_head *bclean(handle_t *handle, struct super_block *sb,
return bh;
}
-/*
- * If we have fewer than thresh credits, extend by EXT4_MAX_TRANS_DATA.
- * If that fails, restart the transaction & regain write access for the
- * buffer head which is used for block_bitmap modifications.
- */
-static int extend_or_restart_transaction(handle_t *handle, int thresh)
+static int ext4_resize_ensure_credits_batch(handle_t *handle, int credits)
{
- int err;
-
- if (ext4_handle_has_enough_credits(handle, thresh))
- return 0;
-
- err = ext4_journal_extend(handle, EXT4_MAX_TRANS_DATA);
- if (err < 0)
- return err;
- if (err) {
- err = ext4_journal_restart(handle, EXT4_MAX_TRANS_DATA);
- if (err)
- return err;
- }
-
- return 0;
+ return ext4_journal_ensure_credits_fn(handle, credits,
+ EXT4_MAX_TRANS_DATA, 0, 0);
}
/*
@@ -451,8 +433,8 @@ static int set_flexbg_block_bitmap(struct super_block *sb, handle_t *handle,
continue;
}
- err = extend_or_restart_transaction(handle, 1);
- if (err)
+ err = ext4_resize_ensure_credits_batch(handle, 1);
+ if (err < 0)
return err;
bh = sb_getblk(sb, flex_gd->groups[group].block_bitmap);
@@ -544,8 +526,8 @@ static int setup_new_flex_group_blocks(struct super_block *sb,
struct buffer_head *gdb;
ext4_debug("update backup group %#04llx\n", block);
- err = extend_or_restart_transaction(handle, 1);
- if (err)
+ err = ext4_resize_ensure_credits_batch(handle, 1);
+ if (err < 0)
goto out;
gdb = sb_getblk(sb, block);
@@ -602,8 +584,8 @@ handle_bb:
/* Initialize block bitmap of the @group */
block = group_data[i].block_bitmap;
- err = extend_or_restart_transaction(handle, 1);
- if (err)
+ err = ext4_resize_ensure_credits_batch(handle, 1);
+ if (err < 0)
goto out;
bh = bclean(handle, sb, block);
@@ -631,8 +613,8 @@ handle_ib:
/* Initialize inode bitmap of the @group */
block = group_data[i].inode_bitmap;
- err = extend_or_restart_transaction(handle, 1);
- if (err)
+ err = ext4_resize_ensure_credits_batch(handle, 1);
+ if (err < 0)
goto out;
/* Mark unused entries in inode bitmap used */
bh = bclean(handle, sb, block);
@@ -1109,10 +1091,8 @@ static void update_backups(struct super_block *sb, sector_t blk_off, char *data,
ext4_fsblk_t backup_block;
/* Out of journal space, and can't get more - abort - so sad */
- if (ext4_handle_valid(handle) &&
- handle->h_buffer_credits == 0 &&
- ext4_journal_extend(handle, EXT4_MAX_TRANS_DATA) &&
- (err = ext4_journal_restart(handle, EXT4_MAX_TRANS_DATA)))
+ err = ext4_resize_ensure_credits_batch(handle, 1);
+ if (err < 0)
break;
if (meta_bg == 0)
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index dd654e53ba3d..1d82b56d9b11 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -1172,9 +1172,9 @@ void ext4_clear_inode(struct inode *inode)
{
invalidate_inode_buffers(inode);
clear_inode(inode);
- dquot_drop(inode);
ext4_discard_preallocations(inode);
ext4_es_remove_extent(inode, 0, EXT_MAX_BLOCKS);
+ dquot_drop(inode);
if (EXT4_I(inode)->jinode) {
jbd2_journal_release_jbd_inode(EXT4_JOURNAL(inode),
EXT4_I(inode)->jinode);
@@ -1345,6 +1345,18 @@ static bool ext4_dummy_context(struct inode *inode)
return DUMMY_ENCRYPTION_ENABLED(EXT4_SB(inode->i_sb));
}
+static bool ext4_has_stable_inodes(struct super_block *sb)
+{
+ return ext4_has_feature_stable_inodes(sb);
+}
+
+static void ext4_get_ino_and_lblk_bits(struct super_block *sb,
+ int *ino_bits_ret, int *lblk_bits_ret)
+{
+ *ino_bits_ret = 8 * sizeof(EXT4_SB(sb)->s_es->s_inodes_count);
+ *lblk_bits_ret = 8 * sizeof(ext4_lblk_t);
+}
+
static const struct fscrypt_operations ext4_cryptops = {
.key_prefix = "ext4:",
.get_context = ext4_get_context,
@@ -1352,6 +1364,8 @@ static const struct fscrypt_operations ext4_cryptops = {
.dummy_context = ext4_dummy_context,
.empty_dir = ext4_empty_dir,
.max_namelen = EXT4_NAME_LEN,
+ .has_stable_inodes = ext4_has_stable_inodes,
+ .get_ino_and_lblk_bits = ext4_get_ino_and_lblk_bits,
};
#endif
@@ -1374,7 +1388,6 @@ static ssize_t ext4_quota_write(struct super_block *sb, int type,
static int ext4_quota_enable(struct super_block *sb, int type, int format_id,
unsigned int flags);
static int ext4_enable_quotas(struct super_block *sb);
-static int ext4_get_next_id(struct super_block *sb, struct kqid *qid);
static struct dquot **ext4_get_dquots(struct inode *inode)
{
@@ -1392,7 +1405,7 @@ static const struct dquot_operations ext4_quota_operations = {
.destroy_dquot = dquot_destroy,
.get_projid = ext4_get_projid,
.get_inode_usage = ext4_get_inode_usage,
- .get_next_id = ext4_get_next_id,
+ .get_next_id = dquot_get_next_id,
};
static const struct quotactl_ops ext4_qctl_operations = {
@@ -2051,7 +2064,7 @@ static int parse_options(char *options, struct super_block *sb,
unsigned int *journal_ioprio,
int is_remount)
{
- struct ext4_sb_info *sbi = EXT4_SB(sb);
+ struct ext4_sb_info __maybe_unused *sbi = EXT4_SB(sb);
char *p, __maybe_unused *usr_qf_name, __maybe_unused *grp_qf_name;
substring_t args[MAX_OPT_ARGS];
int token;
@@ -2105,16 +2118,6 @@ static int parse_options(char *options, struct super_block *sb,
}
}
#endif
- if (test_opt(sb, DIOREAD_NOLOCK)) {
- int blocksize =
- BLOCK_SIZE << le32_to_cpu(sbi->s_es->s_log_block_size);
-
- if (blocksize < PAGE_SIZE) {
- ext4_msg(sb, KERN_ERR, "can't mount with "
- "dioread_nolock if block size != PAGE_SIZE");
- return 0;
- }
- }
return 1;
}
@@ -3555,12 +3558,15 @@ static void ext4_clamp_want_extra_isize(struct super_block *sb)
{
struct ext4_sb_info *sbi = EXT4_SB(sb);
struct ext4_super_block *es = sbi->s_es;
+ unsigned def_extra_isize = sizeof(struct ext4_inode) -
+ EXT4_GOOD_OLD_INODE_SIZE;
- /* determine the minimum size of new large inodes, if present */
- if (sbi->s_inode_size > EXT4_GOOD_OLD_INODE_SIZE &&
- sbi->s_want_extra_isize == 0) {
- sbi->s_want_extra_isize = sizeof(struct ext4_inode) -
- EXT4_GOOD_OLD_INODE_SIZE;
+ if (sbi->s_inode_size == EXT4_GOOD_OLD_INODE_SIZE) {
+ sbi->s_want_extra_isize = 0;
+ return;
+ }
+ if (sbi->s_want_extra_isize < 4) {
+ sbi->s_want_extra_isize = def_extra_isize;
if (ext4_has_feature_extra_isize(sb)) {
if (sbi->s_want_extra_isize <
le16_to_cpu(es->s_want_extra_isize))
@@ -3573,10 +3579,10 @@ static void ext4_clamp_want_extra_isize(struct super_block *sb)
}
}
/* Check if enough inode space is available */
- if (EXT4_GOOD_OLD_INODE_SIZE + sbi->s_want_extra_isize >
- sbi->s_inode_size) {
- sbi->s_want_extra_isize = sizeof(struct ext4_inode) -
- EXT4_GOOD_OLD_INODE_SIZE;
+ if ((sbi->s_want_extra_isize > sbi->s_inode_size) ||
+ (EXT4_GOOD_OLD_INODE_SIZE + sbi->s_want_extra_isize >
+ sbi->s_inode_size)) {
+ sbi->s_want_extra_isize = def_extra_isize;
ext4_msg(sb, KERN_INFO,
"required extra inode space not available");
}
@@ -4439,13 +4445,6 @@ no_journal:
}
}
- if ((DUMMY_ENCRYPTION_ENABLED(sbi) || ext4_has_feature_encrypt(sb)) &&
- (blocksize != PAGE_SIZE)) {
- ext4_msg(sb, KERN_ERR,
- "Unsupported blocksize for fs encryption");
- goto failed_mount_wq;
- }
-
if (ext4_has_feature_verity(sb) && blocksize != PAGE_SIZE) {
ext4_msg(sb, KERN_ERR, "Unsupported blocksize for fs-verity");
goto failed_mount_wq;
@@ -5835,7 +5834,7 @@ static int ext4_quota_enable(struct super_block *sb, int type, int format_id,
/* Don't account quota for quota files to avoid recursion */
qf_inode->i_flags |= S_NOQUOTA;
lockdep_set_quota_inode(qf_inode, I_DATA_SEM_QUOTA);
- err = dquot_enable(qf_inode, type, format_id, flags);
+ err = dquot_load_quota_inode(qf_inode, type, format_id, flags);
if (err)
lockdep_set_quota_inode(qf_inode, I_DATA_SEM_NORMAL);
iput(qf_inode);
@@ -6019,18 +6018,6 @@ out:
}
return len;
}
-
-static int ext4_get_next_id(struct super_block *sb, struct kqid *qid)
-{
- const struct quota_format_ops *ops;
-
- if (!sb_has_quota_loaded(sb, qid->type))
- return -ESRCH;
- ops = sb_dqopt(sb)->ops[qid->type];
- if (!ops || !ops->get_next_id)
- return -ENOSYS;
- return dquot_get_next_id(sb, qid);
-}
#endif
static struct dentry *ext4_mount(struct file_system_type *fs_type, int flags,
diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c
index 491f9ee4040e..8966a5439a22 100644
--- a/fs/ext4/xattr.c
+++ b/fs/ext4/xattr.c
@@ -967,55 +967,6 @@ int __ext4_xattr_set_credits(struct super_block *sb, struct inode *inode,
return credits;
}
-static int ext4_xattr_ensure_credits(handle_t *handle, struct inode *inode,
- int credits, struct buffer_head *bh,
- bool dirty, bool block_csum)
-{
- int error;
-
- if (!ext4_handle_valid(handle))
- return 0;
-
- if (handle->h_buffer_credits >= credits)
- return 0;
-
- error = ext4_journal_extend(handle, credits - handle->h_buffer_credits);
- if (!error)
- return 0;
- if (error < 0) {
- ext4_warning(inode->i_sb, "Extend journal (error %d)", error);
- return error;
- }
-
- if (bh && dirty) {
- if (block_csum)
- ext4_xattr_block_csum_set(inode, bh);
- error = ext4_handle_dirty_metadata(handle, NULL, bh);
- if (error) {
- ext4_warning(inode->i_sb, "Handle metadata (error %d)",
- error);
- return error;
- }
- }
-
- error = ext4_journal_restart(handle, credits);
- if (error) {
- ext4_warning(inode->i_sb, "Restart journal (error %d)", error);
- return error;
- }
-
- if (bh) {
- error = ext4_journal_get_write_access(handle, bh);
- if (error) {
- ext4_warning(inode->i_sb,
- "Get write access failed (error %d)",
- error);
- return error;
- }
- }
- return 0;
-}
-
static int ext4_xattr_inode_update_ref(handle_t *handle, struct inode *ea_inode,
int ref_change)
{
@@ -1149,6 +1100,24 @@ cleanup:
return saved_err;
}
+static int ext4_xattr_restart_fn(handle_t *handle, struct inode *inode,
+ struct buffer_head *bh, bool block_csum, bool dirty)
+{
+ int error;
+
+ if (bh && dirty) {
+ if (block_csum)
+ ext4_xattr_block_csum_set(inode, bh);
+ error = ext4_handle_dirty_metadata(handle, NULL, bh);
+ if (error) {
+ ext4_warning(inode->i_sb, "Handle metadata (error %d)",
+ error);
+ return error;
+ }
+ }
+ return 0;
+}
+
static void
ext4_xattr_inode_dec_ref_all(handle_t *handle, struct inode *parent,
struct buffer_head *bh,
@@ -1185,13 +1154,24 @@ ext4_xattr_inode_dec_ref_all(handle_t *handle, struct inode *parent,
continue;
}
- err = ext4_xattr_ensure_credits(handle, parent, credits, bh,
- dirty, block_csum);
- if (err) {
+ err = ext4_journal_ensure_credits_fn(handle, credits, credits,
+ ext4_free_metadata_revoke_credits(parent->i_sb, 1),
+ ext4_xattr_restart_fn(handle, parent, bh, block_csum,
+ dirty));
+ if (err < 0) {
ext4_warning_inode(ea_inode, "Ensure credits err=%d",
err);
continue;
}
+ if (err > 0) {
+ err = ext4_journal_get_write_access(handle, bh);
+ if (err) {
+ ext4_warning_inode(ea_inode,
+ "Re-get write access err=%d",
+ err);
+ continue;
+ }
+ }
err = ext4_xattr_inode_dec_ref(handle, ea_inode);
if (err) {
@@ -2335,7 +2315,7 @@ ext4_xattr_set_handle(handle_t *handle, struct inode *inode, int name_index,
flags & XATTR_CREATE);
brelse(bh);
- if (!ext4_handle_has_enough_credits(handle, credits)) {
+ if (jbd2_handle_buffer_credits(handle) < credits) {
error = -ENOSPC;
goto cleanup;
}
@@ -2862,11 +2842,9 @@ int ext4_xattr_delete_inode(handle_t *handle, struct inode *inode,
struct inode *ea_inode;
int error;
- error = ext4_xattr_ensure_credits(handle, inode, extra_credits,
- NULL /* bh */,
- false /* dirty */,
- false /* block_csum */);
- if (error) {
+ error = ext4_journal_ensure_credits(handle, extra_credits,
+ ext4_free_metadata_revoke_credits(inode->i_sb, 1));
+ if (error < 0) {
EXT4_ERROR_INODE(inode, "ensure credits (error %d)", error);
goto cleanup;
}
diff --git a/fs/f2fs/checkpoint.c b/fs/f2fs/checkpoint.c
index a0eef95b9e0e..ffdaba0c55d2 100644
--- a/fs/f2fs/checkpoint.c
+++ b/fs/f2fs/checkpoint.c
@@ -581,7 +581,7 @@ int f2fs_acquire_orphan_inode(struct f2fs_sb_info *sbi)
if (time_to_inject(sbi, FAULT_ORPHAN)) {
spin_unlock(&im->ino_lock);
- f2fs_show_injection_info(FAULT_ORPHAN);
+ f2fs_show_injection_info(sbi, FAULT_ORPHAN);
return -ENOSPC;
}
diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index 5755e897a5f0..a034cd0ce021 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -29,6 +29,7 @@
#define NUM_PREALLOC_POST_READ_CTXS 128
static struct kmem_cache *bio_post_read_ctx_cache;
+static struct kmem_cache *bio_entry_slab;
static mempool_t *bio_post_read_ctx_pool;
static bool __is_cp_guaranteed(struct page *page)
@@ -167,9 +168,10 @@ static bool f2fs_bio_post_read_required(struct bio *bio)
static void f2fs_read_end_io(struct bio *bio)
{
- if (time_to_inject(F2FS_P_SB(bio_first_page_all(bio)),
- FAULT_READ_IO)) {
- f2fs_show_injection_info(FAULT_READ_IO);
+ struct f2fs_sb_info *sbi = F2FS_P_SB(bio_first_page_all(bio));
+
+ if (time_to_inject(sbi, FAULT_READ_IO)) {
+ f2fs_show_injection_info(sbi, FAULT_READ_IO);
bio->bi_status = BLK_STS_IOERR;
}
@@ -191,7 +193,7 @@ static void f2fs_write_end_io(struct bio *bio)
struct bvec_iter_all iter_all;
if (time_to_inject(sbi, FAULT_WRITE_IO)) {
- f2fs_show_injection_info(FAULT_WRITE_IO);
+ f2fs_show_injection_info(sbi, FAULT_WRITE_IO);
bio->bi_status = BLK_STS_IOERR;
}
@@ -543,6 +545,126 @@ static bool io_is_mergeable(struct f2fs_sb_info *sbi, struct bio *bio,
return io_type_is_mergeable(io, fio);
}
+static void add_bio_entry(struct f2fs_sb_info *sbi, struct bio *bio,
+ struct page *page, enum temp_type temp)
+{
+ struct f2fs_bio_info *io = sbi->write_io[DATA] + temp;
+ struct bio_entry *be;
+
+ be = f2fs_kmem_cache_alloc(bio_entry_slab, GFP_NOFS);
+ be->bio = bio;
+ bio_get(bio);
+
+ if (bio_add_page(bio, page, PAGE_SIZE, 0) != PAGE_SIZE)
+ f2fs_bug_on(sbi, 1);
+
+ down_write(&io->bio_list_lock);
+ list_add_tail(&be->list, &io->bio_list);
+ up_write(&io->bio_list_lock);
+}
+
+static void del_bio_entry(struct bio_entry *be)
+{
+ list_del(&be->list);
+ kmem_cache_free(bio_entry_slab, be);
+}
+
+static int add_ipu_page(struct f2fs_sb_info *sbi, struct bio **bio,
+ struct page *page)
+{
+ enum temp_type temp;
+ bool found = false;
+ int ret = -EAGAIN;
+
+ for (temp = HOT; temp < NR_TEMP_TYPE && !found; temp++) {
+ struct f2fs_bio_info *io = sbi->write_io[DATA] + temp;
+ struct list_head *head = &io->bio_list;
+ struct bio_entry *be;
+
+ down_write(&io->bio_list_lock);
+ list_for_each_entry(be, head, list) {
+ if (be->bio != *bio)
+ continue;
+
+ found = true;
+
+ if (bio_add_page(*bio, page, PAGE_SIZE, 0) == PAGE_SIZE) {
+ ret = 0;
+ break;
+ }
+
+ /* bio is full */
+ del_bio_entry(be);
+ __submit_bio(sbi, *bio, DATA);
+ break;
+ }
+ up_write(&io->bio_list_lock);
+ }
+
+ if (ret) {
+ bio_put(*bio);
+ *bio = NULL;
+ }
+
+ return ret;
+}
+
+void f2fs_submit_merged_ipu_write(struct f2fs_sb_info *sbi,
+ struct bio **bio, struct page *page)
+{
+ enum temp_type temp;
+ bool found = false;
+ struct bio *target = bio ? *bio : NULL;
+
+ for (temp = HOT; temp < NR_TEMP_TYPE && !found; temp++) {
+ struct f2fs_bio_info *io = sbi->write_io[DATA] + temp;
+ struct list_head *head = &io->bio_list;
+ struct bio_entry *be;
+
+ if (list_empty(head))
+ continue;
+
+ down_read(&io->bio_list_lock);
+ list_for_each_entry(be, head, list) {
+ if (target)
+ found = (target == be->bio);
+ else
+ found = __has_merged_page(be->bio, NULL,
+ page, 0);
+ if (found)
+ break;
+ }
+ up_read(&io->bio_list_lock);
+
+ if (!found)
+ continue;
+
+ found = false;
+
+ down_write(&io->bio_list_lock);
+ list_for_each_entry(be, head, list) {
+ if (target)
+ found = (target == be->bio);
+ else
+ found = __has_merged_page(be->bio, NULL,
+ page, 0);
+ if (found) {
+ target = be->bio;
+ del_bio_entry(be);
+ break;
+ }
+ }
+ up_write(&io->bio_list_lock);
+ }
+
+ if (found)
+ __submit_bio(sbi, target, DATA);
+ if (bio && *bio) {
+ bio_put(*bio);
+ *bio = NULL;
+ }
+}
+
int f2fs_merge_page_bio(struct f2fs_io_info *fio)
{
struct bio *bio = *fio->bio;
@@ -557,20 +679,17 @@ int f2fs_merge_page_bio(struct f2fs_io_info *fio)
f2fs_trace_ios(fio, 0);
if (bio && !page_is_mergeable(fio->sbi, bio, *fio->last_block,
- fio->new_blkaddr)) {
- __submit_bio(fio->sbi, bio, fio->type);
- bio = NULL;
- }
+ fio->new_blkaddr))
+ f2fs_submit_merged_ipu_write(fio->sbi, &bio, NULL);
alloc_new:
if (!bio) {
bio = __bio_alloc(fio, BIO_MAX_PAGES);
bio_set_op_attrs(bio, fio->op, fio->op_flags);
- }
- if (bio_add_page(bio, page, PAGE_SIZE, 0) < PAGE_SIZE) {
- __submit_bio(fio->sbi, bio, fio->type);
- bio = NULL;
- goto alloc_new;
+ add_bio_entry(fio->sbi, bio, page, fio->temp);
+ } else {
+ if (add_ipu_page(fio->sbi, &bio, page))
+ goto alloc_new;
}
if (fio->io_wbc)
@@ -584,19 +703,6 @@ alloc_new:
return 0;
}
-static void f2fs_submit_ipu_bio(struct f2fs_sb_info *sbi, struct bio **bio,
- struct page *page)
-{
- if (!bio)
- return;
-
- if (!__has_merged_page(*bio, NULL, page, 0))
- return;
-
- __submit_bio(sbi, *bio, DATA);
- *bio = NULL;
-}
-
void f2fs_submit_page_write(struct f2fs_io_info *fio)
{
struct f2fs_sb_info *sbi = fio->sbi;
@@ -2098,7 +2204,7 @@ static int __write_data_page(struct page *page, bool *submitted,
loff_t i_size = i_size_read(inode);
const pgoff_t end_index = ((unsigned long long) i_size)
>> PAGE_SHIFT;
- loff_t psize = (page->index + 1) << PAGE_SHIFT;
+ loff_t psize = (loff_t)(page->index + 1) << PAGE_SHIFT;
unsigned offset = 0;
bool need_balance_fs = false;
int err = 0;
@@ -2215,14 +2321,12 @@ out:
unlock_page(page);
if (!S_ISDIR(inode->i_mode) && !IS_NOQUOTA(inode) &&
- !F2FS_I(inode)->cp_task) {
- f2fs_submit_ipu_bio(sbi, bio, page);
+ !F2FS_I(inode)->cp_task)
f2fs_balance_fs(sbi, need_balance_fs);
- }
if (unlikely(f2fs_cp_error(sbi))) {
- f2fs_submit_ipu_bio(sbi, bio, page);
f2fs_submit_merged_write(sbi, DATA);
+ f2fs_submit_merged_ipu_write(sbi, bio, NULL);
submitted = NULL;
}
@@ -2342,13 +2446,11 @@ continue_unlock:
}
if (PageWriteback(page)) {
- if (wbc->sync_mode != WB_SYNC_NONE) {
+ if (wbc->sync_mode != WB_SYNC_NONE)
f2fs_wait_on_page_writeback(page,
DATA, true, true);
- f2fs_submit_ipu_bio(sbi, &bio, page);
- } else {
+ else
goto continue_unlock;
- }
}
if (!clear_page_dirty_for_io(page))
@@ -2406,7 +2508,7 @@ continue_unlock:
NULL, 0, DATA);
/* submit cached bio of IPU write */
if (bio)
- __submit_bio(sbi, bio, DATA);
+ f2fs_submit_merged_ipu_write(sbi, &bio, NULL);
return ret;
}
@@ -3211,8 +3313,22 @@ fail:
return -ENOMEM;
}
-void __exit f2fs_destroy_post_read_processing(void)
+void f2fs_destroy_post_read_processing(void)
{
mempool_destroy(bio_post_read_ctx_pool);
kmem_cache_destroy(bio_post_read_ctx_cache);
}
+
+int __init f2fs_init_bio_entry_cache(void)
+{
+ bio_entry_slab = f2fs_kmem_cache_create("bio_entry_slab",
+ sizeof(struct bio_entry));
+ if (!bio_entry_slab)
+ return -ENOMEM;
+ return 0;
+}
+
+void __exit f2fs_destroy_bio_entry_cache(void)
+{
+ kmem_cache_destroy(bio_entry_slab);
+}
diff --git a/fs/f2fs/dir.c b/fs/f2fs/dir.c
index 4033778bcbbf..c967cacf979e 100644
--- a/fs/f2fs/dir.c
+++ b/fs/f2fs/dir.c
@@ -628,7 +628,7 @@ int f2fs_add_regular_entry(struct inode *dir, const struct qstr *new_name,
start:
if (time_to_inject(F2FS_I_SB(dir), FAULT_DIR_DEPTH)) {
- f2fs_show_injection_info(FAULT_DIR_DEPTH);
+ f2fs_show_injection_info(F2FS_I_SB(dir), FAULT_DIR_DEPTH);
return -ENOSPC;
}
@@ -919,8 +919,9 @@ int f2fs_fill_dentries(struct dir_context *ctx, struct f2fs_dentry_ptr *d,
bit_pos++;
ctx->pos = start_pos + bit_pos;
printk_ratelimited(
- "%s, invalid namelen(0), ino:%u, run fsck to fix.",
- KERN_WARNING, le32_to_cpu(de->ino));
+ "%sF2FS-fs (%s): invalid namelen(0), ino:%u, run fsck to fix.",
+ KERN_WARNING, sbi->sb->s_id,
+ le32_to_cpu(de->ino));
set_sbi_flag(sbi, SBI_NEED_FSCK);
continue;
}
diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index 4024790028aa..5a888a063c7f 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -890,6 +890,7 @@ enum {
CURSEG_WARM_NODE, /* direct node blocks of normal files */
CURSEG_COLD_NODE, /* indirect node blocks */
NO_CHECK_TYPE,
+ CURSEG_COLD_DATA_PINNED,/* cold data for pinned file */
};
struct flush_cmd {
@@ -1068,6 +1069,11 @@ struct f2fs_io_info {
unsigned char version; /* version of the node */
};
+struct bio_entry {
+ struct bio *bio;
+ struct list_head list;
+};
+
#define is_read_io(rw) ((rw) == READ)
struct f2fs_bio_info {
struct f2fs_sb_info *sbi; /* f2fs superblock */
@@ -1077,6 +1083,8 @@ struct f2fs_bio_info {
struct rw_semaphore io_rwsem; /* blocking op for bio */
spinlock_t io_lock; /* serialize DATA/NODE IOs */
struct list_head io_list; /* track fios */
+ struct list_head bio_list; /* bio entry list head */
+ struct rw_semaphore bio_list_lock; /* lock to protect bio entry list */
};
#define FDEV(i) (sbi->devs[i])
@@ -1289,11 +1297,13 @@ struct f2fs_sb_info {
unsigned int gc_mode; /* current GC state */
unsigned int next_victim_seg[2]; /* next segment in victim section */
/* for skip statistic */
+ unsigned int atomic_files; /* # of opened atomic file */
unsigned long long skipped_atomic_files[2]; /* FG_GC and BG_GC */
unsigned long long skipped_gc_rwsem; /* FG_GC only */
/* threshold for gc trials on pinned files */
u64 gc_pin_file_threshold;
+ struct rw_semaphore pin_sem;
/* maximum # of trials to find a victim segment for SSR and GC */
unsigned int max_victim_search;
@@ -1365,9 +1375,10 @@ struct f2fs_private_dio {
};
#ifdef CONFIG_F2FS_FAULT_INJECTION
-#define f2fs_show_injection_info(type) \
- printk_ratelimited("%sF2FS-fs : inject %s in %s of %pS\n", \
- KERN_INFO, f2fs_fault_name[type], \
+#define f2fs_show_injection_info(sbi, type) \
+ printk_ratelimited("%sF2FS-fs (%s) : inject %s in %s of %pS\n", \
+ KERN_INFO, sbi->sb->s_id, \
+ f2fs_fault_name[type], \
__func__, __builtin_return_address(0))
static inline bool time_to_inject(struct f2fs_sb_info *sbi, int type)
{
@@ -1387,7 +1398,7 @@ static inline bool time_to_inject(struct f2fs_sb_info *sbi, int type)
return false;
}
#else
-#define f2fs_show_injection_info(type) do { } while (0)
+#define f2fs_show_injection_info(sbi, type) do { } while (0)
static inline bool time_to_inject(struct f2fs_sb_info *sbi, int type)
{
return false;
@@ -1772,7 +1783,7 @@ static inline int inc_valid_block_count(struct f2fs_sb_info *sbi,
return ret;
if (time_to_inject(sbi, FAULT_BLOCK)) {
- f2fs_show_injection_info(FAULT_BLOCK);
+ f2fs_show_injection_info(sbi, FAULT_BLOCK);
release = *count;
goto release_quota;
}
@@ -2024,7 +2035,7 @@ static inline int inc_valid_node_count(struct f2fs_sb_info *sbi,
}
if (time_to_inject(sbi, FAULT_BLOCK)) {
- f2fs_show_injection_info(FAULT_BLOCK);
+ f2fs_show_injection_info(sbi, FAULT_BLOCK);
goto enospc;
}
@@ -2139,7 +2150,8 @@ static inline struct page *f2fs_grab_cache_page(struct address_space *mapping,
return page;
if (time_to_inject(F2FS_M_SB(mapping), FAULT_PAGE_ALLOC)) {
- f2fs_show_injection_info(FAULT_PAGE_ALLOC);
+ f2fs_show_injection_info(F2FS_M_SB(mapping),
+ FAULT_PAGE_ALLOC);
return NULL;
}
}
@@ -2154,7 +2166,7 @@ static inline struct page *f2fs_pagecache_get_page(
int fgp_flags, gfp_t gfp_mask)
{
if (time_to_inject(F2FS_M_SB(mapping), FAULT_PAGE_GET)) {
- f2fs_show_injection_info(FAULT_PAGE_GET);
+ f2fs_show_injection_info(F2FS_M_SB(mapping), FAULT_PAGE_GET);
return NULL;
}
@@ -2223,7 +2235,7 @@ static inline struct bio *f2fs_bio_alloc(struct f2fs_sb_info *sbi,
return bio;
}
if (time_to_inject(sbi, FAULT_ALLOC_BIO)) {
- f2fs_show_injection_info(FAULT_ALLOC_BIO);
+ f2fs_show_injection_info(sbi, FAULT_ALLOC_BIO);
return NULL;
}
@@ -2704,6 +2716,20 @@ static inline void clear_file(struct inode *inode, int type)
f2fs_mark_inode_dirty_sync(inode, true);
}
+static inline bool f2fs_is_time_consistent(struct inode *inode)
+{
+ if (!timespec64_equal(F2FS_I(inode)->i_disk_time, &inode->i_atime))
+ return false;
+ if (!timespec64_equal(F2FS_I(inode)->i_disk_time + 1, &inode->i_ctime))
+ return false;
+ if (!timespec64_equal(F2FS_I(inode)->i_disk_time + 2, &inode->i_mtime))
+ return false;
+ if (!timespec64_equal(F2FS_I(inode)->i_disk_time + 3,
+ &F2FS_I(inode)->i_crtime))
+ return false;
+ return true;
+}
+
static inline bool f2fs_skip_inode_update(struct inode *inode, int dsync)
{
bool ret;
@@ -2721,14 +2747,7 @@ static inline bool f2fs_skip_inode_update(struct inode *inode, int dsync)
i_size_read(inode) & ~PAGE_MASK)
return false;
- if (!timespec64_equal(F2FS_I(inode)->i_disk_time, &inode->i_atime))
- return false;
- if (!timespec64_equal(F2FS_I(inode)->i_disk_time + 1, &inode->i_ctime))
- return false;
- if (!timespec64_equal(F2FS_I(inode)->i_disk_time + 2, &inode->i_mtime))
- return false;
- if (!timespec64_equal(F2FS_I(inode)->i_disk_time + 3,
- &F2FS_I(inode)->i_crtime))
+ if (!f2fs_is_time_consistent(inode))
return false;
down_read(&F2FS_I(inode)->i_sem);
@@ -2783,7 +2802,7 @@ static inline void *f2fs_kmalloc(struct f2fs_sb_info *sbi,
void *ret;
if (time_to_inject(sbi, FAULT_KMALLOC)) {
- f2fs_show_injection_info(FAULT_KMALLOC);
+ f2fs_show_injection_info(sbi, FAULT_KMALLOC);
return NULL;
}
@@ -2804,7 +2823,7 @@ static inline void *f2fs_kvmalloc(struct f2fs_sb_info *sbi,
size_t size, gfp_t flags)
{
if (time_to_inject(sbi, FAULT_KVMALLOC)) {
- f2fs_show_injection_info(FAULT_KVMALLOC);
+ f2fs_show_injection_info(sbi, FAULT_KVMALLOC);
return NULL;
}
@@ -3102,7 +3121,7 @@ void f2fs_release_discard_addrs(struct f2fs_sb_info *sbi);
int f2fs_npages_for_summary_flush(struct f2fs_sb_info *sbi, bool for_ra);
void allocate_segment_for_resize(struct f2fs_sb_info *sbi, int type,
unsigned int start, unsigned int end);
-void f2fs_allocate_new_segments(struct f2fs_sb_info *sbi);
+void f2fs_allocate_new_segments(struct f2fs_sb_info *sbi, int type);
int f2fs_trim_fs(struct f2fs_sb_info *sbi, struct fstrim_range *range);
bool f2fs_exist_trim_candidates(struct f2fs_sb_info *sbi,
struct cp_control *cpc);
@@ -3188,10 +3207,14 @@ void f2fs_destroy_checkpoint_caches(void);
*/
int f2fs_init_post_read_processing(void);
void f2fs_destroy_post_read_processing(void);
+int f2fs_init_bio_entry_cache(void);
+void f2fs_destroy_bio_entry_cache(void);
void f2fs_submit_merged_write(struct f2fs_sb_info *sbi, enum page_type type);
void f2fs_submit_merged_write_cond(struct f2fs_sb_info *sbi,
struct inode *inode, struct page *page,
nid_t ino, enum page_type type);
+void f2fs_submit_merged_ipu_write(struct f2fs_sb_info *sbi,
+ struct bio **bio, struct page *page);
void f2fs_flush_merged_writes(struct f2fs_sb_info *sbi);
int f2fs_submit_page_bio(struct f2fs_io_info *fio);
int f2fs_merge_page_bio(struct f2fs_io_info *fio);
diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c
index 29bc0a542759..85af112e868d 100644
--- a/fs/f2fs/file.c
+++ b/fs/f2fs/file.c
@@ -681,7 +681,7 @@ int f2fs_truncate(struct inode *inode)
trace_f2fs_truncate(inode);
if (time_to_inject(F2FS_I_SB(inode), FAULT_TRUNCATE)) {
- f2fs_show_injection_info(FAULT_TRUNCATE);
+ f2fs_show_injection_info(F2FS_I_SB(inode), FAULT_TRUNCATE);
return -EIO;
}
@@ -726,11 +726,14 @@ int f2fs_getattr(const struct path *path, struct kstat *stat,
stat->attributes |= STATX_ATTR_IMMUTABLE;
if (flags & F2FS_NODUMP_FL)
stat->attributes |= STATX_ATTR_NODUMP;
+ if (IS_VERITY(inode))
+ stat->attributes |= STATX_ATTR_VERITY;
stat->attributes_mask |= (STATX_ATTR_APPEND |
STATX_ATTR_ENCRYPTED |
STATX_ATTR_IMMUTABLE |
- STATX_ATTR_NODUMP);
+ STATX_ATTR_NODUMP |
+ STATX_ATTR_VERITY);
generic_fillattr(inode, stat);
@@ -1139,7 +1142,7 @@ static int __clone_blkaddrs(struct inode *src_inode, struct inode *dst_inode,
}
dn.ofs_in_node++;
i++;
- new_size = (dst + i) << PAGE_SHIFT;
+ new_size = (loff_t)(dst + i) << PAGE_SHIFT;
if (dst_inode->i_size < new_size)
f2fs_i_size_write(dst_inode, new_size);
} while (--ilen && (do_replace[i] || blkaddr[i] == NULL_ADDR));
@@ -1545,12 +1548,44 @@ static int expand_inode_data(struct inode *inode, loff_t offset,
if (off_end)
map.m_len++;
- if (f2fs_is_pinned_file(inode))
- map.m_seg_type = CURSEG_COLD_DATA;
+ if (!map.m_len)
+ return 0;
+
+ if (f2fs_is_pinned_file(inode)) {
+ block_t len = (map.m_len >> sbi->log_blocks_per_seg) <<
+ sbi->log_blocks_per_seg;
+ block_t done = 0;
+
+ if (map.m_len % sbi->blocks_per_seg)
+ len += sbi->blocks_per_seg;
+
+ map.m_len = sbi->blocks_per_seg;
+next_alloc:
+ if (has_not_enough_free_secs(sbi, 0,
+ GET_SEC_FROM_SEG(sbi, overprovision_segments(sbi)))) {
+ mutex_lock(&sbi->gc_mutex);
+ err = f2fs_gc(sbi, true, false, NULL_SEGNO);
+ if (err && err != -ENODATA && err != -EAGAIN)
+ goto out_err;
+ }
+
+ down_write(&sbi->pin_sem);
+ map.m_seg_type = CURSEG_COLD_DATA_PINNED;
+ f2fs_allocate_new_segments(sbi, CURSEG_COLD_DATA);
+ err = f2fs_map_blocks(inode, &map, 1, F2FS_GET_BLOCK_PRE_DIO);
+ up_write(&sbi->pin_sem);
- err = f2fs_map_blocks(inode, &map, 1, (f2fs_is_pinned_file(inode) ?
- F2FS_GET_BLOCK_PRE_DIO :
- F2FS_GET_BLOCK_PRE_AIO));
+ done += map.m_len;
+ len -= map.m_len;
+ map.m_lblk += map.m_len;
+ if (!err && len)
+ goto next_alloc;
+
+ map.m_len = done;
+ } else {
+ err = f2fs_map_blocks(inode, &map, 1, F2FS_GET_BLOCK_PRE_AIO);
+ }
+out_err:
if (err) {
pgoff_t last_off;
@@ -1890,6 +1925,7 @@ static int f2fs_ioc_start_atomic_write(struct file *filp)
spin_lock(&sbi->inode_lock[ATOMIC_FILE]);
if (list_empty(&fi->inmem_ilist))
list_add_tail(&fi->inmem_ilist, &sbi->inode_list[ATOMIC_FILE]);
+ sbi->atomic_files++;
spin_unlock(&sbi->inode_lock[ATOMIC_FILE]);
/* add inode in inmem_list first and set atomic_file */
@@ -3403,6 +3439,7 @@ long f2fs_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
case F2FS_IOC_RELEASE_VOLATILE_WRITE:
case F2FS_IOC_ABORT_VOLATILE_WRITE:
case F2FS_IOC_SHUTDOWN:
+ case FITRIM:
case F2FS_IOC_SET_ENCRYPTION_POLICY:
case F2FS_IOC_GET_ENCRYPTION_PWSALT:
case F2FS_IOC_GET_ENCRYPTION_POLICY:
diff --git a/fs/f2fs/gc.c b/fs/f2fs/gc.c
index 5877bd729689..b3d399623290 100644
--- a/fs/f2fs/gc.c
+++ b/fs/f2fs/gc.c
@@ -54,7 +54,7 @@ static int gc_thread_func(void *data)
}
if (time_to_inject(sbi, FAULT_CHECKPOINT)) {
- f2fs_show_injection_info(FAULT_CHECKPOINT);
+ f2fs_show_injection_info(sbi, FAULT_CHECKPOINT);
f2fs_stop_checkpoint(sbi, false);
}
@@ -1012,8 +1012,14 @@ next_step:
block_t start_bidx;
nid_t nid = le32_to_cpu(entry->nid);
- /* stop BG_GC if there is not enough free sections. */
- if (gc_type == BG_GC && has_not_enough_free_secs(sbi, 0, 0))
+ /*
+ * stop BG_GC if there is not enough free sections.
+ * Or, stop GC if the segment becomes fully valid caused by
+ * race condition along with SSR block allocation.
+ */
+ if ((gc_type == BG_GC && has_not_enough_free_secs(sbi, 0, 0)) ||
+ get_valid_blocks(sbi, segno, false) ==
+ sbi->blocks_per_seg)
return submitted;
if (check_valid_map(sbi, segno, off) == 0)
@@ -1437,11 +1443,20 @@ static void update_sb_metadata(struct f2fs_sb_info *sbi, int secs)
raw_sb->segment_count_main = cpu_to_le32(segment_count_main + segs);
raw_sb->block_count = cpu_to_le64(block_count +
(long long)segs * sbi->blocks_per_seg);
+ if (f2fs_is_multi_device(sbi)) {
+ int last_dev = sbi->s_ndevs - 1;
+ int dev_segs =
+ le32_to_cpu(raw_sb->devs[last_dev].total_segments);
+
+ raw_sb->devs[last_dev].total_segments =
+ cpu_to_le32(dev_segs + segs);
+ }
}
static void update_fs_metadata(struct f2fs_sb_info *sbi, int secs)
{
int segs = secs * sbi->segs_per_sec;
+ long long blks = (long long)segs * sbi->blocks_per_seg;
long long user_block_count =
le64_to_cpu(F2FS_CKPT(sbi)->user_block_count);
@@ -1449,8 +1464,20 @@ static void update_fs_metadata(struct f2fs_sb_info *sbi, int secs)
MAIN_SEGS(sbi) = (int)MAIN_SEGS(sbi) + segs;
FREE_I(sbi)->free_sections = (int)FREE_I(sbi)->free_sections + secs;
FREE_I(sbi)->free_segments = (int)FREE_I(sbi)->free_segments + segs;
- F2FS_CKPT(sbi)->user_block_count = cpu_to_le64(user_block_count +
- (long long)segs * sbi->blocks_per_seg);
+ F2FS_CKPT(sbi)->user_block_count = cpu_to_le64(user_block_count + blks);
+
+ if (f2fs_is_multi_device(sbi)) {
+ int last_dev = sbi->s_ndevs - 1;
+
+ FDEV(last_dev).total_segments =
+ (int)FDEV(last_dev).total_segments + segs;
+ FDEV(last_dev).end_blk =
+ (long long)FDEV(last_dev).end_blk + blks;
+#ifdef CONFIG_BLK_DEV_ZONED
+ FDEV(last_dev).nr_blkz = (int)FDEV(last_dev).nr_blkz +
+ (int)(blks >> sbi->log_blocks_per_blkz);
+#endif
+ }
}
int f2fs_resize_fs(struct f2fs_sb_info *sbi, __u64 block_count)
@@ -1465,6 +1492,15 @@ int f2fs_resize_fs(struct f2fs_sb_info *sbi, __u64 block_count)
if (block_count > old_block_count)
return -EINVAL;
+ if (f2fs_is_multi_device(sbi)) {
+ int last_dev = sbi->s_ndevs - 1;
+ __u64 last_segs = FDEV(last_dev).total_segments;
+
+ if (block_count + last_segs * sbi->blocks_per_seg <=
+ old_block_count)
+ return -EINVAL;
+ }
+
/* new fs size should align to section size */
div_u64_rem(block_count, BLKS_PER_SEC(sbi), &rem);
if (rem)
diff --git a/fs/f2fs/inode.c b/fs/f2fs/inode.c
index db4fec30c30d..502bd491336a 100644
--- a/fs/f2fs/inode.c
+++ b/fs/f2fs/inode.c
@@ -615,7 +615,11 @@ int f2fs_write_inode(struct inode *inode, struct writeback_control *wbc)
inode->i_ino == F2FS_META_INO(sbi))
return 0;
- if (!is_inode_flag_set(inode, FI_DIRTY_INODE))
+ /*
+ * atime could be updated without dirtying f2fs inode in lazytime mode
+ */
+ if (f2fs_is_time_consistent(inode) &&
+ !is_inode_flag_set(inode, FI_DIRTY_INODE))
return 0;
if (!f2fs_is_checkpoint_ready(sbi))
@@ -677,7 +681,7 @@ retry:
err = f2fs_truncate(inode);
if (time_to_inject(sbi, FAULT_EVICT_INODE)) {
- f2fs_show_injection_info(FAULT_EVICT_INODE);
+ f2fs_show_injection_info(sbi, FAULT_EVICT_INODE);
err = -EIO;
}
diff --git a/fs/f2fs/namei.c b/fs/f2fs/namei.c
index 4faf06e8bf89..a1c507b0b4ac 100644
--- a/fs/f2fs/namei.c
+++ b/fs/f2fs/namei.c
@@ -981,7 +981,8 @@ static int f2fs_rename(struct inode *old_dir, struct dentry *old_dentry,
if (!old_dir_entry || whiteout)
file_lost_pino(old_inode);
else
- F2FS_I(old_inode)->i_pino = new_dir->i_ino;
+ /* adjust dir's i_pino to pass fsck check */
+ f2fs_i_pino_write(old_inode, new_dir->i_ino);
up_write(&F2FS_I(old_inode)->i_sem);
old_inode->i_ctime = current_time(old_inode);
@@ -1141,7 +1142,11 @@ static int f2fs_cross_rename(struct inode *old_dir, struct dentry *old_dentry,
f2fs_set_link(old_dir, old_entry, old_page, new_inode);
down_write(&F2FS_I(old_inode)->i_sem);
- file_lost_pino(old_inode);
+ if (!old_dir_entry)
+ file_lost_pino(old_inode);
+ else
+ /* adjust dir's i_pino to pass fsck check */
+ f2fs_i_pino_write(old_inode, new_dir->i_ino);
up_write(&F2FS_I(old_inode)->i_sem);
old_dir->i_ctime = current_time(old_dir);
@@ -1156,7 +1161,11 @@ static int f2fs_cross_rename(struct inode *old_dir, struct dentry *old_dentry,
f2fs_set_link(new_dir, new_entry, new_page, old_inode);
down_write(&F2FS_I(new_inode)->i_sem);
- file_lost_pino(new_inode);
+ if (!new_dir_entry)
+ file_lost_pino(new_inode);
+ else
+ /* adjust dir's i_pino to pass fsck check */
+ f2fs_i_pino_write(new_inode, old_dir->i_ino);
up_write(&F2FS_I(new_inode)->i_sem);
new_dir->i_ctime = current_time(new_dir);
diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c
index 8b66bc4c004b..3314a0f3405e 100644
--- a/fs/f2fs/node.c
+++ b/fs/f2fs/node.c
@@ -2349,7 +2349,6 @@ static int __f2fs_build_free_nids(struct f2fs_sb_info *sbi,
if (ret) {
up_read(&nm_i->nat_tree_lock);
- f2fs_bug_on(sbi, !mount);
f2fs_err(sbi, "NAT is corrupt, run fsck to fix it");
return ret;
}
@@ -2399,7 +2398,7 @@ bool f2fs_alloc_nid(struct f2fs_sb_info *sbi, nid_t *nid)
struct free_nid *i = NULL;
retry:
if (time_to_inject(sbi, FAULT_ALLOC_NID)) {
- f2fs_show_injection_info(FAULT_ALLOC_NID);
+ f2fs_show_injection_info(sbi, FAULT_ALLOC_NID);
return false;
}
diff --git a/fs/f2fs/recovery.c b/fs/f2fs/recovery.c
index 783773e4560d..76477f71d4ee 100644
--- a/fs/f2fs/recovery.c
+++ b/fs/f2fs/recovery.c
@@ -711,7 +711,7 @@ next:
f2fs_put_page(page, 1);
}
if (!err)
- f2fs_allocate_new_segments(sbi);
+ f2fs_allocate_new_segments(sbi, NO_CHECK_TYPE);
return err;
}
diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c
index 808709581481..56e81447e2f3 100644
--- a/fs/f2fs/segment.c
+++ b/fs/f2fs/segment.c
@@ -288,6 +288,8 @@ void f2fs_drop_inmem_pages_all(struct f2fs_sb_info *sbi, bool gc_failure)
struct list_head *head = &sbi->inode_list[ATOMIC_FILE];
struct inode *inode;
struct f2fs_inode_info *fi;
+ unsigned int count = sbi->atomic_files;
+ unsigned int looped = 0;
next:
spin_lock(&sbi->inode_lock[ATOMIC_FILE]);
if (list_empty(head)) {
@@ -296,22 +298,26 @@ next:
}
fi = list_first_entry(head, struct f2fs_inode_info, inmem_ilist);
inode = igrab(&fi->vfs_inode);
+ if (inode)
+ list_move_tail(&fi->inmem_ilist, head);
spin_unlock(&sbi->inode_lock[ATOMIC_FILE]);
if (inode) {
if (gc_failure) {
- if (fi->i_gc_failures[GC_FAILURE_ATOMIC])
- goto drop;
- goto skip;
+ if (!fi->i_gc_failures[GC_FAILURE_ATOMIC])
+ goto skip;
}
-drop:
set_inode_flag(inode, FI_ATOMIC_REVOKE_REQUEST);
f2fs_drop_inmem_pages(inode);
+skip:
iput(inode);
}
-skip:
congestion_wait(BLK_RW_ASYNC, HZ/50);
cond_resched();
+ if (gc_failure) {
+ if (++looped >= count)
+ return;
+ }
goto next;
}
@@ -327,13 +333,16 @@ void f2fs_drop_inmem_pages(struct inode *inode)
mutex_unlock(&fi->inmem_lock);
}
- clear_inode_flag(inode, FI_ATOMIC_FILE);
fi->i_gc_failures[GC_FAILURE_ATOMIC] = 0;
stat_dec_atomic_write(inode);
spin_lock(&sbi->inode_lock[ATOMIC_FILE]);
if (!list_empty(&fi->inmem_ilist))
list_del_init(&fi->inmem_ilist);
+ if (f2fs_is_atomic_file(inode)) {
+ clear_inode_flag(inode, FI_ATOMIC_FILE);
+ sbi->atomic_files--;
+ }
spin_unlock(&sbi->inode_lock[ATOMIC_FILE]);
}
@@ -480,7 +489,7 @@ int f2fs_commit_inmem_pages(struct inode *inode)
void f2fs_balance_fs(struct f2fs_sb_info *sbi, bool need)
{
if (time_to_inject(sbi, FAULT_CHECKPOINT)) {
- f2fs_show_injection_info(FAULT_CHECKPOINT);
+ f2fs_show_injection_info(sbi, FAULT_CHECKPOINT);
f2fs_stop_checkpoint(sbi, false);
}
@@ -1008,8 +1017,9 @@ static void __remove_discard_cmd(struct f2fs_sb_info *sbi,
if (dc->error)
printk_ratelimited(
- "%sF2FS-fs: Issue discard(%u, %u, %u) failed, ret: %d",
- KERN_INFO, dc->lstart, dc->start, dc->len, dc->error);
+ "%sF2FS-fs (%s): Issue discard(%u, %u, %u) failed, ret: %d",
+ KERN_INFO, sbi->sb->s_id,
+ dc->lstart, dc->start, dc->len, dc->error);
__detach_discard_cmd(dcc, dc);
}
@@ -1149,7 +1159,7 @@ static int __submit_discard_cmd(struct f2fs_sb_info *sbi,
dc->len += len;
if (time_to_inject(sbi, FAULT_DISCARD)) {
- f2fs_show_injection_info(FAULT_DISCARD);
+ f2fs_show_injection_info(sbi, FAULT_DISCARD);
err = -EIO;
goto submit;
}
@@ -1771,7 +1781,8 @@ static int __f2fs_issue_discard_zone(struct f2fs_sb_info *sbi,
return -EIO;
}
trace_f2fs_issue_reset_zone(bdev, blkstart);
- return blkdev_reset_zones(bdev, sector, nr_sects, GFP_NOFS);
+ return blkdev_zone_mgmt(bdev, REQ_OP_ZONE_RESET,
+ sector, nr_sects, GFP_NOFS);
}
/* For conventional zones, use regular discard if supported */
@@ -2690,7 +2701,7 @@ unlock:
up_read(&SM_I(sbi)->curseg_lock);
}
-void f2fs_allocate_new_segments(struct f2fs_sb_info *sbi)
+void f2fs_allocate_new_segments(struct f2fs_sb_info *sbi, int type)
{
struct curseg_info *curseg;
unsigned int old_segno;
@@ -2699,10 +2710,17 @@ void f2fs_allocate_new_segments(struct f2fs_sb_info *sbi)
down_write(&SIT_I(sbi)->sentry_lock);
for (i = CURSEG_HOT_DATA; i <= CURSEG_COLD_DATA; i++) {
+ if (type != NO_CHECK_TYPE && i != type)
+ continue;
+
curseg = CURSEG_I(sbi, i);
- old_segno = curseg->segno;
- SIT_I(sbi)->s_ops->allocate_segment(sbi, i, true);
- locate_dirty_segment(sbi, old_segno);
+ if (type == NO_CHECK_TYPE || curseg->next_blkoff ||
+ get_valid_blocks(sbi, curseg->segno, false) ||
+ get_ckpt_valid_blocks(sbi, curseg->segno)) {
+ old_segno = curseg->segno;
+ SIT_I(sbi)->s_ops->allocate_segment(sbi, i, true);
+ locate_dirty_segment(sbi, old_segno);
+ }
}
up_write(&SIT_I(sbi)->sentry_lock);
@@ -3068,6 +3086,19 @@ void f2fs_allocate_data_block(struct f2fs_sb_info *sbi, struct page *page,
{
struct sit_info *sit_i = SIT_I(sbi);
struct curseg_info *curseg = CURSEG_I(sbi, type);
+ bool put_pin_sem = false;
+
+ if (type == CURSEG_COLD_DATA) {
+ /* GC during CURSEG_COLD_DATA_PINNED allocation */
+ if (down_read_trylock(&sbi->pin_sem)) {
+ put_pin_sem = true;
+ } else {
+ type = CURSEG_WARM_DATA;
+ curseg = CURSEG_I(sbi, type);
+ }
+ } else if (type == CURSEG_COLD_DATA_PINNED) {
+ type = CURSEG_COLD_DATA;
+ }
down_read(&SM_I(sbi)->curseg_lock);
@@ -3133,6 +3164,9 @@ void f2fs_allocate_data_block(struct f2fs_sb_info *sbi, struct page *page,
mutex_unlock(&curseg->curseg_mutex);
up_read(&SM_I(sbi)->curseg_lock);
+
+ if (put_pin_sem)
+ up_read(&sbi->pin_sem);
}
static void update_device_state(struct f2fs_io_info *fio)
@@ -3379,7 +3413,10 @@ void f2fs_wait_on_page_writeback(struct page *page,
if (PageWriteback(page)) {
struct f2fs_sb_info *sbi = F2FS_P_SB(page);
+ /* submit cached LFS IO */
f2fs_submit_merged_write_cond(sbi, NULL, page, 0, type);
+ /* sbumit cached IPU IO */
+ f2fs_submit_merged_ipu_write(sbi, NULL, page);
if (ordered) {
wait_on_page_writeback(page);
f2fs_bug_on(sbi, locked && PageWriteback(page));
diff --git a/fs/f2fs/segment.h b/fs/f2fs/segment.h
index 325781a1ae4d..a95467b202ea 100644
--- a/fs/f2fs/segment.h
+++ b/fs/f2fs/segment.h
@@ -313,6 +313,8 @@ struct sit_entry_set {
*/
static inline struct curseg_info *CURSEG_I(struct f2fs_sb_info *sbi, int type)
{
+ if (type == CURSEG_COLD_DATA_PINNED)
+ type = CURSEG_COLD_DATA;
return (struct curseg_info *)(SM_I(sbi)->curseg_array + type);
}
diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c
index 1443cee15863..5111e1ffe58a 100644
--- a/fs/f2fs/super.c
+++ b/fs/f2fs/super.c
@@ -1213,9 +1213,13 @@ static int f2fs_statfs_project(struct super_block *sb,
return PTR_ERR(dquot);
spin_lock(&dquot->dq_dqb_lock);
- limit = (dquot->dq_dqb.dqb_bsoftlimit ?
- dquot->dq_dqb.dqb_bsoftlimit :
- dquot->dq_dqb.dqb_bhardlimit) >> sb->s_blocksize_bits;
+ limit = 0;
+ if (dquot->dq_dqb.dqb_bsoftlimit)
+ limit = dquot->dq_dqb.dqb_bsoftlimit;
+ if (dquot->dq_dqb.dqb_bhardlimit &&
+ (!limit || dquot->dq_dqb.dqb_bhardlimit < limit))
+ limit = dquot->dq_dqb.dqb_bhardlimit;
+
if (limit && buf->f_blocks > limit) {
curblock = dquot->dq_dqb.dqb_curspace >> sb->s_blocksize_bits;
buf->f_blocks = limit;
@@ -1224,9 +1228,13 @@ static int f2fs_statfs_project(struct super_block *sb,
(buf->f_blocks - curblock) : 0;
}
- limit = dquot->dq_dqb.dqb_isoftlimit ?
- dquot->dq_dqb.dqb_isoftlimit :
- dquot->dq_dqb.dqb_ihardlimit;
+ limit = 0;
+ if (dquot->dq_dqb.dqb_isoftlimit)
+ limit = dquot->dq_dqb.dqb_isoftlimit;
+ if (dquot->dq_dqb.dqb_ihardlimit &&
+ (!limit || dquot->dq_dqb.dqb_ihardlimit < limit))
+ limit = dquot->dq_dqb.dqb_ihardlimit;
+
if (limit && buf->f_files > limit) {
buf->f_files = limit;
buf->f_ffree =
@@ -1932,7 +1940,7 @@ static int f2fs_quota_enable(struct super_block *sb, int type, int format_id,
/* Don't account quota for quota files to avoid recursion */
qf_inode->i_flags |= S_NOQUOTA;
- err = dquot_enable(qf_inode, type, format_id, flags);
+ err = dquot_load_quota_inode(qf_inode, type, format_id, flags);
iput(qf_inode);
return err;
}
@@ -2308,13 +2316,27 @@ static bool f2fs_dummy_context(struct inode *inode)
return DUMMY_ENCRYPTION_ENABLED(F2FS_I_SB(inode));
}
+static bool f2fs_has_stable_inodes(struct super_block *sb)
+{
+ return true;
+}
+
+static void f2fs_get_ino_and_lblk_bits(struct super_block *sb,
+ int *ino_bits_ret, int *lblk_bits_ret)
+{
+ *ino_bits_ret = 8 * sizeof(nid_t);
+ *lblk_bits_ret = 8 * sizeof(block_t);
+}
+
static const struct fscrypt_operations f2fs_cryptops = {
- .key_prefix = "f2fs:",
- .get_context = f2fs_get_context,
- .set_context = f2fs_set_context,
- .dummy_context = f2fs_dummy_context,
- .empty_dir = f2fs_empty_dir,
- .max_namelen = F2FS_NAME_LEN,
+ .key_prefix = "f2fs:",
+ .get_context = f2fs_get_context,
+ .set_context = f2fs_set_context,
+ .dummy_context = f2fs_dummy_context,
+ .empty_dir = f2fs_empty_dir,
+ .max_namelen = F2FS_NAME_LEN,
+ .has_stable_inodes = f2fs_has_stable_inodes,
+ .get_ino_and_lblk_bits = f2fs_get_ino_and_lblk_bits,
};
#endif
@@ -2604,6 +2626,21 @@ static int sanity_check_raw_super(struct f2fs_sb_info *sbi,
return -EFSCORRUPTED;
}
+ if (RDEV(0).path[0]) {
+ block_t dev_seg_count = le32_to_cpu(RDEV(0).total_segments);
+ int i = 1;
+
+ while (i < MAX_DEVICES && RDEV(i).path[0]) {
+ dev_seg_count += le32_to_cpu(RDEV(i).total_segments);
+ i++;
+ }
+ if (segment_count != dev_seg_count) {
+ f2fs_info(sbi, "Segment count (%u) mismatch with total segments from devices (%u)",
+ segment_count, dev_seg_count);
+ return -EFSCORRUPTED;
+ }
+ }
+
if (secs_per_zone > total_sections || !secs_per_zone) {
f2fs_info(sbi, "Wrong secs_per_zone / total_sections (%u, %u)",
secs_per_zone, total_sections);
@@ -2838,6 +2875,7 @@ static void init_sb_info(struct f2fs_sb_info *sbi)
spin_lock_init(&sbi->dev_lock);
init_rwsem(&sbi->sb_lock);
+ init_rwsem(&sbi->pin_sem);
}
static int init_percpu_info(struct f2fs_sb_info *sbi)
@@ -2857,15 +2895,21 @@ static int init_percpu_info(struct f2fs_sb_info *sbi)
}
#ifdef CONFIG_BLK_DEV_ZONED
+static int f2fs_report_zone_cb(struct blk_zone *zone, unsigned int idx,
+ void *data)
+{
+ struct f2fs_dev_info *dev = data;
+
+ if (zone->type != BLK_ZONE_TYPE_CONVENTIONAL)
+ set_bit(idx, dev->blkz_seq);
+ return 0;
+}
+
static int init_blkz_info(struct f2fs_sb_info *sbi, int devi)
{
struct block_device *bdev = FDEV(devi).bdev;
sector_t nr_sectors = bdev->bd_part->nr_sects;
- sector_t sector = 0;
- struct blk_zone *zones;
- unsigned int i, nr_zones;
- unsigned int n = 0;
- int err = -EIO;
+ int ret;
if (!f2fs_sb_has_blkzoned(sbi))
return 0;
@@ -2890,38 +2934,13 @@ static int init_blkz_info(struct f2fs_sb_info *sbi, int devi)
if (!FDEV(devi).blkz_seq)
return -ENOMEM;
-#define F2FS_REPORT_NR_ZONES 4096
-
- zones = f2fs_kzalloc(sbi,
- array_size(F2FS_REPORT_NR_ZONES,
- sizeof(struct blk_zone)),
- GFP_KERNEL);
- if (!zones)
- return -ENOMEM;
-
/* Get block zones type */
- while (zones && sector < nr_sectors) {
-
- nr_zones = F2FS_REPORT_NR_ZONES;
- err = blkdev_report_zones(bdev, sector, zones, &nr_zones);
- if (err)
- break;
- if (!nr_zones) {
- err = -EIO;
- break;
- }
-
- for (i = 0; i < nr_zones; i++) {
- if (zones[i].type != BLK_ZONE_TYPE_CONVENTIONAL)
- set_bit(n, FDEV(devi).blkz_seq);
- sector += zones[i].len;
- n++;
- }
- }
-
- kvfree(zones);
+ ret = blkdev_report_zones(bdev, 0, BLK_ALL_ZONES, f2fs_report_zone_cb,
+ &FDEV(devi));
+ if (ret < 0)
+ return ret;
- return err;
+ return 0;
}
#endif
@@ -2951,6 +2970,7 @@ static int read_raw_super_block(struct f2fs_sb_info *sbi,
f2fs_err(sbi, "Unable to read %dth superblock",
block + 1);
err = -EIO;
+ *recovery = 1;
continue;
}
@@ -2960,6 +2980,7 @@ static int read_raw_super_block(struct f2fs_sb_info *sbi,
f2fs_err(sbi, "Can't find valid F2FS filesystem in %dth superblock",
block + 1);
brelse(bh);
+ *recovery = 1;
continue;
}
@@ -2972,10 +2993,6 @@ static int read_raw_super_block(struct f2fs_sb_info *sbi,
brelse(bh);
}
- /* Fail to read any one of the superblocks*/
- if (err < 0)
- *recovery = 1;
-
/* No valid superblock */
if (!*raw_super)
kvfree(super);
@@ -3329,6 +3346,8 @@ try_onemore:
sbi->write_io[i][j].bio = NULL;
spin_lock_init(&sbi->write_io[i][j].io_lock);
INIT_LIST_HEAD(&sbi->write_io[i][j].io_list);
+ INIT_LIST_HEAD(&sbi->write_io[i][j].bio_list);
+ init_rwsem(&sbi->write_io[i][j].bio_list_lock);
}
}
@@ -3740,8 +3759,13 @@ static int __init init_f2fs_fs(void)
err = f2fs_init_post_read_processing();
if (err)
goto free_root_stats;
+ err = f2fs_init_bio_entry_cache();
+ if (err)
+ goto free_post_read;
return 0;
+free_post_read:
+ f2fs_destroy_post_read_processing();
free_root_stats:
f2fs_destroy_root_stats();
unregister_filesystem(&f2fs_fs_type);
@@ -3765,6 +3789,7 @@ fail:
static void __exit exit_f2fs_fs(void)
{
+ f2fs_destroy_bio_entry_cache();
f2fs_destroy_post_read_processing();
f2fs_destroy_root_stats();
unregister_filesystem(&f2fs_fs_type);
diff --git a/fs/f2fs/sysfs.c b/fs/f2fs/sysfs.c
index b558b64a4c9c..70945ceb9c0c 100644
--- a/fs/f2fs/sysfs.c
+++ b/fs/f2fs/sysfs.c
@@ -154,6 +154,8 @@ static ssize_t features_show(struct f2fs_attr *a,
if (f2fs_sb_has_casefold(sbi))
len += snprintf(buf + len, PAGE_SIZE - len, "%s%s",
len ? ", " : "", "casefold");
+ len += snprintf(buf + len, PAGE_SIZE - len, "%s%s",
+ len ? ", " : "", "pin_file");
len += snprintf(buf + len, PAGE_SIZE - len, "\n");
return len;
}
@@ -443,6 +445,7 @@ F2FS_RW_ATTR(GC_THREAD, f2fs_gc_kthread, gc_no_gc_sleep_time, no_gc_sleep_time);
F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, gc_idle, gc_mode);
F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, gc_urgent, gc_mode);
F2FS_RW_ATTR(SM_INFO, f2fs_sm_info, reclaim_segments, rec_prefree_segments);
+F2FS_RW_ATTR(SM_INFO, f2fs_sm_info, main_blkaddr, main_blkaddr);
F2FS_RW_ATTR(DCC_INFO, discard_cmd_control, max_small_discards, max_discards);
F2FS_RW_ATTR(DCC_INFO, discard_cmd_control, discard_granularity, discard_granularity);
F2FS_RW_ATTR(RESERVED_BLOCKS, f2fs_sb_info, reserved_blocks, reserved_blocks);
@@ -510,6 +513,7 @@ static struct attribute *f2fs_attrs[] = {
ATTR_LIST(gc_idle),
ATTR_LIST(gc_urgent),
ATTR_LIST(reclaim_segments),
+ ATTR_LIST(main_blkaddr),
ATTR_LIST(max_small_discards),
ATTR_LIST(discard_granularity),
ATTR_LIST(batched_trim_sections),
diff --git a/fs/f2fs/xattr.c b/fs/f2fs/xattr.c
index 181900af2576..296b3189448a 100644
--- a/fs/f2fs/xattr.c
+++ b/fs/f2fs/xattr.c
@@ -539,8 +539,9 @@ out:
ssize_t f2fs_listxattr(struct dentry *dentry, char *buffer, size_t buffer_size)
{
struct inode *inode = d_inode(dentry);
+ nid_t xnid = F2FS_I(inode)->i_xattr_nid;
struct f2fs_xattr_entry *entry;
- void *base_addr;
+ void *base_addr, *last_base_addr;
int error = 0;
size_t rest = buffer_size;
@@ -550,6 +551,8 @@ ssize_t f2fs_listxattr(struct dentry *dentry, char *buffer, size_t buffer_size)
if (error)
return error;
+ last_base_addr = (void *)base_addr + XATTR_SIZE(xnid, inode);
+
list_for_each_xattr(entry, base_addr) {
const struct xattr_handler *handler =
f2fs_xattr_handler(entry->e_name_index);
@@ -557,6 +560,15 @@ ssize_t f2fs_listxattr(struct dentry *dentry, char *buffer, size_t buffer_size)
size_t prefix_len;
size_t size;
+ if ((void *)(entry) + sizeof(__u32) > last_base_addr ||
+ (void *)XATTR_NEXT_ENTRY(entry) > last_base_addr) {
+ f2fs_err(F2FS_I_SB(inode), "inode (%lu) has corrupted xattr",
+ inode->i_ino);
+ set_sbi_flag(F2FS_I_SB(inode), SBI_NEED_FSCK);
+ error = -EFSCORRUPTED;
+ goto cleanup;
+ }
+
if (!handler || (handler->list && !handler->list(dentry)))
continue;
diff --git a/fs/fat/file.c b/fs/fat/file.c
index 4614c0ba5f1c..bdc4503c00a3 100644
--- a/fs/fat/file.c
+++ b/fs/fat/file.c
@@ -172,15 +172,6 @@ long fat_generic_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
}
}
-#ifdef CONFIG_COMPAT
-static long fat_generic_compat_ioctl(struct file *filp, unsigned int cmd,
- unsigned long arg)
-
-{
- return fat_generic_ioctl(filp, cmd, (unsigned long)compat_ptr(arg));
-}
-#endif
-
static int fat_file_release(struct inode *inode, struct file *filp)
{
if ((filp->f_mode & FMODE_WRITE) &&
@@ -215,9 +206,7 @@ const struct file_operations fat_file_operations = {
.mmap = generic_file_mmap,
.release = fat_file_release,
.unlocked_ioctl = fat_generic_ioctl,
-#ifdef CONFIG_COMPAT
- .compat_ioctl = fat_generic_compat_ioctl,
-#endif
+ .compat_ioctl = compat_ptr_ioctl,
.fsync = fat_file_fsync,
.splice_read = generic_file_splice_read,
.splice_write = iter_file_splice_write,
diff --git a/fs/fcntl.c b/fs/fcntl.c
index 3d40771e8e7c..41b6438bd2d9 100644
--- a/fs/fcntl.c
+++ b/fs/fcntl.c
@@ -261,7 +261,7 @@ static int f_getowner_uids(struct file *filp, unsigned long arg)
static bool rw_hint_valid(enum rw_hint hint)
{
switch (hint) {
- case RWF_WRITE_LIFE_NOT_SET:
+ case RWH_WRITE_LIFE_NOT_SET:
case RWH_WRITE_LIFE_NONE:
case RWH_WRITE_LIFE_SHORT:
case RWH_WRITE_LIFE_MEDIUM:
diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index e88421d9a48d..335607b8c5c0 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -576,10 +576,13 @@ void wbc_attach_and_unlock_inode(struct writeback_control *wbc,
spin_unlock(&inode->i_lock);
/*
- * A dying wb indicates that the memcg-blkcg mapping has changed
- * and a new wb is already serving the memcg. Switch immediately.
+ * A dying wb indicates that either the blkcg associated with the
+ * memcg changed or the associated memcg is dying. In the first
+ * case, a replacement wb should already be available and we should
+ * refresh the wb immediately. In the second case, trying to
+ * refresh will keep failing.
*/
- if (unlikely(wb_dying(wbc->wb)))
+ if (unlikely(wb_dying(wbc->wb) && !css_is_dying(wbc->wb->memcg_css)))
inode_switch_wbs(inode, wbc->wb_id);
}
EXPORT_SYMBOL_GPL(wbc_attach_and_unlock_inode);
@@ -905,7 +908,7 @@ restart:
* cgroup_writeback_by_id - initiate cgroup writeback from bdi and memcg IDs
* @bdi_id: target bdi id
* @memcg_id: target memcg css id
- * @nr_pages: number of pages to write, 0 for best-effort dirty flushing
+ * @nr: number of pages to write, 0 for best-effort dirty flushing
* @reason: reason why some writeback work initiated
* @done: target wb_completion
*
diff --git a/fs/fuse/Kconfig b/fs/fuse/Kconfig
index 0635cba19971..eb2a585572dc 100644
--- a/fs/fuse/Kconfig
+++ b/fs/fuse/Kconfig
@@ -34,7 +34,7 @@ config VIRTIO_FS
select VIRTIO
help
The Virtio Filesystem allows guests to mount file systems from the
- host.
+ host.
If you want to share files between guests or with the host, answer Y
- or M.
+ or M.
diff --git a/fs/fuse/Makefile b/fs/fuse/Makefile
index 6419a2b3510d..3e8cebfb59b7 100644
--- a/fs/fuse/Makefile
+++ b/fs/fuse/Makefile
@@ -5,6 +5,7 @@
obj-$(CONFIG_FUSE_FS) += fuse.o
obj-$(CONFIG_CUSE) += cuse.o
-obj-$(CONFIG_VIRTIO_FS) += virtio_fs.o
+obj-$(CONFIG_VIRTIO_FS) += virtiofs.o
fuse-objs := dev.o dir.o file.o inode.o control.o xattr.o acl.o readdir.o
+virtiofs-y += virtio_fs.o
diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c
index dadd617d826c..8e02d76fe104 100644
--- a/fs/fuse/dev.c
+++ b/fs/fuse/dev.c
@@ -276,10 +276,12 @@ static void flush_bg_queue(struct fuse_conn *fc)
void fuse_request_end(struct fuse_conn *fc, struct fuse_req *req)
{
struct fuse_iqueue *fiq = &fc->iq;
- bool async = req->args->end;
+ bool async;
if (test_and_set_bit(FR_FINISHED, &req->flags))
goto put_request;
+
+ async = req->args->end;
/*
* test_and_set_bit() implies smp_mb() between bit
* changing and below intr_entry check. Pairs with
@@ -703,7 +705,7 @@ static int fuse_copy_fill(struct fuse_copy_state *cs)
cs->pipebufs++;
cs->nr_segs--;
} else {
- if (cs->nr_segs == cs->pipe->buffers)
+ if (cs->nr_segs >= cs->pipe->max_usage)
return -EIO;
page = alloc_page(GFP_HIGHUSER);
@@ -879,7 +881,7 @@ static int fuse_ref_page(struct fuse_copy_state *cs, struct page *page,
struct pipe_buffer *buf;
int err;
- if (cs->nr_segs == cs->pipe->buffers)
+ if (cs->nr_segs >= cs->pipe->max_usage)
return -EIO;
err = unlock_request(cs->req);
@@ -1341,7 +1343,7 @@ static ssize_t fuse_dev_splice_read(struct file *in, loff_t *ppos,
if (!fud)
return -EPERM;
- bufs = kvmalloc_array(pipe->buffers, sizeof(struct pipe_buffer),
+ bufs = kvmalloc_array(pipe->max_usage, sizeof(struct pipe_buffer),
GFP_KERNEL);
if (!bufs)
return -ENOMEM;
@@ -1353,7 +1355,7 @@ static ssize_t fuse_dev_splice_read(struct file *in, loff_t *ppos,
if (ret < 0)
goto out;
- if (pipe->nrbufs + cs.nr_segs > pipe->buffers) {
+ if (pipe_occupancy(pipe->head, pipe->tail) + cs.nr_segs > pipe->max_usage) {
ret = -EIO;
goto out;
}
@@ -1935,6 +1937,7 @@ static ssize_t fuse_dev_splice_write(struct pipe_inode_info *pipe,
struct file *out, loff_t *ppos,
size_t len, unsigned int flags)
{
+ unsigned int head, tail, mask, count;
unsigned nbuf;
unsigned idx;
struct pipe_buffer *bufs;
@@ -1949,8 +1952,12 @@ static ssize_t fuse_dev_splice_write(struct pipe_inode_info *pipe,
pipe_lock(pipe);
- bufs = kvmalloc_array(pipe->nrbufs, sizeof(struct pipe_buffer),
- GFP_KERNEL);
+ head = pipe->head;
+ tail = pipe->tail;
+ mask = pipe->ring_size - 1;
+ count = head - tail;
+
+ bufs = kvmalloc_array(count, sizeof(struct pipe_buffer), GFP_KERNEL);
if (!bufs) {
pipe_unlock(pipe);
return -ENOMEM;
@@ -1958,8 +1965,8 @@ static ssize_t fuse_dev_splice_write(struct pipe_inode_info *pipe,
nbuf = 0;
rem = 0;
- for (idx = 0; idx < pipe->nrbufs && rem < len; idx++)
- rem += pipe->bufs[(pipe->curbuf + idx) & (pipe->buffers - 1)].len;
+ for (idx = tail; idx != head && rem < len; idx++)
+ rem += pipe->bufs[idx & mask].len;
ret = -EINVAL;
if (rem < len)
@@ -1970,16 +1977,16 @@ static ssize_t fuse_dev_splice_write(struct pipe_inode_info *pipe,
struct pipe_buffer *ibuf;
struct pipe_buffer *obuf;
- BUG_ON(nbuf >= pipe->buffers);
- BUG_ON(!pipe->nrbufs);
- ibuf = &pipe->bufs[pipe->curbuf];
+ BUG_ON(nbuf >= pipe->ring_size);
+ BUG_ON(tail == head);
+ ibuf = &pipe->bufs[tail & mask];
obuf = &bufs[nbuf];
if (rem >= ibuf->len) {
*obuf = *ibuf;
ibuf->ops = NULL;
- pipe->curbuf = (pipe->curbuf + 1) & (pipe->buffers - 1);
- pipe->nrbufs--;
+ tail++;
+ pipe->tail = tail;
} else {
if (!pipe_buf_get(pipe, ibuf))
goto out_free;
@@ -2260,7 +2267,7 @@ const struct file_operations fuse_dev_operations = {
.release = fuse_dev_release,
.fasync = fuse_dev_fasync,
.unlocked_ioctl = fuse_dev_ioctl,
- .compat_ioctl = fuse_dev_ioctl,
+ .compat_ioctl = compat_ptr_ioctl,
};
EXPORT_SYMBOL_GPL(fuse_dev_operations);
diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c
index d572c900bb0f..ee190119f45c 100644
--- a/fs/fuse/dir.c
+++ b/fs/fuse/dir.c
@@ -248,7 +248,8 @@ static int fuse_dentry_revalidate(struct dentry *entry, unsigned int flags)
kfree(forget);
if (ret == -ENOMEM)
goto out;
- if (ret || (outarg.attr.mode ^ inode->i_mode) & S_IFMT)
+ if (ret || fuse_invalid_attr(&outarg.attr) ||
+ (outarg.attr.mode ^ inode->i_mode) & S_IFMT)
goto invalid;
forget_all_cached_acls(inode);
@@ -319,6 +320,12 @@ int fuse_valid_type(int m)
S_ISBLK(m) || S_ISFIFO(m) || S_ISSOCK(m);
}
+bool fuse_invalid_attr(struct fuse_attr *attr)
+{
+ return !fuse_valid_type(attr->mode) ||
+ attr->size > LLONG_MAX;
+}
+
int fuse_lookup_name(struct super_block *sb, u64 nodeid, const struct qstr *name,
struct fuse_entry_out *outarg, struct inode **inode)
{
@@ -350,7 +357,7 @@ int fuse_lookup_name(struct super_block *sb, u64 nodeid, const struct qstr *name
err = -EIO;
if (!outarg->nodeid)
goto out_put_forget;
- if (!fuse_valid_type(outarg->attr.mode))
+ if (fuse_invalid_attr(&outarg->attr))
goto out_put_forget;
*inode = fuse_iget(sb, outarg->nodeid, outarg->generation,
@@ -405,7 +412,8 @@ static struct dentry *fuse_lookup(struct inode *dir, struct dentry *entry,
else
fuse_invalidate_entry_cache(entry);
- fuse_advise_use_readdirplus(dir);
+ if (inode)
+ fuse_advise_use_readdirplus(dir);
return newent;
out_iput:
@@ -474,7 +482,8 @@ static int fuse_create_open(struct inode *dir, struct dentry *entry,
goto out_free_ff;
err = -EIO;
- if (!S_ISREG(outentry.attr.mode) || invalid_nodeid(outentry.nodeid))
+ if (!S_ISREG(outentry.attr.mode) || invalid_nodeid(outentry.nodeid) ||
+ fuse_invalid_attr(&outentry.attr))
goto out_free_ff;
ff->fh = outopen.fh;
@@ -582,7 +591,7 @@ static int create_new_entry(struct fuse_conn *fc, struct fuse_args *args,
goto out_put_forget_req;
err = -EIO;
- if (invalid_nodeid(outarg.nodeid))
+ if (invalid_nodeid(outarg.nodeid) || fuse_invalid_attr(&outarg.attr))
goto out_put_forget_req;
if ((outarg.attr.mode ^ mode) & S_IFMT)
@@ -861,7 +870,8 @@ static int fuse_link(struct dentry *entry, struct inode *newdir,
spin_lock(&fi->lock);
fi->attr_version = atomic64_inc_return(&fc->attr_version);
- inc_nlink(inode);
+ if (likely(inode->i_nlink < UINT_MAX))
+ inc_nlink(inode);
spin_unlock(&fi->lock);
fuse_invalidate_attr(inode);
fuse_update_ctime(inode);
@@ -941,7 +951,8 @@ static int fuse_do_getattr(struct inode *inode, struct kstat *stat,
args.out_args[0].value = &outarg;
err = fuse_simple_request(fc, &args);
if (!err) {
- if ((inode->i_mode ^ outarg.attr.mode) & S_IFMT) {
+ if (fuse_invalid_attr(&outarg.attr) ||
+ (inode->i_mode ^ outarg.attr.mode) & S_IFMT) {
make_bad_inode(inode);
err = -EIO;
} else {
@@ -1521,6 +1532,19 @@ int fuse_do_setattr(struct dentry *dentry, struct iattr *attr,
is_truncate = true;
}
+ /* Flush dirty data/metadata before non-truncate SETATTR */
+ if (is_wb && S_ISREG(inode->i_mode) &&
+ attr->ia_valid &
+ (ATTR_MODE | ATTR_UID | ATTR_GID | ATTR_MTIME_SET |
+ ATTR_TIMES_SET)) {
+ err = write_inode_now(inode, true);
+ if (err)
+ return err;
+
+ fuse_set_nowrite(inode);
+ fuse_release_nowrite(inode);
+ }
+
if (is_truncate) {
fuse_set_nowrite(inode);
set_bit(FUSE_I_SIZE_UNSTABLE, &fi->state);
@@ -1549,7 +1573,8 @@ int fuse_do_setattr(struct dentry *dentry, struct iattr *attr,
goto error;
}
- if ((inode->i_mode ^ outarg.attr.mode) & S_IFMT) {
+ if (fuse_invalid_attr(&outarg.attr) ||
+ (inode->i_mode ^ outarg.attr.mode) & S_IFMT) {
make_bad_inode(inode);
err = -EIO;
goto error;
diff --git a/fs/fuse/file.c b/fs/fuse/file.c
index 0f0225686aee..a63d779eac10 100644
--- a/fs/fuse/file.c
+++ b/fs/fuse/file.c
@@ -217,7 +217,7 @@ int fuse_open_common(struct inode *inode, struct file *file, bool isdir)
{
struct fuse_conn *fc = get_fuse_conn(inode);
int err;
- bool lock_inode = (file->f_flags & O_TRUNC) &&
+ bool is_wb_truncate = (file->f_flags & O_TRUNC) &&
fc->atomic_o_trunc &&
fc->writeback_cache;
@@ -225,16 +225,20 @@ int fuse_open_common(struct inode *inode, struct file *file, bool isdir)
if (err)
return err;
- if (lock_inode)
+ if (is_wb_truncate) {
inode_lock(inode);
+ fuse_set_nowrite(inode);
+ }
err = fuse_do_open(fc, get_node_id(inode), file, isdir);
if (!err)
fuse_finish_open(inode, file);
- if (lock_inode)
+ if (is_wb_truncate) {
+ fuse_release_nowrite(inode);
inode_unlock(inode);
+ }
return err;
}
@@ -709,8 +713,10 @@ static ssize_t fuse_async_req_send(struct fuse_conn *fc,
ia->ap.args.end = fuse_aio_complete_req;
err = fuse_simple_background(fc, &ia->ap.args, GFP_KERNEL);
+ if (err)
+ fuse_aio_complete_req(fc, &ia->ap.args, err);
- return err ?: num_bytes;
+ return num_bytes;
}
static ssize_t fuse_send_read(struct fuse_io_args *ia, loff_t pos, size_t count,
@@ -1092,6 +1098,8 @@ static ssize_t fuse_send_write_pages(struct fuse_io_args *ia,
ia->write.in.flags = fuse_write_flags(iocb);
err = fuse_simple_request(fc, &ap->args);
+ if (!err && ia->write.out.size > count)
+ err = -EIO;
offset = ap->descs[0].offset;
count = ia->write.out.size;
@@ -1997,7 +2005,7 @@ static int fuse_writepages_fill(struct page *page,
if (!data->ff) {
err = -EIO;
- data->ff = fuse_write_file_get(fc, get_fuse_inode(inode));
+ data->ff = fuse_write_file_get(fc, fi);
if (!data->ff)
goto out_unlock;
}
@@ -2042,8 +2050,6 @@ static int fuse_writepages_fill(struct page *page,
* under writeback, so we can release the page lock.
*/
if (data->wpa == NULL) {
- struct fuse_inode *fi = get_fuse_inode(inode);
-
err = -ENOMEM;
wpa = fuse_writepage_args_alloc();
if (!wpa) {
diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h
index 956aeaf961ae..aa75e2305b75 100644
--- a/fs/fuse/fuse_i.h
+++ b/fs/fuse/fuse_i.h
@@ -479,6 +479,7 @@ struct fuse_fs_context {
bool destroy:1;
bool no_control:1;
bool no_force_umount:1;
+ bool no_mount_options:1;
unsigned int max_read;
unsigned int blksize;
const char *subtype;
@@ -713,6 +714,9 @@ struct fuse_conn {
/** Do not allow MNT_FORCE umount */
unsigned int no_force_umount:1;
+ /* Do not show mount options */
+ unsigned int no_mount_options:1;
+
/** The number of requests waiting for completion */
atomic_t num_waiting;
@@ -985,6 +989,8 @@ void fuse_ctl_remove_conn(struct fuse_conn *fc);
*/
int fuse_valid_type(int m);
+bool fuse_invalid_attr(struct fuse_attr *attr);
+
/**
* Is current process allowed to perform filesystem operation?
*/
diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c
index e040e2a2b621..16aec32f7f3d 100644
--- a/fs/fuse/inode.c
+++ b/fs/fuse/inode.c
@@ -558,6 +558,9 @@ static int fuse_show_options(struct seq_file *m, struct dentry *root)
struct super_block *sb = root->d_sb;
struct fuse_conn *fc = get_fuse_conn_super(sb);
+ if (fc->no_mount_options)
+ return 0;
+
seq_printf(m, ",user_id=%u", from_kuid_munged(fc->user_ns, fc->user_id));
seq_printf(m, ",group_id=%u", from_kgid_munged(fc->user_ns, fc->group_id));
if (fc->default_permissions)
@@ -1180,6 +1183,7 @@ int fuse_fill_super_common(struct super_block *sb, struct fuse_fs_context *ctx)
fc->destroy = ctx->destroy;
fc->no_control = ctx->no_control;
fc->no_force_umount = ctx->no_force_umount;
+ fc->no_mount_options = ctx->no_mount_options;
err = -ENOMEM;
root = fuse_get_root_inode(sb, ctx->rootmode);
diff --git a/fs/fuse/readdir.c b/fs/fuse/readdir.c
index 5c38b9d84c6e..6a40f75a0d25 100644
--- a/fs/fuse/readdir.c
+++ b/fs/fuse/readdir.c
@@ -184,7 +184,7 @@ static int fuse_direntplus_link(struct file *file,
if (invalid_nodeid(o->nodeid))
return -EIO;
- if (!fuse_valid_type(o->attr.mode))
+ if (fuse_invalid_attr(&o->attr))
return -EIO;
fc = get_fuse_conn(dir);
diff --git a/fs/fuse/virtio_fs.c b/fs/fuse/virtio_fs.c
index 6af3f131e468..bade74768903 100644
--- a/fs/fuse/virtio_fs.c
+++ b/fs/fuse/virtio_fs.c
@@ -30,10 +30,12 @@ struct virtio_fs_vq {
struct virtqueue *vq; /* protected by ->lock */
struct work_struct done_work;
struct list_head queued_reqs;
+ struct list_head end_reqs; /* End these requests */
struct delayed_work dispatch_work;
struct fuse_dev *fud;
bool connected;
long in_flight;
+ struct completion in_flight_zero; /* No inflight requests */
char name[24];
} ____cacheline_aligned_in_smp;
@@ -47,13 +49,20 @@ struct virtio_fs {
unsigned int num_request_queues; /* number of request queues */
};
-struct virtio_fs_forget {
+struct virtio_fs_forget_req {
struct fuse_in_header ih;
struct fuse_forget_in arg;
+};
+
+struct virtio_fs_forget {
/* This request can be temporarily queued on virt queue */
struct list_head list;
+ struct virtio_fs_forget_req req;
};
+static int virtio_fs_enqueue_req(struct virtio_fs_vq *fsvq,
+ struct fuse_req *req, bool in_flight);
+
static inline struct virtio_fs_vq *vq_to_fsvq(struct virtqueue *vq)
{
struct virtio_fs *fs = vq->vdev->priv;
@@ -66,6 +75,21 @@ static inline struct fuse_pqueue *vq_to_fpq(struct virtqueue *vq)
return &vq_to_fsvq(vq)->fud->pq;
}
+/* Should be called with fsvq->lock held. */
+static inline void inc_in_flight_req(struct virtio_fs_vq *fsvq)
+{
+ fsvq->in_flight++;
+}
+
+/* Should be called with fsvq->lock held. */
+static inline void dec_in_flight_req(struct virtio_fs_vq *fsvq)
+{
+ WARN_ON(fsvq->in_flight <= 0);
+ fsvq->in_flight--;
+ if (!fsvq->in_flight)
+ complete(&fsvq->in_flight_zero);
+}
+
static void release_virtio_fs_obj(struct kref *ref)
{
struct virtio_fs *vfs = container_of(ref, struct virtio_fs, refcount);
@@ -94,51 +118,46 @@ static void virtio_fs_drain_queue(struct virtio_fs_vq *fsvq)
WARN_ON(fsvq->in_flight < 0);
/* Wait for in flight requests to finish.*/
- while (1) {
- spin_lock(&fsvq->lock);
- if (!fsvq->in_flight) {
- spin_unlock(&fsvq->lock);
- break;
- }
+ spin_lock(&fsvq->lock);
+ if (fsvq->in_flight) {
+ /* We are holding virtio_fs_mutex. There should not be any
+ * waiters waiting for completion.
+ */
+ reinit_completion(&fsvq->in_flight_zero);
+ spin_unlock(&fsvq->lock);
+ wait_for_completion(&fsvq->in_flight_zero);
+ } else {
spin_unlock(&fsvq->lock);
- /* TODO use completion instead of timeout */
- usleep_range(1000, 2000);
}
flush_work(&fsvq->done_work);
flush_delayed_work(&fsvq->dispatch_work);
}
-static inline void drain_hiprio_queued_reqs(struct virtio_fs_vq *fsvq)
-{
- struct virtio_fs_forget *forget;
-
- spin_lock(&fsvq->lock);
- while (1) {
- forget = list_first_entry_or_null(&fsvq->queued_reqs,
- struct virtio_fs_forget, list);
- if (!forget)
- break;
- list_del(&forget->list);
- kfree(forget);
- }
- spin_unlock(&fsvq->lock);
-}
-
-static void virtio_fs_drain_all_queues(struct virtio_fs *fs)
+static void virtio_fs_drain_all_queues_locked(struct virtio_fs *fs)
{
struct virtio_fs_vq *fsvq;
int i;
for (i = 0; i < fs->nvqs; i++) {
fsvq = &fs->vqs[i];
- if (i == VQ_HIPRIO)
- drain_hiprio_queued_reqs(fsvq);
-
virtio_fs_drain_queue(fsvq);
}
}
+static void virtio_fs_drain_all_queues(struct virtio_fs *fs)
+{
+ /* Provides mutual exclusion between ->remove and ->kill_sb
+ * paths. We don't want both of these draining queue at the
+ * same time. Current completion logic reinits completion
+ * and that means there should not be any other thread
+ * doing reinit or waiting for completion already.
+ */
+ mutex_lock(&virtio_fs_mutex);
+ virtio_fs_drain_all_queues_locked(fs);
+ mutex_unlock(&virtio_fs_mutex);
+}
+
static void virtio_fs_start_all_queues(struct virtio_fs *fs)
{
struct virtio_fs_vq *fsvq;
@@ -253,74 +272,148 @@ static void virtio_fs_hiprio_done_work(struct work_struct *work)
while ((req = virtqueue_get_buf(vq, &len)) != NULL) {
kfree(req);
- fsvq->in_flight--;
+ dec_in_flight_req(fsvq);
}
} while (!virtqueue_enable_cb(vq) && likely(!virtqueue_is_broken(vq)));
spin_unlock(&fsvq->lock);
}
-static void virtio_fs_dummy_dispatch_work(struct work_struct *work)
+static void virtio_fs_request_dispatch_work(struct work_struct *work)
{
-}
-
-static void virtio_fs_hiprio_dispatch_work(struct work_struct *work)
-{
- struct virtio_fs_forget *forget;
+ struct fuse_req *req;
struct virtio_fs_vq *fsvq = container_of(work, struct virtio_fs_vq,
dispatch_work.work);
- struct virtqueue *vq = fsvq->vq;
- struct scatterlist sg;
- struct scatterlist *sgs[] = {&sg};
- bool notify;
+ struct fuse_conn *fc = fsvq->fud->fc;
int ret;
pr_debug("virtio-fs: worker %s called.\n", __func__);
while (1) {
spin_lock(&fsvq->lock);
- forget = list_first_entry_or_null(&fsvq->queued_reqs,
- struct virtio_fs_forget, list);
- if (!forget) {
+ req = list_first_entry_or_null(&fsvq->end_reqs, struct fuse_req,
+ list);
+ if (!req) {
spin_unlock(&fsvq->lock);
- return;
+ break;
}
- list_del(&forget->list);
- if (!fsvq->connected) {
+ list_del_init(&req->list);
+ spin_unlock(&fsvq->lock);
+ fuse_request_end(fc, req);
+ }
+
+ /* Dispatch pending requests */
+ while (1) {
+ spin_lock(&fsvq->lock);
+ req = list_first_entry_or_null(&fsvq->queued_reqs,
+ struct fuse_req, list);
+ if (!req) {
spin_unlock(&fsvq->lock);
- kfree(forget);
- continue;
+ return;
}
+ list_del_init(&req->list);
+ spin_unlock(&fsvq->lock);
- sg_init_one(&sg, forget, sizeof(*forget));
-
- /* Enqueue the request */
- dev_dbg(&vq->vdev->dev, "%s\n", __func__);
- ret = virtqueue_add_sgs(vq, sgs, 1, 0, forget, GFP_ATOMIC);
+ ret = virtio_fs_enqueue_req(fsvq, req, true);
if (ret < 0) {
if (ret == -ENOMEM || ret == -ENOSPC) {
- pr_debug("virtio-fs: Could not queue FORGET: err=%d. Will try later\n",
- ret);
- list_add_tail(&forget->list,
- &fsvq->queued_reqs);
+ spin_lock(&fsvq->lock);
+ list_add_tail(&req->list, &fsvq->queued_reqs);
schedule_delayed_work(&fsvq->dispatch_work,
- msecs_to_jiffies(1));
- } else {
- pr_debug("virtio-fs: Could not queue FORGET: err=%d. Dropping it.\n",
- ret);
- kfree(forget);
+ msecs_to_jiffies(1));
+ spin_unlock(&fsvq->lock);
+ return;
}
+ req->out.h.error = ret;
+ spin_lock(&fsvq->lock);
+ dec_in_flight_req(fsvq);
+ spin_unlock(&fsvq->lock);
+ pr_err("virtio-fs: virtio_fs_enqueue_req() failed %d\n",
+ ret);
+ fuse_request_end(fc, req);
+ }
+ }
+}
+
+/*
+ * Returns 1 if queue is full and sender should wait a bit before sending
+ * next request, 0 otherwise.
+ */
+static int send_forget_request(struct virtio_fs_vq *fsvq,
+ struct virtio_fs_forget *forget,
+ bool in_flight)
+{
+ struct scatterlist sg;
+ struct virtqueue *vq;
+ int ret = 0;
+ bool notify;
+ struct virtio_fs_forget_req *req = &forget->req;
+
+ spin_lock(&fsvq->lock);
+ if (!fsvq->connected) {
+ if (in_flight)
+ dec_in_flight_req(fsvq);
+ kfree(forget);
+ goto out;
+ }
+
+ sg_init_one(&sg, req, sizeof(*req));
+ vq = fsvq->vq;
+ dev_dbg(&vq->vdev->dev, "%s\n", __func__);
+
+ ret = virtqueue_add_outbuf(vq, &sg, 1, forget, GFP_ATOMIC);
+ if (ret < 0) {
+ if (ret == -ENOMEM || ret == -ENOSPC) {
+ pr_debug("virtio-fs: Could not queue FORGET: err=%d. Will try later\n",
+ ret);
+ list_add_tail(&forget->list, &fsvq->queued_reqs);
+ schedule_delayed_work(&fsvq->dispatch_work,
+ msecs_to_jiffies(1));
+ if (!in_flight)
+ inc_in_flight_req(fsvq);
+ /* Queue is full */
+ ret = 1;
+ } else {
+ pr_debug("virtio-fs: Could not queue FORGET: err=%d. Dropping it.\n",
+ ret);
+ kfree(forget);
+ if (in_flight)
+ dec_in_flight_req(fsvq);
+ }
+ goto out;
+ }
+
+ if (!in_flight)
+ inc_in_flight_req(fsvq);
+ notify = virtqueue_kick_prepare(vq);
+ spin_unlock(&fsvq->lock);
+
+ if (notify)
+ virtqueue_notify(vq);
+ return ret;
+out:
+ spin_unlock(&fsvq->lock);
+ return ret;
+}
+
+static void virtio_fs_hiprio_dispatch_work(struct work_struct *work)
+{
+ struct virtio_fs_forget *forget;
+ struct virtio_fs_vq *fsvq = container_of(work, struct virtio_fs_vq,
+ dispatch_work.work);
+ pr_debug("virtio-fs: worker %s called.\n", __func__);
+ while (1) {
+ spin_lock(&fsvq->lock);
+ forget = list_first_entry_or_null(&fsvq->queued_reqs,
+ struct virtio_fs_forget, list);
+ if (!forget) {
spin_unlock(&fsvq->lock);
return;
}
- fsvq->in_flight++;
- notify = virtqueue_kick_prepare(vq);
+ list_del(&forget->list);
spin_unlock(&fsvq->lock);
-
- if (notify)
- virtqueue_notify(vq);
- pr_debug("virtio-fs: worker %s dispatched one forget request.\n",
- __func__);
+ if (send_forget_request(fsvq, forget, true))
+ return;
}
}
@@ -452,7 +545,7 @@ static void virtio_fs_requests_done_work(struct work_struct *work)
fuse_request_end(fc, req);
spin_lock(&fsvq->lock);
- fsvq->in_flight--;
+ dec_in_flight_req(fsvq);
spin_unlock(&fsvq->lock);
}
}
@@ -502,8 +595,10 @@ static int virtio_fs_setup_vqs(struct virtio_device *vdev,
names[VQ_HIPRIO] = fs->vqs[VQ_HIPRIO].name;
INIT_WORK(&fs->vqs[VQ_HIPRIO].done_work, virtio_fs_hiprio_done_work);
INIT_LIST_HEAD(&fs->vqs[VQ_HIPRIO].queued_reqs);
+ INIT_LIST_HEAD(&fs->vqs[VQ_HIPRIO].end_reqs);
INIT_DELAYED_WORK(&fs->vqs[VQ_HIPRIO].dispatch_work,
virtio_fs_hiprio_dispatch_work);
+ init_completion(&fs->vqs[VQ_HIPRIO].in_flight_zero);
spin_lock_init(&fs->vqs[VQ_HIPRIO].lock);
/* Initialize the requests virtqueues */
@@ -511,8 +606,10 @@ static int virtio_fs_setup_vqs(struct virtio_device *vdev,
spin_lock_init(&fs->vqs[i].lock);
INIT_WORK(&fs->vqs[i].done_work, virtio_fs_requests_done_work);
INIT_DELAYED_WORK(&fs->vqs[i].dispatch_work,
- virtio_fs_dummy_dispatch_work);
+ virtio_fs_request_dispatch_work);
INIT_LIST_HEAD(&fs->vqs[i].queued_reqs);
+ INIT_LIST_HEAD(&fs->vqs[i].end_reqs);
+ init_completion(&fs->vqs[i].in_flight_zero);
snprintf(fs->vqs[i].name, sizeof(fs->vqs[i].name),
"requests.%u", i - VQ_REQUEST);
callbacks[i] = virtio_fs_vq_done;
@@ -606,7 +703,7 @@ static void virtio_fs_remove(struct virtio_device *vdev)
/* This device is going away. No one should get new reference */
list_del_init(&fs->list);
virtio_fs_stop_all_queues(fs);
- virtio_fs_drain_all_queues(fs);
+ virtio_fs_drain_all_queues_locked(fs);
vdev->config->reset(vdev);
virtio_fs_cleanup_vqs(vdev, fs);
@@ -631,12 +728,12 @@ static int virtio_fs_restore(struct virtio_device *vdev)
}
#endif /* CONFIG_PM_SLEEP */
-const static struct virtio_device_id id_table[] = {
+static const struct virtio_device_id id_table[] = {
{ VIRTIO_ID_FS, VIRTIO_DEV_ANY_ID },
{},
};
-const static unsigned int feature_table[] = {};
+static const unsigned int feature_table[] = {};
static struct virtio_driver virtio_fs_driver = {
.driver.name = KBUILD_MODNAME,
@@ -657,14 +754,10 @@ __releases(fiq->lock)
{
struct fuse_forget_link *link;
struct virtio_fs_forget *forget;
- struct scatterlist sg;
- struct scatterlist *sgs[] = {&sg};
+ struct virtio_fs_forget_req *req;
struct virtio_fs *fs;
- struct virtqueue *vq;
struct virtio_fs_vq *fsvq;
- bool notify;
u64 unique;
- int ret;
link = fuse_dequeue_forget(fiq, 1, NULL);
unique = fuse_get_unique(fiq);
@@ -675,56 +768,19 @@ __releases(fiq->lock)
/* Allocate a buffer for the request */
forget = kmalloc(sizeof(*forget), GFP_NOFS | __GFP_NOFAIL);
+ req = &forget->req;
- forget->ih = (struct fuse_in_header){
+ req->ih = (struct fuse_in_header){
.opcode = FUSE_FORGET,
.nodeid = link->forget_one.nodeid,
.unique = unique,
- .len = sizeof(*forget),
+ .len = sizeof(*req),
};
- forget->arg = (struct fuse_forget_in){
+ req->arg = (struct fuse_forget_in){
.nlookup = link->forget_one.nlookup,
};
- sg_init_one(&sg, forget, sizeof(*forget));
-
- /* Enqueue the request */
- spin_lock(&fsvq->lock);
-
- if (!fsvq->connected) {
- kfree(forget);
- spin_unlock(&fsvq->lock);
- goto out;
- }
-
- vq = fsvq->vq;
- dev_dbg(&vq->vdev->dev, "%s\n", __func__);
-
- ret = virtqueue_add_sgs(vq, sgs, 1, 0, forget, GFP_ATOMIC);
- if (ret < 0) {
- if (ret == -ENOMEM || ret == -ENOSPC) {
- pr_debug("virtio-fs: Could not queue FORGET: err=%d. Will try later.\n",
- ret);
- list_add_tail(&forget->list, &fsvq->queued_reqs);
- schedule_delayed_work(&fsvq->dispatch_work,
- msecs_to_jiffies(1));
- } else {
- pr_debug("virtio-fs: Could not queue FORGET: err=%d. Dropping it.\n",
- ret);
- kfree(forget);
- }
- spin_unlock(&fsvq->lock);
- goto out;
- }
-
- fsvq->in_flight++;
- notify = virtqueue_kick_prepare(vq);
-
- spin_unlock(&fsvq->lock);
-
- if (notify)
- virtqueue_notify(vq);
-out:
+ send_forget_request(fsvq, forget, false);
kfree(link);
}
@@ -819,7 +875,7 @@ static unsigned int sg_init_fuse_args(struct scatterlist *sg,
/* Add a request to a virtqueue and kick the device */
static int virtio_fs_enqueue_req(struct virtio_fs_vq *fsvq,
- struct fuse_req *req)
+ struct fuse_req *req, bool in_flight)
{
/* requests need at least 4 elements */
struct scatterlist *stack_sgs[6];
@@ -835,6 +891,7 @@ static int virtio_fs_enqueue_req(struct virtio_fs_vq *fsvq,
unsigned int i;
int ret;
bool notify;
+ struct fuse_pqueue *fpq;
/* Does the sglist fit on the stack? */
total_sgs = sg_count_fuse_req(req);
@@ -889,7 +946,17 @@ static int virtio_fs_enqueue_req(struct virtio_fs_vq *fsvq,
goto out;
}
- fsvq->in_flight++;
+ /* Request successfully sent. */
+ fpq = &fsvq->fud->pq;
+ spin_lock(&fpq->lock);
+ list_add_tail(&req->list, fpq->processing);
+ spin_unlock(&fpq->lock);
+ set_bit(FR_SENT, &req->flags);
+ /* matches barrier in request_wait_answer() */
+ smp_mb__after_atomic();
+
+ if (!in_flight)
+ inc_in_flight_req(fsvq);
notify = virtqueue_kick_prepare(vq);
spin_unlock(&fsvq->lock);
@@ -915,9 +982,8 @@ __releases(fiq->lock)
{
unsigned int queue_id = VQ_REQUEST; /* TODO multiqueue */
struct virtio_fs *fs;
- struct fuse_conn *fc;
struct fuse_req *req;
- struct fuse_pqueue *fpq;
+ struct virtio_fs_vq *fsvq;
int ret;
WARN_ON(list_empty(&fiq->pending));
@@ -928,49 +994,41 @@ __releases(fiq->lock)
spin_unlock(&fiq->lock);
fs = fiq->priv;
- fc = fs->vqs[queue_id].fud->fc;
pr_debug("%s: opcode %u unique %#llx nodeid %#llx in.len %u out.len %u\n",
__func__, req->in.h.opcode, req->in.h.unique,
req->in.h.nodeid, req->in.h.len,
fuse_len_args(req->args->out_numargs, req->args->out_args));
- fpq = &fs->vqs[queue_id].fud->pq;
- spin_lock(&fpq->lock);
- if (!fpq->connected) {
- spin_unlock(&fpq->lock);
- req->out.h.error = -ENODEV;
- pr_err("virtio-fs: %s disconnected\n", __func__);
- fuse_request_end(fc, req);
- return;
- }
- list_add_tail(&req->list, fpq->processing);
- spin_unlock(&fpq->lock);
- set_bit(FR_SENT, &req->flags);
- /* matches barrier in request_wait_answer() */
- smp_mb__after_atomic();
-
-retry:
- ret = virtio_fs_enqueue_req(&fs->vqs[queue_id], req);
+ fsvq = &fs->vqs[queue_id];
+ ret = virtio_fs_enqueue_req(fsvq, req, false);
if (ret < 0) {
if (ret == -ENOMEM || ret == -ENOSPC) {
- /* Virtqueue full. Retry submission */
- /* TODO use completion instead of timeout */
- usleep_range(20, 30);
- goto retry;
+ /*
+ * Virtqueue full. Retry submission from worker
+ * context as we might be holding fc->bg_lock.
+ */
+ spin_lock(&fsvq->lock);
+ list_add_tail(&req->list, &fsvq->queued_reqs);
+ inc_in_flight_req(fsvq);
+ schedule_delayed_work(&fsvq->dispatch_work,
+ msecs_to_jiffies(1));
+ spin_unlock(&fsvq->lock);
+ return;
}
req->out.h.error = ret;
pr_err("virtio-fs: virtio_fs_enqueue_req() failed %d\n", ret);
- spin_lock(&fpq->lock);
- clear_bit(FR_SENT, &req->flags);
- list_del_init(&req->list);
- spin_unlock(&fpq->lock);
- fuse_request_end(fc, req);
+
+ /* Can't end request in submission context. Use a worker */
+ spin_lock(&fsvq->lock);
+ list_add_tail(&req->list, &fsvq->end_reqs);
+ schedule_delayed_work(&fsvq->dispatch_work, 0);
+ spin_unlock(&fsvq->lock);
return;
}
}
-const static struct fuse_iqueue_ops virtio_fs_fiq_ops = {
+static const struct fuse_iqueue_ops virtio_fs_fiq_ops = {
.wake_forget_and_unlock = virtio_fs_wake_forget_and_unlock,
.wake_interrupt_and_unlock = virtio_fs_wake_interrupt_and_unlock,
.wake_pending_and_unlock = virtio_fs_wake_pending_and_unlock,
@@ -992,6 +1050,7 @@ static int virtio_fs_fill_super(struct super_block *sb)
.destroy = true,
.no_control = true,
.no_force_umount = true,
+ .no_mount_options = true,
};
mutex_lock(&virtio_fs_mutex);
diff --git a/fs/gfs2/aops.c b/fs/gfs2/aops.c
index b9fe975d7625..9c6df721321a 100644
--- a/fs/gfs2/aops.c
+++ b/fs/gfs2/aops.c
@@ -133,7 +133,7 @@ static int gfs2_write_full_page(struct page *page, get_block_t *get_block,
* the page size, the remaining memory is zeroed when mapped, and
* writes to that region are not written out to the file."
*/
- offset = i_size & (PAGE_SIZE-1);
+ offset = i_size & (PAGE_SIZE - 1);
if (page->index == end_index && offset)
zero_user_segment(page, offset, PAGE_SIZE);
@@ -497,7 +497,7 @@ static int __gfs2_readpage(void *file, struct page *page)
error = mpage_readpage(page, gfs2_block_map);
}
- if (unlikely(test_bit(SDF_WITHDRAWN, &sdp->sd_flags)))
+ if (unlikely(gfs2_withdrawn(sdp)))
return -EIO;
return error;
@@ -614,7 +614,7 @@ static int gfs2_readpages(struct file *file, struct address_space *mapping,
gfs2_glock_dq(&gh);
out_uninit:
gfs2_holder_uninit(&gh);
- if (unlikely(test_bit(SDF_WITHDRAWN, &sdp->sd_flags)))
+ if (unlikely(gfs2_withdrawn(sdp)))
ret = -EIO;
return ret;
}
diff --git a/fs/gfs2/bmap.c b/fs/gfs2/bmap.c
index 516103248272..08f6fbb3655e 100644
--- a/fs/gfs2/bmap.c
+++ b/fs/gfs2/bmap.c
@@ -2441,8 +2441,16 @@ int __gfs2_punch_hole(struct file *file, loff_t offset, loff_t length)
struct inode *inode = file_inode(file);
struct gfs2_inode *ip = GFS2_I(inode);
struct gfs2_sbd *sdp = GFS2_SB(inode);
+ unsigned int blocksize = i_blocksize(inode);
+ loff_t start, end;
int error;
+ start = round_down(offset, blocksize);
+ end = round_up(offset + length, blocksize) - 1;
+ error = filemap_write_and_wait_range(inode->i_mapping, start, end);
+ if (error)
+ return error;
+
if (gfs2_is_jdata(ip))
error = gfs2_trans_begin(sdp, RES_DINODE + 2 * RES_JDATA,
GFS2_JTRUNC_REVOKES);
@@ -2456,9 +2464,8 @@ int __gfs2_punch_hole(struct file *file, loff_t offset, loff_t length)
if (error)
goto out;
} else {
- unsigned int start_off, end_len, blocksize;
+ unsigned int start_off, end_len;
- blocksize = i_blocksize(inode);
start_off = offset & (blocksize - 1);
end_len = (offset + length) & (blocksize - 1);
if (start_off) {
diff --git a/fs/gfs2/file.c b/fs/gfs2/file.c
index f0caee2b7c00..9d58295ccf7a 100644
--- a/fs/gfs2/file.c
+++ b/fs/gfs2/file.c
@@ -6,6 +6,7 @@
#include <linux/slab.h>
#include <linux/spinlock.h>
+#include <linux/compat.h>
#include <linux/completion.h>
#include <linux/buffer_head.h>
#include <linux/pagemap.h>
@@ -354,6 +355,31 @@ static long gfs2_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
return -ENOTTY;
}
+#ifdef CONFIG_COMPAT
+static long gfs2_compat_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
+{
+ switch(cmd) {
+ /* These are just misnamed, they actually get/put from/to user an int */
+ case FS_IOC32_GETFLAGS:
+ cmd = FS_IOC_GETFLAGS;
+ break;
+ case FS_IOC32_SETFLAGS:
+ cmd = FS_IOC_SETFLAGS;
+ break;
+ /* Keep this list in sync with gfs2_ioctl */
+ case FITRIM:
+ case FS_IOC_GETFSLABEL:
+ break;
+ default:
+ return -ENOIOCTLCMD;
+ }
+
+ return gfs2_ioctl(filp, cmd, (unsigned long)compat_ptr(arg));
+}
+#else
+#define gfs2_compat_ioctl NULL
+#endif
+
/**
* gfs2_size_hint - Give a hint to the size of a write request
* @filep: The struct file
@@ -381,27 +407,28 @@ static void gfs2_size_hint(struct file *filep, loff_t offset, size_t size)
/**
* gfs2_allocate_page_backing - Allocate blocks for a write fault
* @page: The (locked) page to allocate backing for
+ * @length: Size of the allocation
*
* We try to allocate all the blocks required for the page in one go. This
* might fail for various reasons, so we keep trying until all the blocks to
* back this page are allocated. If some of the blocks are already allocated,
* that is ok too.
*/
-static int gfs2_allocate_page_backing(struct page *page)
+static int gfs2_allocate_page_backing(struct page *page, unsigned int length)
{
u64 pos = page_offset(page);
- u64 size = PAGE_SIZE;
do {
struct iomap iomap = { };
- if (gfs2_iomap_get_alloc(page->mapping->host, pos, 1, &iomap))
+ if (gfs2_iomap_get_alloc(page->mapping->host, pos, length, &iomap))
return -EIO;
- iomap.length = min(iomap.length, size);
- size -= iomap.length;
+ if (length < iomap.length)
+ iomap.length = length;
+ length -= iomap.length;
pos += iomap.length;
- } while (size > 0);
+ } while (length > 0);
return 0;
}
@@ -422,10 +449,10 @@ static vm_fault_t gfs2_page_mkwrite(struct vm_fault *vmf)
struct gfs2_inode *ip = GFS2_I(inode);
struct gfs2_sbd *sdp = GFS2_SB(inode);
struct gfs2_alloc_parms ap = { .aflags = 0, };
- unsigned long last_index;
- u64 pos = page_offset(page);
+ u64 offset = page_offset(page);
unsigned int data_blocks, ind_blocks, rblocks;
struct gfs2_holder gh;
+ unsigned int length;
loff_t size;
int ret;
@@ -435,20 +462,39 @@ static vm_fault_t gfs2_page_mkwrite(struct vm_fault *vmf)
if (ret)
goto out;
- gfs2_size_hint(vmf->vma->vm_file, pos, PAGE_SIZE);
-
gfs2_holder_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, &gh);
ret = gfs2_glock_nq(&gh);
if (ret)
goto out_uninit;
+ /* Check page index against inode size */
+ size = i_size_read(inode);
+ if (offset >= size) {
+ ret = -EINVAL;
+ goto out_unlock;
+ }
+
/* Update file times before taking page lock */
file_update_time(vmf->vma->vm_file);
+ /* page is wholly or partially inside EOF */
+ if (offset > size - PAGE_SIZE)
+ length = offset_in_page(size);
+ else
+ length = PAGE_SIZE;
+
+ gfs2_size_hint(vmf->vma->vm_file, offset, length);
+
set_bit(GLF_DIRTY, &ip->i_gl->gl_flags);
set_bit(GIF_SW_PAGED, &ip->i_flags);
- if (!gfs2_write_alloc_required(ip, pos, PAGE_SIZE)) {
+ /*
+ * iomap_writepage / iomap_writepages currently don't support inline
+ * files, so always unstuff here.
+ */
+
+ if (!gfs2_is_stuffed(ip) &&
+ !gfs2_write_alloc_required(ip, offset, length)) {
lock_page(page);
if (!PageUptodate(page) || page->mapping != inode->i_mapping) {
ret = -EAGAIN;
@@ -461,7 +507,7 @@ static vm_fault_t gfs2_page_mkwrite(struct vm_fault *vmf)
if (ret)
goto out_unlock;
- gfs2_write_calc_reserv(ip, PAGE_SIZE, &data_blocks, &ind_blocks);
+ gfs2_write_calc_reserv(ip, length, &data_blocks, &ind_blocks);
ap.target = data_blocks + ind_blocks;
ret = gfs2_quota_lock_check(ip, &ap);
if (ret)
@@ -482,13 +528,6 @@ static vm_fault_t gfs2_page_mkwrite(struct vm_fault *vmf)
goto out_trans_fail;
lock_page(page);
- ret = -EINVAL;
- size = i_size_read(inode);
- last_index = (size - 1) >> PAGE_SHIFT;
- /* Check page index against inode size */
- if (size == 0 || (page->index > last_index))
- goto out_trans_end;
-
ret = -EAGAIN;
/* If truncated, we must retry the operation, we may have raced
* with the glock demotion code.
@@ -501,7 +540,7 @@ static vm_fault_t gfs2_page_mkwrite(struct vm_fault *vmf)
if (gfs2_is_stuffed(ip))
ret = gfs2_unstuff_dinode(ip, page);
if (ret == 0)
- ret = gfs2_allocate_page_backing(page);
+ ret = gfs2_allocate_page_backing(page, length);
out_trans_end:
if (ret)
@@ -935,6 +974,7 @@ out:
brelse(dibh);
return error;
}
+
/**
* calc_max_reserv() - Reverse of write_calc_reserv. Given a number of
* blocks, determine how many bytes can be written.
@@ -1182,7 +1222,7 @@ static int gfs2_lock(struct file *file, int cmd, struct file_lock *fl)
cmd = F_SETLK;
fl->fl_type = F_UNLCK;
}
- if (unlikely(test_bit(SDF_WITHDRAWN, &sdp->sd_flags))) {
+ if (unlikely(gfs2_withdrawn(sdp))) {
if (fl->fl_type == F_UNLCK)
locks_lock_file_wait(file, fl);
return -EIO;
@@ -1295,6 +1335,7 @@ const struct file_operations gfs2_file_fops = {
.write_iter = gfs2_file_write_iter,
.iopoll = iomap_dio_iopoll,
.unlocked_ioctl = gfs2_ioctl,
+ .compat_ioctl = gfs2_compat_ioctl,
.mmap = gfs2_mmap,
.open = gfs2_open,
.release = gfs2_release,
@@ -1310,6 +1351,7 @@ const struct file_operations gfs2_file_fops = {
const struct file_operations gfs2_dir_fops = {
.iterate_shared = gfs2_readdir,
.unlocked_ioctl = gfs2_ioctl,
+ .compat_ioctl = gfs2_compat_ioctl,
.open = gfs2_open,
.release = gfs2_release,
.fsync = gfs2_fsync,
@@ -1326,6 +1368,7 @@ const struct file_operations gfs2_file_fops_nolock = {
.write_iter = gfs2_file_write_iter,
.iopoll = iomap_dio_iopoll,
.unlocked_ioctl = gfs2_ioctl,
+ .compat_ioctl = gfs2_compat_ioctl,
.mmap = gfs2_mmap,
.open = gfs2_open,
.release = gfs2_release,
@@ -1339,6 +1382,7 @@ const struct file_operations gfs2_file_fops_nolock = {
const struct file_operations gfs2_dir_fops_nolock = {
.iterate_shared = gfs2_readdir,
.unlocked_ioctl = gfs2_ioctl,
+ .compat_ioctl = gfs2_compat_ioctl,
.open = gfs2_open,
.release = gfs2_release,
.fsync = gfs2_fsync,
diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c
index 0290a22ebccf..b7123de7c180 100644
--- a/fs/gfs2/glock.c
+++ b/fs/gfs2/glock.c
@@ -549,7 +549,7 @@ __acquires(&gl->gl_lockref.lock)
unsigned int lck_flags = (unsigned int)(gh ? gh->gh_flags : 0);
int ret;
- if (unlikely(test_bit(SDF_WITHDRAWN, &sdp->sd_flags)) &&
+ if (unlikely(gfs2_withdrawn(sdp)) &&
target != LM_ST_UNLOCKED)
return;
lck_flags &= (LM_FLAG_TRY | LM_FLAG_TRY_1CB | LM_FLAG_NOEXP |
@@ -558,7 +558,14 @@ __acquires(&gl->gl_lockref.lock)
GLOCK_BUG_ON(gl, gl->gl_state == gl->gl_target);
if ((target == LM_ST_UNLOCKED || target == LM_ST_DEFERRED) &&
glops->go_inval) {
- set_bit(GLF_INVALIDATE_IN_PROGRESS, &gl->gl_flags);
+ /*
+ * If another process is already doing the invalidate, let that
+ * finish first. The glock state machine will get back to this
+ * holder again later.
+ */
+ if (test_and_set_bit(GLF_INVALIDATE_IN_PROGRESS,
+ &gl->gl_flags))
+ return;
do_error(gl, 0); /* Fail queued try locks */
}
gl->gl_req = target;
@@ -586,8 +593,7 @@ __acquires(&gl->gl_lockref.lock)
}
else if (ret) {
fs_err(sdp, "lm_lock ret %d\n", ret);
- GLOCK_BUG_ON(gl, !test_bit(SDF_WITHDRAWN,
- &sdp->sd_flags));
+ GLOCK_BUG_ON(gl, !gfs2_withdrawn(sdp));
}
} else { /* lock_nolock */
finish_xmote(gl, target);
@@ -1191,7 +1197,7 @@ int gfs2_glock_nq(struct gfs2_holder *gh)
struct gfs2_sbd *sdp = gl->gl_name.ln_sbd;
int error = 0;
- if (unlikely(test_bit(SDF_WITHDRAWN, &sdp->sd_flags)))
+ if (unlikely(gfs2_withdrawn(sdp)))
return -EIO;
if (test_bit(GLF_LRU, &gl->gl_flags))
diff --git a/fs/gfs2/glops.c b/fs/gfs2/glops.c
index ff213690e364..4ede1f18de85 100644
--- a/fs/gfs2/glops.c
+++ b/fs/gfs2/glops.c
@@ -350,7 +350,7 @@ static int gfs2_dinode_in(struct gfs2_inode *ip, const void *buf)
ip->i_inode.i_rdev = MKDEV(be32_to_cpu(str->di_major),
be32_to_cpu(str->di_minor));
break;
- };
+ }
i_uid_write(&ip->i_inode, be32_to_cpu(str->di_uid));
i_gid_write(&ip->i_inode, be32_to_cpu(str->di_gid));
@@ -540,7 +540,7 @@ static int freeze_go_xmote_bh(struct gfs2_glock *gl, struct gfs2_holder *gh)
gfs2_consist(sdp);
/* Initialize some head of the log stuff */
- if (!test_bit(SDF_WITHDRAWN, &sdp->sd_flags)) {
+ if (!gfs2_withdrawn(sdp)) {
sdp->sd_log_sequence = head.lh_sequence + 1;
gfs2_log_pointers_init(sdp, head.lh_blkno);
}
diff --git a/fs/gfs2/inode.c b/fs/gfs2/inode.c
index e1e18fb587eb..dafef10b91f1 100644
--- a/fs/gfs2/inode.c
+++ b/fs/gfs2/inode.c
@@ -656,7 +656,6 @@ static int gfs2_create_inode(struct inode *dir, struct dentry *dentry,
inode->i_rdev = dev;
inode->i_size = size;
inode->i_atime = inode->i_mtime = inode->i_ctime = current_time(inode);
- gfs2_set_inode_blocks(inode, 1);
munge_mode_uid_gid(dip, inode);
check_and_update_goal(dip);
ip->i_goal = dip->i_goal;
@@ -712,7 +711,7 @@ static int gfs2_create_inode(struct inode *dir, struct dentry *dentry,
error = gfs2_trans_begin(sdp, blocks, 0);
if (error)
- goto fail_gunlock2;
+ goto fail_free_inode;
if (blocks > 1) {
ip->i_eattr = ip->i_no_addr + 1;
@@ -723,7 +722,7 @@ static int gfs2_create_inode(struct inode *dir, struct dentry *dentry,
error = gfs2_glock_get(sdp, ip->i_no_addr, &gfs2_iopen_glops, CREATE, &io_gl);
if (error)
- goto fail_gunlock2;
+ goto fail_free_inode;
BUG_ON(test_and_set_bit(GLF_INODE_CREATING, &io_gl->gl_flags));
@@ -732,7 +731,6 @@ static int gfs2_create_inode(struct inode *dir, struct dentry *dentry,
goto fail_gunlock2;
glock_set_object(ip->i_iopen_gh.gh_gl, ip);
- gfs2_glock_put(io_gl);
gfs2_set_iop(inode);
insert_inode_hash(inode);
@@ -765,6 +763,8 @@ static int gfs2_create_inode(struct inode *dir, struct dentry *dentry,
mark_inode_dirty(inode);
d_instantiate(dentry, inode);
+ /* After instantiate, errors should result in evict which will destroy
+ * both inode and iopen glocks properly. */
if (file) {
file->f_mode |= FMODE_CREATED;
error = finish_open(file, dentry, gfs2_open_common);
@@ -772,15 +772,15 @@ static int gfs2_create_inode(struct inode *dir, struct dentry *dentry,
gfs2_glock_dq_uninit(ghs);
gfs2_glock_dq_uninit(ghs + 1);
clear_bit(GLF_INODE_CREATING, &io_gl->gl_flags);
+ gfs2_glock_put(io_gl);
return error;
fail_gunlock3:
glock_clear_object(io_gl, ip);
gfs2_glock_dq_uninit(&ip->i_iopen_gh);
- gfs2_glock_put(io_gl);
fail_gunlock2:
- if (io_gl)
- clear_bit(GLF_INODE_CREATING, &io_gl->gl_flags);
+ clear_bit(GLF_INODE_CREATING, &io_gl->gl_flags);
+ gfs2_glock_put(io_gl);
fail_free_inode:
if (ip->i_gl) {
glock_clear_object(ip->i_gl, ip);
@@ -1475,7 +1475,7 @@ static int gfs2_rename(struct inode *odir, struct dentry *odentry,
error = -EEXIST;
default:
goto out_gunlock;
- };
+ }
if (odip != ndip) {
if (!ndip->i_inode.i_nlink) {
diff --git a/fs/gfs2/log.c b/fs/gfs2/log.c
index 58e237fba565..eb3f2e7b8085 100644
--- a/fs/gfs2/log.c
+++ b/fs/gfs2/log.c
@@ -31,6 +31,8 @@
#include "dir.h"
#include "trace_gfs2.h"
+static void gfs2_log_shutdown(struct gfs2_sbd *sdp);
+
/**
* gfs2_struct2blk - compute stuff
* @sdp: the filesystem
@@ -159,7 +161,8 @@ restart:
list_for_each_entry_reverse(tr, head, tr_list) {
if (wbc->nr_to_write <= 0)
break;
- if (gfs2_ail1_start_one(sdp, wbc, tr, &withdraw))
+ if (gfs2_ail1_start_one(sdp, wbc, tr, &withdraw) &&
+ !gfs2_withdrawn(sdp))
goto restart;
}
spin_unlock(&sdp->sd_ail_lock);
@@ -609,6 +612,14 @@ void gfs2_add_revoke(struct gfs2_sbd *sdp, struct gfs2_bufdata *bd)
list_add(&bd->bd_list, &sdp->sd_log_revokes);
}
+void gfs2_glock_remove_revoke(struct gfs2_glock *gl)
+{
+ if (atomic_dec_return(&gl->gl_revokes) == 0) {
+ clear_bit(GLF_LFLUSH, &gl->gl_flags);
+ gfs2_glock_queue_put(gl);
+ }
+}
+
void gfs2_write_revokes(struct gfs2_sbd *sdp)
{
struct gfs2_trans *tr;
@@ -682,12 +693,16 @@ void gfs2_write_log_header(struct gfs2_sbd *sdp, struct gfs2_jdesc *jd,
{
struct gfs2_log_header *lh;
u32 hash, crc;
- struct page *page = mempool_alloc(gfs2_page_pool, GFP_NOIO);
+ struct page *page;
struct gfs2_statfs_change_host *l_sc = &sdp->sd_statfs_local;
struct timespec64 tv;
struct super_block *sb = sdp->sd_vfs;
u64 dblock;
+ if (gfs2_withdrawn(sdp))
+ goto out;
+
+ page = mempool_alloc(gfs2_page_pool, GFP_NOIO);
lh = page_address(page);
clear_page(lh);
@@ -707,7 +722,7 @@ void gfs2_write_log_header(struct gfs2_sbd *sdp, struct gfs2_jdesc *jd,
lh->lh_nsec = cpu_to_be32(tv.tv_nsec);
lh->lh_sec = cpu_to_be64(tv.tv_sec);
if (!list_empty(&jd->extent_list))
- dblock = gfs2_log_bmap(sdp);
+ dblock = gfs2_log_bmap(jd, lblock);
else {
int ret = gfs2_lblk_to_dblk(jd->jd_inode, lblock, &dblock);
if (gfs2_assert_withdraw(sdp, ret == 0))
@@ -740,6 +755,7 @@ void gfs2_write_log_header(struct gfs2_sbd *sdp, struct gfs2_jdesc *jd,
gfs2_log_write(sdp, page, sb->s_blocksize, 0, dblock);
gfs2_log_submit_bio(&sdp->sd_log_bio, REQ_OP_WRITE | op_flags);
+out:
log_flush_wait(sdp);
}
@@ -768,6 +784,7 @@ static void log_write_header(struct gfs2_sbd *sdp, u32 flags)
sdp->sd_log_idle = (tail == sdp->sd_log_flush_head);
gfs2_write_log_header(sdp, sdp->sd_jdesc, sdp->sd_log_sequence++, tail,
sdp->sd_log_flush_head, flags, op_flags);
+ gfs2_log_incr_head(sdp);
if (sdp->sd_log_tail != tail)
log_pull_tail(sdp, tail);
@@ -948,7 +965,7 @@ void gfs2_log_commit(struct gfs2_sbd *sdp, struct gfs2_trans *tr)
*
*/
-void gfs2_log_shutdown(struct gfs2_sbd *sdp)
+static void gfs2_log_shutdown(struct gfs2_sbd *sdp)
{
gfs2_assert_withdraw(sdp, !sdp->sd_log_blks_reserved);
gfs2_assert_withdraw(sdp, !sdp->sd_log_num_revoke);
diff --git a/fs/gfs2/log.h b/fs/gfs2/log.h
index 2315fca47a2b..2ff163a8dce1 100644
--- a/fs/gfs2/log.h
+++ b/fs/gfs2/log.h
@@ -74,9 +74,9 @@ extern void gfs2_log_flush(struct gfs2_sbd *sdp, struct gfs2_glock *gl,
extern void gfs2_log_commit(struct gfs2_sbd *sdp, struct gfs2_trans *trans);
extern void gfs2_ail1_flush(struct gfs2_sbd *sdp, struct writeback_control *wbc);
-extern void gfs2_log_shutdown(struct gfs2_sbd *sdp);
extern int gfs2_logd(void *data);
extern void gfs2_add_revoke(struct gfs2_sbd *sdp, struct gfs2_bufdata *bd);
+extern void gfs2_glock_remove_revoke(struct gfs2_glock *gl);
extern void gfs2_write_revokes(struct gfs2_sbd *sdp);
#endif /* __LOG_DOT_H__ */
diff --git a/fs/gfs2/lops.c b/fs/gfs2/lops.c
index 5b17979af539..55fed7daf2b1 100644
--- a/fs/gfs2/lops.c
+++ b/fs/gfs2/lops.c
@@ -129,7 +129,7 @@ static void gfs2_unpin(struct gfs2_sbd *sdp, struct buffer_head *bh,
atomic_dec(&sdp->sd_log_pinned);
}
-static void gfs2_log_incr_head(struct gfs2_sbd *sdp)
+void gfs2_log_incr_head(struct gfs2_sbd *sdp)
{
BUG_ON((sdp->sd_log_flush_head == sdp->sd_log_tail) &&
(sdp->sd_log_flush_head != sdp->sd_log_head));
@@ -138,18 +138,13 @@ static void gfs2_log_incr_head(struct gfs2_sbd *sdp)
sdp->sd_log_flush_head = 0;
}
-u64 gfs2_log_bmap(struct gfs2_sbd *sdp)
+u64 gfs2_log_bmap(struct gfs2_jdesc *jd, unsigned int lblock)
{
- unsigned int lbn = sdp->sd_log_flush_head;
struct gfs2_journal_extent *je;
- u64 block;
- list_for_each_entry(je, &sdp->sd_jdesc->extent_list, list) {
- if ((lbn >= je->lblock) && (lbn < (je->lblock + je->blocks))) {
- block = je->dblock + lbn - je->lblock;
- gfs2_log_incr_head(sdp);
- return block;
- }
+ list_for_each_entry(je, &jd->extent_list, list) {
+ if (lblock >= je->lblock && lblock < je->lblock + je->blocks)
+ return je->dblock + lblock - je->lblock;
}
return -1;
@@ -351,8 +346,11 @@ void gfs2_log_write(struct gfs2_sbd *sdp, struct page *page,
static void gfs2_log_write_bh(struct gfs2_sbd *sdp, struct buffer_head *bh)
{
- gfs2_log_write(sdp, bh->b_page, bh->b_size, bh_offset(bh),
- gfs2_log_bmap(sdp));
+ u64 dblock;
+
+ dblock = gfs2_log_bmap(sdp->sd_jdesc, sdp->sd_log_flush_head);
+ gfs2_log_incr_head(sdp);
+ gfs2_log_write(sdp, bh->b_page, bh->b_size, bh_offset(bh), dblock);
}
/**
@@ -369,8 +367,11 @@ static void gfs2_log_write_bh(struct gfs2_sbd *sdp, struct buffer_head *bh)
void gfs2_log_write_page(struct gfs2_sbd *sdp, struct page *page)
{
struct super_block *sb = sdp->sd_vfs;
- gfs2_log_write(sdp, page, sb->s_blocksize, 0,
- gfs2_log_bmap(sdp));
+ u64 dblock;
+
+ dblock = gfs2_log_bmap(sdp->sd_jdesc, sdp->sd_log_flush_head);
+ gfs2_log_incr_head(sdp);
+ gfs2_log_write(sdp, page, sb->s_blocksize, 0, dblock);
}
/**
@@ -882,10 +883,7 @@ static void revoke_lo_after_commit(struct gfs2_sbd *sdp, struct gfs2_trans *tr)
bd = list_entry(head->next, struct gfs2_bufdata, bd_list);
list_del_init(&bd->bd_list);
gl = bd->bd_gl;
- if (atomic_dec_return(&gl->gl_revokes) == 0) {
- clear_bit(GLF_LFLUSH, &gl->gl_flags);
- gfs2_glock_queue_put(gl);
- }
+ gfs2_glock_remove_revoke(gl);
kmem_cache_free(gfs2_bufdata_cachep, bd);
}
}
diff --git a/fs/gfs2/lops.h b/fs/gfs2/lops.h
index 9c059957a733..9c5e4e491e03 100644
--- a/fs/gfs2/lops.h
+++ b/fs/gfs2/lops.h
@@ -18,7 +18,8 @@
~(2 * sizeof(__be64) - 1))
extern const struct gfs2_log_operations *gfs2_log_ops[];
-extern u64 gfs2_log_bmap(struct gfs2_sbd *sdp);
+extern void gfs2_log_incr_head(struct gfs2_sbd *sdp);
+extern u64 gfs2_log_bmap(struct gfs2_jdesc *jd, unsigned int lbn);
extern void gfs2_log_write(struct gfs2_sbd *sdp, struct page *page,
unsigned size, unsigned offset, u64 blkno);
extern void gfs2_log_write_page(struct gfs2_sbd *sdp, struct page *page);
diff --git a/fs/gfs2/meta_io.c b/fs/gfs2/meta_io.c
index 662ef36c1874..0c3772974030 100644
--- a/fs/gfs2/meta_io.c
+++ b/fs/gfs2/meta_io.c
@@ -251,7 +251,7 @@ int gfs2_meta_read(struct gfs2_glock *gl, u64 blkno, int flags,
struct buffer_head *bh, *bhs[2];
int num = 0;
- if (unlikely(test_bit(SDF_WITHDRAWN, &sdp->sd_flags))) {
+ if (unlikely(gfs2_withdrawn(sdp))) {
*bhp = NULL;
return -EIO;
}
@@ -309,7 +309,7 @@ int gfs2_meta_read(struct gfs2_glock *gl, u64 blkno, int flags,
int gfs2_meta_wait(struct gfs2_sbd *sdp, struct buffer_head *bh)
{
- if (unlikely(test_bit(SDF_WITHDRAWN, &sdp->sd_flags)))
+ if (unlikely(gfs2_withdrawn(sdp)))
return -EIO;
wait_on_buffer(bh);
@@ -320,7 +320,7 @@ int gfs2_meta_wait(struct gfs2_sbd *sdp, struct buffer_head *bh)
gfs2_io_error_bh_wd(sdp, bh);
return -EIO;
}
- if (unlikely(test_bit(SDF_WITHDRAWN, &sdp->sd_flags)))
+ if (unlikely(gfs2_withdrawn(sdp)))
return -EIO;
return 0;
diff --git a/fs/gfs2/ops_fstype.c b/fs/gfs2/ops_fstype.c
index 681b44682b0d..e8b7b0ce8404 100644
--- a/fs/gfs2/ops_fstype.c
+++ b/fs/gfs2/ops_fstype.c
@@ -1006,8 +1006,7 @@ hostdata_error:
void gfs2_lm_unmount(struct gfs2_sbd *sdp)
{
const struct lm_lockops *lm = sdp->sd_lockstruct.ls_ops;
- if (likely(!test_bit(SDF_WITHDRAWN, &sdp->sd_flags)) &&
- lm->lm_unmount)
+ if (likely(!gfs2_withdrawn(sdp)) && lm->lm_unmount)
lm->lm_unmount(sdp);
}
@@ -1328,7 +1327,7 @@ static const struct fs_parameter_enum gfs2_param_enums[] = {
{}
};
-const struct fs_parameter_description gfs2_fs_parameters = {
+static const struct fs_parameter_description gfs2_fs_parameters = {
.name = "gfs2",
.specs = gfs2_param_specs,
.enums = gfs2_param_enums,
@@ -1540,17 +1539,23 @@ static int gfs2_init_fs_context(struct fs_context *fc)
{
struct gfs2_args *args;
- args = kzalloc(sizeof(*args), GFP_KERNEL);
+ args = kmalloc(sizeof(*args), GFP_KERNEL);
if (args == NULL)
return -ENOMEM;
- args->ar_quota = GFS2_QUOTA_DEFAULT;
- args->ar_data = GFS2_DATA_DEFAULT;
- args->ar_commit = 30;
- args->ar_statfs_quantum = 30;
- args->ar_quota_quantum = 60;
- args->ar_errors = GFS2_ERRORS_DEFAULT;
+ if (fc->purpose == FS_CONTEXT_FOR_RECONFIGURE) {
+ struct gfs2_sbd *sdp = fc->root->d_sb->s_fs_info;
+ *args = sdp->sd_args;
+ } else {
+ memset(args, 0, sizeof(*args));
+ args->ar_quota = GFS2_QUOTA_DEFAULT;
+ args->ar_data = GFS2_DATA_DEFAULT;
+ args->ar_commit = 30;
+ args->ar_statfs_quantum = 30;
+ args->ar_quota_quantum = 60;
+ args->ar_errors = GFS2_ERRORS_DEFAULT;
+ }
fc->fs_private = args;
fc->ops = &gfs2_context_ops;
return 0;
@@ -1600,6 +1605,7 @@ static int gfs2_meta_get_tree(struct fs_context *fc)
}
static const struct fs_context_operations gfs2_meta_context_ops = {
+ .free = gfs2_fc_free,
.get_tree = gfs2_meta_get_tree,
};
diff --git a/fs/gfs2/quota.c b/fs/gfs2/quota.c
index 7c016a082aa6..e9f93045eb01 100644
--- a/fs/gfs2/quota.c
+++ b/fs/gfs2/quota.c
@@ -1273,7 +1273,7 @@ int gfs2_quota_sync(struct super_block *sb, int type)
{
struct gfs2_sbd *sdp = sb->s_fs_info;
struct gfs2_quota_data **qda;
- unsigned int max_qd = PAGE_SIZE/sizeof(struct gfs2_holder);
+ unsigned int max_qd = PAGE_SIZE / sizeof(struct gfs2_holder);
unsigned int num_qd;
unsigned int x;
int error = 0;
@@ -1475,7 +1475,7 @@ static void quotad_error(struct gfs2_sbd *sdp, const char *msg, int error)
{
if (error == 0 || error == -EROFS)
return;
- if (!test_bit(SDF_WITHDRAWN, &sdp->sd_flags)) {
+ if (!gfs2_withdrawn(sdp)) {
fs_err(sdp, "gfs2_quotad: %s error %d\n", msg, error);
sdp->sd_log_error = error;
wake_up(&sdp->sd_logd_waitq);
diff --git a/fs/gfs2/recovery.c b/fs/gfs2/recovery.c
index c529f8749a89..85f830e56945 100644
--- a/fs/gfs2/recovery.c
+++ b/fs/gfs2/recovery.c
@@ -263,11 +263,13 @@ static void clean_journal(struct gfs2_jdesc *jd,
u32 lblock = head->lh_blkno;
gfs2_replay_incr_blk(jd, &lblock);
- if (jd->jd_jid == sdp->sd_lockstruct.ls_jid)
- sdp->sd_log_flush_head = lblock;
gfs2_write_log_header(sdp, jd, head->lh_sequence + 1, 0, lblock,
GFS2_LOG_HEAD_UNMOUNT | GFS2_LOG_HEAD_RECOVERY,
REQ_PREFLUSH | REQ_FUA | REQ_META | REQ_SYNC);
+ if (jd->jd_jid == sdp->sd_lockstruct.ls_jid) {
+ sdp->sd_log_flush_head = lblock;
+ gfs2_log_incr_head(sdp);
+ }
}
@@ -326,7 +328,7 @@ void gfs2_recover_func(struct work_struct *work)
default:
goto fail;
- };
+ }
error = gfs2_glock_nq_init(ip->i_gl, LM_ST_SHARED,
LM_FLAG_NOEXP | GL_NOCACHE, &ji_gh);
diff --git a/fs/gfs2/super.c b/fs/gfs2/super.c
index 5fa1eec4fb4f..68cc7c291a81 100644
--- a/fs/gfs2/super.c
+++ b/fs/gfs2/super.c
@@ -399,8 +399,7 @@ struct lfcc {
* Returns: errno
*/
-static int gfs2_lock_fs_check_clean(struct gfs2_sbd *sdp,
- struct gfs2_holder *freeze_gh)
+static int gfs2_lock_fs_check_clean(struct gfs2_sbd *sdp)
{
struct gfs2_inode *ip;
struct gfs2_jdesc *jd;
@@ -425,7 +424,9 @@ static int gfs2_lock_fs_check_clean(struct gfs2_sbd *sdp,
}
error = gfs2_glock_nq_init(sdp->sd_freeze_gl, LM_ST_EXCLUSIVE,
- GL_NOCACHE, freeze_gh);
+ GL_NOCACHE, &sdp->sd_freeze_gh);
+ if (error)
+ goto out;
list_for_each_entry(jd, &sdp->sd_jindex_list, jd_list) {
error = gfs2_jdesc_check(jd);
@@ -441,7 +442,7 @@ static int gfs2_lock_fs_check_clean(struct gfs2_sbd *sdp,
}
if (error)
- gfs2_glock_dq_uninit(freeze_gh);
+ gfs2_glock_dq_uninit(&sdp->sd_freeze_gh);
out:
while (!list_empty(&list)) {
@@ -553,7 +554,7 @@ static void gfs2_dirty_inode(struct inode *inode, int flags)
if (!(flags & I_DIRTY_INODE))
return;
- if (unlikely(test_bit(SDF_WITHDRAWN, &sdp->sd_flags)))
+ if (unlikely(gfs2_withdrawn(sdp)))
return;
if (!gfs2_glock_is_locked_by_me(ip->i_gl)) {
ret = gfs2_glock_nq_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, &gh);
@@ -602,7 +603,7 @@ int gfs2_make_fs_ro(struct gfs2_sbd *sdp)
error = gfs2_glock_nq_init(sdp->sd_freeze_gl, LM_ST_SHARED, GL_NOCACHE,
&freeze_gh);
- if (error && !test_bit(SDF_WITHDRAWN, &sdp->sd_flags))
+ if (error && !gfs2_withdrawn(sdp))
return error;
flush_workqueue(gfs2_delete_workqueue);
@@ -761,21 +762,25 @@ static int gfs2_freeze(struct super_block *sb)
if (atomic_read(&sdp->sd_freeze_state) != SFS_UNFROZEN)
goto out;
- if (test_bit(SDF_WITHDRAWN, &sdp->sd_flags)) {
- error = -EINVAL;
- goto out;
- }
-
for (;;) {
- error = gfs2_lock_fs_check_clean(sdp, &sdp->sd_freeze_gh);
+ if (gfs2_withdrawn(sdp)) {
+ error = -EINVAL;
+ goto out;
+ }
+
+ error = gfs2_lock_fs_check_clean(sdp);
if (!error)
break;
if (error == -EBUSY)
fs_err(sdp, "waiting for recovery before freeze\n");
- else
+ else if (error == -EIO) {
+ fs_err(sdp, "Fatal IO error: cannot freeze gfs2 due "
+ "to recovery error.\n");
+ goto out;
+ } else {
fs_err(sdp, "error freezing FS: %d\n", error);
-
+ }
fs_err(sdp, "retrying...\n");
msleep(1000);
}
diff --git a/fs/gfs2/sys.c b/fs/gfs2/sys.c
index dd15b8e4af2c..8ccb68f4ed16 100644
--- a/fs/gfs2/sys.c
+++ b/fs/gfs2/sys.c
@@ -118,7 +118,7 @@ static ssize_t freeze_store(struct gfs2_sbd *sdp, const char *buf, size_t len)
static ssize_t withdraw_show(struct gfs2_sbd *sdp, char *buf)
{
- unsigned int b = test_bit(SDF_WITHDRAWN, &sdp->sd_flags);
+ unsigned int b = gfs2_withdrawn(sdp);
return snprintf(buf, PAGE_SIZE, "%u\n", b);
}
diff --git a/fs/gfs2/trans.c b/fs/gfs2/trans.c
index 35e3059255fe..9d4227330de4 100644
--- a/fs/gfs2/trans.c
+++ b/fs/gfs2/trans.c
@@ -262,6 +262,8 @@ void gfs2_trans_remove_revoke(struct gfs2_sbd *sdp, u64 blkno, unsigned int len)
list_del_init(&bd->bd_list);
gfs2_assert_withdraw(sdp, sdp->sd_log_num_revoke);
sdp->sd_log_num_revoke--;
+ if (bd->bd_gl)
+ gfs2_glock_remove_revoke(bd->bd_gl);
kmem_cache_free(gfs2_bufdata_cachep, bd);
tr->tr_num_revoke--;
if (--n == 0)
diff --git a/fs/gfs2/util.c b/fs/gfs2/util.c
index c45159133d8e..ec600b487498 100644
--- a/fs/gfs2/util.c
+++ b/fs/gfs2/util.c
@@ -258,7 +258,7 @@ void gfs2_io_error_bh_i(struct gfs2_sbd *sdp, struct buffer_head *bh,
const char *function, char *file, unsigned int line,
bool withdraw)
{
- if (!test_bit(SDF_WITHDRAWN, &sdp->sd_flags))
+ if (!gfs2_withdrawn(sdp))
fs_err(sdp,
"fatal: I/O error\n"
" block = %llu\n"
diff --git a/fs/gfs2/util.h b/fs/gfs2/util.h
index 4b68b2c1fe56..f2702bc9837c 100644
--- a/fs/gfs2/util.h
+++ b/fs/gfs2/util.h
@@ -164,6 +164,15 @@ static inline unsigned int gfs2_tune_get_i(struct gfs2_tune *gt,
return x;
}
+/**
+ * gfs2_withdrawn - test whether the file system is withdrawing or withdrawn
+ * @sdp: the superblock
+ */
+static inline bool gfs2_withdrawn(struct gfs2_sbd *sdp)
+{
+ return test_bit(SDF_WITHDRAWN, &sdp->sd_flags);
+}
+
#define gfs2_tune_get(sdp, field) \
gfs2_tune_get_i(&(sdp)->sd_tune, &(sdp)->sd_tune.field)
diff --git a/fs/hpfs/dir.c b/fs/hpfs/dir.c
index d85230c84ef2..f32f15669996 100644
--- a/fs/hpfs/dir.c
+++ b/fs/hpfs/dir.c
@@ -325,4 +325,5 @@ const struct file_operations hpfs_dir_ops =
.release = hpfs_dir_release,
.fsync = hpfs_file_fsync,
.unlocked_ioctl = hpfs_ioctl,
+ .compat_ioctl = compat_ptr_ioctl,
};
diff --git a/fs/hpfs/file.c b/fs/hpfs/file.c
index 1ecec124e76f..b36abf9cb345 100644
--- a/fs/hpfs/file.c
+++ b/fs/hpfs/file.c
@@ -215,6 +215,7 @@ const struct file_operations hpfs_file_ops =
.fsync = hpfs_file_fsync,
.splice_read = generic_file_splice_read,
.unlocked_ioctl = hpfs_ioctl,
+ .compat_ioctl = compat_ptr_ioctl,
};
const struct inode_operations hpfs_file_iops =
diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c
index a478df035651..d5c2a3158610 100644
--- a/fs/hugetlbfs/inode.c
+++ b/fs/hugetlbfs/inode.c
@@ -440,7 +440,7 @@ static void remove_inode_hugepages(struct inode *inode, loff_t lstart,
u32 hash;
index = page->index;
- hash = hugetlb_fault_mutex_hash(h, mapping, index, 0);
+ hash = hugetlb_fault_mutex_hash(mapping, index);
mutex_lock(&hugetlb_fault_mutex_table[hash]);
/*
@@ -644,7 +644,7 @@ static long hugetlbfs_fallocate(struct file *file, int mode, loff_t offset,
addr = index * hpage_size;
/* mutex taken here, fault path and hole punch */
- hash = hugetlb_fault_mutex_hash(h, mapping, index, addr);
+ hash = hugetlb_fault_mutex_hash(mapping, index);
mutex_lock(&hugetlb_fault_mutex_table[hash]);
/* See if already present in mapping to avoid alloc/free */
@@ -815,8 +815,11 @@ static struct inode *hugetlbfs_get_inode(struct super_block *sb,
/*
* File creation. Allocate an inode, and we're done..
*/
-static int hugetlbfs_mknod(struct inode *dir,
- struct dentry *dentry, umode_t mode, dev_t dev)
+static int do_hugetlbfs_mknod(struct inode *dir,
+ struct dentry *dentry,
+ umode_t mode,
+ dev_t dev,
+ bool tmpfile)
{
struct inode *inode;
int error = -ENOSPC;
@@ -824,13 +827,23 @@ static int hugetlbfs_mknod(struct inode *dir,
inode = hugetlbfs_get_inode(dir->i_sb, dir, mode, dev);
if (inode) {
dir->i_ctime = dir->i_mtime = current_time(dir);
- d_instantiate(dentry, inode);
- dget(dentry); /* Extra count - pin the dentry in core */
+ if (tmpfile) {
+ d_tmpfile(dentry, inode);
+ } else {
+ d_instantiate(dentry, inode);
+ dget(dentry);/* Extra count - pin the dentry in core */
+ }
error = 0;
}
return error;
}
+static int hugetlbfs_mknod(struct inode *dir,
+ struct dentry *dentry, umode_t mode, dev_t dev)
+{
+ return do_hugetlbfs_mknod(dir, dentry, mode, dev, false);
+}
+
static int hugetlbfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
{
int retval = hugetlbfs_mknod(dir, dentry, mode | S_IFDIR, 0);
@@ -844,6 +857,12 @@ static int hugetlbfs_create(struct inode *dir, struct dentry *dentry, umode_t mo
return hugetlbfs_mknod(dir, dentry, mode | S_IFREG, 0);
}
+static int hugetlbfs_tmpfile(struct inode *dir,
+ struct dentry *dentry, umode_t mode)
+{
+ return do_hugetlbfs_mknod(dir, dentry, mode | S_IFREG, 0, true);
+}
+
static int hugetlbfs_symlink(struct inode *dir,
struct dentry *dentry, const char *symname)
{
@@ -1102,6 +1121,7 @@ static const struct inode_operations hugetlbfs_dir_inode_operations = {
.mknod = hugetlbfs_mknod,
.rename = simple_rename,
.setattr = hugetlbfs_setattr,
+ .tmpfile = hugetlbfs_tmpfile,
};
static const struct inode_operations hugetlbfs_inode_operations = {
@@ -1461,28 +1481,41 @@ static int __init init_hugetlbfs_fs(void)
sizeof(struct hugetlbfs_inode_info),
0, SLAB_ACCOUNT, init_once);
if (hugetlbfs_inode_cachep == NULL)
- goto out2;
+ goto out;
error = register_filesystem(&hugetlbfs_fs_type);
if (error)
- goto out;
+ goto out_free;
+ /* default hstate mount is required */
+ mnt = mount_one_hugetlbfs(&hstates[default_hstate_idx]);
+ if (IS_ERR(mnt)) {
+ error = PTR_ERR(mnt);
+ goto out_unreg;
+ }
+ hugetlbfs_vfsmount[default_hstate_idx] = mnt;
+
+ /* other hstates are optional */
i = 0;
for_each_hstate(h) {
+ if (i == default_hstate_idx)
+ continue;
+
mnt = mount_one_hugetlbfs(h);
- if (IS_ERR(mnt) && i == 0) {
- error = PTR_ERR(mnt);
- goto out;
- }
- hugetlbfs_vfsmount[i] = mnt;
+ if (IS_ERR(mnt))
+ hugetlbfs_vfsmount[i] = NULL;
+ else
+ hugetlbfs_vfsmount[i] = mnt;
i++;
}
return 0;
- out:
+ out_unreg:
+ (void)unregister_filesystem(&hugetlbfs_fs_type);
+ out_free:
kmem_cache_destroy(hugetlbfs_inode_cachep);
- out2:
+ out:
return error;
}
fs_initcall(init_hugetlbfs_fs)
diff --git a/fs/io-wq.c b/fs/io-wq.c
new file mode 100644
index 000000000000..74b40506c5d9
--- /dev/null
+++ b/fs/io-wq.c
@@ -0,0 +1,1094 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Basic worker thread pool for io_uring
+ *
+ * Copyright (C) 2019 Jens Axboe
+ *
+ */
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/errno.h>
+#include <linux/sched/signal.h>
+#include <linux/mm.h>
+#include <linux/mmu_context.h>
+#include <linux/sched/mm.h>
+#include <linux/percpu.h>
+#include <linux/slab.h>
+#include <linux/kthread.h>
+#include <linux/rculist_nulls.h>
+
+#include "io-wq.h"
+
+#define WORKER_IDLE_TIMEOUT (5 * HZ)
+
+enum {
+ IO_WORKER_F_UP = 1, /* up and active */
+ IO_WORKER_F_RUNNING = 2, /* account as running */
+ IO_WORKER_F_FREE = 4, /* worker on free list */
+ IO_WORKER_F_EXITING = 8, /* worker exiting */
+ IO_WORKER_F_FIXED = 16, /* static idle worker */
+ IO_WORKER_F_BOUND = 32, /* is doing bounded work */
+};
+
+enum {
+ IO_WQ_BIT_EXIT = 0, /* wq exiting */
+ IO_WQ_BIT_CANCEL = 1, /* cancel work on list */
+ IO_WQ_BIT_ERROR = 2, /* error on setup */
+};
+
+enum {
+ IO_WQE_FLAG_STALLED = 1, /* stalled on hash */
+};
+
+/*
+ * One for each thread in a wqe pool
+ */
+struct io_worker {
+ refcount_t ref;
+ unsigned flags;
+ struct hlist_nulls_node nulls_node;
+ struct list_head all_list;
+ struct task_struct *task;
+ wait_queue_head_t wait;
+ struct io_wqe *wqe;
+
+ struct io_wq_work *cur_work;
+ spinlock_t lock;
+
+ struct rcu_head rcu;
+ struct mm_struct *mm;
+ const struct cred *creds;
+ struct files_struct *restore_files;
+};
+
+#if BITS_PER_LONG == 64
+#define IO_WQ_HASH_ORDER 6
+#else
+#define IO_WQ_HASH_ORDER 5
+#endif
+
+struct io_wqe_acct {
+ unsigned nr_workers;
+ unsigned max_workers;
+ atomic_t nr_running;
+};
+
+enum {
+ IO_WQ_ACCT_BOUND,
+ IO_WQ_ACCT_UNBOUND,
+};
+
+/*
+ * Per-node worker thread pool
+ */
+struct io_wqe {
+ struct {
+ spinlock_t lock;
+ struct io_wq_work_list work_list;
+ unsigned long hash_map;
+ unsigned flags;
+ } ____cacheline_aligned_in_smp;
+
+ int node;
+ struct io_wqe_acct acct[2];
+
+ struct hlist_nulls_head free_list;
+ struct hlist_nulls_head busy_list;
+ struct list_head all_list;
+
+ struct io_wq *wq;
+};
+
+/*
+ * Per io_wq state
+ */
+struct io_wq {
+ struct io_wqe **wqes;
+ unsigned long state;
+
+ get_work_fn *get_work;
+ put_work_fn *put_work;
+
+ struct task_struct *manager;
+ struct user_struct *user;
+ const struct cred *creds;
+ struct mm_struct *mm;
+ refcount_t refs;
+ struct completion done;
+};
+
+static bool io_worker_get(struct io_worker *worker)
+{
+ return refcount_inc_not_zero(&worker->ref);
+}
+
+static void io_worker_release(struct io_worker *worker)
+{
+ if (refcount_dec_and_test(&worker->ref))
+ wake_up_process(worker->task);
+}
+
+/*
+ * Note: drops the wqe->lock if returning true! The caller must re-acquire
+ * the lock in that case. Some callers need to restart handling if this
+ * happens, so we can't just re-acquire the lock on behalf of the caller.
+ */
+static bool __io_worker_unuse(struct io_wqe *wqe, struct io_worker *worker)
+{
+ bool dropped_lock = false;
+
+ if (worker->creds) {
+ revert_creds(worker->creds);
+ worker->creds = NULL;
+ }
+
+ if (current->files != worker->restore_files) {
+ __acquire(&wqe->lock);
+ spin_unlock_irq(&wqe->lock);
+ dropped_lock = true;
+
+ task_lock(current);
+ current->files = worker->restore_files;
+ task_unlock(current);
+ }
+
+ /*
+ * If we have an active mm, we need to drop the wq lock before unusing
+ * it. If we do, return true and let the caller retry the idle loop.
+ */
+ if (worker->mm) {
+ if (!dropped_lock) {
+ __acquire(&wqe->lock);
+ spin_unlock_irq(&wqe->lock);
+ dropped_lock = true;
+ }
+ __set_current_state(TASK_RUNNING);
+ set_fs(KERNEL_DS);
+ unuse_mm(worker->mm);
+ mmput(worker->mm);
+ worker->mm = NULL;
+ }
+
+ return dropped_lock;
+}
+
+static inline struct io_wqe_acct *io_work_get_acct(struct io_wqe *wqe,
+ struct io_wq_work *work)
+{
+ if (work->flags & IO_WQ_WORK_UNBOUND)
+ return &wqe->acct[IO_WQ_ACCT_UNBOUND];
+
+ return &wqe->acct[IO_WQ_ACCT_BOUND];
+}
+
+static inline struct io_wqe_acct *io_wqe_get_acct(struct io_wqe *wqe,
+ struct io_worker *worker)
+{
+ if (worker->flags & IO_WORKER_F_BOUND)
+ return &wqe->acct[IO_WQ_ACCT_BOUND];
+
+ return &wqe->acct[IO_WQ_ACCT_UNBOUND];
+}
+
+static void io_worker_exit(struct io_worker *worker)
+{
+ struct io_wqe *wqe = worker->wqe;
+ struct io_wqe_acct *acct = io_wqe_get_acct(wqe, worker);
+ unsigned nr_workers;
+
+ /*
+ * If we're not at zero, someone else is holding a brief reference
+ * to the worker. Wait for that to go away.
+ */
+ set_current_state(TASK_INTERRUPTIBLE);
+ if (!refcount_dec_and_test(&worker->ref))
+ schedule();
+ __set_current_state(TASK_RUNNING);
+
+ preempt_disable();
+ current->flags &= ~PF_IO_WORKER;
+ if (worker->flags & IO_WORKER_F_RUNNING)
+ atomic_dec(&acct->nr_running);
+ if (!(worker->flags & IO_WORKER_F_BOUND))
+ atomic_dec(&wqe->wq->user->processes);
+ worker->flags = 0;
+ preempt_enable();
+
+ spin_lock_irq(&wqe->lock);
+ hlist_nulls_del_rcu(&worker->nulls_node);
+ list_del_rcu(&worker->all_list);
+ if (__io_worker_unuse(wqe, worker)) {
+ __release(&wqe->lock);
+ spin_lock_irq(&wqe->lock);
+ }
+ acct->nr_workers--;
+ nr_workers = wqe->acct[IO_WQ_ACCT_BOUND].nr_workers +
+ wqe->acct[IO_WQ_ACCT_UNBOUND].nr_workers;
+ spin_unlock_irq(&wqe->lock);
+
+ /* all workers gone, wq exit can proceed */
+ if (!nr_workers && refcount_dec_and_test(&wqe->wq->refs))
+ complete(&wqe->wq->done);
+
+ kfree_rcu(worker, rcu);
+}
+
+static inline bool io_wqe_run_queue(struct io_wqe *wqe)
+ __must_hold(wqe->lock)
+{
+ if (!wq_list_empty(&wqe->work_list) &&
+ !(wqe->flags & IO_WQE_FLAG_STALLED))
+ return true;
+ return false;
+}
+
+/*
+ * Check head of free list for an available worker. If one isn't available,
+ * caller must wake up the wq manager to create one.
+ */
+static bool io_wqe_activate_free_worker(struct io_wqe *wqe)
+ __must_hold(RCU)
+{
+ struct hlist_nulls_node *n;
+ struct io_worker *worker;
+
+ n = rcu_dereference(hlist_nulls_first_rcu(&wqe->free_list));
+ if (is_a_nulls(n))
+ return false;
+
+ worker = hlist_nulls_entry(n, struct io_worker, nulls_node);
+ if (io_worker_get(worker)) {
+ wake_up(&worker->wait);
+ io_worker_release(worker);
+ return true;
+ }
+
+ return false;
+}
+
+/*
+ * We need a worker. If we find a free one, we're good. If not, and we're
+ * below the max number of workers, wake up the manager to create one.
+ */
+static void io_wqe_wake_worker(struct io_wqe *wqe, struct io_wqe_acct *acct)
+{
+ bool ret;
+
+ /*
+ * Most likely an attempt to queue unbounded work on an io_wq that
+ * wasn't setup with any unbounded workers.
+ */
+ WARN_ON_ONCE(!acct->max_workers);
+
+ rcu_read_lock();
+ ret = io_wqe_activate_free_worker(wqe);
+ rcu_read_unlock();
+
+ if (!ret && acct->nr_workers < acct->max_workers)
+ wake_up_process(wqe->wq->manager);
+}
+
+static void io_wqe_inc_running(struct io_wqe *wqe, struct io_worker *worker)
+{
+ struct io_wqe_acct *acct = io_wqe_get_acct(wqe, worker);
+
+ atomic_inc(&acct->nr_running);
+}
+
+static void io_wqe_dec_running(struct io_wqe *wqe, struct io_worker *worker)
+ __must_hold(wqe->lock)
+{
+ struct io_wqe_acct *acct = io_wqe_get_acct(wqe, worker);
+
+ if (atomic_dec_and_test(&acct->nr_running) && io_wqe_run_queue(wqe))
+ io_wqe_wake_worker(wqe, acct);
+}
+
+static void io_worker_start(struct io_wqe *wqe, struct io_worker *worker)
+{
+ allow_kernel_signal(SIGINT);
+
+ current->flags |= PF_IO_WORKER;
+
+ worker->flags |= (IO_WORKER_F_UP | IO_WORKER_F_RUNNING);
+ worker->restore_files = current->files;
+ io_wqe_inc_running(wqe, worker);
+}
+
+/*
+ * Worker will start processing some work. Move it to the busy list, if
+ * it's currently on the freelist
+ */
+static void __io_worker_busy(struct io_wqe *wqe, struct io_worker *worker,
+ struct io_wq_work *work)
+ __must_hold(wqe->lock)
+{
+ bool worker_bound, work_bound;
+
+ if (worker->flags & IO_WORKER_F_FREE) {
+ worker->flags &= ~IO_WORKER_F_FREE;
+ hlist_nulls_del_init_rcu(&worker->nulls_node);
+ hlist_nulls_add_head_rcu(&worker->nulls_node, &wqe->busy_list);
+ }
+
+ /*
+ * If worker is moving from bound to unbound (or vice versa), then
+ * ensure we update the running accounting.
+ */
+ worker_bound = (worker->flags & IO_WORKER_F_BOUND) != 0;
+ work_bound = (work->flags & IO_WQ_WORK_UNBOUND) == 0;
+ if (worker_bound != work_bound) {
+ io_wqe_dec_running(wqe, worker);
+ if (work_bound) {
+ worker->flags |= IO_WORKER_F_BOUND;
+ wqe->acct[IO_WQ_ACCT_UNBOUND].nr_workers--;
+ wqe->acct[IO_WQ_ACCT_BOUND].nr_workers++;
+ atomic_dec(&wqe->wq->user->processes);
+ } else {
+ worker->flags &= ~IO_WORKER_F_BOUND;
+ wqe->acct[IO_WQ_ACCT_UNBOUND].nr_workers++;
+ wqe->acct[IO_WQ_ACCT_BOUND].nr_workers--;
+ atomic_inc(&wqe->wq->user->processes);
+ }
+ io_wqe_inc_running(wqe, worker);
+ }
+}
+
+/*
+ * No work, worker going to sleep. Move to freelist, and unuse mm if we
+ * have one attached. Dropping the mm may potentially sleep, so we drop
+ * the lock in that case and return success. Since the caller has to
+ * retry the loop in that case (we changed task state), we don't regrab
+ * the lock if we return success.
+ */
+static bool __io_worker_idle(struct io_wqe *wqe, struct io_worker *worker)
+ __must_hold(wqe->lock)
+{
+ if (!(worker->flags & IO_WORKER_F_FREE)) {
+ worker->flags |= IO_WORKER_F_FREE;
+ hlist_nulls_del_init_rcu(&worker->nulls_node);
+ hlist_nulls_add_head_rcu(&worker->nulls_node, &wqe->free_list);
+ }
+
+ return __io_worker_unuse(wqe, worker);
+}
+
+static struct io_wq_work *io_get_next_work(struct io_wqe *wqe, unsigned *hash)
+ __must_hold(wqe->lock)
+{
+ struct io_wq_work_node *node, *prev;
+ struct io_wq_work *work;
+
+ wq_list_for_each(node, prev, &wqe->work_list) {
+ work = container_of(node, struct io_wq_work, list);
+
+ /* not hashed, can run anytime */
+ if (!(work->flags & IO_WQ_WORK_HASHED)) {
+ wq_node_del(&wqe->work_list, node, prev);
+ return work;
+ }
+
+ /* hashed, can run if not already running */
+ *hash = work->flags >> IO_WQ_HASH_SHIFT;
+ if (!(wqe->hash_map & BIT_ULL(*hash))) {
+ wqe->hash_map |= BIT_ULL(*hash);
+ wq_node_del(&wqe->work_list, node, prev);
+ return work;
+ }
+ }
+
+ return NULL;
+}
+
+static void io_worker_handle_work(struct io_worker *worker)
+ __releases(wqe->lock)
+{
+ struct io_wq_work *work, *old_work = NULL, *put_work = NULL;
+ struct io_wqe *wqe = worker->wqe;
+ struct io_wq *wq = wqe->wq;
+
+ do {
+ unsigned hash = -1U;
+
+ /*
+ * If we got some work, mark us as busy. If we didn't, but
+ * the list isn't empty, it means we stalled on hashed work.
+ * Mark us stalled so we don't keep looking for work when we
+ * can't make progress, any work completion or insertion will
+ * clear the stalled flag.
+ */
+ work = io_get_next_work(wqe, &hash);
+ if (work)
+ __io_worker_busy(wqe, worker, work);
+ else if (!wq_list_empty(&wqe->work_list))
+ wqe->flags |= IO_WQE_FLAG_STALLED;
+
+ spin_unlock_irq(&wqe->lock);
+ if (put_work && wq->put_work)
+ wq->put_work(old_work);
+ if (!work)
+ break;
+next:
+ /* flush any pending signals before assigning new work */
+ if (signal_pending(current))
+ flush_signals(current);
+
+ spin_lock_irq(&worker->lock);
+ worker->cur_work = work;
+ spin_unlock_irq(&worker->lock);
+
+ if (work->flags & IO_WQ_WORK_CB)
+ work->func(&work);
+
+ if ((work->flags & IO_WQ_WORK_NEEDS_FILES) &&
+ current->files != work->files) {
+ task_lock(current);
+ current->files = work->files;
+ task_unlock(current);
+ }
+ if ((work->flags & IO_WQ_WORK_NEEDS_USER) && !worker->mm &&
+ wq->mm && mmget_not_zero(wq->mm)) {
+ use_mm(wq->mm);
+ set_fs(USER_DS);
+ worker->mm = wq->mm;
+ }
+ if (!worker->creds)
+ worker->creds = override_creds(wq->creds);
+ if (test_bit(IO_WQ_BIT_CANCEL, &wq->state))
+ work->flags |= IO_WQ_WORK_CANCEL;
+ if (worker->mm)
+ work->flags |= IO_WQ_WORK_HAS_MM;
+
+ if (wq->get_work && !(work->flags & IO_WQ_WORK_INTERNAL)) {
+ put_work = work;
+ wq->get_work(work);
+ }
+
+ old_work = work;
+ work->func(&work);
+
+ spin_lock_irq(&worker->lock);
+ worker->cur_work = NULL;
+ spin_unlock_irq(&worker->lock);
+
+ spin_lock_irq(&wqe->lock);
+
+ if (hash != -1U) {
+ wqe->hash_map &= ~BIT_ULL(hash);
+ wqe->flags &= ~IO_WQE_FLAG_STALLED;
+ }
+ if (work && work != old_work) {
+ spin_unlock_irq(&wqe->lock);
+
+ if (put_work && wq->put_work) {
+ wq->put_work(put_work);
+ put_work = NULL;
+ }
+
+ /* dependent work not hashed */
+ hash = -1U;
+ goto next;
+ }
+ } while (1);
+}
+
+static int io_wqe_worker(void *data)
+{
+ struct io_worker *worker = data;
+ struct io_wqe *wqe = worker->wqe;
+ struct io_wq *wq = wqe->wq;
+ DEFINE_WAIT(wait);
+
+ io_worker_start(wqe, worker);
+
+ while (!test_bit(IO_WQ_BIT_EXIT, &wq->state)) {
+ prepare_to_wait(&worker->wait, &wait, TASK_INTERRUPTIBLE);
+
+ spin_lock_irq(&wqe->lock);
+ if (io_wqe_run_queue(wqe)) {
+ __set_current_state(TASK_RUNNING);
+ io_worker_handle_work(worker);
+ continue;
+ }
+ /* drops the lock on success, retry */
+ if (__io_worker_idle(wqe, worker)) {
+ __release(&wqe->lock);
+ continue;
+ }
+ spin_unlock_irq(&wqe->lock);
+ if (signal_pending(current))
+ flush_signals(current);
+ if (schedule_timeout(WORKER_IDLE_TIMEOUT))
+ continue;
+ /* timed out, exit unless we're the fixed worker */
+ if (test_bit(IO_WQ_BIT_EXIT, &wq->state) ||
+ !(worker->flags & IO_WORKER_F_FIXED))
+ break;
+ }
+
+ finish_wait(&worker->wait, &wait);
+
+ if (test_bit(IO_WQ_BIT_EXIT, &wq->state)) {
+ spin_lock_irq(&wqe->lock);
+ if (!wq_list_empty(&wqe->work_list))
+ io_worker_handle_work(worker);
+ else
+ spin_unlock_irq(&wqe->lock);
+ }
+
+ io_worker_exit(worker);
+ return 0;
+}
+
+/*
+ * Called when a worker is scheduled in. Mark us as currently running.
+ */
+void io_wq_worker_running(struct task_struct *tsk)
+{
+ struct io_worker *worker = kthread_data(tsk);
+ struct io_wqe *wqe = worker->wqe;
+
+ if (!(worker->flags & IO_WORKER_F_UP))
+ return;
+ if (worker->flags & IO_WORKER_F_RUNNING)
+ return;
+ worker->flags |= IO_WORKER_F_RUNNING;
+ io_wqe_inc_running(wqe, worker);
+}
+
+/*
+ * Called when worker is going to sleep. If there are no workers currently
+ * running and we have work pending, wake up a free one or have the manager
+ * set one up.
+ */
+void io_wq_worker_sleeping(struct task_struct *tsk)
+{
+ struct io_worker *worker = kthread_data(tsk);
+ struct io_wqe *wqe = worker->wqe;
+
+ if (!(worker->flags & IO_WORKER_F_UP))
+ return;
+ if (!(worker->flags & IO_WORKER_F_RUNNING))
+ return;
+
+ worker->flags &= ~IO_WORKER_F_RUNNING;
+
+ spin_lock_irq(&wqe->lock);
+ io_wqe_dec_running(wqe, worker);
+ spin_unlock_irq(&wqe->lock);
+}
+
+static bool create_io_worker(struct io_wq *wq, struct io_wqe *wqe, int index)
+{
+ struct io_wqe_acct *acct =&wqe->acct[index];
+ struct io_worker *worker;
+
+ worker = kzalloc_node(sizeof(*worker), GFP_KERNEL, wqe->node);
+ if (!worker)
+ return false;
+
+ refcount_set(&worker->ref, 1);
+ worker->nulls_node.pprev = NULL;
+ init_waitqueue_head(&worker->wait);
+ worker->wqe = wqe;
+ spin_lock_init(&worker->lock);
+
+ worker->task = kthread_create_on_node(io_wqe_worker, worker, wqe->node,
+ "io_wqe_worker-%d/%d", index, wqe->node);
+ if (IS_ERR(worker->task)) {
+ kfree(worker);
+ return false;
+ }
+
+ spin_lock_irq(&wqe->lock);
+ hlist_nulls_add_head_rcu(&worker->nulls_node, &wqe->free_list);
+ list_add_tail_rcu(&worker->all_list, &wqe->all_list);
+ worker->flags |= IO_WORKER_F_FREE;
+ if (index == IO_WQ_ACCT_BOUND)
+ worker->flags |= IO_WORKER_F_BOUND;
+ if (!acct->nr_workers && (worker->flags & IO_WORKER_F_BOUND))
+ worker->flags |= IO_WORKER_F_FIXED;
+ acct->nr_workers++;
+ spin_unlock_irq(&wqe->lock);
+
+ if (index == IO_WQ_ACCT_UNBOUND)
+ atomic_inc(&wq->user->processes);
+
+ wake_up_process(worker->task);
+ return true;
+}
+
+static inline bool io_wqe_need_worker(struct io_wqe *wqe, int index)
+ __must_hold(wqe->lock)
+{
+ struct io_wqe_acct *acct = &wqe->acct[index];
+
+ /* if we have available workers or no work, no need */
+ if (!hlist_nulls_empty(&wqe->free_list) || !io_wqe_run_queue(wqe))
+ return false;
+ return acct->nr_workers < acct->max_workers;
+}
+
+/*
+ * Manager thread. Tasked with creating new workers, if we need them.
+ */
+static int io_wq_manager(void *data)
+{
+ struct io_wq *wq = data;
+ int workers_to_create = num_possible_nodes();
+ int node;
+
+ /* create fixed workers */
+ refcount_set(&wq->refs, workers_to_create);
+ for_each_node(node) {
+ if (!create_io_worker(wq, wq->wqes[node], IO_WQ_ACCT_BOUND))
+ goto err;
+ workers_to_create--;
+ }
+
+ complete(&wq->done);
+
+ while (!kthread_should_stop()) {
+ for_each_node(node) {
+ struct io_wqe *wqe = wq->wqes[node];
+ bool fork_worker[2] = { false, false };
+
+ spin_lock_irq(&wqe->lock);
+ if (io_wqe_need_worker(wqe, IO_WQ_ACCT_BOUND))
+ fork_worker[IO_WQ_ACCT_BOUND] = true;
+ if (io_wqe_need_worker(wqe, IO_WQ_ACCT_UNBOUND))
+ fork_worker[IO_WQ_ACCT_UNBOUND] = true;
+ spin_unlock_irq(&wqe->lock);
+ if (fork_worker[IO_WQ_ACCT_BOUND])
+ create_io_worker(wq, wqe, IO_WQ_ACCT_BOUND);
+ if (fork_worker[IO_WQ_ACCT_UNBOUND])
+ create_io_worker(wq, wqe, IO_WQ_ACCT_UNBOUND);
+ }
+ set_current_state(TASK_INTERRUPTIBLE);
+ schedule_timeout(HZ);
+ }
+
+ return 0;
+err:
+ set_bit(IO_WQ_BIT_ERROR, &wq->state);
+ set_bit(IO_WQ_BIT_EXIT, &wq->state);
+ if (refcount_sub_and_test(workers_to_create, &wq->refs))
+ complete(&wq->done);
+ return 0;
+}
+
+static bool io_wq_can_queue(struct io_wqe *wqe, struct io_wqe_acct *acct,
+ struct io_wq_work *work)
+{
+ bool free_worker;
+
+ if (!(work->flags & IO_WQ_WORK_UNBOUND))
+ return true;
+ if (atomic_read(&acct->nr_running))
+ return true;
+
+ rcu_read_lock();
+ free_worker = !hlist_nulls_empty(&wqe->free_list);
+ rcu_read_unlock();
+ if (free_worker)
+ return true;
+
+ if (atomic_read(&wqe->wq->user->processes) >= acct->max_workers &&
+ !(capable(CAP_SYS_RESOURCE) || capable(CAP_SYS_ADMIN)))
+ return false;
+
+ return true;
+}
+
+static void io_wqe_enqueue(struct io_wqe *wqe, struct io_wq_work *work)
+{
+ struct io_wqe_acct *acct = io_work_get_acct(wqe, work);
+ unsigned long flags;
+
+ /*
+ * Do early check to see if we need a new unbound worker, and if we do,
+ * if we're allowed to do so. This isn't 100% accurate as there's a
+ * gap between this check and incrementing the value, but that's OK.
+ * It's close enough to not be an issue, fork() has the same delay.
+ */
+ if (unlikely(!io_wq_can_queue(wqe, acct, work))) {
+ work->flags |= IO_WQ_WORK_CANCEL;
+ work->func(&work);
+ return;
+ }
+
+ spin_lock_irqsave(&wqe->lock, flags);
+ wq_list_add_tail(&work->list, &wqe->work_list);
+ wqe->flags &= ~IO_WQE_FLAG_STALLED;
+ spin_unlock_irqrestore(&wqe->lock, flags);
+
+ if (!atomic_read(&acct->nr_running))
+ io_wqe_wake_worker(wqe, acct);
+}
+
+void io_wq_enqueue(struct io_wq *wq, struct io_wq_work *work)
+{
+ struct io_wqe *wqe = wq->wqes[numa_node_id()];
+
+ io_wqe_enqueue(wqe, work);
+}
+
+/*
+ * Enqueue work, hashed by some key. Work items that hash to the same value
+ * will not be done in parallel. Used to limit concurrent writes, generally
+ * hashed by inode.
+ */
+void io_wq_enqueue_hashed(struct io_wq *wq, struct io_wq_work *work, void *val)
+{
+ struct io_wqe *wqe = wq->wqes[numa_node_id()];
+ unsigned bit;
+
+
+ bit = hash_ptr(val, IO_WQ_HASH_ORDER);
+ work->flags |= (IO_WQ_WORK_HASHED | (bit << IO_WQ_HASH_SHIFT));
+ io_wqe_enqueue(wqe, work);
+}
+
+static bool io_wqe_worker_send_sig(struct io_worker *worker, void *data)
+{
+ send_sig(SIGINT, worker->task, 1);
+ return false;
+}
+
+/*
+ * Iterate the passed in list and call the specific function for each
+ * worker that isn't exiting
+ */
+static bool io_wq_for_each_worker(struct io_wqe *wqe,
+ bool (*func)(struct io_worker *, void *),
+ void *data)
+{
+ struct io_worker *worker;
+ bool ret = false;
+
+ list_for_each_entry_rcu(worker, &wqe->all_list, all_list) {
+ if (io_worker_get(worker)) {
+ ret = func(worker, data);
+ io_worker_release(worker);
+ if (ret)
+ break;
+ }
+ }
+
+ return ret;
+}
+
+void io_wq_cancel_all(struct io_wq *wq)
+{
+ int node;
+
+ set_bit(IO_WQ_BIT_CANCEL, &wq->state);
+
+ /*
+ * Browse both lists, as there's a gap between handing work off
+ * to a worker and the worker putting itself on the busy_list
+ */
+ rcu_read_lock();
+ for_each_node(node) {
+ struct io_wqe *wqe = wq->wqes[node];
+
+ io_wq_for_each_worker(wqe, io_wqe_worker_send_sig, NULL);
+ }
+ rcu_read_unlock();
+}
+
+struct io_cb_cancel_data {
+ struct io_wqe *wqe;
+ work_cancel_fn *cancel;
+ void *caller_data;
+};
+
+static bool io_work_cancel(struct io_worker *worker, void *cancel_data)
+{
+ struct io_cb_cancel_data *data = cancel_data;
+ unsigned long flags;
+ bool ret = false;
+
+ /*
+ * Hold the lock to avoid ->cur_work going out of scope, caller
+ * may dereference the passed in work.
+ */
+ spin_lock_irqsave(&worker->lock, flags);
+ if (worker->cur_work &&
+ data->cancel(worker->cur_work, data->caller_data)) {
+ send_sig(SIGINT, worker->task, 1);
+ ret = true;
+ }
+ spin_unlock_irqrestore(&worker->lock, flags);
+
+ return ret;
+}
+
+static enum io_wq_cancel io_wqe_cancel_cb_work(struct io_wqe *wqe,
+ work_cancel_fn *cancel,
+ void *cancel_data)
+{
+ struct io_cb_cancel_data data = {
+ .wqe = wqe,
+ .cancel = cancel,
+ .caller_data = cancel_data,
+ };
+ struct io_wq_work_node *node, *prev;
+ struct io_wq_work *work;
+ unsigned long flags;
+ bool found = false;
+
+ spin_lock_irqsave(&wqe->lock, flags);
+ wq_list_for_each(node, prev, &wqe->work_list) {
+ work = container_of(node, struct io_wq_work, list);
+
+ if (cancel(work, cancel_data)) {
+ wq_node_del(&wqe->work_list, node, prev);
+ found = true;
+ break;
+ }
+ }
+ spin_unlock_irqrestore(&wqe->lock, flags);
+
+ if (found) {
+ work->flags |= IO_WQ_WORK_CANCEL;
+ work->func(&work);
+ return IO_WQ_CANCEL_OK;
+ }
+
+ rcu_read_lock();
+ found = io_wq_for_each_worker(wqe, io_work_cancel, &data);
+ rcu_read_unlock();
+ return found ? IO_WQ_CANCEL_RUNNING : IO_WQ_CANCEL_NOTFOUND;
+}
+
+enum io_wq_cancel io_wq_cancel_cb(struct io_wq *wq, work_cancel_fn *cancel,
+ void *data)
+{
+ enum io_wq_cancel ret = IO_WQ_CANCEL_NOTFOUND;
+ int node;
+
+ for_each_node(node) {
+ struct io_wqe *wqe = wq->wqes[node];
+
+ ret = io_wqe_cancel_cb_work(wqe, cancel, data);
+ if (ret != IO_WQ_CANCEL_NOTFOUND)
+ break;
+ }
+
+ return ret;
+}
+
+static bool io_wq_worker_cancel(struct io_worker *worker, void *data)
+{
+ struct io_wq_work *work = data;
+ unsigned long flags;
+ bool ret = false;
+
+ if (worker->cur_work != work)
+ return false;
+
+ spin_lock_irqsave(&worker->lock, flags);
+ if (worker->cur_work == work) {
+ send_sig(SIGINT, worker->task, 1);
+ ret = true;
+ }
+ spin_unlock_irqrestore(&worker->lock, flags);
+
+ return ret;
+}
+
+static enum io_wq_cancel io_wqe_cancel_work(struct io_wqe *wqe,
+ struct io_wq_work *cwork)
+{
+ struct io_wq_work_node *node, *prev;
+ struct io_wq_work *work;
+ unsigned long flags;
+ bool found = false;
+
+ cwork->flags |= IO_WQ_WORK_CANCEL;
+
+ /*
+ * First check pending list, if we're lucky we can just remove it
+ * from there. CANCEL_OK means that the work is returned as-new,
+ * no completion will be posted for it.
+ */
+ spin_lock_irqsave(&wqe->lock, flags);
+ wq_list_for_each(node, prev, &wqe->work_list) {
+ work = container_of(node, struct io_wq_work, list);
+
+ if (work == cwork) {
+ wq_node_del(&wqe->work_list, node, prev);
+ found = true;
+ break;
+ }
+ }
+ spin_unlock_irqrestore(&wqe->lock, flags);
+
+ if (found) {
+ work->flags |= IO_WQ_WORK_CANCEL;
+ work->func(&work);
+ return IO_WQ_CANCEL_OK;
+ }
+
+ /*
+ * Now check if a free (going busy) or busy worker has the work
+ * currently running. If we find it there, we'll return CANCEL_RUNNING
+ * as an indication that we attempte to signal cancellation. The
+ * completion will run normally in this case.
+ */
+ rcu_read_lock();
+ found = io_wq_for_each_worker(wqe, io_wq_worker_cancel, cwork);
+ rcu_read_unlock();
+ return found ? IO_WQ_CANCEL_RUNNING : IO_WQ_CANCEL_NOTFOUND;
+}
+
+enum io_wq_cancel io_wq_cancel_work(struct io_wq *wq, struct io_wq_work *cwork)
+{
+ enum io_wq_cancel ret = IO_WQ_CANCEL_NOTFOUND;
+ int node;
+
+ for_each_node(node) {
+ struct io_wqe *wqe = wq->wqes[node];
+
+ ret = io_wqe_cancel_work(wqe, cwork);
+ if (ret != IO_WQ_CANCEL_NOTFOUND)
+ break;
+ }
+
+ return ret;
+}
+
+struct io_wq_flush_data {
+ struct io_wq_work work;
+ struct completion done;
+};
+
+static void io_wq_flush_func(struct io_wq_work **workptr)
+{
+ struct io_wq_work *work = *workptr;
+ struct io_wq_flush_data *data;
+
+ data = container_of(work, struct io_wq_flush_data, work);
+ complete(&data->done);
+}
+
+/*
+ * Doesn't wait for previously queued work to finish. When this completes,
+ * it just means that previously queued work was started.
+ */
+void io_wq_flush(struct io_wq *wq)
+{
+ struct io_wq_flush_data data;
+ int node;
+
+ for_each_node(node) {
+ struct io_wqe *wqe = wq->wqes[node];
+
+ init_completion(&data.done);
+ INIT_IO_WORK(&data.work, io_wq_flush_func);
+ data.work.flags |= IO_WQ_WORK_INTERNAL;
+ io_wqe_enqueue(wqe, &data.work);
+ wait_for_completion(&data.done);
+ }
+}
+
+struct io_wq *io_wq_create(unsigned bounded, struct io_wq_data *data)
+{
+ int ret = -ENOMEM, node;
+ struct io_wq *wq;
+
+ wq = kzalloc(sizeof(*wq), GFP_KERNEL);
+ if (!wq)
+ return ERR_PTR(-ENOMEM);
+
+ wq->wqes = kcalloc(nr_node_ids, sizeof(struct io_wqe *), GFP_KERNEL);
+ if (!wq->wqes) {
+ kfree(wq);
+ return ERR_PTR(-ENOMEM);
+ }
+
+ wq->get_work = data->get_work;
+ wq->put_work = data->put_work;
+
+ /* caller must already hold a reference to this */
+ wq->user = data->user;
+ wq->creds = data->creds;
+
+ for_each_node(node) {
+ struct io_wqe *wqe;
+
+ wqe = kzalloc_node(sizeof(struct io_wqe), GFP_KERNEL, node);
+ if (!wqe)
+ goto err;
+ wq->wqes[node] = wqe;
+ wqe->node = node;
+ wqe->acct[IO_WQ_ACCT_BOUND].max_workers = bounded;
+ atomic_set(&wqe->acct[IO_WQ_ACCT_BOUND].nr_running, 0);
+ if (wq->user) {
+ wqe->acct[IO_WQ_ACCT_UNBOUND].max_workers =
+ task_rlimit(current, RLIMIT_NPROC);
+ }
+ atomic_set(&wqe->acct[IO_WQ_ACCT_UNBOUND].nr_running, 0);
+ wqe->node = node;
+ wqe->wq = wq;
+ spin_lock_init(&wqe->lock);
+ INIT_WQ_LIST(&wqe->work_list);
+ INIT_HLIST_NULLS_HEAD(&wqe->free_list, 0);
+ INIT_HLIST_NULLS_HEAD(&wqe->busy_list, 1);
+ INIT_LIST_HEAD(&wqe->all_list);
+ }
+
+ init_completion(&wq->done);
+
+ /* caller must have already done mmgrab() on this mm */
+ wq->mm = data->mm;
+
+ wq->manager = kthread_create(io_wq_manager, wq, "io_wq_manager");
+ if (!IS_ERR(wq->manager)) {
+ wake_up_process(wq->manager);
+ wait_for_completion(&wq->done);
+ if (test_bit(IO_WQ_BIT_ERROR, &wq->state)) {
+ ret = -ENOMEM;
+ goto err;
+ }
+ reinit_completion(&wq->done);
+ return wq;
+ }
+
+ ret = PTR_ERR(wq->manager);
+ complete(&wq->done);
+err:
+ for_each_node(node)
+ kfree(wq->wqes[node]);
+ kfree(wq->wqes);
+ kfree(wq);
+ return ERR_PTR(ret);
+}
+
+static bool io_wq_worker_wake(struct io_worker *worker, void *data)
+{
+ wake_up_process(worker->task);
+ return false;
+}
+
+void io_wq_destroy(struct io_wq *wq)
+{
+ int node;
+
+ set_bit(IO_WQ_BIT_EXIT, &wq->state);
+ if (wq->manager)
+ kthread_stop(wq->manager);
+
+ rcu_read_lock();
+ for_each_node(node)
+ io_wq_for_each_worker(wq->wqes[node], io_wq_worker_wake, NULL);
+ rcu_read_unlock();
+
+ wait_for_completion(&wq->done);
+
+ for_each_node(node)
+ kfree(wq->wqes[node]);
+ kfree(wq->wqes);
+ kfree(wq);
+}
diff --git a/fs/io-wq.h b/fs/io-wq.h
new file mode 100644
index 000000000000..7c333a28e2a7
--- /dev/null
+++ b/fs/io-wq.h
@@ -0,0 +1,124 @@
+#ifndef INTERNAL_IO_WQ_H
+#define INTERNAL_IO_WQ_H
+
+struct io_wq;
+
+enum {
+ IO_WQ_WORK_CANCEL = 1,
+ IO_WQ_WORK_HAS_MM = 2,
+ IO_WQ_WORK_HASHED = 4,
+ IO_WQ_WORK_NEEDS_USER = 8,
+ IO_WQ_WORK_NEEDS_FILES = 16,
+ IO_WQ_WORK_UNBOUND = 32,
+ IO_WQ_WORK_INTERNAL = 64,
+ IO_WQ_WORK_CB = 128,
+
+ IO_WQ_HASH_SHIFT = 24, /* upper 8 bits are used for hash key */
+};
+
+enum io_wq_cancel {
+ IO_WQ_CANCEL_OK, /* cancelled before started */
+ IO_WQ_CANCEL_RUNNING, /* found, running, and attempted cancelled */
+ IO_WQ_CANCEL_NOTFOUND, /* work not found */
+};
+
+struct io_wq_work_node {
+ struct io_wq_work_node *next;
+};
+
+struct io_wq_work_list {
+ struct io_wq_work_node *first;
+ struct io_wq_work_node *last;
+};
+
+static inline void wq_list_add_tail(struct io_wq_work_node *node,
+ struct io_wq_work_list *list)
+{
+ if (!list->first) {
+ list->first = list->last = node;
+ } else {
+ list->last->next = node;
+ list->last = node;
+ }
+}
+
+static inline void wq_node_del(struct io_wq_work_list *list,
+ struct io_wq_work_node *node,
+ struct io_wq_work_node *prev)
+{
+ if (node == list->first)
+ list->first = node->next;
+ if (node == list->last)
+ list->last = prev;
+ if (prev)
+ prev->next = node->next;
+ node->next = NULL;
+}
+
+#define wq_list_for_each(pos, prv, head) \
+ for (pos = (head)->first, prv = NULL; pos; prv = pos, pos = (pos)->next)
+
+#define wq_list_empty(list) ((list)->first == NULL)
+#define INIT_WQ_LIST(list) do { \
+ (list)->first = NULL; \
+ (list)->last = NULL; \
+} while (0)
+
+struct io_wq_work {
+ union {
+ struct io_wq_work_node list;
+ void *data;
+ };
+ void (*func)(struct io_wq_work **);
+ struct files_struct *files;
+ unsigned flags;
+};
+
+#define INIT_IO_WORK(work, _func) \
+ do { \
+ (work)->list.next = NULL; \
+ (work)->func = _func; \
+ (work)->flags = 0; \
+ (work)->files = NULL; \
+ } while (0) \
+
+typedef void (get_work_fn)(struct io_wq_work *);
+typedef void (put_work_fn)(struct io_wq_work *);
+
+struct io_wq_data {
+ struct mm_struct *mm;
+ struct user_struct *user;
+ const struct cred *creds;
+
+ get_work_fn *get_work;
+ put_work_fn *put_work;
+};
+
+struct io_wq *io_wq_create(unsigned bounded, struct io_wq_data *data);
+void io_wq_destroy(struct io_wq *wq);
+
+void io_wq_enqueue(struct io_wq *wq, struct io_wq_work *work);
+void io_wq_enqueue_hashed(struct io_wq *wq, struct io_wq_work *work, void *val);
+void io_wq_flush(struct io_wq *wq);
+
+void io_wq_cancel_all(struct io_wq *wq);
+enum io_wq_cancel io_wq_cancel_work(struct io_wq *wq, struct io_wq_work *cwork);
+
+typedef bool (work_cancel_fn)(struct io_wq_work *, void *);
+
+enum io_wq_cancel io_wq_cancel_cb(struct io_wq *wq, work_cancel_fn *cancel,
+ void *data);
+
+#if defined(CONFIG_IO_WQ)
+extern void io_wq_worker_sleeping(struct task_struct *);
+extern void io_wq_worker_running(struct task_struct *);
+#else
+static inline void io_wq_worker_sleeping(struct task_struct *tsk)
+{
+}
+static inline void io_wq_worker_running(struct task_struct *tsk)
+{
+}
+#endif /* CONFIG_IO_WQ */
+
+#endif /* INTERNAL_IO_WQ_H */
diff --git a/fs/io_uring.c b/fs/io_uring.c
index 76fdbe84aff5..405be10da73d 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -56,7 +56,6 @@
#include <linux/mmu_context.h>
#include <linux/percpu.h>
#include <linux/slab.h>
-#include <linux/workqueue.h>
#include <linux/kthread.h>
#include <linux/blkdev.h>
#include <linux/bvec.h>
@@ -70,13 +69,26 @@
#include <linux/nospec.h>
#include <linux/sizes.h>
#include <linux/hugetlb.h>
+#include <linux/highmem.h>
+
+#define CREATE_TRACE_POINTS
+#include <trace/events/io_uring.h>
#include <uapi/linux/io_uring.h>
#include "internal.h"
+#include "io-wq.h"
#define IORING_MAX_ENTRIES 32768
-#define IORING_MAX_FIXED_FILES 1024
+#define IORING_MAX_CQ_ENTRIES (2 * IORING_MAX_ENTRIES)
+
+/*
+ * Shift of 9 is 512 entries, or exactly one page on 64-bit archs
+ */
+#define IORING_FILE_TABLE_SHIFT 9
+#define IORING_MAX_FILES_TABLE (1U << IORING_FILE_TABLE_SHIFT)
+#define IORING_FILE_TABLE_MASK (IORING_MAX_FILES_TABLE - 1)
+#define IORING_MAX_FIXED_FILES (64 * IORING_MAX_FILES_TABLE)
struct io_uring {
u32 head ____cacheline_aligned_in_smp;
@@ -133,7 +145,7 @@ struct io_rings {
/*
* Number of completion events lost because the queue was full;
* this should be avoided by the application by making sure
- * there are not more requests pending thatn there is space in
+ * there are not more requests pending than there is space in
* the completion queue.
*
* Written by the kernel, shouldn't be modified by the
@@ -161,14 +173,8 @@ struct io_mapped_ubuf {
unsigned int nr_bvecs;
};
-struct async_list {
- spinlock_t lock;
- atomic_t cnt;
- struct list_head list;
-
- struct file *file;
- off_t io_start;
- size_t io_len;
+struct fixed_file_table {
+ struct file **files;
};
struct io_ring_ctx {
@@ -180,6 +186,8 @@ struct io_ring_ctx {
unsigned int flags;
bool compat;
bool account_mem;
+ bool cq_overflow_flushed;
+ bool drain_next;
/*
* Ring buffer of indices into array of io_uring_sqe, which is
@@ -197,37 +205,31 @@ struct io_ring_ctx {
unsigned sq_entries;
unsigned sq_mask;
unsigned sq_thread_idle;
+ unsigned cached_sq_dropped;
+ atomic_t cached_cq_overflow;
struct io_uring_sqe *sq_sqes;
struct list_head defer_list;
struct list_head timeout_list;
+ struct list_head cq_overflow_list;
+
+ wait_queue_head_t inflight_wait;
} ____cacheline_aligned_in_smp;
+ struct io_rings *rings;
+
/* IO offload */
- struct workqueue_struct *sqo_wq[2];
+ struct io_wq *io_wq;
struct task_struct *sqo_thread; /* if using sq thread polling */
struct mm_struct *sqo_mm;
wait_queue_head_t sqo_wait;
- struct completion sqo_thread_started;
-
- struct {
- unsigned cached_cq_tail;
- unsigned cq_entries;
- unsigned cq_mask;
- struct wait_queue_head cq_wait;
- struct fasync_struct *cq_fasync;
- struct eventfd_ctx *cq_ev_fd;
- atomic_t cq_timeouts;
- } ____cacheline_aligned_in_smp;
-
- struct io_rings *rings;
/*
* If used, fixed file set. Writers must ensure that ->refs is dead,
* readers must ensure that ->refs is alive as long as the file* is
* used. Only updated through io_uring_register(2).
*/
- struct file **user_files;
+ struct fixed_file_table *file_table;
unsigned nr_user_files;
/* if used, fixed mapped user buffers */
@@ -236,7 +238,27 @@ struct io_ring_ctx {
struct user_struct *user;
- struct completion ctx_done;
+ const struct cred *creds;
+
+ /* 0 is for ctx quiesce/reinit/free, 1 is for sqo_thread started */
+ struct completion *completions;
+
+ /* if all else fails... */
+ struct io_kiocb *fallback_req;
+
+#if defined(CONFIG_UNIX)
+ struct socket *ring_sock;
+#endif
+
+ struct {
+ unsigned cached_cq_tail;
+ unsigned cq_entries;
+ unsigned cq_mask;
+ atomic_t cq_timeouts;
+ struct wait_queue_head cq_wait;
+ struct fasync_struct *cq_fasync;
+ struct eventfd_ctx *cq_ev_fd;
+ } ____cacheline_aligned_in_smp;
struct {
struct mutex uring_lock;
@@ -253,23 +275,12 @@ struct io_ring_ctx {
* manipulate the list, hence no extra locking is needed there.
*/
struct list_head poll_list;
- struct list_head cancel_list;
- } ____cacheline_aligned_in_smp;
+ struct hlist_head *cancel_hash;
+ unsigned cancel_hash_bits;
- struct async_list pending_async[2];
-
-#if defined(CONFIG_UNIX)
- struct socket *ring_sock;
-#endif
-};
-
-struct sqe_submit {
- const struct io_uring_sqe *sqe;
- unsigned short index;
- u32 sequence;
- bool has_user;
- bool needs_lock;
- bool needs_fixed_file;
+ spinlock_t inflight_lock;
+ struct list_head inflight_list;
+ } ____cacheline_aligned_in_smp;
};
/*
@@ -282,12 +293,43 @@ struct io_poll_iocb {
__poll_t events;
bool done;
bool canceled;
- struct wait_queue_entry wait;
+ struct wait_queue_entry *wait;
};
-struct io_timeout {
- struct file *file;
+struct io_timeout_data {
+ struct io_kiocb *req;
struct hrtimer timer;
+ struct timespec64 ts;
+ enum hrtimer_mode mode;
+ u32 seq_offset;
+};
+
+struct io_async_connect {
+ struct sockaddr_storage address;
+};
+
+struct io_async_msghdr {
+ struct iovec fast_iov[UIO_FASTIOV];
+ struct iovec *iov;
+ struct sockaddr __user *uaddr;
+ struct msghdr msg;
+};
+
+struct io_async_rw {
+ struct iovec fast_iov[UIO_FASTIOV];
+ struct iovec *iov;
+ ssize_t nr_segs;
+ ssize_t size;
+};
+
+struct io_async_ctx {
+ struct io_uring_sqe sqe;
+ union {
+ struct io_async_rw rw;
+ struct io_async_msghdr msg;
+ struct io_async_connect connect;
+ struct io_timeout_data timeout;
+ };
};
/*
@@ -301,32 +343,47 @@ struct io_kiocb {
struct file *file;
struct kiocb rw;
struct io_poll_iocb poll;
- struct io_timeout timeout;
};
- struct sqe_submit submit;
+ const struct io_uring_sqe *sqe;
+ struct io_async_ctx *io;
+ struct file *ring_file;
+ int ring_fd;
+ bool has_user;
+ bool in_async;
+ bool needs_fixed_file;
struct io_ring_ctx *ctx;
- struct list_head list;
+ union {
+ struct list_head list;
+ struct hlist_node hash_node;
+ };
struct list_head link_list;
unsigned int flags;
refcount_t refs;
#define REQ_F_NOWAIT 1 /* must not punt to workers */
#define REQ_F_IOPOLL_COMPLETED 2 /* polled IO has completed */
#define REQ_F_FIXED_FILE 4 /* ctx owns file */
-#define REQ_F_SEQ_PREV 8 /* sequential with previous */
+#define REQ_F_LINK_NEXT 8 /* already grabbed next link */
#define REQ_F_IO_DRAIN 16 /* drain existing IO first */
#define REQ_F_IO_DRAINED 32 /* drain done */
#define REQ_F_LINK 64 /* linked sqes */
-#define REQ_F_LINK_DONE 128 /* linked sqes done */
+#define REQ_F_LINK_TIMEOUT 128 /* has linked timeout */
#define REQ_F_FAIL_LINK 256 /* fail rest of links */
-#define REQ_F_SHADOW_DRAIN 512 /* link-drain shadow req */
+#define REQ_F_DRAIN_LINK 512 /* link should be fully drained */
#define REQ_F_TIMEOUT 1024 /* timeout request */
+#define REQ_F_ISREG 2048 /* regular file */
+#define REQ_F_MUST_PUNT 4096 /* must be punted even for NONBLOCK */
+#define REQ_F_TIMEOUT_NOSEQ 8192 /* no timeout sequence */
+#define REQ_F_INFLIGHT 16384 /* on inflight list */
+#define REQ_F_COMP_LOCKED 32768 /* completion under lock */
u64 user_data;
u32 result;
u32 sequence;
- struct work_struct work;
+ struct list_head inflight_entry;
+
+ struct io_wq_work work;
};
#define IO_PLUG_THRESHOLD 2
@@ -352,10 +409,14 @@ struct io_submit_state {
unsigned int ios_left;
};
-static void io_sq_wq_submit_work(struct work_struct *work);
-static void io_cqring_fill_event(struct io_ring_ctx *ctx, u64 ki_user_data,
- long res);
+static void io_wq_submit_work(struct io_wq_work **workptr);
+static void io_cqring_fill_event(struct io_kiocb *req, long res);
static void __io_free_req(struct io_kiocb *req);
+static void io_put_req(struct io_kiocb *req);
+static void io_double_put_req(struct io_kiocb *req);
+static void __io_double_put_req(struct io_kiocb *req);
+static struct io_kiocb *io_prep_linked_timeout(struct io_kiocb *req);
+static void io_queue_linked_timeout(struct io_kiocb *req);
static struct kmem_cache *req_cachep;
@@ -378,56 +439,83 @@ static void io_ring_ctx_ref_free(struct percpu_ref *ref)
{
struct io_ring_ctx *ctx = container_of(ref, struct io_ring_ctx, refs);
- complete(&ctx->ctx_done);
+ complete(&ctx->completions[0]);
}
static struct io_ring_ctx *io_ring_ctx_alloc(struct io_uring_params *p)
{
struct io_ring_ctx *ctx;
- int i;
+ int hash_bits;
ctx = kzalloc(sizeof(*ctx), GFP_KERNEL);
if (!ctx)
return NULL;
+ ctx->fallback_req = kmem_cache_alloc(req_cachep, GFP_KERNEL);
+ if (!ctx->fallback_req)
+ goto err;
+
+ ctx->completions = kmalloc(2 * sizeof(struct completion), GFP_KERNEL);
+ if (!ctx->completions)
+ goto err;
+
+ /*
+ * Use 5 bits less than the max cq entries, that should give us around
+ * 32 entries per hash list if totally full and uniformly spread.
+ */
+ hash_bits = ilog2(p->cq_entries);
+ hash_bits -= 5;
+ if (hash_bits <= 0)
+ hash_bits = 1;
+ ctx->cancel_hash_bits = hash_bits;
+ ctx->cancel_hash = kmalloc((1U << hash_bits) * sizeof(struct hlist_head),
+ GFP_KERNEL);
+ if (!ctx->cancel_hash)
+ goto err;
+ __hash_init(ctx->cancel_hash, 1U << hash_bits);
+
if (percpu_ref_init(&ctx->refs, io_ring_ctx_ref_free,
- PERCPU_REF_ALLOW_REINIT, GFP_KERNEL)) {
- kfree(ctx);
- return NULL;
- }
+ PERCPU_REF_ALLOW_REINIT, GFP_KERNEL))
+ goto err;
ctx->flags = p->flags;
init_waitqueue_head(&ctx->cq_wait);
- init_completion(&ctx->ctx_done);
- init_completion(&ctx->sqo_thread_started);
+ INIT_LIST_HEAD(&ctx->cq_overflow_list);
+ init_completion(&ctx->completions[0]);
+ init_completion(&ctx->completions[1]);
mutex_init(&ctx->uring_lock);
init_waitqueue_head(&ctx->wait);
- for (i = 0; i < ARRAY_SIZE(ctx->pending_async); i++) {
- spin_lock_init(&ctx->pending_async[i].lock);
- INIT_LIST_HEAD(&ctx->pending_async[i].list);
- atomic_set(&ctx->pending_async[i].cnt, 0);
- }
spin_lock_init(&ctx->completion_lock);
INIT_LIST_HEAD(&ctx->poll_list);
- INIT_LIST_HEAD(&ctx->cancel_list);
INIT_LIST_HEAD(&ctx->defer_list);
INIT_LIST_HEAD(&ctx->timeout_list);
+ init_waitqueue_head(&ctx->inflight_wait);
+ spin_lock_init(&ctx->inflight_lock);
+ INIT_LIST_HEAD(&ctx->inflight_list);
return ctx;
+err:
+ if (ctx->fallback_req)
+ kmem_cache_free(req_cachep, ctx->fallback_req);
+ kfree(ctx->completions);
+ kfree(ctx->cancel_hash);
+ kfree(ctx);
+ return NULL;
}
-static inline bool __io_sequence_defer(struct io_ring_ctx *ctx,
- struct io_kiocb *req)
+static inline bool __req_need_defer(struct io_kiocb *req)
{
- return req->sequence != ctx->cached_cq_tail + ctx->rings->sq_dropped;
+ struct io_ring_ctx *ctx = req->ctx;
+
+ return req->sequence != ctx->cached_cq_tail + ctx->cached_sq_dropped
+ + atomic_read(&ctx->cached_cq_overflow);
}
-static inline bool io_sequence_defer(struct io_ring_ctx *ctx,
- struct io_kiocb *req)
+static inline bool req_need_defer(struct io_kiocb *req)
{
- if ((req->flags & (REQ_F_IO_DRAIN|REQ_F_IO_DRAINED)) != REQ_F_IO_DRAIN)
- return false;
+ if ((req->flags & (REQ_F_IO_DRAIN|REQ_F_IO_DRAINED)) == REQ_F_IO_DRAIN)
+ return __req_need_defer(req);
- return __io_sequence_defer(ctx, req);
+ return false;
}
static struct io_kiocb *io_get_deferred_req(struct io_ring_ctx *ctx)
@@ -435,7 +523,7 @@ static struct io_kiocb *io_get_deferred_req(struct io_ring_ctx *ctx)
struct io_kiocb *req;
req = list_first_entry_or_null(&ctx->defer_list, struct io_kiocb, list);
- if (req && !io_sequence_defer(ctx, req)) {
+ if (req && !req_need_defer(req)) {
list_del_init(&req->list);
return req;
}
@@ -448,9 +536,13 @@ static struct io_kiocb *io_get_timeout_req(struct io_ring_ctx *ctx)
struct io_kiocb *req;
req = list_first_entry_or_null(&ctx->timeout_list, struct io_kiocb, list);
- if (req && !__io_sequence_defer(ctx, req)) {
- list_del_init(&req->list);
- return req;
+ if (req) {
+ if (req->flags & REQ_F_TIMEOUT_NOSEQ)
+ return NULL;
+ if (!__req_need_defer(req)) {
+ list_del_init(&req->list);
+ return req;
+ }
}
return NULL;
@@ -471,33 +563,80 @@ static void __io_commit_cqring(struct io_ring_ctx *ctx)
}
}
-static inline void io_queue_async_work(struct io_ring_ctx *ctx,
- struct io_kiocb *req)
+static inline bool io_sqe_needs_user(const struct io_uring_sqe *sqe)
+{
+ u8 opcode = READ_ONCE(sqe->opcode);
+
+ return !(opcode == IORING_OP_READ_FIXED ||
+ opcode == IORING_OP_WRITE_FIXED);
+}
+
+static inline bool io_prep_async_work(struct io_kiocb *req,
+ struct io_kiocb **link)
{
- int rw = 0;
+ bool do_hashed = false;
- if (req->submit.sqe) {
- switch (req->submit.sqe->opcode) {
+ if (req->sqe) {
+ switch (req->sqe->opcode) {
case IORING_OP_WRITEV:
case IORING_OP_WRITE_FIXED:
- rw = !(req->rw.ki_flags & IOCB_DIRECT);
+ do_hashed = true;
+ /* fall-through */
+ case IORING_OP_READV:
+ case IORING_OP_READ_FIXED:
+ case IORING_OP_SENDMSG:
+ case IORING_OP_RECVMSG:
+ case IORING_OP_ACCEPT:
+ case IORING_OP_POLL_ADD:
+ case IORING_OP_CONNECT:
+ /*
+ * We know REQ_F_ISREG is not set on some of these
+ * opcodes, but this enables us to keep the check in
+ * just one place.
+ */
+ if (!(req->flags & REQ_F_ISREG))
+ req->work.flags |= IO_WQ_WORK_UNBOUND;
break;
}
+ if (io_sqe_needs_user(req->sqe))
+ req->work.flags |= IO_WQ_WORK_NEEDS_USER;
}
- queue_work(ctx->sqo_wq[rw], &req->work);
+ *link = io_prep_linked_timeout(req);
+ return do_hashed;
+}
+
+static inline void io_queue_async_work(struct io_kiocb *req)
+{
+ struct io_ring_ctx *ctx = req->ctx;
+ struct io_kiocb *link;
+ bool do_hashed;
+
+ do_hashed = io_prep_async_work(req, &link);
+
+ trace_io_uring_queue_async_work(ctx, do_hashed, req, &req->work,
+ req->flags);
+ if (!do_hashed) {
+ io_wq_enqueue(ctx->io_wq, &req->work);
+ } else {
+ io_wq_enqueue_hashed(ctx->io_wq, &req->work,
+ file_inode(req->file));
+ }
+
+ if (link)
+ io_queue_linked_timeout(link);
}
static void io_kill_timeout(struct io_kiocb *req)
{
int ret;
- ret = hrtimer_try_to_cancel(&req->timeout.timer);
+ ret = hrtimer_try_to_cancel(&req->io->timeout.timer);
if (ret != -1) {
atomic_inc(&req->ctx->cq_timeouts);
- list_del(&req->list);
- io_cqring_fill_event(req->ctx, req->user_data, 0);
- __io_free_req(req);
+ list_del_init(&req->list);
+ io_cqring_fill_event(req, 0);
+ io_put_req(req);
}
}
@@ -521,13 +660,8 @@ static void io_commit_cqring(struct io_ring_ctx *ctx)
__io_commit_cqring(ctx);
while ((req = io_get_deferred_req(ctx)) != NULL) {
- if (req->flags & REQ_F_SHADOW_DRAIN) {
- /* Just for drain, free it. */
- __io_free_req(req);
- continue;
- }
req->flags |= REQ_F_IO_DRAINED;
- io_queue_async_work(ctx, req);
+ io_queue_async_work(req);
}
}
@@ -549,51 +683,128 @@ static struct io_uring_cqe *io_get_cqring(struct io_ring_ctx *ctx)
return &rings->cqes[tail & ctx->cq_mask];
}
-static void io_cqring_fill_event(struct io_ring_ctx *ctx, u64 ki_user_data,
- long res)
+static void io_cqring_ev_posted(struct io_ring_ctx *ctx)
+{
+ if (waitqueue_active(&ctx->wait))
+ wake_up(&ctx->wait);
+ if (waitqueue_active(&ctx->sqo_wait))
+ wake_up(&ctx->sqo_wait);
+ if (ctx->cq_ev_fd)
+ eventfd_signal(ctx->cq_ev_fd, 1);
+}
+
+/* Returns true if there are no backlogged entries after the flush */
+static bool io_cqring_overflow_flush(struct io_ring_ctx *ctx, bool force)
{
+ struct io_rings *rings = ctx->rings;
+ struct io_uring_cqe *cqe;
+ struct io_kiocb *req;
+ unsigned long flags;
+ LIST_HEAD(list);
+
+ if (!force) {
+ if (list_empty_careful(&ctx->cq_overflow_list))
+ return true;
+ if ((ctx->cached_cq_tail - READ_ONCE(rings->cq.head) ==
+ rings->cq_ring_entries))
+ return false;
+ }
+
+ spin_lock_irqsave(&ctx->completion_lock, flags);
+
+ /* if force is set, the ring is going away. always drop after that */
+ if (force)
+ ctx->cq_overflow_flushed = true;
+
+ cqe = NULL;
+ while (!list_empty(&ctx->cq_overflow_list)) {
+ cqe = io_get_cqring(ctx);
+ if (!cqe && !force)
+ break;
+
+ req = list_first_entry(&ctx->cq_overflow_list, struct io_kiocb,
+ list);
+ list_move(&req->list, &list);
+ if (cqe) {
+ WRITE_ONCE(cqe->user_data, req->user_data);
+ WRITE_ONCE(cqe->res, req->result);
+ WRITE_ONCE(cqe->flags, 0);
+ } else {
+ WRITE_ONCE(ctx->rings->cq_overflow,
+ atomic_inc_return(&ctx->cached_cq_overflow));
+ }
+ }
+
+ io_commit_cqring(ctx);
+ spin_unlock_irqrestore(&ctx->completion_lock, flags);
+ io_cqring_ev_posted(ctx);
+
+ while (!list_empty(&list)) {
+ req = list_first_entry(&list, struct io_kiocb, list);
+ list_del(&req->list);
+ io_put_req(req);
+ }
+
+ return cqe != NULL;
+}
+
+static void io_cqring_fill_event(struct io_kiocb *req, long res)
+{
+ struct io_ring_ctx *ctx = req->ctx;
struct io_uring_cqe *cqe;
+ trace_io_uring_complete(ctx, req->user_data, res);
+
/*
* If we can't get a cq entry, userspace overflowed the
* submission (by quite a lot). Increment the overflow count in
* the ring.
*/
cqe = io_get_cqring(ctx);
- if (cqe) {
- WRITE_ONCE(cqe->user_data, ki_user_data);
+ if (likely(cqe)) {
+ WRITE_ONCE(cqe->user_data, req->user_data);
WRITE_ONCE(cqe->res, res);
WRITE_ONCE(cqe->flags, 0);
+ } else if (ctx->cq_overflow_flushed) {
+ WRITE_ONCE(ctx->rings->cq_overflow,
+ atomic_inc_return(&ctx->cached_cq_overflow));
} else {
- unsigned overflow = READ_ONCE(ctx->rings->cq_overflow);
-
- WRITE_ONCE(ctx->rings->cq_overflow, overflow + 1);
+ refcount_inc(&req->refs);
+ req->result = res;
+ list_add_tail(&req->list, &ctx->cq_overflow_list);
}
}
-static void io_cqring_ev_posted(struct io_ring_ctx *ctx)
-{
- if (waitqueue_active(&ctx->wait))
- wake_up(&ctx->wait);
- if (waitqueue_active(&ctx->sqo_wait))
- wake_up(&ctx->sqo_wait);
- if (ctx->cq_ev_fd)
- eventfd_signal(ctx->cq_ev_fd, 1);
-}
-
-static void io_cqring_add_event(struct io_ring_ctx *ctx, u64 user_data,
- long res)
+static void io_cqring_add_event(struct io_kiocb *req, long res)
{
+ struct io_ring_ctx *ctx = req->ctx;
unsigned long flags;
spin_lock_irqsave(&ctx->completion_lock, flags);
- io_cqring_fill_event(ctx, user_data, res);
+ io_cqring_fill_event(req, res);
io_commit_cqring(ctx);
spin_unlock_irqrestore(&ctx->completion_lock, flags);
io_cqring_ev_posted(ctx);
}
+static inline bool io_is_fallback_req(struct io_kiocb *req)
+{
+ return req == (struct io_kiocb *)
+ ((unsigned long) req->ctx->fallback_req & ~1UL);
+}
+
+static struct io_kiocb *io_get_fallback_req(struct io_ring_ctx *ctx)
+{
+ struct io_kiocb *req;
+
+ req = ctx->fallback_req;
+ if (!test_and_set_bit_lock(0, (unsigned long *) ctx->fallback_req))
+ return req;
+
+ return NULL;
+}
+
static struct io_kiocb *io_get_req(struct io_ring_ctx *ctx,
struct io_submit_state *state)
{
@@ -606,7 +817,7 @@ static struct io_kiocb *io_get_req(struct io_ring_ctx *ctx,
if (!state) {
req = kmem_cache_alloc(req_cachep, gfp);
if (unlikely(!req))
- goto out;
+ goto fallback;
} else if (!state->free_reqs) {
size_t sz;
int ret;
@@ -621,7 +832,7 @@ static struct io_kiocb *io_get_req(struct io_ring_ctx *ctx,
if (unlikely(ret <= 0)) {
state->reqs[0] = kmem_cache_alloc(req_cachep, gfp);
if (!state->reqs[0])
- goto out;
+ goto fallback;
ret = 1;
}
state->free_reqs = ret - 1;
@@ -633,14 +844,21 @@ static struct io_kiocb *io_get_req(struct io_ring_ctx *ctx,
state->cur_req++;
}
+got_it:
+ req->io = NULL;
+ req->ring_file = NULL;
req->file = NULL;
req->ctx = ctx;
req->flags = 0;
/* one is dropped after submission, the other at completion */
refcount_set(&req->refs, 2);
req->result = 0;
+ INIT_IO_WORK(&req->work, io_wq_submit_work);
return req;
-out:
+fallback:
+ req = io_get_fallback_req(ctx);
+ if (req)
+ goto got_it;
percpu_ref_put(&ctx->refs);
return NULL;
}
@@ -656,34 +874,81 @@ static void io_free_req_many(struct io_ring_ctx *ctx, void **reqs, int *nr)
static void __io_free_req(struct io_kiocb *req)
{
+ struct io_ring_ctx *ctx = req->ctx;
+
+ if (req->io)
+ kfree(req->io);
if (req->file && !(req->flags & REQ_F_FIXED_FILE))
fput(req->file);
- percpu_ref_put(&req->ctx->refs);
- kmem_cache_free(req_cachep, req);
+ if (req->flags & REQ_F_INFLIGHT) {
+ unsigned long flags;
+
+ spin_lock_irqsave(&ctx->inflight_lock, flags);
+ list_del(&req->inflight_entry);
+ if (waitqueue_active(&ctx->inflight_wait))
+ wake_up(&ctx->inflight_wait);
+ spin_unlock_irqrestore(&ctx->inflight_lock, flags);
+ }
+ percpu_ref_put(&ctx->refs);
+ if (likely(!io_is_fallback_req(req)))
+ kmem_cache_free(req_cachep, req);
+ else
+ clear_bit_unlock(0, (unsigned long *) ctx->fallback_req);
}
-static void io_req_link_next(struct io_kiocb *req)
+static bool io_link_cancel_timeout(struct io_kiocb *req)
{
- struct io_kiocb *nxt;
+ struct io_ring_ctx *ctx = req->ctx;
+ int ret;
+
+ ret = hrtimer_try_to_cancel(&req->io->timeout.timer);
+ if (ret != -1) {
+ io_cqring_fill_event(req, -ECANCELED);
+ io_commit_cqring(ctx);
+ req->flags &= ~REQ_F_LINK;
+ io_put_req(req);
+ return true;
+ }
+
+ return false;
+}
+
+static void io_req_link_next(struct io_kiocb *req, struct io_kiocb **nxtptr)
+{
+ struct io_ring_ctx *ctx = req->ctx;
+ bool wake_ev = false;
+
+ /* Already got next link */
+ if (req->flags & REQ_F_LINK_NEXT)
+ return;
/*
* The list should never be empty when we are called here. But could
* potentially happen if the chain is messed up, check to be on the
* safe side.
*/
- nxt = list_first_entry_or_null(&req->link_list, struct io_kiocb, list);
- if (nxt) {
- list_del(&nxt->list);
- if (!list_empty(&req->link_list)) {
- INIT_LIST_HEAD(&nxt->link_list);
- list_splice(&req->link_list, &nxt->link_list);
- nxt->flags |= REQ_F_LINK;
+ while (!list_empty(&req->link_list)) {
+ struct io_kiocb *nxt = list_first_entry(&req->link_list,
+ struct io_kiocb, link_list);
+
+ if (unlikely((req->flags & REQ_F_LINK_TIMEOUT) &&
+ (nxt->flags & REQ_F_TIMEOUT))) {
+ list_del_init(&nxt->link_list);
+ wake_ev |= io_link_cancel_timeout(nxt);
+ req->flags &= ~REQ_F_LINK_TIMEOUT;
+ continue;
}
- nxt->flags |= REQ_F_LINK_DONE;
- INIT_WORK(&nxt->work, io_sq_wq_submit_work);
- io_queue_async_work(req->ctx, nxt);
+ list_del_init(&req->link_list);
+ if (!list_empty(&nxt->link_list))
+ nxt->flags |= REQ_F_LINK;
+ *nxtptr = nxt;
+ break;
}
+
+ req->flags |= REQ_F_LINK_NEXT;
+ if (wake_ev)
+ io_cqring_ev_posted(ctx);
}
/*
@@ -691,33 +956,86 @@ static void io_req_link_next(struct io_kiocb *req)
*/
static void io_fail_links(struct io_kiocb *req)
{
- struct io_kiocb *link;
+ struct io_ring_ctx *ctx = req->ctx;
+ unsigned long flags;
+
+ spin_lock_irqsave(&ctx->completion_lock, flags);
while (!list_empty(&req->link_list)) {
- link = list_first_entry(&req->link_list, struct io_kiocb, list);
- list_del(&link->list);
+ struct io_kiocb *link = list_first_entry(&req->link_list,
+ struct io_kiocb, link_list);
+
+ list_del_init(&link->link_list);
+ trace_io_uring_fail_link(req, link);
- io_cqring_add_event(req->ctx, link->user_data, -ECANCELED);
- __io_free_req(link);
+ if ((req->flags & REQ_F_LINK_TIMEOUT) &&
+ link->sqe->opcode == IORING_OP_LINK_TIMEOUT) {
+ io_link_cancel_timeout(link);
+ } else {
+ io_cqring_fill_event(link, -ECANCELED);
+ __io_double_put_req(link);
+ }
+ req->flags &= ~REQ_F_LINK_TIMEOUT;
}
+
+ io_commit_cqring(ctx);
+ spin_unlock_irqrestore(&ctx->completion_lock, flags);
+ io_cqring_ev_posted(ctx);
}
-static void io_free_req(struct io_kiocb *req)
+static void io_req_find_next(struct io_kiocb *req, struct io_kiocb **nxt)
{
+ if (likely(!(req->flags & REQ_F_LINK)))
+ return;
+
/*
* If LINK is set, we have dependent requests in this chain. If we
* didn't fail this request, queue the first one up, moving any other
* dependencies to the next request. In case of failure, fail the rest
* of the chain.
*/
- if (req->flags & REQ_F_LINK) {
- if (req->flags & REQ_F_FAIL_LINK)
- io_fail_links(req);
- else
- io_req_link_next(req);
+ if (req->flags & REQ_F_FAIL_LINK) {
+ io_fail_links(req);
+ } else if ((req->flags & (REQ_F_LINK_TIMEOUT | REQ_F_COMP_LOCKED)) ==
+ REQ_F_LINK_TIMEOUT) {
+ struct io_ring_ctx *ctx = req->ctx;
+ unsigned long flags;
+
+ /*
+ * If this is a timeout link, we could be racing with the
+ * timeout timer. Grab the completion lock for this case to
+ * protect against that.
+ */
+ spin_lock_irqsave(&ctx->completion_lock, flags);
+ io_req_link_next(req, nxt);
+ spin_unlock_irqrestore(&ctx->completion_lock, flags);
+ } else {
+ io_req_link_next(req, nxt);
}
+}
+
+static void io_free_req(struct io_kiocb *req)
+{
+ struct io_kiocb *nxt = NULL;
+ io_req_find_next(req, &nxt);
__io_free_req(req);
+
+ if (nxt)
+ io_queue_async_work(nxt);
+}
+
+/*
+ * Drop reference to request, return next in chain (if there is one) if this
+ * was the last reference to this request.
+ */
+__attribute__((nonnull))
+static void io_put_req_find_next(struct io_kiocb *req, struct io_kiocb **nxtptr)
+{
+ io_req_find_next(req, nxtptr);
+
+ if (refcount_dec_and_test(&req->refs))
+ __io_free_req(req);
}
static void io_put_req(struct io_kiocb *req)
@@ -726,13 +1044,51 @@ static void io_put_req(struct io_kiocb *req)
io_free_req(req);
}
-static unsigned io_cqring_events(struct io_rings *rings)
+/*
+ * Must only be used if we don't need to care about links, usually from
+ * within the completion handling itself.
+ */
+static void __io_double_put_req(struct io_kiocb *req)
+{
+ /* drop both submit and complete references */
+ if (refcount_sub_and_test(2, &req->refs))
+ __io_free_req(req);
+}
+
+static void io_double_put_req(struct io_kiocb *req)
{
+ /* drop both submit and complete references */
+ if (refcount_sub_and_test(2, &req->refs))
+ io_free_req(req);
+}
+
+static unsigned io_cqring_events(struct io_ring_ctx *ctx, bool noflush)
+{
+ struct io_rings *rings = ctx->rings;
+
+ /*
+ * noflush == true is from the waitqueue handler, just ensure we wake
+ * up the task, and the next invocation will flush the entries. We
+ * cannot safely to it from here.
+ */
+ if (noflush && !list_empty(&ctx->cq_overflow_list))
+ return -1U;
+
+ io_cqring_overflow_flush(ctx, false);
+
/* See comment at the top of this file */
smp_rmb();
return READ_ONCE(rings->cq.tail) - READ_ONCE(rings->cq.head);
}
+static inline unsigned int io_sqring_entries(struct io_ring_ctx *ctx)
+{
+ struct io_rings *rings = ctx->rings;
+
+ /* make sure SQ entry isn't read before tail */
+ return smp_load_acquire(&rings->sq.tail) - ctx->cached_sq_head;
+}
+
/*
* Find and free completed poll iocbs
*/
@@ -748,7 +1104,7 @@ static void io_iopoll_complete(struct io_ring_ctx *ctx, unsigned int *nr_events,
req = list_first_entry(done, struct io_kiocb, list);
list_del(&req->list);
- io_cqring_fill_event(ctx, req->user_data, req->result);
+ io_cqring_fill_event(req, req->result);
(*nr_events)++;
if (refcount_dec_and_test(&req->refs)) {
@@ -757,8 +1113,9 @@ static void io_iopoll_complete(struct io_ring_ctx *ctx, unsigned int *nr_events,
* completions for those, only batch free for fixed
* file and non-linked commands.
*/
- if ((req->flags & (REQ_F_FIXED_FILE|REQ_F_LINK)) ==
- REQ_F_FIXED_FILE) {
+ if (((req->flags & (REQ_F_FIXED_FILE|REQ_F_LINK)) ==
+ REQ_F_FIXED_FILE) && !io_is_fallback_req(req) &&
+ !req->io) {
reqs[to_free++] = req;
if (to_free == ARRAY_SIZE(reqs))
io_free_req_many(ctx, reqs, &to_free);
@@ -862,19 +1219,11 @@ static void io_iopoll_reap_events(struct io_ring_ctx *ctx)
mutex_unlock(&ctx->uring_lock);
}
-static int io_iopoll_check(struct io_ring_ctx *ctx, unsigned *nr_events,
- long min)
+static int __io_iopoll_check(struct io_ring_ctx *ctx, unsigned *nr_events,
+ long min)
{
- int iters, ret = 0;
-
- /*
- * We disallow the app entering submit/complete with polling, but we
- * still need to lock the ring to prevent racing with polled issue
- * that got punted to a workqueue.
- */
- mutex_lock(&ctx->uring_lock);
+ int iters = 0, ret = 0;
- iters = 0;
do {
int tmin = 0;
@@ -883,7 +1232,7 @@ static int io_iopoll_check(struct io_ring_ctx *ctx, unsigned *nr_events,
* If we do, we can potentially be spinning for commands that
* already triggered a CQE (eg in error).
*/
- if (io_cqring_events(ctx->rings))
+ if (io_cqring_events(ctx, false))
break;
/*
@@ -910,42 +1259,76 @@ static int io_iopoll_check(struct io_ring_ctx *ctx, unsigned *nr_events,
ret = 0;
} while (min && !*nr_events && !need_resched());
+ return ret;
+}
+
+static int io_iopoll_check(struct io_ring_ctx *ctx, unsigned *nr_events,
+ long min)
+{
+ int ret;
+
+ /*
+ * We disallow the app entering submit/complete with polling, but we
+ * still need to lock the ring to prevent racing with polled issue
+ * that got punted to a workqueue.
+ */
+ mutex_lock(&ctx->uring_lock);
+ ret = __io_iopoll_check(ctx, nr_events, min);
mutex_unlock(&ctx->uring_lock);
return ret;
}
-static void kiocb_end_write(struct kiocb *kiocb)
+static void kiocb_end_write(struct io_kiocb *req)
{
- if (kiocb->ki_flags & IOCB_WRITE) {
- struct inode *inode = file_inode(kiocb->ki_filp);
+ /*
+ * Tell lockdep we inherited freeze protection from submission
+ * thread.
+ */
+ if (req->flags & REQ_F_ISREG) {
+ struct inode *inode = file_inode(req->file);
- /*
- * Tell lockdep we inherited freeze protection from submission
- * thread.
- */
- if (S_ISREG(inode->i_mode))
- __sb_writers_acquired(inode->i_sb, SB_FREEZE_WRITE);
- file_end_write(kiocb->ki_filp);
+ __sb_writers_acquired(inode->i_sb, SB_FREEZE_WRITE);
}
+ file_end_write(req->file);
}
-static void io_complete_rw(struct kiocb *kiocb, long res, long res2)
+static void io_complete_rw_common(struct kiocb *kiocb, long res)
{
struct io_kiocb *req = container_of(kiocb, struct io_kiocb, rw);
- kiocb_end_write(kiocb);
+ if (kiocb->ki_flags & IOCB_WRITE)
+ kiocb_end_write(req);
if ((req->flags & REQ_F_LINK) && res != req->result)
req->flags |= REQ_F_FAIL_LINK;
- io_cqring_add_event(req->ctx, req->user_data, res);
+ io_cqring_add_event(req, res);
+}
+
+static void io_complete_rw(struct kiocb *kiocb, long res, long res2)
+{
+ struct io_kiocb *req = container_of(kiocb, struct io_kiocb, rw);
+
+ io_complete_rw_common(kiocb, res);
io_put_req(req);
}
+static struct io_kiocb *__io_complete_rw(struct kiocb *kiocb, long res)
+{
+ struct io_kiocb *req = container_of(kiocb, struct io_kiocb, rw);
+ struct io_kiocb *nxt = NULL;
+
+ io_complete_rw_common(kiocb, res);
+ io_put_req_find_next(req, &nxt);
+
+ return nxt;
+}
+
static void io_complete_rw_iopoll(struct kiocb *kiocb, long res, long res2)
{
struct io_kiocb *req = container_of(kiocb, struct io_kiocb, rw);
- kiocb_end_write(kiocb);
+ if (kiocb->ki_flags & IOCB_WRITE)
+ kiocb_end_write(req);
if ((req->flags & REQ_F_LINK) && res != req->result)
req->flags |= REQ_F_FAIL_LINK;
@@ -1047,10 +1430,9 @@ static bool io_file_supports_async(struct file *file)
return false;
}
-static int io_prep_rw(struct io_kiocb *req, const struct sqe_submit *s,
- bool force_nonblock)
+static int io_prep_rw(struct io_kiocb *req, bool force_nonblock)
{
- const struct io_uring_sqe *sqe = s->sqe;
+ const struct io_uring_sqe *sqe = req->sqe;
struct io_ring_ctx *ctx = req->ctx;
struct kiocb *kiocb = &req->rw;
unsigned ioprio;
@@ -1059,8 +1441,8 @@ static int io_prep_rw(struct io_kiocb *req, const struct sqe_submit *s,
if (!req->file)
return -EBADF;
- if (force_nonblock && !io_file_supports_async(req->file))
- force_nonblock = false;
+ if (S_ISREG(file_inode(req->file)->i_mode))
+ req->flags |= REQ_F_ISREG;
kiocb->ki_pos = READ_ONCE(sqe->off);
kiocb->ki_flags = iocb_flags(kiocb->ki_filp);
@@ -1081,7 +1463,8 @@ static int io_prep_rw(struct io_kiocb *req, const struct sqe_submit *s,
return ret;
/* don't allow async punt if RWF_NOWAIT was requested */
- if (kiocb->ki_flags & IOCB_NOWAIT)
+ if ((kiocb->ki_flags & IOCB_NOWAIT) ||
+ (req->file->f_flags & O_NONBLOCK))
req->flags |= REQ_F_NOWAIT;
if (force_nonblock)
@@ -1094,6 +1477,7 @@ static int io_prep_rw(struct io_kiocb *req, const struct sqe_submit *s,
kiocb->ki_flags |= IOCB_HIPRI;
kiocb->ki_complete = io_complete_rw_iopoll;
+ req->result = 0;
} else {
if (kiocb->ki_flags & IOCB_HIPRI)
return -EINVAL;
@@ -1123,9 +1507,18 @@ static inline void io_rw_done(struct kiocb *kiocb, ssize_t ret)
}
}
-static int io_import_fixed(struct io_ring_ctx *ctx, int rw,
- const struct io_uring_sqe *sqe,
- struct iov_iter *iter)
+static void kiocb_done(struct kiocb *kiocb, ssize_t ret, struct io_kiocb **nxt,
+ bool in_async)
+{
+ if (in_async && ret >= 0 && kiocb->ki_complete == io_complete_rw)
+ *nxt = __io_complete_rw(kiocb, ret);
+ else
+ io_rw_done(kiocb, ret);
+}
+
+static ssize_t io_import_fixed(struct io_ring_ctx *ctx, int rw,
+ const struct io_uring_sqe *sqe,
+ struct iov_iter *iter)
{
size_t len = READ_ONCE(sqe->len);
struct io_mapped_ubuf *imu;
@@ -1194,14 +1587,13 @@ static int io_import_fixed(struct io_ring_ctx *ctx, int rw,
}
}
- return 0;
+ return len;
}
-static ssize_t io_import_iovec(struct io_ring_ctx *ctx, int rw,
- const struct sqe_submit *s, struct iovec **iovec,
- struct iov_iter *iter)
+static ssize_t io_import_iovec(int rw, struct io_kiocb *req,
+ struct iovec **iovec, struct iov_iter *iter)
{
- const struct io_uring_sqe *sqe = s->sqe;
+ const struct io_uring_sqe *sqe = req->sqe;
void __user *buf = u64_to_user_ptr(READ_ONCE(sqe->addr));
size_t sqe_len = READ_ONCE(sqe->len);
u8 opcode;
@@ -1215,18 +1607,26 @@ static ssize_t io_import_iovec(struct io_ring_ctx *ctx, int rw,
* flag.
*/
opcode = READ_ONCE(sqe->opcode);
- if (opcode == IORING_OP_READ_FIXED ||
- opcode == IORING_OP_WRITE_FIXED) {
- ssize_t ret = io_import_fixed(ctx, rw, sqe, iter);
+ if (opcode == IORING_OP_READ_FIXED || opcode == IORING_OP_WRITE_FIXED) {
*iovec = NULL;
- return ret;
+ return io_import_fixed(req->ctx, rw, sqe, iter);
}
- if (!s->has_user)
+ if (req->io) {
+ struct io_async_rw *iorw = &req->io->rw;
+
+ *iovec = iorw->iov;
+ iov_iter_init(iter, rw, *iovec, iorw->nr_segs, iorw->size);
+ if (iorw->iov == iorw->fast_iov)
+ *iovec = NULL;
+ return iorw->size;
+ }
+
+ if (!req->has_user)
return -EFAULT;
#ifdef CONFIG_COMPAT
- if (ctx->compat)
+ if (req->ctx->compat)
return compat_import_iovec(rw, buf, sqe_len, UIO_FASTIOV,
iovec, iter);
#endif
@@ -1234,65 +1634,6 @@ static ssize_t io_import_iovec(struct io_ring_ctx *ctx, int rw,
return import_iovec(rw, buf, sqe_len, UIO_FASTIOV, iovec, iter);
}
-static inline bool io_should_merge(struct async_list *al, struct kiocb *kiocb)
-{
- if (al->file == kiocb->ki_filp) {
- off_t start, end;
-
- /*
- * Allow merging if we're anywhere in the range of the same
- * page. Generally this happens for sub-page reads or writes,
- * and it's beneficial to allow the first worker to bring the
- * page in and the piggy backed work can then work on the
- * cached page.
- */
- start = al->io_start & PAGE_MASK;
- end = (al->io_start + al->io_len + PAGE_SIZE - 1) & PAGE_MASK;
- if (kiocb->ki_pos >= start && kiocb->ki_pos <= end)
- return true;
- }
-
- al->file = NULL;
- return false;
-}
-
-/*
- * Make a note of the last file/offset/direction we punted to async
- * context. We'll use this information to see if we can piggy back a
- * sequential request onto the previous one, if it's still hasn't been
- * completed by the async worker.
- */
-static void io_async_list_note(int rw, struct io_kiocb *req, size_t len)
-{
- struct async_list *async_list = &req->ctx->pending_async[rw];
- struct kiocb *kiocb = &req->rw;
- struct file *filp = kiocb->ki_filp;
-
- if (io_should_merge(async_list, kiocb)) {
- unsigned long max_bytes;
-
- /* Use 8x RA size as a decent limiter for both reads/writes */
- max_bytes = filp->f_ra.ra_pages << (PAGE_SHIFT + 3);
- if (!max_bytes)
- max_bytes = VM_READAHEAD_PAGES << (PAGE_SHIFT + 3);
-
- /* If max len are exceeded, reset the state */
- if (async_list->io_len + len <= max_bytes) {
- req->flags |= REQ_F_SEQ_PREV;
- async_list->io_len += len;
- } else {
- async_list->file = NULL;
- }
- }
-
- /* New file? Reset state. */
- if (async_list->file != filp) {
- async_list->io_start = kiocb->ki_pos;
- async_list->io_len = len;
- async_list->file = filp;
- }
-}
-
/*
* For files that don't have ->read_iter() and ->write_iter(), handle them
* by looping over ->read() or ->write() manually.
@@ -1313,9 +1654,19 @@ static ssize_t loop_rw_iter(int rw, struct file *file, struct kiocb *kiocb,
return -EAGAIN;
while (iov_iter_count(iter)) {
- struct iovec iovec = iov_iter_iovec(iter);
+ struct iovec iovec;
ssize_t nr;
+ if (!iov_iter_is_bvec(iter)) {
+ iovec = iov_iter_iovec(iter);
+ } else {
+ /* fixed buffers import bvec */
+ iovec.iov_base = kmap(iter->bvec->bv_page)
+ + iter->iov_offset;
+ iovec.iov_len = min(iter->count,
+ iter->bvec->bv_len - iter->iov_offset);
+ }
+
if (rw == READ) {
nr = file->f_op->read(file, iovec.iov_base,
iovec.iov_len, &kiocb->ki_pos);
@@ -1324,6 +1675,9 @@ static ssize_t loop_rw_iter(int rw, struct file *file, struct kiocb *kiocb,
iovec.iov_len, &kiocb->ki_pos);
}
+ if (iov_iter_is_bvec(iter))
+ kunmap(iter->bvec->bv_page);
+
if (nr < 0) {
if (!ret)
ret = nr;
@@ -1338,7 +1692,51 @@ static ssize_t loop_rw_iter(int rw, struct file *file, struct kiocb *kiocb,
return ret;
}
-static int io_read(struct io_kiocb *req, const struct sqe_submit *s,
+static void io_req_map_io(struct io_kiocb *req, ssize_t io_size,
+ struct iovec *iovec, struct iovec *fast_iov,
+ struct iov_iter *iter)
+{
+ req->io->rw.nr_segs = iter->nr_segs;
+ req->io->rw.size = io_size;
+ req->io->rw.iov = iovec;
+ if (!req->io->rw.iov) {
+ req->io->rw.iov = req->io->rw.fast_iov;
+ memcpy(req->io->rw.iov, fast_iov,
+ sizeof(struct iovec) * iter->nr_segs);
+ }
+}
+
+static int io_setup_async_io(struct io_kiocb *req, ssize_t io_size,
+ struct iovec *iovec, struct iovec *fast_iov,
+ struct iov_iter *iter)
+{
+ req->io = kmalloc(sizeof(*req->io), GFP_KERNEL);
+ if (req->io) {
+ io_req_map_io(req, io_size, iovec, fast_iov, iter);
+ memcpy(&req->io->sqe, req->sqe, sizeof(req->io->sqe));
+ req->sqe = &req->io->sqe;
+ return 0;
+ }
+
+ return -ENOMEM;
+}
+
+static int io_read_prep(struct io_kiocb *req, struct iovec **iovec,
+ struct iov_iter *iter, bool force_nonblock)
+{
+ ssize_t ret;
+
+ ret = io_prep_rw(req, force_nonblock);
+ if (ret)
+ return ret;
+
+ if (unlikely(!(req->file->f_mode & FMODE_READ)))
+ return -EBADF;
+
+ return io_import_iovec(READ, req, iovec, iter);
+}
+
+static int io_read(struct io_kiocb *req, struct io_kiocb **nxt,
bool force_nonblock)
{
struct iovec inline_vecs[UIO_FASTIOV], *iovec = inline_vecs;
@@ -1346,23 +1744,31 @@ static int io_read(struct io_kiocb *req, const struct sqe_submit *s,
struct iov_iter iter;
struct file *file;
size_t iov_count;
- ssize_t read_size, ret;
+ ssize_t io_size, ret;
- ret = io_prep_rw(req, s, force_nonblock);
- if (ret)
- return ret;
- file = kiocb->ki_filp;
-
- if (unlikely(!(file->f_mode & FMODE_READ)))
- return -EBADF;
-
- ret = io_import_iovec(req->ctx, READ, s, &iovec, &iter);
- if (ret < 0)
- return ret;
+ if (!req->io) {
+ ret = io_read_prep(req, &iovec, &iter, force_nonblock);
+ if (ret < 0)
+ return ret;
+ } else {
+ ret = io_import_iovec(READ, req, &iovec, &iter);
+ if (ret < 0)
+ return ret;
+ }
- read_size = ret;
+ file = req->file;
+ io_size = ret;
if (req->flags & REQ_F_LINK)
- req->result = read_size;
+ req->result = io_size;
+
+ /*
+ * If the file doesn't support async, mark it as REQ_F_MUST_PUNT so
+ * we know to async punt it even if it was opened O_NONBLOCK
+ */
+ if (force_nonblock && !io_file_supports_async(file)) {
+ req->flags |= REQ_F_MUST_PUNT;
+ goto copy_iov;
+ }
iov_count = iov_iter_count(&iter);
ret = rw_verify_area(READ, file, &kiocb->ki_pos, iov_count);
@@ -1382,26 +1788,43 @@ static int io_read(struct io_kiocb *req, const struct sqe_submit *s,
* need async punt anyway, so it's more efficient to do it
* here.
*/
- if (force_nonblock && ret2 > 0 && ret2 < read_size)
+ if (force_nonblock && !(req->flags & REQ_F_NOWAIT) &&
+ (req->flags & REQ_F_ISREG) &&
+ ret2 > 0 && ret2 < io_size)
ret2 = -EAGAIN;
/* Catch -EAGAIN return for forced non-blocking submission */
if (!force_nonblock || ret2 != -EAGAIN) {
- io_rw_done(kiocb, ret2);
+ kiocb_done(kiocb, ret2, nxt, req->in_async);
} else {
- /*
- * If ->needs_lock is true, we're already in async
- * context.
- */
- if (!s->needs_lock)
- io_async_list_note(READ, req, iov_count);
- ret = -EAGAIN;
+copy_iov:
+ ret = io_setup_async_io(req, io_size, iovec,
+ inline_vecs, &iter);
+ if (ret)
+ goto out_free;
+ return -EAGAIN;
}
}
+out_free:
kfree(iovec);
return ret;
}
-static int io_write(struct io_kiocb *req, const struct sqe_submit *s,
+static int io_write_prep(struct io_kiocb *req, struct iovec **iovec,
+ struct iov_iter *iter, bool force_nonblock)
+{
+ ssize_t ret;
+
+ ret = io_prep_rw(req, force_nonblock);
+ if (ret)
+ return ret;
+
+ if (unlikely(!(req->file->f_mode & FMODE_WRITE)))
+ return -EBADF;
+
+ return io_import_iovec(WRITE, req, iovec, iter);
+}
+
+static int io_write(struct io_kiocb *req, struct io_kiocb **nxt,
bool force_nonblock)
{
struct iovec inline_vecs[UIO_FASTIOV], *iovec = inline_vecs;
@@ -1409,33 +1832,36 @@ static int io_write(struct io_kiocb *req, const struct sqe_submit *s,
struct iov_iter iter;
struct file *file;
size_t iov_count;
- ssize_t ret;
+ ssize_t ret, io_size;
- ret = io_prep_rw(req, s, force_nonblock);
- if (ret)
- return ret;
+ if (!req->io) {
+ ret = io_write_prep(req, &iovec, &iter, force_nonblock);
+ if (ret < 0)
+ return ret;
+ } else {
+ ret = io_import_iovec(WRITE, req, &iovec, &iter);
+ if (ret < 0)
+ return ret;
+ }
file = kiocb->ki_filp;
- if (unlikely(!(file->f_mode & FMODE_WRITE)))
- return -EBADF;
-
- ret = io_import_iovec(req->ctx, WRITE, s, &iovec, &iter);
- if (ret < 0)
- return ret;
-
+ io_size = ret;
if (req->flags & REQ_F_LINK)
- req->result = ret;
-
- iov_count = iov_iter_count(&iter);
+ req->result = io_size;
- ret = -EAGAIN;
- if (force_nonblock && !(kiocb->ki_flags & IOCB_DIRECT)) {
- /* If ->needs_lock is true, we're already in async context. */
- if (!s->needs_lock)
- io_async_list_note(WRITE, req, iov_count);
- goto out_free;
+ /*
+ * If the file doesn't support async, mark it as REQ_F_MUST_PUNT so
+ * we know to async punt it even if it was opened O_NONBLOCK
+ */
+ if (force_nonblock && !io_file_supports_async(req->file)) {
+ req->flags |= REQ_F_MUST_PUNT;
+ goto copy_iov;
}
+ if (force_nonblock && !(kiocb->ki_flags & IOCB_DIRECT))
+ goto copy_iov;
+
+ iov_count = iov_iter_count(&iter);
ret = rw_verify_area(WRITE, file, &kiocb->ki_pos, iov_count);
if (!ret) {
ssize_t ret2;
@@ -1447,7 +1873,7 @@ static int io_write(struct io_kiocb *req, const struct sqe_submit *s,
* released so that it doesn't complain about the held lock when
* we return to userspace.
*/
- if (S_ISREG(file_inode(file)->i_mode)) {
+ if (req->flags & REQ_F_ISREG) {
__sb_start_write(file_inode(file)->i_sb,
SB_FREEZE_WRITE, true);
__sb_writers_release(file_inode(file)->i_sb,
@@ -1460,15 +1886,14 @@ static int io_write(struct io_kiocb *req, const struct sqe_submit *s,
else
ret2 = loop_rw_iter(WRITE, file, kiocb, &iter);
if (!force_nonblock || ret2 != -EAGAIN) {
- io_rw_done(kiocb, ret2);
+ kiocb_done(kiocb, ret2, nxt, req->in_async);
} else {
- /*
- * If ->needs_lock is true, we're already in async
- * context.
- */
- if (!s->needs_lock)
- io_async_list_note(WRITE, req, iov_count);
- ret = -EAGAIN;
+copy_iov:
+ ret = io_setup_async_io(req, io_size, iovec,
+ inline_vecs, &iter);
+ if (ret)
+ goto out_free;
+ return -EAGAIN;
}
}
out_free:
@@ -1479,15 +1904,14 @@ out_free:
/*
* IORING_OP_NOP just posts a completion event, nothing else.
*/
-static int io_nop(struct io_kiocb *req, u64 user_data)
+static int io_nop(struct io_kiocb *req)
{
struct io_ring_ctx *ctx = req->ctx;
- long err = 0;
if (unlikely(ctx->flags & IORING_SETUP_IOPOLL))
return -EINVAL;
- io_cqring_add_event(ctx, user_data, err);
+ io_cqring_add_event(req, 0);
io_put_req(req);
return 0;
}
@@ -1508,7 +1932,7 @@ static int io_prep_fsync(struct io_kiocb *req, const struct io_uring_sqe *sqe)
}
static int io_fsync(struct io_kiocb *req, const struct io_uring_sqe *sqe,
- bool force_nonblock)
+ struct io_kiocb **nxt, bool force_nonblock)
{
loff_t sqe_off = READ_ONCE(sqe->off);
loff_t sqe_len = READ_ONCE(sqe->len);
@@ -1534,8 +1958,8 @@ static int io_fsync(struct io_kiocb *req, const struct io_uring_sqe *sqe,
if (ret < 0 && (req->flags & REQ_F_LINK))
req->flags |= REQ_F_FAIL_LINK;
- io_cqring_add_event(req->ctx, sqe->user_data, ret);
- io_put_req(req);
+ io_cqring_add_event(req, ret);
+ io_put_req_find_next(req, nxt);
return 0;
}
@@ -1557,6 +1981,7 @@ static int io_prep_sfr(struct io_kiocb *req, const struct io_uring_sqe *sqe)
static int io_sync_file_range(struct io_kiocb *req,
const struct io_uring_sqe *sqe,
+ struct io_kiocb **nxt,
bool force_nonblock)
{
loff_t sqe_off;
@@ -1580,17 +2005,109 @@ static int io_sync_file_range(struct io_kiocb *req,
if (ret < 0 && (req->flags & REQ_F_LINK))
req->flags |= REQ_F_FAIL_LINK;
- io_cqring_add_event(req->ctx, sqe->user_data, ret);
- io_put_req(req);
+ io_cqring_add_event(req, ret);
+ io_put_req_find_next(req, nxt);
+ return 0;
+}
+
+static int io_sendmsg_prep(struct io_kiocb *req, struct io_async_ctx *io)
+{
+#if defined(CONFIG_NET)
+ const struct io_uring_sqe *sqe = req->sqe;
+ struct user_msghdr __user *msg;
+ unsigned flags;
+
+ flags = READ_ONCE(sqe->msg_flags);
+ msg = (struct user_msghdr __user *)(unsigned long) READ_ONCE(sqe->addr);
+ return sendmsg_copy_msghdr(&io->msg.msg, msg, flags, &io->msg.iov);
+#else
+ return 0;
+#endif
+}
+
+static int io_sendmsg(struct io_kiocb *req, const struct io_uring_sqe *sqe,
+ struct io_kiocb **nxt, bool force_nonblock)
+{
+#if defined(CONFIG_NET)
+ struct socket *sock;
+ int ret;
+
+ if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL))
+ return -EINVAL;
+
+ sock = sock_from_file(req->file, &ret);
+ if (sock) {
+ struct io_async_ctx io, *copy;
+ struct sockaddr_storage addr;
+ struct msghdr *kmsg;
+ unsigned flags;
+
+ flags = READ_ONCE(sqe->msg_flags);
+ if (flags & MSG_DONTWAIT)
+ req->flags |= REQ_F_NOWAIT;
+ else if (force_nonblock)
+ flags |= MSG_DONTWAIT;
+
+ if (req->io) {
+ kmsg = &req->io->msg.msg;
+ kmsg->msg_name = &addr;
+ } else {
+ kmsg = &io.msg.msg;
+ kmsg->msg_name = &addr;
+ io.msg.iov = io.msg.fast_iov;
+ ret = io_sendmsg_prep(req, &io);
+ if (ret)
+ goto out;
+ }
+
+ ret = __sys_sendmsg_sock(sock, kmsg, flags);
+ if (force_nonblock && ret == -EAGAIN) {
+ copy = kmalloc(sizeof(*copy), GFP_KERNEL);
+ if (!copy) {
+ ret = -ENOMEM;
+ goto out;
+ }
+ memcpy(&copy->msg, &io.msg, sizeof(copy->msg));
+ req->io = copy;
+ memcpy(&req->io->sqe, req->sqe, sizeof(*req->sqe));
+ req->sqe = &req->io->sqe;
+ return ret;
+ }
+ if (ret == -ERESTARTSYS)
+ ret = -EINTR;
+ }
+
+out:
+ io_cqring_add_event(req, ret);
+ if (ret < 0 && (req->flags & REQ_F_LINK))
+ req->flags |= REQ_F_FAIL_LINK;
+ io_put_req_find_next(req, nxt);
return 0;
+#else
+ return -EOPNOTSUPP;
+#endif
}
+static int io_recvmsg_prep(struct io_kiocb *req, struct io_async_ctx *io)
+{
#if defined(CONFIG_NET)
-static int io_send_recvmsg(struct io_kiocb *req, const struct io_uring_sqe *sqe,
- bool force_nonblock,
- long (*fn)(struct socket *, struct user_msghdr __user *,
- unsigned int))
+ const struct io_uring_sqe *sqe = req->sqe;
+ struct user_msghdr __user *msg;
+ unsigned flags;
+
+ flags = READ_ONCE(sqe->msg_flags);
+ msg = (struct user_msghdr __user *)(unsigned long) READ_ONCE(sqe->addr);
+ return recvmsg_copy_msghdr(&io->msg.msg, msg, flags, &io->msg.uaddr,
+ &io->msg.iov);
+#else
+ return 0;
+#endif
+}
+
+static int io_recvmsg(struct io_kiocb *req, const struct io_uring_sqe *sqe,
+ struct io_kiocb **nxt, bool force_nonblock)
{
+#if defined(CONFIG_NET)
struct socket *sock;
int ret;
@@ -1600,6 +2117,9 @@ static int io_send_recvmsg(struct io_kiocb *req, const struct io_uring_sqe *sqe,
sock = sock_from_file(req->file, &ret);
if (sock) {
struct user_msghdr __user *msg;
+ struct io_async_ctx io, *copy;
+ struct sockaddr_storage addr;
+ struct msghdr *kmsg;
unsigned flags;
flags = READ_ONCE(sqe->msg_flags);
@@ -1610,33 +2130,144 @@ static int io_send_recvmsg(struct io_kiocb *req, const struct io_uring_sqe *sqe,
msg = (struct user_msghdr __user *) (unsigned long)
READ_ONCE(sqe->addr);
+ if (req->io) {
+ kmsg = &req->io->msg.msg;
+ kmsg->msg_name = &addr;
+ } else {
+ kmsg = &io.msg.msg;
+ kmsg->msg_name = &addr;
+ io.msg.iov = io.msg.fast_iov;
+ ret = io_recvmsg_prep(req, &io);
+ if (ret)
+ goto out;
+ }
- ret = fn(sock, msg, flags);
- if (force_nonblock && ret == -EAGAIN)
+ ret = __sys_recvmsg_sock(sock, kmsg, msg, io.msg.uaddr, flags);
+ if (force_nonblock && ret == -EAGAIN) {
+ copy = kmalloc(sizeof(*copy), GFP_KERNEL);
+ if (!copy) {
+ ret = -ENOMEM;
+ goto out;
+ }
+ memcpy(copy, &io, sizeof(*copy));
+ req->io = copy;
+ memcpy(&req->io->sqe, req->sqe, sizeof(*req->sqe));
+ req->sqe = &req->io->sqe;
return ret;
+ }
+ if (ret == -ERESTARTSYS)
+ ret = -EINTR;
}
- io_cqring_add_event(req->ctx, sqe->user_data, ret);
- io_put_req(req);
+out:
+ io_cqring_add_event(req, ret);
+ if (ret < 0 && (req->flags & REQ_F_LINK))
+ req->flags |= REQ_F_FAIL_LINK;
+ io_put_req_find_next(req, nxt);
return 0;
-}
+#else
+ return -EOPNOTSUPP;
#endif
+}
-static int io_sendmsg(struct io_kiocb *req, const struct io_uring_sqe *sqe,
- bool force_nonblock)
+static int io_accept(struct io_kiocb *req, const struct io_uring_sqe *sqe,
+ struct io_kiocb **nxt, bool force_nonblock)
{
#if defined(CONFIG_NET)
- return io_send_recvmsg(req, sqe, force_nonblock, __sys_sendmsg_sock);
+ struct sockaddr __user *addr;
+ int __user *addr_len;
+ unsigned file_flags;
+ int flags, ret;
+
+ if (unlikely(req->ctx->flags & (IORING_SETUP_IOPOLL|IORING_SETUP_SQPOLL)))
+ return -EINVAL;
+ if (sqe->ioprio || sqe->len || sqe->buf_index)
+ return -EINVAL;
+
+ addr = (struct sockaddr __user *) (unsigned long) READ_ONCE(sqe->addr);
+ addr_len = (int __user *) (unsigned long) READ_ONCE(sqe->addr2);
+ flags = READ_ONCE(sqe->accept_flags);
+ file_flags = force_nonblock ? O_NONBLOCK : 0;
+
+ ret = __sys_accept4_file(req->file, file_flags, addr, addr_len, flags);
+ if (ret == -EAGAIN && force_nonblock) {
+ req->work.flags |= IO_WQ_WORK_NEEDS_FILES;
+ return -EAGAIN;
+ }
+ if (ret == -ERESTARTSYS)
+ ret = -EINTR;
+ if (ret < 0 && (req->flags & REQ_F_LINK))
+ req->flags |= REQ_F_FAIL_LINK;
+ io_cqring_add_event(req, ret);
+ io_put_req_find_next(req, nxt);
+ return 0;
#else
return -EOPNOTSUPP;
#endif
}
-static int io_recvmsg(struct io_kiocb *req, const struct io_uring_sqe *sqe,
- bool force_nonblock)
+static int io_connect_prep(struct io_kiocb *req, struct io_async_ctx *io)
+{
+#if defined(CONFIG_NET)
+ const struct io_uring_sqe *sqe = req->sqe;
+ struct sockaddr __user *addr;
+ int addr_len;
+
+ addr = (struct sockaddr __user *) (unsigned long) READ_ONCE(sqe->addr);
+ addr_len = READ_ONCE(sqe->addr2);
+ return move_addr_to_kernel(addr, addr_len, &io->connect.address);
+#else
+ return 0;
+#endif
+}
+
+static int io_connect(struct io_kiocb *req, const struct io_uring_sqe *sqe,
+ struct io_kiocb **nxt, bool force_nonblock)
{
#if defined(CONFIG_NET)
- return io_send_recvmsg(req, sqe, force_nonblock, __sys_recvmsg_sock);
+ struct io_async_ctx __io, *io;
+ unsigned file_flags;
+ int addr_len, ret;
+
+ if (unlikely(req->ctx->flags & (IORING_SETUP_IOPOLL|IORING_SETUP_SQPOLL)))
+ return -EINVAL;
+ if (sqe->ioprio || sqe->len || sqe->buf_index || sqe->rw_flags)
+ return -EINVAL;
+
+ addr_len = READ_ONCE(sqe->addr2);
+ file_flags = force_nonblock ? O_NONBLOCK : 0;
+
+ if (req->io) {
+ io = req->io;
+ } else {
+ ret = io_connect_prep(req, &__io);
+ if (ret)
+ goto out;
+ io = &__io;
+ }
+
+ ret = __sys_connect_file(req->file, &io->connect.address, addr_len,
+ file_flags);
+ if ((ret == -EAGAIN || ret == -EINPROGRESS) && force_nonblock) {
+ io = kmalloc(sizeof(*io), GFP_KERNEL);
+ if (!io) {
+ ret = -ENOMEM;
+ goto out;
+ }
+ memcpy(&io->connect, &__io.connect, sizeof(io->connect));
+ req->io = io;
+ memcpy(&io->sqe, req->sqe, sizeof(*req->sqe));
+ req->sqe = &io->sqe;
+ return -EAGAIN;
+ }
+ if (ret == -ERESTARTSYS)
+ ret = -EINTR;
+out:
+ if (ret < 0 && (req->flags & REQ_F_LINK))
+ req->flags |= REQ_F_FAIL_LINK;
+ io_cqring_add_event(req, ret);
+ io_put_req_find_next(req, nxt);
+ return 0;
#else
return -EOPNOTSUPP;
#endif
@@ -1648,27 +2279,47 @@ static void io_poll_remove_one(struct io_kiocb *req)
spin_lock(&poll->head->lock);
WRITE_ONCE(poll->canceled, true);
- if (!list_empty(&poll->wait.entry)) {
- list_del_init(&poll->wait.entry);
- io_queue_async_work(req->ctx, req);
+ if (!list_empty(&poll->wait->entry)) {
+ list_del_init(&poll->wait->entry);
+ io_queue_async_work(req);
}
spin_unlock(&poll->head->lock);
-
- list_del_init(&req->list);
+ hash_del(&req->hash_node);
}
static void io_poll_remove_all(struct io_ring_ctx *ctx)
{
+ struct hlist_node *tmp;
struct io_kiocb *req;
+ int i;
spin_lock_irq(&ctx->completion_lock);
- while (!list_empty(&ctx->cancel_list)) {
- req = list_first_entry(&ctx->cancel_list, struct io_kiocb,list);
- io_poll_remove_one(req);
+ for (i = 0; i < (1U << ctx->cancel_hash_bits); i++) {
+ struct hlist_head *list;
+
+ list = &ctx->cancel_hash[i];
+ hlist_for_each_entry_safe(req, tmp, list, hash_node)
+ io_poll_remove_one(req);
}
spin_unlock_irq(&ctx->completion_lock);
}
+static int io_poll_cancel(struct io_ring_ctx *ctx, __u64 sqe_addr)
+{
+ struct hlist_head *list;
+ struct io_kiocb *req;
+
+ list = &ctx->cancel_hash[hash_long(sqe_addr, ctx->cancel_hash_bits)];
+ hlist_for_each_entry(req, list, hash_node) {
+ if (sqe_addr == req->user_data) {
+ io_poll_remove_one(req);
+ return 0;
+ }
+ }
+
+ return -ENOENT;
+}
+
/*
* Find a running poll command that matches one specified in sqe->addr,
* and remove it if found.
@@ -1676,8 +2327,7 @@ static void io_poll_remove_all(struct io_ring_ctx *ctx)
static int io_poll_remove(struct io_kiocb *req, const struct io_uring_sqe *sqe)
{
struct io_ring_ctx *ctx = req->ctx;
- struct io_kiocb *poll_req, *next;
- int ret = -ENOENT;
+ int ret;
if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL))
return -EINVAL;
@@ -1686,37 +2336,48 @@ static int io_poll_remove(struct io_kiocb *req, const struct io_uring_sqe *sqe)
return -EINVAL;
spin_lock_irq(&ctx->completion_lock);
- list_for_each_entry_safe(poll_req, next, &ctx->cancel_list, list) {
- if (READ_ONCE(sqe->addr) == poll_req->user_data) {
- io_poll_remove_one(poll_req);
- ret = 0;
- break;
- }
- }
+ ret = io_poll_cancel(ctx, READ_ONCE(sqe->addr));
spin_unlock_irq(&ctx->completion_lock);
- io_cqring_add_event(req->ctx, sqe->user_data, ret);
+ io_cqring_add_event(req, ret);
+ if (ret < 0 && (req->flags & REQ_F_LINK))
+ req->flags |= REQ_F_FAIL_LINK;
io_put_req(req);
return 0;
}
-static void io_poll_complete(struct io_ring_ctx *ctx, struct io_kiocb *req,
- __poll_t mask)
+static void io_poll_complete(struct io_kiocb *req, __poll_t mask, int error)
{
+ struct io_ring_ctx *ctx = req->ctx;
+
req->poll.done = true;
- io_cqring_fill_event(ctx, req->user_data, mangle_poll(mask));
+ kfree(req->poll.wait);
+ if (error)
+ io_cqring_fill_event(req, error);
+ else
+ io_cqring_fill_event(req, mangle_poll(mask));
io_commit_cqring(ctx);
}
-static void io_poll_complete_work(struct work_struct *work)
+static void io_poll_complete_work(struct io_wq_work **workptr)
{
+ struct io_wq_work *work = *workptr;
struct io_kiocb *req = container_of(work, struct io_kiocb, work);
struct io_poll_iocb *poll = &req->poll;
struct poll_table_struct pt = { ._key = poll->events };
struct io_ring_ctx *ctx = req->ctx;
+ struct io_kiocb *nxt = NULL;
__poll_t mask = 0;
+ int ret = 0;
- if (!READ_ONCE(poll->canceled))
+ if (work->flags & IO_WQ_WORK_CANCEL) {
+ WRITE_ONCE(poll->canceled, true);
+ ret = -ECANCELED;
+ } else if (READ_ONCE(poll->canceled)) {
+ ret = -ECANCELED;
+ }
+
+ if (ret != -ECANCELED)
mask = vfs_poll(poll->file, &pt) & poll->events;
/*
@@ -1727,24 +2388,28 @@ static void io_poll_complete_work(struct work_struct *work)
* avoid further branches in the fast path.
*/
spin_lock_irq(&ctx->completion_lock);
- if (!mask && !READ_ONCE(poll->canceled)) {
- add_wait_queue(poll->head, &poll->wait);
+ if (!mask && ret != -ECANCELED) {
+ add_wait_queue(poll->head, poll->wait);
spin_unlock_irq(&ctx->completion_lock);
return;
}
- list_del_init(&req->list);
- io_poll_complete(ctx, req, mask);
+ hash_del(&req->hash_node);
+ io_poll_complete(req, mask, ret);
spin_unlock_irq(&ctx->completion_lock);
io_cqring_ev_posted(ctx);
- io_put_req(req);
+
+ if (ret < 0 && req->flags & REQ_F_LINK)
+ req->flags |= REQ_F_FAIL_LINK;
+ io_put_req_find_next(req, &nxt);
+ if (nxt)
+ *workptr = &nxt->work;
}
static int io_poll_wake(struct wait_queue_entry *wait, unsigned mode, int sync,
void *key)
{
- struct io_poll_iocb *poll = container_of(wait, struct io_poll_iocb,
- wait);
+ struct io_poll_iocb *poll = wait->private;
struct io_kiocb *req = container_of(poll, struct io_kiocb, poll);
struct io_ring_ctx *ctx = req->ctx;
__poll_t mask = key_to_poll(key);
@@ -1754,17 +2419,24 @@ static int io_poll_wake(struct wait_queue_entry *wait, unsigned mode, int sync,
if (mask && !(mask & poll->events))
return 0;
- list_del_init(&poll->wait.entry);
+ list_del_init(&poll->wait->entry);
+ /*
+ * Run completion inline if we can. We're using trylock here because
+ * we are violating the completion_lock -> poll wq lock ordering.
+ * If we have a link timeout we're going to need the completion_lock
+ * for finalizing the request, mark us as having grabbed that already.
+ */
if (mask && spin_trylock_irqsave(&ctx->completion_lock, flags)) {
- list_del(&req->list);
- io_poll_complete(ctx, req, mask);
+ hash_del(&req->hash_node);
+ io_poll_complete(req, mask, 0);
+ req->flags |= REQ_F_COMP_LOCKED;
+ io_put_req(req);
spin_unlock_irqrestore(&ctx->completion_lock, flags);
io_cqring_ev_posted(ctx);
- io_put_req(req);
} else {
- io_queue_async_work(ctx, req);
+ io_queue_async_work(req);
}
return 1;
@@ -1788,10 +2460,20 @@ static void io_poll_queue_proc(struct file *file, struct wait_queue_head *head,
pt->error = 0;
pt->req->poll.head = head;
- add_wait_queue(head, &pt->req->poll.wait);
+ add_wait_queue(head, pt->req->poll.wait);
+}
+
+static void io_poll_req_insert(struct io_kiocb *req)
+{
+ struct io_ring_ctx *ctx = req->ctx;
+ struct hlist_head *list;
+
+ list = &ctx->cancel_hash[hash_long(req->user_data, ctx->cancel_hash_bits)];
+ hlist_add_head(&req->hash_node, list);
}
-static int io_poll_add(struct io_kiocb *req, const struct io_uring_sqe *sqe)
+static int io_poll_add(struct io_kiocb *req, const struct io_uring_sqe *sqe,
+ struct io_kiocb **nxt)
{
struct io_poll_iocb *poll = &req->poll;
struct io_ring_ctx *ctx = req->ctx;
@@ -1807,10 +2489,15 @@ static int io_poll_add(struct io_kiocb *req, const struct io_uring_sqe *sqe)
if (!poll->file)
return -EBADF;
- req->submit.sqe = NULL;
- INIT_WORK(&req->work, io_poll_complete_work);
+ poll->wait = kmalloc(sizeof(*poll->wait), GFP_KERNEL);
+ if (!poll->wait)
+ return -ENOMEM;
+
+ req->io = NULL;
+ INIT_IO_WORK(&req->work, io_poll_complete_work);
events = READ_ONCE(sqe->poll_events);
poll->events = demangle_poll(events) | EPOLLERR | EPOLLHUP;
+ INIT_HLIST_NODE(&req->hash_node);
poll->head = NULL;
poll->done = false;
@@ -1822,8 +2509,9 @@ static int io_poll_add(struct io_kiocb *req, const struct io_uring_sqe *sqe)
ipt.error = -EINVAL; /* same as no support for IOCB_CMD_POLL */
/* initialized the list so that we can do list_empty checks */
- INIT_LIST_HEAD(&poll->wait.entry);
- init_waitqueue_func_entry(&poll->wait, io_poll_wake);
+ INIT_LIST_HEAD(&poll->wait->entry);
+ init_waitqueue_func_entry(poll->wait, io_poll_wake);
+ poll->wait->private = poll;
INIT_LIST_HEAD(&req->list);
@@ -1832,187 +2520,464 @@ static int io_poll_add(struct io_kiocb *req, const struct io_uring_sqe *sqe)
spin_lock_irq(&ctx->completion_lock);
if (likely(poll->head)) {
spin_lock(&poll->head->lock);
- if (unlikely(list_empty(&poll->wait.entry))) {
+ if (unlikely(list_empty(&poll->wait->entry))) {
if (ipt.error)
cancel = true;
ipt.error = 0;
mask = 0;
}
if (mask || ipt.error)
- list_del_init(&poll->wait.entry);
+ list_del_init(&poll->wait->entry);
else if (cancel)
WRITE_ONCE(poll->canceled, true);
else if (!poll->done) /* actually waiting for an event */
- list_add_tail(&req->list, &ctx->cancel_list);
+ io_poll_req_insert(req);
spin_unlock(&poll->head->lock);
}
if (mask) { /* no async, we'd stolen it */
ipt.error = 0;
- io_poll_complete(ctx, req, mask);
+ io_poll_complete(req, mask, 0);
}
spin_unlock_irq(&ctx->completion_lock);
if (mask) {
io_cqring_ev_posted(ctx);
- io_put_req(req);
+ io_put_req_find_next(req, nxt);
}
return ipt.error;
}
static enum hrtimer_restart io_timeout_fn(struct hrtimer *timer)
{
- struct io_ring_ctx *ctx;
- struct io_kiocb *req;
+ struct io_timeout_data *data = container_of(timer,
+ struct io_timeout_data, timer);
+ struct io_kiocb *req = data->req;
+ struct io_ring_ctx *ctx = req->ctx;
unsigned long flags;
- req = container_of(timer, struct io_kiocb, timeout.timer);
- ctx = req->ctx;
atomic_inc(&ctx->cq_timeouts);
spin_lock_irqsave(&ctx->completion_lock, flags);
- list_del(&req->list);
+ /*
+ * We could be racing with timeout deletion. If the list is empty,
+ * then timeout lookup already found it and will be handling it.
+ */
+ if (!list_empty(&req->list)) {
+ struct io_kiocb *prev;
+
+ /*
+ * Adjust the reqs sequence before the current one because it
+ * will consume a slot in the cq_ring and the the cq_tail
+ * pointer will be increased, otherwise other timeout reqs may
+ * return in advance without waiting for enough wait_nr.
+ */
+ prev = req;
+ list_for_each_entry_continue_reverse(prev, &ctx->timeout_list, list)
+ prev->sequence++;
+ list_del_init(&req->list);
+ }
- io_cqring_fill_event(ctx, req->user_data, -ETIME);
+ io_cqring_fill_event(req, -ETIME);
io_commit_cqring(ctx);
spin_unlock_irqrestore(&ctx->completion_lock, flags);
io_cqring_ev_posted(ctx);
-
+ if (req->flags & REQ_F_LINK)
+ req->flags |= REQ_F_FAIL_LINK;
io_put_req(req);
return HRTIMER_NORESTART;
}
-static int io_timeout(struct io_kiocb *req, const struct io_uring_sqe *sqe)
+static int io_timeout_cancel(struct io_ring_ctx *ctx, __u64 user_data)
+{
+ struct io_kiocb *req;
+ int ret = -ENOENT;
+
+ list_for_each_entry(req, &ctx->timeout_list, list) {
+ if (user_data == req->user_data) {
+ list_del_init(&req->list);
+ ret = 0;
+ break;
+ }
+ }
+
+ if (ret == -ENOENT)
+ return ret;
+
+ ret = hrtimer_try_to_cancel(&req->io->timeout.timer);
+ if (ret == -1)
+ return -EALREADY;
+
+ if (req->flags & REQ_F_LINK)
+ req->flags |= REQ_F_FAIL_LINK;
+ io_cqring_fill_event(req, -ECANCELED);
+ io_put_req(req);
+ return 0;
+}
+
+/*
+ * Remove or update an existing timeout command
+ */
+static int io_timeout_remove(struct io_kiocb *req,
+ const struct io_uring_sqe *sqe)
{
- unsigned count, req_dist, tail_index;
struct io_ring_ctx *ctx = req->ctx;
- struct list_head *entry;
- struct timespec64 ts;
+ unsigned flags;
+ int ret;
if (unlikely(ctx->flags & IORING_SETUP_IOPOLL))
return -EINVAL;
- if (sqe->flags || sqe->ioprio || sqe->buf_index || sqe->timeout_flags ||
- sqe->len != 1)
+ if (sqe->flags || sqe->ioprio || sqe->buf_index || sqe->len)
+ return -EINVAL;
+ flags = READ_ONCE(sqe->timeout_flags);
+ if (flags)
+ return -EINVAL;
+
+ spin_lock_irq(&ctx->completion_lock);
+ ret = io_timeout_cancel(ctx, READ_ONCE(sqe->addr));
+
+ io_cqring_fill_event(req, ret);
+ io_commit_cqring(ctx);
+ spin_unlock_irq(&ctx->completion_lock);
+ io_cqring_ev_posted(ctx);
+ if (ret < 0 && req->flags & REQ_F_LINK)
+ req->flags |= REQ_F_FAIL_LINK;
+ io_put_req(req);
+ return 0;
+}
+
+static int io_timeout_prep(struct io_kiocb *req, struct io_async_ctx *io,
+ bool is_timeout_link)
+{
+ const struct io_uring_sqe *sqe = req->sqe;
+ struct io_timeout_data *data;
+ unsigned flags;
+
+ if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL))
+ return -EINVAL;
+ if (sqe->ioprio || sqe->buf_index || sqe->len != 1)
+ return -EINVAL;
+ if (sqe->off && is_timeout_link)
+ return -EINVAL;
+ flags = READ_ONCE(sqe->timeout_flags);
+ if (flags & ~IORING_TIMEOUT_ABS)
return -EINVAL;
- if (get_timespec64(&ts, u64_to_user_ptr(sqe->addr)))
+ data = &io->timeout;
+ data->req = req;
+ req->flags |= REQ_F_TIMEOUT;
+
+ if (get_timespec64(&data->ts, u64_to_user_ptr(sqe->addr)))
return -EFAULT;
+ if (flags & IORING_TIMEOUT_ABS)
+ data->mode = HRTIMER_MODE_ABS;
+ else
+ data->mode = HRTIMER_MODE_REL;
+
+ hrtimer_init(&data->timer, CLOCK_MONOTONIC, data->mode);
+ req->io = io;
+ return 0;
+}
+
+static int io_timeout(struct io_kiocb *req, const struct io_uring_sqe *sqe)
+{
+ unsigned count;
+ struct io_ring_ctx *ctx = req->ctx;
+ struct io_timeout_data *data;
+ struct io_async_ctx *io;
+ struct list_head *entry;
+ unsigned span = 0;
+
+ io = req->io;
+ if (!io) {
+ int ret;
+
+ io = kmalloc(sizeof(*io), GFP_KERNEL);
+ if (!io)
+ return -ENOMEM;
+ ret = io_timeout_prep(req, io, false);
+ if (ret) {
+ kfree(io);
+ return ret;
+ }
+ }
+ data = &req->io->timeout;
+
/*
* sqe->off holds how many events that need to occur for this
- * timeout event to be satisfied.
+ * timeout event to be satisfied. If it isn't set, then this is
+ * a pure timeout request, sequence isn't used.
*/
count = READ_ONCE(sqe->off);
- if (!count)
- count = 1;
+ if (!count) {
+ req->flags |= REQ_F_TIMEOUT_NOSEQ;
+ spin_lock_irq(&ctx->completion_lock);
+ entry = ctx->timeout_list.prev;
+ goto add;
+ }
req->sequence = ctx->cached_sq_head + count - 1;
- req->flags |= REQ_F_TIMEOUT;
+ data->seq_offset = count;
/*
* Insertion sort, ensuring the first entry in the list is always
* the one we need first.
*/
- tail_index = ctx->cached_cq_tail - ctx->rings->sq_dropped;
- req_dist = req->sequence - tail_index;
spin_lock_irq(&ctx->completion_lock);
list_for_each_prev(entry, &ctx->timeout_list) {
struct io_kiocb *nxt = list_entry(entry, struct io_kiocb, list);
- unsigned dist;
+ unsigned nxt_sq_head;
+ long long tmp, tmp_nxt;
+ u32 nxt_offset = nxt->io->timeout.seq_offset;
+
+ if (nxt->flags & REQ_F_TIMEOUT_NOSEQ)
+ continue;
+
+ /*
+ * Since cached_sq_head + count - 1 can overflow, use type long
+ * long to store it.
+ */
+ tmp = (long long)ctx->cached_sq_head + count - 1;
+ nxt_sq_head = nxt->sequence - nxt_offset + 1;
+ tmp_nxt = (long long)nxt_sq_head + nxt_offset - 1;
+
+ /*
+ * cached_sq_head may overflow, and it will never overflow twice
+ * once there is some timeout req still be valid.
+ */
+ if (ctx->cached_sq_head < nxt_sq_head)
+ tmp += UINT_MAX;
- dist = nxt->sequence - tail_index;
- if (req_dist >= dist)
+ if (tmp > tmp_nxt)
break;
+
+ /*
+ * Sequence of reqs after the insert one and itself should
+ * be adjusted because each timeout req consumes a slot.
+ */
+ span++;
+ nxt->sequence++;
}
+ req->sequence -= span;
+add:
list_add(&req->list, entry);
+ data->timer.function = io_timeout_fn;
+ hrtimer_start(&data->timer, timespec64_to_ktime(data->ts), data->mode);
spin_unlock_irq(&ctx->completion_lock);
+ return 0;
+}
+
+static bool io_cancel_cb(struct io_wq_work *work, void *data)
+{
+ struct io_kiocb *req = container_of(work, struct io_kiocb, work);
- hrtimer_init(&req->timeout.timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
- req->timeout.timer.function = io_timeout_fn;
- hrtimer_start(&req->timeout.timer, timespec64_to_ktime(ts),
- HRTIMER_MODE_REL);
+ return req->user_data == (unsigned long) data;
+}
+
+static int io_async_cancel_one(struct io_ring_ctx *ctx, void *sqe_addr)
+{
+ enum io_wq_cancel cancel_ret;
+ int ret = 0;
+
+ cancel_ret = io_wq_cancel_cb(ctx->io_wq, io_cancel_cb, sqe_addr);
+ switch (cancel_ret) {
+ case IO_WQ_CANCEL_OK:
+ ret = 0;
+ break;
+ case IO_WQ_CANCEL_RUNNING:
+ ret = -EALREADY;
+ break;
+ case IO_WQ_CANCEL_NOTFOUND:
+ ret = -ENOENT;
+ break;
+ }
+
+ return ret;
+}
+
+static void io_async_find_and_cancel(struct io_ring_ctx *ctx,
+ struct io_kiocb *req, __u64 sqe_addr,
+ struct io_kiocb **nxt, int success_ret)
+{
+ unsigned long flags;
+ int ret;
+
+ ret = io_async_cancel_one(ctx, (void *) (unsigned long) sqe_addr);
+ if (ret != -ENOENT) {
+ spin_lock_irqsave(&ctx->completion_lock, flags);
+ goto done;
+ }
+
+ spin_lock_irqsave(&ctx->completion_lock, flags);
+ ret = io_timeout_cancel(ctx, sqe_addr);
+ if (ret != -ENOENT)
+ goto done;
+ ret = io_poll_cancel(ctx, sqe_addr);
+done:
+ if (!ret)
+ ret = success_ret;
+ io_cqring_fill_event(req, ret);
+ io_commit_cqring(ctx);
+ spin_unlock_irqrestore(&ctx->completion_lock, flags);
+ io_cqring_ev_posted(ctx);
+
+ if (ret < 0 && (req->flags & REQ_F_LINK))
+ req->flags |= REQ_F_FAIL_LINK;
+ io_put_req_find_next(req, nxt);
+}
+
+static int io_async_cancel(struct io_kiocb *req, const struct io_uring_sqe *sqe,
+ struct io_kiocb **nxt)
+{
+ struct io_ring_ctx *ctx = req->ctx;
+
+ if (unlikely(ctx->flags & IORING_SETUP_IOPOLL))
+ return -EINVAL;
+ if (sqe->flags || sqe->ioprio || sqe->off || sqe->len ||
+ sqe->cancel_flags)
+ return -EINVAL;
+
+ io_async_find_and_cancel(ctx, req, READ_ONCE(sqe->addr), nxt, 0);
+ return 0;
+}
+
+static int io_req_defer_prep(struct io_kiocb *req, struct io_async_ctx *io)
+{
+ struct iovec inline_vecs[UIO_FASTIOV], *iovec = inline_vecs;
+ struct iov_iter iter;
+ ssize_t ret;
+
+ memcpy(&io->sqe, req->sqe, sizeof(io->sqe));
+ req->sqe = &io->sqe;
+
+ switch (io->sqe.opcode) {
+ case IORING_OP_READV:
+ case IORING_OP_READ_FIXED:
+ ret = io_read_prep(req, &iovec, &iter, true);
+ break;
+ case IORING_OP_WRITEV:
+ case IORING_OP_WRITE_FIXED:
+ ret = io_write_prep(req, &iovec, &iter, true);
+ break;
+ case IORING_OP_SENDMSG:
+ ret = io_sendmsg_prep(req, io);
+ break;
+ case IORING_OP_RECVMSG:
+ ret = io_recvmsg_prep(req, io);
+ break;
+ case IORING_OP_CONNECT:
+ ret = io_connect_prep(req, io);
+ break;
+ case IORING_OP_TIMEOUT:
+ return io_timeout_prep(req, io, false);
+ case IORING_OP_LINK_TIMEOUT:
+ return io_timeout_prep(req, io, true);
+ default:
+ req->io = io;
+ return 0;
+ }
+
+ if (ret < 0)
+ return ret;
+
+ req->io = io;
+ io_req_map_io(req, ret, iovec, inline_vecs, &iter);
return 0;
}
-static int io_req_defer(struct io_ring_ctx *ctx, struct io_kiocb *req,
- const struct io_uring_sqe *sqe)
+static int io_req_defer(struct io_kiocb *req)
{
- struct io_uring_sqe *sqe_copy;
+ struct io_ring_ctx *ctx = req->ctx;
+ struct io_async_ctx *io;
+ int ret;
- if (!io_sequence_defer(ctx, req) && list_empty(&ctx->defer_list))
+ /* Still need defer if there is pending req in defer list. */
+ if (!req_need_defer(req) && list_empty(&ctx->defer_list))
return 0;
- sqe_copy = kmalloc(sizeof(*sqe_copy), GFP_KERNEL);
- if (!sqe_copy)
+ io = kmalloc(sizeof(*io), GFP_KERNEL);
+ if (!io)
return -EAGAIN;
+ ret = io_req_defer_prep(req, io);
+ if (ret < 0) {
+ kfree(io);
+ return ret;
+ }
+
spin_lock_irq(&ctx->completion_lock);
- if (!io_sequence_defer(ctx, req) && list_empty(&ctx->defer_list)) {
+ if (!req_need_defer(req) && list_empty(&ctx->defer_list)) {
spin_unlock_irq(&ctx->completion_lock);
- kfree(sqe_copy);
return 0;
}
- memcpy(sqe_copy, sqe, sizeof(*sqe_copy));
- req->submit.sqe = sqe_copy;
-
- INIT_WORK(&req->work, io_sq_wq_submit_work);
+ trace_io_uring_defer(ctx, req, req->user_data);
list_add_tail(&req->list, &ctx->defer_list);
spin_unlock_irq(&ctx->completion_lock);
return -EIOCBQUEUED;
}
-static int __io_submit_sqe(struct io_ring_ctx *ctx, struct io_kiocb *req,
- const struct sqe_submit *s, bool force_nonblock)
+__attribute__((nonnull))
+static int io_issue_sqe(struct io_kiocb *req, struct io_kiocb **nxt,
+ bool force_nonblock)
{
int ret, opcode;
+ struct io_ring_ctx *ctx = req->ctx;
- req->user_data = READ_ONCE(s->sqe->user_data);
-
- if (unlikely(s->index >= ctx->sq_entries))
- return -EINVAL;
-
- opcode = READ_ONCE(s->sqe->opcode);
+ opcode = READ_ONCE(req->sqe->opcode);
switch (opcode) {
case IORING_OP_NOP:
- ret = io_nop(req, req->user_data);
+ ret = io_nop(req);
break;
case IORING_OP_READV:
- if (unlikely(s->sqe->buf_index))
+ if (unlikely(req->sqe->buf_index))
return -EINVAL;
- ret = io_read(req, s, force_nonblock);
+ ret = io_read(req, nxt, force_nonblock);
break;
case IORING_OP_WRITEV:
- if (unlikely(s->sqe->buf_index))
+ if (unlikely(req->sqe->buf_index))
return -EINVAL;
- ret = io_write(req, s, force_nonblock);
+ ret = io_write(req, nxt, force_nonblock);
break;
case IORING_OP_READ_FIXED:
- ret = io_read(req, s, force_nonblock);
+ ret = io_read(req, nxt, force_nonblock);
break;
case IORING_OP_WRITE_FIXED:
- ret = io_write(req, s, force_nonblock);
+ ret = io_write(req, nxt, force_nonblock);
break;
case IORING_OP_FSYNC:
- ret = io_fsync(req, s->sqe, force_nonblock);
+ ret = io_fsync(req, req->sqe, nxt, force_nonblock);
break;
case IORING_OP_POLL_ADD:
- ret = io_poll_add(req, s->sqe);
+ ret = io_poll_add(req, req->sqe, nxt);
break;
case IORING_OP_POLL_REMOVE:
- ret = io_poll_remove(req, s->sqe);
+ ret = io_poll_remove(req, req->sqe);
break;
case IORING_OP_SYNC_FILE_RANGE:
- ret = io_sync_file_range(req, s->sqe, force_nonblock);
+ ret = io_sync_file_range(req, req->sqe, nxt, force_nonblock);
break;
case IORING_OP_SENDMSG:
- ret = io_sendmsg(req, s->sqe, force_nonblock);
+ ret = io_sendmsg(req, req->sqe, nxt, force_nonblock);
break;
case IORING_OP_RECVMSG:
- ret = io_recvmsg(req, s->sqe, force_nonblock);
+ ret = io_recvmsg(req, req->sqe, nxt, force_nonblock);
break;
case IORING_OP_TIMEOUT:
- ret = io_timeout(req, s->sqe);
+ ret = io_timeout(req, req->sqe);
+ break;
+ case IORING_OP_TIMEOUT_REMOVE:
+ ret = io_timeout_remove(req, req->sqe);
+ break;
+ case IORING_OP_ACCEPT:
+ ret = io_accept(req, req->sqe, nxt, force_nonblock);
+ break;
+ case IORING_OP_CONNECT:
+ ret = io_connect(req, req->sqe, nxt, force_nonblock);
+ break;
+ case IORING_OP_ASYNC_CANCEL:
+ ret = io_async_cancel(req, req->sqe, nxt);
break;
default:
ret = -EINVAL;
@@ -2027,187 +2992,76 @@ static int __io_submit_sqe(struct io_ring_ctx *ctx, struct io_kiocb *req,
return -EAGAIN;
/* workqueue context doesn't hold uring_lock, grab it now */
- if (s->needs_lock)
+ if (req->in_async)
mutex_lock(&ctx->uring_lock);
io_iopoll_req_issued(req);
- if (s->needs_lock)
+ if (req->in_async)
mutex_unlock(&ctx->uring_lock);
}
return 0;
}
-static struct async_list *io_async_list_from_sqe(struct io_ring_ctx *ctx,
- const struct io_uring_sqe *sqe)
+static void io_link_work_cb(struct io_wq_work **workptr)
{
- switch (sqe->opcode) {
- case IORING_OP_READV:
- case IORING_OP_READ_FIXED:
- return &ctx->pending_async[READ];
- case IORING_OP_WRITEV:
- case IORING_OP_WRITE_FIXED:
- return &ctx->pending_async[WRITE];
- default:
- return NULL;
- }
-}
+ struct io_wq_work *work = *workptr;
+ struct io_kiocb *link = work->data;
-static inline bool io_sqe_needs_user(const struct io_uring_sqe *sqe)
-{
- u8 opcode = READ_ONCE(sqe->opcode);
-
- return !(opcode == IORING_OP_READ_FIXED ||
- opcode == IORING_OP_WRITE_FIXED);
+ io_queue_linked_timeout(link);
+ work->func = io_wq_submit_work;
}
-static void io_sq_wq_submit_work(struct work_struct *work)
+static void io_wq_submit_work(struct io_wq_work **workptr)
{
+ struct io_wq_work *work = *workptr;
struct io_kiocb *req = container_of(work, struct io_kiocb, work);
- struct io_ring_ctx *ctx = req->ctx;
- struct mm_struct *cur_mm = NULL;
- struct async_list *async_list;
- LIST_HEAD(req_list);
- mm_segment_t old_fs;
- int ret;
+ struct io_kiocb *nxt = NULL;
+ int ret = 0;
- async_list = io_async_list_from_sqe(ctx, req->submit.sqe);
-restart:
- do {
- struct sqe_submit *s = &req->submit;
- const struct io_uring_sqe *sqe = s->sqe;
- unsigned int flags = req->flags;
+ /* Ensure we clear previously set non-block flag */
+ req->rw.ki_flags &= ~IOCB_NOWAIT;
- /* Ensure we clear previously set non-block flag */
- req->rw.ki_flags &= ~IOCB_NOWAIT;
+ if (work->flags & IO_WQ_WORK_CANCEL)
+ ret = -ECANCELED;
- ret = 0;
- if (io_sqe_needs_user(sqe) && !cur_mm) {
- if (!mmget_not_zero(ctx->sqo_mm)) {
- ret = -EFAULT;
- } else {
- cur_mm = ctx->sqo_mm;
- use_mm(cur_mm);
- old_fs = get_fs();
- set_fs(USER_DS);
- }
- }
+ if (!ret) {
+ req->has_user = (work->flags & IO_WQ_WORK_HAS_MM) != 0;
+ req->in_async = true;
+ do {
+ ret = io_issue_sqe(req, &nxt, false);
+ /*
+ * We can get EAGAIN for polled IO even though we're
+ * forcing a sync submission from here, since we can't
+ * wait for request slots on the block side.
+ */
+ if (ret != -EAGAIN)
+ break;
+ cond_resched();
+ } while (1);
+ }
- if (!ret) {
- s->has_user = cur_mm != NULL;
- s->needs_lock = true;
- do {
- ret = __io_submit_sqe(ctx, req, s, false);
- /*
- * We can get EAGAIN for polled IO even though
- * we're forcing a sync submission from here,
- * since we can't wait for request slots on the
- * block side.
- */
- if (ret != -EAGAIN)
- break;
- cond_resched();
- } while (1);
- }
+ /* drop submission reference */
+ io_put_req(req);
- /* drop submission reference */
+ if (ret) {
+ if (req->flags & REQ_F_LINK)
+ req->flags |= REQ_F_FAIL_LINK;
+ io_cqring_add_event(req, ret);
io_put_req(req);
-
- if (ret) {
- io_cqring_add_event(ctx, sqe->user_data, ret);
- io_put_req(req);
- }
-
- /* async context always use a copy of the sqe */
- kfree(sqe);
-
- /* req from defer and link list needn't decrease async cnt */
- if (flags & (REQ_F_IO_DRAINED | REQ_F_LINK_DONE))
- goto out;
-
- if (!async_list)
- break;
- if (!list_empty(&req_list)) {
- req = list_first_entry(&req_list, struct io_kiocb,
- list);
- list_del(&req->list);
- continue;
- }
- if (list_empty(&async_list->list))
- break;
-
- req = NULL;
- spin_lock(&async_list->lock);
- if (list_empty(&async_list->list)) {
- spin_unlock(&async_list->lock);
- break;
- }
- list_splice_init(&async_list->list, &req_list);
- spin_unlock(&async_list->lock);
-
- req = list_first_entry(&req_list, struct io_kiocb, list);
- list_del(&req->list);
- } while (req);
-
- /*
- * Rare case of racing with a submitter. If we find the count has
- * dropped to zero AND we have pending work items, then restart
- * the processing. This is a tiny race window.
- */
- if (async_list) {
- ret = atomic_dec_return(&async_list->cnt);
- while (!ret && !list_empty(&async_list->list)) {
- spin_lock(&async_list->lock);
- atomic_inc(&async_list->cnt);
- list_splice_init(&async_list->list, &req_list);
- spin_unlock(&async_list->lock);
-
- if (!list_empty(&req_list)) {
- req = list_first_entry(&req_list,
- struct io_kiocb, list);
- list_del(&req->list);
- goto restart;
- }
- ret = atomic_dec_return(&async_list->cnt);
- }
- }
-
-out:
- if (cur_mm) {
- set_fs(old_fs);
- unuse_mm(cur_mm);
- mmput(cur_mm);
}
-}
-
-/*
- * See if we can piggy back onto previously submitted work, that is still
- * running. We currently only allow this if the new request is sequential
- * to the previous one we punted.
- */
-static bool io_add_to_prev_work(struct async_list *list, struct io_kiocb *req)
-{
- bool ret;
- if (!list)
- return false;
- if (!(req->flags & REQ_F_SEQ_PREV))
- return false;
- if (!atomic_read(&list->cnt))
- return false;
+ /* if a dependent link is ready, pass it back */
+ if (!ret && nxt) {
+ struct io_kiocb *link;
- ret = true;
- spin_lock(&list->lock);
- list_add_tail(&req->list, &list->list);
- /*
- * Ensure we see a simultaneous modification from io_sq_wq_submit_work()
- */
- smp_mb();
- if (!atomic_read(&list->cnt)) {
- list_del_init(&req->list);
- ret = false;
+ io_prep_async_work(nxt, &link);
+ *workptr = &nxt->work;
+ if (link) {
+ nxt->work.flags |= IO_WQ_WORK_CB;
+ nxt->work.func = io_link_work_cb;
+ nxt->work.data = link;
+ }
}
- spin_unlock(&list->lock);
- return ret;
}
static bool io_op_needs_file(const struct io_uring_sqe *sqe)
@@ -2217,42 +3071,53 @@ static bool io_op_needs_file(const struct io_uring_sqe *sqe)
switch (op) {
case IORING_OP_NOP:
case IORING_OP_POLL_REMOVE:
+ case IORING_OP_TIMEOUT:
+ case IORING_OP_TIMEOUT_REMOVE:
+ case IORING_OP_ASYNC_CANCEL:
+ case IORING_OP_LINK_TIMEOUT:
return false;
default:
return true;
}
}
-static int io_req_set_file(struct io_ring_ctx *ctx, const struct sqe_submit *s,
- struct io_submit_state *state, struct io_kiocb *req)
+static inline struct file *io_file_from_index(struct io_ring_ctx *ctx,
+ int index)
{
+ struct fixed_file_table *table;
+
+ table = &ctx->file_table[index >> IORING_FILE_TABLE_SHIFT];
+ return table->files[index & IORING_FILE_TABLE_MASK];
+}
+
+static int io_req_set_file(struct io_submit_state *state, struct io_kiocb *req)
+{
+ struct io_ring_ctx *ctx = req->ctx;
unsigned flags;
int fd;
- flags = READ_ONCE(s->sqe->flags);
- fd = READ_ONCE(s->sqe->fd);
+ flags = READ_ONCE(req->sqe->flags);
+ fd = READ_ONCE(req->sqe->fd);
if (flags & IOSQE_IO_DRAIN)
req->flags |= REQ_F_IO_DRAIN;
- /*
- * All io need record the previous position, if LINK vs DARIN,
- * it can be used to mark the position of the first IO in the
- * link list.
- */
- req->sequence = s->sequence;
- if (!io_op_needs_file(s->sqe))
+ if (!io_op_needs_file(req->sqe))
return 0;
if (flags & IOSQE_FIXED_FILE) {
- if (unlikely(!ctx->user_files ||
+ if (unlikely(!ctx->file_table ||
(unsigned) fd >= ctx->nr_user_files))
return -EBADF;
- req->file = ctx->user_files[fd];
+ fd = array_index_nospec(fd, ctx->nr_user_files);
+ req->file = io_file_from_index(ctx, fd);
+ if (!req->file)
+ return -EBADF;
req->flags |= REQ_F_FIXED_FILE;
} else {
- if (s->needs_fixed_file)
+ if (req->needs_fixed_file)
return -EBADF;
+ trace_io_uring_file_get(ctx, fd);
req->file = io_file_get(state, fd);
if (unlikely(!req->file))
return -EBADF;
@@ -2261,139 +3126,213 @@ static int io_req_set_file(struct io_ring_ctx *ctx, const struct sqe_submit *s,
return 0;
}
-static int __io_queue_sqe(struct io_ring_ctx *ctx, struct io_kiocb *req,
- struct sqe_submit *s, bool force_nonblock)
+static int io_grab_files(struct io_kiocb *req)
{
- int ret;
+ int ret = -EBADF;
+ struct io_ring_ctx *ctx = req->ctx;
- ret = __io_submit_sqe(ctx, req, s, force_nonblock);
- if (ret == -EAGAIN && !(req->flags & REQ_F_NOWAIT)) {
- struct io_uring_sqe *sqe_copy;
-
- sqe_copy = kmemdup(s->sqe, sizeof(*sqe_copy), GFP_KERNEL);
- if (sqe_copy) {
- struct async_list *list;
-
- s->sqe = sqe_copy;
- memcpy(&req->submit, s, sizeof(*s));
- list = io_async_list_from_sqe(ctx, s->sqe);
- if (!io_add_to_prev_work(list, req)) {
- if (list)
- atomic_inc(&list->cnt);
- INIT_WORK(&req->work, io_sq_wq_submit_work);
- io_queue_async_work(ctx, req);
- }
+ rcu_read_lock();
+ spin_lock_irq(&ctx->inflight_lock);
+ /*
+ * We use the f_ops->flush() handler to ensure that we can flush
+ * out work accessing these files if the fd is closed. Check if
+ * the fd has changed since we started down this path, and disallow
+ * this operation if it has.
+ */
+ if (fcheck(req->ring_fd) == req->ring_file) {
+ list_add(&req->inflight_entry, &ctx->inflight_list);
+ req->flags |= REQ_F_INFLIGHT;
+ req->work.files = current->files;
+ ret = 0;
+ }
+ spin_unlock_irq(&ctx->inflight_lock);
+ rcu_read_unlock();
- /*
- * Queued up for async execution, worker will release
- * submit reference when the iocb is actually submitted.
- */
- return 0;
- }
+ return ret;
+}
+
+static enum hrtimer_restart io_link_timeout_fn(struct hrtimer *timer)
+{
+ struct io_timeout_data *data = container_of(timer,
+ struct io_timeout_data, timer);
+ struct io_kiocb *req = data->req;
+ struct io_ring_ctx *ctx = req->ctx;
+ struct io_kiocb *prev = NULL;
+ unsigned long flags;
+
+ spin_lock_irqsave(&ctx->completion_lock, flags);
+
+ /*
+ * We don't expect the list to be empty, that will only happen if we
+ * race with the completion of the linked work.
+ */
+ if (!list_empty(&req->link_list)) {
+ prev = list_entry(req->link_list.prev, struct io_kiocb,
+ link_list);
+ if (refcount_inc_not_zero(&prev->refs)) {
+ list_del_init(&req->link_list);
+ prev->flags &= ~REQ_F_LINK_TIMEOUT;
+ } else
+ prev = NULL;
}
- /* drop submission reference */
- io_put_req(req);
+ spin_unlock_irqrestore(&ctx->completion_lock, flags);
- /* and drop final reference, if we failed */
- if (ret) {
- io_cqring_add_event(ctx, req->user_data, ret);
- if (req->flags & REQ_F_LINK)
- req->flags |= REQ_F_FAIL_LINK;
+ if (prev) {
+ if (prev->flags & REQ_F_LINK)
+ prev->flags |= REQ_F_FAIL_LINK;
+ io_async_find_and_cancel(ctx, req, prev->user_data, NULL,
+ -ETIME);
+ io_put_req(prev);
+ } else {
+ io_cqring_add_event(req, -ETIME);
io_put_req(req);
}
-
- return ret;
+ return HRTIMER_NORESTART;
}
-static int io_queue_sqe(struct io_ring_ctx *ctx, struct io_kiocb *req,
- struct sqe_submit *s, bool force_nonblock)
+static void io_queue_linked_timeout(struct io_kiocb *req)
{
- int ret;
+ struct io_ring_ctx *ctx = req->ctx;
- ret = io_req_defer(ctx, req, s->sqe);
- if (ret) {
- if (ret != -EIOCBQUEUED) {
- io_free_req(req);
- io_cqring_add_event(ctx, s->sqe->user_data, ret);
- }
- return 0;
+ /*
+ * If the list is now empty, then our linked request finished before
+ * we got a chance to setup the timer
+ */
+ spin_lock_irq(&ctx->completion_lock);
+ if (!list_empty(&req->link_list)) {
+ struct io_timeout_data *data = &req->io->timeout;
+
+ data->timer.function = io_link_timeout_fn;
+ hrtimer_start(&data->timer, timespec64_to_ktime(data->ts),
+ data->mode);
}
+ spin_unlock_irq(&ctx->completion_lock);
+
+ /* drop submission reference */
+ io_put_req(req);
+}
+
+static struct io_kiocb *io_prep_linked_timeout(struct io_kiocb *req)
+{
+ struct io_kiocb *nxt;
+
+ if (!(req->flags & REQ_F_LINK))
+ return NULL;
+
+ nxt = list_first_entry_or_null(&req->link_list, struct io_kiocb,
+ link_list);
+ if (!nxt || nxt->sqe->opcode != IORING_OP_LINK_TIMEOUT)
+ return NULL;
- return __io_queue_sqe(ctx, req, s, force_nonblock);
+ req->flags |= REQ_F_LINK_TIMEOUT;
+ return nxt;
}
-static int io_queue_link_head(struct io_ring_ctx *ctx, struct io_kiocb *req,
- struct sqe_submit *s, struct io_kiocb *shadow,
- bool force_nonblock)
+static void __io_queue_sqe(struct io_kiocb *req)
{
+ struct io_kiocb *linked_timeout = io_prep_linked_timeout(req);
+ struct io_kiocb *nxt = NULL;
int ret;
- int need_submit = false;
- if (!shadow)
- return io_queue_sqe(ctx, req, s, force_nonblock);
+ ret = io_issue_sqe(req, &nxt, true);
+ if (nxt)
+ io_queue_async_work(nxt);
/*
- * Mark the first IO in link list as DRAIN, let all the following
- * IOs enter the defer list. all IO needs to be completed before link
- * list.
+ * We async punt it if the file wasn't marked NOWAIT, or if the file
+ * doesn't support non-blocking read/write attempts
*/
- req->flags |= REQ_F_IO_DRAIN;
- ret = io_req_defer(ctx, req, s->sqe);
- if (ret) {
- if (ret != -EIOCBQUEUED) {
- io_free_req(req);
- io_cqring_add_event(ctx, s->sqe->user_data, ret);
- return 0;
+ if (ret == -EAGAIN && (!(req->flags & REQ_F_NOWAIT) ||
+ (req->flags & REQ_F_MUST_PUNT))) {
+ if (req->work.flags & IO_WQ_WORK_NEEDS_FILES) {
+ ret = io_grab_files(req);
+ if (ret)
+ goto err;
}
- } else {
+
/*
- * If ret == 0 means that all IOs in front of link io are
- * running done. let's queue link head.
+ * Queued up for async execution, worker will release
+ * submit reference when the iocb is actually submitted.
*/
- need_submit = true;
+ io_queue_async_work(req);
+ return;
}
- /* Insert shadow req to defer_list, blocking next IOs */
- spin_lock_irq(&ctx->completion_lock);
- list_add_tail(&shadow->list, &ctx->defer_list);
- spin_unlock_irq(&ctx->completion_lock);
+err:
+ /* drop submission reference */
+ io_put_req(req);
- if (need_submit)
- return __io_queue_sqe(ctx, req, s, force_nonblock);
+ if (linked_timeout) {
+ if (!ret)
+ io_queue_linked_timeout(linked_timeout);
+ else
+ io_put_req(linked_timeout);
+ }
- return 0;
+ /* and drop final reference, if we failed */
+ if (ret) {
+ io_cqring_add_event(req, ret);
+ if (req->flags & REQ_F_LINK)
+ req->flags |= REQ_F_FAIL_LINK;
+ io_put_req(req);
+ }
}
+static void io_queue_sqe(struct io_kiocb *req)
+{
+ int ret;
+
+ if (unlikely(req->ctx->drain_next)) {
+ req->flags |= REQ_F_IO_DRAIN;
+ req->ctx->drain_next = false;
+ }
+ req->ctx->drain_next = (req->flags & REQ_F_DRAIN_LINK);
+
+ ret = io_req_defer(req);
+ if (ret) {
+ if (ret != -EIOCBQUEUED) {
+ io_cqring_add_event(req, ret);
+ if (req->flags & REQ_F_LINK)
+ req->flags |= REQ_F_FAIL_LINK;
+ io_double_put_req(req);
+ }
+ } else
+ __io_queue_sqe(req);
+}
+
+static inline void io_queue_link_head(struct io_kiocb *req)
+{
+ if (unlikely(req->flags & REQ_F_FAIL_LINK)) {
+ io_cqring_add_event(req, -ECANCELED);
+ io_double_put_req(req);
+ } else
+ io_queue_sqe(req);
+}
+
+
#define SQE_VALID_FLAGS (IOSQE_FIXED_FILE|IOSQE_IO_DRAIN|IOSQE_IO_LINK)
-static void io_submit_sqe(struct io_ring_ctx *ctx, struct sqe_submit *s,
- struct io_submit_state *state, struct io_kiocb **link,
- bool force_nonblock)
+static bool io_submit_sqe(struct io_kiocb *req, struct io_submit_state *state,
+ struct io_kiocb **link)
{
- struct io_uring_sqe *sqe_copy;
- struct io_kiocb *req;
+ struct io_ring_ctx *ctx = req->ctx;
int ret;
+ req->user_data = req->sqe->user_data;
+
/* enforce forwards compatibility on users */
- if (unlikely(s->sqe->flags & ~SQE_VALID_FLAGS)) {
+ if (unlikely(req->sqe->flags & ~SQE_VALID_FLAGS)) {
ret = -EINVAL;
- goto err;
+ goto err_req;
}
- req = io_get_req(ctx, state);
- if (unlikely(!req)) {
- ret = -EAGAIN;
- goto err;
- }
-
- ret = io_req_set_file(ctx, s, state, req);
+ ret = io_req_set_file(state, req);
if (unlikely(ret)) {
err_req:
- io_free_req(req);
-err:
- io_cqring_add_event(ctx, s->sqe->user_data, ret);
- return;
+ io_cqring_add_event(req, ret);
+ io_double_put_req(req);
+ return false;
}
/*
@@ -2405,25 +3344,35 @@ err:
*/
if (*link) {
struct io_kiocb *prev = *link;
+ struct io_async_ctx *io;
+
+ if (req->sqe->flags & IOSQE_IO_DRAIN)
+ (*link)->flags |= REQ_F_DRAIN_LINK | REQ_F_IO_DRAIN;
- sqe_copy = kmemdup(s->sqe, sizeof(*sqe_copy), GFP_KERNEL);
- if (!sqe_copy) {
+ io = kmalloc(sizeof(*io), GFP_KERNEL);
+ if (!io) {
ret = -EAGAIN;
goto err_req;
}
- s->sqe = sqe_copy;
- memcpy(&req->submit, s, sizeof(*s));
- list_add_tail(&req->list, &prev->link_list);
- } else if (s->sqe->flags & IOSQE_IO_LINK) {
+ ret = io_req_defer_prep(req, io);
+ if (ret) {
+ kfree(io);
+ prev->flags |= REQ_F_FAIL_LINK;
+ goto err_req;
+ }
+ trace_io_uring_link(ctx, req, prev);
+ list_add_tail(&req->link_list, &prev->link_list);
+ } else if (req->sqe->flags & IOSQE_IO_LINK) {
req->flags |= REQ_F_LINK;
- memcpy(&req->submit, s, sizeof(*s));
INIT_LIST_HEAD(&req->link_list);
*link = req;
} else {
- io_queue_sqe(ctx, req, s, force_nonblock);
+ io_queue_sqe(req);
}
+
+ return true;
}
/*
@@ -2442,7 +3391,7 @@ static void io_submit_state_end(struct io_submit_state *state)
* Start submission side cache.
*/
static void io_submit_state_start(struct io_submit_state *state,
- struct io_ring_ctx *ctx, unsigned max_ios)
+ unsigned int max_ios)
{
blk_start_plug(&state->plug);
state->free_reqs = 0;
@@ -2472,7 +3421,7 @@ static void io_commit_sqring(struct io_ring_ctx *ctx)
* used, it's important that those reads are done through READ_ONCE() to
* prevent a re-load down the line.
*/
-static bool io_get_sqring(struct io_ring_ctx *ctx, struct sqe_submit *s)
+static bool io_get_sqring(struct io_ring_ctx *ctx, struct io_kiocb *req)
{
struct io_rings *rings = ctx->rings;
u32 *sq_array = ctx->sq_array;
@@ -2488,108 +3437,143 @@ static bool io_get_sqring(struct io_ring_ctx *ctx, struct sqe_submit *s)
*/
head = ctx->cached_sq_head;
/* make sure SQ entry isn't read before tail */
- if (head == smp_load_acquire(&rings->sq.tail))
+ if (unlikely(head == smp_load_acquire(&rings->sq.tail)))
return false;
head = READ_ONCE(sq_array[head & ctx->sq_mask]);
- if (head < ctx->sq_entries) {
- s->index = head;
- s->sqe = &ctx->sq_sqes[head];
- s->sequence = ctx->cached_sq_head;
+ if (likely(head < ctx->sq_entries)) {
+ /*
+ * All io need record the previous position, if LINK vs DARIN,
+ * it can be used to mark the position of the first IO in the
+ * link list.
+ */
+ req->sequence = ctx->cached_sq_head;
+ req->sqe = &ctx->sq_sqes[head];
ctx->cached_sq_head++;
return true;
}
/* drop invalid entries */
ctx->cached_sq_head++;
- rings->sq_dropped++;
+ ctx->cached_sq_dropped++;
+ WRITE_ONCE(rings->sq_dropped, ctx->cached_sq_dropped);
return false;
}
-static int io_submit_sqes(struct io_ring_ctx *ctx, struct sqe_submit *sqes,
- unsigned int nr, bool has_user, bool mm_fault)
+static int io_submit_sqes(struct io_ring_ctx *ctx, unsigned int nr,
+ struct file *ring_file, int ring_fd,
+ struct mm_struct **mm, bool async)
{
struct io_submit_state state, *statep = NULL;
struct io_kiocb *link = NULL;
- struct io_kiocb *shadow_req = NULL;
- bool prev_was_link = false;
int i, submitted = 0;
+ bool mm_fault = false;
+
+ /* if we have a backlog and couldn't flush it all, return BUSY */
+ if (!list_empty(&ctx->cq_overflow_list) &&
+ !io_cqring_overflow_flush(ctx, false))
+ return -EBUSY;
if (nr > IO_PLUG_THRESHOLD) {
- io_submit_state_start(&state, ctx, nr);
+ io_submit_state_start(&state, nr);
statep = &state;
}
for (i = 0; i < nr; i++) {
+ struct io_kiocb *req;
+ unsigned int sqe_flags;
+
+ req = io_get_req(ctx, statep);
+ if (unlikely(!req)) {
+ if (!submitted)
+ submitted = -EAGAIN;
+ break;
+ }
+ if (!io_get_sqring(ctx, req)) {
+ __io_free_req(req);
+ break;
+ }
+
+ if (io_sqe_needs_user(req->sqe) && !*mm) {
+ mm_fault = mm_fault || !mmget_not_zero(ctx->sqo_mm);
+ if (!mm_fault) {
+ use_mm(ctx->sqo_mm);
+ *mm = ctx->sqo_mm;
+ }
+ }
+
+ submitted++;
+ sqe_flags = req->sqe->flags;
+
+ req->ring_file = ring_file;
+ req->ring_fd = ring_fd;
+ req->has_user = *mm != NULL;
+ req->in_async = async;
+ req->needs_fixed_file = async;
+ trace_io_uring_submit_sqe(ctx, req->sqe->user_data,
+ true, async);
+ if (!io_submit_sqe(req, statep, &link))
+ break;
/*
* If previous wasn't linked and we have a linked command,
* that's the end of the chain. Submit the previous link.
*/
- if (!prev_was_link && link) {
- io_queue_link_head(ctx, link, &link->submit, shadow_req,
- true);
+ if (!(sqe_flags & IOSQE_IO_LINK) && link) {
+ io_queue_link_head(link);
link = NULL;
- shadow_req = NULL;
- }
- prev_was_link = (sqes[i].sqe->flags & IOSQE_IO_LINK) != 0;
-
- if (link && (sqes[i].sqe->flags & IOSQE_IO_DRAIN)) {
- if (!shadow_req) {
- shadow_req = io_get_req(ctx, NULL);
- if (unlikely(!shadow_req))
- goto out;
- shadow_req->flags |= (REQ_F_IO_DRAIN | REQ_F_SHADOW_DRAIN);
- refcount_dec(&shadow_req->refs);
- }
- shadow_req->sequence = sqes[i].sequence;
- }
-
-out:
- if (unlikely(mm_fault)) {
- io_cqring_add_event(ctx, sqes[i].sqe->user_data,
- -EFAULT);
- } else {
- sqes[i].has_user = has_user;
- sqes[i].needs_lock = true;
- sqes[i].needs_fixed_file = true;
- io_submit_sqe(ctx, &sqes[i], statep, &link, true);
- submitted++;
}
}
if (link)
- io_queue_link_head(ctx, link, &link->submit, shadow_req, true);
+ io_queue_link_head(link);
if (statep)
io_submit_state_end(&state);
+ /* Commit SQ ring head once we've consumed and submitted all SQEs */
+ io_commit_sqring(ctx);
+
return submitted;
}
static int io_sq_thread(void *data)
{
- struct sqe_submit sqes[IO_IOPOLL_BATCH];
struct io_ring_ctx *ctx = data;
struct mm_struct *cur_mm = NULL;
+ const struct cred *old_cred;
mm_segment_t old_fs;
DEFINE_WAIT(wait);
unsigned inflight;
unsigned long timeout;
+ int ret;
- complete(&ctx->sqo_thread_started);
+ complete(&ctx->completions[1]);
old_fs = get_fs();
set_fs(USER_DS);
+ old_cred = override_creds(ctx->creds);
- timeout = inflight = 0;
+ ret = timeout = inflight = 0;
while (!kthread_should_park()) {
- bool all_fixed, mm_fault = false;
- int i;
+ unsigned int to_submit;
if (inflight) {
unsigned nr_events = 0;
if (ctx->flags & IORING_SETUP_IOPOLL) {
- io_iopoll_check(ctx, &nr_events, 0);
+ /*
+ * inflight is the count of the maximum possible
+ * entries we submitted, but it can be smaller
+ * if we dropped some of them. If we don't have
+ * poll entries available, then we know that we
+ * have nothing left to poll for. Reset the
+ * inflight count to zero in that case.
+ */
+ mutex_lock(&ctx->uring_lock);
+ if (!list_empty(&ctx->poll_list))
+ __io_iopoll_check(ctx, &nr_events, 0);
+ else
+ inflight = 0;
+ mutex_unlock(&ctx->uring_lock);
} else {
/*
* Normal IO, just pretend everything completed.
@@ -2603,13 +3587,22 @@ static int io_sq_thread(void *data)
timeout = jiffies + ctx->sq_thread_idle;
}
- if (!io_get_sqring(ctx, &sqes[0])) {
+ to_submit = io_sqring_entries(ctx);
+
+ /*
+ * If submit got -EBUSY, flag us as needing the application
+ * to enter the kernel to reap and flush events.
+ */
+ if (!to_submit || ret == -EBUSY) {
/*
* We're polling. If we're within the defined idle
* period, then let us spin without work before going
- * to sleep.
+ * to sleep. The exception is if we got EBUSY doing
+ * more IO, we should wait for the application to
+ * reap events and wake us up.
*/
- if (inflight || !time_after(jiffies, timeout)) {
+ if (inflight ||
+ (!time_after(jiffies, timeout) && ret != -EBUSY)) {
cond_resched();
continue;
}
@@ -2634,7 +3627,8 @@ static int io_sq_thread(void *data)
/* make sure to read SQ tail after writing flags */
smp_mb();
- if (!io_get_sqring(ctx, &sqes[0])) {
+ to_submit = io_sqring_entries(ctx);
+ if (!to_submit || ret == -EBUSY) {
if (kthread_should_park()) {
finish_wait(&ctx->sqo_wait, &wait);
break;
@@ -2652,31 +3646,10 @@ static int io_sq_thread(void *data)
ctx->rings->sq_flags &= ~IORING_SQ_NEED_WAKEUP;
}
- i = 0;
- all_fixed = true;
- do {
- if (all_fixed && io_sqe_needs_user(sqes[i].sqe))
- all_fixed = false;
-
- i++;
- if (i == ARRAY_SIZE(sqes))
- break;
- } while (io_get_sqring(ctx, &sqes[i]));
-
- /* Unless all new commands are FIXED regions, grab mm */
- if (!all_fixed && !cur_mm) {
- mm_fault = !mmget_not_zero(ctx->sqo_mm);
- if (!mm_fault) {
- use_mm(ctx->sqo_mm);
- cur_mm = ctx->sqo_mm;
- }
- }
-
- inflight += io_submit_sqes(ctx, sqes, i, cur_mm != NULL,
- mm_fault);
-
- /* Commit SQ ring head once we've consumed all SQEs */
- io_commit_sqring(ctx);
+ to_submit = min(to_submit, ctx->sq_entries);
+ ret = io_submit_sqes(ctx, to_submit, NULL, -1, &cur_mm, true);
+ if (ret > 0)
+ inflight += ret;
}
set_fs(old_fs);
@@ -2684,85 +3657,13 @@ static int io_sq_thread(void *data)
unuse_mm(cur_mm);
mmput(cur_mm);
}
+ revert_creds(old_cred);
kthread_parkme();
return 0;
}
-static int io_ring_submit(struct io_ring_ctx *ctx, unsigned int to_submit,
- bool block_for_last)
-{
- struct io_submit_state state, *statep = NULL;
- struct io_kiocb *link = NULL;
- struct io_kiocb *shadow_req = NULL;
- bool prev_was_link = false;
- int i, submit = 0;
-
- if (to_submit > IO_PLUG_THRESHOLD) {
- io_submit_state_start(&state, ctx, to_submit);
- statep = &state;
- }
-
- for (i = 0; i < to_submit; i++) {
- bool force_nonblock = true;
- struct sqe_submit s;
-
- if (!io_get_sqring(ctx, &s))
- break;
-
- /*
- * If previous wasn't linked and we have a linked command,
- * that's the end of the chain. Submit the previous link.
- */
- if (!prev_was_link && link) {
- io_queue_link_head(ctx, link, &link->submit, shadow_req,
- force_nonblock);
- link = NULL;
- shadow_req = NULL;
- }
- prev_was_link = (s.sqe->flags & IOSQE_IO_LINK) != 0;
-
- if (link && (s.sqe->flags & IOSQE_IO_DRAIN)) {
- if (!shadow_req) {
- shadow_req = io_get_req(ctx, NULL);
- if (unlikely(!shadow_req))
- goto out;
- shadow_req->flags |= (REQ_F_IO_DRAIN | REQ_F_SHADOW_DRAIN);
- refcount_dec(&shadow_req->refs);
- }
- shadow_req->sequence = s.sequence;
- }
-
-out:
- s.has_user = true;
- s.needs_lock = false;
- s.needs_fixed_file = false;
- submit++;
-
- /*
- * The caller will block for events after submit, submit the
- * last IO non-blocking. This is either the only IO it's
- * submitting, or it already submitted the previous ones. This
- * improves performance by avoiding an async punt that we don't
- * need to do.
- */
- if (block_for_last && submit == to_submit)
- force_nonblock = false;
-
- io_submit_sqe(ctx, &s, statep, &link, force_nonblock);
- }
- io_commit_sqring(ctx);
-
- if (link)
- io_queue_link_head(ctx, link, &link->submit, shadow_req,
- !block_for_last);
- if (statep)
- io_submit_state_end(statep);
-
- return submit;
-}
-
struct io_wait_queue {
struct wait_queue_entry wq;
struct io_ring_ctx *ctx;
@@ -2770,7 +3671,7 @@ struct io_wait_queue {
unsigned nr_timeouts;
};
-static inline bool io_should_wake(struct io_wait_queue *iowq)
+static inline bool io_should_wake(struct io_wait_queue *iowq, bool noflush)
{
struct io_ring_ctx *ctx = iowq->ctx;
@@ -2779,7 +3680,7 @@ static inline bool io_should_wake(struct io_wait_queue *iowq)
* started waiting. For timeouts, we always want to return to userspace,
* regardless of event count.
*/
- return io_cqring_events(ctx->rings) >= iowq->to_wait ||
+ return io_cqring_events(ctx, noflush) >= iowq->to_wait ||
atomic_read(&ctx->cq_timeouts) != iowq->nr_timeouts;
}
@@ -2789,7 +3690,8 @@ static int io_wake_function(struct wait_queue_entry *curr, unsigned int mode,
struct io_wait_queue *iowq = container_of(curr, struct io_wait_queue,
wq);
- if (!io_should_wake(iowq))
+ /* use noflush == true, as we can't safely rely on locking context */
+ if (!io_should_wake(iowq, true))
return -1;
return autoremove_wake_function(curr, mode, wake_flags, key);
@@ -2812,9 +3714,9 @@ static int io_cqring_wait(struct io_ring_ctx *ctx, int min_events,
.to_wait = min_events,
};
struct io_rings *rings = ctx->rings;
- int ret;
+ int ret = 0;
- if (io_cqring_events(rings) >= min_events)
+ if (io_cqring_events(ctx, false) >= min_events)
return 0;
if (sig) {
@@ -2830,24 +3732,22 @@ static int io_cqring_wait(struct io_ring_ctx *ctx, int min_events,
return ret;
}
- ret = 0;
iowq.nr_timeouts = atomic_read(&ctx->cq_timeouts);
+ trace_io_uring_cqring_wait(ctx, min_events);
do {
prepare_to_wait_exclusive(&ctx->wait, &iowq.wq,
TASK_INTERRUPTIBLE);
- if (io_should_wake(&iowq))
+ if (io_should_wake(&iowq, false))
break;
schedule();
if (signal_pending(current)) {
- ret = -ERESTARTSYS;
+ ret = -EINTR;
break;
}
} while (1);
finish_wait(&ctx->wait, &iowq.wq);
- restore_saved_sigmask_unless(ret == -ERESTARTSYS);
- if (ret == -ERESTARTSYS)
- ret = -EINTR;
+ restore_saved_sigmask_unless(ret == -EINTR);
return READ_ONCE(rings->cq.head) == READ_ONCE(rings->cq.tail) ? ret : 0;
}
@@ -2865,19 +3765,29 @@ static void __io_sqe_files_unregister(struct io_ring_ctx *ctx)
#else
int i;
- for (i = 0; i < ctx->nr_user_files; i++)
- fput(ctx->user_files[i]);
+ for (i = 0; i < ctx->nr_user_files; i++) {
+ struct file *file;
+
+ file = io_file_from_index(ctx, i);
+ if (file)
+ fput(file);
+ }
#endif
}
static int io_sqe_files_unregister(struct io_ring_ctx *ctx)
{
- if (!ctx->user_files)
+ unsigned nr_tables, i;
+
+ if (!ctx->file_table)
return -ENXIO;
__io_sqe_files_unregister(ctx);
- kfree(ctx->user_files);
- ctx->user_files = NULL;
+ nr_tables = DIV_ROUND_UP(ctx->nr_user_files, IORING_MAX_FILES_TABLE);
+ for (i = 0; i < nr_tables; i++)
+ kfree(ctx->file_table[i].files);
+ kfree(ctx->file_table);
+ ctx->file_table = NULL;
ctx->nr_user_files = 0;
return 0;
}
@@ -2885,7 +3795,7 @@ static int io_sqe_files_unregister(struct io_ring_ctx *ctx)
static void io_sq_thread_stop(struct io_ring_ctx *ctx)
{
if (ctx->sqo_thread) {
- wait_for_completion(&ctx->sqo_thread_started);
+ wait_for_completion(&ctx->completions[1]);
/*
* The park is a bit of a work-around, without it we get
* warning spews on shutdown with SQPOLL set and affinity
@@ -2899,15 +3809,11 @@ static void io_sq_thread_stop(struct io_ring_ctx *ctx)
static void io_finish_async(struct io_ring_ctx *ctx)
{
- int i;
-
io_sq_thread_stop(ctx);
- for (i = 0; i < ARRAY_SIZE(ctx->sqo_wq); i++) {
- if (ctx->sqo_wq[i]) {
- destroy_workqueue(ctx->sqo_wq[i]);
- ctx->sqo_wq[i] = NULL;
- }
+ if (ctx->io_wq) {
+ io_wq_destroy(ctx->io_wq);
+ ctx->io_wq = NULL;
}
}
@@ -2915,11 +3821,9 @@ static void io_finish_async(struct io_ring_ctx *ctx)
static void io_destruct_skb(struct sk_buff *skb)
{
struct io_ring_ctx *ctx = skb->sk->sk_user_data;
- int i;
- for (i = 0; i < ARRAY_SIZE(ctx->sqo_wq); i++)
- if (ctx->sqo_wq[i])
- flush_workqueue(ctx->sqo_wq[i]);
+ if (ctx->io_wq)
+ io_wq_flush(ctx->io_wq);
unix_destruct_scm(skb);
}
@@ -2934,7 +3838,7 @@ static int __io_sqe_files_scm(struct io_ring_ctx *ctx, int nr, int offset)
struct sock *sk = ctx->ring_sock->sk;
struct scm_fp_list *fpl;
struct sk_buff *skb;
- int i;
+ int i, nr_files;
if (!capable(CAP_SYS_RESOURCE) && !capable(CAP_SYS_ADMIN)) {
unsigned long inflight = ctx->user->unix_inflight + nr;
@@ -2954,21 +3858,33 @@ static int __io_sqe_files_scm(struct io_ring_ctx *ctx, int nr, int offset)
}
skb->sk = sk;
- skb->destructor = io_destruct_skb;
+ nr_files = 0;
fpl->user = get_uid(ctx->user);
for (i = 0; i < nr; i++) {
- fpl->fp[i] = get_file(ctx->user_files[i + offset]);
- unix_inflight(fpl->user, fpl->fp[i]);
+ struct file *file = io_file_from_index(ctx, i + offset);
+
+ if (!file)
+ continue;
+ fpl->fp[nr_files] = get_file(file);
+ unix_inflight(fpl->user, fpl->fp[nr_files]);
+ nr_files++;
}
- fpl->max = fpl->count = nr;
- UNIXCB(skb).fp = fpl;
- refcount_add(skb->truesize, &sk->sk_wmem_alloc);
- skb_queue_head(&sk->sk_receive_queue, skb);
+ if (nr_files) {
+ fpl->max = SCM_MAX_FD;
+ fpl->count = nr_files;
+ UNIXCB(skb).fp = fpl;
+ skb->destructor = io_destruct_skb;
+ refcount_add(skb->truesize, &sk->sk_wmem_alloc);
+ skb_queue_head(&sk->sk_receive_queue, skb);
- for (i = 0; i < nr; i++)
- fput(fpl->fp[i]);
+ for (i = 0; i < nr_files; i++)
+ fput(fpl->fp[i]);
+ } else {
+ kfree_skb(skb);
+ kfree(fpl);
+ }
return 0;
}
@@ -2999,7 +3915,10 @@ static int io_sqe_files_scm(struct io_ring_ctx *ctx)
return 0;
while (total < ctx->nr_user_files) {
- fput(ctx->user_files[total]);
+ struct file *file = io_file_from_index(ctx, total);
+
+ if (file)
+ fput(file);
total++;
}
@@ -3012,33 +3931,79 @@ static int io_sqe_files_scm(struct io_ring_ctx *ctx)
}
#endif
+static int io_sqe_alloc_file_tables(struct io_ring_ctx *ctx, unsigned nr_tables,
+ unsigned nr_files)
+{
+ int i;
+
+ for (i = 0; i < nr_tables; i++) {
+ struct fixed_file_table *table = &ctx->file_table[i];
+ unsigned this_files;
+
+ this_files = min(nr_files, IORING_MAX_FILES_TABLE);
+ table->files = kcalloc(this_files, sizeof(struct file *),
+ GFP_KERNEL);
+ if (!table->files)
+ break;
+ nr_files -= this_files;
+ }
+
+ if (i == nr_tables)
+ return 0;
+
+ for (i = 0; i < nr_tables; i++) {
+ struct fixed_file_table *table = &ctx->file_table[i];
+ kfree(table->files);
+ }
+ return 1;
+}
+
static int io_sqe_files_register(struct io_ring_ctx *ctx, void __user *arg,
unsigned nr_args)
{
__s32 __user *fds = (__s32 __user *) arg;
+ unsigned nr_tables;
int fd, ret = 0;
unsigned i;
- if (ctx->user_files)
+ if (ctx->file_table)
return -EBUSY;
if (!nr_args)
return -EINVAL;
if (nr_args > IORING_MAX_FIXED_FILES)
return -EMFILE;
- ctx->user_files = kcalloc(nr_args, sizeof(struct file *), GFP_KERNEL);
- if (!ctx->user_files)
+ nr_tables = DIV_ROUND_UP(nr_args, IORING_MAX_FILES_TABLE);
+ ctx->file_table = kcalloc(nr_tables, sizeof(struct fixed_file_table),
+ GFP_KERNEL);
+ if (!ctx->file_table)
return -ENOMEM;
- for (i = 0; i < nr_args; i++) {
+ if (io_sqe_alloc_file_tables(ctx, nr_tables, nr_args)) {
+ kfree(ctx->file_table);
+ ctx->file_table = NULL;
+ return -ENOMEM;
+ }
+
+ for (i = 0; i < nr_args; i++, ctx->nr_user_files++) {
+ struct fixed_file_table *table;
+ unsigned index;
+
ret = -EFAULT;
if (copy_from_user(&fd, &fds[i], sizeof(fd)))
break;
+ /* allow sparse sets */
+ if (fd == -1) {
+ ret = 0;
+ continue;
+ }
- ctx->user_files[i] = fget(fd);
+ table = &ctx->file_table[i >> IORING_FILE_TABLE_SHIFT];
+ index = i & IORING_FILE_TABLE_MASK;
+ table->files[index] = fget(fd);
ret = -EBADF;
- if (!ctx->user_files[i])
+ if (!table->files[index])
break;
/*
* Don't allow io_uring instances to be registered. If UNIX
@@ -3047,20 +4012,26 @@ static int io_sqe_files_register(struct io_ring_ctx *ctx, void __user *arg,
* handle it just fine, but there's still no point in allowing
* a ring fd as it doesn't support regular read/write anyway.
*/
- if (ctx->user_files[i]->f_op == &io_uring_fops) {
- fput(ctx->user_files[i]);
+ if (table->files[index]->f_op == &io_uring_fops) {
+ fput(table->files[index]);
break;
}
- ctx->nr_user_files++;
ret = 0;
}
if (ret) {
- for (i = 0; i < ctx->nr_user_files; i++)
- fput(ctx->user_files[i]);
+ for (i = 0; i < ctx->nr_user_files; i++) {
+ struct file *file;
+
+ file = io_file_from_index(ctx, i);
+ if (file)
+ fput(file);
+ }
+ for (i = 0; i < nr_tables; i++)
+ kfree(ctx->file_table[i].files);
- kfree(ctx->user_files);
- ctx->user_files = NULL;
+ kfree(ctx->file_table);
+ ctx->file_table = NULL;
ctx->nr_user_files = 0;
return ret;
}
@@ -3072,9 +4043,202 @@ static int io_sqe_files_register(struct io_ring_ctx *ctx, void __user *arg,
return ret;
}
+static void io_sqe_file_unregister(struct io_ring_ctx *ctx, int index)
+{
+#if defined(CONFIG_UNIX)
+ struct file *file = io_file_from_index(ctx, index);
+ struct sock *sock = ctx->ring_sock->sk;
+ struct sk_buff_head list, *head = &sock->sk_receive_queue;
+ struct sk_buff *skb;
+ int i;
+
+ __skb_queue_head_init(&list);
+
+ /*
+ * Find the skb that holds this file in its SCM_RIGHTS. When found,
+ * remove this entry and rearrange the file array.
+ */
+ skb = skb_dequeue(head);
+ while (skb) {
+ struct scm_fp_list *fp;
+
+ fp = UNIXCB(skb).fp;
+ for (i = 0; i < fp->count; i++) {
+ int left;
+
+ if (fp->fp[i] != file)
+ continue;
+
+ unix_notinflight(fp->user, fp->fp[i]);
+ left = fp->count - 1 - i;
+ if (left) {
+ memmove(&fp->fp[i], &fp->fp[i + 1],
+ left * sizeof(struct file *));
+ }
+ fp->count--;
+ if (!fp->count) {
+ kfree_skb(skb);
+ skb = NULL;
+ } else {
+ __skb_queue_tail(&list, skb);
+ }
+ fput(file);
+ file = NULL;
+ break;
+ }
+
+ if (!file)
+ break;
+
+ __skb_queue_tail(&list, skb);
+
+ skb = skb_dequeue(head);
+ }
+
+ if (skb_peek(&list)) {
+ spin_lock_irq(&head->lock);
+ while ((skb = __skb_dequeue(&list)) != NULL)
+ __skb_queue_tail(head, skb);
+ spin_unlock_irq(&head->lock);
+ }
+#else
+ fput(io_file_from_index(ctx, index));
+#endif
+}
+
+static int io_sqe_file_register(struct io_ring_ctx *ctx, struct file *file,
+ int index)
+{
+#if defined(CONFIG_UNIX)
+ struct sock *sock = ctx->ring_sock->sk;
+ struct sk_buff_head *head = &sock->sk_receive_queue;
+ struct sk_buff *skb;
+
+ /*
+ * See if we can merge this file into an existing skb SCM_RIGHTS
+ * file set. If there's no room, fall back to allocating a new skb
+ * and filling it in.
+ */
+ spin_lock_irq(&head->lock);
+ skb = skb_peek(head);
+ if (skb) {
+ struct scm_fp_list *fpl = UNIXCB(skb).fp;
+
+ if (fpl->count < SCM_MAX_FD) {
+ __skb_unlink(skb, head);
+ spin_unlock_irq(&head->lock);
+ fpl->fp[fpl->count] = get_file(file);
+ unix_inflight(fpl->user, fpl->fp[fpl->count]);
+ fpl->count++;
+ spin_lock_irq(&head->lock);
+ __skb_queue_head(head, skb);
+ } else {
+ skb = NULL;
+ }
+ }
+ spin_unlock_irq(&head->lock);
+
+ if (skb) {
+ fput(file);
+ return 0;
+ }
+
+ return __io_sqe_files_scm(ctx, 1, index);
+#else
+ return 0;
+#endif
+}
+
+static int io_sqe_files_update(struct io_ring_ctx *ctx, void __user *arg,
+ unsigned nr_args)
+{
+ struct io_uring_files_update up;
+ __s32 __user *fds;
+ int fd, i, err;
+ __u32 done;
+
+ if (!ctx->file_table)
+ return -ENXIO;
+ if (!nr_args)
+ return -EINVAL;
+ if (copy_from_user(&up, arg, sizeof(up)))
+ return -EFAULT;
+ if (check_add_overflow(up.offset, nr_args, &done))
+ return -EOVERFLOW;
+ if (done > ctx->nr_user_files)
+ return -EINVAL;
+
+ done = 0;
+ fds = (__s32 __user *) up.fds;
+ while (nr_args) {
+ struct fixed_file_table *table;
+ unsigned index;
+
+ err = 0;
+ if (copy_from_user(&fd, &fds[done], sizeof(fd))) {
+ err = -EFAULT;
+ break;
+ }
+ i = array_index_nospec(up.offset, ctx->nr_user_files);
+ table = &ctx->file_table[i >> IORING_FILE_TABLE_SHIFT];
+ index = i & IORING_FILE_TABLE_MASK;
+ if (table->files[index]) {
+ io_sqe_file_unregister(ctx, i);
+ table->files[index] = NULL;
+ }
+ if (fd != -1) {
+ struct file *file;
+
+ file = fget(fd);
+ if (!file) {
+ err = -EBADF;
+ break;
+ }
+ /*
+ * Don't allow io_uring instances to be registered. If
+ * UNIX isn't enabled, then this causes a reference
+ * cycle and this instance can never get freed. If UNIX
+ * is enabled we'll handle it just fine, but there's
+ * still no point in allowing a ring fd as it doesn't
+ * support regular read/write anyway.
+ */
+ if (file->f_op == &io_uring_fops) {
+ fput(file);
+ err = -EBADF;
+ break;
+ }
+ table->files[index] = file;
+ err = io_sqe_file_register(ctx, file, i);
+ if (err)
+ break;
+ }
+ nr_args--;
+ done++;
+ up.offset++;
+ }
+
+ return done ? done : err;
+}
+
+static void io_put_work(struct io_wq_work *work)
+{
+ struct io_kiocb *req = container_of(work, struct io_kiocb, work);
+
+ io_put_req(req);
+}
+
+static void io_get_work(struct io_wq_work *work)
+{
+ struct io_kiocb *req = container_of(work, struct io_kiocb, work);
+
+ refcount_inc(&req->refs);
+}
+
static int io_sq_offload_start(struct io_ring_ctx *ctx,
struct io_uring_params *p)
{
+ struct io_wq_data data;
+ unsigned concurrency;
int ret;
init_waitqueue_head(&ctx->sqo_wait);
@@ -3118,26 +4282,18 @@ static int io_sq_offload_start(struct io_ring_ctx *ctx,
goto err;
}
- /* Do QD, or 2 * CPUS, whatever is smallest */
- ctx->sqo_wq[0] = alloc_workqueue("io_ring-wq",
- WQ_UNBOUND | WQ_FREEZABLE,
- min(ctx->sq_entries - 1, 2 * num_online_cpus()));
- if (!ctx->sqo_wq[0]) {
- ret = -ENOMEM;
- goto err;
- }
-
- /*
- * This is for buffered writes, where we want to limit the parallelism
- * due to file locking in file systems. As "normal" buffered writes
- * should parellelize on writeout quite nicely, limit us to having 2
- * pending. This avoids massive contention on the inode when doing
- * buffered async writes.
- */
- ctx->sqo_wq[1] = alloc_workqueue("io_ring-write-wq",
- WQ_UNBOUND | WQ_FREEZABLE, 2);
- if (!ctx->sqo_wq[1]) {
- ret = -ENOMEM;
+ data.mm = ctx->sqo_mm;
+ data.user = ctx->user;
+ data.creds = ctx->creds;
+ data.get_work = io_get_work;
+ data.put_work = io_put_work;
+
+ /* Do QD, or 4 * CPUS, whatever is smallest */
+ concurrency = min(ctx->sq_entries, 4 * num_online_cpus());
+ ctx->io_wq = io_wq_create(concurrency, &data);
+ if (IS_ERR(ctx->io_wq)) {
+ ret = PTR_ERR(ctx->io_wq);
+ ctx->io_wq = NULL;
goto err;
}
@@ -3483,6 +4639,10 @@ static void io_ring_ctx_free(struct io_ring_ctx *ctx)
io_unaccount_mem(ctx->user,
ring_pages(ctx->sq_entries, ctx->cq_entries));
free_uid(ctx->user);
+ put_cred(ctx->creds);
+ kfree(ctx->completions);
+ kfree(ctx->cancel_hash);
+ kmem_cache_free(req_cachep, ctx->fallback_req);
kfree(ctx);
}
@@ -3521,8 +4681,15 @@ static void io_ring_ctx_wait_and_kill(struct io_ring_ctx *ctx)
io_kill_timeouts(ctx);
io_poll_remove_all(ctx);
+
+ if (ctx->io_wq)
+ io_wq_cancel_all(ctx->io_wq);
+
io_iopoll_reap_events(ctx);
- wait_for_completion(&ctx->ctx_done);
+ /* if we failed setting up the ctx, we might not have any rings */
+ if (ctx->rings)
+ io_cqring_overflow_flush(ctx, true);
+ wait_for_completion(&ctx->completions[0]);
io_ring_ctx_free(ctx);
}
@@ -3535,12 +4702,58 @@ static int io_uring_release(struct inode *inode, struct file *file)
return 0;
}
-static int io_uring_mmap(struct file *file, struct vm_area_struct *vma)
+static void io_uring_cancel_files(struct io_ring_ctx *ctx,
+ struct files_struct *files)
+{
+ struct io_kiocb *req;
+ DEFINE_WAIT(wait);
+
+ while (!list_empty_careful(&ctx->inflight_list)) {
+ struct io_kiocb *cancel_req = NULL;
+
+ spin_lock_irq(&ctx->inflight_lock);
+ list_for_each_entry(req, &ctx->inflight_list, inflight_entry) {
+ if (req->work.files != files)
+ continue;
+ /* req is being completed, ignore */
+ if (!refcount_inc_not_zero(&req->refs))
+ continue;
+ cancel_req = req;
+ break;
+ }
+ if (cancel_req)
+ prepare_to_wait(&ctx->inflight_wait, &wait,
+ TASK_UNINTERRUPTIBLE);
+ spin_unlock_irq(&ctx->inflight_lock);
+
+ /* We need to keep going until we don't find a matching req */
+ if (!cancel_req)
+ break;
+
+ io_wq_cancel_work(ctx->io_wq, &cancel_req->work);
+ io_put_req(cancel_req);
+ schedule();
+ }
+ finish_wait(&ctx->inflight_wait, &wait);
+}
+
+static int io_uring_flush(struct file *file, void *data)
{
- loff_t offset = (loff_t) vma->vm_pgoff << PAGE_SHIFT;
- unsigned long sz = vma->vm_end - vma->vm_start;
struct io_ring_ctx *ctx = file->private_data;
- unsigned long pfn;
+
+ io_uring_cancel_files(ctx, data);
+ if (fatal_signal_pending(current) || (current->flags & PF_EXITING)) {
+ io_cqring_overflow_flush(ctx, true);
+ io_wq_cancel_all(ctx->io_wq);
+ }
+ return 0;
+}
+
+static void *io_uring_validate_mmap_request(struct file *file,
+ loff_t pgoff, size_t sz)
+{
+ struct io_ring_ctx *ctx = file->private_data;
+ loff_t offset = pgoff << PAGE_SHIFT;
struct page *page;
void *ptr;
@@ -3553,17 +4766,59 @@ static int io_uring_mmap(struct file *file, struct vm_area_struct *vma)
ptr = ctx->sq_sqes;
break;
default:
- return -EINVAL;
+ return ERR_PTR(-EINVAL);
}
page = virt_to_head_page(ptr);
if (sz > page_size(page))
- return -EINVAL;
+ return ERR_PTR(-EINVAL);
+
+ return ptr;
+}
+
+#ifdef CONFIG_MMU
+
+static int io_uring_mmap(struct file *file, struct vm_area_struct *vma)
+{
+ size_t sz = vma->vm_end - vma->vm_start;
+ unsigned long pfn;
+ void *ptr;
+
+ ptr = io_uring_validate_mmap_request(file, vma->vm_pgoff, sz);
+ if (IS_ERR(ptr))
+ return PTR_ERR(ptr);
pfn = virt_to_phys(ptr) >> PAGE_SHIFT;
return remap_pfn_range(vma, vma->vm_start, pfn, sz, vma->vm_page_prot);
}
+#else /* !CONFIG_MMU */
+
+static int io_uring_mmap(struct file *file, struct vm_area_struct *vma)
+{
+ return vma->vm_flags & (VM_SHARED | VM_MAYSHARE) ? 0 : -EINVAL;
+}
+
+static unsigned int io_uring_nommu_mmap_capabilities(struct file *file)
+{
+ return NOMMU_MAP_DIRECT | NOMMU_MAP_READ | NOMMU_MAP_WRITE;
+}
+
+static unsigned long io_uring_nommu_get_unmapped_area(struct file *file,
+ unsigned long addr, unsigned long len,
+ unsigned long pgoff, unsigned long flags)
+{
+ void *ptr;
+
+ ptr = io_uring_validate_mmap_request(file, pgoff, len);
+ if (IS_ERR(ptr))
+ return PTR_ERR(ptr);
+
+ return (unsigned long) ptr;
+}
+
+#endif /* !CONFIG_MMU */
+
SYSCALL_DEFINE6(io_uring_enter, unsigned int, fd, u32, to_submit,
u32, min_complete, u32, flags, const sigset_t __user *, sig,
size_t, sigsz)
@@ -3596,25 +4851,20 @@ SYSCALL_DEFINE6(io_uring_enter, unsigned int, fd, u32, to_submit,
*/
ret = 0;
if (ctx->flags & IORING_SETUP_SQPOLL) {
+ if (!list_empty_careful(&ctx->cq_overflow_list))
+ io_cqring_overflow_flush(ctx, false);
if (flags & IORING_ENTER_SQ_WAKEUP)
wake_up(&ctx->sqo_wait);
submitted = to_submit;
} else if (to_submit) {
- bool block_for_last = false;
+ struct mm_struct *cur_mm;
to_submit = min(to_submit, ctx->sq_entries);
-
- /*
- * Allow last submission to block in a series, IFF the caller
- * asked to wait for events and we don't currently have
- * enough. This potentially avoids an async punt.
- */
- if (to_submit == min_complete &&
- io_cqring_events(ctx->rings) < min_complete)
- block_for_last = true;
-
mutex_lock(&ctx->uring_lock);
- submitted = io_ring_submit(ctx, to_submit, block_for_last);
+ /* already have mm, so io_submit_sqes() won't try to grab it */
+ cur_mm = ctx->sqo_mm;
+ submitted = io_submit_sqes(ctx, to_submit, f.file, fd,
+ &cur_mm, false);
mutex_unlock(&ctx->uring_lock);
}
if (flags & IORING_ENTER_GETEVENTS) {
@@ -3637,7 +4887,12 @@ out_fput:
static const struct file_operations io_uring_fops = {
.release = io_uring_release,
+ .flush = io_uring_flush,
.mmap = io_uring_mmap,
+#ifndef CONFIG_MMU
+ .get_unmapped_area = io_uring_nommu_get_unmapped_area,
+ .mmap_capabilities = io_uring_nommu_mmap_capabilities,
+#endif
.poll = io_uring_poll,
.fasync = io_uring_fasync,
};
@@ -3668,12 +4923,18 @@ static int io_allocate_scq_urings(struct io_ring_ctx *ctx,
ctx->cq_entries = rings->cq_ring_entries;
size = array_size(sizeof(struct io_uring_sqe), p->sq_entries);
- if (size == SIZE_MAX)
+ if (size == SIZE_MAX) {
+ io_mem_free(ctx->rings);
+ ctx->rings = NULL;
return -EOVERFLOW;
+ }
ctx->sq_sqes = io_mem_alloc(size);
- if (!ctx->sq_sqes)
+ if (!ctx->sq_sqes) {
+ io_mem_free(ctx->rings);
+ ctx->rings = NULL;
return -ENOMEM;
+ }
return 0;
}
@@ -3736,10 +4997,23 @@ static int io_uring_create(unsigned entries, struct io_uring_params *p)
* Use twice as many entries for the CQ ring. It's possible for the
* application to drive a higher depth than the size of the SQ ring,
* since the sqes are only used at submission time. This allows for
- * some flexibility in overcommitting a bit.
+ * some flexibility in overcommitting a bit. If the application has
+ * set IORING_SETUP_CQSIZE, it will have passed in the desired number
+ * of CQ ring entries manually.
*/
p->sq_entries = roundup_pow_of_two(entries);
- p->cq_entries = 2 * p->sq_entries;
+ if (p->flags & IORING_SETUP_CQSIZE) {
+ /*
+ * If IORING_SETUP_CQSIZE is set, we do the same roundup
+ * to a power-of-two, if it isn't already. We do NOT impose
+ * any cq vs sq ring sizing.
+ */
+ if (p->cq_entries < p->sq_entries || p->cq_entries > IORING_MAX_CQ_ENTRIES)
+ return -EINVAL;
+ p->cq_entries = roundup_pow_of_two(p->cq_entries);
+ } else {
+ p->cq_entries = 2 * p->sq_entries;
+ }
user = get_uid(current_user());
account_mem = !capable(CAP_IPC_LOCK);
@@ -3764,6 +5038,7 @@ static int io_uring_create(unsigned entries, struct io_uring_params *p)
ctx->compat = in_compat_syscall();
ctx->account_mem = account_mem;
ctx->user = user;
+ ctx->creds = get_current_cred();
ret = io_allocate_scq_urings(ctx, p);
if (ret)
@@ -3773,10 +5048,6 @@ static int io_uring_create(unsigned entries, struct io_uring_params *p)
if (ret)
goto err;
- ret = io_uring_get_fd(ctx);
- if (ret < 0)
- goto err;
-
memset(&p->sq_off, 0, sizeof(p->sq_off));
p->sq_off.head = offsetof(struct io_rings, sq.head);
p->sq_off.tail = offsetof(struct io_rings, sq.tail);
@@ -3794,7 +5065,17 @@ static int io_uring_create(unsigned entries, struct io_uring_params *p)
p->cq_off.overflow = offsetof(struct io_rings, cq_overflow);
p->cq_off.cqes = offsetof(struct io_rings, cqes);
- p->features = IORING_FEAT_SINGLE_MMAP;
+ /*
+ * Install ring fd as the very last thing, so we don't risk someone
+ * having closed it before we finish setup
+ */
+ ret = io_uring_get_fd(ctx);
+ if (ret < 0)
+ goto err;
+
+ p->features = IORING_FEAT_SINGLE_MMAP | IORING_FEAT_NODROP |
+ IORING_FEAT_SUBMIT_STABLE;
+ trace_io_uring_create(ret, ctx, p->sq_entries, p->cq_entries, p->flags);
return ret;
err:
io_ring_ctx_wait_and_kill(ctx);
@@ -3820,7 +5101,7 @@ static long io_uring_setup(u32 entries, struct io_uring_params __user *params)
}
if (p.flags & ~(IORING_SETUP_IOPOLL | IORING_SETUP_SQPOLL |
- IORING_SETUP_SQ_AFF))
+ IORING_SETUP_SQ_AFF | IORING_SETUP_CQSIZE))
return -EINVAL;
ret = io_uring_create(entries, &p);
@@ -3864,7 +5145,7 @@ static int __io_uring_register(struct io_ring_ctx *ctx, unsigned opcode,
* no new references will come in after we've killed the percpu ref.
*/
mutex_unlock(&ctx->uring_lock);
- wait_for_completion(&ctx->ctx_done);
+ wait_for_completion(&ctx->completions[0]);
mutex_lock(&ctx->uring_lock);
switch (opcode) {
@@ -3886,6 +5167,9 @@ static int __io_uring_register(struct io_ring_ctx *ctx, unsigned opcode,
break;
ret = io_sqe_files_unregister(ctx);
break;
+ case IORING_REGISTER_FILES_UPDATE:
+ ret = io_sqe_files_update(ctx, arg, nr_args);
+ break;
case IORING_REGISTER_EVENTFD:
ret = -EINVAL;
if (nr_args != 1)
@@ -3904,7 +5188,7 @@ static int __io_uring_register(struct io_ring_ctx *ctx, unsigned opcode,
}
/* bring the ctx back to life */
- reinit_completion(&ctx->ctx_done);
+ reinit_completion(&ctx->completions[0]);
percpu_ref_reinit(&ctx->refs);
return ret;
}
@@ -3929,6 +5213,8 @@ SYSCALL_DEFINE4(io_uring_register, unsigned int, fd, unsigned int, opcode,
mutex_lock(&ctx->uring_lock);
ret = __io_uring_register(ctx, opcode, arg, nr_args);
mutex_unlock(&ctx->uring_lock);
+ trace_io_uring_register(ctx, opcode, ctx->nr_user_files, ctx->nr_user_bufs,
+ ctx->cq_ev_fd != NULL, ret);
out_fput:
fdput(f);
return ret;
diff --git a/fs/ioctl.c b/fs/ioctl.c
index 55c7cfb0e599..2f5e4e5b97e1 100644
--- a/fs/ioctl.c
+++ b/fs/ioctl.c
@@ -8,6 +8,7 @@
#include <linux/syscalls.h>
#include <linux/mm.h>
#include <linux/capability.h>
+#include <linux/compat.h>
#include <linux/file.h>
#include <linux/fs.h>
#include <linux/security.h>
@@ -174,10 +175,9 @@ static int fiemap_check_ranges(struct super_block *sb,
return 0;
}
-static int ioctl_fiemap(struct file *filp, unsigned long arg)
+static int ioctl_fiemap(struct file *filp, struct fiemap __user *ufiemap)
{
struct fiemap fiemap;
- struct fiemap __user *ufiemap = (struct fiemap __user *) arg;
struct fiemap_extent_info fieinfo = { 0, };
struct inode *inode = file_inode(filp);
struct super_block *sb = inode->i_sb;
@@ -244,7 +244,8 @@ fdput:
return ret;
}
-static long ioctl_file_clone_range(struct file *file, void __user *argp)
+static long ioctl_file_clone_range(struct file *file,
+ struct file_clone_range __user *argp)
{
struct file_clone_range args;
@@ -491,6 +492,35 @@ int ioctl_preallocate(struct file *filp, int mode, void __user *argp)
sr.l_len);
}
+/* on ia32 l_start is on a 32-bit boundary */
+#if defined CONFIG_COMPAT && defined(CONFIG_X86_64)
+/* just account for different alignment */
+int compat_ioctl_preallocate(struct file *file, int mode,
+ struct space_resv_32 __user *argp)
+{
+ struct inode *inode = file_inode(file);
+ struct space_resv_32 sr;
+
+ if (copy_from_user(&sr, argp, sizeof(sr)))
+ return -EFAULT;
+
+ switch (sr.l_whence) {
+ case SEEK_SET:
+ break;
+ case SEEK_CUR:
+ sr.l_start += file->f_pos;
+ break;
+ case SEEK_END:
+ sr.l_start += i_size_read(inode);
+ break;
+ default:
+ return -EINVAL;
+ }
+
+ return vfs_fallocate(file, mode | FALLOC_FL_KEEP_SIZE, sr.l_start, sr.l_len);
+}
+#endif
+
static int file_ioctl(struct file *filp, unsigned int cmd,
unsigned long arg)
{
@@ -590,9 +620,9 @@ static int ioctl_fsthaw(struct file *filp)
return thaw_super(sb);
}
-static int ioctl_file_dedupe_range(struct file *file, void __user *arg)
+static int ioctl_file_dedupe_range(struct file *file,
+ struct file_dedupe_range __user *argp)
{
- struct file_dedupe_range __user *argp = arg;
struct file_dedupe_range *same = NULL;
int ret;
unsigned long size;
@@ -641,7 +671,7 @@ int do_vfs_ioctl(struct file *filp, unsigned int fd, unsigned int cmd,
unsigned long arg)
{
int error = 0;
- int __user *argp = (int __user *)arg;
+ void __user *argp = (void __user *)arg;
struct inode *inode = file_inode(filp);
switch (cmd) {
@@ -680,13 +710,13 @@ int do_vfs_ioctl(struct file *filp, unsigned int fd, unsigned int cmd,
break;
case FS_IOC_FIEMAP:
- return ioctl_fiemap(filp, arg);
+ return ioctl_fiemap(filp, argp);
case FIGETBSZ:
/* anon_bdev filesystems may not have a block size */
if (!inode->i_sb->s_blocksize)
return -EINVAL;
- return put_user(inode->i_sb->s_blocksize, argp);
+ return put_user(inode->i_sb->s_blocksize, (int __user *)argp);
case FICLONE:
return ioctl_file_clone(filp, arg, 0, 0, 0);
@@ -725,3 +755,37 @@ SYSCALL_DEFINE3(ioctl, unsigned int, fd, unsigned int, cmd, unsigned long, arg)
{
return ksys_ioctl(fd, cmd, arg);
}
+
+#ifdef CONFIG_COMPAT
+/**
+ * compat_ptr_ioctl - generic implementation of .compat_ioctl file operation
+ *
+ * This is not normally called as a function, but instead set in struct
+ * file_operations as
+ *
+ * .compat_ioctl = compat_ptr_ioctl,
+ *
+ * On most architectures, the compat_ptr_ioctl() just passes all arguments
+ * to the corresponding ->ioctl handler. The exception is arch/s390, where
+ * compat_ptr() clears the top bit of a 32-bit pointer value, so user space
+ * pointers to the second 2GB alias the first 2GB, as is the case for
+ * native 32-bit s390 user space.
+ *
+ * The compat_ptr_ioctl() function must therefore be used only with ioctl
+ * functions that either ignore the argument or pass a pointer to a
+ * compatible data type.
+ *
+ * If any ioctl command handled by fops->unlocked_ioctl passes a plain
+ * integer instead of a pointer, or any of the passed data types
+ * is incompatible between 32-bit and 64-bit architectures, a proper
+ * handler is required instead of compat_ptr_ioctl.
+ */
+long compat_ptr_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
+{
+ if (!file->f_op->unlocked_ioctl)
+ return -ENOIOCTLCMD;
+
+ return file->f_op->unlocked_ioctl(file, cmd, (unsigned long)compat_ptr(arg));
+}
+EXPORT_SYMBOL(compat_ptr_ioctl);
+#endif
diff --git a/fs/iomap/apply.c b/fs/iomap/apply.c
index 484dd8eda861..76925b40b5fd 100644
--- a/fs/iomap/apply.c
+++ b/fs/iomap/apply.c
@@ -7,6 +7,7 @@
#include <linux/compiler.h>
#include <linux/fs.h>
#include <linux/iomap.h>
+#include "trace.h"
/*
* Execute a iomap write on a segment of the mapping that spans a
@@ -28,6 +29,8 @@ iomap_apply(struct inode *inode, loff_t pos, loff_t length, unsigned flags,
loff_t written = 0, ret;
u64 end;
+ trace_iomap_apply(inode, pos, length, flags, ops, actor, _RET_IP_);
+
/*
* Need to map a range from start position for length bytes. This can
* span multiple pages - it is only guaranteed to return a range of a
@@ -48,6 +51,10 @@ iomap_apply(struct inode *inode, loff_t pos, loff_t length, unsigned flags,
if (WARN_ON(iomap.length == 0))
return -EIO;
+ trace_iomap_apply_dstmap(inode, &iomap);
+ if (srcmap.type != IOMAP_HOLE)
+ trace_iomap_apply_srcmap(inode, &srcmap);
+
/*
* Cut down the length to the one actually provided by the filesystem,
* as it might not be able to give us the whole size that we requested.
diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c
index c62e807956b6..d33c7bc5ee92 100644
--- a/fs/iomap/buffered-io.c
+++ b/fs/iomap/buffered-io.c
@@ -1067,20 +1067,19 @@ vm_fault_t iomap_page_mkwrite(struct vm_fault *vmf, const struct iomap_ops *ops)
lock_page(page);
size = i_size_read(inode);
- if ((page->mapping != inode->i_mapping) ||
- (page_offset(page) > size)) {
+ offset = page_offset(page);
+ if (page->mapping != inode->i_mapping || offset > size) {
/* We overload EFAULT to mean page got truncated */
ret = -EFAULT;
goto out_unlock;
}
/* page is wholly or partially inside EOF */
- if (((page->index + 1) << PAGE_SHIFT) > size)
+ if (offset > size - PAGE_SIZE)
length = offset_in_page(size);
else
length = PAGE_SIZE;
- offset = page_offset(page);
while (length > 0) {
ret = iomap_apply(inode, offset, length,
IOMAP_WRITE | IOMAP_FAULT, ops, page,
diff --git a/fs/iomap/direct-io.c b/fs/iomap/direct-io.c
index 49bf9780e3ed..23837926c0c5 100644
--- a/fs/iomap/direct-io.c
+++ b/fs/iomap/direct-io.c
@@ -201,12 +201,12 @@ iomap_dio_bio_actor(struct inode *inode, loff_t pos, loff_t length,
unsigned int blkbits = blksize_bits(bdev_logical_block_size(iomap->bdev));
unsigned int fs_block_size = i_blocksize(inode), pad;
unsigned int align = iov_iter_alignment(dio->submit.iter);
- struct iov_iter iter;
struct bio *bio;
bool need_zeroout = false;
bool use_fua = false;
int nr_pages, ret = 0;
size_t copied = 0;
+ size_t orig_count;
if ((pos | length | align) & ((1 << blkbits) - 1))
return -EINVAL;
@@ -236,15 +236,18 @@ iomap_dio_bio_actor(struct inode *inode, loff_t pos, loff_t length,
}
/*
- * Operate on a partial iter trimmed to the extent we were called for.
- * We'll update the iter in the dio once we're done with this extent.
+ * Save the original count and trim the iter to just the extent we
+ * are operating on right now. The iter will be re-expanded once
+ * we are done.
*/
- iter = *dio->submit.iter;
- iov_iter_truncate(&iter, length);
+ orig_count = iov_iter_count(dio->submit.iter);
+ iov_iter_truncate(dio->submit.iter, length);
- nr_pages = iov_iter_npages(&iter, BIO_MAX_PAGES);
- if (nr_pages <= 0)
- return nr_pages;
+ nr_pages = iov_iter_npages(dio->submit.iter, BIO_MAX_PAGES);
+ if (nr_pages <= 0) {
+ ret = nr_pages;
+ goto out;
+ }
if (need_zeroout) {
/* zero out from the start of the block to the write offset */
@@ -257,7 +260,8 @@ iomap_dio_bio_actor(struct inode *inode, loff_t pos, loff_t length,
size_t n;
if (dio->error) {
iov_iter_revert(dio->submit.iter, copied);
- return 0;
+ copied = ret = 0;
+ goto out;
}
bio = bio_alloc(GFP_KERNEL, nr_pages);
@@ -268,7 +272,7 @@ iomap_dio_bio_actor(struct inode *inode, loff_t pos, loff_t length,
bio->bi_private = dio;
bio->bi_end_io = iomap_dio_bio_end_io;
- ret = bio_iov_iter_get_pages(bio, &iter);
+ ret = bio_iov_iter_get_pages(bio, dio->submit.iter);
if (unlikely(ret)) {
/*
* We have to stop part way through an IO. We must fall
@@ -294,13 +298,11 @@ iomap_dio_bio_actor(struct inode *inode, loff_t pos, loff_t length,
bio_set_pages_dirty(bio);
}
- iov_iter_advance(dio->submit.iter, n);
-
dio->size += n;
pos += n;
copied += n;
- nr_pages = iov_iter_npages(&iter, BIO_MAX_PAGES);
+ nr_pages = iov_iter_npages(dio->submit.iter, BIO_MAX_PAGES);
iomap_dio_submit_bio(dio, iomap, bio);
} while (nr_pages);
@@ -318,7 +320,12 @@ zero_tail:
if (pad)
iomap_dio_zero(dio, iomap, pos, fs_block_size - pad);
}
- return copied ? copied : ret;
+out:
+ /* Undo iter limitation to current extent */
+ iov_iter_reexpand(dio->submit.iter, orig_count - copied);
+ if (copied)
+ return copied;
+ return ret;
}
static loff_t
@@ -398,7 +405,7 @@ iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
struct address_space *mapping = iocb->ki_filp->f_mapping;
struct inode *inode = file_inode(iocb->ki_filp);
size_t count = iov_iter_count(iter);
- loff_t pos = iocb->ki_pos, start = pos;
+ loff_t pos = iocb->ki_pos;
loff_t end = iocb->ki_pos + count - 1, ret = 0;
unsigned int flags = IOMAP_DIRECT;
struct blk_plug plug;
@@ -433,7 +440,7 @@ iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
if (pos >= dio->i_size)
goto out_free_dio;
- if (iter_is_iovec(iter) && iov_iter_rw(iter) == READ)
+ if (iter_is_iovec(iter))
dio->flags |= IOMAP_DIO_DIRTY;
} else {
flags |= IOMAP_WRITE;
@@ -454,14 +461,14 @@ iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
}
if (iocb->ki_flags & IOCB_NOWAIT) {
- if (filemap_range_has_page(mapping, start, end)) {
+ if (filemap_range_has_page(mapping, pos, end)) {
ret = -EAGAIN;
goto out_free_dio;
}
flags |= IOMAP_NOWAIT;
}
- ret = filemap_write_and_wait_range(mapping, start, end);
+ ret = filemap_write_and_wait_range(mapping, pos, end);
if (ret)
goto out_free_dio;
@@ -472,7 +479,7 @@ iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
* pretty crazy thing to do, so we don't support it 100%.
*/
ret = invalidate_inode_pages2_range(mapping,
- start >> PAGE_SHIFT, end >> PAGE_SHIFT);
+ pos >> PAGE_SHIFT, end >> PAGE_SHIFT);
if (ret)
dio_warn_stale_pagecache(iocb->ki_filp);
ret = 0;
@@ -500,8 +507,15 @@ iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
}
pos += ret;
- if (iov_iter_rw(iter) == READ && pos >= dio->i_size)
+ if (iov_iter_rw(iter) == READ && pos >= dio->i_size) {
+ /*
+ * We only report that we've read data up to i_size.
+ * Revert iter to a state corresponding to that as
+ * some callers (such as splice code) rely on it.
+ */
+ iov_iter_revert(iter, pos - dio->i_size);
break;
+ }
} while ((count = iov_iter_count(iter)) > 0);
blk_finish_plug(&plug);
diff --git a/fs/iomap/fiemap.c b/fs/iomap/fiemap.c
index 690ef2d7c6c8..bccf305ea9ce 100644
--- a/fs/iomap/fiemap.c
+++ b/fs/iomap/fiemap.c
@@ -133,12 +133,16 @@ iomap_bmap(struct address_space *mapping, sector_t bno,
struct inode *inode = mapping->host;
loff_t pos = bno << inode->i_blkbits;
unsigned blocksize = i_blocksize(inode);
+ int ret;
if (filemap_write_and_wait(mapping))
return 0;
bno = 0;
- iomap_apply(inode, pos, blocksize, 0, ops, &bno, iomap_bmap_actor);
+ ret = iomap_apply(inode, pos, blocksize, 0, ops, &bno,
+ iomap_bmap_actor);
+ if (ret)
+ return 0;
return bno;
}
EXPORT_SYMBOL_GPL(iomap_bmap);
diff --git a/fs/iomap/trace.h b/fs/iomap/trace.h
index 4ca1aa2f3f6e..6dc227b8c47e 100644
--- a/fs/iomap/trace.h
+++ b/fs/iomap/trace.h
@@ -80,6 +80,109 @@ DEFINE_PAGE_EVENT(iomap_writepage);
DEFINE_PAGE_EVENT(iomap_releasepage);
DEFINE_PAGE_EVENT(iomap_invalidatepage);
+#define IOMAP_TYPE_STRINGS \
+ { IOMAP_HOLE, "HOLE" }, \
+ { IOMAP_DELALLOC, "DELALLOC" }, \
+ { IOMAP_MAPPED, "MAPPED" }, \
+ { IOMAP_UNWRITTEN, "UNWRITTEN" }, \
+ { IOMAP_INLINE, "INLINE" }
+
+#define IOMAP_FLAGS_STRINGS \
+ { IOMAP_WRITE, "WRITE" }, \
+ { IOMAP_ZERO, "ZERO" }, \
+ { IOMAP_REPORT, "REPORT" }, \
+ { IOMAP_FAULT, "FAULT" }, \
+ { IOMAP_DIRECT, "DIRECT" }, \
+ { IOMAP_NOWAIT, "NOWAIT" }
+
+#define IOMAP_F_FLAGS_STRINGS \
+ { IOMAP_F_NEW, "NEW" }, \
+ { IOMAP_F_DIRTY, "DIRTY" }, \
+ { IOMAP_F_SHARED, "SHARED" }, \
+ { IOMAP_F_MERGED, "MERGED" }, \
+ { IOMAP_F_BUFFER_HEAD, "BH" }, \
+ { IOMAP_F_SIZE_CHANGED, "SIZE_CHANGED" }
+
+DECLARE_EVENT_CLASS(iomap_class,
+ TP_PROTO(struct inode *inode, struct iomap *iomap),
+ TP_ARGS(inode, iomap),
+ TP_STRUCT__entry(
+ __field(dev_t, dev)
+ __field(u64, ino)
+ __field(u64, addr)
+ __field(loff_t, offset)
+ __field(u64, length)
+ __field(u16, type)
+ __field(u16, flags)
+ __field(dev_t, bdev)
+ ),
+ TP_fast_assign(
+ __entry->dev = inode->i_sb->s_dev;
+ __entry->ino = inode->i_ino;
+ __entry->addr = iomap->addr;
+ __entry->offset = iomap->offset;
+ __entry->length = iomap->length;
+ __entry->type = iomap->type;
+ __entry->flags = iomap->flags;
+ __entry->bdev = iomap->bdev ? iomap->bdev->bd_dev : 0;
+ ),
+ TP_printk("dev %d:%d ino 0x%llx bdev %d:%d addr %lld offset %lld "
+ "length %llu type %s flags %s",
+ MAJOR(__entry->dev), MINOR(__entry->dev),
+ __entry->ino,
+ MAJOR(__entry->bdev), MINOR(__entry->bdev),
+ __entry->addr,
+ __entry->offset,
+ __entry->length,
+ __print_symbolic(__entry->type, IOMAP_TYPE_STRINGS),
+ __print_flags(__entry->flags, "|", IOMAP_F_FLAGS_STRINGS))
+)
+
+#define DEFINE_IOMAP_EVENT(name) \
+DEFINE_EVENT(iomap_class, name, \
+ TP_PROTO(struct inode *inode, struct iomap *iomap), \
+ TP_ARGS(inode, iomap))
+DEFINE_IOMAP_EVENT(iomap_apply_dstmap);
+DEFINE_IOMAP_EVENT(iomap_apply_srcmap);
+
+TRACE_EVENT(iomap_apply,
+ TP_PROTO(struct inode *inode, loff_t pos, loff_t length,
+ unsigned int flags, const void *ops, void *actor,
+ unsigned long caller),
+ TP_ARGS(inode, pos, length, flags, ops, actor, caller),
+ TP_STRUCT__entry(
+ __field(dev_t, dev)
+ __field(u64, ino)
+ __field(loff_t, pos)
+ __field(loff_t, length)
+ __field(unsigned int, flags)
+ __field(const void *, ops)
+ __field(void *, actor)
+ __field(unsigned long, caller)
+ ),
+ TP_fast_assign(
+ __entry->dev = inode->i_sb->s_dev;
+ __entry->ino = inode->i_ino;
+ __entry->pos = pos;
+ __entry->length = length;
+ __entry->flags = flags;
+ __entry->ops = ops;
+ __entry->actor = actor;
+ __entry->caller = caller;
+ ),
+ TP_printk("dev %d:%d ino 0x%llx pos %lld length %lld flags %s (0x%x) "
+ "ops %ps caller %pS actor %ps",
+ MAJOR(__entry->dev), MINOR(__entry->dev),
+ __entry->ino,
+ __entry->pos,
+ __entry->length,
+ __print_flags(__entry->flags, "|", IOMAP_FLAGS_STRINGS),
+ __entry->flags,
+ __entry->ops,
+ (void *)__entry->caller,
+ __entry->actor)
+);
+
#endif /* _IOMAP_TRACE_H */
#undef TRACE_INCLUDE_PATH
diff --git a/fs/jbd2/checkpoint.c b/fs/jbd2/checkpoint.c
index a1909066bde6..8fff6677a5da 100644
--- a/fs/jbd2/checkpoint.c
+++ b/fs/jbd2/checkpoint.c
@@ -110,7 +110,7 @@ void __jbd2_log_wait_for_space(journal_t *journal)
int nblocks, space_left;
/* assert_spin_locked(&journal->j_state_lock); */
- nblocks = jbd2_space_needed(journal);
+ nblocks = journal->j_max_transaction_buffers;
while (jbd2_log_space_left(journal) < nblocks) {
write_unlock(&journal->j_state_lock);
mutex_lock_io(&journal->j_checkpoint_mutex);
diff --git a/fs/jbd2/commit.c b/fs/jbd2/commit.c
index 132fb92098c7..7f0b362b3842 100644
--- a/fs/jbd2/commit.c
+++ b/fs/jbd2/commit.c
@@ -482,10 +482,10 @@ void jbd2_journal_commit_transaction(journal_t *journal)
if (jh->b_committed_data) {
struct buffer_head *bh = jh2bh(jh);
- jbd_lock_bh_state(bh);
+ spin_lock(&jh->b_state_lock);
jbd2_free(jh->b_committed_data, bh->b_size);
jh->b_committed_data = NULL;
- jbd_unlock_bh_state(bh);
+ spin_unlock(&jh->b_state_lock);
}
jbd2_journal_refile_buffer(journal, jh);
}
@@ -560,8 +560,7 @@ void jbd2_journal_commit_transaction(journal_t *journal)
stats.run.rs_logging = jiffies;
stats.run.rs_flushing = jbd2_time_diff(stats.run.rs_flushing,
stats.run.rs_logging);
- stats.run.rs_blocks =
- atomic_read(&commit_transaction->t_outstanding_credits);
+ stats.run.rs_blocks = commit_transaction->t_nr_buffers;
stats.run.rs_blocks_logged = 0;
J_ASSERT(commit_transaction->t_nr_buffers <=
@@ -642,8 +641,7 @@ void jbd2_journal_commit_transaction(journal_t *journal)
/*
* start_this_handle() uses t_outstanding_credits to determine
- * the free space in the log, but this counter is changed
- * by jbd2_journal_next_log_block() also.
+ * the free space in the log.
*/
atomic_dec(&commit_transaction->t_outstanding_credits);
@@ -727,7 +725,6 @@ start_journal_io:
submit_bh(REQ_OP_WRITE, REQ_SYNC, bh);
}
cond_resched();
- stats.run.rs_blocks_logged += bufs;
/* Force a new descriptor to be generated next
time round the loop. */
@@ -814,6 +811,7 @@ start_journal_io:
if (unlikely(!buffer_uptodate(bh)))
err = -EIO;
jbd2_unfile_log_bh(bh);
+ stats.run.rs_blocks_logged++;
/*
* The list contains temporary buffer heads created by
@@ -859,6 +857,7 @@ start_journal_io:
BUFFER_TRACE(bh, "ph5: control buffer writeout done: unfile");
clear_buffer_jwrite(bh);
jbd2_unfile_log_bh(bh);
+ stats.run.rs_blocks_logged++;
__brelse(bh); /* One for getblk */
/* AKPM: bforget here */
}
@@ -880,6 +879,7 @@ start_journal_io:
}
if (cbh)
err = journal_wait_on_commit_record(journal, cbh);
+ stats.run.rs_blocks_logged++;
if (jbd2_has_feature_async_commit(journal) &&
journal->j_flags & JBD2_BARRIER) {
blkdev_issue_flush(journal->j_dev, GFP_NOFS, NULL);
@@ -888,6 +888,9 @@ start_journal_io:
if (err)
jbd2_journal_abort(journal, err);
+ WARN_ON_ONCE(
+ atomic_read(&commit_transaction->t_outstanding_credits) < 0);
+
/*
* Now disk caches for filesystem device are flushed so we are safe to
* erase checkpointed transactions from the log by updating journal
@@ -918,6 +921,7 @@ restart_loop:
transaction_t *cp_transaction;
struct buffer_head *bh;
int try_to_free = 0;
+ bool drop_ref;
jh = commit_transaction->t_forget;
spin_unlock(&journal->j_list_lock);
@@ -927,7 +931,7 @@ restart_loop:
* done with it.
*/
get_bh(bh);
- jbd_lock_bh_state(bh);
+ spin_lock(&jh->b_state_lock);
J_ASSERT_JH(jh, jh->b_transaction == commit_transaction);
/*
@@ -1022,8 +1026,10 @@ restart_loop:
try_to_free = 1;
}
JBUFFER_TRACE(jh, "refile or unfile buffer");
- __jbd2_journal_refile_buffer(jh);
- jbd_unlock_bh_state(bh);
+ drop_ref = __jbd2_journal_refile_buffer(jh);
+ spin_unlock(&jh->b_state_lock);
+ if (drop_ref)
+ jbd2_journal_put_journal_head(jh);
if (try_to_free)
release_buffer_page(bh); /* Drops bh reference */
else
diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c
index 1c58859aa592..5e408ee24a1a 100644
--- a/fs/jbd2/journal.c
+++ b/fs/jbd2/journal.c
@@ -363,7 +363,7 @@ int jbd2_journal_write_metadata_buffer(transaction_t *transaction,
/* keep subsequent assertions sane */
atomic_set(&new_bh->b_count, 1);
- jbd_lock_bh_state(bh_in);
+ spin_lock(&jh_in->b_state_lock);
repeat:
/*
* If a new transaction has already done a buffer copy-out, then
@@ -405,13 +405,13 @@ repeat:
if (need_copy_out && !done_copy_out) {
char *tmp;
- jbd_unlock_bh_state(bh_in);
+ spin_unlock(&jh_in->b_state_lock);
tmp = jbd2_alloc(bh_in->b_size, GFP_NOFS);
if (!tmp) {
brelse(new_bh);
return -ENOMEM;
}
- jbd_lock_bh_state(bh_in);
+ spin_lock(&jh_in->b_state_lock);
if (jh_in->b_frozen_data) {
jbd2_free(tmp, bh_in->b_size);
goto repeat;
@@ -464,7 +464,7 @@ repeat:
__jbd2_journal_file_buffer(jh_in, transaction, BJ_Shadow);
spin_unlock(&journal->j_list_lock);
set_buffer_shadow(bh_in);
- jbd_unlock_bh_state(bh_in);
+ spin_unlock(&jh_in->b_state_lock);
return do_escape | (done_copy_out << 1);
}
@@ -840,6 +840,7 @@ jbd2_journal_get_descriptor_buffer(transaction_t *transaction, int type)
bh = __getblk(journal->j_dev, blocknr, journal->j_blocksize);
if (!bh)
return NULL;
+ atomic_dec(&transaction->t_outstanding_credits);
lock_buffer(bh);
memset(bh->b_data, 0, journal->j_blocksize);
header = (journal_header_t *)bh->b_data;
@@ -1098,6 +1099,16 @@ static void jbd2_stats_proc_exit(journal_t *journal)
remove_proc_entry(journal->j_devname, proc_jbd2_stats);
}
+/* Minimum size of descriptor tag */
+static int jbd2_min_tag_size(void)
+{
+ /*
+ * Tag with 32-bit block numbers does not use last four bytes of the
+ * structure
+ */
+ return sizeof(journal_block_tag_t) - 4;
+}
+
/*
* Management for journal control blocks: functions to create and
* destroy journal_t structures, and to initialise and read existing
@@ -1156,7 +1167,8 @@ static journal_t *journal_init_common(struct block_device *bdev,
journal->j_fs_dev = fs_dev;
journal->j_blk_offset = start;
journal->j_maxlen = len;
- n = journal->j_blocksize / sizeof(journal_block_tag_t);
+ /* We need enough buffers to write out full descriptor block. */
+ n = journal->j_blocksize / jbd2_min_tag_size();
journal->j_wbufsize = n;
journal->j_wbuf = kmalloc_array(n, sizeof(struct buffer_head *),
GFP_KERNEL);
@@ -1488,6 +1500,21 @@ void jbd2_journal_update_sb_errno(journal_t *journal)
}
EXPORT_SYMBOL(jbd2_journal_update_sb_errno);
+static int journal_revoke_records_per_block(journal_t *journal)
+{
+ int record_size;
+ int space = journal->j_blocksize - sizeof(jbd2_journal_revoke_header_t);
+
+ if (jbd2_has_feature_64bit(journal))
+ record_size = 8;
+ else
+ record_size = 4;
+
+ if (jbd2_journal_has_csum_v2or3(journal))
+ space -= sizeof(struct jbd2_journal_block_tail);
+ return space / record_size;
+}
+
/*
* Read the superblock for a given journal, performing initial
* validation of the format.
@@ -1596,6 +1623,8 @@ static int journal_get_superblock(journal_t *journal)
sizeof(sb->s_uuid));
}
+ journal->j_revoke_records_per_block =
+ journal_revoke_records_per_block(journal);
set_buffer_verified(bh);
return 0;
@@ -1916,6 +1945,8 @@ int jbd2_journal_set_features (journal_t *journal, unsigned long compat,
sb->s_feature_ro_compat |= cpu_to_be32(ro);
sb->s_feature_incompat |= cpu_to_be32(incompat);
unlock_buffer(journal->j_sb_buffer);
+ journal->j_revoke_records_per_block =
+ journal_revoke_records_per_block(journal);
return 1;
#undef COMPAT_FEATURE_ON
@@ -1946,6 +1977,8 @@ void jbd2_journal_clear_features(journal_t *journal, unsigned long compat,
sb->s_feature_compat &= ~cpu_to_be32(compat);
sb->s_feature_ro_compat &= ~cpu_to_be32(ro);
sb->s_feature_incompat &= ~cpu_to_be32(incompat);
+ journal->j_revoke_records_per_block =
+ journal_revoke_records_per_block(journal);
}
EXPORT_SYMBOL(jbd2_journal_clear_features);
@@ -2410,6 +2443,8 @@ static struct journal_head *journal_alloc_journal_head(void)
ret = kmem_cache_zalloc(jbd2_journal_head_cache,
GFP_NOFS | __GFP_NOFAIL);
}
+ if (ret)
+ spin_lock_init(&ret->b_state_lock);
return ret;
}
@@ -2529,17 +2564,23 @@ static void __journal_remove_journal_head(struct buffer_head *bh)
J_ASSERT_BH(bh, buffer_jbd(bh));
J_ASSERT_BH(bh, jh2bh(jh) == bh);
BUFFER_TRACE(bh, "remove journal_head");
+
+ /* Unlink before dropping the lock */
+ bh->b_private = NULL;
+ jh->b_bh = NULL; /* debug, really */
+ clear_buffer_jbd(bh);
+}
+
+static void journal_release_journal_head(struct journal_head *jh, size_t b_size)
+{
if (jh->b_frozen_data) {
printk(KERN_WARNING "%s: freeing b_frozen_data\n", __func__);
- jbd2_free(jh->b_frozen_data, bh->b_size);
+ jbd2_free(jh->b_frozen_data, b_size);
}
if (jh->b_committed_data) {
printk(KERN_WARNING "%s: freeing b_committed_data\n", __func__);
- jbd2_free(jh->b_committed_data, bh->b_size);
+ jbd2_free(jh->b_committed_data, b_size);
}
- bh->b_private = NULL;
- jh->b_bh = NULL; /* debug, really */
- clear_buffer_jbd(bh);
journal_free_journal_head(jh);
}
@@ -2557,9 +2598,11 @@ void jbd2_journal_put_journal_head(struct journal_head *jh)
if (!jh->b_jcount) {
__journal_remove_journal_head(bh);
jbd_unlock_bh_journal_head(bh);
+ journal_release_journal_head(jh, bh->b_size);
__brelse(bh);
- } else
+ } else {
jbd_unlock_bh_journal_head(bh);
+ }
}
/*
diff --git a/fs/jbd2/revoke.c b/fs/jbd2/revoke.c
index f08073d7bbf5..fa608788b93d 100644
--- a/fs/jbd2/revoke.c
+++ b/fs/jbd2/revoke.c
@@ -371,6 +371,11 @@ int jbd2_journal_revoke(handle_t *handle, unsigned long long blocknr,
}
#endif
+ if (WARN_ON_ONCE(handle->h_revoke_credits <= 0)) {
+ if (!bh_in)
+ brelse(bh);
+ return -EIO;
+ }
/* We really ought not ever to revoke twice in a row without
first having the revoke cancelled: it's illegal to free a
block twice without allocating it in between! */
@@ -391,6 +396,7 @@ int jbd2_journal_revoke(handle_t *handle, unsigned long long blocknr,
__brelse(bh);
}
}
+ handle->h_revoke_credits--;
jbd_debug(2, "insert revoke for block %llu, bh_in=%p\n",blocknr, bh_in);
err = insert_revoke_hash(journal, blocknr,
diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c
index bee8498d7792..27b9f9dee434 100644
--- a/fs/jbd2/transaction.c
+++ b/fs/jbd2/transaction.c
@@ -63,6 +63,28 @@ void jbd2_journal_free_transaction(transaction_t *transaction)
}
/*
+ * Base amount of descriptor blocks we reserve for each transaction.
+ */
+static int jbd2_descriptor_blocks_per_trans(journal_t *journal)
+{
+ int tag_space = journal->j_blocksize - sizeof(journal_header_t);
+ int tags_per_block;
+
+ /* Subtract UUID */
+ tag_space -= 16;
+ if (jbd2_journal_has_csum_v2or3(journal))
+ tag_space -= sizeof(struct jbd2_journal_block_tail);
+ /* Commit code leaves a slack space of 16 bytes at the end of block */
+ tags_per_block = (tag_space - 16) / journal_tag_bytes(journal);
+ /*
+ * Revoke descriptors are accounted separately so we need to reserve
+ * space for commit block and normal transaction descriptor blocks.
+ */
+ return 1 + DIV_ROUND_UP(journal->j_max_transaction_buffers,
+ tags_per_block);
+}
+
+/*
* jbd2_get_transaction: obtain a new transaction_t object.
*
* Simply initialise a new transaction. Initialize it in
@@ -88,7 +110,9 @@ static void jbd2_get_transaction(journal_t *journal,
spin_lock_init(&transaction->t_handle_lock);
atomic_set(&transaction->t_updates, 0);
atomic_set(&transaction->t_outstanding_credits,
+ jbd2_descriptor_blocks_per_trans(journal) +
atomic_read(&journal->j_reserved_credits));
+ atomic_set(&transaction->t_outstanding_revokes, 0);
atomic_set(&transaction->t_handle_count, 0);
INIT_LIST_HEAD(&transaction->t_inode_list);
INIT_LIST_HEAD(&transaction->t_private_list);
@@ -258,12 +282,13 @@ static int add_transaction_credits(journal_t *journal, int blocks,
* *before* starting to dirty potentially checkpointed buffers
* in the new transaction.
*/
- if (jbd2_log_space_left(journal) < jbd2_space_needed(journal)) {
+ if (jbd2_log_space_left(journal) < journal->j_max_transaction_buffers) {
atomic_sub(total, &t->t_outstanding_credits);
read_unlock(&journal->j_state_lock);
jbd2_might_wait_for_commit(journal);
write_lock(&journal->j_state_lock);
- if (jbd2_log_space_left(journal) < jbd2_space_needed(journal))
+ if (jbd2_log_space_left(journal) <
+ journal->j_max_transaction_buffers)
__jbd2_log_wait_for_space(journal);
write_unlock(&journal->j_state_lock);
return 1;
@@ -299,12 +324,12 @@ static int start_this_handle(journal_t *journal, handle_t *handle,
gfp_t gfp_mask)
{
transaction_t *transaction, *new_transaction = NULL;
- int blocks = handle->h_buffer_credits;
+ int blocks = handle->h_total_credits;
int rsv_blocks = 0;
unsigned long ts = jiffies;
if (handle->h_rsv_handle)
- rsv_blocks = handle->h_rsv_handle->h_buffer_credits;
+ rsv_blocks = handle->h_rsv_handle->h_total_credits;
/*
* Limit the number of reserved credits to 1/2 of maximum transaction
@@ -405,6 +430,7 @@ repeat:
update_t_max_wait(transaction, ts);
handle->h_transaction = transaction;
handle->h_requested_credits = blocks;
+ handle->h_revoke_credits_requested = handle->h_revoke_credits;
handle->h_start_jiffies = jiffies;
atomic_inc(&transaction->t_updates);
atomic_inc(&transaction->t_handle_count);
@@ -431,15 +457,15 @@ static handle_t *new_handle(int nblocks)
handle_t *handle = jbd2_alloc_handle(GFP_NOFS);
if (!handle)
return NULL;
- handle->h_buffer_credits = nblocks;
+ handle->h_total_credits = nblocks;
handle->h_ref = 1;
return handle;
}
handle_t *jbd2__journal_start(journal_t *journal, int nblocks, int rsv_blocks,
- gfp_t gfp_mask, unsigned int type,
- unsigned int line_no)
+ int revoke_records, gfp_t gfp_mask,
+ unsigned int type, unsigned int line_no)
{
handle_t *handle = journal_current_handle();
int err;
@@ -453,6 +479,8 @@ handle_t *jbd2__journal_start(journal_t *journal, int nblocks, int rsv_blocks,
return handle;
}
+ nblocks += DIV_ROUND_UP(revoke_records,
+ journal->j_revoke_records_per_block);
handle = new_handle(nblocks);
if (!handle)
return ERR_PTR(-ENOMEM);
@@ -468,6 +496,7 @@ handle_t *jbd2__journal_start(journal_t *journal, int nblocks, int rsv_blocks,
rsv_handle->h_journal = journal;
handle->h_rsv_handle = rsv_handle;
}
+ handle->h_revoke_credits = revoke_records;
err = start_this_handle(journal, handle, gfp_mask);
if (err < 0) {
@@ -508,16 +537,21 @@ EXPORT_SYMBOL(jbd2__journal_start);
*/
handle_t *jbd2_journal_start(journal_t *journal, int nblocks)
{
- return jbd2__journal_start(journal, nblocks, 0, GFP_NOFS, 0, 0);
+ return jbd2__journal_start(journal, nblocks, 0, 0, GFP_NOFS, 0, 0);
}
EXPORT_SYMBOL(jbd2_journal_start);
-void jbd2_journal_free_reserved(handle_t *handle)
+static void __jbd2_journal_unreserve_handle(handle_t *handle)
{
journal_t *journal = handle->h_journal;
WARN_ON(!handle->h_reserved);
- sub_reserved_credits(journal, handle->h_buffer_credits);
+ sub_reserved_credits(journal, handle->h_total_credits);
+}
+
+void jbd2_journal_free_reserved(handle_t *handle)
+{
+ __jbd2_journal_unreserve_handle(handle);
jbd2_free_handle(handle);
}
EXPORT_SYMBOL(jbd2_journal_free_reserved);
@@ -571,7 +605,7 @@ int jbd2_journal_start_reserved(handle_t *handle, unsigned int type,
handle->h_line_no = line_no;
trace_jbd2_handle_start(journal->j_fs_dev->bd_dev,
handle->h_transaction->t_tid, type,
- line_no, handle->h_buffer_credits);
+ line_no, handle->h_total_credits);
return 0;
}
EXPORT_SYMBOL(jbd2_journal_start_reserved);
@@ -580,6 +614,7 @@ EXPORT_SYMBOL(jbd2_journal_start_reserved);
* int jbd2_journal_extend() - extend buffer credits.
* @handle: handle to 'extend'
* @nblocks: nr blocks to try to extend by.
+ * @revoke_records: number of revoke records to try to extend by.
*
* Some transactions, such as large extends and truncates, can be done
* atomically all at once or in several stages. The operation requests
@@ -596,7 +631,7 @@ EXPORT_SYMBOL(jbd2_journal_start_reserved);
* return code < 0 implies an error
* return code > 0 implies normal transaction-full status.
*/
-int jbd2_journal_extend(handle_t *handle, int nblocks)
+int jbd2_journal_extend(handle_t *handle, int nblocks, int revoke_records)
{
transaction_t *transaction = handle->h_transaction;
journal_t *journal;
@@ -618,6 +653,12 @@ int jbd2_journal_extend(handle_t *handle, int nblocks)
goto error_out;
}
+ nblocks += DIV_ROUND_UP(
+ handle->h_revoke_credits_requested + revoke_records,
+ journal->j_revoke_records_per_block) -
+ DIV_ROUND_UP(
+ handle->h_revoke_credits_requested,
+ journal->j_revoke_records_per_block);
spin_lock(&transaction->t_handle_lock);
wanted = atomic_add_return(nblocks,
&transaction->t_outstanding_credits);
@@ -629,22 +670,16 @@ int jbd2_journal_extend(handle_t *handle, int nblocks)
goto unlock;
}
- if (wanted + (wanted >> JBD2_CONTROL_BLOCKS_SHIFT) >
- jbd2_log_space_left(journal)) {
- jbd_debug(3, "denied handle %p %d blocks: "
- "insufficient log space\n", handle, nblocks);
- atomic_sub(nblocks, &transaction->t_outstanding_credits);
- goto unlock;
- }
-
trace_jbd2_handle_extend(journal->j_fs_dev->bd_dev,
transaction->t_tid,
handle->h_type, handle->h_line_no,
- handle->h_buffer_credits,
+ handle->h_total_credits,
nblocks);
- handle->h_buffer_credits += nblocks;
+ handle->h_total_credits += nblocks;
handle->h_requested_credits += nblocks;
+ handle->h_revoke_credits += revoke_records;
+ handle->h_revoke_credits_requested += revoke_records;
result = 0;
jbd_debug(3, "extended handle %p by %d\n", handle, nblocks);
@@ -655,11 +690,55 @@ error_out:
return result;
}
+static void stop_this_handle(handle_t *handle)
+{
+ transaction_t *transaction = handle->h_transaction;
+ journal_t *journal = transaction->t_journal;
+ int revokes;
+
+ J_ASSERT(journal_current_handle() == handle);
+ J_ASSERT(atomic_read(&transaction->t_updates) > 0);
+ current->journal_info = NULL;
+ /*
+ * Subtract necessary revoke descriptor blocks from handle credits. We
+ * take care to account only for revoke descriptor blocks the
+ * transaction will really need as large sequences of transactions with
+ * small numbers of revokes are relatively common.
+ */
+ revokes = handle->h_revoke_credits_requested - handle->h_revoke_credits;
+ if (revokes) {
+ int t_revokes, revoke_descriptors;
+ int rr_per_blk = journal->j_revoke_records_per_block;
+
+ WARN_ON_ONCE(DIV_ROUND_UP(revokes, rr_per_blk)
+ > handle->h_total_credits);
+ t_revokes = atomic_add_return(revokes,
+ &transaction->t_outstanding_revokes);
+ revoke_descriptors =
+ DIV_ROUND_UP(t_revokes, rr_per_blk) -
+ DIV_ROUND_UP(t_revokes - revokes, rr_per_blk);
+ handle->h_total_credits -= revoke_descriptors;
+ }
+ atomic_sub(handle->h_total_credits,
+ &transaction->t_outstanding_credits);
+ if (handle->h_rsv_handle)
+ __jbd2_journal_unreserve_handle(handle->h_rsv_handle);
+ if (atomic_dec_and_test(&transaction->t_updates))
+ wake_up(&journal->j_wait_updates);
+
+ rwsem_release(&journal->j_trans_commit_map, _THIS_IP_);
+ /*
+ * Scope of the GFP_NOFS context is over here and so we can restore the
+ * original alloc context.
+ */
+ memalloc_nofs_restore(handle->saved_alloc_context);
+}
/**
* int jbd2_journal_restart() - restart a handle .
* @handle: handle to restart
* @nblocks: nr credits requested
+ * @revoke_records: number of revoke record credits requested
* @gfp_mask: memory allocation flags (for start_this_handle)
*
* Restart a handle for a multi-transaction filesystem
@@ -672,56 +751,48 @@ error_out:
* credits. We preserve reserved handle if there's any attached to the
* passed in handle.
*/
-int jbd2__journal_restart(handle_t *handle, int nblocks, gfp_t gfp_mask)
+int jbd2__journal_restart(handle_t *handle, int nblocks, int revoke_records,
+ gfp_t gfp_mask)
{
transaction_t *transaction = handle->h_transaction;
journal_t *journal;
tid_t tid;
- int need_to_start, ret;
+ int need_to_start;
+ int ret;
/* If we've had an abort of any type, don't even think about
* actually doing the restart! */
if (is_handle_aborted(handle))
return 0;
journal = transaction->t_journal;
+ tid = transaction->t_tid;
/*
* First unlink the handle from its current transaction, and start the
* commit on that.
*/
- J_ASSERT(atomic_read(&transaction->t_updates) > 0);
- J_ASSERT(journal_current_handle() == handle);
-
- read_lock(&journal->j_state_lock);
- spin_lock(&transaction->t_handle_lock);
- atomic_sub(handle->h_buffer_credits,
- &transaction->t_outstanding_credits);
- if (handle->h_rsv_handle) {
- sub_reserved_credits(journal,
- handle->h_rsv_handle->h_buffer_credits);
- }
- if (atomic_dec_and_test(&transaction->t_updates))
- wake_up(&journal->j_wait_updates);
- tid = transaction->t_tid;
- spin_unlock(&transaction->t_handle_lock);
+ jbd_debug(2, "restarting handle %p\n", handle);
+ stop_this_handle(handle);
handle->h_transaction = NULL;
- current->journal_info = NULL;
- jbd_debug(2, "restarting handle %p\n", handle);
+ /*
+ * TODO: If we use READ_ONCE / WRITE_ONCE for j_commit_request we can
+ * get rid of pointless j_state_lock traffic like this.
+ */
+ read_lock(&journal->j_state_lock);
need_to_start = !tid_geq(journal->j_commit_request, tid);
read_unlock(&journal->j_state_lock);
if (need_to_start)
jbd2_log_start_commit(journal, tid);
-
- rwsem_release(&journal->j_trans_commit_map, 1, _THIS_IP_);
- handle->h_buffer_credits = nblocks;
- /*
- * Restore the original nofs context because the journal restart
- * is basically the same thing as journal stop and start.
- * start_this_handle will start a new nofs context.
- */
- memalloc_nofs_restore(handle->saved_alloc_context);
+ handle->h_total_credits = nblocks +
+ DIV_ROUND_UP(revoke_records,
+ journal->j_revoke_records_per_block);
+ handle->h_revoke_credits = revoke_records;
ret = start_this_handle(journal, handle, gfp_mask);
+ trace_jbd2_handle_restart(journal->j_fs_dev->bd_dev,
+ ret ? 0 : handle->h_transaction->t_tid,
+ handle->h_type, handle->h_line_no,
+ handle->h_total_credits);
return ret;
}
EXPORT_SYMBOL(jbd2__journal_restart);
@@ -729,7 +800,7 @@ EXPORT_SYMBOL(jbd2__journal_restart);
int jbd2_journal_restart(handle_t *handle, int nblocks)
{
- return jbd2__journal_restart(handle, nblocks, GFP_NOFS);
+ return jbd2__journal_restart(handle, nblocks, 0, GFP_NOFS);
}
EXPORT_SYMBOL(jbd2_journal_restart);
@@ -879,7 +950,7 @@ repeat:
start_lock = jiffies;
lock_buffer(bh);
- jbd_lock_bh_state(bh);
+ spin_lock(&jh->b_state_lock);
/* If it takes too long to lock the buffer, trace it */
time_lock = jbd2_time_diff(start_lock, jiffies);
@@ -929,7 +1000,7 @@ repeat:
error = -EROFS;
if (is_handle_aborted(handle)) {
- jbd_unlock_bh_state(bh);
+ spin_unlock(&jh->b_state_lock);
goto out;
}
error = 0;
@@ -993,7 +1064,7 @@ repeat:
*/
if (buffer_shadow(bh)) {
JBUFFER_TRACE(jh, "on shadow: sleep");
- jbd_unlock_bh_state(bh);
+ spin_unlock(&jh->b_state_lock);
wait_on_bit_io(&bh->b_state, BH_Shadow, TASK_UNINTERRUPTIBLE);
goto repeat;
}
@@ -1014,7 +1085,7 @@ repeat:
JBUFFER_TRACE(jh, "generate frozen data");
if (!frozen_buffer) {
JBUFFER_TRACE(jh, "allocate memory for buffer");
- jbd_unlock_bh_state(bh);
+ spin_unlock(&jh->b_state_lock);
frozen_buffer = jbd2_alloc(jh2bh(jh)->b_size,
GFP_NOFS | __GFP_NOFAIL);
goto repeat;
@@ -1033,7 +1104,7 @@ attach_next:
jh->b_next_transaction = transaction;
done:
- jbd_unlock_bh_state(bh);
+ spin_unlock(&jh->b_state_lock);
/*
* If we are about to journal a buffer, then any revoke pending on it is
@@ -1172,7 +1243,7 @@ int jbd2_journal_get_create_access(handle_t *handle, struct buffer_head *bh)
* that case: the transaction must have deleted the buffer for it to be
* reused here.
*/
- jbd_lock_bh_state(bh);
+ spin_lock(&jh->b_state_lock);
J_ASSERT_JH(jh, (jh->b_transaction == transaction ||
jh->b_transaction == NULL ||
(jh->b_transaction == journal->j_committing_transaction &&
@@ -1207,7 +1278,7 @@ int jbd2_journal_get_create_access(handle_t *handle, struct buffer_head *bh)
jh->b_next_transaction = transaction;
spin_unlock(&journal->j_list_lock);
}
- jbd_unlock_bh_state(bh);
+ spin_unlock(&jh->b_state_lock);
/*
* akpm: I added this. ext3_alloc_branch can pick up new indirect
@@ -1275,13 +1346,13 @@ repeat:
committed_data = jbd2_alloc(jh2bh(jh)->b_size,
GFP_NOFS|__GFP_NOFAIL);
- jbd_lock_bh_state(bh);
+ spin_lock(&jh->b_state_lock);
if (!jh->b_committed_data) {
/* Copy out the current buffer contents into the
* preserved, committed copy. */
JBUFFER_TRACE(jh, "generate b_committed data");
if (!committed_data) {
- jbd_unlock_bh_state(bh);
+ spin_unlock(&jh->b_state_lock);
goto repeat;
}
@@ -1289,7 +1360,7 @@ repeat:
committed_data = NULL;
memcpy(jh->b_committed_data, bh->b_data, bh->b_size);
}
- jbd_unlock_bh_state(bh);
+ spin_unlock(&jh->b_state_lock);
out:
jbd2_journal_put_journal_head(jh);
if (unlikely(committed_data))
@@ -1390,16 +1461,16 @@ int jbd2_journal_dirty_metadata(handle_t *handle, struct buffer_head *bh)
*/
if (jh->b_transaction != transaction &&
jh->b_next_transaction != transaction) {
- jbd_lock_bh_state(bh);
+ spin_lock(&jh->b_state_lock);
J_ASSERT_JH(jh, jh->b_transaction == transaction ||
jh->b_next_transaction == transaction);
- jbd_unlock_bh_state(bh);
+ spin_unlock(&jh->b_state_lock);
}
if (jh->b_modified == 1) {
/* If it's in our transaction it must be in BJ_Metadata list. */
if (jh->b_transaction == transaction &&
jh->b_jlist != BJ_Metadata) {
- jbd_lock_bh_state(bh);
+ spin_lock(&jh->b_state_lock);
if (jh->b_transaction == transaction &&
jh->b_jlist != BJ_Metadata)
pr_err("JBD2: assertion failure: h_type=%u "
@@ -1409,13 +1480,13 @@ int jbd2_journal_dirty_metadata(handle_t *handle, struct buffer_head *bh)
jh->b_jlist);
J_ASSERT_JH(jh, jh->b_transaction != transaction ||
jh->b_jlist == BJ_Metadata);
- jbd_unlock_bh_state(bh);
+ spin_unlock(&jh->b_state_lock);
}
goto out;
}
journal = transaction->t_journal;
- jbd_lock_bh_state(bh);
+ spin_lock(&jh->b_state_lock);
if (jh->b_modified == 0) {
/*
@@ -1423,12 +1494,12 @@ int jbd2_journal_dirty_metadata(handle_t *handle, struct buffer_head *bh)
* of the transaction. This needs to be done
* once a transaction -bzzz
*/
- if (handle->h_buffer_credits <= 0) {
+ if (WARN_ON_ONCE(jbd2_handle_buffer_credits(handle) <= 0)) {
ret = -ENOSPC;
goto out_unlock_bh;
}
jh->b_modified = 1;
- handle->h_buffer_credits--;
+ handle->h_total_credits--;
}
/*
@@ -1501,7 +1572,7 @@ int jbd2_journal_dirty_metadata(handle_t *handle, struct buffer_head *bh)
__jbd2_journal_file_buffer(jh, transaction, BJ_Metadata);
spin_unlock(&journal->j_list_lock);
out_unlock_bh:
- jbd_unlock_bh_state(bh);
+ spin_unlock(&jh->b_state_lock);
out:
JBUFFER_TRACE(jh, "exit");
return ret;
@@ -1539,18 +1610,20 @@ int jbd2_journal_forget (handle_t *handle, struct buffer_head *bh)
BUFFER_TRACE(bh, "entry");
- jbd_lock_bh_state(bh);
+ jh = jbd2_journal_grab_journal_head(bh);
+ if (!jh) {
+ __bforget(bh);
+ return 0;
+ }
- if (!buffer_jbd(bh))
- goto not_jbd;
- jh = bh2jh(bh);
+ spin_lock(&jh->b_state_lock);
/* Critical error: attempting to delete a bitmap buffer, maybe?
* Don't do any jbd operations, and return an error. */
if (!J_EXPECT_JH(jh, !jh->b_committed_data,
"inconsistent data on disk")) {
err = -EIO;
- goto not_jbd;
+ goto drop;
}
/* keep track of whether or not this transaction modified us */
@@ -1598,10 +1671,7 @@ int jbd2_journal_forget (handle_t *handle, struct buffer_head *bh)
__jbd2_journal_file_buffer(jh, transaction, BJ_Forget);
} else {
__jbd2_journal_unfile_buffer(jh);
- if (!buffer_jbd(bh)) {
- spin_unlock(&journal->j_list_lock);
- goto not_jbd;
- }
+ jbd2_journal_put_journal_head(jh);
}
spin_unlock(&journal->j_list_lock);
} else if (jh->b_transaction) {
@@ -1643,7 +1713,7 @@ int jbd2_journal_forget (handle_t *handle, struct buffer_head *bh)
if (!jh->b_cp_transaction) {
JBUFFER_TRACE(jh, "belongs to none transaction");
spin_unlock(&journal->j_list_lock);
- goto not_jbd;
+ goto drop;
}
/*
@@ -1653,7 +1723,7 @@ int jbd2_journal_forget (handle_t *handle, struct buffer_head *bh)
if (!buffer_dirty(bh)) {
__jbd2_journal_remove_checkpoint(jh);
spin_unlock(&journal->j_list_lock);
- goto not_jbd;
+ goto drop;
}
/*
@@ -1666,20 +1736,15 @@ int jbd2_journal_forget (handle_t *handle, struct buffer_head *bh)
__jbd2_journal_file_buffer(jh, transaction, BJ_Forget);
spin_unlock(&journal->j_list_lock);
}
-
- jbd_unlock_bh_state(bh);
- __brelse(bh);
drop:
+ __brelse(bh);
+ spin_unlock(&jh->b_state_lock);
+ jbd2_journal_put_journal_head(jh);
if (drop_reserve) {
/* no need to reserve log space for this block -bzzz */
- handle->h_buffer_credits++;
+ handle->h_total_credits++;
}
return err;
-
-not_jbd:
- jbd_unlock_bh_state(bh);
- __bforget(bh);
- goto drop;
}
/**
@@ -1706,45 +1771,34 @@ int jbd2_journal_stop(handle_t *handle)
tid_t tid;
pid_t pid;
+ if (--handle->h_ref > 0) {
+ jbd_debug(4, "h_ref %d -> %d\n", handle->h_ref + 1,
+ handle->h_ref);
+ if (is_handle_aborted(handle))
+ return -EIO;
+ return 0;
+ }
if (!transaction) {
/*
- * Handle is already detached from the transaction so
- * there is nothing to do other than decrease a refcount,
- * or free the handle if refcount drops to zero
+ * Handle is already detached from the transaction so there is
+ * nothing to do other than free the handle.
*/
- if (--handle->h_ref > 0) {
- jbd_debug(4, "h_ref %d -> %d\n", handle->h_ref + 1,
- handle->h_ref);
- return err;
- } else {
- if (handle->h_rsv_handle)
- jbd2_free_handle(handle->h_rsv_handle);
- goto free_and_exit;
- }
+ memalloc_nofs_restore(handle->saved_alloc_context);
+ goto free_and_exit;
}
journal = transaction->t_journal;
-
- J_ASSERT(journal_current_handle() == handle);
+ tid = transaction->t_tid;
if (is_handle_aborted(handle))
err = -EIO;
- else
- J_ASSERT(atomic_read(&transaction->t_updates) > 0);
-
- if (--handle->h_ref > 0) {
- jbd_debug(4, "h_ref %d -> %d\n", handle->h_ref + 1,
- handle->h_ref);
- return err;
- }
jbd_debug(4, "Handle %p going down\n", handle);
trace_jbd2_handle_stats(journal->j_fs_dev->bd_dev,
- transaction->t_tid,
- handle->h_type, handle->h_line_no,
+ tid, handle->h_type, handle->h_line_no,
jiffies - handle->h_start_jiffies,
handle->h_sync, handle->h_requested_credits,
(handle->h_requested_credits -
- handle->h_buffer_credits));
+ handle->h_total_credits));
/*
* Implement synchronous transaction batching. If the handle
@@ -1804,19 +1858,13 @@ int jbd2_journal_stop(handle_t *handle)
if (handle->h_sync)
transaction->t_synchronous_commit = 1;
- current->journal_info = NULL;
- atomic_sub(handle->h_buffer_credits,
- &transaction->t_outstanding_credits);
/*
* If the handle is marked SYNC, we need to set another commit
- * going! We also want to force a commit if the current
- * transaction is occupying too much of the log, or if the
- * transaction is too old now.
+ * going! We also want to force a commit if the transaction is too
+ * old now.
*/
if (handle->h_sync ||
- (atomic_read(&transaction->t_outstanding_credits) >
- journal->j_max_transaction_buffers) ||
time_after_eq(jiffies, transaction->t_expires)) {
/* Do this even for aborted journals: an abort still
* completes the commit thread, it just doesn't write
@@ -1825,7 +1873,7 @@ int jbd2_journal_stop(handle_t *handle)
jbd_debug(2, "transaction too old, requesting commit for "
"handle %p\n", handle);
/* This is non-blocking */
- jbd2_log_start_commit(journal, transaction->t_tid);
+ jbd2_log_start_commit(journal, tid);
/*
* Special case: JBD2_SYNC synchronous updates require us
@@ -1836,31 +1884,19 @@ int jbd2_journal_stop(handle_t *handle)
}
/*
- * Once we drop t_updates, if it goes to zero the transaction
- * could start committing on us and eventually disappear. So
- * once we do this, we must not dereference transaction
- * pointer again.
+ * Once stop_this_handle() drops t_updates, the transaction could start
+ * committing on us and eventually disappear. So we must not
+ * dereference transaction pointer again after calling
+ * stop_this_handle().
*/
- tid = transaction->t_tid;
- if (atomic_dec_and_test(&transaction->t_updates)) {
- wake_up(&journal->j_wait_updates);
- if (journal->j_barrier_count)
- wake_up(&journal->j_wait_transaction_locked);
- }
-
- rwsem_release(&journal->j_trans_commit_map, 1, _THIS_IP_);
+ stop_this_handle(handle);
if (wait_for_commit)
err = jbd2_log_wait_commit(journal, tid);
- if (handle->h_rsv_handle)
- jbd2_journal_free_reserved(handle->h_rsv_handle);
free_and_exit:
- /*
- * Scope of the GFP_NOFS context is over here and so we can restore the
- * original alloc context.
- */
- memalloc_nofs_restore(handle->saved_alloc_context);
+ if (handle->h_rsv_handle)
+ jbd2_free_handle(handle->h_rsv_handle);
jbd2_free_handle(handle);
return err;
}
@@ -1878,7 +1914,7 @@ free_and_exit:
*
* j_list_lock is held.
*
- * jbd_lock_bh_state(jh2bh(jh)) is held.
+ * jh->b_state_lock is held.
*/
static inline void
@@ -1902,7 +1938,7 @@ __blist_add_buffer(struct journal_head **list, struct journal_head *jh)
*
* Called with j_list_lock held, and the journal may not be locked.
*
- * jbd_lock_bh_state(jh2bh(jh)) is held.
+ * jh->b_state_lock is held.
*/
static inline void
@@ -1934,7 +1970,7 @@ static void __jbd2_journal_temp_unlink_buffer(struct journal_head *jh)
transaction_t *transaction;
struct buffer_head *bh = jh2bh(jh);
- J_ASSERT_JH(jh, jbd_is_locked_bh_state(bh));
+ lockdep_assert_held(&jh->b_state_lock);
transaction = jh->b_transaction;
if (transaction)
assert_spin_locked(&transaction->t_journal->j_list_lock);
@@ -1971,17 +2007,15 @@ static void __jbd2_journal_temp_unlink_buffer(struct journal_head *jh)
}
/*
- * Remove buffer from all transactions.
+ * Remove buffer from all transactions. The caller is responsible for dropping
+ * the jh reference that belonged to the transaction.
*
* Called with bh_state lock and j_list_lock
- *
- * jh and bh may be already freed when this function returns.
*/
static void __jbd2_journal_unfile_buffer(struct journal_head *jh)
{
__jbd2_journal_temp_unlink_buffer(jh);
jh->b_transaction = NULL;
- jbd2_journal_put_journal_head(jh);
}
void jbd2_journal_unfile_buffer(journal_t *journal, struct journal_head *jh)
@@ -1990,18 +2024,19 @@ void jbd2_journal_unfile_buffer(journal_t *journal, struct journal_head *jh)
/* Get reference so that buffer cannot be freed before we unlock it */
get_bh(bh);
- jbd_lock_bh_state(bh);
+ spin_lock(&jh->b_state_lock);
spin_lock(&journal->j_list_lock);
__jbd2_journal_unfile_buffer(jh);
spin_unlock(&journal->j_list_lock);
- jbd_unlock_bh_state(bh);
+ spin_unlock(&jh->b_state_lock);
+ jbd2_journal_put_journal_head(jh);
__brelse(bh);
}
/*
* Called from jbd2_journal_try_to_free_buffers().
*
- * Called under jbd_lock_bh_state(bh)
+ * Called under jh->b_state_lock
*/
static void
__journal_try_to_free_buffer(journal_t *journal, struct buffer_head *bh)
@@ -2088,10 +2123,10 @@ int jbd2_journal_try_to_free_buffers(journal_t *journal,
if (!jh)
continue;
- jbd_lock_bh_state(bh);
+ spin_lock(&jh->b_state_lock);
__journal_try_to_free_buffer(journal, bh);
+ spin_unlock(&jh->b_state_lock);
jbd2_journal_put_journal_head(jh);
- jbd_unlock_bh_state(bh);
if (buffer_jbd(bh))
goto busy;
} while ((bh = bh->b_this_page) != head);
@@ -2112,7 +2147,7 @@ busy:
*
* Called under j_list_lock.
*
- * Called under jbd_lock_bh_state(bh).
+ * Called under jh->b_state_lock.
*/
static int __dispose_buffer(struct journal_head *jh, transaction_t *transaction)
{
@@ -2133,6 +2168,7 @@ static int __dispose_buffer(struct journal_head *jh, transaction_t *transaction)
} else {
JBUFFER_TRACE(jh, "on running transaction");
__jbd2_journal_unfile_buffer(jh);
+ jbd2_journal_put_journal_head(jh);
}
return may_free;
}
@@ -2199,18 +2235,15 @@ static int journal_unmap_buffer(journal_t *journal, struct buffer_head *bh,
* holding the page lock. --sct
*/
- if (!buffer_jbd(bh))
+ jh = jbd2_journal_grab_journal_head(bh);
+ if (!jh)
goto zap_buffer_unlocked;
/* OK, we have data buffer in journaled mode */
write_lock(&journal->j_state_lock);
- jbd_lock_bh_state(bh);
+ spin_lock(&jh->b_state_lock);
spin_lock(&journal->j_list_lock);
- jh = jbd2_journal_grab_journal_head(bh);
- if (!jh)
- goto zap_buffer_no_jh;
-
/*
* We cannot remove the buffer from checkpoint lists until the
* transaction adding inode to orphan list (let's call it T)
@@ -2289,10 +2322,10 @@ static int journal_unmap_buffer(journal_t *journal, struct buffer_head *bh,
* for commit and try again.
*/
if (partial_page) {
- jbd2_journal_put_journal_head(jh);
spin_unlock(&journal->j_list_lock);
- jbd_unlock_bh_state(bh);
+ spin_unlock(&jh->b_state_lock);
write_unlock(&journal->j_state_lock);
+ jbd2_journal_put_journal_head(jh);
return -EBUSY;
}
/*
@@ -2304,10 +2337,10 @@ static int journal_unmap_buffer(journal_t *journal, struct buffer_head *bh,
set_buffer_freed(bh);
if (journal->j_running_transaction && buffer_jbddirty(bh))
jh->b_next_transaction = journal->j_running_transaction;
- jbd2_journal_put_journal_head(jh);
spin_unlock(&journal->j_list_lock);
- jbd_unlock_bh_state(bh);
+ spin_unlock(&jh->b_state_lock);
write_unlock(&journal->j_state_lock);
+ jbd2_journal_put_journal_head(jh);
return 0;
} else {
/* Good, the buffer belongs to the running transaction.
@@ -2331,11 +2364,10 @@ zap_buffer:
* here.
*/
jh->b_modified = 0;
- jbd2_journal_put_journal_head(jh);
-zap_buffer_no_jh:
spin_unlock(&journal->j_list_lock);
- jbd_unlock_bh_state(bh);
+ spin_unlock(&jh->b_state_lock);
write_unlock(&journal->j_state_lock);
+ jbd2_journal_put_journal_head(jh);
zap_buffer_unlocked:
clear_buffer_dirty(bh);
J_ASSERT_BH(bh, !buffer_jbddirty(bh));
@@ -2422,7 +2454,7 @@ void __jbd2_journal_file_buffer(struct journal_head *jh,
int was_dirty = 0;
struct buffer_head *bh = jh2bh(jh);
- J_ASSERT_JH(jh, jbd_is_locked_bh_state(bh));
+ lockdep_assert_held(&jh->b_state_lock);
assert_spin_locked(&transaction->t_journal->j_list_lock);
J_ASSERT_JH(jh, jh->b_jlist < BJ_Types);
@@ -2484,11 +2516,11 @@ void __jbd2_journal_file_buffer(struct journal_head *jh,
void jbd2_journal_file_buffer(struct journal_head *jh,
transaction_t *transaction, int jlist)
{
- jbd_lock_bh_state(jh2bh(jh));
+ spin_lock(&jh->b_state_lock);
spin_lock(&transaction->t_journal->j_list_lock);
__jbd2_journal_file_buffer(jh, transaction, jlist);
spin_unlock(&transaction->t_journal->j_list_lock);
- jbd_unlock_bh_state(jh2bh(jh));
+ spin_unlock(&jh->b_state_lock);
}
/*
@@ -2498,23 +2530,25 @@ void jbd2_journal_file_buffer(struct journal_head *jh,
* buffer on that transaction's metadata list.
*
* Called under j_list_lock
- * Called under jbd_lock_bh_state(jh2bh(jh))
+ * Called under jh->b_state_lock
*
- * jh and bh may be already free when this function returns
+ * When this function returns true, there's no next transaction to refile to
+ * and the caller has to drop jh reference through
+ * jbd2_journal_put_journal_head().
*/
-void __jbd2_journal_refile_buffer(struct journal_head *jh)
+bool __jbd2_journal_refile_buffer(struct journal_head *jh)
{
int was_dirty, jlist;
struct buffer_head *bh = jh2bh(jh);
- J_ASSERT_JH(jh, jbd_is_locked_bh_state(bh));
+ lockdep_assert_held(&jh->b_state_lock);
if (jh->b_transaction)
assert_spin_locked(&jh->b_transaction->t_journal->j_list_lock);
/* If the buffer is now unused, just drop it. */
if (jh->b_next_transaction == NULL) {
__jbd2_journal_unfile_buffer(jh);
- return;
+ return true;
}
/*
@@ -2542,6 +2576,7 @@ void __jbd2_journal_refile_buffer(struct journal_head *jh)
if (was_dirty)
set_buffer_jbddirty(bh);
+ return false;
}
/*
@@ -2552,16 +2587,15 @@ void __jbd2_journal_refile_buffer(struct journal_head *jh)
*/
void jbd2_journal_refile_buffer(journal_t *journal, struct journal_head *jh)
{
- struct buffer_head *bh = jh2bh(jh);
+ bool drop;
- /* Get reference so that buffer cannot be freed before we unlock it */
- get_bh(bh);
- jbd_lock_bh_state(bh);
+ spin_lock(&jh->b_state_lock);
spin_lock(&journal->j_list_lock);
- __jbd2_journal_refile_buffer(jh);
- jbd_unlock_bh_state(bh);
+ drop = __jbd2_journal_refile_buffer(jh);
+ spin_unlock(&jh->b_state_lock);
spin_unlock(&journal->j_list_lock);
- __brelse(bh);
+ if (drop)
+ jbd2_journal_put_journal_head(jh);
}
/*
diff --git a/fs/jffs2/nodelist.c b/fs/jffs2/nodelist.c
index 021a4a2190ee..b86c78d178c6 100644
--- a/fs/jffs2/nodelist.c
+++ b/fs/jffs2/nodelist.c
@@ -226,7 +226,7 @@ static int jffs2_add_frag_to_fragtree(struct jffs2_sb_info *c, struct rb_root *r
lastend = this->ofs + this->size;
} else {
dbg_fragtree2("lookup gave no frag\n");
- return -EINVAL;
+ lastend = 0;
}
/* See if we ran off the end of the fragtree */
diff --git a/fs/kernfs/dir.c b/fs/kernfs/dir.c
index 6ebae6bbe6a5..9d96e6871e1a 100644
--- a/fs/kernfs/dir.c
+++ b/fs/kernfs/dir.c
@@ -438,7 +438,7 @@ void kernfs_put_active(struct kernfs_node *kn)
return;
if (kernfs_lockdep(kn))
- rwsem_release(&kn->dep_map, 1, _RET_IP_);
+ rwsem_release(&kn->dep_map, _RET_IP_);
v = atomic_dec_return(&kn->active);
if (likely(v != KN_DEACTIVATED_BIAS))
return;
@@ -476,7 +476,7 @@ static void kernfs_drain(struct kernfs_node *kn)
if (kernfs_lockdep(kn)) {
lock_acquired(&kn->dep_map, _RET_IP_);
- rwsem_release(&kn->dep_map, 1, _RET_IP_);
+ rwsem_release(&kn->dep_map, _RET_IP_);
}
kernfs_drain_open_files(kn);
@@ -508,10 +508,6 @@ void kernfs_put(struct kernfs_node *kn)
struct kernfs_node *parent;
struct kernfs_root *root;
- /*
- * kernfs_node is freed with ->count 0, kernfs_find_and_get_node_by_ino
- * depends on this to filter reused stale node
- */
if (!kn || !atomic_dec_and_test(&kn->count))
return;
root = kernfs_root(kn);
@@ -536,7 +532,7 @@ void kernfs_put(struct kernfs_node *kn)
kmem_cache_free(kernfs_iattrs_cache, kn->iattr);
}
spin_lock(&kernfs_idr_lock);
- idr_remove(&root->ino_idr, kn->id.ino);
+ idr_remove(&root->ino_idr, (u32)kernfs_ino(kn));
spin_unlock(&kernfs_idr_lock);
kmem_cache_free(kernfs_node_cache, kn);
@@ -621,8 +617,7 @@ static struct kernfs_node *__kernfs_new_node(struct kernfs_root *root,
unsigned flags)
{
struct kernfs_node *kn;
- u32 gen;
- int cursor;
+ u32 id_highbits;
int ret;
name = kstrdup_const(name, GFP_KERNEL);
@@ -635,23 +630,19 @@ static struct kernfs_node *__kernfs_new_node(struct kernfs_root *root,
idr_preload(GFP_KERNEL);
spin_lock(&kernfs_idr_lock);
- cursor = idr_get_cursor(&root->ino_idr);
ret = idr_alloc_cyclic(&root->ino_idr, kn, 1, 0, GFP_ATOMIC);
- if (ret >= 0 && ret < cursor)
- root->next_generation++;
- gen = root->next_generation;
+ if (ret >= 0 && ret < root->last_id_lowbits)
+ root->id_highbits++;
+ id_highbits = root->id_highbits;
+ root->last_id_lowbits = ret;
spin_unlock(&kernfs_idr_lock);
idr_preload_end();
if (ret < 0)
goto err_out2;
- kn->id.ino = ret;
- kn->id.generation = gen;
- /*
- * set ino first. This RELEASE is paired with atomic_inc_not_zero in
- * kernfs_find_and_get_node_by_ino
- */
- atomic_set_release(&kn->count, 1);
+ kn->id = (u64)id_highbits << 32 | ret;
+
+ atomic_set(&kn->count, 1);
atomic_set(&kn->active, KN_DEACTIVATED_BIAS);
RB_CLEAR_NODE(&kn->rb);
@@ -680,7 +671,7 @@ static struct kernfs_node *__kernfs_new_node(struct kernfs_root *root,
return kn;
err_out3:
- idr_remove(&root->ino_idr, kn->id.ino);
+ idr_remove(&root->ino_idr, (u32)kernfs_ino(kn));
err_out2:
kmem_cache_free(kernfs_node_cache, kn);
err_out1:
@@ -705,50 +696,52 @@ struct kernfs_node *kernfs_new_node(struct kernfs_node *parent,
}
/*
- * kernfs_find_and_get_node_by_ino - get kernfs_node from inode number
+ * kernfs_find_and_get_node_by_id - get kernfs_node from node id
* @root: the kernfs root
- * @ino: inode number
+ * @id: the target node id
+ *
+ * @id's lower 32bits encode ino and upper gen. If the gen portion is
+ * zero, all generations are matched.
*
* RETURNS:
* NULL on failure. Return a kernfs node with reference counter incremented
*/
-struct kernfs_node *kernfs_find_and_get_node_by_ino(struct kernfs_root *root,
- unsigned int ino)
+struct kernfs_node *kernfs_find_and_get_node_by_id(struct kernfs_root *root,
+ u64 id)
{
struct kernfs_node *kn;
+ ino_t ino = kernfs_id_ino(id);
+ u32 gen = kernfs_id_gen(id);
- rcu_read_lock();
- kn = idr_find(&root->ino_idr, ino);
+ spin_lock(&kernfs_idr_lock);
+
+ kn = idr_find(&root->ino_idr, (u32)ino);
if (!kn)
- goto out;
+ goto err_unlock;
- /*
- * Since kernfs_node is freed in RCU, it's possible an old node for ino
- * is freed, but reused before RCU grace period. But a freed node (see
- * kernfs_put) or an incompletedly initialized node (see
- * __kernfs_new_node) should have 'count' 0. We can use this fact to
- * filter out such node.
- */
- if (!atomic_inc_not_zero(&kn->count)) {
- kn = NULL;
- goto out;
+ if (sizeof(ino_t) >= sizeof(u64)) {
+ /* we looked up with the low 32bits, compare the whole */
+ if (kernfs_ino(kn) != ino)
+ goto err_unlock;
+ } else {
+ /* 0 matches all generations */
+ if (unlikely(gen && kernfs_gen(kn) != gen))
+ goto err_unlock;
}
/*
- * The node could be a new node or a reused node. If it's a new node,
- * we are ok. If it's reused because of RCU (because of
- * SLAB_TYPESAFE_BY_RCU), the __kernfs_new_node always sets its 'ino'
- * before 'count'. So if 'count' is uptodate, 'ino' should be uptodate,
- * hence we can use 'ino' to filter stale node.
+ * ACTIVATED is protected with kernfs_mutex but it was clear when
+ * @kn was added to idr and we just wanna see it set. No need to
+ * grab kernfs_mutex.
*/
- if (kn->id.ino != ino)
- goto out;
- rcu_read_unlock();
+ if (unlikely(!(kn->flags & KERNFS_ACTIVATED) ||
+ !atomic_inc_not_zero(&kn->count)))
+ goto err_unlock;
+ spin_unlock(&kernfs_idr_lock);
return kn;
-out:
- rcu_read_unlock();
- kernfs_put(kn);
+err_unlock:
+ spin_unlock(&kernfs_idr_lock);
return NULL;
}
@@ -962,7 +955,17 @@ struct kernfs_root *kernfs_create_root(struct kernfs_syscall_ops *scops,
idr_init(&root->ino_idr);
INIT_LIST_HEAD(&root->supers);
- root->next_generation = 1;
+
+ /*
+ * On 64bit ino setups, id is ino. On 32bit, low 32bits are ino.
+ * High bits generation. The starting value for both ino and
+ * genenration is 1. Initialize upper 32bit allocation
+ * accordingly.
+ */
+ if (sizeof(ino_t) >= sizeof(u64))
+ root->id_highbits = 0;
+ else
+ root->id_highbits = 1;
kn = __kernfs_new_node(root, NULL, "", S_IFDIR | S_IRUGO | S_IXUGO,
GLOBAL_ROOT_UID, GLOBAL_ROOT_GID,
@@ -1678,7 +1681,7 @@ static int kernfs_fop_readdir(struct file *file, struct dir_context *ctx)
const char *name = pos->name;
unsigned int type = dt_type(pos);
int len = strlen(name);
- ino_t ino = pos->id.ino;
+ ino_t ino = kernfs_ino(pos);
ctx->pos = pos->hash;
file->private_data = pos;
diff --git a/fs/kernfs/file.c b/fs/kernfs/file.c
index e8c792b49616..34366db3620d 100644
--- a/fs/kernfs/file.c
+++ b/fs/kernfs/file.c
@@ -892,7 +892,7 @@ repeat:
* have the matching @file available. Look up the inodes
* and generate the events manually.
*/
- inode = ilookup(info->sb, kn->id.ino);
+ inode = ilookup(info->sb, kernfs_ino(kn));
if (!inode)
continue;
@@ -901,7 +901,7 @@ repeat:
if (parent) {
struct inode *p_inode;
- p_inode = ilookup(info->sb, parent->id.ino);
+ p_inode = ilookup(info->sb, kernfs_ino(parent));
if (p_inode) {
fsnotify(p_inode, FS_MODIFY | FS_EVENT_ON_CHILD,
inode, FSNOTIFY_EVENT_INODE, &name, 0);
diff --git a/fs/kernfs/inode.c b/fs/kernfs/inode.c
index f3eaa8869f42..eac277c63d42 100644
--- a/fs/kernfs/inode.c
+++ b/fs/kernfs/inode.c
@@ -201,7 +201,7 @@ static void kernfs_init_inode(struct kernfs_node *kn, struct inode *inode)
inode->i_private = kn;
inode->i_mapping->a_ops = &kernfs_aops;
inode->i_op = &kernfs_iops;
- inode->i_generation = kn->id.generation;
+ inode->i_generation = kernfs_gen(kn);
set_default_inode_attr(inode, kn->mode);
kernfs_refresh_inode(kn, inode);
@@ -247,7 +247,7 @@ struct inode *kernfs_get_inode(struct super_block *sb, struct kernfs_node *kn)
{
struct inode *inode;
- inode = iget_locked(sb, kn->id.ino);
+ inode = iget_locked(sb, kernfs_ino(kn));
if (inode && (inode->i_state & I_NEW))
kernfs_init_inode(kn, inode);
diff --git a/fs/kernfs/kernfs-internal.h b/fs/kernfs/kernfs-internal.h
index 02ce570a9a3c..2f3c51d55261 100644
--- a/fs/kernfs/kernfs-internal.h
+++ b/fs/kernfs/kernfs-internal.h
@@ -109,8 +109,6 @@ struct kernfs_node *kernfs_new_node(struct kernfs_node *parent,
const char *name, umode_t mode,
kuid_t uid, kgid_t gid,
unsigned flags);
-struct kernfs_node *kernfs_find_and_get_node_by_ino(struct kernfs_root *root,
- unsigned int ino);
/*
* file.c
diff --git a/fs/kernfs/mount.c b/fs/kernfs/mount.c
index 6c12fac2c287..9dc7e7a64e10 100644
--- a/fs/kernfs/mount.c
+++ b/fs/kernfs/mount.c
@@ -53,63 +53,85 @@ const struct super_operations kernfs_sops = {
.show_path = kernfs_sop_show_path,
};
-/*
- * Similar to kernfs_fh_get_inode, this one gets kernfs node from inode
- * number and generation
- */
-struct kernfs_node *kernfs_get_node_by_id(struct kernfs_root *root,
- const union kernfs_node_id *id)
+static int kernfs_encode_fh(struct inode *inode, __u32 *fh, int *max_len,
+ struct inode *parent)
{
- struct kernfs_node *kn;
+ struct kernfs_node *kn = inode->i_private;
- kn = kernfs_find_and_get_node_by_ino(root, id->ino);
- if (!kn)
- return NULL;
- if (kn->id.generation != id->generation) {
- kernfs_put(kn);
- return NULL;
+ if (*max_len < 2) {
+ *max_len = 2;
+ return FILEID_INVALID;
}
- return kn;
+
+ *max_len = 2;
+ *(u64 *)fh = kn->id;
+ return FILEID_KERNFS;
}
-static struct inode *kernfs_fh_get_inode(struct super_block *sb,
- u64 ino, u32 generation)
+static struct dentry *__kernfs_fh_to_dentry(struct super_block *sb,
+ struct fid *fid, int fh_len,
+ int fh_type, bool get_parent)
{
struct kernfs_super_info *info = kernfs_info(sb);
- struct inode *inode;
struct kernfs_node *kn;
+ struct inode *inode;
+ u64 id;
- if (ino == 0)
- return ERR_PTR(-ESTALE);
+ if (fh_len < 2)
+ return NULL;
+
+ switch (fh_type) {
+ case FILEID_KERNFS:
+ id = *(u64 *)fid;
+ break;
+ case FILEID_INO32_GEN:
+ case FILEID_INO32_GEN_PARENT:
+ /*
+ * blk_log_action() exposes "LOW32,HIGH32" pair without
+ * type and userland can call us with generic fid
+ * constructed from them. Combine it back to ID. See
+ * blk_log_action().
+ */
+ id = ((u64)fid->i32.gen << 32) | fid->i32.ino;
+ break;
+ default:
+ return NULL;
+ }
- kn = kernfs_find_and_get_node_by_ino(info->root, ino);
+ kn = kernfs_find_and_get_node_by_id(info->root, id);
if (!kn)
return ERR_PTR(-ESTALE);
+
+ if (get_parent) {
+ struct kernfs_node *parent;
+
+ parent = kernfs_get_parent(kn);
+ kernfs_put(kn);
+ kn = parent;
+ if (!kn)
+ return ERR_PTR(-ESTALE);
+ }
+
inode = kernfs_get_inode(sb, kn);
kernfs_put(kn);
if (!inode)
return ERR_PTR(-ESTALE);
- if (generation && inode->i_generation != generation) {
- /* we didn't find the right inode.. */
- iput(inode);
- return ERR_PTR(-ESTALE);
- }
- return inode;
+ return d_obtain_alias(inode);
}
-static struct dentry *kernfs_fh_to_dentry(struct super_block *sb, struct fid *fid,
- int fh_len, int fh_type)
+static struct dentry *kernfs_fh_to_dentry(struct super_block *sb,
+ struct fid *fid, int fh_len,
+ int fh_type)
{
- return generic_fh_to_dentry(sb, fid, fh_len, fh_type,
- kernfs_fh_get_inode);
+ return __kernfs_fh_to_dentry(sb, fid, fh_len, fh_type, false);
}
-static struct dentry *kernfs_fh_to_parent(struct super_block *sb, struct fid *fid,
- int fh_len, int fh_type)
+static struct dentry *kernfs_fh_to_parent(struct super_block *sb,
+ struct fid *fid, int fh_len,
+ int fh_type)
{
- return generic_fh_to_parent(sb, fid, fh_len, fh_type,
- kernfs_fh_get_inode);
+ return __kernfs_fh_to_dentry(sb, fid, fh_len, fh_type, true);
}
static struct dentry *kernfs_get_parent_dentry(struct dentry *child)
@@ -120,6 +142,7 @@ static struct dentry *kernfs_get_parent_dentry(struct dentry *child)
}
static const struct export_operations kernfs_export_ops = {
+ .encode_fh = kernfs_encode_fh,
.fh_to_dentry = kernfs_fh_to_dentry,
.fh_to_parent = kernfs_fh_to_parent,
.get_parent = kernfs_get_parent_dentry,
@@ -200,7 +223,7 @@ struct dentry *kernfs_node_dentry(struct kernfs_node *kn,
dput(dentry);
return ERR_PTR(-EINVAL);
}
- dtmp = lookup_one_len_unlocked(kntmp->name, dentry,
+ dtmp = lookup_positive_unlocked(kntmp->name, dentry,
strlen(kntmp->name));
dput(dentry);
if (IS_ERR(dtmp))
@@ -363,18 +386,9 @@ void kernfs_kill_sb(struct super_block *sb)
void __init kernfs_init(void)
{
-
- /*
- * the slab is freed in RCU context, so kernfs_find_and_get_node_by_ino
- * can access the slab lock free. This could introduce stale nodes,
- * please see how kernfs_find_and_get_node_by_ino filters out stale
- * nodes.
- */
kernfs_node_cache = kmem_cache_create("kernfs_node_cache",
sizeof(struct kernfs_node),
- 0,
- SLAB_PANIC | SLAB_TYPESAFE_BY_RCU,
- NULL);
+ 0, SLAB_PANIC, NULL);
/* Creates slab cache for kernfs inode attributes */
kernfs_iattrs_cache = kmem_cache_create("kernfs_iattrs_cache",
diff --git a/fs/libfs.c b/fs/libfs.c
index 540611b99b9a..1463b038ffc4 100644
--- a/fs/libfs.c
+++ b/fs/libfs.c
@@ -473,8 +473,7 @@ EXPORT_SYMBOL(simple_write_begin);
/**
* simple_write_end - .write_end helper for non-block-device FSes
- * @available: See .write_end of address_space_operations
- * @file: "
+ * @file: See .write_end of address_space_operations
* @mapping: "
* @pos: "
* @len: "
diff --git a/fs/lockd/host.c b/fs/lockd/host.c
index 7d46fafdbbe5..0afb6d59bad0 100644
--- a/fs/lockd/host.c
+++ b/fs/lockd/host.c
@@ -464,7 +464,8 @@ nlm_bind_host(struct nlm_host *host)
.version = host->h_version,
.authflavor = RPC_AUTH_UNIX,
.flags = (RPC_CLNT_CREATE_NOPING |
- RPC_CLNT_CREATE_AUTOBIND),
+ RPC_CLNT_CREATE_AUTOBIND |
+ RPC_CLNT_CREATE_REUSEPORT),
.cred = host->h_cred,
};
diff --git a/fs/namei.c b/fs/namei.c
index 671c3c1a3425..d6c91d1e88cb 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -925,7 +925,7 @@ static inline int may_follow_link(struct nameidata *nd)
return -ECHILD;
audit_inode(nd->name, nd->stack[0].link.dentry, 0);
- audit_log_link_denied("follow_link");
+ audit_log_path_denied(AUDIT_ANOM_LINK, "follow_link");
return -EACCES;
}
@@ -993,7 +993,7 @@ static int may_linkat(struct path *link)
if (safe_hardlink_source(inode) || inode_owner_or_capable(inode))
return 0;
- audit_log_link_denied("linkat");
+ audit_log_path_denied(AUDIT_ANOM_LINK, "linkat");
return -EPERM;
}
@@ -1031,6 +1031,10 @@ static int may_create_in_sticky(struct dentry * const dir,
(dir->d_inode->i_mode & 0020 &&
((sysctl_protected_fifos >= 2 && S_ISFIFO(inode->i_mode)) ||
(sysctl_protected_regular >= 2 && S_ISREG(inode->i_mode))))) {
+ const char *operation = S_ISFIFO(inode->i_mode) ?
+ "sticky_create_fifo" :
+ "sticky_create_regular";
+ audit_log_path_denied(AUDIT_ANOM_CREAT, operation);
return -EACCES;
}
return 0;
@@ -1206,25 +1210,25 @@ static int follow_automount(struct path *path, struct nameidata *nd,
* - Flagged as automount point
*
* This may only be called in refwalk mode.
+ * On success path->dentry is known positive.
*
* Serialization is taken care of in namespace.c
*/
static int follow_managed(struct path *path, struct nameidata *nd)
{
struct vfsmount *mnt = path->mnt; /* held by caller, must be left alone */
- unsigned managed;
+ unsigned flags;
bool need_mntput = false;
int ret = 0;
/* Given that we're not holding a lock here, we retain the value in a
* local variable for each dentry as we look at it so that we don't see
* the components of that value change under us */
- while (managed = READ_ONCE(path->dentry->d_flags),
- managed &= DCACHE_MANAGED_DENTRY,
- unlikely(managed != 0)) {
+ while (flags = smp_load_acquire(&path->dentry->d_flags),
+ unlikely(flags & DCACHE_MANAGED_DENTRY)) {
/* Allow the filesystem to manage the transit without i_mutex
* being held. */
- if (managed & DCACHE_MANAGE_TRANSIT) {
+ if (flags & DCACHE_MANAGE_TRANSIT) {
BUG_ON(!path->dentry->d_op);
BUG_ON(!path->dentry->d_op->d_manage);
ret = path->dentry->d_op->d_manage(path, false);
@@ -1233,7 +1237,7 @@ static int follow_managed(struct path *path, struct nameidata *nd)
}
/* Transit to a mounted filesystem. */
- if (managed & DCACHE_MOUNTED) {
+ if (flags & DCACHE_MOUNTED) {
struct vfsmount *mounted = lookup_mnt(path);
if (mounted) {
dput(path->dentry);
@@ -1252,7 +1256,7 @@ static int follow_managed(struct path *path, struct nameidata *nd)
}
/* Handle an automount point */
- if (managed & DCACHE_NEED_AUTOMOUNT) {
+ if (flags & DCACHE_NEED_AUTOMOUNT) {
ret = follow_automount(path, nd, &need_mntput);
if (ret < 0)
break;
@@ -1265,10 +1269,12 @@ static int follow_managed(struct path *path, struct nameidata *nd)
if (need_mntput && path->mnt == mnt)
mntput(path->mnt);
- if (ret == -EISDIR || !ret)
- ret = 1;
if (need_mntput)
nd->flags |= LOOKUP_JUMPED;
+ if (ret == -EISDIR || !ret)
+ ret = 1;
+ if (ret > 0 && unlikely(d_flags_negative(flags)))
+ ret = -ENOENT;
if (unlikely(ret < 0))
path_put_conditional(path, nd);
return ret;
@@ -1617,10 +1623,6 @@ static int lookup_fast(struct nameidata *nd,
dput(dentry);
return status;
}
- if (unlikely(d_is_negative(dentry))) {
- dput(dentry);
- return -ENOENT;
- }
path->mnt = mnt;
path->dentry = dentry;
@@ -1807,11 +1809,6 @@ static int walk_component(struct nameidata *nd, int flags)
if (unlikely(err < 0))
return err;
- if (unlikely(d_is_negative(path.dentry))) {
- path_to_nameidata(&path, nd);
- return -ENOENT;
- }
-
seq = 0; /* we are already out of RCU mode */
inode = d_backing_inode(path.dentry);
}
@@ -2564,6 +2561,26 @@ struct dentry *lookup_one_len_unlocked(const char *name,
}
EXPORT_SYMBOL(lookup_one_len_unlocked);
+/*
+ * Like lookup_one_len_unlocked(), except that it yields ERR_PTR(-ENOENT)
+ * on negatives. Returns known positive or ERR_PTR(); that's what
+ * most of the users want. Note that pinned negative with unlocked parent
+ * _can_ become positive at any time, so callers of lookup_one_len_unlocked()
+ * need to be very careful; pinned positives have ->d_inode stable, so
+ * this one avoids such problems.
+ */
+struct dentry *lookup_positive_unlocked(const char *name,
+ struct dentry *base, int len)
+{
+ struct dentry *ret = lookup_one_len_unlocked(name, base, len);
+ if (!IS_ERR(ret) && d_flags_negative(smp_load_acquire(&ret->d_flags))) {
+ dput(ret);
+ ret = ERR_PTR(-ENOENT);
+ }
+ return ret;
+}
+EXPORT_SYMBOL(lookup_positive_unlocked);
+
#ifdef CONFIG_UNIX98_PTYS
int path_pts(struct path *path)
{
@@ -2658,7 +2675,7 @@ mountpoint_last(struct nameidata *nd)
return PTR_ERR(path.dentry);
}
}
- if (d_is_negative(path.dentry)) {
+ if (d_flags_negative(smp_load_acquire(&path.dentry->d_flags))) {
dput(path.dentry);
return -ENOENT;
}
@@ -3352,11 +3369,6 @@ static int do_last(struct nameidata *nd,
if (unlikely(error < 0))
return error;
- if (unlikely(d_is_negative(path.dentry))) {
- path_to_nameidata(&path, nd);
- return -ENOENT;
- }
-
/*
* create/update audit record if it already exists.
*/
diff --git a/fs/namespace.c b/fs/namespace.c
index fe0e9e1410fe..2adfe7b166a3 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -2478,8 +2478,10 @@ static void mnt_warn_timestamp_expiry(struct path *mountpoint, struct vfsmount *
time64_to_tm(sb->s_time_max, 0, &tm);
- pr_warn("Mounted %s file system at %s supports timestamps until %04ld (0x%llx)\n",
- sb->s_type->name, mntpath,
+ pr_warn("%s filesystem being %s at %s supports timestamps until %04ld (0x%llx)\n",
+ sb->s_type->name,
+ is_mounted(mnt) ? "remounted" : "mounted",
+ mntpath,
tm.tm_year+1900, (unsigned long long)sb->s_time_max);
free_page((unsigned long)buf);
@@ -2764,14 +2766,11 @@ static int do_new_mount_fc(struct fs_context *fc, struct path *mountpoint,
if (IS_ERR(mnt))
return PTR_ERR(mnt);
- error = do_add_mount(real_mount(mnt), mountpoint, mnt_flags);
- if (error < 0) {
- mntput(mnt);
- return error;
- }
-
mnt_warn_timestamp_expiry(mountpoint, mnt);
+ error = do_add_mount(real_mount(mnt), mountpoint, mnt_flags);
+ if (error < 0)
+ mntput(mnt);
return error;
}
diff --git a/fs/nfs/callback.h b/fs/nfs/callback.h
index 8f34daf85f70..549350259840 100644
--- a/fs/nfs/callback.h
+++ b/fs/nfs/callback.h
@@ -72,8 +72,8 @@ struct cb_getattrres {
uint32_t bitmap[2];
uint64_t size;
uint64_t change_attr;
- struct timespec ctime;
- struct timespec mtime;
+ struct timespec64 ctime;
+ struct timespec64 mtime;
};
struct cb_recallargs {
diff --git a/fs/nfs/callback_proc.c b/fs/nfs/callback_proc.c
index f39924ba050b..cd4c6bc81cae 100644
--- a/fs/nfs/callback_proc.c
+++ b/fs/nfs/callback_proc.c
@@ -26,7 +26,6 @@ __be32 nfs4_callback_getattr(void *argp, void *resp,
struct cb_getattrargs *args = argp;
struct cb_getattrres *res = resp;
struct nfs_delegation *delegation;
- struct nfs_inode *nfsi;
struct inode *inode;
res->status = htonl(NFS4ERR_OP_NOT_IN_SESSION);
@@ -47,17 +46,16 @@ __be32 nfs4_callback_getattr(void *argp, void *resp,
-ntohl(res->status));
goto out;
}
- nfsi = NFS_I(inode);
rcu_read_lock();
- delegation = rcu_dereference(nfsi->delegation);
+ delegation = nfs4_get_valid_delegation(inode);
if (delegation == NULL || (delegation->type & FMODE_WRITE) == 0)
goto out_iput;
res->size = i_size_read(inode);
res->change_attr = delegation->change_attr;
if (nfs_have_writebacks(inode))
res->change_attr++;
- res->ctime = timespec64_to_timespec(inode->i_ctime);
- res->mtime = timespec64_to_timespec(inode->i_mtime);
+ res->ctime = inode->i_ctime;
+ res->mtime = inode->i_mtime;
res->bitmap[0] = (FATTR4_WORD0_CHANGE|FATTR4_WORD0_SIZE) &
args->bitmap[0];
res->bitmap[1] = (FATTR4_WORD1_TIME_METADATA|FATTR4_WORD1_TIME_MODIFY) &
diff --git a/fs/nfs/callback_xdr.c b/fs/nfs/callback_xdr.c
index 73a5a5ea2976..03a20f5716c7 100644
--- a/fs/nfs/callback_xdr.c
+++ b/fs/nfs/callback_xdr.c
@@ -627,7 +627,7 @@ static __be32 encode_attr_size(struct xdr_stream *xdr, const uint32_t *bitmap, u
return 0;
}
-static __be32 encode_attr_time(struct xdr_stream *xdr, const struct timespec *time)
+static __be32 encode_attr_time(struct xdr_stream *xdr, const struct timespec64 *time)
{
__be32 *p;
@@ -639,14 +639,14 @@ static __be32 encode_attr_time(struct xdr_stream *xdr, const struct timespec *ti
return 0;
}
-static __be32 encode_attr_ctime(struct xdr_stream *xdr, const uint32_t *bitmap, const struct timespec *time)
+static __be32 encode_attr_ctime(struct xdr_stream *xdr, const uint32_t *bitmap, const struct timespec64 *time)
{
if (!(bitmap[1] & FATTR4_WORD1_TIME_METADATA))
return 0;
return encode_attr_time(xdr,time);
}
-static __be32 encode_attr_mtime(struct xdr_stream *xdr, const uint32_t *bitmap, const struct timespec *time)
+static __be32 encode_attr_mtime(struct xdr_stream *xdr, const uint32_t *bitmap, const struct timespec64 *time)
{
if (!(bitmap[1] & FATTR4_WORD1_TIME_MODIFY))
return 0;
diff --git a/fs/nfs/client.c b/fs/nfs/client.c
index 30838304a0bf..02110a30a49e 100644
--- a/fs/nfs/client.c
+++ b/fs/nfs/client.c
@@ -312,6 +312,12 @@ again:
/* Match nfsv4 minorversion */
if (clp->cl_minorversion != data->minorversion)
continue;
+
+ /* Match request for a dedicated DS */
+ if (test_bit(NFS_CS_DS, &data->init_flags) !=
+ test_bit(NFS_CS_DS, &clp->cl_flags))
+ continue;
+
/* Match the full socket address */
if (!rpc_cmp_addr_port(sap, clap))
/* Match all xprt_switch full socket addresses */
@@ -515,6 +521,10 @@ int nfs_create_rpc_client(struct nfs_client *clp,
args.flags |= RPC_CLNT_CREATE_NONPRIVPORT;
if (test_bit(NFS_CS_INFINITE_SLOTS, &clp->cl_flags))
args.flags |= RPC_CLNT_CREATE_INFINITE_SLOTS;
+ if (test_bit(NFS_CS_NOPING, &clp->cl_flags))
+ args.flags |= RPC_CLNT_CREATE_NOPING;
+ if (test_bit(NFS_CS_REUSEPORT, &clp->cl_flags))
+ args.flags |= RPC_CLNT_CREATE_REUSEPORT;
if (!IS_ERR(clp->cl_rpcclient))
return 0;
@@ -662,6 +672,7 @@ static int nfs_init_server(struct nfs_server *server,
.timeparms = &timeparms,
.cred = server->cred,
.nconnect = data->nfs_server.nconnect,
+ .init_flags = (1UL << NFS_CS_REUSEPORT),
};
struct nfs_client *clp;
int error;
diff --git a/fs/nfs/delegation.c b/fs/nfs/delegation.c
index 071b90a45933..fe57b2b5314a 100644
--- a/fs/nfs/delegation.c
+++ b/fs/nfs/delegation.c
@@ -53,6 +53,16 @@ nfs4_is_valid_delegation(const struct nfs_delegation *delegation,
return false;
}
+struct nfs_delegation *nfs4_get_valid_delegation(const struct inode *inode)
+{
+ struct nfs_delegation *delegation;
+
+ delegation = rcu_dereference(NFS_I(inode)->delegation);
+ if (nfs4_is_valid_delegation(delegation, 0))
+ return delegation;
+ return NULL;
+}
+
static int
nfs4_do_check_delegation(struct inode *inode, fmode_t flags, bool mark)
{
@@ -189,7 +199,7 @@ void nfs_inode_reclaim_delegation(struct inode *inode, const struct cred *cred,
delegation = rcu_dereference(NFS_I(inode)->delegation);
if (delegation != NULL) {
spin_lock(&delegation->lock);
- if (delegation->inode != NULL) {
+ if (nfs4_is_valid_delegation(delegation, 0)) {
nfs4_stateid_copy(&delegation->stateid, stateid);
delegation->type = type;
delegation->pagemod_limit = pagemod_limit;
@@ -219,7 +229,6 @@ static int nfs_do_return_delegation(struct inode *inode, struct nfs_delegation *
delegation->cred,
&delegation->stateid,
issync);
- nfs_free_delegation(delegation);
return res;
}
@@ -288,7 +297,10 @@ nfs_detach_delegation_locked(struct nfs_inode *nfsi,
return NULL;
spin_lock(&delegation->lock);
- set_bit(NFS_DELEGATION_RETURNING, &delegation->flags);
+ if (!delegation->inode) {
+ spin_unlock(&delegation->lock);
+ return NULL;
+ }
list_del_rcu(&delegation->super_list);
delegation->inode = NULL;
rcu_assign_pointer(nfsi->delegation, NULL);
@@ -315,10 +327,12 @@ nfs_inode_detach_delegation(struct inode *inode)
struct nfs_server *server = NFS_SERVER(inode);
struct nfs_delegation *delegation;
- delegation = nfs_start_delegation_return(nfsi);
- if (delegation == NULL)
- return NULL;
- return nfs_detach_delegation(nfsi, delegation, server);
+ rcu_read_lock();
+ delegation = rcu_dereference(nfsi->delegation);
+ if (delegation != NULL)
+ delegation = nfs_detach_delegation(nfsi, delegation, server);
+ rcu_read_unlock();
+ return delegation;
}
static void
@@ -329,6 +343,7 @@ nfs_update_inplace_delegation(struct nfs_delegation *delegation,
delegation->stateid.seqid = update->stateid.seqid;
smp_wmb();
delegation->type = update->type;
+ clear_bit(NFS_DELEGATION_REVOKED, &delegation->flags);
}
}
@@ -369,14 +384,18 @@ int nfs_inode_set_delegation(struct inode *inode, const struct cred *cred,
spin_lock(&clp->cl_lock);
old_delegation = rcu_dereference_protected(nfsi->delegation,
lockdep_is_held(&clp->cl_lock));
- if (old_delegation != NULL) {
- /* Is this an update of the existing delegation? */
- if (nfs4_stateid_match_other(&old_delegation->stateid,
- &delegation->stateid)) {
- nfs_update_inplace_delegation(old_delegation,
- delegation);
- goto out;
- }
+ if (old_delegation == NULL)
+ goto add_new;
+ /* Is this an update of the existing delegation? */
+ if (nfs4_stateid_match_other(&old_delegation->stateid,
+ &delegation->stateid)) {
+ spin_lock(&old_delegation->lock);
+ nfs_update_inplace_delegation(old_delegation,
+ delegation);
+ spin_unlock(&old_delegation->lock);
+ goto out;
+ }
+ if (!test_bit(NFS_DELEGATION_REVOKED, &old_delegation->flags)) {
/*
* Deal with broken servers that hand out two
* delegations for the same file.
@@ -395,11 +414,11 @@ int nfs_inode_set_delegation(struct inode *inode, const struct cred *cred,
if (test_and_set_bit(NFS_DELEGATION_RETURNING,
&old_delegation->flags))
goto out;
- freeme = nfs_detach_delegation_locked(nfsi,
- old_delegation, clp);
- if (freeme == NULL)
- goto out;
}
+ freeme = nfs_detach_delegation_locked(nfsi, old_delegation, clp);
+ if (freeme == NULL)
+ goto out;
+add_new:
list_add_tail_rcu(&delegation->super_list, &server->delegations);
rcu_assign_pointer(nfsi->delegation, delegation);
delegation = NULL;
@@ -414,8 +433,10 @@ out:
spin_unlock(&clp->cl_lock);
if (delegation != NULL)
nfs_free_delegation(delegation);
- if (freeme != NULL)
+ if (freeme != NULL) {
nfs_do_return_delegation(inode, freeme, 0);
+ nfs_free_delegation(freeme);
+ }
return status;
}
@@ -425,7 +446,6 @@ out:
static int nfs_end_delegation_return(struct inode *inode, struct nfs_delegation *delegation, int issync)
{
struct nfs_client *clp = NFS_SERVER(inode)->nfs_client;
- struct nfs_inode *nfsi = NFS_I(inode);
int err = 0;
if (delegation == NULL)
@@ -447,8 +467,6 @@ static int nfs_end_delegation_return(struct inode *inode, struct nfs_delegation
nfs_abort_delegation_return(delegation, clp);
goto out;
}
- if (!nfs_detach_delegation(nfsi, delegation, NFS_SERVER(inode)))
- goto out;
err = nfs_do_return_delegation(inode, delegation, issync);
out:
@@ -459,8 +477,6 @@ static bool nfs_delegation_need_return(struct nfs_delegation *delegation)
{
bool ret = false;
- if (test_bit(NFS_DELEGATION_RETURNING, &delegation->flags))
- goto out;
if (test_and_clear_bit(NFS_DELEGATION_RETURN, &delegation->flags))
ret = true;
if (test_and_clear_bit(NFS_DELEGATION_RETURN_IF_CLOSED, &delegation->flags) && !ret) {
@@ -472,7 +488,10 @@ static bool nfs_delegation_need_return(struct nfs_delegation *delegation)
ret = true;
spin_unlock(&delegation->lock);
}
-out:
+ if (test_bit(NFS_DELEGATION_RETURNING, &delegation->flags) ||
+ test_bit(NFS_DELEGATION_REVOKED, &delegation->flags))
+ ret = false;
+
return ret;
}
@@ -575,19 +594,23 @@ restart:
}
/**
- * nfs_inode_return_delegation_noreclaim - return delegation, don't reclaim opens
+ * nfs_inode_evict_delegation - return delegation, don't reclaim opens
* @inode: inode to process
*
* Does not protect against delegation reclaims, therefore really only safe
- * to be called from nfs4_clear_inode().
+ * to be called from nfs4_clear_inode(). Guaranteed to always free
+ * the delegation structure.
*/
-void nfs_inode_return_delegation_noreclaim(struct inode *inode)
+void nfs_inode_evict_delegation(struct inode *inode)
{
struct nfs_delegation *delegation;
delegation = nfs_inode_detach_delegation(inode);
- if (delegation != NULL)
+ if (delegation != NULL) {
+ set_bit(NFS_DELEGATION_INODE_FREEING, &delegation->flags);
nfs_do_return_delegation(inode, delegation, 1);
+ nfs_free_delegation(delegation);
+ }
}
/**
@@ -623,10 +646,18 @@ int nfs4_inode_return_delegation(struct inode *inode)
*/
int nfs4_inode_make_writeable(struct inode *inode)
{
- if (!nfs4_has_session(NFS_SERVER(inode)->nfs_client) ||
- !nfs4_check_delegation(inode, FMODE_WRITE))
- return nfs4_inode_return_delegation(inode);
- return 0;
+ struct nfs_delegation *delegation;
+
+ rcu_read_lock();
+ delegation = nfs4_get_valid_delegation(inode);
+ if (delegation == NULL ||
+ (nfs4_has_session(NFS_SERVER(inode)->nfs_client) &&
+ (delegation->type & FMODE_WRITE))) {
+ rcu_read_unlock();
+ return 0;
+ }
+ rcu_read_unlock();
+ return nfs4_inode_return_delegation(inode);
}
static void nfs_mark_return_if_closed_delegation(struct nfs_server *server,
@@ -734,10 +765,9 @@ static void nfs_mark_delegation_revoked(struct nfs_server *server,
{
set_bit(NFS_DELEGATION_REVOKED, &delegation->flags);
delegation->stateid.type = NFS4_INVALID_STATEID_TYPE;
- nfs_mark_return_delegation(server, delegation);
}
-static bool nfs_revoke_delegation(struct inode *inode,
+static void nfs_revoke_delegation(struct inode *inode,
const nfs4_stateid *stateid)
{
struct nfs_delegation *delegation;
@@ -751,29 +781,69 @@ static bool nfs_revoke_delegation(struct inode *inode,
if (stateid == NULL) {
nfs4_stateid_copy(&tmp, &delegation->stateid);
stateid = &tmp;
- } else if (!nfs4_stateid_match(stateid, &delegation->stateid))
- goto out;
+ } else {
+ if (!nfs4_stateid_match_other(stateid, &delegation->stateid))
+ goto out;
+ spin_lock(&delegation->lock);
+ if (stateid->seqid) {
+ if (nfs4_stateid_is_newer(&delegation->stateid, stateid)) {
+ spin_unlock(&delegation->lock);
+ goto out;
+ }
+ delegation->stateid.seqid = stateid->seqid;
+ }
+ spin_unlock(&delegation->lock);
+ }
nfs_mark_delegation_revoked(NFS_SERVER(inode), delegation);
ret = true;
out:
rcu_read_unlock();
if (ret)
nfs_inode_find_state_and_recover(inode, stateid);
- return ret;
}
void nfs_remove_bad_delegation(struct inode *inode,
const nfs4_stateid *stateid)
{
+ nfs_revoke_delegation(inode, stateid);
+}
+EXPORT_SYMBOL_GPL(nfs_remove_bad_delegation);
+
+void nfs_delegation_mark_returned(struct inode *inode,
+ const nfs4_stateid *stateid)
+{
struct nfs_delegation *delegation;
- if (!nfs_revoke_delegation(inode, stateid))
+ if (!inode)
return;
- delegation = nfs_inode_detach_delegation(inode);
- if (delegation)
- nfs_free_delegation(delegation);
+
+ rcu_read_lock();
+ delegation = rcu_dereference(NFS_I(inode)->delegation);
+ if (!delegation)
+ goto out_rcu_unlock;
+
+ spin_lock(&delegation->lock);
+ if (!nfs4_stateid_match_other(stateid, &delegation->stateid))
+ goto out_spin_unlock;
+ if (stateid->seqid) {
+ /* If delegation->stateid is newer, dont mark as returned */
+ if (nfs4_stateid_is_newer(&delegation->stateid, stateid))
+ goto out_clear_returning;
+ if (delegation->stateid.seqid != stateid->seqid)
+ delegation->stateid.seqid = stateid->seqid;
+ }
+
+ nfs_mark_delegation_revoked(NFS_SERVER(inode), delegation);
+
+out_clear_returning:
+ clear_bit(NFS_DELEGATION_RETURNING, &delegation->flags);
+out_spin_unlock:
+ spin_unlock(&delegation->lock);
+out_rcu_unlock:
+ rcu_read_unlock();
+
+ nfs_inode_find_state_and_recover(inode, stateid);
}
-EXPORT_SYMBOL_GPL(nfs_remove_bad_delegation);
/**
* nfs_expire_unused_delegation_types
@@ -830,7 +900,7 @@ int nfs_async_inode_return_delegation(struct inode *inode,
struct nfs_delegation *delegation;
rcu_read_lock();
- delegation = rcu_dereference(NFS_I(inode)->delegation);
+ delegation = nfs4_get_valid_delegation(inode);
if (delegation == NULL)
goto out_enoent;
if (stateid != NULL &&
@@ -856,6 +926,7 @@ nfs_delegation_find_inode_server(struct nfs_server *server,
list_for_each_entry_rcu(delegation, &server->delegations, super_list) {
spin_lock(&delegation->lock);
if (delegation->inode != NULL &&
+ !test_bit(NFS_DELEGATION_REVOKED, &delegation->flags) &&
nfs_compare_fh(fhandle, &NFS_I(delegation->inode)->fh) == 0) {
freeme = igrab(delegation->inode);
if (freeme && nfs_sb_active(freeme->i_sb))
@@ -1130,7 +1201,8 @@ void nfs_inode_find_delegation_state_and_recover(struct inode *inode,
rcu_read_lock();
delegation = rcu_dereference(NFS_I(inode)->delegation);
if (delegation &&
- nfs4_stateid_match_other(&delegation->stateid, stateid)) {
+ nfs4_stateid_match_or_older(&delegation->stateid, stateid) &&
+ !test_bit(NFS_DELEGATION_REVOKED, &delegation->flags)) {
nfs_mark_test_expired_delegation(NFS_SERVER(inode), delegation);
found = true;
}
@@ -1179,9 +1251,11 @@ bool nfs4_refresh_delegation_stateid(nfs4_stateid *dst, struct inode *inode)
rcu_read_lock();
delegation = rcu_dereference(NFS_I(inode)->delegation);
if (delegation != NULL &&
- nfs4_stateid_match_other(dst, &delegation->stateid)) {
+ nfs4_stateid_match_other(dst, &delegation->stateid) &&
+ nfs4_stateid_is_newer(&delegation->stateid, dst) &&
+ !test_bit(NFS_DELEGATION_REVOKED, &delegation->flags)) {
dst->seqid = delegation->stateid.seqid;
- return ret;
+ ret = true;
}
rcu_read_unlock();
out:
diff --git a/fs/nfs/delegation.h b/fs/nfs/delegation.h
index 9eb87ae4c982..15d3484be028 100644
--- a/fs/nfs/delegation.h
+++ b/fs/nfs/delegation.h
@@ -43,7 +43,7 @@ void nfs_inode_reclaim_delegation(struct inode *inode, const struct cred *cred,
fmode_t type, const nfs4_stateid *stateid, unsigned long pagemod_limit);
int nfs4_inode_return_delegation(struct inode *inode);
int nfs_async_inode_return_delegation(struct inode *inode, const nfs4_stateid *stateid);
-void nfs_inode_return_delegation_noreclaim(struct inode *inode);
+void nfs_inode_evict_delegation(struct inode *inode);
struct inode *nfs_delegation_find_inode(struct nfs_client *clp, const struct nfs_fh *fhandle);
void nfs_server_return_all_delegations(struct nfs_server *);
@@ -53,6 +53,7 @@ void nfs_expire_unreferenced_delegations(struct nfs_client *clp);
int nfs_client_return_marked_delegations(struct nfs_client *clp);
int nfs_delegations_present(struct nfs_client *clp);
void nfs_remove_bad_delegation(struct inode *inode, const nfs4_stateid *stateid);
+void nfs_delegation_mark_returned(struct inode *inode, const nfs4_stateid *stateid);
void nfs_delegation_mark_reclaim(struct nfs_client *clp);
void nfs_delegation_reap_unclaimed(struct nfs_client *clp);
@@ -68,6 +69,7 @@ int nfs4_lock_delegation_recall(struct file_lock *fl, struct nfs4_state *state,
bool nfs4_copy_delegation_stateid(struct inode *inode, fmode_t flags, nfs4_stateid *dst, const struct cred **cred);
bool nfs4_refresh_delegation_stateid(nfs4_stateid *dst, struct inode *inode);
+struct nfs_delegation *nfs4_get_valid_delegation(const struct inode *inode);
void nfs_mark_delegation_referenced(struct nfs_delegation *delegation);
int nfs4_have_delegation(struct inode *inode, fmode_t flags);
int nfs4_check_delegation(struct inode *inode, fmode_t flags);
diff --git a/fs/nfs/export.c b/fs/nfs/export.c
index deecb67638aa..3430d6891e89 100644
--- a/fs/nfs/export.c
+++ b/fs/nfs/export.c
@@ -105,6 +105,7 @@ nfs_fh_to_dentry(struct super_block *sb, struct fid *fid,
ret = rpc_ops->getattr(NFS_SB(sb), server_fh, fattr, label, 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;
}
diff --git a/fs/nfs/file.c b/fs/nfs/file.c
index 95dc90570786..8eb731d9be3e 100644
--- a/fs/nfs/file.c
+++ b/fs/nfs/file.c
@@ -649,7 +649,7 @@ out:
out_swapfile:
printk(KERN_INFO "NFS: attempt to write to active swap file!\n");
- return -EBUSY;
+ return -ETXTBSY;
}
EXPORT_SYMBOL_GPL(nfs_file_write);
diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c
index 2a03bfeec10a..b0b4b9f303fd 100644
--- a/fs/nfs/inode.c
+++ b/fs/nfs/inode.c
@@ -504,15 +504,15 @@ nfs_fhget(struct super_block *sb, struct nfs_fh *fh, struct nfs_fattr *fattr, st
nfsi->read_cache_jiffies = fattr->time_start;
nfsi->attr_gencount = fattr->gencount;
if (fattr->valid & NFS_ATTR_FATTR_ATIME)
- inode->i_atime = timespec_to_timespec64(fattr->atime);
+ inode->i_atime = fattr->atime;
else if (nfs_server_capable(inode, NFS_CAP_ATIME))
nfs_set_cache_invalid(inode, NFS_INO_INVALID_ATIME);
if (fattr->valid & NFS_ATTR_FATTR_MTIME)
- inode->i_mtime = timespec_to_timespec64(fattr->mtime);
+ inode->i_mtime = fattr->mtime;
else if (nfs_server_capable(inode, NFS_CAP_MTIME))
nfs_set_cache_invalid(inode, NFS_INO_INVALID_MTIME);
if (fattr->valid & NFS_ATTR_FATTR_CTIME)
- inode->i_ctime = timespec_to_timespec64(fattr->ctime);
+ inode->i_ctime = fattr->ctime;
else if (nfs_server_capable(inode, NFS_CAP_CTIME))
nfs_set_cache_invalid(inode, NFS_INO_INVALID_CTIME);
if (fattr->valid & NFS_ATTR_FATTR_CHANGE)
@@ -698,7 +698,7 @@ void nfs_setattr_update_inode(struct inode *inode, struct iattr *attr,
if ((attr->ia_valid & ATTR_GID) != 0)
inode->i_gid = attr->ia_gid;
if (fattr->valid & NFS_ATTR_FATTR_CTIME)
- inode->i_ctime = timespec_to_timespec64(fattr->ctime);
+ inode->i_ctime = fattr->ctime;
else
nfs_set_cache_invalid(inode, NFS_INO_INVALID_CHANGE
| NFS_INO_INVALID_CTIME);
@@ -709,14 +709,14 @@ void nfs_setattr_update_inode(struct inode *inode, struct iattr *attr,
NFS_I(inode)->cache_validity &= ~(NFS_INO_INVALID_ATIME
| NFS_INO_INVALID_CTIME);
if (fattr->valid & NFS_ATTR_FATTR_ATIME)
- inode->i_atime = timespec_to_timespec64(fattr->atime);
+ inode->i_atime = fattr->atime;
else if (attr->ia_valid & ATTR_ATIME_SET)
inode->i_atime = attr->ia_atime;
else
nfs_set_cache_invalid(inode, NFS_INO_INVALID_ATIME);
if (fattr->valid & NFS_ATTR_FATTR_CTIME)
- inode->i_ctime = timespec_to_timespec64(fattr->ctime);
+ inode->i_ctime = fattr->ctime;
else
nfs_set_cache_invalid(inode, NFS_INO_INVALID_CHANGE
| NFS_INO_INVALID_CTIME);
@@ -725,14 +725,14 @@ void nfs_setattr_update_inode(struct inode *inode, struct iattr *attr,
NFS_I(inode)->cache_validity &= ~(NFS_INO_INVALID_MTIME
| NFS_INO_INVALID_CTIME);
if (fattr->valid & NFS_ATTR_FATTR_MTIME)
- inode->i_mtime = timespec_to_timespec64(fattr->mtime);
+ inode->i_mtime = fattr->mtime;
else if (attr->ia_valid & ATTR_MTIME_SET)
inode->i_mtime = attr->ia_mtime;
else
nfs_set_cache_invalid(inode, NFS_INO_INVALID_MTIME);
if (fattr->valid & NFS_ATTR_FATTR_CTIME)
- inode->i_ctime = timespec_to_timespec64(fattr->ctime);
+ inode->i_ctime = fattr->ctime;
else
nfs_set_cache_invalid(inode, NFS_INO_INVALID_CHANGE
| NFS_INO_INVALID_CTIME);
@@ -1351,7 +1351,7 @@ static bool nfs_file_has_buffered_writers(struct nfs_inode *nfsi)
static void nfs_wcc_update_inode(struct inode *inode, struct nfs_fattr *fattr)
{
- struct timespec ts;
+ struct timespec64 ts;
if ((fattr->valid & NFS_ATTR_FATTR_PRECHANGE)
&& (fattr->valid & NFS_ATTR_FATTR_CHANGE)
@@ -1361,18 +1361,18 @@ static void nfs_wcc_update_inode(struct inode *inode, struct nfs_fattr *fattr)
nfs_set_cache_invalid(inode, NFS_INO_INVALID_DATA);
}
/* If we have atomic WCC data, we may update some attributes */
- ts = timespec64_to_timespec(inode->i_ctime);
+ ts = inode->i_ctime;
if ((fattr->valid & NFS_ATTR_FATTR_PRECTIME)
&& (fattr->valid & NFS_ATTR_FATTR_CTIME)
- && timespec_equal(&ts, &fattr->pre_ctime)) {
- inode->i_ctime = timespec_to_timespec64(fattr->ctime);
+ && timespec64_equal(&ts, &fattr->pre_ctime)) {
+ inode->i_ctime = fattr->ctime;
}
- ts = timespec64_to_timespec(inode->i_mtime);
+ ts = inode->i_mtime;
if ((fattr->valid & NFS_ATTR_FATTR_PREMTIME)
&& (fattr->valid & NFS_ATTR_FATTR_MTIME)
- && timespec_equal(&ts, &fattr->pre_mtime)) {
- inode->i_mtime = timespec_to_timespec64(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);
}
@@ -1398,7 +1398,7 @@ static int nfs_check_inode_attributes(struct inode *inode, struct nfs_fattr *fat
struct nfs_inode *nfsi = NFS_I(inode);
loff_t cur_size, new_isize;
unsigned long invalid = 0;
- struct timespec ts;
+ struct timespec64 ts;
if (NFS_PROTO(inode)->have_delegation(inode, FMODE_READ))
return 0;
@@ -1425,12 +1425,12 @@ static int nfs_check_inode_attributes(struct inode *inode, struct nfs_fattr *fat
invalid |= NFS_INO_INVALID_CHANGE
| NFS_INO_REVAL_PAGECACHE;
- ts = timespec64_to_timespec(inode->i_mtime);
- if ((fattr->valid & NFS_ATTR_FATTR_MTIME) && !timespec_equal(&ts, &fattr->mtime))
+ ts = inode->i_mtime;
+ if ((fattr->valid & NFS_ATTR_FATTR_MTIME) && !timespec64_equal(&ts, &fattr->mtime))
invalid |= NFS_INO_INVALID_MTIME;
- ts = timespec64_to_timespec(inode->i_ctime);
- if ((fattr->valid & NFS_ATTR_FATTR_CTIME) && !timespec_equal(&ts, &fattr->ctime))
+ ts = inode->i_ctime;
+ if ((fattr->valid & NFS_ATTR_FATTR_CTIME) && !timespec64_equal(&ts, &fattr->ctime))
invalid |= NFS_INO_INVALID_CTIME;
if (fattr->valid & NFS_ATTR_FATTR_SIZE) {
@@ -1460,8 +1460,8 @@ static int nfs_check_inode_attributes(struct inode *inode, struct nfs_fattr *fat
if ((fattr->valid & NFS_ATTR_FATTR_NLINK) && inode->i_nlink != fattr->nlink)
invalid |= NFS_INO_INVALID_OTHER;
- ts = timespec64_to_timespec(inode->i_atime);
- if ((fattr->valid & NFS_ATTR_FATTR_ATIME) && !timespec_equal(&ts, &fattr->atime))
+ ts = inode->i_atime;
+ if ((fattr->valid & NFS_ATTR_FATTR_ATIME) && !timespec64_equal(&ts, &fattr->atime))
invalid |= NFS_INO_INVALID_ATIME;
if (invalid != 0)
@@ -1733,12 +1733,12 @@ int nfs_post_op_update_inode_force_wcc_locked(struct inode *inode, struct nfs_fa
}
if ((fattr->valid & NFS_ATTR_FATTR_CTIME) != 0 &&
(fattr->valid & NFS_ATTR_FATTR_PRECTIME) == 0) {
- fattr->pre_ctime = timespec64_to_timespec(inode->i_ctime);
+ fattr->pre_ctime = inode->i_ctime;
fattr->valid |= NFS_ATTR_FATTR_PRECTIME;
}
if ((fattr->valid & NFS_ATTR_FATTR_MTIME) != 0 &&
(fattr->valid & NFS_ATTR_FATTR_PREMTIME) == 0) {
- fattr->pre_mtime = timespec64_to_timespec(inode->i_mtime);
+ fattr->pre_mtime = inode->i_mtime;
fattr->valid |= NFS_ATTR_FATTR_PREMTIME;
}
if ((fattr->valid & NFS_ATTR_FATTR_SIZE) != 0 &&
@@ -1899,7 +1899,7 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
}
if (fattr->valid & NFS_ATTR_FATTR_MTIME) {
- inode->i_mtime = timespec_to_timespec64(fattr->mtime);
+ inode->i_mtime = fattr->mtime;
} else if (server->caps & NFS_CAP_MTIME) {
nfsi->cache_validity |= save_cache_validity &
(NFS_INO_INVALID_MTIME
@@ -1908,7 +1908,7 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
}
if (fattr->valid & NFS_ATTR_FATTR_CTIME) {
- inode->i_ctime = timespec_to_timespec64(fattr->ctime);
+ inode->i_ctime = fattr->ctime;
} else if (server->caps & NFS_CAP_CTIME) {
nfsi->cache_validity |= save_cache_validity &
(NFS_INO_INVALID_CTIME
@@ -1946,7 +1946,7 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
if (fattr->valid & NFS_ATTR_FATTR_ATIME)
- inode->i_atime = timespec_to_timespec64(fattr->atime);
+ inode->i_atime = fattr->atime;
else if (server->caps & NFS_CAP_ATIME) {
nfsi->cache_validity |= save_cache_validity &
(NFS_INO_INVALID_ATIME
diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h
index 447a3c17fa8e..24a65da58aa9 100644
--- a/fs/nfs/internal.h
+++ b/fs/nfs/internal.h
@@ -713,7 +713,7 @@ unsigned int nfs_page_array_len(unsigned int base, size_t len)
* 1024*1024*1024.
*/
static inline
-u64 nfs_timespec_to_change_attr(const struct timespec *ts)
+u64 nfs_timespec_to_change_attr(const struct timespec64 *ts)
{
return ((u64)ts->tv_sec << 30) + ts->tv_nsec;
}
diff --git a/fs/nfs/namespace.c b/fs/nfs/namespace.c
index 9287eb666322..5e0e9d29f5c5 100644
--- a/fs/nfs/namespace.c
+++ b/fs/nfs/namespace.c
@@ -157,6 +157,9 @@ struct vfsmount *nfs_d_automount(struct path *path)
if (IS_ERR(mnt))
goto out;
+ if (nfs_mountpoint_expiry_timeout < 0)
+ goto out;
+
mntget(mnt); /* prevent immediate expiration */
mnt_set_expiry(mnt, &nfs_automount_list);
schedule_delayed_work(&nfs_automount_task, nfs_mountpoint_expiry_timeout);
diff --git a/fs/nfs/nfs2xdr.c b/fs/nfs/nfs2xdr.c
index cbc17a203248..d94c7abdf25a 100644
--- a/fs/nfs/nfs2xdr.c
+++ b/fs/nfs/nfs2xdr.c
@@ -209,9 +209,9 @@ static int decode_fhandle(struct xdr_stream *xdr, struct nfs_fh *fh)
* unsigned int useconds;
* };
*/
-static __be32 *xdr_encode_time(__be32 *p, const struct timespec *timep)
+static __be32 *xdr_encode_time(__be32 *p, const struct timespec64 *timep)
{
- *p++ = cpu_to_be32(timep->tv_sec);
+ *p++ = cpu_to_be32((u32)timep->tv_sec);
if (timep->tv_nsec != 0)
*p++ = cpu_to_be32(timep->tv_nsec / NSEC_PER_USEC);
else
@@ -227,14 +227,14 @@ static __be32 *xdr_encode_time(__be32 *p, const struct timespec *timep)
* Illustrated" by Brent Callaghan, Addison-Wesley, ISBN 0-201-32750-5.
*/
static __be32 *xdr_encode_current_server_time(__be32 *p,
- const struct timespec *timep)
+ const struct timespec64 *timep)
{
*p++ = cpu_to_be32(timep->tv_sec);
*p++ = cpu_to_be32(1000000);
return p;
}
-static __be32 *xdr_decode_time(__be32 *p, struct timespec *timep)
+static __be32 *xdr_decode_time(__be32 *p, struct timespec64 *timep)
{
timep->tv_sec = be32_to_cpup(p++);
timep->tv_nsec = be32_to_cpup(p++) * NSEC_PER_USEC;
@@ -339,7 +339,6 @@ static __be32 *xdr_time_not_set(__be32 *p)
static void encode_sattr(struct xdr_stream *xdr, const struct iattr *attr,
struct user_namespace *userns)
{
- struct timespec ts;
__be32 *p;
p = xdr_reserve_space(xdr, NFS_sattr_sz << 2);
@@ -362,19 +361,15 @@ static void encode_sattr(struct xdr_stream *xdr, const struct iattr *attr,
*p++ = cpu_to_be32(NFS2_SATTR_NOT_SET);
if (attr->ia_valid & ATTR_ATIME_SET) {
- ts = timespec64_to_timespec(attr->ia_atime);
- p = xdr_encode_time(p, &ts);
+ p = xdr_encode_time(p, &attr->ia_atime);
} else if (attr->ia_valid & ATTR_ATIME) {
- ts = timespec64_to_timespec(attr->ia_atime);
- p = xdr_encode_current_server_time(p, &ts);
+ p = xdr_encode_current_server_time(p, &attr->ia_atime);
} else
p = xdr_time_not_set(p);
if (attr->ia_valid & ATTR_MTIME_SET) {
- ts = timespec64_to_timespec(attr->ia_atime);
- xdr_encode_time(p, &ts);
+ xdr_encode_time(p, &attr->ia_mtime);
} else if (attr->ia_valid & ATTR_MTIME) {
- ts = timespec64_to_timespec(attr->ia_mtime);
- xdr_encode_current_server_time(p, &ts);
+ xdr_encode_current_server_time(p, &attr->ia_mtime);
} else
xdr_time_not_set(p);
}
diff --git a/fs/nfs/nfs3client.c b/fs/nfs/nfs3client.c
index 148ceb74d27c..223904bc40a7 100644
--- a/fs/nfs/nfs3client.c
+++ b/fs/nfs/nfs3client.c
@@ -106,7 +106,10 @@ struct nfs_client *nfs3_set_ds_client(struct nfs_server *mds_srv,
cl_init.nconnect = mds_clp->cl_nconnect;
if (mds_srv->flags & NFS_MOUNT_NORESVPORT)
- set_bit(NFS_CS_NORESVPORT, &cl_init.init_flags);
+ __set_bit(NFS_CS_NORESVPORT, &cl_init.init_flags);
+
+ __set_bit(NFS_CS_NOPING, &cl_init.init_flags);
+ __set_bit(NFS_CS_DS, &cl_init.init_flags);
/* Use the MDS nfs_client cl_ipaddr. */
nfs_init_timeout_values(&ds_timeout, ds_proto, ds_timeo, ds_retrans);
diff --git a/fs/nfs/nfs3xdr.c b/fs/nfs/nfs3xdr.c
index 602767850b36..927eb680f161 100644
--- a/fs/nfs/nfs3xdr.c
+++ b/fs/nfs/nfs3xdr.c
@@ -456,14 +456,14 @@ static void zero_nfs_fh3(struct nfs_fh *fh)
* uint32 nseconds;
* };
*/
-static __be32 *xdr_encode_nfstime3(__be32 *p, const struct timespec *timep)
+static __be32 *xdr_encode_nfstime3(__be32 *p, const struct timespec64 *timep)
{
- *p++ = cpu_to_be32(timep->tv_sec);
+ *p++ = cpu_to_be32((u32)timep->tv_sec);
*p++ = cpu_to_be32(timep->tv_nsec);
return p;
}
-static __be32 *xdr_decode_nfstime3(__be32 *p, struct timespec *timep)
+static __be32 *xdr_decode_nfstime3(__be32 *p, struct timespec64 *timep)
{
timep->tv_sec = be32_to_cpup(p++);
timep->tv_nsec = be32_to_cpup(p++);
@@ -533,7 +533,6 @@ static __be32 *xdr_decode_nfstime3(__be32 *p, struct timespec *timep)
static void encode_sattr3(struct xdr_stream *xdr, const struct iattr *attr,
struct user_namespace *userns)
{
- struct timespec ts;
u32 nbytes;
__be32 *p;
@@ -583,10 +582,8 @@ static void encode_sattr3(struct xdr_stream *xdr, const struct iattr *attr,
*p++ = xdr_zero;
if (attr->ia_valid & ATTR_ATIME_SET) {
- struct timespec ts;
*p++ = xdr_two;
- ts = timespec64_to_timespec(attr->ia_atime);
- p = xdr_encode_nfstime3(p, &ts);
+ p = xdr_encode_nfstime3(p, &attr->ia_atime);
} else if (attr->ia_valid & ATTR_ATIME) {
*p++ = xdr_one;
} else
@@ -594,8 +591,7 @@ static void encode_sattr3(struct xdr_stream *xdr, const struct iattr *attr,
if (attr->ia_valid & ATTR_MTIME_SET) {
*p++ = xdr_two;
- ts = timespec64_to_timespec(attr->ia_mtime);
- xdr_encode_nfstime3(p, &ts);
+ xdr_encode_nfstime3(p, &attr->ia_mtime);
} else if (attr->ia_valid & ATTR_MTIME) {
*p = xdr_one;
} else
diff --git a/fs/nfs/nfs42.h b/fs/nfs/nfs42.h
index 901cca7542f9..c891af949886 100644
--- a/fs/nfs/nfs42.h
+++ b/fs/nfs/nfs42.h
@@ -13,8 +13,10 @@
#define PNFS_LAYOUTSTATS_MAXDEV (4)
/* nfs4.2proc.c */
+#ifdef CONFIG_NFS_V4_2
int nfs42_proc_allocate(struct file *, loff_t, loff_t);
-ssize_t nfs42_proc_copy(struct file *, loff_t, struct file *, loff_t, size_t);
+ssize_t nfs42_proc_copy(struct file *, loff_t, struct file *, loff_t, size_t,
+ struct nl4_server *, nfs4_stateid *, bool);
int nfs42_proc_deallocate(struct file *, loff_t, loff_t);
loff_t nfs42_proc_llseek(struct file *, loff_t, int);
int nfs42_proc_layoutstats_generic(struct nfs_server *,
@@ -23,5 +25,16 @@ int nfs42_proc_clone(struct file *, struct file *, loff_t, loff_t, loff_t);
int nfs42_proc_layouterror(struct pnfs_layout_segment *lseg,
const struct nfs42_layout_error *errors,
size_t n);
+int nfs42_proc_copy_notify(struct file *, struct file *,
+ struct nfs42_copy_notify_res *);
+static inline bool nfs42_files_from_same_server(struct file *in,
+ struct file *out)
+{
+ struct nfs_client *c_in = (NFS_SERVER(file_inode(in)))->nfs_client;
+ struct nfs_client *c_out = (NFS_SERVER(file_inode(out)))->nfs_client;
+ return nfs4_check_serverowner_major_id(c_in->cl_serverowner,
+ c_out->cl_serverowner);
+}
+#endif /* CONFIG_NFS_V4_2 */
#endif /* __LINUX_FS_NFS_NFS4_2_H */
diff --git a/fs/nfs/nfs42proc.c b/fs/nfs/nfs42proc.c
index 5196bfa7894d..1fe83e0f663e 100644
--- a/fs/nfs/nfs42proc.c
+++ b/fs/nfs/nfs42proc.c
@@ -3,6 +3,7 @@
* Copyright (c) 2014 Anna Schumaker <Anna.Schumaker@Netapp.com>
*/
#include <linux/fs.h>
+#include <linux/sunrpc/addr.h>
#include <linux/sunrpc/sched.h>
#include <linux/nfs.h>
#include <linux/nfs3.h>
@@ -15,10 +16,30 @@
#include "pnfs.h"
#include "nfs4session.h"
#include "internal.h"
+#include "delegation.h"
#define NFSDBG_FACILITY NFSDBG_PROC
static int nfs42_do_offload_cancel_async(struct file *dst, nfs4_stateid *std);
+static void nfs42_set_netaddr(struct file *filep, struct nfs42_netaddr *naddr)
+{
+ struct nfs_client *clp = (NFS_SERVER(file_inode(filep)))->nfs_client;
+ unsigned short port = 2049;
+
+ rcu_read_lock();
+ naddr->netid_len = scnprintf(naddr->netid,
+ sizeof(naddr->netid), "%s",
+ rpc_peeraddr2str(clp->cl_rpcclient,
+ RPC_DISPLAY_NETID));
+ naddr->addr_len = scnprintf(naddr->addr,
+ sizeof(naddr->addr),
+ "%s.%u.%u",
+ rpc_peeraddr2str(clp->cl_rpcclient,
+ RPC_DISPLAY_ADDR),
+ port >> 8, port & 255);
+ rcu_read_unlock();
+}
+
static int _nfs42_proc_fallocate(struct rpc_message *msg, struct file *filep,
struct nfs_lock_context *lock, loff_t offset, loff_t len)
{
@@ -28,7 +49,7 @@ static int _nfs42_proc_fallocate(struct rpc_message *msg, struct file *filep,
.falloc_fh = NFS_FH(inode),
.falloc_offset = offset,
.falloc_length = len,
- .falloc_bitmask = server->cache_consistency_bitmask,
+ .falloc_bitmask = nfs4_fattr_bitmap,
};
struct nfs42_falloc_res res = {
.falloc_server = server,
@@ -132,22 +153,26 @@ out_unlock:
}
static int handle_async_copy(struct nfs42_copy_res *res,
- struct nfs_server *server,
+ struct nfs_server *dst_server,
+ struct nfs_server *src_server,
struct file *src,
struct file *dst,
- nfs4_stateid *src_stateid)
+ nfs4_stateid *src_stateid,
+ bool *restart)
{
struct nfs4_copy_state *copy, *tmp_copy;
int status = NFS4_OK;
bool found_pending = false;
- struct nfs_open_context *ctx = nfs_file_open_context(dst);
+ struct nfs_open_context *dst_ctx = nfs_file_open_context(dst);
+ struct nfs_open_context *src_ctx = nfs_file_open_context(src);
copy = kzalloc(sizeof(struct nfs4_copy_state), GFP_NOFS);
if (!copy)
return -ENOMEM;
- spin_lock(&server->nfs_client->cl_lock);
- list_for_each_entry(tmp_copy, &server->nfs_client->pending_cb_stateids,
+ spin_lock(&dst_server->nfs_client->cl_lock);
+ list_for_each_entry(tmp_copy,
+ &dst_server->nfs_client->pending_cb_stateids,
copies) {
if (memcmp(&res->write_res.stateid, &tmp_copy->stateid,
NFS4_STATEID_SIZE))
@@ -157,7 +182,7 @@ static int handle_async_copy(struct nfs42_copy_res *res,
break;
}
if (found_pending) {
- spin_unlock(&server->nfs_client->cl_lock);
+ spin_unlock(&dst_server->nfs_client->cl_lock);
kfree(copy);
copy = tmp_copy;
goto out;
@@ -165,19 +190,32 @@ static int handle_async_copy(struct nfs42_copy_res *res,
memcpy(&copy->stateid, &res->write_res.stateid, NFS4_STATEID_SIZE);
init_completion(&copy->completion);
- copy->parent_state = ctx->state;
+ copy->parent_dst_state = dst_ctx->state;
+ copy->parent_src_state = src_ctx->state;
- list_add_tail(&copy->copies, &server->ss_copies);
- spin_unlock(&server->nfs_client->cl_lock);
+ list_add_tail(&copy->copies, &dst_server->ss_copies);
+ spin_unlock(&dst_server->nfs_client->cl_lock);
+
+ if (dst_server != src_server) {
+ spin_lock(&src_server->nfs_client->cl_lock);
+ list_add_tail(&copy->src_copies, &src_server->ss_copies);
+ spin_unlock(&src_server->nfs_client->cl_lock);
+ }
status = wait_for_completion_interruptible(&copy->completion);
- spin_lock(&server->nfs_client->cl_lock);
+ spin_lock(&dst_server->nfs_client->cl_lock);
list_del_init(&copy->copies);
- spin_unlock(&server->nfs_client->cl_lock);
+ spin_unlock(&dst_server->nfs_client->cl_lock);
+ if (dst_server != src_server) {
+ spin_lock(&src_server->nfs_client->cl_lock);
+ list_del_init(&copy->src_copies);
+ spin_unlock(&src_server->nfs_client->cl_lock);
+ }
if (status == -ERESTARTSYS) {
goto out_cancel;
- } else if (copy->flags) {
+ } else if (copy->flags || copy->error == NFS4ERR_PARTNER_NO_AUTH) {
status = -EAGAIN;
+ *restart = true;
goto out_cancel;
}
out:
@@ -185,12 +223,14 @@ out:
memcpy(&res->write_res.verifier, &copy->verf, sizeof(copy->verf));
status = -copy->error;
+out_free:
kfree(copy);
return status;
out_cancel:
nfs42_do_offload_cancel_async(dst, &copy->stateid);
- kfree(copy);
- return status;
+ if (!nfs42_files_from_same_server(src, dst))
+ nfs42_do_offload_cancel_async(src, src_stateid);
+ goto out_free;
}
static int process_copy_commit(struct file *dst, loff_t pos_dst,
@@ -222,7 +262,10 @@ static ssize_t _nfs42_proc_copy(struct file *src,
struct file *dst,
struct nfs_lock_context *dst_lock,
struct nfs42_copy_args *args,
- struct nfs42_copy_res *res)
+ struct nfs42_copy_res *res,
+ struct nl4_server *nss,
+ nfs4_stateid *cnr_stateid,
+ bool *restart)
{
struct rpc_message msg = {
.rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_COPY],
@@ -230,17 +273,23 @@ static ssize_t _nfs42_proc_copy(struct file *src,
.rpc_resp = res,
};
struct inode *dst_inode = file_inode(dst);
- struct nfs_server *server = NFS_SERVER(dst_inode);
+ struct inode *src_inode = file_inode(src);
+ struct nfs_server *dst_server = NFS_SERVER(dst_inode);
+ struct nfs_server *src_server = NFS_SERVER(src_inode);
loff_t pos_src = args->src_pos;
loff_t pos_dst = args->dst_pos;
size_t count = args->count;
ssize_t status;
- status = nfs4_set_rw_stateid(&args->src_stateid, src_lock->open_context,
- src_lock, FMODE_READ);
- if (status)
- return status;
-
+ if (nss) {
+ args->cp_src = nss;
+ nfs4_stateid_copy(&args->src_stateid, cnr_stateid);
+ } else {
+ status = nfs4_set_rw_stateid(&args->src_stateid,
+ src_lock->open_context, src_lock, FMODE_READ);
+ if (status)
+ return status;
+ }
status = nfs_filemap_write_and_wait_range(file_inode(src)->i_mapping,
pos_src, pos_src + (loff_t)count - 1);
if (status)
@@ -262,13 +311,15 @@ static ssize_t _nfs42_proc_copy(struct file *src,
if (!res->commit_res.verf)
return -ENOMEM;
}
+ set_bit(NFS_CLNT_SRC_SSC_COPY_STATE,
+ &src_lock->open_context->state->flags);
set_bit(NFS_CLNT_DST_SSC_COPY_STATE,
&dst_lock->open_context->state->flags);
- status = nfs4_call_sync(server->client, server, &msg,
+ status = nfs4_call_sync(dst_server->client, dst_server, &msg,
&args->seq_args, &res->seq_res, 0);
if (status == -ENOTSUPP)
- server->caps &= ~NFS_CAP_COPY;
+ dst_server->caps &= ~NFS_CAP_COPY;
if (status)
goto out;
@@ -280,8 +331,8 @@ static ssize_t _nfs42_proc_copy(struct file *src,
}
if (!res->synchronous) {
- status = handle_async_copy(res, server, src, dst,
- &args->src_stateid);
+ status = handle_async_copy(res, dst_server, src_server, src,
+ dst, &args->src_stateid, restart);
if (status)
return status;
}
@@ -304,8 +355,9 @@ out:
}
ssize_t nfs42_proc_copy(struct file *src, loff_t pos_src,
- struct file *dst, loff_t pos_dst,
- size_t count)
+ struct file *dst, loff_t pos_dst, size_t count,
+ struct nl4_server *nss,
+ nfs4_stateid *cnr_stateid, bool sync)
{
struct nfs_server *server = NFS_SERVER(file_inode(dst));
struct nfs_lock_context *src_lock;
@@ -316,7 +368,7 @@ ssize_t nfs42_proc_copy(struct file *src, loff_t pos_src,
.dst_fh = NFS_FH(file_inode(dst)),
.dst_pos = pos_dst,
.count = count,
- .sync = false,
+ .sync = sync,
};
struct nfs42_copy_res res;
struct nfs4_exception src_exception = {
@@ -328,6 +380,7 @@ ssize_t nfs42_proc_copy(struct file *src, loff_t pos_src,
.stateid = &args.dst_stateid,
};
ssize_t err, err2;
+ bool restart = false;
src_lock = nfs_get_lock_context(nfs_file_open_context(src));
if (IS_ERR(src_lock))
@@ -347,21 +400,33 @@ ssize_t nfs42_proc_copy(struct file *src, loff_t pos_src,
inode_lock(file_inode(dst));
err = _nfs42_proc_copy(src, src_lock,
dst, dst_lock,
- &args, &res);
+ &args, &res,
+ nss, cnr_stateid, &restart);
inode_unlock(file_inode(dst));
if (err >= 0)
break;
- if (err == -ENOTSUPP) {
+ if (err == -ENOTSUPP &&
+ nfs42_files_from_same_server(src, dst)) {
err = -EOPNOTSUPP;
break;
} else if (err == -EAGAIN) {
- dst_exception.retry = 1;
- continue;
+ if (!restart) {
+ dst_exception.retry = 1;
+ continue;
+ }
+ break;
} else if (err == -NFS4ERR_OFFLOAD_NO_REQS && !args.sync) {
args.sync = true;
dst_exception.retry = 1;
continue;
+ } else if ((err == -ESTALE ||
+ err == -NFS4ERR_OFFLOAD_DENIED ||
+ err == -ENOTSUPP) &&
+ !nfs42_files_from_same_server(src, dst)) {
+ nfs42_do_offload_cancel_async(src, &args.src_stateid);
+ err = -EOPNOTSUPP;
+ break;
}
err2 = nfs4_handle_exception(server, err, &src_exception);
@@ -459,6 +524,76 @@ static int nfs42_do_offload_cancel_async(struct file *dst,
return status;
}
+static int _nfs42_proc_copy_notify(struct file *src, struct file *dst,
+ struct nfs42_copy_notify_args *args,
+ struct nfs42_copy_notify_res *res)
+{
+ struct nfs_server *src_server = NFS_SERVER(file_inode(src));
+ struct rpc_message msg = {
+ .rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_COPY_NOTIFY],
+ .rpc_argp = args,
+ .rpc_resp = res,
+ };
+ int status;
+ struct nfs_open_context *ctx;
+ struct nfs_lock_context *l_ctx;
+
+ ctx = get_nfs_open_context(nfs_file_open_context(src));
+ l_ctx = nfs_get_lock_context(ctx);
+ if (IS_ERR(l_ctx))
+ return PTR_ERR(l_ctx);
+
+ status = nfs4_set_rw_stateid(&args->cna_src_stateid, ctx, l_ctx,
+ FMODE_READ);
+ nfs_put_lock_context(l_ctx);
+ if (status)
+ return status;
+
+ status = nfs4_call_sync(src_server->client, src_server, &msg,
+ &args->cna_seq_args, &res->cnr_seq_res, 0);
+ if (status == -ENOTSUPP)
+ src_server->caps &= ~NFS_CAP_COPY_NOTIFY;
+
+ put_nfs_open_context(nfs_file_open_context(src));
+ return status;
+}
+
+int nfs42_proc_copy_notify(struct file *src, struct file *dst,
+ struct nfs42_copy_notify_res *res)
+{
+ struct nfs_server *src_server = NFS_SERVER(file_inode(src));
+ struct nfs42_copy_notify_args *args;
+ struct nfs4_exception exception = {
+ .inode = file_inode(src),
+ };
+ int status;
+
+ if (!(src_server->caps & NFS_CAP_COPY_NOTIFY))
+ return -EOPNOTSUPP;
+
+ args = kzalloc(sizeof(struct nfs42_copy_notify_args), GFP_NOFS);
+ if (args == NULL)
+ return -ENOMEM;
+
+ args->cna_src_fh = NFS_FH(file_inode(src)),
+ args->cna_dst.nl4_type = NL4_NETADDR;
+ nfs42_set_netaddr(dst, &args->cna_dst.u.nl4_addr);
+ exception.stateid = &args->cna_src_stateid;
+
+ do {
+ status = _nfs42_proc_copy_notify(src, dst, args, res);
+ if (status == -ENOTSUPP) {
+ status = -EOPNOTSUPP;
+ goto out;
+ }
+ status = nfs4_handle_exception(src_server, status, &exception);
+ } while (exception.retry);
+
+out:
+ kfree(args);
+ return status;
+}
+
static loff_t _nfs42_proc_llseek(struct file *filep,
struct nfs_lock_context *lock, loff_t offset, int whence)
{
diff --git a/fs/nfs/nfs42xdr.c b/fs/nfs/nfs42xdr.c
index aed865a84629..c03f3246d6c5 100644
--- a/fs/nfs/nfs42xdr.c
+++ b/fs/nfs/nfs42xdr.c
@@ -21,7 +21,10 @@
#define encode_copy_maxsz (op_encode_hdr_maxsz + \
XDR_QUADLEN(NFS4_STATEID_SIZE) + \
XDR_QUADLEN(NFS4_STATEID_SIZE) + \
- 2 + 2 + 2 + 1 + 1 + 1)
+ 2 + 2 + 2 + 1 + 1 + 1 +\
+ 1 + /* One cnr_source_server */\
+ 1 + /* nl4_type */ \
+ 1 + XDR_QUADLEN(NFS4_OPAQUE_LIMIT))
#define decode_copy_maxsz (op_decode_hdr_maxsz + \
NFS42_WRITE_RES_SIZE + \
1 /* cr_consecutive */ + \
@@ -29,6 +32,16 @@
#define encode_offload_cancel_maxsz (op_encode_hdr_maxsz + \
XDR_QUADLEN(NFS4_STATEID_SIZE))
#define decode_offload_cancel_maxsz (op_decode_hdr_maxsz)
+#define encode_copy_notify_maxsz (op_encode_hdr_maxsz + \
+ XDR_QUADLEN(NFS4_STATEID_SIZE) + \
+ 1 + /* nl4_type */ \
+ 1 + XDR_QUADLEN(NFS4_OPAQUE_LIMIT))
+#define decode_copy_notify_maxsz (op_decode_hdr_maxsz + \
+ 3 + /* cnr_lease_time */\
+ XDR_QUADLEN(NFS4_STATEID_SIZE) + \
+ 1 + /* Support 1 cnr_source_server */\
+ 1 + /* nl4_type */ \
+ 1 + XDR_QUADLEN(NFS4_OPAQUE_LIMIT))
#define encode_deallocate_maxsz (op_encode_hdr_maxsz + \
encode_fallocate_maxsz)
#define decode_deallocate_maxsz (op_decode_hdr_maxsz)
@@ -99,6 +112,12 @@
decode_sequence_maxsz + \
decode_putfh_maxsz + \
decode_offload_cancel_maxsz)
+#define NFS4_enc_copy_notify_sz (compound_encode_hdr_maxsz + \
+ encode_putfh_maxsz + \
+ encode_copy_notify_maxsz)
+#define NFS4_dec_copy_notify_sz (compound_decode_hdr_maxsz + \
+ decode_putfh_maxsz + \
+ decode_copy_notify_maxsz)
#define NFS4_enc_deallocate_sz (compound_encode_hdr_maxsz + \
encode_sequence_maxsz + \
encode_putfh_maxsz + \
@@ -166,6 +185,26 @@ static void encode_allocate(struct xdr_stream *xdr,
encode_fallocate(xdr, args);
}
+static void encode_nl4_server(struct xdr_stream *xdr,
+ const struct nl4_server *ns)
+{
+ encode_uint32(xdr, ns->nl4_type);
+ switch (ns->nl4_type) {
+ case NL4_NAME:
+ case NL4_URL:
+ encode_string(xdr, ns->u.nl4_str_sz, ns->u.nl4_str);
+ break;
+ case NL4_NETADDR:
+ encode_string(xdr, ns->u.nl4_addr.netid_len,
+ ns->u.nl4_addr.netid);
+ encode_string(xdr, ns->u.nl4_addr.addr_len,
+ ns->u.nl4_addr.addr);
+ break;
+ default:
+ WARN_ON_ONCE(1);
+ }
+}
+
static void encode_copy(struct xdr_stream *xdr,
const struct nfs42_copy_args *args,
struct compound_hdr *hdr)
@@ -180,7 +219,12 @@ static void encode_copy(struct xdr_stream *xdr,
encode_uint32(xdr, 1); /* consecutive = true */
encode_uint32(xdr, args->sync);
- encode_uint32(xdr, 0); /* src server list */
+ if (args->cp_src == NULL) { /* intra-ssc */
+ encode_uint32(xdr, 0); /* no src server list */
+ return;
+ }
+ encode_uint32(xdr, 1); /* supporting 1 server */
+ encode_nl4_server(xdr, args->cp_src);
}
static void encode_offload_cancel(struct xdr_stream *xdr,
@@ -191,6 +235,15 @@ static void encode_offload_cancel(struct xdr_stream *xdr,
encode_nfs4_stateid(xdr, &args->osa_stateid);
}
+static void encode_copy_notify(struct xdr_stream *xdr,
+ const struct nfs42_copy_notify_args *args,
+ struct compound_hdr *hdr)
+{
+ encode_op_hdr(xdr, OP_COPY_NOTIFY, decode_copy_notify_maxsz, hdr);
+ encode_nfs4_stateid(xdr, &args->cna_src_stateid);
+ encode_nl4_server(xdr, &args->cna_dst);
+}
+
static void encode_deallocate(struct xdr_stream *xdr,
const struct nfs42_falloc_args *args,
struct compound_hdr *hdr)
@@ -355,6 +408,25 @@ static void nfs4_xdr_enc_offload_cancel(struct rpc_rqst *req,
}
/*
+ * Encode COPY_NOTIFY request
+ */
+static void nfs4_xdr_enc_copy_notify(struct rpc_rqst *req,
+ struct xdr_stream *xdr,
+ const void *data)
+{
+ const struct nfs42_copy_notify_args *args = data;
+ struct compound_hdr hdr = {
+ .minorversion = nfs4_xdr_minorversion(&args->cna_seq_args),
+ };
+
+ encode_compound_hdr(xdr, req, &hdr);
+ encode_sequence(xdr, &args->cna_seq_args, &hdr);
+ encode_putfh(xdr, args->cna_src_fh, &hdr);
+ encode_copy_notify(xdr, args, &hdr);
+ encode_nops(&hdr);
+}
+
+/*
* Encode DEALLOCATE request
*/
static void nfs4_xdr_enc_deallocate(struct rpc_rqst *req,
@@ -490,6 +562,58 @@ static int decode_write_response(struct xdr_stream *xdr,
return decode_verifier(xdr, &res->verifier.verifier);
}
+static int decode_nl4_server(struct xdr_stream *xdr, struct nl4_server *ns)
+{
+ struct nfs42_netaddr *naddr;
+ uint32_t dummy;
+ char *dummy_str;
+ __be32 *p;
+ int status;
+
+ /* nl_type */
+ p = xdr_inline_decode(xdr, 4);
+ if (unlikely(!p))
+ return -EIO;
+ ns->nl4_type = be32_to_cpup(p);
+ switch (ns->nl4_type) {
+ case NL4_NAME:
+ case NL4_URL:
+ status = decode_opaque_inline(xdr, &dummy, &dummy_str);
+ if (unlikely(status))
+ return status;
+ if (unlikely(dummy > NFS4_OPAQUE_LIMIT))
+ return -EIO;
+ memcpy(&ns->u.nl4_str, dummy_str, dummy);
+ ns->u.nl4_str_sz = dummy;
+ break;
+ case NL4_NETADDR:
+ naddr = &ns->u.nl4_addr;
+
+ /* netid string */
+ status = decode_opaque_inline(xdr, &dummy, &dummy_str);
+ if (unlikely(status))
+ return status;
+ if (unlikely(dummy > RPCBIND_MAXNETIDLEN))
+ return -EIO;
+ naddr->netid_len = dummy;
+ memcpy(naddr->netid, dummy_str, naddr->netid_len);
+
+ /* uaddr string */
+ status = decode_opaque_inline(xdr, &dummy, &dummy_str);
+ if (unlikely(status))
+ return status;
+ if (unlikely(dummy > RPCBIND_MAXUADDRLEN))
+ return -EIO;
+ naddr->addr_len = dummy;
+ memcpy(naddr->addr, dummy_str, naddr->addr_len);
+ break;
+ default:
+ WARN_ON_ONCE(1);
+ return -EIO;
+ }
+ return 0;
+}
+
static int decode_copy_requirements(struct xdr_stream *xdr,
struct nfs42_copy_res *res) {
__be32 *p;
@@ -529,6 +653,42 @@ static int decode_offload_cancel(struct xdr_stream *xdr,
return decode_op_hdr(xdr, OP_OFFLOAD_CANCEL);
}
+static int decode_copy_notify(struct xdr_stream *xdr,
+ struct nfs42_copy_notify_res *res)
+{
+ __be32 *p;
+ int status, count;
+
+ status = decode_op_hdr(xdr, OP_COPY_NOTIFY);
+ if (status)
+ return status;
+ /* cnr_lease_time */
+ p = xdr_inline_decode(xdr, 12);
+ if (unlikely(!p))
+ return -EIO;
+ p = xdr_decode_hyper(p, &res->cnr_lease_time.seconds);
+ res->cnr_lease_time.nseconds = be32_to_cpup(p);
+
+ status = decode_opaque_fixed(xdr, &res->cnr_stateid, NFS4_STATEID_SIZE);
+ if (unlikely(status))
+ return -EIO;
+
+ /* number of source addresses */
+ p = xdr_inline_decode(xdr, 4);
+ if (unlikely(!p))
+ return -EIO;
+
+ count = be32_to_cpup(p);
+ if (count > 1)
+ pr_warn("NFS: %s: nsvr %d > Supported. Use first servers\n",
+ __func__, count);
+
+ status = decode_nl4_server(xdr, &res->cnr_src);
+ if (unlikely(status))
+ return -EIO;
+ return 0;
+}
+
static int decode_deallocate(struct xdr_stream *xdr, struct nfs42_falloc_res *res)
{
return decode_op_hdr(xdr, OP_DEALLOCATE);
@@ -657,6 +817,32 @@ out:
}
/*
+ * Decode COPY_NOTIFY response
+ */
+static int nfs4_xdr_dec_copy_notify(struct rpc_rqst *rqstp,
+ struct xdr_stream *xdr,
+ void *data)
+{
+ struct nfs42_copy_notify_res *res = data;
+ struct compound_hdr hdr;
+ int status;
+
+ status = decode_compound_hdr(xdr, &hdr);
+ if (status)
+ goto out;
+ status = decode_sequence(xdr, &res->cnr_seq_res, rqstp);
+ if (status)
+ goto out;
+ status = decode_putfh(xdr);
+ if (status)
+ goto out;
+ status = decode_copy_notify(xdr, res);
+
+out:
+ return status;
+}
+
+/*
* Decode DEALLOCATE request
*/
static int nfs4_xdr_dec_deallocate(struct rpc_rqst *rqstp,
diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h
index 16b2e5cc3e94..a7a73b1d1fec 100644
--- a/fs/nfs/nfs4_fs.h
+++ b/fs/nfs/nfs4_fs.h
@@ -166,9 +166,9 @@ enum {
NFS_STATE_RECOVERY_FAILED, /* OPEN stateid state recovery failed */
NFS_STATE_MAY_NOTIFY_LOCK, /* server may CB_NOTIFY_LOCK */
NFS_STATE_CHANGE_WAIT, /* A state changing operation is outstanding */
-#ifdef CONFIG_NFS_V4_2
NFS_CLNT_DST_SSC_COPY_STATE, /* dst server open state on client*/
-#endif /* CONFIG_NFS_V4_2 */
+ NFS_CLNT_SRC_SSC_COPY_STATE, /* src server open state on client*/
+ NFS_SRV_SSC_COPY_STATE, /* ssc state on the dst server */
};
struct nfs4_state {
@@ -311,6 +311,13 @@ extern int nfs4_set_rw_stateid(nfs4_stateid *stateid,
const struct nfs_open_context *ctx,
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);
+extern int update_open_stateid(struct nfs4_state *state,
+ const nfs4_stateid *open_stateid,
+ const nfs4_stateid *deleg_stateid,
+ fmode_t fmode);
extern int nfs4_proc_get_lease_time(struct nfs_client *clp,
struct nfs_fsinfo *fsinfo);
@@ -445,6 +452,8 @@ extern void nfs4_set_lease_period(struct nfs_client *clp,
/* nfs4state.c */
+extern const nfs4_stateid current_stateid;
+
const struct cred *nfs4_get_clid_cred(struct nfs_client *clp);
const struct cred *nfs4_get_machine_cred(struct nfs_client *clp);
const struct cred *nfs4_get_renew_cred(struct nfs_client *clp);
@@ -457,6 +466,8 @@ int nfs41_discover_server_trunking(struct nfs_client *clp,
struct nfs_client **, const struct cred *);
extern void nfs4_schedule_session_recovery(struct nfs4_session *, int);
extern void nfs41_notify_server(struct nfs_client *);
+bool nfs4_check_serverowner_major_id(struct nfs41_server_owner *o1,
+ struct nfs41_server_owner *o2);
#else
static inline void nfs4_schedule_session_recovery(struct nfs4_session *session, int err)
{
@@ -572,6 +583,12 @@ static inline bool nfs4_stateid_is_newer(const nfs4_stateid *s1, const nfs4_stat
return (s32)(be32_to_cpu(s1->seqid) - be32_to_cpu(s2->seqid)) > 0;
}
+static inline bool nfs4_stateid_match_or_older(const nfs4_stateid *dst, const nfs4_stateid *src)
+{
+ return nfs4_stateid_match_other(dst, src) &&
+ !(src->seqid && nfs4_stateid_is_newer(dst, src));
+}
+
static inline void nfs4_stateid_seqid_inc(nfs4_stateid *s1)
{
u32 seqid = be32_to_cpu(s1->seqid);
diff --git a/fs/nfs/nfs4client.c b/fs/nfs/nfs4client.c
index da6204025a2d..460d6251c405 100644
--- a/fs/nfs/nfs4client.c
+++ b/fs/nfs/nfs4client.c
@@ -629,7 +629,7 @@ out:
/*
* Returns true if the server major ids match
*/
-static bool
+bool
nfs4_check_serverowner_major_id(struct nfs41_server_owner *o1,
struct nfs41_server_owner *o2)
{
@@ -879,14 +879,17 @@ static int nfs4_set_client(struct nfs_server *server,
};
struct nfs_client *clp;
- if (minorversion > 0 && proto == XPRT_TRANSPORT_TCP)
+ if (minorversion == 0)
+ __set_bit(NFS_CS_REUSEPORT, &cl_init.init_flags);
+ else if (proto == XPRT_TRANSPORT_TCP)
cl_init.nconnect = nconnect;
+
if (server->flags & NFS_MOUNT_NORESVPORT)
- set_bit(NFS_CS_NORESVPORT, &cl_init.init_flags);
+ __set_bit(NFS_CS_NORESVPORT, &cl_init.init_flags);
if (server->options & NFS_OPTION_MIGRATION)
- set_bit(NFS_CS_MIGRATION, &cl_init.init_flags);
+ __set_bit(NFS_CS_MIGRATION, &cl_init.init_flags);
if (test_bit(NFS_MIG_TSM_POSSIBLE, &server->mig_status))
- set_bit(NFS_CS_TSM_POSSIBLE, &cl_init.init_flags);
+ __set_bit(NFS_CS_TSM_POSSIBLE, &cl_init.init_flags);
server->port = rpc_get_port(addr);
/* Allocate or find a client reference we can use */
diff --git a/fs/nfs/nfs4file.c b/fs/nfs/nfs4file.c
index 339663d04bf8..620de905cba9 100644
--- a/fs/nfs/nfs4file.c
+++ b/fs/nfs/nfs4file.c
@@ -133,14 +133,55 @@ static ssize_t __nfs4_copy_file_range(struct file *file_in, loff_t pos_in,
struct file *file_out, loff_t pos_out,
size_t count, unsigned int flags)
{
+ struct nfs42_copy_notify_res *cn_resp = NULL;
+ struct nl4_server *nss = NULL;
+ nfs4_stateid *cnrs = NULL;
+ ssize_t ret;
+ bool sync = false;
+
/* Only offload copy if superblock is the same */
- if (file_inode(file_in)->i_sb != file_inode(file_out)->i_sb)
+ if (file_in->f_op != &nfs4_file_operations)
return -EXDEV;
if (!nfs_server_capable(file_inode(file_out), NFS_CAP_COPY))
return -EOPNOTSUPP;
if (file_inode(file_in) == file_inode(file_out))
return -EOPNOTSUPP;
- return nfs42_proc_copy(file_in, pos_in, file_out, pos_out, count);
+ /* if the copy size if smaller than 2 RPC payloads, make it
+ * synchronous
+ */
+ if (count <= 2 * NFS_SERVER(file_inode(file_in))->rsize)
+ sync = true;
+retry:
+ if (!nfs42_files_from_same_server(file_in, file_out)) {
+ /* for inter copy, if copy size if smaller than 12 RPC
+ * payloads, fallback to traditional copy. There are
+ * 14 RPCs during an NFSv4.x mount between source/dest
+ * servers.
+ */
+ if (sync ||
+ count <= 14 * NFS_SERVER(file_inode(file_in))->rsize)
+ return -EOPNOTSUPP;
+ cn_resp = kzalloc(sizeof(struct nfs42_copy_notify_res),
+ GFP_NOFS);
+ if (unlikely(cn_resp == NULL))
+ return -ENOMEM;
+
+ ret = nfs42_proc_copy_notify(file_in, file_out, cn_resp);
+ if (ret) {
+ ret = -EOPNOTSUPP;
+ goto out;
+ }
+ nss = &cn_resp->cnr_src;
+ cnrs = &cn_resp->cnr_stateid;
+ }
+ ret = nfs42_proc_copy(file_in, pos_in, file_out, pos_out, count,
+ nss, cnrs, sync);
+out:
+ if (!nfs42_files_from_same_server(file_in, file_out))
+ kfree(cn_resp);
+ if (ret == -EAGAIN)
+ goto retry;
+ return ret;
}
static ssize_t nfs4_copy_file_range(struct file *file_in, loff_t pos_in,
@@ -263,6 +304,102 @@ out_unlock:
out:
return ret < 0 ? ret : count;
}
+
+static int read_name_gen = 1;
+#define SSC_READ_NAME_BODY "ssc_read_%d"
+
+struct file *
+nfs42_ssc_open(struct vfsmount *ss_mnt, struct nfs_fh *src_fh,
+ nfs4_stateid *stateid)
+{
+ struct nfs_fattr fattr;
+ struct file *filep, *res;
+ struct nfs_server *server;
+ struct inode *r_ino = NULL;
+ struct nfs_open_context *ctx;
+ struct nfs4_state_owner *sp;
+ char *read_name = NULL;
+ int len, status = 0;
+
+ server = NFS_SERVER(ss_mnt->mnt_root->d_inode);
+
+ nfs_fattr_init(&fattr);
+
+ status = nfs4_proc_getattr(server, src_fh, &fattr, NULL, NULL);
+ if (status < 0) {
+ res = ERR_PTR(status);
+ goto out;
+ }
+
+ res = ERR_PTR(-ENOMEM);
+ len = strlen(SSC_READ_NAME_BODY) + 16;
+ read_name = kzalloc(len, GFP_NOFS);
+ if (read_name == NULL)
+ 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);
+ 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,
+ 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);
+ if (IS_ERR(ctx)) {
+ res = ERR_CAST(ctx);
+ goto out_filep;
+ }
+
+ res = ERR_PTR(-EINVAL);
+ sp = nfs4_get_state_owner(server, ctx->cred, GFP_KERNEL);
+ if (sp == NULL)
+ goto out_ctx;
+
+ ctx->state = nfs4_get_open_state(r_ino, sp);
+ if (ctx->state == NULL)
+ goto out_stateowner;
+
+ set_bit(NFS_SRV_SSC_COPY_STATE, &ctx->state->flags);
+ set_bit(NFS_OPEN_STATE, &ctx->state->flags);
+ memcpy(&ctx->state->open_stateid.other, &stateid->other,
+ NFS4_STATEID_OTHER_SIZE);
+ update_open_stateid(ctx->state, stateid, NULL, filep->f_mode);
+
+ nfs_file_set_open_context(filep, ctx);
+ put_nfs_open_context(ctx);
+
+ file_ra_state_init(&filep->f_ra, filep->f_mapping->host->i_mapping);
+ res = filep;
+out_free_name:
+ kfree(read_name);
+out:
+ return res;
+out_stateowner:
+ nfs4_put_state_owner(sp);
+out_ctx:
+ put_nfs_open_context(ctx);
+out_filep:
+ fput(filep);
+ goto out_free_name;
+}
+EXPORT_SYMBOL_GPL(nfs42_ssc_open);
+void nfs42_ssc_close(struct file *filep)
+{
+ struct nfs_open_context *ctx = nfs_file_open_context(filep);
+
+ ctx->state->flags = 0;
+}
+EXPORT_SYMBOL_GPL(nfs42_ssc_close);
#endif /* CONFIG_NFS_V4_2 */
const struct file_operations nfs4_file_operations = {
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index ab8ca20fd579..76d37161409a 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -91,7 +91,6 @@ 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 *, struct nfs_fh *, struct nfs_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 nfs4_label *label, struct inode *inode);
static int nfs4_do_setattr(struct inode *inode, const struct cred *cred,
struct nfs_fattr *fattr, struct iattr *sattr,
@@ -476,6 +475,7 @@ static int nfs4_do_handle_exception(struct nfs_server *server,
case -NFS4ERR_ADMIN_REVOKED:
case -NFS4ERR_EXPIRED:
case -NFS4ERR_BAD_STATEID:
+ case -NFS4ERR_PARTNER_NO_AUTH:
if (inode != NULL && stateid != NULL) {
nfs_inode_find_state_and_recover(inode,
stateid);
@@ -521,9 +521,7 @@ static int nfs4_do_handle_exception(struct nfs_server *server,
case -NFS4ERR_DEADSESSION:
case -NFS4ERR_SEQ_FALSE_RETRY:
case -NFS4ERR_SEQ_MISORDERED:
- dprintk("%s ERROR: %d Reset session\n", __func__,
- errorcode);
- nfs4_schedule_session_recovery(clp->cl_session, errorcode);
+ /* Handled in nfs41_sequence_process() */
goto wait_on_recovery;
#endif /* defined(CONFIG_NFS_V4_1) */
case -NFS4ERR_FILE_OPEN:
@@ -782,6 +780,7 @@ static int nfs41_sequence_process(struct rpc_task *task,
struct nfs4_session *session;
struct nfs4_slot *slot = res->sr_slot;
struct nfs_client *clp;
+ int status;
int ret = 1;
if (slot == NULL)
@@ -793,8 +792,13 @@ static int nfs41_sequence_process(struct rpc_task *task,
session = slot->table->session;
trace_nfs4_sequence_done(session, res);
+
+ status = res->sr_status;
+ if (task->tk_status == -NFS4ERR_DEADSESSION)
+ status = -NFS4ERR_DEADSESSION;
+
/* Check the SEQUENCE operation status */
- switch (res->sr_status) {
+ switch (status) {
case 0:
/* Mark this sequence number as having been acked */
nfs4_slot_sequence_acked(slot, slot->seq_nr);
@@ -866,6 +870,10 @@ static int nfs41_sequence_process(struct rpc_task *task,
*/
slot->seq_nr = slot->seq_nr_highest_sent;
goto out_retry;
+ case -NFS4ERR_BADSESSION:
+ case -NFS4ERR_DEADSESSION:
+ case -NFS4ERR_CONN_NOT_BOUND_TO_SESSION:
+ goto session_recover;
default:
/* Just update the slot sequence no. */
slot->seq_done = 1;
@@ -876,8 +884,10 @@ out:
out_noaction:
return ret;
session_recover:
- nfs4_schedule_session_recovery(session, res->sr_status);
- goto retry_nowait;
+ nfs4_schedule_session_recovery(session, status);
+ dprintk("%s ERROR: %d Reset session\n", __func__, status);
+ nfs41_sequence_free_slot(res);
+ goto out;
retry_new_seq:
++slot->seq_nr;
retry_nowait:
@@ -1440,8 +1450,6 @@ static int can_open_delegated(struct nfs_delegation *delegation, fmode_t fmode,
return 0;
if ((delegation->type & fmode) != fmode)
return 0;
- if (test_bit(NFS_DELEGATION_RETURNING, &delegation->flags))
- return 0;
switch (claim) {
case NFS4_OPEN_CLAIM_NULL:
case NFS4_OPEN_CLAIM_FH:
@@ -1718,7 +1726,7 @@ static void nfs_state_clear_delegation(struct nfs4_state *state)
write_sequnlock(&state->seqlock);
}
-static int update_open_stateid(struct nfs4_state *state,
+int update_open_stateid(struct nfs4_state *state,
const nfs4_stateid *open_stateid,
const nfs4_stateid *delegation,
fmode_t fmode)
@@ -1739,7 +1747,7 @@ static int update_open_stateid(struct nfs4_state *state,
ret = 1;
}
- deleg_cur = rcu_dereference(nfsi->delegation);
+ deleg_cur = nfs4_get_valid_delegation(state->inode);
if (deleg_cur == NULL)
goto no_delegation;
@@ -1751,7 +1759,7 @@ static int update_open_stateid(struct nfs4_state *state,
if (delegation == NULL)
delegation = &deleg_cur->stateid;
- else if (!nfs4_stateid_match(&deleg_cur->stateid, delegation))
+ else if (!nfs4_stateid_match_other(&deleg_cur->stateid, delegation))
goto no_delegation_unlock;
nfs_mark_delegation_referenced(deleg_cur);
@@ -1798,7 +1806,7 @@ static void nfs4_return_incompatible_delegation(struct inode *inode, fmode_t fmo
fmode &= FMODE_READ|FMODE_WRITE;
rcu_read_lock();
- delegation = rcu_dereference(NFS_I(inode)->delegation);
+ delegation = nfs4_get_valid_delegation(inode);
if (delegation == NULL || (delegation->type & fmode) == fmode) {
rcu_read_unlock();
return;
@@ -1810,7 +1818,6 @@ static void nfs4_return_incompatible_delegation(struct inode *inode, fmode_t fmo
static struct nfs4_state *nfs4_try_open_cached(struct nfs4_opendata *opendata)
{
struct nfs4_state *state = opendata->state;
- struct nfs_inode *nfsi = NFS_I(state->inode);
struct nfs_delegation *delegation;
int open_mode = opendata->o_arg.open_flags;
fmode_t fmode = opendata->o_arg.fmode;
@@ -1827,7 +1834,7 @@ static struct nfs4_state *nfs4_try_open_cached(struct nfs4_opendata *opendata)
}
spin_unlock(&state->owner->so_lock);
rcu_read_lock();
- delegation = rcu_dereference(nfsi->delegation);
+ delegation = nfs4_get_valid_delegation(state->inode);
if (!can_open_delegated(delegation, fmode, claim)) {
rcu_read_unlock();
break;
@@ -2191,7 +2198,6 @@ static int nfs4_handle_delegation_recall_error(struct nfs_server *server, struct
case -NFS4ERR_BAD_HIGH_SLOT:
case -NFS4ERR_CONN_NOT_BOUND_TO_SESSION:
case -NFS4ERR_DEADSESSION:
- nfs4_schedule_session_recovery(server->nfs_client->cl_session, err);
return -EAGAIN;
case -NFS4ERR_STALE_CLIENTID:
case -NFS4ERR_STALE_STATEID:
@@ -2371,7 +2377,7 @@ static void nfs4_open_prepare(struct rpc_task *task, void *calldata)
data->o_arg.open_flags, claim))
goto out_no_action;
rcu_read_lock();
- delegation = rcu_dereference(NFS_I(data->state->inode)->delegation);
+ delegation = nfs4_get_valid_delegation(data->state->inode);
if (can_open_delegated(delegation, data->o_arg.fmode, claim))
goto unlock_no_action;
rcu_read_unlock();
@@ -4065,7 +4071,7 @@ static int _nfs4_proc_getattr(struct nfs_server *server, struct nfs_fh *fhandle,
return nfs4_call_sync(server->client, server, &msg, &args.seq_args, &res.seq_res, 0);
}
-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)
{
@@ -5101,12 +5107,12 @@ static bool nfs4_stateid_is_current(nfs4_stateid *stateid,
const struct nfs_lock_context *l_ctx,
fmode_t fmode)
{
- nfs4_stateid current_stateid;
+ nfs4_stateid _current_stateid;
/* If the current stateid represents a lost lock, then exit */
- if (nfs4_set_rw_stateid(&current_stateid, ctx, l_ctx, fmode) == -EIO)
+ if (nfs4_set_rw_stateid(&_current_stateid, ctx, l_ctx, fmode) == -EIO)
return true;
- return nfs4_stateid_match(stateid, &current_stateid);
+ return nfs4_stateid_match(stateid, &_current_stateid);
}
static bool nfs4_error_stateid_expired(int err)
@@ -6199,10 +6205,13 @@ static void nfs4_delegreturn_done(struct rpc_task *task, void *calldata)
task->tk_status = 0;
break;
case -NFS4ERR_OLD_STATEID:
- if (nfs4_refresh_delegation_stateid(&data->stateid, data->inode))
- goto out_restart;
- task->tk_status = 0;
- break;
+ if (!nfs4_refresh_delegation_stateid(&data->stateid, data->inode))
+ nfs4_stateid_seqid_inc(&data->stateid);
+ if (data->args.bitmask) {
+ data->args.bitmask = NULL;
+ data->res.fattr = NULL;
+ }
+ goto out_restart;
case -NFS4ERR_ACCESS:
if (data->args.bitmask) {
data->args.bitmask = NULL;
@@ -6217,6 +6226,7 @@ static void nfs4_delegreturn_done(struct rpc_task *task, void *calldata)
if (exception.retry)
goto out_restart;
}
+ nfs_delegation_mark_returned(data->inode, data->args.stateid);
data->rpc_status = task->tk_status;
return;
out_restart:
@@ -6246,8 +6256,10 @@ static void nfs4_delegreturn_prepare(struct rpc_task *task, void *data)
d_data = (struct nfs4_delegreturndata *)data;
- if (!d_data->lr.roc && nfs4_wait_on_layoutreturn(d_data->inode, task))
+ if (!d_data->lr.roc && nfs4_wait_on_layoutreturn(d_data->inode, task)) {
+ nfs4_sequence_done(task, &d_data->res.seq_res);
return;
+ }
lo = d_data->args.lr_args ? d_data->args.lr_args->layout : NULL;
if (lo && !pnfs_layout_is_valid(lo)) {
@@ -7823,6 +7835,15 @@ nfs41_same_server_scope(struct nfs41_server_scope *a,
static void
nfs4_bind_one_conn_to_session_done(struct rpc_task *task, void *calldata)
{
+ struct nfs41_bind_conn_to_session_args *args = task->tk_msg.rpc_argp;
+ struct nfs_client *clp = args->client;
+
+ switch (task->tk_status) {
+ case -NFS4ERR_BADSESSION:
+ case -NFS4ERR_DEADSESSION:
+ nfs4_schedule_session_recovery(clp->cl_session,
+ task->tk_status);
+ }
}
static const struct rpc_call_ops nfs4_bind_one_conn_to_session_ops = {
@@ -8870,8 +8891,6 @@ static int nfs41_reclaim_complete_handle_errors(struct rpc_task *task, struct nf
case -NFS4ERR_BADSESSION:
case -NFS4ERR_DEADSESSION:
case -NFS4ERR_CONN_NOT_BOUND_TO_SESSION:
- nfs4_schedule_session_recovery(clp->cl_session,
- task->tk_status);
break;
default:
nfs4_schedule_lease_recovery(clp);
@@ -9900,6 +9919,7 @@ static const struct nfs4_minor_version_ops nfs_v4_2_minor_ops = {
| NFS_CAP_ALLOCATE
| NFS_CAP_COPY
| NFS_CAP_OFFLOAD_CANCEL
+ | NFS_CAP_COPY_NOTIFY
| NFS_CAP_DEALLOCATE
| NFS_CAP_SEEK
| NFS_CAP_LAYOUTSTATS
diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c
index 0c6d53dc3672..34552329233d 100644
--- a/fs/nfs/nfs4state.c
+++ b/fs/nfs/nfs4state.c
@@ -60,6 +60,7 @@
#include "nfs4session.h"
#include "pnfs.h"
#include "netns.h"
+#include "nfs4trace.h"
#define NFSDBG_FACILITY NFSDBG_STATE
@@ -1407,7 +1408,7 @@ nfs_state_find_lock_state_by_stateid(struct nfs4_state *state,
list_for_each_entry(pos, &state->lock_states, ls_locks) {
if (!test_bit(NFS_LOCK_INITIALIZED, &pos->ls_flags))
continue;
- if (nfs4_stateid_match_other(&pos->ls_stateid, stateid))
+ if (nfs4_stateid_match_or_older(&pos->ls_stateid, stateid))
return pos;
}
return NULL;
@@ -1441,12 +1442,13 @@ void nfs_inode_find_state_and_recover(struct inode *inode,
state = ctx->state;
if (state == NULL)
continue;
- if (nfs4_stateid_match_other(&state->stateid, stateid) &&
+ if (nfs4_stateid_match_or_older(&state->stateid, stateid) &&
nfs4_state_mark_reclaim_nograce(clp, state)) {
found = true;
continue;
}
- if (nfs4_stateid_match_other(&state->open_stateid, stateid) &&
+ if (test_bit(NFS_OPEN_STATE, &state->flags) &&
+ nfs4_stateid_match_or_older(&state->open_stateid, stateid) &&
nfs4_state_mark_reclaim_nograce(clp, state)) {
found = true;
continue;
@@ -1556,16 +1558,32 @@ static void nfs42_complete_copies(struct nfs4_state_owner *sp, struct nfs4_state
{
struct nfs4_copy_state *copy;
- if (!test_bit(NFS_CLNT_DST_SSC_COPY_STATE, &state->flags))
+ if (!test_bit(NFS_CLNT_DST_SSC_COPY_STATE, &state->flags) &&
+ !test_bit(NFS_CLNT_SRC_SSC_COPY_STATE, &state->flags))
return;
spin_lock(&sp->so_server->nfs_client->cl_lock);
list_for_each_entry(copy, &sp->so_server->ss_copies, copies) {
- if (!nfs4_stateid_match_other(&state->stateid, &copy->parent_state->stateid))
- continue;
+ if ((test_bit(NFS_CLNT_DST_SSC_COPY_STATE, &state->flags) &&
+ !nfs4_stateid_match_other(&state->stateid,
+ &copy->parent_dst_state->stateid)))
+ continue;
copy->flags = 1;
- complete(&copy->completion);
- break;
+ if (test_and_clear_bit(NFS_CLNT_DST_SSC_COPY_STATE,
+ &state->flags)) {
+ clear_bit(NFS_CLNT_SRC_SSC_COPY_STATE, &state->flags);
+ complete(&copy->completion);
+ }
+ }
+ list_for_each_entry(copy, &sp->so_server->ss_copies, src_copies) {
+ if ((test_bit(NFS_CLNT_SRC_SSC_COPY_STATE, &state->flags) &&
+ !nfs4_stateid_match_other(&state->stateid,
+ &copy->parent_src_state->stateid)))
+ continue;
+ copy->flags = 1;
+ if (test_and_clear_bit(NFS_CLNT_DST_SSC_COPY_STATE,
+ &state->flags))
+ complete(&copy->completion);
}
spin_unlock(&sp->so_server->nfs_client->cl_lock);
}
@@ -1593,6 +1611,7 @@ static int __nfs4_reclaim_open_state(struct nfs4_state_owner *sp, struct nfs4_st
if (!test_bit(NFS_DELEGATED_STATE, &state->flags)) {
spin_lock(&state->state_lock);
list_for_each_entry(lock, &state->lock_states, ls_locks) {
+ trace_nfs4_state_lock_reclaim(state, lock);
if (!test_bit(NFS_LOCK_INITIALIZED, &lock->ls_flags))
pr_warn_ratelimited("NFS: %s: Lock reclaim failed!\n", __func__);
}
@@ -1609,6 +1628,9 @@ static int nfs4_reclaim_open_state(struct nfs4_state_owner *sp, const struct nfs
struct nfs4_state *state;
unsigned int loop = 0;
int status = 0;
+#ifdef CONFIG_NFS_V4_2
+ bool found_ssc_copy_state = false;
+#endif /* CONFIG_NFS_V4_2 */
/* Note: we rely on the sp->so_states list being ordered
* so that we always reclaim open(O_RDWR) and/or open(O_WRITE)
@@ -1628,6 +1650,13 @@ restart:
continue;
if (state->state == 0)
continue;
+#ifdef CONFIG_NFS_V4_2
+ if (test_bit(NFS_SRV_SSC_COPY_STATE, &state->flags)) {
+ nfs4_state_mark_recovery_failed(state, -EIO);
+ found_ssc_copy_state = true;
+ continue;
+ }
+#endif /* CONFIG_NFS_V4_2 */
refcount_inc(&state->count);
spin_unlock(&sp->so_lock);
status = __nfs4_reclaim_open_state(sp, state, ops);
@@ -1682,6 +1711,10 @@ restart:
}
raw_write_seqcount_end(&sp->so_reclaim_seqcount);
spin_unlock(&sp->so_lock);
+#ifdef CONFIG_NFS_V4_2
+ if (found_ssc_copy_state)
+ return -EIO;
+#endif /* CONFIG_NFS_V4_2 */
return 0;
out_err:
nfs4_put_open_state(state);
@@ -2508,6 +2541,7 @@ static void nfs4_state_manager(struct nfs_client *clp)
/* Ensure exclusive access to NFSv4 state */
do {
+ trace_nfs4_state_mgr(clp);
clear_bit(NFS4CLNT_RUN_MANAGER, &clp->cl_state);
if (test_bit(NFS4CLNT_PURGE_STATE, &clp->cl_state)) {
section = "purge state";
@@ -2621,6 +2655,7 @@ static void nfs4_state_manager(struct nfs_client *clp)
out_error:
if (strlen(section))
section_sep = ": ";
+ trace_nfs4_state_mgr_failed(clp, section, status);
pr_warn_ratelimited("NFS: state manager%s%s failed on NFSv4 server %s"
" with error %d\n", section_sep, section,
clp->cl_hostname, -status);
diff --git a/fs/nfs/nfs4super.c b/fs/nfs/nfs4super.c
index 04c57066a11a..2c9cbade561a 100644
--- a/fs/nfs/nfs4super.c
+++ b/fs/nfs/nfs4super.c
@@ -92,8 +92,8 @@ static void nfs4_evict_inode(struct inode *inode)
{
truncate_inode_pages_final(&inode->i_data);
clear_inode(inode);
- /* If we are holding a delegation, return it! */
- nfs_inode_return_delegation_noreclaim(inode);
+ /* If we are holding a delegation, return and free it */
+ nfs_inode_evict_delegation(inode);
/* Note that above delegreturn would trigger pnfs return-on-close */
pnfs_return_layout(inode);
pnfs_destroy_layout(NFS_I(inode));
diff --git a/fs/nfs/nfs4trace.h b/fs/nfs/nfs4trace.h
index b2f395fa7350..e60b6fbd5ada 100644
--- a/fs/nfs/nfs4trace.h
+++ b/fs/nfs/nfs4trace.h
@@ -562,6 +562,99 @@ TRACE_EVENT(nfs4_setup_sequence,
)
);
+TRACE_DEFINE_ENUM(NFS4CLNT_MANAGER_RUNNING);
+TRACE_DEFINE_ENUM(NFS4CLNT_CHECK_LEASE);
+TRACE_DEFINE_ENUM(NFS4CLNT_LEASE_EXPIRED);
+TRACE_DEFINE_ENUM(NFS4CLNT_RECLAIM_REBOOT);
+TRACE_DEFINE_ENUM(NFS4CLNT_RECLAIM_NOGRACE);
+TRACE_DEFINE_ENUM(NFS4CLNT_DELEGRETURN);
+TRACE_DEFINE_ENUM(NFS4CLNT_SESSION_RESET);
+TRACE_DEFINE_ENUM(NFS4CLNT_LEASE_CONFIRM);
+TRACE_DEFINE_ENUM(NFS4CLNT_SERVER_SCOPE_MISMATCH);
+TRACE_DEFINE_ENUM(NFS4CLNT_PURGE_STATE);
+TRACE_DEFINE_ENUM(NFS4CLNT_BIND_CONN_TO_SESSION);
+TRACE_DEFINE_ENUM(NFS4CLNT_MOVED);
+TRACE_DEFINE_ENUM(NFS4CLNT_LEASE_MOVED);
+TRACE_DEFINE_ENUM(NFS4CLNT_DELEGATION_EXPIRED);
+TRACE_DEFINE_ENUM(NFS4CLNT_RUN_MANAGER);
+TRACE_DEFINE_ENUM(NFS4CLNT_DELEGRETURN_RUNNING);
+
+#define show_nfs4_clp_state(state) \
+ __print_flags(state, "|", \
+ { NFS4CLNT_MANAGER_RUNNING, "MANAGER_RUNNING" }, \
+ { NFS4CLNT_CHECK_LEASE, "CHECK_LEASE" }, \
+ { NFS4CLNT_LEASE_EXPIRED, "LEASE_EXPIRED" }, \
+ { NFS4CLNT_RECLAIM_REBOOT, "RECLAIM_REBOOT" }, \
+ { NFS4CLNT_RECLAIM_NOGRACE, "RECLAIM_NOGRACE" }, \
+ { NFS4CLNT_DELEGRETURN, "DELEGRETURN" }, \
+ { NFS4CLNT_SESSION_RESET, "SESSION_RESET" }, \
+ { NFS4CLNT_LEASE_CONFIRM, "LEASE_CONFIRM" }, \
+ { NFS4CLNT_SERVER_SCOPE_MISMATCH, \
+ "SERVER_SCOPE_MISMATCH" }, \
+ { NFS4CLNT_PURGE_STATE, "PURGE_STATE" }, \
+ { NFS4CLNT_BIND_CONN_TO_SESSION, \
+ "BIND_CONN_TO_SESSION" }, \
+ { NFS4CLNT_MOVED, "MOVED" }, \
+ { NFS4CLNT_LEASE_MOVED, "LEASE_MOVED" }, \
+ { NFS4CLNT_DELEGATION_EXPIRED, "DELEGATION_EXPIRED" }, \
+ { NFS4CLNT_RUN_MANAGER, "RUN_MANAGER" }, \
+ { NFS4CLNT_DELEGRETURN_RUNNING, "DELEGRETURN_RUNNING" })
+
+TRACE_EVENT(nfs4_state_mgr,
+ TP_PROTO(
+ const struct nfs_client *clp
+ ),
+
+ TP_ARGS(clp),
+
+ TP_STRUCT__entry(
+ __field(unsigned long, state)
+ __string(hostname, clp->cl_hostname)
+ ),
+
+ TP_fast_assign(
+ __entry->state = clp->cl_state;
+ __assign_str(hostname, clp->cl_hostname)
+ ),
+
+ TP_printk(
+ "hostname=%s clp state=%s", __get_str(hostname),
+ show_nfs4_clp_state(__entry->state)
+ )
+)
+
+TRACE_EVENT(nfs4_state_mgr_failed,
+ TP_PROTO(
+ const struct nfs_client *clp,
+ const char *section,
+ int status
+ ),
+
+ TP_ARGS(clp, section, status),
+
+ TP_STRUCT__entry(
+ __field(unsigned long, error)
+ __field(unsigned long, state)
+ __string(hostname, clp->cl_hostname)
+ __string(section, section)
+ ),
+
+ TP_fast_assign(
+ __entry->error = status;
+ __entry->state = clp->cl_state;
+ __assign_str(hostname, clp->cl_hostname);
+ __assign_str(section, section);
+ ),
+
+ TP_printk(
+ "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)
+
+ )
+)
+
TRACE_EVENT(nfs4_xdr_status,
TP_PROTO(
const struct xdr_stream *xdr,
@@ -929,6 +1022,88 @@ TRACE_EVENT(nfs4_set_lock,
)
);
+TRACE_DEFINE_ENUM(LK_STATE_IN_USE);
+TRACE_DEFINE_ENUM(NFS_DELEGATED_STATE);
+TRACE_DEFINE_ENUM(NFS_OPEN_STATE);
+TRACE_DEFINE_ENUM(NFS_O_RDONLY_STATE);
+TRACE_DEFINE_ENUM(NFS_O_WRONLY_STATE);
+TRACE_DEFINE_ENUM(NFS_O_RDWR_STATE);
+TRACE_DEFINE_ENUM(NFS_STATE_RECLAIM_REBOOT);
+TRACE_DEFINE_ENUM(NFS_STATE_RECLAIM_NOGRACE);
+TRACE_DEFINE_ENUM(NFS_STATE_POSIX_LOCKS);
+TRACE_DEFINE_ENUM(NFS_STATE_RECOVERY_FAILED);
+TRACE_DEFINE_ENUM(NFS_STATE_MAY_NOTIFY_LOCK);
+TRACE_DEFINE_ENUM(NFS_STATE_CHANGE_WAIT);
+TRACE_DEFINE_ENUM(NFS_CLNT_DST_SSC_COPY_STATE);
+TRACE_DEFINE_ENUM(NFS_CLNT_SRC_SSC_COPY_STATE);
+TRACE_DEFINE_ENUM(NFS_SRV_SSC_COPY_STATE);
+
+#define show_nfs4_state_flags(flags) \
+ __print_flags(flags, "|", \
+ { LK_STATE_IN_USE, "IN_USE" }, \
+ { NFS_DELEGATED_STATE, "DELEGATED" }, \
+ { NFS_OPEN_STATE, "OPEN" }, \
+ { NFS_O_RDONLY_STATE, "O_RDONLY" }, \
+ { NFS_O_WRONLY_STATE, "O_WRONLY" }, \
+ { NFS_O_RDWR_STATE, "O_RDWR" }, \
+ { NFS_STATE_RECLAIM_REBOOT, "RECLAIM_REBOOT" }, \
+ { NFS_STATE_RECLAIM_NOGRACE, "RECLAIM_NOGRACE" }, \
+ { NFS_STATE_POSIX_LOCKS, "POSIX_LOCKS" }, \
+ { NFS_STATE_RECOVERY_FAILED, "RECOVERY_FAILED" }, \
+ { NFS_STATE_MAY_NOTIFY_LOCK, "MAY_NOTIFY_LOCK" }, \
+ { NFS_STATE_CHANGE_WAIT, "CHANGE_WAIT" }, \
+ { NFS_CLNT_DST_SSC_COPY_STATE, "CLNT_DST_SSC_COPY" }, \
+ { NFS_CLNT_SRC_SSC_COPY_STATE, "CLNT_SRC_SSC_COPY" }, \
+ { NFS_SRV_SSC_COPY_STATE, "SRV_SSC_COPY" })
+
+#define show_nfs4_lock_flags(flags) \
+ __print_flags(flags, "|", \
+ { BIT(NFS_LOCK_INITIALIZED), "INITIALIZED" }, \
+ { BIT(NFS_LOCK_LOST), "LOST" })
+
+TRACE_EVENT(nfs4_state_lock_reclaim,
+ TP_PROTO(
+ const struct nfs4_state *state,
+ const struct nfs4_lock_state *lock
+ ),
+
+ TP_ARGS(state, lock),
+
+ TP_STRUCT__entry(
+ __field(dev_t, dev)
+ __field(u32, fhandle)
+ __field(u64, fileid)
+ __field(unsigned long, state_flags)
+ __field(unsigned long, lock_flags)
+ __field(int, stateid_seq)
+ __field(u32, stateid_hash)
+ ),
+
+ TP_fast_assign(
+ const struct inode *inode = state->inode;
+
+ __entry->dev = inode->i_sb->s_dev;
+ __entry->fileid = NFS_FILEID(inode);
+ __entry->fhandle = nfs_fhandle_hash(NFS_FH(inode));
+ __entry->state_flags = state->flags;
+ __entry->lock_flags = lock->ls_flags;
+ __entry->stateid_seq =
+ be32_to_cpu(state->stateid.seqid);
+ __entry->stateid_hash =
+ nfs_stateid_hash(&state->stateid);
+ ),
+
+ TP_printk(
+ "fileid=%02x:%02x:%llu fhandle=0x%08x "
+ "stateid=%d:0x%08x state_flags=%s lock_flags=%s",
+ MAJOR(__entry->dev), MINOR(__entry->dev),
+ (unsigned long long)__entry->fileid, __entry->fhandle,
+ __entry->stateid_seq, __entry->stateid_hash,
+ show_nfs4_state_flags(__entry->state_flags),
+ show_nfs4_lock_flags(__entry->lock_flags)
+ )
+)
+
DECLARE_EVENT_CLASS(nfs4_set_delegation_event,
TP_PROTO(
const struct inode *inode,
diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c
index ab07db0f07cd..936c57779ff4 100644
--- a/fs/nfs/nfs4xdr.c
+++ b/fs/nfs/nfs4xdr.c
@@ -1059,7 +1059,7 @@ static void encode_nfs4_verifier(struct xdr_stream *xdr, const nfs4_verifier *ve
}
static __be32 *
-xdr_encode_nfstime4(__be32 *p, const struct timespec *t)
+xdr_encode_nfstime4(__be32 *p, const struct timespec64 *t)
{
p = xdr_encode_hyper(p, (__s64)t->tv_sec);
*p++ = cpu_to_be32(t->tv_nsec);
@@ -1072,7 +1072,6 @@ static void encode_attrs(struct xdr_stream *xdr, const struct iattr *iap,
const struct nfs_server *server,
const uint32_t attrmask[])
{
- struct timespec ts;
char owner_name[IDMAP_NAMESZ];
char owner_group[IDMAP_NAMESZ];
int owner_namelen = 0;
@@ -1161,16 +1160,14 @@ static void encode_attrs(struct xdr_stream *xdr, const struct iattr *iap,
if (bmval[1] & FATTR4_WORD1_TIME_ACCESS_SET) {
if (iap->ia_valid & ATTR_ATIME_SET) {
*p++ = cpu_to_be32(NFS4_SET_TO_CLIENT_TIME);
- ts = timespec64_to_timespec(iap->ia_atime);
- p = xdr_encode_nfstime4(p, &ts);
+ p = xdr_encode_nfstime4(p, &iap->ia_atime);
} else
*p++ = cpu_to_be32(NFS4_SET_TO_SERVER_TIME);
}
if (bmval[1] & FATTR4_WORD1_TIME_MODIFY_SET) {
if (iap->ia_valid & ATTR_MTIME_SET) {
*p++ = cpu_to_be32(NFS4_SET_TO_CLIENT_TIME);
- ts = timespec64_to_timespec(iap->ia_mtime);
- p = xdr_encode_nfstime4(p, &ts);
+ p = xdr_encode_nfstime4(p, &iap->ia_mtime);
} else
*p++ = cpu_to_be32(NFS4_SET_TO_SERVER_TIME);
}
@@ -4065,17 +4062,17 @@ static int decode_attr_space_used(struct xdr_stream *xdr, uint32_t *bitmap, uint
}
static __be32 *
-xdr_decode_nfstime4(__be32 *p, struct timespec *t)
+xdr_decode_nfstime4(__be32 *p, struct timespec64 *t)
{
__u64 sec;
p = xdr_decode_hyper(p, &sec);
- t-> tv_sec = (time_t)sec;
+ t-> tv_sec = sec;
t->tv_nsec = be32_to_cpup(p++);
return p;
}
-static int decode_attr_time(struct xdr_stream *xdr, struct timespec *time)
+static int decode_attr_time(struct xdr_stream *xdr, struct timespec64 *time)
{
__be32 *p;
@@ -4086,7 +4083,7 @@ static int decode_attr_time(struct xdr_stream *xdr, struct timespec *time)
return 0;
}
-static int decode_attr_time_access(struct xdr_stream *xdr, uint32_t *bitmap, struct timespec *time)
+static int decode_attr_time_access(struct xdr_stream *xdr, uint32_t *bitmap, struct timespec64 *time)
{
int status = 0;
@@ -4104,7 +4101,7 @@ static int decode_attr_time_access(struct xdr_stream *xdr, uint32_t *bitmap, str
return status;
}
-static int decode_attr_time_metadata(struct xdr_stream *xdr, uint32_t *bitmap, struct timespec *time)
+static int decode_attr_time_metadata(struct xdr_stream *xdr, uint32_t *bitmap, struct timespec64 *time)
{
int status = 0;
@@ -4123,7 +4120,7 @@ static int decode_attr_time_metadata(struct xdr_stream *xdr, uint32_t *bitmap, s
}
static int decode_attr_time_delta(struct xdr_stream *xdr, uint32_t *bitmap,
- struct timespec *time)
+ struct timespec64 *time)
{
int status = 0;
@@ -4186,7 +4183,7 @@ static int decode_attr_security_label(struct xdr_stream *xdr, uint32_t *bitmap,
return status;
}
-static int decode_attr_time_modify(struct xdr_stream *xdr, uint32_t *bitmap, struct timespec *time)
+static int decode_attr_time_modify(struct xdr_stream *xdr, uint32_t *bitmap, struct timespec64 *time)
{
int status = 0;
@@ -7581,6 +7578,7 @@ const struct rpc_procinfo nfs4_procedures[] = {
PROC42(CLONE, enc_clone, dec_clone),
PROC42(COPY, enc_copy, dec_copy),
PROC42(OFFLOAD_CANCEL, enc_offload_cancel, dec_offload_cancel),
+ PROC42(COPY_NOTIFY, enc_copy_notify, dec_copy_notify),
PROC(LOOKUPP, enc_lookupp, dec_lookupp),
PROC42(LAYOUTERROR, enc_layouterror, dec_layouterror),
};
diff --git a/fs/nfs/nfstrace.h b/fs/nfs/nfstrace.h
index 361cc10d6f95..f64a33d2a1d1 100644
--- a/fs/nfs/nfstrace.h
+++ b/fs/nfs/nfstrace.h
@@ -1065,6 +1065,39 @@ TRACE_EVENT(nfs_commit_done,
)
);
+TRACE_EVENT(nfs_fh_to_dentry,
+ TP_PROTO(
+ const struct super_block *sb,
+ const struct nfs_fh *fh,
+ u64 fileid,
+ int error
+ ),
+
+ TP_ARGS(sb, fh, fileid, error),
+
+ TP_STRUCT__entry(
+ __field(int, error)
+ __field(dev_t, dev)
+ __field(u32, fhandle)
+ __field(u64, fileid)
+ ),
+
+ TP_fast_assign(
+ __entry->error = error;
+ __entry->dev = sb->s_dev;
+ __entry->fileid = fileid;
+ __entry->fhandle = nfs_fhandle_hash(fh);
+ ),
+
+ TP_printk(
+ "error=%d fileid=%02x:%02x:%llu fhandle=0x%08x ",
+ __entry->error,
+ MAJOR(__entry->dev), MINOR(__entry->dev),
+ (unsigned long long)__entry->fileid,
+ __entry->fhandle
+ )
+);
+
TRACE_DEFINE_ENUM(NFS_OK);
TRACE_DEFINE_ENUM(NFSERR_PERM);
TRACE_DEFINE_ENUM(NFSERR_NOENT);
diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c
index bb80034a7661..cec3070ab577 100644
--- a/fs/nfs/pnfs.c
+++ b/fs/nfs/pnfs.c
@@ -2160,8 +2160,6 @@ out_unlock:
return NULL;
}
-extern const nfs4_stateid current_stateid;
-
static void _lgopen_prepare_attached(struct nfs4_opendata *data,
struct nfs_open_context *ctx)
{
diff --git a/fs/nfs/super.c b/fs/nfs/super.c
index a84df7d63403..8d8d04bb9d64 100644
--- a/fs/nfs/super.c
+++ b/fs/nfs/super.c
@@ -1592,7 +1592,7 @@ static int nfs_parse_mount_options(char *raw,
dfprintk(MOUNT, "NFS: invalid "
"lookupcache argument\n");
return 0;
- };
+ }
break;
case Opt_fscache_uniq:
if (nfs_get_option_str(args, &mnt->fscache_uniq))
@@ -1625,7 +1625,7 @@ static int nfs_parse_mount_options(char *raw,
dfprintk(MOUNT, "NFS: invalid "
"local_lock argument\n");
return 0;
- };
+ }
break;
/*
@@ -2585,7 +2585,7 @@ static void nfs_get_cache_cookie(struct super_block *sb,
if (mnt_s->fscache_key) {
uniq = mnt_s->fscache_key->key.uniquifier;
ulen = mnt_s->fscache_key->key.uniq_len;
- };
+ }
} else
return;
diff --git a/fs/nfs/sysfs.c b/fs/nfs/sysfs.c
index 4f3390b20239..c489496b5659 100644
--- a/fs/nfs/sysfs.c
+++ b/fs/nfs/sysfs.c
@@ -121,8 +121,7 @@ static void nfs_netns_client_release(struct kobject *kobj)
struct nfs_netns_client,
kobject);
- if (c->identifier)
- kfree(c->identifier);
+ kfree(c->identifier);
kfree(c);
}
diff --git a/fs/nfsd/Kconfig b/fs/nfsd/Kconfig
index 10cefb0c07c7..f2f81561ebb6 100644
--- a/fs/nfsd/Kconfig
+++ b/fs/nfsd/Kconfig
@@ -73,7 +73,8 @@ config NFSD_V4
select NFSD_V3
select FS_POSIX_ACL
select SUNRPC_GSS
- select CRYPTO
+ select CRYPTO_MD5
+ select CRYPTO_SHA256
select GRACE_PERIOD
help
This option enables support in your system's NFS server for
diff --git a/fs/nfsd/filecache.c b/fs/nfsd/filecache.c
index ef55e9b1cd4e..32a9bf22ac08 100644
--- a/fs/nfsd/filecache.c
+++ b/fs/nfsd/filecache.c
@@ -685,8 +685,6 @@ nfsd_file_cache_purge(struct net *net)
void
nfsd_file_cache_shutdown(void)
{
- LIST_HEAD(dispose);
-
set_bit(NFSD_FILE_SHUTDOWN, &nfsd_file_lru_flags);
lease_unregister_notifier(&nfsd_file_lease_notifier);
diff --git a/fs/nfsd/nfs3xdr.c b/fs/nfsd/nfs3xdr.c
index 86e5658651f1..195ab7a0fc89 100644
--- a/fs/nfsd/nfs3xdr.c
+++ b/fs/nfsd/nfs3xdr.c
@@ -863,13 +863,11 @@ compose_entry_fh(struct nfsd3_readdirres *cd, struct svc_fh *fhp,
} else
dchild = dget(dparent);
} else
- dchild = lookup_one_len_unlocked(name, dparent, namlen);
+ dchild = lookup_positive_unlocked(name, dparent, namlen);
if (IS_ERR(dchild))
return rv;
if (d_mountpoint(dchild))
goto out;
- if (d_really_is_negative(dchild))
- goto out;
if (dchild->d_inode->i_ino != ino)
goto out;
rv = fh_compose(fhp, exp, dchild, &cd->fh);
diff --git a/fs/nfsd/nfs4callback.c b/fs/nfsd/nfs4callback.c
index 524111420b48..24534db87e86 100644
--- a/fs/nfsd/nfs4callback.c
+++ b/fs/nfsd/nfs4callback.c
@@ -826,6 +826,31 @@ static int max_cb_time(struct net *net)
return max(nn->nfsd4_lease/10, (time_t)1) * HZ;
}
+static struct workqueue_struct *callback_wq;
+
+static bool nfsd4_queue_cb(struct nfsd4_callback *cb)
+{
+ return queue_work(callback_wq, &cb->cb_work);
+}
+
+static void nfsd41_cb_inflight_begin(struct nfs4_client *clp)
+{
+ atomic_inc(&clp->cl_cb_inflight);
+}
+
+static void nfsd41_cb_inflight_end(struct nfs4_client *clp)
+{
+
+ if (atomic_dec_and_test(&clp->cl_cb_inflight))
+ wake_up_var(&clp->cl_cb_inflight);
+}
+
+static void nfsd41_cb_inflight_wait_complete(struct nfs4_client *clp)
+{
+ wait_var_event(&clp->cl_cb_inflight,
+ !atomic_read(&clp->cl_cb_inflight));
+}
+
static const struct cred *get_backchannel_cred(struct nfs4_client *clp, struct rpc_clnt *client, struct nfsd4_session *ses)
{
if (clp->cl_minorversion == 0) {
@@ -937,14 +962,21 @@ static void nfsd4_cb_probe_done(struct rpc_task *task, void *calldata)
clp->cl_cb_state = NFSD4_CB_UP;
}
+static void nfsd4_cb_probe_release(void *calldata)
+{
+ struct nfs4_client *clp = container_of(calldata, struct nfs4_client, cl_cb_null);
+
+ nfsd41_cb_inflight_end(clp);
+
+}
+
static const struct rpc_call_ops nfsd4_cb_probe_ops = {
/* XXX: release method to ensure we set the cb channel down if
* necessary on early failure? */
.rpc_call_done = nfsd4_cb_probe_done,
+ .rpc_release = nfsd4_cb_probe_release,
};
-static struct workqueue_struct *callback_wq;
-
/*
* Poke the callback thread to process any updates to the callback
* parameters, and send a null probe.
@@ -975,9 +1007,12 @@ void nfsd4_change_callback(struct nfs4_client *clp, struct nfs4_cb_conn *conn)
* If the slot is available, then mark it busy. Otherwise, set the
* thread for sleeping on the callback RPC wait queue.
*/
-static bool nfsd41_cb_get_slot(struct nfs4_client *clp, struct rpc_task *task)
+static bool nfsd41_cb_get_slot(struct nfsd4_callback *cb, struct rpc_task *task)
{
- if (test_and_set_bit(0, &clp->cl_cb_slot_busy) != 0) {
+ struct nfs4_client *clp = cb->cb_clp;
+
+ if (!cb->cb_holds_slot &&
+ test_and_set_bit(0, &clp->cl_cb_slot_busy) != 0) {
rpc_sleep_on(&clp->cl_cb_waitq, task, NULL);
/* Race breaker */
if (test_and_set_bit(0, &clp->cl_cb_slot_busy) != 0) {
@@ -986,9 +1021,31 @@ static bool nfsd41_cb_get_slot(struct nfs4_client *clp, struct rpc_task *task)
}
rpc_wake_up_queued_task(&clp->cl_cb_waitq, task);
}
+ cb->cb_holds_slot = true;
return true;
}
+static void nfsd41_cb_release_slot(struct nfsd4_callback *cb)
+{
+ struct nfs4_client *clp = cb->cb_clp;
+
+ if (cb->cb_holds_slot) {
+ cb->cb_holds_slot = false;
+ clear_bit(0, &clp->cl_cb_slot_busy);
+ rpc_wake_up_next(&clp->cl_cb_waitq);
+ }
+}
+
+static void nfsd41_destroy_cb(struct nfsd4_callback *cb)
+{
+ struct nfs4_client *clp = cb->cb_clp;
+
+ nfsd41_cb_release_slot(cb);
+ if (cb->cb_ops && cb->cb_ops->release)
+ cb->cb_ops->release(cb);
+ nfsd41_cb_inflight_end(clp);
+}
+
/*
* TODO: cb_sequence should support referring call lists, cachethis, multiple
* slots, and mark callback channel down on communication errors.
@@ -1005,11 +1062,8 @@ static void nfsd4_cb_prepare(struct rpc_task *task, void *calldata)
*/
cb->cb_seq_status = 1;
cb->cb_status = 0;
- if (minorversion) {
- if (!cb->cb_holds_slot && !nfsd41_cb_get_slot(clp, task))
- return;
- cb->cb_holds_slot = true;
- }
+ if (minorversion && !nfsd41_cb_get_slot(cb, task))
+ return;
rpc_call_start(task);
}
@@ -1072,13 +1126,12 @@ static bool nfsd4_cb_sequence_done(struct rpc_task *task, struct nfsd4_callback
}
break;
default:
+ nfsd4_mark_cb_fault(cb->cb_clp, cb->cb_seq_status);
dprintk("%s: unprocessed error %d\n", __func__,
cb->cb_seq_status);
}
- cb->cb_holds_slot = false;
- clear_bit(0, &clp->cl_cb_slot_busy);
- rpc_wake_up_next(&clp->cl_cb_waitq);
+ nfsd41_cb_release_slot(cb);
dprintk("%s: freed slot, new seqid=%d\n", __func__,
clp->cl_cb_session->se_cb_seq_nr);
@@ -1091,8 +1144,10 @@ retry_nowait:
ret = false;
goto out;
need_restart:
- task->tk_status = 0;
- cb->cb_need_restart = true;
+ if (!test_bit(NFSD4_CLIENT_CB_KILL, &clp->cl_flags)) {
+ task->tk_status = 0;
+ cb->cb_need_restart = true;
+ }
return false;
}
@@ -1134,9 +1189,9 @@ static void nfsd4_cb_release(void *calldata)
struct nfsd4_callback *cb = calldata;
if (cb->cb_need_restart)
- nfsd4_run_cb(cb);
+ nfsd4_queue_cb(cb);
else
- cb->cb_ops->release(cb);
+ nfsd41_destroy_cb(cb);
}
@@ -1170,6 +1225,7 @@ void nfsd4_shutdown_callback(struct nfs4_client *clp)
*/
nfsd4_run_cb(&clp->cl_cb_null);
flush_workqueue(callback_wq);
+ nfsd41_cb_inflight_wait_complete(clp);
}
/* requires cl_lock: */
@@ -1187,6 +1243,12 @@ static struct nfsd4_conn * __nfsd4_find_backchannel(struct nfs4_client *clp)
return NULL;
}
+/*
+ * Note there isn't a lot of locking in this code; instead we depend on
+ * the fact that it is run from the callback_wq, which won't run two
+ * work items at once. So, for example, callback_wq handles all access
+ * of cl_cb_client and all calls to rpc_create or rpc_shutdown_client.
+ */
static void nfsd4_process_cb_update(struct nfsd4_callback *cb)
{
struct nfs4_cb_conn conn;
@@ -1255,8 +1317,7 @@ nfsd4_run_cb_work(struct work_struct *work)
clnt = clp->cl_cb_client;
if (!clnt) {
/* Callback channel broken, or client killed; give up: */
- if (cb->cb_ops && cb->cb_ops->release)
- cb->cb_ops->release(cb);
+ nfsd41_destroy_cb(cb);
return;
}
@@ -1265,6 +1326,7 @@ nfsd4_run_cb_work(struct work_struct *work)
*/
if (!cb->cb_ops && clp->cl_minorversion) {
clp->cl_cb_state = NFSD4_CB_UP;
+ nfsd41_destroy_cb(cb);
return;
}
@@ -1290,5 +1352,9 @@ void nfsd4_init_cb(struct nfsd4_callback *cb, struct nfs4_client *clp,
void nfsd4_run_cb(struct nfsd4_callback *cb)
{
- queue_work(callback_wq, &cb->cb_work);
+ struct nfs4_client *clp = cb->cb_clp;
+
+ nfsd41_cb_inflight_begin(clp);
+ if (!nfsd4_queue_cb(cb))
+ nfsd41_cb_inflight_end(clp);
}
diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c
index 4e3e77b76411..4798667af647 100644
--- a/fs/nfsd/nfs4proc.c
+++ b/fs/nfsd/nfs4proc.c
@@ -1077,7 +1077,8 @@ nfsd4_clone(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
goto out;
status = nfsd4_clone_file_range(src->nf_file, clone->cl_src_pos,
- dst->nf_file, clone->cl_dst_pos, clone->cl_count);
+ dst->nf_file, clone->cl_dst_pos, clone->cl_count,
+ EX_ISSYNC(cstate->current_fh.fh_export));
nfsd_file_put(dst);
nfsd_file_put(src);
@@ -1297,7 +1298,8 @@ nfsd4_copy(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
out:
return status;
out_err:
- cleanup_async_copy(async_copy);
+ if (async_copy)
+ cleanup_async_copy(async_copy);
goto out;
}
diff --git a/fs/nfsd/nfs4recover.c b/fs/nfsd/nfs4recover.c
index cdc75ad4438b..2481e7662128 100644
--- a/fs/nfsd/nfs4recover.c
+++ b/fs/nfsd/nfs4recover.c
@@ -1578,6 +1578,7 @@ nfsd4_cld_tracking_init(struct net *net)
struct nfsd_net *nn = net_generic(net, nfsd_net_id);
bool running;
int retries = 10;
+ struct crypto_shash *tfm;
status = nfs4_cld_state_init(net);
if (status)
@@ -1586,11 +1587,6 @@ nfsd4_cld_tracking_init(struct net *net)
status = __nfsd4_init_cld_pipe(net);
if (status)
goto err_shutdown;
- nn->cld_net->cn_tfm = crypto_alloc_shash("sha256", 0, 0);
- if (IS_ERR(nn->cld_net->cn_tfm)) {
- status = PTR_ERR(nn->cld_net->cn_tfm);
- goto err_remove;
- }
/*
* rpc pipe upcalls take 30 seconds to time out, so we don't want to
@@ -1607,6 +1603,12 @@ nfsd4_cld_tracking_init(struct net *net)
status = -ETIMEDOUT;
goto err_remove;
}
+ tfm = crypto_alloc_shash("sha256", 0, 0);
+ if (IS_ERR(tfm)) {
+ status = PTR_ERR(tfm);
+ goto err_remove;
+ }
+ nn->cld_net->cn_tfm = tfm;
status = nfsd4_cld_get_version(nn);
if (status == -EOPNOTSUPP)
@@ -1850,19 +1852,14 @@ nfsd4_umh_cltrack_upcall(char *cmd, char *arg, char *env0, char *env1)
static char *
bin_to_hex_dup(const unsigned char *src, int srclen)
{
- int i;
- char *buf, *hex;
+ char *buf;
/* +1 for terminating NULL */
- buf = kmalloc((srclen * 2) + 1, GFP_KERNEL);
+ buf = kzalloc((srclen * 2) + 1, GFP_KERNEL);
if (!buf)
return buf;
- hex = buf;
- for (i = 0; i < srclen; i++) {
- sprintf(hex, "%2.2x", *src++);
- hex += 2;
- }
+ bin2hex(buf, src, srclen);
return buf;
}
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index c65aeaa812d4..369e574c5092 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -2382,10 +2382,10 @@ static int nfs4_show_open(struct seq_file *s, struct nfs4_stid *st)
access = bmap_to_share_mode(ols->st_access_bmap);
deny = bmap_to_share_mode(ols->st_deny_bmap);
- seq_printf(s, "access: \%s\%s, ",
+ seq_printf(s, "access: %s%s, ",
access & NFS4_SHARE_ACCESS_READ ? "r" : "-",
access & NFS4_SHARE_ACCESS_WRITE ? "w" : "-");
- seq_printf(s, "deny: \%s\%s, ",
+ seq_printf(s, "deny: %s%s, ",
deny & NFS4_SHARE_ACCESS_READ ? "r" : "-",
deny & NFS4_SHARE_ACCESS_WRITE ? "w" : "-");
@@ -3548,12 +3548,17 @@ static bool replay_matches_cache(struct svc_rqst *rqstp,
(bool)seq->cachethis)
return false;
/*
- * If there's an error than the reply can have fewer ops than
- * the call. But if we cached a reply with *more* ops than the
- * call you're sending us now, then this new call is clearly not
- * really a replay of the old one:
+ * If there's an error then the reply can have fewer ops than
+ * the call.
*/
- if (slot->sl_opcnt < argp->opcnt)
+ if (slot->sl_opcnt < argp->opcnt && !slot->sl_status)
+ return false;
+ /*
+ * But if we cached a reply with *more* ops than the call you're
+ * sending us now, then this new call is clearly not really a
+ * replay of the old one:
+ */
+ if (slot->sl_opcnt > argp->opcnt)
return false;
/* This is the only check explicitly called by spec: */
if (!same_creds(&rqstp->rq_cred, &slot->sl_cred))
diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c
index 533d0fc3c96b..d2dc4c0e22e8 100644
--- a/fs/nfsd/nfs4xdr.c
+++ b/fs/nfsd/nfs4xdr.c
@@ -2991,18 +2991,9 @@ nfsd4_encode_dirent_fattr(struct xdr_stream *xdr, struct nfsd4_readdir *cd,
__be32 nfserr;
int ignore_crossmnt = 0;
- dentry = lookup_one_len_unlocked(name, cd->rd_fhp->fh_dentry, namlen);
+ dentry = lookup_positive_unlocked(name, cd->rd_fhp->fh_dentry, namlen);
if (IS_ERR(dentry))
return nfserrno(PTR_ERR(dentry));
- if (d_really_is_negative(dentry)) {
- /*
- * we're not holding the i_mutex here, so there's
- * a window where this directory entry could have gone
- * away.
- */
- dput(dentry);
- return nfserr_noent;
- }
exp_get(exp);
/*
@@ -3461,7 +3452,6 @@ static __be32 nfsd4_encode_splice_read(
struct xdr_stream *xdr = &resp->xdr;
struct xdr_buf *buf = xdr->buf;
u32 eof;
- long len;
int space_left;
__be32 nfserr;
__be32 *p = xdr->p - 2;
@@ -3470,7 +3460,6 @@ static __be32 nfsd4_encode_splice_read(
if (xdr->end - xdr->p < 1)
return nfserr_resource;
- len = maxcount;
nfserr = nfsd_splice_read(read->rd_rqstp, read->rd_fhp,
file, read->rd_offset, &maxcount, &eof);
read->rd_length = maxcount;
diff --git a/fs/nfsd/nfsd.h b/fs/nfsd/nfsd.h
index af2947551e9c..57b93d95fa5c 100644
--- a/fs/nfsd/nfsd.h
+++ b/fs/nfsd/nfsd.h
@@ -280,7 +280,8 @@ void nfsd_lockd_shutdown(void);
#define nfserr_union_notsupp cpu_to_be32(NFS4ERR_UNION_NOTSUPP)
#define nfserr_offload_denied cpu_to_be32(NFS4ERR_OFFLOAD_DENIED)
#define nfserr_wrong_lfs cpu_to_be32(NFS4ERR_WRONG_LFS)
-#define nfserr_badlabel cpu_to_be32(NFS4ERR_BADLABEL)
+#define nfserr_badlabel cpu_to_be32(NFS4ERR_BADLABEL)
+#define nfserr_file_open cpu_to_be32(NFS4ERR_FILE_OPEN)
/* error codes for internal use */
/* if a request fails due to kmalloc failure, it gets dropped.
diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c
index fdf7ed4bd5dd..e8bee8ff30c5 100644
--- a/fs/nfsd/nfssvc.c
+++ b/fs/nfsd/nfssvc.c
@@ -95,12 +95,11 @@ static const struct svc_version *nfsd_acl_version[] = {
#define NFSD_ACL_MINVERS 2
#define NFSD_ACL_NRVERS ARRAY_SIZE(nfsd_acl_version)
-static const struct svc_version *nfsd_acl_versions[NFSD_ACL_NRVERS];
static struct svc_program nfsd_acl_program = {
.pg_prog = NFS_ACL_PROGRAM,
.pg_nvers = NFSD_ACL_NRVERS,
- .pg_vers = nfsd_acl_versions,
+ .pg_vers = nfsd_acl_version,
.pg_name = "nfsacl",
.pg_class = "nfsd",
.pg_stats = &nfsd_acl_svcstats,
diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h
index 46f56afb6cb8..d61b83b9654c 100644
--- a/fs/nfsd/state.h
+++ b/fs/nfsd/state.h
@@ -367,6 +367,7 @@ struct nfs4_client {
struct net *net;
struct list_head async_copies; /* list of async copies */
spinlock_t async_lock; /* lock for async copies */
+ atomic_t cl_cb_inflight; /* Outstanding callbacks */
};
/* struct nfs4_client_reset
diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c
index bd0a385df3fc..c0dc491537a6 100644
--- a/fs/nfsd/vfs.c
+++ b/fs/nfsd/vfs.c
@@ -525,7 +525,7 @@ __be32 nfsd4_set_nfs4_label(struct svc_rqst *rqstp, struct svc_fh *fhp,
#endif
__be32 nfsd4_clone_file_range(struct file *src, u64 src_pos, struct file *dst,
- u64 dst_pos, u64 count)
+ u64 dst_pos, u64 count, bool sync)
{
loff_t cloned;
@@ -534,6 +534,12 @@ __be32 nfsd4_clone_file_range(struct file *src, u64 src_pos, struct file *dst,
return nfserrno(cloned);
if (count && cloned != count)
return nfserrno(-EINVAL);
+ if (sync) {
+ loff_t dst_end = count ? dst_pos + count - 1 : LLONG_MAX;
+ int status = vfs_fsync_range(dst, dst_pos, dst_end, 0);
+ if (status < 0)
+ return nfserrno(status);
+ }
return 0;
}
@@ -1809,7 +1815,17 @@ nfsd_unlink(struct svc_rqst *rqstp, struct svc_fh *fhp, int type,
out_drop_write:
fh_drop_write(fhp);
out_nfserr:
- err = nfserrno(host_err);
+ if (host_err == -EBUSY) {
+ /* name is mounted-on. There is no perfect
+ * error status.
+ */
+ if (nfsd_v4client(rqstp))
+ err = nfserr_file_open;
+ else
+ err = nfserr_acces;
+ } else {
+ err = nfserrno(host_err);
+ }
out:
return err;
}
diff --git a/fs/nfsd/vfs.h b/fs/nfsd/vfs.h
index a13fd9d7e1f5..cc110a10bfe8 100644
--- a/fs/nfsd/vfs.h
+++ b/fs/nfsd/vfs.h
@@ -56,7 +56,7 @@ __be32 nfsd4_set_nfs4_label(struct svc_rqst *, struct svc_fh *,
__be32 nfsd4_vfs_fallocate(struct svc_rqst *, struct svc_fh *,
struct file *, loff_t, loff_t, int);
__be32 nfsd4_clone_file_range(struct file *, u64, struct file *,
- u64, u64);
+ u64, u64, bool);
#endif /* CONFIG_NFSD_V4 */
__be32 nfsd_create_locked(struct svc_rqst *, struct svc_fh *,
char *name, int len, struct iattr *attrs,
diff --git a/fs/nilfs2/ioctl.c b/fs/nilfs2/ioctl.c
index 91b9dac6b2cc..4ba73dbf3e8d 100644
--- a/fs/nilfs2/ioctl.c
+++ b/fs/nilfs2/ioctl.c
@@ -1354,6 +1354,7 @@ long nilfs_compat_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
case NILFS_IOCTL_SYNC:
case NILFS_IOCTL_RESIZE:
case NILFS_IOCTL_SET_ALLOC_RANGE:
+ case FITRIM:
break;
default:
return -ENOIOCTLCMD;
diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c
index 8508ab575017..0aa362b88550 100644
--- a/fs/notify/fanotify/fanotify_user.c
+++ b/fs/notify/fanotify/fanotify_user.c
@@ -523,7 +523,7 @@ static const struct file_operations fanotify_fops = {
.fasync = NULL,
.release = fanotify_release,
.unlocked_ioctl = fanotify_ioctl,
- .compat_ioctl = fanotify_ioctl,
+ .compat_ioctl = compat_ptr_ioctl,
.llseek = noop_llseek,
};
diff --git a/fs/notify/fdinfo.c b/fs/notify/fdinfo.c
index 1e2bfd26b352..ef83f4020554 100644
--- a/fs/notify/fdinfo.c
+++ b/fs/notify/fdinfo.c
@@ -50,7 +50,7 @@ static void show_mark_fhandle(struct seq_file *m, struct inode *inode)
f.handle.handle_bytes = sizeof(f.pad);
size = f.handle.handle_bytes >> 2;
- ret = exportfs_encode_inode_fh(inode, (struct fid *)f.handle.f_handle, &size, 0);
+ ret = exportfs_encode_inode_fh(inode, (struct fid *)f.handle.f_handle, &size, NULL);
if ((ret == FILEID_INVALID) || (ret < 0)) {
WARN_ONCE(1, "Can't encode file handler for inotify: %d\n", ret);
return;
diff --git a/fs/notify/fsnotify.c b/fs/notify/fsnotify.c
index 2ecef6155fc0..3e77b728a22b 100644
--- a/fs/notify/fsnotify.c
+++ b/fs/notify/fsnotify.c
@@ -381,8 +381,6 @@ out:
}
EXPORT_SYMBOL_GPL(fsnotify);
-extern struct kmem_cache *fsnotify_mark_connector_cachep;
-
static __init int fsnotify_init(void)
{
int ret;
diff --git a/fs/notify/fsnotify.h b/fs/notify/fsnotify.h
index f3462828a0e2..ff2063ec6b0f 100644
--- a/fs/notify/fsnotify.h
+++ b/fs/notify/fsnotify.h
@@ -65,4 +65,6 @@ extern void __fsnotify_update_child_dentry_flags(struct inode *inode);
extern struct fsnotify_event_holder *fsnotify_alloc_event_holder(void);
extern void fsnotify_destroy_event_holder(struct fsnotify_event_holder *holder);
+extern struct kmem_cache *fsnotify_mark_connector_cachep;
+
#endif /* __FS_NOTIFY_FSNOTIFY_H_ */
diff --git a/fs/ocfs2/acl.c b/fs/ocfs2/acl.c
index 3e7da392aa6f..bb981ec76456 100644
--- a/fs/ocfs2/acl.c
+++ b/fs/ocfs2/acl.c
@@ -327,8 +327,8 @@ int ocfs2_acl_chmod(struct inode *inode, struct buffer_head *bh)
down_read(&OCFS2_I(inode)->ip_xattr_sem);
acl = ocfs2_get_acl_nolock(inode, ACL_TYPE_ACCESS, bh);
up_read(&OCFS2_I(inode)->ip_xattr_sem);
- if (IS_ERR(acl) || !acl)
- return PTR_ERR(acl);
+ if (IS_ERR_OR_NULL(acl))
+ return PTR_ERR_OR_ZERO(acl);
ret = __posix_acl_chmod(&acl, GFP_KERNEL, inode->i_mode);
if (ret)
return ret;
diff --git a/fs/ocfs2/alloc.c b/fs/ocfs2/alloc.c
index f9baefc76cf9..88534eb0e7c2 100644
--- a/fs/ocfs2/alloc.c
+++ b/fs/ocfs2/alloc.c
@@ -2288,9 +2288,9 @@ static int ocfs2_extend_rotate_transaction(handle_t *handle, int subtree_depth,
int ret = 0;
int credits = (path->p_tree_depth - subtree_depth) * 2 + 1 + op_credits;
- if (handle->h_buffer_credits < credits)
+ if (jbd2_handle_buffer_credits(handle) < credits)
ret = ocfs2_extend_trans(handle,
- credits - handle->h_buffer_credits);
+ credits - jbd2_handle_buffer_credits(handle));
return ret;
}
@@ -2367,7 +2367,7 @@ static int ocfs2_rotate_tree_right(handle_t *handle,
struct ocfs2_path *right_path,
struct ocfs2_path **ret_left_path)
{
- int ret, start, orig_credits = handle->h_buffer_credits;
+ int ret, start, orig_credits = jbd2_handle_buffer_credits(handle);
u32 cpos;
struct ocfs2_path *left_path = NULL;
struct super_block *sb = ocfs2_metadata_cache_get_super(et->et_ci);
@@ -3148,7 +3148,7 @@ static int ocfs2_rotate_tree_left(handle_t *handle,
struct ocfs2_path *path,
struct ocfs2_cached_dealloc_ctxt *dealloc)
{
- int ret, orig_credits = handle->h_buffer_credits;
+ int ret, orig_credits = jbd2_handle_buffer_credits(handle);
struct ocfs2_path *tmp_path = NULL, *restart_path = NULL;
struct ocfs2_extent_block *eb;
struct ocfs2_extent_list *el;
@@ -3386,8 +3386,8 @@ static int ocfs2_merge_rec_right(struct ocfs2_path *left_path,
right_path);
ret = ocfs2_extend_rotate_transaction(handle, subtree_index,
- handle->h_buffer_credits,
- right_path);
+ jbd2_handle_buffer_credits(handle),
+ right_path);
if (ret) {
mlog_errno(ret);
goto out;
@@ -3548,8 +3548,8 @@ static int ocfs2_merge_rec_left(struct ocfs2_path *right_path,
right_path);
ret = ocfs2_extend_rotate_transaction(handle, subtree_index,
- handle->h_buffer_credits,
- left_path);
+ jbd2_handle_buffer_credits(handle),
+ left_path);
if (ret) {
mlog_errno(ret);
goto out;
@@ -3623,7 +3623,7 @@ static int ocfs2_merge_rec_left(struct ocfs2_path *right_path,
le16_to_cpu(el->l_next_free_rec) == 1) {
/* extend credit for ocfs2_remove_rightmost_path */
ret = ocfs2_extend_rotate_transaction(handle, 0,
- handle->h_buffer_credits,
+ jbd2_handle_buffer_credits(handle),
right_path);
if (ret) {
mlog_errno(ret);
@@ -3669,7 +3669,7 @@ static int ocfs2_try_to_merge_extent(handle_t *handle,
if (ctxt->c_split_covers_rec && ctxt->c_has_empty_extent) {
/* extend credit for ocfs2_remove_rightmost_path */
ret = ocfs2_extend_rotate_transaction(handle, 0,
- handle->h_buffer_credits,
+ jbd2_handle_buffer_credits(handle),
path);
if (ret) {
mlog_errno(ret);
@@ -3725,7 +3725,7 @@ static int ocfs2_try_to_merge_extent(handle_t *handle,
/* extend credit for ocfs2_remove_rightmost_path */
ret = ocfs2_extend_rotate_transaction(handle, 0,
- handle->h_buffer_credits,
+ jbd2_handle_buffer_credits(handle),
path);
if (ret) {
mlog_errno(ret);
@@ -3755,7 +3755,7 @@ static int ocfs2_try_to_merge_extent(handle_t *handle,
/* extend credit for ocfs2_remove_rightmost_path */
ret = ocfs2_extend_rotate_transaction(handle, 0,
- handle->h_buffer_credits,
+ jbd2_handle_buffer_credits(handle),
path);
if (ret) {
mlog_errno(ret);
@@ -3799,7 +3799,7 @@ static int ocfs2_try_to_merge_extent(handle_t *handle,
if (ctxt->c_split_covers_rec) {
/* extend credit for ocfs2_remove_rightmost_path */
ret = ocfs2_extend_rotate_transaction(handle, 0,
- handle->h_buffer_credits,
+ jbd2_handle_buffer_credits(handle),
path);
if (ret) {
mlog_errno(ret);
@@ -5358,7 +5358,7 @@ static int ocfs2_truncate_rec(handle_t *handle,
if (ocfs2_is_empty_extent(&el->l_recs[0]) && index > 0) {
/* extend credit for ocfs2_remove_rightmost_path */
ret = ocfs2_extend_rotate_transaction(handle, 0,
- handle->h_buffer_credits,
+ jbd2_handle_buffer_credits(handle),
path);
if (ret) {
mlog_errno(ret);
@@ -5427,8 +5427,8 @@ static int ocfs2_truncate_rec(handle_t *handle,
}
ret = ocfs2_extend_rotate_transaction(handle, 0,
- handle->h_buffer_credits,
- path);
+ jbd2_handle_buffer_credits(handle),
+ path);
if (ret) {
mlog_errno(ret);
goto out;
diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c
index 9cd0a6815933..3a67a6518ddf 100644
--- a/fs/ocfs2/aops.c
+++ b/fs/ocfs2/aops.c
@@ -11,7 +11,6 @@
#include <linux/pagemap.h>
#include <asm/byteorder.h>
#include <linux/swap.h>
-#include <linux/pipe_fs_i.h>
#include <linux/mpage.h>
#include <linux/quotaops.h>
#include <linux/blkdev.h>
diff --git a/fs/ocfs2/dlmglue.c b/fs/ocfs2/dlmglue.c
index 6e774c5ea13b..1c4c51f3df60 100644
--- a/fs/ocfs2/dlmglue.c
+++ b/fs/ocfs2/dlmglue.c
@@ -1687,7 +1687,7 @@ static void __ocfs2_cluster_unlock(struct ocfs2_super *osb,
spin_unlock_irqrestore(&lockres->l_lock, flags);
#ifdef CONFIG_DEBUG_LOCK_ALLOC
if (lockres->l_lockdep_map.key != NULL)
- rwsem_release(&lockres->l_lockdep_map, 1, caller_ip);
+ rwsem_release(&lockres->l_lockdep_map, caller_ip);
#endif
}
diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c
index 2e982db3e1ae..9876db52913a 100644
--- a/fs/ocfs2/file.c
+++ b/fs/ocfs2/file.c
@@ -1230,6 +1230,7 @@ int ocfs2_setattr(struct dentry *dentry, struct iattr *attr)
transfer_to[USRQUOTA] = dqget(sb, make_kqid_uid(attr->ia_uid));
if (IS_ERR(transfer_to[USRQUOTA])) {
status = PTR_ERR(transfer_to[USRQUOTA]);
+ transfer_to[USRQUOTA] = NULL;
goto bail_unlock;
}
}
@@ -1239,6 +1240,7 @@ int ocfs2_setattr(struct dentry *dentry, struct iattr *attr)
transfer_to[GRPQUOTA] = dqget(sb, make_kqid_gid(attr->ia_gid));
if (IS_ERR(transfer_to[GRPQUOTA])) {
status = PTR_ERR(transfer_to[GRPQUOTA]);
+ transfer_to[GRPQUOTA] = NULL;
goto bail_unlock;
}
}
@@ -2096,53 +2098,89 @@ static int ocfs2_is_io_unaligned(struct inode *inode, size_t count, loff_t pos)
return 0;
}
-static int ocfs2_prepare_inode_for_refcount(struct inode *inode,
- struct file *file,
- loff_t pos, size_t count,
- int *meta_level)
+static int ocfs2_inode_lock_for_extent_tree(struct inode *inode,
+ struct buffer_head **di_bh,
+ int meta_level,
+ int overwrite_io,
+ int write_sem,
+ int wait)
{
- int ret;
- struct buffer_head *di_bh = NULL;
- u32 cpos = pos >> OCFS2_SB(inode->i_sb)->s_clustersize_bits;
- u32 clusters =
- ocfs2_clusters_for_bytes(inode->i_sb, pos + count) - cpos;
+ int ret = 0;
- ret = ocfs2_inode_lock(inode, &di_bh, 1);
- if (ret) {
- mlog_errno(ret);
+ if (wait)
+ ret = ocfs2_inode_lock(inode, NULL, meta_level);
+ else
+ ret = ocfs2_try_inode_lock(inode,
+ overwrite_io ? NULL : di_bh, meta_level);
+ if (ret < 0)
goto out;
+
+ if (wait) {
+ if (write_sem)
+ down_write(&OCFS2_I(inode)->ip_alloc_sem);
+ else
+ down_read(&OCFS2_I(inode)->ip_alloc_sem);
+ } else {
+ if (write_sem)
+ ret = down_write_trylock(&OCFS2_I(inode)->ip_alloc_sem);
+ else
+ ret = down_read_trylock(&OCFS2_I(inode)->ip_alloc_sem);
+
+ if (!ret) {
+ ret = -EAGAIN;
+ goto out_unlock;
+ }
}
- *meta_level = 1;
+ return ret;
- ret = ocfs2_refcount_cow(inode, di_bh, cpos, clusters, UINT_MAX);
- if (ret)
- mlog_errno(ret);
+out_unlock:
+ brelse(*di_bh);
+ ocfs2_inode_unlock(inode, meta_level);
out:
- brelse(di_bh);
return ret;
}
+static void ocfs2_inode_unlock_for_extent_tree(struct inode *inode,
+ struct buffer_head **di_bh,
+ int meta_level,
+ int write_sem)
+{
+ if (write_sem)
+ up_write(&OCFS2_I(inode)->ip_alloc_sem);
+ else
+ up_read(&OCFS2_I(inode)->ip_alloc_sem);
+
+ brelse(*di_bh);
+ *di_bh = NULL;
+
+ if (meta_level >= 0)
+ ocfs2_inode_unlock(inode, meta_level);
+}
+
static int ocfs2_prepare_inode_for_write(struct file *file,
loff_t pos, size_t count, int wait)
{
int ret = 0, meta_level = 0, overwrite_io = 0;
+ int write_sem = 0;
struct dentry *dentry = file->f_path.dentry;
struct inode *inode = d_inode(dentry);
struct buffer_head *di_bh = NULL;
+ u32 cpos;
+ u32 clusters;
/*
* We start with a read level meta lock and only jump to an ex
* if we need to make modifications here.
*/
for(;;) {
- if (wait)
- ret = ocfs2_inode_lock(inode, NULL, meta_level);
- else
- ret = ocfs2_try_inode_lock(inode,
- overwrite_io ? NULL : &di_bh, meta_level);
+ ret = ocfs2_inode_lock_for_extent_tree(inode,
+ &di_bh,
+ meta_level,
+ overwrite_io,
+ write_sem,
+ wait);
if (ret < 0) {
- meta_level = -1;
if (ret != -EAGAIN)
mlog_errno(ret);
goto out;
@@ -2154,15 +2192,8 @@ static int ocfs2_prepare_inode_for_write(struct file *file,
*/
if (!wait && !overwrite_io) {
overwrite_io = 1;
- if (!down_read_trylock(&OCFS2_I(inode)->ip_alloc_sem)) {
- ret = -EAGAIN;
- goto out_unlock;
- }
ret = ocfs2_overwrite_io(inode, di_bh, pos, count);
- brelse(di_bh);
- di_bh = NULL;
- up_read(&OCFS2_I(inode)->ip_alloc_sem);
if (ret < 0) {
if (ret != -EAGAIN)
mlog_errno(ret);
@@ -2181,7 +2212,10 @@ static int ocfs2_prepare_inode_for_write(struct file *file,
* set inode->i_size at the end of a write. */
if (should_remove_suid(dentry)) {
if (meta_level == 0) {
- ocfs2_inode_unlock(inode, meta_level);
+ ocfs2_inode_unlock_for_extent_tree(inode,
+ &di_bh,
+ meta_level,
+ write_sem);
meta_level = 1;
continue;
}
@@ -2195,18 +2229,32 @@ static int ocfs2_prepare_inode_for_write(struct file *file,
ret = ocfs2_check_range_for_refcount(inode, pos, count);
if (ret == 1) {
- ocfs2_inode_unlock(inode, meta_level);
- meta_level = -1;
-
- ret = ocfs2_prepare_inode_for_refcount(inode,
- file,
- pos,
- count,
- &meta_level);
+ ocfs2_inode_unlock_for_extent_tree(inode,
+ &di_bh,
+ meta_level,
+ write_sem);
+ ret = ocfs2_inode_lock_for_extent_tree(inode,
+ &di_bh,
+ meta_level,
+ overwrite_io,
+ 1,
+ wait);
+ write_sem = 1;
+ if (ret < 0) {
+ if (ret != -EAGAIN)
+ mlog_errno(ret);
+ goto out;
+ }
+
+ cpos = pos >> OCFS2_SB(inode->i_sb)->s_clustersize_bits;
+ clusters =
+ ocfs2_clusters_for_bytes(inode->i_sb, pos + count) - cpos;
+ ret = ocfs2_refcount_cow(inode, di_bh, cpos, clusters, UINT_MAX);
}
if (ret < 0) {
- mlog_errno(ret);
+ if (ret != -EAGAIN)
+ mlog_errno(ret);
goto out_unlock;
}
@@ -2217,10 +2265,10 @@ out_unlock:
trace_ocfs2_prepare_inode_for_write(OCFS2_I(inode)->ip_blkno,
pos, count, wait);
- brelse(di_bh);
-
- if (meta_level >= 0)
- ocfs2_inode_unlock(inode, meta_level);
+ ocfs2_inode_unlock_for_extent_tree(inode,
+ &di_bh,
+ meta_level,
+ write_sem);
out:
return ret;
diff --git a/fs/ocfs2/ioctl.c b/fs/ocfs2/ioctl.c
index efeea208fdeb..89984172fc4a 100644
--- a/fs/ocfs2/ioctl.c
+++ b/fs/ocfs2/ioctl.c
@@ -985,6 +985,7 @@ long ocfs2_compat_ioctl(struct file *file, unsigned cmd, unsigned long arg)
return -EFAULT;
return ocfs2_info_handle(inode, &info, 1);
+ case FITRIM:
case OCFS2_IOC_MOVE_EXT:
break;
default:
diff --git a/fs/ocfs2/journal.c b/fs/ocfs2/journal.c
index 930e3d388579..1afe57f425a0 100644
--- a/fs/ocfs2/journal.c
+++ b/fs/ocfs2/journal.c
@@ -217,7 +217,8 @@ void ocfs2_recovery_exit(struct ocfs2_super *osb)
/* At this point, we know that no more recovery threads can be
* launched, so wait for any recovery completion work to
* complete. */
- flush_workqueue(osb->ocfs2_wq);
+ if (osb->ocfs2_wq)
+ flush_workqueue(osb->ocfs2_wq);
/*
* Now that recovery is shut down, and the osb is about to be
@@ -419,14 +420,14 @@ int ocfs2_extend_trans(handle_t *handle, int nblocks)
if (!nblocks)
return 0;
- old_nblocks = handle->h_buffer_credits;
+ old_nblocks = jbd2_handle_buffer_credits(handle);
trace_ocfs2_extend_trans(old_nblocks, nblocks);
#ifdef CONFIG_OCFS2_DEBUG_FS
status = 1;
#else
- status = jbd2_journal_extend(handle, nblocks);
+ status = jbd2_journal_extend(handle, nblocks, 0);
if (status < 0) {
mlog_errno(status);
goto bail;
@@ -460,13 +461,13 @@ int ocfs2_allocate_extend_trans(handle_t *handle, int thresh)
BUG_ON(!handle);
- old_nblks = handle->h_buffer_credits;
+ old_nblks = jbd2_handle_buffer_credits(handle);
trace_ocfs2_allocate_extend_trans(old_nblks, thresh);
if (old_nblks < thresh)
return 0;
- status = jbd2_journal_extend(handle, OCFS2_MAX_TRANS_DATA);
+ status = jbd2_journal_extend(handle, OCFS2_MAX_TRANS_DATA, 0);
if (status < 0) {
mlog_errno(status);
goto bail;
diff --git a/fs/ocfs2/localalloc.c b/fs/ocfs2/localalloc.c
index 158e5af767fd..720e9f94957e 100644
--- a/fs/ocfs2/localalloc.c
+++ b/fs/ocfs2/localalloc.c
@@ -377,7 +377,8 @@ void ocfs2_shutdown_local_alloc(struct ocfs2_super *osb)
struct ocfs2_dinode *alloc = NULL;
cancel_delayed_work(&osb->la_enable_wq);
- flush_workqueue(osb->ocfs2_wq);
+ if (osb->ocfs2_wq)
+ flush_workqueue(osb->ocfs2_wq);
if (osb->local_alloc_state == OCFS2_LA_UNUSED)
goto out;
diff --git a/fs/ocfs2/quota_global.c b/fs/ocfs2/quota_global.c
index 7a922190a8c7..eda83487c9ec 100644
--- a/fs/ocfs2/quota_global.c
+++ b/fs/ocfs2/quota_global.c
@@ -728,7 +728,7 @@ static int ocfs2_release_dquot(struct dquot *dquot)
mutex_lock(&dquot->dq_lock);
/* Check whether we are not racing with some other dqget() */
- if (atomic_read(&dquot->dq_count) > 1)
+ if (dquot_is_busy(dquot))
goto out;
/* Running from downconvert thread? Postpone quota processing to wq */
if (current == osb->dc_task) {
diff --git a/fs/ocfs2/suballoc.c b/fs/ocfs2/suballoc.c
index 69c21a3843af..4180c3ef0a68 100644
--- a/fs/ocfs2/suballoc.c
+++ b/fs/ocfs2/suballoc.c
@@ -1252,6 +1252,7 @@ static int ocfs2_test_bg_bit_allocatable(struct buffer_head *bg_bh,
int nr)
{
struct ocfs2_group_desc *bg = (struct ocfs2_group_desc *) bg_bh->b_data;
+ struct journal_head *jh;
int ret;
if (ocfs2_test_bit(nr, (unsigned long *)bg->bg_bitmap))
@@ -1260,13 +1261,14 @@ static int ocfs2_test_bg_bit_allocatable(struct buffer_head *bg_bh,
if (!buffer_jbd(bg_bh))
return 1;
- jbd_lock_bh_state(bg_bh);
- bg = (struct ocfs2_group_desc *) bh2jh(bg_bh)->b_committed_data;
+ jh = bh2jh(bg_bh);
+ spin_lock(&jh->b_state_lock);
+ bg = (struct ocfs2_group_desc *) jh->b_committed_data;
if (bg)
ret = !ocfs2_test_bit(nr, (unsigned long *)bg->bg_bitmap);
else
ret = 1;
- jbd_unlock_bh_state(bg_bh);
+ spin_unlock(&jh->b_state_lock);
return ret;
}
@@ -2387,6 +2389,7 @@ static int ocfs2_block_group_clear_bits(handle_t *handle,
int status;
unsigned int tmp;
struct ocfs2_group_desc *undo_bg = NULL;
+ struct journal_head *jh;
/* The caller got this descriptor from
* ocfs2_read_group_descriptor(). Any corruption is a code bug. */
@@ -2405,10 +2408,10 @@ static int ocfs2_block_group_clear_bits(handle_t *handle,
goto bail;
}
+ jh = bh2jh(group_bh);
if (undo_fn) {
- jbd_lock_bh_state(group_bh);
- undo_bg = (struct ocfs2_group_desc *)
- bh2jh(group_bh)->b_committed_data;
+ spin_lock(&jh->b_state_lock);
+ undo_bg = (struct ocfs2_group_desc *) jh->b_committed_data;
BUG_ON(!undo_bg);
}
@@ -2423,7 +2426,7 @@ static int ocfs2_block_group_clear_bits(handle_t *handle,
le16_add_cpu(&bg->bg_free_bits_count, num_bits);
if (le16_to_cpu(bg->bg_free_bits_count) > le16_to_cpu(bg->bg_bits)) {
if (undo_fn)
- jbd_unlock_bh_state(group_bh);
+ spin_unlock(&jh->b_state_lock);
return ocfs2_error(alloc_inode->i_sb, "Group descriptor # %llu has bit count %u but claims %u are freed. num_bits %d\n",
(unsigned long long)le64_to_cpu(bg->bg_blkno),
le16_to_cpu(bg->bg_bits),
@@ -2432,7 +2435,7 @@ static int ocfs2_block_group_clear_bits(handle_t *handle,
}
if (undo_fn)
- jbd_unlock_bh_state(group_bh);
+ spin_unlock(&jh->b_state_lock);
ocfs2_journal_dirty(handle, group_bh);
bail:
diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c
index c81e86c62380..05dd68ade293 100644
--- a/fs/ocfs2/super.c
+++ b/fs/ocfs2/super.c
@@ -926,8 +926,8 @@ static int ocfs2_enable_quotas(struct ocfs2_super *osb)
status = -ENOENT;
goto out_quota_off;
}
- status = dquot_enable(inode[type], type, QFMT_OCFS2,
- DQUOT_USAGE_ENABLED);
+ status = dquot_load_quota_inode(inode[type], type, QFMT_OCFS2,
+ DQUOT_USAGE_ENABLED);
if (status < 0)
goto out_quota_off;
}
diff --git a/fs/ocfs2/xattr.c b/fs/ocfs2/xattr.c
index d8507972ee13..90c830e3758e 100644
--- a/fs/ocfs2/xattr.c
+++ b/fs/ocfs2/xattr.c
@@ -1490,6 +1490,18 @@ static int ocfs2_xa_check_space(struct ocfs2_xa_loc *loc,
return loc->xl_ops->xlo_check_space(loc, xi);
}
+static void ocfs2_xa_add_entry(struct ocfs2_xa_loc *loc, u32 name_hash)
+{
+ loc->xl_ops->xlo_add_entry(loc, name_hash);
+ loc->xl_entry->xe_name_hash = cpu_to_le32(name_hash);
+ /*
+ * We can't leave the new entry's xe_name_offset at zero or
+ * add_namevalue() will go nuts. We set it to the size of our
+ * storage so that it can never be less than any other entry.
+ */
+ loc->xl_entry->xe_name_offset = cpu_to_le16(loc->xl_size);
+}
+
static void ocfs2_xa_add_namevalue(struct ocfs2_xa_loc *loc,
struct ocfs2_xattr_info *xi)
{
@@ -2121,31 +2133,29 @@ static int ocfs2_xa_prepare_entry(struct ocfs2_xa_loc *loc,
if (rc)
goto out;
- if (!loc->xl_entry) {
- rc = -EINVAL;
- goto out;
- }
-
- if (ocfs2_xa_can_reuse_entry(loc, xi)) {
- orig_value_size = loc->xl_entry->xe_value_size;
- rc = ocfs2_xa_reuse_entry(loc, xi, ctxt);
- if (rc)
- goto out;
- goto alloc_value;
- }
+ if (loc->xl_entry) {
+ if (ocfs2_xa_can_reuse_entry(loc, xi)) {
+ orig_value_size = loc->xl_entry->xe_value_size;
+ rc = ocfs2_xa_reuse_entry(loc, xi, ctxt);
+ if (rc)
+ goto out;
+ goto alloc_value;
+ }
- if (!ocfs2_xattr_is_local(loc->xl_entry)) {
- orig_clusters = ocfs2_xa_value_clusters(loc);
- rc = ocfs2_xa_value_truncate(loc, 0, ctxt);
- if (rc) {
- mlog_errno(rc);
- ocfs2_xa_cleanup_value_truncate(loc,
- "overwriting",
- orig_clusters);
- goto out;
+ if (!ocfs2_xattr_is_local(loc->xl_entry)) {
+ orig_clusters = ocfs2_xa_value_clusters(loc);
+ rc = ocfs2_xa_value_truncate(loc, 0, ctxt);
+ if (rc) {
+ mlog_errno(rc);
+ ocfs2_xa_cleanup_value_truncate(loc,
+ "overwriting",
+ orig_clusters);
+ goto out;
+ }
}
- }
- ocfs2_xa_wipe_namevalue(loc);
+ ocfs2_xa_wipe_namevalue(loc);
+ } else
+ ocfs2_xa_add_entry(loc, name_hash);
/*
* If we get here, we have a blank entry. Fill it. We grow our
diff --git a/fs/orangefs/file.c b/fs/orangefs/file.c
index a5612abc0936..c740159d9ad1 100644
--- a/fs/orangefs/file.c
+++ b/fs/orangefs/file.c
@@ -46,8 +46,9 @@ static int flush_racache(struct inode *inode)
* Post and wait for the I/O upcall to finish
*/
ssize_t wait_for_direct_io(enum ORANGEFS_io_type type, struct inode *inode,
- loff_t *offset, struct iov_iter *iter, size_t total_size,
- loff_t readahead_size, struct orangefs_write_range *wr, int *index_return)
+ loff_t *offset, struct iov_iter *iter, size_t total_size,
+ loff_t readahead_size, struct orangefs_write_range *wr,
+ int *index_return, struct file *file)
{
struct orangefs_inode_s *orangefs_inode = ORANGEFS_I(inode);
struct orangefs_khandle *handle = &orangefs_inode->refn.khandle;
@@ -55,6 +56,8 @@ ssize_t wait_for_direct_io(enum ORANGEFS_io_type type, struct inode *inode,
int buffer_index;
ssize_t ret;
size_t copy_amount;
+ int open_for_read;
+ int open_for_write;
new_op = op_alloc(ORANGEFS_VFS_OP_FILE_IO);
if (!new_op)
@@ -90,6 +93,38 @@ populate_shared_memory:
new_op->upcall.uid = from_kuid(&init_user_ns, wr->uid);
new_op->upcall.gid = from_kgid(&init_user_ns, wr->gid);
}
+ /*
+ * Orangefs has no open, and orangefs checks file permissions
+ * on each file access. Posix requires that file permissions
+ * be checked on open and nowhere else. Orangefs-through-the-kernel
+ * needs to seem posix compliant.
+ *
+ * The VFS opens files, even if the filesystem provides no
+ * method. We can see if a file was successfully opened for
+ * read and or for write by looking at file->f_mode.
+ *
+ * When writes are flowing from the page cache, file is no
+ * longer available. We can trust the VFS to have checked
+ * file->f_mode before writing to the page cache.
+ *
+ * The mode of a file might change between when it is opened
+ * and IO commences, or it might be created with an arbitrary mode.
+ *
+ * We'll make sure we don't hit EACCES during the IO stage by
+ * using UID 0. Some of the time we have access without changing
+ * to UID 0 - how to check?
+ */
+ if (file) {
+ open_for_write = file->f_mode & FMODE_WRITE;
+ open_for_read = file->f_mode & FMODE_READ;
+ } else {
+ open_for_write = 1;
+ open_for_read = 0; /* not relevant? */
+ }
+ if ((type == ORANGEFS_IO_WRITE) && open_for_write)
+ new_op->upcall.uid = 0;
+ if ((type == ORANGEFS_IO_READ) && open_for_read)
+ new_op->upcall.uid = 0;
gossip_debug(GOSSIP_FILE_DEBUG,
"%s(%pU): offset: %llu total_size: %zd\n",
diff --git a/fs/orangefs/inode.c b/fs/orangefs/inode.c
index efb12197da18..961c0fd8675a 100644
--- a/fs/orangefs/inode.c
+++ b/fs/orangefs/inode.c
@@ -55,7 +55,7 @@ static int orangefs_writepage_locked(struct page *page,
iov_iter_bvec(&iter, WRITE, &bv, 1, wlen);
ret = wait_for_direct_io(ORANGEFS_IO_WRITE, inode, &off, &iter, wlen,
- len, wr, NULL);
+ len, wr, NULL, NULL);
if (ret < 0) {
SetPageError(page);
mapping_set_error(page->mapping, ret);
@@ -126,7 +126,7 @@ static int orangefs_writepages_work(struct orangefs_writepages *ow,
wr.uid = ow->uid;
wr.gid = ow->gid;
ret = wait_for_direct_io(ORANGEFS_IO_WRITE, inode, &off, &iter, ow->len,
- 0, &wr, NULL);
+ 0, &wr, NULL, NULL);
if (ret < 0) {
for (i = 0; i < ow->npages; i++) {
SetPageError(ow->pages[i]);
@@ -311,7 +311,7 @@ static int orangefs_readpage(struct file *file, struct page *page)
iov_iter_bvec(&iter, READ, &bv, 1, PAGE_SIZE);
ret = wait_for_direct_io(ORANGEFS_IO_READ, inode, &off, &iter,
- read_size, inode->i_size, NULL, &buffer_index);
+ read_size, inode->i_size, NULL, &buffer_index, file);
remaining = ret;
/* this will only zero remaining unread portions of the page data */
iov_iter_zero(~0U, &iter);
@@ -651,7 +651,7 @@ static ssize_t orangefs_direct_IO(struct kiocb *iocb,
(int)*offset);
ret = wait_for_direct_io(type, inode, offset, iter,
- each_count, 0, NULL, NULL);
+ each_count, 0, NULL, NULL, file);
gossip_debug(GOSSIP_FILE_DEBUG,
"%s(%pU): return from wait_for_io:%d\n",
__func__,
diff --git a/fs/orangefs/orangefs-kernel.h b/fs/orangefs/orangefs-kernel.h
index 34a6c99fa29b..ed67f39fa7ce 100644
--- a/fs/orangefs/orangefs-kernel.h
+++ b/fs/orangefs/orangefs-kernel.h
@@ -398,7 +398,8 @@ bool __is_daemon_in_service(void);
*/
int orangefs_revalidate_mapping(struct inode *);
ssize_t wait_for_direct_io(enum ORANGEFS_io_type, struct inode *, loff_t *,
- struct iov_iter *, size_t, loff_t, struct orangefs_write_range *, int *);
+ struct iov_iter *, size_t, loff_t, struct orangefs_write_range *, int *,
+ struct file *);
ssize_t do_readv_writev(enum ORANGEFS_io_type, struct file *, loff_t *,
struct iov_iter *);
diff --git a/fs/overlayfs/namei.c b/fs/overlayfs/namei.c
index e9717c2f7d45..c269d6033525 100644
--- a/fs/overlayfs/namei.c
+++ b/fs/overlayfs/namei.c
@@ -200,7 +200,7 @@ static int ovl_lookup_single(struct dentry *base, struct ovl_lookup_data *d,
int err;
bool last_element = !post[0];
- this = lookup_one_len_unlocked(name, base, namelen);
+ this = lookup_positive_unlocked(name, base, namelen);
if (IS_ERR(this)) {
err = PTR_ERR(this);
this = NULL;
@@ -208,8 +208,6 @@ static int ovl_lookup_single(struct dentry *base, struct ovl_lookup_data *d,
goto out;
goto out_err;
}
- if (!this->d_inode)
- goto put_and_out;
if (ovl_dentry_weird(this)) {
/* Don't support traversing automounts and other weirdness */
@@ -651,7 +649,7 @@ struct dentry *ovl_get_index_fh(struct ovl_fs *ofs, struct ovl_fh *fh)
if (err)
return ERR_PTR(err);
- index = lookup_one_len_unlocked(name.name, ofs->indexdir, name.len);
+ index = lookup_positive_unlocked(name.name, ofs->indexdir, name.len);
kfree(name.name);
if (IS_ERR(index)) {
if (PTR_ERR(index) == -ENOENT)
@@ -659,9 +657,7 @@ struct dentry *ovl_get_index_fh(struct ovl_fs *ofs, struct ovl_fh *fh)
return index;
}
- if (d_is_negative(index))
- err = 0;
- else if (ovl_is_whiteout(index))
+ if (ovl_is_whiteout(index))
err = -ESTALE;
else if (ovl_dentry_weird(index))
err = -EIO;
@@ -685,7 +681,7 @@ struct dentry *ovl_lookup_index(struct ovl_fs *ofs, struct dentry *upper,
if (err)
return ERR_PTR(err);
- index = lookup_one_len_unlocked(name.name, ofs->indexdir, name.len);
+ index = lookup_positive_unlocked(name.name, ofs->indexdir, name.len);
if (IS_ERR(index)) {
err = PTR_ERR(index);
if (err == -ENOENT) {
@@ -700,9 +696,7 @@ struct dentry *ovl_lookup_index(struct ovl_fs *ofs, struct dentry *upper,
}
inode = d_inode(index);
- if (d_is_negative(index)) {
- goto out_dput;
- } else if (ovl_is_whiteout(index) && !verify) {
+ if (ovl_is_whiteout(index) && !verify) {
/*
* When index lookup is called with !verify for decoding an
* overlay file handle, a whiteout index implies that decode
@@ -1131,7 +1125,7 @@ bool ovl_lower_positive(struct dentry *dentry)
struct dentry *this;
struct dentry *lowerdir = poe->lowerstack[i].dentry;
- this = lookup_one_len_unlocked(name->name, lowerdir,
+ this = lookup_positive_unlocked(name->name, lowerdir,
name->len);
if (IS_ERR(this)) {
switch (PTR_ERR(this)) {
@@ -1148,10 +1142,8 @@ bool ovl_lower_positive(struct dentry *dentry)
break;
}
} else {
- if (this->d_inode) {
- positive = !ovl_is_whiteout(this);
- done = true;
- }
+ positive = !ovl_is_whiteout(this);
+ done = true;
dput(this);
}
}
diff --git a/fs/pipe.c b/fs/pipe.c
index 8a2ab2f974bd..87109e761fa5 100644
--- a/fs/pipe.c
+++ b/fs/pipe.c
@@ -43,10 +43,12 @@ unsigned long pipe_user_pages_hard;
unsigned long pipe_user_pages_soft = PIPE_DEF_BUFFERS * INR_OPEN_CUR;
/*
- * We use a start+len construction, which provides full use of the
- * allocated memory.
- * -- Florian Coosmann (FGC)
- *
+ * We use head and tail indices that aren't masked off, except at the point of
+ * dereference, but rather they're allowed to wrap naturally. This means there
+ * isn't a dead spot in the buffer, but the ring has to be a power of two and
+ * <= 2^31.
+ * -- David Howells 2019-09-23.
+ *
* Reads with count = 0 should always return 0.
* -- Julian Bradfield 1999-06-07.
*
@@ -268,27 +270,48 @@ static bool pipe_buf_can_merge(struct pipe_buffer *buf)
return buf->ops == &anon_pipe_buf_ops;
}
+/* Done while waiting without holding the pipe lock - thus the READ_ONCE() */
+static inline bool pipe_readable(const struct pipe_inode_info *pipe)
+{
+ unsigned int head = READ_ONCE(pipe->head);
+ unsigned int tail = READ_ONCE(pipe->tail);
+ unsigned int writers = READ_ONCE(pipe->writers);
+
+ return !pipe_empty(head, tail) || !writers;
+}
+
static ssize_t
pipe_read(struct kiocb *iocb, struct iov_iter *to)
{
size_t total_len = iov_iter_count(to);
struct file *filp = iocb->ki_filp;
struct pipe_inode_info *pipe = filp->private_data;
- int do_wakeup;
+ bool was_full;
ssize_t ret;
/* Null read succeeds. */
if (unlikely(total_len == 0))
return 0;
- do_wakeup = 0;
ret = 0;
__pipe_lock(pipe);
+
+ /*
+ * We only wake up writers if the pipe was full when we started
+ * reading in order to avoid unnecessary wakeups.
+ *
+ * But when we do wake up writers, we do so using a sync wakeup
+ * (WF_SYNC), because we want them to get going and generate more
+ * data for us.
+ */
+ was_full = pipe_full(pipe->head, pipe->tail, pipe->max_usage);
for (;;) {
- int bufs = pipe->nrbufs;
- if (bufs) {
- int curbuf = pipe->curbuf;
- struct pipe_buffer *buf = pipe->bufs + curbuf;
+ unsigned int head = pipe->head;
+ unsigned int tail = pipe->tail;
+ unsigned int mask = pipe->ring_size - 1;
+
+ if (!pipe_empty(head, tail)) {
+ struct pipe_buffer *buf = &pipe->bufs[tail & mask];
size_t chars = buf->len;
size_t written;
int error;
@@ -321,47 +344,43 @@ pipe_read(struct kiocb *iocb, struct iov_iter *to)
if (!buf->len) {
pipe_buf_release(pipe, buf);
- curbuf = (curbuf + 1) & (pipe->buffers - 1);
- pipe->curbuf = curbuf;
- pipe->nrbufs = --bufs;
- do_wakeup = 1;
+ spin_lock_irq(&pipe->wait.lock);
+ tail++;
+ pipe->tail = tail;
+ spin_unlock_irq(&pipe->wait.lock);
}
total_len -= chars;
if (!total_len)
break; /* common path: read succeeded */
+ if (!pipe_empty(head, tail)) /* More to do? */
+ continue;
}
- if (bufs) /* More to do? */
- continue;
+
if (!pipe->writers)
break;
- if (!pipe->waiting_writers) {
- /* syscall merging: Usually we must not sleep
- * if O_NONBLOCK is set, or if we got some data.
- * But if a writer sleeps in kernel space, then
- * we can wait for that data without violating POSIX.
- */
- if (ret)
- break;
- if (filp->f_flags & O_NONBLOCK) {
- ret = -EAGAIN;
- break;
- }
+ if (ret)
+ break;
+ if (filp->f_flags & O_NONBLOCK) {
+ ret = -EAGAIN;
+ break;
}
if (signal_pending(current)) {
if (!ret)
ret = -ERESTARTSYS;
break;
}
- if (do_wakeup) {
+ __pipe_unlock(pipe);
+ if (was_full) {
wake_up_interruptible_sync_poll(&pipe->wait, EPOLLOUT | EPOLLWRNORM);
- kill_fasync(&pipe->fasync_writers, SIGIO, POLL_OUT);
+ kill_fasync(&pipe->fasync_writers, SIGIO, POLL_OUT);
}
- pipe_wait(pipe);
+ wait_event_interruptible(pipe->wait, pipe_readable(pipe));
+ __pipe_lock(pipe);
+ was_full = pipe_full(pipe->head, pipe->tail, pipe->max_usage);
}
__pipe_unlock(pipe);
- /* Signal writers asynchronously that there is more room. */
- if (do_wakeup) {
+ if (was_full) {
wake_up_interruptible_sync_poll(&pipe->wait, EPOLLOUT | EPOLLWRNORM);
kill_fasync(&pipe->fasync_writers, SIGIO, POLL_OUT);
}
@@ -375,15 +394,27 @@ static inline int is_packetized(struct file *file)
return (file->f_flags & O_DIRECT) != 0;
}
+/* Done while waiting without holding the pipe lock - thus the READ_ONCE() */
+static inline bool pipe_writable(const struct pipe_inode_info *pipe)
+{
+ unsigned int head = READ_ONCE(pipe->head);
+ unsigned int tail = READ_ONCE(pipe->tail);
+ unsigned int max_usage = READ_ONCE(pipe->max_usage);
+
+ return !pipe_full(head, tail, max_usage) ||
+ !READ_ONCE(pipe->readers);
+}
+
static ssize_t
pipe_write(struct kiocb *iocb, struct iov_iter *from)
{
struct file *filp = iocb->ki_filp;
struct pipe_inode_info *pipe = filp->private_data;
+ unsigned int head;
ssize_t ret = 0;
- int do_wakeup = 0;
size_t total_len = iov_iter_count(from);
ssize_t chars;
+ bool was_empty = false;
/* Null write succeeds. */
if (unlikely(total_len == 0))
@@ -397,12 +428,23 @@ pipe_write(struct kiocb *iocb, struct iov_iter *from)
goto out;
}
- /* We try to merge small writes */
- chars = total_len & (PAGE_SIZE-1); /* size of the last buffer */
- if (pipe->nrbufs && chars != 0) {
- int lastbuf = (pipe->curbuf + pipe->nrbufs - 1) &
- (pipe->buffers - 1);
- struct pipe_buffer *buf = pipe->bufs + lastbuf;
+ /*
+ * Only wake up if the pipe started out empty, since
+ * otherwise there should be no readers waiting.
+ *
+ * If it wasn't empty we try to merge new data into
+ * the last buffer.
+ *
+ * That naturally merges small writes, but it also
+ * page-aligs the rest of the writes for large writes
+ * spanning multiple pages.
+ */
+ head = pipe->head;
+ was_empty = pipe_empty(head, pipe->tail);
+ chars = total_len & (PAGE_SIZE-1);
+ if (chars && !was_empty) {
+ unsigned int mask = pipe->ring_size - 1;
+ struct pipe_buffer *buf = &pipe->bufs[(head - 1) & mask];
int offset = buf->offset + buf->len;
if (pipe_buf_can_merge(buf) && offset + chars <= PAGE_SIZE) {
@@ -415,7 +457,7 @@ pipe_write(struct kiocb *iocb, struct iov_iter *from)
ret = -EFAULT;
goto out;
}
- do_wakeup = 1;
+
buf->len += ret;
if (!iov_iter_count(from))
goto out;
@@ -423,18 +465,17 @@ pipe_write(struct kiocb *iocb, struct iov_iter *from)
}
for (;;) {
- int bufs;
-
if (!pipe->readers) {
send_sig(SIGPIPE, current, 0);
if (!ret)
ret = -EPIPE;
break;
}
- bufs = pipe->nrbufs;
- if (bufs < pipe->buffers) {
- int newbuf = (pipe->curbuf + bufs) & (pipe->buffers-1);
- struct pipe_buffer *buf = pipe->bufs + newbuf;
+
+ head = pipe->head;
+ if (!pipe_full(head, pipe->tail, pipe->max_usage)) {
+ unsigned int mask = pipe->ring_size - 1;
+ struct pipe_buffer *buf = &pipe->bufs[head & mask];
struct page *page = pipe->tmp_page;
int copied;
@@ -446,38 +487,54 @@ pipe_write(struct kiocb *iocb, struct iov_iter *from)
}
pipe->tmp_page = page;
}
- /* Always wake up, even if the copy fails. Otherwise
- * we lock up (O_NONBLOCK-)readers that sleep due to
- * syscall merging.
- * FIXME! Is this really true?
+
+ /* Allocate a slot in the ring in advance and attach an
+ * empty buffer. If we fault or otherwise fail to use
+ * it, either the reader will consume it or it'll still
+ * be there for the next write.
*/
- do_wakeup = 1;
- copied = copy_page_from_iter(page, 0, PAGE_SIZE, from);
- if (unlikely(copied < PAGE_SIZE && iov_iter_count(from))) {
- if (!ret)
- ret = -EFAULT;
- break;
+ spin_lock_irq(&pipe->wait.lock);
+
+ head = pipe->head;
+ if (pipe_full(head, pipe->tail, pipe->max_usage)) {
+ spin_unlock_irq(&pipe->wait.lock);
+ continue;
}
- ret += copied;
+
+ pipe->head = head + 1;
+ spin_unlock_irq(&pipe->wait.lock);
/* Insert it into the buffer array */
+ buf = &pipe->bufs[head & mask];
buf->page = page;
buf->ops = &anon_pipe_buf_ops;
buf->offset = 0;
- buf->len = copied;
+ buf->len = 0;
buf->flags = 0;
if (is_packetized(filp)) {
buf->ops = &packet_pipe_buf_ops;
buf->flags = PIPE_BUF_FLAG_PACKET;
}
- pipe->nrbufs = ++bufs;
pipe->tmp_page = NULL;
+ copied = copy_page_from_iter(page, 0, PAGE_SIZE, from);
+ if (unlikely(copied < PAGE_SIZE && iov_iter_count(from))) {
+ if (!ret)
+ ret = -EFAULT;
+ break;
+ }
+ ret += copied;
+ buf->offset = 0;
+ buf->len = copied;
+
if (!iov_iter_count(from))
break;
}
- if (bufs < pipe->buffers)
+
+ if (!pipe_full(head, pipe->tail, pipe->max_usage))
continue;
+
+ /* Wait for buffer space to become available. */
if (filp->f_flags & O_NONBLOCK) {
if (!ret)
ret = -EAGAIN;
@@ -488,18 +545,35 @@ pipe_write(struct kiocb *iocb, struct iov_iter *from)
ret = -ERESTARTSYS;
break;
}
- if (do_wakeup) {
+
+ /*
+ * We're going to release the pipe lock and wait for more
+ * space. We wake up any readers if necessary, and then
+ * after waiting we need to re-check whether the pipe
+ * become empty while we dropped the lock.
+ */
+ __pipe_unlock(pipe);
+ if (was_empty) {
wake_up_interruptible_sync_poll(&pipe->wait, EPOLLIN | EPOLLRDNORM);
kill_fasync(&pipe->fasync_readers, SIGIO, POLL_IN);
- do_wakeup = 0;
}
- pipe->waiting_writers++;
- pipe_wait(pipe);
- pipe->waiting_writers--;
+ wait_event_interruptible(pipe->wait, pipe_writable(pipe));
+ __pipe_lock(pipe);
+ was_empty = pipe_empty(head, pipe->tail);
}
out:
__pipe_unlock(pipe);
- if (do_wakeup) {
+
+ /*
+ * If we do do a wakeup event, we do a 'sync' wakeup, because we
+ * want the reader to start processing things asap, rather than
+ * leave the data pending.
+ *
+ * This is particularly important for small writes, because of
+ * how (for example) the GNU make jobserver uses small writes to
+ * wake up pending jobs
+ */
+ if (was_empty) {
wake_up_interruptible_sync_poll(&pipe->wait, EPOLLIN | EPOLLRDNORM);
kill_fasync(&pipe->fasync_readers, SIGIO, POLL_IN);
}
@@ -515,17 +589,19 @@ out:
static long pipe_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
{
struct pipe_inode_info *pipe = filp->private_data;
- int count, buf, nrbufs;
+ int count, head, tail, mask;
switch (cmd) {
case FIONREAD:
__pipe_lock(pipe);
count = 0;
- buf = pipe->curbuf;
- nrbufs = pipe->nrbufs;
- while (--nrbufs >= 0) {
- count += pipe->bufs[buf].len;
- buf = (buf+1) & (pipe->buffers - 1);
+ head = pipe->head;
+ tail = pipe->tail;
+ mask = pipe->ring_size - 1;
+
+ while (tail != head) {
+ count += pipe->bufs[tail & mask].len;
+ tail++;
}
__pipe_unlock(pipe);
@@ -541,21 +617,35 @@ pipe_poll(struct file *filp, poll_table *wait)
{
__poll_t mask;
struct pipe_inode_info *pipe = filp->private_data;
- int nrbufs;
+ unsigned int head, tail;
+ /*
+ * Reading only -- no need for acquiring the semaphore.
+ *
+ * But because this is racy, the code has to add the
+ * entry to the poll table _first_ ..
+ */
poll_wait(filp, &pipe->wait, wait);
- /* Reading only -- no need for acquiring the semaphore. */
- nrbufs = pipe->nrbufs;
+ /*
+ * .. and only then can you do the racy tests. That way,
+ * if something changes and you got it wrong, the poll
+ * table entry will wake you up and fix it.
+ */
+ head = READ_ONCE(pipe->head);
+ tail = READ_ONCE(pipe->tail);
+
mask = 0;
if (filp->f_mode & FMODE_READ) {
- mask = (nrbufs > 0) ? EPOLLIN | EPOLLRDNORM : 0;
+ if (!pipe_empty(head, tail))
+ mask |= EPOLLIN | EPOLLRDNORM;
if (!pipe->writers && filp->f_version != pipe->w_counter)
mask |= EPOLLHUP;
}
if (filp->f_mode & FMODE_WRITE) {
- mask |= (nrbufs < pipe->buffers) ? EPOLLOUT | EPOLLWRNORM : 0;
+ if (!pipe_full(head, tail, pipe->max_usage))
+ mask |= EPOLLOUT | EPOLLWRNORM;
/*
* Most Unices do not set EPOLLERR for FIFOs but on Linux they
* behave exactly like pipes for poll().
@@ -679,7 +769,8 @@ struct pipe_inode_info *alloc_pipe_info(void)
if (pipe->bufs) {
init_waitqueue_head(&pipe->wait);
pipe->r_counter = pipe->w_counter = 1;
- pipe->buffers = pipe_bufs;
+ pipe->max_usage = pipe_bufs;
+ pipe->ring_size = pipe_bufs;
pipe->user = user;
mutex_init(&pipe->mutex);
return pipe;
@@ -697,9 +788,9 @@ void free_pipe_info(struct pipe_inode_info *pipe)
{
int i;
- (void) account_pipe_buffers(pipe->user, pipe->buffers, 0);
+ (void) account_pipe_buffers(pipe->user, pipe->ring_size, 0);
free_uid(pipe->user);
- for (i = 0; i < pipe->buffers; i++) {
+ for (i = 0; i < pipe->ring_size; i++) {
struct pipe_buffer *buf = pipe->bufs + i;
if (buf->ops)
pipe_buf_release(pipe, buf);
@@ -793,6 +884,8 @@ int create_pipe_files(struct file **res, int flags)
}
res[0]->private_data = inode->i_pipe;
res[1] = f;
+ stream_open(inode, res[0]);
+ stream_open(inode, res[1]);
return 0;
}
@@ -880,7 +973,7 @@ SYSCALL_DEFINE1(pipe, int __user *, fildes)
static int wait_for_partner(struct pipe_inode_info *pipe, unsigned int *cnt)
{
- int cur = *cnt;
+ int cur = *cnt;
while (cur == *cnt) {
pipe_wait(pipe);
@@ -931,9 +1024,9 @@ static int fifo_open(struct inode *inode, struct file *filp)
__pipe_lock(pipe);
/* We can only do regular read/write on fifos */
- filp->f_mode &= (FMODE_READ | FMODE_WRITE);
+ stream_open(inode, filp);
- switch (filp->f_mode) {
+ switch (filp->f_mode & (FMODE_READ | FMODE_WRITE)) {
case FMODE_READ:
/*
* O_RDONLY
@@ -955,7 +1048,7 @@ static int fifo_open(struct inode *inode, struct file *filp)
}
}
break;
-
+
case FMODE_WRITE:
/*
* O_WRONLY
@@ -975,7 +1068,7 @@ static int fifo_open(struct inode *inode, struct file *filp)
goto err_wr;
}
break;
-
+
case FMODE_READ | FMODE_WRITE:
/*
* O_RDWR
@@ -1054,14 +1147,14 @@ unsigned int round_pipe_size(unsigned long size)
static long pipe_set_size(struct pipe_inode_info *pipe, unsigned long arg)
{
struct pipe_buffer *bufs;
- unsigned int size, nr_pages;
+ unsigned int size, nr_slots, head, tail, mask, n;
unsigned long user_bufs;
long ret = 0;
size = round_pipe_size(arg);
- nr_pages = size >> PAGE_SHIFT;
+ nr_slots = size >> PAGE_SHIFT;
- if (!nr_pages)
+ if (!nr_slots)
return -EINVAL;
/*
@@ -1071,13 +1164,13 @@ static long pipe_set_size(struct pipe_inode_info *pipe, unsigned long arg)
* Decreasing the pipe capacity is always permitted, even
* if the user is currently over a limit.
*/
- if (nr_pages > pipe->buffers &&
+ if (nr_slots > pipe->ring_size &&
size > pipe_max_size && !capable(CAP_SYS_RESOURCE))
return -EPERM;
- user_bufs = account_pipe_buffers(pipe->user, pipe->buffers, nr_pages);
+ user_bufs = account_pipe_buffers(pipe->user, pipe->ring_size, nr_slots);
- if (nr_pages > pipe->buffers &&
+ if (nr_slots > pipe->ring_size &&
(too_many_pipe_buffers_hard(user_bufs) ||
too_many_pipe_buffers_soft(user_bufs)) &&
is_unprivileged_user()) {
@@ -1086,17 +1179,21 @@ static long pipe_set_size(struct pipe_inode_info *pipe, unsigned long arg)
}
/*
- * We can shrink the pipe, if arg >= pipe->nrbufs. Since we don't
- * expect a lot of shrink+grow operations, just free and allocate
- * again like we would do for growing. If the pipe currently
+ * We can shrink the pipe, if arg is greater than the ring occupancy.
+ * Since we don't expect a lot of shrink+grow operations, just free and
+ * allocate again like we would do for growing. If the pipe currently
* contains more buffers than arg, then return busy.
*/
- if (nr_pages < pipe->nrbufs) {
+ mask = pipe->ring_size - 1;
+ head = pipe->head;
+ tail = pipe->tail;
+ n = pipe_occupancy(pipe->head, pipe->tail);
+ if (nr_slots < n) {
ret = -EBUSY;
goto out_revert_acct;
}
- bufs = kcalloc(nr_pages, sizeof(*bufs),
+ bufs = kcalloc(nr_slots, sizeof(*bufs),
GFP_KERNEL_ACCOUNT | __GFP_NOWARN);
if (unlikely(!bufs)) {
ret = -ENOMEM;
@@ -1105,33 +1202,38 @@ static long pipe_set_size(struct pipe_inode_info *pipe, unsigned long arg)
/*
* The pipe array wraps around, so just start the new one at zero
- * and adjust the indexes.
+ * and adjust the indices.
*/
- if (pipe->nrbufs) {
- unsigned int tail;
- unsigned int head;
-
- tail = pipe->curbuf + pipe->nrbufs;
- if (tail < pipe->buffers)
- tail = 0;
- else
- tail &= (pipe->buffers - 1);
-
- head = pipe->nrbufs - tail;
- if (head)
- memcpy(bufs, pipe->bufs + pipe->curbuf, head * sizeof(struct pipe_buffer));
- if (tail)
- memcpy(bufs + head, pipe->bufs, tail * sizeof(struct pipe_buffer));
+ if (n > 0) {
+ unsigned int h = head & mask;
+ unsigned int t = tail & mask;
+ if (h > t) {
+ memcpy(bufs, pipe->bufs + t,
+ n * sizeof(struct pipe_buffer));
+ } else {
+ unsigned int tsize = pipe->ring_size - t;
+ if (h > 0)
+ memcpy(bufs + tsize, pipe->bufs,
+ h * sizeof(struct pipe_buffer));
+ memcpy(bufs, pipe->bufs + t,
+ tsize * sizeof(struct pipe_buffer));
+ }
}
- pipe->curbuf = 0;
+ head = n;
+ tail = 0;
+
kfree(pipe->bufs);
pipe->bufs = bufs;
- pipe->buffers = nr_pages;
- return nr_pages * PAGE_SIZE;
+ pipe->ring_size = nr_slots;
+ pipe->max_usage = nr_slots;
+ pipe->tail = tail;
+ pipe->head = head;
+ wake_up_interruptible_all(&pipe->wait);
+ return pipe->max_usage * PAGE_SIZE;
out_revert_acct:
- (void) account_pipe_buffers(pipe->user, nr_pages, pipe->buffers);
+ (void) account_pipe_buffers(pipe->user, nr_slots, pipe->ring_size);
return ret;
}
@@ -1161,7 +1263,7 @@ long pipe_fcntl(struct file *file, unsigned int cmd, unsigned long arg)
ret = pipe_set_size(pipe, arg);
break;
case F_GETPIPE_SZ:
- ret = pipe->buffers * PAGE_SIZE;
+ ret = pipe->max_usage * PAGE_SIZE;
break;
default:
ret = -EINVAL;
diff --git a/fs/proc/Kconfig b/fs/proc/Kconfig
index cb5629bd5fff..733881a6387b 100644
--- a/fs/proc/Kconfig
+++ b/fs/proc/Kconfig
@@ -42,8 +42,8 @@ config PROC_VMCORE
bool "/proc/vmcore support"
depends on PROC_FS && CRASH_DUMP
default y
- help
- Exports the dump image of crashed kernel in ELF format.
+ help
+ Exports the dump image of crashed kernel in ELF format.
config PROC_VMCORE_DEVICE_DUMP
bool "Device Hardware/Firmware Log Collection"
@@ -72,7 +72,7 @@ config PROC_SYSCTL
a recompile of the kernel or reboot of the system. The primary
interface is through /proc/sys. If you say Y here a tree of
modifiable sysctl entries will be generated beneath the
- /proc/sys directory. They are explained in the files
+ /proc/sys directory. They are explained in the files
in <file:Documentation/admin-guide/sysctl/>. Note that enabling this
option will enlarge the kernel by at least 8 KB.
@@ -88,7 +88,7 @@ config PROC_PAGE_MONITOR
Various /proc files exist to monitor process memory utilization:
/proc/pid/smaps, /proc/pid/clear_refs, /proc/pid/pagemap,
/proc/kpagecount, and /proc/kpageflags. Disabling these
- interfaces will reduce the size of the kernel by approximately 4kb.
+ interfaces will reduce the size of the kernel by approximately 4kb.
config PROC_CHILDREN
bool "Include /proc/<pid>/task/<tid>/children file"
diff --git a/fs/proc/array.c b/fs/proc/array.c
index 46dcb6f0eccf..5efaf3708ec6 100644
--- a/fs/proc/array.c
+++ b/fs/proc/array.c
@@ -533,7 +533,7 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns,
nice = task_nice(task);
/* convert nsec -> ticks */
- start_time = nsec_to_clock_t(task->real_start_time);
+ start_time = nsec_to_clock_t(task->start_boottime);
seq_put_decimal_ull(m, "", pid_nr_ns(pid, ns));
seq_puts(m, " (");
diff --git a/fs/proc/generic.c b/fs/proc/generic.c
index 64e9ee1b129e..074e9585c699 100644
--- a/fs/proc/generic.c
+++ b/fs/proc/generic.c
@@ -138,8 +138,12 @@ static int proc_getattr(const struct path *path, struct kstat *stat,
{
struct inode *inode = d_inode(path->dentry);
struct proc_dir_entry *de = PDE(inode);
- if (de && de->nlink)
- set_nlink(inode, de->nlink);
+ if (de) {
+ nlink_t nlink = READ_ONCE(de->nlink);
+ if (nlink > 0) {
+ set_nlink(inode, nlink);
+ }
+ }
generic_fillattr(inode, stat);
return 0;
@@ -159,7 +163,6 @@ static int __xlate_proc_name(const char *name, struct proc_dir_entry **ret,
{
const char *cp = name, *next;
struct proc_dir_entry *de;
- unsigned int len;
de = *ret;
if (!de)
@@ -170,13 +173,12 @@ static int __xlate_proc_name(const char *name, struct proc_dir_entry **ret,
if (!next)
break;
- len = next - cp;
- de = pde_subdir_find(de, cp, len);
+ de = pde_subdir_find(de, cp, next - cp);
if (!de) {
WARN(1, "name '%s'\n", name);
return -ENOENT;
}
- cp += len + 1;
+ cp = next + 1;
}
*residual = cp;
*ret = de;
@@ -362,6 +364,7 @@ struct proc_dir_entry *proc_register(struct proc_dir_entry *dir,
write_unlock(&proc_subdir_lock);
goto out_free_inum;
}
+ dir->nlink++;
write_unlock(&proc_subdir_lock);
return dp;
@@ -472,10 +475,7 @@ struct proc_dir_entry *proc_mkdir_data(const char *name, umode_t mode,
ent->data = data;
ent->proc_fops = &proc_dir_operations;
ent->proc_iops = &proc_dir_inode_operations;
- parent->nlink++;
ent = proc_register(parent, ent);
- if (!ent)
- parent->nlink--;
}
return ent;
}
@@ -505,10 +505,7 @@ struct proc_dir_entry *proc_create_mount_point(const char *name)
ent->data = NULL;
ent->proc_fops = NULL;
ent->proc_iops = NULL;
- parent->nlink++;
ent = proc_register(parent, ent);
- if (!ent)
- parent->nlink--;
}
return ent;
}
@@ -666,8 +663,12 @@ void remove_proc_entry(const char *name, struct proc_dir_entry *parent)
len = strlen(fn);
de = pde_subdir_find(parent, fn, len);
- if (de)
+ if (de) {
rb_erase(&de->subdir_node, &parent->subdir);
+ if (S_ISDIR(de->mode)) {
+ parent->nlink--;
+ }
+ }
write_unlock(&proc_subdir_lock);
if (!de) {
WARN(1, "name '%s'\n", name);
@@ -676,9 +677,6 @@ void remove_proc_entry(const char *name, struct proc_dir_entry *parent)
proc_entry_rundown(de);
- if (S_ISDIR(de->mode))
- parent->nlink--;
- de->nlink = 0;
WARN(pde_subdir_first(de),
"%s: removing non-empty directory '%s/%s', leaking at least '%s'\n",
__func__, de->parent->name, de->name, pde_subdir_first(de)->name);
@@ -714,13 +712,12 @@ int remove_proc_subtree(const char *name, struct proc_dir_entry *parent)
de = next;
continue;
}
- write_unlock(&proc_subdir_lock);
-
- proc_entry_rundown(de);
next = de->parent;
if (S_ISDIR(de->mode))
next->nlink--;
- de->nlink = 0;
+ write_unlock(&proc_subdir_lock);
+
+ proc_entry_rundown(de);
if (de == root)
break;
pde_put(de);
diff --git a/fs/proc/internal.h b/fs/proc/internal.h
index cd0c8d5ce9a1..0f3b557c9b77 100644
--- a/fs/proc/internal.h
+++ b/fs/proc/internal.h
@@ -197,8 +197,8 @@ extern ssize_t proc_simple_write(struct file *, const char __user *, size_t, lof
* inode.c
*/
struct pde_opener {
- struct file *file;
struct list_head lh;
+ struct file *file;
bool closing;
struct completion *c;
} __randomize_layout;
diff --git a/fs/proc/meminfo.c b/fs/proc/meminfo.c
index ac9247371871..8c1f1bb1a5ce 100644
--- a/fs/proc/meminfo.c
+++ b/fs/proc/meminfo.c
@@ -132,9 +132,9 @@ static int meminfo_proc_show(struct seq_file *m, void *v)
global_node_page_state(NR_SHMEM_THPS) * HPAGE_PMD_NR);
show_val_kb(m, "ShmemPmdMapped: ",
global_node_page_state(NR_SHMEM_PMDMAPPED) * HPAGE_PMD_NR);
- show_val_kb(m, "FileHugePages: ",
+ show_val_kb(m, "FileHugePages: ",
global_node_page_state(NR_FILE_THPS) * HPAGE_PMD_NR);
- show_val_kb(m, "FilePmdMapped: ",
+ show_val_kb(m, "FilePmdMapped: ",
global_node_page_state(NR_FILE_PMDMAPPED) * HPAGE_PMD_NR);
#endif
diff --git a/fs/proc/page.c b/fs/proc/page.c
index 544d1ee15aee..7c952ee732e6 100644
--- a/fs/proc/page.c
+++ b/fs/proc/page.c
@@ -42,10 +42,12 @@ static ssize_t kpagecount_read(struct file *file, char __user *buf,
return -EINVAL;
while (count > 0) {
- if (pfn_valid(pfn))
- ppage = pfn_to_page(pfn);
- else
- ppage = NULL;
+ /*
+ * TODO: ZONE_DEVICE support requires to identify
+ * memmaps that were actually initialized.
+ */
+ ppage = pfn_to_online_page(pfn);
+
if (!ppage || PageSlab(ppage) || page_has_type(ppage))
pcount = 0;
else
@@ -216,10 +218,11 @@ static ssize_t kpageflags_read(struct file *file, char __user *buf,
return -EINVAL;
while (count > 0) {
- if (pfn_valid(pfn))
- ppage = pfn_to_page(pfn);
- else
- ppage = NULL;
+ /*
+ * TODO: ZONE_DEVICE support requires to identify
+ * memmaps that were actually initialized.
+ */
+ ppage = pfn_to_online_page(pfn);
if (put_user(stable_page_flags(ppage), out)) {
ret = -EFAULT;
@@ -261,10 +264,11 @@ static ssize_t kpagecgroup_read(struct file *file, char __user *buf,
return -EINVAL;
while (count > 0) {
- if (pfn_valid(pfn))
- ppage = pfn_to_page(pfn);
- else
- ppage = NULL;
+ /*
+ * TODO: ZONE_DEVICE support requires to identify
+ * memmaps that were actually initialized.
+ */
+ ppage = pfn_to_online_page(pfn);
if (ppage)
ino = page_cgroup_ino(ppage);
diff --git a/fs/proc/stat.c b/fs/proc/stat.c
index 80c305f206bb..37bdbec5b402 100644
--- a/fs/proc/stat.c
+++ b/fs/proc/stat.c
@@ -120,20 +120,23 @@ static int show_stat(struct seq_file *p, void *v)
getboottime64(&boottime);
for_each_possible_cpu(i) {
- struct kernel_cpustat *kcs = &kcpustat_cpu(i);
-
- user += kcs->cpustat[CPUTIME_USER];
- nice += kcs->cpustat[CPUTIME_NICE];
- system += kcs->cpustat[CPUTIME_SYSTEM];
- idle += get_idle_time(kcs, i);
- iowait += get_iowait_time(kcs, i);
- irq += kcs->cpustat[CPUTIME_IRQ];
- softirq += kcs->cpustat[CPUTIME_SOFTIRQ];
- steal += kcs->cpustat[CPUTIME_STEAL];
- guest += kcs->cpustat[CPUTIME_GUEST];
- guest_nice += kcs->cpustat[CPUTIME_GUEST_NICE];
- sum += kstat_cpu_irqs_sum(i);
- sum += arch_irq_stat_cpu(i);
+ struct kernel_cpustat kcpustat;
+ u64 *cpustat = kcpustat.cpustat;
+
+ kcpustat_cpu_fetch(&kcpustat, i);
+
+ user += cpustat[CPUTIME_USER];
+ nice += cpustat[CPUTIME_NICE];
+ system += cpustat[CPUTIME_SYSTEM];
+ idle += get_idle_time(&kcpustat, i);
+ iowait += get_iowait_time(&kcpustat, i);
+ irq += cpustat[CPUTIME_IRQ];
+ softirq += cpustat[CPUTIME_SOFTIRQ];
+ steal += cpustat[CPUTIME_STEAL];
+ guest += cpustat[CPUTIME_GUEST];
+ guest_nice += cpustat[CPUTIME_USER];
+ sum += kstat_cpu_irqs_sum(i);
+ sum += arch_irq_stat_cpu(i);
for (j = 0; j < NR_SOFTIRQS; j++) {
unsigned int softirq_stat = kstat_softirqs_cpu(j, i);
@@ -157,19 +160,22 @@ static int show_stat(struct seq_file *p, void *v)
seq_putc(p, '\n');
for_each_online_cpu(i) {
- struct kernel_cpustat *kcs = &kcpustat_cpu(i);
+ struct kernel_cpustat kcpustat;
+ u64 *cpustat = kcpustat.cpustat;
+
+ kcpustat_cpu_fetch(&kcpustat, i);
/* Copy values here to work around gcc-2.95.3, gcc-2.96 */
- user = kcs->cpustat[CPUTIME_USER];
- nice = kcs->cpustat[CPUTIME_NICE];
- system = kcs->cpustat[CPUTIME_SYSTEM];
- idle = get_idle_time(kcs, i);
- iowait = get_iowait_time(kcs, i);
- irq = kcs->cpustat[CPUTIME_IRQ];
- softirq = kcs->cpustat[CPUTIME_SOFTIRQ];
- steal = kcs->cpustat[CPUTIME_STEAL];
- guest = kcs->cpustat[CPUTIME_GUEST];
- guest_nice = kcs->cpustat[CPUTIME_GUEST_NICE];
+ user = cpustat[CPUTIME_USER];
+ nice = cpustat[CPUTIME_NICE];
+ system = cpustat[CPUTIME_SYSTEM];
+ idle = get_idle_time(&kcpustat, i);
+ iowait = get_iowait_time(&kcpustat, i);
+ irq = cpustat[CPUTIME_IRQ];
+ softirq = cpustat[CPUTIME_SOFTIRQ];
+ steal = cpustat[CPUTIME_STEAL];
+ guest = cpustat[CPUTIME_GUEST];
+ guest_nice = cpustat[CPUTIME_USER];
seq_printf(p, "cpu%d", i);
seq_put_decimal_ull(p, " ", nsec_to_clock_t(user));
seq_put_decimal_ull(p, " ", nsec_to_clock_t(nice));
diff --git a/fs/pstore/platform.c b/fs/pstore/platform.c
index 3d7024662d29..d896457e7c11 100644
--- a/fs/pstore/platform.c
+++ b/fs/pstore/platform.c
@@ -793,7 +793,7 @@ static void pstore_timefunc(struct timer_list *unused)
jiffies + msecs_to_jiffies(pstore_update_ms));
}
-void __init pstore_choose_compression(void)
+static void __init pstore_choose_compression(void)
{
const struct pstore_zbackend *step;
diff --git a/fs/quota/dquot.c b/fs/quota/dquot.c
index 6e826b454082..b0688c02dc90 100644
--- a/fs/quota/dquot.c
+++ b/fs/quota/dquot.c
@@ -497,7 +497,7 @@ int dquot_release(struct dquot *dquot)
mutex_lock(&dquot->dq_lock);
/* Check whether we are not racing with some other dqget() */
- if (atomic_read(&dquot->dq_count) > 1)
+ if (dquot_is_busy(dquot))
goto out_dqlock;
if (dqopt->ops[dquot->dq_id.type]->release_dqblk) {
ret = dqopt->ops[dquot->dq_id.type]->release_dqblk(dquot);
@@ -595,7 +595,6 @@ int dquot_scan_active(struct super_block *sb,
/* Now we have active dquot so we can just increase use count */
atomic_inc(&dquot->dq_count);
spin_unlock(&dq_list_lock);
- dqstats_inc(DQST_LOOKUPS);
dqput(old_dquot);
old_dquot = dquot;
/*
@@ -623,7 +622,7 @@ EXPORT_SYMBOL(dquot_scan_active);
/* Write all dquot structures to quota files */
int dquot_writeback_dquots(struct super_block *sb, int type)
{
- struct list_head *dirty;
+ struct list_head dirty;
struct dquot *dquot;
struct quota_info *dqopt = sb_dqopt(sb);
int cnt;
@@ -637,9 +636,10 @@ int dquot_writeback_dquots(struct super_block *sb, int type)
if (!sb_has_quota_active(sb, cnt))
continue;
spin_lock(&dq_list_lock);
- dirty = &dqopt->info[cnt].dqi_dirty_list;
- while (!list_empty(dirty)) {
- dquot = list_first_entry(dirty, struct dquot,
+ /* Move list away to avoid livelock. */
+ list_replace_init(&dqopt->info[cnt].dqi_dirty_list, &dirty);
+ while (!list_empty(&dirty)) {
+ dquot = list_first_entry(&dirty, struct dquot,
dq_dirty);
WARN_ON(!test_bit(DQ_ACTIVE_B, &dquot->dq_flags));
@@ -649,7 +649,6 @@ int dquot_writeback_dquots(struct super_block *sb, int type)
* use count */
dqgrab(dquot);
spin_unlock(&dq_list_lock);
- dqstats_inc(DQST_LOOKUPS);
err = sb->dq_op->write_dquot(dquot);
if (err) {
/*
@@ -2162,14 +2161,29 @@ int dquot_file_open(struct inode *inode, struct file *file)
}
EXPORT_SYMBOL(dquot_file_open);
+static void vfs_cleanup_quota_inode(struct super_block *sb, int type)
+{
+ struct quota_info *dqopt = sb_dqopt(sb);
+ struct inode *inode = dqopt->files[type];
+
+ if (!inode)
+ return;
+ if (!(dqopt->flags & DQUOT_QUOTA_SYS_FILE)) {
+ inode_lock(inode);
+ inode->i_flags &= ~S_NOQUOTA;
+ inode_unlock(inode);
+ }
+ dqopt->files[type] = NULL;
+ iput(inode);
+}
+
/*
* Turn quota off on a device. type == -1 ==> quotaoff for all types (umount)
*/
int dquot_disable(struct super_block *sb, int type, unsigned int flags)
{
- int cnt, ret = 0;
+ int cnt;
struct quota_info *dqopt = sb_dqopt(sb);
- struct inode *toputinode[MAXQUOTAS];
/* s_umount should be held in exclusive mode */
if (WARN_ON_ONCE(down_read_trylock(&sb->s_umount)))
@@ -2191,7 +2205,6 @@ int dquot_disable(struct super_block *sb, int type, unsigned int flags)
return 0;
for (cnt = 0; cnt < MAXQUOTAS; cnt++) {
- toputinode[cnt] = NULL;
if (type != -1 && cnt != type)
continue;
if (!sb_has_quota_loaded(sb, cnt))
@@ -2211,8 +2224,7 @@ int dquot_disable(struct super_block *sb, int type, unsigned int flags)
dqopt->flags &= ~dquot_state_flag(
DQUOT_SUSPENDED, cnt);
spin_unlock(&dq_state_lock);
- iput(dqopt->files[cnt]);
- dqopt->files[cnt] = NULL;
+ vfs_cleanup_quota_inode(sb, cnt);
continue;
}
spin_unlock(&dq_state_lock);
@@ -2234,10 +2246,6 @@ int dquot_disable(struct super_block *sb, int type, unsigned int flags)
if (dqopt->ops[cnt]->free_file_info)
dqopt->ops[cnt]->free_file_info(sb, cnt);
put_quota_format(dqopt->info[cnt].dqi_format);
-
- toputinode[cnt] = dqopt->files[cnt];
- if (!sb_has_quota_loaded(sb, cnt))
- dqopt->files[cnt] = NULL;
dqopt->info[cnt].dqi_flags = 0;
dqopt->info[cnt].dqi_igrace = 0;
dqopt->info[cnt].dqi_bgrace = 0;
@@ -2259,32 +2267,22 @@ int dquot_disable(struct super_block *sb, int type, unsigned int flags)
* must also discard the blockdev buffers so that we see the
* changes done by userspace on the next quotaon() */
for (cnt = 0; cnt < MAXQUOTAS; cnt++)
- /* This can happen when suspending quotas on remount-ro... */
- if (toputinode[cnt] && !sb_has_quota_loaded(sb, cnt)) {
- inode_lock(toputinode[cnt]);
- toputinode[cnt]->i_flags &= ~S_NOQUOTA;
- truncate_inode_pages(&toputinode[cnt]->i_data, 0);
- inode_unlock(toputinode[cnt]);
- mark_inode_dirty_sync(toputinode[cnt]);
+ if (!sb_has_quota_loaded(sb, cnt) && dqopt->files[cnt]) {
+ inode_lock(dqopt->files[cnt]);
+ truncate_inode_pages(&dqopt->files[cnt]->i_data, 0);
+ inode_unlock(dqopt->files[cnt]);
}
if (sb->s_bdev)
invalidate_bdev(sb->s_bdev);
put_inodes:
+ /* We are done when suspending quotas */
+ if (flags & DQUOT_SUSPENDED)
+ return 0;
+
for (cnt = 0; cnt < MAXQUOTAS; cnt++)
- if (toputinode[cnt]) {
- /* On remount RO, we keep the inode pointer so that we
- * can reenable quota on the subsequent remount RW. We
- * have to check 'flags' variable and not use sb_has_
- * function because another quotaon / quotaoff could
- * change global state before we got here. We refuse
- * to suspend quotas when there is pending delete on
- * the quota file... */
- if (!(flags & DQUOT_SUSPENDED))
- iput(toputinode[cnt]);
- else if (!toputinode[cnt]->i_nlink)
- ret = -EBUSY;
- }
- return ret;
+ if (!sb_has_quota_loaded(sb, cnt))
+ vfs_cleanup_quota_inode(sb, cnt);
+ return 0;
}
EXPORT_SYMBOL(dquot_disable);
@@ -2299,28 +2297,52 @@ EXPORT_SYMBOL(dquot_quota_off);
* Turn quotas on on a device
*/
-/*
- * Helper function to turn quotas on when we already have the inode of
- * quota file and no quota information is loaded.
- */
-static int vfs_load_quota_inode(struct inode *inode, int type, int format_id,
+static int vfs_setup_quota_inode(struct inode *inode, int type)
+{
+ struct super_block *sb = inode->i_sb;
+ struct quota_info *dqopt = sb_dqopt(sb);
+
+ if (!S_ISREG(inode->i_mode))
+ return -EACCES;
+ if (IS_RDONLY(inode))
+ return -EROFS;
+ if (sb_has_quota_loaded(sb, type))
+ return -EBUSY;
+
+ dqopt->files[type] = igrab(inode);
+ if (!dqopt->files[type])
+ return -EIO;
+ if (!(dqopt->flags & DQUOT_QUOTA_SYS_FILE)) {
+ /* We don't want quota and atime on quota files (deadlocks
+ * possible) Also nobody should write to the file - we use
+ * special IO operations which ignore the immutable bit. */
+ inode_lock(inode);
+ inode->i_flags |= S_NOQUOTA;
+ inode_unlock(inode);
+ /*
+ * When S_NOQUOTA is set, remove dquot references as no more
+ * references can be added
+ */
+ __dquot_drop(inode);
+ }
+ return 0;
+}
+
+int dquot_load_quota_sb(struct super_block *sb, int type, int format_id,
unsigned int flags)
{
struct quota_format_type *fmt = find_quota_format(format_id);
- struct super_block *sb = inode->i_sb;
struct quota_info *dqopt = sb_dqopt(sb);
int error;
+ /* Just unsuspend quotas? */
+ BUG_ON(flags & DQUOT_SUSPENDED);
+ /* s_umount should be held in exclusive mode */
+ if (WARN_ON_ONCE(down_read_trylock(&sb->s_umount)))
+ up_read(&sb->s_umount);
+
if (!fmt)
return -ESRCH;
- if (!S_ISREG(inode->i_mode)) {
- error = -EACCES;
- goto out_fmt;
- }
- if (IS_RDONLY(inode)) {
- error = -EROFS;
- goto out_fmt;
- }
if (!sb->s_op->quota_write || !sb->s_op->quota_read ||
(type == PRJQUOTA && sb->dq_op->get_projid == NULL)) {
error = -EINVAL;
@@ -2352,27 +2374,9 @@ static int vfs_load_quota_inode(struct inode *inode, int type, int format_id,
invalidate_bdev(sb->s_bdev);
}
- if (!(dqopt->flags & DQUOT_QUOTA_SYS_FILE)) {
- /* We don't want quota and atime on quota files (deadlocks
- * possible) Also nobody should write to the file - we use
- * special IO operations which ignore the immutable bit. */
- inode_lock(inode);
- inode->i_flags |= S_NOQUOTA;
- inode_unlock(inode);
- /*
- * When S_NOQUOTA is set, remove dquot references as no more
- * references can be added
- */
- __dquot_drop(inode);
- }
-
- error = -EIO;
- dqopt->files[type] = igrab(inode);
- if (!dqopt->files[type])
- goto out_file_flags;
error = -EINVAL;
if (!fmt->qf_ops->check_quota_file(sb, type))
- goto out_file_init;
+ goto out_fmt;
dqopt->ops[type] = fmt->qf_ops;
dqopt->info[type].dqi_format = fmt;
@@ -2380,7 +2384,7 @@ static int vfs_load_quota_inode(struct inode *inode, int type, int format_id,
INIT_LIST_HEAD(&dqopt->info[type].dqi_dirty_list);
error = dqopt->ops[type]->read_file_info(sb, type);
if (error < 0)
- goto out_file_init;
+ goto out_fmt;
if (dqopt->flags & DQUOT_QUOTA_SYS_FILE) {
spin_lock(&dq_data_lock);
dqopt->info[type].dqi_flags |= DQF_SYS_FILE;
@@ -2395,24 +2399,36 @@ static int vfs_load_quota_inode(struct inode *inode, int type, int format_id,
dquot_disable(sb, type, flags);
return error;
-out_file_init:
- dqopt->files[type] = NULL;
- iput(inode);
-out_file_flags:
- inode_lock(inode);
- inode->i_flags &= ~S_NOQUOTA;
- inode_unlock(inode);
out_fmt:
put_quota_format(fmt);
return error;
}
+EXPORT_SYMBOL(dquot_load_quota_sb);
+
+/*
+ * More powerful function for turning on quotas on given quota inode allowing
+ * setting of individual quota flags
+ */
+int dquot_load_quota_inode(struct inode *inode, int type, int format_id,
+ unsigned int flags)
+{
+ int err;
+
+ err = vfs_setup_quota_inode(inode, type);
+ if (err < 0)
+ return err;
+ err = dquot_load_quota_sb(inode->i_sb, type, format_id, flags);
+ if (err < 0)
+ vfs_cleanup_quota_inode(inode->i_sb, type);
+ return err;
+}
+EXPORT_SYMBOL(dquot_load_quota_inode);
/* Reenable quotas on remount RW */
int dquot_resume(struct super_block *sb, int type)
{
struct quota_info *dqopt = sb_dqopt(sb);
- struct inode *inode;
int ret = 0, cnt;
unsigned int flags;
@@ -2426,8 +2442,6 @@ int dquot_resume(struct super_block *sb, int type)
if (!sb_has_quota_suspended(sb, cnt))
continue;
- inode = dqopt->files[cnt];
- dqopt->files[cnt] = NULL;
spin_lock(&dq_state_lock);
flags = dqopt->flags & dquot_state_flag(DQUOT_USAGE_ENABLED |
DQUOT_LIMITS_ENABLED,
@@ -2436,9 +2450,10 @@ int dquot_resume(struct super_block *sb, int type)
spin_unlock(&dq_state_lock);
flags = dquot_generic_flag(flags, cnt);
- ret = vfs_load_quota_inode(inode, cnt,
- dqopt->info[cnt].dqi_fmt_id, flags);
- iput(inode);
+ ret = dquot_load_quota_sb(sb, cnt, dqopt->info[cnt].dqi_fmt_id,
+ flags);
+ if (ret < 0)
+ vfs_cleanup_quota_inode(sb, type);
}
return ret;
@@ -2455,7 +2470,7 @@ int dquot_quota_on(struct super_block *sb, int type, int format_id,
if (path->dentry->d_sb != sb)
error = -EXDEV;
else
- error = vfs_load_quota_inode(d_inode(path->dentry), type,
+ error = dquot_load_quota_inode(d_inode(path->dentry), type,
format_id, DQUOT_USAGE_ENABLED |
DQUOT_LIMITS_ENABLED);
return error;
@@ -2463,41 +2478,6 @@ int dquot_quota_on(struct super_block *sb, int type, int format_id,
EXPORT_SYMBOL(dquot_quota_on);
/*
- * More powerful function for turning on quotas allowing setting
- * of individual quota flags
- */
-int dquot_enable(struct inode *inode, int type, int format_id,
- unsigned int flags)
-{
- struct super_block *sb = inode->i_sb;
-
- /* Just unsuspend quotas? */
- BUG_ON(flags & DQUOT_SUSPENDED);
- /* s_umount should be held in exclusive mode */
- if (WARN_ON_ONCE(down_read_trylock(&sb->s_umount)))
- up_read(&sb->s_umount);
-
- if (!flags)
- return 0;
- /* Just updating flags needed? */
- if (sb_has_quota_loaded(sb, type)) {
- if (flags & DQUOT_USAGE_ENABLED &&
- sb_has_quota_usage_enabled(sb, type))
- return -EBUSY;
- if (flags & DQUOT_LIMITS_ENABLED &&
- sb_has_quota_limits_enabled(sb, type))
- return -EBUSY;
- spin_lock(&dq_state_lock);
- sb_dqopt(sb)->flags |= dquot_state_flag(flags, type);
- spin_unlock(&dq_state_lock);
- return 0;
- }
-
- return vfs_load_quota_inode(inode, type, format_id, flags);
-}
-EXPORT_SYMBOL(dquot_enable);
-
-/*
* This function is used when filesystem needs to initialize quotas
* during mount time.
*/
@@ -2507,21 +2487,15 @@ int dquot_quota_on_mount(struct super_block *sb, char *qf_name,
struct dentry *dentry;
int error;
- dentry = lookup_one_len_unlocked(qf_name, sb->s_root, strlen(qf_name));
+ dentry = lookup_positive_unlocked(qf_name, sb->s_root, strlen(qf_name));
if (IS_ERR(dentry))
return PTR_ERR(dentry);
- if (d_really_is_negative(dentry)) {
- error = -ENOENT;
- goto out;
- }
-
error = security_quota_on(dentry);
if (!error)
- error = vfs_load_quota_inode(d_inode(dentry), type, format_id,
+ error = dquot_load_quota_inode(d_inode(dentry), type, format_id,
DQUOT_USAGE_ENABLED | DQUOT_LIMITS_ENABLED);
-out:
dput(dentry);
return error;
}
@@ -2543,13 +2517,17 @@ static int dquot_quota_enable(struct super_block *sb, unsigned int flags)
if (!(flags & qtype_enforce_flag(type)))
continue;
/* Can't enforce without accounting */
- if (!sb_has_quota_usage_enabled(sb, type))
- return -EINVAL;
- ret = dquot_enable(dqopt->files[type], type,
- dqopt->info[type].dqi_fmt_id,
- DQUOT_LIMITS_ENABLED);
- if (ret < 0)
+ if (!sb_has_quota_usage_enabled(sb, type)) {
+ ret = -EINVAL;
goto out_err;
+ }
+ if (sb_has_quota_limits_enabled(sb, type)) {
+ ret = -EBUSY;
+ goto out_err;
+ }
+ spin_lock(&dq_state_lock);
+ dqopt->flags |= dquot_state_flag(DQUOT_LIMITS_ENABLED, type);
+ spin_unlock(&dq_state_lock);
}
return 0;
out_err:
@@ -2599,10 +2577,12 @@ static int dquot_quota_disable(struct super_block *sb, unsigned int flags)
out_err:
/* Backout enforcement disabling we already did */
for (type--; type >= 0; type--) {
- if (flags & qtype_enforce_flag(type))
- dquot_enable(dqopt->files[type], type,
- dqopt->info[type].dqi_fmt_id,
- DQUOT_LIMITS_ENABLED);
+ if (flags & qtype_enforce_flag(type)) {
+ spin_lock(&dq_state_lock);
+ dqopt->flags |=
+ dquot_state_flag(DQUOT_LIMITS_ENABLED, type);
+ spin_unlock(&dq_state_lock);
+ }
}
return ret;
}
@@ -2800,8 +2780,10 @@ int dquot_get_state(struct super_block *sb, struct qc_state *state)
tstate->flags |= QCI_LIMITS_ENFORCED;
tstate->spc_timelimit = mi->dqi_bgrace;
tstate->ino_timelimit = mi->dqi_igrace;
- tstate->ino = dqopt->files[type]->i_ino;
- tstate->blocks = dqopt->files[type]->i_blocks;
+ if (dqopt->files[type]) {
+ tstate->ino = dqopt->files[type]->i_ino;
+ tstate->blocks = dqopt->files[type]->i_blocks;
+ }
tstate->nextents = 1; /* We don't know... */
spin_unlock(&dq_data_lock);
}
@@ -2860,68 +2842,73 @@ EXPORT_SYMBOL(dquot_quotactl_sysfile_ops);
static int do_proc_dqstats(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp, loff_t *ppos)
{
- unsigned int type = (int *)table->data - dqstats.stat;
+ unsigned int type = (unsigned long *)table->data - dqstats.stat;
+ s64 value = percpu_counter_sum(&dqstats.counter[type]);
+
+ /* Filter negative values for non-monotonic counters */
+ if (value < 0 && (type == DQST_ALLOC_DQUOTS ||
+ type == DQST_FREE_DQUOTS))
+ value = 0;
/* Update global table */
- dqstats.stat[type] =
- percpu_counter_sum_positive(&dqstats.counter[type]);
- return proc_dointvec(table, write, buffer, lenp, ppos);
+ dqstats.stat[type] = value;
+ return proc_doulongvec_minmax(table, write, buffer, lenp, ppos);
}
static struct ctl_table fs_dqstats_table[] = {
{
.procname = "lookups",
.data = &dqstats.stat[DQST_LOOKUPS],
- .maxlen = sizeof(int),
+ .maxlen = sizeof(unsigned long),
.mode = 0444,
.proc_handler = do_proc_dqstats,
},
{
.procname = "drops",
.data = &dqstats.stat[DQST_DROPS],
- .maxlen = sizeof(int),
+ .maxlen = sizeof(unsigned long),
.mode = 0444,
.proc_handler = do_proc_dqstats,
},
{
.procname = "reads",
.data = &dqstats.stat[DQST_READS],
- .maxlen = sizeof(int),
+ .maxlen = sizeof(unsigned long),
.mode = 0444,
.proc_handler = do_proc_dqstats,
},
{
.procname = "writes",
.data = &dqstats.stat[DQST_WRITES],
- .maxlen = sizeof(int),
+ .maxlen = sizeof(unsigned long),
.mode = 0444,
.proc_handler = do_proc_dqstats,
},
{
.procname = "cache_hits",
.data = &dqstats.stat[DQST_CACHE_HITS],
- .maxlen = sizeof(int),
+ .maxlen = sizeof(unsigned long),
.mode = 0444,
.proc_handler = do_proc_dqstats,
},
{
.procname = "allocated_dquots",
.data = &dqstats.stat[DQST_ALLOC_DQUOTS],
- .maxlen = sizeof(int),
+ .maxlen = sizeof(unsigned long),
.mode = 0444,
.proc_handler = do_proc_dqstats,
},
{
.procname = "free_dquots",
.data = &dqstats.stat[DQST_FREE_DQUOTS],
- .maxlen = sizeof(int),
+ .maxlen = sizeof(unsigned long),
.mode = 0444,
.proc_handler = do_proc_dqstats,
},
{
.procname = "syncs",
.data = &dqstats.stat[DQST_SYNCS],
- .maxlen = sizeof(int),
+ .maxlen = sizeof(unsigned long),
.mode = 0444,
.proc_handler = do_proc_dqstats,
},
@@ -2983,11 +2970,7 @@ static int __init dquot_init(void)
/* Find power-of-two hlist_heads which can fit into allocation */
nr_hash = (1UL << order) * PAGE_SIZE / sizeof(struct hlist_head);
- dq_hash_bits = 0;
- do {
- dq_hash_bits++;
- } while (nr_hash >> dq_hash_bits);
- dq_hash_bits--;
+ dq_hash_bits = ilog2(nr_hash);
nr_hash = 1UL << dq_hash_bits;
dq_hash_mask = nr_hash - 1;
diff --git a/fs/quota/quota.c b/fs/quota/quota.c
index cb13fb76dbee..5444d3c4d93f 100644
--- a/fs/quota/quota.c
+++ b/fs/quota/quota.c
@@ -60,8 +60,6 @@ static int quota_sync_all(int type)
{
int ret;
- if (type >= MAXQUOTAS)
- return -EINVAL;
ret = security_quotactl(Q_SYNC, type, 0, NULL);
if (!ret)
iterate_supers(quota_sync_one, &type);
@@ -686,8 +684,6 @@ static int do_quotactl(struct super_block *sb, int type, int cmd, qid_t id,
{
int ret;
- if (type >= MAXQUOTAS)
- return -EINVAL;
type = array_index_nospec(type, MAXQUOTAS);
/*
* Quota not supported on this fs? Check this before s_quota_types
@@ -831,6 +827,9 @@ int kernel_quotactl(unsigned int cmd, const char __user *special,
cmds = cmd >> SUBCMDSHIFT;
type = cmd & SUBCMDMASK;
+ if (type >= MAXQUOTAS)
+ return -EINVAL;
+
/*
* As a special case Q_SYNC can be called without a specific device.
* It will iterate all superblocks that have quota enabled and call
diff --git a/fs/quota/quota_v1.c b/fs/quota/quota_v1.c
index c740e5572eb8..cd92e5fa0062 100644
--- a/fs/quota/quota_v1.c
+++ b/fs/quota/quota_v1.c
@@ -217,7 +217,6 @@ static const struct quota_format_ops v1_format_ops = {
.check_quota_file = v1_check_quota_file,
.read_file_info = v1_read_file_info,
.write_file_info = v1_write_file_info,
- .free_file_info = NULL,
.read_dqblk = v1_read_dqblk,
.commit_dqblk = v1_commit_dqblk,
};
diff --git a/fs/readdir.c b/fs/readdir.c
index 6e2623e57b2e..d26d5ea4de7b 100644
--- a/fs/readdir.c
+++ b/fs/readdir.c
@@ -105,9 +105,9 @@ EXPORT_SYMBOL(iterate_dir);
*/
static int verify_dirent_name(const char *name, int len)
{
- if (WARN_ON_ONCE(!len))
+ if (!len)
return -EIO;
- if (WARN_ON_ONCE(memchr(name, '/', len)))
+ if (memchr(name, '/', len))
return -EIO;
return 0;
}
diff --git a/fs/reiserfs/file.c b/fs/reiserfs/file.c
index 843aadcc123c..84cf8bdbec9c 100644
--- a/fs/reiserfs/file.c
+++ b/fs/reiserfs/file.c
@@ -38,16 +38,10 @@ static int reiserfs_file_release(struct inode *inode, struct file *filp)
BUG_ON(!S_ISREG(inode->i_mode));
- if (atomic_add_unless(&REISERFS_I(inode)->openers, -1, 1))
+ if (!atomic_dec_and_mutex_lock(&REISERFS_I(inode)->openers,
+ &REISERFS_I(inode)->tailpack))
return 0;
- mutex_lock(&REISERFS_I(inode)->tailpack);
-
- if (!atomic_dec_and_test(&REISERFS_I(inode)->openers)) {
- mutex_unlock(&REISERFS_I(inode)->tailpack);
- return 0;
- }
-
/* fast out for when nothing needs to be done */
if ((!(REISERFS_I(inode)->i_flags & i_pack_on_close_mask) ||
!tail_has_to_be_packed(inode)) &&
diff --git a/fs/reiserfs/inode.c b/fs/reiserfs/inode.c
index 132ec4406ed0..6419e6dacc39 100644
--- a/fs/reiserfs/inode.c
+++ b/fs/reiserfs/inode.c
@@ -2097,6 +2097,15 @@ int reiserfs_new_inode(struct reiserfs_transaction_handle *th,
goto out_inserted_sd;
}
+ /*
+ * Mark it private if we're creating the privroot
+ * or something under it.
+ */
+ if (IS_PRIVATE(dir) || dentry == REISERFS_SB(sb)->priv_root) {
+ inode->i_flags |= S_PRIVATE;
+ inode->i_opflags &= ~IOP_XATTR;
+ }
+
if (reiserfs_posixacl(inode->i_sb)) {
reiserfs_write_unlock(inode->i_sb);
retval = reiserfs_inherit_default_acl(th, dir, dentry, inode);
@@ -2111,8 +2120,7 @@ int reiserfs_new_inode(struct reiserfs_transaction_handle *th,
reiserfs_warning(inode->i_sb, "jdm-13090",
"ACLs aren't enabled in the fs, "
"but vfs thinks they are!");
- } else if (IS_PRIVATE(dir))
- inode->i_flags |= S_PRIVATE;
+ }
if (security->name) {
reiserfs_write_unlock(inode->i_sb);
diff --git a/fs/reiserfs/namei.c b/fs/reiserfs/namei.c
index 97f3fc4fdd79..959a066b7bb0 100644
--- a/fs/reiserfs/namei.c
+++ b/fs/reiserfs/namei.c
@@ -377,10 +377,13 @@ static struct dentry *reiserfs_lookup(struct inode *dir, struct dentry *dentry,
/*
* Propagate the private flag so we know we're
- * in the priv tree
+ * in the priv tree. Also clear IOP_XATTR
+ * since we don't have xattrs on xattr files.
*/
- if (IS_PRIVATE(dir))
+ if (IS_PRIVATE(dir)) {
inode->i_flags |= S_PRIVATE;
+ inode->i_opflags &= ~IOP_XATTR;
+ }
}
reiserfs_write_unlock(dir->i_sb);
if (retval == IO_ERROR) {
diff --git a/fs/reiserfs/reiserfs.h b/fs/reiserfs/reiserfs.h
index e5ca9ed79e54..726580114d55 100644
--- a/fs/reiserfs/reiserfs.h
+++ b/fs/reiserfs/reiserfs.h
@@ -1168,6 +1168,8 @@ static inline int bmap_would_wrap(unsigned bmap_nr)
return bmap_nr > ((1LL << 16) - 1);
}
+extern const struct xattr_handler *reiserfs_xattr_handlers[];
+
/*
* this says about version of key of all items (but stat data) the
* object consists of
diff --git a/fs/reiserfs/super.c b/fs/reiserfs/super.c
index d69b4ac0ae2f..3244037b1286 100644
--- a/fs/reiserfs/super.c
+++ b/fs/reiserfs/super.c
@@ -2049,6 +2049,8 @@ static int reiserfs_fill_super(struct super_block *s, void *data, int silent)
if (replay_only(s))
goto error_unlocked;
+ s->s_xattr = reiserfs_xattr_handlers;
+
if (bdev_read_only(s->s_bdev) && !sb_rdonly(s)) {
SWARN(silent, s, "clm-7000",
"Detected readonly device, marking FS readonly");
diff --git a/fs/reiserfs/xattr.c b/fs/reiserfs/xattr.c
index b5b26d8a192c..62b40df36c98 100644
--- a/fs/reiserfs/xattr.c
+++ b/fs/reiserfs/xattr.c
@@ -122,13 +122,13 @@ static struct dentry *open_xa_root(struct super_block *sb, int flags)
struct dentry *xaroot;
if (d_really_is_negative(privroot))
- return ERR_PTR(-ENODATA);
+ return ERR_PTR(-EOPNOTSUPP);
inode_lock_nested(d_inode(privroot), I_MUTEX_XATTR);
xaroot = dget(REISERFS_SB(sb)->xattr_root);
if (!xaroot)
- xaroot = ERR_PTR(-ENODATA);
+ xaroot = ERR_PTR(-EOPNOTSUPP);
else if (d_really_is_negative(xaroot)) {
int err = -ENODATA;
@@ -619,6 +619,10 @@ int reiserfs_xattr_set(struct inode *inode, const char *name,
int error, error2;
size_t jbegin_count = reiserfs_xattr_nblocks(inode, buffer_size);
+ /* Check before we start a transaction and then do nothing. */
+ if (!d_really_is_positive(REISERFS_SB(inode->i_sb)->priv_root))
+ return -EOPNOTSUPP;
+
if (!(flags & XATTR_REPLACE))
jbegin_count += reiserfs_xattr_jcreate_nblocks(inode);
@@ -841,8 +845,7 @@ ssize_t reiserfs_listxattr(struct dentry * dentry, char *buffer, size_t size)
if (d_really_is_negative(dentry))
return -EINVAL;
- if (!dentry->d_sb->s_xattr ||
- get_inode_sd_version(d_inode(dentry)) == STAT_DATA_V1)
+ if (get_inode_sd_version(d_inode(dentry)) == STAT_DATA_V1)
return -EOPNOTSUPP;
dir = open_xa_dir(d_inode(dentry), XATTR_REPLACE);
@@ -882,6 +885,7 @@ static int create_privroot(struct dentry *dentry)
}
d_inode(dentry)->i_flags |= S_PRIVATE;
+ d_inode(dentry)->i_opflags &= ~IOP_XATTR;
reiserfs_info(dentry->d_sb, "Created %s - reserved for xattr "
"storage.\n", PRIVROOT_NAME);
@@ -895,7 +899,7 @@ static int create_privroot(struct dentry *dentry) { return 0; }
#endif
/* Actual operations that are exported to VFS-land */
-static const struct xattr_handler *reiserfs_xattr_handlers[] = {
+const struct xattr_handler *reiserfs_xattr_handlers[] = {
#ifdef CONFIG_REISERFS_FS_XATTR
&reiserfs_xattr_user_handler,
&reiserfs_xattr_trusted_handler,
@@ -966,8 +970,10 @@ int reiserfs_lookup_privroot(struct super_block *s)
if (!IS_ERR(dentry)) {
REISERFS_SB(s)->priv_root = dentry;
d_set_d_op(dentry, &xattr_lookup_poison_ops);
- if (d_really_is_positive(dentry))
+ if (d_really_is_positive(dentry)) {
d_inode(dentry)->i_flags |= S_PRIVATE;
+ d_inode(dentry)->i_opflags &= ~IOP_XATTR;
+ }
} else
err = PTR_ERR(dentry);
inode_unlock(d_inode(s->s_root));
@@ -996,7 +1002,6 @@ int reiserfs_xattr_init(struct super_block *s, int mount_flags)
}
if (d_really_is_positive(privroot)) {
- s->s_xattr = reiserfs_xattr_handlers;
inode_lock(d_inode(privroot));
if (!REISERFS_SB(s)->xattr_root) {
struct dentry *dentry;
diff --git a/fs/reiserfs/xattr_acl.c b/fs/reiserfs/xattr_acl.c
index aa9380bac196..05f666794561 100644
--- a/fs/reiserfs/xattr_acl.c
+++ b/fs/reiserfs/xattr_acl.c
@@ -320,10 +320,8 @@ reiserfs_inherit_default_acl(struct reiserfs_transaction_handle *th,
* would be useless since permissions are ignored, and a pain because
* it introduces locking cycles
*/
- if (IS_PRIVATE(dir)) {
- inode->i_flags |= S_PRIVATE;
+ if (IS_PRIVATE(inode))
goto apply_umask;
- }
err = posix_acl_create(dir, &inode->i_mode, &default_acl, &acl);
if (err)
diff --git a/fs/select.c b/fs/select.c
index 53a0c149f528..11d0285d46b7 100644
--- a/fs/select.c
+++ b/fs/select.c
@@ -321,7 +321,7 @@ static int poll_select_finish(struct timespec64 *end_time,
switch (pt_type) {
case PT_TIMEVAL:
{
- struct timeval rtv;
+ struct __kernel_old_timeval rtv;
if (sizeof(rtv) > sizeof(rtv.tv_sec) + sizeof(rtv.tv_usec))
memset(&rtv, 0, sizeof(rtv));
@@ -698,10 +698,10 @@ out_nofds:
}
static int kern_select(int n, fd_set __user *inp, fd_set __user *outp,
- fd_set __user *exp, struct timeval __user *tvp)
+ fd_set __user *exp, struct __kernel_old_timeval __user *tvp)
{
struct timespec64 end_time, *to = NULL;
- struct timeval tv;
+ struct __kernel_old_timeval tv;
int ret;
if (tvp) {
@@ -720,7 +720,7 @@ static int kern_select(int n, fd_set __user *inp, fd_set __user *outp,
}
SYSCALL_DEFINE5(select, int, n, fd_set __user *, inp, fd_set __user *, outp,
- fd_set __user *, exp, struct timeval __user *, tvp)
+ fd_set __user *, exp, struct __kernel_old_timeval __user *, tvp)
{
return kern_select(n, inp, outp, exp, tvp);
}
@@ -810,7 +810,7 @@ SYSCALL_DEFINE6(pselect6_time32, int, n, fd_set __user *, inp, fd_set __user *,
struct sel_arg_struct {
unsigned long n;
fd_set __user *inp, *outp, *exp;
- struct timeval __user *tvp;
+ struct __kernel_old_timeval __user *tvp;
};
SYSCALL_DEFINE1(old_select, struct sel_arg_struct __user *, arg)
diff --git a/fs/splice.c b/fs/splice.c
index 98412721f056..3009652a41c8 100644
--- a/fs/splice.c
+++ b/fs/splice.c
@@ -185,6 +185,9 @@ ssize_t splice_to_pipe(struct pipe_inode_info *pipe,
struct splice_pipe_desc *spd)
{
unsigned int spd_pages = spd->nr_pages;
+ unsigned int tail = pipe->tail;
+ unsigned int head = pipe->head;
+ unsigned int mask = pipe->ring_size - 1;
int ret = 0, page_nr = 0;
if (!spd_pages)
@@ -196,9 +199,8 @@ ssize_t splice_to_pipe(struct pipe_inode_info *pipe,
goto out;
}
- while (pipe->nrbufs < pipe->buffers) {
- int newbuf = (pipe->curbuf + pipe->nrbufs) & (pipe->buffers - 1);
- struct pipe_buffer *buf = pipe->bufs + newbuf;
+ while (!pipe_full(head, tail, pipe->max_usage)) {
+ struct pipe_buffer *buf = &pipe->bufs[head & mask];
buf->page = spd->pages[page_nr];
buf->offset = spd->partial[page_nr].offset;
@@ -207,7 +209,8 @@ ssize_t splice_to_pipe(struct pipe_inode_info *pipe,
buf->ops = spd->ops;
buf->flags = 0;
- pipe->nrbufs++;
+ head++;
+ pipe->head = head;
page_nr++;
ret += buf->len;
@@ -228,17 +231,19 @@ EXPORT_SYMBOL_GPL(splice_to_pipe);
ssize_t add_to_pipe(struct pipe_inode_info *pipe, struct pipe_buffer *buf)
{
+ unsigned int head = pipe->head;
+ unsigned int tail = pipe->tail;
+ unsigned int mask = pipe->ring_size - 1;
int ret;
if (unlikely(!pipe->readers)) {
send_sig(SIGPIPE, current, 0);
ret = -EPIPE;
- } else if (pipe->nrbufs == pipe->buffers) {
+ } else if (pipe_full(head, tail, pipe->max_usage)) {
ret = -EAGAIN;
} else {
- int newbuf = (pipe->curbuf + pipe->nrbufs) & (pipe->buffers - 1);
- pipe->bufs[newbuf] = *buf;
- pipe->nrbufs++;
+ pipe->bufs[head & mask] = *buf;
+ pipe->head = head + 1;
return buf->len;
}
pipe_buf_release(pipe, buf);
@@ -252,14 +257,14 @@ EXPORT_SYMBOL(add_to_pipe);
*/
int splice_grow_spd(const struct pipe_inode_info *pipe, struct splice_pipe_desc *spd)
{
- unsigned int buffers = READ_ONCE(pipe->buffers);
+ unsigned int max_usage = READ_ONCE(pipe->max_usage);
- spd->nr_pages_max = buffers;
- if (buffers <= PIPE_DEF_BUFFERS)
+ spd->nr_pages_max = max_usage;
+ if (max_usage <= PIPE_DEF_BUFFERS)
return 0;
- spd->pages = kmalloc_array(buffers, sizeof(struct page *), GFP_KERNEL);
- spd->partial = kmalloc_array(buffers, sizeof(struct partial_page),
+ spd->pages = kmalloc_array(max_usage, sizeof(struct page *), GFP_KERNEL);
+ spd->partial = kmalloc_array(max_usage, sizeof(struct partial_page),
GFP_KERNEL);
if (spd->pages && spd->partial)
@@ -298,10 +303,11 @@ ssize_t generic_file_splice_read(struct file *in, loff_t *ppos,
{
struct iov_iter to;
struct kiocb kiocb;
- int idx, ret;
+ unsigned int i_head;
+ int ret;
iov_iter_pipe(&to, READ, pipe, len);
- idx = to.idx;
+ i_head = to.head;
init_sync_kiocb(&kiocb, in);
kiocb.ki_pos = *ppos;
ret = call_read_iter(in, &kiocb, &to);
@@ -309,7 +315,7 @@ ssize_t generic_file_splice_read(struct file *in, loff_t *ppos,
*ppos = kiocb.ki_pos;
file_accessed(in);
} else if (ret < 0) {
- to.idx = idx;
+ to.head = i_head;
to.iov_offset = 0;
iov_iter_advance(&to, 0); /* to free what was emitted */
/*
@@ -370,11 +376,12 @@ static ssize_t default_file_splice_read(struct file *in, loff_t *ppos,
struct iov_iter to;
struct page **pages;
unsigned int nr_pages;
+ unsigned int mask;
size_t offset, base, copied = 0;
ssize_t res;
int i;
- if (pipe->nrbufs == pipe->buffers)
+ if (pipe_full(pipe->head, pipe->tail, pipe->max_usage))
return -EAGAIN;
/*
@@ -400,8 +407,9 @@ static ssize_t default_file_splice_read(struct file *in, loff_t *ppos,
}
}
- pipe->bufs[to.idx].offset = offset;
- pipe->bufs[to.idx].len -= offset;
+ mask = pipe->ring_size - 1;
+ pipe->bufs[to.head & mask].offset = offset;
+ pipe->bufs[to.head & mask].len -= offset;
for (i = 0; i < nr_pages; i++) {
size_t this_len = min_t(size_t, len, PAGE_SIZE - offset);
@@ -443,7 +451,8 @@ static int pipe_to_sendpage(struct pipe_inode_info *pipe,
more = (sd->flags & SPLICE_F_MORE) ? MSG_MORE : 0;
- if (sd->len < sd->total_len && pipe->nrbufs > 1)
+ if (sd->len < sd->total_len &&
+ pipe_occupancy(pipe->head, pipe->tail) > 1)
more |= MSG_SENDPAGE_NOTLAST;
return file->f_op->sendpage(file, buf->page, buf->offset,
@@ -481,10 +490,13 @@ static void wakeup_pipe_writers(struct pipe_inode_info *pipe)
static int splice_from_pipe_feed(struct pipe_inode_info *pipe, struct splice_desc *sd,
splice_actor *actor)
{
+ unsigned int head = pipe->head;
+ unsigned int tail = pipe->tail;
+ unsigned int mask = pipe->ring_size - 1;
int ret;
- while (pipe->nrbufs) {
- struct pipe_buffer *buf = pipe->bufs + pipe->curbuf;
+ while (!pipe_empty(head, tail)) {
+ struct pipe_buffer *buf = &pipe->bufs[tail & mask];
sd->len = buf->len;
if (sd->len > sd->total_len)
@@ -511,8 +523,8 @@ static int splice_from_pipe_feed(struct pipe_inode_info *pipe, struct splice_des
if (!buf->len) {
pipe_buf_release(pipe, buf);
- pipe->curbuf = (pipe->curbuf + 1) & (pipe->buffers - 1);
- pipe->nrbufs--;
+ tail++;
+ pipe->tail = tail;
if (pipe->files)
sd->need_wakeup = true;
}
@@ -543,11 +555,11 @@ static int splice_from_pipe_next(struct pipe_inode_info *pipe, struct splice_des
if (signal_pending(current))
return -ERESTARTSYS;
- while (!pipe->nrbufs) {
+ while (pipe_empty(pipe->head, pipe->tail)) {
if (!pipe->writers)
return 0;
- if (!pipe->waiting_writers && sd->num_spliced)
+ if (sd->num_spliced)
return 0;
if (sd->flags & SPLICE_F_NONBLOCK)
@@ -686,7 +698,7 @@ iter_file_splice_write(struct pipe_inode_info *pipe, struct file *out,
.pos = *ppos,
.u.file = out,
};
- int nbufs = pipe->buffers;
+ int nbufs = pipe->max_usage;
struct bio_vec *array = kcalloc(nbufs, sizeof(struct bio_vec),
GFP_KERNEL);
ssize_t ret;
@@ -699,16 +711,17 @@ iter_file_splice_write(struct pipe_inode_info *pipe, struct file *out,
splice_from_pipe_begin(&sd);
while (sd.total_len) {
struct iov_iter from;
+ unsigned int head, tail, mask;
size_t left;
- int n, idx;
+ int n;
ret = splice_from_pipe_next(pipe, &sd);
if (ret <= 0)
break;
- if (unlikely(nbufs < pipe->buffers)) {
+ if (unlikely(nbufs < pipe->max_usage)) {
kfree(array);
- nbufs = pipe->buffers;
+ nbufs = pipe->max_usage;
array = kcalloc(nbufs, sizeof(struct bio_vec),
GFP_KERNEL);
if (!array) {
@@ -717,18 +730,19 @@ iter_file_splice_write(struct pipe_inode_info *pipe, struct file *out,
}
}
+ head = pipe->head;
+ tail = pipe->tail;
+ mask = pipe->ring_size - 1;
+
/* build the vector */
left = sd.total_len;
- for (n = 0, idx = pipe->curbuf; left && n < pipe->nrbufs; n++, idx++) {
- struct pipe_buffer *buf = pipe->bufs + idx;
+ for (n = 0; !pipe_empty(head, tail) && left && n < nbufs; tail++, n++) {
+ struct pipe_buffer *buf = &pipe->bufs[tail & mask];
size_t this_len = buf->len;
if (this_len > left)
this_len = left;
- if (idx == pipe->buffers - 1)
- idx = -1;
-
ret = pipe_buf_confirm(pipe, buf);
if (unlikely(ret)) {
if (ret == -ENODATA)
@@ -752,14 +766,15 @@ iter_file_splice_write(struct pipe_inode_info *pipe, struct file *out,
*ppos = sd.pos;
/* dismiss the fully eaten buffers, adjust the partial one */
+ tail = pipe->tail;
while (ret) {
- struct pipe_buffer *buf = pipe->bufs + pipe->curbuf;
+ struct pipe_buffer *buf = &pipe->bufs[tail & mask];
if (ret >= buf->len) {
ret -= buf->len;
buf->len = 0;
pipe_buf_release(pipe, buf);
- pipe->curbuf = (pipe->curbuf + 1) & (pipe->buffers - 1);
- pipe->nrbufs--;
+ tail++;
+ pipe->tail = tail;
if (pipe->files)
sd.need_wakeup = true;
} else {
@@ -942,15 +957,17 @@ ssize_t splice_direct_to_actor(struct file *in, struct splice_desc *sd,
sd->flags &= ~SPLICE_F_NONBLOCK;
more = sd->flags & SPLICE_F_MORE;
- WARN_ON_ONCE(pipe->nrbufs != 0);
+ WARN_ON_ONCE(!pipe_empty(pipe->head, pipe->tail));
while (len) {
+ unsigned int p_space;
size_t read_len;
loff_t pos = sd->pos, prev_pos = pos;
/* Don't try to read more the pipe has space for. */
- read_len = min_t(size_t, len,
- (pipe->buffers - pipe->nrbufs) << PAGE_SHIFT);
+ p_space = pipe->max_usage -
+ pipe_occupancy(pipe->head, pipe->tail);
+ read_len = min_t(size_t, len, p_space << PAGE_SHIFT);
ret = do_splice_to(in, &pos, pipe, read_len, flags);
if (unlikely(ret <= 0))
goto out_release;
@@ -989,7 +1006,7 @@ ssize_t splice_direct_to_actor(struct file *in, struct splice_desc *sd,
}
done:
- pipe->nrbufs = pipe->curbuf = 0;
+ pipe->tail = pipe->head = 0;
file_accessed(in);
return bytes;
@@ -998,8 +1015,8 @@ out_release:
* If we did an incomplete transfer we must release
* the pipe buffers in question:
*/
- for (i = 0; i < pipe->buffers; i++) {
- struct pipe_buffer *buf = pipe->bufs + i;
+ for (i = 0; i < pipe->ring_size; i++) {
+ struct pipe_buffer *buf = &pipe->bufs[i];
if (buf->ops)
pipe_buf_release(pipe, buf);
@@ -1075,15 +1092,13 @@ static int wait_for_space(struct pipe_inode_info *pipe, unsigned flags)
send_sig(SIGPIPE, current, 0);
return -EPIPE;
}
- if (pipe->nrbufs != pipe->buffers)
+ if (!pipe_full(pipe->head, pipe->tail, pipe->max_usage))
return 0;
if (flags & SPLICE_F_NONBLOCK)
return -EAGAIN;
if (signal_pending(current))
return -ERESTARTSYS;
- pipe->waiting_writers++;
pipe_wait(pipe);
- pipe->waiting_writers--;
}
}
@@ -1180,8 +1195,15 @@ static long do_splice(struct file *in, loff_t __user *off_in,
pipe_lock(opipe);
ret = wait_for_space(opipe, flags);
- if (!ret)
+ if (!ret) {
+ unsigned int p_space;
+
+ /* Don't try to read more the pipe has space for. */
+ p_space = opipe->max_usage - pipe_occupancy(opipe->head, opipe->tail);
+ len = min_t(size_t, len, p_space << PAGE_SHIFT);
+
ret = do_splice_to(in, &offset, opipe, len, flags);
+ }
pipe_unlock(opipe);
if (ret > 0)
wakeup_pipe_readers(opipe);
@@ -1442,27 +1464,25 @@ static int ipipe_prep(struct pipe_inode_info *pipe, unsigned int flags)
int ret;
/*
- * Check ->nrbufs without the inode lock first. This function
+ * Check the pipe occupancy without the inode lock first. This function
* is speculative anyways, so missing one is ok.
*/
- if (pipe->nrbufs)
+ if (!pipe_empty(pipe->head, pipe->tail))
return 0;
ret = 0;
pipe_lock(pipe);
- while (!pipe->nrbufs) {
+ while (pipe_empty(pipe->head, pipe->tail)) {
if (signal_pending(current)) {
ret = -ERESTARTSYS;
break;
}
if (!pipe->writers)
break;
- if (!pipe->waiting_writers) {
- if (flags & SPLICE_F_NONBLOCK) {
- ret = -EAGAIN;
- break;
- }
+ if (flags & SPLICE_F_NONBLOCK) {
+ ret = -EAGAIN;
+ break;
}
pipe_wait(pipe);
}
@@ -1480,16 +1500,16 @@ static int opipe_prep(struct pipe_inode_info *pipe, unsigned int flags)
int ret;
/*
- * Check ->nrbufs without the inode lock first. This function
+ * Check pipe occupancy without the inode lock first. This function
* is speculative anyways, so missing one is ok.
*/
- if (pipe->nrbufs < pipe->buffers)
+ if (pipe_full(pipe->head, pipe->tail, pipe->max_usage))
return 0;
ret = 0;
pipe_lock(pipe);
- while (pipe->nrbufs >= pipe->buffers) {
+ while (pipe_full(pipe->head, pipe->tail, pipe->max_usage)) {
if (!pipe->readers) {
send_sig(SIGPIPE, current, 0);
ret = -EPIPE;
@@ -1503,9 +1523,7 @@ static int opipe_prep(struct pipe_inode_info *pipe, unsigned int flags)
ret = -ERESTARTSYS;
break;
}
- pipe->waiting_writers++;
pipe_wait(pipe);
- pipe->waiting_writers--;
}
pipe_unlock(pipe);
@@ -1520,7 +1538,10 @@ static int splice_pipe_to_pipe(struct pipe_inode_info *ipipe,
size_t len, unsigned int flags)
{
struct pipe_buffer *ibuf, *obuf;
- int ret = 0, nbuf;
+ unsigned int i_head, o_head;
+ unsigned int i_tail, o_tail;
+ unsigned int i_mask, o_mask;
+ int ret = 0;
bool input_wakeup = false;
@@ -1540,7 +1561,14 @@ retry:
*/
pipe_double_lock(ipipe, opipe);
+ i_tail = ipipe->tail;
+ i_mask = ipipe->ring_size - 1;
+ o_head = opipe->head;
+ o_mask = opipe->ring_size - 1;
+
do {
+ size_t o_len;
+
if (!opipe->readers) {
send_sig(SIGPIPE, current, 0);
if (!ret)
@@ -1548,14 +1576,18 @@ retry:
break;
}
- if (!ipipe->nrbufs && !ipipe->writers)
+ i_head = ipipe->head;
+ o_tail = opipe->tail;
+
+ if (pipe_empty(i_head, i_tail) && !ipipe->writers)
break;
/*
* Cannot make any progress, because either the input
* pipe is empty or the output pipe is full.
*/
- if (!ipipe->nrbufs || opipe->nrbufs >= opipe->buffers) {
+ if (pipe_empty(i_head, i_tail) ||
+ pipe_full(o_head, o_tail, opipe->max_usage)) {
/* Already processed some buffers, break */
if (ret)
break;
@@ -1575,9 +1607,8 @@ retry:
goto retry;
}
- ibuf = ipipe->bufs + ipipe->curbuf;
- nbuf = (opipe->curbuf + opipe->nrbufs) & (opipe->buffers - 1);
- obuf = opipe->bufs + nbuf;
+ ibuf = &ipipe->bufs[i_tail & i_mask];
+ obuf = &opipe->bufs[o_head & o_mask];
if (len >= ibuf->len) {
/*
@@ -1585,10 +1616,12 @@ retry:
*/
*obuf = *ibuf;
ibuf->ops = NULL;
- opipe->nrbufs++;
- ipipe->curbuf = (ipipe->curbuf + 1) & (ipipe->buffers - 1);
- ipipe->nrbufs--;
+ i_tail++;
+ ipipe->tail = i_tail;
input_wakeup = true;
+ o_len = obuf->len;
+ o_head++;
+ opipe->head = o_head;
} else {
/*
* Get a reference to this pipe buffer,
@@ -1610,12 +1643,14 @@ retry:
pipe_buf_mark_unmergeable(obuf);
obuf->len = len;
- opipe->nrbufs++;
- ibuf->offset += obuf->len;
- ibuf->len -= obuf->len;
+ ibuf->offset += len;
+ ibuf->len -= len;
+ o_len = len;
+ o_head++;
+ opipe->head = o_head;
}
- ret += obuf->len;
- len -= obuf->len;
+ ret += o_len;
+ len -= o_len;
} while (len);
pipe_unlock(ipipe);
@@ -1641,7 +1676,10 @@ static int link_pipe(struct pipe_inode_info *ipipe,
size_t len, unsigned int flags)
{
struct pipe_buffer *ibuf, *obuf;
- int ret = 0, i = 0, nbuf;
+ unsigned int i_head, o_head;
+ unsigned int i_tail, o_tail;
+ unsigned int i_mask, o_mask;
+ int ret = 0;
/*
* Potential ABBA deadlock, work around it by ordering lock
@@ -1650,6 +1688,11 @@ static int link_pipe(struct pipe_inode_info *ipipe,
*/
pipe_double_lock(ipipe, opipe);
+ i_tail = ipipe->tail;
+ i_mask = ipipe->ring_size - 1;
+ o_head = opipe->head;
+ o_mask = opipe->ring_size - 1;
+
do {
if (!opipe->readers) {
send_sig(SIGPIPE, current, 0);
@@ -1658,15 +1701,19 @@ static int link_pipe(struct pipe_inode_info *ipipe,
break;
}
+ i_head = ipipe->head;
+ o_tail = opipe->tail;
+
/*
- * If we have iterated all input buffers or ran out of
+ * If we have iterated all input buffers or run out of
* output room, break.
*/
- if (i >= ipipe->nrbufs || opipe->nrbufs >= opipe->buffers)
+ if (pipe_empty(i_head, i_tail) ||
+ pipe_full(o_head, o_tail, opipe->max_usage))
break;
- ibuf = ipipe->bufs + ((ipipe->curbuf + i) & (ipipe->buffers-1));
- nbuf = (opipe->curbuf + opipe->nrbufs) & (opipe->buffers - 1);
+ ibuf = &ipipe->bufs[i_tail & i_mask];
+ obuf = &opipe->bufs[o_head & o_mask];
/*
* Get a reference to this pipe buffer,
@@ -1678,7 +1725,6 @@ static int link_pipe(struct pipe_inode_info *ipipe,
break;
}
- obuf = opipe->bufs + nbuf;
*obuf = *ibuf;
/*
@@ -1691,19 +1737,13 @@ static int link_pipe(struct pipe_inode_info *ipipe,
if (obuf->len > len)
obuf->len = len;
-
- opipe->nrbufs++;
ret += obuf->len;
len -= obuf->len;
- i++;
- } while (len);
- /*
- * return EAGAIN if we have the potential of some data in the
- * future, otherwise just return 0
- */
- if (!ret && ipipe->waiting_writers && (flags & SPLICE_F_NONBLOCK))
- ret = -EAGAIN;
+ o_head++;
+ opipe->head = o_head;
+ i_tail++;
+ } while (len);
pipe_unlock(ipipe);
pipe_unlock(opipe);
diff --git a/fs/timerfd.c b/fs/timerfd.c
index 48305ba41e3c..ac7f59a58f94 100644
--- a/fs/timerfd.c
+++ b/fs/timerfd.c
@@ -302,11 +302,11 @@ static ssize_t timerfd_read(struct file *file, char __user *buf, size_t count,
static void timerfd_show(struct seq_file *m, struct file *file)
{
struct timerfd_ctx *ctx = file->private_data;
- struct itimerspec t;
+ struct timespec64 value, interval;
spin_lock_irq(&ctx->wqh.lock);
- t.it_value = ktime_to_timespec(timerfd_get_remaining(ctx));
- t.it_interval = ktime_to_timespec(ctx->tintv);
+ value = ktime_to_timespec64(timerfd_get_remaining(ctx));
+ interval = ktime_to_timespec64(ctx->tintv);
spin_unlock_irq(&ctx->wqh.lock);
seq_printf(m,
@@ -318,10 +318,10 @@ static void timerfd_show(struct seq_file *m, struct file *file)
ctx->clockid,
(unsigned long long)ctx->ticks,
ctx->settime_flags,
- (unsigned long long)t.it_value.tv_sec,
- (unsigned long long)t.it_value.tv_nsec,
- (unsigned long long)t.it_interval.tv_sec,
- (unsigned long long)t.it_interval.tv_nsec);
+ (unsigned long long)value.tv_sec,
+ (unsigned long long)value.tv_nsec,
+ (unsigned long long)interval.tv_sec,
+ (unsigned long long)interval.tv_nsec);
}
#else
#define timerfd_show NULL
diff --git a/fs/ubifs/debug.c b/fs/ubifs/debug.c
index e4b52783819d..0f5a480fe264 100644
--- a/fs/ubifs/debug.c
+++ b/fs/ubifs/debug.c
@@ -2737,18 +2737,6 @@ static ssize_t dfs_file_write(struct file *file, const char __user *u,
struct dentry *dent = file->f_path.dentry;
int val;
- /*
- * TODO: this is racy - the file-system might have already been
- * unmounted and we'd oops in this case. The plan is to fix it with
- * help of 'iterate_supers_type()' which we should have in v3.0: when
- * a debugfs opened, we rember FS's UUID in file->private_data. Then
- * whenever we access the FS via a debugfs file, we iterate all UBIFS
- * superblocks and fine the one with the same UUID, and take the
- * locking right.
- *
- * The other way to go suggested by Al Viro is to create a separate
- * 'ubifs-debug' file-system instead.
- */
if (file->f_path.dentry == d->dfs_dump_lprops) {
ubifs_dump_lprops(c);
return count;
diff --git a/fs/ubifs/journal.c b/fs/ubifs/journal.c
index 4fd9683b8245..388fe8f5dc51 100644
--- a/fs/ubifs/journal.c
+++ b/fs/ubifs/journal.c
@@ -503,7 +503,7 @@ static void mark_inode_clean(struct ubifs_info *c, struct ubifs_inode *ui)
static void set_dent_cookie(struct ubifs_info *c, struct ubifs_dent_node *dent)
{
if (c->double_hash)
- dent->cookie = prandom_u32();
+ dent->cookie = (__force __le32) prandom_u32();
else
dent->cookie = 0;
}
@@ -899,7 +899,7 @@ int ubifs_jnl_write_inode(struct ubifs_info *c, const struct inode *inode)
fname_name(&nm) = xent->name;
fname_len(&nm) = le16_to_cpu(xent->nlen);
- xino = ubifs_iget(c->vfs_sb, xent->inum);
+ xino = ubifs_iget(c->vfs_sb, le64_to_cpu(xent->inum));
if (IS_ERR(xino)) {
err = PTR_ERR(xino);
ubifs_err(c, "dead directory entry '%s', error %d",
diff --git a/fs/ubifs/orphan.c b/fs/ubifs/orphan.c
index 3b4b4114f208..54d6db61106f 100644
--- a/fs/ubifs/orphan.c
+++ b/fs/ubifs/orphan.c
@@ -631,12 +631,17 @@ static int do_kill_orphans(struct ubifs_info *c, struct ubifs_scan_leb *sleb,
ino_t inum;
int i, n, err, first = 1;
+ ino = kmalloc(UBIFS_MAX_INO_NODE_SZ, GFP_NOFS);
+ if (!ino)
+ return -ENOMEM;
+
list_for_each_entry(snod, &sleb->nodes, list) {
if (snod->type != UBIFS_ORPH_NODE) {
ubifs_err(c, "invalid node type %d in orphan area at %d:%d",
snod->type, sleb->lnum, snod->offs);
ubifs_dump_node(c, snod->node);
- return -EINVAL;
+ err = -EINVAL;
+ goto out_free;
}
orph = snod->node;
@@ -663,20 +668,18 @@ static int do_kill_orphans(struct ubifs_info *c, struct ubifs_scan_leb *sleb,
ubifs_err(c, "out of order commit number %llu in orphan node at %d:%d",
cmt_no, sleb->lnum, snod->offs);
ubifs_dump_node(c, snod->node);
- return -EINVAL;
+ err = -EINVAL;
+ goto out_free;
}
dbg_rcvry("out of date LEB %d", sleb->lnum);
*outofdate = 1;
- return 0;
+ err = 0;
+ goto out_free;
}
if (first)
first = 0;
- ino = kmalloc(UBIFS_MAX_INO_NODE_SZ, GFP_NOFS);
- if (!ino)
- return -ENOMEM;
-
n = (le32_to_cpu(orph->ch.len) - UBIFS_ORPH_NODE_SZ) >> 3;
for (i = 0; i < n; i++) {
union ubifs_key key1, key2;
diff --git a/fs/ubifs/sb.c b/fs/ubifs/sb.c
index a551eb3e9b89..2b7c04bf8983 100644
--- a/fs/ubifs/sb.c
+++ b/fs/ubifs/sb.c
@@ -184,7 +184,7 @@ static int create_default_filesystem(struct ubifs_info *c)
if (err)
goto out;
} else {
- sup->hash_algo = 0xffff;
+ sup->hash_algo = cpu_to_le16(0xffff);
}
sup->ch.node_type = UBIFS_SB_NODE;
diff --git a/fs/ubifs/super.c b/fs/ubifs/super.c
index 7d4547e5202d..5e1e8ec0589e 100644
--- a/fs/ubifs/super.c
+++ b/fs/ubifs/super.c
@@ -2267,10 +2267,8 @@ static struct dentry *ubifs_mount(struct file_system_type *fs_type, int flags,
}
} else {
err = ubifs_fill_super(sb, data, flags & SB_SILENT ? 1 : 0);
- if (err) {
- kfree(c);
+ if (err)
goto out_deact;
- }
/* We do not support atime */
sb->s_flags |= SB_ACTIVE;
if (IS_ENABLED(CONFIG_UBIFS_ATIME_SUPPORT))
diff --git a/fs/ubifs/tnc_commit.c b/fs/ubifs/tnc_commit.c
index a384a0f9ff32..234be1c4dc87 100644
--- a/fs/ubifs/tnc_commit.c
+++ b/fs/ubifs/tnc_commit.c
@@ -212,7 +212,7 @@ static int is_idx_node_in_use(struct ubifs_info *c, union ubifs_key *key,
/**
* layout_leb_in_gaps - layout index nodes using in-the-gaps method.
* @c: UBIFS file-system description object
- * @p: return LEB number here
+ * @p: return LEB number in @c->gap_lebs[p]
*
* This function lays out new index nodes for dirty znodes using in-the-gaps
* method of TNC commit.
@@ -221,7 +221,7 @@ static int is_idx_node_in_use(struct ubifs_info *c, union ubifs_key *key,
* This function returns the number of index nodes written into the gaps, or a
* negative error code on failure.
*/
-static int layout_leb_in_gaps(struct ubifs_info *c, int *p)
+static int layout_leb_in_gaps(struct ubifs_info *c, int p)
{
struct ubifs_scan_leb *sleb;
struct ubifs_scan_node *snod;
@@ -236,7 +236,7 @@ static int layout_leb_in_gaps(struct ubifs_info *c, int *p)
* filled, however we do not check there at present.
*/
return lnum; /* Error code */
- *p = lnum;
+ c->gap_lebs[p] = lnum;
dbg_gc("LEB %d", lnum);
/*
* Scan the index LEB. We use the generic scan for this even though
@@ -355,7 +355,7 @@ static int get_leb_cnt(struct ubifs_info *c, int cnt)
*/
static int layout_in_gaps(struct ubifs_info *c, int cnt)
{
- int err, leb_needed_cnt, written, *p;
+ int err, leb_needed_cnt, written, p = 0, old_idx_lebs, *gap_lebs;
dbg_gc("%d znodes to write", cnt);
@@ -364,9 +364,9 @@ static int layout_in_gaps(struct ubifs_info *c, int cnt)
if (!c->gap_lebs)
return -ENOMEM;
- p = c->gap_lebs;
+ old_idx_lebs = c->lst.idx_lebs;
do {
- ubifs_assert(c, p < c->gap_lebs + c->lst.idx_lebs);
+ ubifs_assert(c, p < c->lst.idx_lebs);
written = layout_leb_in_gaps(c, p);
if (written < 0) {
err = written;
@@ -392,9 +392,29 @@ static int layout_in_gaps(struct ubifs_info *c, int cnt)
leb_needed_cnt = get_leb_cnt(c, cnt);
dbg_gc("%d znodes remaining, need %d LEBs, have %d", cnt,
leb_needed_cnt, c->ileb_cnt);
+ /*
+ * Dynamically change the size of @c->gap_lebs to prevent
+ * oob, because @c->lst.idx_lebs could be increased by
+ * function @get_idx_gc_leb (called by layout_leb_in_gaps->
+ * ubifs_find_dirty_idx_leb) during loop. Only enlarge
+ * @c->gap_lebs when needed.
+ *
+ */
+ if (leb_needed_cnt > c->ileb_cnt && p >= old_idx_lebs &&
+ old_idx_lebs < c->lst.idx_lebs) {
+ old_idx_lebs = c->lst.idx_lebs;
+ gap_lebs = krealloc(c->gap_lebs, sizeof(int) *
+ (old_idx_lebs + 1), GFP_NOFS);
+ if (!gap_lebs) {
+ kfree(c->gap_lebs);
+ c->gap_lebs = NULL;
+ return -ENOMEM;
+ }
+ c->gap_lebs = gap_lebs;
+ }
} while (leb_needed_cnt > c->ileb_cnt);
- *p = -1;
+ c->gap_lebs[p] = -1;
return 0;
}
diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c
index f9fd18670e22..37df7c9eedb1 100644
--- a/fs/userfaultfd.c
+++ b/fs/userfaultfd.c
@@ -1460,7 +1460,8 @@ static int userfaultfd_register(struct userfaultfd_ctx *ctx,
start = vma->vm_start;
vma_end = min(end, vma->vm_end);
- new_flags = (vma->vm_flags & ~vm_flags) | vm_flags;
+ new_flags = (vma->vm_flags &
+ ~(VM_UFFD_MISSING|VM_UFFD_WP)) | vm_flags;
prev = vma_merge(mm, prev, start, vma_end, new_flags,
vma->anon_vma, vma->vm_file, vma->vm_pgoff,
vma_policy(vma),
@@ -1834,13 +1835,12 @@ static int userfaultfd_api(struct userfaultfd_ctx *ctx,
if (copy_from_user(&uffdio_api, buf, sizeof(uffdio_api)))
goto out;
features = uffdio_api.features;
- if (uffdio_api.api != UFFD_API || (features & ~UFFD_API_FEATURES)) {
- memset(&uffdio_api, 0, sizeof(uffdio_api));
- if (copy_to_user(buf, &uffdio_api, sizeof(uffdio_api)))
- goto out;
- ret = -EINVAL;
- goto out;
- }
+ ret = -EINVAL;
+ if (uffdio_api.api != UFFD_API || (features & ~UFFD_API_FEATURES))
+ goto err_out;
+ ret = -EPERM;
+ if ((features & UFFD_FEATURE_EVENT_FORK) && !capable(CAP_SYS_PTRACE))
+ goto err_out;
/* report all available features and ioctls to userland */
uffdio_api.features = UFFD_API_FEATURES;
uffdio_api.ioctls = UFFD_API_IOCTLS;
@@ -1853,6 +1853,11 @@ static int userfaultfd_api(struct userfaultfd_ctx *ctx,
ret = 0;
out:
return ret;
+err_out:
+ memset(&uffdio_api, 0, sizeof(uffdio_api));
+ if (copy_to_user(buf, &uffdio_api, sizeof(uffdio_api)))
+ ret = -EFAULT;
+ goto out;
}
static long userfaultfd_ioctl(struct file *file, unsigned cmd,
@@ -1923,7 +1928,7 @@ static const struct file_operations userfaultfd_fops = {
.poll = userfaultfd_poll,
.read = userfaultfd_read,
.unlocked_ioctl = userfaultfd_ioctl,
- .compat_ioctl = userfaultfd_ioctl,
+ .compat_ioctl = compat_ptr_ioctl,
.llseek = noop_llseek,
};
diff --git a/fs/utimes.c b/fs/utimes.c
index 1ba3f7883870..c952b6b3d8a0 100644
--- a/fs/utimes.c
+++ b/fs/utimes.c
@@ -161,9 +161,9 @@ SYSCALL_DEFINE4(utimensat, int, dfd, const char __user *, filename,
* utimensat() instead.
*/
static long do_futimesat(int dfd, const char __user *filename,
- struct timeval __user *utimes)
+ struct __kernel_old_timeval __user *utimes)
{
- struct timeval times[2];
+ struct __kernel_old_timeval times[2];
struct timespec64 tstimes[2];
if (utimes) {
@@ -190,13 +190,13 @@ static long do_futimesat(int dfd, const char __user *filename,
SYSCALL_DEFINE3(futimesat, int, dfd, const char __user *, filename,
- struct timeval __user *, utimes)
+ struct __kernel_old_timeval __user *, utimes)
{
return do_futimesat(dfd, filename, utimes);
}
SYSCALL_DEFINE2(utimes, char __user *, filename,
- struct timeval __user *, utimes)
+ struct __kernel_old_timeval __user *, utimes)
{
return do_futimesat(AT_FDCWD, filename, utimes);
}
diff --git a/fs/xfs/libxfs/xfs_fs.h b/fs/xfs/libxfs/xfs_fs.h
index 37f680b9a570..ef95ca07d084 100644
--- a/fs/xfs/libxfs/xfs_fs.h
+++ b/fs/xfs/libxfs/xfs_fs.h
@@ -366,11 +366,11 @@ struct xfs_bulkstat {
uint64_t bs_blocks; /* number of blocks */
uint64_t bs_xflags; /* extended flags */
- uint64_t bs_atime; /* access time, seconds */
- uint64_t bs_mtime; /* modify time, seconds */
+ int64_t bs_atime; /* access time, seconds */
+ int64_t bs_mtime; /* modify time, seconds */
- uint64_t bs_ctime; /* inode change time, seconds */
- uint64_t bs_btime; /* creation time, seconds */
+ int64_t bs_ctime; /* inode change time, seconds */
+ int64_t bs_btime; /* creation time, seconds */
uint32_t bs_gen; /* generation count */
uint32_t bs_uid; /* user id */