parallel lookups: actual switch to rwsem
ta-da!
The main issue is the lack of down_write_killable(), so the places
like readdir.c switched to plain inode_lock(); once killable
variants of rwsem primitives appear, that'll be dealt with.
lockdep side also might need more work
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index 5a23806..0b8ba71 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -837,9 +837,11 @@
struct dentry *dentry;
int error;
- error = mutex_lock_killable_nested(&dir->i_mutex, I_MUTEX_PARENT);
- if (error == -EINTR)
- return error;
+ inode_lock_nested(dir, I_MUTEX_PARENT);
+ // XXX: should've been
+ // mutex_lock_killable_nested(&dir->i_mutex, I_MUTEX_PARENT);
+ // if (error == -EINTR)
+ // return error;
dentry = lookup_one_len(name, parent->dentry, namelen);
error = PTR_ERR(dentry);
@@ -2366,9 +2368,11 @@
goto out;
- err = mutex_lock_killable_nested(&dir->i_mutex, I_MUTEX_PARENT);
- if (err == -EINTR)
- goto out_drop_write;
+ inode_lock_nested(dir, I_MUTEX_PARENT);
+ // XXX: should've been
+ // err = mutex_lock_killable_nested(&dir->i_mutex, I_MUTEX_PARENT);
+ // if (err == -EINTR)
+ // goto out_drop_write;
dentry = lookup_one_len(vol_args->name, parent, namelen);
if (IS_ERR(dentry)) {
err = PTR_ERR(dentry);
@@ -2558,7 +2562,7 @@
dput(dentry);
out_unlock_dir:
inode_unlock(dir);
-out_drop_write:
+//out_drop_write:
mnt_drop_write_file(file);
out:
kfree(vol_args);
diff --git a/fs/configfs/inode.c b/fs/configfs/inode.c
index 03d124a..0387968 100644
--- a/fs/configfs/inode.c
+++ b/fs/configfs/inode.c
@@ -156,7 +156,7 @@
if (depth > 0) {
if (depth <= ARRAY_SIZE(default_group_class)) {
- lockdep_set_class(&inode->i_mutex,
+ lockdep_set_class(&inode->i_rwsem,
&default_group_class[depth - 1]);
} else {
/*
diff --git a/fs/dcache.c b/fs/dcache.c
index 59fcffc..e49ba7d 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -2932,7 +2932,8 @@
static int __d_unalias(struct inode *inode,
struct dentry *dentry, struct dentry *alias)
{
- struct mutex *m1 = NULL, *m2 = NULL;
+ struct mutex *m1 = NULL;
+ struct rw_semaphore *m2 = NULL;
int ret = -ESTALE;
/* If alias and dentry share a parent, then no extra locks required */
@@ -2943,15 +2944,15 @@
if (!mutex_trylock(&dentry->d_sb->s_vfs_rename_mutex))
goto out_err;
m1 = &dentry->d_sb->s_vfs_rename_mutex;
- if (!inode_trylock(alias->d_parent->d_inode))
+ if (!inode_trylock_shared(alias->d_parent->d_inode))
goto out_err;
- m2 = &alias->d_parent->d_inode->i_mutex;
+ m2 = &alias->d_parent->d_inode->i_rwsem;
out_unalias:
__d_move(alias, dentry, false);
ret = 0;
out_err:
if (m2)
- mutex_unlock(m2);
+ up_read(m2);
if (m1)
mutex_unlock(m1);
return ret;
diff --git a/fs/gfs2/ops_fstype.c b/fs/gfs2/ops_fstype.c
index c09c63d..4546360 100644
--- a/fs/gfs2/ops_fstype.c
+++ b/fs/gfs2/ops_fstype.c
@@ -824,7 +824,7 @@
* i_mutex on quota files is special. Since this inode is hidden system
* file, we are safe to define locking ourselves.
*/
- lockdep_set_class(&sdp->sd_quota_inode->i_mutex,
+ lockdep_set_class(&sdp->sd_quota_inode->i_rwsem,
&gfs2_quota_imutex_key);
error = gfs2_rindex_update(sdp);
diff --git a/fs/inode.c b/fs/inode.c
index 4b884f7..4ccbc21 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -166,8 +166,8 @@
spin_lock_init(&inode->i_lock);
lockdep_set_class(&inode->i_lock, &sb->s_type->i_lock_key);
- mutex_init(&inode->i_mutex);
- lockdep_set_class(&inode->i_mutex, &sb->s_type->i_mutex_key);
+ init_rwsem(&inode->i_rwsem);
+ lockdep_set_class(&inode->i_rwsem, &sb->s_type->i_mutex_key);
atomic_set(&inode->i_dio_count, 0);
@@ -925,13 +925,13 @@
struct file_system_type *type = inode->i_sb->s_type;
/* Set new key only if filesystem hasn't already changed it */
- if (lockdep_match_class(&inode->i_mutex, &type->i_mutex_key)) {
+ if (lockdep_match_class(&inode->i_rwsem, &type->i_mutex_key)) {
/*
* ensure nobody is actually holding i_mutex
*/
- mutex_destroy(&inode->i_mutex);
- mutex_init(&inode->i_mutex);
- lockdep_set_class(&inode->i_mutex,
+ // mutex_destroy(&inode->i_mutex);
+ init_rwsem(&inode->i_rwsem);
+ lockdep_set_class(&inode->i_rwsem,
&type->i_mutex_dir_key);
}
}
diff --git a/fs/namei.c b/fs/namei.c
index 7babb5e..8249852 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -1607,7 +1607,7 @@
struct inode *inode = dir->d_inode;
DECLARE_WAIT_QUEUE_HEAD_ONSTACK(wq);
- inode_lock(inode);
+ inode_lock_shared(inode);
/* Don't go there if it's already dead */
if (unlikely(IS_DEADDIR(inode)))
goto out;
@@ -1638,7 +1638,7 @@
}
}
out:
- inode_unlock(inode);
+ inode_unlock_shared(inode);
return dentry;
}
diff --git a/fs/ocfs2/inode.c b/fs/ocfs2/inode.c
index 12f4a9e..0748777 100644
--- a/fs/ocfs2/inode.c
+++ b/fs/ocfs2/inode.c
@@ -262,7 +262,7 @@
inode->i_ino = args->fi_ino;
OCFS2_I(inode)->ip_blkno = args->fi_blkno;
if (args->fi_sysfile_type != 0)
- lockdep_set_class(&inode->i_mutex,
+ lockdep_set_class(&inode->i_rwsem,
&ocfs2_sysfile_lock_key[args->fi_sysfile_type]);
if (args->fi_sysfile_type == USER_QUOTA_SYSTEM_INODE ||
args->fi_sysfile_type == GROUP_QUOTA_SYSTEM_INODE ||
diff --git a/fs/overlayfs/readdir.c b/fs/overlayfs/readdir.c
index 6ec1e43..da186ee 100644
--- a/fs/overlayfs/readdir.c
+++ b/fs/overlayfs/readdir.c
@@ -218,7 +218,9 @@
cap_raise(override_cred->cap_effective, CAP_DAC_OVERRIDE);
old_cred = override_creds(override_cred);
- err = mutex_lock_killable(&dir->d_inode->i_mutex);
+ inode_lock(dir->d_inode);
+ err = 0;
+ // XXX: err = mutex_lock_killable(&dir->d_inode->i_mutex);
if (!err) {
while (rdd->first_maybe_whiteout) {
p = rdd->first_maybe_whiteout;
diff --git a/fs/readdir.c b/fs/readdir.c
index e69ef3b..bf583e8 100644
--- a/fs/readdir.c
+++ b/fs/readdir.c
@@ -32,9 +32,10 @@
if (res)
goto out;
- res = mutex_lock_killable(&inode->i_mutex);
- if (res)
- goto out;
+ inode_lock(inode);
+ // res = mutex_lock_killable(&inode->i_mutex);
+ // if (res)
+ // goto out;
res = -ENOENT;
if (!IS_DEADDIR(inode)) {