summaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
authorAl Viro <viro@zeniv.linux.org.uk>2016-04-15 15:08:36 -0400
committerAl Viro <viro@zeniv.linux.org.uk>2016-05-02 19:49:28 -0400
commit9902af79c01a8e39bb99b922fa3eef6d4ea23d69 (patch)
treeb04cc75b5e4a028bfdb619e0a0a0f8cd71113ff2
parentd9171b9345261e0d941d92fdda5672b5db67f968 (diff)
downloadlinux-stable-9902af79c01a8e39bb99b922fa3eef6d4ea23d69.tar.gz
linux-stable-9902af79c01a8e39bb99b922fa3eef6d4ea23d69.tar.bz2
linux-stable-9902af79c01a8e39bb99b922fa3eef6d4ea23d69.zip
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>
-rw-r--r--Documentation/filesystems/porting18
-rw-r--r--fs/btrfs/ioctl.c18
-rw-r--r--fs/configfs/inode.c2
-rw-r--r--fs/dcache.c9
-rw-r--r--fs/gfs2/ops_fstype.c2
-rw-r--r--fs/inode.c12
-rw-r--r--fs/namei.c4
-rw-r--r--fs/ocfs2/inode.c2
-rw-r--r--fs/overlayfs/readdir.c4
-rw-r--r--fs/readdir.c7
-rw-r--r--include/linux/fs.h27
11 files changed, 73 insertions, 32 deletions
diff --git a/Documentation/filesystems/porting b/Documentation/filesystems/porting
index 8810e2367fe6..1567a53857bd 100644
--- a/Documentation/filesystems/porting
+++ b/Documentation/filesystems/porting
@@ -539,3 +539,21 @@ in your dentry operations instead.
it's a symlink. Checking ->i_mode is really needed now. In-tree we had
to fix shmem_destroy_callback() that used to take that kind of shortcut;
watch out, since that shortcut is no longer valid.
+--
+[mandatory]
+ ->i_mutex is replaced with ->i_rwsem now. inode_lock() et.al. work as
+ they used to - they just take it exclusive. However, ->lookup() may be
+ called with parent locked shared. Its instances must not
+ * use d_instantiate) and d_rehash() separately - use d_add() or
+ d_splice_alias() instead.
+ * use d_rehash() alone - call d_add(new_dentry, NULL) instead.
+ * in the unlikely case when (read-only) access to filesystem
+ data structures needs exclusion for some reason, arrange it
+ yourself. None of the in-tree filesystems needed that.
+ * rely on ->d_parent and ->d_name not changing after dentry has
+ been fed to d_add() or d_splice_alias(). Again, none of the
+ in-tree instances relied upon that.
+ We are guaranteed that lookups of the same name in the same directory
+ will not happen in parallel ("same" in the sense of your ->d_compare()).
+ Lookups on different names in the same directory can and do happen in
+ parallel now.
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index 5a23806ae418..0b8ba717175b 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -837,9 +837,11 @@ static noinline int btrfs_mksubvol(struct path *parent,
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 @@ static noinline int btrfs_ioctl_snap_destroy(struct file *file,
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 @@ out_dput:
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 03d124ae27d7..0387968e6f47 100644
--- a/fs/configfs/inode.c
+++ b/fs/configfs/inode.c
@@ -156,7 +156,7 @@ static void configfs_set_inode_lock_class(struct configfs_dirent *sd,
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 59fcffcbf096..e49ba7d1b957 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -2932,7 +2932,8 @@ struct dentry *d_ancestor(struct dentry *p1, struct dentry *p2)
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 @@ static int __d_unalias(struct inode *inode,
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 c09c63dcd7a2..45463600fb81 100644
--- a/fs/gfs2/ops_fstype.c
+++ b/fs/gfs2/ops_fstype.c
@@ -824,7 +824,7 @@ static int init_inodes(struct gfs2_sbd *sdp, int undo)
* 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 4b884f73214e..4ccbc21b30ce 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -166,8 +166,8 @@ int inode_init_always(struct super_block *sb, struct inode *inode)
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 @@ void lockdep_annotate_inode_mutex_key(struct inode *inode)
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 7babb5e5f276..8249852b5fc6 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -1607,7 +1607,7 @@ static struct dentry *lookup_slow(const struct qstr *name,
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 @@ again:
}
}
out:
- inode_unlock(inode);
+ inode_unlock_shared(inode);
return dentry;
}
diff --git a/fs/ocfs2/inode.c b/fs/ocfs2/inode.c
index 12f4a9e9800f..0748777f2e2a 100644
--- a/fs/ocfs2/inode.c
+++ b/fs/ocfs2/inode.c
@@ -262,7 +262,7 @@ static int ocfs2_init_locked_inode(struct inode *inode, void *opaque)
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 6ec1e43a9a54..da186ee4f846 100644
--- a/fs/overlayfs/readdir.c
+++ b/fs/overlayfs/readdir.c
@@ -218,7 +218,9 @@ static int ovl_check_whiteouts(struct dentry *dir, struct ovl_readdir_data *rdd)
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 e69ef3b79787..bf583e848a1a 100644
--- a/fs/readdir.c
+++ b/fs/readdir.c
@@ -32,9 +32,10 @@ int iterate_dir(struct file *file, struct dir_context *ctx)
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)) {
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 00cecc5a2f75..3018f31f7aa0 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -647,7 +647,7 @@ struct inode {
/* Misc */
unsigned long i_state;
- struct mutex i_mutex;
+ struct rw_semaphore i_rwsem;
unsigned long dirtied_when; /* jiffies of first dirtying */
unsigned long dirtied_time_when;
@@ -734,27 +734,42 @@ enum inode_i_mutex_lock_class
static inline void inode_lock(struct inode *inode)
{
- mutex_lock(&inode->i_mutex);
+ down_write(&inode->i_rwsem);
}
static inline void inode_unlock(struct inode *inode)
{
- mutex_unlock(&inode->i_mutex);
+ up_write(&inode->i_rwsem);
+}
+
+static inline void inode_lock_shared(struct inode *inode)
+{
+ down_read(&inode->i_rwsem);
+}
+
+static inline void inode_unlock_shared(struct inode *inode)
+{
+ up_read(&inode->i_rwsem);
}
static inline int inode_trylock(struct inode *inode)
{
- return mutex_trylock(&inode->i_mutex);
+ return down_write_trylock(&inode->i_rwsem);
+}
+
+static inline int inode_trylock_shared(struct inode *inode)
+{
+ return down_read_trylock(&inode->i_rwsem);
}
static inline int inode_is_locked(struct inode *inode)
{
- return mutex_is_locked(&inode->i_mutex);
+ return rwsem_is_locked(&inode->i_rwsem);
}
static inline void inode_lock_nested(struct inode *inode, unsigned subclass)
{
- mutex_lock_nested(&inode->i_mutex, subclass);
+ down_write_nested(&inode->i_rwsem, subclass);
}
void lock_two_nondirectories(struct inode *, struct inode*);