The inode operations .permission() and .getattr() use the kernfs node
write lock but all that's needed is to keep the rb tree stable while
updating the inode attributes as well as protecting the update itself
against concurrent changes.
And .permission() is called frequently during path walks and can cause
quite a bit of contention between kernfs node operations and path
walks when the number of concurrent walks is high.
To change kernfs_iop_getattr() and kernfs_iop_permission() to take
the rw sem read lock instead of the write lock an additional lock is
needed to protect against multiple processes concurrently updating
the inode attributes and link count in kernfs_refresh_inode().
The inode i_lock seems like the sensible thing to use to protect these
inode attribute updates so use it in kernfs_refresh_inode().
The last hunk in the patch, applied to kernfs_fill_super(), is possibly
not needed but taking the lock was present originally and I prefer to
continue to take it so the rb tree is held stable during the call to
kernfs_refresh_inode() made by kernfs_get_inode().
Signed-off-by: Ian Kent <raven@xxxxxxxxxx>
---
fs/kernfs/inode.c | 10 ++++++----
fs/kernfs/mount.c | 4 ++--
2 files changed, 8 insertions(+), 6 deletions(-)
diff --git a/fs/kernfs/inode.c b/fs/kernfs/inode.c
index 3b01e9e61f14e..6728ecd81eb37 100644
--- a/fs/kernfs/inode.c
+++ b/fs/kernfs/inode.c
@@ -172,6 +172,7 @@ static void kernfs_refresh_inode(struct kernfs_node *kn, struct inode *inode)
{
struct kernfs_iattrs *attrs = kn->iattr;
+ spin_lock(&inode->i_lock);
inode->i_mode = kn->mode;
if (attrs)
/*
@@ -182,6 +183,7 @@ static void kernfs_refresh_inode(struct kernfs_node *kn, struct inode *inode)
if (kernfs_type(kn) == KERNFS_DIR)
set_nlink(inode, kn->dir.subdirs + 2);
+ spin_unlock(&inode->i_lock);
}
int kernfs_iop_getattr(struct user_namespace *mnt_userns,
@@ -191,9 +193,9 @@ int kernfs_iop_getattr(struct user_namespace *mnt_userns,
struct inode *inode = d_inode(path->dentry);
struct kernfs_node *kn = inode->i_private;
- down_write(&kernfs_rwsem);
+ down_read(&kernfs_rwsem);
kernfs_refresh_inode(kn, inode);
- up_write(&kernfs_rwsem);
+ up_read(&kernfs_rwsem);
generic_fillattr(&init_user_ns, inode, stat);
return 0;
@@ -284,9 +286,9 @@ int kernfs_iop_permission(struct user_namespace *mnt_userns,
kn = inode->i_private;
- down_write(&kernfs_rwsem);
+ down_read(&kernfs_rwsem);
kernfs_refresh_inode(kn, inode);
- up_write(&kernfs_rwsem);
+ up_read(&kernfs_rwsem);
return generic_permission(&init_user_ns, inode, mask);
}
diff --git a/fs/kernfs/mount.c b/fs/kernfs/mount.c
index baa4155ba2edf..f2f909d09f522 100644
--- a/fs/kernfs/mount.c
+++ b/fs/kernfs/mount.c
@@ -255,9 +255,9 @@ static int kernfs_fill_super(struct super_block *sb, struct kernfs_fs_context *k
sb->s_shrink.seeks = 0;
/* get root inode, initialize and unlock it */
- down_write(&kernfs_rwsem);
+ down_read(&kernfs_rwsem);
inode = kernfs_get_inode(sb, info->root->kn);
- up_write(&kernfs_rwsem);
+ up_read(&kernfs_rwsem);
if (!inode) {
pr_debug("kernfs: could not get root inode\n");
return -ENOMEM;
