kernfs_node->u.completion is used to notify deactivation completion from kernfs_put_active() to kernfs_deactivate(). We now allow multiple racing removals of the same node and the current removal scheme is no longer correct - kernfs_remove() invocation may return before the node is properly deactivated if it races against another removal. The removal path will be restructured to address the issue.
To help such restructure which requires supporting multiple waiters, this patch replaces kernfs_node->u.completion with kernfs_root->deactivate_waitq. This makes deactivation event notifications share a per-root waitqueue_head; however, the wait path is quite cold and this will also allow shaving one pointer off kernfs_node. Signed-off-by: Tejun Heo <t...@kernel.org> --- fs/kernfs/dir.c | 27 +++++++++++---------------- include/linux/kernfs.h | 4 ++-- 2 files changed, 13 insertions(+), 18 deletions(-) diff --git a/fs/kernfs/dir.c b/fs/kernfs/dir.c index 510b506..ed62de6 100644 --- a/fs/kernfs/dir.c +++ b/fs/kernfs/dir.c @@ -8,6 +8,7 @@ * This file is released under the GPLv2. */ +#include <linux/sched.h> #include <linux/fs.h> #include <linux/namei.h> #include <linux/idr.h> @@ -151,6 +152,7 @@ struct kernfs_node *kernfs_get_active(struct kernfs_node *kn) */ void kernfs_put_active(struct kernfs_node *kn) { + struct kernfs_root *root = kernfs_root(kn); int v; if (unlikely(!kn)) @@ -162,11 +164,7 @@ void kernfs_put_active(struct kernfs_node *kn) if (likely(v != KN_DEACTIVATED_BIAS)) return; - /* - * atomic_dec_return() is a mb(), we'll always see the updated - * kn->u.completion. - */ - complete(kn->u.completion); + wake_up_all(&root->deactivate_waitq); } /** @@ -177,26 +175,22 @@ void kernfs_put_active(struct kernfs_node *kn) */ static void kernfs_deactivate(struct kernfs_node *kn) { - DECLARE_COMPLETION_ONSTACK(wait); - int v; + struct kernfs_root *root = kernfs_root(kn); BUG_ON(!(kn->flags & KERNFS_REMOVED)); if (!(kernfs_type(kn) & KERNFS_ACTIVE_REF)) return; - kn->u.completion = (void *)&wait; - rwsem_acquire(&kn->dep_map, 0, 0, _RET_IP_); - /* atomic_add_return() is a mb(), put_active() will always see - * the updated kn->u.completion. - */ - v = atomic_add_return(KN_DEACTIVATED_BIAS, &kn->active); - if (v != KN_DEACTIVATED_BIAS) { + atomic_add(KN_DEACTIVATED_BIAS, &kn->active); + + if (atomic_read(&kn->active) != KN_DEACTIVATED_BIAS) lock_contended(&kn->dep_map, _RET_IP_); - wait_for_completion(&wait); - } + + wait_event(root->deactivate_waitq, + atomic_read(&kn->active) == KN_DEACTIVATED_BIAS); lock_acquired(&kn->dep_map, _RET_IP_); rwsem_release(&kn->dep_map, 1, _RET_IP_); @@ -613,6 +607,7 @@ struct kernfs_root *kernfs_create_root(struct kernfs_dir_ops *kdops, void *priv) root->dir_ops = kdops; root->kn = kn; + init_waitqueue_head(&root->deactivate_waitq); return root; } diff --git a/include/linux/kernfs.h b/include/linux/kernfs.h index d2c439d..232f1a6 100644 --- a/include/linux/kernfs.h +++ b/include/linux/kernfs.h @@ -15,7 +15,7 @@ #include <linux/lockdep.h> #include <linux/rbtree.h> #include <linux/atomic.h> -#include <linux/completion.h> +#include <linux/wait.h> struct file; struct iattr; @@ -91,7 +91,6 @@ struct kernfs_node { struct rb_node rb; union { - struct completion *completion; struct kernfs_node *removed_list; } u; @@ -132,6 +131,7 @@ struct kernfs_root { /* private fields, do not use outside kernfs proper */ struct ida ino_ida; struct kernfs_dir_ops *dir_ops; + wait_queue_head_t deactivate_waitq; }; struct kernfs_open_file { -- 1.8.4.2 -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majord...@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/