mmu_notifier: add call_srcu and sync function for listener to delay call and sync
When kernel device drivers or subsystems want to bind their lifespan to
t= he lifespan of the mm_struct, they usually use one of the following
methods:
1. Manually calling a function in the interested kernel module. The
funct= ion call needs to be placed in mmput. This method was rejected
by several ker= nel maintainers.
2. Registering to the mmu notifier release mechanism.
The problem with the latter approach is that the mmu_notifier_release
cal= lback is called from__mmu_notifier_release (called from exit_mmap).
That functi= on iterates over the list of mmu notifiers and don't expect
the release call= back function to remove itself from the list.
Therefore, the callback function= in the kernel module can't release the
mmu_notifier_object, which is actuall= y the kernel module's object
itself. As a result, the destruction of the kernel module's object must
to be done in a delayed fashion.
This patch adds support for this delayed callback, by adding a new
mmu_notifier_call_srcu function that receives a function ptr and calls
th= at function with call_srcu. In that function, the kernel module
releases its object. To use mmu_notifier_call_srcu, the calling module
needs to call b= efore that a new function called
mmu_notifier_unregister_no_release that as its= name implies,
unregisters a notifier without calling its notifier release call= back.
This patch also adds a function that will call barrier_srcu so those
kern= el modules can sync with mmu_notifier.
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Jérôme Glisse <jglisse@redhat.com>
Signed-off-by: Oded Gabbay <oded.gabbay@amd.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
diff --git a/mm/mmu_notifier.c b/mm/mmu_notifier.c
index 41cefdf..950813b 100644
--- a/mm/mmu_notifier.c
+++ b/mm/mmu_notifier.c
@@ -23,6 +23,25 @@
static struct srcu_struct srcu;
/*
+ * This function allows mmu_notifier::release callback to delay a call to
+ * a function that will free appropriate resources. The function must be
+ * quick and must not block.
+ */
+void mmu_notifier_call_srcu(struct rcu_head *rcu,
+ void (*func)(struct rcu_head *rcu))
+{
+ call_srcu(&srcu, rcu, func);
+}
+EXPORT_SYMBOL_GPL(mmu_notifier_call_srcu);
+
+void mmu_notifier_synchronize(void)
+{
+ /* Wait for any running method to finish. */
+ srcu_barrier(&srcu);
+}
+EXPORT_SYMBOL_GPL(mmu_notifier_synchronize);
+
+/*
* This function can't run concurrently against mmu_notifier_register
* because mm->mm_users > 0 during mmu_notifier_register and exit_mmap
* runs with mm_users == 0. Other tasks may still invoke mmu notifiers
@@ -53,7 +72,6 @@
*/
if (mn->ops->release)
mn->ops->release(mn, mm);
- srcu_read_unlock(&srcu, id);
spin_lock(&mm->mmu_notifier_mm->lock);
while (unlikely(!hlist_empty(&mm->mmu_notifier_mm->list))) {
@@ -69,6 +87,7 @@
hlist_del_init_rcu(&mn->hlist);
}
spin_unlock(&mm->mmu_notifier_mm->lock);
+ srcu_read_unlock(&srcu, id);
/*
* synchronize_srcu here prevents mmu_notifier_release from returning to
@@ -325,6 +344,25 @@
}
EXPORT_SYMBOL_GPL(mmu_notifier_unregister);
+/*
+ * Same as mmu_notifier_unregister but no callback and no srcu synchronization.
+ */
+void mmu_notifier_unregister_no_release(struct mmu_notifier *mn,
+ struct mm_struct *mm)
+{
+ spin_lock(&mm->mmu_notifier_mm->lock);
+ /*
+ * Can not use list_del_rcu() since __mmu_notifier_release
+ * can delete it before we hold the lock.
+ */
+ hlist_del_init_rcu(&mn->hlist);
+ spin_unlock(&mm->mmu_notifier_mm->lock);
+
+ BUG_ON(atomic_read(&mm->mm_count) <= 0);
+ mmdrop(mm);
+}
+EXPORT_SYMBOL_GPL(mmu_notifier_unregister_no_release);
+
static int __init mmu_notifier_init(void)
{
return init_srcu_struct(&srcu);