1 files changed, 111 insertions, 77 deletions

diff --git a/mm/mmu_notifier.c b/mm/mmu_notifier.c
index 438951d366f..41cefdf0aad 100644
--- a/mm/mmu_notifier.c
+++ b/mm/mmu_notifier.c
@@ -11,13 +11,17 @@
 
 #include <linux/rculist.h>
 #include <linux/mmu_notifier.h>
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/mm.h>
 #include <linux/err.h>
+#include <linux/srcu.h>
 #include <linux/rcupdate.h>
 #include <linux/sched.h>
 #include <linux/slab.h>
 
+/* global SRCU for all MMs */
+static struct srcu_struct srcu;
+
 /*
  * This function can't run concurrently against mmu_notifier_register
  * because mm->mm_users > 0 during mmu_notifier_register and exit_mmap
@@ -25,14 +29,31 @@
  * in parallel despite there being no task using this mm any more,
  * through the vmas outside of the exit_mmap context, such as with
  * vmtruncate. This serializes against mmu_notifier_unregister with
- * the mmu_notifier_mm->lock in addition to RCU and it serializes
- * against the other mmu notifiers with RCU. struct mmu_notifier_mm
+ * the mmu_notifier_mm->lock in addition to SRCU and it serializes
+ * against the other mmu notifiers with SRCU. struct mmu_notifier_mm
  * can't go away from under us as exit_mmap holds an mm_count pin
  * itself.
  */
 void __mmu_notifier_release(struct mm_struct *mm)
 {
 	struct mmu_notifier *mn;
+	int id;
+
+	/*
+	 * SRCU here will block mmu_notifier_unregister until
+	 * ->release returns.
+	 */
+	id = srcu_read_lock(&srcu);
+	hlist_for_each_entry_rcu(mn, &mm->mmu_notifier_mm->list, hlist)
+		/*
+		 * If ->release runs before mmu_notifier_unregister it must be
+		 * handled, as it's the only way for the driver to flush all
+		 * existing sptes and stop the driver from establishing any more
+		 * sptes before all the pages in the mm are freed.
+		 */
+		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))) {
@@ -41,41 +62,24 @@ void __mmu_notifier_release(struct mm_struct *mm)
 				 hlist);
 		/*
 		 * We arrived before mmu_notifier_unregister so
-		 * mmu_notifier_unregister will do nothing other than
-		 * to wait ->release to finish and
-		 * mmu_notifier_unregister to return.
+		 * mmu_notifier_unregister will do nothing other than to wait
+		 * for ->release to finish and for mmu_notifier_unregister to
+		 * return.
 		 */
 		hlist_del_init_rcu(&mn->hlist);
-		/*
-		 * RCU here will block mmu_notifier_unregister until
-		 * ->release returns.
-		 */
-		rcu_read_lock();
-		spin_unlock(&mm->mmu_notifier_mm->lock);
-		/*
-		 * if ->release runs before mmu_notifier_unregister it
-		 * must be handled as it's the only way for the driver
-		 * to flush all existing sptes and stop the driver
-		 * from establishing any more sptes before all the
-		 * pages in the mm are freed.
-		 */
-		if (mn->ops->release)
-			mn->ops->release(mn, mm);
-		rcu_read_unlock();
-		spin_lock(&mm->mmu_notifier_mm->lock);
 	}
 	spin_unlock(&mm->mmu_notifier_mm->lock);
 
 	/*
-	 * synchronize_rcu here prevents mmu_notifier_release to
-	 * return to exit_mmap (which would proceed freeing all pages
-	 * in the mm) until the ->release method returns, if it was
-	 * invoked by mmu_notifier_unregister.
+	 * synchronize_srcu here prevents mmu_notifier_release from returning to
+	 * exit_mmap (which would proceed with freeing all pages in the mm)
+	 * until the ->release method returns, if it was invoked by
+	 * mmu_notifier_unregister.
 	 *
-	 * The mmu_notifier_mm can't go away from under us because one
-	 * mm_count is hold by exit_mmap.
+	 * The mmu_notifier_mm can't go away from under us because one mm_count
+	 * is held by exit_mmap.
 	 */
-	synchronize_rcu();
+	synchronize_srcu(&srcu);
 }
 
 /*
@@ -87,15 +91,33 @@ int __mmu_notifier_clear_flush_young(struct mm_struct *mm,
 					unsigned long address)
 {
 	struct mmu_notifier *mn;
-	struct hlist_node *n;
-	int young = 0;
+	int young = 0, id;
 
-	rcu_read_lock();
-	hlist_for_each_entry_rcu(mn, n, &mm->mmu_notifier_mm->list, hlist) {
+	id = srcu_read_lock(&srcu);
+	hlist_for_each_entry_rcu(mn, &mm->mmu_notifier_mm->list, hlist) {
 		if (mn->ops->clear_flush_young)
 			young |= mn->ops->clear_flush_young(mn, mm, address);
 	}
-	rcu_read_unlock();
+	srcu_read_unlock(&srcu, id);
+
+	return young;
+}
+
+int __mmu_notifier_test_young(struct mm_struct *mm,
+			      unsigned long address)
+{
+	struct mmu_notifier *mn;
+	int young = 0, id;
+
+	id = srcu_read_lock(&srcu);
+	hlist_for_each_entry_rcu(mn, &mm->mmu_notifier_mm->list, hlist) {
+		if (mn->ops->test_young) {
+			young = mn->ops->test_young(mn, mm, address);
+			if (young)
+				break;
+		}
+	}
+	srcu_read_unlock(&srcu, id);
 
 	return young;
 }
@@ -104,63 +126,59 @@ void __mmu_notifier_change_pte(struct mm_struct *mm, unsigned long address,
 			       pte_t pte)
 {
 	struct mmu_notifier *mn;
-	struct hlist_node *n;
+	int id;
 
-	rcu_read_lock();
-	hlist_for_each_entry_rcu(mn, n, &mm->mmu_notifier_mm->list, hlist) {
+	id = srcu_read_lock(&srcu);
+	hlist_for_each_entry_rcu(mn, &mm->mmu_notifier_mm->list, hlist) {
 		if (mn->ops->change_pte)
 			mn->ops->change_pte(mn, mm, address, pte);
-		/*
-		 * Some drivers don't have change_pte,
-		 * so we must call invalidate_page in that case.
-		 */
-		else if (mn->ops->invalidate_page)
-			mn->ops->invalidate_page(mn, mm, address);
 	}
-	rcu_read_unlock();
+	srcu_read_unlock(&srcu, id);
 }
 
 void __mmu_notifier_invalidate_page(struct mm_struct *mm,
 					  unsigned long address)
 {
 	struct mmu_notifier *mn;
-	struct hlist_node *n;
+	int id;
 
-	rcu_read_lock();
-	hlist_for_each_entry_rcu(mn, n, &mm->mmu_notifier_mm->list, hlist) {
+	id = srcu_read_lock(&srcu);
+	hlist_for_each_entry_rcu(mn, &mm->mmu_notifier_mm->list, hlist) {
 		if (mn->ops->invalidate_page)
 			mn->ops->invalidate_page(mn, mm, address);
 	}
-	rcu_read_unlock();
+	srcu_read_unlock(&srcu, id);
 }
 
 void __mmu_notifier_invalidate_range_start(struct mm_struct *mm,
 				  unsigned long start, unsigned long end)
 {
 	struct mmu_notifier *mn;
-	struct hlist_node *n;
+	int id;
 
-	rcu_read_lock();
-	hlist_for_each_entry_rcu(mn, n, &mm->mmu_notifier_mm->list, hlist) {
+	id = srcu_read_lock(&srcu);
+	hlist_for_each_entry_rcu(mn, &mm->mmu_notifier_mm->list, hlist) {
 		if (mn->ops->invalidate_range_start)
 			mn->ops->invalidate_range_start(mn, mm, start, end);
 	}
-	rcu_read_unlock();
+	srcu_read_unlock(&srcu, id);
 }
+EXPORT_SYMBOL_GPL(__mmu_notifier_invalidate_range_start);
 
 void __mmu_notifier_invalidate_range_end(struct mm_struct *mm,
 				  unsigned long start, unsigned long end)
 {
 	struct mmu_notifier *mn;
-	struct hlist_node *n;
+	int id;
 
-	rcu_read_lock();
-	hlist_for_each_entry_rcu(mn, n, &mm->mmu_notifier_mm->list, hlist) {
+	id = srcu_read_lock(&srcu);
+	hlist_for_each_entry_rcu(mn, &mm->mmu_notifier_mm->list, hlist) {
 		if (mn->ops->invalidate_range_end)
 			mn->ops->invalidate_range_end(mn, mm, start, end);
 	}
-	rcu_read_unlock();
+	srcu_read_unlock(&srcu, id);
 }
+EXPORT_SYMBOL_GPL(__mmu_notifier_invalidate_range_end);
 
 static int do_mmu_notifier_register(struct mmu_notifier *mn,
 				    struct mm_struct *mm,
@@ -171,6 +189,12 @@ static int do_mmu_notifier_register(struct mmu_notifier *mn,
 
 	BUG_ON(atomic_read(&mm->mm_users) <= 0);
 
+	/*
+	 * Verify that mmu_notifier_init() already run and the global srcu is
+	 * initialized.
+	 */
+	BUG_ON(!srcu.per_cpu_ref);
+
 	ret = -ENOMEM;
 	mmu_notifier_mm = kmalloc(sizeof(struct mmu_notifier_mm), GFP_KERNEL);
 	if (unlikely(!mmu_notifier_mm))
@@ -180,11 +204,12 @@ static int do_mmu_notifier_register(struct mmu_notifier *mn,
 		down_write(&mm->mmap_sem);
 	ret = mm_take_all_locks(mm);
 	if (unlikely(ret))
-		goto out_cleanup;
+		goto out_clean;
 
 	if (!mm_has_notifiers(mm)) {
 		INIT_HLIST_HEAD(&mmu_notifier_mm->list);
 		spin_lock_init(&mmu_notifier_mm->lock);
+
 		mm->mmu_notifier_mm = mmu_notifier_mm;
 		mmu_notifier_mm = NULL;
 	}
@@ -203,10 +228,9 @@ static int do_mmu_notifier_register(struct mmu_notifier *mn,
 	spin_unlock(&mm->mmu_notifier_mm->lock);
 
 	mm_drop_all_locks(mm);
-out_cleanup:
+out_clean:
 	if (take_mmap_sem)
 		up_write(&mm->mmap_sem);
-	/* kfree() does nothing if mmu_notifier_mm is NULL */
 	kfree(mmu_notifier_mm);
 out:
 	BUG_ON(atomic_read(&mm->mm_users) <= 0);
@@ -253,8 +277,8 @@ void __mmu_notifier_mm_destroy(struct mm_struct *mm)
 /*
  * This releases the mm_count pin automatically and frees the mm
  * structure if it was the last user of it. It serializes against
- * running mmu notifiers with RCU and against mmu_notifier_unregister
- * with the unregister lock + RCU. All sptes must be dropped before
+ * running mmu notifiers with SRCU and against mmu_notifier_unregister
+ * with the unregister lock + SRCU. All sptes must be dropped before
  * calling mmu_notifier_unregister. ->release or any other notifier
  * method may be invoked concurrently with mmu_notifier_unregister,
  * and only after mmu_notifier_unregister returned we're guaranteed
@@ -264,35 +288,45 @@ void mmu_notifier_unregister(struct mmu_notifier *mn, struct mm_struct *mm)
 {
 	BUG_ON(atomic_read(&mm->mm_count) <= 0);
 
-	spin_lock(&mm->mmu_notifier_mm->lock);
 	if (!hlist_unhashed(&mn->hlist)) {
-		hlist_del_rcu(&mn->hlist);
-
 		/*
-		 * RCU here will force exit_mmap to wait ->release to finish
-		 * before freeing the pages.
+		 * SRCU here will force exit_mmap to wait for ->release to
+		 * finish before freeing the pages.
 		 */
-		rcu_read_lock();
-		spin_unlock(&mm->mmu_notifier_mm->lock);
+		int id;
+
+		id = srcu_read_lock(&srcu);
 		/*
-		 * exit_mmap will block in mmu_notifier_release to
-		 * guarantee ->release is called before freeing the
-		 * pages.
+		 * exit_mmap will block in mmu_notifier_release to guarantee
+		 * that ->release is called before freeing the pages.
 		 */
 		if (mn->ops->release)
 			mn->ops->release(mn, mm);
-		rcu_read_unlock();
-	} else
+		srcu_read_unlock(&srcu, id);
+
+		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);
+	}
 
 	/*
-	 * Wait any running method to finish, of course including
-	 * ->release if it was run by mmu_notifier_relase instead of us.
+	 * Wait for any running method to finish, of course including
+	 * ->release if it was run by mmu_notifier_release instead of us.
 	 */
-	synchronize_rcu();
+	synchronize_srcu(&srcu);
 
 	BUG_ON(atomic_read(&mm->mm_count) <= 0);
 
 	mmdrop(mm);
 }
 EXPORT_SYMBOL_GPL(mmu_notifier_unregister);
+
+static int __init mmu_notifier_init(void)
+{
+	return init_srcu_struct(&srcu);
+}
+subsys_initcall(mmu_notifier_init);