[PATCH v2 hmm 04/11] mm/hmm: Simplify hmm_get_or_create and make it reliable

[Jason Gunthorpe <jgg-uk2M96/98Pc@public.gmane.org>]

From: Jason Gunthorpe <jgg@mellanox.com>

As coded this function can false-fail in various racy situations. Make it
reliable by running only under the write side of the mmap_sem and avoiding
the false-failing compare/exchange pattern.

Also make the locking very easy to understand by only ever reading or
writing mm->hmm while holding the write side of the mmap_sem.

Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
---
v2:
- Fix error unwind of mmgrab (Jerome)
- Use hmm local instead of 2nd container_of (Jerome)
---
 mm/hmm.c | 80 ++++++++++++++++++++------------------------------------
 1 file changed, 29 insertions(+), 51 deletions(-)

diff --git a/mm/hmm.c b/mm/hmm.c
index cc7c26fda3300e..dc30edad9a8a02 100644
--- a/mm/hmm.c
+++ b/mm/hmm.c
@@ -40,16 +40,6 @@
 #if IS_ENABLED(CONFIG_HMM_MIRROR)
 static const struct mmu_notifier_ops hmm_mmu_notifier_ops;
 
-static inline struct hmm *mm_get_hmm(struct mm_struct *mm)
-{
-	struct hmm *hmm = READ_ONCE(mm->hmm);
-
-	if (hmm && kref_get_unless_zero(&hmm->kref))
-		return hmm;
-
-	return NULL;
-}
-
 /**
  * hmm_get_or_create - register HMM against an mm (HMM internal)
  *
@@ -64,11 +54,20 @@ static inline struct hmm *mm_get_hmm(struct mm_struct *mm)
  */
 static struct hmm *hmm_get_or_create(struct mm_struct *mm)
 {
-	struct hmm *hmm = mm_get_hmm(mm);
-	bool cleanup = false;
+	struct hmm *hmm;
 
-	if (hmm)
-		return hmm;
+	lockdep_assert_held_exclusive(&mm->mmap_sem);
+
+	if (mm->hmm) {
+		if (kref_get_unless_zero(&mm->hmm->kref))
+			return mm->hmm;
+		/*
+		 * The hmm is being freed by some other CPU and is pending a
+		 * RCU grace period, but this CPU can NULL now it since we
+		 * have the mmap_sem.
+		 */
+		mm->hmm = NULL;
+	}
 
 	hmm = kmalloc(sizeof(*hmm), GFP_KERNEL);
 	if (!hmm)
@@ -83,57 +82,36 @@ static struct hmm *hmm_get_or_create(struct mm_struct *mm)
 	hmm->notifiers = 0;
 	hmm->dead = false;
 	hmm->mm = mm;
-	mmgrab(hmm->mm);
-
-	spin_lock(&mm->page_table_lock);
-	if (!mm->hmm)
-		mm->hmm = hmm;
-	else
-		cleanup = true;
-	spin_unlock(&mm->page_table_lock);
 
-	if (cleanup)
-		goto error;
-
-	/*
-	 * We should only get here if hold the mmap_sem in write mode ie on
-	 * registration of first mirror through hmm_mirror_register()
-	 */
 	hmm->mmu_notifier.ops = &hmm_mmu_notifier_ops;
-	if (__mmu_notifier_register(&hmm->mmu_notifier, mm))
-		goto error_mm;
+	if (__mmu_notifier_register(&hmm->mmu_notifier, mm)) {
+		kfree(hmm);
+		return NULL;
+	}
 
+	mmgrab(hmm->mm);
+	mm->hmm = hmm;
 	return hmm;
-
-error_mm:
-	spin_lock(&mm->page_table_lock);
-	if (mm->hmm == hmm)
-		mm->hmm = NULL;
-	spin_unlock(&mm->page_table_lock);
-error:
-	mmdrop(hmm->mm);
-	kfree(hmm);
-	return NULL;
 }
 
 static void hmm_free_rcu(struct rcu_head *rcu)
 {
-	kfree(container_of(rcu, struct hmm, rcu));
+	struct hmm *hmm = container_of(rcu, struct hmm, rcu);
+
+	down_write(&hmm->mm->mmap_sem);
+	if (hmm->mm->hmm == hmm)
+		hmm->mm->hmm = NULL;
+	up_write(&hmm->mm->mmap_sem);
+	mmdrop(hmm->mm);
+
+	kfree(hmm);
 }
 
 static void hmm_free(struct kref *kref)
 {
 	struct hmm *hmm = container_of(kref, struct hmm, kref);
-	struct mm_struct *mm = hmm->mm;
-
-	mmu_notifier_unregister_no_release(&hmm->mmu_notifier, mm);
 
-	spin_lock(&mm->page_table_lock);
-	if (mm->hmm == hmm)
-		mm->hmm = NULL;
-	spin_unlock(&mm->page_table_lock);
-
-	mmdrop(hmm->mm);
+	mmu_notifier_unregister_no_release(&hmm->mmu_notifier, hmm->mm);
 	mmu_notifier_call_srcu(&hmm->rcu, hmm_free_rcu);
 }
 
-- 
2.21.0

_______________________________________________
amd-gfx mailing list
amd-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/amd-gfx