mm/hmm: fix use after free with struct hmm in the mmu notifiers

mmu_notifier_unregister_no_release() is not a fence and the mmu_notifier
system will continue to reference hmm->mn until the srcu grace period
expires.

Resulting in use after free races like this:

         CPU0                                     CPU1
                                               __mmu_notifier_invalidate_range_start()
                                                 srcu_read_lock
                                                 hlist_for_each ()
                                                   // mn == hmm->mn
hmm_mirror_unregister()
  hmm_put()
    hmm_free()
      mmu_notifier_unregister_no_release()
         hlist_del_init_rcu(hmm-mn->list)
			                           mn->ops->invalidate_range_start(mn, range);
					             mm_get_hmm()
      mm->hmm = NULL;
      kfree(hmm)
                                                     mutex_lock(&hmm->lock);

Use SRCU to kfree the hmm memory so that the notifiers can rely on hmm
existing. Get the now-safe hmm struct through container_of and directly
check kref_get_unless_zero to lock it against free.

Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Reviewed-by: Ira Weiny <ira.weiny@intel.com>
Reviewed-by: John Hubbard <jhubbard@nvidia.com>
Reviewed-by: Ralph Campbell <rcampbell@nvidia.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Tested-by: Philip Yang <Philip.Yang@amd.com>

include/linux/hmm.h

@@ -93,6 +93,7 @@ struct hmm {
 	struct mmu_notifier	mmu_notifier;
 	struct rw_semaphore	mirrors_sem;
 	wait_queue_head_t	wq;
+	struct rcu_head		rcu;
 	long			notifiers;
 	bool			dead;
 };

mm/hmm.c

@@ -104,6 +104,11 @@ static struct hmm *hmm_get_or_create(struct mm_struct *mm)
 	return NULL;
 }
 
+static void hmm_free_rcu(struct rcu_head *rcu)
+{
+	kfree(container_of(rcu, struct hmm, rcu));
+}
+
 static void hmm_free(struct kref *kref)
 {
 	struct hmm *hmm = container_of(kref, struct hmm, kref);
@@ -116,7 +121,7 @@ static void hmm_free(struct kref *kref)
 		mm->hmm = NULL;
 	spin_unlock(&mm->page_table_lock);
 
-	kfree(hmm);
+	mmu_notifier_call_srcu(&hmm->rcu, hmm_free_rcu);
 }
 
 static inline void hmm_put(struct hmm *hmm)
@@ -144,10 +149,14 @@ void hmm_mm_destroy(struct mm_struct *mm)
 
 static void hmm_release(struct mmu_notifier *mn, struct mm_struct *mm)
 {
-	struct hmm *hmm = mm_get_hmm(mm);
+	struct hmm *hmm = container_of(mn, struct hmm, mmu_notifier);
 	struct hmm_mirror *mirror;
 	struct hmm_range *range;
 
+	/* Bail out if hmm is in the process of being freed */
+	if (!kref_get_unless_zero(&hmm->kref))
+		return;
+
 	/* Report this HMM as dying. */
 	hmm->dead = true;
 
@@ -185,13 +194,14 @@ static void hmm_release(struct mmu_notifier *mn, struct mm_struct *mm)
 static int hmm_invalidate_range_start(struct mmu_notifier *mn,
 			const struct mmu_notifier_range *nrange)
 {
-	struct hmm *hmm = mm_get_hmm(nrange->mm);
+	struct hmm *hmm = container_of(mn, struct hmm, mmu_notifier);
 	struct hmm_mirror *mirror;
 	struct hmm_update update;
 	struct hmm_range *range;
 	int ret = 0;
 
-	VM_BUG_ON(!hmm);
+	if (!kref_get_unless_zero(&hmm->kref))
+		return 0;
 
 	update.start = nrange->start;
 	update.end = nrange->end;
@@ -236,9 +246,10 @@ static int hmm_invalidate_range_start(struct mmu_notifier *mn,
 static void hmm_invalidate_range_end(struct mmu_notifier *mn,
 			const struct mmu_notifier_range *nrange)
 {
-	struct hmm *hmm = mm_get_hmm(nrange->mm);
+	struct hmm *hmm = container_of(mn, struct hmm, mmu_notifier);
 
-	VM_BUG_ON(!hmm);
+	if (!kref_get_unless_zero(&hmm->kref))
+		return;
 
 	mutex_lock(&hmm->lock);
 	hmm->notifiers--;