[RFC][PATCH] hugetlb: fix resv_map leak in error path

[Dave Hansen]

When called for anonymous (non-shared) mappings,
hugetlb_reserve_pages() does a resv_map_alloc().  It depends on
code in hugetlbfs's vm_ops->close() to release that allocation.

However, in the mmap() failure path, we do a plain unmap_region()
without the remove_vma() which actually calls vm_ops->close().

This is a decent fix.  This leak could get reintroduced if
new code (say, after hugetlb_reserve_pages() in
hugetlbfs_file_mmap()) decides to return an error.  But, I think
it would have to unroll the reservation anyway.

This hasn't been extensively tested.  Pretty much compile and
boot tested along with Christoph's test case.

Comments?


Signed-off-by: Dave Hansen <dave@xxxxxxxxxxxxxxxxxx>
---

 mm/hugetlb.c |   28 ++++++++++++++++++++++------
 1 file changed, 22 insertions(+), 6 deletions(-)

Index: linux-3.2.0/mm/hugetlb.c
===================================================================
--- linux-3.2.0.orig/mm/hugetlb.c	2012-01-04 17:55:44.000000000 -0600
+++ linux-3.2.0/mm/hugetlb.c	2012-05-22 03:32:37.760054550 -0500
@@ -2068,6 +2068,15 @@ static void hugetlb_vm_op_open(struct vm
 		kref_get(&reservations->refs);
 }

+static void resv_map_put(struct vm_area_struct *vma)
+{
+	struct resv_map *reservations = vma_resv_map(vma);
+
+	if (!reservations)
+		return;
+	kref_put(&reservations->refs, resv_map_release);
+}
+
 static void hugetlb_vm_op_close(struct vm_area_struct *vma)
 {
 	struct hstate *h = hstate_vma(vma);
@@ -2083,7 +2092,7 @@ static void hugetlb_vm_op_close(struct v
 		reserve = (end - start) -
 			region_count(&reservations->regions, start, end);

-		kref_put(&reservations->refs, resv_map_release);
+		resv_map_put(vma);

 		if (reserve) {
 			hugetlb_acct_memory(h, -reserve);
@@ -2883,12 +2892,16 @@ int hugetlb_reserve_pages(struct inode *
 		set_vma_resv_flags(vma, HPAGE_RESV_OWNER);
 	}

-	if (chg < 0)
-		return chg;
+	if (chg < 0) {
+		ret = chg;
+		goto out_err;
+	}

 	/* There must be enough filesystem quota for the mapping */
-	if (hugetlb_get_quota(inode->i_mapping, chg))
-		return -ENOSPC;
+	if (hugetlb_get_quota(inode->i_mapping, chg)) {
+		ret = -ENOSPC;
+		goto out_err;
+	}

 	/*
 	 * Check enough hugepages are available for the reservation.
@@ -2897,7 +2910,7 @@ int hugetlb_reserve_pages(struct inode *
 	ret = hugetlb_acct_memory(h, chg);
 	if (ret < 0) {
 		hugetlb_put_quota(inode->i_mapping, chg);
-		return ret;
+		goto out_err;
 	}

 	/*
@@ -2914,6 +2927,9 @@ int hugetlb_reserve_pages(struct inode *
 	if (!vma || vma->vm_flags & VM_MAYSHARE)
 		region_add(&inode->i_mapping->private_list, from, to);
 	return 0;
+out_err:
+	resv_map_put(vma);
+	return ret;
 }

 void hugetlb_unreserve_pages(struct inode *inode, long offset, long freed)

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/