hugetlbfs: always use address space in inode for resv_map pointer

Continuing discussion about 58b6e5e8f1ad ("hugetlbfs: fix memory leak for
resv_map") brought up the issue that inode->i_mapping may not point to the
address space embedded within the inode at inode eviction time.  The
hugetlbfs truncate routine handles this by explicitly using inode->i_data.
However, code cleaning up the resv_map will still use the address space
pointed to by inode->i_mapping.  Luckily, private_data is NULL for address
spaces in all such cases today but, there is no guarantee this will
continue.

Change all hugetlbfs code getting a resv_map pointer to explicitly get it
from the address space embedded within the inode.  In addition, add more
comments in the code to indicate why this is being done.

Link: http://lkml.kernel.org/r/20190419204435.16984-1-mike.kravetz@oracle.com
Signed-off-by: Mike Kravetz <mike.kravetz@oracle.com>
Reported-by: Yufen Yu <yuyufen@huawei.com>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Cc: "Kirill A . Shutemov" <kirill.shutemov@linux.intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c
index f232371..1dcc571 100644 (file)
--- a/fs/hugetlbfs/inode.c
+++ b/fs/hugetlbfs/inode.c
@@ -497,8 +497,15 @@ static void hugetlbfs_evict_inode(struct inode *inode)
        struct resv_map *resv_map;
 
        remove_inode_hugepages(inode, 0, LLONG_MAX);
-       resv_map = (struct resv_map *)inode->i_mapping->private_data;
-       /* root inode doesn't have the resv_map, so we should check it */
+
+       /*
+        * Get the resv_map from the address space embedded in the inode.
+        * This is the address space which points to any resv_map allocated
+        * at inode creation time.  If this is a device special inode,
+        * i_mapping may not point to the original address space.
+        */
+       resv_map = (struct resv_map *)(&inode->i_data)->private_data;
+       /* Only regular and link inodes have associated reserve maps */
        if (resv_map)
                resv_map_release(&resv_map->refs);
        clear_inode(inode);

diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index cab38ef..81718c5 100644 (file)
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -740,7 +740,15 @@ void resv_map_release(struct kref *ref)
 
 static inline struct resv_map *inode_resv_map(struct inode *inode)
 {
-       return inode->i_mapping->private_data;
+       /*
+        * At inode evict time, i_mapping may not point to the original
+        * address space within the inode.  This original address space
+        * contains the pointer to the resv_map.  So, always use the
+        * address space embedded within the inode.
+        * The VERY common case is inode->mapping == &inode->i_data but,
+        * this may not be true for device special inodes.
+        */
+       return (struct resv_map *)(&inode->i_data)->private_data;
 }
 
 static struct resv_map *vma_resv_map(struct vm_area_struct *vma)
@@ -4518,6 +4526,11 @@ int hugetlb_reserve_pages(struct inode *inode,
         * called to make the mapping read-write. Assume !vma is a shm mapping
         */
        if (!vma || vma->vm_flags & VM_MAYSHARE) {
+               /*
+                * resv_map can not be NULL as hugetlb_reserve_pages is only
+                * called for inodes for which resv_maps were created (see
+                * hugetlbfs_get_inode).
+                */
                resv_map = inode_resv_map(inode);
 
                chg = region_chg(resv_map, from, to);
@@ -4609,6 +4622,10 @@ long hugetlb_unreserve_pages(struct inode *inode, long start, long end,
        struct hugepage_subpool *spool = subpool_inode(inode);
        long gbl_reserve;
 
+       /*
+        * Since this routine can be called in the evict inode path for all
+        * hugetlbfs inodes, resv_map could be NULL.
+        */
        if (resv_map) {
                chg = region_del(resv_map, start, end);
                /*