The VMA lock is used to prevent high-granularity HugeTLB mappings from
being collapsed while other threads are doing high-granularity page
table walks.
Signed-off-by: James Houghton <jthoughton@xxxxxxxxxx>
---
include/linux/hugetlb.h | 12 ++++++++++++
mm/rmap.c | 3 ++-
2 files changed, 14 insertions(+), 1 deletion(-)
diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index b7cf45535d64..daf993fdbc38 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -156,6 +156,18 @@ struct file_region {
#endif
};
+/*
+ * The HugeTLB VMA lock is used to synchronize HugeTLB page table walks.
+ * Right now, it is only used for VM_SHARED mappings.
+ * - The read lock is held when we want to stabilize mappings (prevent PMD
+ * unsharing or MADV_COLLAPSE for high-granularity mappings).
+ * - The write lock is held when we want to free mappings (PMD unsharing and
+ * MADV_COLLAPSE for high-granularity mappings).
+ *
+ * Note: For PMD unsharing and MADV_COLLAPSE, the i_mmap_rwsem is held for
+ * writing as well, so page table walkers will also be safe if they hold
+ * i_mmap_rwsem for at least reading. See hugetlb_walk() for more information.
+ */
struct hugetlb_vma_lock {
struct kref refs;
struct rw_semaphore rw_sema;
diff --git a/mm/rmap.c b/mm/rmap.c
index ff7e6c770b0a..076ea77010e5 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -47,7 +47,8 @@
*
* hugetlbfs PageHuge() take locks in this order:
* hugetlb_fault_mutex (hugetlbfs specific page fault mutex)
- * vma_lock (hugetlb specific lock for pmd_sharing)
+ * vma_lock (hugetlb specific lock for pmd_sharing and high-granularity
+ * mapping)
* mapping->i_mmap_rwsem (also used for hugetlb pmd sharing)
* page->flags PG_locked (lock_page)
*/
--
2.39.0.314.g84b9a713c41-goog
