hugetlb: add vma based lock for pmd sharing

Allocate a new hugetlb_vma_lock structure and hang off vm_private_data for
synchronization use by vmas that could be involved in pmd sharing.  This
data structure contains a rw semaphore that is the primary tool used for
synchronization.

This new structure is ref counted, so that it can exist when NOT attached
to a vma.  This is only helpful in resolving lock ordering issues where
code may need to obtain the vma_lock while there are no guarantees the vma
may go away.  By obtaining a ref on the structure, it can be guaranteed
that at least the rw semaphore will not go away.

Only add infrastructure for the new lock here.  Actual use will be added
in subsequent patches.

[[email protected]: fix build issue for missing hugetlb_vma_lock_release]
  Link: https://lkml.kernel.org/r/YyNUtA1vRASOE4+M@monkey
Link: https://lkml.kernel.org/r/[email protected]
Signed-off-by: Mike Kravetz <[email protected]>
Reviewed-by: Miaohe Lin <[email protected]>
Cc: Andrea Arcangeli <[email protected]>
Cc: "Aneesh Kumar K.V" <[email protected]>
Cc: Axel Rasmussen <[email protected]>
Cc: David Hildenbrand <[email protected]>
Cc: Davidlohr Bueso <[email protected]>
Cc: James Houghton <[email protected]>
Cc: "Kirill A. Shutemov" <[email protected]>
Cc: Michal Hocko <[email protected]>
Cc: Mina Almasry <[email protected]>
Cc: Muchun Song <[email protected]>
Cc: Naoya Horiguchi <[email protected]>
Cc: Pasha Tatashin <[email protected]>
Cc: Peter Xu <[email protected]>
Cc: Prakash Sangappa <[email protected]>
Cc: Sven Schnelle <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>

Author: mjkravetz

include/linux/hugetlb.h

@@ -115,6 +115,12 @@ struct file_region {
 #endif
 };
 
+struct hugetlb_vma_lock {
+	struct kref refs;
+	struct rw_semaphore rw_sema;
+	struct vm_area_struct *vma;
+};
+
 extern struct resv_map *resv_map_alloc(void);
 void resv_map_release(struct kref *ref);
 
@@ -127,7 +133,7 @@ struct hugepage_subpool *hugepage_new_subpool(struct hstate *h, long max_hpages,
 						long min_hpages);
 void hugepage_put_subpool(struct hugepage_subpool *spool);
 
-void reset_vma_resv_huge_pages(struct vm_area_struct *vma);
+void hugetlb_dup_vma_private(struct vm_area_struct *vma);
 void clear_vma_resv_huge_pages(struct vm_area_struct *vma);
 int hugetlb_sysctl_handler(struct ctl_table *, int, void *, size_t *, loff_t *);
 int hugetlb_overcommit_handler(struct ctl_table *, int, void *, size_t *,
@@ -215,6 +221,14 @@ struct page *follow_huge_pud(struct mm_struct *mm, unsigned long address,
 struct page *follow_huge_pgd(struct mm_struct *mm, unsigned long address,
 			     pgd_t *pgd, int flags);
 
+void hugetlb_vma_lock_read(struct vm_area_struct *vma);
+void hugetlb_vma_unlock_read(struct vm_area_struct *vma);
+void hugetlb_vma_lock_write(struct vm_area_struct *vma);
+void hugetlb_vma_unlock_write(struct vm_area_struct *vma);
+int hugetlb_vma_trylock_write(struct vm_area_struct *vma);
+void hugetlb_vma_assert_locked(struct vm_area_struct *vma);
+void hugetlb_vma_lock_release(struct kref *kref);
+
 int pmd_huge(pmd_t pmd);
 int pud_huge(pud_t pud);
 unsigned long hugetlb_change_protection(struct vm_area_struct *vma,
@@ -226,7 +240,7 @@ void hugetlb_unshare_all_pmds(struct vm_area_struct *vma);
 
 #else /* !CONFIG_HUGETLB_PAGE */
 
-static inline void reset_vma_resv_huge_pages(struct vm_area_struct *vma)
+static inline void hugetlb_dup_vma_private(struct vm_area_struct *vma)
 {
 }
 
@@ -337,6 +351,31 @@ static inline int prepare_hugepage_range(struct file *file,
 	return -EINVAL;
 }
 
+static inline void hugetlb_vma_lock_read(struct vm_area_struct *vma)
+{
+}
+
+static inline void hugetlb_vma_unlock_read(struct vm_area_struct *vma)
+{
+}
+
+static inline void hugetlb_vma_lock_write(struct vm_area_struct *vma)
+{
+}
+
+static inline void hugetlb_vma_unlock_write(struct vm_area_struct *vma)
+{
+}
+
+static inline int hugetlb_vma_trylock_write(struct vm_area_struct *vma)
+{
+	return 1;
+}
+
+static inline void hugetlb_vma_assert_locked(struct vm_area_struct *vma)
+{
+}
+
 static inline int pmd_huge(pmd_t pmd)
 {
 	return 0;

kernel/fork.c

@@ -674,12 +674,10 @@ static __latent_entropy int dup_mmap(struct mm_struct *mm,
 		}
 
 		/*
-		 * Clear hugetlb-related page reserves for children. This only
-		 * affects MAP_PRIVATE mappings. Faults generated by the child
-		 * are not guaranteed to succeed, even if read-only
+		 * Copy/update hugetlb private vma information.
 		 */
 		if (is_vm_hugetlb_page(tmp))
-			reset_vma_resv_huge_pages(tmp);
+			hugetlb_dup_vma_private(tmp);
 
 		/* Link the vma into the MT */
 		mas.index = tmp->vm_start;