@@ -1349,6 +1349,47 @@ static inline int fixup_user_fault(struct task_struct *tsk,
}
#endif
+#ifdef CONFIG_SPF
+static inline void vm_write_begin(struct vm_area_struct *vma)
+{
+ write_seqcount_begin(&vma->vm_sequence);
+}
+static inline void vm_write_begin_nested(struct vm_area_struct *vma,
+ int subclass)
+{
+ write_seqcount_begin_nested(&vma->vm_sequence, subclass);
+}
+static inline void vm_write_end(struct vm_area_struct *vma)
+{
+ write_seqcount_end(&vma->vm_sequence);
+}
+static inline void vm_raw_write_begin(struct vm_area_struct *vma)
+{
+ raw_write_seqcount_begin(&vma->vm_sequence);
+}
+static inline void vm_raw_write_end(struct vm_area_struct *vma)
+{
+ raw_write_seqcount_end(&vma->vm_sequence);
+}
+#else
+static inline void vm_write_begin(struct vm_area_struct *vma)
+{
+}
+static inline void vm_write_begin_nested(struct vm_area_struct *vma,
+ int subclass)
+{
+}
+static inline void vm_write_end(struct vm_area_struct *vma)
+{
+}
+static inline void vm_raw_write_begin(struct vm_area_struct *vma)
+{
+}
+static inline void vm_raw_write_end(struct vm_area_struct *vma)
+{
+}
+#endif /* CONFIG_SPF */
+
extern int access_process_vm(struct task_struct *tsk, unsigned long addr, void *buf, int len,
unsigned int gup_flags);
extern int access_remote_vm(struct mm_struct *mm, unsigned long addr,
@@ -346,6 +346,9 @@ struct vm_area_struct {
struct mempolicy *vm_policy; /* NUMA policy for the VMA */
#endif
struct vm_userfaultfd_ctx vm_userfaultfd_ctx;
+#ifdef CONFIG_SPF
+ seqcount_t vm_sequence;
+#endif
} __randomize_layout;
struct core_thread {
@@ -1504,6 +1504,7 @@ void unmap_page_range(struct mmu_gather *tlb,
unsigned long next;
BUG_ON(addr >= end);
+ vm_write_begin(vma);
tlb_start_vma(tlb, vma);
pgd = pgd_offset(vma->vm_mm, addr);
do {
@@ -1513,6 +1514,7 @@ void unmap_page_range(struct mmu_gather *tlb,
next = zap_p4d_range(tlb, vma, pgd, addr, next, details);
} while (pgd++, addr = next, addr != end);
tlb_end_vma(tlb, vma);
+ vm_write_end(vma);
}
@@ -558,6 +558,10 @@ void __vma_link_rb(struct mm_struct *mm, struct vm_area_struct *vma,
else
mm->highest_vm_end = vm_end_gap(vma);
+#ifdef CONFIG_SPF
+ seqcount_init(&vma->vm_sequence);
+#endif
+
/*
* vma->vm_prev wasn't known when we followed the rbtree to find the
* correct insertion point for that vma. As a result, we could not
@@ -692,6 +696,30 @@ int __vma_adjust(struct vm_area_struct *vma, unsigned long start,
long adjust_next = 0;
int remove_next = 0;
+ /*
+ * Why using vm_raw_write*() functions here to avoid lockdep's warning ?
+ *
+ * Locked is complaining about a theoretical lock dependency, involving
+ * 3 locks:
+ * mapping->i_mmap_rwsem --> vma->vm_sequence --> fs_reclaim
+ *
+ * Here are the major path leading to this dependency :
+ * 1. __vma_adjust() mmap_sem -> vm_sequence -> i_mmap_rwsem
+ * 2. move_vmap() mmap_sem -> vm_sequence -> fs_reclaim
+ * 3. __alloc_pages_nodemask() fs_reclaim -> i_mmap_rwsem
+ * 4. unmap_mapping_range() i_mmap_rwsem -> vm_sequence
+ *
+ * So there is no way to solve this easily, especially because in
+ * unmap_mapping_range() the i_mmap_rwsem is grab while the impacted
+ * VMAs are not yet known.
+ * However, the way the vm_seq is used is guarantying that we will
+ * never block on it since we just check for its value and never wait
+ * for it to move, see vma_has_changed() and handle_speculative_fault().
+ */
+ vm_raw_write_begin(vma);
+ if (next)
+ vm_raw_write_begin(next);
+
if (next && !insert) {
struct vm_area_struct *exporter = NULL, *importer = NULL;
@@ -903,6 +931,7 @@ int __vma_adjust(struct vm_area_struct *vma, unsigned long start,
mm->map_count--;
mpol_put(vma_policy(next));
kmem_cache_free(vm_area_cachep, next);
+ vm_raw_write_end(next);
/*
* In mprotect's case 6 (see comments on vma_merge),
* we must remove another next too. It would clutter
@@ -916,6 +945,8 @@ int __vma_adjust(struct vm_area_struct *vma, unsigned long start,
* "vma->vm_next" gap must be updated.
*/
next = vma->vm_next;
+ if (next)
+ vm_raw_write_begin(next);
} else {
/*
* For the scope of the comment "next" and
@@ -933,10 +964,9 @@ int __vma_adjust(struct vm_area_struct *vma, unsigned long start,
remove_next = 1;
end = next->vm_end;
goto again;
- }
- else if (next)
+ } else if (next) {
vma_gap_update(next);
- else {
+ } else {
/*
* If remove_next == 2 we obviously can't
* reach this path.
@@ -962,6 +992,10 @@ int __vma_adjust(struct vm_area_struct *vma, unsigned long start,
if (insert && file)
uprobe_mmap(insert);
+ if (next && next != vma)
+ vm_raw_write_end(next);
+ vm_raw_write_end(vma);
+
validate_mm(mm);
return 0;