BACKPORT: mseal: replace can_modify_mm_madv with a vma variant

Replace can_modify_mm_madv() with a single vma variant, and associated
checks in madvise.

While we're at it, also invert the order of checks in:
 if (unlikely(is_ro_anon(vma) && !can_modify_vma(vma))

Checking if we can modify the vma itself (through vm_flags) is certainly
cheaper than is_ro_anon() due to arch_vma_access_permitted() looking at
e.g pkeys registers (with extra branches) in some architectures.

This patch allows for partial madvise success when finding a sealed VMA,
which historically has been allowed in Linux.

Link: https://lkml.kernel.org/r/[email protected]
Change-Id: I0808016433305eb5e663d1de1cc697cac2c12dd8
Signed-off-by: Pedro Falcato <[email protected]>
Reviewed-by: Liam R. Howlett <[email protected]>
Reviewed-by: Lorenzo Stoakes <[email protected]>
Cc: Jeff Xu <[email protected]>
Cc: Kees Cook <[email protected]>
Cc: Linus Torvalds <[email protected]>
Cc: Michael Ellerman <[email protected]>
Cc: Shuah Khan <[email protected]>
Cc: Vlastimil Babka <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
(cherry picked from commit 23c57d1)

Author: heatd

mm/internal.h

@@ -1486,6 +1486,8 @@ static inline bool can_modify_vma(struct vm_area_struct *vma)
 	return true;
 }
 
+bool can_modify_vma_madv(struct vm_area_struct *vma, int behavior);
+
 #else
 static inline int can_do_mseal(unsigned long flags)
 {
@@ -1509,5 +1511,10 @@ static inline bool can_modify_vma(struct vm_area_struct *vma)
 	return true;
 }
 
+static inline bool can_modify_vma_madv(struct vm_area_struct *vma, int behavior)
+{
+	return true;
+}
+
 #endif
 #endif	/* __MM_INTERNAL_H */

mm/madvise.c

@@ -1090,6 +1090,9 @@ static int madvise_vma_behavior(struct vm_area_struct *vma,
 	struct anon_vma_name *anon_name;
 	unsigned long new_flags = vma->vm_flags;
 
+	if (unlikely(!can_modify_vma_madv(vma, behavior)))
+		return -EPERM;
+
 	switch (behavior) {
 	case MADV_REMOVE:
 		return madvise_remove(vma, prev, start, end);
@@ -1508,21 +1511,11 @@ int do_madvise(struct mm_struct *mm, unsigned long start, size_t len_in, int beh
 	start = untagged_addr_remote(mm, start);
 	end = start + len;
 
-	/*
-	 * Check if the address range is sealed for do_madvise().
-	 * can_modify_mm_madv assumes we have acquired the lock on MM.
-	 */
-	if (unlikely(!can_modify_mm_madv(mm, start, end, behavior))) {
-		error = -EPERM;
-		goto out;
-	}
-
 	blk_start_plug(&plug);
 	error = madvise_walk_vmas(mm, start, end, behavior,
 			madvise_vma_behavior);
 	blk_finish_plug(&plug);
 
-out:
 	if (write)
 		mmap_write_unlock(mm);
 	else

mm/mseal.c

@@ -76,24 +76,15 @@ bool can_modify_mm(struct mm_struct *mm, unsigned long start, unsigned long end)
 }
 
 /*
- * Check if the vmas of a memory range are allowed to be modified by madvise.
- * the memory ranger can have a gap (unallocated memory).
- * return true, if it is allowed.
+ * Check if a vma is allowed to be modified by madvise.
  */
-bool can_modify_mm_madv(struct mm_struct *mm, unsigned long start, unsigned long end,
-		int behavior)
+bool can_modify_vma_madv(struct vm_area_struct *vma, int behavior)
 {
-	struct vm_area_struct *vma;
-
-	VMA_ITERATOR(vmi, mm, start);
-
 	if (!is_madv_discard(behavior))
 		return true;
 
-	/* going through each vma to check. */
-	for_each_vma_range(vmi, vma, end)
-		if (unlikely(is_ro_anon(vma) && !can_modify_vma(vma)))
-			return false;
+	if (unlikely(!can_modify_vma(vma) && is_ro_anon(vma)))
+		return false;
 
 	/* Allow by default. */
 	return true;