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/20240817-mseal-depessimize-v3-5-d8d2e037df30@gmail.com
Signed-off-by: Pedro Falcato <pedro.falcato@gmail.com>
Reviewed-by: Liam R. Howlett <Liam.Howlett@Oracle.com>
Reviewed-by: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Cc: Jeff Xu <jeffxu@chromium.org>
Cc: Kees Cook <kees@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Shuah Khan <shuah@kernel.org>
Cc: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

mm/internal.h

@@ -1361,8 +1361,6 @@ static inline int can_do_mseal(unsigned long flags)
 
 bool can_modify_mm(struct mm_struct *mm, unsigned long start,
 		unsigned long end);
-bool can_modify_mm_madv(struct mm_struct *mm, unsigned long start,
-		unsigned long end, int behavior);
 #else
 static inline int can_do_mseal(unsigned long flags)
 {

mm/madvise.c

@@ -1031,6 +1031,9 @@ 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);
@@ -1448,15 +1451,6 @@ 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);
 	switch (behavior) {
 	case MADV_POPULATE_READ:
@@ -1470,7 +1464,6 @@ int do_madvise(struct mm_struct *mm, unsigned long start, size_t len_in, int beh
 	}
 	blk_finish_plug(&plug);
 
-out:
 	if (write)
 		mmap_write_unlock(mm);
 	else

mm/mseal.c

@@ -75,23 +75,14 @@ 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.
+ * Check if a vma is allowed to be modified by madvise.
- * the memory ranger can have a gap (unallocated memory).
- * return true, if it is allowed.
  */
-bool can_modify_mm_madv(struct mm_struct *mm, unsigned long start, unsigned long end,
+bool can_modify_vma_madv(struct vm_area_struct *vma, int behavior)
-		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. */
+	if (unlikely(!can_modify_vma(vma) && is_ro_anon(vma)))
-	for_each_vma_range(vmi, vma, end)
-		if (unlikely(is_ro_anon(vma) && !can_modify_vma(vma)))
 		return false;
 
 	/* Allow by default. */

mm/vma.h

@@ -380,6 +380,8 @@ 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 bool can_modify_vma(struct vm_area_struct *vma)
@@ -387,6 +389,11 @@ 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_VMA_H */