1 files changed, 44 insertions, 122 deletions

diff --git a/mm/mseal.c b/mm/mseal.c
index c27197ac04e8..e5b205562d2e 100644
--- a/mm/mseal.c
+++ b/mm/mseal.c
@@ -11,148 +11,74 @@
 #include <linux/mman.h>
 #include <linux/mm.h>
 #include <linux/mm_inline.h>
-#include <linux/mmu_context.h>
 #include <linux/syscalls.h>
 #include <linux/sched.h>
 #include "internal.h"
 
-static inline void set_vma_sealed(struct vm_area_struct *vma)
-{
-	vm_flags_set(vma, VM_SEALED);
-}
-
-static bool is_madv_discard(int behavior)
-{
-	switch (behavior) {
-	case MADV_FREE:
-	case MADV_DONTNEED:
-	case MADV_DONTNEED_LOCKED:
-	case MADV_REMOVE:
-	case MADV_DONTFORK:
-	case MADV_WIPEONFORK:
-	case MADV_GUARD_INSTALL:
-		return true;
-	}
-
-	return false;
-}
-
-static bool is_ro_anon(struct vm_area_struct *vma)
-{
-	/* check anonymous mapping. */
-	if (vma->vm_file || vma->vm_flags & VM_SHARED)
-		return false;
-
-	/*
-	 * check for non-writable:
-	 * PROT=RO or PKRU is not writeable.
-	 */
-	if (!(vma->vm_flags & VM_WRITE) ||
-		!arch_vma_access_permitted(vma, true, false, false))
-		return true;
-
-	return false;
-}
-
 /*
- * Check if a vma is allowed to be modified by madvise.
+ * mseal() disallows an input range which contain unmapped ranges (VMA holes).
+ *
+ * It disallows unmapped regions from start to end whether they exist at the
+ * start, in the middle, or at the end of the range, or any combination thereof.
+ *
+ * This is because after sealng a range, there's nothing to stop memory mapping
+ * of ranges in the remaining gaps later, meaning that the user might then
+ * wrongly consider the entirety of the mseal()'d range to be sealed when it
+ * in fact isn't.
  */
-bool can_modify_vma_madv(struct vm_area_struct *vma, int behavior)
-{
-	if (!is_madv_discard(behavior))
-		return true;
-
-	if (unlikely(!can_modify_vma(vma) && is_ro_anon(vma)))
-		return false;
-
-	/* Allow by default. */
-	return true;
-}
-
-static int mseal_fixup(struct vma_iterator *vmi, struct vm_area_struct *vma,
-		struct vm_area_struct **prev, unsigned long start,
-		unsigned long end, vm_flags_t newflags)
-{
-	int ret = 0;
-	vm_flags_t oldflags = vma->vm_flags;
-
-	if (newflags == oldflags)
-		goto out;
-
-	vma = vma_modify_flags(vmi, *prev, vma, start, end, newflags);
-	if (IS_ERR(vma)) {
-		ret = PTR_ERR(vma);
-		goto out;
-	}
-
-	set_vma_sealed(vma);
-out:
-	*prev = vma;
-	return ret;
-}
 
 /*
- * Check for do_mseal:
- * 1> start is part of a valid vma.
- * 2> end is part of a valid vma.
- * 3> No gap (unallocated address) between start and end.
- * 4> map is sealable.
+ * Does the [start, end) range contain any unmapped memory?
+ *
+ * We ensure that:
+ * - start is part of a valid VMA.
+ * - end is part of a valid VMA.
+ * - no gap (unallocated memory) exists between start and end.
  */
-static int check_mm_seal(unsigned long start, unsigned long end)
+static bool range_contains_unmapped(struct mm_struct *mm,
+		unsigned long start, unsigned long end)
 {
 	struct vm_area_struct *vma;
-	unsigned long nstart = start;
-
+	unsigned long prev_end = start;
 	VMA_ITERATOR(vmi, current->mm, start);
 
-	/* going through each vma to check. */
 	for_each_vma_range(vmi, vma, end) {
-		if (vma->vm_start > nstart)
-			/* unallocated memory found. */
-			return -ENOMEM;
-
-		if (vma->vm_end >= end)
-			return 0;
+		if (vma->vm_start > prev_end)
+			return true;
 
-		nstart = vma->vm_end;
+		prev_end = vma->vm_end;
 	}
 
-	return -ENOMEM;
+	return prev_end < end;
 }
 
-/*
- * Apply sealing.
- */
-static int apply_mm_seal(unsigned long start, unsigned long end)
+static int mseal_apply(struct mm_struct *mm,
+		unsigned long start, unsigned long end)
 {
-	unsigned long nstart;
 	struct vm_area_struct *vma, *prev;
+	unsigned long curr_start = start;
+	VMA_ITERATOR(vmi, mm, start);
 
-	VMA_ITERATOR(vmi, current->mm, start);
-
+	/* We know there are no gaps so this will be non-NULL. */
 	vma = vma_iter_load(&vmi);
-	/*
-	 * Note: check_mm_seal should already checked ENOMEM case.
-	 * so vma should not be null, same for the other ENOMEM cases.
-	 */
 	prev = vma_prev(&vmi);
 	if (start > vma->vm_start)
 		prev = vma;
 
-	nstart = start;
 	for_each_vma_range(vmi, vma, end) {
-		int error;
-		unsigned long tmp;
-		vm_flags_t newflags;
+		unsigned long curr_end = MIN(vma->vm_end, end);
 
-		newflags = vma->vm_flags | VM_SEALED;
-		tmp = vma->vm_end;
-		if (tmp > end)
-			tmp = end;
-		error = mseal_fixup(&vmi, vma, &prev, nstart, tmp, newflags);
-		if (error)
-			return error;
-		nstart = vma_iter_end(&vmi);
+		if (!(vma->vm_flags & VM_SEALED)) {
+			vma = vma_modify_flags(&vmi, prev, vma,
+					curr_start, curr_end,
+					vma->vm_flags | VM_SEALED);
+			if (IS_ERR(vma))
+				return PTR_ERR(vma);
+			vm_flags_set(vma, VM_SEALED);
+		}
+
+		prev = vma;
+		curr_start = curr_end;
 	}
 
 	return 0;
@@ -240,14 +166,10 @@ int do_mseal(unsigned long start, size_t len_in, unsigned long flags)
 	if (mmap_write_lock_killable(mm))
 		return -EINTR;
 
-	/*
-	 * First pass, this helps to avoid
-	 * partial sealing in case of error in input address range,
-	 * e.g. ENOMEM error.
-	 */
-	ret = check_mm_seal(start, end);
-	if (ret)
+	if (range_contains_unmapped(mm, start, end)) {
+		ret = -ENOMEM;
 		goto out;
+	}
 
 	/*
 	 * Second pass, this should success, unless there are errors
@@ -255,10 +177,10 @@ int do_mseal(unsigned long start, size_t len_in, unsigned long flags)
 	 * reaching the max supported VMAs, however, those cases shall
 	 * be rare.
 	 */
-	ret = apply_mm_seal(start, end);
+	ret = mseal_apply(mm, start, end);
 
 out:
-	mmap_write_unlock(current->mm);
+	mmap_write_unlock(mm);
 	return ret;
 }