mm/mseal: update madvise() logic

The madvise() logic is inexplicably performed in mm/mseal.c - this ought
to be located in mm/madvise.c.

Additionally can_modify_vma_madv() is inconsistently named and, in
combination with is_ro_anon(), is very confusing logic.

Put a static function in mm/madvise.c instead - can_madvise_modify() -
that spells out exactly what's happening.  Also explicitly check for an
anon VMA.

Also add commentary to explain what's going on.

Essentially - we disallow discarding of data in mseal()'d mappings in
instances where the user couldn't otherwise write to that data.

We retain the existing behaviour here regarding MAP_PRIVATE mappings of
file-backed mappings, which entails some complexity - while this, strictly
speaking - appears to violate mseal() semantics, it may interact badly
with users which expect to be able to madvise(MADV_DONTNEED) .text
mappings for instance.

We may revisit this at a later date.

No functional change intended.

Link: https://lkml.kernel.org/r/492a98d9189646e92c8f23f4cce41ed323fe01df.1753431105.git.lorenzo.stoakes@oracle.com
Signed-off-by: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Reviewed-by: Liam R. Howlett <Liam.Howlett@oracle.com>
Reviewed-by: Pedro Falcato <pfalcato@suse.de>
Acked-by: David Hildenbrand <david@redhat.com>
Cc: Jann Horn <jannh@google.com>
Cc: Jeff Xu <jeffxu@chromium.org>
Cc: Kees Cook <kees@kernel.org>
Cc: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

1 files changed, 70 insertions, 1 deletions

diff --git a/mm/madvise.c b/mm/madvise.c
index bb80fc5ea08f..7f9af2dbd044 100644
--- a/mm/madvise.c
+++ b/mm/madvise.c
@@ -19,6 +19,7 @@
 #include <linux/sched.h>
 #include <linux/sched/mm.h>
 #include <linux/mm_inline.h>
+#include <linux/mmu_context.h>
 #include <linux/string.h>
 #include <linux/uio.h>
 #include <linux/ksm.h>
@@ -1256,6 +1257,74 @@ static long madvise_guard_remove(struct madvise_behavior *madv_behavior)
 			       &guard_remove_walk_ops, NULL);
 }
 
+#ifdef CONFIG_64BIT
+/* Does the madvise operation result in discarding of mapped data? */
+static bool is_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;
+}
+
+/*
+ * We are restricted from madvise()'ing mseal()'d VMAs only in very particular
+ * circumstances - discarding of data from read-only anonymous SEALED mappings.
+ *
+ * This is because users cannot trivally discard data from these VMAs, and may
+ * only do so via an appropriate madvise() call.
+ */
+static bool can_madvise_modify(struct madvise_behavior *madv_behavior)
+{
+	struct vm_area_struct *vma = madv_behavior->vma;
+
+	/* If the VMA isn't sealed we're good. */
+	if (can_modify_vma(vma))
+		return true;
+
+	/* For a sealed VMA, we only care about discard operations. */
+	if (!is_discard(madv_behavior->behavior))
+		return true;
+
+	/*
+	 * We explicitly permit all file-backed mappings, whether MAP_SHARED or
+	 * MAP_PRIVATE.
+	 *
+	 * The latter causes some complications. Because now, one can mmap()
+	 * read/write a MAP_PRIVATE mapping, write to it, then mprotect()
+	 * read-only, mseal() and a discard will be permitted.
+	 *
+	 * However, in order to avoid issues with potential use of madvise(...,
+	 * MADV_DONTNEED) of mseal()'d .text mappings we, for the time being,
+	 * permit this.
+	 */
+	if (!vma_is_anonymous(vma))
+		return true;
+
+	/* If the user could write to the mapping anyway, then this is fine. */
+	if ((vma->vm_flags & VM_WRITE) &&
+	    arch_vma_access_permitted(vma, /* write= */ true,
+			/* execute= */ false, /* foreign= */ false))
+		return true;
+
+	/* Otherwise, we are not permitted to perform this operation. */
+	return false;
+}
+#else
+static bool can_madvise_modify(struct madvise_behavior *madv_behavior)
+{
+	return true;
+}
+#endif
+
 /*
  * Apply an madvise behavior to a region of a vma.  madvise_update_vma
  * will handle splitting a vm area into separate areas, each area with its own
@@ -1269,7 +1338,7 @@ static int madvise_vma_behavior(struct madvise_behavior *madv_behavior)
 	struct madvise_behavior_range *range = &madv_behavior->range;
 	int error;
 
-	if (unlikely(!can_modify_vma_madv(madv_behavior->vma, behavior)))
+	if (unlikely(!can_madvise_modify(madv_behavior)))
 		return -EPERM;
 
 	switch (behavior) {