[PATCH v1 1/2] mseal: Two fixes for madvise(MADV_DONTNEED) when sealed

[jeffxu]

From: Jeff Xu <jeffxu@xxxxxxxxxxxx>

Two fixes for madvise(MADV_DONTNEED) when sealed.

For PROT_NONE mappings, the previous blocking of
madvise(MADV_DONTNEED) is unnecessary. As PROT_NONE already prohibits
memory access, madvise(MADV_DONTNEED) should be allowed to proceed in
order to free the page.

For file-backed, private, read-only memory mappings, we previously did
not block the madvise(MADV_DONTNEED). This was based on
the assumption that the memory's content, being file-backed, could be
retrieved from the file if accessed again. However, this assumption
failed to consider scenarios where a mapping is initially created as
read-write, modified, and subsequently changed to read-only. The newly
introduced VM_WASWRITE flag addresses this oversight.

Reported-by: Pedro Falcato <pedro.falcato@xxxxxxxxx>
Link:https://lore.kernel.org/all/CABi2SkW2XzuZ2-TunWOVzTEX1qc29LhjfNQ3hD4Nym8U-_f+ug@xxxxxxxxxxxxxx/
Fixes: 8be7258aad44 ("mseal: add mseal syscall")
Cc: <stable@xxxxxxxxxxxxxxx> # 6.11.y: 4d1b3416659b: mm: move can_modify_vma to mm/vma.h
Cc: <stable@xxxxxxxxxxxxxxx> # 6.11.y: 4a2dd02b0916: mm/mprotect: replace can_modify_mm with can_modify_vma
Cc: <stable@xxxxxxxxxxxxxxx> # 6.11.y: 23c57d1fa2b9: mseal: replace can_modify_mm_madv with a vma variant
Cc: <stable@xxxxxxxxxxxxxxx> # 6.11.y
Signed-off-by: Jeff Xu <jeffxu@xxxxxxxxxxxx>
---
 include/linux/mm.h |  2 ++
 mm/mprotect.c      |  3 +++
 mm/mseal.c         | 42 ++++++++++++++++++++++++++++++++++++------
 3 files changed, 41 insertions(+), 6 deletions(-)

diff --git a/include/linux/mm.h b/include/linux/mm.h
index 4c32003c8404..b402eca2565a 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -430,6 +430,8 @@ extern unsigned int kobjsize(const void *objp);
 #ifdef CONFIG_64BIT
 /* VM is sealed, in vm_flags */
 #define VM_SEALED	_BITUL(63)
+/* VM was writable */
+#define VM_WASWRITE	_BITUL(62)
 #endif
 
 /* Bits set in the VMA until the stack is in its final location */
diff --git a/mm/mprotect.c b/mm/mprotect.c
index 0c5d6d06107d..6397135ca526 100644
--- a/mm/mprotect.c
+++ b/mm/mprotect.c
@@ -821,6 +821,9 @@ static int do_mprotect_pkey(unsigned long start, size_t len,
 			break;
 		}
 
+		if ((vma->vm_flags & VM_WRITE) && !(newflags & VM_WRITE))
+			newflags |= VM_WASWRITE;
+
 		error = security_file_mprotect(vma, reqprot, prot);
 		if (error)
 			break;
diff --git a/mm/mseal.c b/mm/mseal.c
index ece977bd21e1..28f28487be17 100644
--- a/mm/mseal.c
+++ b/mm/mseal.c
@@ -36,12 +36,8 @@ static bool is_madv_discard(int behavior)
 	return false;
 }
 
-static bool is_ro_anon(struct vm_area_struct *vma)
+static bool anon_is_ro(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.
@@ -53,6 +49,22 @@ static bool is_ro_anon(struct vm_area_struct *vma)
 	return false;
 }
 
+static bool vma_is_prot_none(struct vm_area_struct *vma)
+{
+	if ((vma->vm_flags & VM_ACCESS_FLAGS) == VM_NONE)
+		return true;
+
+	return false;
+}
+
+static bool vma_was_writable_turn_readonly(struct vm_area_struct *vma)
+{
+	if (!(vma->vm_flags & VM_WRITE) && vma->vm_flags & VM_WASWRITE)
+		return true;
+
+	return false;
+}
+
 /*
  * Check if a vma is allowed to be modified by madvise.
  */
@@ -61,7 +73,25 @@ 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)))
+	/* not sealed */
+	if (likely(can_modify_vma(vma)))
+		return true;
+
+	/* PROT_NONE mapping */
+	if (vma_is_prot_none(vma))
+		return true;
+
+	/* file-backed private mapping */
+	if (vma->vm_file) {
+		/* read-only but was writeable */
+		if (vma_was_writable_turn_readonly(vma))
+			return false;
+
+		return true;
+	}
+
+	/* anonymous mapping is read-only */
+	if (anon_is_ro(vma))
 		return false;
 
 	/* Allow by default. */
-- 
2.47.0.rc1.288.g06298d1525-goog