[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <5d932ec1f9d0ea115aac65067e4cb8241a06e791.1752497324.git.lorenzo.stoakes@oracle.com>
Date: Mon, 14 Jul 2025 14:00:37 +0100
From: Lorenzo Stoakes <lorenzo.stoakes@...cle.com>
To: Andrew Morton <akpm@...ux-foundation.org>
Cc: "Liam R . Howlett" <Liam.Howlett@...cle.com>,
David Hildenbrand <david@...hat.com>, Vlastimil Babka <vbabka@...e.cz>,
Jann Horn <jannh@...gle.com>, Pedro Falcato <pfalcato@...e.de>,
linux-mm@...ck.org, linux-kernel@...r.kernel.org,
Jeff Xu <jeffxu@...omium.org>
Subject: [PATCH 2/5] mm/mseal: move madvise() logic to mm/madvise.c
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.
Additionally add commentary to explain what's going on.
No functional change intended.
Signed-off-by: Lorenzo Stoakes <lorenzo.stoakes@...cle.com>
---
mm/madvise.c | 62 +++++++++++++++++++++++++++++++++++++++++++++++++++-
mm/mseal.c | 49 -----------------------------------------
mm/vma.h | 7 ------
3 files changed, 61 insertions(+), 57 deletions(-)
diff --git a/mm/madvise.c b/mm/madvise.c
index 9de9b7c797c6..75757ba418a8 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 +1257,65 @@ 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 operation won't discard, we're good. */
+ if (!is_discard(madv_behavior->behavior))
+ return true;
+
+ /* If the VMA isn't sealed we're also good. */
+ if (can_modify_vma(vma))
+ return true;
+
+ /* File-backed mappings don't lose data on discard. */
+ if (!vma_is_anonymous(vma))
+ return true;
+
+ /*
+ * If the VMA is writable and the architecture permits write access,
+ * then discarding is fine.
+ */
+ if ((vma->vm_flags & VM_WRITE) &&
+ arch_vma_access_permitted(vma, /* write= */ true,
+ /* execute= */ false, /* foreign= */ false))
+ return true;
+
+ 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 +1329,7 @@ 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) {
diff --git a/mm/mseal.c b/mm/mseal.c
index c27197ac04e8..1308e88ab184 100644
--- a/mm/mseal.c
+++ b/mm/mseal.c
@@ -11,7 +11,6 @@
#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"
@@ -21,54 +20,6 @@ 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.
- */
-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)
diff --git a/mm/vma.h b/mm/vma.h
index cf6e3a6371b6..6515045ba342 100644
--- a/mm/vma.h
+++ b/mm/vma.h
@@ -578,8 +578,6 @@ 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)
@@ -587,11 +585,6 @@ 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
#if defined(CONFIG_STACK_GROWSUP)
--
2.50.1
Powered by blists - more mailing lists