[PATCH v2 2/3] mm/mseal: limit scope of mseal address zero to address zero

[Lorenzo Stoakes (ARM)]

Commit 44f65d900698 ("binfmt_elf: mseal address zero") unconditionally
provided do_mseal() to any internal kernel caller in order to address a
corner case slated for possible removal.

It also incorrectly attempts to mseal without checking to see whether the
mapping even succeeded.

Restrict the scope to the corner case by providing mseal_mmap_page_zero()
which asserts the MMAP_PAGE_ZERO personality.

Avoid unnecessary checks in the start, end range by abstracting the actual
mseal()'ing to mseal_range() and have mseal_mmap_page_zero() call that
instead.

Also only try to seal the VMA if we mapped the VMA. This isn't strictly
necessary as the operation would error out anyway, but it's useless work
and could be problematic if me make future changes to mseal semantics.

Acked-by: David Hildenbrand (Arm) <david@xxxxxxxxxx>
Signed-off-by: Lorenzo Stoakes (ARM) <ljs@xxxxxxxxxx>
---
 fs/binfmt_elf.c    |  7 ++-----
 include/linux/mm.h |  8 ++------
 mm/mseal.c         | 49 +++++++++++++++++++++++++++++++++++--------------
 3 files changed, 39 insertions(+), 25 deletions(-)

diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c
index 16a56b6b3f6c..e3131a311995 100644
--- a/fs/binfmt_elf.c
+++ b/fs/binfmt_elf.c
@@ -1353,11 +1353,8 @@ static int load_elf_binary(struct linux_binprm *bprm)
 		   emulate the SVr4 behavior. Sigh. */
 		error = vm_mmap(NULL, 0, PAGE_SIZE, PROT_READ | PROT_EXEC,
 				MAP_FIXED | MAP_PRIVATE, 0);
-
-		retval = do_mseal(0, PAGE_SIZE, 0);
-		if (retval)
-			pr_warn_ratelimited("pid=%d, couldn't seal address 0, ret=%d.\n",
-					    task_pid_nr(current), retval);
+		if (!error)
+			mseal_mmap_page_zero();
 	}
 
 	regs = current_pt_regs();
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 550fb92957d1..87feaa5a2b78 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -5291,13 +5291,9 @@ int reserve_mem_find_by_name(const char *name, phys_addr_t *start, phys_addr_t *
 int reserve_mem_release_by_name(const char *name);
 
 #ifdef CONFIG_64BIT
-int do_mseal(unsigned long start, size_t len_in, unsigned long flags);
+void mseal_mmap_page_zero(void);
 #else
-static inline int do_mseal(unsigned long start, size_t len_in, unsigned long flags)
-{
-	/* noop on 32 bit */
-	return 0;
-}
+static inline void mseal_mmap_page_zero(void) {}
 #endif
 
 /*
diff --git a/mm/mseal.c b/mm/mseal.c
index 430a252a6da4..2a516da694c6 100644
--- a/mm/mseal.c
+++ b/mm/mseal.c
@@ -32,7 +32,7 @@ static bool range_contains_unmapped(unsigned long start, unsigned long end)
 	return prev_end < end;
 }
 
-static int mseal_apply(unsigned long start, unsigned long end)
+static int __mseal_range(unsigned long start, unsigned long end)
 {
 	VMA_ITERATOR(vmi, current->mm, start);
 	struct vm_area_struct *vma, *prev;
@@ -66,6 +66,38 @@ static int mseal_apply(unsigned long start, unsigned long end)
 	return 0;
 }
 
+static int mseal_range(unsigned long start, unsigned long end)
+{
+	int err;
+
+	err = mmap_write_lock_killable(current->mm);
+	if (err)
+		return err;
+	if (range_contains_unmapped(start, end))
+		err = -ENOMEM;
+	else
+		err = __mseal_range(start, end);
+	mmap_write_unlock(current->mm);
+	return err;
+}
+
+/**
+ * mseal_mmap_page_zero() - If the MMAP_PAGE_ZERO personality is set, mseal()
+ * the page mapped at address zero.
+ */
+void mseal_mmap_page_zero(void)
+{
+	int err;
+
+	if (WARN_ON_ONCE(!(current->personality & MMAP_PAGE_ZERO)))
+		return;
+
+	err = mseal_range(0, PAGE_SIZE);
+	if (err)
+		pr_warn_ratelimited("pid=%d, couldn't seal address 0, ret=%d.\n",
+				    task_pid_nr(current), err);
+}
+
 /*
  * mseal(2) seals the VM's meta data from
  * selected syscalls.
@@ -118,11 +150,9 @@ static int mseal_apply(unsigned long start, unsigned long end)
  *
  *  unseal() is not supported.
  */
-int do_mseal(unsigned long start, size_t len_in, unsigned long flags)
+static int do_mseal(unsigned long start, size_t len_in, unsigned long flags)
 {
-	struct mm_struct *mm = current->mm;
 	unsigned long end;
-	int ret = 0;
 	size_t len;
 
 	/* Verify flags not set. */
@@ -145,16 +175,7 @@ int do_mseal(unsigned long start, size_t len_in, unsigned long flags)
 	if (end == start)
 		return 0;
 
-	if (mmap_write_lock_killable(mm))
-		return -EINTR;
-
-	if (range_contains_unmapped(start, end))
-		ret = -ENOMEM;
-	else
-		ret = mseal_apply(start, end);
-
-	mmap_write_unlock(mm);
-	return ret;
+	return mseal_range(start, end);
 }
 
 SYSCALL_DEFINE3(mseal, unsigned long, start, size_t, len, unsigned long,

-- 
2.55.0