The patch titled
Subject: fs: clear file privilege bits when mmap writing
has been added to the -mm tree. Its filename is
fs-clear-file-privilege-bits-when-mmap-writing.patch
This patch should soon appear at
http://ozlabs.org/~akpm/mmots/broken-out/fs-clear-file-privilege-bits-when-mmap-writing.patch
and later at
http://ozlabs.org/~akpm/mmotm/broken-out/fs-clear-file-privilege-bits-when-mmap-writing.patch
Before you just go and hit "reply", please:
a) Consider who else should be cc'ed
b) Prefer to cc a suitable mailing list as well
c) Ideally: find the original patch on the mailing list and do a
reply-to-all to that, adding suitable additional cc's
*** Remember to use Documentation/SubmitChecklist when testing your code ***
The -mm tree is included into linux-next and is updated
there every 3-4 working days
------------------------------------------------------
From: Kees Cook <keescook@xxxxxxxxxxxx>
Subject: fs: clear file privilege bits when mmap writing
Normally, when a user can modify a file that has setuid or setgid bits,
those bits are cleared when they are not the file owner or a member of the
group. This is enforced when using write and truncate but not when
writing to a shared mmap on the file. This could allow the file writer to
gain privileges by changing a binary without losing the setuid/setgid/caps
bits.
Changing the bits requires holding inode->i_mutex, so it cannot be done
during the page fault (due to mmap_sem being held during the fault).
Instead, clear the bits if PROT_WRITE is being used at mmap open time.
But we can't do the check in the right place inside mmap, so we have to do
it before holding mmap_sem, which means duplicating some checks, which
have to be available to the non-MMU builds too.
Signed-off-by: Kees Cook <keescook@xxxxxxxxxxxx>
Cc: Jan Kara <jack@xxxxxxx>
Cc: Willy Tarreau <w@xxxxxx>
Cc: "Eric W. Biederman" <ebiederm@xxxxxxxxxxxx>
Cc: "Kirill A. Shutemov" <kirill.shutemov@xxxxxxxxxxxxxxx>
Cc: Oleg Nesterov <oleg@xxxxxxxxxx>
Cc: Rik van Riel <riel@xxxxxxxxxx>
Cc: Chen Gang <gang.chen.5i5j@xxxxxxxxx>
Cc: Davidlohr Bueso <dave@xxxxxxxxxxxx>
Cc: Andrea Arcangeli <aarcange@xxxxxxxxxx>
Cc: Alexander Viro <viro@xxxxxxxxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
include/linux/mm.h | 1
mm/mmap.c | 19 +++-------------
mm/util.c | 50 +++++++++++++++++++++++++++++++++++++++++++
3 files changed, 55 insertions(+), 15 deletions(-)
diff -puN include/linux/mm.h~fs-clear-file-privilege-bits-when-mmap-writing include/linux/mm.h
--- a/include/linux/mm.h~fs-clear-file-privilege-bits-when-mmap-writing
+++ a/include/linux/mm.h
@@ -1943,6 +1943,7 @@ extern unsigned long get_unmapped_area(s
extern unsigned long mmap_region(struct file *file, unsigned long addr,
unsigned long len, vm_flags_t vm_flags, unsigned long pgoff);
+extern int do_mmap_shared_checks(struct file *file, unsigned long prot);
extern unsigned long do_mmap(struct file *file, unsigned long addr,
unsigned long len, unsigned long prot, unsigned long flags,
vm_flags_t vm_flags, unsigned long pgoff, unsigned long *populate);
diff -puN mm/mmap.c~fs-clear-file-privilege-bits-when-mmap-writing mm/mmap.c
--- a/mm/mmap.c~fs-clear-file-privilege-bits-when-mmap-writing
+++ a/mm/mmap.c
@@ -1333,24 +1333,13 @@ unsigned long do_mmap(struct file *file,
if (file) {
struct inode *inode = file_inode(file);
+ int err;
switch (flags & MAP_TYPE) {
case MAP_SHARED:
- if ((prot&PROT_WRITE) && !(file->f_mode&FMODE_WRITE))
- return -EACCES;
-
- /*
- * Make sure we don't allow writing to an append-only
- * file..
- */
- if (IS_APPEND(inode) && (file->f_mode & FMODE_WRITE))
- return -EACCES;
-
- /*
- * Make sure there are no mandatory locks on the file.
- */
- if (locks_verify_locked(file))
- return -EAGAIN;
+ err = do_mmap_shared_checks(file, prot);
+ if (err)
+ return err;
vm_flags |= VM_SHARED | VM_MAYSHARE;
if (!(file->f_mode & FMODE_WRITE))
diff -puN mm/util.c~fs-clear-file-privilege-bits-when-mmap-writing mm/util.c
--- a/mm/util.c~fs-clear-file-privilege-bits-when-mmap-writing
+++ a/mm/util.c
@@ -283,6 +283,29 @@ int __weak get_user_pages_fast(unsigned
}
EXPORT_SYMBOL_GPL(get_user_pages_fast);
+int do_mmap_shared_checks(struct file *file, unsigned long prot)
+{
+ struct inode *inode = file_inode(file);
+
+ if ((prot & PROT_WRITE) && !(file->f_mode & FMODE_WRITE))
+ return -EACCES;
+
+ /*
+ * Make sure we don't allow writing to an append-only
+ * file..
+ */
+ if (IS_APPEND(inode) && (file->f_mode & FMODE_WRITE))
+ return -EACCES;
+
+ /*
+ * Make sure there are no mandatory locks on the file.
+ */
+ if (locks_verify_locked(file))
+ return -EAGAIN;
+
+ return 0;
+}
+
unsigned long vm_mmap_pgoff(struct file *file, unsigned long addr,
unsigned long len, unsigned long prot,
unsigned long flag, unsigned long pgoff)
@@ -291,6 +314,33 @@ unsigned long vm_mmap_pgoff(struct file
struct mm_struct *mm = current->mm;
unsigned long populate;
+ /*
+ * If we must remove privs, we do it here since doing it during
+ * page fault may be expensive and cannot hold inode->i_mutex,
+ * since mm->mmap_sem is already held.
+ */
+ if (file && (flag & MAP_TYPE) == MAP_SHARED && (prot & PROT_WRITE)) {
+ struct inode *inode = file_inode(file);
+ int err;
+
+ if (!IS_NOSEC(inode)) {
+ /*
+ * Make sure we can't strip privs from a file that
+ * wouldn't otherwise be allowed to be mmapped.
+ */
+ err = do_mmap_shared_checks(file, prot);
+ if (err)
+ return err;
+
+ mutex_lock(&inode->i_mutex);
+ err = file_remove_privs(file);
+ mutex_unlock(&inode->i_mutex);
+
+ if (err)
+ return err;
+ }
+ }
+
ret = security_mmap_file(file, prot, flag);
if (!ret) {
down_write(&mm->mmap_sem);
_
Patches currently in -mm which might be from keescook@xxxxxxxxxxxx are
fs-clear-file-privilege-bits-when-mmap-writing.patch
sysctl-enable-strict-writes.patch
--
To unsubscribe from this list: send the line "unsubscribe mm-commits" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
