alistair23-linux/include/linux/userfaultfd_k.h
Peter Xu cefdca0a86 userfaultfd/sysctl: add vm.unprivileged_userfaultfd
Userfaultfd can be misued to make it easier to exploit existing
use-after-free (and similar) bugs that might otherwise only make a
short window or race condition available.  By using userfaultfd to
stall a kernel thread, a malicious program can keep some state that it
wrote, stable for an extended period, which it can then access using an
existing exploit.  While it doesn't cause the exploit itself, and while
it's not the only thing that can stall a kernel thread when accessing a
memory location, it's one of the few that never needs privilege.

We can add a flag, allowing userfaultfd to be restricted, so that in
general it won't be useable by arbitrary user programs, but in
environments that require userfaultfd it can be turned back on.

Add a global sysctl knob "vm.unprivileged_userfaultfd" to control
whether userfaultfd is allowed by unprivileged users.  When this is
set to zero, only privileged users (root user, or users with the
CAP_SYS_PTRACE capability) will be able to use the userfaultfd
syscalls.

Andrea said:

: The only difference between the bpf sysctl and the userfaultfd sysctl
: this way is that the bpf sysctl adds the CAP_SYS_ADMIN capability
: requirement, while userfaultfd adds the CAP_SYS_PTRACE requirement,
: because the userfaultfd monitor is more likely to need CAP_SYS_PTRACE
: already if it's doing other kind of tracking on processes runtime, in
: addition of userfaultfd.  In other words both syscalls works only for
: root, when the two sysctl are opt-in set to 1.

[dgilbert@redhat.com: changelog additions]
[akpm@linux-foundation.org: documentation tweak, per Mike]
Link: http://lkml.kernel.org/r/20190319030722.12441-2-peterx@redhat.com
Signed-off-by: Peter Xu <peterx@redhat.com>
Suggested-by: Andrea Arcangeli <aarcange@redhat.com>
Suggested-by: Mike Rapoport <rppt@linux.ibm.com>
Reviewed-by: Mike Rapoport <rppt@linux.ibm.com>
Reviewed-by: Andrea Arcangeli <aarcange@redhat.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Luis Chamberlain <mcgrof@kernel.org>
Cc: Maxime Coquelin <maxime.coquelin@redhat.com>
Cc: Maya Gokhale <gokhale2@llnl.gov>
Cc: Jerome Glisse <jglisse@redhat.com>
Cc: Pavel Emelyanov <xemul@virtuozzo.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Martin Cracauer <cracauer@cons.org>
Cc: Denis Plotnikov <dplotnikov@virtuozzo.com>
Cc: Marty McFadden <mcfadden8@llnl.gov>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Kees Cook <keescook@chromium.org>
Cc: Mel Gorman <mgorman@suse.de>
Cc: "Kirill A . Shutemov" <kirill@shutemov.name>
Cc: "Dr . David Alan Gilbert" <dgilbert@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-05-14 09:47:45 -07:00

148 lines
3.7 KiB
C

/* SPDX-License-Identifier: GPL-2.0 */
/*
* include/linux/userfaultfd_k.h
*
* Copyright (C) 2015 Red Hat, Inc.
*
*/
#ifndef _LINUX_USERFAULTFD_K_H
#define _LINUX_USERFAULTFD_K_H
#ifdef CONFIG_USERFAULTFD
#include <linux/userfaultfd.h> /* linux/include/uapi/linux/userfaultfd.h */
#include <linux/fcntl.h>
/*
* CAREFUL: Check include/uapi/asm-generic/fcntl.h when defining
* new flags, since they might collide with O_* ones. We want
* to re-use O_* flags that couldn't possibly have a meaning
* from userfaultfd, in order to leave a free define-space for
* shared O_* flags.
*/
#define UFFD_CLOEXEC O_CLOEXEC
#define UFFD_NONBLOCK O_NONBLOCK
#define UFFD_SHARED_FCNTL_FLAGS (O_CLOEXEC | O_NONBLOCK)
#define UFFD_FLAGS_SET (EFD_SHARED_FCNTL_FLAGS)
extern int sysctl_unprivileged_userfaultfd;
extern vm_fault_t handle_userfault(struct vm_fault *vmf, unsigned long reason);
extern ssize_t mcopy_atomic(struct mm_struct *dst_mm, unsigned long dst_start,
unsigned long src_start, unsigned long len,
bool *mmap_changing);
extern ssize_t mfill_zeropage(struct mm_struct *dst_mm,
unsigned long dst_start,
unsigned long len,
bool *mmap_changing);
/* mm helpers */
static inline bool is_mergeable_vm_userfaultfd_ctx(struct vm_area_struct *vma,
struct vm_userfaultfd_ctx vm_ctx)
{
return vma->vm_userfaultfd_ctx.ctx == vm_ctx.ctx;
}
static inline bool userfaultfd_missing(struct vm_area_struct *vma)
{
return vma->vm_flags & VM_UFFD_MISSING;
}
static inline bool userfaultfd_armed(struct vm_area_struct *vma)
{
return vma->vm_flags & (VM_UFFD_MISSING | VM_UFFD_WP);
}
extern int dup_userfaultfd(struct vm_area_struct *, struct list_head *);
extern void dup_userfaultfd_complete(struct list_head *);
extern void mremap_userfaultfd_prep(struct vm_area_struct *,
struct vm_userfaultfd_ctx *);
extern void mremap_userfaultfd_complete(struct vm_userfaultfd_ctx *,
unsigned long from, unsigned long to,
unsigned long len);
extern bool userfaultfd_remove(struct vm_area_struct *vma,
unsigned long start,
unsigned long end);
extern int userfaultfd_unmap_prep(struct vm_area_struct *vma,
unsigned long start, unsigned long end,
struct list_head *uf);
extern void userfaultfd_unmap_complete(struct mm_struct *mm,
struct list_head *uf);
#else /* CONFIG_USERFAULTFD */
/* mm helpers */
static inline vm_fault_t handle_userfault(struct vm_fault *vmf,
unsigned long reason)
{
return VM_FAULT_SIGBUS;
}
static inline bool is_mergeable_vm_userfaultfd_ctx(struct vm_area_struct *vma,
struct vm_userfaultfd_ctx vm_ctx)
{
return true;
}
static inline bool userfaultfd_missing(struct vm_area_struct *vma)
{
return false;
}
static inline bool userfaultfd_armed(struct vm_area_struct *vma)
{
return false;
}
static inline int dup_userfaultfd(struct vm_area_struct *vma,
struct list_head *l)
{
return 0;
}
static inline void dup_userfaultfd_complete(struct list_head *l)
{
}
static inline void mremap_userfaultfd_prep(struct vm_area_struct *vma,
struct vm_userfaultfd_ctx *ctx)
{
}
static inline void mremap_userfaultfd_complete(struct vm_userfaultfd_ctx *ctx,
unsigned long from,
unsigned long to,
unsigned long len)
{
}
static inline bool userfaultfd_remove(struct vm_area_struct *vma,
unsigned long start,
unsigned long end)
{
return true;
}
static inline int userfaultfd_unmap_prep(struct vm_area_struct *vma,
unsigned long start, unsigned long end,
struct list_head *uf)
{
return 0;
}
static inline void userfaultfd_unmap_complete(struct mm_struct *mm,
struct list_head *uf)
{
}
#endif /* CONFIG_USERFAULTFD */
#endif /* _LINUX_USERFAULTFD_K_H */