On Wed, Oct 26, 2022 at 04:04:56PM +0100, Joey Gouly wrote:
> The aim of such policy is to prevent a user task from creating an
> executable mapping that is also writeable.
>
> An example of mmap() returning -EACCESS if the policy is enabled:
>
> mmap(0, size, PROT_READ | PROT_WRITE | PROT_EXEC, flags, 0, 0);
>
> Similarly, mprotect() would return -EACCESS below:
>
> addr = mmap(0, size, PROT_READ | PROT_EXEC, flags, 0, 0);
> mprotect(addr, size, PROT_READ | PROT_WRITE | PROT_EXEC);
>
> The BPF filter that systemd MDWE uses is stateless, and disallows
> mprotect() with PROT_EXEC completely. This new prctl allows PROT_EXEC to
> be enabled if it was already PROT_EXEC, which allows the following case:
>
> addr = mmap(0, size, PROT_READ | PROT_EXEC, flags, 0, 0);
> mprotect(addr, size, PROT_READ | PROT_EXEC | PROT_BTI);
>
> where PROT_BTI enables branch tracking identification on arm64.
>
> Signed-off-by: Joey Gouly <joey.gouly@xxxxxxx>
> Co-developed-by: Catalin Marinas <catalin.marinas@xxxxxxx>
> Signed-off-by: Catalin Marinas <catalin.marinas@xxxxxxx>
> Cc: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
> ---
> include/linux/mman.h | 15 +++++++++++++++
> include/linux/sched/coredump.h | 6 +++++-
> include/uapi/linux/prctl.h | 6 ++++++
> kernel/sys.c | 18 ++++++++++++++++++
> mm/mmap.c | 3 +++
> mm/mprotect.c | 5 +++++
> 6 files changed, 52 insertions(+), 1 deletion(-)
>
> diff --git a/include/linux/mman.h b/include/linux/mman.h
> index 58b3abd457a3..d84fdeab6b5e 100644
> --- a/include/linux/mman.h
> +++ b/include/linux/mman.h
> @@ -156,4 +156,19 @@ calc_vm_flag_bits(unsigned long flags)
> }
>
> unsigned long vm_commit_limit(void);
> +
> +static inline bool map_deny_write_exec(struct vm_area_struct *vma, unsigned long vm_flags)
Traditionally, it is easier to write these in the positive instead of
needing to parse a double-negative.
static inline bool allow_write_exec(...)
> +{
> + if (!test_bit(MMF_HAS_MDWE, ¤t->mm->flags))
> + return false;
> +
> + if ((vm_flags & VM_EXEC) && (vm_flags & VM_WRITE))
> + return true;
> +
> + if (vma && !(vma->vm_flags & VM_EXEC) && (vm_flags & VM_EXEC))
> + return true;
> +
> + return false;
> +}
Since this is implementation "2" from the earlier discussion[1], I think
some comments in here are good to have. (e.g. to explain to people
reading this code why there is a vma test, etc.) Perhaps even explicit
repeat the implementation expectations.
Restating from that thread:
2. "is not already PROT_EXEC":
a) mmap(PROT_READ|PROT_WRITE|PROT_EXEC); // fails
b) mmap(PROT_READ|PROT_EXEC);
mprotect(PROT_READ|PROT_EXEC|PROT_BTI); // passes
c) mmap(PROT_READ);
mprotect(PROT_READ|PROT_EXEC); // fails
d) mmap(PROT_READ|PROT_WRITE);
mprotect(PROT_READ);
mprotect(PROT_READ|PROT_EXEC); // fails
[1] https://lore.kernel.org/linux-arm-kernel/YmGjYYlcSVz38rOe@xxxxxxx/
> #endif /* _LINUX_MMAN_H */
> diff --git a/include/linux/sched/coredump.h b/include/linux/sched/coredump.h
> index 8270ad7ae14c..0e17ae7fbfd3 100644
> --- a/include/linux/sched/coredump.h
> +++ b/include/linux/sched/coredump.h
> @@ -81,9 +81,13 @@ static inline int get_dumpable(struct mm_struct *mm)
> * lifecycle of this mm, just for simplicity.
> */
> #define MMF_HAS_PINNED 27 /* FOLL_PIN has run, never cleared */
> +
> +#define MMF_HAS_MDWE 28
> +#define MMF_HAS_MDWE_MASK (1 << MMF_HAS_MDWE)
> +
> #define MMF_DISABLE_THP_MASK (1 << MMF_DISABLE_THP)
>
> #define MMF_INIT_MASK (MMF_DUMPABLE_MASK | MMF_DUMP_FILTER_MASK |\
> - MMF_DISABLE_THP_MASK)
> + MMF_DISABLE_THP_MASK | MMF_HAS_MDWE_MASK)
Good, yes, new "live forever" bit here. Perhaps bikeshedding over the
name, see below.
>
> #endif /* _LINUX_SCHED_COREDUMP_H */
> diff --git a/include/uapi/linux/prctl.h b/include/uapi/linux/prctl.h
> index a5e06dcbba13..ab9db1e86230 100644
> --- a/include/uapi/linux/prctl.h
> +++ b/include/uapi/linux/prctl.h
> @@ -281,6 +281,12 @@ struct prctl_mm_map {
> # define PR_SME_VL_LEN_MASK 0xffff
> # define PR_SME_VL_INHERIT (1 << 17) /* inherit across exec */
>
> +/* Memory deny write / execute */
> +#define PR_SET_MDWE 65
> +# define PR_MDWE_FLAG_MMAP 1
> +
> +#define PR_GET_MDWE 66
> +
> #define PR_SET_VMA 0x53564d41
> # define PR_SET_VMA_ANON_NAME 0
>
> diff --git a/kernel/sys.c b/kernel/sys.c
> index 5fd54bf0e886..08e1dd6d2533 100644
> --- a/kernel/sys.c
> +++ b/kernel/sys.c
> @@ -2348,6 +2348,18 @@ static int prctl_set_vma(unsigned long opt, unsigned long start,
> }
> #endif /* CONFIG_ANON_VMA_NAME */
>
> +static inline int prctl_set_mdwe(void)
> +{
> + set_bit(MMF_HAS_MDWE, ¤t->mm->flags);
> +
> + return 0;
> +}
> +
> +static inline int prctl_get_mdwe(void)
> +{
> + return test_bit(MMF_HAS_MDWE, ¤t->mm->flags);
> +}
These will need to change -- the aren't constructed for future expansion
at all. At the very least, all the arguments need to passed to be
checked that they are zero. e.g.:
int prctl_set_mdwe(unsigned long bits, unsigned long arg3,
unsigned long arg4, unsigned long arg5)
{
if (arg3 || arg4 || arg5)
return -EINVAL;
...
return 0;
}
Otherwise, there's no way to add arguments in the future because old
userspace may have been sending arbitrary junk on the stack, etc.
And regardless, I think we'll need some explicit flag bits here, since
we can see there has been a long history of various other desired
features that may end up living in here. For now, a single bit is fine.
The intended behavior is the inability to _add_ PROT_EXEC to an existing
vma, and to deny the creating of a W+X vma to begin with, so perhaps
this bit can be named MDWE_FLAG_REFUSE_EXEC_GAIN?
Then the above "..." becomes:
if (bits & ~(MDWE_FLAG_REFUSE_EXEC_GAIN))
return -EINVAL;
if (bits & MDWE_FLAG_REFUSE_EXEC_GAIN)
set_bit(MMF_HAS_MDWE, ¤t->mm->flags);
else if (test_bit(MMF_HAS_MDWE, ¤t->mm->flags))
return -EPERM; /* Cannot unset the flag */
And prctl_get_mdwe() becomes:
int prctl_get_mdwe(unsigned long arg2, unsigned long arg3,
unsigned long arg4, unsigned long arg5)
{
if (arg2 || arg3 || arg4 || arg5)
return -EINVAL;
return test_bit(MMF_HAS_MDWE, ¤t->mm->flags) ?
MDWE_FLAG_REFUSE_EXEC_GAIN : 0;
}
> +
> SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3,
> unsigned long, arg4, unsigned long, arg5)
> {
> @@ -2623,6 +2635,12 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3,
> error = sched_core_share_pid(arg2, arg3, arg4, arg5);
> break;
> #endif
> + case PR_SET_MDWE:
> + error = prctl_set_mdwe();
> + break;
> + case PR_GET_MDWE:
> + error = prctl_get_mdwe();
> + break;
> case PR_SET_VMA:
> error = prctl_set_vma(arg2, arg3, arg4, arg5);
> break;
> diff --git a/mm/mmap.c b/mm/mmap.c
> index 099468aee4d8..42eaf6683216 100644
> --- a/mm/mmap.c
> +++ b/mm/mmap.c
> @@ -1409,6 +1409,9 @@ unsigned long do_mmap(struct file *file, unsigned long addr,
> vm_flags |= VM_NORESERVE;
> }
>
> + if (map_deny_write_exec(NULL, vm_flags))
> + return -EACCES;
> +
This seems like the wrong place to do the check -- that the vma argument
is a hard-coded "NULL" is evidence that something is wrong. Shouldn't
it live in mmap_region()? What happens with MAP_FIXED, when there is
an underlying vma? i.e. an MAP_FIXED will, I think, bypass the intended
check. For example, we had "c" above:
c) mmap(PROT_READ);
mprotect(PROT_READ|PROT_EXEC); // fails
But this would allow another case:
e) addr = mmap(..., PROT_READ, ...);
mmap(addr, ..., PROT_READ | PROT_EXEC, MAP_FIXED, ...); // passes
> addr = mmap_region(file, addr, len, vm_flags, pgoff, uf);
> if (!IS_ERR_VALUE(addr) &&
> ((vm_flags & VM_LOCKED) ||
> diff --git a/mm/mprotect.c b/mm/mprotect.c
> index 8d770855b591..af71ef0788fd 100644
> --- a/mm/mprotect.c
> +++ b/mm/mprotect.c
> @@ -766,6 +766,11 @@ static int do_mprotect_pkey(unsigned long start, size_t len,
> break;
> }
>
> + if (map_deny_write_exec(vma, newflags)) {
> + error = -EACCES;
> + goto out;
> + }
> +
This looks like the right place. Any rationale for why it's before
arch_validate_flags()?
> /* Allow architectures to sanity-check the new flags */
> if (!arch_validate_flags(newflags)) {
> error = -EINVAL;
-Kees
--
Kees Cook
