On 13/02/2019 21:41, Evgenii Stepanov wrote:
On Wed, Feb 13, 2019 at 9:43 AM Dave Martin <Dave.Martin@xxxxxxx> wrote:
On Wed, Feb 13, 2019 at 04:42:11PM +0000, Kevin Brodsky wrote:
(+Cc other people with MTE experience: Branislav, Ruben)
[...]
I'm wondering whether we can piggy-back on existing concepts.
We could say that recolouring memory is safe when and only when
unmapping of the page or removing permissions on the page (via
munmap/mremap/mprotect) would be safe. Otherwise, the resulting
behaviour of the process is undefined.
Is that a sufficient requirement? I don't think that anything prevents you
from using mprotect() on say [vvar], but we don't necessarily want to map
[vvar] as tagged. I'm not sure it's easy to define what "safe" would mean
here.
I think the origin rules have to apply too: [vvar] is not a regular,
private page but a weird, shared thing mapped for you by the kernel.
Presumably userspace _cannot_ do mprotect(PROT_WRITE) on it.
I'm also assuming that userspace cannot recolour memory in read-only
pages. That sounds bad if there's no way to prevent it.
That sounds like something we would like to do to catch out of bounds
read of .rodata globals.
Another potentially interesting use case for MTE is infinite hardware
watchpoints - that would require trapping reads for individual tagging
granules, include those in read-only binary segment.
I think we should keep this discussion for a later, separate thread. Vincenzo's
proposal is about allowing userspace to pass tags at the syscall interface. The set
of mappings allowed to be tagged by userspace (in MTE) should be contained in the set
of mappings that userspace can pass tagged pointers to (at the syscall interface),
but they are not necessarily the same. Private read-only mappings are an edge case
(you can pass tagged pointers to them, the memory may or may not be mapped as tagged,
but in any case it is not possible to change the memory tags via such mapping).
[...]
It might be reasonable to do the check in access_ok() and skip it in
__put_user() etc.
(I seem to remember some separate discussion about abolishing
__put_user() and friends though, due to the accident risk they pose.)
Keep in mind that with MTE, there is no need to do any explicit check when
accessing user memory via a user-provided pointer. The tagged user pointer
is directly passed to copy_*_user() or put_user(). If the load/store causes
a tag fault, then it is handled just like a page fault (i.e. invoking the
fixup handler). As far as I can tell, there's no need to do anything special
in access_ok() in that case.
[The above applies to precise mode. In imprecise mode, some more work will
be needed after the load/store to check whether a tag fault happened.]
Fair enough, I'm a bit hazy on the details as of right now..
[...]
There are many possible ways to deploy MTE, and debugging is just one of
them. For instance, you may want to turn on heap colouring for some
processes in the system, including in production.
To implement enforceable protection, or as a diagnostic tool for when
something goes wrong?
In the latter case it's still OK for the kernel's tag checking not to be
exhaustive.
Regarding those cases where it is impossible to check tags at the point of
accessing user memory, it is indeed possible to check the memory tags at the
point of stripping the tag from the user pointer. Given that some MTE
use-cases favour performance over tag check coverage, the ideal approach
would be to make these checks configurable (e.g. check one granule, check
all of them, or check none). I don't know how feasible this is in practice.
Check all granules of a massive DMA buffer?
That doesn't sounds feasible without explicit support in the hardware to
have the DMA check tags itself as the memory is accessed. MTE by itself
doesn't provide for this IIUC (at least, it would require support in the
platform, not just the CPU).
We do not want to bake any assumptions into the ABI about whether a
given data transfer may or may not be offloaded to DMA. That feels
like a slippery slope.
Providing we get the checks for free in put_user/get_user/
copy_{to,from}_user(), those will cover a lot of cases though, for
non-bulk-IO cases.
My assumption has been that at this point in time we are mainly aiming
to support the debug/diagnostic use cases today.
MTE can be used both for diagnostics (imprecise mode is especially suitable for
that), and to halt execution when something wrong is detected. Even in the latter
case, one cannot expect exhaustive checking from MTE, because the way it works is
fundamentally statistical; an invalid pointer may by chance have the right tag to
access the given location. So again, I think that a best-effort approach is
appropriate when the kernel accesses user memory, in terms of checking that tags match.
More specifically, different use-cases come with different tradeoffs (performance /
tag check coverage). That's why I am suggesting that in the cases where tag checks
would need to be done _explicitly_ (before losing the user-provided tag), it would be
nice to be able to choose how much should be checked. I am not suggesting that always
checking all the granules by default is sane. Maybe checking just the first granule
is the right default.
I don't think we need to get to the bottom of this specific aspect at this point.
This ABI proposal is not about memory tagging, so there is no need to specify how or
when tag checking is done. As long as this ABI allows tagged pointers, pointing to
mappings that could be potentially tagged, to be passed to syscalls, I don't think
further relaxations are needed to enable memory tagging.
Kevin
At least, those are the low(ish)-hanging fruit.
Others are better placed than me to comment on the goals here.
Cheers
---Dave
