[v3,0/5] Use EFI variables for random seed

EFI has a rather unique benefit that it has access to some limited
non-volatile storage, where the kernel can store a random seed. This
series wires that up, with EFISTUB reading the seed and passing it to
the kernel, and with the kernel writing a new seed when the RNG is
initialized.

Patches 1 and 2 are to go through Ard's EFI tree, while patches 3, 4,
and 5 are to go through my RNG tree.

Jason A. Donenfeld (5):
  efi: vars: prohibit reading random seed variables
  efi: stub: use random seed from EFI variable
  random: add back async readiness notifier
  vsprintf: initialize siphash key using notifier
  efi: random: refresh non-volatile random seed when RNG is initialized

 drivers/char/random.c                 | 22 +++++++++++
 drivers/firmware/efi/efi.c            | 19 +++++++++
 drivers/firmware/efi/libstub/random.c | 55 +++++++++++++++++++++------
 fs/efivarfs/inode.c                   |  4 ++
 fs/efivarfs/super.c                   |  3 ++
 include/linux/random.h                |  1 +
 lib/vsprintf.c                        | 14 +++----
 7 files changed, 97 insertions(+), 21 deletions(-)

On Tue, Nov 22, 2022 at 03:04:00AM +0100, Jason A. Donenfeld wrote:
> In anticipation of putting random seeds in EFI variables, it's important
> that the random GUID namespace of variables remains hidden from
> userspace. We accomplish this by not populating efivarfs with entries
> from that GUID, as well as denying the creation of new ones in that
> GUID.

What's the concern here? Booting an older kernel would allow a malicious 
actor to either read the seed variable or set it to a value under their 
control, so we can't guarantee that the information is secret.

Hi,

On Sun, Nov 27, 2022 at 09:00:40PM +0000, Matthew Garrett wrote:
> On Tue, Nov 22, 2022 at 03:04:00AM +0100, Jason A. Donenfeld wrote:
> > In anticipation of putting random seeds in EFI variables, it's important
> > that the random GUID namespace of variables remains hidden from
> > userspace. We accomplish this by not populating efivarfs with entries
> > from that GUID, as well as denying the creation of new ones in that
> > GUID.
> 
> What's the concern here? Booting an older kernel would allow a malicious 
> actor to either read the seed variable or set it to a value under their 
> control, so we can't guarantee that the information is secret.

The security model is the same as that of random seed files, on, say,
BSD. If you remove the hard drive or change the operating system or what
have you, then sure, you can fiddle with the seed and read it. But the
running operating system shouldn't show it to you if it can help it.
Consider, for example, systemd's use of EFI variables for the
SystemToken. There, they have PID 1 take care of chmod'ing it before
other processes start.  But of course a different OS or even EFI shell
could just read it. So, think of this as just basic runtime safety --
like what people do when they set the umask before writing a random seed
file -- rather than some type of ultimate secrecy.

(And either way, the larger picture is that it's much more important to
get as much random data from as many sources as possible as soon as
possible, rather than being overly paranoid about every one single
source that we start excluding sources. A plethora of sources is better
off here.)

Jason