Re: pkeys: Reserve PKEY_DISABLE_READ

[Florian Weimer <fweimer@redhat.com>]

* Ram Pai:

> On Thu, Nov 08, 2018 at 01:05:09PM +0100, Florian Weimer wrote:
>> Would it be possible to reserve a bit for PKEY_DISABLE_READ?
>> 
>> I think the POWER implementation can disable read access at the hardware
>> level, but not write access, and that cannot be expressed with the
>> current PKEY_DISABLE_ACCESS and PKEY_DISABLE_WRITE bits.
>
> POWER hardware can disable-read and can **also disable-write**
> at the hardware level. It can disable-execute aswell at the
> hardware level.   For example if the key bits for a given key in the AMR
> register is  
> 	0b01  it is read-disable
> 	0b10  it is write-disable
>
> To support access-disable, we make the key value 0b11.
>
> So in case if you want to know if the key is read-disable 'bitwise-and' it
> against 0x1.  i.e  (x & 0x1)

Not sure if we covered that alreay, but my problem is that I cannot
translate a 0b01 mask to a PKEY_DISABLE_* flag combination with the
current flags.  0b10 and 0b11 are fine.

POWER also loses the distinction between PKEY_DISABLE_ACCESS and
PKEY_DISABLE_ACCESS | PKEY_DISABLE_WRITE, but that's fine.  This breaks
the current glibc test case, but I have a patch for that.  Arguably, the
test is wrong or at least overly strict in what it accepts.

Thanks,
Florian