Re: [PATCH] x86/mm: Decouple dynamic __PHYSICAL_MASK from AMD SME

2018-04-20 Thread Kirill A. Shutemov
On Tue, Apr 10, 2018 at 09:33:39AM +, Kirill A. Shutemov wrote: > AMD SME claims one bit from physical address to indicate whether the > page is encrypted or not. To achieve that we clear out the bit from > __PHYSICAL_MASK. > > The capability to adjust __PHYSICAL_MASK is required beyond AMD SM

[PATCH] x86/mm: Decouple dynamic __PHYSICAL_MASK from AMD SME

2018-04-10 Thread Kirill A. Shutemov
AMD SME claims one bit from physical address to indicate whether the page is encrypted or not. To achieve that we clear out the bit from __PHYSICAL_MASK. The capability to adjust __PHYSICAL_MASK is required beyond AMD SME. For instance for upcoming Intel Multi-Key Total Memory Encryption. Factor

Re: [PATCH] x86/mm: Decouple dynamic __PHYSICAL_MASK from AMD SME

2018-02-14 Thread Kirill A. Shutemov
On Wed, Feb 14, 2018 at 09:09:05AM -0600, Tom Lendacky wrote: > On 2/14/2018 3:02 AM, Kirill A. Shutemov wrote: > > On Wed, Feb 14, 2018 at 08:30:20PM +1300, Kai Huang wrote: > >> On Tue, 2018-02-13 at 22:57 -0600, Tom Lendacky wrote: > >>> On 2/13/2018 10:21 PM, Kirill A. Shutemov wrote: > On

Re: [PATCH] x86/mm: Decouple dynamic __PHYSICAL_MASK from AMD SME

2018-02-14 Thread Tom Lendacky
On 2/14/2018 3:02 AM, Kirill A. Shutemov wrote: > On Wed, Feb 14, 2018 at 08:30:20PM +1300, Kai Huang wrote: >> On Tue, 2018-02-13 at 22:57 -0600, Tom Lendacky wrote: >>> On 2/13/2018 10:21 PM, Kirill A. Shutemov wrote: On Tue, Feb 13, 2018 at 10:10:22PM -0600, Tom Lendacky wrote: > On 2/8

Re: [PATCH] x86/mm: Decouple dynamic __PHYSICAL_MASK from AMD SME

2018-02-14 Thread Tom Lendacky
On 2/14/2018 1:30 AM, Kai Huang wrote: > On Tue, 2018-02-13 at 22:57 -0600, Tom Lendacky wrote: >> On 2/13/2018 10:21 PM, Kirill A. Shutemov wrote: >>> On Tue, Feb 13, 2018 at 10:10:22PM -0600, Tom Lendacky wrote: On 2/8/2018 6:55 AM, Kirill A. Shutemov wrote: > AMD SME claims one bit from

Re: [PATCH] x86/mm: Decouple dynamic __PHYSICAL_MASK from AMD SME

2018-02-14 Thread Kirill A. Shutemov
On Wed, Feb 14, 2018 at 08:30:20PM +1300, Kai Huang wrote: > On Tue, 2018-02-13 at 22:57 -0600, Tom Lendacky wrote: > > On 2/13/2018 10:21 PM, Kirill A. Shutemov wrote: > > > On Tue, Feb 13, 2018 at 10:10:22PM -0600, Tom Lendacky wrote: > > > > On 2/8/2018 6:55 AM, Kirill A. Shutemov wrote: > > > >

Re: [PATCH] x86/mm: Decouple dynamic __PHYSICAL_MASK from AMD SME

2018-02-13 Thread Kai Huang
On Tue, 2018-02-13 at 22:57 -0600, Tom Lendacky wrote: > On 2/13/2018 10:21 PM, Kirill A. Shutemov wrote: > > On Tue, Feb 13, 2018 at 10:10:22PM -0600, Tom Lendacky wrote: > > > On 2/8/2018 6:55 AM, Kirill A. Shutemov wrote: > > > > AMD SME claims one bit from physical address to indicate > > > > w

Re: [PATCH] x86/mm: Decouple dynamic __PHYSICAL_MASK from AMD SME

2018-02-13 Thread Tom Lendacky
On 2/13/2018 10:21 PM, Kirill A. Shutemov wrote: > On Tue, Feb 13, 2018 at 10:10:22PM -0600, Tom Lendacky wrote: >> On 2/8/2018 6:55 AM, Kirill A. Shutemov wrote: >>> AMD SME claims one bit from physical address to indicate whether the >>> page is encrypted or not. To achieve that we clear out the

Re: [PATCH] x86/mm: Decouple dynamic __PHYSICAL_MASK from AMD SME

2018-02-13 Thread Kirill A. Shutemov
On Tue, Feb 13, 2018 at 10:10:22PM -0600, Tom Lendacky wrote: > On 2/8/2018 6:55 AM, Kirill A. Shutemov wrote: > > AMD SME claims one bit from physical address to indicate whether the > > page is encrypted or not. To achieve that we clear out the bit from > > __PHYSICAL_MASK. > > I was actually wo

Re: [PATCH] x86/mm: Decouple dynamic __PHYSICAL_MASK from AMD SME

2018-02-13 Thread Tom Lendacky
On 2/8/2018 6:55 AM, Kirill A. Shutemov wrote: > AMD SME claims one bit from physical address to indicate whether the > page is encrypted or not. To achieve that we clear out the bit from > __PHYSICAL_MASK. I was actually working on a suggestion by Linus to use one of the software page table bits

[PATCH] x86/mm: Decouple dynamic __PHYSICAL_MASK from AMD SME

2018-02-08 Thread Kirill A. Shutemov
AMD SME claims one bit from physical address to indicate whether the page is encrypted or not. To achieve that we clear out the bit from __PHYSICAL_MASK. The capability to adjust __PHYSICAL_MASK is required beyond AMD SME. For instance for upcoming Intel Multi-Key Total Memory Encryption. Let's f