All of lore.kernel.org
 help / color / mirror / Atom feed
From: Rob Gardner <rob.gardner@oracle.com>
To: David Miller <davem@davemloft.net>, khalid.aziz@oracle.com
Cc: corbet@lwn.net, akpm@linux-foundation.org,
	dingel@linux.vnet.ibm.com, bob.picco@oracle.com,
	kirill.shutemov@linux.intel.com, aneesh.kumar@linux.vnet.ibm.com,
	aarcange@redhat.com, arnd@arndb.de, sparclinux@vger.kernel.org,
	mhocko@suse.cz, chris.hyser@oracle.com, richard@nod.at,
	vbabka@suse.cz, koct9i@gmail.com, oleg@redhat.com,
	gthelen@google.com, jack@suse.cz, xiexiuqi@huawei.com,
	Vineet.Gupta1@synopsys.com, luto@kernel.org,
	ebiederm@xmission.com, bsegall@google.com, geert@linux-m68k.org,
	dave@stgolabs.net, adobriyan@gmail.com,
	linux-doc@vger.kernel.org, linux-kernel@vger.kernel.org,
	linux-mm@kvack.org, linux-arch@vger.kernel.org,
	linux-api@vger.kernel.org
Subject: Re: [PATCH v2] sparc64: Add support for Application Data Integrity (ADI)
Date: Mon, 7 Mar 2016 15:13:31 -0800	[thread overview]
Message-ID: <56DE0B1B.1000000@oracle.com> (raw)
In-Reply-To: <20160307.163850.1494834587897617780.davem@davemloft.net>

On 03/07/2016 01:38 PM, David Miller wrote:
> From: Khalid Aziz <khalid.aziz@oracle.com>
> Date: Mon, 7 Mar 2016 14:33:56 -0700
>
>> On 03/07/2016 12:16 PM, David Miller wrote:
>>> From: Khalid Aziz <khalid.aziz@oracle.com>
>>> Date: Mon, 7 Mar 2016 11:24:54 -0700
>>>
>>>> Tags can be cleared by user by setting tag to 0. Tags are
>>>> automatically cleared by the hardware when the mapping for a virtual
>>>> address is removed from TSB (which is why swappable pages are a
>>>> problem), so kernel does not have to do it as part of clean up.
>>> You might be able to crib some bits for the Tag in the swp_entry_t,
>>> it's
>>> 64-bit and you can therefore steal bits from the offset field.
>>>
>>> That way you'll have the ADI tag in the page tables, ready to
>>> re-install
>>> at swapin time.
>>>
>> That is a possibility but limited in scope. An address range covered
>> by a single TTE can have large number of tags. Version tags are set on
>> cacheline. In extreme case, one could set a tag for each set of
>> 64-bytes in a page. Also tags are set completely in userspace and no
>> transition occurs to kernel space, so kernel has no idea of what tags
>> have been set. I have not found a way to query the MMU on tags.
>>
>> I will think some more about it.
> That would mean that ADI is impossible to use for swappable memory.
>
> ...
>
> If that's true I'm extremely disappointed that they devoted so much
> silicon and engineering to this feature yet didn't take that one
> critical step to make it generally useful. :(

You can easily read ADI tags with a simple ldxa #ASI_MCD_PRIMARY 
instruction.

Rob


--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

WARNING: multiple messages have this Message-ID (diff)
From: Rob Gardner <rob.gardner@oracle.com>
To: David Miller <davem@davemloft.net>, khalid.aziz@oracle.com
Cc: corbet@lwn.net, akpm@linux-foundation.org,
	dingel@linux.vnet.ibm.com, bob.picco@oracle.com,
	kirill.shutemov@linux.intel.com, aneesh.kumar@linux.vnet.ibm.com,
	aarcange@redhat.com, arnd@arndb.de, sparclinux@vger.kernel.org,
	mhocko@suse.cz, chris.hyser@oracle.com, richard@nod.at,
	vbabka@suse.cz, koct9i@gmail.com, oleg@redhat.com,
	gthelen@google.com, jack@suse.cz, xiexiuqi@huawei.com,
	Vineet.Gupta1@synopsys.com, luto@kernel.org,
	ebiederm@xmission.com, bsegall@google.com, geert@linux-m68k.org,
	dave@stgolabs.net, adobriyan@gmail.com,
	linux-doc@vger.kernel.org, linux-kernel@vger.kernel.org,
	linux-mm@kvack.org, linux-arch@vger.kernel.org,
	linux-api@vger.kernel.org
Subject: Re: [PATCH v2] sparc64: Add support for Application Data Integrity (ADI)
Date: Mon, 7 Mar 2016 15:13:31 -0800	[thread overview]
Message-ID: <56DE0B1B.1000000@oracle.com> (raw)
Message-ID: <20160307231331.xXplsbnL6P9SmvkVSKG6-VQJ3eacr-cIsuq-F5Gs-Qg@z> (raw)
In-Reply-To: <20160307.163850.1494834587897617780.davem@davemloft.net>

On 03/07/2016 01:38 PM, David Miller wrote:
> From: Khalid Aziz <khalid.aziz@oracle.com>
> Date: Mon, 7 Mar 2016 14:33:56 -0700
>
>> On 03/07/2016 12:16 PM, David Miller wrote:
>>> From: Khalid Aziz <khalid.aziz@oracle.com>
>>> Date: Mon, 7 Mar 2016 11:24:54 -0700
>>>
>>>> Tags can be cleared by user by setting tag to 0. Tags are
>>>> automatically cleared by the hardware when the mapping for a virtual
>>>> address is removed from TSB (which is why swappable pages are a
>>>> problem), so kernel does not have to do it as part of clean up.
>>> You might be able to crib some bits for the Tag in the swp_entry_t,
>>> it's
>>> 64-bit and you can therefore steal bits from the offset field.
>>>
>>> That way you'll have the ADI tag in the page tables, ready to
>>> re-install
>>> at swapin time.
>>>
>> That is a possibility but limited in scope. An address range covered
>> by a single TTE can have large number of tags. Version tags are set on
>> cacheline. In extreme case, one could set a tag for each set of
>> 64-bytes in a page. Also tags are set completely in userspace and no
>> transition occurs to kernel space, so kernel has no idea of what tags
>> have been set. I have not found a way to query the MMU on tags.
>>
>> I will think some more about it.
> That would mean that ADI is impossible to use for swappable memory.
>
> ...
>
> If that's true I'm extremely disappointed that they devoted so much
> silicon and engineering to this feature yet didn't take that one
> critical step to make it generally useful. :(

You can easily read ADI tags with a simple ldxa #ASI_MCD_PRIMARY 
instruction.

Rob



WARNING: multiple messages have this Message-ID (diff)
From: Rob Gardner <rob.gardner@oracle.com>
To: David Miller <davem@davemloft.net>, khalid.aziz@oracle.com
Cc: corbet@lwn.net, akpm@linux-foundation.org,
	dingel@linux.vnet.ibm.com, bob.picco@oracle.com,
	kirill.shutemov@linux.intel.com, aneesh.kumar@linux.vnet.ibm.com,
	aarcange@redhat.com, arnd@arndb.de, sparclinux@vger.kernel.org,
	mhocko@suse.cz, chris.hyser@oracle.com, richard@nod.at,
	vbabka@suse.cz, koct9i@gmail.com, oleg@redhat.com,
	gthelen@google.com, jack@suse.cz, xiexiuqi@huawei.com,
	Vineet.Gupta1@synopsys.com, luto@kernel.org,
	ebiederm@xmission.com, bsegall@google.com, geert@linux-m68k.org,
	dave@stgolabs.net, adobriyan@gmail.com,
	linux-doc@vger.kernel.org, linux-kernel@vger.kernel.org,
	linux-mm@kvack.org, linux-arch@vger.kernel.org,
	linux-api@vger.kernel.org
Subject: Re: [PATCH v2] sparc64: Add support for Application Data Integrity (ADI)
Date: Mon, 07 Mar 2016 23:13:31 +0000	[thread overview]
Message-ID: <56DE0B1B.1000000@oracle.com> (raw)
In-Reply-To: <20160307.163850.1494834587897617780.davem@davemloft.net>

On 03/07/2016 01:38 PM, David Miller wrote:
> From: Khalid Aziz <khalid.aziz@oracle.com>
> Date: Mon, 7 Mar 2016 14:33:56 -0700
>
>> On 03/07/2016 12:16 PM, David Miller wrote:
>>> From: Khalid Aziz <khalid.aziz@oracle.com>
>>> Date: Mon, 7 Mar 2016 11:24:54 -0700
>>>
>>>> Tags can be cleared by user by setting tag to 0. Tags are
>>>> automatically cleared by the hardware when the mapping for a virtual
>>>> address is removed from TSB (which is why swappable pages are a
>>>> problem), so kernel does not have to do it as part of clean up.
>>> You might be able to crib some bits for the Tag in the swp_entry_t,
>>> it's
>>> 64-bit and you can therefore steal bits from the offset field.
>>>
>>> That way you'll have the ADI tag in the page tables, ready to
>>> re-install
>>> at swapin time.
>>>
>> That is a possibility but limited in scope. An address range covered
>> by a single TTE can have large number of tags. Version tags are set on
>> cacheline. In extreme case, one could set a tag for each set of
>> 64-bytes in a page. Also tags are set completely in userspace and no
>> transition occurs to kernel space, so kernel has no idea of what tags
>> have been set. I have not found a way to query the MMU on tags.
>>
>> I will think some more about it.
> That would mean that ADI is impossible to use for swappable memory.
>
> ...
>
> If that's true I'm extremely disappointed that they devoted so much
> silicon and engineering to this feature yet didn't take that one
> critical step to make it generally useful. :(

You can easily read ADI tags with a simple ldxa #ASI_MCD_PRIMARY 
instruction.

Rob



  reply	other threads:[~2016-03-07 23:13 UTC|newest]

Thread overview: 212+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2016-03-02 20:39 [PATCH v2] sparc64: Add support for Application Data Integrity (ADI) Khalid Aziz
2016-03-02 20:39 ` Khalid Aziz
2016-03-02 20:39 ` Khalid Aziz
2016-03-02 23:08 ` Julian Calaby
2016-03-02 23:08   ` Julian Calaby
2016-03-02 23:08   ` Julian Calaby
2016-03-02 23:08   ` Julian Calaby
2016-03-03  0:25   ` Khalid Aziz
2016-03-03  0:25     ` Khalid Aziz
2016-03-03  0:25     ` Khalid Aziz
2016-03-03  0:25     ` Khalid Aziz
2016-03-03  0:48     ` Julian Calaby
2016-03-03  0:48       ` Julian Calaby
2016-03-03  0:48       ` Julian Calaby
2016-03-03  0:48       ` Julian Calaby
2016-03-03 17:28       ` Khalid Aziz
2016-03-03 17:28         ` Khalid Aziz
2016-03-03 17:28         ` Khalid Aziz
2016-03-03 17:28         ` Khalid Aziz
2016-03-06  4:07 ` David Miller
2016-03-06  4:07   ` David Miller
2016-03-06  4:07   ` David Miller
2016-03-07 15:07   ` Khalid Aziz
2016-03-07 15:07     ` Khalid Aziz
2016-03-07 15:07     ` Khalid Aziz
2016-03-07 15:30     ` Rob Gardner
2016-03-07 15:30       ` Rob Gardner
2016-03-07 15:30       ` Rob Gardner
2016-03-07 15:43       ` Andy Lutomirski
2016-03-07 15:43         ` Andy Lutomirski
2016-03-07 15:43         ` Andy Lutomirski
2016-03-07 15:43         ` Andy Lutomirski
2016-03-07 16:06         ` Khalid Aziz
2016-03-07 16:06           ` Khalid Aziz
2016-03-07 16:06           ` Khalid Aziz
2016-03-07 16:06           ` Khalid Aziz
2016-03-07 17:46           ` Dave Hansen
2016-03-07 17:46             ` Dave Hansen
2016-03-07 17:46             ` Dave Hansen
2016-03-07 17:46             ` Dave Hansen
2016-03-07 17:53             ` Andy Lutomirski
2016-03-07 17:53               ` Andy Lutomirski
2016-03-07 17:53               ` Andy Lutomirski
2016-03-07 17:53               ` Andy Lutomirski
2016-03-07 18:12               ` Dave Hansen
2016-03-07 18:12                 ` Dave Hansen
2016-03-07 18:12                 ` Dave Hansen
2016-03-07 18:12                 ` Dave Hansen
2016-03-07 18:39                 ` Khalid Aziz
2016-03-07 18:39                   ` Khalid Aziz
2016-03-07 18:39                   ` Khalid Aziz
2016-03-07 18:39                   ` Khalid Aziz
2016-03-07 18:53                   ` Andy Lutomirski
2016-03-07 18:53                     ` Andy Lutomirski
2016-03-07 18:53                     ` Andy Lutomirski
2016-03-07 18:53                     ` Andy Lutomirski
     [not found]                     ` <CALCETrVNM7ZcN7WnmLRMDqGrcYXn9xYWJfjMVwFLdiQS63-TcA-JsoAwUIsXosN+BqQ9rBEUg@public.gmane.org>
2016-03-07 19:22                       ` David Miller
2016-03-07 19:22                         ` David Miller
2016-03-07 19:22                         ` David Miller
2016-03-07 19:22                         ` David Miller
2016-03-07 19:46                         ` Khalid Aziz
2016-03-07 19:46                           ` Khalid Aziz
2016-03-07 19:46                           ` Khalid Aziz
2016-03-07 22:40                           ` Dave Hansen
2016-03-07 22:40                             ` Dave Hansen
2016-03-07 22:40                             ` Dave Hansen
2016-03-08  1:31                   ` Rob Gardner
2016-03-08  1:31                     ` Rob Gardner
2016-03-08  1:31                     ` Rob Gardner
2016-03-08  1:31                     ` Rob Gardner
2016-03-07 21:06             ` Khalid Aziz
2016-03-07 21:06               ` Khalid Aziz
2016-03-07 21:06               ` Khalid Aziz
2016-03-07 21:06               ` Khalid Aziz
2016-03-08 19:57               ` David Miller
2016-03-08 19:57                 ` David Miller
2016-03-08 19:57                 ` David Miller
2016-03-08 20:16                 ` Khalid Aziz
2016-03-08 20:16                   ` Khalid Aziz
2016-03-08 20:16                   ` Khalid Aziz
2016-03-08 20:27                   ` David Miller
2016-03-08 20:27                     ` David Miller
2016-03-08 20:27                     ` David Miller
2016-03-08 20:59                     ` Khalid Aziz
2016-03-08 20:59                       ` Khalid Aziz
2016-03-08 20:59                       ` Khalid Aziz
2016-03-07 15:45       ` Khalid Aziz
2016-03-07 15:45         ` Khalid Aziz
2016-03-07 15:45         ` Khalid Aziz
2016-03-07 16:45     ` David Miller
2016-03-07 16:45       ` David Miller
2016-03-07 16:45       ` David Miller
2016-03-07 17:51       ` Khalid Aziz
2016-03-07 17:51         ` Khalid Aziz
2016-03-07 17:51         ` Khalid Aziz
     [not found]     ` <56DD9949.1000106-QHcLZuEGTsvQT0dZR+AlfA@public.gmane.org>
2016-03-07 16:56       ` David Miller
2016-03-07 16:56         ` David Miller
2016-03-07 16:56         ` David Miller
2016-03-07 16:56         ` David Miller
2016-03-07 18:04         ` Khalid Aziz
2016-03-07 18:04           ` Khalid Aziz
2016-03-07 18:04           ` Khalid Aziz
     [not found]           ` <56DDC2B6.6020009-QHcLZuEGTsvQT0dZR+AlfA@public.gmane.org>
2016-03-07 18:08             ` Andy Lutomirski
2016-03-07 18:08               ` Andy Lutomirski
2016-03-07 18:08               ` Andy Lutomirski
2016-03-07 18:08               ` Andy Lutomirski
2016-03-07 18:22               ` Khalid Aziz
2016-03-07 18:22                 ` Khalid Aziz
2016-03-07 18:22                 ` Khalid Aziz
2016-03-07 18:22                 ` Khalid Aziz
2016-03-07 18:49                 ` Andy Lutomirski
2016-03-07 18:49                   ` Andy Lutomirski
2016-03-07 18:49                   ` Andy Lutomirski
2016-03-07 18:49                   ` Andy Lutomirski
2016-03-07 19:19                   ` David Miller
2016-03-07 19:19                     ` David Miller
2016-03-07 19:19                     ` David Miller
2016-03-07 19:44                   ` Khalid Aziz
2016-03-07 19:44                     ` Khalid Aziz
2016-03-07 19:44                     ` Khalid Aziz
2016-03-07 19:44                     ` Khalid Aziz
2016-03-07 19:54                     ` Andy Lutomirski
2016-03-07 19:54                       ` Andy Lutomirski
2016-03-07 19:54                       ` Andy Lutomirski
2016-03-07 19:54                       ` Andy Lutomirski
2016-03-07 20:41                       ` Khalid Aziz
2016-03-07 20:41                         ` Khalid Aziz
2016-03-07 20:41                         ` Khalid Aziz
2016-03-07 20:41                         ` Khalid Aziz
     [not found]                         ` <56DDE783.8090009-QHcLZuEGTsvQT0dZR+AlfA@public.gmane.org>
2016-03-07 20:58                           ` David Miller
2016-03-07 20:58                             ` David Miller
2016-03-07 20:58                             ` David Miller
2016-03-07 20:58                             ` David Miller
2016-03-07 21:02                             ` Andy Lutomirski
2016-03-07 21:02                               ` Andy Lutomirski
2016-03-07 21:02                               ` Andy Lutomirski
2016-03-07 21:02                               ` Andy Lutomirski
2016-03-07 21:09                             ` Khalid Aziz
2016-03-07 21:09                               ` Khalid Aziz
2016-03-07 21:09                               ` Khalid Aziz
2016-03-07 23:34                             ` James Morris
2016-03-07 23:34                               ` James Morris
2016-03-07 23:34                               ` James Morris
2016-03-07 23:48                       ` James Morris
2016-03-07 23:48                         ` James Morris
2016-03-07 23:48                         ` James Morris
2016-03-07 23:48                         ` James Morris
2016-03-08  9:33                         ` James Morris
2016-03-08  9:33                           ` James Morris
2016-03-08  9:33                           ` James Morris
2016-03-08  9:33                           ` James Morris
2016-03-07 18:09           ` Rob Gardner
2016-03-07 18:09             ` Rob Gardner
2016-03-07 18:09             ` Rob Gardner
2016-03-07 18:24             ` Khalid Aziz
2016-03-07 18:24               ` Khalid Aziz
2016-03-07 18:24               ` Khalid Aziz
2016-03-07 19:16               ` David Miller
2016-03-07 19:16                 ` David Miller
2016-03-07 19:16                 ` David Miller
2016-03-07 21:33                 ` Khalid Aziz
2016-03-07 21:33                   ` Khalid Aziz
2016-03-07 21:33                   ` Khalid Aziz
2016-03-07 21:38                   ` David Miller
2016-03-07 21:38                     ` David Miller
2016-03-07 21:38                     ` David Miller
2016-03-07 23:13                     ` Rob Gardner [this message]
2016-03-07 23:13                       ` Rob Gardner
2016-03-07 23:13                       ` Rob Gardner
2016-03-08  4:13                       ` David Miller
2016-03-08  4:13                         ` David Miller
2016-03-08  4:13                         ` David Miller
2016-03-07 23:12                   ` Rob Gardner
2016-03-07 23:12                     ` Rob Gardner
2016-03-07 23:12                     ` Rob Gardner
2016-03-07 23:27                     ` Khalid Aziz
2016-03-07 23:27                       ` Khalid Aziz
2016-03-07 23:27                       ` Khalid Aziz
2016-03-08  0:21                 ` Khalid Aziz
2016-03-08  0:21                   ` Khalid Aziz
2016-03-08  0:21                   ` Khalid Aziz
2016-03-08  4:24                   ` David Miller
2016-03-08  4:24                     ` David Miller
2016-03-08  4:24                     ` David Miller
2016-03-07 23:32               ` Rob Gardner
2016-03-07 23:32                 ` Rob Gardner
2016-03-07 23:32                 ` Rob Gardner
2016-03-07 19:09           ` David Miller
2016-03-07 19:09             ` David Miller
2016-03-07 19:09             ` David Miller
2016-03-07 21:27             ` Khalid Aziz
2016-03-07 21:27               ` Khalid Aziz
2016-03-07 21:27               ` Khalid Aziz
     [not found]               ` <56DDF22D.9090102-QHcLZuEGTsvQT0dZR+AlfA@public.gmane.org>
2016-03-07 21:34                 ` David Miller
2016-03-07 21:34                   ` David Miller
2016-03-07 21:34                   ` David Miller
2016-03-07 21:34                   ` David Miller
2016-03-07 22:30                   ` Khalid Aziz
2016-03-07 22:30                     ` Khalid Aziz
2016-03-07 22:30                     ` Khalid Aziz
2016-03-07 17:32 ` Dave Hansen
2016-03-07 17:32   ` Dave Hansen
2016-03-07 17:32   ` Dave Hansen
2016-03-07 17:35 ` Dave Hansen
2016-03-07 17:35   ` Dave Hansen
2016-03-07 17:35   ` Dave Hansen
2016-03-07 18:15   ` Khalid Aziz
2016-03-07 18:15     ` Khalid Aziz
2016-03-07 18:15     ` Khalid Aziz
2016-03-07 19:06   ` David Miller
2016-03-07 19:06     ` David Miller
2016-03-07 19:06     ` David Miller

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=56DE0B1B.1000000@oracle.com \
    --to=rob.gardner@oracle.com \
    --cc=Vineet.Gupta1@synopsys.com \
    --cc=aarcange@redhat.com \
    --cc=adobriyan@gmail.com \
    --cc=akpm@linux-foundation.org \
    --cc=aneesh.kumar@linux.vnet.ibm.com \
    --cc=arnd@arndb.de \
    --cc=bob.picco@oracle.com \
    --cc=bsegall@google.com \
    --cc=chris.hyser@oracle.com \
    --cc=corbet@lwn.net \
    --cc=dave@stgolabs.net \
    --cc=davem@davemloft.net \
    --cc=dingel@linux.vnet.ibm.com \
    --cc=ebiederm@xmission.com \
    --cc=geert@linux-m68k.org \
    --cc=gthelen@google.com \
    --cc=jack@suse.cz \
    --cc=khalid.aziz@oracle.com \
    --cc=kirill.shutemov@linux.intel.com \
    --cc=koct9i@gmail.com \
    --cc=linux-api@vger.kernel.org \
    --cc=linux-arch@vger.kernel.org \
    --cc=linux-doc@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=luto@kernel.org \
    --cc=mhocko@suse.cz \
    --cc=oleg@redhat.com \
    --cc=richard@nod.at \
    --cc=sparclinux@vger.kernel.org \
    --cc=vbabka@suse.cz \
    --cc=xiexiuqi@huawei.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.