All of lore.kernel.org
 help / color / mirror / Atom feed
From: One Thousand Gnomes <gnomes@lxorguk.ukuu.org.uk>
To: Qiaowei Ren <qiaowei.ren@intel.com>
Cc: "H. Peter Anvin" <hpa@zytor.com>,
	Thomas Gleixner <tglx@linutronix.de>,
	Ingo Molnar <mingo@redhat.com>,
	Dave Hansen <dave.hansen@intel.com>,
	x86@kernel.org, linux-mm@kvack.org, linux-kernel@vger.kernel.org
Subject: Re: [PATCH v8 08/10] x86, mpx: add prctl commands PR_MPX_REGISTER, PR_MPX_UNREGISTER
Date: Mon, 15 Sep 2014 01:00:25 +0100	[thread overview]
Message-ID: <20140915010025.5940c946@alan.etchedpixels.co.uk> (raw)
In-Reply-To: <1410425210-24789-9-git-send-email-qiaowei.ren@intel.com>

> The base of the bounds directory is set into mm_struct during
> PR_MPX_REGISTER command execution. This member can be used to
> check whether one application is mpx enabled.

Not really because by the time you ask the question another thread might
have decided to unregister it.


> +int mpx_register(struct task_struct *tsk)
> +{
> +	struct mm_struct *mm = tsk->mm;
> +
> +	if (!cpu_has_mpx)
> +		return -EINVAL;
> +
> +	/*
> +	 * runtime in the userspace will be responsible for allocation of
> +	 * the bounds directory. Then, it will save the base of the bounds
> +	 * directory into XSAVE/XRSTOR Save Area and enable MPX through
> +	 * XRSTOR instruction.
> +	 *
> +	 * fpu_xsave() is expected to be very expensive. In order to do
> +	 * performance optimization, here we get the base of the bounds
> +	 * directory and then save it into mm_struct to be used in future.
> +	 */
> +	mm->bd_addr = task_get_bounds_dir(tsk);
> +	if (!mm->bd_addr)
> +		return -EINVAL;

What stops two threads calling this in parallel ?
> +
> +	return 0;
> +}
> +
> +int mpx_unregister(struct task_struct *tsk)
> +{
> +	struct mm_struct *mm = current->mm;
> +
> +	if (!cpu_has_mpx)
> +		return -EINVAL;
> +
> +	mm->bd_addr = NULL;

or indeed calling this in parallel

What are the semantics across execve() ?

Alan

WARNING: multiple messages have this Message-ID (diff)
From: One Thousand Gnomes <gnomes@lxorguk.ukuu.org.uk>
To: Qiaowei Ren <qiaowei.ren@intel.com>
Cc: "H. Peter Anvin" <hpa@zytor.com>,
	Thomas Gleixner <tglx@linutronix.de>,
	Ingo Molnar <mingo@redhat.com>,
	Dave Hansen <dave.hansen@intel.com>,
	x86@kernel.org, linux-mm@kvack.org, linux-kernel@vger.kernel.org
Subject: Re: [PATCH v8 08/10] x86, mpx: add prctl commands PR_MPX_REGISTER, PR_MPX_UNREGISTER
Date: Mon, 15 Sep 2014 01:00:25 +0100	[thread overview]
Message-ID: <20140915010025.5940c946@alan.etchedpixels.co.uk> (raw)
In-Reply-To: <1410425210-24789-9-git-send-email-qiaowei.ren@intel.com>

> The base of the bounds directory is set into mm_struct during
> PR_MPX_REGISTER command execution. This member can be used to
> check whether one application is mpx enabled.

Not really because by the time you ask the question another thread might
have decided to unregister it.


> +int mpx_register(struct task_struct *tsk)
> +{
> +	struct mm_struct *mm = tsk->mm;
> +
> +	if (!cpu_has_mpx)
> +		return -EINVAL;
> +
> +	/*
> +	 * runtime in the userspace will be responsible for allocation of
> +	 * the bounds directory. Then, it will save the base of the bounds
> +	 * directory into XSAVE/XRSTOR Save Area and enable MPX through
> +	 * XRSTOR instruction.
> +	 *
> +	 * fpu_xsave() is expected to be very expensive. In order to do
> +	 * performance optimization, here we get the base of the bounds
> +	 * directory and then save it into mm_struct to be used in future.
> +	 */
> +	mm->bd_addr = task_get_bounds_dir(tsk);
> +	if (!mm->bd_addr)
> +		return -EINVAL;

What stops two threads calling this in parallel ?
> +
> +	return 0;
> +}
> +
> +int mpx_unregister(struct task_struct *tsk)
> +{
> +	struct mm_struct *mm = current->mm;
> +
> +	if (!cpu_has_mpx)
> +		return -EINVAL;
> +
> +	mm->bd_addr = NULL;

or indeed calling this in parallel

What are the semantics across execve() ?

Alan

--
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>

  parent reply	other threads:[~2014-09-15  0:01 UTC|newest]

Thread overview: 130+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2014-09-11  8:46 [PATCH v8 00/10] Intel MPX support Qiaowei Ren
2014-09-11  8:46 ` Qiaowei Ren
2014-09-11  8:46 ` [PATCH v8 01/10] x86, mpx: introduce VM_MPX to indicate that a VMA is MPX specific Qiaowei Ren
2014-09-11  8:46   ` Qiaowei Ren
2014-09-11  8:46 ` [PATCH v8 02/10] x86, mpx: add MPX specific mmap interface Qiaowei Ren
2014-09-11  8:46   ` Qiaowei Ren
2014-09-11  8:46 ` [PATCH v8 03/10] x86, mpx: add macro cpu_has_mpx Qiaowei Ren
2014-09-11  8:46   ` Qiaowei Ren
2014-09-11  8:46 ` [PATCH v8 04/10] x86, mpx: hook #BR exception handler to allocate bound tables Qiaowei Ren
2014-09-11  8:46   ` Qiaowei Ren
2014-09-12 22:58   ` Dave Hansen
2014-09-12 22:58     ` Dave Hansen
2014-09-13  7:24     ` Ren, Qiaowei
2014-09-13  7:24       ` Ren, Qiaowei
2014-09-24 14:40   ` Dave Hansen
2014-09-24 14:40     ` Dave Hansen
2014-09-11  8:46 ` [PATCH v8 05/10] x86, mpx: extend siginfo structure to include bound violation information Qiaowei Ren
2014-09-11  8:46   ` Qiaowei Ren
2014-09-11  8:46 ` [PATCH v8 06/10] mips: sync struct siginfo with general version Qiaowei Ren
2014-09-11  8:46   ` Qiaowei Ren
2014-09-11 22:13   ` Thomas Gleixner
2014-09-11 22:13     ` Thomas Gleixner
2014-09-12  2:54     ` Ren, Qiaowei
2014-09-12  2:54       ` Ren, Qiaowei
2014-09-12  8:17       ` Thomas Gleixner
2014-09-12  8:17         ` Thomas Gleixner
2014-09-13  7:13         ` Ren, Qiaowei
2014-09-13  7:13           ` Ren, Qiaowei
2014-09-11  8:46 ` [PATCH v8 07/10] x86, mpx: decode MPX instruction to get bound violation information Qiaowei Ren
2014-09-11  8:46   ` Qiaowei Ren
2014-09-11 22:18   ` Thomas Gleixner
2014-09-11 22:18     ` Thomas Gleixner
2014-09-11 22:32     ` Dave Hansen
2014-09-11 22:32       ` Dave Hansen
2014-09-11 22:35       ` H. Peter Anvin
2014-09-11 22:35         ` H. Peter Anvin
2014-09-11 23:37         ` Thomas Gleixner
2014-09-11 23:37           ` Thomas Gleixner
2014-09-12  4:44           ` H. Peter Anvin
2014-09-12  4:44             ` H. Peter Anvin
2014-09-12 13:10             ` Thomas Gleixner
2014-09-12 13:10               ` Thomas Gleixner
2014-09-12 13:39               ` H. Peter Anvin
2014-09-12 13:39                 ` H. Peter Anvin
2014-09-12 17:48                 ` Thomas Gleixner
2014-09-12 17:48                   ` Thomas Gleixner
2014-09-12 17:52         ` Thomas Gleixner
2014-09-12 17:52           ` Thomas Gleixner
2014-09-12 19:07           ` H. Peter Anvin
2014-09-12 19:07             ` H. Peter Anvin
2014-09-11  8:46 ` [PATCH v8 08/10] x86, mpx: add prctl commands PR_MPX_REGISTER, PR_MPX_UNREGISTER Qiaowei Ren
2014-09-11  8:46   ` Qiaowei Ren
2014-09-11 15:03   ` Dave Hansen
2014-09-11 15:03     ` Dave Hansen
2014-09-12  3:10     ` Ren, Qiaowei
2014-09-12  3:10       ` Ren, Qiaowei
2014-09-11 23:28   ` Thomas Gleixner
2014-09-11 23:28     ` Thomas Gleixner
2014-09-12  0:10     ` Dave Hansen
2014-09-12  0:10       ` Dave Hansen
2014-09-12  8:11       ` Thomas Gleixner
2014-09-12  8:11         ` Thomas Gleixner
2014-09-12  9:24         ` Thomas Gleixner
2014-09-12  9:24           ` Thomas Gleixner
2014-09-12 14:36           ` Dave Hansen
2014-09-12 14:36             ` Dave Hansen
2014-09-12 17:34             ` Thomas Gleixner
2014-09-12 17:34               ` Thomas Gleixner
2014-09-12 18:42               ` Thomas Gleixner
2014-09-12 18:42                 ` Thomas Gleixner
2014-09-12 20:35                 ` Dave Hansen
2014-09-12 20:35                   ` Dave Hansen
2014-09-12 20:18               ` Dave Hansen
2014-09-12 20:18                 ` Dave Hansen
2014-09-13  9:01                 ` Thomas Gleixner
2014-09-13  9:01                   ` Thomas Gleixner
2014-09-12 15:22         ` Dave Hansen
2014-09-12 15:22           ` Dave Hansen
2014-09-12 17:42           ` Thomas Gleixner
2014-09-12 17:42             ` Thomas Gleixner
2014-09-12 20:33             ` Dave Hansen
2014-09-12 20:33               ` Dave Hansen
2014-09-15  0:00   ` One Thousand Gnomes [this message]
2014-09-15  0:00     ` One Thousand Gnomes
2014-09-16  3:20     ` Ren, Qiaowei
2014-09-16  3:20       ` Ren, Qiaowei
2014-09-16  4:17       ` Dave Hansen
2014-09-16  4:17         ` Dave Hansen
2014-09-16  7:50   ` Kevin Easton
2014-09-16  7:50     ` Kevin Easton
2014-09-18  0:40     ` Ren, Qiaowei
2014-09-18  0:40       ` Ren, Qiaowei
2014-09-18  3:23       ` Kevin Easton
2014-09-18  3:23         ` Kevin Easton
2014-09-18  2:37         ` Ren, Qiaowei
2014-09-18  2:37           ` Ren, Qiaowei
2014-09-18  4:43         ` Dave Hansen
2014-09-18  4:43           ` Dave Hansen
2014-09-18  7:17           ` Kevin Easton
2014-09-18  7:17             ` Kevin Easton
2014-09-18  6:20             ` Dave Hansen
2014-09-18  6:20               ` Dave Hansen
2014-09-11  8:46 ` [PATCH v8 09/10] x86, mpx: cleanup unused bound tables Qiaowei Ren
2014-09-11  8:46   ` Qiaowei Ren
2014-09-11 14:59   ` Dave Hansen
2014-09-11 14:59     ` Dave Hansen
2014-09-12  3:02     ` Ren, Qiaowei
2014-09-12  3:02       ` Ren, Qiaowei
2014-09-12  4:59       ` Dave Hansen
2014-09-12  4:59         ` Dave Hansen
2014-09-15 20:53   ` Dave Hansen
2014-09-15 20:53     ` Dave Hansen
2014-09-16  8:06     ` Ren, Qiaowei
2014-09-16  8:06       ` Ren, Qiaowei
2014-09-11  8:46 ` [PATCH v8 10/10] x86, mpx: add documentation on Intel MPX Qiaowei Ren
2014-09-11  8:46   ` Qiaowei Ren
2014-09-12  0:51 ` [PATCH v8 00/10] Intel MPX support Dave Hansen
2014-09-12  0:51   ` Dave Hansen
2014-09-12 19:21   ` Thomas Gleixner
2014-09-12 19:21     ` Thomas Gleixner
2014-09-12 21:23     ` Dave Hansen
2014-09-12 21:23       ` Dave Hansen
2014-09-13  9:25       ` Thomas Gleixner
2014-09-13  9:25         ` Thomas Gleixner
2014-09-12 21:31     ` Dave Hansen
2014-09-12 21:31       ` Dave Hansen
2014-09-12 22:08     ` Dave Hansen
2014-09-12 22:08       ` Dave Hansen
2014-09-13  9:39       ` Thomas Gleixner
2014-09-13  9:39         ` Thomas Gleixner

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=20140915010025.5940c946@alan.etchedpixels.co.uk \
    --to=gnomes@lxorguk.ukuu.org.uk \
    --cc=dave.hansen@intel.com \
    --cc=hpa@zytor.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=mingo@redhat.com \
    --cc=qiaowei.ren@intel.com \
    --cc=tglx@linutronix.de \
    --cc=x86@kernel.org \
    /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.