From: Andy Lutomirski <luto@amacapital.net>
To: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Oleg Nesterov <oleg@redhat.com>, X86 ML <x86@kernel.org>,
Dave Hansen <dave.hansen@linux.intel.com>,
Borislav Petkov <bp@alien8.de>,
Linux Kernel Mailing List <linux-kernel@vger.kernel.org>,
"linux-mm@kvack.org" <linux-mm@kvack.org>,
Brian Gerst <brgerst@gmail.com>
Subject: Re: [RFC 09/13] x86/mm: Disable interrupts when flushing the TLB using CR3
Date: Fri, 8 Jan 2016 16:18:08 -0800 [thread overview]
Message-ID: <CALCETrX9yheo2VK=jhqvikumXrPfdHmNCLgkjugLQnLWSawv9A@mail.gmail.com> (raw)
In-Reply-To: <CA+55aFxChuKFYyUtG6a+zn82JFB=9XaM6mH9V+kdYa9iEDKUzQ@mail.gmail.com>
On Jan 8, 2016 3:41 PM, "Linus Torvalds" <torvalds@linux-foundation.org> wrote:
>
> On Fri, Jan 8, 2016 at 3:15 PM, Andy Lutomirski <luto@kernel.org> wrote:
> > + /*
> > + * We mustn't be preempted or handle an IPI while reading and
> > + * writing CR3. Preemption could switch mms and switch back, and
> > + * an IPI could call leave_mm. Either of those could cause our
> > + * PCID to change asynchronously.
> > + */
> > + raw_local_irq_save(flags);
> > native_write_cr3(native_read_cr3());
> > + raw_local_irq_restore(flags);
>
> This seems sad for two reasons:
>
> - it adds unnecessary overhead on non-pcid setups (32-bit being an
> example of that)
I can certainly skip the flag saving on !PCID.
>
> - on pcid setups, wouldn't invpcid_flush_single_context() be better?
>
I played with that and it was slower. I don't pretend that makes any sense.
> So on the whole I hate it.
>
> Why isn't this something like
>
> if (static_cpu_has_safe(X86_FEATURE_INVPCID)) {
> invpcid_flush_single_context();
> return;
> }
> native_write_cr3(native_read_cr3());
>
> *without* any flag saving crud?
>
> And yes, that means that we'd require X86_FEATURE_INVPCID in order to
> use X86_FEATURE_PCID, but that seems fine.
I have an SNB "Extreme" with PCID but not INVPCID, and there could be
a whole generation of servers like that. I think we should fully
support them.
We might be able to get away with just disabling preemption instead of
IRQs, at least if mm == active_mm.
>
> Or is there some reason you wanted the odd flags version? If so, that
> should be documented.
What do you mean "odd"?
--Andy
next prev parent reply other threads:[~2016-01-09 0:18 UTC|newest]
Thread overview: 43+ messages / expand[flat|nested] mbox.gz Atom feed top
2016-01-08 23:15 [RFC 00/13] x86/mm: PCID and INVPCID Andy Lutomirski
2016-01-08 23:15 ` [RFC 01/13] x86/paravirt: Turn KASAN off for parvirt.o Andy Lutomirski
2016-01-10 18:59 ` Borislav Petkov
2016-01-11 12:51 ` Andrey Ryabinin
2016-01-11 12:51 ` [PATCH 1/2] x86/kasan: clear kasan_zero_page after TLB flush Andrey Ryabinin
2016-01-18 22:24 ` Andy Lutomirski
2016-02-09 16:06 ` [tip:x86/mm] x86/kasan: Clear " tip-bot for Andrey Ryabinin
2016-01-11 12:51 ` [PATCH 2/2] x86/kasan: write protect kasan zero shadow Andrey Ryabinin
2016-01-18 22:24 ` Andy Lutomirski
2016-02-09 16:07 ` [tip:x86/mm] x86/kasan: Write " tip-bot for Andrey Ryabinin
2016-01-29 10:35 ` [RFC 01/13] x86/paravirt: Turn KASAN off for parvirt.o Borislav Petkov
2016-01-08 23:15 ` [RFC 02/13] x86/mm: Add INVPCID helpers Andy Lutomirski
2016-01-08 23:15 ` [RFC 03/13] x86/mm: Add a noinvpcid option to turn off INVPCID Andy Lutomirski
2016-01-08 23:15 ` [RFC 04/13] x86/mm: If INVPCID is available, use it to flush global mappings Andy Lutomirski
2016-01-08 23:15 ` [RFC 05/13] x86/mm: Add barriers and document switch_mm-vs-flush synchronization Andy Lutomirski
2016-06-03 17:42 ` Nadav Amit
2016-06-09 17:24 ` Andy Lutomirski
2016-06-09 19:45 ` Nadav Amit
2016-09-06 1:22 ` Wanpeng Li
2016-01-08 23:15 ` [RFC 06/13] x86/mm: Disable PCID on 32-bit kernels Andy Lutomirski
2016-01-08 23:15 ` [RFC 07/13] x86/mm: Add nopcid to turn off PCID Andy Lutomirski
2016-01-08 23:15 ` [RFC 08/13] x86/mm: Teach CR3 readers about PCID Andy Lutomirski
2016-01-08 23:15 ` [RFC 09/13] x86/mm: Disable interrupts when flushing the TLB using CR3 Andy Lutomirski
2016-01-08 23:41 ` Linus Torvalds
2016-01-09 0:18 ` Andy Lutomirski [this message]
2016-01-09 2:20 ` Linus Torvalds
2016-01-11 10:51 ` Ingo Molnar
2016-01-13 23:32 ` Andy Lutomirski
2016-01-13 23:35 ` Andy Lutomirski
2016-01-13 23:43 ` Dave Hansen
2016-01-13 23:51 ` Andy Lutomirski
2016-01-13 23:56 ` Dave Hansen
2016-01-14 0:34 ` Andy Lutomirski
2016-01-08 23:15 ` [RFC 10/13] x86/mm: Factor out remote TLB flushing Andy Lutomirski
2016-01-08 23:15 ` [RFC 11/13] x86/mm: Build arch/x86/mm/tlb.c even on !SMP Andy Lutomirski
2016-01-08 23:55 ` Dave Hansen
2016-01-08 23:15 ` [RFC 12/13] x86/mm: Uninline switch_mm Andy Lutomirski
2016-01-08 23:15 ` [RFC 13/13] x86/mm: Try to preserve old TLB entries using PCID Andy Lutomirski
2016-01-09 0:27 ` Dave Hansen
2016-01-09 2:19 ` Andy Lutomirski
2016-01-08 23:31 ` [RFC 00/13] x86/mm: PCID and INVPCID Linus Torvalds
2016-01-08 23:36 ` Andy Lutomirski
2016-01-08 23:42 ` Linus Torvalds
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='CALCETrX9yheo2VK=jhqvikumXrPfdHmNCLgkjugLQnLWSawv9A@mail.gmail.com' \
--to=luto@amacapital.net \
--cc=bp@alien8.de \
--cc=brgerst@gmail.com \
--cc=dave.hansen@linux.intel.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=oleg@redhat.com \
--cc=torvalds@linux-foundation.org \
--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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).