From: Andy Lutomirski <luto@kernel.org>
To: Peter Zijlstra <peterz@infradead.org>
Cc: Nadav Amit <namit@vmware.com>,
Thomas Gleixner <tglx@linutronix.de>,
LKML <linux-kernel@vger.kernel.org>,
Ingo Molnar <mingo@redhat.com>, X86 ML <x86@kernel.org>,
Arnd Bergmann <arnd@arndb.de>,
linux-arch <linux-arch@vger.kernel.org>,
Andy Lutomirski <luto@kernel.org>,
Masami Hiramatsu <mhiramat@kernel.org>,
Kees Cook <keescook@chromium.org>
Subject: Re: [RFC PATCH 5/6] x86/alternatives: use temporary mm for text poking
Date: Wed, 29 Aug 2018 08:46:04 -0700 [thread overview]
Message-ID: <CALCETrXe9CUMo3c44UtmkxD4w68PvmoypdCyvCFvWiZVuxy=sQ@mail.gmail.com> (raw)
In-Reply-To: <20180829092839.GP24124@hirez.programming.kicks-ass.net>
On Wed, Aug 29, 2018 at 2:28 AM, Peter Zijlstra <peterz@infradead.org> wrote:
> On Wed, Aug 29, 2018 at 01:11:46AM -0700, Nadav Amit wrote:
>> + pte_clear(poking_mm, poking_addr, ptep);
>> +
>> + /*
>> + * __flush_tlb_one_user() performs a redundant TLB flush when PTI is on,
>> + * as it also flushes the corresponding "user" address spaces, which
>> + * does not exist.
>> + *
>> + * Poking, however, is already very inefficient since it does not try to
>> + * batch updates, so we ignore this problem for the time being.
>> + *
>> + * Since the PTEs do not exist in other kernel address-spaces, we do
>> + * not use __flush_tlb_one_kernel(), which when PTI is on would cause
>> + * more unwarranted TLB flushes.
>> + */
>
> yuck :-), but yeah.
I'm sure we covered this ad nauseum when PTI was being developed, but
we were kind of in a rush, so:
Why do we do INVPCID at all? The fallback path for non-INVPCID
systems uses invalidate_user_asid(), which should be faster than the
invpcid path. And doesn't do a redundant flush in this case.
Can we just drop the INVPCID? While we're at it, we could drop
X86_FEATURE_INVPCID_SINGLE entirely, since that's the only user.
--Andy
next prev parent reply other threads:[~2018-08-29 15:46 UTC|newest]
Thread overview: 34+ messages / expand[flat|nested] mbox.gz Atom feed top
2018-08-29 8:11 [RFC PATCH 0/6] x86: text_poke() fixes Nadav Amit
2018-08-29 8:11 ` [RFC PATCH 1/6] x86/alternative: assert text_mutex is taken Nadav Amit
2018-08-29 8:59 ` Masami Hiramatsu
2018-08-29 17:11 ` Nadav Amit
2018-08-29 19:36 ` Nadav Amit
2018-08-29 20:13 ` Sean Christopherson
2018-08-29 20:44 ` Nadav Amit
2018-08-29 21:00 ` Sean Christopherson
2018-08-29 22:56 ` Nadav Amit
2018-08-30 2:26 ` Masami Hiramatsu
2018-08-30 5:23 ` Nadav Amit
2018-08-29 8:11 ` [RFC PATCH 2/6] x86/mm: temporary mm struct Nadav Amit
2018-08-29 9:49 ` Masami Hiramatsu
2018-08-29 15:41 ` Andy Lutomirski
2018-08-29 16:54 ` Nadav Amit
2018-08-29 21:38 ` Andy Lutomirski
2018-08-30 1:38 ` Masami Hiramatsu
2018-08-30 1:59 ` Andy Lutomirski
2018-08-31 4:42 ` Masami Hiramatsu
2018-08-29 15:46 ` Andy Lutomirski
2018-08-29 8:11 ` [RFC PATCH 3/6] fork: provide a function for copying init_mm Nadav Amit
2018-08-29 9:54 ` Masami Hiramatsu
2018-08-29 8:11 ` [RFC PATCH 4/6] x86/alternatives: initializing temporary mm for patching Nadav Amit
2018-08-29 13:21 ` Masami Hiramatsu
2018-08-29 17:45 ` Nadav Amit
2018-08-29 8:11 ` [RFC PATCH 5/6] x86/alternatives: use temporary mm for text poking Nadav Amit
2018-08-29 9:28 ` Peter Zijlstra
2018-08-29 15:46 ` Andy Lutomirski [this message]
2018-08-29 16:14 ` Peter Zijlstra
2018-08-29 16:32 ` Andy Lutomirski
2018-08-29 16:37 ` Dave Hansen
2018-08-29 8:11 ` [RFC PATCH 6/6] x86/alternatives: remove text_poke() return value Nadav Amit
2018-08-29 9:52 ` Masami Hiramatsu
2018-08-29 17:15 ` Nadav Amit
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='CALCETrXe9CUMo3c44UtmkxD4w68PvmoypdCyvCFvWiZVuxy=sQ@mail.gmail.com' \
--to=luto@kernel.org \
--cc=arnd@arndb.de \
--cc=keescook@chromium.org \
--cc=linux-arch@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=mhiramat@kernel.org \
--cc=mingo@redhat.com \
--cc=namit@vmware.com \
--cc=peterz@infradead.org \
--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 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).