From: Peter Zijlstra <peterz@infradead.org>
To: Tim Chen <tim.c.chen@linux.intel.com>
Cc: Ingo Molnar <mingo@kernel.org>, Dave Hansen <dave@sr71.net>,
hpa@zytor.com, tglx@linutronix.de, torvalds@linux-foundation.org,
linux-kernel@vger.kernel.org, dwmw@amazon.co.uk,
linux-tip-commits@vger.kernel.org, Borislav Petkov <bp@alien8.de>,
Arjan van de Ven <arjan@infradead.org>
Subject: Re: [tip:x86/pti] x86/speculation: Use IBRS if available before calling into firmware
Date: Wed, 14 Feb 2018 09:56:14 +0100 [thread overview]
Message-ID: <20180214085614.GT25181@hirez.programming.kicks-ass.net> (raw)
In-Reply-To: <5c3ba123-abbe-f153-7b75-a89d31d25c72@linux.intel.com>
On Tue, Feb 13, 2018 at 05:49:47PM -0800, Tim Chen wrote:
> static inline void firmware_restrict_branch_speculation_start(void)
> {
> + if (this_cpu_inc_return(spec_ctrl_ibrs_fw_depth) == 1)
> + alternative_msr_write(MSR_IA32_SPEC_CTRL, SPEC_CTRL_IBRS,
> X86_FEATURE_USE_IBRS_FW);
> }
>
> static inline void firmware_restrict_branch_speculation_end(void)
> {
> + if (this_cpu_dec_return(spec_ctrl_ibrs_fw_depth) == 0)
> + alternative_msr_write(MSR_IA32_SPEC_CTRL, 0,
> + X86_FEATURE_USE_IBRS_FW);
> }
At the very least this must disable and re-enable preemption, such that
we guarantee we inc/dec the same counter. ISTR some firmware calls (EFI)
actually are preemptible so that wouldn't work.
Further, consider:
this_cpu_inc_return() // 0->1
<NMI>
this_cpu_inc_return() // 1->2
call_broken_arse_firmware()
this_cpu_dec_return() // 2->1
</NMI>
wrmsr(SPEC_CTRL, IBRS);
/* from dodgy firmware crap */
this_cpu_dec_return() // 1->0
wrmsr(SPEC_CTRL, 0);
next prev parent reply other threads:[~2018-02-14 8:56 UTC|newest]
Thread overview: 75+ messages / expand[flat|nested] mbox.gz Atom feed top
2018-02-10 23:39 [PATCH v2 0/6] Spectre v2 updates David Woodhouse
2018-02-10 23:39 ` [PATCH v2 1/6] x86/speculation: Update Speculation Control microcode blacklist David Woodhouse
2018-02-11 12:08 ` [tip:x86/pti] " tip-bot for David Woodhouse
2018-02-12 9:50 ` [PATCH v2 1/6] " Darren Kenny
2018-02-12 14:16 ` David Woodhouse
2018-02-12 14:32 ` Thomas Gleixner
2018-02-10 23:39 ` [PATCH v2 2/6] Revert "x86/speculation: Simplify indirect_branch_prediction_barrier()" David Woodhouse
2018-02-11 12:09 ` [tip:x86/pti] " tip-bot for David Woodhouse
2018-02-13 8:58 ` tip-bot for David Woodhouse
2018-02-13 9:41 ` Peter Zijlstra
2018-02-13 11:28 ` Ingo Molnar
2018-02-13 13:28 ` Peter Zijlstra
2018-02-13 13:38 ` Ingo Molnar
2018-02-13 15:26 ` [tip:x86/pti] x86/speculation: Add <asm/msr-index.h> dependency tip-bot for Peter Zijlstra
2018-02-15 0:28 ` tip-bot for Peter Zijlstra
2018-02-10 23:39 ` [PATCH v2 3/6] KVM: x86: Reduce retpoline performance impact in slot_handle_level_range() David Woodhouse
2018-02-11 12:09 ` [tip:x86/pti] KVM/x86: Reduce retpoline performance impact in slot_handle_level_range(), by always inlining iterator helper methods tip-bot for David Woodhouse
2018-02-13 8:58 ` tip-bot for David Woodhouse
2018-02-10 23:39 ` [PATCH v2 4/6] X86/nVMX: Properly set spec_ctrl and pred_cmd before merging MSRs David Woodhouse
2018-02-11 12:10 ` [tip:x86/pti] " tip-bot for KarimAllah Ahmed
2018-02-13 8:59 ` tip-bot for KarimAllah Ahmed
2018-02-10 23:39 ` [PATCH v2 5/6] KVM/nVMX: Set the CPU_BASED_USE_MSR_BITMAPS if we have a valid L02 MSR bitmap David Woodhouse
2018-02-11 10:19 ` Ingo Molnar
[not found] ` <1518345844.3677.365.camel@amazon.co.uk>
2018-02-11 10:55 ` Ingo Molnar
2018-02-11 12:10 ` [tip:x86/pti] " tip-bot for KarimAllah Ahmed
2018-02-13 8:59 ` tip-bot for KarimAllah Ahmed
2018-02-10 23:39 ` [PATCH v2 6/6] x86/speculation: Use IBRS if available before calling into firmware David Woodhouse
2018-02-11 11:46 ` Ingo Molnar
2018-02-11 10:41 ` [PATCH v2 0/6] Spectre v2 updates Ingo Molnar
2018-02-11 15:19 ` [PATCH v2.1] x86/speculation: Use IBRS if available before calling into firmware David Woodhouse
2018-02-11 18:50 ` [PATCH] x86/speculation: Clean up various Spectre related details Ingo Molnar
2018-02-11 19:25 ` David Woodhouse
2018-02-11 19:43 ` Ingo Molnar
2018-02-12 15:30 ` David Woodhouse
2018-02-13 8:04 ` Ingo Molnar
2018-02-11 19:19 ` [tip:x86/pti] x86/speculation: Use IBRS if available before calling into firmware tip-bot for David Woodhouse
2018-02-12 5:59 ` afzal mohammed
2018-02-12 16:30 ` David Woodhouse
2018-02-12 10:22 ` Ingo Molnar
2018-02-12 11:50 ` Peter Zijlstra
2018-02-12 12:27 ` David Woodhouse
2018-02-12 13:06 ` Peter Zijlstra
2018-02-13 7:58 ` Ingo Molnar
2018-02-12 12:28 ` Peter Zijlstra
2018-02-12 16:13 ` Dave Hansen
2018-02-12 16:58 ` Peter Zijlstra
2018-02-13 7:55 ` Ingo Molnar
2018-02-14 1:49 ` Tim Chen
2018-02-14 8:56 ` Peter Zijlstra [this message]
2018-02-14 8:57 ` Peter Zijlstra
2018-02-14 19:20 ` Tim Chen
2018-02-14 23:19 ` Ingo Molnar
2018-02-15 2:01 ` Tim Chen
2018-02-14 9:31 ` [PATCH] watchdog: hpwdt: Remove spinlock acquire and BIOS calls from NMI context Ingo Molnar
2018-02-14 9:38 ` Peter Zijlstra
2018-02-14 10:39 ` Ingo Molnar
2018-02-14 9:44 ` Borislav Petkov
2018-02-14 18:13 ` Jerry Hoemann
2018-02-14 23:17 ` Ingo Molnar
2018-02-15 17:44 ` Jerry Hoemann
2018-02-15 19:02 ` Ingo Molnar
2018-02-15 19:48 ` Peter Zijlstra
2018-02-16 18:44 ` [tip:x86/pti] x86/speculation: Use IBRS if available before calling into firmware Tim Chen
2018-02-16 19:16 ` David Woodhouse
2018-02-16 23:46 ` Tim Chen
2018-02-17 10:26 ` Ingo Molnar
2018-02-19 9:20 ` Peter Zijlstra
2018-02-19 9:29 ` David Woodhouse
2018-02-19 9:39 ` Ingo Molnar
2018-02-19 9:44 ` David Woodhouse
2018-02-19 10:08 ` Peter Zijlstra
2018-02-19 9:36 ` Ingo Molnar
2018-02-12 8:27 ` [PATCH v2 0/6] Spectre v2 updates Paolo Bonzini
2018-02-13 7:59 ` Ingo Molnar
2018-02-19 10:50 [PATCH v3 1/4] x86/speculation: Use IBRS if available before calling into firmware David Woodhouse
2018-02-20 10:29 ` [tip:x86/pti] " tip-bot for David Woodhouse
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=20180214085614.GT25181@hirez.programming.kicks-ass.net \
--to=peterz@infradead.org \
--cc=arjan@infradead.org \
--cc=bp@alien8.de \
--cc=dave@sr71.net \
--cc=dwmw@amazon.co.uk \
--cc=hpa@zytor.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-tip-commits@vger.kernel.org \
--cc=mingo@kernel.org \
--cc=tglx@linutronix.de \
--cc=tim.c.chen@linux.intel.com \
--cc=torvalds@linux-foundation.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
Powered by JetHome