linux-kernel - [PATCH v2] clocksource: tsc: respect tsc bootparam for clocksource_tsc

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [thread-next>] [day] [month] [year] [list]

Message-ID: <20191024175945.14338-1-mzhivich@akamai.com>
Date:   Thu, 24 Oct 2019 13:59:45 -0400
From:   Michael Zhivich <mzhivich@...mai.com>
To:     <linux-kernel@...r.kernel.org>
CC:     <tglx@...utronix.de>, <mingo@...hat.com>, <bp@...en8.de>,
        <hpa@...or.com>, <rafael.j.wysocki@...el.com>,
        Michael Zhivich <mzhivich@...mai.com>
Subject: [PATCH v2] clocksource: tsc: respect tsc bootparam for clocksource_tsc_early

Introduction of clocksource_tsc_early broke functionality of "tsc=reliable"
and "tsc=nowatchdog" bootparams, since clocksource_tsc_early is *always*
registered with CLOCK_SOURCE_MUST_VERIFY and thus put on the watchdog list.

This frequently causes TSC to be declared unstable during boot:

  clocksource: timekeeping watchdog on CPU0: Marking clocksource
               'tsc-early' as unstable because the skew is too large:
  clocksource: 'refined-jiffies' wd_now: fffb7018 wd_last: fffb6e9d 
               mask: ffffffff
  clocksource: 'tsc-early' cs_now: 68a6a7070f6a0 cs_last: 68a69ab6f74d6 
               mask: ffffffffffffffff
  tsc: Marking TSC unstable due to clocksource watchdog

The corresponding elapsed times are cs_nsec=1224152026 and wd_nsec=378942392, so
watchdog differs from TSC by 0.84 seconds.  Since jiffies is not guaranteed
to provide reliable timekeeping due to possibility of missing timer
interrupts, this is a false positive.

This issue affects machines running with HPET disabled; otherwise, HPET would
be the watchdog for tsc-early clocksource, and this situation would be avoided. 

Restore previous behavior by respecting "tsc=reliable" and "tsc=nowatchdog"
boot params when registering clocksource_tsc_early.

Fixes: aa83c45762a24 ("x86/tsc: Introduce early tsc clocksource")
Signed-off-by: Michael Zhivich <mzhivich@...mai.com>
---
 arch/x86/kernel/tsc.c | 3 +++
 1 file changed, 3 insertions(+)

 Changes from v1: updated commit message, added "Fixes" tag.

diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index c59454c382fd..7e322e2daaf5 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -1505,6 +1505,9 @@ void __init tsc_init(void)
 		return;
 	}

+	if (tsc_clocksource_reliable || no_tsc_watchdog)
+		clocksource_tsc_early.flags &= ~CLOCK_SOURCE_MUST_VERIFY;
+
 	clocksource_register_khz(&clocksource_tsc_early, tsc_khz);
 	detect_art();
 }
-- 
2.17.1