public inbox for linux-kernel@vger.kernel.org
 help / color / mirror / Atom feed
From: Thomas Gleixner <tglx@linutronix.de>
To: LKML <linux-kernel@vger.kernel.org>
Cc: John Stultz <john.stultz@linaro.org>,
	Peter Zijlstra <peterz@infradead.org>,
	Ingo Molnar <mingo@kernel.org>,
	David Gibson <david@gibson.dropbear.id.au>,
	Liav Rehana <liavr@mellanox.com>,
	Chris Metcalf <cmetcalf@mellanox.com>,
	Richard Cochran <richardcochran@gmail.com>,
	Parit Bhargava <prarit@redhat.com>,
	Laurent Vivier <lvivier@redhat.com>,
	"Christopher S. Hall" <christopher.s.hall@intel.com>
Subject: [patch 5/6] [RFD] timekeeping: Provide optional 128bit math
Date: Thu, 08 Dec 2016 20:49:39 -0000	[thread overview]
Message-ID: <20161208204229.005418487@linutronix.de> (raw)
In-Reply-To: 20161208202623.883855034@linutronix.de

[-- Attachment #1: timekeeping--Provide-optional-128bit-math.patch --]
[-- Type: text/plain, Size: 2877 bytes --]

If the timekeeping CPU is scheduled out long enough by a hypervisor the
clocksource delta multiplication can overflow and as a result time can go
backwards. That's insane to begin with, but people already triggered a
signed multiplication overflow, so a unsigned overflow is not necessarily
impossible.

Implement optional 128bit math which can be selected by a config option.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 kernel/time/Kconfig       |   15 +++++++++++++++
 kernel/time/timekeeping.c |   38 ++++++++++++++++++++++++++++++++++++--
 2 files changed, 51 insertions(+), 2 deletions(-)

--- a/kernel/time/Kconfig
+++ b/kernel/time/Kconfig
@@ -51,6 +51,21 @@ config GENERIC_CLOCKEVENTS_MIN_ADJUST
 config GENERIC_CMOS_UPDATE
 	bool
 
+config TIMEKEEPING_USE_128BIT_MATH
+	bool "Enable 128 bit math in the timekeeping hotpath"
+	default n
+	depends on !ARCH_USES_GETTIMEOFFSET && EXPERT
+	help
+
+	  If VMs get scheduled out for a long time then the clocksource
+	  delta to nanoseconds conversion in timekeeping can overflow the
+	  64bit multiplication. As a result time going backwards might be
+	  observed.
+
+	  Enable this only if you want to support insane setups with
+	  massive overcommitment as this introduces overhead into the
+	  timekeeping hotpath.
+
 if GENERIC_CLOCKEVENTS
 menu "Timers subsystem"
 
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -298,8 +298,41 @@ u32 (*arch_gettimeoffset)(void) = defaul
 static inline u32 arch_gettimeoffset(void) { return 0; }
 #endif
 
-static inline u64 timekeeping_delta_to_ns(struct tk_read_base *tkr,
-					  cycle_t delta)
+/*
+ * Enabled when timekeeping is supposed to deal with virtualization keeping
+ * VMs long enough scheduled out that the 64 * 32 bit multiplication in
+ * timekeeping_delta_to_ns() overflows 64bit.
+ */
+#ifdef CONFIG_TIMEKEEPING_USE_128BIT_MATH
+
+#if defined(CONFIG_ARCH_SUPPORTS_INT128) && defined(__SIZEOF_INT128__)
+static inline u64 timekeeping_delta_to_ns(struct tk_read_base *tkr, u64 delta)
+{
+	unsigned __int128 nsec;
+
+	nsec = ((unsigned __int128)delta * tkr->mult) + tkr->xtime_nsec;
+	return (u64) (nsec >> tkr->shift);
+}
+#else
+static inline u64 timekeeping_delta_to_ns(struct tk_read_base *tkr, u64 delta)
+{
+	u32 dh, dl;
+	u64 nsec;
+
+	dl = delta;
+	dh = delta >> 32;
+
+	nsec = ((u64)dl * tkr->mult) + tkr->xtime_nsec;
+	nsec >>= tkr->shift;
+	if (unlikely(dh))
+		nsec += ((u64)dh * tkr->mult) << (32 - tkr->shift);
+	return nsec;
+}
+#endif
+
+#else /* CONFIG_TIMEKEEPING_USE_128BIT_MATH */
+
+static inline u64 timekeeping_delta_to_ns(struct tk_read_base *tkr, u64 delta)
 {
 	u64 nsec;
 
@@ -309,6 +342,7 @@ static inline u64 timekeeping_delta_to_n
 	/* If arch requires, add in get_arch_timeoffset() */
 	return nsec + arch_gettimeoffset();
 }
+#endif
 
 static inline u64 timekeeping_get_ns(struct tk_read_base *tkr)
 {

  parent reply	other threads:[~2016-12-08 20:52 UTC|newest]

Thread overview: 35+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2016-12-08 20:49 [patch 0/6] timekeeping: Cure the signed/unsigned wreckage Thomas Gleixner
2016-12-08 20:49 ` [patch 1/6] timekeeping: Force unsigned clocksource to nanoseconds conversion Thomas Gleixner
2016-12-08 23:38   ` David Gibson
2016-12-09 11:13   ` [tip:timers/core] timekeeping_Force_unsigned_clocksource_to_nanoseconds_conversion tip-bot for Thomas Gleixner
2016-12-08 20:49 ` [patch 2/6] timekeeping: Make the conversion call chain consistently unsigned Thomas Gleixner
2016-12-08 23:39   ` David Gibson
2016-12-09 11:13   ` [tip:timers/core] " tip-bot for Thomas Gleixner
2016-12-08 20:49 ` [patch 3/6] timekeeping: Get rid of pointless typecasts Thomas Gleixner
2016-12-08 23:40   ` David Gibson
2016-12-09 11:14   ` [tip:timers/core] " tip-bot for Thomas Gleixner
2016-12-08 20:49 ` [patch 4/6] timekeeping: Use mul_u64_u32_shr() instead of open coding it Thomas Gleixner
2016-12-08 23:41   ` David Gibson
2016-12-09 11:14   ` [tip:timers/core] " tip-bot for Thomas Gleixner
2016-12-08 20:49 ` Thomas Gleixner [this message]
2016-12-09  4:08   ` [patch 5/6] [RFD] timekeeping: Provide optional 128bit math Ingo Molnar
2016-12-09  4:29     ` Ingo Molnar
2016-12-09  4:39       ` John Stultz
2016-12-09  4:48     ` Peter Zijlstra
2016-12-09  5:22       ` Ingo Molnar
2016-12-09  5:41         ` Peter Zijlstra
2016-12-09  5:11   ` Peter Zijlstra
2016-12-09  6:08     ` Peter Zijlstra
2016-12-09  5:26   ` Peter Zijlstra
2016-12-09  6:38     ` Peter Zijlstra
2016-12-09  8:30       ` Peter Zijlstra
2016-12-09  9:11         ` Peter Zijlstra
2016-12-09 10:01         ` Peter Zijlstra
2016-12-09 17:32         ` Chris Metcalf
2017-01-14 12:51         ` [tip:timers/core] math64, timers: Fix 32bit mul_u64_u32_shr() and friends tip-bot for Peter Zijlstra
2016-12-09 10:18       ` [patch 5/6] [RFD] timekeeping: Provide optional 128bit math Peter Zijlstra
2016-12-09 17:20         ` Chris Metcalf
2016-12-08 20:49 ` [patch 6/6] [RFD] timekeeping: Get rid of cycle_t Thomas Gleixner
2016-12-08 23:43   ` David Gibson
2016-12-09  4:52 ` [patch 0/6] timekeeping: Cure the signed/unsigned wreckage John Stultz
2016-12-09  5:30 ` Peter Zijlstra

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=20161208204229.005418487@linutronix.de \
    --to=tglx@linutronix.de \
    --cc=christopher.s.hall@intel.com \
    --cc=cmetcalf@mellanox.com \
    --cc=david@gibson.dropbear.id.au \
    --cc=john.stultz@linaro.org \
    --cc=liavr@mellanox.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=lvivier@redhat.com \
    --cc=mingo@kernel.org \
    --cc=peterz@infradead.org \
    --cc=prarit@redhat.com \
    --cc=richardcochran@gmail.com \
    /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