LKML Archive on lore.kernel.org
 help / color / Atom feed
From: Thomas Gleixner <tglx@linutronix.de>
To: Chris Clayton <chris2553@googlemail.com>
Cc: LKML <linux-kernel@vger.kernel.org>,
	vincenzo.frascino@arm.com, catalin.marinas@arm.com,
	Will Deacon <will.deacon@arm.com>, Arnd Bergmann <arnd@arndb.de>,
	Daniel Lezcano <daniel.lezcano@linaro.org>,
	Andy Lutomirski <luto@kernel.org>
Subject: [PATCH] timekeeping/vsyscall: Prevent math overflow in BOOTTIME update
Date: Thu, 22 Aug 2019 13:00:15 +0200 (CEST)
Message-ID: <alpine.DEB.2.21.1908221257580.1983@nanos.tec.linutronix.de> (raw)
In-Reply-To: <alpine.DEB.2.21.1908221134110.1983@nanos.tec.linutronix.de>

The VDSO update for CLOCK_BOOTTIME has a overflow issue as it shifts the
nanoseconds based boot time offset left by the clocksource shift. That
overflows once the boot time offset becomes large enough. As a consequence
CLOCK_BOOTTIME in the VDSO becomes a random number causing applications to
misbehave.

Fix it by storing a timespec64 representation of the offset when boot time
is adjusted and add that to the MONOTONIC base time value in the vdso data
page. Using the timespec64 representation avoids a 64bit division in the
update code.

Fixes: 44f57d788e7d ("timekeeping: Provide a generic update_vsyscall() implementation")
Reported-by: Chris Clayton <chris2553@googlemail.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 include/linux/timekeeper_internal.h |    5 +++++
 kernel/time/timekeeping.c           |    5 +++++
 kernel/time/vsyscall.c              |   22 +++++++++++++---------
 3 files changed, 23 insertions(+), 9 deletions(-)

--- a/include/linux/timekeeper_internal.h
+++ b/include/linux/timekeeper_internal.h
@@ -57,6 +57,7 @@ struct tk_read_base {
  * @cs_was_changed_seq:	The sequence number of clocksource change events
  * @next_leap_ktime:	CLOCK_MONOTONIC time value of a pending leap-second
  * @raw_sec:		CLOCK_MONOTONIC_RAW  time in seconds
+ * @monotonic_to_boot:	CLOCK_MONOTONIC to CLOCK_BOOTTIME offset
  * @cycle_interval:	Number of clock cycles in one NTP interval
  * @xtime_interval:	Number of clock shifted nano seconds in one NTP
  *			interval.
@@ -84,6 +85,9 @@ struct tk_read_base {
  *
  * wall_to_monotonic is no longer the boot time, getboottime must be
  * used instead.
+ *
+ * @monotonic_to_boottime is a timespec64 representation of @offs_boot to
+ * accelerate the VDSO update for CLOCK_BOOTTIME.
  */
 struct timekeeper {
 	struct tk_read_base	tkr_mono;
@@ -99,6 +103,7 @@ struct timekeeper {
 	u8			cs_was_changed_seq;
 	ktime_t			next_leap_ktime;
 	u64			raw_sec;
+	struct timespec64	monotonic_to_boot;
 
 	/* The following members are for timekeeping internal use */
 	u64			cycle_interval;
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -146,6 +146,11 @@ static void tk_set_wall_to_mono(struct t
 static inline void tk_update_sleep_time(struct timekeeper *tk, ktime_t delta)
 {
 	tk->offs_boot = ktime_add(tk->offs_boot, delta);
+	/*
+	 * Timespec representation for VDSO update to avoid 64bit division
+	 * on every update.
+	 */
+	tk->monotonic_to_boot = ktime_to_timespec64(tk->offs_boot);
 }
 
 /*
--- a/kernel/time/vsyscall.c
+++ b/kernel/time/vsyscall.c
@@ -17,7 +17,7 @@ static inline void update_vdso_data(stru
 				    struct timekeeper *tk)
 {
 	struct vdso_timestamp *vdso_ts;
-	u64 nsec;
+	u64 nsec, sec;
 
 	vdata[CS_HRES_COARSE].cycle_last	= tk->tkr_mono.cycle_last;
 	vdata[CS_HRES_COARSE].mask		= tk->tkr_mono.mask;
@@ -45,23 +45,27 @@ static inline void update_vdso_data(stru
 	}
 	vdso_ts->nsec	= nsec;
 
-	/* CLOCK_MONOTONIC_RAW */
-	vdso_ts		= &vdata[CS_RAW].basetime[CLOCK_MONOTONIC_RAW];
-	vdso_ts->sec	= tk->raw_sec;
-	vdso_ts->nsec	= tk->tkr_raw.xtime_nsec;
+	/* Copy MONOTONIC time for BOOTTIME */
+	sec	= vdso_ts->sec;
+	/* Add the boot offset */
+	sec	+= tk->monotonic_to_boot.tv_sec;
+	nsec	+= (u64)tk->monotonic_to_boot.tv_nsec << tk->tkr_mono.shift;
 
 	/* CLOCK_BOOTTIME */
 	vdso_ts		= &vdata[CS_HRES_COARSE].basetime[CLOCK_BOOTTIME];
-	vdso_ts->sec	= tk->xtime_sec + tk->wall_to_monotonic.tv_sec;
-	nsec = tk->tkr_mono.xtime_nsec;
-	nsec += ((u64)(tk->wall_to_monotonic.tv_nsec +
-		       ktime_to_ns(tk->offs_boot)) << tk->tkr_mono.shift);
+	vdso_ts->sec	= sec;
+
 	while (nsec >= (((u64)NSEC_PER_SEC) << tk->tkr_mono.shift)) {
 		nsec -= (((u64)NSEC_PER_SEC) << tk->tkr_mono.shift);
 		vdso_ts->sec++;
 	}
 	vdso_ts->nsec	= nsec;
 
+	/* CLOCK_MONOTONIC_RAW */
+	vdso_ts		= &vdata[CS_RAW].basetime[CLOCK_MONOTONIC_RAW];
+	vdso_ts->sec	= tk->raw_sec;
+	vdso_ts->nsec	= tk->tkr_raw.xtime_nsec;
+
 	/* CLOCK_TAI */
 	vdso_ts		= &vdata[CS_HRES_COARSE].basetime[CLOCK_TAI];
 	vdso_ts->sec	= tk->xtime_sec + (s64)tk->tai_offset;

  reply index

Thread overview: 15+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-08-22  6:57 Regression in 5.3-rc1 and later Chris Clayton
2019-08-22  8:57 ` Thomas Gleixner
2019-08-22  9:00   ` Thomas Gleixner
2019-08-22  9:34     ` Thomas Gleixner
2019-08-22 11:00       ` Thomas Gleixner [this message]
2019-08-22 12:52         ` [PATCH] timekeeping/vsyscall: Prevent math overflow in BOOTTIME update Chris Clayton
2019-08-22 16:05           ` Vincenzo Frascino
2019-08-23  0:55         ` [tip: timers/urgent] " tip-bot2 for Thomas Gleixner
2019-08-23 10:36 ` Regression in 5.3-rc1 and later Russell King - ARM Linux admin
2019-08-23 10:40   ` Will Deacon
2019-08-23 11:17     ` Russell King - ARM Linux admin
2019-08-23 12:25       ` Thomas Gleixner
2019-08-23 10:43   ` Vincenzo Frascino
2019-08-23 10:51     ` Russell King - ARM Linux admin
2019-08-23 12:27       ` Thomas Gleixner

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=alpine.DEB.2.21.1908221257580.1983@nanos.tec.linutronix.de \
    --to=tglx@linutronix.de \
    --cc=arnd@arndb.de \
    --cc=catalin.marinas@arm.com \
    --cc=chris2553@googlemail.com \
    --cc=daniel.lezcano@linaro.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=luto@kernel.org \
    --cc=vincenzo.frascino@arm.com \
    --cc=will.deacon@arm.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

LKML Archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lore.kernel.org/lkml/0 lkml/git/0.git
	git clone --mirror https://lore.kernel.org/lkml/1 lkml/git/1.git
	git clone --mirror https://lore.kernel.org/lkml/2 lkml/git/2.git
	git clone --mirror https://lore.kernel.org/lkml/3 lkml/git/3.git
	git clone --mirror https://lore.kernel.org/lkml/4 lkml/git/4.git
	git clone --mirror https://lore.kernel.org/lkml/5 lkml/git/5.git
	git clone --mirror https://lore.kernel.org/lkml/6 lkml/git/6.git
	git clone --mirror https://lore.kernel.org/lkml/7 lkml/git/7.git
	git clone --mirror https://lore.kernel.org/lkml/8 lkml/git/8.git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V2 lkml lkml/ https://lore.kernel.org/lkml \
		linux-kernel@vger.kernel.org
	public-inbox-index lkml

Example config snippet for mirrors

Newsgroup available over NNTP:
	nntp://nntp.lore.kernel.org/org.kernel.vger.linux-kernel


AGPL code for this site: git clone https://public-inbox.org/public-inbox.git