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-prev] [thread-next>] [day] [month] [year] [list]
Message-Id: <20200321113242.120587764@linutronix.de>
Date:   Sat, 21 Mar 2020 12:25:58 +0100
From:   Thomas Gleixner <tglx@...utronix.de>
To:     LKML <linux-kernel@...r.kernel.org>
Cc:     Peter Zijlstra <peterz@...radead.org>,
        Ingo Molnar <mingo@...nel.org>,
        Sebastian Siewior <bigeasy@...utronix.de>,
        Linus Torvalds <torvalds@...ux-foundation.org>,
        Joel Fernandes <joel@...lfernandes.org>,
        Oleg Nesterov <oleg@...hat.com>,
        Davidlohr Bueso <dave@...olabs.net>,
        Logan Gunthorpe <logang@...tatee.com>,
        Bjorn Helgaas <bhelgaas@...gle.com>,
        Kurt Schwemmer <kurt.schwemmer@...rosemi.com>,
        linux-pci@...r.kernel.org,
        Greg Kroah-Hartman <gregkh@...uxfoundation.org>,
        Felipe Balbi <balbi@...nel.org>, linux-usb@...r.kernel.org,
        Kalle Valo <kvalo@...eaurora.org>,
        "David S. Miller" <davem@...emloft.net>,
        linux-wireless@...r.kernel.org, netdev@...r.kernel.org,
        Darren Hart <dvhart@...radead.org>,
        Andy Shevchenko <andy@...radead.org>,
        platform-driver-x86@...r.kernel.org,
        Zhang Rui <rui.zhang@...el.com>,
        "Rafael J. Wysocki" <rafael.j.wysocki@...el.com>,
        linux-pm@...r.kernel.org, Len Brown <lenb@...nel.org>,
        linux-acpi@...r.kernel.org, kbuild test robot <lkp@...el.com>,
        Nick Hu <nickhu@...estech.com>,
        Greentime Hu <green.hu@...il.com>,
        Vincent Chen <deanbo422@...il.com>,
        Guo Ren <guoren@...nel.org>, linux-csky@...r.kernel.org,
        Brian Cain <bcain@...eaurora.org>,
        linux-hexagon@...r.kernel.org, Tony Luck <tony.luck@...el.com>,
        Fenghua Yu <fenghua.yu@...el.com>, linux-ia64@...r.kernel.org,
        Michal Simek <monstr@...str.eu>,
        Michael Ellerman <mpe@...erman.id.au>,
        Arnd Bergmann <arnd@...db.de>,
        Geoff Levand <geoff@...radead.org>,
        linuxppc-dev@...ts.ozlabs.org,
        "Paul E . McKenney" <paulmck@...nel.org>,
        Jonathan Corbet <corbet@....net>,
        Randy Dunlap <rdunlap@...radead.org>,
        Davidlohr Bueso <dbueso@...e.de>
Subject: [patch V3 14/20] timekeeping: Split jiffies seqlock

From: Thomas Gleixner <tglx@...utronix.de>

seqlock consists of a sequence counter and a spinlock_t which is used to
serialize the writers. spinlock_t is substituted by a "sleeping" spinlock
on PREEMPT_RT enabled kernels which breaks the usage in the timekeeping
code as the writers are executed in hard interrupt and therefore
non-preemptible context even on PREEMPT_RT.

The spinlock in seqlock cannot be unconditionally replaced by a
raw_spinlock_t as many seqlock users have nesting spinlock sections or
other code which is not suitable to run in truly atomic context on RT.

Instead of providing a raw_seqlock API for a single use case, open code the
seqlock for the jiffies use case and implement it with a raw_spinlock_t and
a sequence counter.

Signed-off-by: Thomas Gleixner <tglx@...utronix.de>

---
 kernel/time/jiffies.c     |    7 ++++---
 kernel/time/tick-common.c |   10 ++++++----
 kernel/time/tick-sched.c  |   19 ++++++++++++-------
 kernel/time/timekeeping.c |    6 ++++--
 kernel/time/timekeeping.h |    3 ++-
 5 files changed, 28 insertions(+), 17 deletions(-)

--- a/kernel/time/jiffies.c
+++ b/kernel/time/jiffies.c
@@ -58,7 +58,8 @@ static struct clocksource clocksource_ji
 	.max_cycles	= 10,
 };
 
-__cacheline_aligned_in_smp DEFINE_SEQLOCK(jiffies_lock);
+__cacheline_aligned_in_smp DEFINE_RAW_SPINLOCK(jiffies_lock);
+__cacheline_aligned_in_smp seqcount_t jiffies_seq;
 
 #if (BITS_PER_LONG < 64)
 u64 get_jiffies_64(void)
@@ -67,9 +68,9 @@ u64 get_jiffies_64(void)
 	u64 ret;
 
 	do {
-		seq = read_seqbegin(&jiffies_lock);
+		seq = read_seqcount_begin(&jiffies_seq);
 		ret = jiffies_64;
-	} while (read_seqretry(&jiffies_lock, seq));
+	} while (read_seqcount_retry(&jiffies_seq, seq));
 	return ret;
 }
 EXPORT_SYMBOL(get_jiffies_64);
--- a/kernel/time/tick-common.c
+++ b/kernel/time/tick-common.c
@@ -84,13 +84,15 @@ int tick_is_oneshot_available(void)
 static void tick_periodic(int cpu)
 {
 	if (tick_do_timer_cpu == cpu) {
-		write_seqlock(&jiffies_lock);
+		raw_spin_lock(&jiffies_lock);
+		write_seqcount_begin(&jiffies_seq);
 
 		/* Keep track of the next tick event */
 		tick_next_period = ktime_add(tick_next_period, tick_period);
 
 		do_timer(1);
-		write_sequnlock(&jiffies_lock);
+		write_seqcount_end(&jiffies_seq);
+		raw_spin_unlock(&jiffies_lock);
 		update_wall_time();
 	}
 
@@ -162,9 +164,9 @@ void tick_setup_periodic(struct clock_ev
 		ktime_t next;
 
 		do {
-			seq = read_seqbegin(&jiffies_lock);
+			seq = read_seqcount_begin(&jiffies_seq);
 			next = tick_next_period;
-		} while (read_seqretry(&jiffies_lock, seq));
+		} while (read_seqcount_retry(&jiffies_seq, seq));
 
 		clockevents_switch_state(dev, CLOCK_EVT_STATE_ONESHOT);
 
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -65,7 +65,8 @@ static void tick_do_update_jiffies64(kti
 		return;
 
 	/* Reevaluate with jiffies_lock held */
-	write_seqlock(&jiffies_lock);
+	raw_spin_lock(&jiffies_lock);
+	write_seqcount_begin(&jiffies_seq);
 
 	delta = ktime_sub(now, last_jiffies_update);
 	if (delta >= tick_period) {
@@ -91,10 +92,12 @@ static void tick_do_update_jiffies64(kti
 		/* Keep the tick_next_period variable up to date */
 		tick_next_period = ktime_add(last_jiffies_update, tick_period);
 	} else {
-		write_sequnlock(&jiffies_lock);
+		write_seqcount_end(&jiffies_seq);
+		raw_spin_unlock(&jiffies_lock);
 		return;
 	}
-	write_sequnlock(&jiffies_lock);
+	write_seqcount_end(&jiffies_seq);
+	raw_spin_unlock(&jiffies_lock);
 	update_wall_time();
 }
 
@@ -105,12 +108,14 @@ static ktime_t tick_init_jiffy_update(vo
 {
 	ktime_t period;
 
-	write_seqlock(&jiffies_lock);
+	raw_spin_lock(&jiffies_lock);
+	write_seqcount_begin(&jiffies_seq);
 	/* Did we start the jiffies update yet ? */
 	if (last_jiffies_update == 0)
 		last_jiffies_update = tick_next_period;
 	period = last_jiffies_update;
-	write_sequnlock(&jiffies_lock);
+	write_seqcount_end(&jiffies_seq);
+	raw_spin_unlock(&jiffies_lock);
 	return period;
 }
 
@@ -676,10 +681,10 @@ static ktime_t tick_nohz_next_event(stru
 
 	/* Read jiffies and the time when jiffies were updated last */
 	do {
-		seq = read_seqbegin(&jiffies_lock);
+		seq = read_seqcount_begin(&jiffies_seq);
 		basemono = last_jiffies_update;
 		basejiff = jiffies;
-	} while (read_seqretry(&jiffies_lock, seq));
+	} while (read_seqcount_retry(&jiffies_seq, seq));
 	ts->last_jiffies = basejiff;
 	ts->timer_expires_base = basemono;
 
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -2397,8 +2397,10 @@ EXPORT_SYMBOL(hardpps);
  */
 void xtime_update(unsigned long ticks)
 {
-	write_seqlock(&jiffies_lock);
+	raw_spin_lock(&jiffies_lock);
+	write_seqcount_begin(&jiffies_seq);
 	do_timer(ticks);
-	write_sequnlock(&jiffies_lock);
+	write_seqcount_end(&jiffies_seq);
+	raw_spin_unlock(&jiffies_lock);
 	update_wall_time();
 }
--- a/kernel/time/timekeeping.h
+++ b/kernel/time/timekeeping.h
@@ -25,7 +25,8 @@ static inline void sched_clock_resume(vo
 extern void do_timer(unsigned long ticks);
 extern void update_wall_time(void);
 
-extern seqlock_t jiffies_lock;
+extern raw_spinlock_t jiffies_lock;
+extern seqcount_t jiffies_seq;
 
 #define CS_NAME_LEN	32
 


Powered by blists - more mailing lists

Powered by Openwall GNU/*/Linux Powered by OpenVZ