clockevents/clocksources: 3.13 fixes

Hi Thomas and Ingo,

here is a pull request for a single fix for 3.13. It is based on the latest timers/urgent update.

* Soren Brinkmann fixed the cadence_ttc driver where a call to
clk_get_rate happens in an interrupt context. More precisely in an IPI when the broadcast timer is initialized for each cpu in the cpuidle driver

Thanks
-- Daniel

The following changes since commit b0031f227e47919797dc0e1c1990f3ef151ff0cc:

Merge tag 's2mps11-build' of
git://git.kernel.org/pub/scm/linux/kernel/git/broonie/regulator
(2013-12-17 12:57:36 -0800)

are available in the git repository at:

git://git.linaro.org/people/daniel.lezcano/linux.git
clockevents/3.13-fixes

for you to fetch changes up to c1dcc927dae01dfd4904ee82ce2c00b50eab6dc3:

clocksource: cadence_ttc: Fix mutex taken inside interrupt context
(2013-12-30 11:32:24 +0100)

----------------------------------------------------------------
Soren Brinkmann (1):
clocksource: cadence_ttc: Fix mutex taken inside interrupt context

  drivers/clocksource/cadence_ttc_timer.c |   21 +++++++++++++--------
  1 file changed, 13 insertions(+), 8 deletions(-)

  <http://www.linaro.org/> Linaro.org ? Open source software for ARM SoCs

Follow Linaro:  <http://www.facebook.com/pages/Linaro> Facebook |
<http://twitter.com/#!/linaroorg> Twitter |
<http://www.linaro.org/linaro-blog/> Blog

From: Soren Brinkmann <[email protected]>

When the kernel is compiled with:
CONFIG_HIGH_RES_TIMERS=no
CONFIG_HZ_PERIODIC=yes
CONFIG_DEBUG_ATOMIC_SLEEP=yes

The following WARN appears:

WARNING: CPU: 1 PID: 0 at linux/kernel/mutex.c:856 mutex_trylock+0x70/0x1fc()
DEBUG_LOCKS_WARN_ON(in_interrupt())
Modules linked in:
CPU: 1 PID: 0 Comm: swapper/1 Not tainted 3.12.0-xilinx-dirty #93
[<c0014a78>] (unwind_backtrace+0x0/0x11c) from [<c0011b6c>] (show_stack+0x10/0x14)
[<c0011b6c>] (show_stack+0x10/0x14) from [<c039120c>] (dump_stack+0x7c/0xc0)
[<c039120c>] (dump_stack+0x7c/0xc0) from [<c001fda4>] (warn_slowpath_common+0x60/0x84)
[<c001fda4>] (warn_slowpath_common+0x60/0x84) from [<c001fe48>] (warn_slowpath_fmt+0x2c/0x3c)
[<c001fe48>] (warn_slowpath_fmt+0x2c/0x3c) from [<c0392658>] (mutex_trylock+0x70/0x1fc)
[<c0392658>] (mutex_trylock+0x70/0x1fc) from [<c02dfc08>] (clk_prepare_lock+0xc/0xe4)
[<c02dfc08>] (clk_prepare_lock+0xc/0xe4) from [<c02e099c>] (clk_get_rate+0xc/0x44)
[<c02e099c>] (clk_get_rate+0xc/0x44) from [<c02d0394>] (ttc_set_mode+0x34/0x78)
[<c02d0394>] (ttc_set_mode+0x34/0x78) from [<c005f794>] (clockevents_set_mode+0x28/0x5c)
[<c005f794>] (clockevents_set_mode+0x28/0x5c) from [<c00607fc>] (tick_broadcast_on_off+0x190/0x1c0)
[<c00607fc>] (tick_broadcast_on_off+0x190/0x1c0) from [<c005f168>] (clockevents_notify+0x58/0x1ac)
[<c005f168>] (clockevents_notify+0x58/0x1ac) from [<c02b99dc>] (cpuidle_setup_broadcast_timer+0x20/0x24)
[<c02b99dc>] (cpuidle_setup_broadcast_timer+0x20/0x24) from [<c006cd04>] (generic_smp_call_function_single_interrupt+0)
[<c006cd04>] (generic_smp_call_function_single_interrupt+0xe0/0x130) from [<c00138c8>] (handle_IPI+0x88/0x118)
[<c00138c8>] (handle_IPI+0x88/0x118) from [<c0008504>] (gic_handle_irq+0x58/0x60)
[<c0008504>] (gic_handle_irq+0x58/0x60) from [<c0012644>] (__irq_svc+0x44/0x78)
Exception stack(0xef099fa0 to 0xef099fe8)

9fa0: 00000001 ef092100 00000000 ef092100 ef098000 00000015 c0399f2c c0579d74 9fc0: 0000406a 413fc090 00000000 00000000 00000000 ef099fe8 c00666ec c000f46c 9fe0: 20000113 ffffffff
[<c0012644>] (__irq_svc+0x44/0x78) from [<c000f46c>] (arch_cpu_idle+0x34/0x3c) [<c000f46c>] (arch_cpu_idle+0x34/0x3c) from [<c0053980>] (cpu_startup_entry+0xa8/0x10c) [<c0053980>] (cpu_startup_entry+0xa8/0x10c) from [<000085a4>] (0x85a4)

We are in an interrupt context (IPI) and we are calling clk_get_rate in the set_mode function which in turn ends up by getting a mutex... Even if that does not hang, it is a potential kernel deadlock.

It is not allowed to call clk_get_rate() from interrupt context. To avoid such calls the timer input frequency is stored in the driver's data struct which makes it accessible to the driver in any context.

[dlezcano] completed the changelog with the WARN trace and added a more detailed description. Tested on zync zc702.

---
 drivers/clocksource/cadence_ttc_timer.c |   21 +++++++++++++--------
 1 file changed, 13 insertions(+), 8 deletions(-)

index b2bb3a4b..a92350b 100644
@@ -67,11 +67,13 @@
  * struct ttc_timer - This definition defines local timer structure
  *
  * @base_addr:	Base address of timer
+ * @freq:	Timer input clock frequency
  * @clk:	Associated clock source
  * @clk_rate_change_nb	Notifier block for clock rate changes
  */
 struct ttc_timer {
 	void __iomem *base_addr;
+	unsigned long freq;
 	struct clk *clk;
 	struct notifier_block clk_rate_change_nb;
 };

@@ -196,9 +198,8 @@ static void ttc_set_mode(enum clock_event_mode mode,
 
 	switch (mode) {
 	case CLOCK_EVT_MODE_PERIODIC:
-		ttc_set_interval(timer,
-				DIV_ROUND_CLOSEST(clk_get_rate(ttce->ttc.clk),
-					PRESCALE * HZ));
+		ttc_set_interval(timer, DIV_ROUND_CLOSEST(ttce->ttc.freq,
+						PRESCALE * HZ));
 		break;
 	case CLOCK_EVT_MODE_ONESHOT:
 	case CLOCK_EVT_MODE_UNUSED:

@@ -273,6 +274,8 @@ static void __init ttc_setup_clocksource(struct clk *clk, void __iomem *base)
 		return;
 	}
 
+	ttccs->ttc.freq = clk_get_rate(ttccs->ttc.clk);
+
 	ttccs->ttc.clk_rate_change_nb.notifier_call =
 		ttc_rate_change_clocksource_cb;
 	ttccs->ttc.clk_rate_change_nb.next = NULL;

@@ -298,16 +301,14 @@ static void __init ttc_setup_clocksource(struct clk *clk, void __iomem *base)
 	__raw_writel(CNT_CNTRL_RESET,
 		     ttccs->ttc.base_addr + TTC_CNT_CNTRL_OFFSET);
 
-	err = clocksource_register_hz(&ttccs->cs,
-			clk_get_rate(ttccs->ttc.clk) / PRESCALE);
+	err = clocksource_register_hz(&ttccs->cs, ttccs->ttc.freq / PRESCALE);
 	if (WARN_ON(err)) {
 		kfree(ttccs);
 		return;
 	}
 
 	ttc_sched_clock_val_reg = base + TTC_COUNT_VAL_OFFSET;
-	setup_sched_clock(ttc_sched_clock_read, 16,
-			clk_get_rate(ttccs->ttc.clk) / PRESCALE);
+	setup_sched_clock(ttc_sched_clock_read, 16, ttccs->ttc.freq / PRESCALE);
 }
 
 static int ttc_rate_change_clockevent_cb(struct notifier_block *nb,

@@ -334,6 +335,9 @@ static int ttc_rate_change_clockevent_cb(struct notifier_block *nb,
 				ndata->new_rate / PRESCALE);
 		local_irq_restore(flags);
 
+		/* update cached frequency */
+		ttc->freq = ndata->new_rate;
+
 		/* fall through */
 	}
 	case PRE_RATE_CHANGE:

@@ -367,6 +371,7 @@ static void __init ttc_setup_clockevent(struct clk *clk,
 	if (clk_notifier_register(ttcce->ttc.clk,
 				&ttcce->ttc.clk_rate_change_nb))
 		pr_warn("Unable to register clock notifier.\n");
+	ttcce->ttc.freq = clk_get_rate(ttcce->ttc.clk);
 
 	ttcce->ttc.base_addr = base;
 	ttcce->ce.name = "ttc_clockevent";

@@ -396,7 +401,7 @@ static void __init ttc_setup_clockevent(struct clk *clk,
 	}
 
 	clockevents_config_and_register(&ttcce->ce,
-			clk_get_rate(ttcce->ttc.clk) / PRESCALE, 1, 0xfffe);
+			ttcce->ttc.freq / PRESCALE, 1, 0xfffe);
 }
 
 /**

1.7.9.5

Hi Thomas and Ingo,

just a head up for this PR. It has been sent right before the PR for 3.14, so I wanted to me sure you did not missed it.

Thanks
-- Daniel

  <http://www.linaro.org/> Linaro.org ? Open source software for ARM SoCs

Follow Linaro:  <http://www.facebook.com/pages/Linaro> Facebook |
<http://twitter.com/#!/linaroorg> Twitter |
<http://www.linaro.org/linaro-blog/> Blog

Pulled into tip:timers/urgent, thanks Daniel!

Ingo