linux/kernel/time/clockevents.c

779 lines
20 KiB
C
Raw Normal View History

time: Add SPDX license identifiers Update the time(r) core files files with the correct SPDX license identifier based on the license text in the file itself. The SPDX identifier is a legally binding shorthand, which can be used instead of the full boiler plate text. This work is based on a script and data from Philippe Ombredanne, Kate Stewart and myself. The data has been created with two independent license scanners and manual inspection. The following files do not contain any direct license information and have been omitted from the big initial SPDX changes: timeconst.bc: The .bc files were not touched time.c, timer.c, timekeeping.c: Licence was deduced from EXPORT_SYMBOL_GPL As those files do not contain direct license references they fall under the project license, i.e. GPL V2 only. Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Acked-by: Kees Cook <keescook@chromium.org> Acked-by: Ingo Molnar <mingo@kernel.org> Acked-by: John Stultz <john.stultz@linaro.org> Acked-by: Corey Minyard <cminyard@mvista.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Kate Stewart <kstewart@linuxfoundation.org> Cc: Philippe Ombredanne <pombredanne@nexb.com> Cc: Russell King <rmk+kernel@armlinux.org.uk> Cc: Richard Cochran <richardcochran@gmail.com> Cc: Nicolas Pitre <nicolas.pitre@linaro.org> Cc: David Riley <davidriley@chromium.org> Cc: Colin Cross <ccross@android.com> Cc: Mark Brown <broonie@kernel.org> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Link: https://lkml.kernel.org/r/20181031182252.879109557@linutronix.de
2018-11-01 02:21:09 +08:00
// SPDX-License-Identifier: GPL-2.0
/*
* This file contains functions which manage clock event devices.
*
* Copyright(C) 2005-2006, Thomas Gleixner <tglx@linutronix.de>
* Copyright(C) 2005-2007, Red Hat, Inc., Ingo Molnar
* Copyright(C) 2006-2007, Timesys Corp., Thomas Gleixner
*/
#include <linux/clockchips.h>
#include <linux/hrtimer.h>
#include <linux/init.h>
#include <linux/module.h>
#include <linux/smp.h>
#include <linux/device.h>
#include "tick-internal.h"
/* The registered clock event devices */
static LIST_HEAD(clockevent_devices);
static LIST_HEAD(clockevents_released);
/* Protection for the above */
static DEFINE_RAW_SPINLOCK(clockevents_lock);
/* Protection for unbind operations */
static DEFINE_MUTEX(clockevents_mutex);
struct ce_unbind {
struct clock_event_device *ce;
int res;
};
clockevents: Sanitize ticks to nsec conversion Marc Kleine-Budde pointed out, that commit 77cc982 "clocksource: use clockevents_config_and_register() where possible" caused a regression for some of the converted subarchs. The reason is, that the clockevents core code converts the minimal hardware tick delta to a nanosecond value for core internal usage. This conversion is affected by integer math rounding loss, so the backwards conversion to hardware ticks will likely result in a value which is less than the configured hardware limitation. The affected subarchs used their own workaround (SIGH!) which got lost in the conversion. The solution for the issue at hand is simple: adding evt->mult - 1 to the shifted value before the integer divison in the core conversion function takes care of it. But this only works for the case where for the scaled math mult/shift pair "mult <= 1 << shift" is true. For the case where "mult > 1 << shift" we can apply the rounding add only for the minimum delta value to make sure that the backward conversion is not less than the given hardware limit. For the upper bound we need to omit the rounding add, because the backwards conversion is always larger than the original latch value. That would violate the upper bound of the hardware device. Though looking closer at the details of that function reveals another bogosity: The upper bounds check is broken as well. Checking for a resulting "clc" value greater than KTIME_MAX after the conversion is pointless. The conversion does: u64 clc = (latch << evt->shift) / evt->mult; So there is no sanity check for (latch << evt->shift) exceeding the 64bit boundary. The latch argument is "unsigned long", so on a 64bit arch the handed in argument could easily lead to an unnoticed shift overflow. With the above rounding fix applied the calculation before the divison is: u64 clc = (latch << evt->shift) + evt->mult - 1; So we need to make sure, that neither the shift nor the rounding add is overflowing the u64 boundary. [ukl: move assignment to rnd after eventually changing mult, fix build issue and correct comment with the right math] Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Cc: Russell King - ARM Linux <linux@arm.linux.org.uk> Cc: Marc Kleine-Budde <mkl@pengutronix.de> Cc: nicolas.ferre@atmel.com Cc: Marc Pignat <marc.pignat@hevs.ch> Cc: john.stultz@linaro.org Cc: kernel@pengutronix.de Cc: Ronald Wahl <ronald.wahl@raritan.com> Cc: LAK <linux-arm-kernel@lists.infradead.org> Cc: Ludovic Desroches <ludovic.desroches@atmel.com> Cc: stable@vger.kernel.org Link: http://lkml.kernel.org/r/1380052223-24139-1-git-send-email-u.kleine-koenig@pengutronix.de Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
2013-09-25 03:50:23 +08:00
static u64 cev_delta2ns(unsigned long latch, struct clock_event_device *evt,
bool ismax)
{
nohz: Allow 32-bit machines to sleep for more than 2.15 seconds In the dynamic tick code, "max_delta_ns" (member of the "clock_event_device" structure) represents the maximum sleep time that can occur between timer events in nanoseconds. The variable, "max_delta_ns", is defined as an unsigned long which is a 32-bit integer for 32-bit machines and a 64-bit integer for 64-bit machines (if -m64 option is used for gcc). The value of max_delta_ns is set by calling the function "clockevent_delta2ns()" which returns a maximum value of LONG_MAX. For a 32-bit machine LONG_MAX is equal to 0x7fffffff and in nanoseconds this equates to ~2.15 seconds. Hence, the maximum sleep time for a 32-bit machine is ~2.15 seconds, where as for a 64-bit machine it will be many years. This patch changes the type of max_delta_ns to be "u64" instead of "unsigned long" so that this variable is a 64-bit type for both 32-bit and 64-bit machines. It also changes the maximum value returned by clockevent_delta2ns() to KTIME_MAX. Hence this allows a 32-bit machine to sleep for longer than ~2.15 seconds. Please note that this patch also changes "min_delta_ns" to be "u64" too and although this is unnecessary, it makes the patch simpler as it avoids to fixup all callers of clockevent_delta2ns(). [ tglx: changed "unsigned long long" to u64 as we use this data type through out the time code ] Signed-off-by: Jon Hunter <jon-hunter@ti.com> Cc: John Stultz <johnstul@us.ibm.com> LKML-Reference: <1250617512-23567-3-git-send-email-jon-hunter@ti.com> Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2009-08-19 01:45:11 +08:00
u64 clc = (u64) latch << evt->shift;
clockevents: Sanitize ticks to nsec conversion Marc Kleine-Budde pointed out, that commit 77cc982 "clocksource: use clockevents_config_and_register() where possible" caused a regression for some of the converted subarchs. The reason is, that the clockevents core code converts the minimal hardware tick delta to a nanosecond value for core internal usage. This conversion is affected by integer math rounding loss, so the backwards conversion to hardware ticks will likely result in a value which is less than the configured hardware limitation. The affected subarchs used their own workaround (SIGH!) which got lost in the conversion. The solution for the issue at hand is simple: adding evt->mult - 1 to the shifted value before the integer divison in the core conversion function takes care of it. But this only works for the case where for the scaled math mult/shift pair "mult <= 1 << shift" is true. For the case where "mult > 1 << shift" we can apply the rounding add only for the minimum delta value to make sure that the backward conversion is not less than the given hardware limit. For the upper bound we need to omit the rounding add, because the backwards conversion is always larger than the original latch value. That would violate the upper bound of the hardware device. Though looking closer at the details of that function reveals another bogosity: The upper bounds check is broken as well. Checking for a resulting "clc" value greater than KTIME_MAX after the conversion is pointless. The conversion does: u64 clc = (latch << evt->shift) / evt->mult; So there is no sanity check for (latch << evt->shift) exceeding the 64bit boundary. The latch argument is "unsigned long", so on a 64bit arch the handed in argument could easily lead to an unnoticed shift overflow. With the above rounding fix applied the calculation before the divison is: u64 clc = (latch << evt->shift) + evt->mult - 1; So we need to make sure, that neither the shift nor the rounding add is overflowing the u64 boundary. [ukl: move assignment to rnd after eventually changing mult, fix build issue and correct comment with the right math] Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Cc: Russell King - ARM Linux <linux@arm.linux.org.uk> Cc: Marc Kleine-Budde <mkl@pengutronix.de> Cc: nicolas.ferre@atmel.com Cc: Marc Pignat <marc.pignat@hevs.ch> Cc: john.stultz@linaro.org Cc: kernel@pengutronix.de Cc: Ronald Wahl <ronald.wahl@raritan.com> Cc: LAK <linux-arm-kernel@lists.infradead.org> Cc: Ludovic Desroches <ludovic.desroches@atmel.com> Cc: stable@vger.kernel.org Link: http://lkml.kernel.org/r/1380052223-24139-1-git-send-email-u.kleine-koenig@pengutronix.de Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
2013-09-25 03:50:23 +08:00
u64 rnd;
if (WARN_ON(!evt->mult))
evt->mult = 1;
clockevents: Sanitize ticks to nsec conversion Marc Kleine-Budde pointed out, that commit 77cc982 "clocksource: use clockevents_config_and_register() where possible" caused a regression for some of the converted subarchs. The reason is, that the clockevents core code converts the minimal hardware tick delta to a nanosecond value for core internal usage. This conversion is affected by integer math rounding loss, so the backwards conversion to hardware ticks will likely result in a value which is less than the configured hardware limitation. The affected subarchs used their own workaround (SIGH!) which got lost in the conversion. The solution for the issue at hand is simple: adding evt->mult - 1 to the shifted value before the integer divison in the core conversion function takes care of it. But this only works for the case where for the scaled math mult/shift pair "mult <= 1 << shift" is true. For the case where "mult > 1 << shift" we can apply the rounding add only for the minimum delta value to make sure that the backward conversion is not less than the given hardware limit. For the upper bound we need to omit the rounding add, because the backwards conversion is always larger than the original latch value. That would violate the upper bound of the hardware device. Though looking closer at the details of that function reveals another bogosity: The upper bounds check is broken as well. Checking for a resulting "clc" value greater than KTIME_MAX after the conversion is pointless. The conversion does: u64 clc = (latch << evt->shift) / evt->mult; So there is no sanity check for (latch << evt->shift) exceeding the 64bit boundary. The latch argument is "unsigned long", so on a 64bit arch the handed in argument could easily lead to an unnoticed shift overflow. With the above rounding fix applied the calculation before the divison is: u64 clc = (latch << evt->shift) + evt->mult - 1; So we need to make sure, that neither the shift nor the rounding add is overflowing the u64 boundary. [ukl: move assignment to rnd after eventually changing mult, fix build issue and correct comment with the right math] Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Cc: Russell King - ARM Linux <linux@arm.linux.org.uk> Cc: Marc Kleine-Budde <mkl@pengutronix.de> Cc: nicolas.ferre@atmel.com Cc: Marc Pignat <marc.pignat@hevs.ch> Cc: john.stultz@linaro.org Cc: kernel@pengutronix.de Cc: Ronald Wahl <ronald.wahl@raritan.com> Cc: LAK <linux-arm-kernel@lists.infradead.org> Cc: Ludovic Desroches <ludovic.desroches@atmel.com> Cc: stable@vger.kernel.org Link: http://lkml.kernel.org/r/1380052223-24139-1-git-send-email-u.kleine-koenig@pengutronix.de Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
2013-09-25 03:50:23 +08:00
rnd = (u64) evt->mult - 1;
/*
* Upper bound sanity check. If the backwards conversion is
* not equal latch, we know that the above shift overflowed.
*/
if ((clc >> evt->shift) != (u64)latch)
clc = ~0ULL;
/*
* Scaled math oddities:
*
* For mult <= (1 << shift) we can safely add mult - 1 to
* prevent integer rounding loss. So the backwards conversion
* from nsec to device ticks will be correct.
*
* For mult > (1 << shift), i.e. device frequency is > 1GHz we
* need to be careful. Adding mult - 1 will result in a value
* which when converted back to device ticks can be larger
* than latch by up to (mult - 1) >> shift. For the min_delta
* calculation we still want to apply this in order to stay
* above the minimum device ticks limit. For the upper limit
* we would end up with a latch value larger than the upper
* limit of the device, so we omit the add to stay below the
* device upper boundary.
*
* Also omit the add if it would overflow the u64 boundary.
*/
if ((~0ULL - clc > rnd) &&
(!ismax || evt->mult <= (1ULL << evt->shift)))
clockevents: Sanitize ticks to nsec conversion Marc Kleine-Budde pointed out, that commit 77cc982 "clocksource: use clockevents_config_and_register() where possible" caused a regression for some of the converted subarchs. The reason is, that the clockevents core code converts the minimal hardware tick delta to a nanosecond value for core internal usage. This conversion is affected by integer math rounding loss, so the backwards conversion to hardware ticks will likely result in a value which is less than the configured hardware limitation. The affected subarchs used their own workaround (SIGH!) which got lost in the conversion. The solution for the issue at hand is simple: adding evt->mult - 1 to the shifted value before the integer divison in the core conversion function takes care of it. But this only works for the case where for the scaled math mult/shift pair "mult <= 1 << shift" is true. For the case where "mult > 1 << shift" we can apply the rounding add only for the minimum delta value to make sure that the backward conversion is not less than the given hardware limit. For the upper bound we need to omit the rounding add, because the backwards conversion is always larger than the original latch value. That would violate the upper bound of the hardware device. Though looking closer at the details of that function reveals another bogosity: The upper bounds check is broken as well. Checking for a resulting "clc" value greater than KTIME_MAX after the conversion is pointless. The conversion does: u64 clc = (latch << evt->shift) / evt->mult; So there is no sanity check for (latch << evt->shift) exceeding the 64bit boundary. The latch argument is "unsigned long", so on a 64bit arch the handed in argument could easily lead to an unnoticed shift overflow. With the above rounding fix applied the calculation before the divison is: u64 clc = (latch << evt->shift) + evt->mult - 1; So we need to make sure, that neither the shift nor the rounding add is overflowing the u64 boundary. [ukl: move assignment to rnd after eventually changing mult, fix build issue and correct comment with the right math] Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Cc: Russell King - ARM Linux <linux@arm.linux.org.uk> Cc: Marc Kleine-Budde <mkl@pengutronix.de> Cc: nicolas.ferre@atmel.com Cc: Marc Pignat <marc.pignat@hevs.ch> Cc: john.stultz@linaro.org Cc: kernel@pengutronix.de Cc: Ronald Wahl <ronald.wahl@raritan.com> Cc: LAK <linux-arm-kernel@lists.infradead.org> Cc: Ludovic Desroches <ludovic.desroches@atmel.com> Cc: stable@vger.kernel.org Link: http://lkml.kernel.org/r/1380052223-24139-1-git-send-email-u.kleine-koenig@pengutronix.de Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
2013-09-25 03:50:23 +08:00
clc += rnd;
do_div(clc, evt->mult);
clockevents: Sanitize ticks to nsec conversion Marc Kleine-Budde pointed out, that commit 77cc982 "clocksource: use clockevents_config_and_register() where possible" caused a regression for some of the converted subarchs. The reason is, that the clockevents core code converts the minimal hardware tick delta to a nanosecond value for core internal usage. This conversion is affected by integer math rounding loss, so the backwards conversion to hardware ticks will likely result in a value which is less than the configured hardware limitation. The affected subarchs used their own workaround (SIGH!) which got lost in the conversion. The solution for the issue at hand is simple: adding evt->mult - 1 to the shifted value before the integer divison in the core conversion function takes care of it. But this only works for the case where for the scaled math mult/shift pair "mult <= 1 << shift" is true. For the case where "mult > 1 << shift" we can apply the rounding add only for the minimum delta value to make sure that the backward conversion is not less than the given hardware limit. For the upper bound we need to omit the rounding add, because the backwards conversion is always larger than the original latch value. That would violate the upper bound of the hardware device. Though looking closer at the details of that function reveals another bogosity: The upper bounds check is broken as well. Checking for a resulting "clc" value greater than KTIME_MAX after the conversion is pointless. The conversion does: u64 clc = (latch << evt->shift) / evt->mult; So there is no sanity check for (latch << evt->shift) exceeding the 64bit boundary. The latch argument is "unsigned long", so on a 64bit arch the handed in argument could easily lead to an unnoticed shift overflow. With the above rounding fix applied the calculation before the divison is: u64 clc = (latch << evt->shift) + evt->mult - 1; So we need to make sure, that neither the shift nor the rounding add is overflowing the u64 boundary. [ukl: move assignment to rnd after eventually changing mult, fix build issue and correct comment with the right math] Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Cc: Russell King - ARM Linux <linux@arm.linux.org.uk> Cc: Marc Kleine-Budde <mkl@pengutronix.de> Cc: nicolas.ferre@atmel.com Cc: Marc Pignat <marc.pignat@hevs.ch> Cc: john.stultz@linaro.org Cc: kernel@pengutronix.de Cc: Ronald Wahl <ronald.wahl@raritan.com> Cc: LAK <linux-arm-kernel@lists.infradead.org> Cc: Ludovic Desroches <ludovic.desroches@atmel.com> Cc: stable@vger.kernel.org Link: http://lkml.kernel.org/r/1380052223-24139-1-git-send-email-u.kleine-koenig@pengutronix.de Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
2013-09-25 03:50:23 +08:00
/* Deltas less than 1usec are pointless noise */
return clc > 1000 ? clc : 1000;
}
/**
* clockevents_delta2ns - Convert a latch value (device ticks) to nanoseconds
* @latch: value to convert
* @evt: pointer to clock event device descriptor
*
* Math helper, returns latch value converted to nanoseconds (bound checked)
*/
u64 clockevent_delta2ns(unsigned long latch, struct clock_event_device *evt)
{
return cev_delta2ns(latch, evt, false);
}
EXPORT_SYMBOL_GPL(clockevent_delta2ns);
static int __clockevents_switch_state(struct clock_event_device *dev,
enum clock_event_state state)
clockevents: Introduce mode specific callbacks It is not possible for the clockevents core to know which modes (other than those with a corresponding feature flag) are supported by a particular implementation. And drivers are expected to handle transition to all modes elegantly, as ->set_mode() would be issued for them unconditionally. Now, adding support for a new mode complicates things a bit if we want to use the legacy ->set_mode() callback. We need to closely review all clockevents drivers to see if they would break on addition of a new mode. And after such reviews, it is found that we have to do non-trivial changes to most of the drivers [1]. Introduce mode-specific set_mode_*() callbacks, some of which the drivers may or may not implement. A missing callback would clearly convey the message that the corresponding mode isn't supported. A driver may still choose to keep supporting the legacy ->set_mode() callback, but ->set_mode() wouldn't be supporting any new modes beyond RESUME. If a driver wants to benefit from using a new mode, it would be required to migrate to the mode specific callbacks. The legacy ->set_mode() callback and the newly introduced mode-specific callbacks are mutually exclusive. Only one of them should be supported by the driver. Sanity check is done at the time of registration to distinguish between optional and required callbacks and to make error recovery and handling simpler. If the legacy ->set_mode() callback is provided, all mode specific ones would be ignored by the core but a warning is thrown if they are present. Call sites calling ->set_mode() directly are also updated to use __clockevents_set_mode() instead, as ->set_mode() may not be available anymore for few drivers. [1] https://lkml.org/lkml/2014/12/9/605 [2] https://lkml.org/lkml/2015/1/23/255 Suggested-by: Thomas Gleixner <tglx@linutronix.de> [2] Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Daniel Lezcano <daniel.lezcano@linaro.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: John Stultz <john.stultz@linaro.org> Cc: Kevin Hilman <khilman@linaro.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Preeti U Murthy <preeti@linux.vnet.ibm.com> Cc: linaro-kernel@lists.linaro.org Cc: linaro-networking@linaro.org Link: http://lkml.kernel.org/r/792d59a40423f0acffc9bb0bec9de1341a06fa02.1423788565.git.viresh.kumar@linaro.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-02-13 08:54:56 +08:00
{
if (dev->features & CLOCK_EVT_FEAT_DUMMY)
return 0;
clockevents: Manage device's state separately for the core 'enum clock_event_mode' is used for two purposes today: - to pass mode to the driver of clockevent device::set_mode(). - for managing state of the device for clockevents core. For supporting new modes/states we have moved away from the legacy set_mode() callback to new per-mode/state callbacks. New modes/states shouldn't be exposed to the legacy (now OBSOLOTE) callbacks and so we shouldn't add new states to 'enum clock_event_mode'. Lets have separate enums for the two use cases mentioned above. Keep using the earlier enum for legacy set_mode() callback and mark it OBSOLETE. And add another enum to clearly specify the possible states of a clockevent device. This also renames the newly added per-mode callbacks to reflect state changes. We haven't got rid of 'mode' member of 'struct clock_event_device' as it is used by some of the clockevent drivers and it would automatically die down once we migrate those drivers to the new interface. It ('mode') is only updated now for the drivers using the legacy interface. Suggested-by: Peter Zijlstra <peterz@infradead.org> Suggested-by: Ingo Molnar <mingo@kernel.org> Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org> Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Daniel Lezcano <daniel.lezcano@linaro.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Kevin Hilman <khilman@linaro.org> Cc: Preeti U Murthy <preeti@linux.vnet.ibm.com> Cc: linaro-kernel@lists.linaro.org Cc: linaro-networking@linaro.org Cc: linux-arm-kernel@lists.infradead.org Link: http://lkml.kernel.org/r/b6b0143a8a57bd58352ad35e08c25424c879c0cb.1425037853.git.viresh.kumar@linaro.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-02-27 19:51:33 +08:00
/* Transition with new state-specific callbacks */
switch (state) {
case CLOCK_EVT_STATE_DETACHED:
/* The clockevent device is getting replaced. Shut it down. */
clockevents: Introduce mode specific callbacks It is not possible for the clockevents core to know which modes (other than those with a corresponding feature flag) are supported by a particular implementation. And drivers are expected to handle transition to all modes elegantly, as ->set_mode() would be issued for them unconditionally. Now, adding support for a new mode complicates things a bit if we want to use the legacy ->set_mode() callback. We need to closely review all clockevents drivers to see if they would break on addition of a new mode. And after such reviews, it is found that we have to do non-trivial changes to most of the drivers [1]. Introduce mode-specific set_mode_*() callbacks, some of which the drivers may or may not implement. A missing callback would clearly convey the message that the corresponding mode isn't supported. A driver may still choose to keep supporting the legacy ->set_mode() callback, but ->set_mode() wouldn't be supporting any new modes beyond RESUME. If a driver wants to benefit from using a new mode, it would be required to migrate to the mode specific callbacks. The legacy ->set_mode() callback and the newly introduced mode-specific callbacks are mutually exclusive. Only one of them should be supported by the driver. Sanity check is done at the time of registration to distinguish between optional and required callbacks and to make error recovery and handling simpler. If the legacy ->set_mode() callback is provided, all mode specific ones would be ignored by the core but a warning is thrown if they are present. Call sites calling ->set_mode() directly are also updated to use __clockevents_set_mode() instead, as ->set_mode() may not be available anymore for few drivers. [1] https://lkml.org/lkml/2014/12/9/605 [2] https://lkml.org/lkml/2015/1/23/255 Suggested-by: Thomas Gleixner <tglx@linutronix.de> [2] Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Daniel Lezcano <daniel.lezcano@linaro.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: John Stultz <john.stultz@linaro.org> Cc: Kevin Hilman <khilman@linaro.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Preeti U Murthy <preeti@linux.vnet.ibm.com> Cc: linaro-kernel@lists.linaro.org Cc: linaro-networking@linaro.org Link: http://lkml.kernel.org/r/792d59a40423f0acffc9bb0bec9de1341a06fa02.1423788565.git.viresh.kumar@linaro.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-02-13 08:54:56 +08:00
clockevents: Manage device's state separately for the core 'enum clock_event_mode' is used for two purposes today: - to pass mode to the driver of clockevent device::set_mode(). - for managing state of the device for clockevents core. For supporting new modes/states we have moved away from the legacy set_mode() callback to new per-mode/state callbacks. New modes/states shouldn't be exposed to the legacy (now OBSOLOTE) callbacks and so we shouldn't add new states to 'enum clock_event_mode'. Lets have separate enums for the two use cases mentioned above. Keep using the earlier enum for legacy set_mode() callback and mark it OBSOLETE. And add another enum to clearly specify the possible states of a clockevent device. This also renames the newly added per-mode callbacks to reflect state changes. We haven't got rid of 'mode' member of 'struct clock_event_device' as it is used by some of the clockevent drivers and it would automatically die down once we migrate those drivers to the new interface. It ('mode') is only updated now for the drivers using the legacy interface. Suggested-by: Peter Zijlstra <peterz@infradead.org> Suggested-by: Ingo Molnar <mingo@kernel.org> Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org> Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Daniel Lezcano <daniel.lezcano@linaro.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Kevin Hilman <khilman@linaro.org> Cc: Preeti U Murthy <preeti@linux.vnet.ibm.com> Cc: linaro-kernel@lists.linaro.org Cc: linaro-networking@linaro.org Cc: linux-arm-kernel@lists.infradead.org Link: http://lkml.kernel.org/r/b6b0143a8a57bd58352ad35e08c25424c879c0cb.1425037853.git.viresh.kumar@linaro.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-02-27 19:51:33 +08:00
case CLOCK_EVT_STATE_SHUTDOWN:
if (dev->set_state_shutdown)
return dev->set_state_shutdown(dev);
return 0;
clockevents: Introduce mode specific callbacks It is not possible for the clockevents core to know which modes (other than those with a corresponding feature flag) are supported by a particular implementation. And drivers are expected to handle transition to all modes elegantly, as ->set_mode() would be issued for them unconditionally. Now, adding support for a new mode complicates things a bit if we want to use the legacy ->set_mode() callback. We need to closely review all clockevents drivers to see if they would break on addition of a new mode. And after such reviews, it is found that we have to do non-trivial changes to most of the drivers [1]. Introduce mode-specific set_mode_*() callbacks, some of which the drivers may or may not implement. A missing callback would clearly convey the message that the corresponding mode isn't supported. A driver may still choose to keep supporting the legacy ->set_mode() callback, but ->set_mode() wouldn't be supporting any new modes beyond RESUME. If a driver wants to benefit from using a new mode, it would be required to migrate to the mode specific callbacks. The legacy ->set_mode() callback and the newly introduced mode-specific callbacks are mutually exclusive. Only one of them should be supported by the driver. Sanity check is done at the time of registration to distinguish between optional and required callbacks and to make error recovery and handling simpler. If the legacy ->set_mode() callback is provided, all mode specific ones would be ignored by the core but a warning is thrown if they are present. Call sites calling ->set_mode() directly are also updated to use __clockevents_set_mode() instead, as ->set_mode() may not be available anymore for few drivers. [1] https://lkml.org/lkml/2014/12/9/605 [2] https://lkml.org/lkml/2015/1/23/255 Suggested-by: Thomas Gleixner <tglx@linutronix.de> [2] Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Daniel Lezcano <daniel.lezcano@linaro.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: John Stultz <john.stultz@linaro.org> Cc: Kevin Hilman <khilman@linaro.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Preeti U Murthy <preeti@linux.vnet.ibm.com> Cc: linaro-kernel@lists.linaro.org Cc: linaro-networking@linaro.org Link: http://lkml.kernel.org/r/792d59a40423f0acffc9bb0bec9de1341a06fa02.1423788565.git.viresh.kumar@linaro.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-02-13 08:54:56 +08:00
clockevents: Manage device's state separately for the core 'enum clock_event_mode' is used for two purposes today: - to pass mode to the driver of clockevent device::set_mode(). - for managing state of the device for clockevents core. For supporting new modes/states we have moved away from the legacy set_mode() callback to new per-mode/state callbacks. New modes/states shouldn't be exposed to the legacy (now OBSOLOTE) callbacks and so we shouldn't add new states to 'enum clock_event_mode'. Lets have separate enums for the two use cases mentioned above. Keep using the earlier enum for legacy set_mode() callback and mark it OBSOLETE. And add another enum to clearly specify the possible states of a clockevent device. This also renames the newly added per-mode callbacks to reflect state changes. We haven't got rid of 'mode' member of 'struct clock_event_device' as it is used by some of the clockevent drivers and it would automatically die down once we migrate those drivers to the new interface. It ('mode') is only updated now for the drivers using the legacy interface. Suggested-by: Peter Zijlstra <peterz@infradead.org> Suggested-by: Ingo Molnar <mingo@kernel.org> Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org> Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Daniel Lezcano <daniel.lezcano@linaro.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Kevin Hilman <khilman@linaro.org> Cc: Preeti U Murthy <preeti@linux.vnet.ibm.com> Cc: linaro-kernel@lists.linaro.org Cc: linaro-networking@linaro.org Cc: linux-arm-kernel@lists.infradead.org Link: http://lkml.kernel.org/r/b6b0143a8a57bd58352ad35e08c25424c879c0cb.1425037853.git.viresh.kumar@linaro.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-02-27 19:51:33 +08:00
case CLOCK_EVT_STATE_PERIODIC:
clockevents: Introduce mode specific callbacks It is not possible for the clockevents core to know which modes (other than those with a corresponding feature flag) are supported by a particular implementation. And drivers are expected to handle transition to all modes elegantly, as ->set_mode() would be issued for them unconditionally. Now, adding support for a new mode complicates things a bit if we want to use the legacy ->set_mode() callback. We need to closely review all clockevents drivers to see if they would break on addition of a new mode. And after such reviews, it is found that we have to do non-trivial changes to most of the drivers [1]. Introduce mode-specific set_mode_*() callbacks, some of which the drivers may or may not implement. A missing callback would clearly convey the message that the corresponding mode isn't supported. A driver may still choose to keep supporting the legacy ->set_mode() callback, but ->set_mode() wouldn't be supporting any new modes beyond RESUME. If a driver wants to benefit from using a new mode, it would be required to migrate to the mode specific callbacks. The legacy ->set_mode() callback and the newly introduced mode-specific callbacks are mutually exclusive. Only one of them should be supported by the driver. Sanity check is done at the time of registration to distinguish between optional and required callbacks and to make error recovery and handling simpler. If the legacy ->set_mode() callback is provided, all mode specific ones would be ignored by the core but a warning is thrown if they are present. Call sites calling ->set_mode() directly are also updated to use __clockevents_set_mode() instead, as ->set_mode() may not be available anymore for few drivers. [1] https://lkml.org/lkml/2014/12/9/605 [2] https://lkml.org/lkml/2015/1/23/255 Suggested-by: Thomas Gleixner <tglx@linutronix.de> [2] Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Daniel Lezcano <daniel.lezcano@linaro.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: John Stultz <john.stultz@linaro.org> Cc: Kevin Hilman <khilman@linaro.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Preeti U Murthy <preeti@linux.vnet.ibm.com> Cc: linaro-kernel@lists.linaro.org Cc: linaro-networking@linaro.org Link: http://lkml.kernel.org/r/792d59a40423f0acffc9bb0bec9de1341a06fa02.1423788565.git.viresh.kumar@linaro.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-02-13 08:54:56 +08:00
/* Core internal bug */
if (!(dev->features & CLOCK_EVT_FEAT_PERIODIC))
return -ENOSYS;
if (dev->set_state_periodic)
return dev->set_state_periodic(dev);
return 0;
clockevents: Introduce mode specific callbacks It is not possible for the clockevents core to know which modes (other than those with a corresponding feature flag) are supported by a particular implementation. And drivers are expected to handle transition to all modes elegantly, as ->set_mode() would be issued for them unconditionally. Now, adding support for a new mode complicates things a bit if we want to use the legacy ->set_mode() callback. We need to closely review all clockevents drivers to see if they would break on addition of a new mode. And after such reviews, it is found that we have to do non-trivial changes to most of the drivers [1]. Introduce mode-specific set_mode_*() callbacks, some of which the drivers may or may not implement. A missing callback would clearly convey the message that the corresponding mode isn't supported. A driver may still choose to keep supporting the legacy ->set_mode() callback, but ->set_mode() wouldn't be supporting any new modes beyond RESUME. If a driver wants to benefit from using a new mode, it would be required to migrate to the mode specific callbacks. The legacy ->set_mode() callback and the newly introduced mode-specific callbacks are mutually exclusive. Only one of them should be supported by the driver. Sanity check is done at the time of registration to distinguish between optional and required callbacks and to make error recovery and handling simpler. If the legacy ->set_mode() callback is provided, all mode specific ones would be ignored by the core but a warning is thrown if they are present. Call sites calling ->set_mode() directly are also updated to use __clockevents_set_mode() instead, as ->set_mode() may not be available anymore for few drivers. [1] https://lkml.org/lkml/2014/12/9/605 [2] https://lkml.org/lkml/2015/1/23/255 Suggested-by: Thomas Gleixner <tglx@linutronix.de> [2] Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Daniel Lezcano <daniel.lezcano@linaro.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: John Stultz <john.stultz@linaro.org> Cc: Kevin Hilman <khilman@linaro.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Preeti U Murthy <preeti@linux.vnet.ibm.com> Cc: linaro-kernel@lists.linaro.org Cc: linaro-networking@linaro.org Link: http://lkml.kernel.org/r/792d59a40423f0acffc9bb0bec9de1341a06fa02.1423788565.git.viresh.kumar@linaro.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-02-13 08:54:56 +08:00
clockevents: Manage device's state separately for the core 'enum clock_event_mode' is used for two purposes today: - to pass mode to the driver of clockevent device::set_mode(). - for managing state of the device for clockevents core. For supporting new modes/states we have moved away from the legacy set_mode() callback to new per-mode/state callbacks. New modes/states shouldn't be exposed to the legacy (now OBSOLOTE) callbacks and so we shouldn't add new states to 'enum clock_event_mode'. Lets have separate enums for the two use cases mentioned above. Keep using the earlier enum for legacy set_mode() callback and mark it OBSOLETE. And add another enum to clearly specify the possible states of a clockevent device. This also renames the newly added per-mode callbacks to reflect state changes. We haven't got rid of 'mode' member of 'struct clock_event_device' as it is used by some of the clockevent drivers and it would automatically die down once we migrate those drivers to the new interface. It ('mode') is only updated now for the drivers using the legacy interface. Suggested-by: Peter Zijlstra <peterz@infradead.org> Suggested-by: Ingo Molnar <mingo@kernel.org> Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org> Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Daniel Lezcano <daniel.lezcano@linaro.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Kevin Hilman <khilman@linaro.org> Cc: Preeti U Murthy <preeti@linux.vnet.ibm.com> Cc: linaro-kernel@lists.linaro.org Cc: linaro-networking@linaro.org Cc: linux-arm-kernel@lists.infradead.org Link: http://lkml.kernel.org/r/b6b0143a8a57bd58352ad35e08c25424c879c0cb.1425037853.git.viresh.kumar@linaro.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-02-27 19:51:33 +08:00
case CLOCK_EVT_STATE_ONESHOT:
clockevents: Introduce mode specific callbacks It is not possible for the clockevents core to know which modes (other than those with a corresponding feature flag) are supported by a particular implementation. And drivers are expected to handle transition to all modes elegantly, as ->set_mode() would be issued for them unconditionally. Now, adding support for a new mode complicates things a bit if we want to use the legacy ->set_mode() callback. We need to closely review all clockevents drivers to see if they would break on addition of a new mode. And after such reviews, it is found that we have to do non-trivial changes to most of the drivers [1]. Introduce mode-specific set_mode_*() callbacks, some of which the drivers may or may not implement. A missing callback would clearly convey the message that the corresponding mode isn't supported. A driver may still choose to keep supporting the legacy ->set_mode() callback, but ->set_mode() wouldn't be supporting any new modes beyond RESUME. If a driver wants to benefit from using a new mode, it would be required to migrate to the mode specific callbacks. The legacy ->set_mode() callback and the newly introduced mode-specific callbacks are mutually exclusive. Only one of them should be supported by the driver. Sanity check is done at the time of registration to distinguish between optional and required callbacks and to make error recovery and handling simpler. If the legacy ->set_mode() callback is provided, all mode specific ones would be ignored by the core but a warning is thrown if they are present. Call sites calling ->set_mode() directly are also updated to use __clockevents_set_mode() instead, as ->set_mode() may not be available anymore for few drivers. [1] https://lkml.org/lkml/2014/12/9/605 [2] https://lkml.org/lkml/2015/1/23/255 Suggested-by: Thomas Gleixner <tglx@linutronix.de> [2] Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Daniel Lezcano <daniel.lezcano@linaro.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: John Stultz <john.stultz@linaro.org> Cc: Kevin Hilman <khilman@linaro.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Preeti U Murthy <preeti@linux.vnet.ibm.com> Cc: linaro-kernel@lists.linaro.org Cc: linaro-networking@linaro.org Link: http://lkml.kernel.org/r/792d59a40423f0acffc9bb0bec9de1341a06fa02.1423788565.git.viresh.kumar@linaro.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-02-13 08:54:56 +08:00
/* Core internal bug */
if (!(dev->features & CLOCK_EVT_FEAT_ONESHOT))
return -ENOSYS;
if (dev->set_state_oneshot)
return dev->set_state_oneshot(dev);
return 0;
clockevents: Introduce mode specific callbacks It is not possible for the clockevents core to know which modes (other than those with a corresponding feature flag) are supported by a particular implementation. And drivers are expected to handle transition to all modes elegantly, as ->set_mode() would be issued for them unconditionally. Now, adding support for a new mode complicates things a bit if we want to use the legacy ->set_mode() callback. We need to closely review all clockevents drivers to see if they would break on addition of a new mode. And after such reviews, it is found that we have to do non-trivial changes to most of the drivers [1]. Introduce mode-specific set_mode_*() callbacks, some of which the drivers may or may not implement. A missing callback would clearly convey the message that the corresponding mode isn't supported. A driver may still choose to keep supporting the legacy ->set_mode() callback, but ->set_mode() wouldn't be supporting any new modes beyond RESUME. If a driver wants to benefit from using a new mode, it would be required to migrate to the mode specific callbacks. The legacy ->set_mode() callback and the newly introduced mode-specific callbacks are mutually exclusive. Only one of them should be supported by the driver. Sanity check is done at the time of registration to distinguish between optional and required callbacks and to make error recovery and handling simpler. If the legacy ->set_mode() callback is provided, all mode specific ones would be ignored by the core but a warning is thrown if they are present. Call sites calling ->set_mode() directly are also updated to use __clockevents_set_mode() instead, as ->set_mode() may not be available anymore for few drivers. [1] https://lkml.org/lkml/2014/12/9/605 [2] https://lkml.org/lkml/2015/1/23/255 Suggested-by: Thomas Gleixner <tglx@linutronix.de> [2] Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Daniel Lezcano <daniel.lezcano@linaro.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: John Stultz <john.stultz@linaro.org> Cc: Kevin Hilman <khilman@linaro.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Preeti U Murthy <preeti@linux.vnet.ibm.com> Cc: linaro-kernel@lists.linaro.org Cc: linaro-networking@linaro.org Link: http://lkml.kernel.org/r/792d59a40423f0acffc9bb0bec9de1341a06fa02.1423788565.git.viresh.kumar@linaro.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-02-13 08:54:56 +08:00
clockevents: Introduce CLOCK_EVT_STATE_ONESHOT_STOPPED state When no timers/hrtimers are pending, the expiry time is set to a special value: 'KTIME_MAX'. This normally happens with NO_HZ_{IDLE|FULL} in both LOWRES/HIGHRES modes. When 'expiry == KTIME_MAX', we either cancel the 'tick-sched' hrtimer (NOHZ_MODE_HIGHRES) or skip reprogramming clockevent device (NOHZ_MODE_LOWRES). But, the clockevent device is already reprogrammed from the tick-handler for next tick. As the clock event device is programmed in ONESHOT mode it will at least fire one more time (unnecessarily). Timers on few implementations (like arm_arch_timer, etc.) only support PERIODIC mode and their drivers emulate ONESHOT over that. Which means that on these platforms we will get spurious interrupts periodically (at last programmed interval rate, normally tick rate). In order to avoid spurious interrupts, the clockevent device should be stopped or its interrupts should be masked. A simple (yet hacky) solution to get this fixed could be: update hrtimer_force_reprogram() to always reprogram clockevent device and update clockevent drivers to STOP generating events (or delay it to max time) when 'expires' is set to KTIME_MAX. But the drawback here is that every clockevent driver has to be hacked for this particular case and its very easy for new ones to miss this. However, Thomas suggested to add an optional state ONESHOT_STOPPED to solve this problem: lkml.org/lkml/2014/5/9/508. This patch adds support for ONESHOT_STOPPED state in clockevents core. It will only be available to drivers that implement the state-specific callbacks instead of the legacy ->set_mode() callback. Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org> Reviewed-by: Preeti U. Murthy <preeti@linux.vnet.ibm.com> Cc: linaro-kernel@lists.linaro.org Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Kevin Hilman <khilman@linaro.org> Cc: Daniel Lezcano <daniel.lezcano@linaro.org> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/b8b383a03ac07b13312c16850b5106b82e4245b5.1428031396.git.viresh.kumar@linaro.org Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2015-04-03 11:34:04 +08:00
case CLOCK_EVT_STATE_ONESHOT_STOPPED:
/* Core internal bug */
if (WARN_ONCE(!clockevent_state_oneshot(dev),
"Current state: %d\n",
clockevent_get_state(dev)))
clockevents: Introduce CLOCK_EVT_STATE_ONESHOT_STOPPED state When no timers/hrtimers are pending, the expiry time is set to a special value: 'KTIME_MAX'. This normally happens with NO_HZ_{IDLE|FULL} in both LOWRES/HIGHRES modes. When 'expiry == KTIME_MAX', we either cancel the 'tick-sched' hrtimer (NOHZ_MODE_HIGHRES) or skip reprogramming clockevent device (NOHZ_MODE_LOWRES). But, the clockevent device is already reprogrammed from the tick-handler for next tick. As the clock event device is programmed in ONESHOT mode it will at least fire one more time (unnecessarily). Timers on few implementations (like arm_arch_timer, etc.) only support PERIODIC mode and their drivers emulate ONESHOT over that. Which means that on these platforms we will get spurious interrupts periodically (at last programmed interval rate, normally tick rate). In order to avoid spurious interrupts, the clockevent device should be stopped or its interrupts should be masked. A simple (yet hacky) solution to get this fixed could be: update hrtimer_force_reprogram() to always reprogram clockevent device and update clockevent drivers to STOP generating events (or delay it to max time) when 'expires' is set to KTIME_MAX. But the drawback here is that every clockevent driver has to be hacked for this particular case and its very easy for new ones to miss this. However, Thomas suggested to add an optional state ONESHOT_STOPPED to solve this problem: lkml.org/lkml/2014/5/9/508. This patch adds support for ONESHOT_STOPPED state in clockevents core. It will only be available to drivers that implement the state-specific callbacks instead of the legacy ->set_mode() callback. Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org> Reviewed-by: Preeti U. Murthy <preeti@linux.vnet.ibm.com> Cc: linaro-kernel@lists.linaro.org Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Kevin Hilman <khilman@linaro.org> Cc: Daniel Lezcano <daniel.lezcano@linaro.org> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/b8b383a03ac07b13312c16850b5106b82e4245b5.1428031396.git.viresh.kumar@linaro.org Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2015-04-03 11:34:04 +08:00
return -EINVAL;
if (dev->set_state_oneshot_stopped)
return dev->set_state_oneshot_stopped(dev);
else
return -ENOSYS;
clockevents: Introduce mode specific callbacks It is not possible for the clockevents core to know which modes (other than those with a corresponding feature flag) are supported by a particular implementation. And drivers are expected to handle transition to all modes elegantly, as ->set_mode() would be issued for them unconditionally. Now, adding support for a new mode complicates things a bit if we want to use the legacy ->set_mode() callback. We need to closely review all clockevents drivers to see if they would break on addition of a new mode. And after such reviews, it is found that we have to do non-trivial changes to most of the drivers [1]. Introduce mode-specific set_mode_*() callbacks, some of which the drivers may or may not implement. A missing callback would clearly convey the message that the corresponding mode isn't supported. A driver may still choose to keep supporting the legacy ->set_mode() callback, but ->set_mode() wouldn't be supporting any new modes beyond RESUME. If a driver wants to benefit from using a new mode, it would be required to migrate to the mode specific callbacks. The legacy ->set_mode() callback and the newly introduced mode-specific callbacks are mutually exclusive. Only one of them should be supported by the driver. Sanity check is done at the time of registration to distinguish between optional and required callbacks and to make error recovery and handling simpler. If the legacy ->set_mode() callback is provided, all mode specific ones would be ignored by the core but a warning is thrown if they are present. Call sites calling ->set_mode() directly are also updated to use __clockevents_set_mode() instead, as ->set_mode() may not be available anymore for few drivers. [1] https://lkml.org/lkml/2014/12/9/605 [2] https://lkml.org/lkml/2015/1/23/255 Suggested-by: Thomas Gleixner <tglx@linutronix.de> [2] Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Daniel Lezcano <daniel.lezcano@linaro.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: John Stultz <john.stultz@linaro.org> Cc: Kevin Hilman <khilman@linaro.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Preeti U Murthy <preeti@linux.vnet.ibm.com> Cc: linaro-kernel@lists.linaro.org Cc: linaro-networking@linaro.org Link: http://lkml.kernel.org/r/792d59a40423f0acffc9bb0bec9de1341a06fa02.1423788565.git.viresh.kumar@linaro.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-02-13 08:54:56 +08:00
default:
return -ENOSYS;
}
}
/**
* clockevents_switch_state - set the operating state of a clock event device
* @dev: device to modify
clockevents: Manage device's state separately for the core 'enum clock_event_mode' is used for two purposes today: - to pass mode to the driver of clockevent device::set_mode(). - for managing state of the device for clockevents core. For supporting new modes/states we have moved away from the legacy set_mode() callback to new per-mode/state callbacks. New modes/states shouldn't be exposed to the legacy (now OBSOLOTE) callbacks and so we shouldn't add new states to 'enum clock_event_mode'. Lets have separate enums for the two use cases mentioned above. Keep using the earlier enum for legacy set_mode() callback and mark it OBSOLETE. And add another enum to clearly specify the possible states of a clockevent device. This also renames the newly added per-mode callbacks to reflect state changes. We haven't got rid of 'mode' member of 'struct clock_event_device' as it is used by some of the clockevent drivers and it would automatically die down once we migrate those drivers to the new interface. It ('mode') is only updated now for the drivers using the legacy interface. Suggested-by: Peter Zijlstra <peterz@infradead.org> Suggested-by: Ingo Molnar <mingo@kernel.org> Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org> Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Daniel Lezcano <daniel.lezcano@linaro.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Kevin Hilman <khilman@linaro.org> Cc: Preeti U Murthy <preeti@linux.vnet.ibm.com> Cc: linaro-kernel@lists.linaro.org Cc: linaro-networking@linaro.org Cc: linux-arm-kernel@lists.infradead.org Link: http://lkml.kernel.org/r/b6b0143a8a57bd58352ad35e08c25424c879c0cb.1425037853.git.viresh.kumar@linaro.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-02-27 19:51:33 +08:00
* @state: new state
*
* Must be called with interrupts disabled !
*/
void clockevents_switch_state(struct clock_event_device *dev,
enum clock_event_state state)
{
if (clockevent_get_state(dev) != state) {
if (__clockevents_switch_state(dev, state))
clockevents: Introduce mode specific callbacks It is not possible for the clockevents core to know which modes (other than those with a corresponding feature flag) are supported by a particular implementation. And drivers are expected to handle transition to all modes elegantly, as ->set_mode() would be issued for them unconditionally. Now, adding support for a new mode complicates things a bit if we want to use the legacy ->set_mode() callback. We need to closely review all clockevents drivers to see if they would break on addition of a new mode. And after such reviews, it is found that we have to do non-trivial changes to most of the drivers [1]. Introduce mode-specific set_mode_*() callbacks, some of which the drivers may or may not implement. A missing callback would clearly convey the message that the corresponding mode isn't supported. A driver may still choose to keep supporting the legacy ->set_mode() callback, but ->set_mode() wouldn't be supporting any new modes beyond RESUME. If a driver wants to benefit from using a new mode, it would be required to migrate to the mode specific callbacks. The legacy ->set_mode() callback and the newly introduced mode-specific callbacks are mutually exclusive. Only one of them should be supported by the driver. Sanity check is done at the time of registration to distinguish between optional and required callbacks and to make error recovery and handling simpler. If the legacy ->set_mode() callback is provided, all mode specific ones would be ignored by the core but a warning is thrown if they are present. Call sites calling ->set_mode() directly are also updated to use __clockevents_set_mode() instead, as ->set_mode() may not be available anymore for few drivers. [1] https://lkml.org/lkml/2014/12/9/605 [2] https://lkml.org/lkml/2015/1/23/255 Suggested-by: Thomas Gleixner <tglx@linutronix.de> [2] Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Daniel Lezcano <daniel.lezcano@linaro.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: John Stultz <john.stultz@linaro.org> Cc: Kevin Hilman <khilman@linaro.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Preeti U Murthy <preeti@linux.vnet.ibm.com> Cc: linaro-kernel@lists.linaro.org Cc: linaro-networking@linaro.org Link: http://lkml.kernel.org/r/792d59a40423f0acffc9bb0bec9de1341a06fa02.1423788565.git.viresh.kumar@linaro.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-02-13 08:54:56 +08:00
return;
clockevent_set_state(dev, state);
/*
* A nsec2cyc multiplicator of 0 is invalid and we'd crash
* on it, so fix it up and emit a warning:
*/
if (clockevent_state_oneshot(dev)) {
if (WARN_ON(!dev->mult))
dev->mult = 1;
}
}
}
/**
* clockevents_shutdown - shutdown the device and clear next_event
* @dev: device to shutdown
*/
void clockevents_shutdown(struct clock_event_device *dev)
{
clockevents_switch_state(dev, CLOCK_EVT_STATE_SHUTDOWN);
dev->next_event = KTIME_MAX;
}
/**
* clockevents_tick_resume - Resume the tick device before using it again
* @dev: device to resume
*/
int clockevents_tick_resume(struct clock_event_device *dev)
{
int ret = 0;
if (dev->tick_resume)
clockevents: Manage device's state separately for the core 'enum clock_event_mode' is used for two purposes today: - to pass mode to the driver of clockevent device::set_mode(). - for managing state of the device for clockevents core. For supporting new modes/states we have moved away from the legacy set_mode() callback to new per-mode/state callbacks. New modes/states shouldn't be exposed to the legacy (now OBSOLOTE) callbacks and so we shouldn't add new states to 'enum clock_event_mode'. Lets have separate enums for the two use cases mentioned above. Keep using the earlier enum for legacy set_mode() callback and mark it OBSOLETE. And add another enum to clearly specify the possible states of a clockevent device. This also renames the newly added per-mode callbacks to reflect state changes. We haven't got rid of 'mode' member of 'struct clock_event_device' as it is used by some of the clockevent drivers and it would automatically die down once we migrate those drivers to the new interface. It ('mode') is only updated now for the drivers using the legacy interface. Suggested-by: Peter Zijlstra <peterz@infradead.org> Suggested-by: Ingo Molnar <mingo@kernel.org> Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org> Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Daniel Lezcano <daniel.lezcano@linaro.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Kevin Hilman <khilman@linaro.org> Cc: Preeti U Murthy <preeti@linux.vnet.ibm.com> Cc: linaro-kernel@lists.linaro.org Cc: linaro-networking@linaro.org Cc: linux-arm-kernel@lists.infradead.org Link: http://lkml.kernel.org/r/b6b0143a8a57bd58352ad35e08c25424c879c0cb.1425037853.git.viresh.kumar@linaro.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-02-27 19:51:33 +08:00
ret = dev->tick_resume(dev);
return ret;
}
#ifdef CONFIG_GENERIC_CLOCKEVENTS_MIN_ADJUST
/* Limit min_delta to a jiffie */
#define MIN_DELTA_LIMIT (NSEC_PER_SEC / HZ)
/**
* clockevents_increase_min_delta - raise minimum delta of a clock event device
* @dev: device to increase the minimum delta
*
* Returns 0 on success, -ETIME when the minimum delta reached the limit.
*/
static int clockevents_increase_min_delta(struct clock_event_device *dev)
{
/* Nothing to do if we already reached the limit */
if (dev->min_delta_ns >= MIN_DELTA_LIMIT) {
timer: Fix lock inversion between hrtimer_bases.lock and scheduler locks clockevents_increase_min_delta() calls printk() from under hrtimer_bases.lock. That causes lock inversion on scheduler locks because printk() can call into the scheduler. Lockdep puts it as: ====================================================== [ INFO: possible circular locking dependency detected ] 3.15.0-rc8-06195-g939f04b #2 Not tainted ------------------------------------------------------- trinity-main/74 is trying to acquire lock: (&port_lock_key){-.....}, at: [<811c60be>] serial8250_console_write+0x8c/0x10c but task is already holding lock: (hrtimer_bases.lock){-.-...}, at: [<8103caeb>] hrtimer_try_to_cancel+0x13/0x66 which lock already depends on the new lock. the existing dependency chain (in reverse order) is: -> #5 (hrtimer_bases.lock){-.-...}: [<8104a942>] lock_acquire+0x92/0x101 [<8142f11d>] _raw_spin_lock_irqsave+0x2e/0x3e [<8103c918>] __hrtimer_start_range_ns+0x1c/0x197 [<8107ec20>] perf_swevent_start_hrtimer.part.41+0x7a/0x85 [<81080792>] task_clock_event_start+0x3a/0x3f [<810807a4>] task_clock_event_add+0xd/0x14 [<8108259a>] event_sched_in+0xb6/0x17a [<810826a2>] group_sched_in+0x44/0x122 [<81082885>] ctx_sched_in.isra.67+0x105/0x11f [<810828e6>] perf_event_sched_in.isra.70+0x47/0x4b [<81082bf6>] __perf_install_in_context+0x8b/0xa3 [<8107eb8e>] remote_function+0x12/0x2a [<8105f5af>] smp_call_function_single+0x2d/0x53 [<8107e17d>] task_function_call+0x30/0x36 [<8107fb82>] perf_install_in_context+0x87/0xbb [<810852c9>] SYSC_perf_event_open+0x5c6/0x701 [<810856f9>] SyS_perf_event_open+0x17/0x19 [<8142f8ee>] syscall_call+0x7/0xb -> #4 (&ctx->lock){......}: [<8104a942>] lock_acquire+0x92/0x101 [<8142f04c>] _raw_spin_lock+0x21/0x30 [<81081df3>] __perf_event_task_sched_out+0x1dc/0x34f [<8142cacc>] __schedule+0x4c6/0x4cb [<8142cae0>] schedule+0xf/0x11 [<8142f9a6>] work_resched+0x5/0x30 -> #3 (&rq->lock){-.-.-.}: [<8104a942>] lock_acquire+0x92/0x101 [<8142f04c>] _raw_spin_lock+0x21/0x30 [<81040873>] __task_rq_lock+0x33/0x3a [<8104184c>] wake_up_new_task+0x25/0xc2 [<8102474b>] do_fork+0x15c/0x2a0 [<810248a9>] kernel_thread+0x1a/0x1f [<814232a2>] rest_init+0x1a/0x10e [<817af949>] start_kernel+0x303/0x308 [<817af2ab>] i386_start_kernel+0x79/0x7d -> #2 (&p->pi_lock){-.-...}: [<8104a942>] lock_acquire+0x92/0x101 [<8142f11d>] _raw_spin_lock_irqsave+0x2e/0x3e [<810413dd>] try_to_wake_up+0x1d/0xd6 [<810414cd>] default_wake_function+0xb/0xd [<810461f3>] __wake_up_common+0x39/0x59 [<81046346>] __wake_up+0x29/0x3b [<811b8733>] tty_wakeup+0x49/0x51 [<811c3568>] uart_write_wakeup+0x17/0x19 [<811c5dc1>] serial8250_tx_chars+0xbc/0xfb [<811c5f28>] serial8250_handle_irq+0x54/0x6a [<811c5f57>] serial8250_default_handle_irq+0x19/0x1c [<811c56d8>] serial8250_interrupt+0x38/0x9e [<810510e7>] handle_irq_event_percpu+0x5f/0x1e2 [<81051296>] handle_irq_event+0x2c/0x43 [<81052cee>] handle_level_irq+0x57/0x80 [<81002a72>] handle_irq+0x46/0x5c [<810027df>] do_IRQ+0x32/0x89 [<8143036e>] common_interrupt+0x2e/0x33 [<8142f23c>] _raw_spin_unlock_irqrestore+0x3f/0x49 [<811c25a4>] uart_start+0x2d/0x32 [<811c2c04>] uart_write+0xc7/0xd6 [<811bc6f6>] n_tty_write+0xb8/0x35e [<811b9beb>] tty_write+0x163/0x1e4 [<811b9cd9>] redirected_tty_write+0x6d/0x75 [<810b6ed6>] vfs_write+0x75/0xb0 [<810b7265>] SyS_write+0x44/0x77 [<8142f8ee>] syscall_call+0x7/0xb -> #1 (&tty->write_wait){-.....}: [<8104a942>] lock_acquire+0x92/0x101 [<8142f11d>] _raw_spin_lock_irqsave+0x2e/0x3e [<81046332>] __wake_up+0x15/0x3b [<811b8733>] tty_wakeup+0x49/0x51 [<811c3568>] uart_write_wakeup+0x17/0x19 [<811c5dc1>] serial8250_tx_chars+0xbc/0xfb [<811c5f28>] serial8250_handle_irq+0x54/0x6a [<811c5f57>] serial8250_default_handle_irq+0x19/0x1c [<811c56d8>] serial8250_interrupt+0x38/0x9e [<810510e7>] handle_irq_event_percpu+0x5f/0x1e2 [<81051296>] handle_irq_event+0x2c/0x43 [<81052cee>] handle_level_irq+0x57/0x80 [<81002a72>] handle_irq+0x46/0x5c [<810027df>] do_IRQ+0x32/0x89 [<8143036e>] common_interrupt+0x2e/0x33 [<8142f23c>] _raw_spin_unlock_irqrestore+0x3f/0x49 [<811c25a4>] uart_start+0x2d/0x32 [<811c2c04>] uart_write+0xc7/0xd6 [<811bc6f6>] n_tty_write+0xb8/0x35e [<811b9beb>] tty_write+0x163/0x1e4 [<811b9cd9>] redirected_tty_write+0x6d/0x75 [<810b6ed6>] vfs_write+0x75/0xb0 [<810b7265>] SyS_write+0x44/0x77 [<8142f8ee>] syscall_call+0x7/0xb -> #0 (&port_lock_key){-.....}: [<8104a62d>] __lock_acquire+0x9ea/0xc6d [<8104a942>] lock_acquire+0x92/0x101 [<8142f11d>] _raw_spin_lock_irqsave+0x2e/0x3e [<811c60be>] serial8250_console_write+0x8c/0x10c [<8104e402>] call_console_drivers.constprop.31+0x87/0x118 [<8104f5d5>] console_unlock+0x1d7/0x398 [<8104fb70>] vprintk_emit+0x3da/0x3e4 [<81425f76>] printk+0x17/0x19 [<8105bfa0>] clockevents_program_min_delta+0x104/0x116 [<8105c548>] clockevents_program_event+0xe7/0xf3 [<8105cc1c>] tick_program_event+0x1e/0x23 [<8103c43c>] hrtimer_force_reprogram+0x88/0x8f [<8103c49e>] __remove_hrtimer+0x5b/0x79 [<8103cb21>] hrtimer_try_to_cancel+0x49/0x66 [<8103cb4b>] hrtimer_cancel+0xd/0x18 [<8107f102>] perf_swevent_cancel_hrtimer.part.60+0x2b/0x30 [<81080705>] task_clock_event_stop+0x20/0x64 [<81080756>] task_clock_event_del+0xd/0xf [<81081350>] event_sched_out+0xab/0x11e [<810813e0>] group_sched_out+0x1d/0x66 [<81081682>] ctx_sched_out+0xaf/0xbf [<81081e04>] __perf_event_task_sched_out+0x1ed/0x34f [<8142cacc>] __schedule+0x4c6/0x4cb [<8142cae0>] schedule+0xf/0x11 [<8142f9a6>] work_resched+0x5/0x30 other info that might help us debug this: Chain exists of: &port_lock_key --> &ctx->lock --> hrtimer_bases.lock Possible unsafe locking scenario: CPU0 CPU1 ---- ---- lock(hrtimer_bases.lock); lock(&ctx->lock); lock(hrtimer_bases.lock); lock(&port_lock_key); *** DEADLOCK *** 4 locks held by trinity-main/74: #0: (&rq->lock){-.-.-.}, at: [<8142c6f3>] __schedule+0xed/0x4cb #1: (&ctx->lock){......}, at: [<81081df3>] __perf_event_task_sched_out+0x1dc/0x34f #2: (hrtimer_bases.lock){-.-...}, at: [<8103caeb>] hrtimer_try_to_cancel+0x13/0x66 #3: (console_lock){+.+...}, at: [<8104fb5d>] vprintk_emit+0x3c7/0x3e4 stack backtrace: CPU: 0 PID: 74 Comm: trinity-main Not tainted 3.15.0-rc8-06195-g939f04b #2 00000000 81c3a310 8b995c14 81426f69 8b995c44 81425a99 8161f671 8161f570 8161f538 8161f559 8161f538 8b995c78 8b142bb0 00000004 8b142fdc 8b142bb0 8b995ca8 8104a62d 8b142fac 000016f2 81c3a310 00000001 00000001 00000003 Call Trace: [<81426f69>] dump_stack+0x16/0x18 [<81425a99>] print_circular_bug+0x18f/0x19c [<8104a62d>] __lock_acquire+0x9ea/0xc6d [<8104a942>] lock_acquire+0x92/0x101 [<811c60be>] ? serial8250_console_write+0x8c/0x10c [<811c6032>] ? wait_for_xmitr+0x76/0x76 [<8142f11d>] _raw_spin_lock_irqsave+0x2e/0x3e [<811c60be>] ? serial8250_console_write+0x8c/0x10c [<811c60be>] serial8250_console_write+0x8c/0x10c [<8104af87>] ? lock_release+0x191/0x223 [<811c6032>] ? wait_for_xmitr+0x76/0x76 [<8104e402>] call_console_drivers.constprop.31+0x87/0x118 [<8104f5d5>] console_unlock+0x1d7/0x398 [<8104fb70>] vprintk_emit+0x3da/0x3e4 [<81425f76>] printk+0x17/0x19 [<8105bfa0>] clockevents_program_min_delta+0x104/0x116 [<8105cc1c>] tick_program_event+0x1e/0x23 [<8103c43c>] hrtimer_force_reprogram+0x88/0x8f [<8103c49e>] __remove_hrtimer+0x5b/0x79 [<8103cb21>] hrtimer_try_to_cancel+0x49/0x66 [<8103cb4b>] hrtimer_cancel+0xd/0x18 [<8107f102>] perf_swevent_cancel_hrtimer.part.60+0x2b/0x30 [<81080705>] task_clock_event_stop+0x20/0x64 [<81080756>] task_clock_event_del+0xd/0xf [<81081350>] event_sched_out+0xab/0x11e [<810813e0>] group_sched_out+0x1d/0x66 [<81081682>] ctx_sched_out+0xaf/0xbf [<81081e04>] __perf_event_task_sched_out+0x1ed/0x34f [<8104416d>] ? __dequeue_entity+0x23/0x27 [<81044505>] ? pick_next_task_fair+0xb1/0x120 [<8142cacc>] __schedule+0x4c6/0x4cb [<81047574>] ? trace_hardirqs_off_caller+0xd7/0x108 [<810475b0>] ? trace_hardirqs_off+0xb/0xd [<81056346>] ? rcu_irq_exit+0x64/0x77 Fix the problem by using printk_deferred() which does not call into the scheduler. Reported-by: Fengguang Wu <fengguang.wu@intel.com> Signed-off-by: Jan Kara <jack@suse.cz> Cc: stable@vger.kernel.org Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2014-08-01 18:20:02 +08:00
printk_deferred(KERN_WARNING
"CE: Reprogramming failure. Giving up\n");
dev->next_event = KTIME_MAX;
return -ETIME;
}
if (dev->min_delta_ns < 5000)
dev->min_delta_ns = 5000;
else
dev->min_delta_ns += dev->min_delta_ns >> 1;
if (dev->min_delta_ns > MIN_DELTA_LIMIT)
dev->min_delta_ns = MIN_DELTA_LIMIT;
timer: Fix lock inversion between hrtimer_bases.lock and scheduler locks clockevents_increase_min_delta() calls printk() from under hrtimer_bases.lock. That causes lock inversion on scheduler locks because printk() can call into the scheduler. Lockdep puts it as: ====================================================== [ INFO: possible circular locking dependency detected ] 3.15.0-rc8-06195-g939f04b #2 Not tainted ------------------------------------------------------- trinity-main/74 is trying to acquire lock: (&port_lock_key){-.....}, at: [<811c60be>] serial8250_console_write+0x8c/0x10c but task is already holding lock: (hrtimer_bases.lock){-.-...}, at: [<8103caeb>] hrtimer_try_to_cancel+0x13/0x66 which lock already depends on the new lock. the existing dependency chain (in reverse order) is: -> #5 (hrtimer_bases.lock){-.-...}: [<8104a942>] lock_acquire+0x92/0x101 [<8142f11d>] _raw_spin_lock_irqsave+0x2e/0x3e [<8103c918>] __hrtimer_start_range_ns+0x1c/0x197 [<8107ec20>] perf_swevent_start_hrtimer.part.41+0x7a/0x85 [<81080792>] task_clock_event_start+0x3a/0x3f [<810807a4>] task_clock_event_add+0xd/0x14 [<8108259a>] event_sched_in+0xb6/0x17a [<810826a2>] group_sched_in+0x44/0x122 [<81082885>] ctx_sched_in.isra.67+0x105/0x11f [<810828e6>] perf_event_sched_in.isra.70+0x47/0x4b [<81082bf6>] __perf_install_in_context+0x8b/0xa3 [<8107eb8e>] remote_function+0x12/0x2a [<8105f5af>] smp_call_function_single+0x2d/0x53 [<8107e17d>] task_function_call+0x30/0x36 [<8107fb82>] perf_install_in_context+0x87/0xbb [<810852c9>] SYSC_perf_event_open+0x5c6/0x701 [<810856f9>] SyS_perf_event_open+0x17/0x19 [<8142f8ee>] syscall_call+0x7/0xb -> #4 (&ctx->lock){......}: [<8104a942>] lock_acquire+0x92/0x101 [<8142f04c>] _raw_spin_lock+0x21/0x30 [<81081df3>] __perf_event_task_sched_out+0x1dc/0x34f [<8142cacc>] __schedule+0x4c6/0x4cb [<8142cae0>] schedule+0xf/0x11 [<8142f9a6>] work_resched+0x5/0x30 -> #3 (&rq->lock){-.-.-.}: [<8104a942>] lock_acquire+0x92/0x101 [<8142f04c>] _raw_spin_lock+0x21/0x30 [<81040873>] __task_rq_lock+0x33/0x3a [<8104184c>] wake_up_new_task+0x25/0xc2 [<8102474b>] do_fork+0x15c/0x2a0 [<810248a9>] kernel_thread+0x1a/0x1f [<814232a2>] rest_init+0x1a/0x10e [<817af949>] start_kernel+0x303/0x308 [<817af2ab>] i386_start_kernel+0x79/0x7d -> #2 (&p->pi_lock){-.-...}: [<8104a942>] lock_acquire+0x92/0x101 [<8142f11d>] _raw_spin_lock_irqsave+0x2e/0x3e [<810413dd>] try_to_wake_up+0x1d/0xd6 [<810414cd>] default_wake_function+0xb/0xd [<810461f3>] __wake_up_common+0x39/0x59 [<81046346>] __wake_up+0x29/0x3b [<811b8733>] tty_wakeup+0x49/0x51 [<811c3568>] uart_write_wakeup+0x17/0x19 [<811c5dc1>] serial8250_tx_chars+0xbc/0xfb [<811c5f28>] serial8250_handle_irq+0x54/0x6a [<811c5f57>] serial8250_default_handle_irq+0x19/0x1c [<811c56d8>] serial8250_interrupt+0x38/0x9e [<810510e7>] handle_irq_event_percpu+0x5f/0x1e2 [<81051296>] handle_irq_event+0x2c/0x43 [<81052cee>] handle_level_irq+0x57/0x80 [<81002a72>] handle_irq+0x46/0x5c [<810027df>] do_IRQ+0x32/0x89 [<8143036e>] common_interrupt+0x2e/0x33 [<8142f23c>] _raw_spin_unlock_irqrestore+0x3f/0x49 [<811c25a4>] uart_start+0x2d/0x32 [<811c2c04>] uart_write+0xc7/0xd6 [<811bc6f6>] n_tty_write+0xb8/0x35e [<811b9beb>] tty_write+0x163/0x1e4 [<811b9cd9>] redirected_tty_write+0x6d/0x75 [<810b6ed6>] vfs_write+0x75/0xb0 [<810b7265>] SyS_write+0x44/0x77 [<8142f8ee>] syscall_call+0x7/0xb -> #1 (&tty->write_wait){-.....}: [<8104a942>] lock_acquire+0x92/0x101 [<8142f11d>] _raw_spin_lock_irqsave+0x2e/0x3e [<81046332>] __wake_up+0x15/0x3b [<811b8733>] tty_wakeup+0x49/0x51 [<811c3568>] uart_write_wakeup+0x17/0x19 [<811c5dc1>] serial8250_tx_chars+0xbc/0xfb [<811c5f28>] serial8250_handle_irq+0x54/0x6a [<811c5f57>] serial8250_default_handle_irq+0x19/0x1c [<811c56d8>] serial8250_interrupt+0x38/0x9e [<810510e7>] handle_irq_event_percpu+0x5f/0x1e2 [<81051296>] handle_irq_event+0x2c/0x43 [<81052cee>] handle_level_irq+0x57/0x80 [<81002a72>] handle_irq+0x46/0x5c [<810027df>] do_IRQ+0x32/0x89 [<8143036e>] common_interrupt+0x2e/0x33 [<8142f23c>] _raw_spin_unlock_irqrestore+0x3f/0x49 [<811c25a4>] uart_start+0x2d/0x32 [<811c2c04>] uart_write+0xc7/0xd6 [<811bc6f6>] n_tty_write+0xb8/0x35e [<811b9beb>] tty_write+0x163/0x1e4 [<811b9cd9>] redirected_tty_write+0x6d/0x75 [<810b6ed6>] vfs_write+0x75/0xb0 [<810b7265>] SyS_write+0x44/0x77 [<8142f8ee>] syscall_call+0x7/0xb -> #0 (&port_lock_key){-.....}: [<8104a62d>] __lock_acquire+0x9ea/0xc6d [<8104a942>] lock_acquire+0x92/0x101 [<8142f11d>] _raw_spin_lock_irqsave+0x2e/0x3e [<811c60be>] serial8250_console_write+0x8c/0x10c [<8104e402>] call_console_drivers.constprop.31+0x87/0x118 [<8104f5d5>] console_unlock+0x1d7/0x398 [<8104fb70>] vprintk_emit+0x3da/0x3e4 [<81425f76>] printk+0x17/0x19 [<8105bfa0>] clockevents_program_min_delta+0x104/0x116 [<8105c548>] clockevents_program_event+0xe7/0xf3 [<8105cc1c>] tick_program_event+0x1e/0x23 [<8103c43c>] hrtimer_force_reprogram+0x88/0x8f [<8103c49e>] __remove_hrtimer+0x5b/0x79 [<8103cb21>] hrtimer_try_to_cancel+0x49/0x66 [<8103cb4b>] hrtimer_cancel+0xd/0x18 [<8107f102>] perf_swevent_cancel_hrtimer.part.60+0x2b/0x30 [<81080705>] task_clock_event_stop+0x20/0x64 [<81080756>] task_clock_event_del+0xd/0xf [<81081350>] event_sched_out+0xab/0x11e [<810813e0>] group_sched_out+0x1d/0x66 [<81081682>] ctx_sched_out+0xaf/0xbf [<81081e04>] __perf_event_task_sched_out+0x1ed/0x34f [<8142cacc>] __schedule+0x4c6/0x4cb [<8142cae0>] schedule+0xf/0x11 [<8142f9a6>] work_resched+0x5/0x30 other info that might help us debug this: Chain exists of: &port_lock_key --> &ctx->lock --> hrtimer_bases.lock Possible unsafe locking scenario: CPU0 CPU1 ---- ---- lock(hrtimer_bases.lock); lock(&ctx->lock); lock(hrtimer_bases.lock); lock(&port_lock_key); *** DEADLOCK *** 4 locks held by trinity-main/74: #0: (&rq->lock){-.-.-.}, at: [<8142c6f3>] __schedule+0xed/0x4cb #1: (&ctx->lock){......}, at: [<81081df3>] __perf_event_task_sched_out+0x1dc/0x34f #2: (hrtimer_bases.lock){-.-...}, at: [<8103caeb>] hrtimer_try_to_cancel+0x13/0x66 #3: (console_lock){+.+...}, at: [<8104fb5d>] vprintk_emit+0x3c7/0x3e4 stack backtrace: CPU: 0 PID: 74 Comm: trinity-main Not tainted 3.15.0-rc8-06195-g939f04b #2 00000000 81c3a310 8b995c14 81426f69 8b995c44 81425a99 8161f671 8161f570 8161f538 8161f559 8161f538 8b995c78 8b142bb0 00000004 8b142fdc 8b142bb0 8b995ca8 8104a62d 8b142fac 000016f2 81c3a310 00000001 00000001 00000003 Call Trace: [<81426f69>] dump_stack+0x16/0x18 [<81425a99>] print_circular_bug+0x18f/0x19c [<8104a62d>] __lock_acquire+0x9ea/0xc6d [<8104a942>] lock_acquire+0x92/0x101 [<811c60be>] ? serial8250_console_write+0x8c/0x10c [<811c6032>] ? wait_for_xmitr+0x76/0x76 [<8142f11d>] _raw_spin_lock_irqsave+0x2e/0x3e [<811c60be>] ? serial8250_console_write+0x8c/0x10c [<811c60be>] serial8250_console_write+0x8c/0x10c [<8104af87>] ? lock_release+0x191/0x223 [<811c6032>] ? wait_for_xmitr+0x76/0x76 [<8104e402>] call_console_drivers.constprop.31+0x87/0x118 [<8104f5d5>] console_unlock+0x1d7/0x398 [<8104fb70>] vprintk_emit+0x3da/0x3e4 [<81425f76>] printk+0x17/0x19 [<8105bfa0>] clockevents_program_min_delta+0x104/0x116 [<8105cc1c>] tick_program_event+0x1e/0x23 [<8103c43c>] hrtimer_force_reprogram+0x88/0x8f [<8103c49e>] __remove_hrtimer+0x5b/0x79 [<8103cb21>] hrtimer_try_to_cancel+0x49/0x66 [<8103cb4b>] hrtimer_cancel+0xd/0x18 [<8107f102>] perf_swevent_cancel_hrtimer.part.60+0x2b/0x30 [<81080705>] task_clock_event_stop+0x20/0x64 [<81080756>] task_clock_event_del+0xd/0xf [<81081350>] event_sched_out+0xab/0x11e [<810813e0>] group_sched_out+0x1d/0x66 [<81081682>] ctx_sched_out+0xaf/0xbf [<81081e04>] __perf_event_task_sched_out+0x1ed/0x34f [<8104416d>] ? __dequeue_entity+0x23/0x27 [<81044505>] ? pick_next_task_fair+0xb1/0x120 [<8142cacc>] __schedule+0x4c6/0x4cb [<81047574>] ? trace_hardirqs_off_caller+0xd7/0x108 [<810475b0>] ? trace_hardirqs_off+0xb/0xd [<81056346>] ? rcu_irq_exit+0x64/0x77 Fix the problem by using printk_deferred() which does not call into the scheduler. Reported-by: Fengguang Wu <fengguang.wu@intel.com> Signed-off-by: Jan Kara <jack@suse.cz> Cc: stable@vger.kernel.org Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2014-08-01 18:20:02 +08:00
printk_deferred(KERN_WARNING
"CE: %s increased min_delta_ns to %llu nsec\n",
dev->name ? dev->name : "?",
(unsigned long long) dev->min_delta_ns);
return 0;
}
/**
* clockevents_program_min_delta - Set clock event device to the minimum delay.
* @dev: device to program
*
* Returns 0 on success, -ETIME when the retry loop failed.
*/
static int clockevents_program_min_delta(struct clock_event_device *dev)
{
unsigned long long clc;
int64_t delta;
int i;
for (i = 0;;) {
delta = dev->min_delta_ns;
dev->next_event = ktime_add_ns(ktime_get(), delta);
if (clockevent_state_shutdown(dev))
return 0;
dev->retries++;
clc = ((unsigned long long) delta * dev->mult) >> dev->shift;
if (dev->set_next_event((unsigned long) clc, dev) == 0)
return 0;
if (++i > 2) {
/*
* We tried 3 times to program the device with the
* given min_delta_ns. Try to increase the minimum
* delta, if that fails as well get out of here.
*/
if (clockevents_increase_min_delta(dev))
return -ETIME;
i = 0;
}
}
}
#else /* CONFIG_GENERIC_CLOCKEVENTS_MIN_ADJUST */
/**
* clockevents_program_min_delta - Set clock event device to the minimum delay.
* @dev: device to program
*
* Returns 0 on success, -ETIME when the retry loop failed.
*/
static int clockevents_program_min_delta(struct clock_event_device *dev)
{
unsigned long long clc;
clockevents: Retry programming min delta up to 10 times When CONFIG_GENERIC_CLOCKEVENTS_MIN_ADJUST=n, the call path hrtimer_reprogram -> clockevents_program_event -> clockevents_program_min_delta will not retry if the clock event driver returns -ETIME. If the driver could not satisfy the program_min_delta for any reason, the lack of a retry means the CPU may not receive a tick interrupt, potentially until the counter does a full period. This leads to rcu_sched timeout messages as the stalled CPU is detected by other CPUs, and other issues if the CPU is holding locks or other resources at the point at which it stalls. There have been a couple of observed mechanisms through which a clock event driver could not satisfy the requested min_delta and return -ETIME. With the MIPS GIC driver, the shared execution resource within MT cores means inconventient latency due to execution of instructions from other hardware threads in the core, within gic_next_event, can result in an event being set in the past. Additionally under virtualisation it is possible to get unexpected latency during a clockevent device's set_next_event() callback which can make it return -ETIME even for a delta based on min_delta_ns. It isn't appropriate to use MIN_ADJUST in the virtualisation case as occasional hypervisor induced high latency will cause min_delta_ns to quickly increase to the maximum. Instead, borrow the retry pattern from the MIN_ADJUST case, but without making adjustments. Retry up to 10 times, each time increasing the attempted delta by min_delta, before giving up. [ Matt: Reworked the loop and made retry increase the delta. ] Signed-off-by: James Hogan <jhogan@kernel.org> Signed-off-by: Matt Redfearn <matt.redfearn@mips.com> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Cc: linux-mips@linux-mips.org Cc: Daniel Lezcano <daniel.lezcano@linaro.org> Cc: "Martin Schwidefsky" <schwidefsky@de.ibm.com> Cc: James Hogan <james.hogan@mips.com> Link: https://lkml.kernel.org/r/1508422643-6075-1-git-send-email-matt.redfearn@mips.com
2017-10-19 22:17:23 +08:00
int64_t delta = 0;
int i;
clockevents: Retry programming min delta up to 10 times When CONFIG_GENERIC_CLOCKEVENTS_MIN_ADJUST=n, the call path hrtimer_reprogram -> clockevents_program_event -> clockevents_program_min_delta will not retry if the clock event driver returns -ETIME. If the driver could not satisfy the program_min_delta for any reason, the lack of a retry means the CPU may not receive a tick interrupt, potentially until the counter does a full period. This leads to rcu_sched timeout messages as the stalled CPU is detected by other CPUs, and other issues if the CPU is holding locks or other resources at the point at which it stalls. There have been a couple of observed mechanisms through which a clock event driver could not satisfy the requested min_delta and return -ETIME. With the MIPS GIC driver, the shared execution resource within MT cores means inconventient latency due to execution of instructions from other hardware threads in the core, within gic_next_event, can result in an event being set in the past. Additionally under virtualisation it is possible to get unexpected latency during a clockevent device's set_next_event() callback which can make it return -ETIME even for a delta based on min_delta_ns. It isn't appropriate to use MIN_ADJUST in the virtualisation case as occasional hypervisor induced high latency will cause min_delta_ns to quickly increase to the maximum. Instead, borrow the retry pattern from the MIN_ADJUST case, but without making adjustments. Retry up to 10 times, each time increasing the attempted delta by min_delta, before giving up. [ Matt: Reworked the loop and made retry increase the delta. ] Signed-off-by: James Hogan <jhogan@kernel.org> Signed-off-by: Matt Redfearn <matt.redfearn@mips.com> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Cc: linux-mips@linux-mips.org Cc: Daniel Lezcano <daniel.lezcano@linaro.org> Cc: "Martin Schwidefsky" <schwidefsky@de.ibm.com> Cc: James Hogan <james.hogan@mips.com> Link: https://lkml.kernel.org/r/1508422643-6075-1-git-send-email-matt.redfearn@mips.com
2017-10-19 22:17:23 +08:00
for (i = 0; i < 10; i++) {
delta += dev->min_delta_ns;
dev->next_event = ktime_add_ns(ktime_get(), delta);
clockevents: Retry programming min delta up to 10 times When CONFIG_GENERIC_CLOCKEVENTS_MIN_ADJUST=n, the call path hrtimer_reprogram -> clockevents_program_event -> clockevents_program_min_delta will not retry if the clock event driver returns -ETIME. If the driver could not satisfy the program_min_delta for any reason, the lack of a retry means the CPU may not receive a tick interrupt, potentially until the counter does a full period. This leads to rcu_sched timeout messages as the stalled CPU is detected by other CPUs, and other issues if the CPU is holding locks or other resources at the point at which it stalls. There have been a couple of observed mechanisms through which a clock event driver could not satisfy the requested min_delta and return -ETIME. With the MIPS GIC driver, the shared execution resource within MT cores means inconventient latency due to execution of instructions from other hardware threads in the core, within gic_next_event, can result in an event being set in the past. Additionally under virtualisation it is possible to get unexpected latency during a clockevent device's set_next_event() callback which can make it return -ETIME even for a delta based on min_delta_ns. It isn't appropriate to use MIN_ADJUST in the virtualisation case as occasional hypervisor induced high latency will cause min_delta_ns to quickly increase to the maximum. Instead, borrow the retry pattern from the MIN_ADJUST case, but without making adjustments. Retry up to 10 times, each time increasing the attempted delta by min_delta, before giving up. [ Matt: Reworked the loop and made retry increase the delta. ] Signed-off-by: James Hogan <jhogan@kernel.org> Signed-off-by: Matt Redfearn <matt.redfearn@mips.com> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Cc: linux-mips@linux-mips.org Cc: Daniel Lezcano <daniel.lezcano@linaro.org> Cc: "Martin Schwidefsky" <schwidefsky@de.ibm.com> Cc: James Hogan <james.hogan@mips.com> Link: https://lkml.kernel.org/r/1508422643-6075-1-git-send-email-matt.redfearn@mips.com
2017-10-19 22:17:23 +08:00
if (clockevent_state_shutdown(dev))
return 0;
clockevents: Retry programming min delta up to 10 times When CONFIG_GENERIC_CLOCKEVENTS_MIN_ADJUST=n, the call path hrtimer_reprogram -> clockevents_program_event -> clockevents_program_min_delta will not retry if the clock event driver returns -ETIME. If the driver could not satisfy the program_min_delta for any reason, the lack of a retry means the CPU may not receive a tick interrupt, potentially until the counter does a full period. This leads to rcu_sched timeout messages as the stalled CPU is detected by other CPUs, and other issues if the CPU is holding locks or other resources at the point at which it stalls. There have been a couple of observed mechanisms through which a clock event driver could not satisfy the requested min_delta and return -ETIME. With the MIPS GIC driver, the shared execution resource within MT cores means inconventient latency due to execution of instructions from other hardware threads in the core, within gic_next_event, can result in an event being set in the past. Additionally under virtualisation it is possible to get unexpected latency during a clockevent device's set_next_event() callback which can make it return -ETIME even for a delta based on min_delta_ns. It isn't appropriate to use MIN_ADJUST in the virtualisation case as occasional hypervisor induced high latency will cause min_delta_ns to quickly increase to the maximum. Instead, borrow the retry pattern from the MIN_ADJUST case, but without making adjustments. Retry up to 10 times, each time increasing the attempted delta by min_delta, before giving up. [ Matt: Reworked the loop and made retry increase the delta. ] Signed-off-by: James Hogan <jhogan@kernel.org> Signed-off-by: Matt Redfearn <matt.redfearn@mips.com> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Cc: linux-mips@linux-mips.org Cc: Daniel Lezcano <daniel.lezcano@linaro.org> Cc: "Martin Schwidefsky" <schwidefsky@de.ibm.com> Cc: James Hogan <james.hogan@mips.com> Link: https://lkml.kernel.org/r/1508422643-6075-1-git-send-email-matt.redfearn@mips.com
2017-10-19 22:17:23 +08:00
dev->retries++;
clc = ((unsigned long long) delta * dev->mult) >> dev->shift;
if (dev->set_next_event((unsigned long) clc, dev) == 0)
return 0;
}
return -ETIME;
}
#endif /* CONFIG_GENERIC_CLOCKEVENTS_MIN_ADJUST */
/**
* clockevents_program_event - Reprogram the clock event device.
* @dev: device to program
* @expires: absolute expiry time (monotonic clock)
* @force: program minimum delay if expires can not be set
*
* Returns 0 on success, -ETIME when the event is in the past.
*/
int clockevents_program_event(struct clock_event_device *dev, ktime_t expires,
bool force)
{
unsigned long long clc;
int64_t delta;
int rc;
if (WARN_ON_ONCE(expires < 0))
return -ETIME;
dev->next_event = expires;
if (clockevent_state_shutdown(dev))
return 0;
/* We must be in ONESHOT state here */
WARN_ONCE(!clockevent_state_oneshot(dev), "Current state: %d\n",
clockevent_get_state(dev));
/* Shortcut for clockevent devices that can deal with ktime. */
if (dev->features & CLOCK_EVT_FEAT_KTIME)
return dev->set_next_ktime(expires, dev);
delta = ktime_to_ns(ktime_sub(expires, ktime_get()));
if (delta <= 0)
return force ? clockevents_program_min_delta(dev) : -ETIME;
delta = min(delta, (int64_t) dev->max_delta_ns);
delta = max(delta, (int64_t) dev->min_delta_ns);
clc = ((unsigned long long) delta * dev->mult) >> dev->shift;
rc = dev->set_next_event((unsigned long) clc, dev);
return (rc && force) ? clockevents_program_min_delta(dev) : rc;
}
/*
* Called after a notify add to make devices available which were
* released from the notifier call.
*/
static void clockevents_notify_released(void)
{
struct clock_event_device *dev;
while (!list_empty(&clockevents_released)) {
dev = list_entry(clockevents_released.next,
struct clock_event_device, list);
list_del(&dev->list);
list_add(&dev->list, &clockevent_devices);
tick_check_new_device(dev);
}
}
/*
* Try to install a replacement clock event device
*/
static int clockevents_replace(struct clock_event_device *ced)
{
struct clock_event_device *dev, *newdev = NULL;
list_for_each_entry(dev, &clockevent_devices, list) {
if (dev == ced || !clockevent_state_detached(dev))
continue;
if (!tick_check_replacement(newdev, dev))
continue;
if (!try_module_get(dev->owner))
continue;
if (newdev)
module_put(newdev->owner);
newdev = dev;
}
if (newdev) {
tick_install_replacement(newdev);
list_del_init(&ced->list);
}
return newdev ? 0 : -EBUSY;
}
/*
* Called with clockevents_mutex and clockevents_lock held
*/
static int __clockevents_try_unbind(struct clock_event_device *ced, int cpu)
{
/* Fast track. Device is unused */
if (clockevent_state_detached(ced)) {
list_del_init(&ced->list);
return 0;
}
return ced == per_cpu(tick_cpu_device, cpu).evtdev ? -EAGAIN : -EBUSY;
}
/*
* SMP function call to unbind a device
*/
static void __clockevents_unbind(void *arg)
{
struct ce_unbind *cu = arg;
int res;
raw_spin_lock(&clockevents_lock);
res = __clockevents_try_unbind(cu->ce, smp_processor_id());
if (res == -EAGAIN)
res = clockevents_replace(cu->ce);
cu->res = res;
raw_spin_unlock(&clockevents_lock);
}
/*
* Issues smp function call to unbind a per cpu device. Called with
* clockevents_mutex held.
*/
static int clockevents_unbind(struct clock_event_device *ced, int cpu)
{
struct ce_unbind cu = { .ce = ced, .res = -ENODEV };
smp_call_function_single(cpu, __clockevents_unbind, &cu, 1);
return cu.res;
}
/*
* Unbind a clockevents device.
*/
int clockevents_unbind_device(struct clock_event_device *ced, int cpu)
{
int ret;
mutex_lock(&clockevents_mutex);
ret = clockevents_unbind(ced, cpu);
mutex_unlock(&clockevents_mutex);
return ret;
}
EXPORT_SYMBOL_GPL(clockevents_unbind_device);
/**
* clockevents_register_device - register a clock event device
* @dev: device to register
*/
void clockevents_register_device(struct clock_event_device *dev)
{
2009-08-18 05:34:59 +08:00
unsigned long flags;
clockevents: Manage device's state separately for the core 'enum clock_event_mode' is used for two purposes today: - to pass mode to the driver of clockevent device::set_mode(). - for managing state of the device for clockevents core. For supporting new modes/states we have moved away from the legacy set_mode() callback to new per-mode/state callbacks. New modes/states shouldn't be exposed to the legacy (now OBSOLOTE) callbacks and so we shouldn't add new states to 'enum clock_event_mode'. Lets have separate enums for the two use cases mentioned above. Keep using the earlier enum for legacy set_mode() callback and mark it OBSOLETE. And add another enum to clearly specify the possible states of a clockevent device. This also renames the newly added per-mode callbacks to reflect state changes. We haven't got rid of 'mode' member of 'struct clock_event_device' as it is used by some of the clockevent drivers and it would automatically die down once we migrate those drivers to the new interface. It ('mode') is only updated now for the drivers using the legacy interface. Suggested-by: Peter Zijlstra <peterz@infradead.org> Suggested-by: Ingo Molnar <mingo@kernel.org> Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org> Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Daniel Lezcano <daniel.lezcano@linaro.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Kevin Hilman <khilman@linaro.org> Cc: Preeti U Murthy <preeti@linux.vnet.ibm.com> Cc: linaro-kernel@lists.linaro.org Cc: linaro-networking@linaro.org Cc: linux-arm-kernel@lists.infradead.org Link: http://lkml.kernel.org/r/b6b0143a8a57bd58352ad35e08c25424c879c0cb.1425037853.git.viresh.kumar@linaro.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-02-27 19:51:33 +08:00
/* Initialize state to DETACHED */
clockevent_set_state(dev, CLOCK_EVT_STATE_DETACHED);
clockevents: Manage device's state separately for the core 'enum clock_event_mode' is used for two purposes today: - to pass mode to the driver of clockevent device::set_mode(). - for managing state of the device for clockevents core. For supporting new modes/states we have moved away from the legacy set_mode() callback to new per-mode/state callbacks. New modes/states shouldn't be exposed to the legacy (now OBSOLOTE) callbacks and so we shouldn't add new states to 'enum clock_event_mode'. Lets have separate enums for the two use cases mentioned above. Keep using the earlier enum for legacy set_mode() callback and mark it OBSOLETE. And add another enum to clearly specify the possible states of a clockevent device. This also renames the newly added per-mode callbacks to reflect state changes. We haven't got rid of 'mode' member of 'struct clock_event_device' as it is used by some of the clockevent drivers and it would automatically die down once we migrate those drivers to the new interface. It ('mode') is only updated now for the drivers using the legacy interface. Suggested-by: Peter Zijlstra <peterz@infradead.org> Suggested-by: Ingo Molnar <mingo@kernel.org> Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org> Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Daniel Lezcano <daniel.lezcano@linaro.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Kevin Hilman <khilman@linaro.org> Cc: Preeti U Murthy <preeti@linux.vnet.ibm.com> Cc: linaro-kernel@lists.linaro.org Cc: linaro-networking@linaro.org Cc: linux-arm-kernel@lists.infradead.org Link: http://lkml.kernel.org/r/b6b0143a8a57bd58352ad35e08c25424c879c0cb.1425037853.git.viresh.kumar@linaro.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-02-27 19:51:33 +08:00
if (!dev->cpumask) {
WARN_ON(num_possible_cpus() > 1);
dev->cpumask = cpumask_of(smp_processor_id());
}
if (dev->cpumask == cpu_all_mask) {
WARN(1, "%s cpumask == cpu_all_mask, using cpu_possible_mask instead\n",
dev->name);
dev->cpumask = cpu_possible_mask;
}
raw_spin_lock_irqsave(&clockevents_lock, flags);
list_add(&dev->list, &clockevent_devices);
tick_check_new_device(dev);
clockevents_notify_released();
raw_spin_unlock_irqrestore(&clockevents_lock, flags);
}
EXPORT_SYMBOL_GPL(clockevents_register_device);
static void clockevents_config(struct clock_event_device *dev, u32 freq)
{
u64 sec;
if (!(dev->features & CLOCK_EVT_FEAT_ONESHOT))
return;
/*
* Calculate the maximum number of seconds we can sleep. Limit
* to 10 minutes for hardware which can program more than
* 32bit ticks so we still get reasonable conversion values.
*/
sec = dev->max_delta_ticks;
do_div(sec, freq);
if (!sec)
sec = 1;
else if (sec > 600 && dev->max_delta_ticks > UINT_MAX)
sec = 600;
clockevents_calc_mult_shift(dev, freq, sec);
clockevents: Sanitize ticks to nsec conversion Marc Kleine-Budde pointed out, that commit 77cc982 "clocksource: use clockevents_config_and_register() where possible" caused a regression for some of the converted subarchs. The reason is, that the clockevents core code converts the minimal hardware tick delta to a nanosecond value for core internal usage. This conversion is affected by integer math rounding loss, so the backwards conversion to hardware ticks will likely result in a value which is less than the configured hardware limitation. The affected subarchs used their own workaround (SIGH!) which got lost in the conversion. The solution for the issue at hand is simple: adding evt->mult - 1 to the shifted value before the integer divison in the core conversion function takes care of it. But this only works for the case where for the scaled math mult/shift pair "mult <= 1 << shift" is true. For the case where "mult > 1 << shift" we can apply the rounding add only for the minimum delta value to make sure that the backward conversion is not less than the given hardware limit. For the upper bound we need to omit the rounding add, because the backwards conversion is always larger than the original latch value. That would violate the upper bound of the hardware device. Though looking closer at the details of that function reveals another bogosity: The upper bounds check is broken as well. Checking for a resulting "clc" value greater than KTIME_MAX after the conversion is pointless. The conversion does: u64 clc = (latch << evt->shift) / evt->mult; So there is no sanity check for (latch << evt->shift) exceeding the 64bit boundary. The latch argument is "unsigned long", so on a 64bit arch the handed in argument could easily lead to an unnoticed shift overflow. With the above rounding fix applied the calculation before the divison is: u64 clc = (latch << evt->shift) + evt->mult - 1; So we need to make sure, that neither the shift nor the rounding add is overflowing the u64 boundary. [ukl: move assignment to rnd after eventually changing mult, fix build issue and correct comment with the right math] Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Cc: Russell King - ARM Linux <linux@arm.linux.org.uk> Cc: Marc Kleine-Budde <mkl@pengutronix.de> Cc: nicolas.ferre@atmel.com Cc: Marc Pignat <marc.pignat@hevs.ch> Cc: john.stultz@linaro.org Cc: kernel@pengutronix.de Cc: Ronald Wahl <ronald.wahl@raritan.com> Cc: LAK <linux-arm-kernel@lists.infradead.org> Cc: Ludovic Desroches <ludovic.desroches@atmel.com> Cc: stable@vger.kernel.org Link: http://lkml.kernel.org/r/1380052223-24139-1-git-send-email-u.kleine-koenig@pengutronix.de Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
2013-09-25 03:50:23 +08:00
dev->min_delta_ns = cev_delta2ns(dev->min_delta_ticks, dev, false);
dev->max_delta_ns = cev_delta2ns(dev->max_delta_ticks, dev, true);
}
/**
* clockevents_config_and_register - Configure and register a clock event device
* @dev: device to register
* @freq: The clock frequency
* @min_delta: The minimum clock ticks to program in oneshot mode
* @max_delta: The maximum clock ticks to program in oneshot mode
*
* min/max_delta can be 0 for devices which do not support oneshot mode.
*/
void clockevents_config_and_register(struct clock_event_device *dev,
u32 freq, unsigned long min_delta,
unsigned long max_delta)
{
dev->min_delta_ticks = min_delta;
dev->max_delta_ticks = max_delta;
clockevents_config(dev, freq);
clockevents_register_device(dev);
}
EXPORT_SYMBOL_GPL(clockevents_config_and_register);
int __clockevents_update_freq(struct clock_event_device *dev, u32 freq)
{
clockevents_config(dev, freq);
if (clockevent_state_oneshot(dev))
return clockevents_program_event(dev, dev->next_event, false);
if (clockevent_state_periodic(dev))
return __clockevents_switch_state(dev, CLOCK_EVT_STATE_PERIODIC);
return 0;
}
/**
* clockevents_update_freq - Update frequency and reprogram a clock event device.
* @dev: device to modify
* @freq: new device frequency
*
* Reconfigure and reprogram a clock event device in oneshot
* mode. Must be called on the cpu for which the device delivers per
* cpu timer events. If called for the broadcast device the core takes
* care of serialization.
*
* Returns 0 on success, -ETIME when the event is in the past.
*/
int clockevents_update_freq(struct clock_event_device *dev, u32 freq)
{
unsigned long flags;
int ret;
local_irq_save(flags);
ret = tick_broadcast_update_freq(dev, freq);
if (ret == -ENODEV)
ret = __clockevents_update_freq(dev, freq);
local_irq_restore(flags);
return ret;
}
/*
* Noop handler when we shut down an event device
*/
void clockevents_handle_noop(struct clock_event_device *dev)
{
}
/**
* clockevents_exchange_device - release and request clock devices
* @old: device to release (can be NULL)
* @new: device to request (can be NULL)
*
* Called from various tick functions with clockevents_lock held and
* interrupts disabled.
*/
void clockevents_exchange_device(struct clock_event_device *old,
struct clock_event_device *new)
{
/*
* Caller releases a clock event device. We queue it into the
* released list and do a notify add later.
*/
if (old) {
module_put(old->owner);
clockevents_switch_state(old, CLOCK_EVT_STATE_DETACHED);
list_del(&old->list);
list_add(&old->list, &clockevents_released);
}
if (new) {
BUG_ON(!clockevent_state_detached(new));
clockevents_shutdown(new);
}
}
/**
* clockevents_suspend - suspend clock devices
*/
void clockevents_suspend(void)
{
struct clock_event_device *dev;
list_for_each_entry_reverse(dev, &clockevent_devices, list)
if (dev->suspend && !clockevent_state_detached(dev))
dev->suspend(dev);
}
/**
* clockevents_resume - resume clock devices
*/
void clockevents_resume(void)
{
struct clock_event_device *dev;
list_for_each_entry(dev, &clockevent_devices, list)
if (dev->resume && !clockevent_state_detached(dev))
dev->resume(dev);
}
#ifdef CONFIG_HOTPLUG_CPU
# ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST
/**
* tick_offline_cpu - Take CPU out of the broadcast mechanism
* @cpu: The outgoing CPU
*
* Called on the outgoing CPU after it took itself offline.
*/
void tick_offline_cpu(unsigned int cpu)
{
raw_spin_lock(&clockevents_lock);
tick_broadcast_offline(cpu);
raw_spin_unlock(&clockevents_lock);
}
# endif
/**
* tick_cleanup_dead_cpu - Cleanup the tick and clockevents of a dead cpu
*/
void tick_cleanup_dead_cpu(int cpu)
{
struct clock_event_device *dev, *tmp;
2009-08-18 05:34:59 +08:00
unsigned long flags;
raw_spin_lock_irqsave(&clockevents_lock, flags);
tick_shutdown(cpu);
/*
* Unregister the clock event devices which were
* released from the users in the notify chain.
*/
list_for_each_entry_safe(dev, tmp, &clockevents_released, list)
list_del(&dev->list);
/*
* Now check whether the CPU has left unused per cpu devices
*/
list_for_each_entry_safe(dev, tmp, &clockevent_devices, list) {
if (cpumask_test_cpu(cpu, dev->cpumask) &&
cpumask_weight(dev->cpumask) == 1 &&
!tick_is_broadcast_device(dev)) {
BUG_ON(!clockevent_state_detached(dev));
list_del(&dev->list);
}
}
raw_spin_unlock_irqrestore(&clockevents_lock, flags);
}
#endif
#ifdef CONFIG_SYSFS
static struct bus_type clockevents_subsys = {
.name = "clockevents",
.dev_name = "clockevent",
};
static DEFINE_PER_CPU(struct device, tick_percpu_dev);
static struct tick_device *tick_get_tick_dev(struct device *dev);
static ssize_t sysfs_show_current_tick_dev(struct device *dev,
struct device_attribute *attr,
char *buf)
{
struct tick_device *td;
ssize_t count = 0;
raw_spin_lock_irq(&clockevents_lock);
td = tick_get_tick_dev(dev);
if (td && td->evtdev)
count = snprintf(buf, PAGE_SIZE, "%s\n", td->evtdev->name);
raw_spin_unlock_irq(&clockevents_lock);
return count;
}
static DEVICE_ATTR(current_device, 0444, sysfs_show_current_tick_dev, NULL);
/* We don't support the abomination of removable broadcast devices */
static ssize_t sysfs_unbind_tick_dev(struct device *dev,
struct device_attribute *attr,
const char *buf, size_t count)
{
char name[CS_NAME_LEN];
ssize_t ret = sysfs_get_uname(buf, name, count);
struct clock_event_device *ce;
if (ret < 0)
return ret;
ret = -ENODEV;
mutex_lock(&clockevents_mutex);
raw_spin_lock_irq(&clockevents_lock);
list_for_each_entry(ce, &clockevent_devices, list) {
if (!strcmp(ce->name, name)) {
ret = __clockevents_try_unbind(ce, dev->id);
break;
}
}
raw_spin_unlock_irq(&clockevents_lock);
/*
* We hold clockevents_mutex, so ce can't go away
*/
if (ret == -EAGAIN)
ret = clockevents_unbind(ce, dev->id);
mutex_unlock(&clockevents_mutex);
return ret ? ret : count;
}
static DEVICE_ATTR(unbind_device, 0200, NULL, sysfs_unbind_tick_dev);
#ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST
static struct device tick_bc_dev = {
.init_name = "broadcast",
.id = 0,
.bus = &clockevents_subsys,
};
static struct tick_device *tick_get_tick_dev(struct device *dev)
{
return dev == &tick_bc_dev ? tick_get_broadcast_device() :
&per_cpu(tick_cpu_device, dev->id);
}
static __init int tick_broadcast_init_sysfs(void)
{
int err = device_register(&tick_bc_dev);
if (!err)
err = device_create_file(&tick_bc_dev, &dev_attr_current_device);
return err;
}
#else
static struct tick_device *tick_get_tick_dev(struct device *dev)
{
return &per_cpu(tick_cpu_device, dev->id);
}
static inline int tick_broadcast_init_sysfs(void) { return 0; }
#endif
static int __init tick_init_sysfs(void)
{
int cpu;
for_each_possible_cpu(cpu) {
struct device *dev = &per_cpu(tick_percpu_dev, cpu);
int err;
dev->id = cpu;
dev->bus = &clockevents_subsys;
err = device_register(dev);
if (!err)
err = device_create_file(dev, &dev_attr_current_device);
if (!err)
err = device_create_file(dev, &dev_attr_unbind_device);
if (err)
return err;
}
return tick_broadcast_init_sysfs();
}
static int __init clockevents_init_sysfs(void)
{
int err = subsys_system_register(&clockevents_subsys, NULL);
if (!err)
err = tick_init_sysfs();
return err;
}
device_initcall(clockevents_init_sysfs);
#endif /* SYSFS */