OpenCloudOS-Kernel/include/linux/hrtimer.h

544 lines
16 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
/*
* hrtimers - High-resolution kernel timers
*
* Copyright(C) 2005, Thomas Gleixner <tglx@linutronix.de>
* Copyright(C) 2005, Red Hat, Inc., Ingo Molnar
*
* data type definitions, declarations, prototypes
*
* Started by: Thomas Gleixner and Ingo Molnar
*/
#ifndef _LINUX_HRTIMER_H
#define _LINUX_HRTIMER_H
#include <linux/hrtimer_defs.h>
#include <linux/rbtree.h>
#include <linux/init.h>
#include <linux/list.h>
#include <linux/percpu.h>
2020-08-06 20:35:11 +08:00
#include <linux/seqlock.h>
#include <linux/timer.h>
#include <linux/timerqueue.h>
struct hrtimer_clock_base;
struct hrtimer_cpu_base;
/*
* Mode arguments of xxx_hrtimer functions:
*
* HRTIMER_MODE_ABS - Time value is absolute
* HRTIMER_MODE_REL - Time value is relative to now
* HRTIMER_MODE_PINNED - Timer is bound to CPU (is only considered
* when starting the timer)
* HRTIMER_MODE_SOFT - Timer callback function will be executed in
* soft irq context
* HRTIMER_MODE_HARD - Timer callback function will be executed in
* hard irq context even on PREEMPT_RT.
*/
enum hrtimer_mode {
HRTIMER_MODE_ABS = 0x00,
HRTIMER_MODE_REL = 0x01,
HRTIMER_MODE_PINNED = 0x02,
HRTIMER_MODE_SOFT = 0x04,
HRTIMER_MODE_HARD = 0x08,
HRTIMER_MODE_ABS_PINNED = HRTIMER_MODE_ABS | HRTIMER_MODE_PINNED,
HRTIMER_MODE_REL_PINNED = HRTIMER_MODE_REL | HRTIMER_MODE_PINNED,
HRTIMER_MODE_ABS_SOFT = HRTIMER_MODE_ABS | HRTIMER_MODE_SOFT,
HRTIMER_MODE_REL_SOFT = HRTIMER_MODE_REL | HRTIMER_MODE_SOFT,
HRTIMER_MODE_ABS_PINNED_SOFT = HRTIMER_MODE_ABS_PINNED | HRTIMER_MODE_SOFT,
HRTIMER_MODE_REL_PINNED_SOFT = HRTIMER_MODE_REL_PINNED | HRTIMER_MODE_SOFT,
HRTIMER_MODE_ABS_HARD = HRTIMER_MODE_ABS | HRTIMER_MODE_HARD,
HRTIMER_MODE_REL_HARD = HRTIMER_MODE_REL | HRTIMER_MODE_HARD,
HRTIMER_MODE_ABS_PINNED_HARD = HRTIMER_MODE_ABS_PINNED | HRTIMER_MODE_HARD,
HRTIMER_MODE_REL_PINNED_HARD = HRTIMER_MODE_REL_PINNED | HRTIMER_MODE_HARD,
};
/*
* Return values for the callback function
*/
enum hrtimer_restart {
HRTIMER_NORESTART, /* Timer is not restarted */
HRTIMER_RESTART, /* Timer must be restarted */
};
/*
* Values to track state of the timer
*
* Possible states:
*
* 0x00 inactive
* 0x01 enqueued into rbtree
*
* The callback state is not part of the timer->state because clearing it would
* mean touching the timer after the callback, this makes it impossible to free
* the timer from the callback function.
*
* Therefore we track the callback state in:
*
* timer->base->cpu_base->running == timer
*
* On SMP it is possible to have a "callback function running and enqueued"
* status. It happens for example when a posix timer expired and the callback
* queued a signal. Between dropping the lock which protects the posix timer
* and reacquiring the base lock of the hrtimer, another CPU can deliver the
* signal and rearm the timer.
*
* All state transitions are protected by cpu_base->lock.
*/
#define HRTIMER_STATE_INACTIVE 0x00
#define HRTIMER_STATE_ENQUEUED 0x01
/**
* struct hrtimer - the basic hrtimer structure
* @node: timerqueue node, which also manages node.expires,
* the absolute expiry time in the hrtimers internal
* representation. The time is related to the clock on
* which the timer is based. Is setup by adding
* slack to the _softexpires value. For non range timers
* identical to _softexpires.
* @_softexpires: the absolute earliest expiry time of the hrtimer.
* The time which was given as expiry time when the timer
* was armed.
* @function: timer expiry callback function
* @base: pointer to the timer base (per cpu and per clock)
* @state: state information (See bit values above)
* @is_rel: Set if the timer was armed relative
hrtimer: Implement support for softirq based hrtimers hrtimer callbacks are always invoked in hard interrupt context. Several users in tree require soft interrupt context for their callbacks and achieve this by combining a hrtimer with a tasklet. The hrtimer schedules the tasklet in hard interrupt context and the tasklet callback gets invoked in softirq context later. That's suboptimal and aside of that the real-time patch moves most of the hrtimers into softirq context. So adding native support for hrtimers expiring in softirq context is a valuable extension for both mainline and the RT patch set. Each valid hrtimer clock id has two associated hrtimer clock bases: one for timers expiring in hardirq context and one for timers expiring in softirq context. Implement the functionality to associate a hrtimer with the hard or softirq related clock bases and update the relevant functions to take them into account when the next expiry time needs to be evaluated. Add a check into the hard interrupt context handler functions to check whether the first expiring softirq based timer has expired. If it's expired the softirq is raised and the accounting of softirq based timers to evaluate the next expiry time for programming the timer hardware is skipped until the softirq processing has finished. At the end of the softirq processing the regular processing is resumed. Suggested-by: Thomas Gleixner <tglx@linutronix.de> Suggested-by: Peter Zijlstra <peterz@infradead.org> Signed-off-by: Anna-Maria Gleixner <anna-maria@linutronix.de> Cc: Christoph Hellwig <hch@lst.de> Cc: John Stultz <john.stultz@linaro.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: keescook@chromium.org Link: http://lkml.kernel.org/r/20171221104205.7269-29-anna-maria@linutronix.de Signed-off-by: Ingo Molnar <mingo@kernel.org>
2017-12-21 18:41:57 +08:00
* @is_soft: Set if hrtimer will be expired in soft interrupt context.
* @is_hard: Set if hrtimer will be expired in hard interrupt context
* even on RT.
*
* The hrtimer structure must be initialized by hrtimer_init()
*/
struct hrtimer {
struct timerqueue_node node;
ktime_t _softexpires;
enum hrtimer_restart (*function)(struct hrtimer *);
struct hrtimer_clock_base *base;
u8 state;
u8 is_rel;
hrtimer: Implement support for softirq based hrtimers hrtimer callbacks are always invoked in hard interrupt context. Several users in tree require soft interrupt context for their callbacks and achieve this by combining a hrtimer with a tasklet. The hrtimer schedules the tasklet in hard interrupt context and the tasklet callback gets invoked in softirq context later. That's suboptimal and aside of that the real-time patch moves most of the hrtimers into softirq context. So adding native support for hrtimers expiring in softirq context is a valuable extension for both mainline and the RT patch set. Each valid hrtimer clock id has two associated hrtimer clock bases: one for timers expiring in hardirq context and one for timers expiring in softirq context. Implement the functionality to associate a hrtimer with the hard or softirq related clock bases and update the relevant functions to take them into account when the next expiry time needs to be evaluated. Add a check into the hard interrupt context handler functions to check whether the first expiring softirq based timer has expired. If it's expired the softirq is raised and the accounting of softirq based timers to evaluate the next expiry time for programming the timer hardware is skipped until the softirq processing has finished. At the end of the softirq processing the regular processing is resumed. Suggested-by: Thomas Gleixner <tglx@linutronix.de> Suggested-by: Peter Zijlstra <peterz@infradead.org> Signed-off-by: Anna-Maria Gleixner <anna-maria@linutronix.de> Cc: Christoph Hellwig <hch@lst.de> Cc: John Stultz <john.stultz@linaro.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: keescook@chromium.org Link: http://lkml.kernel.org/r/20171221104205.7269-29-anna-maria@linutronix.de Signed-off-by: Ingo Molnar <mingo@kernel.org>
2017-12-21 18:41:57 +08:00
u8 is_soft;
u8 is_hard;
};
/**
* struct hrtimer_sleeper - simple sleeper structure
* @timer: embedded timer structure
* @task: task to wake up
*
* task is set to NULL, when the timer expires.
*/
struct hrtimer_sleeper {
struct hrtimer timer;
struct task_struct *task;
};
#ifdef CONFIG_64BIT
hrtimer: Store running timer in hrtimer_clock_base The pointer to the currently running timer is stored in hrtimer_cpu_base before the base lock is dropped and the callback is invoked. This results in two levels of indirections and the upcoming support for softirq based hrtimer requires splitting the "running" storage into soft and hard IRQ context expiry. Storing both in the cpu base would require conditionals in all code paths accessing that information. It's possible to have a per clock base sequence count and running pointer without changing the semantics of the related mechanisms because the timer base pointer cannot be changed while a timer is running the callback. Unfortunately this makes cpu_clock base larger than 32 bytes on 32-bit kernels. Instead of having huge gaps due to alignment, remove the alignment and let the compiler pack CPU base for 32-bit kernels. The resulting cache access patterns are fortunately not really different from the current behaviour. On 64-bit kernels the 64-byte alignment stays and the behaviour is unchanged. This was determined by analyzing the resulting layout and looking at the number of cache lines involved for the frequently used clocks. Signed-off-by: Anna-Maria Gleixner <anna-maria@linutronix.de> Cc: Christoph Hellwig <hch@lst.de> Cc: John Stultz <john.stultz@linaro.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: keescook@chromium.org Link: http://lkml.kernel.org/r/20171221104205.7269-12-anna-maria@linutronix.de Signed-off-by: Ingo Molnar <mingo@kernel.org>
2017-12-21 18:41:40 +08:00
# define __hrtimer_clock_base_align ____cacheline_aligned
#else
hrtimer: Store running timer in hrtimer_clock_base The pointer to the currently running timer is stored in hrtimer_cpu_base before the base lock is dropped and the callback is invoked. This results in two levels of indirections and the upcoming support for softirq based hrtimer requires splitting the "running" storage into soft and hard IRQ context expiry. Storing both in the cpu base would require conditionals in all code paths accessing that information. It's possible to have a per clock base sequence count and running pointer without changing the semantics of the related mechanisms because the timer base pointer cannot be changed while a timer is running the callback. Unfortunately this makes cpu_clock base larger than 32 bytes on 32-bit kernels. Instead of having huge gaps due to alignment, remove the alignment and let the compiler pack CPU base for 32-bit kernels. The resulting cache access patterns are fortunately not really different from the current behaviour. On 64-bit kernels the 64-byte alignment stays and the behaviour is unchanged. This was determined by analyzing the resulting layout and looking at the number of cache lines involved for the frequently used clocks. Signed-off-by: Anna-Maria Gleixner <anna-maria@linutronix.de> Cc: Christoph Hellwig <hch@lst.de> Cc: John Stultz <john.stultz@linaro.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: keescook@chromium.org Link: http://lkml.kernel.org/r/20171221104205.7269-12-anna-maria@linutronix.de Signed-off-by: Ingo Molnar <mingo@kernel.org>
2017-12-21 18:41:40 +08:00
# define __hrtimer_clock_base_align
#endif
/**
* struct hrtimer_clock_base - the timer base for a specific clock
* @cpu_base: per cpu clock base
* @index: clock type index for per_cpu support when moving a
* timer to a base on another cpu.
* @clockid: clock id for per_cpu support
hrtimer: Store running timer in hrtimer_clock_base The pointer to the currently running timer is stored in hrtimer_cpu_base before the base lock is dropped and the callback is invoked. This results in two levels of indirections and the upcoming support for softirq based hrtimer requires splitting the "running" storage into soft and hard IRQ context expiry. Storing both in the cpu base would require conditionals in all code paths accessing that information. It's possible to have a per clock base sequence count and running pointer without changing the semantics of the related mechanisms because the timer base pointer cannot be changed while a timer is running the callback. Unfortunately this makes cpu_clock base larger than 32 bytes on 32-bit kernels. Instead of having huge gaps due to alignment, remove the alignment and let the compiler pack CPU base for 32-bit kernels. The resulting cache access patterns are fortunately not really different from the current behaviour. On 64-bit kernels the 64-byte alignment stays and the behaviour is unchanged. This was determined by analyzing the resulting layout and looking at the number of cache lines involved for the frequently used clocks. Signed-off-by: Anna-Maria Gleixner <anna-maria@linutronix.de> Cc: Christoph Hellwig <hch@lst.de> Cc: John Stultz <john.stultz@linaro.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: keescook@chromium.org Link: http://lkml.kernel.org/r/20171221104205.7269-12-anna-maria@linutronix.de Signed-off-by: Ingo Molnar <mingo@kernel.org>
2017-12-21 18:41:40 +08:00
* @seq: seqcount around __run_hrtimer
* @running: pointer to the currently running hrtimer
* @active: red black tree root node for the active timers
* @get_time: function to retrieve the current time of the clock
* @offset: offset of this clock to the monotonic base
*/
struct hrtimer_clock_base {
struct hrtimer_cpu_base *cpu_base;
hrtimer: Store running timer in hrtimer_clock_base The pointer to the currently running timer is stored in hrtimer_cpu_base before the base lock is dropped and the callback is invoked. This results in two levels of indirections and the upcoming support for softirq based hrtimer requires splitting the "running" storage into soft and hard IRQ context expiry. Storing both in the cpu base would require conditionals in all code paths accessing that information. It's possible to have a per clock base sequence count and running pointer without changing the semantics of the related mechanisms because the timer base pointer cannot be changed while a timer is running the callback. Unfortunately this makes cpu_clock base larger than 32 bytes on 32-bit kernels. Instead of having huge gaps due to alignment, remove the alignment and let the compiler pack CPU base for 32-bit kernels. The resulting cache access patterns are fortunately not really different from the current behaviour. On 64-bit kernels the 64-byte alignment stays and the behaviour is unchanged. This was determined by analyzing the resulting layout and looking at the number of cache lines involved for the frequently used clocks. Signed-off-by: Anna-Maria Gleixner <anna-maria@linutronix.de> Cc: Christoph Hellwig <hch@lst.de> Cc: John Stultz <john.stultz@linaro.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: keescook@chromium.org Link: http://lkml.kernel.org/r/20171221104205.7269-12-anna-maria@linutronix.de Signed-off-by: Ingo Molnar <mingo@kernel.org>
2017-12-21 18:41:40 +08:00
unsigned int index;
clockid_t clockid;
seqcount_raw_spinlock_t seq;
hrtimer: Store running timer in hrtimer_clock_base The pointer to the currently running timer is stored in hrtimer_cpu_base before the base lock is dropped and the callback is invoked. This results in two levels of indirections and the upcoming support for softirq based hrtimer requires splitting the "running" storage into soft and hard IRQ context expiry. Storing both in the cpu base would require conditionals in all code paths accessing that information. It's possible to have a per clock base sequence count and running pointer without changing the semantics of the related mechanisms because the timer base pointer cannot be changed while a timer is running the callback. Unfortunately this makes cpu_clock base larger than 32 bytes on 32-bit kernels. Instead of having huge gaps due to alignment, remove the alignment and let the compiler pack CPU base for 32-bit kernels. The resulting cache access patterns are fortunately not really different from the current behaviour. On 64-bit kernels the 64-byte alignment stays and the behaviour is unchanged. This was determined by analyzing the resulting layout and looking at the number of cache lines involved for the frequently used clocks. Signed-off-by: Anna-Maria Gleixner <anna-maria@linutronix.de> Cc: Christoph Hellwig <hch@lst.de> Cc: John Stultz <john.stultz@linaro.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: keescook@chromium.org Link: http://lkml.kernel.org/r/20171221104205.7269-12-anna-maria@linutronix.de Signed-off-by: Ingo Molnar <mingo@kernel.org>
2017-12-21 18:41:40 +08:00
struct hrtimer *running;
struct timerqueue_head active;
ktime_t (*get_time)(void);
ktime_t offset;
hrtimer: Store running timer in hrtimer_clock_base The pointer to the currently running timer is stored in hrtimer_cpu_base before the base lock is dropped and the callback is invoked. This results in two levels of indirections and the upcoming support for softirq based hrtimer requires splitting the "running" storage into soft and hard IRQ context expiry. Storing both in the cpu base would require conditionals in all code paths accessing that information. It's possible to have a per clock base sequence count and running pointer without changing the semantics of the related mechanisms because the timer base pointer cannot be changed while a timer is running the callback. Unfortunately this makes cpu_clock base larger than 32 bytes on 32-bit kernels. Instead of having huge gaps due to alignment, remove the alignment and let the compiler pack CPU base for 32-bit kernels. The resulting cache access patterns are fortunately not really different from the current behaviour. On 64-bit kernels the 64-byte alignment stays and the behaviour is unchanged. This was determined by analyzing the resulting layout and looking at the number of cache lines involved for the frequently used clocks. Signed-off-by: Anna-Maria Gleixner <anna-maria@linutronix.de> Cc: Christoph Hellwig <hch@lst.de> Cc: John Stultz <john.stultz@linaro.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: keescook@chromium.org Link: http://lkml.kernel.org/r/20171221104205.7269-12-anna-maria@linutronix.de Signed-off-by: Ingo Molnar <mingo@kernel.org>
2017-12-21 18:41:40 +08:00
} __hrtimer_clock_base_align;
enum hrtimer_base_type {
HRTIMER_BASE_MONOTONIC,
HRTIMER_BASE_REALTIME,
Revert: Unify CLOCK_MONOTONIC and CLOCK_BOOTTIME Revert commits 92af4dcb4e1c ("tracing: Unify the "boot" and "mono" tracing clocks") 127bfa5f4342 ("hrtimer: Unify MONOTONIC and BOOTTIME clock behavior") 7250a4047aa6 ("posix-timers: Unify MONOTONIC and BOOTTIME clock behavior") d6c7270e913d ("timekeeping: Remove boot time specific code") f2d6fdbfd238 ("Input: Evdev - unify MONOTONIC and BOOTTIME clock behavior") d6ed449afdb3 ("timekeeping: Make the MONOTONIC clock behave like the BOOTTIME clock") 72199320d49d ("timekeeping: Add the new CLOCK_MONOTONIC_ACTIVE clock") As stated in the pull request for the unification of CLOCK_MONOTONIC and CLOCK_BOOTTIME, it was clear that we might have to revert the change. As reported by several folks systemd and other applications rely on the documented behaviour of CLOCK_MONOTONIC on Linux and break with the above changes. After resume daemons time out and other timeout related issues are observed. Rafael compiled this list: * systemd kills daemons on resume, after >WatchdogSec seconds of suspending (Genki Sky). [Verified that that's because systemd uses CLOCK_MONOTONIC and expects it to not include the suspend time.] * systemd-journald misbehaves after resume: systemd-journald[7266]: File /var/log/journal/016627c3c4784cd4812d4b7e96a34226/system.journal corrupted or uncleanly shut down, renaming and replacing. (Mike Galbraith). * NetworkManager reports "networking disabled" and networking is broken after resume 50% of the time (Pavel). [May be because of systemd.] * MATE desktop dims the display and starts the screensaver right after system resume (Pavel). * Full system hang during resume (me). [May be due to systemd or NM or both.] That happens on debian and open suse systems. It's sad, that these problems were neither catched in -next nor by those folks who expressed interest in this change. Reported-by: Rafael J. Wysocki <rjw@rjwysocki.net> Reported-by: Genki Sky <sky@genki.is>, Reported-by: Pavel Machek <pavel@ucw.cz> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Cc: Dmitry Torokhov <dmitry.torokhov@gmail.com> Cc: John Stultz <john.stultz@linaro.org> Cc: Jonathan Corbet <corbet@lwn.net> Cc: Kevin Easton <kevin@guarana.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Mark Salyzyn <salyzyn@android.com> Cc: Michael Kerrisk <mtk.manpages@gmail.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Petr Mladek <pmladek@suse.com> Cc: Prarit Bhargava <prarit@redhat.com> Cc: Sergey Senozhatsky <sergey.senozhatsky@gmail.com> Cc: Steven Rostedt <rostedt@goodmis.org>
2018-04-25 21:33:38 +08:00
HRTIMER_BASE_BOOTTIME,
HRTIMER_BASE_TAI,
HRTIMER_BASE_MONOTONIC_SOFT,
HRTIMER_BASE_REALTIME_SOFT,
Revert: Unify CLOCK_MONOTONIC and CLOCK_BOOTTIME Revert commits 92af4dcb4e1c ("tracing: Unify the "boot" and "mono" tracing clocks") 127bfa5f4342 ("hrtimer: Unify MONOTONIC and BOOTTIME clock behavior") 7250a4047aa6 ("posix-timers: Unify MONOTONIC and BOOTTIME clock behavior") d6c7270e913d ("timekeeping: Remove boot time specific code") f2d6fdbfd238 ("Input: Evdev - unify MONOTONIC and BOOTTIME clock behavior") d6ed449afdb3 ("timekeeping: Make the MONOTONIC clock behave like the BOOTTIME clock") 72199320d49d ("timekeeping: Add the new CLOCK_MONOTONIC_ACTIVE clock") As stated in the pull request for the unification of CLOCK_MONOTONIC and CLOCK_BOOTTIME, it was clear that we might have to revert the change. As reported by several folks systemd and other applications rely on the documented behaviour of CLOCK_MONOTONIC on Linux and break with the above changes. After resume daemons time out and other timeout related issues are observed. Rafael compiled this list: * systemd kills daemons on resume, after >WatchdogSec seconds of suspending (Genki Sky). [Verified that that's because systemd uses CLOCK_MONOTONIC and expects it to not include the suspend time.] * systemd-journald misbehaves after resume: systemd-journald[7266]: File /var/log/journal/016627c3c4784cd4812d4b7e96a34226/system.journal corrupted or uncleanly shut down, renaming and replacing. (Mike Galbraith). * NetworkManager reports "networking disabled" and networking is broken after resume 50% of the time (Pavel). [May be because of systemd.] * MATE desktop dims the display and starts the screensaver right after system resume (Pavel). * Full system hang during resume (me). [May be due to systemd or NM or both.] That happens on debian and open suse systems. It's sad, that these problems were neither catched in -next nor by those folks who expressed interest in this change. Reported-by: Rafael J. Wysocki <rjw@rjwysocki.net> Reported-by: Genki Sky <sky@genki.is>, Reported-by: Pavel Machek <pavel@ucw.cz> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Cc: Dmitry Torokhov <dmitry.torokhov@gmail.com> Cc: John Stultz <john.stultz@linaro.org> Cc: Jonathan Corbet <corbet@lwn.net> Cc: Kevin Easton <kevin@guarana.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Mark Salyzyn <salyzyn@android.com> Cc: Michael Kerrisk <mtk.manpages@gmail.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Petr Mladek <pmladek@suse.com> Cc: Prarit Bhargava <prarit@redhat.com> Cc: Sergey Senozhatsky <sergey.senozhatsky@gmail.com> Cc: Steven Rostedt <rostedt@goodmis.org>
2018-04-25 21:33:38 +08:00
HRTIMER_BASE_BOOTTIME_SOFT,
HRTIMER_BASE_TAI_SOFT,
HRTIMER_MAX_CLOCK_BASES,
};
/**
* struct hrtimer_cpu_base - the per cpu clock bases
* @lock: lock protecting the base and associated clock bases
* and timers
* @cpu: cpu number
* @active_bases: Bitfield to mark bases with active timers
* @clock_was_set_seq: Sequence counter of clock was set events
* @hres_active: State of high resolution mode
* @in_hrtirq: hrtimer_interrupt() is currently executing
* @hang_detected: The last hrtimer interrupt detected a hang
hrtimer: Implement support for softirq based hrtimers hrtimer callbacks are always invoked in hard interrupt context. Several users in tree require soft interrupt context for their callbacks and achieve this by combining a hrtimer with a tasklet. The hrtimer schedules the tasklet in hard interrupt context and the tasklet callback gets invoked in softirq context later. That's suboptimal and aside of that the real-time patch moves most of the hrtimers into softirq context. So adding native support for hrtimers expiring in softirq context is a valuable extension for both mainline and the RT patch set. Each valid hrtimer clock id has two associated hrtimer clock bases: one for timers expiring in hardirq context and one for timers expiring in softirq context. Implement the functionality to associate a hrtimer with the hard or softirq related clock bases and update the relevant functions to take them into account when the next expiry time needs to be evaluated. Add a check into the hard interrupt context handler functions to check whether the first expiring softirq based timer has expired. If it's expired the softirq is raised and the accounting of softirq based timers to evaluate the next expiry time for programming the timer hardware is skipped until the softirq processing has finished. At the end of the softirq processing the regular processing is resumed. Suggested-by: Thomas Gleixner <tglx@linutronix.de> Suggested-by: Peter Zijlstra <peterz@infradead.org> Signed-off-by: Anna-Maria Gleixner <anna-maria@linutronix.de> Cc: Christoph Hellwig <hch@lst.de> Cc: John Stultz <john.stultz@linaro.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: keescook@chromium.org Link: http://lkml.kernel.org/r/20171221104205.7269-29-anna-maria@linutronix.de Signed-off-by: Ingo Molnar <mingo@kernel.org>
2017-12-21 18:41:57 +08:00
* @softirq_activated: displays, if the softirq is raised - update of softirq
* related settings is not required then.
* @nr_events: Total number of hrtimer interrupt events
* @nr_retries: Total number of hrtimer interrupt retries
* @nr_hangs: Total number of hrtimer interrupt hangs
* @max_hang_time: Maximum time spent in hrtimer_interrupt
hrtimer: Prepare support for PREEMPT_RT When PREEMPT_RT is enabled, the soft interrupt thread can be preempted. If the soft interrupt thread is preempted in the middle of a timer callback, then calling hrtimer_cancel() can lead to two issues: - If the caller is on a remote CPU then it has to spin wait for the timer handler to complete. This can result in unbound priority inversion. - If the caller originates from the task which preempted the timer handler on the same CPU, then spin waiting for the timer handler to complete is never going to end. To avoid these issues, add a new lock to the timer base which is held around the execution of the timer callbacks. If hrtimer_cancel() detects that the timer callback is currently running, it blocks on the expiry lock. When the callback is finished, the expiry lock is dropped by the softirq thread which wakes up the waiter and the system makes progress. This addresses both the priority inversion and the life lock issues. The same issue can happen in virtual machines when the vCPU which runs a timer callback is scheduled out. If a second vCPU of the same guest calls hrtimer_cancel() it will spin wait for the other vCPU to be scheduled back in. The expiry lock mechanism would avoid that. It'd be trivial to enable this when paravirt spinlocks are enabled in a guest, but it's not clear whether this is an actual problem in the wild, so for now it's an RT only mechanism. [ tglx: Refactored it for mainline ] Signed-off-by: Anna-Maria Gleixner <anna-maria@linutronix.de> Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org> Link: https://lkml.kernel.org/r/20190726185753.737767218@linutronix.de
2019-07-27 02:30:59 +08:00
* @softirq_expiry_lock: Lock which is taken while softirq based hrtimer are
* expired
* @timer_waiters: A hrtimer_cancel() invocation waits for the timer
* callback to finish.
* @expires_next: absolute time of the next event, is required for remote
hrtimer: Implement support for softirq based hrtimers hrtimer callbacks are always invoked in hard interrupt context. Several users in tree require soft interrupt context for their callbacks and achieve this by combining a hrtimer with a tasklet. The hrtimer schedules the tasklet in hard interrupt context and the tasklet callback gets invoked in softirq context later. That's suboptimal and aside of that the real-time patch moves most of the hrtimers into softirq context. So adding native support for hrtimers expiring in softirq context is a valuable extension for both mainline and the RT patch set. Each valid hrtimer clock id has two associated hrtimer clock bases: one for timers expiring in hardirq context and one for timers expiring in softirq context. Implement the functionality to associate a hrtimer with the hard or softirq related clock bases and update the relevant functions to take them into account when the next expiry time needs to be evaluated. Add a check into the hard interrupt context handler functions to check whether the first expiring softirq based timer has expired. If it's expired the softirq is raised and the accounting of softirq based timers to evaluate the next expiry time for programming the timer hardware is skipped until the softirq processing has finished. At the end of the softirq processing the regular processing is resumed. Suggested-by: Thomas Gleixner <tglx@linutronix.de> Suggested-by: Peter Zijlstra <peterz@infradead.org> Signed-off-by: Anna-Maria Gleixner <anna-maria@linutronix.de> Cc: Christoph Hellwig <hch@lst.de> Cc: John Stultz <john.stultz@linaro.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: keescook@chromium.org Link: http://lkml.kernel.org/r/20171221104205.7269-29-anna-maria@linutronix.de Signed-off-by: Ingo Molnar <mingo@kernel.org>
2017-12-21 18:41:57 +08:00
* hrtimer enqueue; it is the total first expiry time (hard
* and soft hrtimer are taken into account)
* @next_timer: Pointer to the first expiring timer
hrtimer: Implement support for softirq based hrtimers hrtimer callbacks are always invoked in hard interrupt context. Several users in tree require soft interrupt context for their callbacks and achieve this by combining a hrtimer with a tasklet. The hrtimer schedules the tasklet in hard interrupt context and the tasklet callback gets invoked in softirq context later. That's suboptimal and aside of that the real-time patch moves most of the hrtimers into softirq context. So adding native support for hrtimers expiring in softirq context is a valuable extension for both mainline and the RT patch set. Each valid hrtimer clock id has two associated hrtimer clock bases: one for timers expiring in hardirq context and one for timers expiring in softirq context. Implement the functionality to associate a hrtimer with the hard or softirq related clock bases and update the relevant functions to take them into account when the next expiry time needs to be evaluated. Add a check into the hard interrupt context handler functions to check whether the first expiring softirq based timer has expired. If it's expired the softirq is raised and the accounting of softirq based timers to evaluate the next expiry time for programming the timer hardware is skipped until the softirq processing has finished. At the end of the softirq processing the regular processing is resumed. Suggested-by: Thomas Gleixner <tglx@linutronix.de> Suggested-by: Peter Zijlstra <peterz@infradead.org> Signed-off-by: Anna-Maria Gleixner <anna-maria@linutronix.de> Cc: Christoph Hellwig <hch@lst.de> Cc: John Stultz <john.stultz@linaro.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: keescook@chromium.org Link: http://lkml.kernel.org/r/20171221104205.7269-29-anna-maria@linutronix.de Signed-off-by: Ingo Molnar <mingo@kernel.org>
2017-12-21 18:41:57 +08:00
* @softirq_expires_next: Time to check, if soft queues needs also to be expired
* @softirq_next_timer: Pointer to the first expiring softirq based timer
* @clock_base: array of clock bases for this cpu
*
* Note: next_timer is just an optimization for __remove_hrtimer().
* Do not dereference the pointer because it is not reliable on
* cross cpu removals.
*/
struct hrtimer_cpu_base {
raw_spinlock_t lock;
unsigned int cpu;
unsigned int active_bases;
unsigned int clock_was_set_seq;
hrtimer: Implement support for softirq based hrtimers hrtimer callbacks are always invoked in hard interrupt context. Several users in tree require soft interrupt context for their callbacks and achieve this by combining a hrtimer with a tasklet. The hrtimer schedules the tasklet in hard interrupt context and the tasklet callback gets invoked in softirq context later. That's suboptimal and aside of that the real-time patch moves most of the hrtimers into softirq context. So adding native support for hrtimers expiring in softirq context is a valuable extension for both mainline and the RT patch set. Each valid hrtimer clock id has two associated hrtimer clock bases: one for timers expiring in hardirq context and one for timers expiring in softirq context. Implement the functionality to associate a hrtimer with the hard or softirq related clock bases and update the relevant functions to take them into account when the next expiry time needs to be evaluated. Add a check into the hard interrupt context handler functions to check whether the first expiring softirq based timer has expired. If it's expired the softirq is raised and the accounting of softirq based timers to evaluate the next expiry time for programming the timer hardware is skipped until the softirq processing has finished. At the end of the softirq processing the regular processing is resumed. Suggested-by: Thomas Gleixner <tglx@linutronix.de> Suggested-by: Peter Zijlstra <peterz@infradead.org> Signed-off-by: Anna-Maria Gleixner <anna-maria@linutronix.de> Cc: Christoph Hellwig <hch@lst.de> Cc: John Stultz <john.stultz@linaro.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: keescook@chromium.org Link: http://lkml.kernel.org/r/20171221104205.7269-29-anna-maria@linutronix.de Signed-off-by: Ingo Molnar <mingo@kernel.org>
2017-12-21 18:41:57 +08:00
unsigned int hres_active : 1,
in_hrtirq : 1,
hang_detected : 1,
softirq_activated : 1;
#ifdef CONFIG_HIGH_RES_TIMERS
unsigned int nr_events;
unsigned short nr_retries;
unsigned short nr_hangs;
unsigned int max_hang_time;
hrtimer: Prepare support for PREEMPT_RT When PREEMPT_RT is enabled, the soft interrupt thread can be preempted. If the soft interrupt thread is preempted in the middle of a timer callback, then calling hrtimer_cancel() can lead to two issues: - If the caller is on a remote CPU then it has to spin wait for the timer handler to complete. This can result in unbound priority inversion. - If the caller originates from the task which preempted the timer handler on the same CPU, then spin waiting for the timer handler to complete is never going to end. To avoid these issues, add a new lock to the timer base which is held around the execution of the timer callbacks. If hrtimer_cancel() detects that the timer callback is currently running, it blocks on the expiry lock. When the callback is finished, the expiry lock is dropped by the softirq thread which wakes up the waiter and the system makes progress. This addresses both the priority inversion and the life lock issues. The same issue can happen in virtual machines when the vCPU which runs a timer callback is scheduled out. If a second vCPU of the same guest calls hrtimer_cancel() it will spin wait for the other vCPU to be scheduled back in. The expiry lock mechanism would avoid that. It'd be trivial to enable this when paravirt spinlocks are enabled in a guest, but it's not clear whether this is an actual problem in the wild, so for now it's an RT only mechanism. [ tglx: Refactored it for mainline ] Signed-off-by: Anna-Maria Gleixner <anna-maria@linutronix.de> Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org> Link: https://lkml.kernel.org/r/20190726185753.737767218@linutronix.de
2019-07-27 02:30:59 +08:00
#endif
#ifdef CONFIG_PREEMPT_RT
spinlock_t softirq_expiry_lock;
atomic_t timer_waiters;
#endif
ktime_t expires_next;
struct hrtimer *next_timer;
hrtimer: Implement support for softirq based hrtimers hrtimer callbacks are always invoked in hard interrupt context. Several users in tree require soft interrupt context for their callbacks and achieve this by combining a hrtimer with a tasklet. The hrtimer schedules the tasklet in hard interrupt context and the tasklet callback gets invoked in softirq context later. That's suboptimal and aside of that the real-time patch moves most of the hrtimers into softirq context. So adding native support for hrtimers expiring in softirq context is a valuable extension for both mainline and the RT patch set. Each valid hrtimer clock id has two associated hrtimer clock bases: one for timers expiring in hardirq context and one for timers expiring in softirq context. Implement the functionality to associate a hrtimer with the hard or softirq related clock bases and update the relevant functions to take them into account when the next expiry time needs to be evaluated. Add a check into the hard interrupt context handler functions to check whether the first expiring softirq based timer has expired. If it's expired the softirq is raised and the accounting of softirq based timers to evaluate the next expiry time for programming the timer hardware is skipped until the softirq processing has finished. At the end of the softirq processing the regular processing is resumed. Suggested-by: Thomas Gleixner <tglx@linutronix.de> Suggested-by: Peter Zijlstra <peterz@infradead.org> Signed-off-by: Anna-Maria Gleixner <anna-maria@linutronix.de> Cc: Christoph Hellwig <hch@lst.de> Cc: John Stultz <john.stultz@linaro.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: keescook@chromium.org Link: http://lkml.kernel.org/r/20171221104205.7269-29-anna-maria@linutronix.de Signed-off-by: Ingo Molnar <mingo@kernel.org>
2017-12-21 18:41:57 +08:00
ktime_t softirq_expires_next;
struct hrtimer *softirq_next_timer;
struct hrtimer_clock_base clock_base[HRTIMER_MAX_CLOCK_BASES];
} ____cacheline_aligned;
static inline void hrtimer_set_expires(struct hrtimer *timer, ktime_t time)
{
timer->node.expires = time;
timer->_softexpires = time;
}
static inline void hrtimer_set_expires_range(struct hrtimer *timer, ktime_t time, ktime_t delta)
{
timer->_softexpires = time;
timer->node.expires = ktime_add_safe(time, delta);
}
timer: convert timer_slack_ns from unsigned long to u64 This patchset introduces a /proc/<pid>/timerslack_ns interface which would allow controlling processes to be able to set the timerslack value on other processes in order to save power by avoiding wakeups (Something Android currently does via out-of-tree patches). The first patch tries to fix the internal timer_slack_ns usage which was defined as a long, which limits the slack range to ~4 seconds on 32bit systems. It converts it to a u64, which provides the same basically unlimited slack (500 years) on both 32bit and 64bit machines. The second patch introduces the /proc/<pid>/timerslack_ns interface which allows the full 64bit slack range for a task to be read or set on both 32bit and 64bit machines. With these two patches, on a 32bit machine, after setting the slack on bash to 10 seconds: $ time sleep 1 real 0m10.747s user 0m0.001s sys 0m0.005s The first patch is a little ugly, since I had to chase the slack delta arguments through a number of functions converting them to u64s. Let me know if it makes sense to break that up more or not. Other than that things are fairly straightforward. This patch (of 2): The timer_slack_ns value in the task struct is currently a unsigned long. This means that on 32bit applications, the maximum slack is just over 4 seconds. However, on 64bit machines, its much much larger (~500 years). This disparity could make application development a little (as well as the default_slack) to a u64. This means both 32bit and 64bit systems have the same effective internal slack range. Now the existing ABI via PR_GET_TIMERSLACK and PR_SET_TIMERSLACK specify the interface as a unsigned long, so we preserve that limitation on 32bit systems, where SET_TIMERSLACK can only set the slack to a unsigned long value, and GET_TIMERSLACK will return ULONG_MAX if the slack is actually larger then what can be stored by an unsigned long. This patch also modifies hrtimer functions which specified the slack delta as a unsigned long. Signed-off-by: John Stultz <john.stultz@linaro.org> Cc: Arjan van de Ven <arjan@linux.intel.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Oren Laadan <orenl@cellrox.com> Cc: Ruchi Kandoi <kandoiruchi@google.com> Cc: Rom Lemarchand <romlem@android.com> Cc: Kees Cook <keescook@chromium.org> Cc: Android Kernel Team <kernel-team@android.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-03-18 05:20:51 +08:00
static inline void hrtimer_set_expires_range_ns(struct hrtimer *timer, ktime_t time, u64 delta)
{
timer->_softexpires = time;
timer->node.expires = ktime_add_safe(time, ns_to_ktime(delta));
}
static inline void hrtimer_set_expires_tv64(struct hrtimer *timer, s64 tv64)
{
timer->node.expires = tv64;
timer->_softexpires = tv64;
}
static inline void hrtimer_add_expires(struct hrtimer *timer, ktime_t time)
{
timer->node.expires = ktime_add_safe(timer->node.expires, time);
timer->_softexpires = ktime_add_safe(timer->_softexpires, time);
}
static inline void hrtimer_add_expires_ns(struct hrtimer *timer, u64 ns)
{
timer->node.expires = ktime_add_ns(timer->node.expires, ns);
timer->_softexpires = ktime_add_ns(timer->_softexpires, ns);
}
static inline ktime_t hrtimer_get_expires(const struct hrtimer *timer)
{
return timer->node.expires;
}
static inline ktime_t hrtimer_get_softexpires(const struct hrtimer *timer)
{
return timer->_softexpires;
}
static inline s64 hrtimer_get_expires_tv64(const struct hrtimer *timer)
{
return timer->node.expires;
}
static inline s64 hrtimer_get_softexpires_tv64(const struct hrtimer *timer)
{
return timer->_softexpires;
}
static inline s64 hrtimer_get_expires_ns(const struct hrtimer *timer)
{
return ktime_to_ns(timer->node.expires);
}
static inline ktime_t hrtimer_expires_remaining(const struct hrtimer *timer)
{
return ktime_sub(timer->node.expires, timer->base->get_time());
}
static inline ktime_t hrtimer_cb_get_time(struct hrtimer *timer)
{
return timer->base->get_time();
}
static inline int hrtimer_is_hres_active(struct hrtimer *timer)
{
return IS_ENABLED(CONFIG_HIGH_RES_TIMERS) ?
timer->base->cpu_base->hres_active : 0;
}
#ifdef CONFIG_HIGH_RES_TIMERS
struct clock_event_device;
extern void hrtimer_interrupt(struct clock_event_device *dev);
extern void clock_was_set_delayed(void);
extern unsigned int hrtimer_resolution;
#else
#define hrtimer_resolution (unsigned int)LOW_RES_NSEC
static inline void clock_was_set_delayed(void) { }
#endif
static inline ktime_t
__hrtimer_expires_remaining_adjusted(const struct hrtimer *timer, ktime_t now)
{
ktime_t rem = ktime_sub(timer->node.expires, now);
/*
* Adjust relative timers for the extra we added in
* hrtimer_start_range_ns() to prevent short timeouts.
*/
if (IS_ENABLED(CONFIG_TIME_LOW_RES) && timer->is_rel)
rem -= hrtimer_resolution;
return rem;
}
static inline ktime_t
hrtimer_expires_remaining_adjusted(const struct hrtimer *timer)
{
return __hrtimer_expires_remaining_adjusted(timer,
timer->base->get_time());
}
extern void clock_was_set(void);
#ifdef CONFIG_TIMERFD
extern void timerfd_clock_was_set(void);
#else
static inline void timerfd_clock_was_set(void) { }
#endif
extern void hrtimers_resume(void);
DECLARE_PER_CPU(struct tick_device, tick_cpu_device);
hrtimer: Prepare support for PREEMPT_RT When PREEMPT_RT is enabled, the soft interrupt thread can be preempted. If the soft interrupt thread is preempted in the middle of a timer callback, then calling hrtimer_cancel() can lead to two issues: - If the caller is on a remote CPU then it has to spin wait for the timer handler to complete. This can result in unbound priority inversion. - If the caller originates from the task which preempted the timer handler on the same CPU, then spin waiting for the timer handler to complete is never going to end. To avoid these issues, add a new lock to the timer base which is held around the execution of the timer callbacks. If hrtimer_cancel() detects that the timer callback is currently running, it blocks on the expiry lock. When the callback is finished, the expiry lock is dropped by the softirq thread which wakes up the waiter and the system makes progress. This addresses both the priority inversion and the life lock issues. The same issue can happen in virtual machines when the vCPU which runs a timer callback is scheduled out. If a second vCPU of the same guest calls hrtimer_cancel() it will spin wait for the other vCPU to be scheduled back in. The expiry lock mechanism would avoid that. It'd be trivial to enable this when paravirt spinlocks are enabled in a guest, but it's not clear whether this is an actual problem in the wild, so for now it's an RT only mechanism. [ tglx: Refactored it for mainline ] Signed-off-by: Anna-Maria Gleixner <anna-maria@linutronix.de> Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org> Link: https://lkml.kernel.org/r/20190726185753.737767218@linutronix.de
2019-07-27 02:30:59 +08:00
#ifdef CONFIG_PREEMPT_RT
void hrtimer_cancel_wait_running(const struct hrtimer *timer);
#else
static inline void hrtimer_cancel_wait_running(struct hrtimer *timer)
{
cpu_relax();
}
#endif
/* Exported timer functions: */
/* Initialize timers: */
extern void hrtimer_init(struct hrtimer *timer, clockid_t which_clock,
enum hrtimer_mode mode);
extern void hrtimer_init_sleeper(struct hrtimer_sleeper *sl, clockid_t clock_id,
enum hrtimer_mode mode);
#ifdef CONFIG_DEBUG_OBJECTS_TIMERS
extern void hrtimer_init_on_stack(struct hrtimer *timer, clockid_t which_clock,
enum hrtimer_mode mode);
extern void hrtimer_init_sleeper_on_stack(struct hrtimer_sleeper *sl,
clockid_t clock_id,
enum hrtimer_mode mode);
extern void destroy_hrtimer_on_stack(struct hrtimer *timer);
#else
static inline void hrtimer_init_on_stack(struct hrtimer *timer,
clockid_t which_clock,
enum hrtimer_mode mode)
{
hrtimer_init(timer, which_clock, mode);
}
static inline void hrtimer_init_sleeper_on_stack(struct hrtimer_sleeper *sl,
clockid_t clock_id,
enum hrtimer_mode mode)
{
hrtimer_init_sleeper(sl, clock_id, mode);
}
static inline void destroy_hrtimer_on_stack(struct hrtimer *timer) { }
#endif
/* Basic timer operations: */
extern void hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim,
timer: convert timer_slack_ns from unsigned long to u64 This patchset introduces a /proc/<pid>/timerslack_ns interface which would allow controlling processes to be able to set the timerslack value on other processes in order to save power by avoiding wakeups (Something Android currently does via out-of-tree patches). The first patch tries to fix the internal timer_slack_ns usage which was defined as a long, which limits the slack range to ~4 seconds on 32bit systems. It converts it to a u64, which provides the same basically unlimited slack (500 years) on both 32bit and 64bit machines. The second patch introduces the /proc/<pid>/timerslack_ns interface which allows the full 64bit slack range for a task to be read or set on both 32bit and 64bit machines. With these two patches, on a 32bit machine, after setting the slack on bash to 10 seconds: $ time sleep 1 real 0m10.747s user 0m0.001s sys 0m0.005s The first patch is a little ugly, since I had to chase the slack delta arguments through a number of functions converting them to u64s. Let me know if it makes sense to break that up more or not. Other than that things are fairly straightforward. This patch (of 2): The timer_slack_ns value in the task struct is currently a unsigned long. This means that on 32bit applications, the maximum slack is just over 4 seconds. However, on 64bit machines, its much much larger (~500 years). This disparity could make application development a little (as well as the default_slack) to a u64. This means both 32bit and 64bit systems have the same effective internal slack range. Now the existing ABI via PR_GET_TIMERSLACK and PR_SET_TIMERSLACK specify the interface as a unsigned long, so we preserve that limitation on 32bit systems, where SET_TIMERSLACK can only set the slack to a unsigned long value, and GET_TIMERSLACK will return ULONG_MAX if the slack is actually larger then what can be stored by an unsigned long. This patch also modifies hrtimer functions which specified the slack delta as a unsigned long. Signed-off-by: John Stultz <john.stultz@linaro.org> Cc: Arjan van de Ven <arjan@linux.intel.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Oren Laadan <orenl@cellrox.com> Cc: Ruchi Kandoi <kandoiruchi@google.com> Cc: Rom Lemarchand <romlem@android.com> Cc: Kees Cook <keescook@chromium.org> Cc: Android Kernel Team <kernel-team@android.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-03-18 05:20:51 +08:00
u64 range_ns, const enum hrtimer_mode mode);
/**
* hrtimer_start - (re)start an hrtimer
* @timer: the timer to be added
* @tim: expiry time
* @mode: timer mode: absolute (HRTIMER_MODE_ABS) or
hrtimer: Implement support for softirq based hrtimers hrtimer callbacks are always invoked in hard interrupt context. Several users in tree require soft interrupt context for their callbacks and achieve this by combining a hrtimer with a tasklet. The hrtimer schedules the tasklet in hard interrupt context and the tasklet callback gets invoked in softirq context later. That's suboptimal and aside of that the real-time patch moves most of the hrtimers into softirq context. So adding native support for hrtimers expiring in softirq context is a valuable extension for both mainline and the RT patch set. Each valid hrtimer clock id has two associated hrtimer clock bases: one for timers expiring in hardirq context and one for timers expiring in softirq context. Implement the functionality to associate a hrtimer with the hard or softirq related clock bases and update the relevant functions to take them into account when the next expiry time needs to be evaluated. Add a check into the hard interrupt context handler functions to check whether the first expiring softirq based timer has expired. If it's expired the softirq is raised and the accounting of softirq based timers to evaluate the next expiry time for programming the timer hardware is skipped until the softirq processing has finished. At the end of the softirq processing the regular processing is resumed. Suggested-by: Thomas Gleixner <tglx@linutronix.de> Suggested-by: Peter Zijlstra <peterz@infradead.org> Signed-off-by: Anna-Maria Gleixner <anna-maria@linutronix.de> Cc: Christoph Hellwig <hch@lst.de> Cc: John Stultz <john.stultz@linaro.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: keescook@chromium.org Link: http://lkml.kernel.org/r/20171221104205.7269-29-anna-maria@linutronix.de Signed-off-by: Ingo Molnar <mingo@kernel.org>
2017-12-21 18:41:57 +08:00
* relative (HRTIMER_MODE_REL), and pinned (HRTIMER_MODE_PINNED);
* softirq based mode is considered for debug purpose only!
*/
static inline void hrtimer_start(struct hrtimer *timer, ktime_t tim,
const enum hrtimer_mode mode)
{
hrtimer_start_range_ns(timer, tim, 0, mode);
}
extern int hrtimer_cancel(struct hrtimer *timer);
extern int hrtimer_try_to_cancel(struct hrtimer *timer);
static inline void hrtimer_start_expires(struct hrtimer *timer,
enum hrtimer_mode mode)
{
timer: convert timer_slack_ns from unsigned long to u64 This patchset introduces a /proc/<pid>/timerslack_ns interface which would allow controlling processes to be able to set the timerslack value on other processes in order to save power by avoiding wakeups (Something Android currently does via out-of-tree patches). The first patch tries to fix the internal timer_slack_ns usage which was defined as a long, which limits the slack range to ~4 seconds on 32bit systems. It converts it to a u64, which provides the same basically unlimited slack (500 years) on both 32bit and 64bit machines. The second patch introduces the /proc/<pid>/timerslack_ns interface which allows the full 64bit slack range for a task to be read or set on both 32bit and 64bit machines. With these two patches, on a 32bit machine, after setting the slack on bash to 10 seconds: $ time sleep 1 real 0m10.747s user 0m0.001s sys 0m0.005s The first patch is a little ugly, since I had to chase the slack delta arguments through a number of functions converting them to u64s. Let me know if it makes sense to break that up more or not. Other than that things are fairly straightforward. This patch (of 2): The timer_slack_ns value in the task struct is currently a unsigned long. This means that on 32bit applications, the maximum slack is just over 4 seconds. However, on 64bit machines, its much much larger (~500 years). This disparity could make application development a little (as well as the default_slack) to a u64. This means both 32bit and 64bit systems have the same effective internal slack range. Now the existing ABI via PR_GET_TIMERSLACK and PR_SET_TIMERSLACK specify the interface as a unsigned long, so we preserve that limitation on 32bit systems, where SET_TIMERSLACK can only set the slack to a unsigned long value, and GET_TIMERSLACK will return ULONG_MAX if the slack is actually larger then what can be stored by an unsigned long. This patch also modifies hrtimer functions which specified the slack delta as a unsigned long. Signed-off-by: John Stultz <john.stultz@linaro.org> Cc: Arjan van de Ven <arjan@linux.intel.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Oren Laadan <orenl@cellrox.com> Cc: Ruchi Kandoi <kandoiruchi@google.com> Cc: Rom Lemarchand <romlem@android.com> Cc: Kees Cook <keescook@chromium.org> Cc: Android Kernel Team <kernel-team@android.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-03-18 05:20:51 +08:00
u64 delta;
ktime_t soft, hard;
soft = hrtimer_get_softexpires(timer);
hard = hrtimer_get_expires(timer);
delta = ktime_to_ns(ktime_sub(hard, soft));
hrtimer_start_range_ns(timer, soft, delta, mode);
}
void hrtimer_sleeper_start_expires(struct hrtimer_sleeper *sl,
enum hrtimer_mode mode);
static inline void hrtimer_restart(struct hrtimer *timer)
{
hrtimer_start_expires(timer, HRTIMER_MODE_ABS);
}
/* Query timers: */
extern ktime_t __hrtimer_get_remaining(const struct hrtimer *timer, bool adjust);
/**
* hrtimer_get_remaining - get remaining time for the timer
* @timer: the timer to read
*/
static inline ktime_t hrtimer_get_remaining(const struct hrtimer *timer)
{
return __hrtimer_get_remaining(timer, false);
}
extern u64 hrtimer_get_next_event(void);
extern u64 hrtimer_next_event_without(const struct hrtimer *exclude);
extern bool hrtimer_active(const struct hrtimer *timer);
hrtimer: Annotate lockless access to timer->state syzbot reported various data-race caused by hrtimer_is_queued() reading timer->state. A READ_ONCE() is required there to silence the warning. Also add the corresponding WRITE_ONCE() when timer->state is set. In remove_hrtimer() the hrtimer_is_queued() helper is open coded to avoid loading timer->state twice. KCSAN reported these cases: BUG: KCSAN: data-race in __remove_hrtimer / tcp_pacing_check write to 0xffff8880b2a7d388 of 1 bytes by interrupt on cpu 0: __remove_hrtimer+0x52/0x130 kernel/time/hrtimer.c:991 __run_hrtimer kernel/time/hrtimer.c:1496 [inline] __hrtimer_run_queues+0x250/0x600 kernel/time/hrtimer.c:1576 hrtimer_run_softirq+0x10e/0x150 kernel/time/hrtimer.c:1593 __do_softirq+0x115/0x33f kernel/softirq.c:292 run_ksoftirqd+0x46/0x60 kernel/softirq.c:603 smpboot_thread_fn+0x37d/0x4a0 kernel/smpboot.c:165 kthread+0x1d4/0x200 drivers/block/aoe/aoecmd.c:1253 ret_from_fork+0x1f/0x30 arch/x86/entry/entry_64.S:352 read to 0xffff8880b2a7d388 of 1 bytes by task 24652 on cpu 1: tcp_pacing_check net/ipv4/tcp_output.c:2235 [inline] tcp_pacing_check+0xba/0x130 net/ipv4/tcp_output.c:2225 tcp_xmit_retransmit_queue+0x32c/0x5a0 net/ipv4/tcp_output.c:3044 tcp_xmit_recovery+0x7c/0x120 net/ipv4/tcp_input.c:3558 tcp_ack+0x17b6/0x3170 net/ipv4/tcp_input.c:3717 tcp_rcv_established+0x37e/0xf50 net/ipv4/tcp_input.c:5696 tcp_v4_do_rcv+0x381/0x4e0 net/ipv4/tcp_ipv4.c:1561 sk_backlog_rcv include/net/sock.h:945 [inline] __release_sock+0x135/0x1e0 net/core/sock.c:2435 release_sock+0x61/0x160 net/core/sock.c:2951 sk_stream_wait_memory+0x3d7/0x7c0 net/core/stream.c:145 tcp_sendmsg_locked+0xb47/0x1f30 net/ipv4/tcp.c:1393 tcp_sendmsg+0x39/0x60 net/ipv4/tcp.c:1434 inet_sendmsg+0x6d/0x90 net/ipv4/af_inet.c:807 sock_sendmsg_nosec net/socket.c:637 [inline] sock_sendmsg+0x9f/0xc0 net/socket.c:657 BUG: KCSAN: data-race in __remove_hrtimer / __tcp_ack_snd_check write to 0xffff8880a3a65588 of 1 bytes by interrupt on cpu 0: __remove_hrtimer+0x52/0x130 kernel/time/hrtimer.c:991 __run_hrtimer kernel/time/hrtimer.c:1496 [inline] __hrtimer_run_queues+0x250/0x600 kernel/time/hrtimer.c:1576 hrtimer_run_softirq+0x10e/0x150 kernel/time/hrtimer.c:1593 __do_softirq+0x115/0x33f kernel/softirq.c:292 invoke_softirq kernel/softirq.c:373 [inline] irq_exit+0xbb/0xe0 kernel/softirq.c:413 exiting_irq arch/x86/include/asm/apic.h:536 [inline] smp_apic_timer_interrupt+0xe6/0x280 arch/x86/kernel/apic/apic.c:1137 apic_timer_interrupt+0xf/0x20 arch/x86/entry/entry_64.S:830 read to 0xffff8880a3a65588 of 1 bytes by task 22891 on cpu 1: __tcp_ack_snd_check+0x415/0x4f0 net/ipv4/tcp_input.c:5265 tcp_ack_snd_check net/ipv4/tcp_input.c:5287 [inline] tcp_rcv_established+0x750/0xf50 net/ipv4/tcp_input.c:5708 tcp_v4_do_rcv+0x381/0x4e0 net/ipv4/tcp_ipv4.c:1561 sk_backlog_rcv include/net/sock.h:945 [inline] __release_sock+0x135/0x1e0 net/core/sock.c:2435 release_sock+0x61/0x160 net/core/sock.c:2951 sk_stream_wait_memory+0x3d7/0x7c0 net/core/stream.c:145 tcp_sendmsg_locked+0xb47/0x1f30 net/ipv4/tcp.c:1393 tcp_sendmsg+0x39/0x60 net/ipv4/tcp.c:1434 inet_sendmsg+0x6d/0x90 net/ipv4/af_inet.c:807 sock_sendmsg_nosec net/socket.c:637 [inline] sock_sendmsg+0x9f/0xc0 net/socket.c:657 __sys_sendto+0x21f/0x320 net/socket.c:1952 __do_sys_sendto net/socket.c:1964 [inline] __se_sys_sendto net/socket.c:1960 [inline] __x64_sys_sendto+0x89/0xb0 net/socket.c:1960 do_syscall_64+0xcc/0x370 arch/x86/entry/common.c:290 Reported by Kernel Concurrency Sanitizer on: CPU: 1 PID: 24652 Comm: syz-executor.3 Not tainted 5.4.0-rc3+ #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 [ tglx: Added comments ] Reported-by: syzbot <syzkaller@googlegroups.com> Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Link: https://lkml.kernel.org/r/20191106174804.74723-1-edumazet@google.com
2019-11-07 01:48:04 +08:00
/**
* hrtimer_is_queued - check, whether the timer is on one of the queues
hrtimer: Annotate lockless access to timer->state syzbot reported various data-race caused by hrtimer_is_queued() reading timer->state. A READ_ONCE() is required there to silence the warning. Also add the corresponding WRITE_ONCE() when timer->state is set. In remove_hrtimer() the hrtimer_is_queued() helper is open coded to avoid loading timer->state twice. KCSAN reported these cases: BUG: KCSAN: data-race in __remove_hrtimer / tcp_pacing_check write to 0xffff8880b2a7d388 of 1 bytes by interrupt on cpu 0: __remove_hrtimer+0x52/0x130 kernel/time/hrtimer.c:991 __run_hrtimer kernel/time/hrtimer.c:1496 [inline] __hrtimer_run_queues+0x250/0x600 kernel/time/hrtimer.c:1576 hrtimer_run_softirq+0x10e/0x150 kernel/time/hrtimer.c:1593 __do_softirq+0x115/0x33f kernel/softirq.c:292 run_ksoftirqd+0x46/0x60 kernel/softirq.c:603 smpboot_thread_fn+0x37d/0x4a0 kernel/smpboot.c:165 kthread+0x1d4/0x200 drivers/block/aoe/aoecmd.c:1253 ret_from_fork+0x1f/0x30 arch/x86/entry/entry_64.S:352 read to 0xffff8880b2a7d388 of 1 bytes by task 24652 on cpu 1: tcp_pacing_check net/ipv4/tcp_output.c:2235 [inline] tcp_pacing_check+0xba/0x130 net/ipv4/tcp_output.c:2225 tcp_xmit_retransmit_queue+0x32c/0x5a0 net/ipv4/tcp_output.c:3044 tcp_xmit_recovery+0x7c/0x120 net/ipv4/tcp_input.c:3558 tcp_ack+0x17b6/0x3170 net/ipv4/tcp_input.c:3717 tcp_rcv_established+0x37e/0xf50 net/ipv4/tcp_input.c:5696 tcp_v4_do_rcv+0x381/0x4e0 net/ipv4/tcp_ipv4.c:1561 sk_backlog_rcv include/net/sock.h:945 [inline] __release_sock+0x135/0x1e0 net/core/sock.c:2435 release_sock+0x61/0x160 net/core/sock.c:2951 sk_stream_wait_memory+0x3d7/0x7c0 net/core/stream.c:145 tcp_sendmsg_locked+0xb47/0x1f30 net/ipv4/tcp.c:1393 tcp_sendmsg+0x39/0x60 net/ipv4/tcp.c:1434 inet_sendmsg+0x6d/0x90 net/ipv4/af_inet.c:807 sock_sendmsg_nosec net/socket.c:637 [inline] sock_sendmsg+0x9f/0xc0 net/socket.c:657 BUG: KCSAN: data-race in __remove_hrtimer / __tcp_ack_snd_check write to 0xffff8880a3a65588 of 1 bytes by interrupt on cpu 0: __remove_hrtimer+0x52/0x130 kernel/time/hrtimer.c:991 __run_hrtimer kernel/time/hrtimer.c:1496 [inline] __hrtimer_run_queues+0x250/0x600 kernel/time/hrtimer.c:1576 hrtimer_run_softirq+0x10e/0x150 kernel/time/hrtimer.c:1593 __do_softirq+0x115/0x33f kernel/softirq.c:292 invoke_softirq kernel/softirq.c:373 [inline] irq_exit+0xbb/0xe0 kernel/softirq.c:413 exiting_irq arch/x86/include/asm/apic.h:536 [inline] smp_apic_timer_interrupt+0xe6/0x280 arch/x86/kernel/apic/apic.c:1137 apic_timer_interrupt+0xf/0x20 arch/x86/entry/entry_64.S:830 read to 0xffff8880a3a65588 of 1 bytes by task 22891 on cpu 1: __tcp_ack_snd_check+0x415/0x4f0 net/ipv4/tcp_input.c:5265 tcp_ack_snd_check net/ipv4/tcp_input.c:5287 [inline] tcp_rcv_established+0x750/0xf50 net/ipv4/tcp_input.c:5708 tcp_v4_do_rcv+0x381/0x4e0 net/ipv4/tcp_ipv4.c:1561 sk_backlog_rcv include/net/sock.h:945 [inline] __release_sock+0x135/0x1e0 net/core/sock.c:2435 release_sock+0x61/0x160 net/core/sock.c:2951 sk_stream_wait_memory+0x3d7/0x7c0 net/core/stream.c:145 tcp_sendmsg_locked+0xb47/0x1f30 net/ipv4/tcp.c:1393 tcp_sendmsg+0x39/0x60 net/ipv4/tcp.c:1434 inet_sendmsg+0x6d/0x90 net/ipv4/af_inet.c:807 sock_sendmsg_nosec net/socket.c:637 [inline] sock_sendmsg+0x9f/0xc0 net/socket.c:657 __sys_sendto+0x21f/0x320 net/socket.c:1952 __do_sys_sendto net/socket.c:1964 [inline] __se_sys_sendto net/socket.c:1960 [inline] __x64_sys_sendto+0x89/0xb0 net/socket.c:1960 do_syscall_64+0xcc/0x370 arch/x86/entry/common.c:290 Reported by Kernel Concurrency Sanitizer on: CPU: 1 PID: 24652 Comm: syz-executor.3 Not tainted 5.4.0-rc3+ #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 [ tglx: Added comments ] Reported-by: syzbot <syzkaller@googlegroups.com> Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Link: https://lkml.kernel.org/r/20191106174804.74723-1-edumazet@google.com
2019-11-07 01:48:04 +08:00
* @timer: Timer to check
*
* Returns: True if the timer is queued, false otherwise
*
* The function can be used lockless, but it gives only a current snapshot.
*/
hrtimer: Annotate lockless access to timer->state syzbot reported various data-race caused by hrtimer_is_queued() reading timer->state. A READ_ONCE() is required there to silence the warning. Also add the corresponding WRITE_ONCE() when timer->state is set. In remove_hrtimer() the hrtimer_is_queued() helper is open coded to avoid loading timer->state twice. KCSAN reported these cases: BUG: KCSAN: data-race in __remove_hrtimer / tcp_pacing_check write to 0xffff8880b2a7d388 of 1 bytes by interrupt on cpu 0: __remove_hrtimer+0x52/0x130 kernel/time/hrtimer.c:991 __run_hrtimer kernel/time/hrtimer.c:1496 [inline] __hrtimer_run_queues+0x250/0x600 kernel/time/hrtimer.c:1576 hrtimer_run_softirq+0x10e/0x150 kernel/time/hrtimer.c:1593 __do_softirq+0x115/0x33f kernel/softirq.c:292 run_ksoftirqd+0x46/0x60 kernel/softirq.c:603 smpboot_thread_fn+0x37d/0x4a0 kernel/smpboot.c:165 kthread+0x1d4/0x200 drivers/block/aoe/aoecmd.c:1253 ret_from_fork+0x1f/0x30 arch/x86/entry/entry_64.S:352 read to 0xffff8880b2a7d388 of 1 bytes by task 24652 on cpu 1: tcp_pacing_check net/ipv4/tcp_output.c:2235 [inline] tcp_pacing_check+0xba/0x130 net/ipv4/tcp_output.c:2225 tcp_xmit_retransmit_queue+0x32c/0x5a0 net/ipv4/tcp_output.c:3044 tcp_xmit_recovery+0x7c/0x120 net/ipv4/tcp_input.c:3558 tcp_ack+0x17b6/0x3170 net/ipv4/tcp_input.c:3717 tcp_rcv_established+0x37e/0xf50 net/ipv4/tcp_input.c:5696 tcp_v4_do_rcv+0x381/0x4e0 net/ipv4/tcp_ipv4.c:1561 sk_backlog_rcv include/net/sock.h:945 [inline] __release_sock+0x135/0x1e0 net/core/sock.c:2435 release_sock+0x61/0x160 net/core/sock.c:2951 sk_stream_wait_memory+0x3d7/0x7c0 net/core/stream.c:145 tcp_sendmsg_locked+0xb47/0x1f30 net/ipv4/tcp.c:1393 tcp_sendmsg+0x39/0x60 net/ipv4/tcp.c:1434 inet_sendmsg+0x6d/0x90 net/ipv4/af_inet.c:807 sock_sendmsg_nosec net/socket.c:637 [inline] sock_sendmsg+0x9f/0xc0 net/socket.c:657 BUG: KCSAN: data-race in __remove_hrtimer / __tcp_ack_snd_check write to 0xffff8880a3a65588 of 1 bytes by interrupt on cpu 0: __remove_hrtimer+0x52/0x130 kernel/time/hrtimer.c:991 __run_hrtimer kernel/time/hrtimer.c:1496 [inline] __hrtimer_run_queues+0x250/0x600 kernel/time/hrtimer.c:1576 hrtimer_run_softirq+0x10e/0x150 kernel/time/hrtimer.c:1593 __do_softirq+0x115/0x33f kernel/softirq.c:292 invoke_softirq kernel/softirq.c:373 [inline] irq_exit+0xbb/0xe0 kernel/softirq.c:413 exiting_irq arch/x86/include/asm/apic.h:536 [inline] smp_apic_timer_interrupt+0xe6/0x280 arch/x86/kernel/apic/apic.c:1137 apic_timer_interrupt+0xf/0x20 arch/x86/entry/entry_64.S:830 read to 0xffff8880a3a65588 of 1 bytes by task 22891 on cpu 1: __tcp_ack_snd_check+0x415/0x4f0 net/ipv4/tcp_input.c:5265 tcp_ack_snd_check net/ipv4/tcp_input.c:5287 [inline] tcp_rcv_established+0x750/0xf50 net/ipv4/tcp_input.c:5708 tcp_v4_do_rcv+0x381/0x4e0 net/ipv4/tcp_ipv4.c:1561 sk_backlog_rcv include/net/sock.h:945 [inline] __release_sock+0x135/0x1e0 net/core/sock.c:2435 release_sock+0x61/0x160 net/core/sock.c:2951 sk_stream_wait_memory+0x3d7/0x7c0 net/core/stream.c:145 tcp_sendmsg_locked+0xb47/0x1f30 net/ipv4/tcp.c:1393 tcp_sendmsg+0x39/0x60 net/ipv4/tcp.c:1434 inet_sendmsg+0x6d/0x90 net/ipv4/af_inet.c:807 sock_sendmsg_nosec net/socket.c:637 [inline] sock_sendmsg+0x9f/0xc0 net/socket.c:657 __sys_sendto+0x21f/0x320 net/socket.c:1952 __do_sys_sendto net/socket.c:1964 [inline] __se_sys_sendto net/socket.c:1960 [inline] __x64_sys_sendto+0x89/0xb0 net/socket.c:1960 do_syscall_64+0xcc/0x370 arch/x86/entry/common.c:290 Reported by Kernel Concurrency Sanitizer on: CPU: 1 PID: 24652 Comm: syz-executor.3 Not tainted 5.4.0-rc3+ #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 [ tglx: Added comments ] Reported-by: syzbot <syzkaller@googlegroups.com> Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Link: https://lkml.kernel.org/r/20191106174804.74723-1-edumazet@google.com
2019-11-07 01:48:04 +08:00
static inline bool hrtimer_is_queued(struct hrtimer *timer)
{
hrtimer: Annotate lockless access to timer->state syzbot reported various data-race caused by hrtimer_is_queued() reading timer->state. A READ_ONCE() is required there to silence the warning. Also add the corresponding WRITE_ONCE() when timer->state is set. In remove_hrtimer() the hrtimer_is_queued() helper is open coded to avoid loading timer->state twice. KCSAN reported these cases: BUG: KCSAN: data-race in __remove_hrtimer / tcp_pacing_check write to 0xffff8880b2a7d388 of 1 bytes by interrupt on cpu 0: __remove_hrtimer+0x52/0x130 kernel/time/hrtimer.c:991 __run_hrtimer kernel/time/hrtimer.c:1496 [inline] __hrtimer_run_queues+0x250/0x600 kernel/time/hrtimer.c:1576 hrtimer_run_softirq+0x10e/0x150 kernel/time/hrtimer.c:1593 __do_softirq+0x115/0x33f kernel/softirq.c:292 run_ksoftirqd+0x46/0x60 kernel/softirq.c:603 smpboot_thread_fn+0x37d/0x4a0 kernel/smpboot.c:165 kthread+0x1d4/0x200 drivers/block/aoe/aoecmd.c:1253 ret_from_fork+0x1f/0x30 arch/x86/entry/entry_64.S:352 read to 0xffff8880b2a7d388 of 1 bytes by task 24652 on cpu 1: tcp_pacing_check net/ipv4/tcp_output.c:2235 [inline] tcp_pacing_check+0xba/0x130 net/ipv4/tcp_output.c:2225 tcp_xmit_retransmit_queue+0x32c/0x5a0 net/ipv4/tcp_output.c:3044 tcp_xmit_recovery+0x7c/0x120 net/ipv4/tcp_input.c:3558 tcp_ack+0x17b6/0x3170 net/ipv4/tcp_input.c:3717 tcp_rcv_established+0x37e/0xf50 net/ipv4/tcp_input.c:5696 tcp_v4_do_rcv+0x381/0x4e0 net/ipv4/tcp_ipv4.c:1561 sk_backlog_rcv include/net/sock.h:945 [inline] __release_sock+0x135/0x1e0 net/core/sock.c:2435 release_sock+0x61/0x160 net/core/sock.c:2951 sk_stream_wait_memory+0x3d7/0x7c0 net/core/stream.c:145 tcp_sendmsg_locked+0xb47/0x1f30 net/ipv4/tcp.c:1393 tcp_sendmsg+0x39/0x60 net/ipv4/tcp.c:1434 inet_sendmsg+0x6d/0x90 net/ipv4/af_inet.c:807 sock_sendmsg_nosec net/socket.c:637 [inline] sock_sendmsg+0x9f/0xc0 net/socket.c:657 BUG: KCSAN: data-race in __remove_hrtimer / __tcp_ack_snd_check write to 0xffff8880a3a65588 of 1 bytes by interrupt on cpu 0: __remove_hrtimer+0x52/0x130 kernel/time/hrtimer.c:991 __run_hrtimer kernel/time/hrtimer.c:1496 [inline] __hrtimer_run_queues+0x250/0x600 kernel/time/hrtimer.c:1576 hrtimer_run_softirq+0x10e/0x150 kernel/time/hrtimer.c:1593 __do_softirq+0x115/0x33f kernel/softirq.c:292 invoke_softirq kernel/softirq.c:373 [inline] irq_exit+0xbb/0xe0 kernel/softirq.c:413 exiting_irq arch/x86/include/asm/apic.h:536 [inline] smp_apic_timer_interrupt+0xe6/0x280 arch/x86/kernel/apic/apic.c:1137 apic_timer_interrupt+0xf/0x20 arch/x86/entry/entry_64.S:830 read to 0xffff8880a3a65588 of 1 bytes by task 22891 on cpu 1: __tcp_ack_snd_check+0x415/0x4f0 net/ipv4/tcp_input.c:5265 tcp_ack_snd_check net/ipv4/tcp_input.c:5287 [inline] tcp_rcv_established+0x750/0xf50 net/ipv4/tcp_input.c:5708 tcp_v4_do_rcv+0x381/0x4e0 net/ipv4/tcp_ipv4.c:1561 sk_backlog_rcv include/net/sock.h:945 [inline] __release_sock+0x135/0x1e0 net/core/sock.c:2435 release_sock+0x61/0x160 net/core/sock.c:2951 sk_stream_wait_memory+0x3d7/0x7c0 net/core/stream.c:145 tcp_sendmsg_locked+0xb47/0x1f30 net/ipv4/tcp.c:1393 tcp_sendmsg+0x39/0x60 net/ipv4/tcp.c:1434 inet_sendmsg+0x6d/0x90 net/ipv4/af_inet.c:807 sock_sendmsg_nosec net/socket.c:637 [inline] sock_sendmsg+0x9f/0xc0 net/socket.c:657 __sys_sendto+0x21f/0x320 net/socket.c:1952 __do_sys_sendto net/socket.c:1964 [inline] __se_sys_sendto net/socket.c:1960 [inline] __x64_sys_sendto+0x89/0xb0 net/socket.c:1960 do_syscall_64+0xcc/0x370 arch/x86/entry/common.c:290 Reported by Kernel Concurrency Sanitizer on: CPU: 1 PID: 24652 Comm: syz-executor.3 Not tainted 5.4.0-rc3+ #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 [ tglx: Added comments ] Reported-by: syzbot <syzkaller@googlegroups.com> Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Link: https://lkml.kernel.org/r/20191106174804.74723-1-edumazet@google.com
2019-11-07 01:48:04 +08:00
/* The READ_ONCE pairs with the update functions of timer->state */
return !!(READ_ONCE(timer->state) & HRTIMER_STATE_ENQUEUED);
}
/*
* Helper function to check, whether the timer is running the callback
* function
*/
static inline int hrtimer_callback_running(struct hrtimer *timer)
{
hrtimer: Store running timer in hrtimer_clock_base The pointer to the currently running timer is stored in hrtimer_cpu_base before the base lock is dropped and the callback is invoked. This results in two levels of indirections and the upcoming support for softirq based hrtimer requires splitting the "running" storage into soft and hard IRQ context expiry. Storing both in the cpu base would require conditionals in all code paths accessing that information. It's possible to have a per clock base sequence count and running pointer without changing the semantics of the related mechanisms because the timer base pointer cannot be changed while a timer is running the callback. Unfortunately this makes cpu_clock base larger than 32 bytes on 32-bit kernels. Instead of having huge gaps due to alignment, remove the alignment and let the compiler pack CPU base for 32-bit kernels. The resulting cache access patterns are fortunately not really different from the current behaviour. On 64-bit kernels the 64-byte alignment stays and the behaviour is unchanged. This was determined by analyzing the resulting layout and looking at the number of cache lines involved for the frequently used clocks. Signed-off-by: Anna-Maria Gleixner <anna-maria@linutronix.de> Cc: Christoph Hellwig <hch@lst.de> Cc: John Stultz <john.stultz@linaro.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: keescook@chromium.org Link: http://lkml.kernel.org/r/20171221104205.7269-12-anna-maria@linutronix.de Signed-off-by: Ingo Molnar <mingo@kernel.org>
2017-12-21 18:41:40 +08:00
return timer->base->running == timer;
}
/* Forward a hrtimer so it expires after now: */
timerfd: new timerfd API This is the new timerfd API as it is implemented by the following patch: int timerfd_create(int clockid, int flags); int timerfd_settime(int ufd, int flags, const struct itimerspec *utmr, struct itimerspec *otmr); int timerfd_gettime(int ufd, struct itimerspec *otmr); The timerfd_create() API creates an un-programmed timerfd fd. The "clockid" parameter can be either CLOCK_MONOTONIC or CLOCK_REALTIME. The timerfd_settime() API give new settings by the timerfd fd, by optionally retrieving the previous expiration time (in case the "otmr" parameter is not NULL). The time value specified in "utmr" is absolute, if the TFD_TIMER_ABSTIME bit is set in the "flags" parameter. Otherwise it's a relative time. The timerfd_gettime() API returns the next expiration time of the timer, or {0, 0} if the timerfd has not been set yet. Like the previous timerfd API implementation, read(2) and poll(2) are supported (with the same interface). Here's a simple test program I used to exercise the new timerfd APIs: http://www.xmailserver.org/timerfd-test2.c [akpm@linux-foundation.org: coding-style cleanups] [akpm@linux-foundation.org: fix ia64 build] [akpm@linux-foundation.org: fix m68k build] [akpm@linux-foundation.org: fix mips build] [akpm@linux-foundation.org: fix alpha, arm, blackfin, cris, m68k, s390, sparc and sparc64 builds] [heiko.carstens@de.ibm.com: fix s390] [akpm@linux-foundation.org: fix powerpc build] [akpm@linux-foundation.org: fix sparc64 more] Signed-off-by: Davide Libenzi <davidel@xmailserver.org> Cc: Michael Kerrisk <mtk-manpages@gmx.net> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Davide Libenzi <davidel@xmailserver.org> Cc: Michael Kerrisk <mtk-manpages@gmx.net> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Michael Kerrisk <mtk.manpages@gmail.com> Cc: Davide Libenzi <davidel@xmailserver.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-02-05 14:27:26 +08:00
extern u64
hrtimer_forward(struct hrtimer *timer, ktime_t now, ktime_t interval);
/**
* hrtimer_forward_now - forward the timer expiry so it expires after now
* @timer: hrtimer to forward
* @interval: the interval to forward
*
* Forward the timer expiry so it will expire after the current time
* of the hrtimer clock base. Returns the number of overruns.
*
* Can be safely called from the callback function of @timer. If
* called from other contexts @timer must neither be enqueued nor
* running the callback and the caller needs to take care of
* serialization.
*
* Note: This only updates the timer expiry value and does not requeue
* the timer.
*/
timerfd: new timerfd API This is the new timerfd API as it is implemented by the following patch: int timerfd_create(int clockid, int flags); int timerfd_settime(int ufd, int flags, const struct itimerspec *utmr, struct itimerspec *otmr); int timerfd_gettime(int ufd, struct itimerspec *otmr); The timerfd_create() API creates an un-programmed timerfd fd. The "clockid" parameter can be either CLOCK_MONOTONIC or CLOCK_REALTIME. The timerfd_settime() API give new settings by the timerfd fd, by optionally retrieving the previous expiration time (in case the "otmr" parameter is not NULL). The time value specified in "utmr" is absolute, if the TFD_TIMER_ABSTIME bit is set in the "flags" parameter. Otherwise it's a relative time. The timerfd_gettime() API returns the next expiration time of the timer, or {0, 0} if the timerfd has not been set yet. Like the previous timerfd API implementation, read(2) and poll(2) are supported (with the same interface). Here's a simple test program I used to exercise the new timerfd APIs: http://www.xmailserver.org/timerfd-test2.c [akpm@linux-foundation.org: coding-style cleanups] [akpm@linux-foundation.org: fix ia64 build] [akpm@linux-foundation.org: fix m68k build] [akpm@linux-foundation.org: fix mips build] [akpm@linux-foundation.org: fix alpha, arm, blackfin, cris, m68k, s390, sparc and sparc64 builds] [heiko.carstens@de.ibm.com: fix s390] [akpm@linux-foundation.org: fix powerpc build] [akpm@linux-foundation.org: fix sparc64 more] Signed-off-by: Davide Libenzi <davidel@xmailserver.org> Cc: Michael Kerrisk <mtk-manpages@gmx.net> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Davide Libenzi <davidel@xmailserver.org> Cc: Michael Kerrisk <mtk-manpages@gmx.net> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Michael Kerrisk <mtk.manpages@gmail.com> Cc: Davide Libenzi <davidel@xmailserver.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-02-05 14:27:26 +08:00
static inline u64 hrtimer_forward_now(struct hrtimer *timer,
ktime_t interval)
{
return hrtimer_forward(timer, timer->base->get_time(), interval);
}
/* Precise sleep: */
extern int nanosleep_copyout(struct restart_block *, struct timespec64 *);
extern long hrtimer_nanosleep(ktime_t rqtp, const enum hrtimer_mode mode,
const clockid_t clockid);
timer: convert timer_slack_ns from unsigned long to u64 This patchset introduces a /proc/<pid>/timerslack_ns interface which would allow controlling processes to be able to set the timerslack value on other processes in order to save power by avoiding wakeups (Something Android currently does via out-of-tree patches). The first patch tries to fix the internal timer_slack_ns usage which was defined as a long, which limits the slack range to ~4 seconds on 32bit systems. It converts it to a u64, which provides the same basically unlimited slack (500 years) on both 32bit and 64bit machines. The second patch introduces the /proc/<pid>/timerslack_ns interface which allows the full 64bit slack range for a task to be read or set on both 32bit and 64bit machines. With these two patches, on a 32bit machine, after setting the slack on bash to 10 seconds: $ time sleep 1 real 0m10.747s user 0m0.001s sys 0m0.005s The first patch is a little ugly, since I had to chase the slack delta arguments through a number of functions converting them to u64s. Let me know if it makes sense to break that up more or not. Other than that things are fairly straightforward. This patch (of 2): The timer_slack_ns value in the task struct is currently a unsigned long. This means that on 32bit applications, the maximum slack is just over 4 seconds. However, on 64bit machines, its much much larger (~500 years). This disparity could make application development a little (as well as the default_slack) to a u64. This means both 32bit and 64bit systems have the same effective internal slack range. Now the existing ABI via PR_GET_TIMERSLACK and PR_SET_TIMERSLACK specify the interface as a unsigned long, so we preserve that limitation on 32bit systems, where SET_TIMERSLACK can only set the slack to a unsigned long value, and GET_TIMERSLACK will return ULONG_MAX if the slack is actually larger then what can be stored by an unsigned long. This patch also modifies hrtimer functions which specified the slack delta as a unsigned long. Signed-off-by: John Stultz <john.stultz@linaro.org> Cc: Arjan van de Ven <arjan@linux.intel.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Oren Laadan <orenl@cellrox.com> Cc: Ruchi Kandoi <kandoiruchi@google.com> Cc: Rom Lemarchand <romlem@android.com> Cc: Kees Cook <keescook@chromium.org> Cc: Android Kernel Team <kernel-team@android.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-03-18 05:20:51 +08:00
extern int schedule_hrtimeout_range(ktime_t *expires, u64 delta,
const enum hrtimer_mode mode);
extern int schedule_hrtimeout_range_clock(ktime_t *expires,
timer: convert timer_slack_ns from unsigned long to u64 This patchset introduces a /proc/<pid>/timerslack_ns interface which would allow controlling processes to be able to set the timerslack value on other processes in order to save power by avoiding wakeups (Something Android currently does via out-of-tree patches). The first patch tries to fix the internal timer_slack_ns usage which was defined as a long, which limits the slack range to ~4 seconds on 32bit systems. It converts it to a u64, which provides the same basically unlimited slack (500 years) on both 32bit and 64bit machines. The second patch introduces the /proc/<pid>/timerslack_ns interface which allows the full 64bit slack range for a task to be read or set on both 32bit and 64bit machines. With these two patches, on a 32bit machine, after setting the slack on bash to 10 seconds: $ time sleep 1 real 0m10.747s user 0m0.001s sys 0m0.005s The first patch is a little ugly, since I had to chase the slack delta arguments through a number of functions converting them to u64s. Let me know if it makes sense to break that up more or not. Other than that things are fairly straightforward. This patch (of 2): The timer_slack_ns value in the task struct is currently a unsigned long. This means that on 32bit applications, the maximum slack is just over 4 seconds. However, on 64bit machines, its much much larger (~500 years). This disparity could make application development a little (as well as the default_slack) to a u64. This means both 32bit and 64bit systems have the same effective internal slack range. Now the existing ABI via PR_GET_TIMERSLACK and PR_SET_TIMERSLACK specify the interface as a unsigned long, so we preserve that limitation on 32bit systems, where SET_TIMERSLACK can only set the slack to a unsigned long value, and GET_TIMERSLACK will return ULONG_MAX if the slack is actually larger then what can be stored by an unsigned long. This patch also modifies hrtimer functions which specified the slack delta as a unsigned long. Signed-off-by: John Stultz <john.stultz@linaro.org> Cc: Arjan van de Ven <arjan@linux.intel.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Oren Laadan <orenl@cellrox.com> Cc: Ruchi Kandoi <kandoiruchi@google.com> Cc: Rom Lemarchand <romlem@android.com> Cc: Kees Cook <keescook@chromium.org> Cc: Android Kernel Team <kernel-team@android.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-03-18 05:20:51 +08:00
u64 delta,
const enum hrtimer_mode mode,
clockid_t clock_id);
extern int schedule_hrtimeout(ktime_t *expires, const enum hrtimer_mode mode);
/* Soft interrupt function to run the hrtimer queues: */
extern void hrtimer_run_queues(void);
/* Bootup initialization: */
extern void __init hrtimers_init(void);
/* Show pending timers: */
extern void sysrq_timer_list_show(void);
int hrtimers_prepare_cpu(unsigned int cpu);
#ifdef CONFIG_HOTPLUG_CPU
int hrtimers_dead_cpu(unsigned int cpu);
#else
#define hrtimers_dead_cpu NULL
#endif
#endif