From ca109491f612aab5c8152207631c0444f63da97f Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 25 Nov 2008 12:43:51 +0100 Subject: hrtimer: removing all ur callback modes Impact: cleanup, move all hrtimer processing into hardirq context This is an attempt at removing some of the hrtimer complexity by reducing the number of callback modes to 1. This means that all hrtimer callback functions will be ran from HARD-irq context. I went through all the 30 odd hrtimer callback functions in the kernel and saw only one that I'm not quite sure of, which is the one in net/can/bcm.c - hence I'm CC-ing the folks responsible for that code. Furthermore, the hrtimer core now calls callbacks directly with IRQs disabled in case you try to enqueue an expired timer. If this timer is a periodic timer (which should use hrtimer_forward() to advance its time) then it might be possible to end up in an inf. recursive loop due to the fact that hrtimer_forward() doesn't round up to the next timer granularity, and therefore keeps on calling the callback - obviously this needs a fix. Aside from that, this seems to compile and actually boot on my dual core test box - although I'm sure there are some bugs in, me not hitting any makes me certain :-) Signed-off-by: Peter Zijlstra Signed-off-by: Ingo Molnar --- include/linux/hrtimer.h | 34 ++-------------------------------- include/linux/interrupt.h | 3 --- 2 files changed, 2 insertions(+), 35 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h index 3eba43878dc..bd37078c2d7 100644 --- a/include/linux/hrtimer.h +++ b/include/linux/hrtimer.h @@ -42,26 +42,6 @@ enum hrtimer_restart { HRTIMER_RESTART, /* Timer must be restarted */ }; -/* - * hrtimer callback modes: - * - * HRTIMER_CB_SOFTIRQ: Callback must run in softirq context - * HRTIMER_CB_IRQSAFE_PERCPU: Callback must run in hardirq context - * Special mode for tick emulation and - * scheduler timer. Such timers are per - * cpu and not allowed to be migrated on - * cpu unplug. - * HRTIMER_CB_IRQSAFE_UNLOCKED: Callback should run in hardirq context - * with timer->base lock unlocked - * used for timers which call wakeup to - * avoid lock order problems with rq->lock - */ -enum hrtimer_cb_mode { - HRTIMER_CB_SOFTIRQ, - HRTIMER_CB_IRQSAFE_PERCPU, - HRTIMER_CB_IRQSAFE_UNLOCKED, -}; - /* * Values to track state of the timer * @@ -70,7 +50,6 @@ enum hrtimer_cb_mode { * 0x00 inactive * 0x01 enqueued into rbtree * 0x02 callback function running - * 0x04 callback pending (high resolution mode) * * Special cases: * 0x03 callback function running and enqueued @@ -92,8 +71,7 @@ enum hrtimer_cb_mode { #define HRTIMER_STATE_INACTIVE 0x00 #define HRTIMER_STATE_ENQUEUED 0x01 #define HRTIMER_STATE_CALLBACK 0x02 -#define HRTIMER_STATE_PENDING 0x04 -#define HRTIMER_STATE_MIGRATE 0x08 +#define HRTIMER_STATE_MIGRATE 0x04 /** * struct hrtimer - the basic hrtimer structure @@ -109,8 +87,6 @@ enum hrtimer_cb_mode { * @function: timer expiry callback function * @base: pointer to the timer base (per cpu and per clock) * @state: state information (See bit values above) - * @cb_mode: high resolution timer feature to select the callback execution - * mode * @cb_entry: list head to enqueue an expired timer into the callback list * @start_site: timer statistics field to store the site where the timer * was started @@ -129,7 +105,6 @@ struct hrtimer { struct hrtimer_clock_base *base; unsigned long state; struct list_head cb_entry; - enum hrtimer_cb_mode cb_mode; #ifdef CONFIG_TIMER_STATS int start_pid; void *start_site; @@ -188,15 +163,11 @@ struct hrtimer_clock_base { * @check_clocks: Indictator, when set evaluate time source and clock * event devices whether high resolution mode can be * activated. - * @cb_pending: Expired timers are moved from the rbtree to this - * list in the timer interrupt. The list is processed - * in the softirq. * @nr_events: Total number of timer interrupt events */ struct hrtimer_cpu_base { spinlock_t lock; struct hrtimer_clock_base clock_base[HRTIMER_MAX_CLOCK_BASES]; - struct list_head cb_pending; #ifdef CONFIG_HIGH_RES_TIMERS ktime_t expires_next; int hres_active; @@ -404,8 +375,7 @@ static inline int hrtimer_active(const struct hrtimer *timer) */ static inline int hrtimer_is_queued(struct hrtimer *timer) { - return timer->state & - (HRTIMER_STATE_ENQUEUED | HRTIMER_STATE_PENDING); + return timer->state & HRTIMER_STATE_ENQUEUED; } /* diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h index f58a0cf8929..d6210a97a8c 100644 --- a/include/linux/interrupt.h +++ b/include/linux/interrupt.h @@ -251,9 +251,6 @@ enum BLOCK_SOFTIRQ, TASKLET_SOFTIRQ, SCHED_SOFTIRQ, -#ifdef CONFIG_HIGH_RES_TIMERS - HRTIMER_SOFTIRQ, -#endif RCU_SOFTIRQ, /* Preferable RCU should always be the last softirq */ NR_SOFTIRQS -- cgit v1.2.3 From 27af4245b6ce99e08c6a7c38825383bf51119cc9 Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Mon, 1 Dec 2008 14:18:13 -0800 Subject: posix-timers: use "struct pid*" instead of "struct task_struct*" Impact: restructure, clean up code k_itimer holds the ref to the ->it_process until sys_timer_delete(). This allows to pin up to RLIMIT_SIGPENDING dead task_struct's. Change the code to use "struct pid *" instead. The patch doesn't kill ->it_process, it places ->it_pid into the union. ->it_process is still used by do_cpu_nanosleep() as before. It would be trivial to change the nanosleep code as well, but since it uses it_process in a special way I think it is better to keep this field for grep. The patch bloats the kernel by 104 bytes and it also adds the new pointer, ->it_signal, to k_itimer. It is used by lock_timer() to verify that the found timer was not created by another process. It is not clear why do we use the global database (and thus the global idr_lock) for posix timers. We still need the signal_struct->posix_timers which contains all useable timers, perhaps it is better to use some form of per-process array instead. Signed-off-by: Oleg Nesterov Signed-off-by: Andrew Morton Signed-off-by: Thomas Gleixner --- include/linux/posix-timers.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/posix-timers.h b/include/linux/posix-timers.h index a7c72135554..4f71bf4e628 100644 --- a/include/linux/posix-timers.h +++ b/include/linux/posix-timers.h @@ -45,7 +45,11 @@ struct k_itimer { int it_requeue_pending; /* waiting to requeue this timer */ #define REQUEUE_PENDING 1 int it_sigev_notify; /* notify word of sigevent struct */ - struct task_struct *it_process; /* process to send signal to */ + struct signal_struct *it_signal; + union { + struct pid *it_pid; /* pid of process to send signal to */ + struct task_struct *it_process; /* for clock_nanosleep */ + }; struct sigqueue *sigq; /* signal queue entry. */ union { struct { -- cgit v1.2.3 From c29541b24fb2c6301021637229ae5347c877330a Mon Sep 17 00:00:00 2001 From: Mike Frysinger Date: Mon, 1 Dec 2008 14:18:11 -0800 Subject: linux/timex.h: cleanup for userspace Impact: fix user-space exported use Move all the kernel-specific defines and includes into the __KERNEL__ section so that they don't get leaked into userspace. [akpm@linux-foundation.org: coding-style fixes] Signed-off-by: Mike Frysinger Signed-off-by: Andrew Morton Signed-off-by: Thomas Gleixner --- include/linux/timex.h | 73 ++++++++++++++++++++++++++------------------------- 1 file changed, 37 insertions(+), 36 deletions(-) (limited to 'include/linux') diff --git a/include/linux/timex.h b/include/linux/timex.h index 9007313b5b7..998a55d80ac 100644 --- a/include/linux/timex.h +++ b/include/linux/timex.h @@ -53,46 +53,10 @@ #ifndef _LINUX_TIMEX_H #define _LINUX_TIMEX_H -#include #include -#include - #define NTP_API 4 /* NTP API version */ -/* - * SHIFT_KG and SHIFT_KF establish the damping of the PLL and are chosen - * for a slightly underdamped convergence characteristic. SHIFT_KH - * establishes the damping of the FLL and is chosen by wisdom and black - * art. - * - * MAXTC establishes the maximum time constant of the PLL. With the - * SHIFT_KG and SHIFT_KF values given and a time constant range from - * zero to MAXTC, the PLL will converge in 15 minutes to 16 hours, - * respectively. - */ -#define SHIFT_PLL 4 /* PLL frequency factor (shift) */ -#define SHIFT_FLL 2 /* FLL frequency factor (shift) */ -#define MAXTC 10 /* maximum time constant (shift) */ - -/* - * SHIFT_USEC defines the scaling (shift) of the time_freq and - * time_tolerance variables, which represent the current frequency - * offset and maximum frequency tolerance. - */ -#define SHIFT_USEC 16 /* frequency offset scale (shift) */ -#define PPM_SCALE (NSEC_PER_USEC << (NTP_SCALE_SHIFT - SHIFT_USEC)) -#define PPM_SCALE_INV_SHIFT 19 -#define PPM_SCALE_INV ((1ll << (PPM_SCALE_INV_SHIFT + NTP_SCALE_SHIFT)) / \ - PPM_SCALE + 1) - -#define MAXPHASE 500000000l /* max phase error (ns) */ -#define MAXFREQ 500000 /* max frequency error (ns/s) */ -#define MAXFREQ_SCALED ((s64)MAXFREQ << NTP_SCALE_SHIFT) -#define MINSEC 256 /* min interval between updates (s) */ -#define MAXSEC 2048 /* max interval between updates (s) */ -#define NTP_PHASE_LIMIT ((MAXPHASE / NSEC_PER_USEC) << 5) /* beyond max. dispersion */ - /* * syscall interface - used (mainly by NTP daemon) * to discipline kernel clock oscillator @@ -199,8 +163,45 @@ struct timex { #define TIME_BAD TIME_ERROR /* bw compat */ #ifdef __KERNEL__ +#include +#include +#include + #include +/* + * SHIFT_KG and SHIFT_KF establish the damping of the PLL and are chosen + * for a slightly underdamped convergence characteristic. SHIFT_KH + * establishes the damping of the FLL and is chosen by wisdom and black + * art. + * + * MAXTC establishes the maximum time constant of the PLL. With the + * SHIFT_KG and SHIFT_KF values given and a time constant range from + * zero to MAXTC, the PLL will converge in 15 minutes to 16 hours, + * respectively. + */ +#define SHIFT_PLL 4 /* PLL frequency factor (shift) */ +#define SHIFT_FLL 2 /* FLL frequency factor (shift) */ +#define MAXTC 10 /* maximum time constant (shift) */ + +/* + * SHIFT_USEC defines the scaling (shift) of the time_freq and + * time_tolerance variables, which represent the current frequency + * offset and maximum frequency tolerance. + */ +#define SHIFT_USEC 16 /* frequency offset scale (shift) */ +#define PPM_SCALE (NSEC_PER_USEC << (NTP_SCALE_SHIFT - SHIFT_USEC)) +#define PPM_SCALE_INV_SHIFT 19 +#define PPM_SCALE_INV ((1ll << (PPM_SCALE_INV_SHIFT + NTP_SCALE_SHIFT)) / \ + PPM_SCALE + 1) + +#define MAXPHASE 500000000l /* max phase error (ns) */ +#define MAXFREQ 500000 /* max frequency error (ns/s) */ +#define MAXFREQ_SCALED ((s64)MAXFREQ << NTP_SCALE_SHIFT) +#define MINSEC 256 /* min interval between updates (s) */ +#define MAXSEC 2048 /* max interval between updates (s) */ +#define NTP_PHASE_LIMIT ((MAXPHASE / NSEC_PER_USEC) << 5) /* beyond max. dispersion */ + /* * kernel variables * Note: maximum error = NTP synch distance = dispersion + delay / 2; -- cgit v1.2.3