kernel_optimize_test/include/linux/profile.h

127 lines
2.6 KiB
C
Raw Normal View History

#ifndef _LINUX_PROFILE_H
#define _LINUX_PROFILE_H
#ifdef __KERNEL__
#include <linux/kernel.h>
#include <linux/init.h>
#include <linux/cpumask.h>
#include <linux/cache.h>
#include <asm/errno.h>
extern int prof_on __read_mostly;
#define CPU_PROFILING 1
#define SCHED_PROFILING 2
#define SLEEP_PROFILING 3
#define KVM_PROFILING 4
struct proc_dir_entry;
struct pt_regs;
struct notifier_block;
/* init basic kernel profiler */
void __init profile_init(void);
IRQ: Maintain regs pointer globally rather than passing to IRQ handlers Maintain a per-CPU global "struct pt_regs *" variable which can be used instead of passing regs around manually through all ~1800 interrupt handlers in the Linux kernel. The regs pointer is used in few places, but it potentially costs both stack space and code to pass it around. On the FRV arch, removing the regs parameter from all the genirq function results in a 20% speed up of the IRQ exit path (ie: from leaving timer_interrupt() to leaving do_IRQ()). Where appropriate, an arch may override the generic storage facility and do something different with the variable. On FRV, for instance, the address is maintained in GR28 at all times inside the kernel as part of general exception handling. Having looked over the code, it appears that the parameter may be handed down through up to twenty or so layers of functions. Consider a USB character device attached to a USB hub, attached to a USB controller that posts its interrupts through a cascaded auxiliary interrupt controller. A character device driver may want to pass regs to the sysrq handler through the input layer which adds another few layers of parameter passing. I've build this code with allyesconfig for x86_64 and i386. I've runtested the main part of the code on FRV and i386, though I can't test most of the drivers. I've also done partial conversion for powerpc and MIPS - these at least compile with minimal configurations. This will affect all archs. Mostly the changes should be relatively easy. Take do_IRQ(), store the regs pointer at the beginning, saving the old one: struct pt_regs *old_regs = set_irq_regs(regs); And put the old one back at the end: set_irq_regs(old_regs); Don't pass regs through to generic_handle_irq() or __do_IRQ(). In timer_interrupt(), this sort of change will be necessary: - update_process_times(user_mode(regs)); - profile_tick(CPU_PROFILING, regs); + update_process_times(user_mode(get_irq_regs())); + profile_tick(CPU_PROFILING); I'd like to move update_process_times()'s use of get_irq_regs() into itself, except that i386, alone of the archs, uses something other than user_mode(). Some notes on the interrupt handling in the drivers: (*) input_dev() is now gone entirely. The regs pointer is no longer stored in the input_dev struct. (*) finish_unlinks() in drivers/usb/host/ohci-q.c needs checking. It does something different depending on whether it's been supplied with a regs pointer or not. (*) Various IRQ handler function pointers have been moved to type irq_handler_t. Signed-Off-By: David Howells <dhowells@redhat.com> (cherry picked from 1b16e7ac850969f38b375e511e3fa2f474a33867 commit)
2006-10-05 21:55:46 +08:00
void profile_tick(int);
/*
* Add multiple profiler hits to a given address:
*/
void profile_hits(int, void *ip, unsigned int nr_hits);
/*
* Single profiler hit:
*/
static inline void profile_hit(int type, void *ip)
{
/*
* Speedup for the common (no profiling enabled) case:
*/
if (unlikely(prof_on == type))
profile_hits(type, ip, 1);
}
#ifdef CONFIG_PROC_FS
void create_prof_cpu_mask(struct proc_dir_entry *);
#else
#define create_prof_cpu_mask(x) do { (void)(x); } while (0)
#endif
enum profile_type {
PROFILE_TASK_EXIT,
PROFILE_MUNMAP
};
#ifdef CONFIG_PROFILING
struct task_struct;
struct mm_struct;
/* task is in do_exit() */
void profile_task_exit(struct task_struct * task);
/* task is dead, free task struct ? Returns 1 if
* the task was taken, 0 if the task should be freed.
*/
int profile_handoff_task(struct task_struct * task);
/* sys_munmap */
void profile_munmap(unsigned long addr);
int task_handoff_register(struct notifier_block * n);
int task_handoff_unregister(struct notifier_block * n);
int profile_event_register(enum profile_type, struct notifier_block * n);
int profile_event_unregister(enum profile_type, struct notifier_block * n);
int register_timer_hook(int (*hook)(struct pt_regs *));
void unregister_timer_hook(int (*hook)(struct pt_regs *));
/* Timer based profiling hook */
extern int (*timer_hook)(struct pt_regs *);
struct pt_regs;
#else
static inline int task_handoff_register(struct notifier_block * n)
{
return -ENOSYS;
}
static inline int task_handoff_unregister(struct notifier_block * n)
{
return -ENOSYS;
}
static inline int profile_event_register(enum profile_type t, struct notifier_block * n)
{
return -ENOSYS;
}
static inline int profile_event_unregister(enum profile_type t, struct notifier_block * n)
{
return -ENOSYS;
}
#define profile_task_exit(a) do { } while (0)
#define profile_handoff_task(a) (0)
#define profile_munmap(a) do { } while (0)
static inline int register_timer_hook(int (*hook)(struct pt_regs *))
{
return -ENOSYS;
}
static inline void unregister_timer_hook(int (*hook)(struct pt_regs *))
{
return;
}
#endif /* CONFIG_PROFILING */
#endif /* __KERNEL__ */
#endif /* _LINUX_PROFILE_H */