Re: [PATCH 21/23 -v8] Add markers to various events
From: Mathieu Desnoyers
Date: Thu Jan 31 2008 - 07:06:24 EST
* Steven Rostedt (rostedt@xxxxxxxxxxx) wrote:
> This patch adds markers to various events in the kernel.
> (interrupts, task activation and hrtimers)
>
Hi Steven,
I would propose the following standard for IRQ handler markers:
trace_mark(kernel_irq_entry, "irq_id %u kernel_mode %u", irq,
(regs)?(!user_mode(regs)):(1));
...
trace_mark(kernel_irq_exit, MARK_NOARGS);
So we can know the elaspsed time in irq handlers and whether they are
nested on user of kernel code.
The same for traps :
trace_mark(kernel_arch_trap_entry, "trap_id %d ip #p%ld", trapnr,
instruction_pointer(regs));
Where we know the trap number and the instruction pointer that caused
the trap. Here again, we should put a :
trace_mark(kernel_arch_trap_exit, MARK_NOARGS);
At the end of the trap handlers.
It makes automatic analysis _much_ easier than trying to gather each and
every handler instrumentation which would have a different name...
Mathieu
> Signed-off-by: Steven Rostedt <srostedt@xxxxxxxxxx>
> ---
> arch/x86/kernel/apic_32.c | 2 ++
> arch/x86/kernel/irq_32.c | 1 +
> arch/x86/kernel/irq_64.c | 2 ++
> arch/x86/kernel/traps_32.c | 2 ++
> arch/x86/kernel/traps_64.c | 2 ++
> arch/x86/mm/fault_32.c | 3 +++
> arch/x86/mm/fault_64.c | 3 +++
> kernel/hrtimer.c | 7 +++++++
> kernel/sched.c | 11 +++++++++++
> 9 files changed, 33 insertions(+)
>
> Index: linux-mcount.git/arch/x86/kernel/apic_32.c
> ===================================================================
> --- linux-mcount.git.orig/arch/x86/kernel/apic_32.c 2008-01-30 15:10:16.000000000 -0500
> +++ linux-mcount.git/arch/x86/kernel/apic_32.c 2008-01-30 15:54:06.000000000 -0500
> @@ -581,6 +581,8 @@ notrace fastcall void smp_apic_timer_int
> {
> struct pt_regs *old_regs = set_irq_regs(regs);
>
> + trace_mark(arch_apic_timer, "ip %lx", regs->eip);
> +
> /*
> * NOTE! We'd better ACK the irq immediately,
> * because timer handling can be slow.
> Index: linux-mcount.git/arch/x86/kernel/irq_32.c
> ===================================================================
> --- linux-mcount.git.orig/arch/x86/kernel/irq_32.c 2008-01-30 14:35:48.000000000 -0500
> +++ linux-mcount.git/arch/x86/kernel/irq_32.c 2008-01-30 15:54:06.000000000 -0500
> @@ -85,6 +85,7 @@ fastcall unsigned int do_IRQ(struct pt_r
>
> old_regs = set_irq_regs(regs);
> irq_enter();
> + trace_mark(arch_do_irq, "ip %lx irq %d", regs->eip, irq);
> #ifdef CONFIG_DEBUG_STACKOVERFLOW
> /* Debugging check for stack overflow: is there less than 1KB free? */
> {
> Index: linux-mcount.git/arch/x86/kernel/irq_64.c
> ===================================================================
> --- linux-mcount.git.orig/arch/x86/kernel/irq_64.c 2008-01-30 14:35:48.000000000 -0500
> +++ linux-mcount.git/arch/x86/kernel/irq_64.c 2008-01-30 15:54:06.000000000 -0500
> @@ -149,6 +149,8 @@ asmlinkage unsigned int do_IRQ(struct pt
> irq_enter();
> irq = __get_cpu_var(vector_irq)[vector];
>
> + trace_mark(arch_do_irq, "ip %lx irq %d", regs->rip, irq);
> +
> #ifdef CONFIG_DEBUG_STACKOVERFLOW
> stack_overflow_check(regs);
> #endif
> Index: linux-mcount.git/arch/x86/kernel/traps_32.c
> ===================================================================
> --- linux-mcount.git.orig/arch/x86/kernel/traps_32.c 2008-01-30 14:35:48.000000000 -0500
> +++ linux-mcount.git/arch/x86/kernel/traps_32.c 2008-01-30 15:54:06.000000000 -0500
> @@ -769,6 +769,8 @@ fastcall __kprobes void do_nmi(struct pt
>
> nmi_enter();
>
> + trace_mark(arch_do_nmi, "ip %lx flags %lx", regs->eip, regs->eflags);
> +
> cpu = smp_processor_id();
>
> ++nmi_count(cpu);
> Index: linux-mcount.git/arch/x86/kernel/traps_64.c
> ===================================================================
> --- linux-mcount.git.orig/arch/x86/kernel/traps_64.c 2008-01-30 14:35:48.000000000 -0500
> +++ linux-mcount.git/arch/x86/kernel/traps_64.c 2008-01-30 15:54:06.000000000 -0500
> @@ -782,6 +782,8 @@ asmlinkage __kprobes void default_do_nmi
>
> cpu = smp_processor_id();
>
> + trace_mark(arch_do_nmi, "ip %lx flags %lx", regs->rip, regs->eflags);
> +
> /* Only the BSP gets external NMIs from the system. */
> if (!cpu)
> reason = get_nmi_reason();
> Index: linux-mcount.git/arch/x86/mm/fault_32.c
> ===================================================================
> --- linux-mcount.git.orig/arch/x86/mm/fault_32.c 2008-01-30 14:35:48.000000000 -0500
> +++ linux-mcount.git/arch/x86/mm/fault_32.c 2008-01-30 15:54:06.000000000 -0500
> @@ -311,6 +311,9 @@ fastcall void __kprobes do_page_fault(st
> /* get the address */
> address = read_cr2();
>
> + trace_mark(arch_do_page_fault, "ip %lx err %lx addr %lx",
> + regs->eip, error_code, address);
> +
> tsk = current;
>
> si_code = SEGV_MAPERR;
> Index: linux-mcount.git/arch/x86/mm/fault_64.c
> ===================================================================
> --- linux-mcount.git.orig/arch/x86/mm/fault_64.c 2008-01-30 14:35:48.000000000 -0500
> +++ linux-mcount.git/arch/x86/mm/fault_64.c 2008-01-30 15:54:06.000000000 -0500
> @@ -316,6 +316,9 @@ asmlinkage void __kprobes do_page_fault(
> /* get the address */
> address = read_cr2();
>
> + trace_mark(arch_do_page_fault, "ip %lx err %lx addr %lx",
> + regs->rip, error_code, address);
> +
> info.si_code = SEGV_MAPERR;
>
>
> Index: linux-mcount.git/kernel/hrtimer.c
> ===================================================================
> --- linux-mcount.git.orig/kernel/hrtimer.c 2008-01-30 14:35:48.000000000 -0500
> +++ linux-mcount.git/kernel/hrtimer.c 2008-01-30 15:54:06.000000000 -0500
> @@ -709,6 +709,8 @@ static void enqueue_hrtimer(struct hrtim
> struct hrtimer *entry;
> int leftmost = 1;
>
> + trace_mark(kernel_hrtimer_enqueue,
> + "expires %p timer %p", &timer->expires, timer);
> /*
> * Find the right place in the rbtree:
> */
> @@ -1130,6 +1132,7 @@ void hrtimer_interrupt(struct clock_even
>
> retry:
> now = ktime_get();
> + trace_mark(kernel_hrtimer_interrupt, "now %p", &now);
>
> expires_next.tv64 = KTIME_MAX;
>
> @@ -1168,6 +1171,10 @@ void hrtimer_interrupt(struct clock_even
> continue;
> }
>
> + trace_mark(kernel_hrtimer_interrupt_expire,
> + "expires %p timer %p",
> + &timer->expires, timer);
> +
> __run_hrtimer(timer);
> }
> spin_unlock(&cpu_base->lock);
> Index: linux-mcount.git/kernel/sched.c
> ===================================================================
> --- linux-mcount.git.orig/kernel/sched.c 2008-01-30 15:46:44.000000000 -0500
> +++ linux-mcount.git/kernel/sched.c 2008-01-30 15:54:06.000000000 -0500
> @@ -90,6 +90,11 @@ unsigned long long __attribute__((weak))
> #define PRIO_TO_NICE(prio) ((prio) - MAX_RT_PRIO - 20)
> #define TASK_NICE(p) PRIO_TO_NICE((p)->static_prio)
>
> +#define __PRIO(prio) \
> + ((prio) <= 99 ? 199 - (prio) : (prio) - 120)
> +
> +#define PRIO(p) __PRIO((p)->prio)
> +
> /*
> * 'User priority' is the nice value converted to something we
> * can work with better when scaling various scheduler parameters,
> @@ -1372,6 +1377,9 @@ static void activate_task(struct rq *rq,
> if (p->state == TASK_UNINTERRUPTIBLE)
> rq->nr_uninterruptible--;
>
> + trace_mark(kernel_sched_activate_task,
> + "pid %d prio %d nr_running %ld",
> + p->pid, PRIO(p), rq->nr_running);
> enqueue_task(rq, p, wakeup);
> inc_nr_running(p, rq);
> }
> @@ -1385,6 +1393,9 @@ static void deactivate_task(struct rq *r
> rq->nr_uninterruptible++;
>
> dequeue_task(rq, p, sleep);
> + trace_mark(kernel_sched_deactivate_task,
> + "pid %d prio %d nr_running %ld",
> + p->pid, PRIO(p), rq->nr_running);
> dec_nr_running(p, rq);
> }
>
>
> --
--
Mathieu Desnoyers
Computer Engineering Ph.D. Student, Ecole Polytechnique de Montreal
OpenPGP key fingerprint: 8CD5 52C3 8E3C 4140 715F BA06 3F25 A8FE 3BAE 9A68
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/