mirror of
				https://git.kernel.org/pub/scm/linux/kernel/git/chenhuacai/linux-loongson
				synced 2025-10-31 08:26:29 +00:00 
			
		
		
		
	 a4eaf7f146
			
		
	
	
		a4eaf7f146
		
	
	
	
	
		
			
			Replace pmu::{enable,disable,start,stop,unthrottle} with
pmu::{add,del,start,stop}, all of which take a flags argument.
The new interface extends the capability to stop a counter while
keeping it scheduled on the PMU. We replace the throttled state with
the generic stopped state.
This also allows us to efficiently stop/start counters over certain
code paths (like IRQ handlers).
It also allows scheduling a counter without it starting, allowing for
a generic frozen state (useful for rotating stopped counters).
The stopped state is implemented in two different ways, depending on
how the architecture implemented the throttled state:
 1) We disable the counter:
    a) the pmu has per-counter enable bits, we flip that
    b) we program a NOP event, preserving the counter state
 2) We store the counter state and ignore all read/overflow events
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: paulus <paulus@samba.org>
Cc: stephane eranian <eranian@googlemail.com>
Cc: Robert Richter <robert.richter@amd.com>
Cc: Will Deacon <will.deacon@arm.com>
Cc: Paul Mundt <lethal@linux-sh.org>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Cyrill Gorcunov <gorcunov@gmail.com>
Cc: Lin Ming <ming.m.lin@intel.com>
Cc: Yanmin <yanmin_zhang@linux.intel.com>
Cc: Deng-Cheng Zhu <dengcheng.zhu@gmail.com>
Cc: David Miller <davem@davemloft.net>
Cc: Michael Cree <mcree@orcon.net.nz>
LKML-Reference: <new-submission>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
		
	
			
		
			
				
	
	
		
			188 lines
		
	
	
		
			4.0 KiB
		
	
	
	
		
			C
		
	
	
	
	
	
			
		
		
	
	
			188 lines
		
	
	
		
			4.0 KiB
		
	
	
	
		
			C
		
	
	
	
	
	
| /*
 | |
|  * trace event based perf event profiling/tracing
 | |
|  *
 | |
|  * Copyright (C) 2009 Red Hat Inc, Peter Zijlstra <pzijlstr@redhat.com>
 | |
|  * Copyright (C) 2009-2010 Frederic Weisbecker <fweisbec@gmail.com>
 | |
|  */
 | |
| 
 | |
| #include <linux/module.h>
 | |
| #include <linux/kprobes.h>
 | |
| #include "trace.h"
 | |
| 
 | |
| static char __percpu *perf_trace_buf[PERF_NR_CONTEXTS];
 | |
| 
 | |
| /*
 | |
|  * Force it to be aligned to unsigned long to avoid misaligned accesses
 | |
|  * suprises
 | |
|  */
 | |
| typedef typeof(unsigned long [PERF_MAX_TRACE_SIZE / sizeof(unsigned long)])
 | |
| 	perf_trace_t;
 | |
| 
 | |
| /* Count the events in use (per event id, not per instance) */
 | |
| static int	total_ref_count;
 | |
| 
 | |
| static int perf_trace_event_init(struct ftrace_event_call *tp_event,
 | |
| 				 struct perf_event *p_event)
 | |
| {
 | |
| 	struct hlist_head __percpu *list;
 | |
| 	int ret = -ENOMEM;
 | |
| 	int cpu;
 | |
| 
 | |
| 	p_event->tp_event = tp_event;
 | |
| 	if (tp_event->perf_refcount++ > 0)
 | |
| 		return 0;
 | |
| 
 | |
| 	list = alloc_percpu(struct hlist_head);
 | |
| 	if (!list)
 | |
| 		goto fail;
 | |
| 
 | |
| 	for_each_possible_cpu(cpu)
 | |
| 		INIT_HLIST_HEAD(per_cpu_ptr(list, cpu));
 | |
| 
 | |
| 	tp_event->perf_events = list;
 | |
| 
 | |
| 	if (!total_ref_count) {
 | |
| 		char __percpu *buf;
 | |
| 		int i;
 | |
| 
 | |
| 		for (i = 0; i < PERF_NR_CONTEXTS; i++) {
 | |
| 			buf = (char __percpu *)alloc_percpu(perf_trace_t);
 | |
| 			if (!buf)
 | |
| 				goto fail;
 | |
| 
 | |
| 			perf_trace_buf[i] = buf;
 | |
| 		}
 | |
| 	}
 | |
| 
 | |
| 	ret = tp_event->class->reg(tp_event, TRACE_REG_PERF_REGISTER);
 | |
| 	if (ret)
 | |
| 		goto fail;
 | |
| 
 | |
| 	total_ref_count++;
 | |
| 	return 0;
 | |
| 
 | |
| fail:
 | |
| 	if (!total_ref_count) {
 | |
| 		int i;
 | |
| 
 | |
| 		for (i = 0; i < PERF_NR_CONTEXTS; i++) {
 | |
| 			free_percpu(perf_trace_buf[i]);
 | |
| 			perf_trace_buf[i] = NULL;
 | |
| 		}
 | |
| 	}
 | |
| 
 | |
| 	if (!--tp_event->perf_refcount) {
 | |
| 		free_percpu(tp_event->perf_events);
 | |
| 		tp_event->perf_events = NULL;
 | |
| 	}
 | |
| 
 | |
| 	return ret;
 | |
| }
 | |
| 
 | |
| int perf_trace_init(struct perf_event *p_event)
 | |
| {
 | |
| 	struct ftrace_event_call *tp_event;
 | |
| 	int event_id = p_event->attr.config;
 | |
| 	int ret = -EINVAL;
 | |
| 
 | |
| 	mutex_lock(&event_mutex);
 | |
| 	list_for_each_entry(tp_event, &ftrace_events, list) {
 | |
| 		if (tp_event->event.type == event_id &&
 | |
| 		    tp_event->class && tp_event->class->reg &&
 | |
| 		    try_module_get(tp_event->mod)) {
 | |
| 			ret = perf_trace_event_init(tp_event, p_event);
 | |
| 			if (ret)
 | |
| 				module_put(tp_event->mod);
 | |
| 			break;
 | |
| 		}
 | |
| 	}
 | |
| 	mutex_unlock(&event_mutex);
 | |
| 
 | |
| 	return ret;
 | |
| }
 | |
| 
 | |
| int perf_trace_add(struct perf_event *p_event, int flags)
 | |
| {
 | |
| 	struct ftrace_event_call *tp_event = p_event->tp_event;
 | |
| 	struct hlist_head __percpu *pcpu_list;
 | |
| 	struct hlist_head *list;
 | |
| 
 | |
| 	pcpu_list = tp_event->perf_events;
 | |
| 	if (WARN_ON_ONCE(!pcpu_list))
 | |
| 		return -EINVAL;
 | |
| 
 | |
| 	if (!(flags & PERF_EF_START))
 | |
| 		p_event->hw.state = PERF_HES_STOPPED;
 | |
| 
 | |
| 	list = this_cpu_ptr(pcpu_list);
 | |
| 	hlist_add_head_rcu(&p_event->hlist_entry, list);
 | |
| 
 | |
| 	return 0;
 | |
| }
 | |
| 
 | |
| void perf_trace_del(struct perf_event *p_event, int flags)
 | |
| {
 | |
| 	hlist_del_rcu(&p_event->hlist_entry);
 | |
| }
 | |
| 
 | |
| void perf_trace_destroy(struct perf_event *p_event)
 | |
| {
 | |
| 	struct ftrace_event_call *tp_event = p_event->tp_event;
 | |
| 	int i;
 | |
| 
 | |
| 	mutex_lock(&event_mutex);
 | |
| 	if (--tp_event->perf_refcount > 0)
 | |
| 		goto out;
 | |
| 
 | |
| 	tp_event->class->reg(tp_event, TRACE_REG_PERF_UNREGISTER);
 | |
| 
 | |
| 	/*
 | |
| 	 * Ensure our callback won't be called anymore. The buffers
 | |
| 	 * will be freed after that.
 | |
| 	 */
 | |
| 	tracepoint_synchronize_unregister();
 | |
| 
 | |
| 	free_percpu(tp_event->perf_events);
 | |
| 	tp_event->perf_events = NULL;
 | |
| 
 | |
| 	if (!--total_ref_count) {
 | |
| 		for (i = 0; i < PERF_NR_CONTEXTS; i++) {
 | |
| 			free_percpu(perf_trace_buf[i]);
 | |
| 			perf_trace_buf[i] = NULL;
 | |
| 		}
 | |
| 	}
 | |
| out:
 | |
| 	module_put(tp_event->mod);
 | |
| 	mutex_unlock(&event_mutex);
 | |
| }
 | |
| 
 | |
| __kprobes void *perf_trace_buf_prepare(int size, unsigned short type,
 | |
| 				       struct pt_regs *regs, int *rctxp)
 | |
| {
 | |
| 	struct trace_entry *entry;
 | |
| 	unsigned long flags;
 | |
| 	char *raw_data;
 | |
| 	int pc;
 | |
| 
 | |
| 	BUILD_BUG_ON(PERF_MAX_TRACE_SIZE % sizeof(unsigned long));
 | |
| 
 | |
| 	pc = preempt_count();
 | |
| 
 | |
| 	*rctxp = perf_swevent_get_recursion_context();
 | |
| 	if (*rctxp < 0)
 | |
| 		return NULL;
 | |
| 
 | |
| 	raw_data = this_cpu_ptr(perf_trace_buf[*rctxp]);
 | |
| 
 | |
| 	/* zero the dead bytes from align to not leak stack to user */
 | |
| 	memset(&raw_data[size - sizeof(u64)], 0, sizeof(u64));
 | |
| 
 | |
| 	entry = (struct trace_entry *)raw_data;
 | |
| 	local_save_flags(flags);
 | |
| 	tracing_generic_entry_update(entry, flags, pc);
 | |
| 	entry->type = type;
 | |
| 
 | |
| 	return raw_data;
 | |
| }
 | |
| EXPORT_SYMBOL_GPL(perf_trace_buf_prepare);
 |