perf: Carve out callchain functionality
Split the callchain code from the perf events core into a new kernel/events/callchain.c file. This simplifies a bit the big core.c Signed-off-by: Borislav Petkov <borislav.petkov@amd.com> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Stephane Eranian <eranian@google.com> [keep ctx recursion handling inline and use internal headers] Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1318778104-17152-1-git-send-email-fweisbec@gmail.com Signed-off-by: Ingo Molnar <mingo@elte.hu>
This commit is contained in:
Borislav Petkov
Ingo Molnar
parent
efc96737bd
commit
9251f904f9
4 changed files with 230 additions and 211 deletions
|
|
@ -2,5 +2,5 @@ ifdef CONFIG_FUNCTION_TRACER
|
|||
CFLAGS_REMOVE_core.o = -pg
|
||||
endif
|
||||
|
||||
obj-y := core.o ring_buffer.o
|
||||
obj-y := core.o ring_buffer.o callchain.o
|
||||
obj-$(CONFIG_HAVE_HW_BREAKPOINT) += hw_breakpoint.o
|
||||
|
|
|
|||
191
kernel/events/callchain.c
Normal file
191
kernel/events/callchain.c
Normal file
|
|
@ -0,0 +1,191 @@
|
|||
/*
|
||||
* Performance events callchain code, extracted from core.c:
|
||||
*
|
||||
* Copyright (C) 2008 Thomas Gleixner <tglx@linutronix.de>
|
||||
* Copyright (C) 2008-2011 Red Hat, Inc., Ingo Molnar
|
||||
* Copyright (C) 2008-2011 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com>
|
||||
* Copyright © 2009 Paul Mackerras, IBM Corp. <paulus@au1.ibm.com>
|
||||
*
|
||||
* For licensing details see kernel-base/COPYING
|
||||
*/
|
||||
|
||||
#include <linux/perf_event.h>
|
||||
#include <linux/slab.h>
|
||||
#include "internal.h"
|
||||
|
||||
struct callchain_cpus_entries {
|
||||
struct rcu_head rcu_head;
|
||||
struct perf_callchain_entry *cpu_entries[0];
|
||||
};
|
||||
|
||||
static DEFINE_PER_CPU(int, callchain_recursion[PERF_NR_CONTEXTS]);
|
||||
static atomic_t nr_callchain_events;
|
||||
static DEFINE_MUTEX(callchain_mutex);
|
||||
static struct callchain_cpus_entries *callchain_cpus_entries;
|
||||
|
||||
|
||||
__weak void perf_callchain_kernel(struct perf_callchain_entry *entry,
|
||||
struct pt_regs *regs)
|
||||
{
|
||||
}
|
||||
|
||||
__weak void perf_callchain_user(struct perf_callchain_entry *entry,
|
||||
struct pt_regs *regs)
|
||||
{
|
||||
}
|
||||
|
||||
static void release_callchain_buffers_rcu(struct rcu_head *head)
|
||||
{
|
||||
struct callchain_cpus_entries *entries;
|
||||
int cpu;
|
||||
|
||||
entries = container_of(head, struct callchain_cpus_entries, rcu_head);
|
||||
|
||||
for_each_possible_cpu(cpu)
|
||||
kfree(entries->cpu_entries[cpu]);
|
||||
|
||||
kfree(entries);
|
||||
}
|
||||
|
||||
static void release_callchain_buffers(void)
|
||||
{
|
||||
struct callchain_cpus_entries *entries;
|
||||
|
||||
entries = callchain_cpus_entries;
|
||||
rcu_assign_pointer(callchain_cpus_entries, NULL);
|
||||
call_rcu(&entries->rcu_head, release_callchain_buffers_rcu);
|
||||
}
|
||||
|
||||
static int alloc_callchain_buffers(void)
|
||||
{
|
||||
int cpu;
|
||||
int size;
|
||||
struct callchain_cpus_entries *entries;
|
||||
|
||||
/*
|
||||
* We can't use the percpu allocation API for data that can be
|
||||
* accessed from NMI. Use a temporary manual per cpu allocation
|
||||
* until that gets sorted out.
|
||||
*/
|
||||
size = offsetof(struct callchain_cpus_entries, cpu_entries[nr_cpu_ids]);
|
||||
|
||||
entries = kzalloc(size, GFP_KERNEL);
|
||||
if (!entries)
|
||||
return -ENOMEM;
|
||||
|
||||
size = sizeof(struct perf_callchain_entry) * PERF_NR_CONTEXTS;
|
||||
|
||||
for_each_possible_cpu(cpu) {
|
||||
entries->cpu_entries[cpu] = kmalloc_node(size, GFP_KERNEL,
|
||||
cpu_to_node(cpu));
|
||||
if (!entries->cpu_entries[cpu])
|
||||
goto fail;
|
||||
}
|
||||
|
||||
rcu_assign_pointer(callchain_cpus_entries, entries);
|
||||
|
||||
return 0;
|
||||
|
||||
fail:
|
||||
for_each_possible_cpu(cpu)
|
||||
kfree(entries->cpu_entries[cpu]);
|
||||
kfree(entries);
|
||||
|
||||
return -ENOMEM;
|
||||
}
|
||||
|
||||
int get_callchain_buffers(void)
|
||||
{
|
||||
int err = 0;
|
||||
int count;
|
||||
|
||||
mutex_lock(&callchain_mutex);
|
||||
|
||||
count = atomic_inc_return(&nr_callchain_events);
|
||||
if (WARN_ON_ONCE(count < 1)) {
|
||||
err = -EINVAL;
|
||||
goto exit;
|
||||
}
|
||||
|
||||
if (count > 1) {
|
||||
/* If the allocation failed, give up */
|
||||
if (!callchain_cpus_entries)
|
||||
err = -ENOMEM;
|
||||
goto exit;
|
||||
}
|
||||
|
||||
err = alloc_callchain_buffers();
|
||||
if (err)
|
||||
release_callchain_buffers();
|
||||
exit:
|
||||
mutex_unlock(&callchain_mutex);
|
||||
|
||||
return err;
|
||||
}
|
||||
|
||||
void put_callchain_buffers(void)
|
||||
{
|
||||
if (atomic_dec_and_mutex_lock(&nr_callchain_events, &callchain_mutex)) {
|
||||
release_callchain_buffers();
|
||||
mutex_unlock(&callchain_mutex);
|
||||
}
|
||||
}
|
||||
|
||||
static struct perf_callchain_entry *get_callchain_entry(int *rctx)
|
||||
{
|
||||
int cpu;
|
||||
struct callchain_cpus_entries *entries;
|
||||
|
||||
*rctx = get_recursion_context(__get_cpu_var(callchain_recursion));
|
||||
if (*rctx == -1)
|
||||
return NULL;
|
||||
|
||||
entries = rcu_dereference(callchain_cpus_entries);
|
||||
if (!entries)
|
||||
return NULL;
|
||||
|
||||
cpu = smp_processor_id();
|
||||
|
||||
return &entries->cpu_entries[cpu][*rctx];
|
||||
}
|
||||
|
||||
static void
|
||||
put_callchain_entry(int rctx)
|
||||
{
|
||||
put_recursion_context(__get_cpu_var(callchain_recursion), rctx);
|
||||
}
|
||||
|
||||
struct perf_callchain_entry *perf_callchain(struct pt_regs *regs)
|
||||
{
|
||||
int rctx;
|
||||
struct perf_callchain_entry *entry;
|
||||
|
||||
|
||||
entry = get_callchain_entry(&rctx);
|
||||
if (rctx == -1)
|
||||
return NULL;
|
||||
|
||||
if (!entry)
|
||||
goto exit_put;
|
||||
|
||||
entry->nr = 0;
|
||||
|
||||
if (!user_mode(regs)) {
|
||||
perf_callchain_store(entry, PERF_CONTEXT_KERNEL);
|
||||
perf_callchain_kernel(entry, regs);
|
||||
if (current->mm)
|
||||
regs = task_pt_regs(current);
|
||||
else
|
||||
regs = NULL;
|
||||
}
|
||||
|
||||
if (regs) {
|
||||
perf_callchain_store(entry, PERF_CONTEXT_USER);
|
||||
perf_callchain_user(entry, regs);
|
||||
}
|
||||
|
||||
exit_put:
|
||||
put_callchain_entry(rctx);
|
||||
|
||||
return entry;
|
||||
}
|
||||
|
|
@ -2569,215 +2569,6 @@ static u64 perf_event_read(struct perf_event *event)
|
|||
return perf_event_count(event);
|
||||
}
|
||||
|
||||
/*
|
||||
* Callchain support
|
||||
*/
|
||||
|
||||
struct callchain_cpus_entries {
|
||||
struct rcu_head rcu_head;
|
||||
struct perf_callchain_entry *cpu_entries[0];
|
||||
};
|
||||
|
||||
static DEFINE_PER_CPU(int, callchain_recursion[PERF_NR_CONTEXTS]);
|
||||
static atomic_t nr_callchain_events;
|
||||
static DEFINE_MUTEX(callchain_mutex);
|
||||
struct callchain_cpus_entries *callchain_cpus_entries;
|
||||
|
||||
|
||||
__weak void perf_callchain_kernel(struct perf_callchain_entry *entry,
|
||||
struct pt_regs *regs)
|
||||
{
|
||||
}
|
||||
|
||||
__weak void perf_callchain_user(struct perf_callchain_entry *entry,
|
||||
struct pt_regs *regs)
|
||||
{
|
||||
}
|
||||
|
||||
static void release_callchain_buffers_rcu(struct rcu_head *head)
|
||||
{
|
||||
struct callchain_cpus_entries *entries;
|
||||
int cpu;
|
||||
|
||||
entries = container_of(head, struct callchain_cpus_entries, rcu_head);
|
||||
|
||||
for_each_possible_cpu(cpu)
|
||||
kfree(entries->cpu_entries[cpu]);
|
||||
|
||||
kfree(entries);
|
||||
}
|
||||
|
||||
static void release_callchain_buffers(void)
|
||||
{
|
||||
struct callchain_cpus_entries *entries;
|
||||
|
||||
entries = callchain_cpus_entries;
|
||||
rcu_assign_pointer(callchain_cpus_entries, NULL);
|
||||
call_rcu(&entries->rcu_head, release_callchain_buffers_rcu);
|
||||
}
|
||||
|
||||
static int alloc_callchain_buffers(void)
|
||||
{
|
||||
int cpu;
|
||||
int size;
|
||||
struct callchain_cpus_entries *entries;
|
||||
|
||||
/*
|
||||
* We can't use the percpu allocation API for data that can be
|
||||
* accessed from NMI. Use a temporary manual per cpu allocation
|
||||
* until that gets sorted out.
|
||||
*/
|
||||
size = offsetof(struct callchain_cpus_entries, cpu_entries[nr_cpu_ids]);
|
||||
|
||||
entries = kzalloc(size, GFP_KERNEL);
|
||||
if (!entries)
|
||||
return -ENOMEM;
|
||||
|
||||
size = sizeof(struct perf_callchain_entry) * PERF_NR_CONTEXTS;
|
||||
|
||||
for_each_possible_cpu(cpu) {
|
||||
entries->cpu_entries[cpu] = kmalloc_node(size, GFP_KERNEL,
|
||||
cpu_to_node(cpu));
|
||||
if (!entries->cpu_entries[cpu])
|
||||
goto fail;
|
||||
}
|
||||
|
||||
rcu_assign_pointer(callchain_cpus_entries, entries);
|
||||
|
||||
return 0;
|
||||
|
||||
fail:
|
||||
for_each_possible_cpu(cpu)
|
||||
kfree(entries->cpu_entries[cpu]);
|
||||
kfree(entries);
|
||||
|
||||
return -ENOMEM;
|
||||
}
|
||||
|
||||
static int get_callchain_buffers(void)
|
||||
{
|
||||
int err = 0;
|
||||
int count;
|
||||
|
||||
mutex_lock(&callchain_mutex);
|
||||
|
||||
count = atomic_inc_return(&nr_callchain_events);
|
||||
if (WARN_ON_ONCE(count < 1)) {
|
||||
err = -EINVAL;
|
||||
goto exit;
|
||||
}
|
||||
|
||||
if (count > 1) {
|
||||
/* If the allocation failed, give up */
|
||||
if (!callchain_cpus_entries)
|
||||
err = -ENOMEM;
|
||||
goto exit;
|
||||
}
|
||||
|
||||
err = alloc_callchain_buffers();
|
||||
if (err)
|
||||
release_callchain_buffers();
|
||||
exit:
|
||||
mutex_unlock(&callchain_mutex);
|
||||
|
||||
return err;
|
||||
}
|
||||
|
||||
static void put_callchain_buffers(void)
|
||||
{
|
||||
if (atomic_dec_and_mutex_lock(&nr_callchain_events, &callchain_mutex)) {
|
||||
release_callchain_buffers();
|
||||
mutex_unlock(&callchain_mutex);
|
||||
}
|
||||
}
|
||||
|
||||
static int get_recursion_context(int *recursion)
|
||||
{
|
||||
int rctx;
|
||||
|
||||
if (in_nmi())
|
||||
rctx = 3;
|
||||
else if (in_irq())
|
||||
rctx = 2;
|
||||
else if (in_softirq())
|
||||
rctx = 1;
|
||||
else
|
||||
rctx = 0;
|
||||
|
||||
if (recursion[rctx])
|
||||
return -1;
|
||||
|
||||
recursion[rctx]++;
|
||||
barrier();
|
||||
|
||||
return rctx;
|
||||
}
|
||||
|
||||
static inline void put_recursion_context(int *recursion, int rctx)
|
||||
{
|
||||
barrier();
|
||||
recursion[rctx]--;
|
||||
}
|
||||
|
||||
static struct perf_callchain_entry *get_callchain_entry(int *rctx)
|
||||
{
|
||||
int cpu;
|
||||
struct callchain_cpus_entries *entries;
|
||||
|
||||
*rctx = get_recursion_context(__get_cpu_var(callchain_recursion));
|
||||
if (*rctx == -1)
|
||||
return NULL;
|
||||
|
||||
entries = rcu_dereference(callchain_cpus_entries);
|
||||
if (!entries)
|
||||
return NULL;
|
||||
|
||||
cpu = smp_processor_id();
|
||||
|
||||
return &entries->cpu_entries[cpu][*rctx];
|
||||
}
|
||||
|
||||
static void
|
||||
put_callchain_entry(int rctx)
|
||||
{
|
||||
put_recursion_context(__get_cpu_var(callchain_recursion), rctx);
|
||||
}
|
||||
|
||||
static struct perf_callchain_entry *perf_callchain(struct pt_regs *regs)
|
||||
{
|
||||
int rctx;
|
||||
struct perf_callchain_entry *entry;
|
||||
|
||||
|
||||
entry = get_callchain_entry(&rctx);
|
||||
if (rctx == -1)
|
||||
return NULL;
|
||||
|
||||
if (!entry)
|
||||
goto exit_put;
|
||||
|
||||
entry->nr = 0;
|
||||
|
||||
if (!user_mode(regs)) {
|
||||
perf_callchain_store(entry, PERF_CONTEXT_KERNEL);
|
||||
perf_callchain_kernel(entry, regs);
|
||||
if (current->mm)
|
||||
regs = task_pt_regs(current);
|
||||
else
|
||||
regs = NULL;
|
||||
}
|
||||
|
||||
if (regs) {
|
||||
perf_callchain_store(entry, PERF_CONTEXT_USER);
|
||||
perf_callchain_user(entry, regs);
|
||||
}
|
||||
|
||||
exit_put:
|
||||
put_callchain_entry(rctx);
|
||||
|
||||
return entry;
|
||||
}
|
||||
|
||||
/*
|
||||
* Initialize the perf_event context in a task_struct:
|
||||
*/
|
||||
|
|
|
|||
|
|
@ -1,6 +1,10 @@
|
|||
#ifndef _KERNEL_EVENTS_INTERNAL_H
|
||||
#define _KERNEL_EVENTS_INTERNAL_H
|
||||
|
||||
#include <linux/hardirq.h>
|
||||
|
||||
/* Buffer handling */
|
||||
|
||||
#define RING_BUFFER_WRITABLE 0x01
|
||||
|
||||
struct ring_buffer {
|
||||
|
|
@ -64,7 +68,7 @@ static inline int page_order(struct ring_buffer *rb)
|
|||
}
|
||||
#endif
|
||||
|
||||
static unsigned long perf_data_size(struct ring_buffer *rb)
|
||||
static inline unsigned long perf_data_size(struct ring_buffer *rb)
|
||||
{
|
||||
return rb->nr_pages << (PAGE_SHIFT + page_order(rb));
|
||||
}
|
||||
|
|
@ -93,4 +97,37 @@ __output_copy(struct perf_output_handle *handle,
|
|||
} while (len);
|
||||
}
|
||||
|
||||
/* Callchain handling */
|
||||
extern struct perf_callchain_entry *perf_callchain(struct pt_regs *regs);
|
||||
extern int get_callchain_buffers(void);
|
||||
extern void put_callchain_buffers(void);
|
||||
|
||||
static inline int get_recursion_context(int *recursion)
|
||||
{
|
||||
int rctx;
|
||||
|
||||
if (in_nmi())
|
||||
rctx = 3;
|
||||
else if (in_irq())
|
||||
rctx = 2;
|
||||
else if (in_softirq())
|
||||
rctx = 1;
|
||||
else
|
||||
rctx = 0;
|
||||
|
||||
if (recursion[rctx])
|
||||
return -1;
|
||||
|
||||
recursion[rctx]++;
|
||||
barrier();
|
||||
|
||||
return rctx;
|
||||
}
|
||||
|
||||
static inline void put_recursion_context(int *recursion, int rctx)
|
||||
{
|
||||
barrier();
|
||||
recursion[rctx]--;
|
||||
}
|
||||
|
||||
#endif /* _KERNEL_EVENTS_INTERNAL_H */
|
||||
|
|
|
|||
Loading…
Reference in a new issue