linux/arch/x86/oprofile/op_model_ppro.c

270 lines
6.3 KiB
C
Raw Normal View History

/*
* @file op_model_ppro.h
* Family 6 perfmon and architectural perfmon MSR operations
*
* @remark Copyright 2002 OProfile authors
* @remark Copyright 2008 Intel Corporation
* @remark Read the file COPYING
*
* @author John Levon
* @author Philippe Elie
* @author Graydon Hoare
* @author Andi Kleen
* @author Robert Richter <robert.richter@amd.com>
*/
#include <linux/oprofile.h>
#include <linux/slab.h>
#include <asm/ptrace.h>
#include <asm/msr.h>
#include <asm/apic.h>
#include <asm/nmi.h>
#include "op_x86_model.h"
#include "op_counter.h"
static int num_counters = 2;
static int counter_width = 32;
#define MSR_PPRO_EVENTSEL_RESERVED ((0xFFFFFFFFULL<<32)|(1ULL<<21))
static u64 *reset_value;
static void ppro_fill_in_addresses(struct op_msrs * const msrs)
{
int i;
for (i = 0; i < num_counters; i++) {
if (reserve_perfctr_nmi(MSR_P6_PERFCTR0 + i))
msrs->counters[i].addr = MSR_P6_PERFCTR0 + i;
}
for (i = 0; i < num_counters; i++) {
if (reserve_evntsel_nmi(MSR_P6_EVNTSEL0 + i))
msrs->controls[i].addr = MSR_P6_EVNTSEL0 + i;
}
}
static void ppro_setup_ctrs(struct op_x86_model_spec const *model,
struct op_msrs const * const msrs)
{
u64 val;
int i;
if (!reset_value) {
reset_value = kzalloc(sizeof(reset_value[0]) * num_counters,
GFP_ATOMIC);
if (!reset_value)
return;
}
if (cpu_has_arch_perfmon) {
union cpuid10_eax eax;
eax.full = cpuid_eax(0xa);
/*
* For Core2 (family 6, model 15), don't reset the
* counter width:
*/
if (!(eax.split.version_id == 0 &&
current_cpu_data.x86 == 6 &&
current_cpu_data.x86_model == 15)) {
if (counter_width < eax.split.bit_width)
counter_width = eax.split.bit_width;
}
}
/* clear all counters */
for (i = 0; i < num_counters; ++i) {
if (unlikely(!msrs->controls[i].addr)) {
if (counter_config[i].enabled && !smp_processor_id())
/*
* counter is reserved, this is on all
* cpus, so report only for cpu #0
*/
op_x86_warn_reserved(i);
continue;
}
rdmsrl(msrs->controls[i].addr, val);
if (val & ARCH_PERFMON_EVENTSEL_ENABLE)
op_x86_warn_in_use(i);
val &= model->reserved;
wrmsrl(msrs->controls[i].addr, val);
}
/* avoid a false detection of ctr overflows in NMI handler */
for (i = 0; i < num_counters; ++i) {
if (unlikely(!msrs->counters[i].addr))
continue;
wrmsrl(msrs->counters[i].addr, -1LL);
}
/* enable active counters */
for (i = 0; i < num_counters; ++i) {
if (counter_config[i].enabled && msrs->counters[i].addr) {
reset_value[i] = counter_config[i].count;
wrmsrl(msrs->counters[i].addr, -reset_value[i]);
rdmsrl(msrs->controls[i].addr, val);
val &= model->reserved;
val |= op_x86_get_ctrl(model, &counter_config[i]);
wrmsrl(msrs->controls[i].addr, val);
} else {
reset_value[i] = 0;
}
}
}
static int ppro_check_ctrs(struct pt_regs * const regs,
struct op_msrs const * const msrs)
{
u64 val;
int i;
/*
* This can happen if perf counters are in use when
* we steal the die notifier NMI.
*/
if (unlikely(!reset_value))
goto out;
for (i = 0; i < num_counters; ++i) {
if (!reset_value[i])
continue;
rdmsrl(msrs->counters[i].addr, val);
if (val & (1ULL << (counter_width - 1)))
continue;
oprofile_add_sample(regs, i);
wrmsrl(msrs->counters[i].addr, -reset_value[i]);
}
out:
/* Only P6 based Pentium M need to re-unmask the apic vector but it
* doesn't hurt other P6 variant */
apic_write(APIC_LVTPC, apic_read(APIC_LVTPC) & ~APIC_LVT_MASKED);
/* We can't work out if we really handled an interrupt. We
* might have caught a *second* counter just after overflowing
* the interrupt for this counter then arrives
* and we don't find a counter that's overflowed, so we
* would return 0 and get dazed + confused. Instead we always
* assume we found an overflow. This sucks.
*/
return 1;
}
static void ppro_start(struct op_msrs const * const msrs)
{
u64 val;
int i;
if (!reset_value)
return;
for (i = 0; i < num_counters; ++i) {
if (reset_value[i]) {
rdmsrl(msrs->controls[i].addr, val);
val |= ARCH_PERFMON_EVENTSEL_ENABLE;
wrmsrl(msrs->controls[i].addr, val);
}
}
}
static void ppro_stop(struct op_msrs const * const msrs)
{
u64 val;
int i;
if (!reset_value)
return;
for (i = 0; i < num_counters; ++i) {
if (!reset_value[i])
continue;
rdmsrl(msrs->controls[i].addr, val);
val &= ~ARCH_PERFMON_EVENTSEL_ENABLE;
wrmsrl(msrs->controls[i].addr, val);
}
}
static void ppro_shutdown(struct op_msrs const * const msrs)
{
int i;
for (i = 0; i < num_counters; ++i) {
if (msrs->counters[i].addr)
release_perfctr_nmi(MSR_P6_PERFCTR0 + i);
}
for (i = 0; i < num_counters; ++i) {
if (msrs->controls[i].addr)
release_evntsel_nmi(MSR_P6_EVNTSEL0 + i);
}
if (reset_value) {
kfree(reset_value);
reset_value = NULL;
}
}
struct op_x86_model_spec op_ppro_spec = {
.num_counters = 2,
.num_controls = 2,
.reserved = MSR_PPRO_EVENTSEL_RESERVED,
.fill_in_addresses = &ppro_fill_in_addresses,
.setup_ctrs = &ppro_setup_ctrs,
.check_ctrs = &ppro_check_ctrs,
.start = &ppro_start,
.stop = &ppro_stop,
.shutdown = &ppro_shutdown
};
/*
* Architectural performance monitoring.
*
* Newer Intel CPUs (Core1+) have support for architectural
* events described in CPUID 0xA. See the IA32 SDM Vol3b.18 for details.
* The advantage of this is that it can be done without knowing about
* the specific CPU.
*/
static void arch_perfmon_setup_counters(void)
{
union cpuid10_eax eax;
eax.full = cpuid_eax(0xa);
/* Workaround for BIOS bugs in 6/15. Taken from perfmon2 */
if (eax.split.version_id == 0 && current_cpu_data.x86 == 6 &&
current_cpu_data.x86_model == 15) {
eax.split.version_id = 2;
perf: Do the big rename: Performance Counters -> Performance Events Bye-bye Performance Counters, welcome Performance Events! In the past few months the perfcounters subsystem has grown out its initial role of counting hardware events, and has become (and is becoming) a much broader generic event enumeration, reporting, logging, monitoring, analysis facility. Naming its core object 'perf_counter' and naming the subsystem 'perfcounters' has become more and more of a misnomer. With pending code like hw-breakpoints support the 'counter' name is less and less appropriate. All in one, we've decided to rename the subsystem to 'performance events' and to propagate this rename through all fields, variables and API names. (in an ABI compatible fashion) The word 'event' is also a bit shorter than 'counter' - which makes it slightly more convenient to write/handle as well. Thanks goes to Stephane Eranian who first observed this misnomer and suggested a rename. User-space tooling and ABI compatibility is not affected - this patch should be function-invariant. (Also, defconfigs were not touched to keep the size down.) This patch has been generated via the following script: FILES=$(find * -type f | grep -vE 'oprofile|[^K]config') sed -i \ -e 's/PERF_EVENT_/PERF_RECORD_/g' \ -e 's/PERF_COUNTER/PERF_EVENT/g' \ -e 's/perf_counter/perf_event/g' \ -e 's/nb_counters/nb_events/g' \ -e 's/swcounter/swevent/g' \ -e 's/tpcounter_event/tp_event/g' \ $FILES for N in $(find . -name perf_counter.[ch]); do M=$(echo $N | sed 's/perf_counter/perf_event/g') mv $N $M done FILES=$(find . -name perf_event.*) sed -i \ -e 's/COUNTER_MASK/REG_MASK/g' \ -e 's/COUNTER/EVENT/g' \ -e 's/\<event\>/event_id/g' \ -e 's/counter/event/g' \ -e 's/Counter/Event/g' \ $FILES ... to keep it as correct as possible. This script can also be used by anyone who has pending perfcounters patches - it converts a Linux kernel tree over to the new naming. We tried to time this change to the point in time where the amount of pending patches is the smallest: the end of the merge window. Namespace clashes were fixed up in a preparatory patch - and some stylistic fallout will be fixed up in a subsequent patch. ( NOTE: 'counters' are still the proper terminology when we deal with hardware registers - and these sed scripts are a bit over-eager in renaming them. I've undone some of that, but in case there's something left where 'counter' would be better than 'event' we can undo that on an individual basis instead of touching an otherwise nicely automated patch. ) Suggested-by: Stephane Eranian <eranian@google.com> Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Acked-by: Paul Mackerras <paulus@samba.org> Reviewed-by: Arjan van de Ven <arjan@linux.intel.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: David Howells <dhowells@redhat.com> Cc: Kyle McMartin <kyle@mcmartin.ca> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: "David S. Miller" <davem@davemloft.net> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: <linux-arch@vger.kernel.org> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-21 10:02:48 +00:00
eax.split.num_events = 2;
eax.split.bit_width = 40;
}
perf: Do the big rename: Performance Counters -> Performance Events Bye-bye Performance Counters, welcome Performance Events! In the past few months the perfcounters subsystem has grown out its initial role of counting hardware events, and has become (and is becoming) a much broader generic event enumeration, reporting, logging, monitoring, analysis facility. Naming its core object 'perf_counter' and naming the subsystem 'perfcounters' has become more and more of a misnomer. With pending code like hw-breakpoints support the 'counter' name is less and less appropriate. All in one, we've decided to rename the subsystem to 'performance events' and to propagate this rename through all fields, variables and API names. (in an ABI compatible fashion) The word 'event' is also a bit shorter than 'counter' - which makes it slightly more convenient to write/handle as well. Thanks goes to Stephane Eranian who first observed this misnomer and suggested a rename. User-space tooling and ABI compatibility is not affected - this patch should be function-invariant. (Also, defconfigs were not touched to keep the size down.) This patch has been generated via the following script: FILES=$(find * -type f | grep -vE 'oprofile|[^K]config') sed -i \ -e 's/PERF_EVENT_/PERF_RECORD_/g' \ -e 's/PERF_COUNTER/PERF_EVENT/g' \ -e 's/perf_counter/perf_event/g' \ -e 's/nb_counters/nb_events/g' \ -e 's/swcounter/swevent/g' \ -e 's/tpcounter_event/tp_event/g' \ $FILES for N in $(find . -name perf_counter.[ch]); do M=$(echo $N | sed 's/perf_counter/perf_event/g') mv $N $M done FILES=$(find . -name perf_event.*) sed -i \ -e 's/COUNTER_MASK/REG_MASK/g' \ -e 's/COUNTER/EVENT/g' \ -e 's/\<event\>/event_id/g' \ -e 's/counter/event/g' \ -e 's/Counter/Event/g' \ $FILES ... to keep it as correct as possible. This script can also be used by anyone who has pending perfcounters patches - it converts a Linux kernel tree over to the new naming. We tried to time this change to the point in time where the amount of pending patches is the smallest: the end of the merge window. Namespace clashes were fixed up in a preparatory patch - and some stylistic fallout will be fixed up in a subsequent patch. ( NOTE: 'counters' are still the proper terminology when we deal with hardware registers - and these sed scripts are a bit over-eager in renaming them. I've undone some of that, but in case there's something left where 'counter' would be better than 'event' we can undo that on an individual basis instead of touching an otherwise nicely automated patch. ) Suggested-by: Stephane Eranian <eranian@google.com> Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Acked-by: Paul Mackerras <paulus@samba.org> Reviewed-by: Arjan van de Ven <arjan@linux.intel.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: David Howells <dhowells@redhat.com> Cc: Kyle McMartin <kyle@mcmartin.ca> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: "David S. Miller" <davem@davemloft.net> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: <linux-arch@vger.kernel.org> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-21 10:02:48 +00:00
num_counters = eax.split.num_events;
op_arch_perfmon_spec.num_counters = num_counters;
op_arch_perfmon_spec.num_controls = num_counters;
}
static int arch_perfmon_init(struct oprofile_operations *ignore)
{
arch_perfmon_setup_counters();
return 0;
}
struct op_x86_model_spec op_arch_perfmon_spec = {
.reserved = MSR_PPRO_EVENTSEL_RESERVED,
.init = &arch_perfmon_init,
/* num_counters/num_controls filled in at runtime */
.fill_in_addresses = &ppro_fill_in_addresses,
/* user space does the cpuid check for available events */
.setup_ctrs = &ppro_setup_ctrs,
.check_ctrs = &ppro_check_ctrs,
.start = &ppro_start,
.stop = &ppro_stop,
.shutdown = &ppro_shutdown
};