linux/arch/sparc/kernel/pcr.c

220 lines
4.7 KiB
C
Raw Normal View History

/* pcr.c: Generic sparc64 performance counter infrastructure.
*
* Copyright (C) 2009 David S. Miller (davem@davemloft.net)
*/
#include <linux/kernel.h>
#include <linux/export.h>
#include <linux/init.h>
#include <linux/irq.h>
#include <linux/irq_work.h>
#include <linux/ftrace.h>
#include <asm/pil.h>
#include <asm/pcr.h>
#include <asm/nmi.h>
#include <asm/spitfire.h>
/* This code is shared between various users of the performance
* counters. Users will be oprofile, pseudo-NMI watchdog, and the
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 12:02:48 +02:00
* perf_event support layer.
*/
/* Performance counter interrupts run unmasked at PIL level 15.
* Therefore we can't do things like wakeups and other work
* that expects IRQ disabling to be adhered to in locking etc.
*
* Therefore in such situations we defer the work by signalling
* a lower level cpu IRQ.
*/
void __irq_entry deferred_pcr_work_irq(int irq, struct pt_regs *regs)
{
struct pt_regs *old_regs;
clear_softint(1 << PIL_DEFERRED_PCR_WORK);
old_regs = set_irq_regs(regs);
irq_enter();
#ifdef CONFIG_IRQ_WORK
irq_work_run();
#endif
irq_exit();
set_irq_regs(old_regs);
}
void arch_irq_work_raise(void)
{
set_softint(1 << PIL_DEFERRED_PCR_WORK);
}
const struct pcr_ops *pcr_ops;
EXPORT_SYMBOL_GPL(pcr_ops);
static u64 direct_pcr_read(unsigned long reg_num)
{
u64 val;
WARN_ON_ONCE(reg_num != 0);
__asm__ __volatile__("rd %%pcr, %0" : "=r" (val));
return val;
}
static void direct_pcr_write(unsigned long reg_num, u64 val)
{
WARN_ON_ONCE(reg_num != 0);
__asm__ __volatile__("wr %0, 0x0, %%pcr" : : "r" (val));
}
static u64 direct_pic_read(unsigned long reg_num)
{
u64 val;
WARN_ON_ONCE(reg_num != 0);
__asm__ __volatile__("rd %%pic, %0" : "=r" (val));
return val;
}
static void direct_pic_write(unsigned long reg_num, u64 val)
{
WARN_ON_ONCE(reg_num != 0);
/* Blackbird errata workaround. See commentary in
* arch/sparc64/kernel/smp.c:smp_percpu_timer_interrupt()
* for more information.
*/
__asm__ __volatile__("ba,pt %%xcc, 99f\n\t"
" nop\n\t"
".align 64\n"
"99:wr %0, 0x0, %%pic\n\t"
"rd %%pic, %%g0" : : "r" (val));
}
static u64 direct_picl_value(unsigned int nmi_hz)
{
u32 delta = local_cpu_data().clock_tick / nmi_hz;
return ((u64)((0 - delta) & 0xffffffff)) << 32;
}
static const struct pcr_ops direct_pcr_ops = {
.read_pcr = direct_pcr_read,
.write_pcr = direct_pcr_write,
.read_pic = direct_pic_read,
.write_pic = direct_pic_write,
.nmi_picl_value = direct_picl_value,
.pcr_nmi_enable = (PCR_PIC_PRIV | PCR_STRACE | PCR_UTRACE),
.pcr_nmi_disable = PCR_PIC_PRIV,
};
static void n2_pcr_write(unsigned long reg_num, u64 val)
{
unsigned long ret;
WARN_ON_ONCE(reg_num != 0);
if (val & PCR_N2_HTRACE) {
ret = sun4v_niagara2_setperf(HV_N2_PERF_SPARC_CTL, val);
if (ret != HV_EOK)
direct_pcr_write(reg_num, val);
} else
direct_pcr_write(reg_num, val);
}
static u64 n2_picl_value(unsigned int nmi_hz)
{
u32 delta = local_cpu_data().clock_tick / (nmi_hz << 2);
return ((u64)((0 - delta) & 0xffffffff)) << 32;
}
static const struct pcr_ops n2_pcr_ops = {
.read_pcr = direct_pcr_read,
.write_pcr = n2_pcr_write,
.read_pic = direct_pic_read,
.write_pic = direct_pic_write,
.nmi_picl_value = n2_picl_value,
.pcr_nmi_enable = (PCR_PIC_PRIV | PCR_STRACE | PCR_UTRACE |
PCR_N2_TOE_OV1 |
(2 << PCR_N2_SL1_SHIFT) |
(0xff << PCR_N2_MASK1_SHIFT)),
.pcr_nmi_disable = PCR_PIC_PRIV,
};
static unsigned long perf_hsvc_group;
static unsigned long perf_hsvc_major;
static unsigned long perf_hsvc_minor;
static int __init register_perf_hsvc(void)
{
if (tlb_type == hypervisor) {
switch (sun4v_chip_type) {
case SUN4V_CHIP_NIAGARA1:
perf_hsvc_group = HV_GRP_NIAG_PERF;
break;
case SUN4V_CHIP_NIAGARA2:
perf_hsvc_group = HV_GRP_N2_CPU;
break;
case SUN4V_CHIP_NIAGARA3:
perf_hsvc_group = HV_GRP_KT_CPU;
break;
default:
return -ENODEV;
}
perf_hsvc_major = 1;
perf_hsvc_minor = 0;
if (sun4v_hvapi_register(perf_hsvc_group,
perf_hsvc_major,
&perf_hsvc_minor)) {
printk("perfmon: Could not register hvapi.\n");
return -ENODEV;
}
}
return 0;
}
static void __init unregister_perf_hsvc(void)
{
if (tlb_type != hypervisor)
return;
sun4v_hvapi_unregister(perf_hsvc_group);
}
int __init pcr_arch_init(void)
{
int err = register_perf_hsvc();
if (err)
return err;
switch (tlb_type) {
case hypervisor:
pcr_ops = &n2_pcr_ops;
break;
case cheetah:
case cheetah_plus:
pcr_ops = &direct_pcr_ops;
break;
case spitfire:
/* UltraSPARC-I/II and derivatives lack a profile
* counter overflow interrupt so we can't make use of
* their hardware currently.
*/
/* fallthrough */
default:
err = -ENODEV;
goto out_unregister;
}
return nmi_init();
out_unregister:
unregister_perf_hsvc();
return err;
}