Merge branch 'perf/x86-ibs' into perf/core

This commit is contained in:
Ingo Molnar 2012-05-09 15:22:23 +02:00
commit ad8537cda6
3 changed files with 438 additions and 7 deletions

View File

@ -134,6 +134,8 @@
#define MSR_AMD64_IBSFETCHCTL 0xc0011030
#define MSR_AMD64_IBSFETCHLINAD 0xc0011031
#define MSR_AMD64_IBSFETCHPHYSAD 0xc0011032
#define MSR_AMD64_IBSFETCH_REG_COUNT 3
#define MSR_AMD64_IBSFETCH_REG_MASK ((1UL<<MSR_AMD64_IBSFETCH_REG_COUNT)-1)
#define MSR_AMD64_IBSOPCTL 0xc0011033
#define MSR_AMD64_IBSOPRIP 0xc0011034
#define MSR_AMD64_IBSOPDATA 0xc0011035
@ -141,8 +143,11 @@
#define MSR_AMD64_IBSOPDATA3 0xc0011037
#define MSR_AMD64_IBSDCLINAD 0xc0011038
#define MSR_AMD64_IBSDCPHYSAD 0xc0011039
#define MSR_AMD64_IBSOP_REG_COUNT 7
#define MSR_AMD64_IBSOP_REG_MASK ((1UL<<MSR_AMD64_IBSOP_REG_COUNT)-1)
#define MSR_AMD64_IBSCTL 0xc001103a
#define MSR_AMD64_IBSBRTARGET 0xc001103b
#define MSR_AMD64_IBS_REG_COUNT_MAX 8 /* includes MSR_AMD64_IBSBRTARGET */
/* Fam 15h MSRs */
#define MSR_F15H_PERF_CTL 0xc0010200

View File

@ -178,6 +178,8 @@ struct x86_pmu_capability {
#define IBS_FETCH_MAX_CNT 0x0000FFFFULL
/* IbsOpCtl bits */
/* lower 4 bits of the current count are ignored: */
#define IBS_OP_CUR_CNT (0xFFFF0ULL<<32)
#define IBS_OP_CNT_CTL (1ULL<<19)
#define IBS_OP_VAL (1ULL<<18)
#define IBS_OP_ENABLE (1ULL<<17)

View File

@ -16,36 +16,460 @@ static u32 ibs_caps;
#if defined(CONFIG_PERF_EVENTS) && defined(CONFIG_CPU_SUP_AMD)
static struct pmu perf_ibs;
#include <linux/kprobes.h>
#include <linux/hardirq.h>
#include <asm/nmi.h>
#define IBS_FETCH_CONFIG_MASK (IBS_FETCH_RAND_EN | IBS_FETCH_MAX_CNT)
#define IBS_OP_CONFIG_MASK IBS_OP_MAX_CNT
enum ibs_states {
IBS_ENABLED = 0,
IBS_STARTED = 1,
IBS_STOPPING = 2,
IBS_MAX_STATES,
};
struct cpu_perf_ibs {
struct perf_event *event;
unsigned long state[BITS_TO_LONGS(IBS_MAX_STATES)];
};
struct perf_ibs {
struct pmu pmu;
unsigned int msr;
u64 config_mask;
u64 cnt_mask;
u64 enable_mask;
u64 valid_mask;
u64 max_period;
unsigned long offset_mask[1];
int offset_max;
struct cpu_perf_ibs __percpu *pcpu;
u64 (*get_count)(u64 config);
};
struct perf_ibs_data {
u32 size;
union {
u32 data[0]; /* data buffer starts here */
u32 caps;
};
u64 regs[MSR_AMD64_IBS_REG_COUNT_MAX];
};
static int
perf_event_set_period(struct hw_perf_event *hwc, u64 min, u64 max, u64 *count)
{
s64 left = local64_read(&hwc->period_left);
s64 period = hwc->sample_period;
int overflow = 0;
/*
* If we are way outside a reasonable range then just skip forward:
*/
if (unlikely(left <= -period)) {
left = period;
local64_set(&hwc->period_left, left);
hwc->last_period = period;
overflow = 1;
}
if (unlikely(left <= 0)) {
left += period;
local64_set(&hwc->period_left, left);
hwc->last_period = period;
overflow = 1;
}
if (unlikely(left < min))
left = min;
if (left > max)
left = max;
*count = (u64)left;
return overflow;
}
static int
perf_event_try_update(struct perf_event *event, u64 new_raw_count, int width)
{
struct hw_perf_event *hwc = &event->hw;
int shift = 64 - width;
u64 prev_raw_count;
u64 delta;
/*
* Careful: an NMI might modify the previous event value.
*
* Our tactic to handle this is to first atomically read and
* exchange a new raw count - then add that new-prev delta
* count to the generic event atomically:
*/
prev_raw_count = local64_read(&hwc->prev_count);
if (local64_cmpxchg(&hwc->prev_count, prev_raw_count,
new_raw_count) != prev_raw_count)
return 0;
/*
* Now we have the new raw value and have updated the prev
* timestamp already. We can now calculate the elapsed delta
* (event-)time and add that to the generic event.
*
* Careful, not all hw sign-extends above the physical width
* of the count.
*/
delta = (new_raw_count << shift) - (prev_raw_count << shift);
delta >>= shift;
local64_add(delta, &event->count);
local64_sub(delta, &hwc->period_left);
return 1;
}
static struct perf_ibs perf_ibs_fetch;
static struct perf_ibs perf_ibs_op;
static struct perf_ibs *get_ibs_pmu(int type)
{
if (perf_ibs_fetch.pmu.type == type)
return &perf_ibs_fetch;
if (perf_ibs_op.pmu.type == type)
return &perf_ibs_op;
return NULL;
}
static int perf_ibs_init(struct perf_event *event)
{
if (perf_ibs.type != event->attr.type)
struct hw_perf_event *hwc = &event->hw;
struct perf_ibs *perf_ibs;
u64 max_cnt, config;
perf_ibs = get_ibs_pmu(event->attr.type);
if (!perf_ibs)
return -ENOENT;
config = event->attr.config;
if (config & ~perf_ibs->config_mask)
return -EINVAL;
if (hwc->sample_period) {
if (config & perf_ibs->cnt_mask)
/* raw max_cnt may not be set */
return -EINVAL;
if (hwc->sample_period & 0x0f)
/* lower 4 bits can not be set in ibs max cnt */
return -EINVAL;
} else {
max_cnt = config & perf_ibs->cnt_mask;
config &= ~perf_ibs->cnt_mask;
event->attr.sample_period = max_cnt << 4;
hwc->sample_period = event->attr.sample_period;
}
if (!hwc->sample_period)
return -EINVAL;
hwc->config_base = perf_ibs->msr;
hwc->config = config;
return 0;
}
static int perf_ibs_set_period(struct perf_ibs *perf_ibs,
struct hw_perf_event *hwc, u64 *period)
{
int ret;
/* ignore lower 4 bits in min count: */
ret = perf_event_set_period(hwc, 1<<4, perf_ibs->max_period, period);
local64_set(&hwc->prev_count, 0);
return ret;
}
static u64 get_ibs_fetch_count(u64 config)
{
return (config & IBS_FETCH_CNT) >> 12;
}
static u64 get_ibs_op_count(u64 config)
{
return (config & IBS_OP_CUR_CNT) >> 32;
}
static void
perf_ibs_event_update(struct perf_ibs *perf_ibs, struct perf_event *event,
u64 config)
{
u64 count = perf_ibs->get_count(config);
while (!perf_event_try_update(event, count, 20)) {
rdmsrl(event->hw.config_base, config);
count = perf_ibs->get_count(config);
}
}
/* Note: The enable mask must be encoded in the config argument. */
static inline void perf_ibs_enable_event(struct hw_perf_event *hwc, u64 config)
{
wrmsrl(hwc->config_base, hwc->config | config);
}
/*
* We cannot restore the ibs pmu state, so we always needs to update
* the event while stopping it and then reset the state when starting
* again. Thus, ignoring PERF_EF_RELOAD and PERF_EF_UPDATE flags in
* perf_ibs_start()/perf_ibs_stop() and instead always do it.
*/
static void perf_ibs_start(struct perf_event *event, int flags)
{
struct hw_perf_event *hwc = &event->hw;
struct perf_ibs *perf_ibs = container_of(event->pmu, struct perf_ibs, pmu);
struct cpu_perf_ibs *pcpu = this_cpu_ptr(perf_ibs->pcpu);
u64 config;
if (WARN_ON_ONCE(!(hwc->state & PERF_HES_STOPPED)))
return;
WARN_ON_ONCE(!(hwc->state & PERF_HES_UPTODATE));
hwc->state = 0;
perf_ibs_set_period(perf_ibs, hwc, &config);
config = (config >> 4) | perf_ibs->enable_mask;
set_bit(IBS_STARTED, pcpu->state);
perf_ibs_enable_event(hwc, config);
perf_event_update_userpage(event);
}
static void perf_ibs_stop(struct perf_event *event, int flags)
{
struct hw_perf_event *hwc = &event->hw;
struct perf_ibs *perf_ibs = container_of(event->pmu, struct perf_ibs, pmu);
struct cpu_perf_ibs *pcpu = this_cpu_ptr(perf_ibs->pcpu);
u64 val;
int stopping;
stopping = test_and_clear_bit(IBS_STARTED, pcpu->state);
if (!stopping && (hwc->state & PERF_HES_UPTODATE))
return;
rdmsrl(hwc->config_base, val);
if (stopping) {
set_bit(IBS_STOPPING, pcpu->state);
val &= ~perf_ibs->enable_mask;
wrmsrl(hwc->config_base, val);
WARN_ON_ONCE(hwc->state & PERF_HES_STOPPED);
hwc->state |= PERF_HES_STOPPED;
}
if (hwc->state & PERF_HES_UPTODATE)
return;
perf_ibs_event_update(perf_ibs, event, val);
hwc->state |= PERF_HES_UPTODATE;
}
static int perf_ibs_add(struct perf_event *event, int flags)
{
struct perf_ibs *perf_ibs = container_of(event->pmu, struct perf_ibs, pmu);
struct cpu_perf_ibs *pcpu = this_cpu_ptr(perf_ibs->pcpu);
if (test_and_set_bit(IBS_ENABLED, pcpu->state))
return -ENOSPC;
event->hw.state = PERF_HES_UPTODATE | PERF_HES_STOPPED;
pcpu->event = event;
if (flags & PERF_EF_START)
perf_ibs_start(event, PERF_EF_RELOAD);
return 0;
}
static void perf_ibs_del(struct perf_event *event, int flags)
{
struct perf_ibs *perf_ibs = container_of(event->pmu, struct perf_ibs, pmu);
struct cpu_perf_ibs *pcpu = this_cpu_ptr(perf_ibs->pcpu);
if (!test_and_clear_bit(IBS_ENABLED, pcpu->state))
return;
perf_ibs_stop(event, PERF_EF_UPDATE);
pcpu->event = NULL;
perf_event_update_userpage(event);
}
static struct pmu perf_ibs = {
.event_init= perf_ibs_init,
.add= perf_ibs_add,
.del= perf_ibs_del,
static void perf_ibs_read(struct perf_event *event) { }
static struct perf_ibs perf_ibs_fetch = {
.pmu = {
.task_ctx_nr = perf_invalid_context,
.event_init = perf_ibs_init,
.add = perf_ibs_add,
.del = perf_ibs_del,
.start = perf_ibs_start,
.stop = perf_ibs_stop,
.read = perf_ibs_read,
},
.msr = MSR_AMD64_IBSFETCHCTL,
.config_mask = IBS_FETCH_CONFIG_MASK,
.cnt_mask = IBS_FETCH_MAX_CNT,
.enable_mask = IBS_FETCH_ENABLE,
.valid_mask = IBS_FETCH_VAL,
.max_period = IBS_FETCH_MAX_CNT << 4,
.offset_mask = { MSR_AMD64_IBSFETCH_REG_MASK },
.offset_max = MSR_AMD64_IBSFETCH_REG_COUNT,
.get_count = get_ibs_fetch_count,
};
static struct perf_ibs perf_ibs_op = {
.pmu = {
.task_ctx_nr = perf_invalid_context,
.event_init = perf_ibs_init,
.add = perf_ibs_add,
.del = perf_ibs_del,
.start = perf_ibs_start,
.stop = perf_ibs_stop,
.read = perf_ibs_read,
},
.msr = MSR_AMD64_IBSOPCTL,
.config_mask = IBS_OP_CONFIG_MASK,
.cnt_mask = IBS_OP_MAX_CNT,
.enable_mask = IBS_OP_ENABLE,
.valid_mask = IBS_OP_VAL,
.max_period = IBS_OP_MAX_CNT << 4,
.offset_mask = { MSR_AMD64_IBSOP_REG_MASK },
.offset_max = MSR_AMD64_IBSOP_REG_COUNT,
.get_count = get_ibs_op_count,
};
static int perf_ibs_handle_irq(struct perf_ibs *perf_ibs, struct pt_regs *iregs)
{
struct cpu_perf_ibs *pcpu = this_cpu_ptr(perf_ibs->pcpu);
struct perf_event *event = pcpu->event;
struct hw_perf_event *hwc = &event->hw;
struct perf_sample_data data;
struct perf_raw_record raw;
struct pt_regs regs;
struct perf_ibs_data ibs_data;
int offset, size, overflow, reenable;
unsigned int msr;
u64 *buf, config;
if (!test_bit(IBS_STARTED, pcpu->state)) {
/* Catch spurious interrupts after stopping IBS: */
if (!test_and_clear_bit(IBS_STOPPING, pcpu->state))
return 0;
rdmsrl(perf_ibs->msr, *ibs_data.regs);
return (*ibs_data.regs & perf_ibs->valid_mask) ? 1 : 0;
}
msr = hwc->config_base;
buf = ibs_data.regs;
rdmsrl(msr, *buf);
if (!(*buf++ & perf_ibs->valid_mask))
return 0;
perf_sample_data_init(&data, 0);
if (event->attr.sample_type & PERF_SAMPLE_RAW) {
ibs_data.caps = ibs_caps;
size = 1;
offset = 1;
do {
rdmsrl(msr + offset, *buf++);
size++;
offset = find_next_bit(perf_ibs->offset_mask,
perf_ibs->offset_max,
offset + 1);
} while (offset < perf_ibs->offset_max);
raw.size = sizeof(u32) + sizeof(u64) * size;
raw.data = ibs_data.data;
data.raw = &raw;
}
regs = *iregs; /* XXX: update ip from ibs sample */
/*
* Emulate IbsOpCurCnt in MSRC001_1033 (IbsOpCtl), not
* supported in all cpus. As this triggered an interrupt, we
* set the current count to the max count.
*/
config = ibs_data.regs[0];
if (perf_ibs == &perf_ibs_op && !(ibs_caps & IBS_CAPS_RDWROPCNT)) {
config &= ~IBS_OP_CUR_CNT;
config |= (config & IBS_OP_MAX_CNT) << 36;
}
perf_ibs_event_update(perf_ibs, event, config);
overflow = perf_ibs_set_period(perf_ibs, hwc, &config);
reenable = !(overflow && perf_event_overflow(event, &data, &regs));
config = (config >> 4) | (reenable ? perf_ibs->enable_mask : 0);
perf_ibs_enable_event(hwc, config);
perf_event_update_userpage(event);
return 1;
}
static int __kprobes
perf_ibs_nmi_handler(unsigned int cmd, struct pt_regs *regs)
{
int handled = 0;
handled += perf_ibs_handle_irq(&perf_ibs_fetch, regs);
handled += perf_ibs_handle_irq(&perf_ibs_op, regs);
if (handled)
inc_irq_stat(apic_perf_irqs);
return handled;
}
static __init int perf_ibs_pmu_init(struct perf_ibs *perf_ibs, char *name)
{
struct cpu_perf_ibs __percpu *pcpu;
int ret;
pcpu = alloc_percpu(struct cpu_perf_ibs);
if (!pcpu)
return -ENOMEM;
perf_ibs->pcpu = pcpu;
ret = perf_pmu_register(&perf_ibs->pmu, name, -1);
if (ret) {
perf_ibs->pcpu = NULL;
free_percpu(pcpu);
}
return ret;
}
static __init int perf_event_ibs_init(void)
{
if (!ibs_caps)
return -ENODEV; /* ibs not supported by the cpu */
perf_pmu_register(&perf_ibs, "ibs", -1);
perf_ibs_pmu_init(&perf_ibs_fetch, "ibs_fetch");
perf_ibs_pmu_init(&perf_ibs_op, "ibs_op");
register_nmi_handler(NMI_LOCAL, perf_ibs_nmi_handler, 0, "perf_ibs");
printk(KERN_INFO "perf: AMD IBS detected (0x%08x)\n", ibs_caps);
return 0;