[PATCH 1/2] [WIP] perf: make it possible to collect both, iregs and uregs
From: Milian Wolff
Date: Wed Nov 14 2018 - 08:10:47 EST
Previously, only one set of registers was stored in the perf
data for both, user and interrupt registers. Now, two distinct
sets can be sampled.
Signed-off-by: Milian Wolff <milian.wolff@xxxxxxxx>
Cc: Arnaldo Carvalho de Melo <acme@xxxxxxxxxx>
Cc: Andi Kleen <ak@xxxxxxxxxxxxxxx>
Cc: Jiri Olsa <jolsa@xxxxxxxxxx>
---
arch/x86/events/amd/ibs.c | 2 +-
arch/x86/events/core.c | 2 +-
arch/x86/events/intel/core.c | 2 +-
arch/x86/events/intel/ds.c | 7 +++----
arch/x86/events/intel/knc.c | 2 +-
arch/x86/events/intel/p4.c | 2 +-
arch/x86/kernel/ptrace.c | 2 +-
arch/x86/kvm/pmu.c | 4 ++--
drivers/oprofile/nmi_timer_int.c | 2 +-
include/linux/perf_event.h | 18 +++++++++++------
kernel/events/core.c | 34 ++++++++++++++++----------------
kernel/trace/bpf_trace.c | 2 +-
kernel/watchdog_hld.c | 2 +-
13 files changed, 43 insertions(+), 38 deletions(-)
diff --git a/arch/x86/events/amd/ibs.c b/arch/x86/events/amd/ibs.c
index d50bb4dc0650..567db8878511 100644
--- a/arch/x86/events/amd/ibs.c
+++ b/arch/x86/events/amd/ibs.c
@@ -670,7 +670,7 @@ static int perf_ibs_handle_irq(struct perf_ibs *perf_ibs, struct pt_regs *iregs)
data.raw = &raw;
}
- throttle = perf_event_overflow(event, &data, ®s);
+ throttle = perf_event_overflow(event, &data, ®s, iregs);
out:
if (throttle)
perf_ibs_stop(event, 0);
diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index 106911b603bd..acdcafa57ca0 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -1493,7 +1493,7 @@ int x86_pmu_handle_irq(struct pt_regs *regs)
if (!x86_perf_event_set_period(event))
continue;
- if (perf_event_overflow(event, &data, regs))
+ if (perf_event_overflow(event, &data, regs, regs))
x86_pmu_stop(event, 0);
}
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index 273c62e81546..2156620b3d9e 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -2299,7 +2299,7 @@ static int handle_pmi_common(struct pt_regs *regs, u64 status)
if (has_branch_stack(event))
data.br_stack = &cpuc->lbr_stack;
- if (perf_event_overflow(event, &data, regs))
+ if (perf_event_overflow(event, &data, regs, regs))
x86_pmu_stop(event, 0);
}
diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c
index b7b01d762d32..018fc0649033 100644
--- a/arch/x86/events/intel/ds.c
+++ b/arch/x86/events/intel/ds.c
@@ -639,7 +639,7 @@ int intel_pmu_drain_bts_buffer(void)
* the sample.
*/
rcu_read_lock();
- perf_prepare_sample(&header, &data, event, ®s);
+ perf_prepare_sample(&header, &data, event, ®s, ®s);
if (perf_output_begin(&handle, event, header.size *
(top - base - skip)))
@@ -1273,7 +1273,6 @@ static void setup_pebs_sample_data(struct perf_event *event,
set_linear_ip(regs, pebs->ip);
}
-
if ((sample_type & (PERF_SAMPLE_ADDR | PERF_SAMPLE_PHYS_ADDR)) &&
x86_pmu.intel_cap.pebs_format >= 1)
data->addr = pebs->dla;
@@ -1430,7 +1429,7 @@ static void __intel_pmu_pebs_event(struct perf_event *event,
while (count > 1) {
setup_pebs_sample_data(event, iregs, at, &data, ®s);
- perf_event_output(event, &data, ®s);
+ perf_event_output(event, &data, ®s, iregs);
at += x86_pmu.pebs_record_size;
at = get_next_pebs_record_by_bit(at, top, bit);
count--;
@@ -1442,7 +1441,7 @@ static void __intel_pmu_pebs_event(struct perf_event *event,
* All but the last records are processed.
* The last one is left to be able to call the overflow handler.
*/
- if (perf_event_overflow(event, &data, ®s)) {
+ if (perf_event_overflow(event, &data, ®s, iregs)) {
x86_pmu_stop(event, 0);
return;
}
diff --git a/arch/x86/events/intel/knc.c b/arch/x86/events/intel/knc.c
index 618001c208e8..9ea5a13af83f 100644
--- a/arch/x86/events/intel/knc.c
+++ b/arch/x86/events/intel/knc.c
@@ -252,7 +252,7 @@ static int knc_pmu_handle_irq(struct pt_regs *regs)
perf_sample_data_init(&data, 0, event->hw.last_period);
- if (perf_event_overflow(event, &data, regs))
+ if (perf_event_overflow(event, &data, regs, regs))
x86_pmu_stop(event, 0);
}
diff --git a/arch/x86/events/intel/p4.c b/arch/x86/events/intel/p4.c
index d32c0eed38ca..704457b5f49a 100644
--- a/arch/x86/events/intel/p4.c
+++ b/arch/x86/events/intel/p4.c
@@ -1037,7 +1037,7 @@ static int p4_pmu_handle_irq(struct pt_regs *regs)
continue;
- if (perf_event_overflow(event, &data, regs))
+ if (perf_event_overflow(event, &data, regs, regs))
x86_pmu_stop(event, 0);
}
diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c
index ffae9b9740fd..13b2230e5e9b 100644
--- a/arch/x86/kernel/ptrace.c
+++ b/arch/x86/kernel/ptrace.c
@@ -499,7 +499,7 @@ static int genregs_set(struct task_struct *target,
static void ptrace_triggered(struct perf_event *bp,
struct perf_sample_data *data,
- struct pt_regs *regs)
+ struct pt_regs *regs, struct pt_regs *iregs)
{
int i;
struct thread_struct *thread = &(current->thread);
diff --git a/arch/x86/kvm/pmu.c b/arch/x86/kvm/pmu.c
index 58ead7db71a3..b556b2d467e1 100644
--- a/arch/x86/kvm/pmu.c
+++ b/arch/x86/kvm/pmu.c
@@ -57,7 +57,7 @@ static void kvm_pmi_trigger_fn(struct irq_work *irq_work)
static void kvm_perf_overflow(struct perf_event *perf_event,
struct perf_sample_data *data,
- struct pt_regs *regs)
+ struct pt_regs *regs, struct pt_regs *iregs)
{
struct kvm_pmc *pmc = perf_event->overflow_handler_context;
struct kvm_pmu *pmu = pmc_to_pmu(pmc);
@@ -71,7 +71,7 @@ static void kvm_perf_overflow(struct perf_event *perf_event,
static void kvm_perf_overflow_intr(struct perf_event *perf_event,
struct perf_sample_data *data,
- struct pt_regs *regs)
+ struct pt_regs *regs, struct pt_regs *iregs)
{
struct kvm_pmc *pmc = perf_event->overflow_handler_context;
struct kvm_pmu *pmu = pmc_to_pmu(pmc);
diff --git a/drivers/oprofile/nmi_timer_int.c b/drivers/oprofile/nmi_timer_int.c
index f343bd96609a..110dfef21420 100644
--- a/drivers/oprofile/nmi_timer_int.c
+++ b/drivers/oprofile/nmi_timer_int.c
@@ -28,7 +28,7 @@ static struct perf_event_attr nmi_timer_attr = {
static void nmi_timer_callback(struct perf_event *event,
struct perf_sample_data *data,
- struct pt_regs *regs)
+ struct pt_regs *regs, struct pt_regs *iregs)
{
event->hw.interrupts = 0; /* don't throttle interrupts */
oprofile_add_sample(regs, 0);
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 53c500f0ca79..3a989c64c2c7 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -506,7 +506,8 @@ struct perf_sample_data;
typedef void (*perf_overflow_handler_t)(struct perf_event *,
struct perf_sample_data *,
- struct pt_regs *regs);
+ struct pt_regs *regs,
+ struct pt_regs *iregs);
/*
* Event capabilities. For event_caps and groups caps.
@@ -966,21 +967,26 @@ extern void perf_output_sample(struct perf_output_handle *handle,
extern void perf_prepare_sample(struct perf_event_header *header,
struct perf_sample_data *data,
struct perf_event *event,
- struct pt_regs *regs);
+ struct pt_regs *regs,
+ struct pt_regs *iregs);
extern int perf_event_overflow(struct perf_event *event,
struct perf_sample_data *data,
- struct pt_regs *regs);
+ struct pt_regs *regs,
+ struct pt_regs *iregs);
extern void perf_event_output_forward(struct perf_event *event,
struct perf_sample_data *data,
- struct pt_regs *regs);
+ struct pt_regs *regs,
+ struct pt_regs *iregs);
extern void perf_event_output_backward(struct perf_event *event,
struct perf_sample_data *data,
- struct pt_regs *regs);
+ struct pt_regs *regs,
+ struct pt_regs *iregs);
extern void perf_event_output(struct perf_event *event,
struct perf_sample_data *data,
- struct pt_regs *regs);
+ struct pt_regs *regs,
+ struct pt_regs *iregs);
static inline bool
is_default_overflow_handler(struct perf_event *event)
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 84530ab358c3..1b57602dc6d8 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -6369,7 +6369,7 @@ perf_callchain(struct perf_event *event, struct pt_regs *regs)
void perf_prepare_sample(struct perf_event_header *header,
struct perf_sample_data *data,
struct perf_event *event,
- struct pt_regs *regs)
+ struct pt_regs *regs, struct pt_regs *iregs)
{
u64 sample_type = event->attr.sample_type;
@@ -6474,7 +6474,7 @@ void perf_prepare_sample(struct perf_event_header *header,
/* regs dump ABI info */
int size = sizeof(u64);
- perf_sample_regs_intr(&data->regs_intr, regs);
+ perf_sample_regs_intr(&data->regs_intr, iregs);
if (data->regs_intr.regs) {
u64 mask = event->attr.sample_regs_intr;
@@ -6492,7 +6492,7 @@ void perf_prepare_sample(struct perf_event_header *header,
static __always_inline void
__perf_event_output(struct perf_event *event,
struct perf_sample_data *data,
- struct pt_regs *regs,
+ struct pt_regs *regs, struct pt_regs *iregs,
int (*output_begin)(struct perf_output_handle *,
struct perf_event *,
unsigned int))
@@ -6503,7 +6503,7 @@ __perf_event_output(struct perf_event *event,
/* protect the callchain buffers */
rcu_read_lock();
- perf_prepare_sample(&header, data, event, regs);
+ perf_prepare_sample(&header, data, event, regs, iregs);
if (output_begin(&handle, event, header.size))
goto exit;
@@ -6519,25 +6519,25 @@ __perf_event_output(struct perf_event *event,
void
perf_event_output_forward(struct perf_event *event,
struct perf_sample_data *data,
- struct pt_regs *regs)
+ struct pt_regs *regs, struct pt_regs *iregs)
{
- __perf_event_output(event, data, regs, perf_output_begin_forward);
+ __perf_event_output(event, data, regs, iregs, perf_output_begin_forward);
}
void
perf_event_output_backward(struct perf_event *event,
struct perf_sample_data *data,
- struct pt_regs *regs)
+ struct pt_regs *regs, struct pt_regs *iregs)
{
- __perf_event_output(event, data, regs, perf_output_begin_backward);
+ __perf_event_output(event, data, regs, iregs, perf_output_begin_backward);
}
void
perf_event_output(struct perf_event *event,
struct perf_sample_data *data,
- struct pt_regs *regs)
+ struct pt_regs *regs, struct pt_regs *iregs)
{
- __perf_event_output(event, data, regs, perf_output_begin);
+ __perf_event_output(event, data, regs, iregs, perf_output_begin);
}
/*
@@ -7738,7 +7738,7 @@ int perf_event_account_interrupt(struct perf_event *event)
static int __perf_event_overflow(struct perf_event *event,
int throttle, struct perf_sample_data *data,
- struct pt_regs *regs)
+ struct pt_regs *regs, struct pt_regs *iregs)
{
int events = atomic_read(&event->event_limit);
int ret = 0;
@@ -7765,7 +7765,7 @@ static int __perf_event_overflow(struct perf_event *event,
perf_event_disable_inatomic(event);
}
- READ_ONCE(event->overflow_handler)(event, data, regs);
+ READ_ONCE(event->overflow_handler)(event, data, regs, iregs);
if (*perf_event_fasync(event) && event->pending_kill) {
event->pending_wakeup = 1;
@@ -7777,9 +7777,9 @@ static int __perf_event_overflow(struct perf_event *event,
int perf_event_overflow(struct perf_event *event,
struct perf_sample_data *data,
- struct pt_regs *regs)
+ struct pt_regs *regs, struct pt_regs *iregs)
{
- return __perf_event_overflow(event, 1, data, regs);
+ return __perf_event_overflow(event, 1, data, regs, iregs);
}
/*
@@ -7842,7 +7842,7 @@ static void perf_swevent_overflow(struct perf_event *event, u64 overflow,
for (; overflow; overflow--) {
if (__perf_event_overflow(event, throttle,
- data, regs)) {
+ data, regs, regs)) {
/*
* We inhibit the overflow from happening when
* hwc->interrupts == MAX_INTERRUPTS.
@@ -8550,7 +8550,7 @@ static void bpf_overflow_handler(struct perf_event *event,
if (!ret)
return;
- event->orig_overflow_handler(event, data, regs);
+ event->orig_overflow_handler(event, data, regs, regs);
}
static int perf_event_set_bpf_handler(struct perf_event *event, u32 prog_fd)
@@ -9152,7 +9152,7 @@ static enum hrtimer_restart perf_swevent_hrtimer(struct hrtimer *hrtimer)
if (regs && !perf_exclude_event(event, regs)) {
if (!(event->attr.exclude_idle && is_idle_task(current)))
- if (__perf_event_overflow(event, 1, &data, regs))
+ if (__perf_event_overflow(event, 1, &data, regs, regs))
ret = HRTIMER_NORESTART;
}
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index 08fcfe440c63..6faf12fd6114 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -392,7 +392,7 @@ __bpf_perf_event_output(struct pt_regs *regs, struct bpf_map *map,
if (unlikely(event->oncpu != cpu))
return -EOPNOTSUPP;
- perf_event_output(event, sd, regs);
+ perf_event_output(event, sd, regs, regs);
return 0;
}
diff --git a/kernel/watchdog_hld.c b/kernel/watchdog_hld.c
index 71381168dede..5f4e18d003bb 100644
--- a/kernel/watchdog_hld.c
+++ b/kernel/watchdog_hld.c
@@ -109,7 +109,7 @@ static struct perf_event_attr wd_hw_attr = {
/* Callback function for perf event subsystem */
static void watchdog_overflow_callback(struct perf_event *event,
struct perf_sample_data *data,
- struct pt_regs *regs)
+ struct pt_regs *regs, struct pt_regs *iregs)
{
/* Ensure the watchdog never gets throttled */
event->hw.interrupts = 0;
--
2.19.1
--nextPart5412664.Fr9jt3Aeyc
Content-Disposition: attachment; filename="0002-WIP-perf-unwind-use-iregs-for-unwinding.patch"
Content-Transfer-Encoding: 7Bit
Content-Type: text/x-patch; charset="UTF-8"; name="0002-WIP-perf-unwind-use-iregs-for-unwinding.patch"