Commit 3569c0d7 authored by Yan, Zheng's avatar Yan, Zheng Committed by Ingo Molnar

perf/x86/intel: Implement batched PEBS interrupt handling (large PEBS interrupt threshold)

PEBS always had the capability to log samples to its buffers without
an interrupt. Traditionally perf has not used this but always set the
PEBS threshold to one.

For frequently occurring events (like cycles or branches or load/store)
this in term requires using a relatively high sampling period to avoid
overloading the system, by only processing PMIs. This in term increases
sampling error.

For the common cases we still need to use the PMI because the PEBS
hardware has various limitations. The biggest one is that it can not
supply a callgraph. It also requires setting a fixed period, as the
hardware does not support adaptive period. Another issue is that it
cannot supply a time stamp and some other options. To supply a TID it
requires flushing on context switch. It can however supply the IP, the
load/store address, TSX information, registers, and some other things.

So we can make PEBS work for some specific cases, basically as long as
you can do without a callgraph and can set the period you can use this
new PEBS mode.

The main benefit is the ability to support much lower sampling period
(down to -c 1000) without extensive overhead.

One use cases is for example to increase the resolution of the c2c tool.
Another is double checking when you suspect the standard sampling has
too much sampling error.

Some numbers on the overhead, using cycle soak, comparing the elapsed
time from "kernbench -M -H" between plain (threshold set to one) and
multi (large threshold).

The test command for plain:
  "perf record --time -e cycles:p -c $period -- kernbench -M -H"

The test command for multi:
  "perf record --no-time -e cycles:p -c $period -- kernbench -M -H"

( The only difference of test command between multi and plain is time
  stamp options. Since time stamp is not supported by large PEBS
  threshold, it can be used as a flag to indicate if large threshold is
  enabled during the test. )

	period    plain(Sec)  multi(Sec)  Delta
	10003     32.7        16.5        16.2
	20003     30.2        16.2        14.0
	40003     18.6        14.1        4.5
	80003     16.8        14.6        2.2
	100003    16.9        14.1        2.8
	800003    15.4        15.7        -0.3
	1000003   15.3        15.2        0.2
	2000003   15.3        15.1        0.1

With periods below 100003, plain (threshold one) cause much more
overhead. With 10003 sampling period, the Elapsed Time for multi is
even 2X faster than plain.
Signed-off-by: default avatarYan, Zheng <zheng.z.yan@intel.com>
Signed-off-by: default avatarKan Liang <kan.liang@intel.com>
Signed-off-by: default avatarPeter Zijlstra (Intel) <peterz@infradead.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: acme@infradead.org
Cc: eranian@google.com
Link: http://lkml.kernel.org/r/1430940834-8964-5-git-send-email-kan.liang@intel.comSigned-off-by: default avatarIngo Molnar <mingo@kernel.org>
parent 21509084
...@@ -76,6 +76,7 @@ struct event_constraint { ...@@ -76,6 +76,7 @@ struct event_constraint {
#define PERF_X86_EVENT_RDPMC_ALLOWED 0x0100 /* grant rdpmc permission */ #define PERF_X86_EVENT_RDPMC_ALLOWED 0x0100 /* grant rdpmc permission */
#define PERF_X86_EVENT_EXCL_ACCT 0x0200 /* accounted EXCL event */ #define PERF_X86_EVENT_EXCL_ACCT 0x0200 /* accounted EXCL event */
#define PERF_X86_EVENT_AUTO_RELOAD 0x0400 /* use PEBS auto-reload */ #define PERF_X86_EVENT_AUTO_RELOAD 0x0400 /* use PEBS auto-reload */
#define PERF_X86_EVENT_FREERUNNING 0x0800 /* use freerunning PEBS */
struct amd_nb { struct amd_nb {
...@@ -88,6 +89,16 @@ struct amd_nb { ...@@ -88,6 +89,16 @@ struct amd_nb {
/* The maximal number of PEBS events: */ /* The maximal number of PEBS events: */
#define MAX_PEBS_EVENTS 8 #define MAX_PEBS_EVENTS 8
/*
* Flags PEBS can handle without an PMI.
*
*/
#define PEBS_FREERUNNING_FLAGS \
(PERF_SAMPLE_IP | PERF_SAMPLE_ADDR | \
PERF_SAMPLE_ID | PERF_SAMPLE_CPU | PERF_SAMPLE_STREAM_ID | \
PERF_SAMPLE_DATA_SRC | PERF_SAMPLE_IDENTIFIER | \
PERF_SAMPLE_TRANSACTION)
/* /*
* A debug store configuration. * A debug store configuration.
* *
......
...@@ -2261,8 +2261,11 @@ static int intel_pmu_hw_config(struct perf_event *event) ...@@ -2261,8 +2261,11 @@ static int intel_pmu_hw_config(struct perf_event *event)
return ret; return ret;
if (event->attr.precise_ip) { if (event->attr.precise_ip) {
if (!event->attr.freq) if (!event->attr.freq) {
event->hw.flags |= PERF_X86_EVENT_AUTO_RELOAD; event->hw.flags |= PERF_X86_EVENT_AUTO_RELOAD;
if (!(event->attr.sample_type & ~PEBS_FREERUNNING_FLAGS))
event->hw.flags |= PERF_X86_EVENT_FREERUNNING;
}
if (x86_pmu.pebs_aliases) if (x86_pmu.pebs_aliases)
x86_pmu.pebs_aliases(event); x86_pmu.pebs_aliases(event);
} }
......
...@@ -250,7 +250,7 @@ static int alloc_pebs_buffer(int cpu) ...@@ -250,7 +250,7 @@ static int alloc_pebs_buffer(int cpu)
{ {
struct debug_store *ds = per_cpu(cpu_hw_events, cpu).ds; struct debug_store *ds = per_cpu(cpu_hw_events, cpu).ds;
int node = cpu_to_node(cpu); int node = cpu_to_node(cpu);
int max, thresh = 1; /* always use a single PEBS record */ int max;
void *buffer, *ibuffer; void *buffer, *ibuffer;
if (!x86_pmu.pebs) if (!x86_pmu.pebs)
...@@ -280,9 +280,6 @@ static int alloc_pebs_buffer(int cpu) ...@@ -280,9 +280,6 @@ static int alloc_pebs_buffer(int cpu)
ds->pebs_absolute_maximum = ds->pebs_buffer_base + ds->pebs_absolute_maximum = ds->pebs_buffer_base +
max * x86_pmu.pebs_record_size; max * x86_pmu.pebs_record_size;
ds->pebs_interrupt_threshold = ds->pebs_buffer_base +
thresh * x86_pmu.pebs_record_size;
return 0; return 0;
} }
...@@ -684,14 +681,22 @@ struct event_constraint *intel_pebs_constraints(struct perf_event *event) ...@@ -684,14 +681,22 @@ struct event_constraint *intel_pebs_constraints(struct perf_event *event)
return &emptyconstraint; return &emptyconstraint;
} }
static inline bool pebs_is_enabled(struct cpu_hw_events *cpuc)
{
return (cpuc->pebs_enabled & ((1ULL << MAX_PEBS_EVENTS) - 1));
}
void intel_pmu_pebs_enable(struct perf_event *event) void intel_pmu_pebs_enable(struct perf_event *event)
{ {
struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
struct hw_perf_event *hwc = &event->hw; struct hw_perf_event *hwc = &event->hw;
struct debug_store *ds = cpuc->ds; struct debug_store *ds = cpuc->ds;
bool first_pebs;
u64 threshold;
hwc->config &= ~ARCH_PERFMON_EVENTSEL_INT; hwc->config &= ~ARCH_PERFMON_EVENTSEL_INT;
first_pebs = !pebs_is_enabled(cpuc);
cpuc->pebs_enabled |= 1ULL << hwc->idx; cpuc->pebs_enabled |= 1ULL << hwc->idx;
if (event->hw.flags & PERF_X86_EVENT_PEBS_LDLAT) if (event->hw.flags & PERF_X86_EVENT_PEBS_LDLAT)
...@@ -699,11 +704,25 @@ void intel_pmu_pebs_enable(struct perf_event *event) ...@@ -699,11 +704,25 @@ void intel_pmu_pebs_enable(struct perf_event *event)
else if (event->hw.flags & PERF_X86_EVENT_PEBS_ST) else if (event->hw.flags & PERF_X86_EVENT_PEBS_ST)
cpuc->pebs_enabled |= 1ULL << 63; cpuc->pebs_enabled |= 1ULL << 63;
/*
* When the event is constrained enough we can use a larger
* threshold and run the event with less frequent PMI.
*/
if (hwc->flags & PERF_X86_EVENT_FREERUNNING) {
threshold = ds->pebs_absolute_maximum -
x86_pmu.max_pebs_events * x86_pmu.pebs_record_size;
} else {
threshold = ds->pebs_buffer_base + x86_pmu.pebs_record_size;
}
/* Use auto-reload if possible to save a MSR write in the PMI */ /* Use auto-reload if possible to save a MSR write in the PMI */
if (hwc->flags & PERF_X86_EVENT_AUTO_RELOAD) { if (hwc->flags & PERF_X86_EVENT_AUTO_RELOAD) {
ds->pebs_event_reset[hwc->idx] = ds->pebs_event_reset[hwc->idx] =
(u64)(-hwc->sample_period) & x86_pmu.cntval_mask; (u64)(-hwc->sample_period) & x86_pmu.cntval_mask;
} }
if (first_pebs || ds->pebs_interrupt_threshold > threshold)
ds->pebs_interrupt_threshold = threshold;
} }
void intel_pmu_pebs_disable(struct perf_event *event) void intel_pmu_pebs_disable(struct perf_event *event)
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment