lkml.org 
[lkml]   [2019]   [Apr]   [16]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
Patch in this message
/
Date
From
Subject[tip:perf/core] perf/x86/intel: Extract memory code PEBS parser for reuse
Commit-ID:  48f38aa4cc5a48bc0fe85c5c4b1ab171fbb539b6
Gitweb: https://git.kernel.org/tip/48f38aa4cc5a48bc0fe85c5c4b1ab171fbb539b6
Author: Andi Kleen <ak@linux.intel.com>
AuthorDate: Tue, 2 Apr 2019 12:45:00 -0700
Committer: Ingo Molnar <mingo@kernel.org>
CommitDate: Tue, 16 Apr 2019 12:19:39 +0200

perf/x86/intel: Extract memory code PEBS parser for reuse

Extract some code related to memory profiling from the PEBS record
parser into separate functions. It can be reused by the upcoming
adaptive PEBS parser. No functional changes.
Rename intel_hsw_weight to intel_get_tsx_weight, and
intel_hsw_transaction to intel_get_tsx_transaction. Because the input is
not the hsw pebs format anymore.

Signed-off-by: Andi Kleen <ak@linux.intel.com>
Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Vince Weaver <vincent.weaver@maine.edu>
Cc: acme@kernel.org
Cc: jolsa@kernel.org
Link: https://lkml.kernel.org/r/20190402194509.2832-4-kan.liang@linux.intel.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
arch/x86/events/intel/ds.c | 63 +++++++++++++++++++++++++---------------------
1 file changed, 34 insertions(+), 29 deletions(-)

diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c
index f57e6cb7fd99..2f80b7e282ff 100644
--- a/arch/x86/events/intel/ds.c
+++ b/arch/x86/events/intel/ds.c
@@ -1125,34 +1125,50 @@ static int intel_pmu_pebs_fixup_ip(struct pt_regs *regs)
return 0;
}

-static inline u64 intel_hsw_weight(struct pebs_record_skl *pebs)
+static inline u64 intel_get_tsx_weight(u64 tsx_tuning)
{
- if (pebs->tsx_tuning) {
- union hsw_tsx_tuning tsx = { .value = pebs->tsx_tuning };
+ if (tsx_tuning) {
+ union hsw_tsx_tuning tsx = { .value = tsx_tuning };
return tsx.cycles_last_block;
}
return 0;
}

-static inline u64 intel_hsw_transaction(struct pebs_record_skl *pebs)
+static inline u64 intel_get_tsx_transaction(u64 tsx_tuning, u64 ax)
{
- u64 txn = (pebs->tsx_tuning & PEBS_HSW_TSX_FLAGS) >> 32;
+ u64 txn = (tsx_tuning & PEBS_HSW_TSX_FLAGS) >> 32;

/* For RTM XABORTs also log the abort code from AX */
- if ((txn & PERF_TXN_TRANSACTION) && (pebs->ax & 1))
- txn |= ((pebs->ax >> 24) & 0xff) << PERF_TXN_ABORT_SHIFT;
+ if ((txn & PERF_TXN_TRANSACTION) && (ax & 1))
+ txn |= ((ax >> 24) & 0xff) << PERF_TXN_ABORT_SHIFT;
return txn;
}

+#define PERF_X86_EVENT_PEBS_HSW_PREC \
+ (PERF_X86_EVENT_PEBS_ST_HSW | \
+ PERF_X86_EVENT_PEBS_LD_HSW | \
+ PERF_X86_EVENT_PEBS_NA_HSW)
+
+static u64 get_data_src(struct perf_event *event, u64 aux)
+{
+ u64 val = PERF_MEM_NA;
+ int fl = event->hw.flags;
+ bool fst = fl & (PERF_X86_EVENT_PEBS_ST | PERF_X86_EVENT_PEBS_HSW_PREC);
+
+ if (fl & PERF_X86_EVENT_PEBS_LDLAT)
+ val = load_latency_data(aux);
+ else if (fst && (fl & PERF_X86_EVENT_PEBS_HSW_PREC))
+ val = precise_datala_hsw(event, aux);
+ else if (fst)
+ val = precise_store_data(aux);
+ return val;
+}
+
static void setup_pebs_sample_data(struct perf_event *event,
struct pt_regs *iregs, void *__pebs,
struct perf_sample_data *data,
struct pt_regs *regs)
{
-#define PERF_X86_EVENT_PEBS_HSW_PREC \
- (PERF_X86_EVENT_PEBS_ST_HSW | \
- PERF_X86_EVENT_PEBS_LD_HSW | \
- PERF_X86_EVENT_PEBS_NA_HSW)
/*
* We cast to the biggest pebs_record but are careful not to
* unconditionally access the 'extra' entries.
@@ -1160,17 +1176,13 @@ static void setup_pebs_sample_data(struct perf_event *event,
struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
struct pebs_record_skl *pebs = __pebs;
u64 sample_type;
- int fll, fst, dsrc;
- int fl = event->hw.flags;
+ int fll;

if (pebs == NULL)
return;

sample_type = event->attr.sample_type;
- dsrc = sample_type & PERF_SAMPLE_DATA_SRC;
-
- fll = fl & PERF_X86_EVENT_PEBS_LDLAT;
- fst = fl & (PERF_X86_EVENT_PEBS_ST | PERF_X86_EVENT_PEBS_HSW_PREC);
+ fll = event->hw.flags & PERF_X86_EVENT_PEBS_LDLAT;

perf_sample_data_init(data, 0, event->hw.last_period);

@@ -1185,16 +1197,8 @@ static void setup_pebs_sample_data(struct perf_event *event,
/*
* data.data_src encodes the data source
*/
- if (dsrc) {
- u64 val = PERF_MEM_NA;
- if (fll)
- val = load_latency_data(pebs->dse);
- else if (fst && (fl & PERF_X86_EVENT_PEBS_HSW_PREC))
- val = precise_datala_hsw(event, pebs->dse);
- else if (fst)
- val = precise_store_data(pebs->dse);
- data->data_src.val = val;
- }
+ if (sample_type & PERF_SAMPLE_DATA_SRC)
+ data->data_src.val = get_data_src(event, pebs->dse);

/*
* We must however always use iregs for the unwinder to stay sane; the
@@ -1281,10 +1285,11 @@ static void setup_pebs_sample_data(struct perf_event *event,
if (x86_pmu.intel_cap.pebs_format >= 2) {
/* Only set the TSX weight when no memory weight. */
if ((sample_type & PERF_SAMPLE_WEIGHT) && !fll)
- data->weight = intel_hsw_weight(pebs);
+ data->weight = intel_get_tsx_weight(pebs->tsx_tuning);

if (sample_type & PERF_SAMPLE_TRANSACTION)
- data->txn = intel_hsw_transaction(pebs);
+ data->txn = intel_get_tsx_transaction(pebs->tsx_tuning,
+ pebs->ax);
}

/*
\
 
 \ /
  Last update: 2019-04-16 13:35    [W:0.230 / U:27.024 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site