Groups | Search | Server Info | Keyboard shortcuts | Login | Register [http] [https] [nntp] [nntps]
Groups > linux.kernel > #1578103 > unrolled thread
| Started by | Arnaldo Carvalho de Melo <acme@kernel.org> |
|---|---|
| First post | 2017-02-10 02:50 +0100 |
| Last post | 2017-02-10 09:20 +0100 |
| Articles | 15 on this page of 35 — 3 participants |
Back to article view | Back to linux.kernel
[GIT PULL 00/32] perf/core improvements and fixes Arnaldo Carvalho de Melo <acme@kernel.org> - 2017-02-10 02:50 +0100
[PATCH 17/32] perf vendor events intel: Add uncore events for Haswell Server processor Arnaldo Carvalho de Melo <acme@kernel.org> - 2017-02-10 03:10 +0100
[PATCH 26/32] tools strfilter: Use __fallthrough Arnaldo Carvalho de Melo <acme@kernel.org> - 2017-02-10 03:10 +0100
[PATCH 27/32] perf top: Use __fallthrough Arnaldo Carvalho de Melo <acme@kernel.org> - 2017-02-10 03:10 +0100
[PATCH 21/32] perf vendor events intel: Add uncore events for Xeon Phi (Knights Landing) Arnaldo Carvalho de Melo <acme@kernel.org> - 2017-02-10 03:10 +0100
[PATCH 28/32] perf thread_map: Correctly size buffer used with dirent->dt_name Arnaldo Carvalho de Melo <acme@kernel.org> - 2017-02-10 03:10 +0100
[PATCH 15/32] tools lib traceevent: Robustify do_generate_dynamic_list_file Arnaldo Carvalho de Melo <acme@kernel.org> - 2017-02-10 03:10 +0100
[PATCH 25/32] tools string: Use __fallthrough in perf_atoll() Arnaldo Carvalho de Melo <acme@kernel.org> - 2017-02-10 03:10 +0100
[PATCH 10/32] perf probe: Add option --symfs Arnaldo Carvalho de Melo <acme@kernel.org> - 2017-02-10 03:10 +0100
[PATCH 04/32] perf jevents: Add support for parsing uncore json files Arnaldo Carvalho de Melo <acme@kernel.org> - 2017-02-10 03:40 +0100
[PATCH 06/32] perf pmu: Support event aliases for non cpu// pmus Arnaldo Carvalho de Melo <acme@kernel.org> - 2017-02-10 03:40 +0100
[PATCH 07/32] perf list: Add debug support for outputing alias string Arnaldo Carvalho de Melo <acme@kernel.org> - 2017-02-10 03:40 +0100
[PATCH 08/32] perf sdt: Show proper hint when event not yet in place via 'perf probe' Arnaldo Carvalho de Melo <acme@kernel.org> - 2017-02-10 03:40 +0100
[PATCH 01/32] perf tools arm64: Add support for generating bpf prologue Arnaldo Carvalho de Melo <acme@kernel.org> - 2017-02-10 03:40 +0100
[PATCH 24/32] tools include: Add a __fallthrough statement Arnaldo Carvalho de Melo <acme@kernel.org> - 2017-02-10 03:50 +0100
Re: [PATCH 24/32] tools include: Add a __fallthrough statement Joe Perches <joe@perches.com> - 2017-02-10 04:10 +0100
Re: [PATCH 24/32] tools include: Add a __fallthrough statement Arnaldo Carvalho de Melo <acme@kernel.org> - 2017-02-10 15:50 +0100
[PATCH] compiler/compiler-gcc: Add __fallthrough Joe Perches <joe@perches.com> - 2017-02-10 19:00 +0100
Re: [PATCH] compiler/compiler-gcc: Add __fallthrough Arnaldo Carvalho de Melo <acme@kernel.org> - 2017-02-10 19:20 +0100
Re: [PATCH] compiler/compiler-gcc: Add __fallthrough Joe Perches <joe@perches.com> - 2017-02-10 20:00 +0100
[PATCH 03/32] perf jevents: Parse eventcode as number Arnaldo Carvalho de Melo <acme@kernel.org> - 2017-02-10 03:50 +0100
[PATCH 05/32] perf pmu: Support per pmu json aliases Arnaldo Carvalho de Melo <acme@kernel.org> - 2017-02-10 03:50 +0100
[PATCH 32/32] perf intel-pt: Use __fallthrough Arnaldo Carvalho de Melo <acme@kernel.org> - 2017-02-10 03:50 +0100
[PATCH 20/32] perf vendor events intel: Add uncore events for Sandy Bridge Server Arnaldo Carvalho de Melo <acme@kernel.org> - 2017-02-10 03:50 +0100
[PATCH 11/32] perf tools: Only increase index if perf_evsel__new_idx() succeeds Arnaldo Carvalho de Melo <acme@kernel.org> - 2017-02-10 03:50 +0100
[PATCH 12/32] perf tools: Add missing check for failure in a zalloc() call Arnaldo Carvalho de Melo <acme@kernel.org> - 2017-02-10 03:50 +0100
[PATCH 13/32] perf tools: Use zfree() instead of ad hoc equivalent Arnaldo Carvalho de Melo <acme@kernel.org> - 2017-02-10 03:50 +0100
[PATCH 14/32] perf tools: Use zfree() to avoid keeping dangling pointers Arnaldo Carvalho de Melo <acme@kernel.org> - 2017-02-10 03:50 +0100
[PATCH 02/32] perf bpf: Add missing newline in debug messages Arnaldo Carvalho de Melo <acme@kernel.org> - 2017-02-10 03:50 +0100
[PATCH 22/32] perf vendor events intel: Add uncore events for Broadwell DE Arnaldo Carvalho de Melo <acme@kernel.org> - 2017-02-10 03:50 +0100
[PATCH 29/32] perf header: Fix handling of PERF_EVENT_UPDATE__SCALE Arnaldo Carvalho de Melo <acme@kernel.org> - 2017-02-10 03:50 +0100
[PATCH 18/32] perf vendor events intel: Add uncore events for Broadwell Server Arnaldo Carvalho de Melo <acme@kernel.org> - 2017-02-10 03:50 +0100
[PATCH 30/32] perf bench numa: Avoid possible truncation when using snprintf() Arnaldo Carvalho de Melo <acme@kernel.org> - 2017-02-10 04:10 +0100
[PATCH 19/32] perf vendor events intel: Add uncore events for IvyBridge Server Arnaldo Carvalho de Melo <acme@kernel.org> - 2017-02-10 04:50 +0100
Re: [GIT PULL 00/32] perf/core improvements and fixes Ingo Molnar <mingo@kernel.org> - 2017-02-10 09:20 +0100
Page 2 of 2 — ← Prev page 1 [2]
| From | Arnaldo Carvalho de Melo <acme@kernel.org> |
|---|---|
| Date | 2017-02-10 03:50 +0100 |
| Subject | [PATCH 03/32] perf jevents: Parse eventcode as number |
| Message-ID | <t99rz-5V8-1@gated-at.bofh.it> |
| In reply to | #1578103 |
From: Andi Kleen <ak@linux.intel.com>
The next patch needs to modify event code. Previously eventcode was just
passed through as a string. Now parse it as a number.
v2: Don't special case 0
Signed-off-by: Andi Kleen <ak@linux.intel.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Link: http://lkml.kernel.org/r/20170128020345.19007-2-andi@firstfloor.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/perf/pmu-events/jevents.c | 10 +++++++++-
1 file changed, 9 insertions(+), 1 deletion(-)
diff --git a/tools/perf/pmu-events/jevents.c b/tools/perf/pmu-events/jevents.c
index 41611d7f9873..551377bf8428 100644
--- a/tools/perf/pmu-events/jevents.c
+++ b/tools/perf/pmu-events/jevents.c
@@ -135,7 +135,6 @@ static struct field {
const char *field;
const char *kernel;
} fields[] = {
- { "EventCode", "event=" },
{ "UMask", "umask=" },
{ "CounterMask", "cmask=" },
{ "Invert", "inv=" },
@@ -343,6 +342,7 @@ int json_events(const char *fn,
jsmntok_t *tokens, *tok;
int i, j, len;
char *map;
+ char buf[128];
if (!fn)
return -ENOENT;
@@ -356,6 +356,7 @@ int json_events(const char *fn,
char *event = NULL, *desc = NULL, *name = NULL;
char *long_desc = NULL;
char *extra_desc = NULL;
+ unsigned long long eventcode = 0;
struct msrmap *msr = NULL;
jsmntok_t *msrval = NULL;
jsmntok_t *precise = NULL;
@@ -376,6 +377,11 @@ int json_events(const char *fn,
nz = !json_streq(map, val, "0");
if (match_field(map, field, nz, &event, val)) {
/* ok */
+ } else if (json_streq(map, field, "EventCode")) {
+ char *code = NULL;
+ addfield(map, &code, "", "", val);
+ eventcode |= strtoul(code, NULL, 0);
+ free(code);
} else if (json_streq(map, field, "EventName")) {
addfield(map, &name, "", "", val);
} else if (json_streq(map, field, "BriefDescription")) {
@@ -410,6 +416,8 @@ int json_events(const char *fn,
addfield(map, &extra_desc, " ",
"(Precise event)", NULL);
}
+ snprintf(buf, sizeof buf, "event=%#llx", eventcode);
+ addfield(map, &event, ",", buf, NULL);
if (desc && extra_desc)
addfield(map, &desc, " ", extra_desc, NULL);
if (long_desc && extra_desc)
--
2.9.3
[toc] | [prev] | [next] | [standalone]
| From | Arnaldo Carvalho de Melo <acme@kernel.org> |
|---|---|
| Date | 2017-02-10 03:50 +0100 |
| Subject | [PATCH 05/32] perf pmu: Support per pmu json aliases |
| Message-ID | <t99rA-5V8-19@gated-at.bofh.it> |
| In reply to | #1578103 |
From: Andi Kleen <ak@linux.intel.com>
Add support for registering json aliases per PMU. Any alias with an unit
matching the prefix is registered to the PMU. Uncore has multiple
instances of most units, so all these aliases get registered for each
individual PMU (this is important later to run the event on every
instance of the PMU).
To avoid printing the events multiple times in perf list filter out
duplicated events during printing.
v2: Rely on uncore_ prefix already in unit
v3: Document why calls were reordered
Signed-off-by: Andi Kleen <ak@linux.intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Link: http://lkml.kernel.org/r/20170128020345.19007-4-andi@firstfloor.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/perf/util/pmu.c | 13 +++++++++----
1 file changed, 9 insertions(+), 4 deletions(-)
diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index 6dc3cc050105..8e9d00fd418e 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -590,14 +590,16 @@ static struct perf_pmu *pmu_lookup(const char *name)
if (pmu_format(name, &format))
return NULL;
- if (pmu_aliases(name, &aliases))
+ /*
+ * Check the type first to avoid unnecessary work.
+ */
+ if (pmu_type(name, &type))
return NULL;
- pmu_add_cpu_aliases(&aliases, name);
-
- if (pmu_type(name, &type))
+ if (pmu_aliases(name, &aliases))
return NULL;
+ pmu_add_cpu_aliases(&aliases, name);
pmu = zalloc(sizeof(*pmu));
if (!pmu)
return NULL;
@@ -1195,6 +1197,9 @@ void print_pmu_events(const char *event_glob, bool name_only, bool quiet_flag,
len = j;
qsort(aliases, len, sizeof(struct sevent), cmp_sevent);
for (j = 0; j < len; j++) {
+ /* Skip duplicates */
+ if (j > 0 && !strcmp(aliases[j].name, aliases[j - 1].name))
+ continue;
if (name_only) {
printf("%s ", aliases[j].name);
continue;
--
2.9.3
[toc] | [prev] | [next] | [standalone]
| From | Arnaldo Carvalho de Melo <acme@kernel.org> |
|---|---|
| Date | 2017-02-10 03:50 +0100 |
| Subject | [PATCH 32/32] perf intel-pt: Use __fallthrough |
| Message-ID | <t99rz-5V8-9@gated-at.bofh.it> |
| In reply to | #1578103 |
From: Arnaldo Carvalho de Melo <acme@redhat.com>
To address new warnings emmited by gcc 7, e.g.::
CC /tmp/build/perf/util/intel-pt-decoder/intel-pt-pkt-decoder.o
CC /tmp/build/perf/tests/parse-events.o
util/intel-pt-decoder/intel-pt-pkt-decoder.c: In function 'intel_pt_pkt_desc':
util/intel-pt-decoder/intel-pt-pkt-decoder.c:499:6: error: this statement may fall through [-Werror=implicit-fallthrough=]
if (!(packet->count))
^
util/intel-pt-decoder/intel-pt-pkt-decoder.c:501:2: note: here
case INTEL_PT_CYC:
^~~~
CC /tmp/build/perf/util/intel-pt-decoder/intel-pt-decoder.o
cc1: all warnings being treated as errors
Acked-by: Andi Kleen <ak@linux.intel.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lkml.kernel.org/n/tip-mf0hw789pu9x855us5l32c83@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/perf/util/intel-pt-decoder/intel-pt-decoder.c | 5 +++++
tools/perf/util/intel-pt-decoder/intel-pt-pkt-decoder.c | 2 ++
2 files changed, 7 insertions(+)
diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c
index e4e7dc781d21..7cf7f7aca4d2 100644
--- a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c
+++ b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c
@@ -22,6 +22,7 @@
#include <errno.h>
#include <stdint.h>
#include <inttypes.h>
+#include <linux/compiler.h>
#include "../cache.h"
#include "../util.h"
@@ -1746,6 +1747,7 @@ static int intel_pt_walk_psb(struct intel_pt_decoder *decoder)
switch (decoder->packet.type) {
case INTEL_PT_TIP_PGD:
decoder->continuous_period = false;
+ __fallthrough;
case INTEL_PT_TIP_PGE:
case INTEL_PT_TIP:
intel_pt_log("ERROR: Unexpected packet\n");
@@ -1799,6 +1801,8 @@ static int intel_pt_walk_psb(struct intel_pt_decoder *decoder)
decoder->pge = false;
decoder->continuous_period = false;
intel_pt_clear_tx_flags(decoder);
+ __fallthrough;
+
case INTEL_PT_TNT:
decoder->have_tma = false;
intel_pt_log("ERROR: Unexpected packet\n");
@@ -1839,6 +1843,7 @@ static int intel_pt_walk_to_ip(struct intel_pt_decoder *decoder)
switch (decoder->packet.type) {
case INTEL_PT_TIP_PGD:
decoder->continuous_period = false;
+ __fallthrough;
case INTEL_PT_TIP_PGE:
case INTEL_PT_TIP:
decoder->pge = decoder->packet.type != INTEL_PT_TIP_PGD;
diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-pkt-decoder.c b/tools/perf/util/intel-pt-decoder/intel-pt-pkt-decoder.c
index 4f7b32020487..7528ae4f7e28 100644
--- a/tools/perf/util/intel-pt-decoder/intel-pt-pkt-decoder.c
+++ b/tools/perf/util/intel-pt-decoder/intel-pt-pkt-decoder.c
@@ -17,6 +17,7 @@
#include <string.h>
#include <endian.h>
#include <byteswap.h>
+#include <linux/compiler.h>
#include "intel-pt-pkt-decoder.h"
@@ -498,6 +499,7 @@ int intel_pt_pkt_desc(const struct intel_pt_pkt *packet, char *buf,
case INTEL_PT_FUP:
if (!(packet->count))
return snprintf(buf, buf_len, "%s no ip", name);
+ __fallthrough;
case INTEL_PT_CYC:
case INTEL_PT_VMCS:
case INTEL_PT_MTC:
--
2.9.3
[toc] | [prev] | [next] | [standalone]
| From | Arnaldo Carvalho de Melo <acme@kernel.org> |
|---|---|
| Date | 2017-02-10 03:50 +0100 |
| Subject | [PATCH 20/32] perf vendor events intel: Add uncore events for Sandy Bridge Server |
| Message-ID | <t99rz-5V8-5@gated-at.bofh.it> |
| In reply to | #1578103 |
From: Andi Kleen <ak@linux.intel.com>
This is not a full uncore event list, but a short list of useful
and understandable metrics.
Signed-off-by: Andi Kleen <ak@linux.intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Link: http://lkml.kernel.org/n/tip-c0cix4eprbldfrx5zf60suvh@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
.../pmu-events/arch/x86/jaketown/uncore-cache.json | 209 +++++++++++++++++
.../arch/x86/jaketown/uncore-interconnect.json | 46 ++++
.../arch/x86/jaketown/uncore-memory.json | 79 +++++++
.../pmu-events/arch/x86/jaketown/uncore-power.json | 248 +++++++++++++++++++++
4 files changed, 582 insertions(+)
create mode 100644 tools/perf/pmu-events/arch/x86/jaketown/uncore-cache.json
create mode 100644 tools/perf/pmu-events/arch/x86/jaketown/uncore-interconnect.json
create mode 100644 tools/perf/pmu-events/arch/x86/jaketown/uncore-memory.json
create mode 100644 tools/perf/pmu-events/arch/x86/jaketown/uncore-power.json
diff --git a/tools/perf/pmu-events/arch/x86/jaketown/uncore-cache.json b/tools/perf/pmu-events/arch/x86/jaketown/uncore-cache.json
new file mode 100644
index 000000000000..2f23cf0129e7
--- /dev/null
+++ b/tools/perf/pmu-events/arch/x86/jaketown/uncore-cache.json
@@ -0,0 +1,209 @@
+[
+ {
+ "BriefDescription": "Uncore cache clock ticks. Derived from unc_c_clockticks",
+ "Counter": "0,1,2,3",
+ "EventName": "UNC_C_CLOCKTICKS",
+ "PerPkg": "1",
+ "Unit": "CBO"
+ },
+ {
+ "BriefDescription": "All LLC Misses (code+ data rd + data wr - including demand and prefetch). Derived from unc_c_llc_lookup.any",
+ "Counter": "0,1",
+ "EventCode": "0x34",
+ "EventName": "UNC_C_LLC_LOOKUP.ANY",
+ "Filter": "filter_state=0x1",
+ "PerPkg": "1",
+ "ScaleUnit": "64Bytes",
+ "UMask": "0x11",
+ "Unit": "CBO"
+ },
+ {
+ "BriefDescription": "M line evictions from LLC (writebacks to memory). Derived from unc_c_llc_victims.m_state",
+ "Counter": "0,1",
+ "EventCode": "0x37",
+ "EventName": "UNC_C_LLC_VICTIMS.M_STATE",
+ "PerPkg": "1",
+ "ScaleUnit": "64Bytes",
+ "UMask": "0x1",
+ "Unit": "CBO"
+ },
+ {
+ "BriefDescription": "LLC misses - demand and prefetch data reads - excludes LLC prefetches. Derived from unc_c_tor_inserts.miss_opcode.demand",
+ "Counter": "0,1",
+ "EventCode": "0x35",
+ "EventName": "LLC_MISSES.DATA_READ",
+ "Filter": "filter_opc=0x182",
+ "PerPkg": "1",
+ "ScaleUnit": "64Bytes",
+ "UMask": "0x3",
+ "Unit": "CBO"
+ },
+ {
+ "BriefDescription": "LLC misses - Uncacheable reads. Derived from unc_c_tor_inserts.miss_opcode.uncacheable",
+ "Counter": "0,1",
+ "EventCode": "0x35",
+ "EventName": "LLC_MISSES.UNCACHEABLE",
+ "Filter": "filter_opc=0x187",
+ "PerPkg": "1",
+ "ScaleUnit": "64Bytes",
+ "UMask": "0x3",
+ "Unit": "CBO"
+ },
+ {
+ "BriefDescription": "PCIe allocating writes that miss LLC - DDIO misses. Derived from unc_c_tor_inserts.miss_opcode.ddio_miss",
+ "Counter": "0,1",
+ "EventCode": "0x35",
+ "EventName": "LLC_MISSES.PCIE_WRITE",
+ "Filter": "filter_opc=0x19c",
+ "PerPkg": "1",
+ "ScaleUnit": "64Bytes",
+ "UMask": "0x3",
+ "Unit": "CBO"
+ },
+ {
+ "BriefDescription": "LLC misses for ItoM writes (as part of fast string memcpy stores). Derived from unc_c_tor_inserts.miss_opcode.itom_write",
+ "Counter": "0,1",
+ "EventCode": "0x35",
+ "EventName": "LLC_MISSES.ITOM_WRITE",
+ "Filter": "filter_opc=0x1c8",
+ "PerPkg": "1",
+ "ScaleUnit": "64Bytes",
+ "UMask": "0x3",
+ "Unit": "CBO"
+ },
+ {
+ "BriefDescription": "Streaming stores (full cache line). Derived from unc_c_tor_inserts.opcode.streaming_full",
+ "Counter": "0,1",
+ "EventCode": "0x35",
+ "EventName": "LLC_REFERENCES.STREAMING_FULL",
+ "Filter": "filter_opc=0x18c",
+ "PerPkg": "1",
+ "ScaleUnit": "64Bytes",
+ "UMask": "0x1",
+ "Unit": "CBO"
+ },
+ {
+ "BriefDescription": "Streaming stores (partial cache line). Derived from unc_c_tor_inserts.opcode.streaming_partial",
+ "Counter": "0,1",
+ "EventCode": "0x35",
+ "EventName": "LLC_REFERENCES.STREAMING_PARTIAL",
+ "Filter": "filter_opc=0x18d",
+ "PerPkg": "1",
+ "ScaleUnit": "64Bytes",
+ "UMask": "0x1",
+ "Unit": "CBO"
+ },
+ {
+ "BriefDescription": "Partial PCIe reads. Derived from unc_c_tor_inserts.opcode.pcie_partial",
+ "Counter": "0,1",
+ "EventCode": "0x35",
+ "EventName": "LLC_REFERENCES.PCIE_PARTIAL_READ",
+ "Filter": "filter_opc=0x195",
+ "PerPkg": "1",
+ "ScaleUnit": "64Bytes",
+ "UMask": "0x1",
+ "Unit": "CBO"
+ },
+ {
+ "BriefDescription": "PCIe allocating writes that hit in LLC (DDIO hits). Derived from unc_c_tor_inserts.opcode.ddio_hit",
+ "Counter": "0,1",
+ "EventCode": "0x35",
+ "EventName": "LLC_REFERENCES.PCIE_WRITE",
+ "Filter": "filter_opc=0x19c",
+ "PerPkg": "1",
+ "ScaleUnit": "64Bytes",
+ "UMask": "0x1",
+ "Unit": "CBO"
+ },
+ {
+ "BriefDescription": "PCIe read current. Derived from unc_c_tor_inserts.opcode.pcie_read_current",
+ "Counter": "0,1",
+ "EventCode": "0x35",
+ "EventName": "LLC_REFERENCES.PCIE_READ",
+ "Filter": "filter_opc=0x19e",
+ "PerPkg": "1",
+ "ScaleUnit": "64Bytes",
+ "UMask": "0x1",
+ "Unit": "CBO"
+ },
+ {
+ "BriefDescription": "ItoM write hits (as part of fast string memcpy stores). Derived from unc_c_tor_inserts.opcode.itom_write_hit",
+ "Counter": "0,1",
+ "EventCode": "0x35",
+ "EventName": "LLC_REFERENCES.ITOM_WRITE",
+ "Filter": "filter_opc=0x1c8",
+ "PerPkg": "1",
+ "ScaleUnit": "64Bytes",
+ "UMask": "0x1",
+ "Unit": "CBO"
+ },
+ {
+ "BriefDescription": "PCIe non-snoop reads. Derived from unc_c_tor_inserts.opcode.pcie_read",
+ "Counter": "0,1",
+ "EventCode": "0x35",
+ "EventName": "LLC_REFERENCES.PCIE_NS_READ",
+ "Filter": "filter_opc=0x1e4",
+ "PerPkg": "1",
+ "ScaleUnit": "64Bytes",
+ "UMask": "0x1",
+ "Unit": "CBO"
+ },
+ {
+ "BriefDescription": "PCIe non-snoop writes (partial). Derived from unc_c_tor_inserts.opcode.pcie_partial_write",
+ "Counter": "0,1",
+ "EventCode": "0x35",
+ "EventName": "LLC_REFERENCES.PCIE_NS_PARTIAL_WRITE",
+ "Filter": "filter_opc=0x1e5",
+ "PerPkg": "1",
+ "ScaleUnit": "64Bytes",
+ "UMask": "0x1",
+ "Unit": "CBO"
+ },
+ {
+ "BriefDescription": "PCIe non-snoop writes (full line). Derived from unc_c_tor_inserts.opcode.pcie_full_write",
+ "Counter": "0,1",
+ "EventCode": "0x35",
+ "EventName": "LLC_REFERENCES.PCIE_NS_WRITE",
+ "Filter": "filter_opc=0x1e6",
+ "PerPkg": "1",
+ "ScaleUnit": "64Bytes",
+ "UMask": "0x1",
+ "Unit": "CBO"
+ },
+ {
+ "BriefDescription": "Occupancy counter for all LLC misses; we divide this by UNC_C_CLOCKTICKS to get average Q depth. Derived from unc_c_tor_occupancy.miss_all",
+ "EventCode": "0x36",
+ "EventName": "UNC_C_TOR_OCCUPANCY.MISS_ALL",
+ "Filter": "filter_opc=0x182",
+ "MetricExpr": "(UNC_C_TOR_OCCUPANCY.MISS_ALL / UNC_C_CLOCKTICKS) * 100.",
+ "PerPkg": "1",
+ "UMask": "0xa",
+ "Unit": "CBO"
+ },
+ {
+ "BriefDescription": "Occupancy counter for LLC data reads (demand and L2 prefetch). Derived from unc_c_tor_occupancy.miss_opcode.llc_data_read",
+ "EventCode": "0x36",
+ "EventName": "UNC_C_TOR_OCCUPANCY.LLC_DATA_READ",
+ "PerPkg": "1",
+ "UMask": "0x3",
+ "Unit": "CBO"
+ },
+ {
+ "BriefDescription": "read requests to home agent. Derived from unc_h_requests.reads",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x1",
+ "EventName": "UNC_H_REQUESTS.READS",
+ "PerPkg": "1",
+ "UMask": "0x3",
+ "Unit": "HA"
+ },
+ {
+ "BriefDescription": "write requests to home agent. Derived from unc_h_requests.writes",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x1",
+ "EventName": "UNC_H_REQUESTS.WRITES",
+ "PerPkg": "1",
+ "UMask": "0xc",
+ "Unit": "HA"
+ }
+]
diff --git a/tools/perf/pmu-events/arch/x86/jaketown/uncore-interconnect.json b/tools/perf/pmu-events/arch/x86/jaketown/uncore-interconnect.json
new file mode 100644
index 000000000000..63351876eb57
--- /dev/null
+++ b/tools/perf/pmu-events/arch/x86/jaketown/uncore-interconnect.json
@@ -0,0 +1,46 @@
+[
+ {
+ "BriefDescription": "QPI clock ticks. Used to get percentages of QPI cycles events. Derived from unc_q_clockticks",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x14",
+ "EventName": "UNC_Q_CLOCKTICKS",
+ "PerPkg": "1",
+ "Unit": "QPI LL"
+ },
+ {
+ "BriefDescription": "Cycles where receiving QPI link is in half-width mode. Derived from unc_q_rxl0p_power_cycles",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x10",
+ "EventName": "UNC_Q_RxL0P_POWER_CYCLES",
+ "MetricExpr": "(UNC_Q_RxL0P_POWER_CYCLES / UNC_Q_CLOCKTICKS) * 100.",
+ "PerPkg": "1",
+ "Unit": "QPI LL"
+ },
+ {
+ "BriefDescription": "Cycles where transmitting QPI link is in half-width mode. Derived from unc_q_txl0p_power_cycles",
+ "Counter": "0,1,2,3",
+ "EventCode": "0xd",
+ "EventName": "UNC_Q_TxL0P_POWER_CYCLES",
+ "MetricExpr": "(UNC_Q_TxL0P_POWER_CYCLES / UNC_Q_CLOCKTICKS) * 100.",
+ "PerPkg": "1",
+ "Unit": "QPI LL"
+ },
+ {
+ "BriefDescription": "Number of data flits transmitted . Derived from unc_q_txl_flits_g0.data",
+ "Counter": "0,1,2,3",
+ "EventName": "UNC_Q_TxL_FLITS_G0.DATA",
+ "PerPkg": "1",
+ "ScaleUnit": "8Bytes",
+ "UMask": "0x2",
+ "Unit": "QPI LL"
+ },
+ {
+ "BriefDescription": "Number of non data (control) flits transmitted . Derived from unc_q_txl_flits_g0.non_data",
+ "Counter": "0,1,2,3",
+ "EventName": "UNC_Q_TxL_FLITS_G0.NON_DATA",
+ "PerPkg": "1",
+ "ScaleUnit": "8Bytes",
+ "UMask": "0x4",
+ "Unit": "QPI LL"
+ }
+]
diff --git a/tools/perf/pmu-events/arch/x86/jaketown/uncore-memory.json b/tools/perf/pmu-events/arch/x86/jaketown/uncore-memory.json
new file mode 100644
index 000000000000..e2cf6daa7b37
--- /dev/null
+++ b/tools/perf/pmu-events/arch/x86/jaketown/uncore-memory.json
@@ -0,0 +1,79 @@
+[
+ {
+ "BriefDescription": "Memory page activates. Derived from unc_m_act_count",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x1",
+ "EventName": "UNC_M_ACT_COUNT",
+ "PerPkg": "1",
+ "Unit": "iMC"
+ },
+ {
+ "BriefDescription": "read requests to memory controller. Derived from unc_m_cas_count.rd",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x4",
+ "EventName": "UNC_M_CAS_COUNT.RD",
+ "PerPkg": "1",
+ "UMask": "0x3",
+ "Unit": "iMC"
+ },
+ {
+ "BriefDescription": "write requests to memory controller. Derived from unc_m_cas_count.wr",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x4",
+ "EventName": "UNC_M_CAS_COUNT.WR",
+ "PerPkg": "1",
+ "UMask": "0xc",
+ "Unit": "iMC"
+ },
+ {
+ "BriefDescription": "Memory controller clock ticks. Used to get percentages of memory controller cycles events. Derived from unc_m_clockticks",
+ "Counter": "0,1,2,3",
+ "EventName": "UNC_M_CLOCKTICKS",
+ "PerPkg": "1",
+ "Unit": "iMC"
+ },
+ {
+ "BriefDescription": "Cycles where DRAM ranks are in power down (CKE) mode. Derived from unc_m_power_channel_ppd",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x85",
+ "EventName": "UNC_M_POWER_CHANNEL_PPD",
+ "MetricExpr": "(UNC_M_POWER_CHANNEL_PPD / UNC_M_CLOCKTICKS) * 100.",
+ "PerPkg": "1",
+ "Unit": "iMC"
+ },
+ {
+ "BriefDescription": "Cycles all ranks are in critical thermal throttle. Derived from unc_m_power_critical_throttle_cycles",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x86",
+ "EventName": "UNC_M_POWER_CRITICAL_THROTTLE_CYCLES",
+ "MetricExpr": "(UNC_M_POWER_CRITICAL_THROTTLE_CYCLES / UNC_M_CLOCKTICKS) * 100.",
+ "PerPkg": "1",
+ "Unit": "iMC"
+ },
+ {
+ "BriefDescription": "Cycles Memory is in self refresh power mode. Derived from unc_m_power_self_refresh",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x43",
+ "EventName": "UNC_M_POWER_SELF_REFRESH",
+ "MetricExpr": "(UNC_M_POWER_SELF_REFRESH / UNC_M_CLOCKTICKS) * 100.",
+ "PerPkg": "1",
+ "Unit": "iMC"
+ },
+ {
+ "BriefDescription": "Memory page conflicts. Derived from unc_m_pre_count.page_miss",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x2",
+ "EventName": "UNC_M_PRE_COUNT.PAGE_MISS",
+ "PerPkg": "1",
+ "UMask": "0x1",
+ "Unit": "iMC"
+ },
+ {
+ "BriefDescription": "Occupancy counter for memory read queue. Derived from unc_m_rpq_occupancy",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x80",
+ "EventName": "UNC_M_RPQ_OCCUPANCY",
+ "PerPkg": "1",
+ "Unit": "iMC"
+ }
+]
diff --git a/tools/perf/pmu-events/arch/x86/jaketown/uncore-power.json b/tools/perf/pmu-events/arch/x86/jaketown/uncore-power.json
new file mode 100644
index 000000000000..bbe36d547386
--- /dev/null
+++ b/tools/perf/pmu-events/arch/x86/jaketown/uncore-power.json
@@ -0,0 +1,248 @@
+[
+ {
+ "BriefDescription": "PCU clock ticks. Use to get percentages of PCU cycles events. Derived from unc_p_clockticks",
+ "Counter": "0,1,2,3",
+ "EventName": "UNC_P_CLOCKTICKS",
+ "PerPkg": "1",
+ "Unit": "PCU"
+ },
+ {
+ "BriefDescription": "Counts the number of cycles that the uncore was running at a frequency greater than or equal to the frequency that is configured in the filter. (filter_band0=XXX with XXX in 100Mhz units). One can also use inversion (filter_inv=1) to track cycles when we were less than the configured frequency. Derived from unc_p_freq_band0_cycles",
+ "Counter": "0,1,2,3",
+ "EventCode": "0xb",
+ "EventName": "UNC_P_FREQ_BAND0_CYCLES",
+ "MetricExpr": "(UNC_P_FREQ_BAND0_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+ "PerPkg": "1",
+ "Unit": "PCU"
+ },
+ {
+ "BriefDescription": "Counts the number of cycles that the uncore was running at a frequency greater than or equal to the frequency that is configured in the filter. (filter_band1=XXX with XXX in 100Mhz units). One can also use inversion (filter_inv=1) to track cycles when we were less than the configured frequency. Derived from unc_p_freq_band1_cycles",
+ "Counter": "0,1,2,3",
+ "EventCode": "0xc",
+ "EventName": "UNC_P_FREQ_BAND1_CYCLES",
+ "MetricExpr": "(UNC_P_FREQ_BAND1_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+ "PerPkg": "1",
+ "Unit": "PCU"
+ },
+ {
+ "BriefDescription": "Counts the number of cycles that the uncore was running at a frequency greater than or equal to the frequency that is configured in the filter. (filter_band2=XXX with XXX in 100Mhz units). One can also use inversion (filter_inv=1) to track cycles when we were less than the configured frequency. Derived from unc_p_freq_band2_cycles",
+ "Counter": "0,1,2,3",
+ "EventCode": "0xd",
+ "EventName": "UNC_P_FREQ_BAND2_CYCLES",
+ "MetricExpr": "(UNC_P_FREQ_BAND2_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+ "PerPkg": "1",
+ "Unit": "PCU"
+ },
+ {
+ "BriefDescription": "Counts the number of cycles that the uncore was running at a frequency greater than or equal to the frequency that is configured in the filter. (filter_band3=XXX, with XXX in 100Mhz units). One can also use inversion (filter_inv=1) to track cycles when we were less than the configured frequency. Derived from unc_p_freq_band3_cycles",
+ "Counter": "0,1,2,3",
+ "EventCode": "0xe",
+ "EventName": "UNC_P_FREQ_BAND3_CYCLES",
+ "MetricExpr": "(UNC_P_FREQ_BAND3_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+ "PerPkg": "1",
+ "Unit": "PCU"
+ },
+ {
+ "BriefDescription": "Counts the number of times that the uncore transitioned a frequency greater than or equal to the frequency that is configured in the filter. (filter_band0=XXX with XXX in 100Mhz units). One can also use inversion (filter_inv=1) to track cycles when we were less than the configured frequency. Derived from unc_p_freq_band0_cycles",
+ "Counter": "0,1,2,3",
+ "EventCode": "0xb",
+ "EventName": "UNC_P_FREQ_BAND0_TRANSITIONS",
+ "Filter": "edge=1",
+ "MetricExpr": "(UNC_P_FREQ_BAND0_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+ "PerPkg": "1",
+ "Unit": "PCU"
+ },
+ {
+ "BriefDescription": "Counts the number of times that the uncore transistioned to a frequency greater than or equal to the frequency that is configured in the filter. (filter_band1=XXX with XXX in 100Mhz units). One can also use inversion (filter_inv=1) to track cycles when we were less than the configured frequency. Derived from unc_p_freq_band1_cycles",
+ "Counter": "0,1,2,3",
+ "EventCode": "0xc",
+ "EventName": "UNC_P_FREQ_BAND1_TRANSITIONS",
+ "Filter": "edge=1",
+ "MetricExpr": "(UNC_P_FREQ_BAND1_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+ "PerPkg": "1",
+ "Unit": "PCU"
+ },
+ {
+ "BriefDescription": "Counts the number of cycles that the uncore transitioned to a frequency greater than or equal to the frequency that is configured in the filter. (filter_band2=XXX with XXX in 100Mhz units). One can also use inversion (filter_inv=1) to track cycles when we were less than the configured frequency. Derived from unc_p_freq_band2_cycles",
+ "Counter": "0,1,2,3",
+ "EventCode": "0xd",
+ "EventName": "UNC_P_FREQ_BAND2_TRANSITIONS",
+ "Filter": "edge=1",
+ "MetricExpr": "(UNC_P_FREQ_BAND2_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+ "PerPkg": "1",
+ "Unit": "PCU"
+ },
+ {
+ "BriefDescription": "Counts the number of cycles that the uncore transitioned to a frequency greater than or equal to the frequency that is configured in the filter. (filter_band3=XXX, with XXX in 100Mhz units). One can also use inversion (filter_inv=1) to track cycles when we were less than the configured frequency. Derived from unc_p_freq_band3_cycles",
+ "Counter": "0,1,2,3",
+ "EventCode": "0xe",
+ "EventName": "UNC_P_FREQ_BAND3_TRANSITIONS",
+ "Filter": "edge=1",
+ "MetricExpr": "(UNC_P_FREQ_BAND3_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+ "PerPkg": "1",
+ "Unit": "PCU"
+ },
+ {
+ "BriefDescription": "This is an occupancy event that tracks the number of cores that are in C0. It can be used by itself to get the average number of cores in C0, with threshholding to generate histograms, or with other PCU events and occupancy triggering to capture other details. Derived from unc_p_power_state_occupancy.cores_c0",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x80",
+ "EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C0",
+ "Filter": "occ_sel=1",
+ "MetricExpr": "(UNC_P_POWER_STATE_OCCUPANCY.CORES_C0 / UNC_P_CLOCKTICKS) * 100.",
+ "PerPkg": "1",
+ "Unit": "PCU"
+ },
+ {
+ "BriefDescription": "This is an occupancy event that tracks the number of cores that are in C3. It can be used by itself to get the average number of cores in C0, with threshholding to generate histograms, or with other PCU events and occupancy triggering to capture other details. Derived from unc_p_power_state_occupancy.cores_c3",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x80",
+ "EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C3",
+ "Filter": "occ_sel=2",
+ "MetricExpr": "(UNC_P_POWER_STATE_OCCUPANCY.CORES_C3 / UNC_P_CLOCKTICKS) * 100.",
+ "PerPkg": "1",
+ "Unit": "PCU"
+ },
+ {
+ "BriefDescription": "This is an occupancy event that tracks the number of cores that are in C6. It can be used by itself to get the average number of cores in C0, with threshholding to generate histograms, or with other PCU events . Derived from unc_p_power_state_occupancy.cores_c6",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x80",
+ "EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C6",
+ "Filter": "occ_sel=3",
+ "MetricExpr": "(UNC_P_POWER_STATE_OCCUPANCY.CORES_C6 / UNC_P_CLOCKTICKS) * 100.",
+ "PerPkg": "1",
+ "Unit": "PCU"
+ },
+ {
+ "BriefDescription": "Counts the number of cycles that we are in external PROCHOT mode. This mode is triggered when a sensor off the die determines that something off-die (like DRAM) is too hot and must throttle to avoid damaging the chip. Derived from unc_p_prochot_external_cycles",
+ "Counter": "0,1,2,3",
+ "EventCode": "0xa",
+ "EventName": "UNC_P_PROCHOT_EXTERNAL_CYCLES",
+ "MetricExpr": "(UNC_P_PROCHOT_EXTERNAL_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+ "PerPkg": "1",
+ "Unit": "PCU"
+ },
+ {
+ "BriefDescription": "Counts the number of cycles when temperature is the upper limit on frequency. Derived from unc_p_freq_max_limit_thermal_cycles",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x4",
+ "EventName": "UNC_P_FREQ_MAX_LIMIT_THERMAL_CYCLES",
+ "MetricExpr": "(UNC_P_FREQ_MAX_LIMIT_THERMAL_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+ "PerPkg": "1",
+ "Unit": "PCU"
+ },
+ {
+ "BriefDescription": "Counts the number of cycles when the OS is the upper limit on frequency. Derived from unc_p_freq_max_os_cycles",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x6",
+ "EventName": "UNC_P_FREQ_MAX_OS_CYCLES",
+ "MetricExpr": "(UNC_P_FREQ_MAX_OS_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+ "PerPkg": "1",
+ "Unit": "PCU"
+ },
+ {
+ "BriefDescription": "Counts the number of cycles when power is the upper limit on frequency. Derived from unc_p_freq_max_power_cycles",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x5",
+ "EventName": "UNC_P_FREQ_MAX_POWER_CYCLES",
+ "MetricExpr": "(UNC_P_FREQ_MAX_POWER_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+ "PerPkg": "1",
+ "Unit": "PCU"
+ },
+ {
+ "BriefDescription": "Counts the number of cycles when current is the upper limit on frequency. Derived from unc_p_freq_max_current_cycles",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x7",
+ "EventName": "UNC_P_FREQ_MAX_CURRENT_CYCLES",
+ "MetricExpr": "(UNC_P_FREQ_MAX_CURRENT_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+ "PerPkg": "1",
+ "Unit": "PCU"
+ },
+ {
+ "BriefDescription": "Cycles spent changing Frequency. Derived from unc_p_freq_trans_cycles",
+ "Counter": "0,1,2,3",
+ "EventName": "UNC_P_FREQ_TRANS_CYCLES",
+ "MetricExpr": "(UNC_P_FREQ_TRANS_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+ "PerPkg": "1",
+ "Unit": "PCU"
+ },
+ {
+ "BriefDescription": "Counts the number of cycles that the uncore was running at a frequency greater than or equal to 1.2Ghz. Derived from unc_p_freq_band0_cycles",
+ "Counter": "0,1,2,3",
+ "EventCode": "0xb",
+ "EventName": "UNC_P_FREQ_GE_1200MHZ_CYCLES",
+ "Filter": "filter_band0=1200",
+ "MetricExpr": "(UNC_P_FREQ_GE_1200MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+ "PerPkg": "1",
+ "Unit": "PCU"
+ },
+ {
+ "BriefDescription": "Counts the number of cycles that the uncore was running at a frequency greater than or equal to 2Ghz. Derived from unc_p_freq_band1_cycles",
+ "Counter": "0,1,2,3",
+ "EventCode": "0xc",
+ "EventName": "UNC_P_FREQ_GE_2000MHZ_CYCLES",
+ "Filter": "filter_band1=2000",
+ "MetricExpr": "(UNC_P_FREQ_GE_2000MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+ "PerPkg": "1",
+ "Unit": "PCU"
+ },
+ {
+ "BriefDescription": "Counts the number of cycles that the uncore was running at a frequency greater than or equal to 3Ghz. Derived from unc_p_freq_band2_cycles",
+ "Counter": "0,1,2,3",
+ "EventCode": "0xd",
+ "EventName": "UNC_P_FREQ_GE_3000MHZ_CYCLES",
+ "Filter": "filter_band2=3000",
+ "MetricExpr": "(UNC_P_FREQ_GE_3000MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+ "PerPkg": "1",
+ "Unit": "PCU"
+ },
+ {
+ "BriefDescription": "Counts the number of cycles that the uncore was running at a frequency greater than or equal to 4Ghz. Derived from unc_p_freq_band3_cycles",
+ "Counter": "0,1,2,3",
+ "EventCode": "0xe",
+ "EventName": "UNC_P_FREQ_GE_4000MHZ_CYCLES",
+ "Filter": "filter_band3=4000",
+ "MetricExpr": "(UNC_P_FREQ_GE_4000MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+ "PerPkg": "1",
+ "Unit": "PCU"
+ },
+ {
+ "BriefDescription": "Counts the number of times that the uncore transitioned to a frequency greater than or equal to 1.2Ghz. Derived from unc_p_freq_band0_cycles",
+ "Counter": "0,1,2,3",
+ "EventCode": "0xb",
+ "EventName": "UNC_P_FREQ_GE_1200MHZ_TRANSITIONS",
+ "Filter": "edge=1,filter_band0=1200",
+ "MetricExpr": "(UNC_P_FREQ_GE_1200MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+ "PerPkg": "1",
+ "Unit": "PCU"
+ },
+ {
+ "BriefDescription": "Counts the number of times that the uncore transitioned to a frequency greater than or equal to 2Ghz. Derived from unc_p_freq_band1_cycles",
+ "Counter": "0,1,2,3",
+ "EventCode": "0xc",
+ "EventName": "UNC_P_FREQ_GE_2000MHZ_TRANSITIONS",
+ "Filter": "edge=1,filter_band1=2000",
+ "MetricExpr": "(UNC_P_FREQ_GE_2000MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+ "PerPkg": "1",
+ "Unit": "PCU"
+ },
+ {
+ "BriefDescription": "Counts the number of cycles that the uncore transitioned to a frequency greater than or equal to 3Ghz. Derived from unc_p_freq_band2_cycles",
+ "Counter": "0,1,2,3",
+ "EventCode": "0xd",
+ "EventName": "UNC_P_FREQ_GE_3000MHZ_TRANSITIONS",
+ "Filter": "edge=1,filter_band2=4000",
+ "MetricExpr": "(UNC_P_FREQ_GE_3000MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+ "PerPkg": "1",
+ "Unit": "PCU"
+ },
+ {
+ "BriefDescription": "Counts the number of cycles that the uncore transitioned to a frequency greater than or equal to 4Ghz. Derived from unc_p_freq_band3_cycles",
+ "Counter": "0,1,2,3",
+ "EventCode": "0xe",
+ "EventName": "UNC_P_FREQ_GE_4000MHZ_TRANSITIONS",
+ "Filter": "edge=1,filter_band3=4000",
+ "MetricExpr": "(UNC_P_FREQ_GE_4000MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+ "PerPkg": "1",
+ "Unit": "PCU"
+ }
+]
--
2.9.3
[toc] | [prev] | [next] | [standalone]
| From | Arnaldo Carvalho de Melo <acme@kernel.org> |
|---|---|
| Date | 2017-02-10 03:50 +0100 |
| Subject | [PATCH 11/32] perf tools: Only increase index if perf_evsel__new_idx() succeeds |
| Message-ID | <t99rz-5V8-13@gated-at.bofh.it> |
| In reply to | #1578103 |
From: Taeung Song <treeze.taeung@gmail.com> Signed-off-by: Taeung Song <treeze.taeung@gmail.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Wang Nan <wangnan0@huawei.com> Link: http://lkml.kernel.org/r/1485952447-7013-2-git-send-email-treeze.taeung@gmail.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> --- tools/perf/util/parse-events.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c index 6dbcba7f0969..2720600b13a9 100644 --- a/tools/perf/util/parse-events.c +++ b/tools/perf/util/parse-events.c @@ -310,10 +310,11 @@ __add_event(struct list_head *list, int *idx, event_attr_init(attr); - evsel = perf_evsel__new_idx(attr, (*idx)++); + evsel = perf_evsel__new_idx(attr, *idx); if (!evsel) return NULL; + (*idx)++; evsel->cpus = cpu_map__get(cpus); evsel->own_cpus = cpu_map__get(cpus); -- 2.9.3
[toc] | [prev] | [next] | [standalone]
| From | Arnaldo Carvalho de Melo <acme@kernel.org> |
|---|---|
| Date | 2017-02-10 03:50 +0100 |
| Subject | [PATCH 12/32] perf tools: Add missing check for failure in a zalloc() call |
| Message-ID | <t99rA-5V8-17@gated-at.bofh.it> |
| In reply to | #1578103 |
From: Taeung Song <treeze.taeung@gmail.com>
Signed-off-by: Taeung Song <treeze.taeung@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lkml.kernel.org/r/1485952447-7013-3-git-send-email-treeze.taeung@gmail.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/perf/util/parse-events.c | 2 ++
1 file changed, 2 insertions(+)
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index 2720600b13a9..1f1f77d8d3ab 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -211,6 +211,8 @@ struct tracepoint_path *tracepoint_id_to_path(u64 config)
closedir(evt_dir);
closedir(sys_dir);
path = zalloc(sizeof(*path));
+ if (!path)
+ return NULL;
path->system = malloc(MAX_EVENT_LENGTH);
if (!path->system) {
free(path);
--
2.9.3
[toc] | [prev] | [next] | [standalone]
| From | Arnaldo Carvalho de Melo <acme@kernel.org> |
|---|---|
| Date | 2017-02-10 03:50 +0100 |
| Subject | [PATCH 13/32] perf tools: Use zfree() instead of ad hoc equivalent |
| Message-ID | <t99rA-5V8-27@gated-at.bofh.it> |
| In reply to | #1578103 |
From: Taeung Song <treeze.taeung@gmail.com>
We have zfree(&ptr) for this very common pattern:
free(ptr);
ptr = NULL;
So use it in a few more places.
Signed-off-by: Taeung Song <treeze.taeung@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lkml.kernel.org/r/1485952447-7013-4-git-send-email-treeze.taeung@gmail.com
[ rewrote commit log ]
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/perf/util/parse-events.c | 6 ++----
1 file changed, 2 insertions(+), 4 deletions(-)
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index 1f1f77d8d3ab..ab1ba22d879a 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -254,8 +254,7 @@ struct tracepoint_path *tracepoint_name_to_path(const char *name)
if (path->system == NULL || path->name == NULL) {
zfree(&path->system);
zfree(&path->name);
- free(path);
- path = NULL;
+ zfree(&path);
}
return path;
@@ -1482,8 +1481,7 @@ static void perf_pmu__parse_cleanup(void)
p = perf_pmu_events_list + i;
free(p->symbol);
}
- free(perf_pmu_events_list);
- perf_pmu_events_list = NULL;
+ zfree(&perf_pmu_events_list);
perf_pmu_events_list_num = 0;
}
}
--
2.9.3
[toc] | [prev] | [next] | [standalone]
| From | Arnaldo Carvalho de Melo <acme@kernel.org> |
|---|---|
| Date | 2017-02-10 03:50 +0100 |
| Subject | [PATCH 14/32] perf tools: Use zfree() to avoid keeping dangling pointers |
| Message-ID | <t99rz-5V8-15@gated-at.bofh.it> |
| In reply to | #1578103 |
From: Taeung Song <treeze.taeung@gmail.com>
The cases changed in this patch are for when we free but keep the
pointer to the freed area, which is not always a good idea.
Be more defensive and zero the pointer to avoid possible use after
free bugs to take more time to be detected.
Signed-off-by: Taeung Song <treeze.taeung@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lkml.kernel.org/r/1485952447-7013-5-git-send-email-treeze.taeung@gmail.com
[ rewrote commit log ]
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/perf/util/parse-events.c | 12 ++++++------
1 file changed, 6 insertions(+), 6 deletions(-)
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index ab1ba22d879a..07be0762e53e 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -1479,7 +1479,7 @@ static void perf_pmu__parse_cleanup(void)
for (i = 0; i < perf_pmu_events_list_num; i++) {
p = perf_pmu_events_list + i;
- free(p->symbol);
+ zfree(&p->symbol);
}
zfree(&perf_pmu_events_list);
perf_pmu_events_list_num = 0;
@@ -1570,7 +1570,7 @@ perf_pmu__parse_check(const char *name)
r = bsearch(&p, perf_pmu_events_list,
(size_t) perf_pmu_events_list_num,
sizeof(struct perf_pmu_event_symbol), comp_pmu);
- free(p.symbol);
+ zfree(&p.symbol);
return r ? r->type : PMU_EVENT_SYMBOL_ERR;
}
@@ -1717,8 +1717,8 @@ static void parse_events_print_error(struct parse_events_error *err,
fprintf(stderr, "%*s\\___ %s\n", idx + 1, "", err->str);
if (err->help)
fprintf(stderr, "\n%s\n", err->help);
- free(err->str);
- free(err->help);
+ zfree(&err->str);
+ zfree(&err->help);
}
fprintf(stderr, "Run 'perf list' for a list of valid events\n");
@@ -2413,7 +2413,7 @@ void parse_events_terms__purge(struct list_head *terms)
list_for_each_entry_safe(term, h, terms, list) {
if (term->array.nr_ranges)
- free(term->array.ranges);
+ zfree(&term->array.ranges);
list_del_init(&term->list);
free(term);
}
@@ -2429,7 +2429,7 @@ void parse_events_terms__delete(struct list_head *terms)
void parse_events__clear_array(struct parse_events_array *a)
{
- free(a->ranges);
+ zfree(&a->ranges);
}
void parse_events_evlist_error(struct parse_events_evlist *data,
--
2.9.3
[toc] | [prev] | [next] | [standalone]
| From | Arnaldo Carvalho de Melo <acme@kernel.org> |
|---|---|
| Date | 2017-02-10 03:50 +0100 |
| Subject | [PATCH 02/32] perf bpf: Add missing newline in debug messages |
| Message-ID | <t99rA-5V8-21@gated-at.bofh.it> |
| In reply to | #1578103 |
From: He Kuang <hekuang@huawei.com>
These two debug messages are missing the trailing newline.
Signed-off-by: He Kuang <hekuang@huawei.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Bintian Wang <bintian.wang@huawei.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Wang Nan <wangnan0@huawei.com>
Cc: Will Deacon <will.deacon@arm.com>
Cc: linux-arm-kernel@lists.infradead.org
Link: http://lkml.kernel.org/r/20170207073412.26983-2-hekuang@huawei.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/perf/util/bpf-loader.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/tools/perf/util/bpf-loader.c b/tools/perf/util/bpf-loader.c
index 36c861103291..bc6bc7062eb4 100644
--- a/tools/perf/util/bpf-loader.c
+++ b/tools/perf/util/bpf-loader.c
@@ -670,13 +670,13 @@ int bpf__probe(struct bpf_object *obj)
err = convert_perf_probe_events(pev, 1);
if (err < 0) {
- pr_debug("bpf_probe: failed to convert perf probe events");
+ pr_debug("bpf_probe: failed to convert perf probe events\n");
goto out;
}
err = apply_perf_probe_events(pev, 1);
if (err < 0) {
- pr_debug("bpf_probe: failed to apply perf probe events");
+ pr_debug("bpf_probe: failed to apply perf probe events\n");
goto out;
}
--
2.9.3
[toc] | [prev] | [next] | [standalone]
| From | Arnaldo Carvalho de Melo <acme@kernel.org> |
|---|---|
| Date | 2017-02-10 03:50 +0100 |
| Subject | [PATCH 22/32] perf vendor events intel: Add uncore events for Broadwell DE |
| Message-ID | <t99rA-5V8-25@gated-at.bofh.it> |
| In reply to | #1578103 |
From: Andi Kleen <ak@linux.intel.com>
This is not a full uncore event list, but a short list of useful
and understandable metrics.
Signed-off-by: Andi Kleen <ak@linux.intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Link: http://lkml.kernel.org/n/tip-c0cix4eprbldfrx5zf60suvh@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
.../arch/x86/broadwellde/uncore-cache.json | 317 +++++++++++++++++++++
.../arch/x86/broadwellde/uncore-memory.json | 83 ++++++
.../arch/x86/broadwellde/uncore-power.json | 84 ++++++
3 files changed, 484 insertions(+)
create mode 100644 tools/perf/pmu-events/arch/x86/broadwellde/uncore-cache.json
create mode 100644 tools/perf/pmu-events/arch/x86/broadwellde/uncore-memory.json
create mode 100644 tools/perf/pmu-events/arch/x86/broadwellde/uncore-power.json
diff --git a/tools/perf/pmu-events/arch/x86/broadwellde/uncore-cache.json b/tools/perf/pmu-events/arch/x86/broadwellde/uncore-cache.json
new file mode 100644
index 000000000000..076459c51d4e
--- /dev/null
+++ b/tools/perf/pmu-events/arch/x86/broadwellde/uncore-cache.json
@@ -0,0 +1,317 @@
+[
+ {
+ "BriefDescription": "Uncore cache clock ticks. Derived from unc_c_clockticks",
+ "Counter": "0,1,2,3",
+ "EventName": "UNC_C_CLOCKTICKS",
+ "PerPkg": "1",
+ "Unit": "CBO"
+ },
+ {
+ "BriefDescription": "All LLC Misses (code+ data rd + data wr - including demand and prefetch). Derived from unc_c_llc_lookup.any",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x34",
+ "EventName": "UNC_C_LLC_LOOKUP.ANY",
+ "Filter": "filter_state=0x1",
+ "PerPkg": "1",
+ "ScaleUnit": "64Bytes",
+ "UMask": "0x11",
+ "Unit": "CBO"
+ },
+ {
+ "BriefDescription": "M line evictions from LLC (writebacks to memory). Derived from unc_c_llc_victims.m_state",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x37",
+ "EventName": "UNC_C_LLC_VICTIMS.M_STATE",
+ "PerPkg": "1",
+ "ScaleUnit": "64Bytes",
+ "UMask": "0x1",
+ "Unit": "CBO"
+ },
+ {
+ "BriefDescription": "LLC misses - demand and prefetch data reads - excludes LLC prefetches. Derived from unc_c_tor_inserts.miss_opcode",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x35",
+ "EventName": "LLC_MISSES.DATA_READ",
+ "Filter": "filter_opc=0x182",
+ "PerPkg": "1",
+ "ScaleUnit": "64Bytes",
+ "UMask": "0x3",
+ "Unit": "CBO"
+ },
+ {
+ "BriefDescription": "LLC misses - Uncacheable reads (from cpu) . Derived from unc_c_tor_inserts.miss_opcode",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x35",
+ "EventName": "LLC_MISSES.UNCACHEABLE",
+ "Filter": "filter_opc=0x187",
+ "PerPkg": "1",
+ "ScaleUnit": "64Bytes",
+ "UMask": "0x3",
+ "Unit": "CBO"
+ },
+ {
+ "BriefDescription": "MMIO reads. Derived from unc_c_tor_inserts.miss_opcode",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x35",
+ "EventName": "LLC_MISSES.MMIO_READ",
+ "Filter": "filter_opc=0x187,filter_nc=1",
+ "PerPkg": "1",
+ "ScaleUnit": "64Bytes",
+ "UMask": "0x3",
+ "Unit": "CBO"
+ },
+ {
+ "BriefDescription": "MMIO writes. Derived from unc_c_tor_inserts.miss_opcode",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x35",
+ "EventName": "LLC_MISSES.MMIO_WRITE",
+ "Filter": "filter_opc=0x18f,filter_nc=1",
+ "PerPkg": "1",
+ "ScaleUnit": "64Bytes",
+ "UMask": "0x3",
+ "Unit": "CBO"
+ },
+ {
+ "BriefDescription": "LLC prefetch misses for RFO. Derived from unc_c_tor_inserts.miss_opcode",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x35",
+ "EventName": "LLC_MISSES.RFO_LLC_PREFETCH",
+ "Filter": "filter_opc=0x190",
+ "PerPkg": "1",
+ "ScaleUnit": "64Bytes",
+ "UMask": "0x3",
+ "Unit": "CBO"
+ },
+ {
+ "BriefDescription": "LLC prefetch misses for code reads. Derived from unc_c_tor_inserts.miss_opcode",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x35",
+ "EventName": "LLC_MISSES.CODE_LLC_PREFETCH",
+ "Filter": "filter_opc=0x191",
+ "PerPkg": "1",
+ "ScaleUnit": "64Bytes",
+ "UMask": "0x3",
+ "Unit": "CBO"
+ },
+ {
+ "BriefDescription": "LLC prefetch misses for data reads. Derived from unc_c_tor_inserts.miss_opcode",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x35",
+ "EventName": "LLC_MISSES.DATA_LLC_PREFETCH",
+ "Filter": "filter_opc=0x192",
+ "PerPkg": "1",
+ "ScaleUnit": "64Bytes",
+ "UMask": "0x3",
+ "Unit": "CBO"
+ },
+ {
+ "BriefDescription": "LLC misses for PCIe read current. Derived from unc_c_tor_inserts.miss_opcode",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x35",
+ "EventName": "LLC_MISSES.PCIE_READ",
+ "Filter": "filter_opc=0x19e",
+ "PerPkg": "1",
+ "ScaleUnit": "64Bytes",
+ "UMask": "0x3",
+ "Unit": "CBO"
+ },
+ {
+ "BriefDescription": "ItoM write misses (as part of fast string memcpy stores) + PCIe full line writes. Derived from unc_c_tor_inserts.miss_opcode",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x35",
+ "EventName": "LLC_MISSES.PCIE_WRITE",
+ "Filter": "filter_opc=0x1c8",
+ "PerPkg": "1",
+ "ScaleUnit": "64Bytes",
+ "UMask": "0x3",
+ "Unit": "CBO"
+ },
+ {
+ "BriefDescription": "PCIe write misses (full cache line). Derived from unc_c_tor_inserts.miss_opcode",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x35",
+ "EventName": "LLC_MISSES.PCIE_NON_SNOOP_WRITE",
+ "Filter": "filter_opc=0x1c8,filter_tid=0x3e",
+ "PerPkg": "1",
+ "ScaleUnit": "64Bytes",
+ "UMask": "0x3",
+ "Unit": "CBO"
+ },
+ {
+ "BriefDescription": "PCIe writes (partial cache line). Derived from unc_c_tor_inserts.opcode",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x35",
+ "EventName": "LLC_REFERENCES.PCIE_NS_PARTIAL_WRITE",
+ "Filter": "filter_opc=0x180,filter_tid=0x3e",
+ "PerPkg": "1",
+ "UMask": "0x1",
+ "Unit": "CBO"
+ },
+ {
+ "BriefDescription": "L2 demand and L2 prefetch code references to LLC. Derived from unc_c_tor_inserts.opcode",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x35",
+ "EventName": "LLC_REFERENCES.CODE_LLC_PREFETCH",
+ "Filter": "filter_opc=0x181",
+ "PerPkg": "1",
+ "ScaleUnit": "64Bytes",
+ "UMask": "0x1",
+ "Unit": "CBO"
+ },
+ {
+ "BriefDescription": "Streaming stores (full cache line). Derived from unc_c_tor_inserts.opcode",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x35",
+ "EventName": "LLC_REFERENCES.STREAMING_FULL",
+ "Filter": "filter_opc=0x18c",
+ "PerPkg": "1",
+ "ScaleUnit": "64Bytes",
+ "UMask": "0x1",
+ "Unit": "CBO"
+ },
+ {
+ "BriefDescription": "Streaming stores (partial cache line). Derived from unc_c_tor_inserts.opcode",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x35",
+ "EventName": "LLC_REFERENCES.STREAMING_PARTIAL",
+ "Filter": "filter_opc=0x18d",
+ "PerPkg": "1",
+ "ScaleUnit": "64Bytes",
+ "UMask": "0x1",
+ "Unit": "CBO"
+ },
+ {
+ "BriefDescription": "PCIe read current. Derived from unc_c_tor_inserts.opcode",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x35",
+ "EventName": "LLC_REFERENCES.PCIE_READ",
+ "Filter": "filter_opc=0x19e",
+ "PerPkg": "1",
+ "ScaleUnit": "64Bytes",
+ "UMask": "0x1",
+ "Unit": "CBO"
+ },
+ {
+ "BriefDescription": "PCIe write references (full cache line). Derived from unc_c_tor_inserts.opcode",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x35",
+ "EventName": "LLC_REFERENCES.PCIE_WRITE",
+ "Filter": "filter_opc=0x1c8,filter_tid=0x3e",
+ "PerPkg": "1",
+ "ScaleUnit": "64Bytes",
+ "UMask": "0x1",
+ "Unit": "CBO"
+ },
+ {
+ "BriefDescription": "Occupancy counter for LLC data reads (demand and L2 prefetch). Derived from unc_c_tor_occupancy.miss_opcode",
+ "EventCode": "0x36",
+ "EventName": "UNC_C_TOR_OCCUPANCY.LLC_DATA_READ",
+ "Filter": "filter_opc=0x182",
+ "PerPkg": "1",
+ "UMask": "0x3",
+ "Unit": "CBO"
+ },
+ {
+ "BriefDescription": "read requests to home agent. Derived from unc_h_requests.reads",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x1",
+ "EventName": "UNC_H_REQUESTS.READS",
+ "PerPkg": "1",
+ "UMask": "0x3",
+ "Unit": "HA"
+ },
+ {
+ "BriefDescription": "read requests to local home agent. Derived from unc_h_requests.reads_local",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x1",
+ "EventName": "UNC_H_REQUESTS.READS_LOCAL",
+ "PerPkg": "1",
+ "UMask": "0x1",
+ "Unit": "HA"
+ },
+ {
+ "BriefDescription": "read requests to remote home agent. Derived from unc_h_requests.reads_remote",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x1",
+ "EventName": "UNC_H_REQUESTS.READS_REMOTE",
+ "PerPkg": "1",
+ "UMask": "0x2",
+ "Unit": "HA"
+ },
+ {
+ "BriefDescription": "write requests to home agent. Derived from unc_h_requests.writes",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x1",
+ "EventName": "UNC_H_REQUESTS.WRITES",
+ "PerPkg": "1",
+ "UMask": "0xC",
+ "Unit": "HA"
+ },
+ {
+ "BriefDescription": "write requests to local home agent. Derived from unc_h_requests.writes_local",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x1",
+ "EventName": "UNC_H_REQUESTS.WRITES_LOCAL",
+ "PerPkg": "1",
+ "UMask": "0x4",
+ "Unit": "HA"
+ },
+ {
+ "BriefDescription": "write requests to remote home agent. Derived from unc_h_requests.writes_remote",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x1",
+ "EventName": "UNC_H_REQUESTS.WRITES_REMOTE",
+ "PerPkg": "1",
+ "UMask": "0x8",
+ "Unit": "HA"
+ },
+ {
+ "BriefDescription": "Conflict requests (requests for same address from multiple agents simultaneously). Derived from unc_h_snoop_resp.rspcnflct",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x21",
+ "EventName": "UNC_H_SNOOP_RESP.RSPCNFLCT",
+ "PerPkg": "1",
+ "UMask": "0x40",
+ "Unit": "HA"
+ },
+ {
+ "BriefDescription": "M line forwarded from remote cache along with writeback to memory. Derived from unc_h_snoop_resp.rsp_fwd_wb",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x21",
+ "EventName": "UNC_H_SNOOP_RESP.RSP_FWD_WB",
+ "PerPkg": "1",
+ "ScaleUnit": "64Bytes",
+ "UMask": "0x20",
+ "Unit": "HA"
+ },
+ {
+ "BriefDescription": "M line forwarded from remote cache with no writeback to memory. Derived from unc_h_snoop_resp.rspifwd",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x21",
+ "EventName": "UNC_H_SNOOP_RESP.RSPIFWD",
+ "PerPkg": "1",
+ "ScaleUnit": "64Bytes",
+ "UMask": "0x4",
+ "Unit": "HA"
+ },
+ {
+ "BriefDescription": "Shared line response from remote cache. Derived from unc_h_snoop_resp.rsps",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x21",
+ "EventName": "UNC_H_SNOOP_RESP.RSPS",
+ "PerPkg": "1",
+ "ScaleUnit": "64Bytes",
+ "UMask": "0x2",
+ "Unit": "HA"
+ },
+ {
+ "BriefDescription": "Shared line forwarded from remote cache. Derived from unc_h_snoop_resp.rspsfwd",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x21",
+ "EventName": "UNC_H_SNOOP_RESP.RSPSFWD",
+ "PerPkg": "1",
+ "ScaleUnit": "64Bytes",
+ "UMask": "0x8",
+ "Unit": "HA"
+ }
+]
diff --git a/tools/perf/pmu-events/arch/x86/broadwellde/uncore-memory.json b/tools/perf/pmu-events/arch/x86/broadwellde/uncore-memory.json
new file mode 100644
index 000000000000..d17dc235f734
--- /dev/null
+++ b/tools/perf/pmu-events/arch/x86/broadwellde/uncore-memory.json
@@ -0,0 +1,83 @@
+[
+ {
+ "BriefDescription": "read requests to memory controller. Derived from unc_m_cas_count.rd",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x4",
+ "EventName": "UNC_M_CAS_COUNT.RD",
+ "PerPkg": "1",
+ "ScaleUnit": "64Bytes",
+ "UMask": "0x3",
+ "Unit": "iMC"
+ },
+ {
+ "BriefDescription": "write requests to memory controller. Derived from unc_m_cas_count.wr",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x4",
+ "EventName": "UNC_M_CAS_COUNT.WR",
+ "PerPkg": "1",
+ "ScaleUnit": "64Bytes",
+ "UMask": "0xC",
+ "Unit": "iMC"
+ },
+ {
+ "BriefDescription": "Memory controller clock ticks. Derived from unc_m_clockticks",
+ "Counter": "0,1,2,3",
+ "EventName": "UNC_M_CLOCKTICKS",
+ "PerPkg": "1",
+ "Unit": "iMC"
+ },
+ {
+ "BriefDescription": "Cycles where DRAM ranks are in power down (CKE) mode. Derived from unc_m_power_channel_ppd",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x85",
+ "EventName": "UNC_M_POWER_CHANNEL_PPD",
+ "MetricExpr": "(UNC_M_POWER_CHANNEL_PPD / UNC_M_CLOCKTICKS) * 100.",
+ "PerPkg": "1",
+ "Unit": "iMC"
+ },
+ {
+ "BriefDescription": "Cycles all ranks are in critical thermal throttle. Derived from unc_m_power_critical_throttle_cycles",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x86",
+ "EventName": "UNC_M_POWER_CRITICAL_THROTTLE_CYCLES",
+ "MetricExpr": "(UNC_M_POWER_CRITICAL_THROTTLE_CYCLES / UNC_M_CLOCKTICKS) * 100.",
+ "PerPkg": "1",
+ "Unit": "iMC"
+ },
+ {
+ "BriefDescription": "Cycles Memory is in self refresh power mode. Derived from unc_m_power_self_refresh",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x43",
+ "EventName": "UNC_M_POWER_SELF_REFRESH",
+ "MetricExpr": "(UNC_M_POWER_SELF_REFRESH / UNC_M_CLOCKTICKS) * 100.",
+ "PerPkg": "1",
+ "Unit": "iMC"
+ },
+ {
+ "BriefDescription": "Pre-charges due to page misses. Derived from unc_m_pre_count.page_miss",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x2",
+ "EventName": "UNC_M_PRE_COUNT.PAGE_MISS",
+ "PerPkg": "1",
+ "UMask": "0x1",
+ "Unit": "iMC"
+ },
+ {
+ "BriefDescription": "Pre-charge for reads. Derived from unc_m_pre_count.rd",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x2",
+ "EventName": "UNC_M_PRE_COUNT.RD",
+ "PerPkg": "1",
+ "UMask": "0x4",
+ "Unit": "iMC"
+ },
+ {
+ "BriefDescription": "Pre-charge for writes. Derived from unc_m_pre_count.wr",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x2",
+ "EventName": "UNC_M_PRE_COUNT.WR",
+ "PerPkg": "1",
+ "UMask": "0x8",
+ "Unit": "iMC"
+ }
+]
diff --git a/tools/perf/pmu-events/arch/x86/broadwellde/uncore-power.json b/tools/perf/pmu-events/arch/x86/broadwellde/uncore-power.json
new file mode 100644
index 000000000000..b44d43088bbb
--- /dev/null
+++ b/tools/perf/pmu-events/arch/x86/broadwellde/uncore-power.json
@@ -0,0 +1,84 @@
+[
+ {
+ "BriefDescription": "PCU clock ticks. Use to get percentages of PCU cycles events. Derived from unc_p_clockticks",
+ "Counter": "0,1,2,3",
+ "EventName": "UNC_P_CLOCKTICKS",
+ "PerPkg": "1",
+ "Unit": "PCU"
+ },
+ {
+ "BriefDescription": "C0 and C1. Derived from unc_p_power_state_occupancy.cores_c0",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x80",
+ "EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C0",
+ "Filter": "occ_sel=1",
+ "MetricExpr": "(UNC_P_POWER_STATE_OCCUPANCY.CORES_C0 / UNC_P_CLOCKTICKS) * 100.",
+ "PerPkg": "1",
+ "Unit": "PCU"
+ },
+ {
+ "BriefDescription": "C3. Derived from unc_p_power_state_occupancy.cores_c3",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x80",
+ "EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C3",
+ "Filter": "occ_sel=2",
+ "MetricExpr": "(UNC_P_POWER_STATE_OCCUPANCY.CORES_C3 / UNC_P_CLOCKTICKS) * 100.",
+ "PerPkg": "1",
+ "Unit": "PCU"
+ },
+ {
+ "BriefDescription": "C6 and C7. Derived from unc_p_power_state_occupancy.cores_c6",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x80",
+ "EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C6",
+ "Filter": "occ_sel=3",
+ "MetricExpr": "(UNC_P_POWER_STATE_OCCUPANCY.CORES_C6 / UNC_P_CLOCKTICKS) * 100.",
+ "PerPkg": "1",
+ "Unit": "PCU"
+ },
+ {
+ "BriefDescription": "External Prochot. Derived from unc_p_prochot_external_cycles",
+ "Counter": "0,1,2,3",
+ "EventCode": "0xA",
+ "EventName": "UNC_P_PROCHOT_EXTERNAL_CYCLES",
+ "MetricExpr": "(UNC_P_PROCHOT_EXTERNAL_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+ "PerPkg": "1",
+ "Unit": "PCU"
+ },
+ {
+ "BriefDescription": "Thermal Strongest Upper Limit Cycles. Derived from unc_p_freq_max_limit_thermal_cycles",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x4",
+ "EventName": "UNC_P_FREQ_MAX_LIMIT_THERMAL_CYCLES",
+ "MetricExpr": "(UNC_P_FREQ_MAX_LIMIT_THERMAL_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+ "PerPkg": "1",
+ "Unit": "PCU"
+ },
+ {
+ "BriefDescription": "OS Strongest Upper Limit Cycles. Derived from unc_p_freq_max_os_cycles",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x6",
+ "EventName": "UNC_P_FREQ_MAX_OS_CYCLES",
+ "MetricExpr": "(UNC_P_FREQ_MAX_OS_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+ "PerPkg": "1",
+ "Unit": "PCU"
+ },
+ {
+ "BriefDescription": "Power Strongest Upper Limit Cycles. Derived from unc_p_freq_max_power_cycles",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x5",
+ "EventName": "UNC_P_FREQ_MAX_POWER_CYCLES",
+ "MetricExpr": "(UNC_P_FREQ_MAX_POWER_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+ "PerPkg": "1",
+ "Unit": "PCU"
+ },
+ {
+ "BriefDescription": "Cycles spent changing Frequency. Derived from unc_p_freq_trans_cycles",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x74",
+ "EventName": "UNC_P_FREQ_TRANS_CYCLES",
+ "MetricExpr": "(UNC_P_FREQ_TRANS_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+ "PerPkg": "1",
+ "Unit": "PCU"
+ }
+]
--
2.9.3
[toc] | [prev] | [next] | [standalone]
| From | Arnaldo Carvalho de Melo <acme@kernel.org> |
|---|---|
| Date | 2017-02-10 03:50 +0100 |
| Subject | [PATCH 29/32] perf header: Fix handling of PERF_EVENT_UPDATE__SCALE |
| Message-ID | <t99rA-5V8-29@gated-at.bofh.it> |
| In reply to | #1578103 |
From: Arnaldo Carvalho de Melo <acme@redhat.com>
In commit daeecbc0c431 ("perf tools: Add event_update event scale type"), the
handling of PERF_EVENT_UPDATE__SCALE cast struct event_update_event->data to a
pointer to event_update_event_scale, uses some field from this casted struct
and then ends up falling through to the handling of another event type,
PERF_EVENT_UPDATE__CPUS were it casts that ev->data to yet another type, oops,
fix it by inserting the missing break.
Noticed when building perf using gcc 7 on Fedora Rawhide:
util/header.c: In function 'perf_event__process_event_update':
util/header.c:3207:16: error: this statement may fall through [-Werror=implicit-fallthrough=]
evsel->scale = ev_scale->scale;
~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~
util/header.c:3208:2: note: here
case PERF_EVENT_UPDATE__CPUS:
^~~~
This wasn't noticed because probably PERF_EVENT_UPDATE__CPUS comes after
PERF_EVENT_UPDATE__SCALE, so we would just create a bogus evsel->own_cpus when
processing a PERF_EVENT_UPDATE__SCALE to then leak it and create a new cpu map
with the correct data.
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@intel.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Fixes: daeecbc0c431 ("perf tools: Add event_update event scale type")
Link: http://lkml.kernel.org/n/tip-lukcf9hdj092ax2914ss95at@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/perf/util/header.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index c567d9f0aa92..3d12c16e5103 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -3205,6 +3205,7 @@ int perf_event__process_event_update(struct perf_tool *tool __maybe_unused,
case PERF_EVENT_UPDATE__SCALE:
ev_scale = (struct event_update_event_scale *) ev->data;
evsel->scale = ev_scale->scale;
+ break;
case PERF_EVENT_UPDATE__CPUS:
ev_cpus = (struct event_update_event_cpus *) ev->data;
--
2.9.3
[toc] | [prev] | [next] | [standalone]
| From | Arnaldo Carvalho de Melo <acme@kernel.org> |
|---|---|
| Date | 2017-02-10 03:50 +0100 |
| Subject | [PATCH 18/32] perf vendor events intel: Add uncore events for Broadwell Server |
| Message-ID | <t99rz-5V8-7@gated-at.bofh.it> |
| In reply to | #1578103 |
From: Andi Kleen <ak@linux.intel.com>
This is not a full uncore event list, but a short list of useful
and understandable metrics.
Signed-off-by: Andi Kleen <ak@linux.intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Link: http://lkml.kernel.org/n/tip-c0cix4eprbldfrx5zf60suvh@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
.../arch/x86/broadwellx/uncore-cache.json | 317 +++++++++++++++++++++
.../arch/x86/broadwellx/uncore-interconnect.json | 28 ++
.../arch/x86/broadwellx/uncore-memory.json | 83 ++++++
.../arch/x86/broadwellx/uncore-power.json | 84 ++++++
4 files changed, 512 insertions(+)
create mode 100644 tools/perf/pmu-events/arch/x86/broadwellx/uncore-cache.json
create mode 100644 tools/perf/pmu-events/arch/x86/broadwellx/uncore-interconnect.json
create mode 100644 tools/perf/pmu-events/arch/x86/broadwellx/uncore-memory.json
create mode 100644 tools/perf/pmu-events/arch/x86/broadwellx/uncore-power.json
diff --git a/tools/perf/pmu-events/arch/x86/broadwellx/uncore-cache.json b/tools/perf/pmu-events/arch/x86/broadwellx/uncore-cache.json
new file mode 100644
index 000000000000..076459c51d4e
--- /dev/null
+++ b/tools/perf/pmu-events/arch/x86/broadwellx/uncore-cache.json
@@ -0,0 +1,317 @@
+[
+ {
+ "BriefDescription": "Uncore cache clock ticks. Derived from unc_c_clockticks",
+ "Counter": "0,1,2,3",
+ "EventName": "UNC_C_CLOCKTICKS",
+ "PerPkg": "1",
+ "Unit": "CBO"
+ },
+ {
+ "BriefDescription": "All LLC Misses (code+ data rd + data wr - including demand and prefetch). Derived from unc_c_llc_lookup.any",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x34",
+ "EventName": "UNC_C_LLC_LOOKUP.ANY",
+ "Filter": "filter_state=0x1",
+ "PerPkg": "1",
+ "ScaleUnit": "64Bytes",
+ "UMask": "0x11",
+ "Unit": "CBO"
+ },
+ {
+ "BriefDescription": "M line evictions from LLC (writebacks to memory). Derived from unc_c_llc_victims.m_state",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x37",
+ "EventName": "UNC_C_LLC_VICTIMS.M_STATE",
+ "PerPkg": "1",
+ "ScaleUnit": "64Bytes",
+ "UMask": "0x1",
+ "Unit": "CBO"
+ },
+ {
+ "BriefDescription": "LLC misses - demand and prefetch data reads - excludes LLC prefetches. Derived from unc_c_tor_inserts.miss_opcode",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x35",
+ "EventName": "LLC_MISSES.DATA_READ",
+ "Filter": "filter_opc=0x182",
+ "PerPkg": "1",
+ "ScaleUnit": "64Bytes",
+ "UMask": "0x3",
+ "Unit": "CBO"
+ },
+ {
+ "BriefDescription": "LLC misses - Uncacheable reads (from cpu) . Derived from unc_c_tor_inserts.miss_opcode",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x35",
+ "EventName": "LLC_MISSES.UNCACHEABLE",
+ "Filter": "filter_opc=0x187",
+ "PerPkg": "1",
+ "ScaleUnit": "64Bytes",
+ "UMask": "0x3",
+ "Unit": "CBO"
+ },
+ {
+ "BriefDescription": "MMIO reads. Derived from unc_c_tor_inserts.miss_opcode",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x35",
+ "EventName": "LLC_MISSES.MMIO_READ",
+ "Filter": "filter_opc=0x187,filter_nc=1",
+ "PerPkg": "1",
+ "ScaleUnit": "64Bytes",
+ "UMask": "0x3",
+ "Unit": "CBO"
+ },
+ {
+ "BriefDescription": "MMIO writes. Derived from unc_c_tor_inserts.miss_opcode",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x35",
+ "EventName": "LLC_MISSES.MMIO_WRITE",
+ "Filter": "filter_opc=0x18f,filter_nc=1",
+ "PerPkg": "1",
+ "ScaleUnit": "64Bytes",
+ "UMask": "0x3",
+ "Unit": "CBO"
+ },
+ {
+ "BriefDescription": "LLC prefetch misses for RFO. Derived from unc_c_tor_inserts.miss_opcode",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x35",
+ "EventName": "LLC_MISSES.RFO_LLC_PREFETCH",
+ "Filter": "filter_opc=0x190",
+ "PerPkg": "1",
+ "ScaleUnit": "64Bytes",
+ "UMask": "0x3",
+ "Unit": "CBO"
+ },
+ {
+ "BriefDescription": "LLC prefetch misses for code reads. Derived from unc_c_tor_inserts.miss_opcode",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x35",
+ "EventName": "LLC_MISSES.CODE_LLC_PREFETCH",
+ "Filter": "filter_opc=0x191",
+ "PerPkg": "1",
+ "ScaleUnit": "64Bytes",
+ "UMask": "0x3",
+ "Unit": "CBO"
+ },
+ {
+ "BriefDescription": "LLC prefetch misses for data reads. Derived from unc_c_tor_inserts.miss_opcode",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x35",
+ "EventName": "LLC_MISSES.DATA_LLC_PREFETCH",
+ "Filter": "filter_opc=0x192",
+ "PerPkg": "1",
+ "ScaleUnit": "64Bytes",
+ "UMask": "0x3",
+ "Unit": "CBO"
+ },
+ {
+ "BriefDescription": "LLC misses for PCIe read current. Derived from unc_c_tor_inserts.miss_opcode",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x35",
+ "EventName": "LLC_MISSES.PCIE_READ",
+ "Filter": "filter_opc=0x19e",
+ "PerPkg": "1",
+ "ScaleUnit": "64Bytes",
+ "UMask": "0x3",
+ "Unit": "CBO"
+ },
+ {
+ "BriefDescription": "ItoM write misses (as part of fast string memcpy stores) + PCIe full line writes. Derived from unc_c_tor_inserts.miss_opcode",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x35",
+ "EventName": "LLC_MISSES.PCIE_WRITE",
+ "Filter": "filter_opc=0x1c8",
+ "PerPkg": "1",
+ "ScaleUnit": "64Bytes",
+ "UMask": "0x3",
+ "Unit": "CBO"
+ },
+ {
+ "BriefDescription": "PCIe write misses (full cache line). Derived from unc_c_tor_inserts.miss_opcode",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x35",
+ "EventName": "LLC_MISSES.PCIE_NON_SNOOP_WRITE",
+ "Filter": "filter_opc=0x1c8,filter_tid=0x3e",
+ "PerPkg": "1",
+ "ScaleUnit": "64Bytes",
+ "UMask": "0x3",
+ "Unit": "CBO"
+ },
+ {
+ "BriefDescription": "PCIe writes (partial cache line). Derived from unc_c_tor_inserts.opcode",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x35",
+ "EventName": "LLC_REFERENCES.PCIE_NS_PARTIAL_WRITE",
+ "Filter": "filter_opc=0x180,filter_tid=0x3e",
+ "PerPkg": "1",
+ "UMask": "0x1",
+ "Unit": "CBO"
+ },
+ {
+ "BriefDescription": "L2 demand and L2 prefetch code references to LLC. Derived from unc_c_tor_inserts.opcode",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x35",
+ "EventName": "LLC_REFERENCES.CODE_LLC_PREFETCH",
+ "Filter": "filter_opc=0x181",
+ "PerPkg": "1",
+ "ScaleUnit": "64Bytes",
+ "UMask": "0x1",
+ "Unit": "CBO"
+ },
+ {
+ "BriefDescription": "Streaming stores (full cache line). Derived from unc_c_tor_inserts.opcode",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x35",
+ "EventName": "LLC_REFERENCES.STREAMING_FULL",
+ "Filter": "filter_opc=0x18c",
+ "PerPkg": "1",
+ "ScaleUnit": "64Bytes",
+ "UMask": "0x1",
+ "Unit": "CBO"
+ },
+ {
+ "BriefDescription": "Streaming stores (partial cache line). Derived from unc_c_tor_inserts.opcode",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x35",
+ "EventName": "LLC_REFERENCES.STREAMING_PARTIAL",
+ "Filter": "filter_opc=0x18d",
+ "PerPkg": "1",
+ "ScaleUnit": "64Bytes",
+ "UMask": "0x1",
+ "Unit": "CBO"
+ },
+ {
+ "BriefDescription": "PCIe read current. Derived from unc_c_tor_inserts.opcode",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x35",
+ "EventName": "LLC_REFERENCES.PCIE_READ",
+ "Filter": "filter_opc=0x19e",
+ "PerPkg": "1",
+ "ScaleUnit": "64Bytes",
+ "UMask": "0x1",
+ "Unit": "CBO"
+ },
+ {
+ "BriefDescription": "PCIe write references (full cache line). Derived from unc_c_tor_inserts.opcode",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x35",
+ "EventName": "LLC_REFERENCES.PCIE_WRITE",
+ "Filter": "filter_opc=0x1c8,filter_tid=0x3e",
+ "PerPkg": "1",
+ "ScaleUnit": "64Bytes",
+ "UMask": "0x1",
+ "Unit": "CBO"
+ },
+ {
+ "BriefDescription": "Occupancy counter for LLC data reads (demand and L2 prefetch). Derived from unc_c_tor_occupancy.miss_opcode",
+ "EventCode": "0x36",
+ "EventName": "UNC_C_TOR_OCCUPANCY.LLC_DATA_READ",
+ "Filter": "filter_opc=0x182",
+ "PerPkg": "1",
+ "UMask": "0x3",
+ "Unit": "CBO"
+ },
+ {
+ "BriefDescription": "read requests to home agent. Derived from unc_h_requests.reads",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x1",
+ "EventName": "UNC_H_REQUESTS.READS",
+ "PerPkg": "1",
+ "UMask": "0x3",
+ "Unit": "HA"
+ },
+ {
+ "BriefDescription": "read requests to local home agent. Derived from unc_h_requests.reads_local",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x1",
+ "EventName": "UNC_H_REQUESTS.READS_LOCAL",
+ "PerPkg": "1",
+ "UMask": "0x1",
+ "Unit": "HA"
+ },
+ {
+ "BriefDescription": "read requests to remote home agent. Derived from unc_h_requests.reads_remote",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x1",
+ "EventName": "UNC_H_REQUESTS.READS_REMOTE",
+ "PerPkg": "1",
+ "UMask": "0x2",
+ "Unit": "HA"
+ },
+ {
+ "BriefDescription": "write requests to home agent. Derived from unc_h_requests.writes",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x1",
+ "EventName": "UNC_H_REQUESTS.WRITES",
+ "PerPkg": "1",
+ "UMask": "0xC",
+ "Unit": "HA"
+ },
+ {
+ "BriefDescription": "write requests to local home agent. Derived from unc_h_requests.writes_local",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x1",
+ "EventName": "UNC_H_REQUESTS.WRITES_LOCAL",
+ "PerPkg": "1",
+ "UMask": "0x4",
+ "Unit": "HA"
+ },
+ {
+ "BriefDescription": "write requests to remote home agent. Derived from unc_h_requests.writes_remote",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x1",
+ "EventName": "UNC_H_REQUESTS.WRITES_REMOTE",
+ "PerPkg": "1",
+ "UMask": "0x8",
+ "Unit": "HA"
+ },
+ {
+ "BriefDescription": "Conflict requests (requests for same address from multiple agents simultaneously). Derived from unc_h_snoop_resp.rspcnflct",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x21",
+ "EventName": "UNC_H_SNOOP_RESP.RSPCNFLCT",
+ "PerPkg": "1",
+ "UMask": "0x40",
+ "Unit": "HA"
+ },
+ {
+ "BriefDescription": "M line forwarded from remote cache along with writeback to memory. Derived from unc_h_snoop_resp.rsp_fwd_wb",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x21",
+ "EventName": "UNC_H_SNOOP_RESP.RSP_FWD_WB",
+ "PerPkg": "1",
+ "ScaleUnit": "64Bytes",
+ "UMask": "0x20",
+ "Unit": "HA"
+ },
+ {
+ "BriefDescription": "M line forwarded from remote cache with no writeback to memory. Derived from unc_h_snoop_resp.rspifwd",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x21",
+ "EventName": "UNC_H_SNOOP_RESP.RSPIFWD",
+ "PerPkg": "1",
+ "ScaleUnit": "64Bytes",
+ "UMask": "0x4",
+ "Unit": "HA"
+ },
+ {
+ "BriefDescription": "Shared line response from remote cache. Derived from unc_h_snoop_resp.rsps",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x21",
+ "EventName": "UNC_H_SNOOP_RESP.RSPS",
+ "PerPkg": "1",
+ "ScaleUnit": "64Bytes",
+ "UMask": "0x2",
+ "Unit": "HA"
+ },
+ {
+ "BriefDescription": "Shared line forwarded from remote cache. Derived from unc_h_snoop_resp.rspsfwd",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x21",
+ "EventName": "UNC_H_SNOOP_RESP.RSPSFWD",
+ "PerPkg": "1",
+ "ScaleUnit": "64Bytes",
+ "UMask": "0x8",
+ "Unit": "HA"
+ }
+]
diff --git a/tools/perf/pmu-events/arch/x86/broadwellx/uncore-interconnect.json b/tools/perf/pmu-events/arch/x86/broadwellx/uncore-interconnect.json
new file mode 100644
index 000000000000..39387f7909b2
--- /dev/null
+++ b/tools/perf/pmu-events/arch/x86/broadwellx/uncore-interconnect.json
@@ -0,0 +1,28 @@
+[
+ {
+ "BriefDescription": "QPI clock ticks. Derived from unc_q_clockticks",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x14",
+ "EventName": "UNC_Q_CLOCKTICKS",
+ "PerPkg": "1",
+ "Unit": "QPI LL"
+ },
+ {
+ "BriefDescription": "Number of data flits transmitted . Derived from unc_q_txl_flits_g0.data",
+ "Counter": "0,1,2,3",
+ "EventName": "UNC_Q_TxL_FLITS_G0.DATA",
+ "PerPkg": "1",
+ "ScaleUnit": "8Bytes",
+ "UMask": "0x2",
+ "Unit": "QPI LL"
+ },
+ {
+ "BriefDescription": "Number of non data (control) flits transmitted . Derived from unc_q_txl_flits_g0.non_data",
+ "Counter": "0,1,2,3",
+ "EventName": "UNC_Q_TxL_FLITS_G0.NON_DATA",
+ "PerPkg": "1",
+ "ScaleUnit": "8Bytes",
+ "UMask": "0x4",
+ "Unit": "QPI LL"
+ }
+]
diff --git a/tools/perf/pmu-events/arch/x86/broadwellx/uncore-memory.json b/tools/perf/pmu-events/arch/x86/broadwellx/uncore-memory.json
new file mode 100644
index 000000000000..d17dc235f734
--- /dev/null
+++ b/tools/perf/pmu-events/arch/x86/broadwellx/uncore-memory.json
@@ -0,0 +1,83 @@
+[
+ {
+ "BriefDescription": "read requests to memory controller. Derived from unc_m_cas_count.rd",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x4",
+ "EventName": "UNC_M_CAS_COUNT.RD",
+ "PerPkg": "1",
+ "ScaleUnit": "64Bytes",
+ "UMask": "0x3",
+ "Unit": "iMC"
+ },
+ {
+ "BriefDescription": "write requests to memory controller. Derived from unc_m_cas_count.wr",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x4",
+ "EventName": "UNC_M_CAS_COUNT.WR",
+ "PerPkg": "1",
+ "ScaleUnit": "64Bytes",
+ "UMask": "0xC",
+ "Unit": "iMC"
+ },
+ {
+ "BriefDescription": "Memory controller clock ticks. Derived from unc_m_clockticks",
+ "Counter": "0,1,2,3",
+ "EventName": "UNC_M_CLOCKTICKS",
+ "PerPkg": "1",
+ "Unit": "iMC"
+ },
+ {
+ "BriefDescription": "Cycles where DRAM ranks are in power down (CKE) mode. Derived from unc_m_power_channel_ppd",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x85",
+ "EventName": "UNC_M_POWER_CHANNEL_PPD",
+ "MetricExpr": "(UNC_M_POWER_CHANNEL_PPD / UNC_M_CLOCKTICKS) * 100.",
+ "PerPkg": "1",
+ "Unit": "iMC"
+ },
+ {
+ "BriefDescription": "Cycles all ranks are in critical thermal throttle. Derived from unc_m_power_critical_throttle_cycles",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x86",
+ "EventName": "UNC_M_POWER_CRITICAL_THROTTLE_CYCLES",
+ "MetricExpr": "(UNC_M_POWER_CRITICAL_THROTTLE_CYCLES / UNC_M_CLOCKTICKS) * 100.",
+ "PerPkg": "1",
+ "Unit": "iMC"
+ },
+ {
+ "BriefDescription": "Cycles Memory is in self refresh power mode. Derived from unc_m_power_self_refresh",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x43",
+ "EventName": "UNC_M_POWER_SELF_REFRESH",
+ "MetricExpr": "(UNC_M_POWER_SELF_REFRESH / UNC_M_CLOCKTICKS) * 100.",
+ "PerPkg": "1",
+ "Unit": "iMC"
+ },
+ {
+ "BriefDescription": "Pre-charges due to page misses. Derived from unc_m_pre_count.page_miss",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x2",
+ "EventName": "UNC_M_PRE_COUNT.PAGE_MISS",
+ "PerPkg": "1",
+ "UMask": "0x1",
+ "Unit": "iMC"
+ },
+ {
+ "BriefDescription": "Pre-charge for reads. Derived from unc_m_pre_count.rd",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x2",
+ "EventName": "UNC_M_PRE_COUNT.RD",
+ "PerPkg": "1",
+ "UMask": "0x4",
+ "Unit": "iMC"
+ },
+ {
+ "BriefDescription": "Pre-charge for writes. Derived from unc_m_pre_count.wr",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x2",
+ "EventName": "UNC_M_PRE_COUNT.WR",
+ "PerPkg": "1",
+ "UMask": "0x8",
+ "Unit": "iMC"
+ }
+]
diff --git a/tools/perf/pmu-events/arch/x86/broadwellx/uncore-power.json b/tools/perf/pmu-events/arch/x86/broadwellx/uncore-power.json
new file mode 100644
index 000000000000..b44d43088bbb
--- /dev/null
+++ b/tools/perf/pmu-events/arch/x86/broadwellx/uncore-power.json
@@ -0,0 +1,84 @@
+[
+ {
+ "BriefDescription": "PCU clock ticks. Use to get percentages of PCU cycles events. Derived from unc_p_clockticks",
+ "Counter": "0,1,2,3",
+ "EventName": "UNC_P_CLOCKTICKS",
+ "PerPkg": "1",
+ "Unit": "PCU"
+ },
+ {
+ "BriefDescription": "C0 and C1. Derived from unc_p_power_state_occupancy.cores_c0",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x80",
+ "EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C0",
+ "Filter": "occ_sel=1",
+ "MetricExpr": "(UNC_P_POWER_STATE_OCCUPANCY.CORES_C0 / UNC_P_CLOCKTICKS) * 100.",
+ "PerPkg": "1",
+ "Unit": "PCU"
+ },
+ {
+ "BriefDescription": "C3. Derived from unc_p_power_state_occupancy.cores_c3",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x80",
+ "EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C3",
+ "Filter": "occ_sel=2",
+ "MetricExpr": "(UNC_P_POWER_STATE_OCCUPANCY.CORES_C3 / UNC_P_CLOCKTICKS) * 100.",
+ "PerPkg": "1",
+ "Unit": "PCU"
+ },
+ {
+ "BriefDescription": "C6 and C7. Derived from unc_p_power_state_occupancy.cores_c6",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x80",
+ "EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C6",
+ "Filter": "occ_sel=3",
+ "MetricExpr": "(UNC_P_POWER_STATE_OCCUPANCY.CORES_C6 / UNC_P_CLOCKTICKS) * 100.",
+ "PerPkg": "1",
+ "Unit": "PCU"
+ },
+ {
+ "BriefDescription": "External Prochot. Derived from unc_p_prochot_external_cycles",
+ "Counter": "0,1,2,3",
+ "EventCode": "0xA",
+ "EventName": "UNC_P_PROCHOT_EXTERNAL_CYCLES",
+ "MetricExpr": "(UNC_P_PROCHOT_EXTERNAL_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+ "PerPkg": "1",
+ "Unit": "PCU"
+ },
+ {
+ "BriefDescription": "Thermal Strongest Upper Limit Cycles. Derived from unc_p_freq_max_limit_thermal_cycles",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x4",
+ "EventName": "UNC_P_FREQ_MAX_LIMIT_THERMAL_CYCLES",
+ "MetricExpr": "(UNC_P_FREQ_MAX_LIMIT_THERMAL_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+ "PerPkg": "1",
+ "Unit": "PCU"
+ },
+ {
+ "BriefDescription": "OS Strongest Upper Limit Cycles. Derived from unc_p_freq_max_os_cycles",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x6",
+ "EventName": "UNC_P_FREQ_MAX_OS_CYCLES",
+ "MetricExpr": "(UNC_P_FREQ_MAX_OS_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+ "PerPkg": "1",
+ "Unit": "PCU"
+ },
+ {
+ "BriefDescription": "Power Strongest Upper Limit Cycles. Derived from unc_p_freq_max_power_cycles",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x5",
+ "EventName": "UNC_P_FREQ_MAX_POWER_CYCLES",
+ "MetricExpr": "(UNC_P_FREQ_MAX_POWER_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+ "PerPkg": "1",
+ "Unit": "PCU"
+ },
+ {
+ "BriefDescription": "Cycles spent changing Frequency. Derived from unc_p_freq_trans_cycles",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x74",
+ "EventName": "UNC_P_FREQ_TRANS_CYCLES",
+ "MetricExpr": "(UNC_P_FREQ_TRANS_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+ "PerPkg": "1",
+ "Unit": "PCU"
+ }
+]
--
2.9.3
[toc] | [prev] | [next] | [standalone]
| From | Arnaldo Carvalho de Melo <acme@kernel.org> |
|---|---|
| Date | 2017-02-10 04:10 +0100 |
| Subject | [PATCH 30/32] perf bench numa: Avoid possible truncation when using snprintf() |
| Message-ID | <t99KW-6h2-9@gated-at.bofh.it> |
| In reply to | #1578103 |
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Addressing this warning from gcc 7:
CC /tmp/build/perf/bench/numa.o
bench/numa.c: In function '__bench_numa':
bench/numa.c:1582:42: error: '%d' directive output may be truncated writing between 1 and 10 bytes into a region of size between 8 and 17 [-Werror=format-truncation=]
snprintf(tname, 32, "process%d:thread%d", p, t);
^~
bench/numa.c:1582:25: note: directive argument in the range [0, 2147483647]
snprintf(tname, 32, "process%d:thread%d", p, t);
^~~~~~~~~~~~~~~~~~~~
In file included from /usr/include/stdio.h:939:0,
from bench/../util/util.h:47,
from bench/../builtin.h:4,
from bench/numa.c:11:
/usr/include/bits/stdio2.h:64:10: note: '__builtin___snprintf_chk' output between 17 and 35 bytes into a destination of size 32
return __builtin___snprintf_chk (__s, __n, __USE_FORTIFY_LEVEL - 1,
^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
__bos (__s), __fmt, __va_arg_pack ());
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
cc1: all warnings being treated as errors
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Petr Holasek <pholasek@redhat.com>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lkml.kernel.org/n/tip-twa37vsfqcie5gwpqwnjuuz9@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/perf/bench/numa.c | 6 +++---
1 file changed, 3 insertions(+), 3 deletions(-)
diff --git a/tools/perf/bench/numa.c b/tools/perf/bench/numa.c
index 8efe904e486b..9e5a02d6b9a9 100644
--- a/tools/perf/bench/numa.c
+++ b/tools/perf/bench/numa.c
@@ -1573,13 +1573,13 @@ static int __bench_numa(const char *name)
"GB/sec,", "total-speed", "GB/sec total speed");
if (g->p.show_details >= 2) {
- char tname[32];
+ char tname[14 + 2 * 10 + 1];
struct thread_data *td;
for (p = 0; p < g->p.nr_proc; p++) {
for (t = 0; t < g->p.nr_threads; t++) {
- memset(tname, 0, 32);
+ memset(tname, 0, sizeof(tname));
td = g->threads + p*g->p.nr_threads + t;
- snprintf(tname, 32, "process%d:thread%d", p, t);
+ snprintf(tname, sizeof(tname), "process%d:thread%d", p, t);
print_res(tname, td->speed_gbs,
"GB/sec", "thread-speed", "GB/sec/thread speed");
print_res(tname, td->system_time_ns / NSEC_PER_SEC,
--
2.9.3
[toc] | [prev] | [next] | [standalone]
| From | Arnaldo Carvalho de Melo <acme@kernel.org> |
|---|---|
| Date | 2017-02-10 04:50 +0100 |
| Subject | [PATCH 19/32] perf vendor events intel: Add uncore events for IvyBridge Server |
| Message-ID | <t9anE-6yu-3@gated-at.bofh.it> |
| In reply to | #1578103 |
From: Andi Kleen <ak@linux.intel.com>
This is not a full uncore event list, but a short list of useful
and understandable metrics.
Signed-off-by: Andi Kleen <ak@linux.intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Link: http://lkml.kernel.org/n/tip-c0cix4eprbldfrx5zf60suvh@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
.../pmu-events/arch/x86/ivytown/uncore-cache.json | 322 +++++++++++++++++++++
.../arch/x86/ivytown/uncore-interconnect.json | 46 +++
.../pmu-events/arch/x86/ivytown/uncore-memory.json | 75 +++++
.../pmu-events/arch/x86/ivytown/uncore-power.json | 249 ++++++++++++++++
4 files changed, 692 insertions(+)
create mode 100644 tools/perf/pmu-events/arch/x86/ivytown/uncore-cache.json
create mode 100644 tools/perf/pmu-events/arch/x86/ivytown/uncore-interconnect.json
create mode 100644 tools/perf/pmu-events/arch/x86/ivytown/uncore-memory.json
create mode 100644 tools/perf/pmu-events/arch/x86/ivytown/uncore-power.json
diff --git a/tools/perf/pmu-events/arch/x86/ivytown/uncore-cache.json b/tools/perf/pmu-events/arch/x86/ivytown/uncore-cache.json
new file mode 100644
index 000000000000..2efdc6772e0b
--- /dev/null
+++ b/tools/perf/pmu-events/arch/x86/ivytown/uncore-cache.json
@@ -0,0 +1,322 @@
+[
+ {
+ "BriefDescription": "Uncore cache clock ticks. Derived from unc_c_clockticks",
+ "Counter": "0,1,2,3",
+ "EventName": "UNC_C_CLOCKTICKS",
+ "PerPkg": "1",
+ "Unit": "CBO"
+ },
+ {
+ "BriefDescription": "All LLC Misses (code+ data rd + data wr - including demand and prefetch). Derived from unc_c_llc_lookup.any",
+ "Counter": "0,1",
+ "EventCode": "0x34",
+ "EventName": "UNC_C_LLC_LOOKUP.ANY",
+ "Filter": "filter_state=0x1",
+ "PerPkg": "1",
+ "ScaleUnit": "64Bytes",
+ "UMask": "0x11",
+ "Unit": "CBO"
+ },
+ {
+ "BriefDescription": "M line evictions from LLC (writebacks to memory). Derived from unc_c_llc_victims.m_state",
+ "Counter": "0,1",
+ "EventCode": "0x37",
+ "EventName": "UNC_C_LLC_VICTIMS.M_STATE",
+ "PerPkg": "1",
+ "ScaleUnit": "64Bytes",
+ "UMask": "0x1",
+ "Unit": "CBO"
+ },
+ {
+ "BriefDescription": "LLC misses - demand and prefetch data reads - excludes LLC prefetches. Derived from unc_c_tor_inserts.miss_opcode.demand",
+ "Counter": "0,1",
+ "EventCode": "0x35",
+ "EventName": "LLC_MISSES.DATA_READ",
+ "Filter": "filter_opc=0x182",
+ "PerPkg": "1",
+ "ScaleUnit": "64Bytes",
+ "UMask": "0x3",
+ "Unit": "CBO"
+ },
+ {
+ "BriefDescription": "LLC misses - Uncacheable reads. Derived from unc_c_tor_inserts.miss_opcode.uncacheable",
+ "Counter": "0,1",
+ "EventCode": "0x35",
+ "EventName": "LLC_MISSES.UNCACHEABLE",
+ "Filter": "filter_opc=0x187",
+ "PerPkg": "1",
+ "ScaleUnit": "64Bytes",
+ "UMask": "0x3",
+ "Unit": "CBO"
+ },
+ {
+ "BriefDescription": "LLC prefetch misses for RFO. Derived from unc_c_tor_inserts.miss_opcode.rfo_prefetch",
+ "Counter": "0,1",
+ "EventCode": "0x35",
+ "EventName": "LLC_MISSES.RFO_LLC_PREFETCH",
+ "Filter": "filter_opc=0x190",
+ "PerPkg": "1",
+ "ScaleUnit": "64Bytes",
+ "UMask": "0x3",
+ "Unit": "CBO"
+ },
+ {
+ "BriefDescription": "LLC prefetch misses for code reads. Derived from unc_c_tor_inserts.miss_opcode.code",
+ "Counter": "0,1",
+ "EventCode": "0x35",
+ "EventName": "LLC_MISSES.CODE_LLC_PREFETCH",
+ "Filter": "filter_opc=0x191",
+ "PerPkg": "1",
+ "ScaleUnit": "64Bytes",
+ "UMask": "0x3",
+ "Unit": "CBO"
+ },
+ {
+ "BriefDescription": "LLC prefetch misses for data reads. Derived from unc_c_tor_inserts.miss_opcode.data_read",
+ "Counter": "0,1",
+ "EventCode": "0x35",
+ "EventName": "LLC_MISSES.DATA_LLC_PREFETCH",
+ "Filter": "filter_opc=0x192",
+ "PerPkg": "1",
+ "ScaleUnit": "64Bytes",
+ "UMask": "0x3",
+ "Unit": "CBO"
+ },
+ {
+ "BriefDescription": "PCIe allocating writes that miss LLC - DDIO misses. Derived from unc_c_tor_inserts.miss_opcode.ddio_miss",
+ "Counter": "0,1",
+ "EventCode": "0x35",
+ "EventName": "LLC_MISSES.PCIE_WRITE",
+ "Filter": "filter_opc=0x19c",
+ "PerPkg": "1",
+ "ScaleUnit": "64Bytes",
+ "UMask": "0x3",
+ "Unit": "CBO"
+ },
+ {
+ "BriefDescription": "LLC misses for PCIe read current. Derived from unc_c_tor_inserts.miss_opcode.pcie_read",
+ "Counter": "0,1",
+ "EventCode": "0x35",
+ "EventName": "LLC_MISSES.PCIE_READ",
+ "Filter": "filter_opc=0x19e",
+ "PerPkg": "1",
+ "ScaleUnit": "64Bytes",
+ "UMask": "0x3",
+ "Unit": "CBO"
+ },
+ {
+ "BriefDescription": "LLC misses for ItoM writes (as part of fast string memcpy stores). Derived from unc_c_tor_inserts.miss_opcode.itom_write",
+ "Counter": "0,1",
+ "EventCode": "0x35",
+ "EventName": "LLC_MISSES.ITOM_WRITE",
+ "Filter": "filter_opc=0x1c8",
+ "PerPkg": "1",
+ "ScaleUnit": "64Bytes",
+ "UMask": "0x3",
+ "Unit": "CBO"
+ },
+ {
+ "BriefDescription": "LLC misses for PCIe non-snoop reads. Derived from unc_c_tor_inserts.miss_opcode.pcie_read",
+ "Counter": "0,1",
+ "EventCode": "0x35",
+ "EventName": "LLC_MISSES.PCIE_NON_SNOOP_READ",
+ "Filter": "filter_opc=0x1e4",
+ "PerPkg": "1",
+ "ScaleUnit": "64Bytes",
+ "UMask": "0x3",
+ "Unit": "CBO"
+ },
+ {
+ "BriefDescription": "LLC misses for PCIe non-snoop writes (full line). Derived from unc_c_tor_inserts.miss_opcode.pcie_write",
+ "Counter": "0,1",
+ "EventCode": "0x35",
+ "EventName": "LLC_MISSES.PCIE_NON_SNOOP_WRITE",
+ "Filter": "filter_opc=0x1e6",
+ "PerPkg": "1",
+ "ScaleUnit": "64Bytes",
+ "UMask": "0x3",
+ "Unit": "CBO"
+ },
+ {
+ "BriefDescription": "Streaming stores (full cache line). Derived from unc_c_tor_inserts.opcode.streaming_full",
+ "Counter": "0,1",
+ "EventCode": "0x35",
+ "EventName": "LLC_REFERENCES.STREAMING_FULL",
+ "Filter": "filter_opc=0x18c",
+ "PerPkg": "1",
+ "ScaleUnit": "64Bytes",
+ "UMask": "0x1",
+ "Unit": "CBO"
+ },
+ {
+ "BriefDescription": "Streaming stores (partial cache line). Derived from unc_c_tor_inserts.opcode.streaming_partial",
+ "Counter": "0,1",
+ "EventCode": "0x35",
+ "EventName": "LLC_REFERENCES.STREAMING_PARTIAL",
+ "Filter": "filter_opc=0x18d",
+ "PerPkg": "1",
+ "ScaleUnit": "64Bytes",
+ "UMask": "0x1",
+ "Unit": "CBO"
+ },
+ {
+ "BriefDescription": "Partial PCIe reads. Derived from unc_c_tor_inserts.opcode.pcie_partial",
+ "Counter": "0,1",
+ "EventCode": "0x35",
+ "EventName": "LLC_REFERENCES.PCIE_PARTIAL_READ",
+ "Filter": "filter_opc=0x195",
+ "PerPkg": "1",
+ "ScaleUnit": "64Bytes",
+ "UMask": "0x1",
+ "Unit": "CBO"
+ },
+ {
+ "BriefDescription": "PCIe allocating writes that hit in LLC (DDIO hits). Derived from unc_c_tor_inserts.opcode.ddio_hit",
+ "Counter": "0,1",
+ "EventCode": "0x35",
+ "EventName": "LLC_REFERENCES.PCIE_WRITE",
+ "Filter": "filter_opc=0x19c",
+ "PerPkg": "1",
+ "ScaleUnit": "64Bytes",
+ "UMask": "0x1",
+ "Unit": "CBO"
+ },
+ {
+ "BriefDescription": "PCIe read current. Derived from unc_c_tor_inserts.opcode.pcie_read_current",
+ "Counter": "0,1",
+ "EventCode": "0x35",
+ "EventName": "LLC_REFERENCES.PCIE_READ",
+ "Filter": "filter_opc=0x19e",
+ "PerPkg": "1",
+ "ScaleUnit": "64Bytes",
+ "UMask": "0x1",
+ "Unit": "CBO"
+ },
+ {
+ "BriefDescription": "ItoM write hits (as part of fast string memcpy stores). Derived from unc_c_tor_inserts.opcode.itom_write_hit",
+ "Counter": "0,1",
+ "EventCode": "0x35",
+ "EventName": "LLC_REFERENCES.ITOM_WRITE",
+ "Filter": "filter_opc=0x1c8",
+ "PerPkg": "1",
+ "ScaleUnit": "64Bytes",
+ "UMask": "0x1",
+ "Unit": "CBO"
+ },
+ {
+ "BriefDescription": "PCIe non-snoop reads. Derived from unc_c_tor_inserts.opcode.pcie_read",
+ "Counter": "0,1",
+ "EventCode": "0x35",
+ "EventName": "LLC_REFERENCES.PCIE_NS_READ",
+ "Filter": "filter_opc=0x1e4",
+ "PerPkg": "1",
+ "ScaleUnit": "64Bytes",
+ "UMask": "0x1",
+ "Unit": "CBO"
+ },
+ {
+ "BriefDescription": "PCIe non-snoop writes (partial). Derived from unc_c_tor_inserts.opcode.pcie_partial_write",
+ "Counter": "0,1",
+ "EventCode": "0x35",
+ "EventName": "LLC_REFERENCES.PCIE_NS_PARTIAL_WRITE",
+ "Filter": "filter_opc=0x1e5",
+ "PerPkg": "1",
+ "ScaleUnit": "64Bytes",
+ "UMask": "0x1",
+ "Unit": "CBO"
+ },
+ {
+ "BriefDescription": "PCIe non-snoop writes (full line). Derived from unc_c_tor_inserts.opcode.pcie_full_write",
+ "Counter": "0,1",
+ "EventCode": "0x35",
+ "EventName": "LLC_REFERENCES.PCIE_NS_WRITE",
+ "Filter": "filter_opc=0x1e6",
+ "PerPkg": "1",
+ "ScaleUnit": "64Bytes",
+ "UMask": "0x1",
+ "Unit": "CBO"
+ },
+ {
+ "BriefDescription": "Occupancy for all LLC misses that are addressed to local memory. Derived from unc_c_tor_occupancy.miss_local",
+ "EventCode": "0x36",
+ "EventName": "UNC_C_TOR_OCCUPANCY.MISS_LOCAL",
+ "PerPkg": "1",
+ "UMask": "0x2A",
+ "Unit": "CBO"
+ },
+ {
+ "BriefDescription": "Occupancy counter for LLC data reads (demand and L2 prefetch). Derived from unc_c_tor_occupancy.miss_opcode.llc_data_read",
+ "EventCode": "0x36",
+ "EventName": "UNC_C_TOR_OCCUPANCY.LLC_DATA_READ",
+ "Filter": "filter_opc=0x182",
+ "PerPkg": "1",
+ "UMask": "0x3",
+ "Unit": "CBO"
+ },
+ {
+ "BriefDescription": "Occupancy for all LLC misses that are addressed to remote memory. Derived from unc_c_tor_occupancy.miss_remote",
+ "EventCode": "0x36",
+ "EventName": "UNC_C_TOR_OCCUPANCY.MISS_REMOTE",
+ "PerPkg": "1",
+ "UMask": "0x8A",
+ "Unit": "CBO"
+ },
+ {
+ "BriefDescription": "Read requests to home agent. Derived from unc_h_requests.reads",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x1",
+ "EventName": "UNC_H_REQUESTS.READS",
+ "PerPkg": "1",
+ "UMask": "0x3",
+ "Unit": "HA"
+ },
+ {
+ "BriefDescription": "Write requests to home agent. Derived from unc_h_requests.writes",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x1",
+ "EventName": "UNC_H_REQUESTS.WRITES",
+ "PerPkg": "1",
+ "UMask": "0xC",
+ "Unit": "HA"
+ },
+ {
+ "BriefDescription": "M line forwarded from remote cache along with writeback to memory. Derived from unc_h_snoop_resp.rsp_fwd_wb",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x21",
+ "EventName": "UNC_H_SNOOP_RESP.RSP_FWD_WB",
+ "PerPkg": "1",
+ "ScaleUnit": "64Bytes",
+ "UMask": "0x20",
+ "Unit": "HA"
+ },
+ {
+ "BriefDescription": "M line forwarded from remote cache with no writeback to memory. Derived from unc_h_snoop_resp.rspifwd",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x21",
+ "EventName": "UNC_H_SNOOP_RESP.RSPIFWD",
+ "PerPkg": "1",
+ "ScaleUnit": "64Bytes",
+ "UMask": "0x4",
+ "Unit": "HA"
+ },
+ {
+ "BriefDescription": "Shared line response from remote cache. Derived from unc_h_snoop_resp.rsps",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x21",
+ "EventName": "UNC_H_SNOOP_RESP.RSPS",
+ "PerPkg": "1",
+ "ScaleUnit": "64Bytes",
+ "UMask": "0x2",
+ "Unit": "HA"
+ },
+ {
+ "BriefDescription": "Shared line forwarded from remote cache. Derived from unc_h_snoop_resp.rspsfwd",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x21",
+ "EventName": "UNC_H_SNOOP_RESP.RSPSFWD",
+ "PerPkg": "1",
+ "ScaleUnit": "64Bytes",
+ "UMask": "0x8",
+ "Unit": "HA"
+ }
+]
diff --git a/tools/perf/pmu-events/arch/x86/ivytown/uncore-interconnect.json b/tools/perf/pmu-events/arch/x86/ivytown/uncore-interconnect.json
new file mode 100644
index 000000000000..d7e2fda1d695
--- /dev/null
+++ b/tools/perf/pmu-events/arch/x86/ivytown/uncore-interconnect.json
@@ -0,0 +1,46 @@
+[
+ {
+ "BriefDescription": "QPI clock ticks. Use to get percentages for QPI cycles events. Derived from unc_q_clockticks",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x14",
+ "EventName": "UNC_Q_CLOCKTICKS",
+ "PerPkg": "1",
+ "Unit": "QPI LL"
+ },
+ {
+ "BriefDescription": "Cycles where receiving QPI link is in half-width mode. Derived from unc_q_rxl0p_power_cycles",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x10",
+ "EventName": "UNC_Q_RxL0P_POWER_CYCLES",
+ "MetricExpr": "(UNC_Q_RxL0P_POWER_CYCLES / UNC_Q_CLOCKTICKS) * 100.",
+ "PerPkg": "1",
+ "Unit": "QPI LL"
+ },
+ {
+ "BriefDescription": "Cycles where transmitting QPI link is in half-width mode. Derived from unc_q_txl0p_power_cycles",
+ "Counter": "0,1,2,3",
+ "EventCode": "0xd",
+ "EventName": "UNC_Q_TxL0P_POWER_CYCLES",
+ "MetricExpr": "(UNC_Q_TxL0P_POWER_CYCLES / UNC_Q_CLOCKTICKS) * 100.",
+ "PerPkg": "1",
+ "Unit": "QPI LL"
+ },
+ {
+ "BriefDescription": "Number of data flits transmitted . Derived from unc_q_txl_flits_g0.data",
+ "Counter": "0,1,2,3",
+ "EventName": "UNC_Q_TxL_FLITS_G0.DATA",
+ "PerPkg": "1",
+ "ScaleUnit": "8Bytes",
+ "UMask": "0x2",
+ "Unit": "QPI LL"
+ },
+ {
+ "BriefDescription": "Number of non data (control) flits transmitted . Derived from unc_q_txl_flits_g0.non_data",
+ "Counter": "0,1,2,3",
+ "EventName": "UNC_Q_TxL_FLITS_G0.NON_DATA",
+ "PerPkg": "1",
+ "ScaleUnit": "8Bytes",
+ "UMask": "0x4",
+ "Unit": "QPI LL"
+ }
+]
diff --git a/tools/perf/pmu-events/arch/x86/ivytown/uncore-memory.json b/tools/perf/pmu-events/arch/x86/ivytown/uncore-memory.json
new file mode 100644
index 000000000000..ac4ad4d6357b
--- /dev/null
+++ b/tools/perf/pmu-events/arch/x86/ivytown/uncore-memory.json
@@ -0,0 +1,75 @@
+[
+ {
+ "BriefDescription": "Memory page activates for reads and writes. Derived from unc_m_act_count.rd",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x1",
+ "EventName": "UNC_M_ACT_COUNT.RD",
+ "PerPkg": "1",
+ "UMask": "0x1",
+ "Umask": "0x3",
+ "Unit": "iMC"
+ },
+ {
+ "BriefDescription": "Read requests to memory controller. Derived from unc_m_cas_count.rd",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x4",
+ "EventName": "UNC_M_CAS_COUNT.RD",
+ "PerPkg": "1",
+ "ScaleUnit": "64Bytes",
+ "UMask": "0x3",
+ "Unit": "iMC"
+ },
+ {
+ "BriefDescription": "Write requests to memory controller. Derived from unc_m_cas_count.wr",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x4",
+ "EventName": "UNC_M_CAS_COUNT.WR",
+ "PerPkg": "1",
+ "ScaleUnit": "64Bytes",
+ "UMask": "0xC",
+ "Unit": "iMC"
+ },
+ {
+ "BriefDescription": "Memory controller clock ticks. Use to generate percentages for memory controller CYCLES events. Derived from unc_m_clockticks",
+ "Counter": "0,1,2,3",
+ "EventName": "UNC_M_CLOCKTICKS",
+ "PerPkg": "1",
+ "Unit": "iMC"
+ },
+ {
+ "BriefDescription": "Cycles where DRAM ranks are in power down (CKE) mode. Derived from unc_m_power_channel_ppd",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x85",
+ "EventName": "UNC_M_POWER_CHANNEL_PPD",
+ "MetricExpr": "(UNC_M_POWER_CHANNEL_PPD / UNC_M_CLOCKTICKS) * 100.",
+ "PerPkg": "1",
+ "Unit": "iMC"
+ },
+ {
+ "BriefDescription": "Cycles all ranks are in critical thermal throttle. Derived from unc_m_power_critical_throttle_cycles",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x86",
+ "EventName": "UNC_M_POWER_CRITICAL_THROTTLE_CYCLES",
+ "MetricExpr": "(UNC_M_POWER_CRITICAL_THROTTLE_CYCLES / UNC_M_CLOCKTICKS) * 100.",
+ "PerPkg": "1",
+ "Unit": "iMC"
+ },
+ {
+ "BriefDescription": "Cycles Memory is in self refresh power mode. Derived from unc_m_power_self_refresh",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x43",
+ "EventName": "UNC_M_POWER_SELF_REFRESH",
+ "MetricExpr": "(UNC_M_POWER_SELF_REFRESH / UNC_M_CLOCKTICKS) * 100.",
+ "PerPkg": "1",
+ "Unit": "iMC"
+ },
+ {
+ "BriefDescription": "Memory page conflicts. Derived from unc_m_pre_count.page_miss",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x2",
+ "EventName": "UNC_M_PRE_COUNT.PAGE_MISS",
+ "PerPkg": "1",
+ "UMask": "0x1",
+ "Unit": "iMC"
+ }
+]
diff --git a/tools/perf/pmu-events/arch/x86/ivytown/uncore-power.json b/tools/perf/pmu-events/arch/x86/ivytown/uncore-power.json
new file mode 100644
index 000000000000..dc2586db0dfc
--- /dev/null
+++ b/tools/perf/pmu-events/arch/x86/ivytown/uncore-power.json
@@ -0,0 +1,249 @@
+[
+ {
+ "BriefDescription": "PCU clock ticks. Use to get percentages of PCU cycles events. Derived from unc_p_clockticks",
+ "Counter": "0,1,2,3",
+ "EventName": "UNC_P_CLOCKTICKS",
+ "PerPkg": "1",
+ "Unit": "PCU"
+ },
+ {
+ "BriefDescription": "Counts the number of cycles that the uncore was running at a frequency greater than or equal to the frequency that is configured in the filter. (filter_band0=XXX, with XXX in 100Mhz units). One can also use inversion (filter_inv=1) to track cycles when we were less than the configured frequency. Derived from unc_p_freq_band0_cycles",
+ "Counter": "0,1,2,3",
+ "EventCode": "0xb",
+ "EventName": "UNC_P_FREQ_BAND0_CYCLES",
+ "MetricExpr": "(UNC_P_FREQ_BAND0_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+ "PerPkg": "1",
+ "Unit": "PCU"
+ },
+ {
+ "BriefDescription": "Counts the number of cycles that the uncore was running at a frequency greater than or equal to the frequency that is configured in the filter. (filter_band1=XXX, with XXX in 100Mhz units). One can also use inversion (filter_inv=1) to track cycles when we were less than the configured frequency. Derived from unc_p_freq_band1_cycles",
+ "Counter": "0,1,2,3",
+ "EventCode": "0xc",
+ "EventName": "UNC_P_FREQ_BAND1_CYCLES",
+ "MetricExpr": "(UNC_P_FREQ_BAND1_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+ "PerPkg": "1",
+ "Unit": "PCU"
+ },
+ {
+ "BriefDescription": "Counts the number of cycles that the uncore was running at a frequency greater than or equal to the frequency that is configured in the filter. (filter_band2=XXX, with XXX in 100Mhz units). One can also use inversion (filter_inv=1) to track cycles when we were less than the configured frequency. Derived from unc_p_freq_band2_cycles",
+ "Counter": "0,1,2,3",
+ "EventCode": "0xd",
+ "EventName": "UNC_P_FREQ_BAND2_CYCLES",
+ "MetricExpr": "(UNC_P_FREQ_BAND2_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+ "PerPkg": "1",
+ "Unit": "PCU"
+ },
+ {
+ "BriefDescription": "Counts the number of cycles that the uncore was running at a frequency greater than or equal to the frequency that is configured in the filter. (filter_band3=XXX, with XXX in 100Mhz units). One can also use inversion (filter_inv=1) to track cycles when we were less than the configured frequency. Derived from unc_p_freq_band3_cycles",
+ "Counter": "0,1,2,3",
+ "EventCode": "0xe",
+ "EventName": "UNC_P_FREQ_BAND3_CYCLES",
+ "MetricExpr": "(UNC_P_FREQ_BAND3_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+ "PerPkg": "1",
+ "Unit": "PCU"
+ },
+ {
+ "BriefDescription": "Counts the number of times that the uncore transitioned a frequency greater than or equal to the frequency that is configured in the filter. (filter_band0=XXX, with XXX in 100Mhz units). One can also use inversion (filter_inv=1) to track cycles when we were less than the configured frequency. Derived from unc_p_freq_band0_cycles",
+ "Counter": "0,1,2,3",
+ "EventCode": "0xb",
+ "EventName": "UNC_P_FREQ_BAND0_TRANSITIONS",
+ "Filter": "edge=1",
+ "MetricExpr": "(UNC_P_FREQ_BAND0_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+ "PerPkg": "1",
+ "Unit": "PCU"
+ },
+ {
+ "BriefDescription": "Counts the number of times that the uncore transitioned to a frequency greater than or equal to the frequency that is configured in the filter. (filter_band1=XXX, with XXX in 100Mhz units). One can also use inversion (filter_inv=1) to track cycles when we were less than the configured frequency. Derived from unc_p_freq_band1_cycles",
+ "Counter": "0,1,2,3",
+ "EventCode": "0xc",
+ "EventName": "UNC_P_FREQ_BAND1_TRANSITIONS",
+ "Filter": "edge=1",
+ "MetricExpr": "(UNC_P_FREQ_BAND1_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+ "PerPkg": "1",
+ "Unit": "PCU"
+ },
+ {
+ "BriefDescription": "Counts the number of cycles that the uncore transitioned to a frequency greater than or equal to the frequency that is configured in the filter. (filter_band2=XXX, with XXX in 100Mhz units). One can also use inversion (filter_inv=1) to track cycles when we were less than the configured frequency. Derived from unc_p_freq_band2_cycles",
+ "Counter": "0,1,2,3",
+ "EventCode": "0xd",
+ "EventName": "UNC_P_FREQ_BAND2_TRANSITIONS",
+ "Filter": "edge=1",
+ "MetricExpr": "(UNC_P_FREQ_BAND2_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+ "PerPkg": "1",
+ "Unit": "PCU"
+ },
+ {
+ "BriefDescription": "Counts the number of cycles that the uncore transitioned to a frequency greater than or equal to the frequency that is configured in the filter. (filter_band3=XXX, with XXX in 100Mhz units). One can also use inversion (filter_inv=1) to track cycles when we were less than the configured frequency. Derived from unc_p_freq_band3_cycles",
+ "Counter": "0,1,2,3",
+ "EventCode": "0xe",
+ "EventName": "UNC_P_FREQ_BAND3_TRANSITIONS",
+ "Filter": "edge=1",
+ "MetricExpr": "(UNC_P_FREQ_BAND3_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+ "PerPkg": "1",
+ "Unit": "PCU"
+ },
+ {
+ "BriefDescription": "This is an occupancy event that tracks the number of cores that are in the chosen C-State. It can be used by itself to get the average number of cores in that C-state with threshholding to generate histograms, or with other PCU events and occupancy triggering to capture other details. Derived from unc_p_power_state_occupancy.cores_c0",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x80",
+ "EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C0",
+ "Filter": "occ_sel=1",
+ "MetricExpr": "(UNC_P_POWER_STATE_OCCUPANCY.CORES_C0 / UNC_P_CLOCKTICKS) * 100.",
+ "PerPkg": "1",
+ "Unit": "PCU"
+ },
+ {
+ "BriefDescription": "This is an occupancy event that tracks the number of cores that are in the chosen C-State. It can be used by itself to get the average number of cores in that C-state with threshholding to generate histograms, or with other PCU events and occupancy triggering to capture other details. Derived from unc_p_power_state_occupancy.cores_c3",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x80",
+ "EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C3",
+ "Filter": "occ_sel=2",
+ "MetricExpr": "(UNC_P_POWER_STATE_OCCUPANCY.CORES_C3 / UNC_P_CLOCKTICKS) * 100.",
+ "PerPkg": "1",
+ "Unit": "PCU"
+ },
+ {
+ "BriefDescription": "This is an occupancy event that tracks the number of cores that are in the chosen C-State. It can be used by itself to get the average number of cores in that C-state with threshholding to generate histograms, or with other PCU events and occupancy triggering to capture other details. Derived from unc_p_power_state_occupancy.cores_c6",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x80",
+ "EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C6",
+ "Filter": "occ_sel=3",
+ "MetricExpr": "(UNC_P_POWER_STATE_OCCUPANCY.CORES_C6 / UNC_P_CLOCKTICKS) * 100.",
+ "PerPkg": "1",
+ "Unit": "PCU"
+ },
+ {
+ "BriefDescription": "Counts the number of cycles that we are in external PROCHOT mode. This mode is triggered when a sensor off the die determines that something off-die (like DRAM) is too hot and must throttle to avoid damaging the chip. Derived from unc_p_prochot_external_cycles",
+ "Counter": "0,1,2,3",
+ "EventCode": "0xa",
+ "EventName": "UNC_P_PROCHOT_EXTERNAL_CYCLES",
+ "MetricExpr": "(UNC_P_PROCHOT_EXTERNAL_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+ "PerPkg": "1",
+ "Unit": "PCU"
+ },
+ {
+ "BriefDescription": "Counts the number of cycles when thermal conditions are the upper limit on frequency. This is related to the THERMAL_THROTTLE CYCLES_ABOVE_TEMP event, which always counts cycles when we are above the thermal temperature. This event (STRONGEST_UPPER_LIMIT) is sampled at the output of the algorithm that determines the actual frequency, while THERMAL_THROTTLE looks at the input. Derived from unc_p_freq_max_limit_thermal_cycles",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x4",
+ "EventName": "UNC_P_FREQ_MAX_LIMIT_THERMAL_CYCLES",
+ "MetricExpr": "(UNC_P_FREQ_MAX_LIMIT_THERMAL_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+ "PerPkg": "1",
+ "Unit": "PCU"
+ },
+ {
+ "BriefDescription": "Counts the number of cycles when the OS is the upper limit on frequency. Derived from unc_p_freq_max_os_cycles",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x6",
+ "EventName": "UNC_P_FREQ_MAX_OS_CYCLES",
+ "MetricExpr": "(UNC_P_FREQ_MAX_OS_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+ "PerPkg": "1",
+ "Unit": "PCU"
+ },
+ {
+ "BriefDescription": "Counts the number of cycles when power is the upper limit on frequency. Derived from unc_p_freq_max_power_cycles",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x5",
+ "EventName": "UNC_P_FREQ_MAX_POWER_CYCLES",
+ "MetricExpr": "(UNC_P_FREQ_MAX_POWER_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+ "PerPkg": "1",
+ "Unit": "PCU"
+ },
+ {
+ "BriefDescription": "Counts the number of cycles when current is the upper limit on frequency. Derived from unc_p_freq_max_current_cycles",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x7",
+ "EventName": "UNC_P_FREQ_MAX_CURRENT_CYCLES",
+ "MetricExpr": "(UNC_P_FREQ_MAX_CURRENT_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+ "PerPkg": "1",
+ "Unit": "PCU"
+ },
+ {
+ "BriefDescription": "Counts the number of cycles when the system is changing frequency. This can not be filtered by thread ID. One can also use it with the occupancy counter that monitors number of threads in C0 to estimate the performance impact that frequency transitions had on the system. Derived from unc_p_freq_trans_cycles",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x60",
+ "EventName": "UNC_P_FREQ_TRANS_CYCLES",
+ "MetricExpr": "(UNC_P_FREQ_TRANS_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+ "PerPkg": "1",
+ "Unit": "PCU"
+ },
+ {
+ "BriefDescription": "Counts the number of cycles that the uncore was running at a frequency greater than or equal to 1.2Ghz. Derived from unc_p_freq_band0_cycles",
+ "Counter": "0,1,2,3",
+ "EventCode": "0xb",
+ "EventName": "UNC_P_FREQ_GE_1200MHZ_CYCLES",
+ "Filter": "filter_band0=1200",
+ "MetricExpr": "(UNC_P_FREQ_GE_1200MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+ "PerPkg": "1",
+ "Unit": "PCU"
+ },
+ {
+ "BriefDescription": "Counts the number of cycles that the uncore was running at a frequency greater than or equal to 2Ghz. Derived from unc_p_freq_band1_cycles",
+ "Counter": "0,1,2,3",
+ "EventCode": "0xc",
+ "EventName": "UNC_P_FREQ_GE_2000MHZ_CYCLES",
+ "Filter": "filter_band1=2000",
+ "MetricExpr": "(UNC_P_FREQ_GE_2000MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+ "PerPkg": "1",
+ "Unit": "PCU"
+ },
+ {
+ "BriefDescription": "Counts the number of cycles that the uncore was running at a frequency greater than or equal to 3Ghz. Derived from unc_p_freq_band2_cycles",
+ "Counter": "0,1,2,3",
+ "EventCode": "0xd",
+ "EventName": "UNC_P_FREQ_GE_3000MHZ_CYCLES",
+ "Filter": "filter_band2=3000",
+ "MetricExpr": "(UNC_P_FREQ_GE_3000MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+ "PerPkg": "1",
+ "Unit": "PCU"
+ },
+ {
+ "BriefDescription": "Counts the number of cycles that the uncore was running at a frequency greater than or equal to 4Ghz. Derived from unc_p_freq_band3_cycles",
+ "Counter": "0,1,2,3",
+ "EventCode": "0xe",
+ "EventName": "UNC_P_FREQ_GE_4000MHZ_CYCLES",
+ "Filter": "filter_band3=4000",
+ "MetricExpr": "(UNC_P_FREQ_GE_4000MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+ "PerPkg": "1",
+ "Unit": "PCU"
+ },
+ {
+ "BriefDescription": "Counts the number of times that the uncore transitioned to a frequency greater than or equal to 1.2Ghz. Derived from unc_p_freq_band0_cycles",
+ "Counter": "0,1,2,3",
+ "EventCode": "0xb",
+ "EventName": "UNC_P_FREQ_GE_1200MHZ_TRANSITIONS",
+ "Filter": "edge=1,filter_band0=1200",
+ "MetricExpr": "(UNC_P_FREQ_GE_1200MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+ "PerPkg": "1",
+ "Unit": "PCU"
+ },
+ {
+ "BriefDescription": "Counts the number of times that the uncore transitioned to a frequency greater than or equal to 2Ghz. Derived from unc_p_freq_band1_cycles",
+ "Counter": "0,1,2,3",
+ "EventCode": "0xc",
+ "EventName": "UNC_P_FREQ_GE_2000MHZ_TRANSITIONS",
+ "Filter": "edge=1,filter_band1=2000",
+ "MetricExpr": "(UNC_P_FREQ_GE_2000MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+ "PerPkg": "1",
+ "Unit": "PCU"
+ },
+ {
+ "BriefDescription": "Counts the number of cycles that the uncore transitioned to a frequency greater than or equal to 3Ghz. Derived from unc_p_freq_band2_cycles",
+ "Counter": "0,1,2,3",
+ "EventCode": "0xd",
+ "EventName": "UNC_P_FREQ_GE_3000MHZ_TRANSITIONS",
+ "Filter": "edge=1,filter_band2=4000",
+ "MetricExpr": "(UNC_P_FREQ_GE_3000MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+ "PerPkg": "1",
+ "Unit": "PCU"
+ },
+ {
+ "BriefDescription": "Counts the number of cycles that the uncore transitioned to a frequency greater than or equal to 4Ghz. Derived from unc_p_freq_band3_cycles",
+ "Counter": "0,1,2,3",
+ "EventCode": "0xe",
+ "EventName": "UNC_P_FREQ_GE_4000MHZ_TRANSITIONS",
+ "Filter": "edge=1,filter_band3=4000",
+ "MetricExpr": "(UNC_P_FREQ_GE_4000MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+ "PerPkg": "1",
+ "Unit": "PCU"
+ }
+]
--
2.9.3
[toc] | [prev] | [next] | [standalone]
| From | Ingo Molnar <mingo@kernel.org> |
|---|---|
| Date | 2017-02-10 09:20 +0100 |
| Message-ID | <t9eAW-To-13@gated-at.bofh.it> |
| In reply to | #1578103 |
* Arnaldo Carvalho de Melo <acme@kernel.org> wrote: > Hi Ingo, > > Please consider pulling, > > - Arnaldo > > Test results at the end of this message, as usual. > > The following changes since commit 53e74a112ce5c1c9b6a6923bdd6612133625d579: > > Merge tag 'perf-urgent-for-mingo-4.10-20170203' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/urgent (2017-02-03 20:42:30 +0100) > > are available in the git repository at: > > git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux.git tags/perf-core-for-mingo-4.11-20170209 > > for you to fetch changes up to 7ea6856d6f5629d742edc23b8b76e6263371ef45: > > perf intel-pt: Use __fallthrough (2017-02-09 16:32:03 -0300) > > ---------------------------------------------------------------- > perf/core improvements and fixes: > > User visible: > > - Add support for parsing Intel uncore vendor event files and add uncore > vendor events for the Intel server processors (Haswell, Broadwell, > IvyBridge), Xeon Phi (Knights Landing) and Broadwell DE (Andi Kleen) > > - Support --symfs in 'perf probe' (Uwe Kleine-König) > > - Add support for generating bpf prologue on the aarch64 architecture (He Kuang) > > - Show proper hint when SDT event not yet in place via 'perf probe' (Ravi Bangoria) > > - Take into account symfs setting when reading file build ID (Victor Kamensky) > > Infrastructure: > > - Map gcc7's '__attribute__ ((fallthrough))', that warns when code > associated to case blocks in switches continue into the next case entry, > to '__falltrough' and use it where warned by gcc, tested on Fedora Rawhide > (Arnaldo Carvalho de Melo) > > - Fix buffer sizes used with snprintf that could lead to truncation, > another warning introduced in gcc7 (Arnaldo Carvalho de Melo) > > - Robustify do_generate_dynamic_list_file in libtraceevent (David Carrillo-Cisneros) > > - Use zfree() in more places (Taeung Song) > > Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> > > ---------------------------------------------------------------- > Andi Kleen (11): > perf jevents: Parse eventcode as number > perf jevents: Add support for parsing uncore json files > perf pmu: Support per pmu json aliases > perf pmu: Support event aliases for non cpu// pmus > perf list: Add debug support for outputing alias string > perf vendor events intel: Add uncore events for Haswell Server processor > perf vendor events intel: Add uncore events for Broadwell Server > perf vendor events intel: Add uncore events for IvyBridge Server > perf vendor events intel: Add uncore events for Sandy Bridge Server > perf vendor events intel: Add uncore events for Xeon Phi (Knights Landing) > perf vendor events intel: Add uncore events for Broadwell DE > > Arnaldo Carvalho de Melo (11): > Merge remote-tracking branch 'tip/perf/urgent' into perf/core > perf tools: Fix include of linux/mman.h > tools include: Add a __fallthrough statement > tools string: Use __fallthrough in perf_atoll() > tools strfilter: Use __fallthrough > perf top: Use __fallthrough > perf thread_map: Correctly size buffer used with dirent->dt_name > perf header: Fix handling of PERF_EVENT_UPDATE__SCALE > perf bench numa: Avoid possible truncation when using snprintf() > perf tests: Avoid possible truncation with dirent->d_name + snprintf > perf intel-pt: Use __fallthrough > > David Carrillo-Cisneros (1): > tools lib traceevent: Robustify do_generate_dynamic_list_file > > He Kuang (2): > perf tools arm64: Add support for generating bpf prologue > perf bpf: Add missing newline in debug messages > > Mickaël Salaün (1): > tools lib bpf: Add missing header to the library > > Ravi Bangoria (1): > perf sdt: Show proper hint when event not yet in place via 'perf probe' > > Taeung Song (4): > perf tools: Only increase index if perf_evsel__new_idx() succeeds > perf tools: Add missing check for failure in a zalloc() call > perf tools: Use zfree() instead of ad hoc equivalent > perf tools: Use zfree() to avoid keeping dangling pointers > > Uwe Kleine-König (1): > perf probe: Add option --symfs > > Victor Kamensky (1): > perf symbols: Take into account symfs setting when reading file build ID > > Makefile | 6 +- > arch/x86/events/Makefile | 13 +- > arch/x86/events/amd/Makefile | 7 + > arch/x86/events/amd/uncore.c | 204 ++++++++----- > arch/x86/events/intel/pt.c | 6 + > include/linux/kprobes.h | 30 +- > include/linux/perf_event.h | 2 +- > kernel/events/core.c | 223 ++++++++------ > kernel/extable.c | 9 +- > kernel/kprobes.c | 73 +++-- > tools/arch/arm/include/uapi/asm/kvm.h | 9 + > tools/arch/powerpc/include/uapi/asm/kvm.h | 5 + > tools/arch/x86/include/asm/cpufeatures.h | 11 + > tools/arch/x86/include/uapi/asm/vmx.h | 5 + > tools/build/Makefile.build | 10 + > tools/include/linux/compiler.h | 9 + > tools/lib/api/fs/fs.c | 16 + > tools/lib/api/fs/fs.h | 1 + > tools/lib/api/fs/tracing_path.c | 32 +- > tools/lib/bpf/bpf.h | 1 + > tools/lib/bpf/libbpf.c | 264 +++++++++++++++-- > tools/lib/bpf/libbpf.h | 19 +- > tools/lib/subcmd/parse-options.h | 19 +- > tools/lib/traceevent/Makefile | 14 +- > tools/perf/Build | 5 +- > tools/perf/Documentation/perf-c2c.txt | 2 +- > tools/perf/Documentation/perf-ftrace.txt | 36 +++ > tools/perf/Documentation/perf-kallsyms.txt | 24 ++ > tools/perf/Documentation/perf-record.txt | 14 +- > tools/perf/Documentation/perf-sched.txt | 2 + > tools/perf/Documentation/perf-script.txt | 4 +- > tools/perf/Documentation/perf-trace.txt | 8 +- > tools/perf/Makefile.config | 6 +- > tools/perf/Makefile.perf | 1 + > tools/perf/arch/arm64/Makefile | 1 + > tools/perf/arch/arm64/include/dwarf-regs-table.h | 12 +- > tools/perf/arch/arm64/util/dwarf-regs.c | 15 +- > tools/perf/bench/numa.c | 6 +- > tools/perf/builtin-c2c.c | 3 +- > tools/perf/builtin-ftrace.c | 265 +++++++++++++++++ > tools/perf/builtin-help.c | 8 +- > tools/perf/builtin-kallsyms.c | 67 +++++ > tools/perf/builtin-kmem.c | 8 +- > tools/perf/builtin-list.c | 3 + > tools/perf/builtin-probe.c | 2 + > tools/perf/builtin-record.c | 158 +++++++++- > tools/perf/builtin-report.c | 4 +- > tools/perf/builtin-sched.c | 130 ++++++++- > tools/perf/builtin-script.c | 3 +- > tools/perf/builtin-top.c | 6 +- > tools/perf/builtin-trace.c | 120 ++++++-- > tools/perf/builtin.h | 2 + > tools/perf/command-list.txt | 2 + > tools/perf/perf.c | 20 +- > .../arch/x86/broadwellde/uncore-cache.json | 317 ++++++++++++++++++++ > .../arch/x86/broadwellde/uncore-memory.json | 83 ++++++ > .../arch/x86/broadwellde/uncore-power.json | 84 ++++++ > .../arch/x86/broadwellx/uncore-cache.json | 317 ++++++++++++++++++++ > .../arch/x86/broadwellx/uncore-interconnect.json | 28 ++ > .../arch/x86/broadwellx/uncore-memory.json | 83 ++++++ > .../arch/x86/broadwellx/uncore-power.json | 84 ++++++ > .../pmu-events/arch/x86/haswellx/uncore-cache.json | 317 ++++++++++++++++++++ > .../arch/x86/haswellx/uncore-interconnect.json | 28 ++ > .../arch/x86/haswellx/uncore-memory.json | 83 ++++++ > .../pmu-events/arch/x86/haswellx/uncore-power.json | 84 ++++++ > .../pmu-events/arch/x86/ivytown/uncore-cache.json | 322 +++++++++++++++++++++ > .../arch/x86/ivytown/uncore-interconnect.json | 46 +++ > .../pmu-events/arch/x86/ivytown/uncore-memory.json | 75 +++++ > .../pmu-events/arch/x86/ivytown/uncore-power.json | 249 ++++++++++++++++ > .../pmu-events/arch/x86/jaketown/uncore-cache.json | 209 +++++++++++++ > .../arch/x86/jaketown/uncore-interconnect.json | 46 +++ > .../arch/x86/jaketown/uncore-memory.json | 79 +++++ > .../pmu-events/arch/x86/jaketown/uncore-power.json | 248 ++++++++++++++++ > .../arch/x86/knightslanding/uncore-memory.json | 42 +++ > tools/perf/pmu-events/jevents.c | 84 +++++- > tools/perf/pmu-events/jevents.h | 4 +- > tools/perf/pmu-events/pmu-events.h | 3 + > tools/perf/tests/Build | 1 + > tools/perf/tests/bpf.c | 42 ++- > tools/perf/tests/builtin-test.c | 4 + > tools/perf/tests/llvm.c | 2 +- > tools/perf/tests/parse-events.c | 8 +- > tools/perf/tests/tests.h | 1 + > tools/perf/tests/unit_number__scnprintf.c | 37 +++ > tools/perf/ui/browsers/hists.c | 60 ++-- > tools/perf/ui/setup.c | 1 + > tools/perf/util/Build | 1 + > tools/perf/util/bpf-loader.c | 4 +- > tools/perf/util/callchain.c | 16 +- > tools/perf/util/config.c | 23 +- > tools/perf/util/data-convert-bt.c | 7 +- > tools/perf/util/dso.c | 48 ++- > tools/perf/util/event.c | 2 +- > tools/perf/util/evlist.c | 12 +- > tools/perf/util/evlist.h | 2 + > tools/perf/util/header.c | 7 +- > tools/perf/util/hist.c | 4 +- > .../perf/util/intel-pt-decoder/intel-pt-decoder.c | 5 + > .../util/intel-pt-decoder/intel-pt-pkt-decoder.c | 2 + > tools/perf/util/intel-pt.c | 4 +- > tools/perf/util/llvm-utils.c | 4 +- > tools/perf/util/machine.c | 19 ++ > tools/perf/util/machine.h | 1 + > tools/perf/util/parse-events.c | 69 +++-- > tools/perf/util/parse-events.y | 35 ++- > tools/perf/util/pmu.c | 109 ++++--- > tools/perf/util/pmu.h | 1 + > tools/perf/util/probe-event.c | 11 +- > .../perf/util/scripting-engines/trace-event-perl.c | 6 +- > tools/perf/util/session.c | 2 +- > tools/perf/util/strfilter.c | 1 + > tools/perf/util/string.c | 2 + > tools/perf/util/symbol.c | 6 +- > tools/perf/util/thread_map.c | 2 +- > tools/perf/util/trace-event-info.c | 71 +++-- > tools/perf/util/trace-event-parse.c | 17 ++ > tools/perf/util/trace-event-read.c | 77 ++++- > tools/perf/util/trace-event.h | 1 + > tools/perf/util/unwind-libunwind-local.c | 54 +++- > tools/perf/util/util.c | 15 +- > tools/perf/util/util.h | 3 +- > tools/scripts/Makefile.include | 12 +- > 122 files changed, 5101 insertions(+), 550 deletions(-) > create mode 100644 arch/x86/events/amd/Makefile > create mode 100644 tools/perf/Documentation/perf-ftrace.txt > create mode 100644 tools/perf/Documentation/perf-kallsyms.txt > create mode 100644 tools/perf/builtin-ftrace.c > create mode 100644 tools/perf/builtin-kallsyms.c > create mode 100644 tools/perf/pmu-events/arch/x86/broadwellde/uncore-cache.json > create mode 100644 tools/perf/pmu-events/arch/x86/broadwellde/uncore-memory.json > create mode 100644 tools/perf/pmu-events/arch/x86/broadwellde/uncore-power.json > create mode 100644 tools/perf/pmu-events/arch/x86/broadwellx/uncore-cache.json > create mode 100644 tools/perf/pmu-events/arch/x86/broadwellx/uncore-interconnect.json > create mode 100644 tools/perf/pmu-events/arch/x86/broadwellx/uncore-memory.json > create mode 100644 tools/perf/pmu-events/arch/x86/broadwellx/uncore-power.json > create mode 100644 tools/perf/pmu-events/arch/x86/haswellx/uncore-cache.json > create mode 100644 tools/perf/pmu-events/arch/x86/haswellx/uncore-interconnect.json > create mode 100644 tools/perf/pmu-events/arch/x86/haswellx/uncore-memory.json > create mode 100644 tools/perf/pmu-events/arch/x86/haswellx/uncore-power.json > create mode 100644 tools/perf/pmu-events/arch/x86/ivytown/uncore-cache.json > create mode 100644 tools/perf/pmu-events/arch/x86/ivytown/uncore-interconnect.json > create mode 100644 tools/perf/pmu-events/arch/x86/ivytown/uncore-memory.json > create mode 100644 tools/perf/pmu-events/arch/x86/ivytown/uncore-power.json > create mode 100644 tools/perf/pmu-events/arch/x86/jaketown/uncore-cache.json > create mode 100644 tools/perf/pmu-events/arch/x86/jaketown/uncore-interconnect.json > create mode 100644 tools/perf/pmu-events/arch/x86/jaketown/uncore-memory.json > create mode 100644 tools/perf/pmu-events/arch/x86/jaketown/uncore-power.json > create mode 100644 tools/perf/pmu-events/arch/x86/knightslanding/uncore-memory.json > create mode 100644 tools/perf/tests/unit_number__scnprintf.c Pulled, thanks a lot Arnaldo! Ingo
[toc] | [prev] | [standalone]
Page 2 of 2 — ← Prev page 1 [2]
Back to top | Article view | linux.kernel
csiph-web