From: kan.liang@linux.intel.com
To: peterz@infradead.org, acme@redhat.com, mingo@kernel.org,
linux-kernel@vger.kernel.org
Cc: jolsa@kernel.org, namhyung@kernel.org,
vitaly.slobodskoy@intel.com, pavel.gerasimov@intel.com,
ak@linux.intel.com, eranian@google.com, mpe@ellerman.id.au,
Kan Liang <kan.liang@linux.intel.com>
Subject: [PATCH V4 03/13] perf tools: Support new branch sample type for LBR TOS
Date: Tue, 19 Nov 2019 06:34:01 -0800 [thread overview]
Message-ID: <20191119143411.3482-4-kan.liang@linux.intel.com> (raw)
In-Reply-To: <20191119143411.3482-1-kan.liang@linux.intel.com>
From: Kan Liang <kan.liang@linux.intel.com>
Support new branch sample type for LBR TOS.
Enable LBR_TOS by default in LBR call stack mode.
If kernel doesn't support the sample type, switching it off.
Add a new branch options "tos" for the new branch sample type.
The branch sample type is 64 bits. Change int to u64 for mode in
struct branch_mode and bit in struct bit_names.
Set tos to -1ULL if the LBR TOS information is unavailable.
Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
---
tools/include/uapi/linux/perf_event.h | 16 ++++++++++++++--
tools/perf/util/event.h | 1 +
tools/perf/util/evsel.c | 20 +++++++++++++++++---
tools/perf/util/evsel.h | 6 ++++++
tools/perf/util/parse-branch-options.c | 3 ++-
tools/perf/util/perf_event_attr_fprintf.c | 3 ++-
6 files changed, 42 insertions(+), 7 deletions(-)
diff --git a/tools/include/uapi/linux/perf_event.h b/tools/include/uapi/linux/perf_event.h
index bb7b271397a6..c2da61c9ace7 100644
--- a/tools/include/uapi/linux/perf_event.h
+++ b/tools/include/uapi/linux/perf_event.h
@@ -180,7 +180,10 @@ enum perf_branch_sample_type_shift {
PERF_SAMPLE_BRANCH_TYPE_SAVE_SHIFT = 16, /* save branch type */
- PERF_SAMPLE_BRANCH_MAX_SHIFT /* non-ABI */
+ PERF_SAMPLE_BRANCH_MAX_SHIFT = 17, /* non-ABI */
+
+ /* PMU specific */
+ PERF_SAMPLE_BRANCH_LBR_TOS_SHIFT = 63, /* save LBR TOS */
};
enum perf_branch_sample_type {
@@ -208,8 +211,13 @@ enum perf_branch_sample_type {
1U << PERF_SAMPLE_BRANCH_TYPE_SAVE_SHIFT,
PERF_SAMPLE_BRANCH_MAX = 1U << PERF_SAMPLE_BRANCH_MAX_SHIFT,
+
+ PERF_SAMPLE_BRANCH_LBR_TOS = 1ULL << PERF_SAMPLE_BRANCH_LBR_TOS_SHIFT,
};
+#define PERF_SAMPLE_BRANCH_MASK ((PERF_SAMPLE_BRANCH_MAX - 1) |\
+ PERF_SAMPLE_BRANCH_LBR_TOS)
+
/*
* Common flow change classification
*/
@@ -849,7 +857,11 @@ enum perf_event_type {
* char data[size];}&& PERF_SAMPLE_RAW
*
* { u64 nr;
- * { u64 from, to, flags } lbr[nr];} && PERF_SAMPLE_BRANCH_STACK
+ * { u64 from, to, flags } lbr[nr];
+ *
+ * # only available if PERF_SAMPLE_BRANCH_LBR_TOS is set
+ * u64 tos;
+ * } && PERF_SAMPLE_BRANCH_STACK
*
* { u64 abi; # enum perf_sample_regs_abi
* u64 regs[weight(mask)]; } && PERF_SAMPLE_REGS_USER
diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h
index a0a0c91cde4a..98794758546b 100644
--- a/tools/perf/util/event.h
+++ b/tools/perf/util/event.h
@@ -130,6 +130,7 @@ struct perf_sample {
u32 raw_size;
u64 data_src;
u64 phys_addr;
+ u64 lbr_tos;
u32 flags;
u16 insn_len;
u8 cpumode;
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 1bf60f325608..b19669eb4437 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -712,7 +712,8 @@ static void __perf_evsel__config_callchain(struct evsel *evsel,
attr->branch_sample_type = PERF_SAMPLE_BRANCH_USER |
PERF_SAMPLE_BRANCH_CALL_STACK |
PERF_SAMPLE_BRANCH_NO_CYCLES |
- PERF_SAMPLE_BRANCH_NO_FLAGS;
+ PERF_SAMPLE_BRANCH_NO_FLAGS |
+ PERF_SAMPLE_BRANCH_LBR_TOS;
}
} else
pr_warning("Cannot use LBR callstack with branch stack. "
@@ -763,7 +764,8 @@ perf_evsel__reset_callgraph(struct evsel *evsel,
if (param->record_mode == CALLCHAIN_LBR) {
perf_evsel__reset_sample_bit(evsel, BRANCH_STACK);
attr->branch_sample_type &= ~(PERF_SAMPLE_BRANCH_USER |
- PERF_SAMPLE_BRANCH_CALL_STACK);
+ PERF_SAMPLE_BRANCH_CALL_STACK |
+ PERF_SAMPLE_BRANCH_LBR_TOS);
}
if (param->record_mode == CALLCHAIN_DWARF) {
perf_evsel__reset_sample_bit(evsel, REGS_USER);
@@ -1641,6 +1643,8 @@ int evsel__open(struct evsel *evsel, struct perf_cpu_map *cpus,
evsel->core.attr.ksymbol = 0;
if (perf_missing_features.bpf)
evsel->core.attr.bpf_event = 0;
+ if (perf_missing_features.lbr_tos)
+ evsel->core.attr.branch_sample_type &= ~PERF_SAMPLE_BRANCH_LBR_TOS;
retry_sample_id:
if (perf_missing_features.sample_id_all)
evsel->core.attr.sample_id_all = 0;
@@ -1752,7 +1756,12 @@ int evsel__open(struct evsel *evsel, struct perf_cpu_map *cpus,
* Must probe features in the order they were added to the
* perf_event_attr interface.
*/
- if (!perf_missing_features.aux_output && evsel->core.attr.aux_output) {
+ if (!perf_missing_features.lbr_tos &&
+ (evsel->core.attr.branch_sample_type & PERF_SAMPLE_BRANCH_LBR_TOS)) {
+ perf_missing_features.lbr_tos = true;
+ pr_debug2("switching off LBR TOS support\n");
+ goto fallback_missing_features;
+ } else if (!perf_missing_features.aux_output && evsel->core.attr.aux_output) {
perf_missing_features.aux_output = true;
pr_debug2_peo("Kernel has no attr.aux_output support, bailing out\n");
goto out_close;
@@ -2129,6 +2138,11 @@ int perf_evsel__parse_sample(struct evsel *evsel, union perf_event *event,
sz = data->branch_stack->nr * sizeof(struct branch_entry);
OVERFLOW_CHECK(array, sz, max_size);
array = (void *)array + sz;
+
+ if (perf_evsel__has_lbr_tos(evsel))
+ data->lbr_tos = *array++;
+ else
+ data->lbr_tos = -1ULL;
}
if (type & PERF_SAMPLE_REGS_USER) {
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index ddc5ee6f6592..43a9fd83f791 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -115,6 +115,7 @@ struct perf_missing_features {
bool ksymbol;
bool bpf;
bool aux_output;
+ bool lbr_tos;
};
extern struct perf_missing_features perf_missing_features;
@@ -377,6 +378,11 @@ for ((_evsel) = _leader; \
(_evsel) && (_evsel)->leader == (_leader); \
(_evsel) = list_entry((_evsel)->core.node.next, struct evsel, core.node))
+static inline bool perf_evsel__has_lbr_tos(const struct evsel *evsel)
+{
+ return evsel->core.attr.branch_sample_type & PERF_SAMPLE_BRANCH_LBR_TOS;
+}
+
static inline bool perf_evsel__has_branch_callstack(const struct evsel *evsel)
{
return evsel->core.attr.branch_sample_type & PERF_SAMPLE_BRANCH_CALL_STACK;
diff --git a/tools/perf/util/parse-branch-options.c b/tools/perf/util/parse-branch-options.c
index bb4aa88c50a8..ce8b9ffc0663 100644
--- a/tools/perf/util/parse-branch-options.c
+++ b/tools/perf/util/parse-branch-options.c
@@ -13,7 +13,7 @@
struct branch_mode {
const char *name;
- int mode;
+ u64 mode;
};
static const struct branch_mode branch_modes[] = {
@@ -32,6 +32,7 @@ static const struct branch_mode branch_modes[] = {
BRANCH_OPT("call", PERF_SAMPLE_BRANCH_CALL),
BRANCH_OPT("save_type", PERF_SAMPLE_BRANCH_TYPE_SAVE),
BRANCH_OPT("stack", PERF_SAMPLE_BRANCH_CALL_STACK),
+ BRANCH_OPT("tos", PERF_SAMPLE_BRANCH_LBR_TOS),
BRANCH_END
};
diff --git a/tools/perf/util/perf_event_attr_fprintf.c b/tools/perf/util/perf_event_attr_fprintf.c
index d4ad3f04923a..3411b67ea92a 100644
--- a/tools/perf/util/perf_event_attr_fprintf.c
+++ b/tools/perf/util/perf_event_attr_fprintf.c
@@ -8,7 +8,7 @@
#include "util/evsel_fprintf.h"
struct bit_names {
- int bit;
+ u64 bit;
const char *name;
};
@@ -50,6 +50,7 @@ static void __p_branch_sample_type(char *buf, size_t size, u64 value)
bit_name(ABORT_TX), bit_name(IN_TX), bit_name(NO_TX),
bit_name(COND), bit_name(CALL_STACK), bit_name(IND_JUMP),
bit_name(CALL), bit_name(NO_FLAGS), bit_name(NO_CYCLES),
+ bit_name(LBR_TOS),
{ .name = NULL, }
};
#undef bit_name
--
2.17.1
next prev parent reply other threads:[~2019-11-19 14:35 UTC|newest]
Thread overview: 21+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-11-19 14:33 [PATCH V4 00/13] Stitch LBR call stack kan.liang
2019-11-19 14:33 ` [PATCH V4 01/13] perf/core: Add new branch sample type for LBR TOS kan.liang
2019-11-19 19:02 ` Stephane Eranian
2019-11-19 22:25 ` Liang, Kan
2019-11-19 22:51 ` Stephane Eranian
2019-11-20 15:06 ` Liang, Kan
2019-11-19 14:34 ` [PATCH V4 02/13] perf/x86/intel: Output LBR TOS information kan.liang
2019-11-19 14:34 ` kan.liang [this message]
2019-11-19 19:00 ` [PATCH V4 03/13] perf tools: Support new branch sample type for LBR TOS Stephane Eranian
2019-11-19 21:31 ` Peter Zijlstra
2019-11-19 22:17 ` Liang, Kan
2019-11-19 14:34 ` [PATCH V4 04/13] perf header: Add check for event attr kan.liang
2019-11-19 14:34 ` [PATCH V4 05/13] perf pmu: Add support for PMU capabilities kan.liang
2019-11-19 14:34 ` [PATCH V4 06/13] perf header: Support CPU " kan.liang
2019-11-19 14:34 ` [PATCH V4 07/13] perf machine: Refine the function for LBR call stack reconstruction kan.liang
2019-11-19 14:34 ` [PATCH V4 08/13] perf tools: Stitch LBR call stack kan.liang
2019-11-19 14:34 ` [PATCH V4 09/13] perf report: Add option to enable the LBR stitching approach kan.liang
2019-11-19 14:34 ` [PATCH V4 10/13] perf script: " kan.liang
2019-11-19 14:34 ` [PATCH V4 11/13] perf top: " kan.liang
2019-11-19 14:34 ` [PATCH V4 12/13] perf c2c: " kan.liang
2019-11-19 14:34 ` [RFC PATCH V4 13/13] perf hist: Add fast path for duplicate entries check approach kan.liang
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20191119143411.3482-4-kan.liang@linux.intel.com \
--to=kan.liang@linux.intel.com \
--cc=acme@redhat.com \
--cc=ak@linux.intel.com \
--cc=eranian@google.com \
--cc=jolsa@kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=mingo@kernel.org \
--cc=mpe@ellerman.id.au \
--cc=namhyung@kernel.org \
--cc=pavel.gerasimov@intel.com \
--cc=peterz@infradead.org \
--cc=vitaly.slobodskoy@intel.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.