From: Ian Rogers <irogers@google.com>
To: Peter Zijlstra <peterz@infradead.org>,
Ingo Molnar <mingo@redhat.com>,
Arnaldo Carvalho de Melo <acme@kernel.org>,
Mark Rutland <mark.rutland@arm.com>,
Alexander Shishkin <alexander.shishkin@linux.intel.com>,
Jiri Olsa <jolsa@kernel.org>, Namhyung Kim <namhyung@kernel.org>,
Ian Rogers <irogers@google.com>,
Adrian Hunter <adrian.hunter@intel.com>,
Nick Terrell <terrelln@fb.com>,
Kan Liang <kan.liang@linux.intel.com>,
Song Liu <song@kernel.org>, Sandipan Das <sandipan.das@amd.com>,
Anshuman Khandual <anshuman.khandual@arm.com>,
James Clark <james.clark@arm.com>,
Liam Howlett <liam.howlett@oracle.com>,
Miguel Ojeda <ojeda@kernel.org>, Leo Yan <leo.yan@linaro.org>,
German Gomez <german.gomez@arm.com>,
Ravi Bangoria <ravi.bangoria@amd.com>,
Artem Savkov <asavkov@redhat.com>,
Athira Rajeev <atrajeev@linux.vnet.ibm.com>,
Andi Kleen <ak@linux.intel.com>,
linux-kernel@vger.kernel.org, linux-perf-users@vger.kernel.org,
bpf@vger.kernel.org
Subject: [PATCH v2 07/13] perf callchain: Make brtype_stat in callchain_list optional
Date: Wed, 11 Oct 2023 23:23:53 -0700 [thread overview]
Message-ID: <20231012062359.1616786-8-irogers@google.com> (raw)
In-Reply-To: <20231012062359.1616786-1-irogers@google.com>
struct callchain_list is 352bytes in size, 232 of which are
brtype_stat. brtype_stat is only used for certain callchain_list
items so make it optional, allocating when necessary. So that
printing doesn't need to deal with an optional brtype_stat, pass
an empty/zero version.
Before:
```
struct callchain_list {
u64 ip; /* 0 8 */
struct map_symbol ms; /* 8 24 */
struct {
_Bool unfolded; /* 32 1 */
_Bool has_children; /* 33 1 */
}; /* 32 2 */
/* XXX 6 bytes hole, try to pack */
u64 branch_count; /* 40 8 */
u64 from_count; /* 48 8 */
u64 predicted_count; /* 56 8 */
/* --- cacheline 1 boundary (64 bytes) --- */
u64 abort_count; /* 64 8 */
u64 cycles_count; /* 72 8 */
u64 iter_count; /* 80 8 */
u64 iter_cycles; /* 88 8 */
struct branch_type_stat brtype_stat; /* 96 232 */
/* --- cacheline 5 boundary (320 bytes) was 8 bytes ago --- */
const char * srcline; /* 328 8 */
struct list_head list; /* 336 16 */
/* size: 352, cachelines: 6, members: 13 */
/* sum members: 346, holes: 1, sum holes: 6 */
/* last cacheline: 32 bytes */
};
```
After:
```
struct callchain_list {
u64 ip; /* 0 8 */
struct map_symbol ms; /* 8 24 */
struct {
_Bool unfolded; /* 32 1 */
_Bool has_children; /* 33 1 */
}; /* 32 2 */
/* XXX 6 bytes hole, try to pack */
u64 branch_count; /* 40 8 */
u64 from_count; /* 48 8 */
u64 predicted_count; /* 56 8 */
/* --- cacheline 1 boundary (64 bytes) --- */
u64 abort_count; /* 64 8 */
u64 cycles_count; /* 72 8 */
u64 iter_count; /* 80 8 */
u64 iter_cycles; /* 88 8 */
struct branch_type_stat * brtype_stat; /* 96 8 */
const char * srcline; /* 104 8 */
struct list_head list; /* 112 16 */
/* size: 128, cachelines: 2, members: 13 */
/* sum members: 122, holes: 1, sum holes: 6 */
};
```
Signed-off-by: Ian Rogers <irogers@google.com>
---
tools/perf/util/callchain.c | 41 +++++++++++++++++++++++++++++--------
tools/perf/util/callchain.h | 2 +-
2 files changed, 34 insertions(+), 9 deletions(-)
diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c
index 229cedee1e68..0a7919c2af91 100644
--- a/tools/perf/util/callchain.c
+++ b/tools/perf/util/callchain.c
@@ -586,7 +586,7 @@ fill_node(struct callchain_node *node, struct callchain_cursor *cursor)
call = zalloc(sizeof(*call));
if (!call) {
perror("not enough memory for the code path tree");
- return -1;
+ return -ENOMEM;
}
call->ip = cursor_node->ip;
call->ms = cursor_node->ms;
@@ -602,7 +602,15 @@ fill_node(struct callchain_node *node, struct callchain_cursor *cursor)
* branch_from is set with value somewhere else
* to imply it's "to" of a branch.
*/
- call->brtype_stat.branch_to = true;
+ if (!call->brtype_stat) {
+ call->brtype_stat = zalloc(sizeof(*call->brtype_stat));
+ if (!call->brtype_stat) {
+ perror("not enough memory for the code path branch statisitcs");
+ free(call->brtype_stat);
+ return -ENOMEM;
+ }
+ }
+ call->brtype_stat->branch_to = true;
if (cursor_node->branch_flags.predicted)
call->predicted_count = 1;
@@ -610,7 +618,7 @@ fill_node(struct callchain_node *node, struct callchain_cursor *cursor)
if (cursor_node->branch_flags.abort)
call->abort_count = 1;
- branch_type_count(&call->brtype_stat,
+ branch_type_count(call->brtype_stat,
&cursor_node->branch_flags,
cursor_node->branch_from,
cursor_node->ip);
@@ -618,7 +626,8 @@ fill_node(struct callchain_node *node, struct callchain_cursor *cursor)
/*
* It's "from" of a branch
*/
- call->brtype_stat.branch_to = false;
+ if (call->brtype_stat && call->brtype_stat->branch_to)
+ call->brtype_stat->branch_to = false;
call->cycles_count =
cursor_node->branch_flags.cycles;
call->iter_count = cursor_node->nr_loop_iter;
@@ -652,6 +661,7 @@ add_child(struct callchain_node *parent,
list_del_init(&call->list);
map__zput(call->ms.map);
maps__zput(call->ms.maps);
+ zfree(&call->brtype_stat);
free(call);
}
free(new);
@@ -762,7 +772,14 @@ static enum match_result match_chain(struct callchain_cursor_node *node,
/*
* It's "to" of a branch
*/
- cnode->brtype_stat.branch_to = true;
+ if (!cnode->brtype_stat) {
+ cnode->brtype_stat = zalloc(sizeof(*cnode->brtype_stat));
+ if (!cnode->brtype_stat) {
+ perror("not enough memory for the code path branch statisitcs");
+ return MATCH_ERROR;
+ }
+ }
+ cnode->brtype_stat->branch_to = true;
if (node->branch_flags.predicted)
cnode->predicted_count++;
@@ -770,7 +787,7 @@ static enum match_result match_chain(struct callchain_cursor_node *node,
if (node->branch_flags.abort)
cnode->abort_count++;
- branch_type_count(&cnode->brtype_stat,
+ branch_type_count(cnode->brtype_stat,
&node->branch_flags,
node->branch_from,
node->ip);
@@ -778,7 +795,8 @@ static enum match_result match_chain(struct callchain_cursor_node *node,
/*
* It's "from" of a branch
*/
- cnode->brtype_stat.branch_to = false;
+ if (cnode->brtype_stat && cnode->brtype_stat->branch_to)
+ cnode->brtype_stat->branch_to = false;
cnode->cycles_count += node->branch_flags.cycles;
cnode->iter_count += node->nr_loop_iter;
cnode->iter_cycles += node->iter_cycles;
@@ -1026,6 +1044,7 @@ merge_chain_branch(struct callchain_cursor *cursor,
maps__zput(ms.maps);
map__zput(list->ms.map);
maps__zput(list->ms.maps);
+ zfree(&list->brtype_stat);
free(list);
}
@@ -1447,11 +1466,14 @@ static int callchain_counts_printf(FILE *fp, char *bf, int bfsize,
int callchain_list_counts__printf_value(struct callchain_list *clist,
FILE *fp, char *bf, int bfsize)
{
+ static const struct branch_type_stat empty_brtype_stat = {};
+ const struct branch_type_stat *brtype_stat;
u64 branch_count, predicted_count;
u64 abort_count, cycles_count;
u64 iter_count, iter_cycles;
u64 from_count;
+ brtype_stat = clist->brtype_stat ?: &empty_brtype_stat;
branch_count = clist->branch_count;
predicted_count = clist->predicted_count;
abort_count = clist->abort_count;
@@ -1463,7 +1485,7 @@ int callchain_list_counts__printf_value(struct callchain_list *clist,
return callchain_counts_printf(fp, bf, bfsize, branch_count,
predicted_count, abort_count,
cycles_count, iter_count, iter_cycles,
- from_count, &clist->brtype_stat);
+ from_count, brtype_stat);
}
static void free_callchain_node(struct callchain_node *node)
@@ -1476,6 +1498,7 @@ static void free_callchain_node(struct callchain_node *node)
list_del_init(&list->list);
map__zput(list->ms.map);
maps__zput(list->ms.maps);
+ zfree(&list->brtype_stat);
free(list);
}
@@ -1483,6 +1506,7 @@ static void free_callchain_node(struct callchain_node *node)
list_del_init(&list->list);
map__zput(list->ms.map);
maps__zput(list->ms.maps);
+ zfree(&list->brtype_stat);
free(list);
}
@@ -1569,6 +1593,7 @@ int callchain_node__make_parent_list(struct callchain_node *node)
list_del_init(&chain->list);
map__zput(chain->ms.map);
maps__zput(chain->ms.maps);
+ zfree(&chain->brtype_stat);
free(chain);
}
return -ENOMEM;
diff --git a/tools/perf/util/callchain.h b/tools/perf/util/callchain.h
index d2618a47deca..86e8a9e81456 100644
--- a/tools/perf/util/callchain.h
+++ b/tools/perf/util/callchain.h
@@ -129,7 +129,7 @@ struct callchain_list {
u64 cycles_count;
u64 iter_count;
u64 iter_cycles;
- struct branch_type_stat brtype_stat;
+ struct branch_type_stat *brtype_stat;
const char *srcline;
struct list_head list;
};
--
2.42.0.609.gbb76f46606-goog
next prev parent reply other threads:[~2023-10-12 6:24 UTC|newest]
Thread overview: 28+ messages / expand[flat|nested] mbox.gz Atom feed top
2023-10-12 6:23 [PATCH v2 00/13] Improvements to memory use Ian Rogers
2023-10-12 6:23 ` [PATCH v2 01/13] perf machine: Avoid out of bounds LBR memory read Ian Rogers
2023-10-12 6:23 ` [PATCH v2 02/13] libperf rc_check: Make implicit enabling work for GCC Ian Rogers
2023-10-12 6:23 ` [PATCH v2 03/13] perf hist: Add missing puts to hist__account_cycles Ian Rogers
2023-10-18 23:16 ` Namhyung Kim
2023-10-24 16:12 ` Ian Rogers
2023-10-12 6:23 ` [PATCH v2 04/13] perf threads: Remove unused dead thread list Ian Rogers
2023-10-12 6:23 ` [PATCH v2 05/13] perf offcpu: Add missed btf_free Ian Rogers
2023-10-12 6:23 ` [PATCH v2 06/13] perf callchain: Make display use of branch_type_stat const Ian Rogers
2023-10-12 6:23 ` Ian Rogers [this message]
2023-10-12 6:23 ` [PATCH v2 08/13] perf callchain: Minor layout changes to callchain_list Ian Rogers
2023-10-12 6:23 ` [PATCH v2 09/13] perf mem_info: Add and use map_symbol__exit and addr_map_symbol__exit Ian Rogers
2023-10-18 23:20 ` Namhyung Kim
2023-10-24 20:52 ` Ian Rogers
2023-10-12 6:23 ` [PATCH v2 10/13] perf record: Lazy load kernel symbols Ian Rogers
2023-10-19 11:02 ` Adrian Hunter
2023-10-24 18:42 ` Ian Rogers
2023-10-12 6:23 ` [PATCH v2 11/13] libperf: Lazily allocate mmap event copy Ian Rogers
2023-10-12 6:23 ` [PATCH v2 12/13] perf mmap: Lazily initialize zstd streams Ian Rogers
2023-10-18 23:21 ` Namhyung Kim
2023-10-24 19:21 ` Ian Rogers
2023-10-12 6:23 ` [PATCH v2 13/13] perf machine thread: Remove exited threads by default Ian Rogers
2023-10-18 23:30 ` Namhyung Kim
2023-10-19 0:39 ` Ian Rogers
2023-10-20 21:08 ` Namhyung Kim
2023-10-23 14:24 ` Adrian Hunter
2023-10-23 18:49 ` Ian Rogers
2023-10-24 5:19 ` Adrian Hunter
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=20231012062359.1616786-8-irogers@google.com \
--to=irogers@google.com \
--cc=acme@kernel.org \
--cc=adrian.hunter@intel.com \
--cc=ak@linux.intel.com \
--cc=alexander.shishkin@linux.intel.com \
--cc=anshuman.khandual@arm.com \
--cc=asavkov@redhat.com \
--cc=atrajeev@linux.vnet.ibm.com \
--cc=bpf@vger.kernel.org \
--cc=german.gomez@arm.com \
--cc=james.clark@arm.com \
--cc=jolsa@kernel.org \
--cc=kan.liang@linux.intel.com \
--cc=leo.yan@linaro.org \
--cc=liam.howlett@oracle.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-perf-users@vger.kernel.org \
--cc=mark.rutland@arm.com \
--cc=mingo@redhat.com \
--cc=namhyung@kernel.org \
--cc=ojeda@kernel.org \
--cc=peterz@infradead.org \
--cc=ravi.bangoria@amd.com \
--cc=sandipan.das@amd.com \
--cc=song@kernel.org \
--cc=terrelln@fb.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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox