From: Arnaldo Carvalho de Melo <acme@kernel.org>
To: Ingo Molnar <mingo@kernel.org>
Cc: Clark Williams <williams@redhat.com>,
linux-kernel@vger.kernel.org, linux-perf-users@vger.kernel.org,
Arnaldo Carvalho de Melo <acme@redhat.com>,
Adrian Hunter <adrian.hunter@intel.com>,
David Ahern <dsahern@gmail.com>, Jiri Olsa <jolsa@kernel.org>,
Namhyung Kim <namhyung@kernel.org>,
Wang Nan <wangnan0@huawei.com>
Subject: [PATCH 10/18] perf tools: Read the cache line size lazily
Date: Sat, 19 May 2018 07:54:59 -0300 [thread overview]
Message-ID: <20180519105507.16450-11-acme@kernel.org> (raw)
In-Reply-To: <20180519105507.16450-1-acme@kernel.org>
From: Arnaldo Carvalho de Melo <acme@redhat.com>
It is not read as commonly as 'page_size', so it makes sense to read it
lazily, caching its value when it is first read.
Less files open unconditionally at startup.
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: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-35xhrq91u94uc1djtclek1ie@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/perf/perf.c | 11 -----------
tools/perf/util/sort.c | 4 ++--
tools/perf/util/sort.h | 4 ++--
tools/perf/util/util.c | 21 ++++++++++++++++++++-
tools/perf/util/util.h | 2 +-
5 files changed, 25 insertions(+), 17 deletions(-)
diff --git a/tools/perf/perf.c b/tools/perf/perf.c
index d5a0878de816..cefd8f74630c 100644
--- a/tools/perf/perf.c
+++ b/tools/perf/perf.c
@@ -421,16 +421,6 @@ void pthread__unblock_sigwinch(void)
pthread_sigmask(SIG_UNBLOCK, &set, NULL);
}
-#ifdef _SC_LEVEL1_DCACHE_LINESIZE
-#define cache_line_size(cacheline_sizep) *cacheline_sizep = sysconf(_SC_LEVEL1_DCACHE_LINESIZE)
-#else
-static void cache_line_size(int *cacheline_sizep)
-{
- if (sysfs__read_int("devices/system/cpu/cpu0/cache/index0/coherency_line_size", cacheline_sizep))
- pr_debug("cannot determine cache line size");
-}
-#endif
-
int main(int argc, const char **argv)
{
int err;
@@ -444,7 +434,6 @@ int main(int argc, const char **argv)
/* The page_size is placed in util object. */
page_size = sysconf(_SC_PAGE_SIZE);
- cache_line_size(&cacheline_size);
if (sysctl__read_int("kernel/perf_event_max_stack", &value) == 0)
sysctl_perf_event_max_stack = value;
diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c
index e65903a695a6..4058ade352a5 100644
--- a/tools/perf/util/sort.c
+++ b/tools/perf/util/sort.c
@@ -2582,7 +2582,7 @@ int sort_dimension__add(struct perf_hpp_list *list, const char *tok,
if (sort__mode != SORT_MODE__MEMORY)
return -EINVAL;
- if (sd->entry == &sort_mem_dcacheline && cacheline_size == 0)
+ if (sd->entry == &sort_mem_dcacheline && cacheline_size() == 0)
return -EINVAL;
if (sd->entry == &sort_mem_daddr_sym)
@@ -2628,7 +2628,7 @@ static int setup_sort_list(struct perf_hpp_list *list, char *str,
if (*tok) {
ret = sort_dimension__add(list, tok, evlist, level);
if (ret == -EINVAL) {
- if (!cacheline_size && !strncasecmp(tok, "dcacheline", strlen(tok)))
+ if (!cacheline_size() && !strncasecmp(tok, "dcacheline", strlen(tok)))
pr_err("The \"dcacheline\" --sort key needs to know the cacheline size and it couldn't be determined on this system");
else
pr_err("Invalid --sort key: `%s'", tok);
diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h
index 035b62e2c60b..9e6896293bbd 100644
--- a/tools/perf/util/sort.h
+++ b/tools/perf/util/sort.h
@@ -186,13 +186,13 @@ static inline float hist_entry__get_percent_limit(struct hist_entry *he)
static inline u64 cl_address(u64 address)
{
/* return the cacheline of the address */
- return (address & ~(cacheline_size - 1));
+ return (address & ~(cacheline_size() - 1));
}
static inline u64 cl_offset(u64 address)
{
/* return the cacheline of the address */
- return (address & (cacheline_size - 1));
+ return (address & (cacheline_size() - 1));
}
enum sort_mode {
diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c
index 1019bbc5dbd8..99ab52165680 100644
--- a/tools/perf/util/util.c
+++ b/tools/perf/util/util.c
@@ -38,7 +38,26 @@ void perf_set_multithreaded(void)
}
unsigned int page_size;
-int cacheline_size;
+
+#ifdef _SC_LEVEL1_DCACHE_LINESIZE
+#define cache_line_size(cacheline_sizep) *cacheline_sizep = sysconf(_SC_LEVEL1_DCACHE_LINESIZE)
+#else
+static void cache_line_size(int *cacheline_sizep)
+{
+ if (sysfs__read_int("devices/system/cpu/cpu0/cache/index0/coherency_line_size", cacheline_sizep))
+ pr_debug("cannot determine cache line size");
+}
+#endif
+
+int cacheline_size(void)
+{
+ static int size;
+
+ if (!size)
+ cache_line_size(&size);
+
+ return size;
+}
int sysctl_perf_event_max_stack = PERF_MAX_STACK_DEPTH;
int sysctl_perf_event_max_contexts_per_stack = PERF_MAX_CONTEXTS_PER_STACK;
diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h
index c9626c206208..74d21dfe0d29 100644
--- a/tools/perf/util/util.h
+++ b/tools/perf/util/util.h
@@ -43,7 +43,7 @@ size_t hex_width(u64 v);
int hex2u64(const char *ptr, u64 *val);
extern unsigned int page_size;
-extern int cacheline_size;
+int __pure cacheline_size(void);
int fetch_kernel_version(unsigned int *puint,
char *str, size_t str_sz);
--
2.14.3
next prev parent reply other threads:[~2018-05-19 10:54 UTC|newest]
Thread overview: 20+ messages / expand[flat|nested] mbox.gz Atom feed top
2018-05-19 10:54 [GIT PULL 00/18] perf/core improvements and fixes Arnaldo Carvalho de Melo
2018-05-19 10:54 ` [PATCH 01/18] perf config: Call perf_config__init() lazily Arnaldo Carvalho de Melo
2018-05-19 10:54 ` [PATCH 02/18] tools lib api: The tracing_mnt variable doesn't need to be global Arnaldo Carvalho de Melo
2018-05-19 10:54 ` [PATCH 03/18] tools lib api: Unexport 'tracing_path' variable Arnaldo Carvalho de Melo
2018-05-19 10:54 ` [PATCH 04/18] tools lib api fs tracing_path: Introduce get/put_events_file() helpers Arnaldo Carvalho de Melo
2018-05-19 10:54 ` [PATCH 05/18] perf tools: Reuse the path to the tracepoint /events/ directory Arnaldo Carvalho de Melo
2018-05-19 10:54 ` [PATCH 06/18] perf parse-events: Use get/put_events_file() Arnaldo Carvalho de Melo
2018-05-19 10:54 ` [PATCH 07/18] tools lib api fs tracing_path: Introduce opendir() method Arnaldo Carvalho de Melo
2018-05-19 10:54 ` [PATCH 08/18] tools lib api fs tracing_path: Make tracing_events_path private Arnaldo Carvalho de Melo
2018-05-19 10:54 ` [PATCH 09/18] tools include compiler-gcc: Add __pure attribute helper Arnaldo Carvalho de Melo
2018-05-19 10:54 ` Arnaldo Carvalho de Melo [this message]
2018-05-19 10:55 ` [PATCH 11/18] perf tools: No need to unconditionally read the max_stack sysctls Arnaldo Carvalho de Melo
2018-05-19 10:55 ` [PATCH 12/18] perf script: Show virtual addresses instead of offsets Arnaldo Carvalho de Melo
2018-05-19 10:55 ` [PATCH 13/18] perf script: Show symbol offsets by default Arnaldo Carvalho de Melo
2018-05-19 10:55 ` [PATCH 14/18] perf annotate: Record the min/max cycles Arnaldo Carvalho de Melo
2018-05-19 10:55 ` [PATCH 15/18] perf annotate: Create hotkey 'c' to show " Arnaldo Carvalho de Melo
2018-05-19 10:55 ` [PATCH 16/18] perf bpf: Fixup include and examples install messages Arnaldo Carvalho de Melo
2018-05-19 10:55 ` [PATCH 17/18] perf machine: Add machine__is() to identify machine arch Arnaldo Carvalho de Melo
2018-05-19 10:55 ` [PATCH 18/18] perf tools: Fix kernel_start for PTI on x86 Arnaldo Carvalho de Melo
2018-05-19 11:33 ` [GIT PULL 00/18] perf/core improvements and fixes Ingo Molnar
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=20180519105507.16450-11-acme@kernel.org \
--to=acme@kernel.org \
--cc=acme@redhat.com \
--cc=adrian.hunter@intel.com \
--cc=dsahern@gmail.com \
--cc=jolsa@kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-perf-users@vger.kernel.org \
--cc=mingo@kernel.org \
--cc=namhyung@kernel.org \
--cc=wangnan0@huawei.com \
--cc=williams@redhat.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;
as well as URLs for NNTP newsgroup(s).