perf tools: Read the cache line size lazily

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>

diff --git a/tools/perf/perf.c b/tools/perf/perf.c
index d5a0878de816060e91c7bed0e86e7d74c8153f49..cefd8f74630cfd1365444b44f128a0c28ce38725 100644 (file)
--- 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 e65903a695a63af21e713f0460fb933f683a5939..4058ade352a53c06680affea09d96b56abedd81b 100644 (file)
--- 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 035b62e2c60b930f27b74f99fe8658a2d6ade3fe..9e6896293bbdf8a2742df0a844bd1357c5067650 100644 (file)
--- 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 1019bbc5dbd8a00ffb98fa90080fe8881f4d8a78..99ab52165680749b085963a3bb92f41838fd85f1 100644 (file)
--- 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 c9626c20620890ba689faa2207d6ade3f4433874..74d21dfe0d2979dc4ab5ebeee9c4eb119ba98c49 100644 (file)
--- 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);