@@ -119,6 +119,7 @@ OPTIONS
to the previous instruction in cycles. And currently supported only on X86
- simd: Flags describing a SIMD operation. "e" for empty Arm SVE predicate. "p" for partial Arm SVE predicate
- type: Data type of sample memory access.
+ - typeoff: Offset in the data type of sample memory access.
By default, comm, dso and symbol keys are used.
(i.e. --sort comm,dso,symbol)
@@ -3679,6 +3679,7 @@ struct annotated_data_type *hist_entry__get_data_type(struct hist_entry *he)
op_loc->offset,
he->stat.nr_events,
he->stat.period);
+ he->mem_type_off = op_loc->offset;
return mem_type;
}
return NULL;
@@ -83,6 +83,7 @@ enum hist_column {
HISTC_ADDR,
HISTC_SIMD,
HISTC_TYPE,
+ HISTC_TYPE_OFFSET,
HISTC_NR_COLS, /* Last entry */
};
@@ -2146,8 +2146,10 @@ static void sort__type_init(struct hist_entry *he)
return;
he->mem_type = hist_entry__get_data_type(he);
- if (he->mem_type == NULL)
+ if (he->mem_type == NULL) {
he->mem_type = &unknown_type;
+ he->mem_type_off = 0;
+ }
}
static int64_t
@@ -2191,6 +2193,84 @@ struct sort_entry sort_type = {
.se_width_idx = HISTC_TYPE,
};
+/* --sort typeoff */
+
+static int64_t
+sort__typeoff_sort(struct hist_entry *left, struct hist_entry *right)
+{
+ struct annotated_data_type *left_type = left->mem_type;
+ struct annotated_data_type *right_type = right->mem_type;
+ int64_t ret;
+
+ if (!left_type) {
+ sort__type_init(left);
+ left_type = left->mem_type;
+ }
+
+ if (!right_type) {
+ sort__type_init(right);
+ right_type = right->mem_type;
+ }
+
+ ret = strcmp(left_type->self.type_name, right_type->self.type_name);
+ if (ret)
+ return ret;
+ return left->mem_type_off - right->mem_type_off;
+}
+
+static void fill_member_name(char *buf, size_t sz, struct annotated_member *m,
+ int offset, bool first)
+{
+ struct annotated_member *child;
+
+ if (list_empty(&m->children))
+ return;
+
+ list_for_each_entry(child, &m->children, node) {
+ if (child->offset <= offset && offset < child->offset + child->size) {
+ int len = 0;
+
+ /* It can have anonymous struct/union members */
+ if (child->var_name) {
+ len = scnprintf(buf, sz, "%s%s",
+ first ? "" : ".", child->var_name);
+ first = false;
+ }
+
+ fill_member_name(buf + len, sz - len, child, offset, first);
+ return;
+ }
+ }
+}
+
+static int hist_entry__typeoff_snprintf(struct hist_entry *he, char *bf,
+ size_t size, unsigned int width __maybe_unused)
+{
+ struct annotated_data_type *he_type = he->mem_type;
+ char buf[4096];
+
+ buf[0] = '\0';
+ if (list_empty(&he_type->self.children))
+ snprintf(buf, sizeof(buf), "no field");
+ else
+ fill_member_name(buf, sizeof(buf), &he_type->self,
+ he->mem_type_off, true);
+ buf[4095] = '\0';
+
+ return repsep_snprintf(bf, size, "%s %+d (%s)", he_type->self.type_name,
+ he->mem_type_off, buf);
+}
+
+struct sort_entry sort_type_offset = {
+ .se_header = "Data Type Offset",
+ .se_cmp = sort__type_cmp,
+ .se_collapse = sort__typeoff_sort,
+ .se_sort = sort__typeoff_sort,
+ .se_init = sort__type_init,
+ .se_snprintf = hist_entry__typeoff_snprintf,
+ .se_width_idx = HISTC_TYPE_OFFSET,
+};
+
struct sort_dimension {
const char *name;
@@ -2247,6 +2327,7 @@ static struct sort_dimension common_sort_dimensions[] = {
DIM(SORT_GLOBAL_RETIRE_LAT, "retire_lat", sort_global_p_stage_cyc),
DIM(SORT_SIMD, "simd", sort_simd),
DIM(SORT_ANNOTATE_DATA_TYPE, "type", sort_type),
+ DIM(SORT_ANNOTATE_DATA_TYPE_OFFSET, "typeoff", sort_type_offset),
};
#undef DIM
@@ -113,6 +113,7 @@ struct hist_entry {
u64 p_stage_cyc;
u8 cpumode;
u8 depth;
+ int mem_type_off;
struct simd_flags simd_flags;
/* We are added by hists__add_dummy_entry. */
@@ -247,6 +248,7 @@ enum sort_type {
SORT_GLOBAL_RETIRE_LAT,
SORT_SIMD,
SORT_ANNOTATE_DATA_TYPE,
+ SORT_ANNOTATE_DATA_TYPE_OFFSET,
/* branch stack specific sort keys */
__SORT_BRANCH_STACK,
The typeoff sort key shows the data type name, offset and the name of the field. This is useful to see which field in the struct is accessed most frequently. $ perf report -s type,typeoff --hierarchy --stdio ... # Overhead Data Type / Data Type Offset # ............ ............................ # ... 1.23% struct cfs_rq 0.19% struct cfs_rq +404 (throttle_count) 0.19% struct cfs_rq +0 (load.weight) 0.19% struct cfs_rq +336 (leaf_cfs_rq_list.next) 0.09% struct cfs_rq +272 (propagate) 0.09% struct cfs_rq +196 (removed.nr) 0.09% struct cfs_rq +80 (curr) 0.09% struct cfs_rq +544 (lt_b_children_throttled) 0.06% struct cfs_rq +320 (rq) Signed-off-by: Namhyung Kim <namhyung@kernel.org> --- tools/perf/Documentation/perf-report.txt | 1 + tools/perf/util/annotate.c | 1 + tools/perf/util/hist.h | 1 + tools/perf/util/sort.c | 83 +++++++++++++++++++++++- tools/perf/util/sort.h | 2 + 5 files changed, 87 insertions(+), 1 deletion(-)