This is a breakdown of perf_mem_data_src.mem_lvl_num. But it's also
divided into two parts because the combination is bigger than 8.
Since there are many entries for different cache levels, 'cache' field
focuses on them. I generalized buffers like LFB, MAB and MHB to L1-buf
and L2-buf.
The rest goes to 'memory' field which can be RAM, CXL, PMEM, IO, etc.
$ perf mem report -F cache,mem,dso --stdio
...
#
# -------------- Cache -------------- --- Memory ---
# L1 L2 L3 L1-buf Other RAM Other Shared Object
# ................................... .............. ....................................
#
53.9% 3.6% 16.2% 21.6% 4.8% 4.8% 95.2% [kernel.kallsyms]
64.7% 1.7% 3.5% 17.4% 12.8% 12.8% 87.2% chrome (deleted)
78.3% 2.8% 0.0% 1.0% 17.9% 17.9% 82.1% libc.so.6
39.6% 1.5% 0.0% 5.7% 53.2% 53.2% 46.8% libxul.so
26.2% 0.0% 0.0% 0.0% 73.8% 73.8% 26.2% [unknown]
85.5% 0.0% 0.0% 14.5% 0.0% 0.0% 100.0% libspa-audioconvert.so
66.3% 4.4% 0.0% 29.4% 0.0% 0.0% 100.0% libglib-2.0.so.0.8200.1 (deleted)
1.9% 0.0% 0.0% 0.0% 98.1% 98.1% 1.9% libmutter-cogl-15.so.0.0.0 (deleted)
10.6% 0.0% 0.0% 89.4% 0.0% 0.0% 100.0% libpulsecommon-16.1.so
0.0% 0.0% 0.0% 100.0% 0.0% 0.0% 100.0% libfreeblpriv3.so (deleted)
...
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Leo Yan <leo.yan@arm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ravi Bangoria <ravi.bangoria@amd.com>
Link: https://lore.kernel.org/r/20250430205548.789750-10-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
__HPP_COLOR_ACC_PERCENT_FN(overhead_acc, period, PERF_HPP_FMT_TYPE__PERCENT)
__HPP_COLOR_ACC_PERCENT_FN(latency_acc, latency, PERF_HPP_FMT_TYPE__LATENCY)
__HPP_COLOR_MEM_STAT_FN(op, OP)
+__HPP_COLOR_MEM_STAT_FN(cache, CACHE)
+__HPP_COLOR_MEM_STAT_FN(memory, MEMORY)
#undef __HPP_COLOR_PERCENT_FN
#undef __HPP_COLOR_ACC_PERCENT_FN
hist_browser__hpp_color_latency_acc;
perf_hpp__format[PERF_HPP__MEM_STAT_OP].color =
hist_browser__hpp_color_mem_stat_op;
+ perf_hpp__format[PERF_HPP__MEM_STAT_CACHE].color =
+ hist_browser__hpp_color_mem_stat_cache;
+ perf_hpp__format[PERF_HPP__MEM_STAT_MEMORY].color =
+ hist_browser__hpp_color_mem_stat_memory;
res_sample_init();
}
switch (fmt->idx) {
case PERF_HPP__MEM_STAT_OP:
return PERF_MEM_STAT_OP;
+ case PERF_HPP__MEM_STAT_CACHE:
+ return PERF_MEM_STAT_CACHE;
+ case PERF_HPP__MEM_STAT_MEMORY:
+ return PERF_MEM_STAT_MEMORY;
default:
break;
}
HPP_AVERAGE_FNS(weight3, weight3)
HPP_MEM_STAT_FNS(op, OP)
+HPP_MEM_STAT_FNS(cache, CACHE)
+HPP_MEM_STAT_FNS(memory, MEMORY)
static int64_t hpp__nop_cmp(struct perf_hpp_fmt *fmt __maybe_unused,
struct hist_entry *a __maybe_unused,
HPP__PRINT_FNS("Weight2", weight2, WEIGHT2),
HPP__PRINT_FNS("Weight3", weight3, WEIGHT3),
HPP__MEM_STAT_PRINT_FNS("Mem Op", op, OP),
+ HPP__MEM_STAT_PRINT_FNS("Cache", cache, CACHE),
+ HPP__MEM_STAT_PRINT_FNS("Memory", memory, MEMORY),
};
struct perf_hpp_list perf_hpp_list = {
break;
case PERF_HPP__MEM_STAT_OP:
+ case PERF_HPP__MEM_STAT_CACHE:
+ case PERF_HPP__MEM_STAT_MEMORY:
fmt->len = MEM_STAT_LEN * MEM_STAT_PRINT_LEN;
break;
PERF_HPP__WEIGHT2,
PERF_HPP__WEIGHT3,
PERF_HPP__MEM_STAT_OP,
+ PERF_HPP__MEM_STAT_CACHE,
+ PERF_HPP__MEM_STAT_MEMORY,
PERF_HPP__MAX_INDEX
};
return MEM_STAT_OP_EXEC;
return MEM_STAT_OP_OTHER;
}
+ case PERF_MEM_STAT_CACHE:
+ switch (src.mem_lvl_num) {
+ case PERF_MEM_LVLNUM_L1:
+ return MEM_STAT_CACHE_L1;
+ case PERF_MEM_LVLNUM_L2:
+ return MEM_STAT_CACHE_L2;
+ case PERF_MEM_LVLNUM_L3:
+ return MEM_STAT_CACHE_L3;
+ case PERF_MEM_LVLNUM_L4:
+ return MEM_STAT_CACHE_L4;
+ case PERF_MEM_LVLNUM_LFB:
+ return MEM_STAT_CACHE_L1_BUF;
+ case PERF_MEM_LVLNUM_L2_MHB:
+ return MEM_STAT_CACHE_L2_BUF;
+ default:
+ return MEM_STAT_CACHE_OTHER;
+ }
+ case PERF_MEM_STAT_MEMORY:
+ switch (src.mem_lvl_num) {
+ case PERF_MEM_LVLNUM_MSC:
+ return MEM_STAT_MEMORY_MSC;
+ case PERF_MEM_LVLNUM_RAM:
+ return MEM_STAT_MEMORY_RAM;
+ case PERF_MEM_LVLNUM_UNC:
+ return MEM_STAT_MEMORY_UNC;
+ case PERF_MEM_LVLNUM_CXL:
+ return MEM_STAT_MEMORY_CXL;
+ case PERF_MEM_LVLNUM_IO:
+ return MEM_STAT_MEMORY_IO;
+ case PERF_MEM_LVLNUM_PMEM:
+ return MEM_STAT_MEMORY_PMEM;
+ default:
+ return MEM_STAT_MEMORY_OTHER;
+ }
default:
break;
}
case MEM_STAT_OP_EXEC:
return "Exec";
case MEM_STAT_OP_OTHER:
+ default:
+ return "Other";
+ }
+ case PERF_MEM_STAT_CACHE:
+ switch (idx) {
+ case MEM_STAT_CACHE_L1:
+ return "L1";
+ case MEM_STAT_CACHE_L2:
+ return "L2";
+ case MEM_STAT_CACHE_L3:
+ return "L3";
+ case MEM_STAT_CACHE_L4:
+ return "L4";
+ case MEM_STAT_CACHE_L1_BUF:
+ return "L1-buf";
+ case MEM_STAT_CACHE_L2_BUF:
+ return "L2-buf";
+ case MEM_STAT_CACHE_OTHER:
+ default:
return "Other";
+ }
+ case PERF_MEM_STAT_MEMORY:
+ switch (idx) {
+ case MEM_STAT_MEMORY_RAM:
+ return "RAM";
+ case MEM_STAT_MEMORY_MSC:
+ return "MSC";
+ case MEM_STAT_MEMORY_UNC:
+ return "Uncach";
+ case MEM_STAT_MEMORY_CXL:
+ return "CXL";
+ case MEM_STAT_MEMORY_IO:
+ return "IO";
+ case MEM_STAT_MEMORY_PMEM:
+ return "PMEM";
+ case MEM_STAT_MEMORY_OTHER:
default:
- break;
+ return "Other";
}
default:
break;
enum mem_stat_type {
PERF_MEM_STAT_OP,
+ PERF_MEM_STAT_CACHE,
+ PERF_MEM_STAT_MEMORY,
};
+#define MEM_STAT_PRINT_LEN 7 /* 1 space + 5 digits + 1 percent sign */
+
enum mem_stat_op {
MEM_STAT_OP_LOAD,
MEM_STAT_OP_STORE,
MEM_STAT_OP_OTHER,
};
-#define MEM_STAT_PRINT_LEN 7 /* 1 space + 5 digits + 1 percent sign */
+enum mem_stat_cache {
+ MEM_STAT_CACHE_L1,
+ MEM_STAT_CACHE_L2,
+ MEM_STAT_CACHE_L3,
+ MEM_STAT_CACHE_L4,
+ MEM_STAT_CACHE_L1_BUF,
+ MEM_STAT_CACHE_L2_BUF,
+ MEM_STAT_CACHE_OTHER,
+};
+
+enum mem_stat_memory {
+ MEM_STAT_MEMORY_RAM,
+ MEM_STAT_MEMORY_MSC,
+ MEM_STAT_MEMORY_UNC,
+ MEM_STAT_MEMORY_CXL,
+ MEM_STAT_MEMORY_IO,
+ MEM_STAT_MEMORY_PMEM,
+ MEM_STAT_MEMORY_OTHER,
+};
int mem_stat_index(const enum mem_stat_type mst, const u64 data_src);
const char *mem_stat_name(const enum mem_stat_type mst, const int idx);
DIM(PERF_HPP__WEIGHT3, "p_stage_cyc"),
/* used for output only when SORT_MODE__MEM */
DIM_MEM(PERF_HPP__MEM_STAT_OP, "op"),
+ DIM_MEM(PERF_HPP__MEM_STAT_CACHE, "cache"),
+ DIM_MEM(PERF_HPP__MEM_STAT_MEMORY, "memory"),
};
#undef DIM_MEM