bpftool: Add {i,d}tlb_misses support for bpftool profile

Commit 47c09d6a("bpftool: Introduce "prog profile" command")
introduced "bpftool prog profile" command which can be used
to profile bpf program with metrics like # of instructions,

This patch added support for itlb_misses and dtlb_misses.
During an internal bpf program performance evaluation,
I found these two metrics are also very useful. The following
is an example output:

 $ bpftool prog profile id 324 duration 3 cycles itlb_misses

           1885029 run_cnt
        5134686073 cycles
            306893 itlb_misses

 $ bpftool prog profile id 324 duration 3 cycles dtlb_misses

           1827382 run_cnt
        4943593648 cycles
           5975636 dtlb_misses

 $ bpftool prog profile id 324 duration 3 cycles llc_misses

           1836527 run_cnt
        5019612972 cycles
           4161041 llc_misses

From the above, we can see quite some dtlb misses, 3 dtlb misses
perf prog run. This might be something worth further investigation.
Signed-off-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Song Liu <songliubraving@fb.com>
Link: https://lore.kernel.org/bpf/20201119073039.4060095-1-yhs@fb.com

tools/bpf/bpftool/prog.c

@@ -1717,6 +1717,34 @@ struct profile_metric {
 		.ratio_desc = "LLC misses per million insns",
 		.ratio_mul = 1e6,
 	},
+	{
+		.name = "itlb_misses",
+		.attr = {
+			.type = PERF_TYPE_HW_CACHE,
+			.config =
+				PERF_COUNT_HW_CACHE_ITLB |
+				(PERF_COUNT_HW_CACHE_OP_READ << 8) |
+				(PERF_COUNT_HW_CACHE_RESULT_MISS << 16),
+			.exclude_user = 1
+		},
+		.ratio_metric = 2,
+		.ratio_desc = "itlb misses per million insns",
+		.ratio_mul = 1e6,
+	},
+	{
+		.name = "dtlb_misses",
+		.attr = {
+			.type = PERF_TYPE_HW_CACHE,
+			.config =
+				PERF_COUNT_HW_CACHE_DTLB |
+				(PERF_COUNT_HW_CACHE_OP_READ << 8) |
+				(PERF_COUNT_HW_CACHE_RESULT_MISS << 16),
+			.exclude_user = 1
+		},
+		.ratio_metric = 2,
+		.ratio_desc = "dtlb misses per million insns",
+		.ratio_mul = 1e6,
+	},
 };
 
 static __u64 profile_total_count;
@@ -2109,7 +2137,7 @@ static int do_help(int argc, char **argv)
 		"                 struct_ops | fentry | fexit | freplace | sk_lookup }\n"
 		"       ATTACH_TYPE := { msg_verdict | stream_verdict | stream_parser |\n"
 		"                        flow_dissector }\n"
-		"       METRIC := { cycles | instructions | l1d_loads | llc_misses }\n"
+		"       METRIC := { cycles | instructions | l1d_loads | llc_misses | itlb_misses | dtlb_misses }\n"
 		"       " HELP_SPEC_OPTIONS "\n"
 		"",
 		bin_name, argv[-2]);