perf stat: Enable iostat mode for x86 platforms

This functionality is based on recently introduced sysfs attributes for
Intel® Xeon® Scalable processor family (code name Skylake-SP):

Commit bb42b3d ("perf/x86/intel/uncore: Expose an Uncore unit to IIO PMON mapping")

Mode is intended to provide four I/O performance metrics in MB per each
PCIe root port:

 - Inbound Read: I/O devices below root port read from the host memory
 - Inbound Write: I/O devices below root port write to the host memory
 - Outbound Read: CPU reads from I/O devices below root port
 - Outbound Write: CPU writes to I/O devices below root port

Each metric requiries only one uncore event which increments at every 4B
transfer in corresponding direction. The formulas to compute metrics
are generic:
    #EventCount * 4B / (1024 * 1024)

Acked-by: Namhyung Kim <namhyung@kernel.org>
Signed-off-by: Alexander Antonov <alexander.antonov@linux.intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Alexey V Bayduraev <alexey.v.bayduraev@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Arnaldo Carvalho de Melo <acme@kernel.org>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://lore.kernel.org/r/20210419094147.15909-4-alexander.antonov@linux.intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

tools/perf/Documentation/perf-iostat.txt

@@ -0,0 +1,88 @@
+perf-iostat(1)
+===============
+
+NAME
+----
+perf-iostat - Show I/O performance metrics
+
+SYNOPSIS
+--------
+[verse]
+'perf iostat' list
+'perf iostat' <ports> -- <command> [<options>]
+
+DESCRIPTION
+-----------
+Mode is intended to provide four I/O performance metrics per each PCIe root port:
+
+- Inbound Read   - I/O devices below root port read from the host memory, in MB
+
+- Inbound Write  - I/O devices below root port write to the host memory, in MB
+
+- Outbound Read  - CPU reads from I/O devices below root port, in MB
+
+- Outbound Write - CPU writes to I/O devices below root port, in MB
+
+OPTIONS
+-------
+<command>...::
+	Any command you can specify in a shell.
+
+list::
+	List all PCIe root ports.
+
+<ports>::
+	Select the root ports for monitoring. Comma-separated list is supported.
+
+EXAMPLES
+--------
+
+1. List all PCIe root ports (example for 2-S platform):
+
+   $ perf iostat list
+   S0-uncore_iio_0<0000:00>
+   S1-uncore_iio_0<0000:80>
+   S0-uncore_iio_1<0000:17>
+   S1-uncore_iio_1<0000:85>
+   S0-uncore_iio_2<0000:3a>
+   S1-uncore_iio_2<0000:ae>
+   S0-uncore_iio_3<0000:5d>
+   S1-uncore_iio_3<0000:d7>
+
+2. Collect metrics for all PCIe root ports:
+
+   $ perf iostat -- dd if=/dev/zero of=/dev/nvme0n1 bs=1M oflag=direct
+   357708+0 records in
+   357707+0 records out
+   375083606016 bytes (375 GB, 349 GiB) copied, 215.974 s, 1.7 GB/s
+
+    Performance counter stats for 'system wide':
+
+      port             Inbound Read(MB)    Inbound Write(MB)    Outbound Read(MB)   Outbound Write(MB)
+   0000:00                    1                    0                    2                    3
+   0000:80                    0                    0                    0                    0
+   0000:17               352552                   43                    0                   21
+   0000:85                    0                    0                    0                    0
+   0000:3a                    3                    0                    0                    0
+   0000:ae                    0                    0                    0                    0
+   0000:5d                    0                    0                    0                    0
+   0000:d7                    0                    0                    0                    0
+
+3. Collect metrics for comma-separated list of PCIe root ports:
+
+   $ perf iostat 0000:17,0:3a -- dd if=/dev/zero of=/dev/nvme0n1 bs=1M oflag=direct
+   357708+0 records in
+   357707+0 records out
+   375083606016 bytes (375 GB, 349 GiB) copied, 197.08 s, 1.9 GB/s
+
+    Performance counter stats for 'system wide':
+
+      port             Inbound Read(MB)    Inbound Write(MB)    Outbound Read(MB)   Outbound Write(MB)
+   0000:17               358559                   44                    0                   22
+   0000:3a                    3                    2                    0                    0
+
+        197.081983474 seconds time elapsed
+
+SEE ALSO
+--------
+linkperf:perf-stat[1]

tools/perf/Makefile.perf

@@ -283,6 +283,7 @@ SCRIPT_SH =
 
 SCRIPT_SH += perf-archive.sh
 SCRIPT_SH += perf-with-kcore.sh
+SCRIPT_SH += perf-iostat.sh
 
 grep-libs = $(filter -l%,$(1))
 strip-libs = $(filter-out -l%,$(1))
@@ -948,6 +949,8 @@ endif
 		$(INSTALL) $(OUTPUT)perf-archive -t '$(DESTDIR_SQ)$(perfexec_instdir_SQ)'
 	$(call QUIET_INSTALL, perf-with-kcore) \
 		$(INSTALL) $(OUTPUT)perf-with-kcore -t '$(DESTDIR_SQ)$(perfexec_instdir_SQ)'
+	$(call QUIET_INSTALL, perf-iostat) \
+		$(INSTALL) $(OUTPUT)perf-iostat -t '$(DESTDIR_SQ)$(perfexec_instdir_SQ)'
 ifndef NO_LIBAUDIT
 	$(call QUIET_INSTALL, strace/groups) \
 		$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(STRACE_GROUPS_INSTDIR_SQ)'; \
@@ -1042,7 +1045,7 @@ bpf-skel-clean:
 	$(call QUIET_CLEAN, bpf-skel) $(RM) -r $(SKEL_TMP_OUT) $(SKELETONS)
 
 clean:: $(LIBTRACEEVENT)-clean $(LIBAPI)-clean $(LIBBPF)-clean $(LIBSUBCMD)-clean $(LIBPERF)-clean fixdep-clean python-clean bpf-skel-clean
-	$(call QUIET_CLEAN, core-objs)  $(RM) $(LIBPERF_A) $(OUTPUT)perf-archive $(OUTPUT)perf-with-kcore $(LANG_BINDINGS)
+	$(call QUIET_CLEAN, core-objs)  $(RM) $(LIBPERF_A) $(OUTPUT)perf-archive $(OUTPUT)perf-with-kcore $(OUTPUT)perf-iostat $(LANG_BINDINGS)
 	$(Q)find $(if $(OUTPUT),$(OUTPUT),.) -name '*.o' -delete -o -name '\.*.cmd' -delete -o -name '\.*.d' -delete
 	$(Q)$(RM) $(OUTPUT).config-detected
 	$(call QUIET_CLEAN, core-progs) $(RM) $(ALL_PROGRAMS) perf perf-read-vdso32 perf-read-vdsox32 $(OUTPUT)pmu-events/jevents $(OUTPUT)$(LIBJVMTI).so

tools/perf/arch/x86/util/Build

@@ -9,6 +9,7 @@ perf-y += event.o
 perf-y += evlist.o
 perf-y += mem-events.o
 perf-y += evsel.o
+perf-y += iostat.o
 
 perf-$(CONFIG_DWARF) += dwarf-regs.o
 perf-$(CONFIG_BPF_PROLOGUE) += dwarf-regs.o