perf mem/c2c: Add load store event mappings for AMD

The 'perf mem' and 'perf c2c' tools are wrappers around 'perf record'
with mem load/ store events. IBS tagged load/store sample provides most
of the information needed for these tools. Wire in the "ibs_op//" event
as mem-ldst event for AMD.

There are some limitations though: Only load/store micro-ops provide
mem/c2c information. Whereas, IBS does not have a way to choose a
particular type of micro-op to tag. This results in many non-LS
micro-ops being tagged which appear as N/A in the perf report. IBS,
being an uncore pmu from kernel point of view[1], does not support per
process monitoring. Thus, perf mem/c2c on AMD are currently supported in
per-cpu mode only.

Example:

  $ sudo perf mem record -- -c 10000
  ^C[ perf record: Woken up 227 times to write data ]
  [ perf record: Captured and wrote 58.760 MB perf.data (836978 samples) ]

  $ sudo perf mem report -F mem,sample,snoop
  Samples: 836K of event 'ibs_op//', Event count (approx.): 8418762
  Memory access                  Samples  Snoop
  N/A                             700620  N/A
  L1 hit                          126675  N/A
  L2 hit                             424  N/A
  L3 hit                             664  HitM
  L3 hit                              10  N/A
  Local RAM hit                        2  N/A
  Remote RAM (1 hop) hit            8558  N/A
  Remote Cache (1 hop) hit             3  N/A
  Remote Cache (1 hop) hit             2  HitM
  Remote Cache (2 hops) hit           10  HitM
  Remote Cache (2 hops) hit            6  N/A
  Uncached hit                         4  N/A
  $

[1]: https://lore.kernel.org/lkml/[email protected]

Signed-off-by: Ravi Bangoria <[email protected]>
Acked-by: Jiri Olsa <[email protected]>
Cc: Alexander Shishkin <[email protected]>
Cc: Ali Saidi <[email protected]>
Cc: Ananth Narayan <[email protected]>
Cc: Andi Kleen <[email protected]>
Cc: Borislav Petkov <[email protected]>
Cc: Dave Hansen <[email protected]>
Cc: H. Peter Anvin <[email protected]>
Cc: Ian Rogers <[email protected]>
Cc: Ingo Molnar <[email protected]>
Cc: Joe Mario <[email protected]>
Cc: Kan Liang <[email protected]>
Cc: Kim Phillips <[email protected]>
Cc: Leo Yan <[email protected]>
Cc: Mark Rutland <[email protected]>
Cc: Namhyung Kim <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Cc: Sandipan Das <[email protected]>
Cc: Santosh Shukla <[email protected]>
Cc: Stephane Eranian <[email protected]>
Cc: Thomas Gleixner <[email protected]>
Cc: [email protected]
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>

tools/perf/Documentation/perf-c2c.txt

@@ -19,9 +19,10 @@ C2C stands for Cache To Cache.
 The perf c2c tool provides means for Shared Data C2C/HITM analysis. It allows
 you to track down the cacheline contentions.
 
-On x86, the tool is based on load latency and precise store facility events
+On Intel, the tool is based on load latency and precise store facility events
 provided by Intel CPUs. On PowerPC, the tool uses random instruction sampling
-with thresholding feature.
+with thresholding feature. On AMD, the tool uses IBS op pmu (due to hardware
+limitations, perf c2c is not supported on Zen3 cpus).
 
 These events provide:
   - memory address of the access
@@ -49,7 +50,8 @@ RECORD OPTIONS
 
 -l::
 --ldlat::
-	Configure mem-loads latency. (x86 only)
+	Configure mem-loads latency. Supported on Intel and Arm64 processors
+	only. Ignored on other archs.
 
 -k::
 --all-kernel::
@@ -135,11 +137,15 @@ Following perf record options are configured by default:
   -W,-d,--phys-data,--sample-cpu
 
 Unless specified otherwise with '-e' option, following events are monitored by
-default on x86:
+default on Intel:
 
   cpu/mem-loads,ldlat=30/P
   cpu/mem-stores/P
 
+following on AMD:
+
+  ibs_op//
+
 and following on PowerPC:
 
   cpu/mem-loads/

tools/perf/Documentation/perf-mem.txt

@@ -85,7 +85,8 @@ RECORD OPTIONS
 	Be more verbose (show counter open errors, etc)
 
 --ldlat <n>::
-	Specify desired latency for loads event. (x86 only)
+	Specify desired latency for loads event. Supported on Intel and Arm64
+	processors only. Ignored on other archs.
 
 In addition, for report all perf report options are valid, and for record
 all perf record options.

tools/perf/arch/x86/util/mem-events.c

@@ -1,7 +1,9 @@
 // SPDX-License-Identifier: GPL-2.0
 #include "util/pmu.h"
+#include "util/env.h"
 #include "map_symbol.h"
 #include "mem-events.h"
+#include "linux/string.h"
 
 static char mem_loads_name[100];
 static bool mem_loads_name__init;
@@ -12,18 +14,43 @@ static char mem_stores_name[100];
 
 #define E(t, n, s) { .tag = t, .name = n, .sysfs_name = s }
 
-static struct perf_mem_event perf_mem_events[PERF_MEM_EVENTS__MAX] = {
+static struct perf_mem_event perf_mem_events_intel[PERF_MEM_EVENTS__MAX] = {
 	E("ldlat-loads",	"%s/mem-loads,ldlat=%u/P",	"%s/events/mem-loads"),
 	E("ldlat-stores",	"%s/mem-stores/P",		"%s/events/mem-stores"),
 	E(NULL,			NULL,				NULL),
 };
 
+static struct perf_mem_event perf_mem_events_amd[PERF_MEM_EVENTS__MAX] = {
+	E(NULL,		NULL,		NULL),
+	E(NULL,		NULL,		NULL),
+	E("mem-ldst",	"ibs_op//",	"ibs_op"),
+};
+
+static int perf_mem_is_amd_cpu(void)
+{
+	struct perf_env env = { .total_mem = 0, };
+
+	perf_env__cpuid(&env);
+	if (env.cpuid && strstarts(env.cpuid, "AuthenticAMD"))
+		return 1;
+	return -1;
+}
+
 struct perf_mem_event *perf_mem_events__ptr(int i)
 {
+	/* 0: Uninitialized, 1: Yes, -1: No */
+	static int is_amd;
+
 	if (i >= PERF_MEM_EVENTS__MAX)
 		return NULL;
 
-	return &perf_mem_events[i];
+	if (!is_amd)
+		is_amd = perf_mem_is_amd_cpu();
+
+	if (is_amd == 1)
+		return &perf_mem_events_amd[i];
+
+	return &perf_mem_events_intel[i];
 }
 
 bool is_mem_loads_aux_event(struct evsel *leader)