2 files changed, 161 insertions, 4 deletions

diff --git a/tools/perf/arch/x86/util/evsel.c b/tools/perf/arch/x86/util/evsel.c
index 9bc80fff3aa0..23a8e662a912 100644
--- a/tools/perf/arch/x86/util/evsel.c
+++ b/tools/perf/arch/x86/util/evsel.c
@@ -1,10 +1,15 @@
 // SPDX-License-Identifier: GPL-2.0
+#include <errno.h>
 #include <stdio.h>
 #include <stdlib.h>
+#include "util/evlist.h"
 #include "util/evsel.h"
+#include "util/evsel_config.h"
 #include "util/env.h"
 #include "util/pmu.h"
 #include "util/pmus.h"
+#include "util/stat.h"
+#include "util/strbuf.h"
 #include "linux/string.h"
 #include "topdown.h"
 #include "evsel.h"
@@ -67,6 +72,57 @@ int arch_evsel__hw_name(struct evsel *evsel, char *bf, size_t size)
 			 event_name);
 }
 
+void arch_evsel__apply_ratio_to_prev(struct evsel *evsel,
+				struct perf_event_attr *attr)
+{
+	struct perf_event_attr *prev_attr = NULL;
+	struct evsel *evsel_prev = NULL;
+	const char *name = "acr_mask";
+	int evsel_idx = 0;
+	__u64 ev_mask, pr_ev_mask;
+
+	if (!perf_pmu__has_format(evsel->pmu, name)) {
+		pr_err("'%s' does not have acr_mask format support\n", evsel->pmu->name);
+		return;
+	}
+	if (perf_pmu__format_type(evsel->pmu, name) !=
+			PERF_PMU_FORMAT_VALUE_CONFIG2) {
+		pr_err("'%s' does not have config2 format support\n", evsel->pmu->name);
+		return;
+	}
+
+	evsel_prev = evsel__prev(evsel);
+	if (!evsel_prev) {
+		pr_err("Previous event does not exist.\n");
+		return;
+	}
+
+	prev_attr = &evsel_prev->core.attr;
+
+	if (prev_attr->config2) {
+		pr_err("'%s' has set config2 (acr_mask?) already, configuration not supported\n", evsel_prev->name);
+		return;
+	}
+
+	/*
+	 * acr_mask (config2) is calculated using the event's index in
+	 * the event group. The first event will use the index of the
+	 * second event as its mask (e.g., 0x2), indicating that the
+	 * second event counter will be reset and a sample taken for
+	 * the first event if its counter overflows. The second event
+	 * will use the mask consisting of the first and second bits
+	 * (e.g., 0x3), meaning both counters will be reset if the
+	 * second event counter overflows.
+	 */
+
+	evsel_idx = evsel__group_idx(evsel);
+	ev_mask = 1ull << evsel_idx;
+	pr_ev_mask = 1ull << (evsel_idx - 1);
+
+	prev_attr->config2 = ev_mask;
+	attr->config2 = ev_mask | pr_ev_mask;
+}
+
 static void ibs_l3miss_warn(void)
 {
 	pr_warning(
@@ -102,13 +158,15 @@ void arch__post_evsel_config(struct evsel *evsel, struct perf_event_attr *attr)
 	}
 }
 
-int arch_evsel__open_strerror(struct evsel *evsel, char *msg, size_t size)
+static int amd_evsel__open_strerror(struct evsel *evsel, char *msg, size_t size)
 {
-	if (!x86__is_amd_cpu())
+	struct perf_pmu *pmu;
+
+	if (evsel->core.attr.precise_ip == 0)
 		return 0;
 
-	if (!evsel->core.attr.precise_ip &&
-	    !(evsel->pmu && !strncmp(evsel->pmu->name, "ibs", 3)))
+	pmu = evsel__find_pmu(evsel);
+	if (!pmu || strncmp(pmu->name, "ibs", 3))
 		return 0;
 
 	/* More verbose IBS errors. */
@@ -118,6 +176,54 @@ int arch_evsel__open_strerror(struct evsel *evsel, char *msg, size_t size)
 		return scnprintf(msg, size, "AMD IBS doesn't support privilege filtering. Try "
 				 "again without the privilege modifiers (like 'k') at the end.");
 	}
+	return 0;
+}
+
+static int intel_evsel__open_strerror(struct evsel *evsel, int err, char *msg, size_t size)
+{
+	struct strbuf sb = STRBUF_INIT;
+	int ret;
+
+	if (err != EINVAL)
+		return 0;
 
+	if (!topdown_sys_has_perf_metrics())
+		return 0;
+
+	if (arch_is_topdown_slots(evsel)) {
+		if (!evsel__is_group_leader(evsel)) {
+			evlist__uniquify_evsel_names(evsel->evlist, &stat_config);
+			evlist__format_evsels(evsel->evlist, &sb, 2048);
+			ret = scnprintf(msg, size, "Topdown slots event can only be group leader "
+					"in '%s'.", sb.buf);
+			strbuf_release(&sb);
+			return ret;
+		}
+	} else if (arch_is_topdown_metrics(evsel)) {
+		struct evsel *pos;
+
+		evlist__for_each_entry(evsel->evlist, pos) {
+			if (pos == evsel || !arch_is_topdown_metrics(pos))
+				continue;
+
+			if (pos->core.attr.config != evsel->core.attr.config)
+				continue;
+
+			evlist__uniquify_evsel_names(evsel->evlist, &stat_config);
+			evlist__format_evsels(evsel->evlist, &sb, 2048);
+			ret = scnprintf(msg, size, "Perf metric event '%s' is duplicated "
+					"in the same group (only one event is allowed) in '%s'.",
+					evsel__name(evsel), sb.buf);
+			strbuf_release(&sb);
+			return ret;
+		}
+	}
 	return 0;
 }
+
+int arch_evsel__open_strerror(struct evsel *evsel, int err, char *msg, size_t size)
+{
+	return x86__is_amd_cpu()
+		? amd_evsel__open_strerror(evsel, msg, size)
+		: intel_evsel__open_strerror(evsel, err, msg, size);
+}
diff --git a/tools/perf/arch/x86/util/kvm-stat.c b/tools/perf/arch/x86/util/kvm-stat.c
index 424716518b75..bff36f9345ea 100644
--- a/tools/perf/arch/x86/util/kvm-stat.c
+++ b/tools/perf/arch/x86/util/kvm-stat.c
@@ -3,9 +3,11 @@
 #include <string.h>
 #include "../../../util/kvm-stat.h"
 #include "../../../util/evsel.h"
+#include "../../../util/env.h"
 #include <asm/svm.h>
 #include <asm/vmx.h>
 #include <asm/kvm.h>
+#include <subcmd/parse-options.h>
 
 define_exit_reasons_table(vmx_exit_reasons, VMX_EXIT_REASONS);
 define_exit_reasons_table(svm_exit_reasons, SVM_EXIT_REASONS);
@@ -211,3 +213,52 @@ int cpu_isa_init(struct perf_kvm_stat *kvm, const char *cpuid)
 
 	return 0;
 }
+
+/*
+ * After KVM supports PEBS for guest on Intel platforms
+ * (https://lore.kernel.org/all/20220411101946.20262-1-likexu@tencent.com/),
+ * host loses the capability to sample guest with PEBS since all PEBS related
+ * MSRs are switched to guest value after vm-entry, like IA32_DS_AREA MSR is
+ * switched to guest GVA at vm-entry. This would lead to "perf kvm record"
+ * fails to sample guest on Intel platforms since "cycles:P" event is used to
+ * sample guest by default.
+ *
+ * So, to avoid this issue explicitly use "cycles" instead of "cycles:P" event
+ * by default to sample guest on Intel platforms.
+ */
+int kvm_add_default_arch_event(int *argc, const char **argv)
+{
+	const char **tmp;
+	bool event = false;
+	int ret = 0, i, j = *argc;
+
+	const struct option event_options[] = {
+		OPT_BOOLEAN('e', "event", &event, NULL),
+		OPT_BOOLEAN(0, "pfm-events", &event, NULL),
+		OPT_END()
+	};
+
+	if (!x86__is_intel_cpu())
+		return 0;
+
+	tmp = calloc(j + 1, sizeof(char *));
+	if (!tmp)
+		return -ENOMEM;
+
+	for (i = 0; i < j; i++)
+		tmp[i] = argv[i];
+
+	parse_options(j, tmp, event_options, NULL, PARSE_OPT_KEEP_UNKNOWN);
+	if (!event) {
+		argv[j++] = STRDUP_FAIL_EXIT("-e");
+		argv[j++] = STRDUP_FAIL_EXIT("cycles");
+		*argc += 2;
+	}
+
+	free(tmp);
+	return 0;
+
+EXIT:
+	free(tmp);
+	return ret;
+}