7 files changed, 549 insertions, 0 deletions

diff --git a/tools/perf/arch/s390/util/Build b/tools/perf/arch/s390/util/Build
new file mode 100644
index 000000000..4a233683c
--- /dev/null
+++ b/tools/perf/arch/s390/util/Build
@@ -0,0 +1,9 @@
+libperf-y += header.o
+libperf-y += kvm-stat.o
+
+libperf-$(CONFIG_DWARF) += dwarf-regs.o
+libperf-$(CONFIG_LIBDW_DWARF_UNWIND) += unwind-libdw.o
+
+libperf-y += machine.o
+
+libperf-$(CONFIG_AUXTRACE) += auxtrace.o
diff --git a/tools/perf/arch/s390/util/auxtrace.c b/tools/perf/arch/s390/util/auxtrace.c
new file mode 100644
index 000000000..44c857388
--- /dev/null
+++ b/tools/perf/arch/s390/util/auxtrace.c
@@ -0,0 +1,120 @@
+#include <stdbool.h>
+#include <linux/kernel.h>
+#include <linux/types.h>
+#include <linux/bitops.h>
+#include <linux/log2.h>
+
+#include "../../util/evlist.h"
+#include "../../util/auxtrace.h"
+#include "../../util/evsel.h"
+
+#define PERF_EVENT_CPUM_SF		0xB0000 /* Event: Basic-sampling */
+#define PERF_EVENT_CPUM_SF_DIAG		0xBD000 /* Event: Combined-sampling */
+#define DEFAULT_AUX_PAGES		128
+#define DEFAULT_FREQ			4000
+
+static void cpumsf_free(struct auxtrace_record *itr)
+{
+	free(itr);
+}
+
+static size_t cpumsf_info_priv_size(struct auxtrace_record *itr __maybe_unused,
+				    struct perf_evlist *evlist __maybe_unused)
+{
+	return 0;
+}
+
+static int
+cpumsf_info_fill(struct auxtrace_record *itr __maybe_unused,
+		 struct perf_session *session __maybe_unused,
+		 struct auxtrace_info_event *auxtrace_info __maybe_unused,
+		 size_t priv_size __maybe_unused)
+{
+	auxtrace_info->type = PERF_AUXTRACE_S390_CPUMSF;
+	return 0;
+}
+
+static unsigned long
+cpumsf_reference(struct auxtrace_record *itr __maybe_unused)
+{
+	return 0;
+}
+
+static int
+cpumsf_recording_options(struct auxtrace_record *ar __maybe_unused,
+			 struct perf_evlist *evlist __maybe_unused,
+			 struct record_opts *opts)
+{
+	unsigned int factor = 1;
+	unsigned int pages;
+
+	opts->full_auxtrace = true;
+
+	/*
+	 * The AUX buffer size should be set properly to avoid
+	 * overflow of samples if it is not set explicitly.
+	 * DEFAULT_AUX_PAGES is an proper size when sampling frequency
+	 * is DEFAULT_FREQ. It is expected to hold about 1/2 second
+	 * of sampling data. The size used for AUX buffer will scale
+	 * according to the specified frequency and DEFAULT_FREQ.
+	 */
+	if (!opts->auxtrace_mmap_pages) {
+		if (opts->user_freq != UINT_MAX)
+			factor = (opts->user_freq + DEFAULT_FREQ
+				  - 1) / DEFAULT_FREQ;
+		pages = DEFAULT_AUX_PAGES * factor;
+		opts->auxtrace_mmap_pages = roundup_pow_of_two(pages);
+	}
+
+	return 0;
+}
+
+static int
+cpumsf_parse_snapshot_options(struct auxtrace_record *itr __maybe_unused,
+			      struct record_opts *opts __maybe_unused,
+			      const char *str __maybe_unused)
+{
+	return 0;
+}
+
+/*
+ * auxtrace_record__init is called when perf record
+ * check if the event really need auxtrace
+ */
+struct auxtrace_record *auxtrace_record__init(struct perf_evlist *evlist,
+					      int *err)
+{
+	struct auxtrace_record *aux;
+	struct perf_evsel *pos;
+	int diagnose = 0;
+
+	*err = 0;
+	if (evlist->nr_entries == 0)
+		return NULL;
+
+	evlist__for_each_entry(evlist, pos) {
+		if (pos->attr.config == PERF_EVENT_CPUM_SF_DIAG) {
+			diagnose = 1;
+			break;
+		}
+	}
+
+	if (!diagnose)
+		return NULL;
+
+	/* sampling in diagnose mode. alloc aux buffer */
+	aux = zalloc(sizeof(*aux));
+	if (aux == NULL) {
+		*err = -ENOMEM;
+		return NULL;
+	}
+
+	aux->parse_snapshot_options = cpumsf_parse_snapshot_options;
+	aux->recording_options = cpumsf_recording_options;
+	aux->info_priv_size = cpumsf_info_priv_size;
+	aux->info_fill = cpumsf_info_fill;
+	aux->free = cpumsf_free;
+	aux->reference = cpumsf_reference;
+
+	return aux;
+}
diff --git a/tools/perf/arch/s390/util/dwarf-regs.c b/tools/perf/arch/s390/util/dwarf-regs.c
new file mode 100644
index 000000000..a8ace5cc6
--- /dev/null
+++ b/tools/perf/arch/s390/util/dwarf-regs.c
@@ -0,0 +1,44 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Mapping of DWARF debug register numbers into register names.
+ *
+ * Copyright IBM Corp. 2010, 2017
+ * Author(s): Heiko Carstens <heiko.carstens@de.ibm.com>,
+ *	      Hendrik Brueckner <brueckner@linux.vnet.ibm.com>
+ *
+ */
+
+#include <errno.h>
+#include <stddef.h>
+#include <stdlib.h>
+#include <linux/kernel.h>
+#include <asm/ptrace.h>
+#include <string.h>
+#include <dwarf-regs.h>
+#include "dwarf-regs-table.h"
+
+const char *get_arch_regstr(unsigned int n)
+{
+	return (n >= ARRAY_SIZE(s390_dwarf_regs)) ? NULL : s390_dwarf_regs[n];
+}
+
+/*
+ * Convert the register name into an offset to struct pt_regs (kernel).
+ * This is required by the BPF prologue generator.  The BPF
+ * program is called in the BPF overflow handler in the perf
+ * core.
+ */
+int regs_query_register_offset(const char *name)
+{
+	unsigned long gpr;
+
+	if (!name || strncmp(name, "%r", 2))
+		return -EINVAL;
+
+	errno = 0;
+	gpr = strtoul(name + 2, NULL, 10);
+	if (errno || gpr >= 16)
+		return -EINVAL;
+
+	return offsetof(user_pt_regs, gprs) + 8 * gpr;
+}
diff --git a/tools/perf/arch/s390/util/header.c b/tools/perf/arch/s390/util/header.c
new file mode 100644
index 000000000..cc72554c3
--- /dev/null
+++ b/tools/perf/arch/s390/util/header.c
@@ -0,0 +1,149 @@
+/*
+ * Implementation of get_cpuid().
+ *
+ * Copyright IBM Corp. 2014, 2018
+ * Author(s): Alexander Yarygin <yarygin@linux.vnet.ibm.com>
+ *	      Thomas Richter <tmricht@linux.vnet.ibm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License (version 2 only)
+ * as published by the Free Software Foundation.
+ */
+
+#include <sys/types.h>
+#include <errno.h>
+#include <unistd.h>
+#include <stdio.h>
+#include <string.h>
+#include <ctype.h>
+
+#include "../../util/header.h"
+#include "../../util/util.h"
+
+#define SYSINFO_MANU	"Manufacturer:"
+#define SYSINFO_TYPE	"Type:"
+#define SYSINFO_MODEL	"Model:"
+#define SRVLVL_CPUMF	"CPU-MF:"
+#define SRVLVL_VERSION	"version="
+#define SRVLVL_AUTHORIZATION	"authorization="
+#define SYSINFO		"/proc/sysinfo"
+#define SRVLVL		"/proc/service_levels"
+
+int get_cpuid(char *buffer, size_t sz)
+{
+	char *cp, *line = NULL, *line2;
+	char type[8], model[33], version[8], manufacturer[32], authorization[8];
+	int tpsize = 0, mdsize = 0, vssize = 0, mfsize = 0, atsize = 0;
+	int read;
+	unsigned long line_sz;
+	size_t nbytes;
+	FILE *sysinfo;
+
+	/*
+	 * Scan /proc/sysinfo line by line and read out values for
+	 * Manufacturer:, Type: and Model:, for example:
+	 * Manufacturer:    IBM
+	 * Type:            2964
+	 * Model:           702              N96
+	 * The first word is the Model Capacity and the second word is
+	 * Model (can be omitted). Both words have a maximum size of 16
+	 * bytes.
+	 */
+	memset(manufacturer, 0, sizeof(manufacturer));
+	memset(type, 0, sizeof(type));
+	memset(model, 0, sizeof(model));
+	memset(version, 0, sizeof(version));
+	memset(authorization, 0, sizeof(authorization));
+
+	sysinfo = fopen(SYSINFO, "r");
+	if (sysinfo == NULL)
+		return errno;
+
+	while ((read = getline(&line, &line_sz, sysinfo)) != -1) {
+		if (!strncmp(line, SYSINFO_MANU, strlen(SYSINFO_MANU))) {
+			line2 = line + strlen(SYSINFO_MANU);
+
+			while ((cp = strtok_r(line2, "\n ", &line2))) {
+				mfsize += scnprintf(manufacturer + mfsize,
+						    sizeof(manufacturer) - mfsize, "%s", cp);
+			}
+		}
+
+		if (!strncmp(line, SYSINFO_TYPE, strlen(SYSINFO_TYPE))) {
+			line2 = line + strlen(SYSINFO_TYPE);
+
+			while ((cp = strtok_r(line2, "\n ", &line2))) {
+				tpsize += scnprintf(type + tpsize,
+						    sizeof(type) - tpsize, "%s", cp);
+			}
+		}
+
+		if (!strncmp(line, SYSINFO_MODEL, strlen(SYSINFO_MODEL))) {
+			line2 = line + strlen(SYSINFO_MODEL);
+
+			while ((cp = strtok_r(line2, "\n ", &line2))) {
+				mdsize += scnprintf(model + mdsize, sizeof(model) - mdsize,
+						    "%s%s", model[0] ? "," : "", cp);
+			}
+			break;
+		}
+	}
+	fclose(sysinfo);
+
+	/* Missing manufacturer, type or model information should not happen */
+	if (!manufacturer[0] || !type[0] || !model[0])
+		return EINVAL;
+
+	/*
+	 * Scan /proc/service_levels and return the CPU-MF counter facility
+	 * version number and authorization level.
+	 * Optional, does not exist on z/VM guests.
+	 */
+	sysinfo = fopen(SRVLVL, "r");
+	if (sysinfo == NULL)
+		goto skip_sysinfo;
+	while ((read = getline(&line, &line_sz, sysinfo)) != -1) {
+		if (strncmp(line, SRVLVL_CPUMF, strlen(SRVLVL_CPUMF)))
+			continue;
+
+		line2 = line + strlen(SRVLVL_CPUMF);
+		while ((cp = strtok_r(line2, "\n ", &line2))) {
+			if (!strncmp(cp, SRVLVL_VERSION,
+				     strlen(SRVLVL_VERSION))) {
+				char *sep = strchr(cp, '=');
+
+				vssize += scnprintf(version + vssize,
+						    sizeof(version) - vssize, "%s", sep + 1);
+			}
+			if (!strncmp(cp, SRVLVL_AUTHORIZATION,
+				     strlen(SRVLVL_AUTHORIZATION))) {
+				char *sep = strchr(cp, '=');
+
+				atsize += scnprintf(authorization + atsize,
+						    sizeof(authorization) - atsize, "%s", sep + 1);
+			}
+		}
+	}
+	fclose(sysinfo);
+
+skip_sysinfo:
+	free(line);
+
+	if (version[0] && authorization[0] )
+		nbytes = snprintf(buffer, sz, "%s,%s,%s,%s,%s",
+				  manufacturer, type, model, version,
+				  authorization);
+	else
+		nbytes = snprintf(buffer, sz, "%s,%s,%s", manufacturer, type,
+				  model);
+	return (nbytes >= sz) ? ENOBUFS : 0;
+}
+
+char *get_cpuid_str(struct perf_pmu *pmu __maybe_unused)
+{
+	char *buf = malloc(128);
+
+	if (buf && get_cpuid(buf, 128))
+		zfree(&buf);
+	return buf;
+}
diff --git a/tools/perf/arch/s390/util/kvm-stat.c b/tools/perf/arch/s390/util/kvm-stat.c
new file mode 100644
index 000000000..aaabab5e2
--- /dev/null
+++ b/tools/perf/arch/s390/util/kvm-stat.c
@@ -0,0 +1,112 @@
+/*
+ * Arch specific functions for perf kvm stat.
+ *
+ * Copyright 2014 IBM Corp.
+ * Author(s): Alexander Yarygin <yarygin@linux.vnet.ibm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License (version 2 only)
+ * as published by the Free Software Foundation.
+ */
+
+#include <errno.h>
+#include "../../util/kvm-stat.h"
+#include <asm/sie.h>
+
+define_exit_reasons_table(sie_exit_reasons, sie_intercept_code);
+define_exit_reasons_table(sie_icpt_insn_codes, icpt_insn_codes);
+define_exit_reasons_table(sie_sigp_order_codes, sigp_order_codes);
+define_exit_reasons_table(sie_diagnose_codes, diagnose_codes);
+define_exit_reasons_table(sie_icpt_prog_codes, icpt_prog_codes);
+
+const char *vcpu_id_str = "id";
+const int decode_str_len = 40;
+const char *kvm_exit_reason = "icptcode";
+const char *kvm_entry_trace = "kvm:kvm_s390_sie_enter";
+const char *kvm_exit_trace = "kvm:kvm_s390_sie_exit";
+
+static void event_icpt_insn_get_key(struct perf_evsel *evsel,
+				    struct perf_sample *sample,
+				    struct event_key *key)
+{
+	unsigned long insn;
+
+	insn = perf_evsel__intval(evsel, sample, "instruction");
+	key->key = icpt_insn_decoder(insn);
+	key->exit_reasons = sie_icpt_insn_codes;
+}
+
+static void event_sigp_get_key(struct perf_evsel *evsel,
+			       struct perf_sample *sample,
+			       struct event_key *key)
+{
+	key->key = perf_evsel__intval(evsel, sample, "order_code");
+	key->exit_reasons = sie_sigp_order_codes;
+}
+
+static void event_diag_get_key(struct perf_evsel *evsel,
+			       struct perf_sample *sample,
+			       struct event_key *key)
+{
+	key->key = perf_evsel__intval(evsel, sample, "code");
+	key->exit_reasons = sie_diagnose_codes;
+}
+
+static void event_icpt_prog_get_key(struct perf_evsel *evsel,
+				    struct perf_sample *sample,
+				    struct event_key *key)
+{
+	key->key = perf_evsel__intval(evsel, sample, "code");
+	key->exit_reasons = sie_icpt_prog_codes;
+}
+
+static struct child_event_ops child_events[] = {
+	{ .name = "kvm:kvm_s390_intercept_instruction",
+	  .get_key = event_icpt_insn_get_key },
+	{ .name = "kvm:kvm_s390_handle_sigp",
+	  .get_key = event_sigp_get_key },
+	{ .name = "kvm:kvm_s390_handle_diag",
+	  .get_key = event_diag_get_key },
+	{ .name = "kvm:kvm_s390_intercept_prog",
+	  .get_key = event_icpt_prog_get_key },
+	{ NULL, NULL },
+};
+
+static struct kvm_events_ops exit_events = {
+	.is_begin_event = exit_event_begin,
+	.is_end_event = exit_event_end,
+	.child_ops = child_events,
+	.decode_key = exit_event_decode_key,
+	.name = "VM-EXIT"
+};
+
+const char *kvm_events_tp[] = {
+	"kvm:kvm_s390_sie_enter",
+	"kvm:kvm_s390_sie_exit",
+	"kvm:kvm_s390_intercept_instruction",
+	"kvm:kvm_s390_handle_sigp",
+	"kvm:kvm_s390_handle_diag",
+	"kvm:kvm_s390_intercept_prog",
+	NULL,
+};
+
+struct kvm_reg_events_ops kvm_reg_events_ops[] = {
+	{ .name = "vmexit", .ops = &exit_events },
+	{ NULL, NULL },
+};
+
+const char * const kvm_skip_events[] = {
+	"Wait state",
+	NULL,
+};
+
+int cpu_isa_init(struct perf_kvm_stat *kvm, const char *cpuid)
+{
+	if (strstr(cpuid, "IBM")) {
+		kvm->exit_reasons = sie_exit_reasons;
+		kvm->exit_reasons_isa = "SIE";
+	} else
+		return -ENOTSUP;
+
+	return 0;
+}
diff --git a/tools/perf/arch/s390/util/machine.c b/tools/perf/arch/s390/util/machine.c
new file mode 100644
index 000000000..c8c86a0c9
--- /dev/null
+++ b/tools/perf/arch/s390/util/machine.c
@@ -0,0 +1,52 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <unistd.h>
+#include <stdio.h>
+#include <string.h>
+#include "util.h"
+#include "machine.h"
+#include "api/fs/fs.h"
+#include "debug.h"
+#include "symbol.h"
+
+int arch__fix_module_text_start(u64 *start, u64 *size, const char *name)
+{
+	u64 m_start = *start;
+	char path[PATH_MAX];
+
+	snprintf(path, PATH_MAX, "module/%.*s/sections/.text",
+				(int)strlen(name) - 2, name + 1);
+	if (sysfs__read_ull(path, (unsigned long long *)start) < 0) {
+		pr_debug2("Using module %s start:%#lx\n", path, m_start);
+		*start = m_start;
+	} else {
+		/* Successful read of the modules segment text start address.
+		 * Calculate difference between module start address
+		 * in memory and module text segment start address.
+		 * For example module load address is 0x3ff8011b000
+		 * (from /proc/modules) and module text segment start
+		 * address is 0x3ff8011b870 (from file above).
+		 *
+		 * Adjust the module size and subtract the GOT table
+		 * size located at the beginning of the module.
+		 */
+		*size -= (*start - m_start);
+	}
+
+	return 0;
+}
+
+/* On s390 kernel text segment start is located at very low memory addresses,
+ * for example 0x10000. Modules are located at very high memory addresses,
+ * for example 0x3ff xxxx xxxx. The gap between end of kernel text segment
+ * and beginning of first module's text segment is very big.
+ * Therefore do not fill this gap and do not assign it to the kernel dso map.
+ */
+void arch__symbols__fixup_end(struct symbol *p, struct symbol *c)
+{
+	if (strchr(p->name, '[') == NULL && strchr(c->name, '['))
+		/* Last kernel symbol mapped to end of page */
+		p->end = roundup(p->end, page_size);
+	else
+		p->end = c->start;
+	pr_debug4("%s sym:%s end:%#lx\n", __func__, p->name, p->end);
+}
diff --git a/tools/perf/arch/s390/util/unwind-libdw.c b/tools/perf/arch/s390/util/unwind-libdw.c
new file mode 100644
index 000000000..387c698cd
--- /dev/null
+++ b/tools/perf/arch/s390/util/unwind-libdw.c
@@ -0,0 +1,63 @@
+#include <linux/kernel.h>
+#include <elfutils/libdwfl.h>
+#include "../../util/unwind-libdw.h"
+#include "../../util/perf_regs.h"
+#include "../../util/event.h"
+#include "dwarf-regs-table.h"
+
+
+bool libdw__arch_set_initial_registers(Dwfl_Thread *thread, void *arg)
+{
+	struct unwind_info *ui = arg;
+	struct regs_dump *user_regs = &ui->sample->user_regs;
+	Dwarf_Word dwarf_regs[ARRAY_SIZE(s390_dwarf_regs)];
+
+#define REG(r) ({						\
+	Dwarf_Word val = 0;					\
+	perf_reg_value(&val, user_regs, PERF_REG_S390_##r);	\
+	val;							\
+})
+	/*
+	 * For DWARF register mapping details,
+	 * see also perf/arch/s390/include/dwarf-regs-table.h
+	 */
+	dwarf_regs[0]  = REG(R0);
+	dwarf_regs[1]  = REG(R1);
+	dwarf_regs[2]  = REG(R2);
+	dwarf_regs[3]  = REG(R3);
+	dwarf_regs[4]  = REG(R4);
+	dwarf_regs[5]  = REG(R5);
+	dwarf_regs[6]  = REG(R6);
+	dwarf_regs[7]  = REG(R7);
+	dwarf_regs[8]  = REG(R8);
+	dwarf_regs[9]  = REG(R9);
+	dwarf_regs[10] = REG(R10);
+	dwarf_regs[11] = REG(R11);
+	dwarf_regs[12] = REG(R12);
+	dwarf_regs[13] = REG(R13);
+	dwarf_regs[14] = REG(R14);
+	dwarf_regs[15] = REG(R15);
+
+	dwarf_regs[16] = REG(FP0);
+	dwarf_regs[17] = REG(FP2);
+	dwarf_regs[18] = REG(FP4);
+	dwarf_regs[19] = REG(FP6);
+	dwarf_regs[20] = REG(FP1);
+	dwarf_regs[21] = REG(FP3);
+	dwarf_regs[22] = REG(FP5);
+	dwarf_regs[23] = REG(FP7);
+	dwarf_regs[24] = REG(FP8);
+	dwarf_regs[25] = REG(FP10);
+	dwarf_regs[26] = REG(FP12);
+	dwarf_regs[27] = REG(FP14);
+	dwarf_regs[28] = REG(FP9);
+	dwarf_regs[29] = REG(FP11);
+	dwarf_regs[30] = REG(FP13);
+	dwarf_regs[31] = REG(FP15);
+
+	dwarf_regs[64] = REG(MASK);
+	dwarf_regs[65] = REG(PC);
+
+	dwfl_thread_state_register_pc(thread, dwarf_regs[65]);
+	return dwfl_thread_state_registers(thread, 0, 32, dwarf_regs);
+}