20 files changed, 1535 insertions, 0 deletions

diff --git a/tools/perf/arch/arm/Build b/tools/perf/arch/arm/Build
new file mode 100644
index 000000000..36222e64b
--- /dev/null
+++ b/tools/perf/arch/arm/Build
@@ -0,0 +1,2 @@
+perf-y += util/
+perf-$(CONFIG_DWARF_UNWIND) += tests/
diff --git a/tools/perf/arch/arm/Makefile b/tools/perf/arch/arm/Makefile
new file mode 100644
index 000000000..1d88fdab1
--- /dev/null
+++ b/tools/perf/arch/arm/Makefile
@@ -0,0 +1,5 @@
+# SPDX-License-Identifier: GPL-2.0-only
+ifndef NO_DWARF
+PERF_HAVE_DWARF_REGS := 1
+endif
+PERF_HAVE_JITDUMP := 1
diff --git a/tools/perf/arch/arm/annotate/instructions.c b/tools/perf/arch/arm/annotate/instructions.c
new file mode 100644
index 000000000..2ff6cedeb
--- /dev/null
+++ b/tools/perf/arch/arm/annotate/instructions.c
@@ -0,0 +1,63 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/compiler.h>
+#include <linux/zalloc.h>
+#include <sys/types.h>
+#include <regex.h>
+#include <stdlib.h>
+
+struct arm_annotate {
+	regex_t call_insn,
+		jump_insn;
+};
+
+static struct ins_ops *arm__associate_instruction_ops(struct arch *arch, const char *name)
+{
+	struct arm_annotate *arm = arch->priv;
+	struct ins_ops *ops;
+	regmatch_t match[2];
+
+	if (!regexec(&arm->call_insn, name, 2, match, 0))
+		ops = &call_ops;
+	else if (!regexec(&arm->jump_insn, name, 2, match, 0))
+		ops = &jump_ops;
+	else
+		return NULL;
+
+	arch__associate_ins_ops(arch, name, ops);
+	return ops;
+}
+
+static int arm__annotate_init(struct arch *arch, char *cpuid __maybe_unused)
+{
+	struct arm_annotate *arm;
+	int err;
+
+	if (arch->initialized)
+		return 0;
+
+	arm = zalloc(sizeof(*arm));
+	if (!arm)
+		return ENOMEM;
+
+#define ARM_CONDS "(cc|cs|eq|ge|gt|hi|le|ls|lt|mi|ne|pl|vc|vs)"
+	err = regcomp(&arm->call_insn, "^blx?" ARM_CONDS "?$", REG_EXTENDED);
+	if (err)
+		goto out_free_arm;
+	err = regcomp(&arm->jump_insn, "^bx?" ARM_CONDS "?$", REG_EXTENDED);
+	if (err)
+		goto out_free_call;
+#undef ARM_CONDS
+
+	arch->initialized = true;
+	arch->priv	  = arm;
+	arch->associate_instruction_ops   = arm__associate_instruction_ops;
+	arch->objdump.comment_char	  = ';';
+	arch->objdump.skip_functions_char = '+';
+	return 0;
+
+out_free_call:
+	regfree(&arm->call_insn);
+out_free_arm:
+	free(arm);
+	return SYMBOL_ANNOTATE_ERRNO__ARCH_INIT_REGEXP;
+}
diff --git a/tools/perf/arch/arm/include/arch-tests.h b/tools/perf/arch/arm/include/arch-tests.h
new file mode 100644
index 000000000..90ec4c8cb
--- /dev/null
+++ b/tools/perf/arch/arm/include/arch-tests.h
@@ -0,0 +1,12 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef ARCH_TESTS_H
+#define ARCH_TESTS_H
+
+#ifdef HAVE_DWARF_UNWIND_SUPPORT
+struct thread;
+struct perf_sample;
+#endif
+
+extern struct test arch_tests[];
+
+#endif
diff --git a/tools/perf/arch/arm/include/dwarf-regs-table.h b/tools/perf/arch/arm/include/dwarf-regs-table.h
new file mode 100644
index 000000000..5a45046fa
--- /dev/null
+++ b/tools/perf/arch/arm/include/dwarf-regs-table.h
@@ -0,0 +1,10 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifdef DEFINE_DWARF_REGSTR_TABLE
+/* This is included in perf/util/dwarf-regs.c */
+
+static const char * const arm_regstr_tbl[] = {
+	"%r0", "%r1", "%r2", "%r3", "%r4",
+	"%r5", "%r6", "%r7", "%r8", "%r9", "%r10",
+	"%fp", "%ip", "%sp", "%lr", "%pc",
+};
+#endif
diff --git a/tools/perf/arch/arm/include/perf_regs.h b/tools/perf/arch/arm/include/perf_regs.h
new file mode 100644
index 000000000..408541928
--- /dev/null
+++ b/tools/perf/arch/arm/include/perf_regs.h
@@ -0,0 +1,60 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef ARCH_PERF_REGS_H
+#define ARCH_PERF_REGS_H
+
+#include <stdlib.h>
+#include <linux/types.h>
+#include <asm/perf_regs.h>
+
+void perf_regs_load(u64 *regs);
+
+#define PERF_REGS_MASK	((1ULL << PERF_REG_ARM_MAX) - 1)
+#define PERF_REGS_MAX	PERF_REG_ARM_MAX
+#define PERF_SAMPLE_REGS_ABI	PERF_SAMPLE_REGS_ABI_32
+
+#define PERF_REG_IP	PERF_REG_ARM_PC
+#define PERF_REG_SP	PERF_REG_ARM_SP
+
+static inline const char *__perf_reg_name(int id)
+{
+	switch (id) {
+	case PERF_REG_ARM_R0:
+		return "r0";
+	case PERF_REG_ARM_R1:
+		return "r1";
+	case PERF_REG_ARM_R2:
+		return "r2";
+	case PERF_REG_ARM_R3:
+		return "r3";
+	case PERF_REG_ARM_R4:
+		return "r4";
+	case PERF_REG_ARM_R5:
+		return "r5";
+	case PERF_REG_ARM_R6:
+		return "r6";
+	case PERF_REG_ARM_R7:
+		return "r7";
+	case PERF_REG_ARM_R8:
+		return "r8";
+	case PERF_REG_ARM_R9:
+		return "r9";
+	case PERF_REG_ARM_R10:
+		return "r10";
+	case PERF_REG_ARM_FP:
+		return "fp";
+	case PERF_REG_ARM_IP:
+		return "ip";
+	case PERF_REG_ARM_SP:
+		return "sp";
+	case PERF_REG_ARM_LR:
+		return "lr";
+	case PERF_REG_ARM_PC:
+		return "pc";
+	default:
+		return NULL;
+	}
+
+	return NULL;
+}
+
+#endif /* ARCH_PERF_REGS_H */
diff --git a/tools/perf/arch/arm/tests/Build b/tools/perf/arch/arm/tests/Build
new file mode 100644
index 000000000..bc8e97380
--- /dev/null
+++ b/tools/perf/arch/arm/tests/Build
@@ -0,0 +1,5 @@
+perf-y += regs_load.o
+perf-y += dwarf-unwind.o
+perf-y += vectors-page.o
+
+perf-y += arch-tests.o
diff --git a/tools/perf/arch/arm/tests/arch-tests.c b/tools/perf/arch/arm/tests/arch-tests.c
new file mode 100644
index 000000000..6848101a8
--- /dev/null
+++ b/tools/perf/arch/arm/tests/arch-tests.c
@@ -0,0 +1,20 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <string.h>
+#include "tests/tests.h"
+#include "arch-tests.h"
+
+struct test arch_tests[] = {
+#ifdef HAVE_DWARF_UNWIND_SUPPORT
+	{
+		.desc = "DWARF unwind",
+		.func = test__dwarf_unwind,
+	},
+#endif
+	{
+		.desc = "Vectors page",
+		.func = test__vectors_page,
+	},
+	{
+		.func = NULL,
+	},
+};
diff --git a/tools/perf/arch/arm/tests/dwarf-unwind.c b/tools/perf/arch/arm/tests/dwarf-unwind.c
new file mode 100644
index 000000000..ccfa87055
--- /dev/null
+++ b/tools/perf/arch/arm/tests/dwarf-unwind.c
@@ -0,0 +1,63 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <string.h>
+#include "perf_regs.h"
+#include "thread.h"
+#include "map.h"
+#include "maps.h"
+#include "event.h"
+#include "debug.h"
+#include "tests/tests.h"
+
+#define STACK_SIZE 8192
+
+static int sample_ustack(struct perf_sample *sample,
+			 struct thread *thread, u64 *regs)
+{
+	struct stack_dump *stack = &sample->user_stack;
+	struct map *map;
+	unsigned long sp;
+	u64 stack_size, *buf;
+
+	buf = malloc(STACK_SIZE);
+	if (!buf) {
+		pr_debug("failed to allocate sample uregs data\n");
+		return -1;
+	}
+
+	sp = (unsigned long) regs[PERF_REG_ARM_SP];
+
+	map = maps__find(thread->maps, (u64)sp);
+	if (!map) {
+		pr_debug("failed to get stack map\n");
+		free(buf);
+		return -1;
+	}
+
+	stack_size = map->end - sp;
+	stack_size = stack_size > STACK_SIZE ? STACK_SIZE : stack_size;
+
+	memcpy(buf, (void *) sp, stack_size);
+	stack->data = (char *) buf;
+	stack->size = stack_size;
+	return 0;
+}
+
+int test__arch_unwind_sample(struct perf_sample *sample,
+			     struct thread *thread)
+{
+	struct regs_dump *regs = &sample->user_regs;
+	u64 *buf;
+
+	buf = calloc(1, sizeof(u64) * PERF_REGS_MAX);
+	if (!buf) {
+		pr_debug("failed to allocate sample uregs data\n");
+		return -1;
+	}
+
+	perf_regs_load(buf);
+	regs->abi  = PERF_SAMPLE_REGS_ABI;
+	regs->regs = buf;
+	regs->mask = PERF_REGS_MASK;
+
+	return sample_ustack(sample, thread, buf);
+}
diff --git a/tools/perf/arch/arm/tests/regs_load.S b/tools/perf/arch/arm/tests/regs_load.S
new file mode 100644
index 000000000..4284307d7
--- /dev/null
+++ b/tools/perf/arch/arm/tests/regs_load.S
@@ -0,0 +1,59 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#include <linux/linkage.h>
+
+#define R0 0x00
+#define R1 0x08
+#define R2 0x10
+#define R3 0x18
+#define R4 0x20
+#define R5 0x28
+#define R6 0x30
+#define R7 0x38
+#define R8 0x40
+#define R9 0x48
+#define SL 0x50
+#define FP 0x58
+#define IP 0x60
+#define SP 0x68
+#define LR 0x70
+#define PC 0x78
+
+/*
+ * Implementation of void perf_regs_load(u64 *regs);
+ *
+ * This functions fills in the 'regs' buffer from the actual registers values,
+ * in the way the perf built-in unwinding test expects them:
+ * - the PC at the time at the call to this function. Since this function
+ *   is called using a bl instruction, the PC value is taken from LR.
+ * The built-in unwinding test then unwinds the call stack from the dwarf
+ * information in unwind__get_entries.
+ *
+ * Notes:
+ * - the 8 bytes stride in the registers offsets comes from the fact
+ * that the registers are stored in an u64 array (u64 *regs),
+ * - the regs buffer needs to be zeroed before the call to this function,
+ * in this case using a calloc in dwarf-unwind.c.
+ */
+
+.text
+.type perf_regs_load,%function
+SYM_FUNC_START(perf_regs_load)
+	str r0, [r0, #R0]
+	str r1, [r0, #R1]
+	str r2, [r0, #R2]
+	str r3, [r0, #R3]
+	str r4, [r0, #R4]
+	str r5, [r0, #R5]
+	str r6, [r0, #R6]
+	str r7, [r0, #R7]
+	str r8, [r0, #R8]
+	str r9, [r0, #R9]
+	str sl, [r0, #SL]
+	str fp, [r0, #FP]
+	str ip, [r0, #IP]
+	str sp, [r0, #SP]
+	str lr, [r0, #LR]
+	str lr, [r0, #PC]	// store pc as lr in order to skip the call
+	                        //  to this function
+	mov pc, lr
+SYM_FUNC_END(perf_regs_load)
diff --git a/tools/perf/arch/arm/tests/vectors-page.c b/tools/perf/arch/arm/tests/vectors-page.c
new file mode 100644
index 000000000..7ffdd7997
--- /dev/null
+++ b/tools/perf/arch/arm/tests/vectors-page.c
@@ -0,0 +1,24 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <stdio.h>
+#include <string.h>
+#include <linux/compiler.h>
+
+#include "debug.h"
+#include "tests/tests.h"
+#include "util/find-map.c"
+
+#define VECTORS__MAP_NAME "[vectors]"
+
+int test__vectors_page(struct test *test __maybe_unused,
+		       int subtest __maybe_unused)
+{
+	void *start, *end;
+
+	if (find_map(&start, &end, VECTORS__MAP_NAME)) {
+		pr_err("%s not found, is CONFIG_KUSER_HELPERS enabled?\n",
+		       VECTORS__MAP_NAME);
+		return TEST_FAIL;
+	}
+
+	return TEST_OK;
+}
diff --git a/tools/perf/arch/arm/util/Build b/tools/perf/arch/arm/util/Build
new file mode 100644
index 000000000..37fc63708
--- /dev/null
+++ b/tools/perf/arch/arm/util/Build
@@ -0,0 +1,8 @@
+perf-y += perf_regs.o
+
+perf-$(CONFIG_DWARF) += dwarf-regs.o
+
+perf-$(CONFIG_LOCAL_LIBUNWIND)    += unwind-libunwind.o
+perf-$(CONFIG_LIBDW_DWARF_UNWIND) += unwind-libdw.o
+
+perf-$(CONFIG_AUXTRACE) += pmu.o auxtrace.o cs-etm.o
diff --git a/tools/perf/arch/arm/util/auxtrace.c b/tools/perf/arch/arm/util/auxtrace.c
new file mode 100644
index 000000000..b187bddbd
--- /dev/null
+++ b/tools/perf/arch/arm/util/auxtrace.c
@@ -0,0 +1,109 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright(C) 2015 Linaro Limited. All rights reserved.
+ * Author: Mathieu Poirier <mathieu.poirier@linaro.org>
+ */
+
+#include <stdbool.h>
+#include <linux/coresight-pmu.h>
+#include <linux/zalloc.h>
+
+#include "../../util/auxtrace.h"
+#include "../../util/debug.h"
+#include "../../util/evlist.h"
+#include "../../util/pmu.h"
+#include "cs-etm.h"
+#include "arm-spe.h"
+
+static struct perf_pmu **find_all_arm_spe_pmus(int *nr_spes, int *err)
+{
+	struct perf_pmu **arm_spe_pmus = NULL;
+	int ret, i, nr_cpus = sysconf(_SC_NPROCESSORS_CONF);
+	/* arm_spe_xxxxxxxxx\0 */
+	char arm_spe_pmu_name[sizeof(ARM_SPE_PMU_NAME) + 10];
+
+	arm_spe_pmus = zalloc(sizeof(struct perf_pmu *) * nr_cpus);
+	if (!arm_spe_pmus) {
+		pr_err("spes alloc failed\n");
+		*err = -ENOMEM;
+		return NULL;
+	}
+
+	for (i = 0; i < nr_cpus; i++) {
+		ret = sprintf(arm_spe_pmu_name, "%s%d", ARM_SPE_PMU_NAME, i);
+		if (ret < 0) {
+			pr_err("sprintf failed\n");
+			*err = -ENOMEM;
+			return NULL;
+		}
+
+		arm_spe_pmus[*nr_spes] = perf_pmu__find(arm_spe_pmu_name);
+		if (arm_spe_pmus[*nr_spes]) {
+			pr_debug2("%s %d: arm_spe_pmu %d type %d name %s\n",
+				 __func__, __LINE__, *nr_spes,
+				 arm_spe_pmus[*nr_spes]->type,
+				 arm_spe_pmus[*nr_spes]->name);
+			(*nr_spes)++;
+		}
+	}
+
+	return arm_spe_pmus;
+}
+
+struct auxtrace_record
+*auxtrace_record__init(struct evlist *evlist, int *err)
+{
+	struct perf_pmu	*cs_etm_pmu;
+	struct evsel *evsel;
+	bool found_etm = false;
+	struct perf_pmu *found_spe = NULL;
+	struct perf_pmu **arm_spe_pmus = NULL;
+	int nr_spes = 0;
+	int i = 0;
+
+	if (!evlist)
+		return NULL;
+
+	cs_etm_pmu = perf_pmu__find(CORESIGHT_ETM_PMU_NAME);
+	arm_spe_pmus = find_all_arm_spe_pmus(&nr_spes, err);
+
+	evlist__for_each_entry(evlist, evsel) {
+		if (cs_etm_pmu &&
+		    evsel->core.attr.type == cs_etm_pmu->type)
+			found_etm = true;
+
+		if (!nr_spes || found_spe)
+			continue;
+
+		for (i = 0; i < nr_spes; i++) {
+			if (evsel->core.attr.type == arm_spe_pmus[i]->type) {
+				found_spe = arm_spe_pmus[i];
+				break;
+			}
+		}
+	}
+	free(arm_spe_pmus);
+
+	if (found_etm && found_spe) {
+		pr_err("Concurrent ARM Coresight ETM and SPE operation not currently supported\n");
+		*err = -EOPNOTSUPP;
+		return NULL;
+	}
+
+	if (found_etm)
+		return cs_etm_record_init(err);
+
+#if defined(__aarch64__)
+	if (found_spe)
+		return arm_spe_recording_init(err, found_spe);
+#endif
+
+	/*
+	 * Clear 'err' even if we haven't found an event - that way perf
+	 * record can still be used even if tracers aren't present.  The NULL
+	 * return value will take care of telling the infrastructure HW tracing
+	 * isn't available.
+	 */
+	*err = 0;
+	return NULL;
+}
diff --git a/tools/perf/arch/arm/util/cs-etm.c b/tools/perf/arch/arm/util/cs-etm.c
new file mode 100644
index 000000000..cad7bf783
--- /dev/null
+++ b/tools/perf/arch/arm/util/cs-etm.c
@@ -0,0 +1,898 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright(C) 2015 Linaro Limited. All rights reserved.
+ * Author: Mathieu Poirier <mathieu.poirier@linaro.org>
+ */
+
+#include <api/fs/fs.h>
+#include <linux/bits.h>
+#include <linux/bitops.h>
+#include <linux/compiler.h>
+#include <linux/coresight-pmu.h>
+#include <linux/kernel.h>
+#include <linux/log2.h>
+#include <linux/string.h>
+#include <linux/types.h>
+#include <linux/zalloc.h>
+
+#include "cs-etm.h"
+#include "../../util/debug.h"
+#include "../../util/record.h"
+#include "../../util/auxtrace.h"
+#include "../../util/cpumap.h"
+#include "../../util/event.h"
+#include "../../util/evlist.h"
+#include "../../util/evsel.h"
+#include "../../util/perf_api_probe.h"
+#include "../../util/evsel_config.h"
+#include "../../util/pmu.h"
+#include "../../util/cs-etm.h"
+#include <internal/lib.h> // page_size
+#include "../../util/session.h"
+
+#include <errno.h>
+#include <stdlib.h>
+#include <sys/stat.h>
+
+struct cs_etm_recording {
+	struct auxtrace_record	itr;
+	struct perf_pmu		*cs_etm_pmu;
+	struct evlist		*evlist;
+	int			wrapped_cnt;
+	bool			*wrapped;
+	bool			snapshot_mode;
+	size_t			snapshot_size;
+};
+
+static const char *metadata_etmv3_ro[CS_ETM_PRIV_MAX] = {
+	[CS_ETM_ETMCCER]	= "mgmt/etmccer",
+	[CS_ETM_ETMIDR]		= "mgmt/etmidr",
+};
+
+static const char *metadata_etmv4_ro[CS_ETMV4_PRIV_MAX] = {
+	[CS_ETMV4_TRCIDR0]		= "trcidr/trcidr0",
+	[CS_ETMV4_TRCIDR1]		= "trcidr/trcidr1",
+	[CS_ETMV4_TRCIDR2]		= "trcidr/trcidr2",
+	[CS_ETMV4_TRCIDR8]		= "trcidr/trcidr8",
+	[CS_ETMV4_TRCAUTHSTATUS]	= "mgmt/trcauthstatus",
+};
+
+static bool cs_etm_is_etmv4(struct auxtrace_record *itr, int cpu);
+
+static int cs_etm_set_context_id(struct auxtrace_record *itr,
+				 struct evsel *evsel, int cpu)
+{
+	struct cs_etm_recording *ptr;
+	struct perf_pmu *cs_etm_pmu;
+	char path[PATH_MAX];
+	int err = -EINVAL;
+	u32 val;
+
+	ptr = container_of(itr, struct cs_etm_recording, itr);
+	cs_etm_pmu = ptr->cs_etm_pmu;
+
+	if (!cs_etm_is_etmv4(itr, cpu))
+		goto out;
+
+	/* Get a handle on TRCIRD2 */
+	snprintf(path, PATH_MAX, "cpu%d/%s",
+		 cpu, metadata_etmv4_ro[CS_ETMV4_TRCIDR2]);
+	err = perf_pmu__scan_file(cs_etm_pmu, path, "%x", &val);
+
+	/* There was a problem reading the file, bailing out */
+	if (err != 1) {
+		pr_err("%s: can't read file %s\n",
+		       CORESIGHT_ETM_PMU_NAME, path);
+		goto out;
+	}
+
+	/*
+	 * TRCIDR2.CIDSIZE, bit [9-5], indicates whether contextID tracing
+	 * is supported:
+	 *  0b00000 Context ID tracing is not supported.
+	 *  0b00100 Maximum of 32-bit Context ID size.
+	 *  All other values are reserved.
+	 */
+	val = BMVAL(val, 5, 9);
+	if (!val || val != 0x4) {
+		err = -EINVAL;
+		goto out;
+	}
+
+	/* All good, let the kernel know */
+	evsel->core.attr.config |= (1 << ETM_OPT_CTXTID);
+	err = 0;
+
+out:
+
+	return err;
+}
+
+static int cs_etm_set_timestamp(struct auxtrace_record *itr,
+				struct evsel *evsel, int cpu)
+{
+	struct cs_etm_recording *ptr;
+	struct perf_pmu *cs_etm_pmu;
+	char path[PATH_MAX];
+	int err = -EINVAL;
+	u32 val;
+
+	ptr = container_of(itr, struct cs_etm_recording, itr);
+	cs_etm_pmu = ptr->cs_etm_pmu;
+
+	if (!cs_etm_is_etmv4(itr, cpu))
+		goto out;
+
+	/* Get a handle on TRCIRD0 */
+	snprintf(path, PATH_MAX, "cpu%d/%s",
+		 cpu, metadata_etmv4_ro[CS_ETMV4_TRCIDR0]);
+	err = perf_pmu__scan_file(cs_etm_pmu, path, "%x", &val);
+
+	/* There was a problem reading the file, bailing out */
+	if (err != 1) {
+		pr_err("%s: can't read file %s\n",
+		       CORESIGHT_ETM_PMU_NAME, path);
+		goto out;
+	}
+
+	/*
+	 * TRCIDR0.TSSIZE, bit [28-24], indicates whether global timestamping
+	 * is supported:
+	 *  0b00000 Global timestamping is not implemented
+	 *  0b00110 Implementation supports a maximum timestamp of 48bits.
+	 *  0b01000 Implementation supports a maximum timestamp of 64bits.
+	 */
+	val &= GENMASK(28, 24);
+	if (!val) {
+		err = -EINVAL;
+		goto out;
+	}
+
+	/* All good, let the kernel know */
+	evsel->core.attr.config |= (1 << ETM_OPT_TS);
+	err = 0;
+
+out:
+	return err;
+}
+
+static int cs_etm_set_option(struct auxtrace_record *itr,
+			     struct evsel *evsel, u32 option)
+{
+	int i, err = -EINVAL;
+	struct perf_cpu_map *event_cpus = evsel->evlist->core.cpus;
+	struct perf_cpu_map *online_cpus = perf_cpu_map__new(NULL);
+
+	/* Set option of each CPU we have */
+	for (i = 0; i < cpu__max_cpu(); i++) {
+		if (!cpu_map__has(event_cpus, i) ||
+		    !cpu_map__has(online_cpus, i))
+			continue;
+
+		if (option & ETM_OPT_CTXTID) {
+			err = cs_etm_set_context_id(itr, evsel, i);
+			if (err)
+				goto out;
+		}
+		if (option & ETM_OPT_TS) {
+			err = cs_etm_set_timestamp(itr, evsel, i);
+			if (err)
+				goto out;
+		}
+		if (option & ~(ETM_OPT_CTXTID | ETM_OPT_TS))
+			/* Nothing else is currently supported */
+			goto out;
+	}
+
+	err = 0;
+out:
+	perf_cpu_map__put(online_cpus);
+	return err;
+}
+
+static int cs_etm_parse_snapshot_options(struct auxtrace_record *itr,
+					 struct record_opts *opts,
+					 const char *str)
+{
+	struct cs_etm_recording *ptr =
+				container_of(itr, struct cs_etm_recording, itr);
+	unsigned long long snapshot_size = 0;
+	char *endptr;
+
+	if (str) {
+		snapshot_size = strtoull(str, &endptr, 0);
+		if (*endptr || snapshot_size > SIZE_MAX)
+			return -1;
+	}
+
+	opts->auxtrace_snapshot_mode = true;
+	opts->auxtrace_snapshot_size = snapshot_size;
+	ptr->snapshot_size = snapshot_size;
+
+	return 0;
+}
+
+static int cs_etm_set_sink_attr(struct perf_pmu *pmu,
+				struct evsel *evsel)
+{
+	char msg[BUFSIZ], path[PATH_MAX], *sink;
+	struct evsel_config_term *term;
+	int ret = -EINVAL;
+	u32 hash;
+
+	if (evsel->core.attr.config2 & GENMASK(31, 0))
+		return 0;
+
+	list_for_each_entry(term, &evsel->config_terms, list) {
+		if (term->type != EVSEL__CONFIG_TERM_DRV_CFG)
+			continue;
+
+		sink = term->val.str;
+		snprintf(path, PATH_MAX, "sinks/%s", sink);
+
+		ret = perf_pmu__scan_file(pmu, path, "%x", &hash);
+		if (ret != 1) {
+			pr_err("failed to set sink \"%s\" on event %s with %d (%s)\n",
+			       sink, evsel__name(evsel), errno,
+			       str_error_r(errno, msg, sizeof(msg)));
+			return ret;
+		}
+
+		evsel->core.attr.config2 |= hash;
+		return 0;
+	}
+
+	/*
+	 * No sink was provided on the command line - allow the CoreSight
+	 * system to look for a default
+	 */
+	return 0;
+}
+
+static int cs_etm_recording_options(struct auxtrace_record *itr,
+				    struct evlist *evlist,
+				    struct record_opts *opts)
+{
+	int ret;
+	struct cs_etm_recording *ptr =
+				container_of(itr, struct cs_etm_recording, itr);
+	struct perf_pmu *cs_etm_pmu = ptr->cs_etm_pmu;
+	struct evsel *evsel, *cs_etm_evsel = NULL;
+	struct perf_cpu_map *cpus = evlist->core.cpus;
+	bool privileged = perf_event_paranoid_check(-1);
+	int err = 0;
+
+	ptr->evlist = evlist;
+	ptr->snapshot_mode = opts->auxtrace_snapshot_mode;
+
+	if (!record_opts__no_switch_events(opts) &&
+	    perf_can_record_switch_events())
+		opts->record_switch_events = true;
+
+	evlist__for_each_entry(evlist, evsel) {
+		if (evsel->core.attr.type == cs_etm_pmu->type) {
+			if (cs_etm_evsel) {
+				pr_err("There may be only one %s event\n",
+				       CORESIGHT_ETM_PMU_NAME);
+				return -EINVAL;
+			}
+			evsel->core.attr.freq = 0;
+			evsel->core.attr.sample_period = 1;
+			cs_etm_evsel = evsel;
+			opts->full_auxtrace = true;
+		}
+	}
+
+	/* no need to continue if at least one event of interest was found */
+	if (!cs_etm_evsel)
+		return 0;
+
+	ret = cs_etm_set_sink_attr(cs_etm_pmu, cs_etm_evsel);
+	if (ret)
+		return ret;
+
+	if (opts->use_clockid) {
+		pr_err("Cannot use clockid (-k option) with %s\n",
+		       CORESIGHT_ETM_PMU_NAME);
+		return -EINVAL;
+	}
+
+	/* we are in snapshot mode */
+	if (opts->auxtrace_snapshot_mode) {
+		/*
+		 * No size were given to '-S' or '-m,', so go with
+		 * the default
+		 */
+		if (!opts->auxtrace_snapshot_size &&
+		    !opts->auxtrace_mmap_pages) {
+			if (privileged) {
+				opts->auxtrace_mmap_pages = MiB(4) / page_size;
+			} else {
+				opts->auxtrace_mmap_pages =
+							KiB(128) / page_size;
+				if (opts->mmap_pages == UINT_MAX)
+					opts->mmap_pages = KiB(256) / page_size;
+			}
+		} else if (!opts->auxtrace_mmap_pages && !privileged &&
+						opts->mmap_pages == UINT_MAX) {
+			opts->mmap_pages = KiB(256) / page_size;
+		}
+
+		/*
+		 * '-m,xyz' was specified but no snapshot size, so make the
+		 * snapshot size as big as the auxtrace mmap area.
+		 */
+		if (!opts->auxtrace_snapshot_size) {
+			opts->auxtrace_snapshot_size =
+				opts->auxtrace_mmap_pages * (size_t)page_size;
+		}
+
+		/*
+		 * -Sxyz was specified but no auxtrace mmap area, so make the
+		 * auxtrace mmap area big enough to fit the requested snapshot
+		 * size.
+		 */
+		if (!opts->auxtrace_mmap_pages) {
+			size_t sz = opts->auxtrace_snapshot_size;
+
+			sz = round_up(sz, page_size) / page_size;
+			opts->auxtrace_mmap_pages = roundup_pow_of_two(sz);
+		}
+
+		/* Snapshost size can't be bigger than the auxtrace area */
+		if (opts->auxtrace_snapshot_size >
+				opts->auxtrace_mmap_pages * (size_t)page_size) {
+			pr_err("Snapshot size %zu must not be greater than AUX area tracing mmap size %zu\n",
+			       opts->auxtrace_snapshot_size,
+			       opts->auxtrace_mmap_pages * (size_t)page_size);
+			return -EINVAL;
+		}
+
+		/* Something went wrong somewhere - this shouldn't happen */
+		if (!opts->auxtrace_snapshot_size ||
+		    !opts->auxtrace_mmap_pages) {
+			pr_err("Failed to calculate default snapshot size and/or AUX area tracing mmap pages\n");
+			return -EINVAL;
+		}
+	}
+
+	/* We are in full trace mode but '-m,xyz' wasn't specified */
+	if (opts->full_auxtrace && !opts->auxtrace_mmap_pages) {
+		if (privileged) {
+			opts->auxtrace_mmap_pages = MiB(4) / page_size;
+		} else {
+			opts->auxtrace_mmap_pages = KiB(128) / page_size;
+			if (opts->mmap_pages == UINT_MAX)
+				opts->mmap_pages = KiB(256) / page_size;
+		}
+
+	}
+
+	/* Validate auxtrace_mmap_pages provided by user */
+	if (opts->auxtrace_mmap_pages) {
+		unsigned int max_page = (KiB(128) / page_size);
+		size_t sz = opts->auxtrace_mmap_pages * (size_t)page_size;
+
+		if (!privileged &&
+		    opts->auxtrace_mmap_pages > max_page) {
+			opts->auxtrace_mmap_pages = max_page;
+			pr_err("auxtrace too big, truncating to %d\n",
+			       max_page);
+		}
+
+		if (!is_power_of_2(sz)) {
+			pr_err("Invalid mmap size for %s: must be a power of 2\n",
+			       CORESIGHT_ETM_PMU_NAME);
+			return -EINVAL;
+		}
+	}
+
+	if (opts->auxtrace_snapshot_mode)
+		pr_debug2("%s snapshot size: %zu\n", CORESIGHT_ETM_PMU_NAME,
+			  opts->auxtrace_snapshot_size);
+
+	/*
+	 * To obtain the auxtrace buffer file descriptor, the auxtrace
+	 * event must come first.
+	 */
+	perf_evlist__to_front(evlist, cs_etm_evsel);
+
+	/*
+	 * In the case of per-cpu mmaps, we need the CPU on the
+	 * AUX event.  We also need the contextID in order to be notified
+	 * when a context switch happened.
+	 */
+	if (!perf_cpu_map__empty(cpus)) {
+		evsel__set_sample_bit(cs_etm_evsel, CPU);
+
+		err = cs_etm_set_option(itr, cs_etm_evsel,
+					ETM_OPT_CTXTID | ETM_OPT_TS);
+		if (err)
+			goto out;
+	}
+
+	/* Add dummy event to keep tracking */
+	if (opts->full_auxtrace) {
+		struct evsel *tracking_evsel;
+
+		err = parse_events(evlist, "dummy:u", NULL);
+		if (err)
+			goto out;
+
+		tracking_evsel = evlist__last(evlist);
+		perf_evlist__set_tracking_event(evlist, tracking_evsel);
+
+		tracking_evsel->core.attr.freq = 0;
+		tracking_evsel->core.attr.sample_period = 1;
+
+		/* In per-cpu case, always need the time of mmap events etc */
+		if (!perf_cpu_map__empty(cpus))
+			evsel__set_sample_bit(tracking_evsel, TIME);
+	}
+
+out:
+	return err;
+}
+
+static u64 cs_etm_get_config(struct auxtrace_record *itr)
+{
+	u64 config = 0;
+	struct cs_etm_recording *ptr =
+			container_of(itr, struct cs_etm_recording, itr);
+	struct perf_pmu *cs_etm_pmu = ptr->cs_etm_pmu;
+	struct evlist *evlist = ptr->evlist;
+	struct evsel *evsel;
+
+	evlist__for_each_entry(evlist, evsel) {
+		if (evsel->core.attr.type == cs_etm_pmu->type) {
+			/*
+			 * Variable perf_event_attr::config is assigned to
+			 * ETMv3/PTM.  The bit fields have been made to match
+			 * the ETMv3.5 ETRMCR register specification.  See the
+			 * PMU_FORMAT_ATTR() declarations in
+			 * drivers/hwtracing/coresight/coresight-perf.c for
+			 * details.
+			 */
+			config = evsel->core.attr.config;
+			break;
+		}
+	}
+
+	return config;
+}
+
+#ifndef BIT
+#define BIT(N) (1UL << (N))
+#endif
+
+static u64 cs_etmv4_get_config(struct auxtrace_record *itr)
+{
+	u64 config = 0;
+	u64 config_opts = 0;
+
+	/*
+	 * The perf event variable config bits represent both
+	 * the command line options and register programming
+	 * bits in ETMv3/PTM. For ETMv4 we must remap options
+	 * to real bits
+	 */
+	config_opts = cs_etm_get_config(itr);
+	if (config_opts & BIT(ETM_OPT_CYCACC))
+		config |= BIT(ETM4_CFG_BIT_CYCACC);
+	if (config_opts & BIT(ETM_OPT_CTXTID))
+		config |= BIT(ETM4_CFG_BIT_CTXTID);
+	if (config_opts & BIT(ETM_OPT_TS))
+		config |= BIT(ETM4_CFG_BIT_TS);
+	if (config_opts & BIT(ETM_OPT_RETSTK))
+		config |= BIT(ETM4_CFG_BIT_RETSTK);
+
+	return config;
+}
+
+static size_t
+cs_etm_info_priv_size(struct auxtrace_record *itr __maybe_unused,
+		      struct evlist *evlist __maybe_unused)
+{
+	int i;
+	int etmv3 = 0, etmv4 = 0;
+	struct perf_cpu_map *event_cpus = evlist->core.cpus;
+	struct perf_cpu_map *online_cpus = perf_cpu_map__new(NULL);
+
+	/* cpu map is not empty, we have specific CPUs to work with */
+	if (!perf_cpu_map__empty(event_cpus)) {
+		for (i = 0; i < cpu__max_cpu(); i++) {
+			if (!cpu_map__has(event_cpus, i) ||
+			    !cpu_map__has(online_cpus, i))
+				continue;
+
+			if (cs_etm_is_etmv4(itr, i))
+				etmv4++;
+			else
+				etmv3++;
+		}
+	} else {
+		/* get configuration for all CPUs in the system */
+		for (i = 0; i < cpu__max_cpu(); i++) {
+			if (!cpu_map__has(online_cpus, i))
+				continue;
+
+			if (cs_etm_is_etmv4(itr, i))
+				etmv4++;
+			else
+				etmv3++;
+		}
+	}
+
+	perf_cpu_map__put(online_cpus);
+
+	return (CS_ETM_HEADER_SIZE +
+	       (etmv4 * CS_ETMV4_PRIV_SIZE) +
+	       (etmv3 * CS_ETMV3_PRIV_SIZE));
+}
+
+static bool cs_etm_is_etmv4(struct auxtrace_record *itr, int cpu)
+{
+	bool ret = false;
+	char path[PATH_MAX];
+	int scan;
+	unsigned int val;
+	struct cs_etm_recording *ptr =
+			container_of(itr, struct cs_etm_recording, itr);
+	struct perf_pmu *cs_etm_pmu = ptr->cs_etm_pmu;
+
+	/* Take any of the RO files for ETMv4 and see if it present */
+	snprintf(path, PATH_MAX, "cpu%d/%s",
+		 cpu, metadata_etmv4_ro[CS_ETMV4_TRCIDR0]);
+	scan = perf_pmu__scan_file(cs_etm_pmu, path, "%x", &val);
+
+	/* The file was read successfully, we have a winner */
+	if (scan == 1)
+		ret = true;
+
+	return ret;
+}
+
+static int cs_etm_get_ro(struct perf_pmu *pmu, int cpu, const char *path)
+{
+	char pmu_path[PATH_MAX];
+	int scan;
+	unsigned int val = 0;
+
+	/* Get RO metadata from sysfs */
+	snprintf(pmu_path, PATH_MAX, "cpu%d/%s", cpu, path);
+
+	scan = perf_pmu__scan_file(pmu, pmu_path, "%x", &val);
+	if (scan != 1)
+		pr_err("%s: error reading: %s\n", __func__, pmu_path);
+
+	return val;
+}
+
+static void cs_etm_get_metadata(int cpu, u32 *offset,
+				struct auxtrace_record *itr,
+				struct perf_record_auxtrace_info *info)
+{
+	u32 increment;
+	u64 magic;
+	struct cs_etm_recording *ptr =
+			container_of(itr, struct cs_etm_recording, itr);
+	struct perf_pmu *cs_etm_pmu = ptr->cs_etm_pmu;
+
+	/* first see what kind of tracer this cpu is affined to */
+	if (cs_etm_is_etmv4(itr, cpu)) {
+		magic = __perf_cs_etmv4_magic;
+		/* Get trace configuration register */
+		info->priv[*offset + CS_ETMV4_TRCCONFIGR] =
+						cs_etmv4_get_config(itr);
+		/* Get traceID from the framework */
+		info->priv[*offset + CS_ETMV4_TRCTRACEIDR] =
+						coresight_get_trace_id(cpu);
+		/* Get read-only information from sysFS */
+		info->priv[*offset + CS_ETMV4_TRCIDR0] =
+			cs_etm_get_ro(cs_etm_pmu, cpu,
+				      metadata_etmv4_ro[CS_ETMV4_TRCIDR0]);
+		info->priv[*offset + CS_ETMV4_TRCIDR1] =
+			cs_etm_get_ro(cs_etm_pmu, cpu,
+				      metadata_etmv4_ro[CS_ETMV4_TRCIDR1]);
+		info->priv[*offset + CS_ETMV4_TRCIDR2] =
+			cs_etm_get_ro(cs_etm_pmu, cpu,
+				      metadata_etmv4_ro[CS_ETMV4_TRCIDR2]);
+		info->priv[*offset + CS_ETMV4_TRCIDR8] =
+			cs_etm_get_ro(cs_etm_pmu, cpu,
+				      metadata_etmv4_ro[CS_ETMV4_TRCIDR8]);
+		info->priv[*offset + CS_ETMV4_TRCAUTHSTATUS] =
+			cs_etm_get_ro(cs_etm_pmu, cpu,
+				      metadata_etmv4_ro
+				      [CS_ETMV4_TRCAUTHSTATUS]);
+
+		/* How much space was used */
+		increment = CS_ETMV4_PRIV_MAX;
+	} else {
+		magic = __perf_cs_etmv3_magic;
+		/* Get configuration register */
+		info->priv[*offset + CS_ETM_ETMCR] = cs_etm_get_config(itr);
+		/* Get traceID from the framework */
+		info->priv[*offset + CS_ETM_ETMTRACEIDR] =
+						coresight_get_trace_id(cpu);
+		/* Get read-only information from sysFS */
+		info->priv[*offset + CS_ETM_ETMCCER] =
+			cs_etm_get_ro(cs_etm_pmu, cpu,
+				      metadata_etmv3_ro[CS_ETM_ETMCCER]);
+		info->priv[*offset + CS_ETM_ETMIDR] =
+			cs_etm_get_ro(cs_etm_pmu, cpu,
+				      metadata_etmv3_ro[CS_ETM_ETMIDR]);
+
+		/* How much space was used */
+		increment = CS_ETM_PRIV_MAX;
+	}
+
+	/* Build generic header portion */
+	info->priv[*offset + CS_ETM_MAGIC] = magic;
+	info->priv[*offset + CS_ETM_CPU] = cpu;
+	/* Where the next CPU entry should start from */
+	*offset += increment;
+}
+
+static int cs_etm_info_fill(struct auxtrace_record *itr,
+			    struct perf_session *session,
+			    struct perf_record_auxtrace_info *info,
+			    size_t priv_size)
+{
+	int i;
+	u32 offset;
+	u64 nr_cpu, type;
+	struct perf_cpu_map *cpu_map;
+	struct perf_cpu_map *event_cpus = session->evlist->core.cpus;
+	struct perf_cpu_map *online_cpus = perf_cpu_map__new(NULL);
+	struct cs_etm_recording *ptr =
+			container_of(itr, struct cs_etm_recording, itr);
+	struct perf_pmu *cs_etm_pmu = ptr->cs_etm_pmu;
+
+	if (priv_size != cs_etm_info_priv_size(itr, session->evlist))
+		return -EINVAL;
+
+	if (!session->evlist->core.nr_mmaps)
+		return -EINVAL;
+
+	/* If the cpu_map is empty all online CPUs are involved */
+	if (perf_cpu_map__empty(event_cpus)) {
+		cpu_map = online_cpus;
+	} else {
+		/* Make sure all specified CPUs are online */
+		for (i = 0; i < perf_cpu_map__nr(event_cpus); i++) {
+			if (cpu_map__has(event_cpus, i) &&
+			    !cpu_map__has(online_cpus, i))
+				return -EINVAL;
+		}
+
+		cpu_map = event_cpus;
+	}
+
+	nr_cpu = perf_cpu_map__nr(cpu_map);
+	/* Get PMU type as dynamically assigned by the core */
+	type = cs_etm_pmu->type;
+
+	/* First fill out the session header */
+	info->type = PERF_AUXTRACE_CS_ETM;
+	info->priv[CS_HEADER_VERSION_0] = 0;
+	info->priv[CS_PMU_TYPE_CPUS] = type << 32;
+	info->priv[CS_PMU_TYPE_CPUS] |= nr_cpu;
+	info->priv[CS_ETM_SNAPSHOT] = ptr->snapshot_mode;
+
+	offset = CS_ETM_SNAPSHOT + 1;
+
+	for (i = 0; i < cpu__max_cpu() && offset < priv_size; i++)
+		if (cpu_map__has(cpu_map, i))
+			cs_etm_get_metadata(i, &offset, itr, info);
+
+	perf_cpu_map__put(online_cpus);
+
+	return 0;
+}
+
+static int cs_etm_alloc_wrapped_array(struct cs_etm_recording *ptr, int idx)
+{
+	bool *wrapped;
+	int cnt = ptr->wrapped_cnt;
+
+	/* Make @ptr->wrapped as big as @idx */
+	while (cnt <= idx)
+		cnt++;
+
+	/*
+	 * Free'ed in cs_etm_recording_free().  Using realloc() to avoid
+	 * cross compilation problems where the host's system supports
+	 * reallocarray() but not the target.
+	 */
+	wrapped = realloc(ptr->wrapped, cnt * sizeof(bool));
+	if (!wrapped)
+		return -ENOMEM;
+
+	wrapped[cnt - 1] = false;
+	ptr->wrapped_cnt = cnt;
+	ptr->wrapped = wrapped;
+
+	return 0;
+}
+
+static bool cs_etm_buffer_has_wrapped(unsigned char *buffer,
+				      size_t buffer_size, u64 head)
+{
+	u64 i, watermark;
+	u64 *buf = (u64 *)buffer;
+	size_t buf_size = buffer_size;
+
+	/*
+	 * We want to look the very last 512 byte (chosen arbitrarily) in
+	 * the ring buffer.
+	 */
+	watermark = buf_size - 512;
+
+	/*
+	 * @head is continuously increasing - if its value is equal or greater
+	 * than the size of the ring buffer, it has wrapped around.
+	 */
+	if (head >= buffer_size)
+		return true;
+
+	/*
+	 * The value of @head is somewhere within the size of the ring buffer.
+	 * This can be that there hasn't been enough data to fill the ring
+	 * buffer yet or the trace time was so long that @head has numerically
+	 * wrapped around.  To find we need to check if we have data at the very
+	 * end of the ring buffer.  We can reliably do this because mmap'ed
+	 * pages are zeroed out and there is a fresh mapping with every new
+	 * session.
+	 */
+
+	/* @head is less than 512 byte from the end of the ring buffer */
+	if (head > watermark)
+		watermark = head;
+
+	/*
+	 * Speed things up by using 64 bit transactions (see "u64 *buf" above)
+	 */
+	watermark >>= 3;
+	buf_size >>= 3;
+
+	/*
+	 * If we find trace data at the end of the ring buffer, @head has
+	 * been there and has numerically wrapped around at least once.
+	 */
+	for (i = watermark; i < buf_size; i++)
+		if (buf[i])
+			return true;
+
+	return false;
+}
+
+static int cs_etm_find_snapshot(struct auxtrace_record *itr,
+				int idx, struct auxtrace_mmap *mm,
+				unsigned char *data,
+				u64 *head, u64 *old)
+{
+	int err;
+	bool wrapped;
+	struct cs_etm_recording *ptr =
+			container_of(itr, struct cs_etm_recording, itr);
+
+	/*
+	 * Allocate memory to keep track of wrapping if this is the first
+	 * time we deal with this *mm.
+	 */
+	if (idx >= ptr->wrapped_cnt) {
+		err = cs_etm_alloc_wrapped_array(ptr, idx);
+		if (err)
+			return err;
+	}
+
+	/*
+	 * Check to see if *head has wrapped around.  If it hasn't only the
+	 * amount of data between *head and *old is snapshot'ed to avoid
+	 * bloating the perf.data file with zeros.  But as soon as *head has
+	 * wrapped around the entire size of the AUX ring buffer it taken.
+	 */
+	wrapped = ptr->wrapped[idx];
+	if (!wrapped && cs_etm_buffer_has_wrapped(data, mm->len, *head)) {
+		wrapped = true;
+		ptr->wrapped[idx] = true;
+	}
+
+	pr_debug3("%s: mmap index %d old head %zu new head %zu size %zu\n",
+		  __func__, idx, (size_t)*old, (size_t)*head, mm->len);
+
+	/* No wrap has occurred, we can just use *head and *old. */
+	if (!wrapped)
+		return 0;
+
+	/*
+	 * *head has wrapped around - adjust *head and *old to pickup the
+	 * entire content of the AUX buffer.
+	 */
+	if (*head >= mm->len) {
+		*old = *head - mm->len;
+	} else {
+		*head += mm->len;
+		*old = *head - mm->len;
+	}
+
+	return 0;
+}
+
+static int cs_etm_snapshot_start(struct auxtrace_record *itr)
+{
+	struct cs_etm_recording *ptr =
+			container_of(itr, struct cs_etm_recording, itr);
+	struct evsel *evsel;
+
+	evlist__for_each_entry(ptr->evlist, evsel) {
+		if (evsel->core.attr.type == ptr->cs_etm_pmu->type)
+			return evsel__disable(evsel);
+	}
+	return -EINVAL;
+}
+
+static int cs_etm_snapshot_finish(struct auxtrace_record *itr)
+{
+	struct cs_etm_recording *ptr =
+			container_of(itr, struct cs_etm_recording, itr);
+	struct evsel *evsel;
+
+	evlist__for_each_entry(ptr->evlist, evsel) {
+		if (evsel->core.attr.type == ptr->cs_etm_pmu->type)
+			return evsel__enable(evsel);
+	}
+	return -EINVAL;
+}
+
+static u64 cs_etm_reference(struct auxtrace_record *itr __maybe_unused)
+{
+	return (((u64) rand() <<  0) & 0x00000000FFFFFFFFull) |
+		(((u64) rand() << 32) & 0xFFFFFFFF00000000ull);
+}
+
+static void cs_etm_recording_free(struct auxtrace_record *itr)
+{
+	struct cs_etm_recording *ptr =
+			container_of(itr, struct cs_etm_recording, itr);
+
+	zfree(&ptr->wrapped);
+	free(ptr);
+}
+
+struct auxtrace_record *cs_etm_record_init(int *err)
+{
+	struct perf_pmu *cs_etm_pmu;
+	struct cs_etm_recording *ptr;
+
+	cs_etm_pmu = perf_pmu__find(CORESIGHT_ETM_PMU_NAME);
+
+	if (!cs_etm_pmu) {
+		*err = -EINVAL;
+		goto out;
+	}
+
+	ptr = zalloc(sizeof(struct cs_etm_recording));
+	if (!ptr) {
+		*err = -ENOMEM;
+		goto out;
+	}
+
+	ptr->cs_etm_pmu			= cs_etm_pmu;
+	ptr->itr.pmu			= cs_etm_pmu;
+	ptr->itr.parse_snapshot_options	= cs_etm_parse_snapshot_options;
+	ptr->itr.recording_options	= cs_etm_recording_options;
+	ptr->itr.info_priv_size		= cs_etm_info_priv_size;
+	ptr->itr.info_fill		= cs_etm_info_fill;
+	ptr->itr.find_snapshot		= cs_etm_find_snapshot;
+	ptr->itr.snapshot_start		= cs_etm_snapshot_start;
+	ptr->itr.snapshot_finish	= cs_etm_snapshot_finish;
+	ptr->itr.reference		= cs_etm_reference;
+	ptr->itr.free			= cs_etm_recording_free;
+	ptr->itr.read_finish		= auxtrace_record__read_finish;
+
+	*err = 0;
+	return &ptr->itr;
+out:
+	return NULL;
+}
diff --git a/tools/perf/arch/arm/util/cs-etm.h b/tools/perf/arch/arm/util/cs-etm.h
new file mode 100644
index 000000000..a3354bda4
--- /dev/null
+++ b/tools/perf/arch/arm/util/cs-etm.h
@@ -0,0 +1,12 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright(C) 2015 Linaro Limited. All rights reserved.
+ * Author: Mathieu Poirier <mathieu.poirier@linaro.org>
+ */
+
+#ifndef INCLUDE__PERF_CS_ETM_H__
+#define INCLUDE__PERF_CS_ETM_H__
+
+struct auxtrace_record *cs_etm_record_init(int *err);
+
+#endif
diff --git a/tools/perf/arch/arm/util/dwarf-regs.c b/tools/perf/arch/arm/util/dwarf-regs.c
new file mode 100644
index 000000000..fc5f71c91
--- /dev/null
+++ b/tools/perf/arch/arm/util/dwarf-regs.c
@@ -0,0 +1,61 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Mapping of DWARF debug register numbers into register names.
+ *
+ * Copyright (C) 2010 Will Deacon, ARM Ltd.
+ */
+
+#include <stddef.h>
+#include <linux/stringify.h>
+#include <dwarf-regs.h>
+
+struct pt_regs_dwarfnum {
+	const char *name;
+	unsigned int dwarfnum;
+};
+
+#define REG_DWARFNUM_NAME(r, num) {.name = r, .dwarfnum = num}
+#define GPR_DWARFNUM_NAME(num) \
+	{.name = __stringify(%r##num), .dwarfnum = num}
+#define REG_DWARFNUM_END {.name = NULL, .dwarfnum = 0}
+
+/*
+ * Reference:
+ * http://infocenter.arm.com/help/topic/com.arm.doc.ihi0040a/IHI0040A_aadwarf.pdf
+ */
+static const struct pt_regs_dwarfnum regdwarfnum_table[] = {
+	GPR_DWARFNUM_NAME(0),
+	GPR_DWARFNUM_NAME(1),
+	GPR_DWARFNUM_NAME(2),
+	GPR_DWARFNUM_NAME(3),
+	GPR_DWARFNUM_NAME(4),
+	GPR_DWARFNUM_NAME(5),
+	GPR_DWARFNUM_NAME(6),
+	GPR_DWARFNUM_NAME(7),
+	GPR_DWARFNUM_NAME(8),
+	GPR_DWARFNUM_NAME(9),
+	GPR_DWARFNUM_NAME(10),
+	REG_DWARFNUM_NAME("%fp", 11),
+	REG_DWARFNUM_NAME("%ip", 12),
+	REG_DWARFNUM_NAME("%sp", 13),
+	REG_DWARFNUM_NAME("%lr", 14),
+	REG_DWARFNUM_NAME("%pc", 15),
+	REG_DWARFNUM_END,
+};
+
+/**
+ * get_arch_regstr() - lookup register name from it's DWARF register number
+ * @n:	the DWARF register number
+ *
+ * get_arch_regstr() returns the name of the register in struct
+ * regdwarfnum_table from it's DWARF register number. If the register is not
+ * found in the table, this returns NULL;
+ */
+const char *get_arch_regstr(unsigned int n)
+{
+	const struct pt_regs_dwarfnum *roff;
+	for (roff = regdwarfnum_table; roff->name != NULL; roff++)
+		if (roff->dwarfnum == n)
+			return roff->name;
+	return NULL;
+}
diff --git a/tools/perf/arch/arm/util/perf_regs.c b/tools/perf/arch/arm/util/perf_regs.c
new file mode 100644
index 000000000..2864e2e37
--- /dev/null
+++ b/tools/perf/arch/arm/util/perf_regs.c
@@ -0,0 +1,6 @@
+// SPDX-License-Identifier: GPL-2.0
+#include "../../util/perf_regs.h"
+
+const struct sample_reg sample_reg_masks[] = {
+	SMPL_REG_END
+};
diff --git a/tools/perf/arch/arm/util/pmu.c b/tools/perf/arch/arm/util/pmu.c
new file mode 100644
index 000000000..bbc297a7e
--- /dev/null
+++ b/tools/perf/arch/arm/util/pmu.c
@@ -0,0 +1,30 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright(C) 2015 Linaro Limited. All rights reserved.
+ * Author: Mathieu Poirier <mathieu.poirier@linaro.org>
+ */
+
+#include <string.h>
+#include <linux/coresight-pmu.h>
+#include <linux/perf_event.h>
+#include <linux/string.h>
+
+#include "arm-spe.h"
+#include "../../util/pmu.h"
+
+struct perf_event_attr
+*perf_pmu__get_default_config(struct perf_pmu *pmu __maybe_unused)
+{
+#ifdef HAVE_AUXTRACE_SUPPORT
+	if (!strcmp(pmu->name, CORESIGHT_ETM_PMU_NAME)) {
+		/* add ETM default config here */
+		pmu->selectable = true;
+#if defined(__aarch64__)
+	} else if (strstarts(pmu->name, ARM_SPE_PMU_NAME)) {
+		return arm_spe_pmu_default_config(pmu);
+#endif
+	}
+
+#endif
+	return NULL;
+}
diff --git a/tools/perf/arch/arm/util/unwind-libdw.c b/tools/perf/arch/arm/util/unwind-libdw.c
new file mode 100644
index 000000000..36ba4c69c
--- /dev/null
+++ b/tools/perf/arch/arm/util/unwind-libdw.c
@@ -0,0 +1,38 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <elfutils/libdwfl.h>
+#include "../../util/unwind-libdw.h"
+#include "../../util/perf_regs.h"
+#include "../../util/event.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[PERF_REG_ARM_MAX];
+
+#define REG(r) ({						\
+	Dwarf_Word val = 0;					\
+	perf_reg_value(&val, user_regs, PERF_REG_ARM_##r);	\
+	val;							\
+})
+
+	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(FP);
+	dwarf_regs[12] = REG(IP);
+	dwarf_regs[13] = REG(SP);
+	dwarf_regs[14] = REG(LR);
+	dwarf_regs[15] = REG(PC);
+
+	return dwfl_thread_state_registers(thread, 0, PERF_REG_ARM_MAX,
+					   dwarf_regs);
+}
diff --git a/tools/perf/arch/arm/util/unwind-libunwind.c b/tools/perf/arch/arm/util/unwind-libunwind.c
new file mode 100644
index 000000000..3a550225d
--- /dev/null
+++ b/tools/perf/arch/arm/util/unwind-libunwind.c
@@ -0,0 +1,50 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <errno.h>
+#include <libunwind.h>
+#include "perf_regs.h"
+#include "../../util/unwind.h"
+#include "../../util/debug.h"
+
+int libunwind__arch_reg_id(int regnum)
+{
+	switch (regnum) {
+	case UNW_ARM_R0:
+		return PERF_REG_ARM_R0;
+	case UNW_ARM_R1:
+		return PERF_REG_ARM_R1;
+	case UNW_ARM_R2:
+		return PERF_REG_ARM_R2;
+	case UNW_ARM_R3:
+		return PERF_REG_ARM_R3;
+	case UNW_ARM_R4:
+		return PERF_REG_ARM_R4;
+	case UNW_ARM_R5:
+		return PERF_REG_ARM_R5;
+	case UNW_ARM_R6:
+		return PERF_REG_ARM_R6;
+	case UNW_ARM_R7:
+		return PERF_REG_ARM_R7;
+	case UNW_ARM_R8:
+		return PERF_REG_ARM_R8;
+	case UNW_ARM_R9:
+		return PERF_REG_ARM_R9;
+	case UNW_ARM_R10:
+		return PERF_REG_ARM_R10;
+	case UNW_ARM_R11:
+		return PERF_REG_ARM_FP;
+	case UNW_ARM_R12:
+		return PERF_REG_ARM_IP;
+	case UNW_ARM_R13:
+		return PERF_REG_ARM_SP;
+	case UNW_ARM_R14:
+		return PERF_REG_ARM_LR;
+	case UNW_ARM_R15:
+		return PERF_REG_ARM_PC;
+	default:
+		pr_err("unwind: invalid reg id %d\n", regnum);
+		return -EINVAL;
+	}
+
+	return -EINVAL;
+}