22 files changed, 1701 insertions, 62 deletions

diff --git a/tools/perf/util/Build b/tools/perf/util/Build
index 7c6a8b461e24..ea0a452550b0 100644
--- a/tools/perf/util/Build
+++ b/tools/perf/util/Build
@@ -44,7 +44,7 @@ libperf-y += machine.o
 libperf-y += map.o
 libperf-y += pstack.o
 libperf-y += session.o
-libperf-$(CONFIG_AUDIT) += syscalltbl.o
+libperf-$(CONFIG_TRACE) += syscalltbl.o
 libperf-y += ordered-events.o
 libperf-y += namespaces.o
 libperf-y += comm.o
@@ -88,6 +88,12 @@ libperf-$(CONFIG_AUXTRACE) += intel-pt.o
 libperf-$(CONFIG_AUXTRACE) += intel-bts.o
 libperf-$(CONFIG_AUXTRACE) += arm-spe.o
 libperf-$(CONFIG_AUXTRACE) += arm-spe-pkt-decoder.o
+
+ifdef CONFIG_LIBOPENCSD
+libperf-$(CONFIG_AUXTRACE) += cs-etm.o
+libperf-$(CONFIG_AUXTRACE) += cs-etm-decoder/
+endif
+
 libperf-y += parse-branch-options.o
 libperf-y += dump-insn.o
 libperf-y += parse-regs-options.o
diff --git a/tools/perf/util/auxtrace.c b/tools/perf/util/auxtrace.c
index 3bba9947ab7f..9faf3b5367db 100644
--- a/tools/perf/util/auxtrace.c
+++ b/tools/perf/util/auxtrace.c
@@ -52,6 +52,7 @@
 #include "debug.h"
 #include <subcmd/parse-options.h>
 
+#include "cs-etm.h"
 #include "intel-pt.h"
 #include "intel-bts.h"
 #include "arm-spe.h"
@@ -914,6 +915,7 @@ int perf_event__process_auxtrace_info(struct perf_tool *tool __maybe_unused,
 	case PERF_AUXTRACE_ARM_SPE:
 		return arm_spe_process_auxtrace_info(event, session);
 	case PERF_AUXTRACE_CS_ETM:
+		return cs_etm__process_auxtrace_info(event, session);
 	case PERF_AUXTRACE_UNKNOWN:
 	default:
 		return -EINVAL;
diff --git a/tools/perf/util/bpf-loader.c b/tools/perf/util/bpf-loader.c
index 72c107fcbc5a..af7ad814b2c3 100644
--- a/tools/perf/util/bpf-loader.c
+++ b/tools/perf/util/bpf-loader.c
@@ -94,7 +94,7 @@ struct bpf_object *bpf__prepare_load(const char *filename, bool source)
 		err = perf_clang__compile_bpf(filename, &obj_buf, &obj_buf_sz);
 		perf_clang__cleanup();
 		if (err) {
-			pr_warning("bpf: builtin compilation failed: %d, try external compiler\n", err);
+			pr_debug("bpf: builtin compilation failed: %d, try external compiler\n", err);
 			err = llvm__compile_bpf(filename, &obj_buf, &obj_buf_sz);
 			if (err)
 				return ERR_PTR(-BPF_LOADER_ERRNO__COMPILE);
@@ -1533,7 +1533,7 @@ int bpf__apply_obj_config(void)
 			(strcmp("__bpf_stdout__", 	\
 				bpf_map__name(pos)) == 0))
 
-int bpf__setup_stdout(struct perf_evlist *evlist __maybe_unused)
+int bpf__setup_stdout(struct perf_evlist *evlist)
 {
 	struct bpf_map_priv *tmpl_priv = NULL;
 	struct bpf_object *obj, *tmp;
diff --git a/tools/perf/util/cgroup.c b/tools/perf/util/cgroup.c
index d9ffc1e6eb39..984f69144f87 100644
--- a/tools/perf/util/cgroup.c
+++ b/tools/perf/util/cgroup.c
@@ -6,6 +6,9 @@
 #include "cgroup.h"
 #include "evlist.h"
 #include <linux/stringify.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <fcntl.h>
 
 int nr_cgroups;
 
diff --git a/tools/perf/util/cs-etm-decoder/Build b/tools/perf/util/cs-etm-decoder/Build
new file mode 100644
index 000000000000..bc22c39c727f
--- /dev/null
+++ b/tools/perf/util/cs-etm-decoder/Build
@@ -0,0 +1 @@
+libperf-$(CONFIG_AUXTRACE) += cs-etm-decoder.o
diff --git a/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c b/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c
new file mode 100644
index 000000000000..1fb01849f1c7
--- /dev/null
+++ b/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c
@@ -0,0 +1,513 @@
+/*
+ * SPDX-License-Identifier: GPL-2.0
+ *
+ * Copyright(C) 2015-2018 Linaro Limited.
+ *
+ * Author: Tor Jeremiassen <tor@ti.com>
+ * Author: Mathieu Poirier <mathieu.poirier@linaro.org>
+ */
+
+#include <linux/err.h>
+#include <linux/list.h>
+#include <stdlib.h>
+#include <opencsd/c_api/opencsd_c_api.h>
+#include <opencsd/etmv4/trc_pkt_types_etmv4.h>
+#include <opencsd/ocsd_if_types.h>
+
+#include "cs-etm.h"
+#include "cs-etm-decoder.h"
+#include "intlist.h"
+#include "util.h"
+
+#define MAX_BUFFER 1024
+
+/* use raw logging */
+#ifdef CS_DEBUG_RAW
+#define CS_LOG_RAW_FRAMES
+#ifdef CS_RAW_PACKED
+#define CS_RAW_DEBUG_FLAGS (OCSD_DFRMTR_UNPACKED_RAW_OUT | \
+			    OCSD_DFRMTR_PACKED_RAW_OUT)
+#else
+#define CS_RAW_DEBUG_FLAGS (OCSD_DFRMTR_UNPACKED_RAW_OUT)
+#endif
+#endif
+
+struct cs_etm_decoder {
+	void *data;
+	void (*packet_printer)(const char *msg);
+	bool trace_on;
+	dcd_tree_handle_t dcd_tree;
+	cs_etm_mem_cb_type mem_access;
+	ocsd_datapath_resp_t prev_return;
+	u32 packet_count;
+	u32 head;
+	u32 tail;
+	struct cs_etm_packet packet_buffer[MAX_BUFFER];
+};
+
+static u32
+cs_etm_decoder__mem_access(const void *context,
+			   const ocsd_vaddr_t address,
+			   const ocsd_mem_space_acc_t mem_space __maybe_unused,
+			   const u32 req_size,
+			   u8 *buffer)
+{
+	struct cs_etm_decoder *decoder = (struct cs_etm_decoder *) context;
+
+	return decoder->mem_access(decoder->data,
+				   address,
+				   req_size,
+				   buffer);
+}
+
+int cs_etm_decoder__add_mem_access_cb(struct cs_etm_decoder *decoder,
+				      u64 start, u64 end,
+				      cs_etm_mem_cb_type cb_func)
+{
+	decoder->mem_access = cb_func;
+
+	if (ocsd_dt_add_callback_mem_acc(decoder->dcd_tree, start, end,
+					 OCSD_MEM_SPACE_ANY,
+					 cs_etm_decoder__mem_access, decoder))
+		return -1;
+
+	return 0;
+}
+
+int cs_etm_decoder__reset(struct cs_etm_decoder *decoder)
+{
+	ocsd_datapath_resp_t dp_ret;
+
+	dp_ret = ocsd_dt_process_data(decoder->dcd_tree, OCSD_OP_RESET,
+				      0, 0, NULL, NULL);
+	if (OCSD_DATA_RESP_IS_FATAL(dp_ret))
+		return -1;
+
+	return 0;
+}
+
+int cs_etm_decoder__get_packet(struct cs_etm_decoder *decoder,
+			       struct cs_etm_packet *packet)
+{
+	if (!decoder || !packet)
+		return -EINVAL;
+
+	/* Nothing to do, might as well just return */
+	if (decoder->packet_count == 0)
+		return 0;
+
+	*packet = decoder->packet_buffer[decoder->head];
+
+	decoder->head = (decoder->head + 1) & (MAX_BUFFER - 1);
+
+	decoder->packet_count--;
+
+	return 1;
+}
+
+static void cs_etm_decoder__gen_etmv4_config(struct cs_etm_trace_params *params,
+					     ocsd_etmv4_cfg *config)
+{
+	config->reg_configr = params->etmv4.reg_configr;
+	config->reg_traceidr = params->etmv4.reg_traceidr;
+	config->reg_idr0 = params->etmv4.reg_idr0;
+	config->reg_idr1 = params->etmv4.reg_idr1;
+	config->reg_idr2 = params->etmv4.reg_idr2;
+	config->reg_idr8 = params->etmv4.reg_idr8;
+	config->reg_idr9 = 0;
+	config->reg_idr10 = 0;
+	config->reg_idr11 = 0;
+	config->reg_idr12 = 0;
+	config->reg_idr13 = 0;
+	config->arch_ver = ARCH_V8;
+	config->core_prof = profile_CortexA;
+}
+
+static void cs_etm_decoder__print_str_cb(const void *p_context,
+					 const char *msg,
+					 const int str_len)
+{
+	if (p_context && str_len)
+		((struct cs_etm_decoder *)p_context)->packet_printer(msg);
+}
+
+static int
+cs_etm_decoder__init_def_logger_printing(struct cs_etm_decoder_params *d_params,
+					 struct cs_etm_decoder *decoder)
+{
+	int ret = 0;
+
+	if (d_params->packet_printer == NULL)
+		return -1;
+
+	decoder->packet_printer = d_params->packet_printer;
+
+	/*
+	 * Set up a library default logger to process any printers
+	 * (packet/raw frame) we add later.
+	 */
+	ret = ocsd_def_errlog_init(OCSD_ERR_SEV_ERROR, 1);
+	if (ret != 0)
+		return -1;
+
+	/* no stdout / err / file output */
+	ret = ocsd_def_errlog_config_output(C_API_MSGLOGOUT_FLG_NONE, NULL);
+	if (ret != 0)
+		return -1;
+
+	/*
+	 * Set the string CB for the default logger, passes strings to
+	 * perf print logger.
+	 */
+	ret = ocsd_def_errlog_set_strprint_cb(decoder->dcd_tree,
+					      (void *)decoder,
+					      cs_etm_decoder__print_str_cb);
+	if (ret != 0)
+		ret = -1;
+
+	return 0;
+}
+
+#ifdef CS_LOG_RAW_FRAMES
+static void
+cs_etm_decoder__init_raw_frame_logging(struct cs_etm_decoder_params *d_params,
+				       struct cs_etm_decoder *decoder)
+{
+	/* Only log these during a --dump operation */
+	if (d_params->operation == CS_ETM_OPERATION_PRINT) {
+		/* set up a library default logger to process the
+		 *  raw frame printer we add later
+		 */
+		ocsd_def_errlog_init(OCSD_ERR_SEV_ERROR, 1);
+
+		/* no stdout / err / file output */
+		ocsd_def_errlog_config_output(C_API_MSGLOGOUT_FLG_NONE, NULL);
+
+		/* set the string CB for the default logger,
+		 * passes strings to perf print logger.
+		 */
+		ocsd_def_errlog_set_strprint_cb(decoder->dcd_tree,
+						(void *)decoder,
+						cs_etm_decoder__print_str_cb);
+
+		/* use the built in library printer for the raw frames */
+		ocsd_dt_set_raw_frame_printer(decoder->dcd_tree,
+					      CS_RAW_DEBUG_FLAGS);
+	}
+}
+#else
+static void
+cs_etm_decoder__init_raw_frame_logging(
+		struct cs_etm_decoder_params *d_params __maybe_unused,
+		struct cs_etm_decoder *decoder __maybe_unused)
+{
+}
+#endif
+
+static int cs_etm_decoder__create_packet_printer(struct cs_etm_decoder *decoder,
+						 const char *decoder_name,
+						 void *trace_config)
+{
+	u8 csid;
+
+	if (ocsd_dt_create_decoder(decoder->dcd_tree, decoder_name,
+				   OCSD_CREATE_FLG_PACKET_PROC,
+				   trace_config, &csid))
+		return -1;
+
+	if (ocsd_dt_set_pkt_protocol_printer(decoder->dcd_tree, csid, 0))
+		return -1;
+
+	return 0;
+}
+
+static int
+cs_etm_decoder__create_etm_packet_printer(struct cs_etm_trace_params *t_params,
+					  struct cs_etm_decoder *decoder)
+{
+	const char *decoder_name;
+	ocsd_etmv4_cfg trace_config_etmv4;
+	void *trace_config;
+
+	switch (t_params->protocol) {
+	case CS_ETM_PROTO_ETMV4i:
+		cs_etm_decoder__gen_etmv4_config(t_params, &trace_config_etmv4);
+		decoder_name = OCSD_BUILTIN_DCD_ETMV4I;
+		trace_config = &trace_config_etmv4;
+		break;
+	default:
+		return -1;
+	}
+
+	return cs_etm_decoder__create_packet_printer(decoder,
+						     decoder_name,
+						     trace_config);
+}
+
+static void cs_etm_decoder__clear_buffer(struct cs_etm_decoder *decoder)
+{
+	int i;
+
+	decoder->head = 0;
+	decoder->tail = 0;
+	decoder->packet_count = 0;
+	for (i = 0; i < MAX_BUFFER; i++) {
+		decoder->packet_buffer[i].start_addr = 0xdeadbeefdeadbeefUL;
+		decoder->packet_buffer[i].end_addr   = 0xdeadbeefdeadbeefUL;
+		decoder->packet_buffer[i].exc	     = false;
+		decoder->packet_buffer[i].exc_ret    = false;
+		decoder->packet_buffer[i].cpu	     = INT_MIN;
+	}
+}
+
+static ocsd_datapath_resp_t
+cs_etm_decoder__buffer_packet(struct cs_etm_decoder *decoder,
+			      const ocsd_generic_trace_elem *elem,
+			      const u8 trace_chan_id,
+			      enum cs_etm_sample_type sample_type)
+{
+	u32 et = 0;
+	struct int_node *inode = NULL;
+
+	if (decoder->packet_count >= MAX_BUFFER - 1)
+		return OCSD_RESP_FATAL_SYS_ERR;
+
+	/* Search the RB tree for the cpu associated with this traceID */
+	inode = intlist__find(traceid_list, trace_chan_id);
+	if (!inode)
+		return OCSD_RESP_FATAL_SYS_ERR;
+
+	et = decoder->tail;
+	decoder->packet_buffer[et].sample_type = sample_type;
+	decoder->packet_buffer[et].start_addr = elem->st_addr;
+	decoder->packet_buffer[et].end_addr = elem->en_addr;
+	decoder->packet_buffer[et].exc = false;
+	decoder->packet_buffer[et].exc_ret = false;
+	decoder->packet_buffer[et].cpu = *((int *)inode->priv);
+
+	/* Wrap around if need be */
+	et = (et + 1) & (MAX_BUFFER - 1);
+
+	decoder->tail = et;
+	decoder->packet_count++;
+
+	if (decoder->packet_count == MAX_BUFFER - 1)
+		return OCSD_RESP_WAIT;
+
+	return OCSD_RESP_CONT;
+}
+
+static ocsd_datapath_resp_t cs_etm_decoder__gen_trace_elem_printer(
+				const void *context,
+				const ocsd_trc_index_t indx __maybe_unused,
+				const u8 trace_chan_id __maybe_unused,
+				const ocsd_generic_trace_elem *elem)
+{
+	ocsd_datapath_resp_t resp = OCSD_RESP_CONT;
+	struct cs_etm_decoder *decoder = (struct cs_etm_decoder *) context;
+
+	switch (elem->elem_type) {
+	case OCSD_GEN_TRC_ELEM_UNKNOWN:
+		break;
+	case OCSD_GEN_TRC_ELEM_NO_SYNC:
+		decoder->trace_on = false;
+		break;
+	case OCSD_GEN_TRC_ELEM_TRACE_ON:
+		decoder->trace_on = true;
+		break;
+	case OCSD_GEN_TRC_ELEM_INSTR_RANGE:
+		resp = cs_etm_decoder__buffer_packet(decoder, elem,
+						     trace_chan_id,
+						     CS_ETM_RANGE);
+		break;
+	case OCSD_GEN_TRC_ELEM_EXCEPTION:
+		decoder->packet_buffer[decoder->tail].exc = true;
+		break;
+	case OCSD_GEN_TRC_ELEM_EXCEPTION_RET:
+		decoder->packet_buffer[decoder->tail].exc_ret = true;
+		break;
+	case OCSD_GEN_TRC_ELEM_PE_CONTEXT:
+	case OCSD_GEN_TRC_ELEM_EO_TRACE:
+	case OCSD_GEN_TRC_ELEM_ADDR_NACC:
+	case OCSD_GEN_TRC_ELEM_TIMESTAMP:
+	case OCSD_GEN_TRC_ELEM_CYCLE_COUNT:
+	case OCSD_GEN_TRC_ELEM_ADDR_UNKNOWN:
+	case OCSD_GEN_TRC_ELEM_EVENT:
+	case OCSD_GEN_TRC_ELEM_SWTRACE:
+	case OCSD_GEN_TRC_ELEM_CUSTOM:
+	default:
+		break;
+	}
+
+	return resp;
+}
+
+static int cs_etm_decoder__create_etm_packet_decoder(
+					struct cs_etm_trace_params *t_params,
+					struct cs_etm_decoder *decoder)
+{
+	const char *decoder_name;
+	ocsd_etmv4_cfg trace_config_etmv4;
+	void *trace_config;
+	u8 csid;
+
+	switch (t_params->protocol) {
+	case CS_ETM_PROTO_ETMV4i:
+		cs_etm_decoder__gen_etmv4_config(t_params, &trace_config_etmv4);
+		decoder_name = OCSD_BUILTIN_DCD_ETMV4I;
+		trace_config = &trace_config_etmv4;
+		break;
+	default:
+		return -1;
+	}
+
+	if (ocsd_dt_create_decoder(decoder->dcd_tree,
+				     decoder_name,
+				     OCSD_CREATE_FLG_FULL_DECODER,
+				     trace_config, &csid))
+		return -1;
+
+	if (ocsd_dt_set_gen_elem_outfn(decoder->dcd_tree,
+				       cs_etm_decoder__gen_trace_elem_printer,
+				       decoder))
+		return -1;
+
+	return 0;
+}
+
+static int
+cs_etm_decoder__create_etm_decoder(struct cs_etm_decoder_params *d_params,
+				   struct cs_etm_trace_params *t_params,
+				   struct cs_etm_decoder *decoder)
+{
+	if (d_params->operation == CS_ETM_OPERATION_PRINT)
+		return cs_etm_decoder__create_etm_packet_printer(t_params,
+								 decoder);
+	else if (d_params->operation == CS_ETM_OPERATION_DECODE)
+		return cs_etm_decoder__create_etm_packet_decoder(t_params,
+								 decoder);
+
+	return -1;
+}
+
+struct cs_etm_decoder *
+cs_etm_decoder__new(int num_cpu, struct cs_etm_decoder_params *d_params,
+		    struct cs_etm_trace_params t_params[])
+{
+	struct cs_etm_decoder *decoder;
+	ocsd_dcd_tree_src_t format;
+	u32 flags;
+	int i, ret;
+
+	if ((!t_params) || (!d_params))
+		return NULL;
+
+	decoder = zalloc(sizeof(*decoder));
+
+	if (!decoder)
+		return NULL;
+
+	decoder->data = d_params->data;
+	decoder->prev_return = OCSD_RESP_CONT;
+	cs_etm_decoder__clear_buffer(decoder);
+	format = (d_params->formatted ? OCSD_TRC_SRC_FRAME_FORMATTED :
+					 OCSD_TRC_SRC_SINGLE);
+	flags = 0;
+	flags |= (d_params->fsyncs ? OCSD_DFRMTR_HAS_FSYNCS : 0);
+	flags |= (d_params->hsyncs ? OCSD_DFRMTR_HAS_HSYNCS : 0);
+	flags |= (d_params->frame_aligned ? OCSD_DFRMTR_FRAME_MEM_ALIGN : 0);
+
+	/*
+	 * Drivers may add barrier frames when used with perf, set up to
+	 * handle this. Barriers const of FSYNC packet repeated 4 times.
+	 */
+	flags |= OCSD_DFRMTR_RESET_ON_4X_FSYNC;
+
+	/* Create decode tree for the data source */
+	decoder->dcd_tree = ocsd_create_dcd_tree(format, flags);
+
+	if (decoder->dcd_tree == 0)
+		goto err_free_decoder;
+
+	/* init library print logging support */
+	ret = cs_etm_decoder__init_def_logger_printing(d_params, decoder);
+	if (ret != 0)
+		goto err_free_decoder_tree;
+
+	/* init raw frame logging if required */
+	cs_etm_decoder__init_raw_frame_logging(d_params, decoder);
+
+	for (i = 0; i < num_cpu; i++) {
+		ret = cs_etm_decoder__create_etm_decoder(d_params,
+							 &t_params[i],
+							 decoder);
+		if (ret != 0)
+			goto err_free_decoder_tree;
+	}
+
+	return decoder;
+
+err_free_decoder_tree:
+	ocsd_destroy_dcd_tree(decoder->dcd_tree);
+err_free_decoder:
+	free(decoder);
+	return NULL;
+}
+
+int cs_etm_decoder__process_data_block(struct cs_etm_decoder *decoder,
+				       u64 indx, const u8 *buf,
+				       size_t len, size_t *consumed)
+{
+	int ret = 0;
+	ocsd_datapath_resp_t cur = OCSD_RESP_CONT;
+	ocsd_datapath_resp_t prev_return = decoder->prev_return;
+	size_t processed = 0;
+	u32 count;
+
+	while (processed < len) {
+		if (OCSD_DATA_RESP_IS_WAIT(prev_return)) {
+			cur = ocsd_dt_process_data(decoder->dcd_tree,
+						   OCSD_OP_FLUSH,
+						   0,
+						   0,
+						   NULL,
+						   NULL);
+		} else if (OCSD_DATA_RESP_IS_CONT(prev_return)) {
+			cur = ocsd_dt_process_data(decoder->dcd_tree,
+						   OCSD_OP_DATA,
+						   indx + processed,
+						   len - processed,
+						   &buf[processed],
+						   &count);
+			processed += count;
+		} else {
+			ret = -EINVAL;
+			break;
+		}
+
+		/*
+		 * Return to the input code if the packet buffer is full.
+		 * Flushing will get done once the packet buffer has been
+		 * processed.
+		 */
+		if (OCSD_DATA_RESP_IS_WAIT(cur))
+			break;
+
+		prev_return = cur;
+	}
+
+	decoder->prev_return = cur;
+	*consumed = processed;
+
+	return ret;
+}
+
+void cs_etm_decoder__free(struct cs_etm_decoder *decoder)
+{
+	if (!decoder)
+		return;
+
+	ocsd_destroy_dcd_tree(decoder->dcd_tree);
+	decoder->dcd_tree = NULL;
+	free(decoder);
+}
diff --git a/tools/perf/util/cs-etm-decoder/cs-etm-decoder.h b/tools/perf/util/cs-etm-decoder/cs-etm-decoder.h
new file mode 100644
index 000000000000..3d2e6205d186
--- /dev/null
+++ b/tools/perf/util/cs-etm-decoder/cs-etm-decoder.h
@@ -0,0 +1,105 @@
+/*
+ * SPDX-License-Identifier: GPL-2.0
+ *
+ * Copyright(C) 2015-2018 Linaro Limited.
+ *
+ * Author: Tor Jeremiassen <tor@ti.com>
+ * Author: Mathieu Poirier <mathieu.poirier@linaro.org>
+ */
+
+#ifndef INCLUDE__CS_ETM_DECODER_H__
+#define INCLUDE__CS_ETM_DECODER_H__
+
+#include <linux/types.h>
+#include <stdio.h>
+
+struct cs_etm_decoder;
+
+struct cs_etm_buffer {
+	const unsigned char *buf;
+	size_t len;
+	u64 offset;
+	u64 ref_timestamp;
+};
+
+enum cs_etm_sample_type {
+	CS_ETM_RANGE = 1 << 0,
+};
+
+struct cs_etm_packet {
+	enum cs_etm_sample_type sample_type;
+	u64 start_addr;
+	u64 end_addr;
+	u8 exc;
+	u8 exc_ret;
+	int cpu;
+};
+
+struct cs_etm_queue;
+
+typedef u32 (*cs_etm_mem_cb_type)(struct cs_etm_queue *, u64,
+				  size_t, u8 *);
+
+struct cs_etmv4_trace_params {
+	u32 reg_idr0;
+	u32 reg_idr1;
+	u32 reg_idr2;
+	u32 reg_idr8;
+	u32 reg_configr;
+	u32 reg_traceidr;
+};
+
+struct cs_etm_trace_params {
+	int protocol;
+	union {
+		struct cs_etmv4_trace_params etmv4;
+	};
+};
+
+struct cs_etm_decoder_params {
+	int operation;
+	void (*packet_printer)(const char *msg);
+	cs_etm_mem_cb_type mem_acc_cb;
+	u8 formatted;
+	u8 fsyncs;
+	u8 hsyncs;
+	u8 frame_aligned;
+	void *data;
+};
+
+/*
+ * The following enums are indexed starting with 1 to align with the
+ * open source coresight trace decoder library.
+ */
+enum {
+	CS_ETM_PROTO_ETMV3 = 1,
+	CS_ETM_PROTO_ETMV4i,
+	CS_ETM_PROTO_ETMV4d,
+};
+
+enum {
+	CS_ETM_OPERATION_PRINT = 1,
+	CS_ETM_OPERATION_DECODE,
+};
+
+int cs_etm_decoder__process_data_block(struct cs_etm_decoder *decoder,
+				       u64 indx, const u8 *buf,
+				       size_t len, size_t *consumed);
+
+struct cs_etm_decoder *
+cs_etm_decoder__new(int num_cpu,
+		    struct cs_etm_decoder_params *d_params,
+		    struct cs_etm_trace_params t_params[]);
+
+void cs_etm_decoder__free(struct cs_etm_decoder *decoder);
+
+int cs_etm_decoder__add_mem_access_cb(struct cs_etm_decoder *decoder,
+				      u64 start, u64 end,
+				      cs_etm_mem_cb_type cb_func);
+
+int cs_etm_decoder__get_packet(struct cs_etm_decoder *decoder,
+			       struct cs_etm_packet *packet);
+
+int cs_etm_decoder__reset(struct cs_etm_decoder *decoder);
+
+#endif /* INCLUDE__CS_ETM_DECODER_H__ */
diff --git a/tools/perf/util/cs-etm.c b/tools/perf/util/cs-etm.c
new file mode 100644
index 000000000000..b9f0a53dfa65
--- /dev/null
+++ b/tools/perf/util/cs-etm.c
@@ -0,0 +1,1023 @@
+/*
+ * SPDX-License-Identifier: GPL-2.0
+ *
+ * Copyright(C) 2015-2018 Linaro Limited.
+ *
+ * Author: Tor Jeremiassen <tor@ti.com>
+ * Author: Mathieu Poirier <mathieu.poirier@linaro.org>
+ */
+
+#include <linux/bitops.h>
+#include <linux/err.h>
+#include <linux/kernel.h>
+#include <linux/log2.h>
+#include <linux/types.h>
+
+#include <stdlib.h>
+
+#include "auxtrace.h"
+#include "color.h"
+#include "cs-etm.h"
+#include "cs-etm-decoder/cs-etm-decoder.h"
+#include "debug.h"
+#include "evlist.h"
+#include "intlist.h"
+#include "machine.h"
+#include "map.h"
+#include "perf.h"
+#include "thread.h"
+#include "thread_map.h"
+#include "thread-stack.h"
+#include "util.h"
+
+#define MAX_TIMESTAMP (~0ULL)
+
+struct cs_etm_auxtrace {
+	struct auxtrace auxtrace;
+	struct auxtrace_queues queues;
+	struct auxtrace_heap heap;
+	struct itrace_synth_opts synth_opts;
+	struct perf_session *session;
+	struct machine *machine;
+	struct thread *unknown_thread;
+
+	u8 timeless_decoding;
+	u8 snapshot_mode;
+	u8 data_queued;
+	u8 sample_branches;
+
+	int num_cpu;
+	u32 auxtrace_type;
+	u64 branches_sample_type;
+	u64 branches_id;
+	u64 **metadata;
+	u64 kernel_start;
+	unsigned int pmu_type;
+};
+
+struct cs_etm_queue {
+	struct cs_etm_auxtrace *etm;
+	struct thread *thread;
+	struct cs_etm_decoder *decoder;
+	struct auxtrace_buffer *buffer;
+	const struct cs_etm_state *state;
+	union perf_event *event_buf;
+	unsigned int queue_nr;
+	pid_t pid, tid;
+	int cpu;
+	u64 time;
+	u64 timestamp;
+	u64 offset;
+};
+
+static int cs_etm__update_queues(struct cs_etm_auxtrace *etm);
+static int cs_etm__process_timeless_queues(struct cs_etm_auxtrace *etm,
+					   pid_t tid, u64 time_);
+
+static void cs_etm__packet_dump(const char *pkt_string)
+{
+	const char *color = PERF_COLOR_BLUE;
+	int len = strlen(pkt_string);
+
+	if (len && (pkt_string[len-1] == '\n'))
+		color_fprintf(stdout, color, "	%s", pkt_string);
+	else
+		color_fprintf(stdout, color, "	%s\n", pkt_string);
+
+	fflush(stdout);
+}
+
+static void cs_etm__dump_event(struct cs_etm_auxtrace *etm,
+			       struct auxtrace_buffer *buffer)
+{
+	int i, ret;
+	const char *color = PERF_COLOR_BLUE;
+	struct cs_etm_decoder_params d_params;
+	struct cs_etm_trace_params *t_params;
+	struct cs_etm_decoder *decoder;
+	size_t buffer_used = 0;
+
+	fprintf(stdout, "\n");
+	color_fprintf(stdout, color,
+		     ". ... CoreSight ETM Trace data: size %zu bytes\n",
+		     buffer->size);
+
+	/* Use metadata to fill in trace parameters for trace decoder */
+	t_params = zalloc(sizeof(*t_params) * etm->num_cpu);
+	for (i = 0; i < etm->num_cpu; i++) {
+		t_params[i].protocol = CS_ETM_PROTO_ETMV4i;
+		t_params[i].etmv4.reg_idr0 = etm->metadata[i][CS_ETMV4_TRCIDR0];
+		t_params[i].etmv4.reg_idr1 = etm->metadata[i][CS_ETMV4_TRCIDR1];
+		t_params[i].etmv4.reg_idr2 = etm->metadata[i][CS_ETMV4_TRCIDR2];
+		t_params[i].etmv4.reg_idr8 = etm->metadata[i][CS_ETMV4_TRCIDR8];
+		t_params[i].etmv4.reg_configr =
+					etm->metadata[i][CS_ETMV4_TRCCONFIGR];
+		t_params[i].etmv4.reg_traceidr =
+					etm->metadata[i][CS_ETMV4_TRCTRACEIDR];
+	}
+
+	/* Set decoder parameters to simply print the trace packets */
+	d_params.packet_printer = cs_etm__packet_dump;
+	d_params.operation = CS_ETM_OPERATION_PRINT;
+	d_params.formatted = true;
+	d_params.fsyncs = false;
+	d_params.hsyncs = false;
+	d_params.frame_aligned = true;
+
+	decoder = cs_etm_decoder__new(etm->num_cpu, &d_params, t_params);
+
+	zfree(&t_params);
+
+	if (!decoder)
+		return;
+	do {
+		size_t consumed;
+
+		ret = cs_etm_decoder__process_data_block(
+				decoder, buffer->offset,
+				&((u8 *)buffer->data)[buffer_used],
+				buffer->size - buffer_used, &consumed);
+		if (ret)
+			break;
+
+		buffer_used += consumed;
+	} while (buffer_used < buffer->size);
+
+	cs_etm_decoder__free(decoder);
+}
+
+static int cs_etm__flush_events(struct perf_session *session,
+				struct perf_tool *tool)
+{
+	int ret;
+	struct cs_etm_auxtrace *etm = container_of(session->auxtrace,
+						   struct cs_etm_auxtrace,
+						   auxtrace);
+	if (dump_trace)
+		return 0;
+
+	if (!tool->ordered_events)
+		return -EINVAL;
+
+	if (!etm->timeless_decoding)
+		return -EINVAL;
+
+	ret = cs_etm__update_queues(etm);
+
+	if (ret < 0)
+		return ret;
+
+	return cs_etm__process_timeless_queues(etm, -1, MAX_TIMESTAMP - 1);
+}
+
+static void cs_etm__free_queue(void *priv)
+{
+	struct cs_etm_queue *etmq = priv;
+
+	free(etmq);
+}
+
+static void cs_etm__free_events(struct perf_session *session)
+{
+	unsigned int i;
+	struct cs_etm_auxtrace *aux = container_of(session->auxtrace,
+						   struct cs_etm_auxtrace,
+						   auxtrace);
+	struct auxtrace_queues *queues = &aux->queues;
+
+	for (i = 0; i < queues->nr_queues; i++) {
+		cs_etm__free_queue(queues->queue_array[i].priv);
+		queues->queue_array[i].priv = NULL;
+	}
+
+	auxtrace_queues__free(queues);
+}
+
+static void cs_etm__free(struct perf_session *session)
+{
+	int i;
+	struct int_node *inode, *tmp;
+	struct cs_etm_auxtrace *aux = container_of(session->auxtrace,
+						   struct cs_etm_auxtrace,
+						   auxtrace);
+	cs_etm__free_events(session);
+	session->auxtrace = NULL;
+
+	/* First remove all traceID/CPU# nodes for the RB tree */
+	intlist__for_each_entry_safe(inode, tmp, traceid_list)
+		intlist__remove(traceid_list, inode);
+	/* Then the RB tree itself */
+	intlist__delete(traceid_list);
+
+	for (i = 0; i < aux->num_cpu; i++)
+		zfree(&aux->metadata[i]);
+
+	zfree(&aux->metadata);
+	zfree(&aux);
+}
+
+static u32 cs_etm__mem_access(struct cs_etm_queue *etmq, u64 address,
+			      size_t size, u8 *buffer)
+{
+	u8  cpumode;
+	u64 offset;
+	int len;
+	struct	 thread *thread;
+	struct	 machine *machine;
+	struct	 addr_location al;
+
+	if (!etmq)
+		return -1;
+
+	machine = etmq->etm->machine;
+	if (address >= etmq->etm->kernel_start)
+		cpumode = PERF_RECORD_MISC_KERNEL;
+	else
+		cpumode = PERF_RECORD_MISC_USER;
+
+	thread = etmq->thread;
+	if (!thread) {
+		if (cpumode != PERF_RECORD_MISC_KERNEL)
+			return -EINVAL;
+		thread = etmq->etm->unknown_thread;
+	}
+
+	thread__find_addr_map(thread, cpumode, MAP__FUNCTION, address, &al);
+
+	if (!al.map || !al.map->dso)
+		return 0;
+
+	if (al.map->dso->data.status == DSO_DATA_STATUS_ERROR &&
+	    dso__data_status_seen(al.map->dso, DSO_DATA_STATUS_SEEN_ITRACE))
+		return 0;
+
+	offset = al.map->map_ip(al.map, address);
+
+	map__load(al.map);
+
+	len = dso__data_read_offset(al.map->dso, machine, offset, buffer, size);
+
+	if (len <= 0)
+		return 0;
+
+	return len;
+}
+
+static struct cs_etm_queue *cs_etm__alloc_queue(struct cs_etm_auxtrace *etm,
+						unsigned int queue_nr)
+{
+	int i;
+	struct cs_etm_decoder_params d_params;
+	struct cs_etm_trace_params  *t_params;
+	struct cs_etm_queue *etmq;
+
+	etmq = zalloc(sizeof(*etmq));
+	if (!etmq)
+		return NULL;
+
+	etmq->event_buf = malloc(PERF_SAMPLE_MAX_SIZE);
+	if (!etmq->event_buf)
+		goto out_free;
+
+	etmq->etm = etm;
+	etmq->queue_nr = queue_nr;
+	etmq->pid = -1;
+	etmq->tid = -1;
+	etmq->cpu = -1;
+
+	/* Use metadata to fill in trace parameters for trace decoder */
+	t_params = zalloc(sizeof(*t_params) * etm->num_cpu);
+
+	if (!t_params)
+		goto out_free;
+
+	for (i = 0; i < etm->num_cpu; i++) {
+		t_params[i].protocol = CS_ETM_PROTO_ETMV4i;
+		t_params[i].etmv4.reg_idr0 = etm->metadata[i][CS_ETMV4_TRCIDR0];
+		t_params[i].etmv4.reg_idr1 = etm->metadata[i][CS_ETMV4_TRCIDR1];
+		t_params[i].etmv4.reg_idr2 = etm->metadata[i][CS_ETMV4_TRCIDR2];
+		t_params[i].etmv4.reg_idr8 = etm->metadata[i][CS_ETMV4_TRCIDR8];
+		t_params[i].etmv4.reg_configr =
+					etm->metadata[i][CS_ETMV4_TRCCONFIGR];
+		t_params[i].etmv4.reg_traceidr =
+					etm->metadata[i][CS_ETMV4_TRCTRACEIDR];
+	}
+
+	/* Set decoder parameters to simply print the trace packets */
+	d_params.packet_printer = cs_etm__packet_dump;
+	d_params.operation = CS_ETM_OPERATION_DECODE;
+	d_params.formatted = true;
+	d_params.fsyncs = false;
+	d_params.hsyncs = false;
+	d_params.frame_aligned = true;
+	d_params.data = etmq;
+
+	etmq->decoder = cs_etm_decoder__new(etm->num_cpu, &d_params, t_params);
+
+	zfree(&t_params);
+
+	if (!etmq->decoder)
+		goto out_free;
+
+	/*
+	 * Register a function to handle all memory accesses required by
+	 * the trace decoder library.
+	 */
+	if (cs_etm_decoder__add_mem_access_cb(etmq->decoder,
+					      0x0L, ((u64) -1L),
+					      cs_etm__mem_access))
+		goto out_free_decoder;
+
+	etmq->offset = 0;
+
+	return etmq;
+
+out_free_decoder:
+	cs_etm_decoder__free(etmq->decoder);
+out_free:
+	zfree(&etmq->event_buf);
+	free(etmq);
+
+	return NULL;
+}
+
+static int cs_etm__setup_queue(struct cs_etm_auxtrace *etm,
+			       struct auxtrace_queue *queue,
+			       unsigned int queue_nr)
+{
+	struct cs_etm_queue *etmq = queue->priv;
+
+	if (list_empty(&queue->head) || etmq)
+		return 0;
+
+	etmq = cs_etm__alloc_queue(etm, queue_nr);
+
+	if (!etmq)
+		return -ENOMEM;
+
+	queue->priv = etmq;
+
+	if (queue->cpu != -1)
+		etmq->cpu = queue->cpu;
+
+	etmq->tid = queue->tid;
+
+	return 0;
+}
+
+static int cs_etm__setup_queues(struct cs_etm_auxtrace *etm)
+{
+	unsigned int i;
+	int ret;
+
+	for (i = 0; i < etm->queues.nr_queues; i++) {
+		ret = cs_etm__setup_queue(etm, &etm->queues.queue_array[i], i);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
+static int cs_etm__update_queues(struct cs_etm_auxtrace *etm)
+{
+	if (etm->queues.new_data) {
+		etm->queues.new_data = false;
+		return cs_etm__setup_queues(etm);
+	}
+
+	return 0;
+}
+
+static int
+cs_etm__get_trace(struct cs_etm_buffer *buff, struct cs_etm_queue *etmq)
+{
+	struct auxtrace_buffer *aux_buffer = etmq->buffer;
+	struct auxtrace_buffer *old_buffer = aux_buffer;
+	struct auxtrace_queue *queue;
+
+	queue = &etmq->etm->queues.queue_array[etmq->queue_nr];
+
+	aux_buffer = auxtrace_buffer__next(queue, aux_buffer);
+
+	/* If no more data, drop the previous auxtrace_buffer and return */
+	if (!aux_buffer) {
+		if (old_buffer)
+			auxtrace_buffer__drop_data(old_buffer);
+		buff->len = 0;
+		return 0;
+	}
+
+	etmq->buffer = aux_buffer;
+
+	/* If the aux_buffer doesn't have data associated, try to load it */
+	if (!aux_buffer->data) {
+		/* get the file desc associated with the perf data file */
+		int fd = perf_data__fd(etmq->etm->session->data);
+
+		aux_buffer->data = auxtrace_buffer__get_data(aux_buffer, fd);
+		if (!aux_buffer->data)
+			return -ENOMEM;
+	}
+
+	/* If valid, drop the previous buffer */
+	if (old_buffer)
+		auxtrace_buffer__drop_data(old_buffer);
+
+	buff->offset = aux_buffer->offset;
+	buff->len = aux_buffer->size;
+	buff->buf = aux_buffer->data;
+
+	buff->ref_timestamp = aux_buffer->reference;
+
+	return buff->len;
+}
+
+static void  cs_etm__set_pid_tid_cpu(struct cs_etm_auxtrace *etm,
+				     struct auxtrace_queue *queue)
+{
+	struct cs_etm_queue *etmq = queue->priv;
+
+	/* CPU-wide tracing isn't supported yet */
+	if (queue->tid == -1)
+		return;
+
+	if ((!etmq->thread) && (etmq->tid != -1))
+		etmq->thread = machine__find_thread(etm->machine, -1,
+						    etmq->tid);
+
+	if (etmq->thread) {
+		etmq->pid = etmq->thread->pid_;
+		if (queue->cpu == -1)
+			etmq->cpu = etmq->thread->cpu;
+	}
+}
+
+/*
+ * The cs etm packet encodes an instruction range between a branch target
+ * and the next taken branch. Generate sample accordingly.
+ */
+static int cs_etm__synth_branch_sample(struct cs_etm_queue *etmq,
+				       struct cs_etm_packet *packet)
+{
+	int ret = 0;
+	struct cs_etm_auxtrace *etm = etmq->etm;
+	struct perf_sample sample = {.ip = 0,};
+	union perf_event *event = etmq->event_buf;
+	u64 start_addr = packet->start_addr;
+	u64 end_addr = packet->end_addr;
+
+	event->sample.header.type = PERF_RECORD_SAMPLE;
+	event->sample.header.misc = PERF_RECORD_MISC_USER;
+	event->sample.header.size = sizeof(struct perf_event_header);
+
+	sample.ip = start_addr;
+	sample.pid = etmq->pid;
+	sample.tid = etmq->tid;
+	sample.addr = end_addr;
+	sample.id = etmq->etm->branches_id;
+	sample.stream_id = etmq->etm->branches_id;
+	sample.period = 1;
+	sample.cpu = packet->cpu;
+	sample.flags = 0;
+	sample.cpumode = PERF_RECORD_MISC_USER;
+
+	ret = perf_session__deliver_synth_event(etm->session, event, &sample);
+
+	if (ret)
+		pr_err(
+		"CS ETM Trace: failed to deliver instruction event, error %d\n",
+		ret);
+
+	return ret;
+}
+
+struct cs_etm_synth {
+	struct perf_tool dummy_tool;
+	struct perf_session *session;
+};
+
+static int cs_etm__event_synth(struct perf_tool *tool,
+			       union perf_event *event,
+			       struct perf_sample *sample __maybe_unused,
+			       struct machine *machine __maybe_unused)
+{
+	struct cs_etm_synth *cs_etm_synth =
+		      container_of(tool, struct cs_etm_synth, dummy_tool);
+
+	return perf_session__deliver_synth_event(cs_etm_synth->session,
+						 event, NULL);
+}
+
+static int cs_etm__synth_event(struct perf_session *session,
+			       struct perf_event_attr *attr, u64 id)
+{
+	struct cs_etm_synth cs_etm_synth;
+
+	memset(&cs_etm_synth, 0, sizeof(struct cs_etm_synth));
+	cs_etm_synth.session = session;
+
+	return perf_event__synthesize_attr(&cs_etm_synth.dummy_tool, attr, 1,
+					   &id, cs_etm__event_synth);
+}
+
+static int cs_etm__synth_events(struct cs_etm_auxtrace *etm,
+				struct perf_session *session)
+{
+	struct perf_evlist *evlist = session->evlist;
+	struct perf_evsel *evsel;
+	struct perf_event_attr attr;
+	bool found = false;
+	u64 id;
+	int err;
+
+	evlist__for_each_entry(evlist, evsel) {
+		if (evsel->attr.type == etm->pmu_type) {
+			found = true;
+			break;
+		}
+	}
+
+	if (!found) {
+		pr_debug("No selected events with CoreSight Trace data\n");
+		return 0;
+	}
+
+	memset(&attr, 0, sizeof(struct perf_event_attr));
+	attr.size = sizeof(struct perf_event_attr);
+	attr.type = PERF_TYPE_HARDWARE;
+	attr.sample_type = evsel->attr.sample_type & PERF_SAMPLE_MASK;
+	attr.sample_type |= PERF_SAMPLE_IP | PERF_SAMPLE_TID |
+			    PERF_SAMPLE_PERIOD;
+	if (etm->timeless_decoding)
+		attr.sample_type &= ~(u64)PERF_SAMPLE_TIME;
+	else
+		attr.sample_type |= PERF_SAMPLE_TIME;
+
+	attr.exclude_user = evsel->attr.exclude_user;
+	attr.exclude_kernel = evsel->attr.exclude_kernel;
+	attr.exclude_hv = evsel->attr.exclude_hv;
+	attr.exclude_host = evsel->attr.exclude_host;
+	attr.exclude_guest = evsel->attr.exclude_guest;
+	attr.sample_id_all = evsel->attr.sample_id_all;
+	attr.read_format = evsel->attr.read_format;
+
+	/* create new id val to be a fixed offset from evsel id */
+	id = evsel->id[0] + 1000000000;
+
+	if (!id)
+		id = 1;
+
+	if (etm->synth_opts.branches) {
+		attr.config = PERF_COUNT_HW_BRANCH_INSTRUCTIONS;
+		attr.sample_period = 1;
+		attr.sample_type |= PERF_SAMPLE_ADDR;
+		err = cs_etm__synth_event(session, &attr, id);
+		if (err)
+			return err;
+		etm->sample_branches = true;
+		etm->branches_sample_type = attr.sample_type;
+		etm->branches_id = id;
+	}
+
+	return 0;
+}
+
+static int cs_etm__sample(struct cs_etm_queue *etmq)
+{
+	int ret;
+	struct cs_etm_packet packet;
+
+	while (1) {
+		ret = cs_etm_decoder__get_packet(etmq->decoder, &packet);
+		if (ret <= 0)
+			return ret;
+
+		/*
+		 * If the packet contains an instruction range, generate an
+		 * instruction sequence event.
+		 */
+		if (packet.sample_type & CS_ETM_RANGE)
+			cs_etm__synth_branch_sample(etmq, &packet);
+	}
+
+	return 0;
+}
+
+static int cs_etm__run_decoder(struct cs_etm_queue *etmq)
+{
+	struct cs_etm_auxtrace *etm = etmq->etm;
+	struct cs_etm_buffer buffer;
+	size_t buffer_used, processed;
+	int err = 0;
+
+	if (!etm->kernel_start)
+		etm->kernel_start = machine__kernel_start(etm->machine);
+
+	/* Go through each buffer in the queue and decode them one by one */
+more:
+	buffer_used = 0;
+	memset(&buffer, 0, sizeof(buffer));
+	err = cs_etm__get_trace(&buffer, etmq);
+	if (err <= 0)
+		return err;
+	/*
+	 * We cannot assume consecutive blocks in the data file are contiguous,
+	 * reset the decoder to force re-sync.
+	 */
+	err = cs_etm_decoder__reset(etmq->decoder);
+	if (err != 0)
+		return err;
+
+	/* Run trace decoder until buffer consumed or end of trace */
+	do {
+		processed = 0;
+
+		err = cs_etm_decoder__process_data_block(
+						etmq->decoder,
+						etmq->offset,
+						&buffer.buf[buffer_used],
+						buffer.len - buffer_used,
+						&processed);
+
+		if (err)
+			return err;
+
+		etmq->offset += processed;
+		buffer_used += processed;
+
+		/*
+		 * Nothing to do with an error condition, let's hope the next
+		 * chunk will be better.
+		 */
+		err = cs_etm__sample(etmq);
+	} while (buffer.len > buffer_used);
+
+goto more;
+
+	return err;
+}
+
+static int cs_etm__process_timeless_queues(struct cs_etm_auxtrace *etm,
+					   pid_t tid, u64 time_)
+{
+	unsigned int i;
+	struct auxtrace_queues *queues = &etm->queues;
+
+	for (i = 0; i < queues->nr_queues; i++) {
+		struct auxtrace_queue *queue = &etm->queues.queue_array[i];
+		struct cs_etm_queue *etmq = queue->priv;
+
+		if (etmq && ((tid == -1) || (etmq->tid == tid))) {
+			etmq->time = time_;
+			cs_etm__set_pid_tid_cpu(etm, queue);
+			cs_etm__run_decoder(etmq);
+		}
+	}
+
+	return 0;
+}
+
+static int cs_etm__process_event(struct perf_session *session,
+				 union perf_event *event,
+				 struct perf_sample *sample,
+				 struct perf_tool *tool)
+{
+	int err = 0;
+	u64 timestamp;
+	struct cs_etm_auxtrace *etm = container_of(session->auxtrace,
+						   struct cs_etm_auxtrace,
+						   auxtrace);
+
+	if (dump_trace)
+		return 0;
+
+	if (!tool->ordered_events) {
+		pr_err("CoreSight ETM Trace requires ordered events\n");
+		return -EINVAL;
+	}
+
+	if (!etm->timeless_decoding)
+		return -EINVAL;
+
+	if (sample->time && (sample->time != (u64) -1))
+		timestamp = sample->time;
+	else
+		timestamp = 0;
+
+	if (timestamp || etm->timeless_decoding) {
+		err = cs_etm__update_queues(etm);
+		if (err)
+			return err;
+	}
+
+	if (event->header.type == PERF_RECORD_EXIT)
+		return cs_etm__process_timeless_queues(etm,
+						       event->fork.tid,
+						       sample->time);
+
+	return 0;
+}
+
+static int cs_etm__process_auxtrace_event(struct perf_session *session,
+					  union perf_event *event,
+					  struct perf_tool *tool __maybe_unused)
+{
+	struct cs_etm_auxtrace *etm = container_of(session->auxtrace,
+						   struct cs_etm_auxtrace,
+						   auxtrace);
+	if (!etm->data_queued) {
+		struct auxtrace_buffer *buffer;
+		off_t  data_offset;
+		int fd = perf_data__fd(session->data);
+		bool is_pipe = perf_data__is_pipe(session->data);
+		int err;
+
+		if (is_pipe)
+			data_offset = 0;
+		else {
+			data_offset = lseek(fd, 0, SEEK_CUR);
+			if (data_offset == -1)
+				return -errno;
+		}
+
+		err = auxtrace_queues__add_event(&etm->queues, session,
+						 event, data_offset, &buffer);
+		if (err)
+			return err;
+
+		if (dump_trace)
+			if (auxtrace_buffer__get_data(buffer, fd)) {
+				cs_etm__dump_event(etm, buffer);
+				auxtrace_buffer__put_data(buffer);
+			}
+	}
+
+	return 0;
+}
+
+static bool cs_etm__is_timeless_decoding(struct cs_etm_auxtrace *etm)
+{
+	struct perf_evsel *evsel;
+	struct perf_evlist *evlist = etm->session->evlist;
+	bool timeless_decoding = true;
+
+	/*
+	 * Circle through the list of event and complain if we find one
+	 * with the time bit set.
+	 */
+	evlist__for_each_entry(evlist, evsel) {
+		if ((evsel->attr.sample_type & PERF_SAMPLE_TIME))
+			timeless_decoding = false;
+	}
+
+	return timeless_decoding;
+}
+
+static const char * const cs_etm_global_header_fmts[] = {
+	[CS_HEADER_VERSION_0]	= "	Header version		       %llx\n",
+	[CS_PMU_TYPE_CPUS]	= "	PMU type/num cpus	       %llx\n",
+	[CS_ETM_SNAPSHOT]	= "	Snapshot		       %llx\n",
+};
+
+static const char * const cs_etm_priv_fmts[] = {
+	[CS_ETM_MAGIC]		= "	Magic number		       %llx\n",
+	[CS_ETM_CPU]		= "	CPU			       %lld\n",
+	[CS_ETM_ETMCR]		= "	ETMCR			       %llx\n",
+	[CS_ETM_ETMTRACEIDR]	= "	ETMTRACEIDR		       %llx\n",
+	[CS_ETM_ETMCCER]	= "	ETMCCER			       %llx\n",
+	[CS_ETM_ETMIDR]		= "	ETMIDR			       %llx\n",
+};
+
+static const char * const cs_etmv4_priv_fmts[] = {
+	[CS_ETM_MAGIC]		= "	Magic number		       %llx\n",
+	[CS_ETM_CPU]		= "	CPU			       %lld\n",
+	[CS_ETMV4_TRCCONFIGR]	= "	TRCCONFIGR		       %llx\n",
+	[CS_ETMV4_TRCTRACEIDR]	= "	TRCTRACEIDR		       %llx\n",
+	[CS_ETMV4_TRCIDR0]	= "	TRCIDR0			       %llx\n",
+	[CS_ETMV4_TRCIDR1]	= "	TRCIDR1			       %llx\n",
+	[CS_ETMV4_TRCIDR2]	= "	TRCIDR2			       %llx\n",
+	[CS_ETMV4_TRCIDR8]	= "	TRCIDR8			       %llx\n",
+	[CS_ETMV4_TRCAUTHSTATUS] = "	TRCAUTHSTATUS		       %llx\n",
+};
+
+static void cs_etm__print_auxtrace_info(u64 *val, int num)
+{
+	int i, j, cpu = 0;
+
+	for (i = 0; i < CS_HEADER_VERSION_0_MAX; i++)
+		fprintf(stdout, cs_etm_global_header_fmts[i], val[i]);
+
+	for (i = CS_HEADER_VERSION_0_MAX; cpu < num; cpu++) {
+		if (val[i] == __perf_cs_etmv3_magic)
+			for (j = 0; j < CS_ETM_PRIV_MAX; j++, i++)
+				fprintf(stdout, cs_etm_priv_fmts[j], val[i]);
+		else if (val[i] == __perf_cs_etmv4_magic)
+			for (j = 0; j < CS_ETMV4_PRIV_MAX; j++, i++)
+				fprintf(stdout, cs_etmv4_priv_fmts[j], val[i]);
+		else
+			/* failure.. return */
+			return;
+	}
+}
+
+int cs_etm__process_auxtrace_info(union perf_event *event,
+				  struct perf_session *session)
+{
+	struct auxtrace_info_event *auxtrace_info = &event->auxtrace_info;
+	struct cs_etm_auxtrace *etm = NULL;
+	struct int_node *inode;
+	unsigned int pmu_type;
+	int event_header_size = sizeof(struct perf_event_header);
+	int info_header_size;
+	int total_size = auxtrace_info->header.size;
+	int priv_size = 0;
+	int num_cpu;
+	int err = 0, idx = -1;
+	int i, j, k;
+	u64 *ptr, *hdr = NULL;
+	u64 **metadata = NULL;
+
+	/*
+	 * sizeof(auxtrace_info_event::type) +
+	 * sizeof(auxtrace_info_event::reserved) == 8
+	 */
+	info_header_size = 8;
+
+	if (total_size < (event_header_size + info_header_size))
+		return -EINVAL;
+
+	priv_size = total_size - event_header_size - info_header_size;
+
+	/* First the global part */
+	ptr = (u64 *) auxtrace_info->priv;
+
+	/* Look for version '0' of the header */
+	if (ptr[0] != 0)
+		return -EINVAL;
+
+	hdr = zalloc(sizeof(*hdr) * CS_HEADER_VERSION_0_MAX);
+	if (!hdr)
+		return -ENOMEM;
+
+	/* Extract header information - see cs-etm.h for format */
+	for (i = 0; i < CS_HEADER_VERSION_0_MAX; i++)
+		hdr[i] = ptr[i];
+	num_cpu = hdr[CS_PMU_TYPE_CPUS] & 0xffffffff;
+	pmu_type = (unsigned int) ((hdr[CS_PMU_TYPE_CPUS] >> 32) &
+				    0xffffffff);
+
+	/*
+	 * Create an RB tree for traceID-CPU# tuple. Since the conversion has
+	 * to be made for each packet that gets decoded, optimizing access in
+	 * anything other than a sequential array is worth doing.
+	 */
+	traceid_list = intlist__new(NULL);
+	if (!traceid_list) {
+		err = -ENOMEM;
+		goto err_free_hdr;
+	}
+
+	metadata = zalloc(sizeof(*metadata) * num_cpu);
+	if (!metadata) {
+		err = -ENOMEM;
+		goto err_free_traceid_list;
+	}
+
+	/*
+	 * The metadata is stored in the auxtrace_info section and encodes
+	 * the configuration of the ARM embedded trace macrocell which is
+	 * required by the trace decoder to properly decode the trace due
+	 * to its highly compressed nature.
+	 */
+	for (j = 0; j < num_cpu; j++) {
+		if (ptr[i] == __perf_cs_etmv3_magic) {
+			metadata[j] = zalloc(sizeof(*metadata[j]) *
+					     CS_ETM_PRIV_MAX);
+			if (!metadata[j]) {
+				err = -ENOMEM;
+				goto err_free_metadata;
+			}
+			for (k = 0; k < CS_ETM_PRIV_MAX; k++)
+				metadata[j][k] = ptr[i + k];
+
+			/* The traceID is our handle */
+			idx = metadata[j][CS_ETM_ETMTRACEIDR];
+			i += CS_ETM_PRIV_MAX;
+		} else if (ptr[i] == __perf_cs_etmv4_magic) {
+			metadata[j] = zalloc(sizeof(*metadata[j]) *
+					     CS_ETMV4_PRIV_MAX);
+			if (!metadata[j]) {
+				err = -ENOMEM;
+				goto err_free_metadata;
+			}
+			for (k = 0; k < CS_ETMV4_PRIV_MAX; k++)
+				metadata[j][k] = ptr[i + k];
+
+			/* The traceID is our handle */
+			idx = metadata[j][CS_ETMV4_TRCTRACEIDR];
+			i += CS_ETMV4_PRIV_MAX;
+		}
+
+		/* Get an RB node for this CPU */
+		inode = intlist__findnew(traceid_list, idx);
+
+		/* Something went wrong, no need to continue */
+		if (!inode) {
+			err = PTR_ERR(inode);
+			goto err_free_metadata;
+		}
+
+		/*
+		 * The node for that CPU should not be taken.
+		 * Back out if that's the case.
+		 */
+		if (inode->priv) {
+			err = -EINVAL;
+			goto err_free_metadata;
+		}
+		/* All good, associate the traceID with the CPU# */
+		inode->priv = &metadata[j][CS_ETM_CPU];
+	}
+
+	/*
+	 * Each of CS_HEADER_VERSION_0_MAX, CS_ETM_PRIV_MAX and
+	 * CS_ETMV4_PRIV_MAX mark how many double words are in the
+	 * global metadata, and each cpu's metadata respectively.
+	 * The following tests if the correct number of double words was
+	 * present in the auxtrace info section.
+	 */
+	if (i * 8 != priv_size) {
+		err = -EINVAL;
+		goto err_free_metadata;
+	}
+
+	etm = zalloc(sizeof(*etm));
+
+	if (!etm) {
+		err = -ENOMEM;
+		goto err_free_metadata;
+	}
+
+	err = auxtrace_queues__init(&etm->queues);
+	if (err)
+		goto err_free_etm;
+
+	etm->session = session;
+	etm->machine = &session->machines.host;
+
+	etm->num_cpu = num_cpu;
+	etm->pmu_type = pmu_type;
+	etm->snapshot_mode = (hdr[CS_ETM_SNAPSHOT] != 0);
+	etm->metadata = metadata;
+	etm->auxtrace_type = auxtrace_info->type;
+	etm->timeless_decoding = cs_etm__is_timeless_decoding(etm);
+
+	etm->auxtrace.process_event = cs_etm__process_event;
+	etm->auxtrace.process_auxtrace_event = cs_etm__process_auxtrace_event;
+	etm->auxtrace.flush_events = cs_etm__flush_events;
+	etm->auxtrace.free_events = cs_etm__free_events;
+	etm->auxtrace.free = cs_etm__free;
+	session->auxtrace = &etm->auxtrace;
+
+	if (dump_trace) {
+		cs_etm__print_auxtrace_info(auxtrace_info->priv, num_cpu);
+		return 0;
+	}
+
+	if (session->itrace_synth_opts && session->itrace_synth_opts->set) {
+		etm->synth_opts = *session->itrace_synth_opts;
+	} else {
+		itrace_synth_opts__set_default(&etm->synth_opts);
+		etm->synth_opts.callchain = false;
+	}
+
+	err = cs_etm__synth_events(etm, session);
+	if (err)
+		goto err_free_queues;
+
+	err = auxtrace_queues__process_index(&etm->queues, session);
+	if (err)
+		goto err_free_queues;
+
+	etm->data_queued = etm->queues.populated;
+
+	return 0;
+
+err_free_queues:
+	auxtrace_queues__free(&etm->queues);
+	session->auxtrace = NULL;
+err_free_etm:
+	zfree(&etm);
+err_free_metadata:
+	/* No need to check @metadata[j], free(NULL) is supported */
+	for (j = 0; j < num_cpu; j++)
+		free(metadata[j]);
+	zfree(&metadata);
+err_free_traceid_list:
+	intlist__delete(traceid_list);
+err_free_hdr:
+	zfree(&hdr);
+
+	return -EINVAL;
+}
diff --git a/tools/perf/util/cs-etm.h b/tools/perf/util/cs-etm.h
index 3cc6bc3263fe..5864d5dca616 100644
--- a/tools/perf/util/cs-etm.h
+++ b/tools/perf/util/cs-etm.h
@@ -18,6 +18,9 @@
 #ifndef INCLUDE__UTIL_PERF_CS_ETM_H__
 #define INCLUDE__UTIL_PERF_CS_ETM_H__
 
+#include "util/event.h"
+#include "util/session.h"
+
 /* Versionning header in case things need tro change in the future.  That way
  * decoding of old snapshot is still possible.
  */
@@ -61,6 +64,9 @@ enum {
 	CS_ETMV4_PRIV_MAX,
 };
 
+/* RB tree for quick conversion between traceID and CPUs */
+struct intlist *traceid_list;
+
 #define KiB(x) ((x) * 1024)
 #define MiB(x) ((x) * 1024 * 1024)
 
@@ -71,4 +77,16 @@ static const u64 __perf_cs_etmv4_magic   = 0x4040404040404040ULL;
 #define CS_ETMV3_PRIV_SIZE (CS_ETM_PRIV_MAX * sizeof(u64))
 #define CS_ETMV4_PRIV_SIZE (CS_ETMV4_PRIV_MAX * sizeof(u64))
 
+#ifdef HAVE_CSTRACE_SUPPORT
+int cs_etm__process_auxtrace_info(union perf_event *event,
+				  struct perf_session *session);
+#else
+static inline int
+cs_etm__process_auxtrace_info(union perf_event *event __maybe_unused,
+			      struct perf_session *session __maybe_unused)
+{
+	return -1;
+}
+#endif
+
 #endif
diff --git a/tools/perf/util/data.c b/tools/perf/util/data.c
index 48094fde0a68..d8cfc19ddb10 100644
--- a/tools/perf/util/data.c
+++ b/tools/perf/util/data.c
@@ -12,16 +12,6 @@
 #include "util.h"
 #include "debug.h"
 
-#ifndef O_CLOEXEC
-#ifdef __sparc__
-#define O_CLOEXEC	0x400000
-#elif defined(__alpha__) || defined(__hppa__)
-#define O_CLOEXEC	010000000
-#else
-#define O_CLOEXEC	02000000
-#endif
-#endif
-
 static bool check_pipe(struct perf_data *data)
 {
 	struct stat st;
diff --git a/tools/perf/util/dso.c b/tools/perf/util/dso.c
index d5b6f7f5baff..36ef45b2e89d 100644
--- a/tools/perf/util/dso.c
+++ b/tools/perf/util/dso.c
@@ -446,7 +446,7 @@ static int do_open(char *name)
 	char sbuf[STRERR_BUFSIZE];
 
 	do {
-		fd = open(name, O_RDONLY);
+		fd = open(name, O_RDONLY|O_CLOEXEC);
 		if (fd >= 0)
 			return fd;
 
diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h
index e5fbd6dd1b01..0f794744919c 100644
--- a/tools/perf/util/event.h
+++ b/tools/perf/util/event.h
@@ -775,8 +775,7 @@ size_t perf_event__sample_event_size(const struct perf_sample *sample, u64 type,
 				     u64 read_format);
 int perf_event__synthesize_sample(union perf_event *event, u64 type,
 				  u64 read_format,
-				  const struct perf_sample *sample,
-				  bool swapped);
+				  const struct perf_sample *sample);
 
 pid_t perf_event__synthesize_comm(struct perf_tool *tool,
 				  union perf_event *event, pid_t pid,
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index 120efd85f2c8..ac35cd214feb 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -25,6 +25,7 @@
 #include "parse-events.h"
 #include <subcmd/parse-options.h>
 
+#include <fcntl.h>
 #include <sys/ioctl.h>
 #include <sys/mman.h>
 
diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h
index e7fbca69cbac..75f8e0ad5d76 100644
--- a/tools/perf/util/evlist.h
+++ b/tools/perf/util/evlist.h
@@ -7,7 +7,6 @@
 #include <linux/refcount.h>
 #include <linux/list.h>
 #include <api/fd/array.h>
-#include <fcntl.h>
 #include <stdio.h>
 #include "../perf.h"
 #include "event.h"
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 85eb84dfdf91..66fa45198a11 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -2472,8 +2472,7 @@ size_t perf_event__sample_event_size(const struct perf_sample *sample, u64 type,
 
 int perf_event__synthesize_sample(union perf_event *event, u64 type,
 				  u64 read_format,
-				  const struct perf_sample *sample,
-				  bool swapped)
+				  const struct perf_sample *sample)
 {
 	u64 *array;
 	size_t sz;
@@ -2498,15 +2497,6 @@ int perf_event__synthesize_sample(union perf_event *event, u64 type,
 	if (type & PERF_SAMPLE_TID) {
 		u.val32[0] = sample->pid;
 		u.val32[1] = sample->tid;
-		if (swapped) {
-			/*
-			 * Inverse of what is done in perf_evsel__parse_sample
-			 */
-			u.val32[0] = bswap_32(u.val32[0]);
-			u.val32[1] = bswap_32(u.val32[1]);
-			u.val64 = bswap_64(u.val64);
-		}
-
 		*array = u.val64;
 		array++;
 	}
@@ -2533,13 +2523,7 @@ int perf_event__synthesize_sample(union perf_event *event, u64 type,
 
 	if (type & PERF_SAMPLE_CPU) {
 		u.val32[0] = sample->cpu;
-		if (swapped) {
-			/*
-			 * Inverse of what is done in perf_evsel__parse_sample
-			 */
-			u.val32[0] = bswap_32(u.val32[0]);
-			u.val64 = bswap_64(u.val64);
-		}
+		u.val32[1] = 0;
 		*array = u.val64;
 		array++;
 	}
@@ -2586,15 +2570,6 @@ int perf_event__synthesize_sample(union perf_event *event, u64 type,
 
 	if (type & PERF_SAMPLE_RAW) {
 		u.val32[0] = sample->raw_size;
-		if (WARN_ONCE(swapped,
-			      "Endianness of raw data not corrected!\n")) {
-			/*
-			 * Inverse of what is done in perf_evsel__parse_sample
-			 */
-			u.val32[0] = bswap_32(u.val32[0]);
-			u.val32[1] = bswap_32(u.val32[1]);
-			u.val64 = bswap_64(u.val64);
-		}
 		*array = u.val64;
 		array = (void *)array + sizeof(u32);
 
diff --git a/tools/perf/util/generate-cmdlist.sh b/tools/perf/util/generate-cmdlist.sh
index 9bbcec4e3365..ff17920a5ebc 100755
--- a/tools/perf/util/generate-cmdlist.sh
+++ b/tools/perf/util/generate-cmdlist.sh
@@ -38,7 +38,7 @@ do
 done
 echo "#endif /* HAVE_LIBELF_SUPPORT */"
 
-echo "#ifdef HAVE_LIBAUDIT_SUPPORT"
+echo "#if defined(HAVE_LIBAUDIT_SUPPORT) || defined(HAVE_SYSCALL_TABLE)"
 sed -n -e 's/^perf-\([^ 	]*\)[ 	].* audit*/\1/p' command-list.txt |
 sort |
 while read cmd
diff --git a/tools/perf/util/intel-bts.c b/tools/perf/util/intel-bts.c
index 5325e65f9711..72db2744876d 100644
--- a/tools/perf/util/intel-bts.c
+++ b/tools/perf/util/intel-bts.c
@@ -67,7 +67,6 @@ struct intel_bts {
 	u64				branches_sample_type;
 	u64				branches_id;
 	size_t				branches_event_size;
-	bool				synth_needs_swap;
 	unsigned long			num_events;
 };
 
@@ -303,8 +302,7 @@ static int intel_bts_synth_branch_sample(struct intel_bts_queue *btsq,
 		event.sample.header.size = bts->branches_event_size;
 		ret = perf_event__synthesize_sample(&event,
 						    bts->branches_sample_type,
-						    0, &sample,
-						    bts->synth_needs_swap);
+						    0, &sample);
 		if (ret)
 			return ret;
 	}
@@ -841,8 +839,6 @@ static int intel_bts_synth_events(struct intel_bts *bts,
 				__perf_evsel__sample_size(attr.sample_type);
 	}
 
-	bts->synth_needs_swap = evsel->needs_swap;
-
 	return 0;
 }
 
diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c
index 23f9ba676df0..3773d9c54f45 100644
--- a/tools/perf/util/intel-pt.c
+++ b/tools/perf/util/intel-pt.c
@@ -104,8 +104,6 @@ struct intel_pt {
 	u64 pwrx_id;
 	u64 cbr_id;
 
-	bool synth_needs_swap;
-
 	u64 tsc_bit;
 	u64 mtc_bit;
 	u64 mtc_freq_bits;
@@ -1101,11 +1099,10 @@ static void intel_pt_prep_b_sample(struct intel_pt *pt,
 }
 
 static int intel_pt_inject_event(union perf_event *event,
-				 struct perf_sample *sample, u64 type,
-				 bool swapped)
+				 struct perf_sample *sample, u64 type)
 {
 	event->header.size = perf_event__sample_event_size(sample, type, 0);
-	return perf_event__synthesize_sample(event, type, 0, sample, swapped);
+	return perf_event__synthesize_sample(event, type, 0, sample);
 }
 
 static inline int intel_pt_opt_inject(struct intel_pt *pt,
@@ -1115,7 +1112,7 @@ static inline int intel_pt_opt_inject(struct intel_pt *pt,
 	if (!pt->synth_opts.inject)
 		return 0;
 
-	return intel_pt_inject_event(event, sample, type, pt->synth_needs_swap);
+	return intel_pt_inject_event(event, sample, type);
 }
 
 static int intel_pt_deliver_synth_b_event(struct intel_pt *pt,
@@ -2329,8 +2326,6 @@ static int intel_pt_synth_events(struct intel_pt *pt,
 		id += 1;
 	}
 
-	pt->synth_needs_swap = evsel->needs_swap;
-
 	return 0;
 }
 
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index 170316795a18..34589c427e52 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -4,6 +4,9 @@
 #include <dirent.h>
 #include <errno.h>
 #include <sys/ioctl.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <fcntl.h>
 #include <sys/param.h>
 #include "term.h"
 #include "../perf.h"
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 8d0fa2f8da16..c71ced7db152 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -1508,10 +1508,10 @@ static s64 perf_session__process_event(struct perf_session *session,
 		return perf_session__process_user_event(session, event, file_offset);
 
 	if (tool->ordered_events) {
-		u64 timestamp;
+		u64 timestamp = -1ULL;
 
 		ret = perf_evlist__parse_sample_timestamp(evlist, event, &timestamp);
-		if (ret)
+		if (ret && ret != -1)
 			return ret;
 
 		ret = perf_session__queue_event(session, event, timestamp, file_offset);
diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c
index 211e7f326b9f..2da4d0456a03 100644
--- a/tools/perf/util/sort.c
+++ b/tools/perf/util/sort.c
@@ -2887,10 +2887,10 @@ static int setup_output_list(struct perf_hpp_list *list, char *str)
 			tok; tok = strtok_r(NULL, ", ", &tmp)) {
 		ret = output_field_add(list, tok);
 		if (ret == -EINVAL) {
-			pr_err("Invalid --fields key: `%s'", tok);
+			ui__error("Invalid --fields key: `%s'", tok);
 			break;
 		} else if (ret == -ESRCH) {
-			pr_err("Unknown --fields key: `%s'", tok);
+			ui__error("Unknown --fields key: `%s'", tok);
 			break;
 		}
 	}
diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h
index 01434509c2e9..9496365da3d7 100644
--- a/tools/perf/util/util.h
+++ b/tools/perf/util/util.h
@@ -68,4 +68,14 @@ extern bool perf_singlethreaded;
 void perf_set_singlethreaded(void);
 void perf_set_multithreaded(void);
 
+#ifndef O_CLOEXEC
+#ifdef __sparc__
+#define O_CLOEXEC      0x400000
+#elif defined(__alpha__) || defined(__hppa__)
+#define O_CLOEXEC      010000000
+#else
+#define O_CLOEXEC      02000000
+#endif
+#endif
+
 #endif /* GIT_COMPAT_UTIL_H */