1 files changed, 207 insertions, 126 deletions

diff --git a/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c b/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c
index cd007cc9c283..e917985bbbe6 100644
--- a/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c
+++ b/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c
@@ -6,16 +6,17 @@
  * Author: Mathieu Poirier <mathieu.poirier@linaro.org>
  */
 
+#include <asm/bug.h>
+#include <linux/coresight-pmu.h>
 #include <linux/err.h>
 #include <linux/list.h>
 #include <linux/zalloc.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 "debug.h"
 #include "intlist.h"
 
 /* use raw logging */
@@ -29,26 +30,37 @@
 #endif
 #endif
 
+/*
+ * Assume a maximum of 0.1ns elapsed per instruction. This would be the
+ * case with a theoretical 10GHz core executing 1 instruction per cycle.
+ * Used to estimate the sample time for synthesized instructions because
+ * Coresight only emits a timestamp for a range of instructions rather
+ * than per instruction.
+ */
+const u32 INSTR_PER_NS = 10;
+
 struct cs_etm_decoder {
 	void *data;
 	void (*packet_printer)(const char *msg);
+	bool suppress_printing;
 	dcd_tree_handle_t dcd_tree;
 	cs_etm_mem_cb_type mem_access;
 	ocsd_datapath_resp_t prev_return;
+	const char *decoder_name;
 };
 
 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 ocsd_mem_space_acc_t mem_space,
 			   const u8 trace_chan_id,
 			   const u32 req_size,
 			   u8 *buffer)
 {
 	struct cs_etm_decoder *decoder = (struct cs_etm_decoder *) context;
 
-	return decoder->mem_access(decoder->data, trace_chan_id,
-				   address, req_size, buffer);
+	return decoder->mem_access(decoder->data, trace_chan_id, address,
+				   req_size, buffer, mem_space);
 }
 
 int cs_etm_decoder__add_mem_access_cb(struct cs_etm_decoder *decoder,
@@ -71,9 +83,10 @@ int cs_etm_decoder__reset(struct cs_etm_decoder *decoder)
 	ocsd_datapath_resp_t dp_ret;
 
 	decoder->prev_return = OCSD_RESP_CONT;
-
+	decoder->suppress_printing = true;
 	dp_ret = ocsd_dt_process_data(decoder->dcd_tree, OCSD_OP_RESET,
 				      0, 0, NULL, NULL);
+	decoder->suppress_printing = false;
 	if (OCSD_DATA_RESP_IS_FATAL(dp_ret))
 		return -1;
 
@@ -108,6 +121,20 @@ int cs_etm_decoder__get_packet(struct cs_etm_packet_queue *packet_queue,
 	return 1;
 }
 
+/*
+ * Calculate the number of nanoseconds elapsed.
+ *
+ * instr_count is updated in place with the remainder of the instructions
+ * which didn't make up a whole nanosecond.
+ */
+static u32 cs_etm_decoder__dec_instr_count_to_ns(u32 *instr_count)
+{
+	const u32 instr_copy = *instr_count;
+
+	*instr_count %= INSTR_PER_NS;
+	return instr_copy / INSTR_PER_NS;
+}
+
 static int cs_etm_decoder__gen_etmv3_config(struct cs_etm_trace_params *params,
 					    ocsd_etmv3_cfg *config)
 {
@@ -121,6 +148,21 @@ static int cs_etm_decoder__gen_etmv3_config(struct cs_etm_trace_params *params,
 	return 0;
 }
 
+#define TRCIDR1_TRCARCHMIN_SHIFT 4
+#define TRCIDR1_TRCARCHMIN_MASK  GENMASK(7, 4)
+#define TRCIDR1_TRCARCHMIN(x)    (((x) & TRCIDR1_TRCARCHMIN_MASK) >> TRCIDR1_TRCARCHMIN_SHIFT)
+
+static enum _ocsd_arch_version cs_etm_decoder__get_etmv4_arch_ver(u32 reg_idr1)
+{
+	/*
+	 * For ETMv4 if the trace minor version is 4 or more then we can assume
+	 * the architecture is ARCH_AA64 rather than just V8.
+	 * ARCH_V8 = V8 architecture
+	 * ARCH_AA64 = Min v8r3 plus additional AA64 PE features
+	 */
+	return TRCIDR1_TRCARCHMIN(reg_idr1) >= 4 ? ARCH_AA64 : ARCH_V8;
+}
+
 static void cs_etm_decoder__gen_etmv4_config(struct cs_etm_trace_params *params,
 					     ocsd_etmv4_cfg *config)
 {
@@ -135,7 +177,21 @@ static void cs_etm_decoder__gen_etmv4_config(struct cs_etm_trace_params *params,
 	config->reg_idr11 = 0;
 	config->reg_idr12 = 0;
 	config->reg_idr13 = 0;
-	config->arch_ver = ARCH_V8;
+	config->arch_ver = cs_etm_decoder__get_etmv4_arch_ver(params->etmv4.reg_idr1);
+	config->core_prof = profile_CortexA;
+}
+
+static void cs_etm_decoder__gen_ete_config(struct cs_etm_trace_params *params,
+					   ocsd_ete_cfg *config)
+{
+	config->reg_configr = params->ete.reg_configr;
+	config->reg_traceidr = params->ete.reg_traceidr;
+	config->reg_idr0 = params->ete.reg_idr0;
+	config->reg_idr1 = params->ete.reg_idr1;
+	config->reg_idr2 = params->ete.reg_idr2;
+	config->reg_idr8 = params->ete.reg_idr8;
+	config->reg_devarch = params->ete.reg_devarch;
+	config->arch_ver = ARCH_AA64;
 	config->core_prof = profile_CortexA;
 }
 
@@ -143,8 +199,10 @@ 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);
+	const struct cs_etm_decoder *decoder = p_context;
+
+	if (p_context && str_len && !decoder->suppress_printing)
+		decoder->packet_printer(msg);
 }
 
 static int
@@ -220,69 +278,22 @@ cs_etm_decoder__init_raw_frame_logging(
 }
 #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_etmv3_cfg config_etmv3;
-	ocsd_etmv4_cfg trace_config_etmv4;
-	void *trace_config;
-
-	switch (t_params->protocol) {
-	case CS_ETM_PROTO_ETMV3:
-	case CS_ETM_PROTO_PTM:
-		cs_etm_decoder__gen_etmv3_config(t_params, &config_etmv3);
-		decoder_name = (t_params->protocol == CS_ETM_PROTO_ETMV3) ?
-							OCSD_BUILTIN_DCD_ETMV3 :
-							OCSD_BUILTIN_DCD_PTM;
-		trace_config = &config_etmv3;
-		break;
-	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 ocsd_datapath_resp_t
 cs_etm_decoder__do_soft_timestamp(struct cs_etm_queue *etmq,
 				  struct cs_etm_packet_queue *packet_queue,
 				  const uint8_t trace_chan_id)
 {
+	u64 estimated_ts;
+
 	/* No timestamp packet has been received, nothing to do */
-	if (!packet_queue->timestamp)
+	if (!packet_queue->next_cs_timestamp)
 		return OCSD_RESP_CONT;
 
-	packet_queue->timestamp = packet_queue->next_timestamp;
+	estimated_ts = packet_queue->cs_timestamp +
+			cs_etm_decoder__dec_instr_count_to_ns(&packet_queue->instr_count);
 
-	/* Estimate the timestamp for the next range packet */
-	packet_queue->next_timestamp += packet_queue->instr_count;
-	packet_queue->instr_count = 0;
+	/* Estimated TS can never be higher than the next real one in the trace */
+	packet_queue->cs_timestamp = min(packet_queue->next_cs_timestamp, estimated_ts);
 
 	/* Tell the front end which traceid_queue needs attention */
 	cs_etm__etmq_set_traceid_queue_timestamp(etmq, trace_chan_id);
@@ -293,9 +304,12 @@ cs_etm_decoder__do_soft_timestamp(struct cs_etm_queue *etmq,
 static ocsd_datapath_resp_t
 cs_etm_decoder__do_hard_timestamp(struct cs_etm_queue *etmq,
 				  const ocsd_generic_trace_elem *elem,
-				  const uint8_t trace_chan_id)
+				  const uint8_t trace_chan_id,
+				  const ocsd_trc_index_t indx)
 {
 	struct cs_etm_packet_queue *packet_queue;
+	u64 converted_timestamp;
+	u64 estimated_first_ts;
 
 	/* First get the packet queue for this traceID */
 	packet_queue = cs_etm__etmq_get_packet_queue(etmq, trace_chan_id);
@@ -303,24 +317,60 @@ cs_etm_decoder__do_hard_timestamp(struct cs_etm_queue *etmq,
 		return OCSD_RESP_FATAL_SYS_ERR;
 
 	/*
+	 * Coresight timestamps are raw timer values which need to be scaled to ns. Assume
+	 * 0 is a bad value so don't try to convert it.
+	 */
+	converted_timestamp = elem->timestamp ?
+				cs_etm__convert_sample_time(etmq, elem->timestamp) : 0;
+
+	/*
 	 * We've seen a timestamp packet before - simply record the new value.
 	 * Function do_soft_timestamp() will report the value to the front end,
 	 * hence asking the decoder to keep decoding rather than stopping.
 	 */
-	if (packet_queue->timestamp) {
-		packet_queue->next_timestamp = elem->timestamp;
+	if (packet_queue->next_cs_timestamp) {
+		/*
+		 * What was next is now where new ranges start from, overwriting
+		 * any previous estimate in cs_timestamp
+		 */
+		packet_queue->cs_timestamp = packet_queue->next_cs_timestamp;
+		packet_queue->next_cs_timestamp = converted_timestamp;
 		return OCSD_RESP_CONT;
 	}
 
-	/*
-	 * This is the first timestamp we've seen since the beginning of traces
-	 * or a discontinuity.  Since timestamps packets are generated *after*
-	 * range packets have been generated, we need to estimate the time at
-	 * which instructions started by substracting the number of instructions
-	 * executed to the timestamp.
-	 */
-	packet_queue->timestamp = elem->timestamp - packet_queue->instr_count;
-	packet_queue->next_timestamp = elem->timestamp;
+	if (!converted_timestamp) {
+		/*
+		 * Zero timestamps can be seen due to misconfiguration or hardware bugs.
+		 * Warn once, and don't try to subtract instr_count as it would result in an
+		 * underflow.
+		 */
+		packet_queue->cs_timestamp = 0;
+		if (!cs_etm__etmq_is_timeless(etmq))
+			pr_warning_once("Zero Coresight timestamp found at Idx:%" OCSD_TRC_IDX_STR
+					". Decoding may be improved by prepending 'Z' to your current --itrace arguments.\n",
+					indx);
+
+	} else if (packet_queue->instr_count / INSTR_PER_NS > converted_timestamp) {
+		/*
+		 * Sanity check that the elem->timestamp - packet_queue->instr_count would not
+		 * result in an underflow. Warn and clamp at 0 if it would.
+		 */
+		packet_queue->cs_timestamp = 0;
+		pr_err("Timestamp calculation underflow at Idx:%" OCSD_TRC_IDX_STR "\n", indx);
+	} else {
+		/*
+		 * This is the first timestamp we've seen since the beginning of traces
+		 * or a discontinuity.  Since timestamps packets are generated *after*
+		 * range packets have been generated, we need to estimate the time at
+		 * which instructions started by subtracting the number of instructions
+		 * executed to the timestamp. Don't estimate earlier than the last used
+		 * timestamp though.
+		 */
+		estimated_first_ts = converted_timestamp -
+					(packet_queue->instr_count / INSTR_PER_NS);
+		packet_queue->cs_timestamp = max(packet_queue->cs_timestamp, estimated_first_ts);
+	}
+	packet_queue->next_cs_timestamp = converted_timestamp;
 	packet_queue->instr_count = 0;
 
 	/* Tell the front end which traceid_queue needs attention */
@@ -333,8 +383,7 @@ cs_etm_decoder__do_hard_timestamp(struct cs_etm_queue *etmq,
 static void
 cs_etm_decoder__reset_timestamp(struct cs_etm_packet_queue *packet_queue)
 {
-	packet_queue->timestamp = 0;
-	packet_queue->next_timestamp = 0;
+	packet_queue->next_cs_timestamp = 0;
 	packet_queue->instr_count = 0;
 }
 
@@ -419,19 +468,10 @@ cs_etm_decoder__buffer_range(struct cs_etm_queue *etmq,
 	packet->last_instr_subtype = elem->last_i_subtype;
 	packet->last_instr_cond = elem->last_instr_cond;
 
-	switch (elem->last_i_type) {
-	case OCSD_INSTR_BR:
-	case OCSD_INSTR_BR_INDIRECT:
+	if (elem->last_i_type == OCSD_INSTR_BR || elem->last_i_type == OCSD_INSTR_BR_INDIRECT)
 		packet->last_instr_taken_branch = elem->last_instr_exec;
-		break;
-	case OCSD_INSTR_ISB:
-	case OCSD_INSTR_DSB_DMB:
-	case OCSD_INSTR_WFI_WFE:
-	case OCSD_INSTR_OTHER:
-	default:
+	else
 		packet->last_instr_taken_branch = false;
-		break;
-	}
 
 	packet->last_instr_size = elem->last_instr_sz;
 
@@ -500,16 +540,34 @@ cs_etm_decoder__set_tid(struct cs_etm_queue *etmq,
 			const ocsd_generic_trace_elem *elem,
 			const uint8_t trace_chan_id)
 {
-	pid_t tid;
+	pid_t tid = -1;
 
-	/* Ignore PE_CONTEXT packets that don't have a valid contextID */
-	if (!elem->context.ctxt_id_valid)
-		return OCSD_RESP_CONT;
+	/*
+	 * Process the PE_CONTEXT packets if we have a valid contextID or VMID.
+	 * If the kernel is running at EL2, the PID is traced in CONTEXTIDR_EL2
+	 * as VMID, Bit ETM_OPT_CTXTID2 is set in this case.
+	 */
+	switch (cs_etm__get_pid_fmt(etmq)) {
+	case CS_ETM_PIDFMT_CTXTID:
+		if (elem->context.ctxt_id_valid)
+			tid = elem->context.context_id;
+		break;
+	case CS_ETM_PIDFMT_CTXTID2:
+		if (elem->context.vmid_valid)
+			tid = elem->context.vmid;
+		break;
+	case CS_ETM_PIDFMT_NONE:
+	default:
+		break;
+	}
 
-	tid =  elem->context.context_id;
-	if (cs_etm__etmq_set_tid(etmq, tid, trace_chan_id))
+	if (cs_etm__etmq_set_tid_el(etmq, tid, trace_chan_id,
+				    elem->context.exception_level))
 		return OCSD_RESP_FATAL_SYS_ERR;
 
+	if (tid == -1)
+		return OCSD_RESP_CONT;
+
 	/*
 	 * A timestamp is generated after a PE_CONTEXT element so make sure
 	 * to rely on that coming one.
@@ -521,7 +579,7 @@ cs_etm_decoder__set_tid(struct cs_etm_queue *etmq,
 
 static ocsd_datapath_resp_t cs_etm_decoder__gen_trace_elem_printer(
 				const void *context,
-				const ocsd_trc_index_t indx __maybe_unused,
+				const ocsd_trc_index_t indx,
 				const u8 trace_chan_id __maybe_unused,
 				const ocsd_generic_trace_elem *elem)
 {
@@ -558,7 +616,8 @@ static ocsd_datapath_resp_t cs_etm_decoder__gen_trace_elem_printer(
 		break;
 	case OCSD_GEN_TRC_ELEM_TIMESTAMP:
 		resp = cs_etm_decoder__do_hard_timestamp(etmq, elem,
-							 trace_chan_id);
+							 trace_chan_id,
+							 indx);
 		break;
 	case OCSD_GEN_TRC_ELEM_PE_CONTEXT:
 		resp = cs_etm_decoder__set_tid(etmq, packet_queue,
@@ -572,6 +631,11 @@ static ocsd_datapath_resp_t cs_etm_decoder__gen_trace_elem_printer(
 	case OCSD_GEN_TRC_ELEM_EVENT:
 	case OCSD_GEN_TRC_ELEM_SWTRACE:
 	case OCSD_GEN_TRC_ELEM_CUSTOM:
+	case OCSD_GEN_TRC_ELEM_SYNC_MARKER:
+	case OCSD_GEN_TRC_ELEM_MEMTRANS:
+#if (OCSD_VER_NUM >= 0x010400)
+	case OCSD_GEN_TRC_ELEM_INSTRUMENTATION:
+#endif
 	default:
 		break;
 	}
@@ -579,65 +643,77 @@ static ocsd_datapath_resp_t cs_etm_decoder__gen_trace_elem_printer(
 	return resp;
 }
 
-static int cs_etm_decoder__create_etm_packet_decoder(
-					struct cs_etm_trace_params *t_params,
-					struct cs_etm_decoder *decoder)
+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)
 {
-	const char *decoder_name;
 	ocsd_etmv3_cfg config_etmv3;
 	ocsd_etmv4_cfg trace_config_etmv4;
+	ocsd_ete_cfg trace_config_ete;
 	void *trace_config;
 	u8 csid;
 
 	switch (t_params->protocol) {
 	case CS_ETM_PROTO_ETMV3:
 	case CS_ETM_PROTO_PTM:
+		csid = (t_params->etmv3.reg_idr & CORESIGHT_TRACE_ID_VAL_MASK);
 		cs_etm_decoder__gen_etmv3_config(t_params, &config_etmv3);
-		decoder_name = (t_params->protocol == CS_ETM_PROTO_ETMV3) ?
+		decoder->decoder_name = (t_params->protocol == CS_ETM_PROTO_ETMV3) ?
 							OCSD_BUILTIN_DCD_ETMV3 :
 							OCSD_BUILTIN_DCD_PTM;
 		trace_config = &config_etmv3;
 		break;
 	case CS_ETM_PROTO_ETMV4i:
+		csid = (t_params->etmv4.reg_traceidr & CORESIGHT_TRACE_ID_VAL_MASK);
 		cs_etm_decoder__gen_etmv4_config(t_params, &trace_config_etmv4);
-		decoder_name = OCSD_BUILTIN_DCD_ETMV4I;
+		decoder->decoder_name = OCSD_BUILTIN_DCD_ETMV4I;
 		trace_config = &trace_config_etmv4;
 		break;
+	case CS_ETM_PROTO_ETE:
+		csid = (t_params->ete.reg_traceidr & CORESIGHT_TRACE_ID_VAL_MASK);
+		cs_etm_decoder__gen_ete_config(t_params, &trace_config_ete);
+		decoder->decoder_name = OCSD_BUILTIN_DCD_ETE;
+		trace_config = &trace_config_ete;
+		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 the CPU has no trace ID associated, no decoder needed */
+	if (csid == CORESIGHT_TRACE_ID_UNUSED_VAL)
+		return 0;
 
-	if (ocsd_dt_set_gen_elem_outfn(decoder->dcd_tree,
-				       cs_etm_decoder__gen_trace_elem_printer,
-				       decoder))
-		return -1;
+	if (d_params->operation == CS_ETM_OPERATION_DECODE) {
+		if (ocsd_dt_create_decoder(decoder->dcd_tree,
+					   decoder->decoder_name,
+					   OCSD_CREATE_FLG_FULL_DECODER,
+					   trace_config, &csid))
+			return -1;
 
-	return 0;
-}
+		if (ocsd_dt_set_gen_elem_outfn(decoder->dcd_tree,
+					       cs_etm_decoder__gen_trace_elem_printer,
+					       decoder))
+			return -1;
 
-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 0;
+	} else if (d_params->operation == CS_ETM_OPERATION_PRINT) {
+		if (ocsd_dt_create_decoder(decoder->dcd_tree, decoder->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;
+	}
 
 	return -1;
 }
 
 struct cs_etm_decoder *
-cs_etm_decoder__new(int num_cpu, struct cs_etm_decoder_params *d_params,
+cs_etm_decoder__new(int decoders, struct cs_etm_decoder_params *d_params,
 		    struct cs_etm_trace_params t_params[])
 {
 	struct cs_etm_decoder *decoder;
@@ -682,7 +758,7 @@ cs_etm_decoder__new(int num_cpu, struct cs_etm_decoder_params *d_params,
 	/* init raw frame logging if required */
 	cs_etm_decoder__init_raw_frame_logging(d_params, decoder);
 
-	for (i = 0; i < num_cpu; i++) {
+	for (i = 0; i < decoders; i++) {
 		ret = cs_etm_decoder__create_etm_decoder(d_params,
 							 &t_params[i],
 							 decoder);
@@ -754,3 +830,8 @@ void cs_etm_decoder__free(struct cs_etm_decoder *decoder)
 	decoder->dcd_tree = NULL;
 	free(decoder);
 }
+
+const char *cs_etm_decoder__get_name(struct cs_etm_decoder *decoder)
+{
+	return decoder->decoder_name;
+}