perf cs-etm: Track exception level

Currently we assume all trace belongs to the host machine so when
the decoder should be looking at the guest kernel maps it can crash
because it looks at the host ones instead.

Avoid one scenario (guest kernel running at EL1) by assigning the
default guest machine to this trace. For userspace trace it's still not
possible to determine guest vs host, but the PIDs should help in this
case.

Committer notes:

Fixed up conflict with:

  perf addr_location: Add init/exit/copy functions

That was only on tmp.perf-tools-next.
Reviewed-by: Leo Yan <leo.yan@linaro.org>
Signed-off-by: James Clark <james.clark@arm.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: John Garry <john.g.garry@oracle.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Mike Leach <mike.leach@linaro.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Suzuki Poulouse <suzuki.poulose@arm.com>
Cc: Will Deacon <will@kernel.org>
Cc: coresight@lists.linaro.org
Cc: linux-arm-kernel@lists.infradead.org
Link: https://lore.kernel.org/r/20230612111403.100613-5-james.clark@arm.comSigned-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

tools/perf/util/cs-etm-decoder/cs-etm-decoder.c

@@ -561,12 +561,13 @@ cs_etm_decoder__set_tid(struct cs_etm_queue *etmq,
 		break;
 	}
 
+	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;
 
-	if (cs_etm__etmq_set_tid(etmq, tid, trace_chan_id))
-		return OCSD_RESP_FATAL_SYS_ERR;
-
 	/*
 	 * A timestamp is generated after a PE_CONTEXT element so make sure
 	 * to rely on that coming one.

tools/perf/util/cs-etm.c

@@ -14,7 +14,6 @@
 #include <linux/types.h>
 #include <linux/zalloc.h>
 
-#include <opencsd/ocsd_if_types.h>
 #include <stdlib.h>
 
 #include "auxtrace.h"
@@ -88,6 +87,8 @@ struct cs_etm_traceid_queue {
 	union perf_event *event_buf;
 	struct thread *thread;
 	struct thread *prev_packet_thread;
+	ocsd_ex_level prev_packet_el;
+	ocsd_ex_level el;
 	struct branch_stack *last_branch;
 	struct branch_stack *last_branch_rb;
 	struct cs_etm_packet *prev_packet;
@@ -482,6 +483,7 @@ static int cs_etm__init_traceid_queue(struct cs_etm_queue *etmq,
 
 	queue = &etmq->etm->queues.queue_array[etmq->queue_nr];
 	tidq->trace_chan_id = trace_chan_id;
+	tidq->el = tidq->prev_packet_el = ocsd_EL_unknown;
 	tidq->thread = machine__findnew_thread(&etm->session->machines.host, -1,
 					       queue->tid);
 	tidq->prev_packet_thread = machine__idle_thread(&etm->session->machines.host);
@@ -629,6 +631,7 @@ static void cs_etm__packet_swap(struct cs_etm_auxtrace *etm,
 		tmp = tidq->packet;
 		tidq->packet = tidq->prev_packet;
 		tidq->prev_packet = tmp;
+		tidq->prev_packet_el = tidq->el;
 		thread__put(tidq->prev_packet_thread);
 		tidq->prev_packet_thread = thread__get(tidq->thread);
 	}
@@ -890,11 +893,43 @@ static bool cs_etm__evsel_is_auxtrace(struct perf_session *session,
 	return evsel->core.attr.type == aux->pmu_type;
 }
 
-static u8 cs_etm__cpu_mode(struct cs_etm_queue *etmq, u64 address)
+static struct machine *cs_etm__get_machine(struct cs_etm_queue *etmq,
+					   ocsd_ex_level el)
 {
-	struct machine *machine;
+	enum cs_etm_pid_fmt pid_fmt = cs_etm__get_pid_fmt(etmq);
 
-	machine = &etmq->etm->session->machines.host;
+	/*
+	 * For any virtualisation based on nVHE (e.g. pKVM), or host kernels
+	 * running at EL1 assume everything is the host.
+	 */
+	if (pid_fmt == CS_ETM_PIDFMT_CTXTID)
+		return &etmq->etm->session->machines.host;
+
+	/*
+	 * Not perfect, but otherwise assume anything in EL1 is the default
+	 * guest, and everything else is the host. Distinguishing between guest
+	 * and host userspaces isn't currently supported either. Neither is
+	 * multiple guest support. All this does is reduce the likeliness of
+	 * decode errors where we look into the host kernel maps when it should
+	 * have been the guest maps.
+	 */
+	switch (el) {
+	case ocsd_EL1:
+		return machines__find_guest(&etmq->etm->session->machines,
+					    DEFAULT_GUEST_KERNEL_ID);
+	case ocsd_EL3:
+	case ocsd_EL2:
+	case ocsd_EL0:
+	case ocsd_EL_unknown:
+	default:
+		return &etmq->etm->session->machines.host;
+	}
+}
+
+static u8 cs_etm__cpu_mode(struct cs_etm_queue *etmq, u64 address,
+			   ocsd_ex_level el)
+{
+	struct machine *machine = cs_etm__get_machine(etmq, el);
 
 	if (address >= machine__kernel_start(machine)) {
 		if (machine__is_host(machine))
@@ -904,10 +939,14 @@ static u8 cs_etm__cpu_mode(struct cs_etm_queue *etmq, u64 address)
 	} else {
 		if (machine__is_host(machine))
 			return PERF_RECORD_MISC_USER;
-		else if (perf_guest)
+		else {
+			/*
+			 * Can't really happen at the moment because
+			 * cs_etm__get_machine() will always return
+			 * machines.host for any non EL1 trace.
+			 */
 			return PERF_RECORD_MISC_GUEST_USER;
-		else
-			return PERF_RECORD_MISC_HYPERVISOR;
+		}
 	}
 }
 
@@ -926,11 +965,12 @@ static u32 cs_etm__mem_access(struct cs_etm_queue *etmq, u8 trace_chan_id,
 		return 0;
 
 	addr_location__init(&al);
-	cpumode = cs_etm__cpu_mode(etmq, address);
 	tidq = cs_etm__etmq_get_traceid_queue(etmq, trace_chan_id);
 	if (!tidq)
 		goto out;
 
+	cpumode = cs_etm__cpu_mode(etmq, address, tidq->el);
+
 	if (!thread__find_map(tidq->thread, cpumode, address, &al))
 		goto out;
 
@@ -1310,10 +1350,11 @@ cs_etm__get_trace(struct cs_etm_queue *etmq)
 	return etmq->buf_len;
 }
 
-static void cs_etm__set_thread(struct cs_etm_auxtrace *etm,
-			       struct cs_etm_traceid_queue *tidq, pid_t tid)
+static void cs_etm__set_thread(struct cs_etm_queue *etmq,
+			       struct cs_etm_traceid_queue *tidq, pid_t tid,
+			       ocsd_ex_level el)
 {
-	struct machine *machine = &etm->session->machines.host;
+	struct machine *machine = cs_etm__get_machine(etmq, el);
 
 	if (tid != -1) {
 		thread__zput(tidq->thread);
@@ -1323,10 +1364,12 @@ static void cs_etm__set_thread(struct cs_etm_auxtrace *etm,
 	/* Couldn't find a known thread */
 	if (!tidq->thread)
 		tidq->thread = machine__idle_thread(machine);
+
+	tidq->el = el;
 }
 
-int cs_etm__etmq_set_tid(struct cs_etm_queue *etmq,
-			 pid_t tid, u8 trace_chan_id)
+int cs_etm__etmq_set_tid_el(struct cs_etm_queue *etmq, pid_t tid,
+			    u8 trace_chan_id, ocsd_ex_level el)
 {
 	struct cs_etm_traceid_queue *tidq;
 
@@ -1334,7 +1377,7 @@ int cs_etm__etmq_set_tid(struct cs_etm_queue *etmq,
 	if (!tidq)
 		return -EINVAL;
 
-	cs_etm__set_thread(etmq->etm, tidq, tid);
+	cs_etm__set_thread(etmq, tidq, tid, el);
 	return 0;
 }
 
@@ -1404,7 +1447,7 @@ static int cs_etm__synth_instruction_sample(struct cs_etm_queue *etmq,
 	struct perf_sample sample = {.ip = 0,};
 
 	event->sample.header.type = PERF_RECORD_SAMPLE;
-	event->sample.header.misc = cs_etm__cpu_mode(etmq, addr);
+	event->sample.header.misc = cs_etm__cpu_mode(etmq, addr, tidq->el);
 	event->sample.header.size = sizeof(struct perf_event_header);
 
 	/* Set time field based on etm auxtrace config. */
@@ -1463,7 +1506,8 @@ static int cs_etm__synth_branch_sample(struct cs_etm_queue *etmq,
 	ip = cs_etm__last_executed_instr(tidq->prev_packet);
 
 	event->sample.header.type = PERF_RECORD_SAMPLE;
-	event->sample.header.misc = cs_etm__cpu_mode(etmq, ip);
+	event->sample.header.misc = cs_etm__cpu_mode(etmq, ip,
+						     tidq->prev_packet_el);
 	event->sample.header.size = sizeof(struct perf_event_header);
 
 	/* Set time field based on etm auxtrace config. */

tools/perf/util/cs-etm.h

@@ -251,10 +251,11 @@ enum cs_etm_pid_fmt {
 };
 
 #ifdef HAVE_CSTRACE_SUPPORT
+#include <opencsd/ocsd_if_types.h>
 int cs_etm__get_cpu(u8 trace_chan_id, int *cpu);
-enum pid_fmt cs_etm__get_pid_fmt(struct cs_etm_queue *etmq);
-int cs_etm__etmq_set_tid(struct cs_etm_queue *etmq,
-			 pid_t tid, u8 trace_chan_id);
+enum cs_etm_pid_fmt cs_etm__get_pid_fmt(struct cs_etm_queue *etmq);
+int cs_etm__etmq_set_tid_el(struct cs_etm_queue *etmq, pid_t tid,
+			    u8 trace_chan_id, ocsd_ex_level el);
 bool cs_etm__etmq_is_timeless(struct cs_etm_queue *etmq);
 void cs_etm__etmq_set_traceid_queue_timestamp(struct cs_etm_queue *etmq,
 					      u8 trace_chan_id);