1 files changed, 287 insertions, 23 deletions

diff --git a/tools/perf/arch/arm/util/cs-etm.c b/tools/perf/arch/arm/util/cs-etm.c
index 911426721170..2b83cc8e4796 100644
--- a/tools/perf/arch/arm/util/cs-etm.c
+++ b/tools/perf/arch/arm/util/cs-etm.c
@@ -22,6 +22,7 @@
 #include "../../util/pmu.h"
 #include "../../util/thread_map.h"
 #include "../../util/cs-etm.h"
+#include "../../util/util.h"
 
 #include <errno.h>
 #include <stdlib.h>
@@ -31,12 +32,158 @@ struct cs_etm_recording {
 	struct auxtrace_record	itr;
 	struct perf_pmu		*cs_etm_pmu;
 	struct perf_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 perf_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->attr.config |= (1 << ETM_OPT_CTXTID);
+	err = 0;
+
+out:
+
+	return err;
+}
+
+static int cs_etm_set_timestamp(struct auxtrace_record *itr,
+				struct perf_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->attr.config |= (1 << ETM_OPT_TS);
+	err = 0;
+
+out:
+	return err;
+}
+
+static int cs_etm_set_option(struct auxtrace_record *itr,
+			     struct perf_evsel *evsel, u32 option)
+{
+	int i, err = -EINVAL;
+	struct cpu_map *event_cpus = evsel->evlist->cpus;
+	struct cpu_map *online_cpus = 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:
+	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)
@@ -105,12 +252,16 @@ static int cs_etm_recording_options(struct auxtrace_record *itr,
 				container_of(itr, struct cs_etm_recording, itr);
 	struct perf_pmu *cs_etm_pmu = ptr->cs_etm_pmu;
 	struct perf_evsel *evsel, *cs_etm_evsel = NULL;
-	const struct cpu_map *cpus = evlist->cpus;
+	struct cpu_map *cpus = evlist->cpus;
 	bool privileged = (geteuid() == 0 || perf_event_paranoid() < 0);
+	int err = 0;
 
 	ptr->evlist = evlist;
 	ptr->snapshot_mode = opts->auxtrace_snapshot_mode;
 
+	if (perf_can_record_switch_events())
+		opts->record_switch_events = true;
+
 	evlist__for_each_entry(evlist, evsel) {
 		if (evsel->attr.type == cs_etm_pmu->type) {
 			if (cs_etm_evsel) {
@@ -241,19 +392,25 @@ static int cs_etm_recording_options(struct auxtrace_record *itr,
 
 	/*
 	 * In the case of per-cpu mmaps, we need the CPU on the
-	 * AUX event.
+	 * AUX event.  We also need the contextID in order to be notified
+	 * when a context switch happened.
 	 */
-	if (!cpu_map__empty(cpus))
+	if (!cpu_map__empty(cpus)) {
 		perf_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 perf_evsel *tracking_evsel;
-		int err;
 
 		err = parse_events(evlist, "dummy:u", NULL);
 		if (err)
-			return err;
+			goto out;
 
 		tracking_evsel = perf_evlist__last(evlist);
 		perf_evlist__set_tracking_event(evlist, tracking_evsel);
@@ -266,7 +423,8 @@ static int cs_etm_recording_options(struct auxtrace_record *itr,
 			perf_evsel__set_sample_bit(tracking_evsel, TIME);
 	}
 
-	return 0;
+out:
+	return err;
 }
 
 static u64 cs_etm_get_config(struct auxtrace_record *itr)
@@ -314,6 +472,8 @@ static u64 cs_etmv4_get_config(struct auxtrace_record *itr)
 	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))
@@ -363,19 +523,6 @@ cs_etm_info_priv_size(struct auxtrace_record *itr __maybe_unused,
 	       (etmv3 * CS_ETMV3_PRIV_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)
 {
 	bool ret = false;
@@ -536,16 +683,131 @@ static int cs_etm_info_fill(struct auxtrace_record *itr,
 	return 0;
 }
 
-static int cs_etm_find_snapshot(struct auxtrace_record *itr __maybe_unused,
+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 __maybe_unused,
+				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);
 
-	*old = *head;
-	*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;
 }
@@ -586,6 +848,8 @@ 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);
 }