1 files changed, 340 insertions, 35 deletions

diff --git a/tools/perf/arch/arm64/util/arm-spe.c b/tools/perf/arch/arm64/util/arm-spe.c
index e3593063b3d1..51ccbfd3d246 100644
--- a/tools/perf/arch/arm64/util/arm-spe.c
+++ b/tools/perf/arch/arm64/util/arm-spe.c
@@ -14,6 +14,7 @@
 #include "../../../util/cpumap.h"
 #include "../../../util/event.h"
 #include "../../../util/evsel.h"
+#include "../../../util/evsel_config.h"
 #include "../../../util/evlist.h"
 #include "../../../util/session.h"
 #include <internal/lib.h> // page_size
@@ -22,6 +23,7 @@
 #include "../../../util/auxtrace.h"
 #include "../../../util/record.h"
 #include "../../../util/arm-spe.h"
+#include <tools/libc_compat.h> // reallocarray
 
 #define KiB(x) ((x) * 1024)
 #define MiB(x) ((x) * 1024 * 1024)
@@ -30,6 +32,8 @@ struct arm_spe_recording {
 	struct auxtrace_record		itr;
 	struct perf_pmu			*arm_spe_pmu;
 	struct evlist		*evlist;
+	int			wrapped_cnt;
+	bool			*wrapped;
 };
 
 static size_t
@@ -60,6 +64,74 @@ static int arm_spe_info_fill(struct auxtrace_record *itr,
 	return 0;
 }
 
+static void
+arm_spe_snapshot_resolve_auxtrace_defaults(struct record_opts *opts,
+					   bool privileged)
+{
+	/*
+	 * The default snapshot size is the auxtrace mmap size. If neither auxtrace mmap size nor
+	 * snapshot size is specified, then the default is 4MiB for privileged users, 128KiB for
+	 * unprivileged users.
+	 *
+	 * The default auxtrace mmap size is 4MiB/page_size for privileged users, 128KiB for
+	 * unprivileged users. If an unprivileged user does not specify mmap pages, the mmap pages
+	 * will be reduced from the default 512KiB/page_size to 256KiB/page_size, otherwise the
+	 * user is likely to get an error as they exceed their mlock limmit.
+	 */
+
+	/*
+	 * No size were given to '-S' or '-m,', so go with the default
+	 */
+	if (!opts->auxtrace_snapshot_size && !opts->auxtrace_mmap_pages) {
+		if (privileged) {
+			opts->auxtrace_mmap_pages = MiB(4) / page_size;
+		} else {
+			opts->auxtrace_mmap_pages = KiB(128) / page_size;
+			if (opts->mmap_pages == UINT_MAX)
+				opts->mmap_pages = KiB(256) / page_size;
+		}
+	} else if (!opts->auxtrace_mmap_pages && !privileged && opts->mmap_pages == UINT_MAX) {
+		opts->mmap_pages = KiB(256) / page_size;
+	}
+
+	/*
+	 * '-m,xyz' was specified but no snapshot size, so make the snapshot size as big as the
+	 * auxtrace mmap area.
+	 */
+	if (!opts->auxtrace_snapshot_size)
+		opts->auxtrace_snapshot_size = opts->auxtrace_mmap_pages * (size_t)page_size;
+
+	/*
+	 * '-Sxyz' was specified but no auxtrace mmap area, so make the auxtrace mmap area big
+	 * enough to fit the requested snapshot size.
+	 */
+	if (!opts->auxtrace_mmap_pages) {
+		size_t sz = opts->auxtrace_snapshot_size;
+
+		sz = round_up(sz, page_size) / page_size;
+		opts->auxtrace_mmap_pages = roundup_pow_of_two(sz);
+	}
+}
+
+static __u64 arm_spe_pmu__sample_period(const struct perf_pmu *arm_spe_pmu)
+{
+	static __u64 sample_period;
+
+	if (sample_period)
+		return sample_period;
+
+	/*
+	 * If kernel driver doesn't advertise a minimum,
+	 * use max allowable by PMSIDR_EL1.INTERVAL
+	 */
+	if (perf_pmu__scan_file(arm_spe_pmu, "caps/min_interval", "%llu",
+				&sample_period) != 1) {
+		pr_debug("arm_spe driver doesn't advertise a min. interval. Using 4096\n");
+		sample_period = 4096;
+	}
+	return sample_period;
+}
+
 static int arm_spe_recording_options(struct auxtrace_record *itr,
 				     struct evlist *evlist,
 				     struct record_opts *opts)
@@ -68,9 +140,11 @@ static int arm_spe_recording_options(struct auxtrace_record *itr,
 			container_of(itr, struct arm_spe_recording, itr);
 	struct perf_pmu *arm_spe_pmu = sper->arm_spe_pmu;
 	struct evsel *evsel, *arm_spe_evsel = NULL;
+	struct perf_cpu_map *cpus = evlist->core.user_requested_cpus;
 	bool privileged = perf_event_paranoid_check(-1);
 	struct evsel *tracking_evsel;
 	int err;
+	u64 bit;
 
 	sper->evlist = evlist;
 
@@ -81,7 +155,8 @@ static int arm_spe_recording_options(struct auxtrace_record *itr,
 				return -EINVAL;
 			}
 			evsel->core.attr.freq = 0;
-			evsel->core.attr.sample_period = 1;
+			evsel->core.attr.sample_period = arm_spe_pmu__sample_period(arm_spe_pmu);
+			evsel->needs_auxtrace_mmap = true;
 			arm_spe_evsel = evsel;
 			opts->full_auxtrace = true;
 		}
@@ -90,8 +165,38 @@ static int arm_spe_recording_options(struct auxtrace_record *itr,
 	if (!opts->full_auxtrace)
 		return 0;
 
+	/*
+	 * we are in snapshot mode.
+	 */
+	if (opts->auxtrace_snapshot_mode) {
+		/*
+		 * Command arguments '-Sxyz' and/or '-m,xyz' are missing, so fill those in with
+		 * default values.
+		 */
+		if (!opts->auxtrace_snapshot_size || !opts->auxtrace_mmap_pages)
+			arm_spe_snapshot_resolve_auxtrace_defaults(opts, privileged);
+
+		/*
+		 * Snapshot size can't be bigger than the auxtrace area.
+		 */
+		if (opts->auxtrace_snapshot_size > opts->auxtrace_mmap_pages * (size_t)page_size) {
+			pr_err("Snapshot size %zu must not be greater than AUX area tracing mmap size %zu\n",
+			       opts->auxtrace_snapshot_size,
+			       opts->auxtrace_mmap_pages * (size_t)page_size);
+			return -EINVAL;
+		}
+
+		/*
+		 * Something went wrong somewhere - this shouldn't happen.
+		 */
+		if (!opts->auxtrace_snapshot_size || !opts->auxtrace_mmap_pages) {
+			pr_err("Failed to calculate default snapshot size and/or AUX area tracing mmap pages\n");
+			return -EINVAL;
+		}
+	}
+
 	/* We are in full trace mode but '-m,xyz' wasn't specified */
-	if (opts->full_auxtrace && !opts->auxtrace_mmap_pages) {
+	if (!opts->auxtrace_mmap_pages) {
 		if (privileged) {
 			opts->auxtrace_mmap_pages = MiB(4) / page_size;
 		} else {
@@ -113,30 +218,246 @@ static int arm_spe_recording_options(struct auxtrace_record *itr,
 		}
 	}
 
+	if (opts->auxtrace_snapshot_mode)
+		pr_debug2("%sx snapshot size: %zu\n", ARM_SPE_PMU_NAME,
+			  opts->auxtrace_snapshot_size);
 
 	/*
 	 * To obtain the auxtrace buffer file descriptor, the auxtrace event
 	 * must come first.
 	 */
-	perf_evlist__to_front(evlist, arm_spe_evsel);
+	evlist__to_front(evlist, arm_spe_evsel);
+
+	/*
+	 * In the case of per-cpu mmaps, sample CPU for AUX event;
+	 * also enable the timestamp tracing for samples correlation.
+	 */
+	if (!perf_cpu_map__has_any_cpu_or_is_empty(cpus)) {
+		evsel__set_sample_bit(arm_spe_evsel, CPU);
+		evsel__set_config_if_unset(arm_spe_pmu, arm_spe_evsel,
+					   "ts_enable", 1);
+	}
+
+	/*
+	 * Set this only so that perf report knows that SPE generates memory info. It has no effect
+	 * on the opening of the event or the SPE data produced.
+	 */
+	evsel__set_sample_bit(arm_spe_evsel, DATA_SRC);
 
-	evsel__set_sample_bit(arm_spe_evsel, CPU);
-	evsel__set_sample_bit(arm_spe_evsel, TIME);
-	evsel__set_sample_bit(arm_spe_evsel, TID);
+	/*
+	 * The PHYS_ADDR flag does not affect the driver behaviour, it is used to
+	 * inform that the resulting output's SPE samples contain physical addresses
+	 * where applicable.
+	 */
+	bit = perf_pmu__format_bits(arm_spe_pmu, "pa_enable");
+	if (arm_spe_evsel->core.attr.config & bit)
+		evsel__set_sample_bit(arm_spe_evsel, PHYS_ADDR);
 
 	/* Add dummy event to keep tracking */
-	err = parse_events(evlist, "dummy:u", NULL);
+	err = parse_event(evlist, "dummy:u");
 	if (err)
 		return err;
 
 	tracking_evsel = evlist__last(evlist);
-	perf_evlist__set_tracking_event(evlist, tracking_evsel);
+	evlist__set_tracking_event(evlist, tracking_evsel);
 
 	tracking_evsel->core.attr.freq = 0;
 	tracking_evsel->core.attr.sample_period = 1;
-	evsel__set_sample_bit(tracking_evsel, TIME);
-	evsel__set_sample_bit(tracking_evsel, CPU);
-	evsel__reset_sample_bit(tracking_evsel, BRANCH_STACK);
+
+	/* In per-cpu case, always need the time of mmap events etc */
+	if (!perf_cpu_map__has_any_cpu_or_is_empty(cpus)) {
+		evsel__set_sample_bit(tracking_evsel, TIME);
+		evsel__set_sample_bit(tracking_evsel, CPU);
+
+		/* also track task context switch */
+		if (!record_opts__no_switch_events(opts))
+			tracking_evsel->core.attr.context_switch = 1;
+	}
+
+	return 0;
+}
+
+static int arm_spe_parse_snapshot_options(struct auxtrace_record *itr __maybe_unused,
+					 struct record_opts *opts,
+					 const char *str)
+{
+	unsigned long long snapshot_size = 0;
+	char *endptr;
+
+	if (str) {
+		snapshot_size = strtoull(str, &endptr, 0);
+		if (*endptr || snapshot_size > SIZE_MAX)
+			return -1;
+	}
+
+	opts->auxtrace_snapshot_mode = true;
+	opts->auxtrace_snapshot_size = snapshot_size;
+
+	return 0;
+}
+
+static int arm_spe_snapshot_start(struct auxtrace_record *itr)
+{
+	struct arm_spe_recording *ptr =
+			container_of(itr, struct arm_spe_recording, itr);
+	struct evsel *evsel;
+
+	evlist__for_each_entry(ptr->evlist, evsel) {
+		if (evsel->core.attr.type == ptr->arm_spe_pmu->type)
+			return evsel__disable(evsel);
+	}
+	return -EINVAL;
+}
+
+static int arm_spe_snapshot_finish(struct auxtrace_record *itr)
+{
+	struct arm_spe_recording *ptr =
+			container_of(itr, struct arm_spe_recording, itr);
+	struct evsel *evsel;
+
+	evlist__for_each_entry(ptr->evlist, evsel) {
+		if (evsel->core.attr.type == ptr->arm_spe_pmu->type)
+			return evsel__enable(evsel);
+	}
+	return -EINVAL;
+}
+
+static int arm_spe_alloc_wrapped_array(struct arm_spe_recording *ptr, int idx)
+{
+	bool *wrapped;
+	int cnt = ptr->wrapped_cnt, new_cnt, i;
+
+	/*
+	 * No need to allocate, so return early.
+	 */
+	if (idx < cnt)
+		return 0;
+
+	/*
+	 * Make ptr->wrapped as big as idx.
+	 */
+	new_cnt = idx + 1;
+
+	/*
+	 * Free'ed in arm_spe_recording_free().
+	 */
+	wrapped = reallocarray(ptr->wrapped, new_cnt, sizeof(bool));
+	if (!wrapped)
+		return -ENOMEM;
+
+	/*
+	 * init new allocated values.
+	 */
+	for (i = cnt; i < new_cnt; i++)
+		wrapped[i] = false;
+
+	ptr->wrapped_cnt = new_cnt;
+	ptr->wrapped = wrapped;
+
+	return 0;
+}
+
+static bool arm_spe_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;
+
+	/*
+	 * Defensively handle the case where head might be continually increasing - if its value is
+	 * equal or greater than the size of the ring buffer, then we can safely determine it has
+	 * wrapped around. Otherwise, continue to detect if head might have wrapped.
+	 */
+	if (head >= buffer_size)
+		return true;
+
+	/*
+	 * We want to look the very last 512 byte (chosen arbitrarily) in the ring buffer.
+	 */
+	watermark = buf_size - 512;
+
+	/*
+	 * 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 /= sizeof(u64);
+	buf_size /= sizeof(u64);
+
+	/*
+	 * 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 arm_spe_find_snapshot(struct auxtrace_record *itr, int idx,
+				  struct auxtrace_mmap *mm, unsigned char *data,
+				  u64 *head, u64 *old)
+{
+	int err;
+	bool wrapped;
+	struct arm_spe_recording *ptr =
+			container_of(itr, struct arm_spe_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 = arm_spe_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 && arm_spe_buffer_has_wrapped(data, mm->len, *head)) {
+		wrapped = true;
+		ptr->wrapped[idx] = true;
+	}
+
+	pr_debug3("%s: mmap index %d old head %zu new head %zu size %zu\n",
+		  __func__, idx, (size_t)*old, (size_t)*head, mm->len);
+
+	/*
+	 * No wrap has occurred, we can just use *head and *old.
+	 */
+	if (!wrapped)
+		return 0;
+
+	/*
+	 * *head has wrapped around - adjust *head and *old to pickup the
+	 * entire content of the AUX buffer.
+	 */
+	if (*head >= mm->len) {
+		*old = *head - mm->len;
+	} else {
+		*head += mm->len;
+		*old = *head - mm->len;
+	}
 
 	return 0;
 }
@@ -155,6 +476,7 @@ static void arm_spe_recording_free(struct auxtrace_record *itr)
 	struct arm_spe_recording *sper =
 			container_of(itr, struct arm_spe_recording, itr);
 
+	zfree(&sper->wrapped);
 	free(sper);
 }
 
@@ -176,6 +498,10 @@ struct auxtrace_record *arm_spe_recording_init(int *err,
 
 	sper->arm_spe_pmu = arm_spe_pmu;
 	sper->itr.pmu = arm_spe_pmu;
+	sper->itr.snapshot_start = arm_spe_snapshot_start;
+	sper->itr.snapshot_finish = arm_spe_snapshot_finish;
+	sper->itr.find_snapshot = arm_spe_find_snapshot;
+	sper->itr.parse_snapshot_options = arm_spe_parse_snapshot_options;
 	sper->itr.recording_options = arm_spe_recording_options;
 	sper->itr.info_priv_size = arm_spe_info_priv_size;
 	sper->itr.info_fill = arm_spe_info_fill;
@@ -188,29 +514,8 @@ struct auxtrace_record *arm_spe_recording_init(int *err,
 	return &sper->itr;
 }
 
-struct perf_event_attr
-*arm_spe_pmu_default_config(struct perf_pmu *arm_spe_pmu)
+void
+arm_spe_pmu_default_config(const struct perf_pmu *arm_spe_pmu, struct perf_event_attr *attr)
 {
-	struct perf_event_attr *attr;
-
-	attr = zalloc(sizeof(struct perf_event_attr));
-	if (!attr) {
-		pr_err("arm_spe default config cannot allocate a perf_event_attr\n");
-		return NULL;
-	}
-
-	/*
-	 * If kernel driver doesn't advertise a minimum,
-	 * use max allowable by PMSIDR_EL1.INTERVAL
-	 */
-	if (perf_pmu__scan_file(arm_spe_pmu, "caps/min_interval", "%llu",
-				  &attr->sample_period) != 1) {
-		pr_debug("arm_spe driver doesn't advertise a min. interval. Using 4096\n");
-		attr->sample_period = 4096;
-	}
-
-	arm_spe_pmu->selectable = true;
-	arm_spe_pmu->is_uncore = false;
-
-	return attr;
+	attr->sample_period = arm_spe_pmu__sample_period(arm_spe_pmu);
 }