[RFC PATCH v1 3/8] perf/core: Implement BUILD_ID_OFFSET sample type

[Ian Rogers]

Expose stack_map_get_build_id_offset for perf_events to use when generating
these samples, and implement the payload writing in the perf event core.

Signed-off-by: Ian Rogers <irogers@xxxxxxxxxx>
---
 include/linux/bpf.h   | 13 +++++++
 kernel/bpf/stackmap.c |  2 +-
 kernel/events/core.c  | 85 ++++++++++++++++++++++++++++++++++++++++++-
 3 files changed, 98 insertions(+), 2 deletions(-)

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 7719f6528445..fd76900a8e47 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -4209,4 +4209,17 @@ static inline int bpf_map_check_op_flags(struct bpf_map *map, u64 flags, u64 all
 	return 0;
 }
 
+struct bpf_stack_build_id;
+#if defined(CONFIG_BPF_SYSCALL) && defined(CONFIG_PERF_EVENTS)
+void stack_map_get_build_id_offset(struct bpf_stack_build_id *id_offs,
+				    u32 trace_nr, bool user, bool may_fault);
+#else
+static inline void stack_map_get_build_id_offset(struct bpf_stack_build_id *id_offs,
+						  u32 trace_nr, bool user, bool may_fault)
+{
+	if (id_offs)
+		id_offs->status = 1; /* BPF_STACK_BUILD_ID_EMPTY */
+}
+#endif
+
 #endif /* _LINUX_BPF_H */
diff --git a/kernel/bpf/stackmap.c b/kernel/bpf/stackmap.c
index 41fe87d7302f..889ceb7cf29b 100644
--- a/kernel/bpf/stackmap.c
+++ b/kernel/bpf/stackmap.c
@@ -411,7 +411,7 @@ static void stack_map_get_build_id_offset_sleepable(struct bpf_stack_build_id *i
  *     id_offs[i].build_id is zeroed out and id_offs[i].status is set to
  *     BPF_STACK_BUILD_ID_IP.
  */
-static void stack_map_get_build_id_offset(struct bpf_stack_build_id *id_offs,
+void stack_map_get_build_id_offset(struct bpf_stack_build_id *id_offs,
 					  u32 trace_nr, bool user, bool may_fault)
 {
 	struct mmap_unlock_irq_work *work = NULL;
diff --git a/kernel/events/core.c b/kernel/events/core.c
index ba5bd6a78fe7..97ac70441602 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -2048,6 +2048,15 @@ static int __perf_event_read_size(u64 read_format, int nr_siblings)
 	return size + nr * entry;
 }
 
+
+struct perf_sample_build_id_offset {
+	u8	size;
+	u8	res1;
+	u16	res2;
+	u8	build_id[BPF_BUILD_ID_SIZE];
+	u64	offset;
+};
+
 static void __perf_event_header_size(struct perf_event *event, u64 sample_type)
 {
 	struct perf_sample_data *data;
@@ -2086,6 +2095,11 @@ static void __perf_event_header_size(struct perf_event *event, u64 sample_type)
 	if (sample_type & PERF_SAMPLE_CODE_PAGE_SIZE)
 		size += sizeof(data->code_page_size);
 
+	if (sample_type & PERF_SAMPLE_BUILD_ID_OFFSET)
+		size += sizeof(struct perf_sample_build_id_offset);
+
+
+
 	event->header_size = size;
 }
 
@@ -8287,6 +8301,62 @@ void perf_output_sample(struct perf_output_handle *handle,
 	if (sample_type & PERF_SAMPLE_READ)
 		perf_output_read(handle, event);
 
+	if (sample_type & PERF_SAMPLE_BUILD_ID_OFFSET) {
+		struct bpf_stack_build_id bpf_bid = { .ip = data->ip };
+		struct perf_sample_build_id_offset bid_offset = { 0 };
+
+		bool is_user = (header->misc & PERF_RECORD_MISC_CPUMODE_MASK) ==
+			       PERF_RECORD_MISC_USER;
+
+		stack_map_get_build_id_offset(
+			&bpf_bid, /*trace_nr=*/1,
+			is_user, /*may_fault=*/false);
+		if (bpf_bid.status == BPF_STACK_BUILD_ID_VALID) {
+			bid_offset.size = BPF_BUILD_ID_SIZE;
+			memcpy(bid_offset.build_id, bpf_bid.build_id,
+				       BPF_BUILD_ID_SIZE);
+			bid_offset.offset = bpf_bid.offset;
+		} else {
+			bid_offset.offset = bpf_bid.ip;
+		}
+		perf_output_put(handle, bid_offset);
+	}
+
+	if (sample_type & PERF_SAMPLE_CALLCHAIN_BUILD_ID_OFFSET) {
+		u64 nr = data->callchain ? data->callchain->nr : 0;
+		struct perf_sample_build_id_offset bid_offset;
+		struct bpf_stack_build_id bpf_bid;
+		u64 i;
+
+		perf_output_put(handle, nr);
+
+		for (i = 0; i < nr; i++) {
+			memset(&bid_offset, /*c=*/0, sizeof(bid_offset));
+			memset(&bpf_bid, /*c=*/0, sizeof(bpf_bid));
+			bpf_bid.ip = data->callchain->ip[i];
+
+			if (data->callchain->ip[i] == PERF_CONTEXT_USER) {
+				bpf_bid.status = BPF_STACK_BUILD_ID_EMPTY;
+			} else {
+				bool is_user = data->callchain->ip[i] < PERF_CONTEXT_MAX;
+
+				stack_map_get_build_id_offset(&bpf_bid, /*trace_nr=*/1,
+					      is_user, /*may_fault=*/false);
+			}
+
+			if (bpf_bid.status == BPF_STACK_BUILD_ID_VALID) {
+				bid_offset.size = BPF_BUILD_ID_SIZE;
+				memcpy(bid_offset.build_id, bpf_bid.build_id,
+			       BPF_BUILD_ID_SIZE);
+				bid_offset.offset = bpf_bid.offset;
+			} else {
+				bid_offset.offset = bpf_bid.ip;
+			}
+			perf_output_put(handle, bid_offset);
+		}
+	}
+
+
 	if (sample_type & PERF_SAMPLE_CALLCHAIN) {
 		int size = 1;
 
@@ -8632,7 +8702,7 @@ void perf_prepare_sample(struct perf_sample_data *data,
 
 	__perf_event_header__init_id(data, event, filtered_sample_type);
 
-	if (filtered_sample_type & PERF_SAMPLE_IP) {
+	if (filtered_sample_type & (PERF_SAMPLE_IP | PERF_SAMPLE_BUILD_ID_OFFSET)) {
 		data->ip = perf_instruction_pointer(event, regs);
 		data->sample_flags |= PERF_SAMPLE_IP;
 	}
@@ -8640,6 +8710,19 @@ void perf_prepare_sample(struct perf_sample_data *data,
 	if (filtered_sample_type & PERF_SAMPLE_CALLCHAIN)
 		perf_sample_save_callchain(data, event, regs);
 
+	if (filtered_sample_type & PERF_SAMPLE_CALLCHAIN_BUILD_ID_OFFSET) {
+		int size = 1;
+
+		if (!data->callchain)
+			data->callchain = perf_callchain(event, regs);
+
+		size += data->callchain->nr *
+			(sizeof(struct perf_sample_build_id_offset) / sizeof(u64));
+		data->dyn_size += size * sizeof(u64);
+		data->sample_flags |= PERF_SAMPLE_CALLCHAIN_BUILD_ID_OFFSET;
+	}
+
+
 	if (filtered_sample_type & PERF_SAMPLE_RAW) {
 		data->raw = NULL;
 		data->dyn_size += sizeof(u64);
-- 
2.55.0.679.g6767b8d81c-goog