Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::3:4 as permitted sender) client-ip=2620:137:e000::3:4;
Sender: Namhyung Kim <namhyung@gmail.com>
From:   Namhyung Kim <namhyung@kernel.org>
To:     Arnaldo Carvalho de Melo <acme@kernel.org>,
        Jiri Olsa <jolsa@kernel.org>,
        Peter Zijlstra <peterz@infradead.org>
Cc:     Ian Rogers <irogers@google.com>,
        Adrian Hunter <adrian.hunter@intel.com>,
        Ingo Molnar <mingo@kernel.org>,
        LKML <linux-kernel@vger.kernel.org>,
        linux-perf-users@vger.kernel.org,
        Linus Torvalds <torvalds@linux-foundation.org>,
        Stephane Eranian <eranian@google.com>,
        Masami Hiramatsu <mhiramat@kernel.org>,
        linux-toolchains@vger.kernel.org, linux-trace-devel@vger.kernel.org
Subject: [PATCH 14/48] perf annotate: Implement hist_entry__get_data_type()
Date:   Wed, 11 Oct 2023 20:50:37 -0700
Message-ID: <20231012035111.676789-15-namhyung@kernel.org>
In-Reply-To: <20231012035111.676789-1-namhyung@kernel.org>
References: <20231012035111.676789-1-namhyung@kernel.org>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

It's the function to find out the type info from the given sample data
and will be called from the hist_entry sort logic when 'type' sort key
is used.

It first calls objdump to disassemble the instructions and figure out
information about memory access at the location.  Maybe we can do it
better by analyzing the instruction directly, but I'll leave it for
later work.

The memory access is determined by checking instruction operands to
have "(" and then extract register name and offset.  It'll return NULL
if no data type is found.

Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/util/annotate.c | 85 ++++++++++++++++++++++++++++++++++++++
 tools/perf/util/annotate.h |  4 ++
 2 files changed, 89 insertions(+)

diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index 9d653a1e84ce..e5dc3d6fc6d0 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -25,6 +25,7 @@
 #include "units.h"
 #include "debug.h"
 #include "annotate.h"
+#include "annotate-data.h"
 #include "evsel.h"
 #include "evlist.h"
 #include "bpf-event.h"
@@ -3591,3 +3592,87 @@ int annotate_get_insn_location(struct arch *arch, struct disasm_line *dl,
 
 	return 0;
 }
+
+static void symbol__ensure_annotate(struct map_symbol *ms, struct evsel *evsel)
+{
+	struct disasm_line *dl, *tmp_dl;
+	struct annotation *notes;
+
+	notes = symbol__annotation(ms->sym);
+	if (!list_empty(&notes->src->source))
+		return;
+
+	if (symbol__annotate(ms, evsel, notes->options, NULL) < 0)
+		return;
+
+	/* remove non-insn disasm lines for simplicity */
+	list_for_each_entry_safe(dl, tmp_dl, &notes->src->source, al.node) {
+		if (dl->al.offset == -1) {
+			list_del(&dl->al.node);
+			free(dl);
+		}
+	}
+}
+
+static struct disasm_line *find_disasm_line(struct symbol *sym, u64 ip)
+{
+	struct disasm_line *dl;
+	struct annotation *notes;
+
+	notes = symbol__annotation(sym);
+
+	list_for_each_entry(dl, &notes->src->source, al.node) {
+		if (sym->start + dl->al.offset == ip)
+			return dl;
+	}
+	return NULL;
+}
+
+/**
+ * hist_entry__get_data_type - find data type for given hist entry
+ * @he: hist entry
+ *
+ * This function first annotates the instruction at @he->ip and extracts
+ * register and offset info from it.  Then it searches the DWARF debug
+ * info to get a variable and type information using the address, register,
+ * and offset.
+ */
+struct annotated_data_type *hist_entry__get_data_type(struct hist_entry *he)
+{
+	struct map_symbol *ms = &he->ms;
+	struct evsel *evsel = hists_to_evsel(he->hists);
+	struct arch *arch;
+	struct disasm_line *dl;
+	struct annotated_insn_loc loc;
+	struct annotated_op_loc *op_loc;
+	u64 ip = he->ip;
+	int i;
+
+	if (ms->map == NULL || ms->sym == NULL)
+		return NULL;
+
+	if (evsel__get_arch(evsel, &arch) < 0)
+		return NULL;
+
+	/* Make sure it runs objdump to get disasm of the function */
+	symbol__ensure_annotate(ms, evsel);
+
+	/*
+	 * Get a disasm to extract the location from the insn.
+	 * This is too slow...
+	 */
+	dl = find_disasm_line(ms->sym, ip);
+	if (dl == NULL)
+		return NULL;
+
+	if (annotate_get_insn_location(arch, dl, &loc) < 0)
+		return NULL;
+
+	for_each_insn_op_loc(&loc, i, op_loc) {
+		if (!op_loc->mem_ref)
+			continue;
+
+		return find_data_type(ms, ip, op_loc->reg, op_loc->offset);
+	}
+	return NULL;
+}
diff --git a/tools/perf/util/annotate.h b/tools/perf/util/annotate.h
index 4adda492233d..299b4a18e804 100644
--- a/tools/perf/util/annotate.h
+++ b/tools/perf/util/annotate.h
@@ -23,6 +23,7 @@ struct option;
 struct perf_sample;
 struct evsel;
 struct symbol;
+struct annotated_data_type;
 
 struct ins {
 	const char     *name;
@@ -473,4 +474,7 @@ struct annotated_insn_loc {
 int annotate_get_insn_location(struct arch *arch, struct disasm_line *dl,
 			       struct annotated_insn_loc *loc);
 
+/* Returns a data type from the sample instruction (if any) */
+struct annotated_data_type *hist_entry__get_data_type(struct hist_entry *he);
+
 #endif	/* __PERF_ANNOTATE_H */
-- 
2.42.0.655.g421f12c284-goog