perf annotate-data: Add find_data_type() to get type from memory access

The find_data_type() is to get a data type from the memory access at the
given address (IP) using a register and an offset.

It requires DWARF debug info in the DSO and searches the list of
variables and function parameters in the scope.

In a pseudo code, it does basically the following:

  find_data_type(dso, ip, reg, offset)
  {
      pc = map__rip_2objdump(ip);
      CU = dwarf_addrdie(dso->dwarf, pc);
      scopes = die_get_scopes(CU, pc);
      for_each_scope(S, scopes) {
          V = die_find_variable_by_reg(S, pc, reg);
          if (V && V.type == pointer_type) {
              T = die_get_real_type(V);
              if (offset < T.size)
                  return T;
          }
      }
      return NULL;
  }

Committer notes:

The 'size' variable in check_variable() is 64-bit, so use PRIu64 and
inttypes.h to debug it.

Ditto at find_data_type_die().

Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: linux-toolchains@vger.kernel.org
Cc: linux-trace-devel@vger.kernel.org
Link: https://lore.kernel.org/r/20231213001323.718046-4-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

3 files changed, 205 insertions, 0 deletions

diff --git a/tools/perf/util/Build b/tools/perf/util/Build
index 132508ebe125..8027f450fa3e 100644
--- a/tools/perf/util/Build
+++ b/tools/perf/util/Build
@@ -196,6 +196,7 @@ perf-$(CONFIG_DWARF) += probe-finder.o
 perf-$(CONFIG_DWARF) += dwarf-aux.o
 perf-$(CONFIG_DWARF) += dwarf-regs.o
 perf-$(CONFIG_DWARF) += debuginfo.o
+perf-$(CONFIG_DWARF) += annotate-data.o
 
 perf-$(CONFIG_LIBDW_DWARF_UNWIND) += unwind-libdw.o
 perf-$(CONFIG_LOCAL_LIBUNWIND)    += unwind-libunwind-local.o
diff --git a/tools/perf/util/annotate-data.c b/tools/perf/util/annotate-data.c
new file mode 100644
index 000000000000..9739ecc841ee
--- /dev/null
+++ b/tools/perf/util/annotate-data.c
@@ -0,0 +1,164 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Convert sample address to data type using DWARF debug info.
+ *
+ * Written by Namhyung Kim <namhyung@kernel.org>
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <inttypes.h>
+
+#include "annotate-data.h"
+#include "debuginfo.h"
+#include "debug.h"
+#include "dso.h"
+#include "map.h"
+#include "map_symbol.h"
+#include "strbuf.h"
+#include "symbol.h"
+
+static bool find_cu_die(struct debuginfo *di, u64 pc, Dwarf_Die *cu_die)
+{
+	Dwarf_Off off, next_off;
+	size_t header_size;
+
+	if (dwarf_addrdie(di->dbg, pc, cu_die) != NULL)
+		return cu_die;
+
+	/*
+	 * There are some kernels don't have full aranges and contain only a few
+	 * aranges entries.  Fallback to iterate all CU entries in .debug_info
+	 * in case it's missing.
+	 */
+	off = 0;
+	while (dwarf_nextcu(di->dbg, off, &next_off, &header_size,
+			    NULL, NULL, NULL) == 0) {
+		if (dwarf_offdie(di->dbg, off + header_size, cu_die) &&
+		    dwarf_haspc(cu_die, pc))
+			return true;
+
+		off = next_off;
+	}
+	return false;
+}
+
+/* The type info will be saved in @type_die */
+static int check_variable(Dwarf_Die *var_die, Dwarf_Die *type_die, int offset)
+{
+	Dwarf_Word size;
+
+	/* Get the type of the variable */
+	if (die_get_real_type(var_die, type_die) == NULL) {
+		pr_debug("variable has no type\n");
+		return -1;
+	}
+
+	/*
+	 * It expects a pointer type for a memory access.
+	 * Convert to a real type it points to.
+	 */
+	if (dwarf_tag(type_die) != DW_TAG_pointer_type ||
+	    die_get_real_type(type_die, type_die) == NULL) {
+		pr_debug("no pointer or no type\n");
+		return -1;
+	}
+
+	/* Get the size of the actual type */
+	if (dwarf_aggregate_size(type_die, &size) < 0) {
+		pr_debug("type size is unknown\n");
+		return -1;
+	}
+
+	/* Minimal sanity check */
+	if ((unsigned)offset >= size) {
+		pr_debug("offset: %d is bigger than size: %" PRIu64 "\n", offset, size);
+		return -1;
+	}
+
+	return 0;
+}
+
+/* The result will be saved in @type_die */
+static int find_data_type_die(struct debuginfo *di, u64 pc,
+			      int reg, int offset, Dwarf_Die *type_die)
+{
+	Dwarf_Die cu_die, var_die;
+	Dwarf_Die *scopes = NULL;
+	int ret = -1;
+	int i, nr_scopes;
+
+	/* Get a compile_unit for this address */
+	if (!find_cu_die(di, pc, &cu_die)) {
+		pr_debug("cannot find CU for address %" PRIx64 "\n", pc);
+		return -1;
+	}
+
+	/* Get a list of nested scopes - i.e. (inlined) functions and blocks. */
+	nr_scopes = die_get_scopes(&cu_die, pc, &scopes);
+
+	/* Search from the inner-most scope to the outer */
+	for (i = nr_scopes - 1; i >= 0; i--) {
+		/* Look up variables/parameters in this scope */
+		if (!die_find_variable_by_reg(&scopes[i], pc, reg, &var_die))
+			continue;
+
+		/* Found a variable, see if it's correct */
+		ret = check_variable(&var_die, type_die, offset);
+		break;
+	}
+
+	free(scopes);
+	return ret;
+}
+
+/**
+ * find_data_type - Return a data type at the location
+ * @ms: map and symbol at the location
+ * @ip: instruction address of the memory access
+ * @reg: register that holds the base address
+ * @offset: offset from the base address
+ *
+ * This functions searches the debug information of the binary to get the data
+ * type it accesses.  The exact location is expressed by (ip, reg, offset).
+ * It return %NULL if not found.
+ */
+struct annotated_data_type *find_data_type(struct map_symbol *ms, u64 ip,
+					   int reg, int offset)
+{
+	struct annotated_data_type *result = NULL;
+	struct dso *dso = map__dso(ms->map);
+	struct debuginfo *di;
+	Dwarf_Die type_die;
+	struct strbuf sb;
+	u64 pc;
+
+	di = debuginfo__new(dso->long_name);
+	if (di == NULL) {
+		pr_debug("cannot get the debug info\n");
+		return NULL;
+	}
+
+	/*
+	 * IP is a relative instruction address from the start of the map, as
+	 * it can be randomized/relocated, it needs to translate to PC which is
+	 * a file address for DWARF processing.
+	 */
+	pc = map__rip_2objdump(ms->map, ip);
+	if (find_data_type_die(di, pc, reg, offset, &type_die) < 0)
+		goto out;
+
+	result = zalloc(sizeof(*result));
+	if (result == NULL)
+		goto out;
+
+	strbuf_init(&sb, 32);
+	if (die_get_typename_from_type(&type_die, &sb) < 0)
+		strbuf_add(&sb, "(unknown type)", 14);
+
+	result->type_name = strbuf_detach(&sb, NULL);
+
+out:
+	debuginfo__delete(di);
+	return result;
+}
diff --git a/tools/perf/util/annotate-data.h b/tools/perf/util/annotate-data.h
new file mode 100644
index 000000000000..633147f78ca5
--- /dev/null
+++ b/tools/perf/util/annotate-data.h
@@ -0,0 +1,40 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _PERF_ANNOTATE_DATA_H
+#define _PERF_ANNOTATE_DATA_H
+
+#include <errno.h>
+#include <linux/compiler.h>
+#include <linux/types.h>
+
+struct map_symbol;
+
+/**
+ * struct annotated_data_type - Data type to profile
+ * @type_name: Name of the data type
+ * @type_size: Size of the data type
+ *
+ * This represents a data type accessed by samples in the profile data.
+ */
+struct annotated_data_type {
+	char *type_name;
+	int type_size;
+};
+
+#ifdef HAVE_DWARF_SUPPORT
+
+/* Returns data type at the location (ip, reg, offset) */
+struct annotated_data_type *find_data_type(struct map_symbol *ms, u64 ip,
+					   int reg, int offset);
+
+#else /* HAVE_DWARF_SUPPORT */
+
+static inline struct annotated_data_type *
+find_data_type(struct map_symbol *ms __maybe_unused, u64 ip __maybe_unused,
+	       int reg __maybe_unused, int offset __maybe_unused)
+{
+	return NULL;
+}
+
+#endif /* HAVE_DWARF_SUPPORT */
+
+#endif /* _PERF_ANNOTATE_DATA_H */