perf annotate: Add disasm_line__parse() to parse raw instruction for powerpc

Currently, the perf tool infrastructure uses the disasm_line__parse
function to parse disassembled line.

Example snippet from objdump:

  objdump  --start-address=<address> --stop-address=<address>  -d --no-show-raw-insn -C <vmlinux>

  c0000000010224b4:	lwz     r10,0(r9)

This line "lwz r10,0(r9)" is parsed to extract instruction name,
registers names and offset.

In powerpc, the approach for data type profiling uses raw instruction
instead of result from objdump to identify the instruction category and
extract the source/target registers.

Example: 38 01 81 e8     ld      r4,312(r1)

Here "38 01 81 e8" is the raw instruction representation. Add function
"disasm_line__parse_powerpc" to handle parsing of raw instruction.
Also update "struct disasm_line" to save the binary code/
With the change, function captures:

line -> "38 01 81 e8     ld      r4,312(r1)"
raw instruction "38 01 81 e8"

Raw instruction is used later to extract the reg/offset fields. Macros
are added to extract opcode and register fields. "struct disasm_line"
is updated to carry union of "bytes" and "raw_insn" of 32 bit to carry raw
code (raw).

Function "disasm_line__parse_powerpc fills the raw instruction hex value
and can use macros to get opcode. There is no changes in existing code
paths, which parses the disassembled code.  The size of raw instruction
depends on architecture.

In case of powerpc, the parsing the disasm line needs to handle cases
for reading binary code directly from DSO as well as parsing the objdump
result. Hence adding the logic into separate function instead of
updating "disasm_line__parse".  The architecture using the instruction
name and present approach is not altered. Since this approach targets
powerpc, the macro implementation is added for powerpc as of now.

Since the disasm_line__parse is used in other cases (perf annotate) and
not only data tye profiling, the powerpc callback includes changes to
work with binary code as well as mnemonic representation.

Also in case if the DSO read fails and libcapstone is not supported, the
approach fallback to use objdump as option. Hence as option, patch has
changes to ensure objdump option also works well.

Reviewed-by: Kajol Jain <kjain@linux.ibm.com>
Reviewed-by: Namhyung Kim <namhyung@kernel.org>
Signed-off-by: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Tested-by: Kajol Jain <kjain@linux.ibm.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Akanksha J N <akanksha@linux.ibm.com>
Cc: Christophe Leroy <christophe.leroy@csgroup.eu>
Cc: Disha Goel <disgoel@linux.vnet.ibm.com>
Cc: Hari Bathini <hbathini@linux.ibm.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Madhavan Srinivasan <maddy@linux.ibm.com>
Cc: Segher Boessenkool <segher@kernel.crashing.org>
Link: https://lore.kernel.org/lkml/20240718084358.72242-5-atrajeev@linux.vnet.ibm.com
[ Add check for strndup() result ]
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

1 files changed, 50 insertions, 1 deletions

diff --git a/tools/perf/util/disasm.c b/tools/perf/util/disasm.c
index 931cd92dcc40..6d4055b9b966 100644
--- a/tools/perf/util/disasm.c
+++ b/tools/perf/util/disasm.c
@@ -44,6 +44,7 @@ static int call__scnprintf(struct ins *ins, char *bf, size_t size,
 
 static void ins__sort(struct arch *arch);
 static int disasm_line__parse(char *line, const char **namep, char **rawp);
+static int disasm_line__parse_powerpc(struct disasm_line *dl);
 
 static __attribute__((constructor)) void symbol__init_regexpr(void)
 {
@@ -845,6 +846,51 @@ out:
 	return -1;
 }
 
+/*
+ * Parses the result captured from symbol__disassemble_*
+ * Example, line read from DSO file in powerpc:
+ * line:    38 01 81 e8
+ * opcode: fetched from arch specific get_opcode_insn
+ * rawp_insn: e8810138
+ *
+ * rawp_insn is used later to extract the reg/offset fields
+ */
+#define	PPC_OP(op)	(((op) >> 26) & 0x3F)
+#define	RAW_BYTES	11
+
+static int disasm_line__parse_powerpc(struct disasm_line *dl)
+{
+	char *line = dl->al.line;
+	const char **namep = &dl->ins.name;
+	char **rawp = &dl->ops.raw;
+	char *tmp_raw_insn, *name_raw_insn = skip_spaces(line);
+	char *name = skip_spaces(name_raw_insn + RAW_BYTES);
+	int objdump = 0;
+
+	if (strlen(line) > RAW_BYTES)
+		objdump = 1;
+
+	if (name_raw_insn[0] == '\0')
+		return -1;
+
+	if (objdump) {
+		disasm_line__parse(name, namep, rawp);
+	} else
+		*namep = "";
+
+	tmp_raw_insn = strndup(name_raw_insn, 11);
+	if (tmp_raw_insn == NULL)
+		return -1;
+
+	remove_spaces(tmp_raw_insn);
+
+	sscanf(tmp_raw_insn, "%x", &dl->raw.raw_insn);
+	if (objdump)
+		dl->raw.raw_insn = be32_to_cpu(dl->raw.raw_insn);
+
+	return 0;
+}
+
 static void annotation_line__init(struct annotation_line *al,
 				  struct annotate_args *args,
 				  int nr)
@@ -898,7 +944,10 @@ struct disasm_line *disasm_line__new(struct annotate_args *args)
 		goto out_delete;
 
 	if (args->offset != -1) {
-		if (disasm_line__parse(dl->al.line, &dl->ins.name, &dl->ops.raw) < 0)
+		if (arch__is(args->arch, "powerpc")) {
+			if (disasm_line__parse_powerpc(dl) < 0)
+				goto out_free_line;
+		} else if (disasm_line__parse(dl->al.line, &dl->ins.name, &dl->ops.raw) < 0)
 			goto out_free_line;
 
 		disasm_line__init_ins(dl, args->arch, &args->ms);