[PATCH v4 03/23] perf annotate-arm64: Generalize arm64_mov__parse to support more instructions

[Tengda Wu]

As the default parser for arm64 instructions, arm64_mov__parse()
currently only supports parsing instructions with the 'addr <symbol>'
suffix. Other instructions are not supported, causing a lack of
source and target information for most regular instructions.

Generalize arm64_mov__parse to extend its parsing capabilities:
1. Parse 'ops->target.raw' and 'ops->source.raw' by default.
2. Utilize arm64__check_multi_regs() to identify if source and
   target contain multiple registers.
3. Maintain backward compatibility for instructions containing the
   'addr <symbol>' suffix.

Signed-off-by: Tengda Wu <wutengda@xxxxxxxxxxxxxxx>
---
 .../perf/util/annotate-arch/annotate-arm64.c  | 158 ++++++++++++++----
 1 file changed, 126 insertions(+), 32 deletions(-)

diff --git a/tools/perf/util/annotate-arch/annotate-arm64.c b/tools/perf/util/annotate-arch/annotate-arm64.c
index 33080fdca125..5e824fd617ee 100644
--- a/tools/perf/util/annotate-arch/annotate-arm64.c
+++ b/tools/perf/util/annotate-arch/annotate-arm64.c
@@ -3,6 +3,8 @@
 #include <errno.h>
 #include <stdlib.h>
 #include <string.h>
+#include <linux/ctype.h>
+#include <linux/string.h>
 #include <linux/zalloc.h>
 #include <regex.h>
 #include "../annotate.h"
@@ -14,59 +16,151 @@ struct arch_arm64 {
 	regex_t jump_insn;
 };
 
-static int arm64_mov__parse(const struct arch *arch __maybe_unused,
+static bool arm64__is_reg(const char *op)
+{
+	if (!op || !*op)
+		return false;
+
+	/*
+	 * General-purpose registers: x0-x30, w0-w30.
+	 * Check for 'x' or 'w' prefix followed by a numeric index.
+	 */
+	if ((op[0] == 'x' || op[0] == 'w') && isdigit(op[1]))
+		return true;
+
+	/* Special-purpose registers: sp. */
+	if (!strncmp(op, "sp", 2))
+		return true;
+
+	/* TODO: Support more registers. */
+	return false;
+}
+
+static bool arm64__check_multi_regs(const struct arch *arch, const char *op)
+{
+	const char *p = op;
+	int reg_count = 0;
+
+	while (p && *p) {
+		p = skip_spaces(p);
+		if (*p == arch->objdump.memory_ref_char)
+			p++;
+
+		if (arm64__is_reg(p))
+			reg_count++;
+
+		if (reg_count >= 2)
+			return true;
+
+		/* Move to next operand after comma */
+		p = strchr(p, ',');
+		if (p)
+			p++;
+	}
+
+	return false;
+}
+
+/*
+ * Duplicate @insn, stripping the comment and trailing whitespace.
+ * Returns a newly allocated string which the caller must free(),
+ * or NULL on allocation failure or if @insn is NULL.
+ */
+static char *rstrip_space_and_comment(const char *insn, char comment_char)
+{
+	const char *end, *comment;
+	size_t len;
+	char *result;
+
+	if (insn == NULL)
+		return NULL;
+
+	comment = strchr(insn, comment_char);
+	if (comment != NULL)
+		end = comment;
+	else
+		end = insn + strlen(insn);
+
+	while (end > insn && isspace(end[-1]))
+		--end;
+
+	len = end - insn;
+	result = malloc(len + 1);
+	if (result == NULL)
+		return NULL;
+
+	memcpy(result, insn, len);
+	result[len] = '\0';
+
+	return result;
+}
+
+static int arm64_mov__parse(const struct arch *arch,
 			    struct ins_operands *ops,
 			    struct map_symbol *ms __maybe_unused,
 			    struct disasm_line *dl __maybe_unused)
 {
-	char *s = strchr(ops->raw, ','), *target, *endptr;
+	char *s = strchr(ops->raw, ','), *source, *endptr;
 
 	if (s == NULL)
 		return -1;
 
+	/* Parse target */
 	*s = '\0';
-	ops->source.raw = strdup(ops->raw);
+	ops->target.raw = strdup(ops->raw);
 	*s = ',';
 
-	if (ops->source.raw == NULL)
-		return -1;
-
-	target = ++s;
-	ops->target.raw = strdup(target);
 	if (ops->target.raw == NULL)
-		goto out_free_source;
+		return -1;
 
-	ops->target.addr = strtoull(target, &endptr, 16);
-	if (endptr == target)
-		goto out_free_target;
+	ops->target.multi_regs = arm64__check_multi_regs(arch, ops->target.raw);
 
-	s = strchr(endptr, '<');
-	if (s == NULL)
-		goto out_free_target;
-	endptr = strchr(s + 1, '>');
-	if (endptr == NULL)
-		goto out_free_target;
-
-	*endptr = '\0';
-	*s = ' ';
-	ops->target.name = strdup(s);
-	*s = '<';
-	*endptr = '>';
-	if (ops->target.name == NULL)
-		goto out_free_target;
+	/* Parse source, stripping comment if present */
+	source = skip_spaces(++s);
+	ops->source.raw = rstrip_space_and_comment(source, arch->objdump.comment_char);
+	if (ops->source.raw == NULL) {
+		zfree(&ops->target.raw);
+		return -1;
+	}
+
+	ops->source.multi_regs = arm64__check_multi_regs(arch, ops->source.raw);
+
+	/* Parse 'addr <symbol>' from source (if any) */
+	ops->source.addr = strtoull(ops->source.raw, &endptr, 16);
+	if (endptr != ops->source.raw) {
+		s = strchr(endptr, '<');
+		if (s == NULL) {
+			ops->source.addr = 0;
+			return 0;
+		}
+		endptr = strrchr(s + 1, '>');
+		if (endptr == NULL) {
+			ops->source.addr = 0;
+			return 0;
+		}
+
+		*endptr = '\0';
+		ops->source.name = strdup(s + 1);
+		*endptr = '>';
+		if (ops->source.name == NULL) {
+			ops->source.addr = 0;
+			return 0;
+		}
+	}
 
 	return 0;
+}
 
-out_free_target:
-	zfree(&ops->target.raw);
-out_free_source:
-	zfree(&ops->source.raw);
-	return -1;
+static int arm64_mov__scnprintf(const struct ins *ins, char *bf, size_t size,
+				struct ins_operands *ops, int max_ins_name)
+{
+	return scnprintf(bf, size, "%-*s %s, %s", max_ins_name, ins->name,
+			 ops->target.raw, ops->source.name ?: ops->source.raw);
 }
 
 static const struct ins_ops arm64_mov_ops = {
 	.parse	   = arm64_mov__parse,
-	.scnprintf = mov__scnprintf,
+	.scnprintf = arm64_mov__scnprintf,
 };
 
 static const struct ins_ops *arm64__associate_instruction_ops(struct arch *arch, const char *name)
-- 
2.34.1