[PATCH v4 08/23] perf annotate-arm64: Implement extract_op_location() callback

Implement the extract_op_location() callback for the arm64 architecture
to handle its specific assembly syntax and addressing modes.

The extractor handles:
1. Standalone immediate operands (e.g., #0x10).
2. Memory references with diverse addressing modes:
   - Signed offset: [base{, #imm|reg}]
   - Pre-index: [base, #imm]!
   - Post-index: [base], #imm|reg
3. Multi-register operands and primary/secondary register extraction.

With this callback in place, 'perf annotate' can now resolve memory
locations and register types on arm64, marking the initial enablement
of data type profiling for this architecture.

Signed-off-by: Tengda Wu <[email protected]>
---
 .../perf/util/annotate-arch/annotate-arm64.c  | 67 +++++++++++++++++++
 tools/perf/util/annotate.h                    | 10 +++
 2 files changed, 77 insertions(+)

diff --git a/tools/perf/util/annotate-arch/annotate-arm64.c b/tools/perf/util/annotate-arch/annotate-arm64.c
index 32752a3bc756..6b4f1228afa9 100644
--- a/tools/perf/util/annotate-arch/annotate-arm64.c
+++ b/tools/perf/util/annotate-arch/annotate-arm64.c
@@ -287,6 +287,72 @@ static const struct ins_ops *arm64__associate_instruction_ops(struct arch *arch,
 	return ops;
 }
 
+static int extract_op_location_arm64(const struct arch *arch,
+				     struct disasm_line *dl __maybe_unused,
+				     const char *op_str, int op_idx __maybe_unused,
+				     struct annotated_op_loc *op_loc)
+{
+	const char *s = op_str;
+	char *p = NULL;
+
+	if (op_str == NULL)
+		return 0;
+
+	/* Handle standalone immediate operands (e.g., #0x10) */
+	if (*s == arch->objdump.imm_char) {
+		op_loc->offset = strtol(s + 1, &p, 0);
+		if (p && p != s + 1)
+			op_loc->imm = true;
+		return 0;
+	}
+
+	/*
+	 * Handle memory references, identify arm64 specific addressing modes.
+	 * Reference: Arm Architecture Reference Manual
+	 *            (DDI 0487), Chapter C1.3.3: Load/store addressing modes.
+	 */
+	if (*s == arch->objdump.memory_ref_char) {
+		op_loc->mem_ref = true;
+
+		p = strchr(s, ']');
+		if (p == NULL)
+			return -1;
+
+		/* Pre-index: [base, #imm]! */
+		if (p[1] == '!')
+			op_loc->addr_mode = PERF_ADDR_MODE_PRE_INDEX;
+		/* Post-index: [base], #imm|reg */
+		else if (p[1] == ',' &&
+			 (strchr(p + 1, arch->objdump.imm_char) ||
+			  arm64__is_reg(skip_spaces(p + 2))))
+			op_loc->addr_mode = PERF_ADDR_MODE_POST_INDEX;
+		/* Signed offset: [base{, #imm|reg}] */
+		else
+			op_loc->addr_mode = PERF_ADDR_MODE_SIGNED_OFFSET;
+
+		s++;
+	}
+
+	/* Extract the primary register */
+	op_loc->reg1 = arch__dwarf_regnum(arch, s);
+	if (op_loc->reg1 == -1)
+		return -1;
+
+	/* Move to the next symbol of the operand, if any */
+	s = strchr(s, ',');
+	if (s == NULL)
+		return 0;
+	s = skip_spaces(s + 1);
+
+	/* Extract secondary register or immediate offset */
+	if (op_loc->multi_regs)
+		op_loc->reg2 = arch__dwarf_regnum(arch, s);
+	else if (*s == arch->objdump.imm_char)
+		op_loc->offset = strtol(s + 1, &p, 0);
+
+	return 0;
+}
+
 const struct arch *arch__new_arm64(const struct e_machine_and_e_flags *id,
 				   const char *cpuid __maybe_unused)
 {
@@ -305,6 +371,7 @@ const struct arch *arch__new_arm64(const struct e_machine_and_e_flags *id,
 	arch->objdump.memory_ref_char	  = '[';
 	arch->objdump.imm_char		  = '#';
 	arch->associate_instruction_ops   = arm64__associate_instruction_ops;
+	arch->extract_op_location	  = extract_op_location_arm64;
 
 	/* bl, blr */
 	err = regcomp(&arm->call_insn, "^blr?$", REG_EXTENDED);
diff --git a/tools/perf/util/annotate.h b/tools/perf/util/annotate.h
index 11b6e4780c02..a44c933f55f5 100644
--- a/tools/perf/util/annotate.h
+++ b/tools/perf/util/annotate.h
@@ -494,12 +494,21 @@ int annotate_check_args(void);
 
 int arch__dwarf_regnum(const struct arch *arch, const char *str);
 
+enum annotated_addr_mode {
+	PERF_ADDR_MODE_NONE = 0,
+
+	PERF_ADDR_MODE_SIGNED_OFFSET,
+	PERF_ADDR_MODE_PRE_INDEX,
+	PERF_ADDR_MODE_POST_INDEX,
+};
+
 /**
  * struct annotated_op_loc - Location info of instruction operand
  * @reg1: First register in the operand
  * @reg2: Second register in the operand
  * @offset: Memory access offset in the operand
  * @segment: Segment selector register
+ * @addr_mode: Addressing mode, only valid if @mem_ref is true
  * @mem_ref: Whether the operand accesses memory
  * @multi_regs: Whether the second register is used
  * @imm: Whether the operand is an immediate value (in offset)
@@ -509,6 +518,7 @@ struct annotated_op_loc {
 	int reg2;
 	int offset;
 	u8 segment;
+	u8 addr_mode;
 	bool mem_ref;
 	bool multi_regs;
 	bool imm;
-- 
2.34.1