perf annotate: Parse x86 segment register location

Add a segment field in the struct annotated_insn_loc and save it for the
segment based addressing like %gs:0x28.  For simplicity it now handles
%gs register only.
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>
Link: https://lore.kernel.org/r/20240319055115.4063940-17-namhyung@kernel.orgSigned-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

tools/perf/util/annotate.c

@@ -94,6 +94,7 @@ struct arch {
 		char skip_functions_char;
 		char register_char;
 		char memory_ref_char;
+		char imm_char;
 	} objdump;
 };
 
@@ -211,6 +212,7 @@ static struct arch architectures[] = {
 			.comment_char = '#',
 			.register_char = '%',
 			.memory_ref_char = '(',
+			.imm_char = '$',
 		},
 	},
 	{
@@ -3585,6 +3587,12 @@ static int extract_reg_offset(struct arch *arch, const char *str,
 	 * %gs:0x18(%rbx).  In that case it should skip the part.
 	 */
 	if (*str == arch->objdump.register_char) {
+		if (arch__is(arch, "x86")) {
+			/* FIXME: Handle other segment registers */
+			if (!strncmp(str, "%gs:", 4))
+				op_loc->segment = INSN_SEG_X86_GS;
+		}
+
 		while (*str && !isdigit(*str) &&
 		       *str != arch->objdump.memory_ref_char)
 			str++;
@@ -3681,12 +3689,32 @@ int annotate_get_insn_location(struct arch *arch, struct disasm_line *dl,
 			op_loc->multi_regs = multi_regs;
 			extract_reg_offset(arch, insn_str, op_loc);
 		} else {
-			char *s = strdup(insn_str);
+			char *s, *p = NULL;
+
+			if (arch__is(arch, "x86")) {
+				/* FIXME: Handle other segment registers */
+				if (!strncmp(insn_str, "%gs:", 4)) {
+					op_loc->segment = INSN_SEG_X86_GS;
+					op_loc->offset = strtol(insn_str + 4,
+								&p, 0);
+					if (p && p != insn_str + 4)
+						op_loc->imm = true;
+					continue;
+				}
+			}
+
+			s = strdup(insn_str);
+			if (s == NULL)
+				return -1;
 
-			if (s) {
+			if (*s == arch->objdump.register_char)
 				op_loc->reg1 = get_dwarf_regnum(s, 0);
-				free(s);
+			else if (*s == arch->objdump.imm_char) {
+				op_loc->offset = strtol(s + 1, &p, 0);
+				if (p && p != s + 1)
+					op_loc->imm = true;
 			}
+			free(s);
 		}
 	}
 
@@ -3881,7 +3909,7 @@ struct annotated_data_type *hist_entry__get_data_type(struct hist_entry *he)
 			.op = op_loc,
 		};
 
-		if (!op_loc->mem_ref)
+		if (!op_loc->mem_ref && op_loc->segment == INSN_SEG_NONE)
 			continue;
 
 		/* Recalculate IP because of LOCK prefix or insn fusion */

tools/perf/util/annotate.h

@@ -511,15 +511,19 @@ int annotate_check_args(void);
  * @reg1: First register in the operand
  * @reg2: Second register in the operand
  * @offset: Memory access offset in the operand
+ * @segment: Segment selector register
  * @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)
  */
 struct annotated_op_loc {
 	int reg1;
 	int reg2;
 	int offset;
+	u8 segment;
 	bool mem_ref;
 	bool multi_regs;
+	bool imm;
 };
 
 enum annotated_insn_ops {
@@ -529,6 +533,17 @@ enum annotated_insn_ops {
 	INSN_OP_MAX,
 };
 
+enum annotated_x86_segment {
+	INSN_SEG_NONE = 0,
+
+	INSN_SEG_X86_CS,
+	INSN_SEG_X86_DS,
+	INSN_SEG_X86_ES,
+	INSN_SEG_X86_FS,
+	INSN_SEG_X86_GS,
+	INSN_SEG_X86_SS,
+};
+
 /**
  * struct annotated_insn_loc - Location info of instruction
  * @ops: Array of location info for source and target operands