diff --git a/tools/perf/util/annotate-arch/annotate-arm64.c b/tools/perf/util/annotate-arch/annotate-arm64.c
index bd060a823b76..270f35876511 100644
--- a/tools/perf/util/annotate-arch/annotate-arm64.c
+++ b/tools/perf/util/annotate-arch/annotate-arm64.c
@@ -12,6 +12,7 @@
 #include "../disasm.h"
 #include "../annotate-data.h"
 #include "../debug.h"
+#include "../dso.h"
 #include "../map.h"
 #include "../symbol.h"
 
@@ -727,13 +728,23 @@ static int propagate_load_reg_state(struct type_state *state,
 		u64 ip = dloc->ms->sym->start + dl->al.offset;
 		u64 addr = src_tsr->imm_value + reg_offset;
 		int offset;
+		u8 kind;
+		const char *var_name = NULL;
+
+		/* it might be per-cpu offset */
+		if (dso__kernel(map__dso(dloc->ms->map)) &&
+		    get_global_var_info(dloc, addr, &var_name, &offset) &&
+		    !strcmp(var_name, "__per_cpu_offset"))
+			kind = TSR_KIND_PERCPU_BASE;
+		else
+			kind = TSR_KIND_TYPE;
 
 		if (!get_global_var_type(cu_die, dloc, ip, addr, &offset, &type_die) ||
 		    !die_get_member_type(&type_die, offset, &type_die))
 			return -1;
 
 		tsr->type = type_die;
-		tsr->kind = TSR_KIND_TYPE;
+		tsr->kind = kind;
 		tsr->offset = 0;
 		tsr->imm_value = 0;
 		tsr->ok = true;
@@ -749,6 +760,12 @@ static int propagate_load_reg_state(struct type_state *state,
 		return 0;
 	}
 
+	/*
+	 * If src_tsr->kind is TSR_KIND_PERCPU_BASE, treat it as an array.
+	 * No special handling is needed here; just fall through to retry
+	 * and resolve the type from the second register.
+	 */
+
 load_non_regoff:
 	/* Try another register if any */
 	if (src->multi_regs && src->reg1 != src->reg2 && sreg != src->reg2 &&
@@ -1046,6 +1063,12 @@ static void update_add_insn_state(struct type_state *state,
 		return;
 	}
 
+	/*
+	 * If src_tsr->kind is TSR_KIND_PERCPU_BASE, treat it as an array.
+	 * No special handling is needed here; just fall through to retry
+	 * and resolve the type from the second register.
+	 */
+
 add_non_regoff:
 	/* Try another register if any */
 	if (src->multi_regs && src->reg1 != src->reg2 && sreg != src->reg2 &&
diff --git a/tools/perf/util/annotate-data.c b/tools/perf/util/annotate-data.c
index 43cd09c0662a..b3de1ca688a2 100644
--- a/tools/perf/util/annotate-data.c
+++ b/tools/perf/util/annotate-data.c
@@ -1307,13 +1307,17 @@ int arch_get_reg_offset(const struct arch *arch, struct annotated_op_loc *op_loc
 
 		/*
 		 * For register-based addressing without shift/extension,
-		 * reg2 may be a constant offset. Use its value as the offset
-		 * from the base register.
+		 * derive the offset from the type of reg2.
 		 */
 		reg2 = op_loc->reg1 == breg ? op_loc->reg2 : op_loc->reg1;
-		if (has_reg_type(state, reg2) && state->regs[reg2].ok &&
-			state->regs[reg2].kind == TSR_KIND_CONST) {
-			*offset = (s64)state->regs[reg2].imm_value;
+		if (has_reg_type(state, reg2) && state->regs[reg2].ok) {
+			if (state->regs[reg2].kind == TSR_KIND_CONST)
+				*offset = (s64)state->regs[reg2].imm_value;
+			else if (state->regs[reg2].kind == TSR_KIND_PERCPU_BASE)
+				*offset = 0;  /* it does not contribute to the offset */
+			else
+				return -1;
+
 			return 0;
 		}
 
@@ -1448,11 +1452,31 @@ static enum type_match_result check_matching_type(struct type_state *state,
 	}
 
 	if (state->regs[reg].kind == TSR_KIND_PERCPU_BASE) {
-		u64 var_addr = (s64) offset;
+		u64 var_addr;
 		int var_offset;
 
 		pr_debug_dtp("percpu var");
 
+		if (arch__is_arm64(dloc->arch)) {
+			int reg2;
+
+			if (!retry || !dloc->op->multi_regs ||
+			    dloc->op->reg1 == dloc->op->reg2 ||
+			    dloc->op->extend_type || dloc->op->shift_type)
+				return PERF_TMR_BAIL_OUT;
+
+			reg2 = dloc->op->reg2;
+			if (!has_reg_type(state, reg2) || !state->regs[reg2].ok)
+				return PERF_TMR_NO_TYPE;
+
+			pr_debug_dtp(" : retry\n");
+			retry = false;
+			reg = reg2;
+			goto again;
+		}
+
+		var_addr = (s64) offset;
+
 		if (dloc->op->multi_regs) {
 			int reg2 = dloc->op->reg2;