perf dwarf-aux: More accurate variable type match for breg

Introduces the function is_breg_access_indirect to determine whether a
memory access involving a DW_OP_breg* operation refers to the variable's
value directly or requires dereferencing the variable's type as a
pointer based on the DWARF expression.

Previously, all breg based accesses were assumed to directly access the
variable's value (is_pointer = false).

The is_breg_access_indirect function handles three cases:

1. Base register + offset only: (e.g., DW_OP_breg7 RSP+88) The
   calculated address is the location of the variable. The access is
   direct, so no type dereference is needed. Returns false.

2. Base register + offset, followed by other operations ending in
   DW_OP_stack_value, including DW_OP_deref: (e.g., DW_OP_breg*,
   DW_OP_deref, DW_OP_stack_value) The DWARF expression computes the
   variable's value, but that value requires a dereference. The memory
   access is fetching that value, so no type dereference is needed.
   Returns false.

3. Base register + offset, followed only by DW_OP_stack_value: (e.g.,
   DW_OP_breg13 R13+256, DW_OP_stack_value) This indicates the value at
   the base + offset is the variable's value. Since this value is being
   used as an address in the memory access, the variable's type is
   treated as a pointer and requires a type dereference. Returns true.

The is_pointer argument passed to match_var_offset is now set by
is_breg_access_indirect for breg accesses.

There are more complex expressions that includes multiple operations and
may require additional handling, such as DW_OP_deref without a
DW_OP_stack_value, or including multiple base registers. They are less
common in the Linux kernel dwarf and are skipped in check_allowed_ops.

Reviewed-by: Namhyung Kim <namhyung@kernel.org>
Signed-off-by: Zecheng Li <zecheng@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Xu Liu <xliuprof@google.com>
Link: https://lore.kernel.org/r/CAJUgMyK2wTiEZB__dtgCELmaNGFWhG1j0g9rv_C=cLD6Zq4_5w@mail.gmail.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

1 files changed, 33 insertions, 5 deletions

diff --git a/tools/perf/util/dwarf-aux.c b/tools/perf/util/dwarf-aux.c
index 920054425578..449bc9ad7aff 100644
--- a/tools/perf/util/dwarf-aux.c
+++ b/tools/perf/util/dwarf-aux.c
@@ -1423,6 +1423,34 @@ static bool match_var_offset(Dwarf_Die *die_mem, struct find_var_data *data,
 	return true;
 }
 
+/**
+ * is_breg_access_indirect - Check if breg based access implies type
+ * dereference
+ * @ops: DWARF operations array
+ * @nops: Number of operations in @ops
+ *
+ * Returns true if the DWARF expression evaluates to the variable's
+ * value, so the memory access on that register needs type dereference.
+ * Returns false if the expression evaluates to the variable's address.
+ * This is called after check_allowed_ops.
+ */
+static bool is_breg_access_indirect(Dwarf_Op *ops, size_t nops)
+{
+	/* only the base register */
+	if (nops == 1)
+		return false;
+
+	if (nops == 2 && ops[1].atom == DW_OP_stack_value)
+		return true;
+
+	if (nops == 3 && (ops[1].atom == DW_OP_deref ||
+		ops[1].atom == DW_OP_deref_size) &&
+		ops[2].atom == DW_OP_stack_value)
+		return false;
+	/* unreachable, OP not supported */
+	return false;
+}
+
 /* Only checks direct child DIEs in the given scope. */
 static int __die_find_var_reg_cb(Dwarf_Die *die_mem, void *arg)
 {
@@ -1451,7 +1479,7 @@ static int __die_find_var_reg_cb(Dwarf_Die *die_mem, void *arg)
 		if (data->is_fbreg && ops->atom == DW_OP_fbreg &&
 		    check_allowed_ops(ops, nops) &&
 		    match_var_offset(die_mem, data, data->offset, ops->number,
-				     /*is_pointer=*/false))
+				     is_breg_access_indirect(ops, nops)))
 			return DIE_FIND_CB_END;
 
 		/* Only match with a simple case */
@@ -1463,11 +1491,11 @@ static int __die_find_var_reg_cb(Dwarf_Die *die_mem, void *arg)
 					     /*is_pointer=*/true))
 				return DIE_FIND_CB_END;
 
-			/* Local variables accessed by a register + offset */
+			/* variables accessed by a register + offset */
 			if (ops->atom == (DW_OP_breg0 + data->reg) &&
 			    check_allowed_ops(ops, nops) &&
 			    match_var_offset(die_mem, data, data->offset, ops->number,
-					     /*is_pointer=*/false))
+					     is_breg_access_indirect(ops, nops)))
 				return DIE_FIND_CB_END;
 		} else {
 			/* pointer variables saved in a register 32 or above */
@@ -1477,11 +1505,11 @@ static int __die_find_var_reg_cb(Dwarf_Die *die_mem, void *arg)
 					     /*is_pointer=*/true))
 				return DIE_FIND_CB_END;
 
-			/* Local variables accessed by a register + offset */
+			/* variables accessed by a register + offset */
 			if (ops->atom == DW_OP_bregx && data->reg == ops->number &&
 			    check_allowed_ops(ops, nops) &&
 			    match_var_offset(die_mem, data, data->offset, ops->number2,
-					     /*is_poitner=*/false))
+					     is_breg_access_indirect(ops, nops)))
 				return DIE_FIND_CB_END;
 		}
 	}