[PATCH v5 26/26] perf annotate-arm64: Support 'mrs' instruction to track 'current' pointer

[Tengda Wu]

Extend update_insn_state_arm64() to handle the 'mrs' instruction,
enabling the tracking of the 'current' task pointer in the kernel.

On arm64, the kernel uses the 'sp_el0' system register to store the
address of the currently executing 'struct task_struct'. This is
typically accessed via the 'get_current()' inline function, resulting
in the instruction 'mrs xN, sp_el0'.

To resolve the data type of the target register, first verify the
access is to 'sp_el0' within a kernel DSO. Then, locate the
'get_current()' inline function's DWARF Die at the current PC and
extract its return type (which should be 'struct task_struct*').

A real-world example is shown below:

  ffff8000800deee8 <kthread_blkcg>:
  ffff8000800deef0:  mrs  x0, sp_el0    // x0 = current
* ffff8000800deef4:  ldr  w1, [x0, #44]

Before this commit, the type flow starts with no information:

  chk [c] reg0 offset=0x2c ok=0 kind=0 cfa : no type information
  final result: no type information

After this commit, the tracker identifies the 'current' pointer
from the system register:

  mrs [8] sp_el0 -> reg0 type='struct task_struct*'
  chk [c] reg0 offset=0x2c ok=1 kind=1 (struct task_struct*) : Good!
  found by insn track: 0x2c(reg0) type-offset=0x2c
  final result: type='struct task_struct'

Signed-off-by: Li Huafei <lihuafei1@xxxxxxxxxx>
Signed-off-by: Tengda Wu <wutengda@xxxxxxxxxxxxxxx>
---
 .../perf/util/annotate-arch/annotate-arm64.c  | 73 ++++++++++++++++++-
 1 file changed, 71 insertions(+), 2 deletions(-)

diff --git a/tools/perf/util/annotate-arch/annotate-arm64.c b/tools/perf/util/annotate-arch/annotate-arm64.c
index 33fef3d15378..d4b8c8d57dd7 100644
--- a/tools/perf/util/annotate-arch/annotate-arm64.c
+++ b/tools/perf/util/annotate-arch/annotate-arm64.c
@@ -4,6 +4,7 @@
 #include <inttypes.h>
 #include <stdlib.h>
 #include <string.h>
+#include <strings.h>
 #include <linux/ctype.h>
 #include <linux/string.h>
 #include <linux/zalloc.h>
@@ -15,6 +16,7 @@
 #include "../dso.h"
 #include "../map.h"
 #include "../symbol.h"
+#include "../strbuf.h"
 
 struct arch_arm64 {
 	struct arch arch;
@@ -1037,6 +1039,71 @@ static void update_adrp_insn_state(struct type_state *state,
 		     insn_offset, tsr->imm_value, dreg);
 }
 
+static void update_mrs_insn_state(struct type_state *state,
+				  struct data_loc_info *dloc, Dwarf_Die *cu_die,
+				  struct disasm_line *dl,
+				  struct annotated_op_loc *dst)
+{
+	struct type_state_reg *tsr;
+	Dwarf_Die type_die;
+	u32 insn_offset = dl->al.offset;
+	int dreg = dst->reg1;
+	Dwarf_Die func_die;
+	Dwarf_Attribute attr;
+	u64 ip, pc;
+	struct strbuf sb;
+	char *type_name;
+
+	if (!has_reg_type(state, dreg))
+		return;
+
+	tsr = &state->regs[dreg];
+	tsr->copied_from = -1;
+
+	/* Handle case difference: LLVM (SP_EL0) vs objdump (sp_el0) */
+	if (!dso__kernel(map__dso(dloc->ms->map)) ||
+	    strcasecmp(dl->ops.source.raw, "sp_el0")) {
+		invalidate_reg_state(tsr);
+		return;
+	}
+
+	ip = dloc->ms->sym->start + dl->al.offset;
+	pc = map__rip_2objdump(dloc->ms->map, ip);
+
+	/*
+	 * Find the inline function 'get_current()' Dwarf_Die and obtain its
+	 * return value data type, which should be 'struct task_struct*'.
+	 */
+	if (!die_find_inlinefunc(cu_die, pc, &func_die) ||
+	    !die_compare_name(&func_die, "get_current") ||
+	    !dwarf_attr_integrate(&func_die, DW_AT_type, &attr) ||
+	    !dwarf_formref_die(&attr, &type_die)) {
+		invalidate_reg_state(tsr);
+		return;
+	}
+
+	strbuf_init(&sb, 32);
+	die_get_typename_from_type(&type_die, &sb);
+	type_name = strbuf_detach(&sb, NULL);
+
+	if (!type_name || strcmp(type_name, "struct task_struct*")) {
+		invalidate_reg_state(tsr);
+		goto out_free;
+	}
+
+	tsr->type = type_die;
+	tsr->kind = TSR_KIND_TYPE;
+	tsr->offset = 0;
+	tsr->imm_value = 0;
+	tsr->ok = true;
+
+	pr_debug_dtp("mrs [%x] sp_el0 -> reg%d", insn_offset, dreg);
+	pr_debug_type_name(&type_die, tsr->kind);
+
+out_free:
+	free(type_name);
+}
+
 static void update_insn_state_arm64(struct type_state *state,
 				    struct data_loc_info *dloc, Dwarf_Die *cu_die,
 				    struct disasm_line *dl)
@@ -1103,7 +1170,7 @@ static void update_insn_state_arm64(struct type_state *state,
 	 * prevent stale type info from propagating to subsequent instructions.
 	 */
 	if (has_reg_type(state, dst->reg1) && !dst->mem_ref &&
-	    strcmp(dl->ins.name, "adrp") &&
+	    strcmp(dl->ins.name, "mrs") && strcmp(dl->ins.name, "adrp") &&
 	    strcmp(dl->ins.name, "add") && strcmp(dl->ins.name, "mov") &&
 	    !is_standard_load_insn(dl->ins.name)) {
 		pr_debug_dtp("%s [%x] invalidate reg%d",
@@ -1117,7 +1184,9 @@ static void update_insn_state_arm64(struct type_state *state,
 		return;
 	}
 
-	if (!strcmp(dl->ins.name, "adrp"))
+	if (!strcmp(dl->ins.name, "mrs"))
+		update_mrs_insn_state(state, dloc, cu_die, dl, dst);
+	else if (!strcmp(dl->ins.name, "adrp"))
 		update_adrp_insn_state(state, dl, dst);
 	else if (!strcmp(dl->ins.name, "add"))
 		update_add_insn_state(state, dloc, dl, src, dst);
-- 
2.34.1