Currently every function is checked for its parameters to identify whether
the signature changed or not. If signature indeed changed, pahole may do
some adjustment for parameters for true signatures.

In clang, any function with the following attribute
      DW_AT_calling_convention        (DW_CC_nocall)
indicates this function having signature changed.
pahole can take advantage of this to avoid parameter checking if
DW_AT_calling_convention is not DW_CC_nocall.

But more importantly, DW_CC_nocall can identify signature-changed functions
and parameters can be checked one-after-another to create the true
signatures. Otherwise, it takes more effort to identify whether a
function has signature changed or not. For example, for funciton
  __bpf_kfunc static void bbr_main(struct sock *sk, u32 ack, int flag,
     const struct rate_sample *rs) { ... }
and bbr_main() is a callback function in
  .cong_control   = bbr_main
in 'struct tcp_congestion_ops tcp_bbr_cong_ops'.
In the above bbr_main(...), parameter 'ack' and 'flag' are not used.
The following are some details:

0x0a713b8d:     DW_TAG_formal_parameter
                  DW_AT_location        (indexed (0x28) loclist = 0x0166d452:
                     [0xffffffff83e77fd9, 0xffffffff83e78016): DW_OP_reg5 RDI
                     ...
                  DW_AT_name    ("sk")
                  DW_AT_type    (0x0a6f5b2b "sock *")
                  ...

0x0a713b98:     DW_TAG_formal_parameter
                  DW_AT_name    ("ack")
                  DW_AT_type    (0x0a6f58fd "u32")
                  ...

0x0a713ba2:     DW_TAG_formal_parameter
                  DW_AT_name    ("flag")
                  DW_AT_type    (0x0a6f57d1 "int")
                  ...

0x0a713bac:     DW_TAG_formal_parameter
                  DW_AT_location        (indexed (0x29) loclist = 0x0166d4a8:
                     [0xffffffff83e77fd9, 0xffffffff83e78016): DW_OP_reg2 RCX
                     ...
                  DW_AT_name    ("rs")
                  DW_AT_type    (0x0a710da5 "const rate_sample *")
                  DW_AT_decl_line       (1027)

Some analysis for the above dwarf can conclude that the 'ark' and 'flag'
may be related to RSI and RDX, considering the last one is RCX. Basically this
requires all parameters are available to collectively decide whether the
true signature can be found or not. In such case, DW_CC_nocall can make things
easier as parameter can be checked one after another.

For a clang built bpf-next kernel, in non-LTO setup, the number of kernel functions
is 69103 and the number of signature changed functions is 875, based on
      DW_AT_calling_convention        (DW_CC_nocall)
indication.

Among 875 signature changed functions, after this patch, 495 functions
can have proper true signatures, mostly due to simple dead argument
elimination. The number of remaining functions, which cannot get the
true signature, is 379. They will be addressed in the subsequent commits.

In llvm23, I implemented [1] which added DW_CC_nocall for ArgumentPromotion pass.
This compiler pass can add additional DW_CC_nocall cases for the following
compilation:
      - Flag -O3 or FullLTO
So once llvm23 available, we may have more DW_CC_nocall cases, hence more
potential true signatures if the kernel is built with -O3 or
with FullLTO (CONFIG_LTO_CLANG_FULL).

  [1] https://github.com/llvm/llvm-project/pull/178973

Signed-off-by: Yonghong Song <yonghong.song@linux.dev>
---
 dwarf_loader.c | 70 ++++++++++++++++++++++++++++++++++++++++++--------
 dwarves.h      |  1 +
 2 files changed, 60 insertions(+), 11 deletions(-)

diff --git a/dwarf_loader.c b/dwarf_loader.c
index 16fb7be..21f8bf1 100644
--- a/dwarf_loader.c
+++ b/dwarf_loader.c
@@ -1190,6 +1190,10 @@ static ptrdiff_t __dwarf_getlocations(Dwarf_Attribute *attr,
 	return ret;
 }
 
+struct func_info {
+	bool signature_changed;
+};
+
 /* For DW_AT_location 'attr':
  * - if first location is DW_OP_regXX with expected number, return the register;
  *   otherwise save the register for later return
@@ -1252,7 +1256,8 @@ out:
 }
 
 static struct parameter *parameter__new(Dwarf_Die *die, struct cu *cu,
-					struct conf_load *conf, int param_idx)
+					struct conf_load *conf, int param_idx,
+					struct func_info *info)
 {
 	struct parameter *parm = tag__alloc(cu, sizeof(*parm));
 
@@ -1263,8 +1268,12 @@ static struct parameter *parameter__new(Dwarf_Die *die, struct cu *cu,
 		tag__init(&parm->tag, cu, die);
 		parm->name = attr_string(die, DW_AT_name, conf);
 		parm->idx = param_idx;
-		if (param_idx >= cu->nr_register_params || param_idx < 0)
+		if (param_idx < 0)
 			return parm;
+		if (!info->signature_changed) {
+			if (cu->producer_clang || param_idx >= cu->nr_register_params)
+				return parm;
+		}
 		/* Parameters which use DW_AT_abstract_origin to point at
 		 * the original parameter definition (with no name in the DIE)
 		 * are the result of later DWARF generation during compilation
@@ -1337,7 +1346,7 @@ static int formal_parameter_pack__load_params(struct formal_parameter_pack *pack
 			continue;
 		}
 
-		struct parameter *param = parameter__new(die, cu, conf, -1);
+		struct parameter *param = parameter__new(die, cu, conf, -1, NULL);
 
 		if (param == NULL)
 			return -1;
@@ -1502,6 +1511,29 @@ static struct ftype *ftype__new(Dwarf_Die *die, struct cu *cu)
 	return ftype;
 }
 
+static bool function__signature_changed(struct function *func, Dwarf_Die *die)
+{
+	/* The inlined DW_TAG_subprogram typically has the original source type for
+	 * abstract origin of a concrete function with address range, inlined subroutine,
+	 * or call site.
+	 */
+	if (func->inlined)
+		return false;
+
+	if (!func->abstract_origin)
+		return attr_numeric(die, DW_AT_calling_convention) == DW_CC_nocall;
+
+	Dwarf_Attribute attr;
+	if (dwarf_attr(die, DW_AT_abstract_origin, &attr)) {
+		Dwarf_Die origin;
+		if (dwarf_formref_die(&attr, &origin))
+			return attr_numeric(&origin, DW_AT_calling_convention) == DW_CC_nocall;
+	}
+
+	/* This should not happen */
+	return false;
+}
+
 static struct function *function__new(Dwarf_Die *die, struct cu *cu, struct conf_load *conf)
 {
 	struct function *func = tag__alloc(cu, sizeof(*func));
@@ -1800,9 +1832,9 @@ static struct tag *die__create_new_parameter(Dwarf_Die *die,
 					     struct ftype *ftype,
 					     struct lexblock *lexblock,
 					     struct cu *cu, struct conf_load *conf,
-					     int param_idx)
+					     int param_idx, struct func_info *info)
 {
-	struct parameter *parm = parameter__new(die, cu, conf, param_idx);
+	struct parameter *parm = parameter__new(die, cu, conf, param_idx, info);
 
 	if (parm == NULL)
 		return NULL;
@@ -1889,7 +1921,7 @@ static struct tag *die__create_new_subroutine_type(Dwarf_Die *die,
 			tag__print_not_supported(die);
 			continue;
 		case DW_TAG_formal_parameter:
-			tag = die__create_new_parameter(die, ftype, NULL, cu, conf, -1);
+			tag = die__create_new_parameter(die, ftype, NULL, cu, conf, -1, NULL);
 			break;
 		case DW_TAG_unspecified_parameters:
 			ftype->unspec_parms = 1;
@@ -2118,7 +2150,8 @@ out_enomem:
 }
 
 static int die__process_function(Dwarf_Die *die, struct ftype *ftype,
-				  struct lexblock *lexblock, struct cu *cu, struct conf_load *conf);
+				 struct lexblock *lexblock, struct cu *cu, struct conf_load *conf,
+				 struct func_info *info);
 
 static int die__create_new_lexblock(Dwarf_Die *die,
 				    struct cu *cu, struct lexblock *father, struct conf_load *conf)
@@ -2126,7 +2159,7 @@ static int die__create_new_lexblock(Dwarf_Die *die,
 	struct lexblock *lexblock = lexblock__new(die, cu);
 
 	if (lexblock != NULL) {
-		if (die__process_function(die, NULL, lexblock, cu, conf) != 0)
+		if (die__process_function(die, NULL, lexblock, cu, conf, NULL) != 0)
 			goto out_delete;
 	}
 	if (father != NULL)
@@ -2246,7 +2279,8 @@ static struct tag *die__create_new_inline_expansion(Dwarf_Die *die,
 }
 
 static int die__process_function(Dwarf_Die *die, struct ftype *ftype,
-				 struct lexblock *lexblock, struct cu *cu, struct conf_load *conf)
+				 struct lexblock *lexblock, struct cu *cu, struct conf_load *conf,
+				 struct func_info *info)
 {
 	int param_idx = 0;
 	Dwarf_Die child;
@@ -2320,7 +2354,7 @@ static int die__process_function(Dwarf_Die *die, struct ftype *ftype,
 			continue;
 		}
 		case DW_TAG_formal_parameter:
-			tag = die__create_new_parameter(die, ftype, lexblock, cu, conf, param_idx++);
+			tag = die__create_new_parameter(die, ftype, lexblock, cu, conf, param_idx++, info);
 			break;
 		case DW_TAG_variable:
 			tag = die__create_new_variable(die, cu, conf, 0);
@@ -2391,9 +2425,10 @@ out_enomem:
 static struct tag *die__create_new_function(Dwarf_Die *die, struct cu *cu, struct conf_load *conf)
 {
 	struct function *function = function__new(die, cu, conf);
+	struct func_info info = { function__signature_changed(function, die) };
 
 	if (function != NULL &&
-	    die__process_function(die, &function->proto, &function->lexblock, cu, conf) != 0) {
+	    die__process_function(die, &function->proto, &function->lexblock, cu, conf, &info) != 0) {
 		function__delete(function, cu);
 		function = NULL;
 	}
@@ -3045,6 +3080,17 @@ static unsigned long long dwarf_tag__orig_id(const struct tag *tag,
 	return cu->extra_dbg_info ? dtag->id : 0;
 }
 
+static bool attr_producer_clang(Dwarf_Die *die)
+{
+	const char *producer;
+
+	producer = attr_string(die, DW_AT_producer, NULL);
+	if (!producer)
+		return false;
+
+	return !!strstr(producer, "clang");
+}
+
 struct debug_fmt_ops dwarf__ops;
 
 static int die__process(Dwarf_Die *die, struct cu *cu, struct conf_load *conf)
@@ -3082,6 +3128,7 @@ static int die__process(Dwarf_Die *die, struct cu *cu, struct conf_load *conf)
 	}
 
 	cu->language = attr_numeric(die, DW_AT_language);
+	cu->producer_clang = attr_producer_clang(die);
 
 	if (conf->early_cu_filter)
 		cu = conf->early_cu_filter(cu);
@@ -3841,6 +3888,7 @@ static int cus__merge_and_process_cu(struct cus *cus, struct conf_load *conf,
 			cu->priv = dcu;
 			cu->dfops = &dwarf__ops;
 			cu->language = attr_numeric(cu_die, DW_AT_language);
+			cu->producer_clang = attr_producer_clang(cu_die);
 			cus__add(cus, cu);
 		}
 
diff --git a/dwarves.h b/dwarves.h
index d7c6474..4cabab0 100644
--- a/dwarves.h
+++ b/dwarves.h
@@ -302,6 +302,7 @@ struct cu {
 	uint8_t		 has_addr_info:1;
 	uint8_t		 uses_global_strings:1;
 	uint8_t		 little_endian:1;
+	uint8_t		 producer_clang:1;
 	uint8_t		 nr_register_params;
 	int		 register_params[ARCH_MAX_REGISTER_PARAMS];
 	int		 functions_saved;
-- 
2.52.0

For llvm dwarf, the dead argument may be in the middle of
DW_TAG_subprogram. So we introduce skip_idx in order to
match expected registers properly.

For example:
  0x00042897:   DW_TAG_subprogram
                  DW_AT_name      ("create_dev")
                  DW_AT_calling_convention        (DW_CC_nocall)
                  DW_AT_type      (0x0002429a "int")
                  ...

  0x000428ab:     DW_TAG_formal_parameter
                    DW_AT_name    ("name")
                    DW_AT_type    (0x000242ed "char *")
                    ...

  0x000428b5:     DW_TAG_formal_parameter
                    DW_AT_location        (indexed (0x3f) loclist = 0x000027f8:
                       [0xffffffff87681370, 0xffffffff8768137a): DW_OP_reg5 RDI
                       [0xffffffff8768137a, 0xffffffff87681392): DW_OP_reg3 RBX
                       [0xffffffff87681392, 0xffffffff876813ae): DW_OP_entry_value(DW_OP_reg5 RDI), DW_OP_stack_value)
                    DW_AT_name    ("dev")
                    DW_AT_type    (0x00026859 "dev_t")
                    ...

With skip_idx, we can identify that the second original argument
'dev' becomes the first one after optimization.

Signed-off-by: Yonghong Song <yonghong.song@linux.dev>
---
 dwarf_loader.c | 19 +++++++++++++++++--
 1 file changed, 17 insertions(+), 2 deletions(-)

diff --git a/dwarf_loader.c b/dwarf_loader.c
index 21f8bf1..a6e6587 100644
--- a/dwarf_loader.c
+++ b/dwarf_loader.c
@@ -1192,6 +1192,7 @@ static ptrdiff_t __dwarf_getlocations(Dwarf_Attribute *attr,
 
 struct func_info {
 	bool signature_changed;
+	int skip_idx;
 };
 
 /* For DW_AT_location 'attr':
@@ -1264,6 +1265,7 @@ static struct parameter *parameter__new(Dwarf_Die *die, struct cu *cu,
 	if (parm != NULL) {
 		bool has_const_value;
 		Dwarf_Attribute attr;
+		int reg_idx;
 
 		tag__init(&parm->tag, cu, die);
 		parm->name = attr_string(die, DW_AT_name, conf);
@@ -1273,7 +1275,18 @@ static struct parameter *parameter__new(Dwarf_Die *die, struct cu *cu,
 		if (!info->signature_changed) {
 			if (cu->producer_clang || param_idx >= cu->nr_register_params)
 				return parm;
+		} else {
+			/* if true_signature is not enabled, mark parameter as
+			 * unexpected_reg since there is a skipped parameter before.
+			 */
+			if (!conf->true_signature && info->skip_idx) {
+				parm->unexpected_reg = 1;
+				return parm;
+			}
 		}
+		reg_idx = param_idx - info->skip_idx;
+		if (reg_idx >= cu->nr_register_params)
+			return parm;
 		/* Parameters which use DW_AT_abstract_origin to point at
 		 * the original parameter definition (with no name in the DIE)
 		 * are the result of later DWARF generation during compilation
@@ -1311,7 +1324,7 @@ static struct parameter *parameter__new(Dwarf_Die *die, struct cu *cu,
 		parm->has_loc = dwarf_attr(die, DW_AT_location, &attr) != NULL;
 
 		if (parm->has_loc) {
-			int expected_reg = cu->register_params[param_idx];
+			int expected_reg = cu->register_params[reg_idx];
 			int actual_reg = parameter__reg(&attr, expected_reg);
 
 			if (actual_reg < 0)
@@ -1324,8 +1337,10 @@ static struct parameter *parameter__new(Dwarf_Die *die, struct cu *cu,
 				 * contents.
 				 */
 				parm->unexpected_reg = 1;
-		} else if (has_const_value) {
+		} else if (has_const_value || info->signature_changed) {
 			parm->optimized = 1;
+			if (info->signature_changed)
+				info->skip_idx++;
 		}
 	}
 
-- 
2.52.0

Later on, More macro return values will be implemented to make
code easier to understand.

Signed-off-by: Yonghong Song <yonghong.song@linux.dev>
---
 dwarf_loader.c | 8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)

diff --git a/dwarf_loader.c b/dwarf_loader.c
index a6e6587..7b3f551 100644
--- a/dwarf_loader.c
+++ b/dwarf_loader.c
@@ -1195,12 +1195,14 @@ struct func_info {
 	int skip_idx;
 };
 
+#define	PARM_DEFAULT_FAIL	-1
+
 /* For DW_AT_location 'attr':
  * - if first location is DW_OP_regXX with expected number, return the register;
  *   otherwise save the register for later return
  * - if location DW_OP_entry_value(DW_OP_regXX) with expected number is in the
  *   list, return the register; otherwise save register for later return
- * - otherwise if no register was found for locations, return -1.
+ * - otherwise if no register was found for locations, return PARM_DEFAULT_FAIL.
  */
 static int parameter__reg(Dwarf_Attribute *attr, int expected_reg)
 {
@@ -1210,7 +1212,7 @@ static int parameter__reg(Dwarf_Attribute *attr, int expected_reg)
 	size_t exprlen, entry_len;
 	ptrdiff_t offset = 0;
 	int loc_num = -1;
-	int ret = -1;
+	int ret = PARM_DEFAULT_FAIL;
 
 	/* use libdw__lock as dwarf_getlocation(s) has concurrency issues
 	 * when libdw is not compiled with experimental --enable-thread-safety
@@ -1327,7 +1329,7 @@ static struct parameter *parameter__new(Dwarf_Die *die, struct cu *cu,
 			int expected_reg = cu->register_params[reg_idx];
 			int actual_reg = parameter__reg(&attr, expected_reg);
 
-			if (actual_reg < 0)
+			if (actual_reg == PARM_DEFAULT_FAIL)
 				parm->optimized = 1;
 			else if (expected_reg >= 0 && expected_reg != actual_reg)
 				/* mark parameters that use an unexpected
-- 
2.52.0

DW_OP_fbreg means the parameter value will be stored on the
stack. So the corresponding parameter register is not used.
For example:

  0x071f7717:   DW_TAG_subprogram
                  DW_AT_name      ("jent_health_failure")
                  DW_AT_calling_convention        (DW_CC_nocall)
                  DW_AT_type      (0x071f7626 "unsigned int")
                  ...

  0x071f7728:     DW_TAG_formal_parameter
                    DW_AT_location        (DW_OP_fbreg -8)
                    DW_AT_name    ("ec")
                    DW_AT_type    (0x071f7ab6 "rand_data *")
                    ...

  0x071f7734:     NULL

In the above, the parameter 'ec' type is a pointer so it perfectly fits
into a register. But the location uses 'DW_OP_fbreg -8' which prevents
from generating a function with true signatures.

Signed-off-by: Yonghong Song <yonghong.song@linux.dev>
---
 dwarf_loader.c | 18 +++++++++++++++---
 1 file changed, 15 insertions(+), 3 deletions(-)

diff --git a/dwarf_loader.c b/dwarf_loader.c
index 7b3f551..c259417 100644
--- a/dwarf_loader.c
+++ b/dwarf_loader.c
@@ -1196,6 +1196,7 @@ struct func_info {
 };
 
 #define	PARM_DEFAULT_FAIL	-1
+#define	PARM_UNEXPECTED		-2
 
 /* For DW_AT_location 'attr':
  * - if first location is DW_OP_regXX with expected number, return the register;
@@ -1204,7 +1205,8 @@ struct func_info {
  *   list, return the register; otherwise save register for later return
  * - otherwise if no register was found for locations, return PARM_DEFAULT_FAIL.
  */
-static int parameter__reg(Dwarf_Attribute *attr, int expected_reg)
+static int parameter__reg(Dwarf_Attribute *attr, int expected_reg, struct conf_load *conf,
+			  struct func_info *info)
 {
 	Dwarf_Addr base, start, end;
 	Dwarf_Op *expr, *entry_ops;
@@ -1240,6 +1242,16 @@ static int parameter__reg(Dwarf_Attribute *attr, int expected_reg)
 			if (ret == expected_reg)
 				goto out;
 			break;
+		case DW_OP_fbreg:
+			/* The locaiton like
+			 *   DW_AT_location        (DW_OP_fbreg +<num>)
+			 * indicates that the parameter is on the stack. But it is possible
+			 * that the parameter can fit in register(s). So conservatively
+			 * mark this parameter not suitable for true signatures.
+			 */
+			if (info->signature_changed && conf->true_signature)
+				ret = PARM_UNEXPECTED;
+			break;
 		/* match DW_OP_entry_value(DW_OP_regXX) at any location */
 		case DW_OP_entry_value:
 		case DW_OP_GNU_entry_value:
@@ -1327,11 +1339,11 @@ static struct parameter *parameter__new(Dwarf_Die *die, struct cu *cu,
 
 		if (parm->has_loc) {
 			int expected_reg = cu->register_params[reg_idx];
-			int actual_reg = parameter__reg(&attr, expected_reg);
+			int actual_reg = parameter__reg(&attr, expected_reg, conf, info);
 
 			if (actual_reg == PARM_DEFAULT_FAIL)
 				parm->optimized = 1;
-			else if (expected_reg >= 0 && expected_reg != actual_reg)
+			else if (actual_reg == PARM_UNEXPECTED || (expected_reg >= 0 && expected_reg != actual_reg))
 				/* mark parameters that use an unexpected
 				 * register to hold a parameter; these will
 				 * be problematic for users of BTF as they
-- 
2.52.0

The change does not change any functionalities. But it allows
DW_OP_stack_value preserved in longer location list for future
parameter checking.

Signed-off-by: Yonghong Song <yonghong.song@linux.dev>
---
 dwarf_loader.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/dwarf_loader.c b/dwarf_loader.c
index c259417..117cd49 100644
--- a/dwarf_loader.c
+++ b/dwarf_loader.c
@@ -1227,7 +1227,7 @@ static int parameter__reg(Dwarf_Attribute *attr, int expected_reg, struct conf_l
 		 * DW_OP_stack_value instructs interpreter to pop current value from
 		 * DWARF expression evaluation stack, and thus is not important here.
 		 */
-		if (exprlen > 1 && expr[exprlen - 1].atom == DW_OP_stack_value)
+		if (exprlen == 2 && expr[exprlen - 1].atom == DW_OP_stack_value)
 			exprlen--;
 
 		if (exprlen != 1)
-- 
2.52.0

The following is an example:

0x00899a78:   DW_TAG_subprogram
                DW_AT_low_pc    (0xffffffff879be480)
                DW_AT_high_pc   (0xffffffff879beac4)
                DW_AT_frame_base        (DW_OP_reg7 RSP)
                DW_AT_call_all_calls    (true)
                DW_AT_name      ("split_mem_range")
                DW_AT_decl_file ("/home/yhs/work/bpf-next/arch/x86/mm/init.c")
                DW_AT_decl_line (401)
                DW_AT_prototyped        (true)
                DW_AT_calling_convention        (DW_CC_nocall)
                DW_AT_type      (0x008861cb "int")

0x00899a8c:     DW_TAG_formal_parameter
                  DW_AT_location        (indexed (0x3e) loclist = 0x000b2195:
                     [0xffffffff879be485, 0xffffffff879be49a): DW_OP_reg5 RDI
                     [0xffffffff879be49a, 0xffffffff879beac4): DW_OP_breg7 RSP+0)
                  DW_AT_name    ("mr")
                  DW_AT_decl_file       ("/home/yhs/work/bpf-next/arch/x86/mm/init.c")
                  DW_AT_decl_line       (401)
                  DW_AT_type    (0x00899c88 "map_range *")

0x00899a98:     DW_TAG_formal_parameter
                  DW_AT_location        (indexed (0x41) loclist = 0x000b21d4:
                     [0xffffffff879be480, 0xffffffff879be554): DW_OP_consts +0, DW_OP_stack_value
                     [0xffffffff879be554, 0xffffffff879be56d): DW_OP_consts +1, DW_OP_stack_value
                     [0xffffffff879be56d, 0xffffffff879be572): DW_OP_reg2 RCX
                     [0xffffffff879be572, 0xffffffff879be638): DW_OP_breg7 RSP+8
                     [0xffffffff879be638, 0xffffffff879be63d): DW_OP_reg0 RAX
                     [0xffffffff879be63d, 0xffffffff879be6ef): DW_OP_breg7 RSP+8
                     [0xffffffff879be6ef, 0xffffffff879be6f5): DW_OP_reg14 R14
                     [0xffffffff879be6f5, 0xffffffff879be6fd): DW_OP_breg7 RSP+8
                     [0xffffffff879be6fd, 0xffffffff879be879): DW_OP_reg14 R14
                     [0xffffffff879be879, 0xffffffff879be931): DW_OP_reg12 R12
                     [0xffffffff879be955, 0xffffffff879be961): DW_OP_reg14 R14
                     [0xffffffff879be961, 0xffffffff879be966): DW_OP_reg12 R12
                     [0xffffffff879be966, 0xffffffff879be976): DW_OP_reg14 R14
                     [0xffffffff879be976, 0xffffffff879be9df): DW_OP_reg12 R12
                     [0xffffffff879be9df, 0xffffffff879be9e5): DW_OP_reg14 R14
                     [0xffffffff879be9fc, 0xffffffff879bea24): DW_OP_consts +0, DW_OP_stack_value
                     [0xffffffff879bea24, 0xffffffff879bea74): DW_OP_breg7 RSP+8
                     [0xffffffff879bea74, 0xffffffff879beac4): DW_OP_reg14 R14)
                  DW_AT_name    ("nr_range")
                  DW_AT_decl_file       ("/home/yhs/work/bpf-next/arch/x86/mm/init.c")
                  DW_AT_decl_line       (401)
                  DW_AT_type    (0x008861cb "int")

0x00899aa4:     DW_TAG_formal_parameter
                  DW_AT_location        (indexed (0x3f) loclist = 0x000b21a7:
                     [0xffffffff879be485, 0xffffffff879be4a4): DW_OP_reg4 RSI
                     [0xffffffff879be4a4, 0xffffffff879be4e6): DW_OP_reg12 R12
                     [0xffffffff879be4e6, 0xffffffff879beac4): DW_OP_entry_value(DW_OP_reg4 RSI), DW_OP_stack_value)
                  DW_AT_name    ("start")
                  DW_AT_decl_file       ("/home/yhs/work/bpf-next/arch/x86/mm/init.c")
                  DW_AT_decl_line       (402)
                  DW_AT_type    (0x008861cf "unsigned long")

0x00899ab0:     DW_TAG_formal_parameter
                  DW_AT_location        (indexed (0x40) loclist = 0x000b21c2:
                     [0xffffffff879be485, 0xffffffff879be4a9): DW_OP_reg1 RDX
                     [0xffffffff879be4a9, 0xffffffff879beac4): DW_OP_breg7 RSP+32)
                  DW_AT_name    ("end")
                  DW_AT_decl_file       ("/home/yhs/work/bpf-next/arch/x86/mm/init.c")
                  DW_AT_decl_line       (403)
                  DW_AT_type    (0x008861cf "unsigned long")

The parameter 'nr_range' is a constant and won't consume any ABI register.

Signed-off-by: Yonghong Song <yonghong.song@linux.dev>
---
 dwarf_loader.c | 46 ++++++++++++++++++++++++++++++++++++++++++----
 1 file changed, 42 insertions(+), 4 deletions(-)

diff --git a/dwarf_loader.c b/dwarf_loader.c
index 117cd49..e10e5d8 100644
--- a/dwarf_loader.c
+++ b/dwarf_loader.c
@@ -1197,6 +1197,21 @@ struct func_info {
 
 #define	PARM_DEFAULT_FAIL	-1
 #define	PARM_UNEXPECTED		-2
+#define	PARM_OPTIMIZED_OUT	-3
+#define	PARM_CONTINUE		-4
+
+static int parameter__multi_exprs(Dwarf_Op *expr, int loc_num) {
+	switch (expr[0].atom) {
+	case DW_OP_lit0 ... DW_OP_lit31:
+	case DW_OP_constu:
+	case DW_OP_consts:
+		if (loc_num != 0)
+			break;
+		return PARM_OPTIMIZED_OUT;
+	}
+
+	return PARM_CONTINUE;
+}
 
 /* For DW_AT_location 'attr':
  * - if first location is DW_OP_regXX with expected number, return the register;
@@ -1230,8 +1245,17 @@ static int parameter__reg(Dwarf_Attribute *attr, int expected_reg, struct conf_l
 		if (exprlen == 2 && expr[exprlen - 1].atom == DW_OP_stack_value)
 			exprlen--;
 
-		if (exprlen != 1)
-			continue;
+		if (exprlen != 1) {
+			if (!info->signature_changed || !conf->true_signature)
+				continue;
+
+			int res;
+			res = parameter__multi_exprs(expr, loc_num);
+			if (res == PARM_CONTINUE)
+				continue;
+			ret = res;
+			goto out;
+		}
 
 		switch (expr->atom) {
 		/* match DW_OP_regXX at first location */
@@ -1252,6 +1276,16 @@ static int parameter__reg(Dwarf_Attribute *attr, int expected_reg, struct conf_l
 			if (info->signature_changed && conf->true_signature)
 				ret = PARM_UNEXPECTED;
 			break;
+		case DW_OP_lit0 ... DW_OP_lit31:
+		case DW_OP_constu:
+		case DW_OP_consts:
+			if (info->signature_changed && conf->true_signature) {
+				if (loc_num != 0)
+					break;
+				ret = PARM_OPTIMIZED_OUT;
+				goto out;
+			}
+			break;
 		/* match DW_OP_entry_value(DW_OP_regXX) at any location */
 		case DW_OP_entry_value:
 		case DW_OP_GNU_entry_value:
@@ -1341,9 +1375,12 @@ static struct parameter *parameter__new(Dwarf_Die *die, struct cu *cu,
 			int expected_reg = cu->register_params[reg_idx];
 			int actual_reg = parameter__reg(&attr, expected_reg, conf, info);
 
-			if (actual_reg == PARM_DEFAULT_FAIL)
+			if (actual_reg == PARM_DEFAULT_FAIL) {
+				parm->optimized = 1;
+			} else if (actual_reg == PARM_OPTIMIZED_OUT) {
 				parm->optimized = 1;
-			else if (actual_reg == PARM_UNEXPECTED || (expected_reg >= 0 && expected_reg != actual_reg))
+				info->skip_idx++;
+			} else if (actual_reg == PARM_UNEXPECTED || (expected_reg >= 0 && expected_reg != actual_reg)) {
 				/* mark parameters that use an unexpected
 				 * register to hold a parameter; these will
 				 * be problematic for users of BTF as they
@@ -1351,6 +1388,7 @@ static struct parameter *parameter__new(Dwarf_Die *die, struct cu *cu,
 				 * contents.
 				 */
 				parm->unexpected_reg = 1;
+			}
 		} else if (has_const_value || info->signature_changed) {
 			parm->optimized = 1;
 			if (info->signature_changed)
-- 
2.52.0

The corresponding type is checked for the parameter.
If the parameter size is less or equal to size of long,
the argument should match the corresponding ABI register.
For example:

0x0aba0808:   DW_TAG_subprogram
                DW_AT_name      ("addrconf_ifdown")
                DW_AT_calling_convention        (DW_CC_nocall)
                DW_AT_type      (0x0ab7d8e9 "int")
		...

0x0aba082b:     DW_TAG_formal_parameter
                  DW_AT_location        (indexed (0x32b) loclist = 0x016eabcd:
                     [0xffffffff83f6fef9, 0xffffffff83f6ff98): DW_OP_reg5 RDI
                     [0xffffffff83f6ff98, 0xffffffff83f70080): DW_OP_reg12 R12
                     [0xffffffff83f70080, 0xffffffff83f70111): DW_OP_breg7 RSP+112
                     [0xffffffff83f70111, 0xffffffff83f7014f): DW_OP_reg12 R12
                     [0xffffffff83f7014f, 0xffffffff83f7123c): DW_OP_breg7 RSP+112
                     [0xffffffff83f7123c, 0xffffffff83f7128c): DW_OP_entry_value(DW_OP_reg5 RDI), DW_OP_stack_value
                     [0xffffffff83f7128c, 0xffffffff83f712a9): DW_OP_reg12 R12
                     [0xffffffff83f712a9, 0xffffffff83f712cd): DW_OP_breg7 RSP+112
                     [0xffffffff83f712cd, 0xffffffff83f712d2): DW_OP_entry_value(DW_OP_reg5 RDI), DW_OP_stack_value
                     [0xffffffff83f712d2, 0xffffffff83f713dd): DW_OP_breg7 RSP+112)
                  DW_AT_name    ("dev")
                  DW_AT_type    (0x0ab7cb7d "net_device *")
		  ...

0x0aba0836:     DW_TAG_formal_parameter
                  DW_AT_location        (indexed (0x32c) loclist = 0x016eac39:
                     [0xffffffff83f6fef9, 0xffffffff83f6ff15): DW_OP_breg4 RSI+0, DW_OP_constu 0xffffffff, DW_OP_and, DW_OP_convert (0x0ab7b571) "DW_ATE_unsigned_1", DW_OP_convert (0x0ab7b576) "DW_ATE_unsigned_8", DW_OP_stack_value
                     [0xffffffff83f6ff15, 0xffffffff83f7127c): DW_OP_breg7 RSP+36, DW_OP_deref_size 0x4, DW_OP_convert (0x0ab7b571) "DW_ATE_unsigned_1", DW_OP_convert (0x0ab7b576) "DW_ATE_unsigned_8", DW_OP_stack_value
                     [0xffffffff83f7128c, 0xffffffff83f713dd): DW_OP_breg7 RSP+36, DW_OP_deref_size 0x4, DW_OP_convert (0x0ab7b571) "DW_ATE_unsigned_1", DW_OP_convert (0x0ab7b576) "DW_ATE_unsigned_8", DW_OP_stack_value)
                  DW_AT_name    ("unregister")
                  DW_AT_type    (0x0ab7c933 "bool")
		  ...

The parameter 'unregister' is the second argument which matches ABI register RSI.
So the function "addrconf_ifdown" signature is valid.

If the parameter size is '2 x size_of_long', more handling is necessary, e.g., below:

0x0a01e174:   DW_TAG_subprogram
                DW_AT_name      ("check_zeroed_sockptr")
                DW_AT_calling_convention        (DW_CC_nocall)
                DW_AT_type      (0x09fead35 "int")
		...

0x0a01e187:     DW_TAG_formal_parameter
                  DW_AT_location        (indexed (0x5b6) loclist = 0x0157f03f:
                     [0xffffffff83c941c0, 0xffffffff83c941c4): DW_OP_reg5 RDI, DW_OP_piece 0x8, DW_OP_reg4 RSI, DW_OP_piece 0x1
                     [0xffffffff83c941c4, 0xffffffff83c941cc): DW_OP_piece 0x8, DW_OP_reg4 RSI, DW_OP_piece 0x1
                     [0xffffffff83c941e1, 0xffffffff83c941e4): DW_OP_piece 0x8, DW_OP_reg4 RSI, DW_OP_piece 0x1)
                  DW_AT_name    ("src")
                  DW_AT_type    (0x09ff832d "sockptr_t")
		  ...

0x0a01e193:     DW_TAG_formal_parameter
                  DW_AT_const_value     (64)
                  DW_AT_name    ("offset")
                  DW_AT_type    (0x09fee984 "size_t")
		  ...

0x0a01e19e:     DW_TAG_formal_parameter
                  DW_AT_location        (indexed (0x5b7) loclist = 0x0157f06b:
                     [0xffffffff83c941c0, 0xffffffff83c941d1): DW_OP_reg1 RDX
                     [0xffffffff83c941d1, 0xffffffff83c941e1): DW_OP_entry_value(DW_OP_reg1 RDX), DW_OP_stack_value
                     [0xffffffff83c941e1, 0xffffffff83c941e9): DW_OP_reg1 RDX)
                  DW_AT_name    ("size")
                  DW_AT_type    (0x09fee984 "size_t")
		  ...

The first parameter 'src' will take two ABI registers. This patch correctly detects such a pattern
to construct the true signature.

However, it is possible that only one 'size_of_long' is used from '2 x size_of_long'. For example

0x019520c6:   DW_TAG_subprogram
                DW_AT_name      ("map_create")
                DW_AT_calling_convention        (DW_CC_nocall)
                DW_AT_type      (0x01934b29 "int")
		...

0x01952111:     DW_TAG_formal_parameter
                  DW_AT_location        (indexed (0x31b) loclist = 0x0034fa0f:
                     [0xffffffff81892345, 0xffffffff8189237c): DW_OP_reg5 RDI
                     [0xffffffff8189237c, 0xffffffff818923bd): DW_OP_reg3 RBX
                     [0xffffffff818923bd, 0xffffffff818923d4): DW_OP_entry_value(DW_OP_reg5 RDI), DW_OP_stack_value
                     [0xffffffff818923d4, 0xffffffff81892dcb): DW_OP_reg3 RBX
                     [0xffffffff81892df3, 0xffffffff81892e01): DW_OP_entry_value(DW_OP_reg5 RDI), DW_OP_stack_value
                     [0xffffffff81892e01, 0xffffffff818932a9): DW_OP_reg3 RBX)
                  DW_AT_name    ("attr")
                  DW_AT_type    (0x01934d17 "bpf_attr *")
		  ...

0x0195211d:     DW_TAG_formal_parameter
                  DW_AT_location        (indexed (0x31a) loclist = 0x0034f9dc:
                     [0xffffffff81892345, 0xffffffff81892357): DW_OP_piece 0x8, DW_OP_reg4 RSI, DW_OP_piece 0x1
                     [0xffffffff81892357, 0xffffffff81892f02): DW_OP_piece 0x8, DW_OP_breg7 RSP+20, DW_OP_deref_size 0x4, DW_OP_stack_value, DW_OP_piece 0x1
                     [0xffffffff81892f07, 0xffffffff818932a9): DW_OP_piece 0x8, DW_OP_breg7 RSP+20, DW_OP_deref_size 0x4, DW_OP_stack_value, DW_OP_piece 0x1)
                  DW_AT_name    ("uattr")
                  DW_AT_type    (0x019512ab "bpfptr_t")
		  ...

For parameter 'uattr', only second half of parameter is used. For such cases,
the name and the type is changed in pahole and eventually going to vmlinux btf.
  [55697] FUNC_PROTO '(anon)' ret_type_id=106780 vlen=2
          'attr' type_id=455
          'uattr__is_kernel' type_id=82014
  [82014] TYPEDEF 'bool' type_id=67434
  [113251] FUNC 'map_create' type_id=55697 linkage=static
You can see the new parameter name is 'uattr__is_kernel' and the type is 'bool'.

This makes thing easier for users to get the true signature.

Signed-off-by: Yonghong Song <yonghong.song@linux.dev>
---
 dwarf_loader.c | 246 +++++++++++++++++++++++++++++++++++++++++++++++--
 dwarves.h      |   1 +
 2 files changed, 240 insertions(+), 7 deletions(-)

diff --git a/dwarf_loader.c b/dwarf_loader.c
index e10e5d8..7d23c7d 100644
--- a/dwarf_loader.c
+++ b/dwarf_loader.c
@@ -1100,6 +1100,16 @@ static void arch__set_register_params(const GElf_Ehdr *ehdr, struct cu *cu)
 	}
 }
 
+static bool arch__agg_use_two_regs(const GElf_Ehdr *ehdr)
+{
+	switch (ehdr->e_machine) {
+	case EM_S390:
+		return false;
+	default:
+		return true;
+	}
+}
+
 static struct template_type_param *template_type_param__new(Dwarf_Die *die, struct cu *cu, struct conf_load *conf)
 {
 	struct template_type_param *ttparm = tag__alloc(cu, sizeof(*ttparm));
@@ -1199,8 +1209,98 @@ struct func_info {
 #define	PARM_UNEXPECTED		-2
 #define	PARM_OPTIMIZED_OUT	-3
 #define	PARM_CONTINUE		-4
+#define	PARM_TWO_ADDR_LEN	-5
+#define	PARM_TO_BE_IMPROVED	-6
+
+static int __get_type_byte_size(Dwarf_Die *die, struct cu *cu) {
+	Dwarf_Attribute attr;
+	if (dwarf_attr(die, DW_AT_type, &attr) == NULL)
+		return 0;
 
-static int parameter__multi_exprs(Dwarf_Op *expr, int loc_num) {
+	Dwarf_Die type_die;
+	if (dwarf_formref_die(&attr, &type_die) == NULL)
+		return 0;
+
+	/* A type does not have byte_size.
+	 * 0x000dac83: DW_TAG_formal_parameter
+			 DW_AT_location        (indexed (0x385) loclist = 0x00016175:
+			   [0xffff800080098cb0, 0xffff800080098cb4): DW_OP_breg8 W8+0
+			   [0xffff800080098cb4, 0xffff800080098ff4): DW_OP_breg31 WSP+16, DW_OP_deref
+			   [0xffff800080099054, 0xffff80008009908c): DW_OP_breg31 WSP+16, DW_OP_deref)
+			 DW_AT_name    ("ubuf")
+			 DW_AT_decl_file       ("/home/yhs/work/bpf-next/arch/arm64/kernel/ptrace.c")
+			 DW_AT_decl_line       (886)
+			 DW_AT_type    (0x000d467e "const void *")
+
+	  * 0x000d467e: DW_TAG_pointer_type
+			  DW_AT_type      (0x000c4320 "const void")
+
+	  * 0x000c4320: DW_TAG_const_type
+	  */
+	if (dwarf_tag(&type_die) == DW_TAG_pointer_type)
+		return cu->addr_size;
+
+	uint64_t bsize = attr_numeric(&type_die, DW_AT_byte_size);
+	if (bsize == 0)
+		return __get_type_byte_size(&type_die, cu);
+
+	return bsize;
+}
+
+static int get_type_byte_size(Dwarf_Die *die, struct cu *cu) {
+	int byte_size = 0;
+
+	Dwarf_Attribute attr;
+	if (dwarf_attr(die, DW_AT_abstract_origin, &attr)) {
+		Dwarf_Die origin;
+		if (dwarf_formref_die(&attr, &origin))
+			byte_size = __get_type_byte_size(&origin, cu);
+	} else {
+		byte_size = __get_type_byte_size(die, cu);
+	}
+	return byte_size;
+}
+
+/* Traverse the parameter type until finding the member type which has expected
+ * struct type offset.
+*/
+static Dwarf_Die *get_member_with_offset(Dwarf_Die *die, int offset, Dwarf_Die *member_die) {
+	Dwarf_Attribute attr;
+	if (dwarf_attr(die, DW_AT_type, &attr) == NULL)
+		return NULL;
+
+	Dwarf_Die type_die;
+	if (dwarf_formref_die(&attr, &type_die) == NULL)
+		return NULL;
+
+	uint64_t bsize = attr_numeric(&type_die, DW_AT_byte_size);
+	if (bsize == 0)
+		return get_member_with_offset(&type_die, offset, member_die);
+
+	if (dwarf_tag(&type_die) != DW_TAG_structure_type)
+		return NULL;
+
+	if (!dwarf_haschildren(&type_die) || dwarf_child(&type_die, member_die) != 0)
+		return NULL;
+	do {
+		if (dwarf_tag(member_die) != DW_TAG_member)
+			continue;
+
+		int off = attr_numeric(member_die, DW_AT_data_bit_offset);
+		if (off == offset * 8)
+			return member_die;
+	} while (dwarf_siblingof(member_die, member_die) == 0);
+
+	return NULL;
+}
+
+/* For two address length case, lower_half and upper_half represents the parameter.
+ * The lower_half and upper_half accumulates field information across possible multiple
+ * location lists.
+ */
+static int parameter__multi_exprs(Dwarf_Op *expr, int loc_num, struct cu *cu, size_t exprlen,
+				  Dwarf_Die *die, int expected_reg, int byte_size,
+				  unsigned long *lower_half, unsigned long *upper_half, int *ret) {
 	switch (expr[0].atom) {
 	case DW_OP_lit0 ... DW_OP_lit31:
 	case DW_OP_constu:
@@ -1210,9 +1310,119 @@ static int parameter__multi_exprs(Dwarf_Op *expr, int loc_num) {
 		return PARM_OPTIMIZED_OUT;
 	}
 
+	if (byte_size <= cu->addr_size || !cu->agg_use_two_regs) {
+		switch (expr[0].atom) {
+		case DW_OP_reg0 ... DW_OP_reg31:
+			if (loc_num != 0)
+				break;
+			*ret = expr[0].atom;
+			if (*ret == expected_reg)
+				return *ret;
+			break;
+		case DW_OP_breg0 ... DW_OP_breg31:
+			if (loc_num != 0)
+				break;
+			bool has_op_stack_value = false;
+			for (int i = 1; i < exprlen; i++) {
+				if (expr[i].atom == DW_OP_stack_value) {
+					has_op_stack_value = true;
+					break;
+				}
+			}
+			if (!has_op_stack_value)
+				break;
+			/* The existence of DW_OP_stack_value means that
+			 * DW_OP_bregX register is used as value.
+			 */
+			*ret = expr[0].atom - DW_OP_breg0 + DW_OP_reg0;
+			if (*ret == expected_reg)
+				return *ret;
+		}
+	} else {
+		/* cu->addr * 2 */
+		int off = 0;
+		for (int i = 0; i < exprlen; i++) {
+			if (expr[i].atom == DW_OP_piece) {
+				int num = expr[i].number;
+				if (i == 0) {
+					off = num;
+					continue;
+				}
+				if (off < cu->addr_size) (*lower_half) |= (1 << off);
+				else (*upper_half) |= (1 << (off - cu->addr_size));
+				off += num;
+			} else if (expr[i].atom >= DW_OP_reg0 && expr[i].atom <= DW_OP_reg31) {
+				if (off < cu->addr_size)
+					*ret = expr[i].atom;
+				else if (*ret < 0)
+					*ret = expr[i].atom;
+			}
+			/* FIXME: not handling DW_OP_bregX yet since we do not have
+			 * a use case for it yet for linux kernel.
+			 */
+		}
+	}
+
 	return PARM_CONTINUE;
 }
 
+/* The lower_half and upper_half, computed in parameter__multi_exprs(), are handled here.
+ */
+static int parameter__handle_two_addr_len(int expected_reg, unsigned long lower_half, unsigned long upper_half,
+					  int ret, Dwarf_Die *die, struct conf_load *conf, struct cu *cu,
+					  struct parameter *parm) {
+	if (!lower_half && !upper_half)
+		return ret;
+
+	if (ret != expected_reg)
+		return ret;
+
+	if (!conf->true_signature)
+		return PARM_DEFAULT_FAIL;
+
+	/* Both halfs are used based on dwarf */
+	if (lower_half && upper_half)
+		return PARM_TWO_ADDR_LEN;
+
+	/* FIXME: parm->name may be NULL due to abstract origin. We do not want to
+	 * update abstract origin as the type in abstract origin may be used
+	 * in some other places. We could remove abstract origin in this parameter
+	 * and add name and type in parameter itself. Right now, for current bpf-next
+	 * repo, we do not have instances below where parm->name is NULL for x86_64 arch.
+	 */
+	if (!parm->name)
+		return PARM_TO_BE_IMPROVED;
+
+	/* FIXME: Only support single field now so we can have a good parameter name and
+	 * type for it.
+	 */
+	if (__builtin_popcountll(lower_half) >= 2 || __builtin_popcountll(upper_half) >= 2)
+		return PARM_TO_BE_IMPROVED;
+
+	int field_offset;
+	if (__builtin_popcountll(lower_half) == 1)
+		field_offset = __builtin_ctzll(lower_half);
+	else
+		field_offset = cu->addr_size + __builtin_ctzll(upper_half);
+
+	/* FIXME: Only struct type is supported. */
+	Dwarf_Die member_die;
+	if (!get_member_with_offset(die, field_offset, &member_die))
+		return PARM_TO_BE_IMPROVED;
+
+	const char *member_name = attr_string(&member_die, DW_AT_name, conf);
+	int len = sizeof(parm->name) + strlen(member_name) + 3;
+	char *new_name = malloc(len);
+	sprintf(new_name, "%s__%s", parm->name, member_name);
+	parm->name = new_name;
+
+	struct tag *tag = &parm->tag;
+	struct dwarf_tag *dtag = tag__dwarf(tag);
+	dwarf_tag__set_attr_type(dtag, type, &member_die, DW_AT_type);
+
+	return ret;
+}
+
 /* For DW_AT_location 'attr':
  * - if first location is DW_OP_regXX with expected number, return the register;
  *   otherwise save the register for later return
@@ -1221,15 +1431,18 @@ static int parameter__multi_exprs(Dwarf_Op *expr, int loc_num) {
  * - otherwise if no register was found for locations, return PARM_DEFAULT_FAIL.
  */
 static int parameter__reg(Dwarf_Attribute *attr, int expected_reg, struct conf_load *conf,
-			  struct func_info *info)
+			  struct func_info *info, struct cu *cu, Dwarf_Die *die,
+			  struct parameter *parm)
 {
 	Dwarf_Addr base, start, end;
 	Dwarf_Op *expr, *entry_ops;
 	Dwarf_Attribute entry_attr;
 	size_t exprlen, entry_len;
 	ptrdiff_t offset = 0;
+	int byte_size = 0;
 	int loc_num = -1;
 	int ret = PARM_DEFAULT_FAIL;
+	unsigned long lower_half = 0, upper_half = 0;
 
 	/* use libdw__lock as dwarf_getlocation(s) has concurrency issues
 	 * when libdw is not compiled with experimental --enable-thread-safety
@@ -1249,8 +1462,17 @@ static int parameter__reg(Dwarf_Attribute *attr, int expected_reg, struct conf_l
 			if (!info->signature_changed || !conf->true_signature)
 				continue;
 
+			if (!byte_size)
+				byte_size = get_type_byte_size(die, cu);
+			/* This should not happen. */
+			if (!byte_size) {
+				ret = PARM_UNEXPECTED;
+				goto out;
+			}
+
 			int res;
-			res = parameter__multi_exprs(expr, loc_num);
+			res = parameter__multi_exprs(expr, loc_num, cu, exprlen, die, expected_reg,
+						     byte_size, &lower_half, &upper_half, &ret);
 			if (res == PARM_CONTINUE)
 				continue;
 			ret = res;
@@ -1299,6 +1521,10 @@ static int parameter__reg(Dwarf_Attribute *attr, int expected_reg, struct conf_l
 			break;
 		}
 	}
+
+	ret = parameter__handle_two_addr_len(expected_reg, lower_half, upper_half,
+					     ret, die, conf, cu, parm);
+
 out:
 	pthread_mutex_unlock(&libdw__lock);
 	return ret;
@@ -1333,8 +1559,6 @@ static struct parameter *parameter__new(Dwarf_Die *die, struct cu *cu,
 			}
 		}
 		reg_idx = param_idx - info->skip_idx;
-		if (reg_idx >= cu->nr_register_params)
-			return parm;
 		/* Parameters which use DW_AT_abstract_origin to point at
 		 * the original parameter definition (with no name in the DIE)
 		 * are the result of later DWARF generation during compilation
@@ -1372,15 +1596,22 @@ static struct parameter *parameter__new(Dwarf_Die *die, struct cu *cu,
 		parm->has_loc = dwarf_attr(die, DW_AT_location, &attr) != NULL;
 
 		if (parm->has_loc) {
+			if (reg_idx >= cu->nr_register_params)
+				return parm;
+
 			int expected_reg = cu->register_params[reg_idx];
-			int actual_reg = parameter__reg(&attr, expected_reg, conf, info);
+			int actual_reg = parameter__reg(&attr, expected_reg, conf, info, cu, die, parm);
 
 			if (actual_reg == PARM_DEFAULT_FAIL) {
 				parm->optimized = 1;
 			} else if (actual_reg == PARM_OPTIMIZED_OUT) {
 				parm->optimized = 1;
 				info->skip_idx++;
-			} else if (actual_reg == PARM_UNEXPECTED || (expected_reg >= 0 && expected_reg != actual_reg)) {
+			} else if (actual_reg == PARM_TWO_ADDR_LEN) {
+				/* account for parameter with two registers */
+				info->skip_idx--;
+			} else if (actual_reg == PARM_UNEXPECTED || actual_reg == PARM_TO_BE_IMPROVED ||
+				   (expected_reg >= 0 && expected_reg != actual_reg)) {
 				/* mark parameters that use an unexpected
 				 * register to hold a parameter; these will
 				 * be problematic for users of BTF as they
@@ -3414,6 +3645,7 @@ static int cu__set_common(struct cu *cu, struct conf_load *conf,
 
 	cu->little_endian = ehdr.e_ident[EI_DATA] == ELFDATA2LSB;
 	cu->nr_register_params = arch__nr_register_params(&ehdr);
+	cu->agg_use_two_regs = arch__agg_use_two_regs(&ehdr);
 	arch__set_register_params(&ehdr, cu);
 	return 0;
 }
diff --git a/dwarves.h b/dwarves.h
index 4cabab0..28792b5 100644
--- a/dwarves.h
+++ b/dwarves.h
@@ -303,6 +303,7 @@ struct cu {
 	uint8_t		 uses_global_strings:1;
 	uint8_t		 little_endian:1;
 	uint8_t		 producer_clang:1;
+	uint8_t		 agg_use_two_regs:1;    /* An aggregate like {long a; long b;} */
 	uint8_t		 nr_register_params;
 	int		 register_params[ARCH_MAX_REGISTER_PARAMS];
 	int		 functions_saved;
-- 
2.52.0

Ensure to skip optimized parameter so btf can generate
proper true signatures.

In the first patch of the patch set, with DW_CC_nocall filtering, 875 functions
have signature changed. With a series of improvement, eventually only 17 functions
remain and unfortunately these functions cannot be converted to true signatures
due to locations. For example,

0x0242f1f7:   DW_TAG_subprogram
                DW_AT_name      ("memblock_find_in_range")
                DW_AT_calling_convention        (DW_CC_nocall)
                DW_AT_type      (0x0242decc "phys_addr_t")
                ...

0x0242f22e:     DW_TAG_formal_parameter
                  DW_AT_location        (indexed (0x14a) loclist = 0x005595bc:
                     [0xffffffff87a000f9, 0xffffffff87a00178): DW_OP_reg5 RDI
                     [0xffffffff87a00178, 0xffffffff87a001be): DW_OP_reg14 R14
                     [0xffffffff87a001be, 0xffffffff87a001c7): DW_OP_entry_value(DW_OP_reg5 RDI), DW_OP_stack_value
                     [0xffffffff87a001c7, 0xffffffff87a00214): DW_OP_reg14 R14)
                  DW_AT_name    ("start")
                  DW_AT_type    (0x0242decc "phys_addr_t")
                  ...

0x0242f239:     DW_TAG_formal_parameter
                  DW_AT_location        (indexed (0x14b) loclist = 0x005595e6:
                     [0xffffffff87a000f9, 0xffffffff87a00175): DW_OP_reg4 RSI
                     [0xffffffff87a00175, 0xffffffff87a001b8): DW_OP_reg3 RBX
                     [0xffffffff87a001b8, 0xffffffff87a001c7): DW_OP_entry_value(DW_OP_reg4 RSI), DW_OP_stack_value
                     [0xffffffff87a001c7, 0xffffffff87a00214): DW_OP_reg3 RBX)
                  DW_AT_name    ("end")
                  DW_AT_type    (0x0242decc "phys_addr_t")
                  ...

0x0242f245:     DW_TAG_formal_parameter
                  DW_AT_location        (indexed (0x14c) loclist = 0x00559610:
                     [0xffffffff87a001e3, 0xffffffff87a001ef): DW_OP_breg4 RSI+0)
                  DW_AT_name    ("size")
                  DW_AT_type    (0x0242decc "phys_addr_t")
                  ...

0x0242f250:     DW_TAG_formal_parameter
                  DW_AT_const_value     (4096)
                  DW_AT_name    ("align")
                  DW_AT_type    (0x0242decc "phys_addr_t")
                  ...

The third parameter 'size' is not from RDX. Hence, true signature is not possible for this function.

I also did some experiments on arm64. The number of signature-changed funcitons
is 863 and finally there are 79 functions cannot be converted to true signatures.
Through dwarf comparison of x86_64 vs. arm64, llvm arm64 backend looks like having
more relaxation to compute parameter values for those signature-changed functions.

Signed-off-by: Yonghong Song <yonghong.song@linux.dev>
---
 btf_encoder.c | 13 +++++++++++--
 1 file changed, 11 insertions(+), 2 deletions(-)

diff --git a/btf_encoder.c b/btf_encoder.c
index d36984a..8e991b1 100644
--- a/btf_encoder.c
+++ b/btf_encoder.c
@@ -1257,15 +1257,21 @@ static int32_t btf_encoder__save_func(struct btf_encoder *encoder, struct functi
 	struct btf *btf = encoder->btf;
 	struct llvm_annotation *annot;
 	struct parameter *param;
-	uint8_t param_idx = 0;
+	uint8_t param_idx = 0, skip_idx = 0;
 	int str_off, err = 0;
 
 	if (!state)
 		return -ENOMEM;
 
+	if (encoder->cu->producer_clang) {
+		ftype__for_each_parameter(ftype, param) {
+			if (param->optimized) skip_idx++;
+		}
+	}
+
 	state->addr = function__addr(fn);
 	state->elf = func;
-	state->nr_parms = ftype->nr_parms + (ftype->unspec_parms ? 1 : 0);
+	state->nr_parms = ftype->nr_parms - skip_idx + (ftype->unspec_parms ? 1 : 0);
 	state->ret_type_id = ftype->tag.type == 0 ? 0 : encoder->type_id_off + ftype->tag.type;
 	if (state->nr_parms > 0) {
 		state->parms = zalloc(state->nr_parms * sizeof(*state->parms));
@@ -1303,6 +1309,9 @@ static int32_t btf_encoder__save_func(struct btf_encoder *encoder, struct functi
 			state->nr_parms--;
 			continue;
 		}
+		if (encoder->cu->producer_clang && param->optimized)
+			continue;
+
 		name = parameter__name(param) ?: "";
 		str_off = btf__add_str(btf, name);
 		if (str_off < 0) {
-- 
2.52.0

Three tests are added.

Test 1: VERBOSE=1 ./clang_parm_optimized.sh
  BTF:   char * foo(struct t * a, struct t * d);
  DWARF: char * foo(struct t * a, int b, struct t * d);
where parameber 'b' is unused.

Test 2: VERBOSE=1 ./clang_parm_optimized_stack.sh
  BTF:   char * foo(struct t * a, struct t * d);
  DWARF: char * foo(struct t * a, int b1, int b2, int b3, int b4, int b5, int b6, struct t * d);
where parameters 'b1' to 'b6' are unused.

Test 3: VERBOSE=1 ./clang_parm_aggregate.sh
  BTF:   long foo(long a__f1, struct t b, int i);
  DWARF: long foo(struct t a, struct t b, int i);
where the 'struct t' definition is 'struct t { long f1; long f2; };', and
a.f2 is not used in the function.

Signed-off-by: Yonghong Song <yonghong.song@linux.dev>
---
 tests/clang_parm_aggregate.sh       | 63 +++++++++++++++++++++++
 tests/clang_parm_optimized.sh       | 77 +++++++++++++++++++++++++++++
 tests/clang_parm_optimized_stack.sh | 77 +++++++++++++++++++++++++++++
 3 files changed, 217 insertions(+)
 create mode 100755 tests/clang_parm_aggregate.sh
 create mode 100755 tests/clang_parm_optimized.sh
 create mode 100755 tests/clang_parm_optimized_stack.sh

diff --git a/tests/clang_parm_aggregate.sh b/tests/clang_parm_aggregate.sh
new file mode 100755
index 0000000..bf47c8c
--- /dev/null
+++ b/tests/clang_parm_aggregate.sh
@@ -0,0 +1,63 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0-only
+
+source test_lib.sh
+
+outdir=$(make_tmpdir)
+
+# Comment this out to save test data.
+trap cleanup EXIT
+
+title_log "Validation of BTF encoding of true_signatures."
+
+clang_true="${outdir}/clang_true"
+CC=$(which clang 2>/dev/null)
+
+if [[ -z "$CC" ]]; then
+	info_log "skip: clang not available"
+	test_skip
+fi
+
+cat > ${clang_true}.c << EOF
+struct t { long f1; long f2; };
+__attribute__((noinline)) static long foo(struct t a, struct t b, int i)
+{
+        return a.f1 + b.f1 + b.f2 + i;
+}
+
+struct t p1, p2;
+int i;
+int main()
+{
+        return (int)foo(p1, p2, i);
+}
+EOF
+
+CFLAGS="$CFLAGS -g -O2"
+${CC} ${CFLAGS} -o $clang_true ${clang_true}.c
+if [[ $? -ne 0 ]]; then
+	error_log "Could not compile ${clang_true}.c"
+	test_fail
+fi
+LLVM_OBJCOPY=objcopy pahole -J --btf_features=+true_signature $clang_true
+if [[ $? -ne 0 ]]; then
+	error_log "Could not encode BTF for $clang_true"
+	test_fail
+fi
+
+btf_optimized=$(pfunct --all --format_path=btf $clang_true |grep "foo")
+if [[ -z "$btf_optimized" ]]; then
+	info_log "skip: no optimizations applied."
+	test_skip
+fi
+
+btf_cmp=$btf_optimized
+dwarf=$(pfunct --all $clang_true |grep "foo")
+
+verbose_log "BTF: $btf_optimized  DWARF: $dwarf"
+
+if [[ "$btf_cmp" == "$dwarf" ]]; then
+	error_log "BTF and DWARF signatures should be different and they are not: BTF: $btf_optimized ; DWARF $dwarf"
+	test_fail
+fi
+test_pass
diff --git a/tests/clang_parm_optimized.sh b/tests/clang_parm_optimized.sh
new file mode 100755
index 0000000..379e6d5
--- /dev/null
+++ b/tests/clang_parm_optimized.sh
@@ -0,0 +1,77 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0-only
+
+source test_lib.sh
+
+outdir=$(make_tmpdir)
+
+# Comment this out to save test data.
+trap cleanup EXIT
+
+title_log "Validation of BTF encoding of true_signatures."
+
+clang_true="${outdir}/clang_true"
+CC=$(which clang 2>/dev/null)
+
+if [[ -z "$CC" ]]; then
+	info_log "skip: clang not available"
+	test_skip
+fi
+
+cat > ${clang_true}.c << EOF
+struct t { int a; };
+__attribute__((noinline)) char *tar(struct t *a, struct t *d)
+{
+	if (a->a == d->a)
+		return (char *)10;
+	else
+		return (char *)0;
+}
+
+__attribute__((noinline)) static char * foo(struct t *a, int b, struct t *d)
+{
+	return tar(a, d);
+}
+
+__attribute__((noinline)) char *bar(struct t *a, struct t *d)
+{
+	return foo(a, 1, d);
+}
+
+struct t p1, p2;
+int main()
+{
+	return !!bar(&p1, &p2);
+}
+EOF
+
+CFLAGS="$CFLAGS -g -O2"
+${CC} ${CFLAGS} -o $clang_true ${clang_true}.c
+if [[ $? -ne 0 ]]; then
+	error_log "Could not compile ${clang_true}.c"
+	test_fail
+fi
+LLVM_OBJCOPY=objcopy pahole -J --btf_features=+true_signature $clang_true
+if [[ $? -ne 0 ]]; then
+	error_log "Could not encode BTF for $clang_true"
+	test_fail
+fi
+
+btf_optimized=$(pfunct --all --format_path=btf $clang_true |grep "foo")
+if [[ -z "$btf_optimized" ]]; then
+	info_log "skip: no optimizations applied."
+	test_skip
+fi
+
+btf_cmp=$btf_optimized
+dwarf=$(pfunct --all $clang_true |grep "foo")
+
+if [[ -n "$VERBOSE" ]]; then
+	printf "   BTF: %s  DWARF: %s\n" "$btf_optimized" "$dwarf"
+fi
+
+if [[ "$btf_cmp" == "$dwarf" ]]; then
+	error_log "BTF and DWARF signatures should be different and they are not: BTF: $btf_optimized ; DWARF $dwarf"
+	test_fail
+fi
+test_pass
diff --git a/tests/clang_parm_optimized_stack.sh b/tests/clang_parm_optimized_stack.sh
new file mode 100755
index 0000000..8638af7
--- /dev/null
+++ b/tests/clang_parm_optimized_stack.sh
@@ -0,0 +1,77 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0-only
+
+source test_lib.sh
+
+outdir=$(make_tmpdir)
+
+# Comment this out to save test data.
+trap cleanup EXIT
+
+title_log "Validation of BTF encoding of true_signatures."
+
+clang_true="${outdir}/clang_true"
+CC=$(which clang 2>/dev/null)
+
+if [[ -z "$CC" ]]; then
+	info_log "skip: clang not available"
+	test_skip
+fi
+
+cat > ${clang_true}.c << EOF
+struct t { int a; };
+__attribute__((noinline)) char *tar(struct t *a, struct t *d)
+{
+        if (a->a == d->a)
+                return (char *)10;
+        else
+                return (char *)0;
+}
+
+__attribute__((noinline)) static char * foo(struct t *a, int b1, int b2, int b3, int b4, int b5, int b6, struct t *d)
+{
+        return tar(a, d);
+}
+
+__attribute__((noinline)) char *bar(struct t *a, struct t *d)
+{
+        return foo(a, 1, 2, 3, 4, 5, 6, d);
+}
+
+struct t p1, p2;
+int main()
+{
+        return !!bar(&p1, &p2);
+}
+EOF
+
+CFLAGS="$CFLAGS -g -O2"
+${CC} ${CFLAGS} -o $clang_true ${clang_true}.c
+if [[ $? -ne 0 ]]; then
+	error_log "Could not compile ${clang_true}.c"
+	test_fail
+fi
+LLVM_OBJCOPY=objcopy pahole -J --btf_features=+true_signature $clang_true
+if [[ $? -ne 0 ]]; then
+	error_log "Could not encode BTF for $clang_true"
+	test_fail
+fi
+
+btf_optimized=$(pfunct --all --format_path=btf $clang_true |grep "foo")
+if [[ -z "$btf_optimized" ]]; then
+	info_log "skip: no optimizations applied."
+	test_skip
+fi
+
+btf_cmp=$btf_optimized
+dwarf=$(pfunct --all $clang_true |grep "foo")
+
+if [[ -n "$VERBOSE" ]]; then
+	printf "   BTF: %s  DWARF: %s\n" "$btf_optimized" "$dwarf"
+fi
+
+if [[ "$btf_cmp" == "$dwarf" ]]; then
+	error_log "BTF and DWARF signatures should be different and they are not: BTF: $btf_optimized ; DWARF $dwarf"
+	test_fail
+fi
+test_pass
-- 
2.52.0